mirror of
https://github.com/nomadkaraoke/karaoke-gen.git
synced 2026-11-20 21:17:56 +09:00
Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
5c71d58a8d | ||
|
|
78d7eedeee | ||
|
|
6fa81c1b69 | ||
|
|
706e6f7527 | ||
|
|
8bbb1351f8 | ||
|
|
18e97dc0a0 | ||
|
|
642c80164c | ||
|
|
46eca212fe | ||
|
|
8d8e64ccc0 | ||
|
|
50f895e88a | ||
|
|
7218b4d176 | ||
|
|
c052fec326 | ||
|
|
70eca20c7a | ||
|
|
0e6a0b43ce | ||
|
|
3cbfbd14d1 | ||
|
|
2f4265e9d0 | ||
|
|
4a74a2cc3a | ||
|
|
cdae92d0b7 | ||
|
|
6e3cf007d2 | ||
|
|
bf6f3ba78b | ||
|
|
d1a5892793 | ||
|
|
4a7b616dde | ||
|
|
e40a122841 | ||
|
|
251d3fa971 | ||
|
|
a24060c4d2 | ||
|
|
2ab0f0dea3 | ||
|
|
41df208e5d | ||
|
|
7ffb219b9f | ||
|
|
f740c68f4b | ||
|
|
14c0abd40f | ||
|
|
4b01f1100f | ||
|
|
6f1bafbcec | ||
|
|
37bdb1e93a | ||
|
|
d6aaaa8544 | ||
|
|
229d23ead1 | ||
|
|
2112596133 | ||
|
|
f2d2bbacd9 | ||
|
|
d0ff5bff33 | ||
|
|
7d8b7266e2 | ||
|
|
252c05a72b | ||
|
|
b69c3a1360 | ||
|
|
989abeaf1b | ||
|
|
d3315593c9 | ||
|
|
f48fc39328 | ||
|
|
15cc62d8e3 | ||
|
|
d2c7a907af | ||
|
|
5e62efbe31 | ||
|
|
bf22d6f033 | ||
|
|
93bdacdbf2 | ||
|
|
0ed5559451 | ||
|
|
1fc735d727 | ||
|
|
8d90775946 | ||
|
|
f3dd715c81 | ||
|
|
fbdd1c4da1 | ||
|
|
050f86a280 | ||
|
|
49febf49cf | ||
|
|
3874e12ca0 | ||
|
|
148624ca36 | ||
|
|
cceb4ec1d2 | ||
|
|
c243577e73 | ||
|
|
91dc5761fc | ||
|
|
b7e61ae87b | ||
|
|
9ff7784a3c | ||
|
|
68eec8b8b9 | ||
|
|
5aa0920fae | ||
|
|
6d81ad804a | ||
|
|
81dca5c673 | ||
|
|
5c29fabd0f | ||
|
|
6951de03b3 | ||
|
|
f1d3423e9d | ||
|
|
82475a8b03 | ||
|
|
8c2be7bfe2 | ||
|
|
b7e157ec15 | ||
|
|
722ec69cda | ||
|
|
67b0601811 | ||
|
|
97a0c642f1 | ||
|
|
71dadc71a2 | ||
|
|
e81ecbbbba | ||
|
|
6897d20358 | ||
|
|
af09ee4b50 | ||
|
|
634bb3a11c | ||
|
|
79cc552226 | ||
|
|
f579f0ce71 | ||
|
|
682f5ef432 | ||
|
|
8015e2a228 | ||
|
|
55b9691fb9 | ||
|
|
6e089850a7 | ||
|
|
5f52cffc34 | ||
|
|
71ebd43771 | ||
|
|
c6bcb8cead | ||
|
|
84288b78d2 | ||
|
|
41d1eda574 | ||
|
|
95b3836fa2 | ||
|
|
8044e06b09 | ||
|
|
542052ceee | ||
|
|
6d3c348dea | ||
|
|
2328cd7dce | ||
|
|
cacdad3dc5 | ||
|
|
59e73f7c90 | ||
|
|
8782e2b455 | ||
|
|
220623c634 | ||
|
|
029e639dcf | ||
|
|
90d36a63f7 | ||
|
|
84928fed33 | ||
|
|
f144797366 | ||
|
|
a86273adf1 | ||
|
|
f0b447823b | ||
|
|
e4336c3f99 | ||
|
|
d55e8b514a | ||
|
|
e333fb2ae0 | ||
|
|
3dd2ee4a86 | ||
|
|
70b1410c0e | ||
|
|
067052448f | ||
|
|
a5bca8781a | ||
|
|
7d1b9ce960 | ||
|
|
311e0a4ad2 | ||
|
|
70977f4807 | ||
|
|
11c8d8d58e | ||
|
|
c15673b27e | ||
|
|
913efcf72a | ||
|
|
ad0a6c3475 | ||
|
|
cd15024c42 | ||
|
|
9906d4bb63 | ||
|
|
9e28f7bd99 | ||
|
|
3ca62aa555 | ||
|
|
8b808b0bf0 | ||
|
|
6985ab31b3 | ||
|
|
706e414e36 | ||
|
|
5ace8b0575 | ||
|
|
bc7d1a2308 | ||
|
|
1741470ddb | ||
|
|
ee9ea7c0c5 | ||
|
|
91b2421c37 | ||
|
|
06748776e3 | ||
|
|
91f51d6a8c | ||
|
|
f2e2617e43 | ||
|
|
198ffc2469 | ||
|
|
0a03a93948 | ||
|
|
501c301f4f | ||
|
|
867a519f6c | ||
|
|
d5db0c955d | ||
|
|
6a371a01a9 | ||
|
|
4d771c9db1 | ||
|
|
5e46cf57fb | ||
|
|
ed3e6ae039 | ||
|
|
4fe7d84789 | ||
|
|
fdd84bad36 | ||
|
|
f52964441a | ||
|
|
92affebded | ||
|
|
3221c2626b | ||
|
|
2ea21b0e51 | ||
|
|
76fa4befd8 | ||
|
|
583dd323dc | ||
|
|
ef2ecb4c55 | ||
|
|
6d28e09fce | ||
|
|
565586aca4 | ||
|
|
9147e2f21b | ||
|
|
9ad20e3a36 | ||
|
|
85a7f62b01 | ||
|
|
09f9e15ff0 | ||
|
|
dd62d30fa9 | ||
|
|
adfd3de651 | ||
|
|
871e97cae7 | ||
|
|
03e1aec641 | ||
|
|
40948c2ada | ||
|
|
2182bf7e58 | ||
|
|
ed723dd6d0 | ||
|
|
ddc4460065 | ||
|
|
b0f3d15112 | ||
|
|
213d3b4311 | ||
|
|
753499db01 | ||
|
|
1b6e682860 | ||
|
|
9baba12280 | ||
|
|
24b7b75ab2 | ||
|
|
0b59b7abfc | ||
|
|
942cbb4f66 | ||
|
|
96383a60d4 | ||
|
|
0cf14be531 | ||
|
|
95edd82555 | ||
|
|
6e02ca3056 | ||
|
|
966e8cc963 | ||
|
|
04b1c8fd3e | ||
|
|
f47b126c08 | ||
|
|
4438293b6d | ||
|
|
de4e92d9bf | ||
|
|
e7f88b60d0 | ||
|
|
fbb1cd7299 | ||
|
|
77820a44c9 | ||
|
|
e92ddd8609 | ||
|
|
a2bf2230ab | ||
|
|
75c6879b7e | ||
|
|
f51ef68179 | ||
|
|
8a5420f5f8 | ||
|
|
c9b7f1bb1a | ||
|
|
d9da1dd360 | ||
|
|
a8fa6b5f46 | ||
|
|
ebe0121938 | ||
|
|
01db9a764a | ||
|
|
f524796f7f | ||
|
|
8372ed211a | ||
|
|
78068ea1d8 | ||
|
|
84d7c12f13 | ||
|
|
7a4ed9661c | ||
|
|
dd62c32026 | ||
|
|
c130fa8a07 | ||
|
|
e0d1fa7536 | ||
|
|
29ffbd4ae2 | ||
|
|
e440f0bbcd | ||
|
|
e0f5a84e54 | ||
|
|
8da57da767 | ||
|
|
b840a12669 | ||
|
|
f7038ce72c | ||
|
|
138ddeecf5 | ||
|
|
a7d9bb40b9 | ||
|
|
20f842fa85 | ||
|
|
1b74199032 | ||
|
|
e75c5b2723 | ||
|
|
9e53bb7934 | ||
|
|
a85727b147 | ||
|
|
3eb8f707b6 | ||
|
|
4b26fe9eac | ||
|
|
4de3ecc85d | ||
|
|
cbb4cd8f9e | ||
|
|
218011cf2a | ||
|
|
22c6e7ed41 | ||
|
|
e104fb9252 | ||
|
|
31931cc55d | ||
|
|
d21729bf3d | ||
|
|
b49a09e1c6 | ||
|
|
e6b2194272 | ||
|
|
a08b83df40 | ||
|
|
53d2ed2828 | ||
|
|
ff20b5ffb3 | ||
|
|
49290f94d7 | ||
|
|
9b114fcb3d | ||
|
|
e507b3f685 | ||
|
|
6d0c765f4d | ||
|
|
8086242d38 | ||
|
|
3c3680632b | ||
|
|
dd5f05b291 | ||
|
|
36a60c09da | ||
|
|
9340ed5d9f | ||
|
|
8959da63a1 | ||
|
|
cb7b4863f5 | ||
|
|
e84a511676 | ||
|
|
aee2b48ffd | ||
|
|
a7652ba72d | ||
|
|
0ce5225bde | ||
|
|
c494685211 | ||
|
|
599625e21a | ||
|
|
5c4404839b | ||
|
|
f699850d30 | ||
|
|
e8d9871d3e | ||
|
|
473253b5ab | ||
|
|
89cc9e9113 | ||
|
|
ec5a816b68 | ||
|
|
7eb082d382 | ||
|
|
1af7ab0bde | ||
|
|
7ba40af80d | ||
|
|
f434e3c93d | ||
|
|
4b6523dbd8 | ||
|
|
d67828b78f | ||
|
|
db55205127 | ||
|
|
01ff0eb042 | ||
|
|
438ea6a836 | ||
|
|
07f48b6213 | ||
|
|
5630cfd253 | ||
|
|
f543ea6efa | ||
|
|
5a2c77978b | ||
|
|
0f7ec8f71e | ||
|
|
dbb6f3b751 | ||
|
|
dd287f8c92 | ||
|
|
07c459258a | ||
|
|
3522fdd223 | ||
|
|
651cbbdbca | ||
|
|
ba4534fdbd | ||
|
|
441f99edeb | ||
|
|
2e145dd927 | ||
|
|
985f5c7718 | ||
|
|
2b5ef28789 | ||
|
|
76940691b1 | ||
|
|
4b346dd369 | ||
|
|
7480950a1b | ||
|
|
64ada25e9c | ||
|
|
de6322dd87 | ||
|
|
49b472429d | ||
|
|
d57282c770 | ||
|
|
a41948fe37 | ||
|
|
ffd4e9e377 | ||
|
|
ef9c4fc243 | ||
|
|
1f030333ae | ||
|
|
707df6af72 |
No files matched your search
@@ -0,0 +1,368 @@
|
||||
---
|
||||
name: Anchor Sequence Optimization
|
||||
overview: Replace the current multiprocessing-based anchor sequence algorithm with an efficient single-threaded implementation using hash-based n-gram indexing, greedy longest-first matching, and simplified scoring to achieve sub-30-second performance in both local and cloud environments.
|
||||
todos:
|
||||
- id: create-golden-fixtures
|
||||
content: Create script to generate 10 golden test fixtures from representative song data (varying lengths/complexity), run current algorithm to capture expected anchor outputs
|
||||
status: completed
|
||||
- id: create-golden-test
|
||||
content: Create test_anchor_sequence_golden.py with regression tests that verify anchor finder output matches fixtures, ensure tests pass with current implementation before any changes
|
||||
status: completed
|
||||
- id: remove-multiprocessing
|
||||
content: Remove multiprocessing.Pool from find_anchors() and _remove_overlapping_sequences(), replace with single-threaded loops
|
||||
status: completed
|
||||
- id: build-ngram-index
|
||||
content: Add _build_ngram_index() method to create hash-based lookup table for O(1) n-gram matching
|
||||
status: completed
|
||||
- id: greedy-skip
|
||||
content: Add covered_positions set tracking and skip logic to avoid processing overlapping n-grams
|
||||
status: completed
|
||||
- id: simple-scoring
|
||||
content: Add _simple_score_anchor() with rule-based heuristics, make spaCy scoring optional via use_nlp_scoring flag
|
||||
status: completed
|
||||
- id: optimize-overlap
|
||||
content: Replace O(n^2) overlap removal with O(n log n) sorted single-pass algorithm
|
||||
status: completed
|
||||
- id: add-perf-tests
|
||||
content: Add performance benchmark test asserting <30 second completion for all fixture sizes
|
||||
status: pending
|
||||
---
|
||||
|
||||
# Anchor Sequence Algorithm Optimization
|
||||
|
||||
## Problem Analysis
|
||||
|
||||
The current `AnchorSequenceFinder` has critical performance issues:
|
||||
|
||||
### Root Causes of Hanging
|
||||
|
||||
1. **Multiprocessing Pool with fork()**: Python's `Pool()` uses `fork()` on Linux, which causes deadlocks in Cloud Run containers
|
||||
2. **spaCy model loading in forked processes**: The `PhraseAnalyzer` loads spaCy's `en_core_web_sm` model, which can hang when forked
|
||||
3. **Pool creation blocking**: The hang occurs before job submission, so timeout checks never trigger
|
||||
|
||||
### Algorithmic Inefficiencies
|
||||
|
||||
1. **O(n^2) n-gram matching**: Linear search through references for each n-gram
|
||||
2. **Redundant work**: Processes all n-gram lengths (3 to ~30) even though longer matches are preferred
|
||||
3. **O(n^2) overlap removal**: Each anchor checked against all previous anchors
|
||||
4. **Expensive phrase scoring**: spaCy NLP called twice per anchor (phrase + context)
|
||||
|
||||
## Proposed Solution: Hash-Based Greedy Algorithm
|
||||
|
||||
### Core Algorithm Changes
|
||||
|
||||
**1. Hash-Based N-gram Index (O(1) lookup instead of O(n))**
|
||||
|
||||
- Pre-build a dictionary mapping n-grams to their positions in each reference
|
||||
- Use tuple of cleaned words as key for O(1) lookup
|
||||
- Build index once during preprocessing
|
||||
|
||||
**2. Greedy Longest-First Matching**
|
||||
|
||||
- Process n-gram lengths from longest to shortest (current behavior)
|
||||
- BUT: Skip positions already covered by longer anchors immediately
|
||||
- Use a "covered positions" set to avoid redundant work
|
||||
|
||||
**3. Single-Threaded Processing**
|
||||
|
||||
- Remove all `multiprocessing.Pool` usage
|
||||
- Use efficient algorithms instead of parallelism
|
||||
- Works identically in local and cloud environments
|
||||
|
||||
**4. Simplified Phrase Scoring (Optional)**
|
||||
|
||||
- Make spaCy-based scoring optional via configuration flag
|
||||
- Default to rule-based heuristic scoring:
|
||||
- Prefer sequences starting/ending at word boundaries
|
||||
- Prefer sequences matching more reference sources
|
||||
- Prefer longer sequences
|
||||
- Option to enable full NLP scoring for higher-quality results offline
|
||||
|
||||
**5. O(n log n) Overlap Removal**
|
||||
|
||||
- Sort anchors by position
|
||||
- Single pass with interval tracking using sorted list
|
||||
- Skip anchors that overlap with any already-selected anchor
|
||||
|
||||
### New Data Structures
|
||||
|
||||
```python
|
||||
# N-gram index: maps (word1, word2, ...) -> {source: [positions]}
|
||||
ngram_index: Dict[Tuple[str, ...], Dict[str, List[int]]]
|
||||
|
||||
# Covered positions in transcription (for greedy skip)
|
||||
covered_trans_positions: Set[int]
|
||||
```
|
||||
|
||||
### Performance Targets
|
||||
|
||||
- **Target**: Complete in under 30 seconds for any song
|
||||
- **Typical song**: 200-400 words, 3 reference sources
|
||||
- **Expected performance**: 1-5 seconds for typical inputs
|
||||
|
||||
## Implementation Plan
|
||||
|
||||
### Execution Order (Critical)
|
||||
|
||||
1. **Phase 0**: Create golden test fixtures and verify tests pass with current code
|
||||
2. **Phase 1-5**: Implement optimizations incrementally, running golden tests after each phase
|
||||
3. **Final**: Add performance benchmarks
|
||||
|
||||
### Files to Create/Modify
|
||||
|
||||
- `lyrics_transcriber_temp/scripts/generate_anchor_fixtures.py` (new)
|
||||
- `lyrics_transcriber_temp/tests/fixtures/anchor_golden/*.json` (new)
|
||||
- `lyrics_transcriber_temp/tests/unit/correction/test_anchor_sequence_golden.py` (new)
|
||||
- `lyrics_transcriber_temp/lyrics_transcriber/correction/anchor_sequence.py` (modify)
|
||||
|
||||
### Key Changes
|
||||
|
||||
**Phase 0: Golden Test Setup** (MUST complete and pass before any algorithm changes)
|
||||
|
||||
- Create fixture generation script with 10 representative test cases
|
||||
- Run script to generate fixtures using current implementation
|
||||
- Create golden test file that loads fixtures and verifies outputs
|
||||
- Verify all golden tests pass with current code
|
||||
|
||||
**Phase 1: Remove Multiprocessing**
|
||||
|
||||
- Replace `Pool().apply_async()` with direct function calls
|
||||
- Remove all pool creation, cleanup, and timeout handling
|
||||
- Single-threaded loop through n-gram lengths
|
||||
|
||||
**Phase 2: Add Hash-Based Index**
|
||||
|
||||
- New method `_build_ngram_index()` that builds lookup table during preprocessing
|
||||
- Modify `_find_matching_sources()` to use O(1) index lookup
|
||||
- Index built once, shared across all n-gram length iterations
|
||||
|
||||
**Phase 3: Greedy Position Skipping**
|
||||
|
||||
- Track covered transcription positions in a set
|
||||
- Skip n-grams that start in already-covered positions
|
||||
- Reduces redundant work significantly for songs with good matches
|
||||
|
||||
**Phase 4: Simplify Scoring**
|
||||
|
||||
- Add `use_nlp_scoring: bool = False` parameter to constructor
|
||||
- New method `_simple_score_anchor()` using rule-based heuristics
|
||||
- Keep spaCy scoring available for offline/high-quality mode
|
||||
|
||||
**Phase 5: Optimize Overlap Removal**
|
||||
|
||||
- Sort anchors by (start_position, -length)
|
||||
- Single pass: keep anchor if no overlap with last kept anchor
|
||||
- O(n log n) total instead of O(n^2)
|
||||
|
||||
## API Compatibility
|
||||
|
||||
The public interface remains unchanged:
|
||||
|
||||
- `find_anchors(transcribed, references, transcription_result) -> List[ScoredAnchor]`
|
||||
- `find_gaps(transcribed, anchors, references, transcription_result) -> List[GapSequence]`
|
||||
|
||||
New optional constructor parameters:
|
||||
|
||||
- `use_nlp_scoring: bool = False` - Enable spaCy-based phrase scoring (slower but higher quality)
|
||||
- Timeout parameter retained but less critical with efficient algorithm
|
||||
|
||||
## Fallback Strategy
|
||||
|
||||
If performance is still insufficient for edge cases:
|
||||
|
||||
1. **Early termination**: Stop after finding sufficient coverage (e.g., 80% of words anchored)
|
||||
2. **Adaptive n-gram range**: Start with medium lengths (8-15), expand only if needed
|
||||
3. **Sampling**: For very long songs, sample n-gram positions instead of exhaustive search
|
||||
|
||||
## Phase 0: Golden Test Setup (BEFORE any algorithm changes)
|
||||
|
||||
### Goal
|
||||
|
||||
Create regression tests using REAL song data from local cache to verify the optimized algorithm produces equivalent results.
|
||||
|
||||
### Cache File Structure (Understanding)
|
||||
|
||||
The local cache at `~/lyrics-transcriber-cache/` contains:
|
||||
|
||||
- **Reference lyrics**: `{provider}_{hash}_converted.json` where provider is spotify/genius/lrclib/musixmatch
|
||||
- Hash is based on (artist, title) lookup - same song shares same hash across providers
|
||||
- `_raw.json` contains metadata (track name, artist)
|
||||
- `_converted.json` contains LyricsData structure with segments/words
|
||||
- **Transcriptions**: `audioshake_{hash}_converted.json`
|
||||
- Hash is based on audio file content (different from reference hash)
|
||||
- Contains TranscriptionData structure
|
||||
- **Anchor results**: `anchors_{hash}.json`
|
||||
- Hash is computed from combined inputs (transcription + all references)
|
||||
|
||||
### Manual Song Selection
|
||||
|
||||
Identify 10 songs from cache with good coverage. Search raw files for track names:
|
||||
|
||||
### Finding Song Mappings
|
||||
|
||||
To link audioshake transcriptions to reference lyrics, search cache files:
|
||||
|
||||
```bash
|
||||
# Find songs by searching raw files for track names
|
||||
grep -h "trackName" ~/lyrics-transcriber-cache/spotify_*_raw.json | head -20
|
||||
|
||||
# Find audioshake files for a known song (e.g., search for filename patterns)
|
||||
ls ~/lyrics-transcriber-cache/audioshake_*_raw.json | head -20
|
||||
|
||||
# Search converted files for specific lyrics text
|
||||
grep -l "Napoleon did surrender" ~/lyrics-transcriber-cache/*_converted.json
|
||||
```
|
||||
|
||||
**Target song list** (reference_hash to be paired with audioshake_hash):
|
||||
|
||||
1. ABBA - Waterloo (refs: 3365f6a1e42388d84bcbfc0ac6f8aa6c) - short, repetitive chorus
|
||||
2. The Format - Time Bomb (refs: 3a3802ec28c4ab6689909b7ef784bb6f) - medium length
|
||||
3. Rancid - Time Bomb (refs: d02d20b854cbc6b890f274bd6c278752) - fast punk lyrics
|
||||
4. Minutemen - Storm in My House (refs: bc625704b26b307d8680ae5235b74994) - short
|
||||
5. + 6 more songs to be identified during fixture generation by exploring cache
|
||||
|
||||
### Fixture Generation Script
|
||||
|
||||
Create `lyrics_transcriber_temp/scripts/generate_anchor_fixtures.py`:
|
||||
|
||||
```python
|
||||
# Input: List of (name, audioshake_hash, reference_hash) tuples
|
||||
# For each:
|
||||
# 1. Load audioshake_{hash}_converted.json as transcription
|
||||
# 2. Load {spotify,genius,lrclib}_{hash}_converted.json as references
|
||||
# 3. Run current AnchorSequenceFinder
|
||||
# 4. Save complete fixture with inputs + outputs
|
||||
```
|
||||
|
||||
The script will:
|
||||
|
||||
1. Accept a config file listing the 10 song mappings
|
||||
2. Load real LyricsData from cache files
|
||||
3. Run the CURRENT AnchorSequenceFinder implementation
|
||||
4. Save fixtures that capture the real behavior
|
||||
|
||||
### Fixture Format
|
||||
|
||||
```
|
||||
lyrics_transcriber_temp/tests/fixtures/anchor_golden/
|
||||
- waterloo_abba.json
|
||||
- time_bomb_format.json
|
||||
- time_bomb_rancid.json
|
||||
- ...
|
||||
```
|
||||
|
||||
Each fixture contains REAL data:
|
||||
|
||||
```json
|
||||
{
|
||||
"name": "waterloo_abba",
|
||||
"description": "ABBA - Waterloo, short song with repetitive chorus",
|
||||
"source_hashes": {
|
||||
"audioshake": "1654b7c0755fad7f23bc888308f274de",
|
||||
"references": "3365f6a1e42388d84bcbfc0ac6f8aa6c"
|
||||
},
|
||||
"transcription": {
|
||||
"segments": [...], // Full LyricsData from audioshake cache
|
||||
"word_count": 150
|
||||
},
|
||||
"references": {
|
||||
"spotify": { "segments": [...] },
|
||||
"genius": { "segments": [...] },
|
||||
"lrclib": { "segments": [...] }
|
||||
},
|
||||
"expected_anchors": [
|
||||
{
|
||||
"text": "My my at Waterloo Napoleon did surrender",
|
||||
"transcription_position": 0,
|
||||
"length": 7,
|
||||
"reference_positions": {"spotify": 0, "genius": 0, "lrclib": 0},
|
||||
"confidence": 1.0
|
||||
},
|
||||
// ... all anchors from current implementation
|
||||
],
|
||||
"expected_anchor_count": 25,
|
||||
"expected_word_coverage": 142,
|
||||
"expected_coverage_percent": 94.6
|
||||
}
|
||||
```
|
||||
|
||||
### Golden Test
|
||||
|
||||
Create `lyrics_transcriber_temp/tests/unit/correction/test_anchor_sequence_golden.py`:
|
||||
|
||||
```python
|
||||
import pytest
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
FIXTURES_DIR = Path(__file__).parent.parent.parent / "fixtures" / "anchor_golden"
|
||||
|
||||
@pytest.fixture(params=list(FIXTURES_DIR.glob("*.json")))
|
||||
def golden_fixture(request):
|
||||
with open(request.param) as f:
|
||||
return json.load(f)
|
||||
|
||||
def test_anchor_count_matches(golden_fixture, anchor_finder):
|
||||
"""Anchor count should be within 10% of expected."""
|
||||
anchors = run_anchor_finder(golden_fixture)
|
||||
expected = golden_fixture["expected_anchor_count"]
|
||||
assert abs(len(anchors) - expected) <= expected * 0.1
|
||||
|
||||
def test_key_anchors_match(golden_fixture, anchor_finder):
|
||||
"""First, last, and longest anchors should match exactly."""
|
||||
anchors = run_anchor_finder(golden_fixture)
|
||||
expected = golden_fixture["expected_anchors"]
|
||||
# Compare first anchor
|
||||
assert anchors[0].text == expected[0]["text"]
|
||||
# Compare positions match
|
||||
...
|
||||
|
||||
def test_word_coverage(golden_fixture, anchor_finder):
|
||||
"""Total word coverage should be within 5% of expected."""
|
||||
anchors = run_anchor_finder(golden_fixture)
|
||||
coverage = calculate_coverage(anchors, golden_fixture)
|
||||
expected = golden_fixture["expected_coverage_percent"]
|
||||
assert abs(coverage - expected) <= 5.0
|
||||
|
||||
def test_no_invalid_positions(golden_fixture, anchor_finder):
|
||||
"""All anchor positions should be valid."""
|
||||
anchors = run_anchor_finder(golden_fixture)
|
||||
word_count = golden_fixture["transcription"]["word_count"]
|
||||
for anchor in anchors:
|
||||
assert 0 <= anchor.transcription_position < word_count
|
||||
```
|
||||
|
||||
### Validation Steps
|
||||
|
||||
1. **Generate fixtures from current implementation**:
|
||||
```bash
|
||||
cd lyrics_transcriber_temp
|
||||
python scripts/generate_anchor_fixtures.py
|
||||
```
|
||||
|
||||
2. **Verify fixtures were created**:
|
||||
```bash
|
||||
ls tests/fixtures/anchor_golden/
|
||||
# Should show 10 .json files
|
||||
```
|
||||
|
||||
3. **Run golden tests with CURRENT implementation**:
|
||||
```bash
|
||||
pytest tests/unit/correction/test_anchor_sequence_golden.py -v
|
||||
```
|
||||
|
||||
4. **All tests MUST pass before any algorithm changes**
|
||||
|
||||
5. **After each optimization phase, re-run golden tests**:
|
||||
```bash
|
||||
pytest tests/unit/correction/test_anchor_sequence_golden.py -v
|
||||
# Must still pass!
|
||||
```
|
||||
|
||||
|
||||
## Testing (Post-Optimization)
|
||||
|
||||
- Golden tests verify correctness (same outputs as before)
|
||||
- Existing unit tests verify API compatibility
|
||||
- Performance benchmark test with 30-second timeout assertion
|
||||
- Test with various song lengths via golden fixtures
|
||||
@@ -0,0 +1,717 @@
|
||||
---
|
||||
name: Instrumental Review UI
|
||||
overview: Add an intelligent instrumental selection workflow with audio analysis, waveform visualization, playback controls, and the ability to mute sections of backing vocals to create custom instrumentals. This replaces the current text-only CLI prompt with a web UI that works for both local and remote workflows, with shared core logic for DRY/maintainable code.
|
||||
todos:
|
||||
- id: shared-core-module
|
||||
content: Create karaoke_gen/instrumental_review/ shared module with AudioAnalyzer and AudioEditor classes (used by both local and remote)
|
||||
status: completed
|
||||
- id: shared-core-tests
|
||||
content: Add comprehensive unit tests for shared module with >80% coverage (tests/unit/test_instrumental_review.py)
|
||||
status: completed
|
||||
- id: backend-services
|
||||
content: Create backend service wrappers that use shared core module (audio_analysis_service.py, audio_editing_service.py)
|
||||
status: completed
|
||||
- id: backend-services-tests
|
||||
content: Add unit tests for backend services with mocked GCS interactions (backend/tests/test_audio_services.py)
|
||||
status: completed
|
||||
- id: api-endpoints
|
||||
content: Add new API endpoints for analysis, audio streaming, and custom instrumental creation
|
||||
status: completed
|
||||
- id: api-endpoints-tests
|
||||
content: Add API endpoint tests with >80% coverage (backend/tests/test_instrumental_api.py)
|
||||
status: completed
|
||||
- id: render-worker-integration
|
||||
content: Integrate audio analysis into render_video_worker before transitioning to awaiting_instrumental_selection
|
||||
status: completed
|
||||
- id: render-worker-tests
|
||||
content: Add/update render_video_worker tests to cover new analysis integration
|
||||
status: completed
|
||||
- id: frontend-components
|
||||
content: Create React components (WaveformDisplay, AudioPlayer, RegionSelector, InstrumentalReviewPage)
|
||||
status: completed
|
||||
- id: local-cli-integration
|
||||
content: Update local gen_cli.py to use shared core module with local file paths (feature parity with remote)
|
||||
status: completed
|
||||
- id: local-cli-review-server
|
||||
content: Add lightweight review server to local CLI for browser-based review (similar to lyrics review pattern)
|
||||
status: completed
|
||||
- id: remote-cli-update
|
||||
content: Update remote_cli.py to use new analysis API and open browser for review
|
||||
status: completed
|
||||
- id: cli-tests
|
||||
content: Add CLI tests verifying feature parity between local and remote modes
|
||||
status: completed
|
||||
- id: integration-tests
|
||||
content: Add end-to-end integration tests for the full instrumental review workflow
|
||||
status: completed
|
||||
---
|
||||
|
||||
# Intelligent Instrumental Selection Plan
|
||||
|
||||
## Current State
|
||||
|
||||
The instrumental selection workflow currently:
|
||||
|
||||
- Presents a simple 1/2 choice in the CLI (clean vs. with_backing)
|
||||
- Requires manual inspection in Audacity to evaluate backing vocals quality
|
||||
- Cannot handle the common "Scenario 3" where backing vocals need partial muting
|
||||
- Has no audio preview capability in remote mode
|
||||
|
||||
## Target Architecture
|
||||
|
||||
```
|
||||
┌────────────────────────────────────────────────────────────────────────────┐
|
||||
│ INSTRUMENTAL REVIEW WORKFLOW │
|
||||
├────────────────────────────────────────────────────────────────────────────┤
|
||||
│ │
|
||||
│ 1. AUDIO ANALYSIS (automatic after render_video completes) │
|
||||
│ │ │
|
||||
│ ├── Analyze backing vocals stem for amplitude │
|
||||
│ ├── Detect audible segments (> -40dB threshold) │
|
||||
│ ├── Generate waveform visualization image │
|
||||
│ └── Store analysis results in job state_data │
|
||||
│ │
|
||||
│ 2. AUTO-DECISION CHECK │
|
||||
│ │ │
|
||||
│ └── IF no audible segments detected: │
|
||||
│ ├── Set recommended_selection = "clean" │
|
||||
│ └── Skip to step 4 (or show minimal UI with suggestion) │
|
||||
│ │
|
||||
│ 3. HUMAN REVIEW (Web UI) │
|
||||
│ │ │
|
||||
│ ├── Display waveform with time axis │
|
||||
│ ├── Show audible segment markers │
|
||||
│ ├── Audio playback with waveform-click seeking │
|
||||
│ ├── Toggle between: clean / with_backing / preview-custom │
|
||||
│ ├── Select regions to mute (click/drag on waveform) │
|
||||
│ └── Create custom instrumental if regions selected │
|
||||
│ │
|
||||
│ 4. SELECTION SUBMISSION │
|
||||
│ │ │
|
||||
│ └── POST /api/jobs/{job_id}/select-instrumental │
|
||||
│ with selection = "clean" | "with_backing" | "custom" │
|
||||
│ │
|
||||
└────────────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## Architecture: Shared Core for DRY/SOLID
|
||||
|
||||
To ensure feature parity between local and remote CLIs while keeping code maintainable, we use a **shared core module** pattern:
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────────────────────┐
|
||||
│ SHARED CORE ARCHITECTURE │
|
||||
├─────────────────────────────────────────────────────────────────────────────┤
|
||||
│ │
|
||||
│ karaoke_gen/instrumental_review/ <── SHARED CORE MODULE │
|
||||
│ ├── __init__.py │
|
||||
│ ├── analyzer.py # AudioAnalyzer class (pure Python, no GCS) │
|
||||
│ ├── editor.py # AudioEditor class (pure Python, no GCS) │
|
||||
│ ├── waveform.py # WaveformGenerator class (matplotlib) │
|
||||
│ └── models.py # Pydantic models: AnalysisResult, MuteRegion │
|
||||
│ │
|
||||
│ ┌─────────────────────┐ ┌──────────────────────┐ │
|
||||
│ │ LOCAL CLI │ │ REMOTE BACKEND │ │
|
||||
│ │ (karaoke-gen) │ │ (Cloud Run) │ │
|
||||
│ ├─────────────────────┤ ├──────────────────────┤ │
|
||||
│ │ │ │ │ │
|
||||
│ │ gen_cli.py │ │ audio_analysis_ │ │
|
||||
│ │ └── uses shared ───┼──────────────┼──► service.py │ │
|
||||
│ │ core directly │ │ └── wraps shared│ │
|
||||
│ │ with local │ │ core with │ │
|
||||
│ │ file paths │ │ GCS I/O │ │
|
||||
│ │ │ │ │ │
|
||||
│ │ local_review_ │ │ audio_editing_ │ │
|
||||
│ │ server.py │ │ service.py │ │
|
||||
│ │ └── serves same ───┼──────────────┼──► (same pattern) │ │
|
||||
│ │ React UI │ │ │ │
|
||||
│ │ │ │ │ │
|
||||
│ └─────────────────────┘ └──────────────────────┘ │
|
||||
│ │
|
||||
│ BENEFITS: │
|
||||
│ ✓ Single source of truth for analysis logic │
|
||||
│ ✓ Bug fixes apply to both local and remote │
|
||||
│ ✓ Easy to test core logic without GCS mocks │
|
||||
│ ✓ Backend services are thin wrappers (Single Responsibility) │
|
||||
│ ✓ Same React UI served by both local server and Cloud Run │
|
||||
│ │
|
||||
└─────────────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### Shared Core Module Design
|
||||
|
||||
```python
|
||||
# karaoke_gen/instrumental_review/analyzer.py
|
||||
class AudioAnalyzer:
|
||||
"""
|
||||
Analyzes audio files for backing vocals content.
|
||||
Pure Python - no cloud dependencies. Works with local file paths.
|
||||
"""
|
||||
def __init__(self, silence_threshold_db: float = -40.0,
|
||||
min_segment_duration_ms: int = 100):
|
||||
self.silence_threshold_db = silence_threshold_db
|
||||
self.min_segment_duration_ms = min_segment_duration_ms
|
||||
|
||||
def analyze(self, audio_path: str) -> AnalysisResult:
|
||||
"""Analyze audio file and return structured result."""
|
||||
...
|
||||
|
||||
def get_amplitude_envelope(self, audio_path: str,
|
||||
window_ms: int = 100) -> List[float]:
|
||||
"""Get amplitude envelope for waveform rendering."""
|
||||
...
|
||||
|
||||
# karaoke_gen/instrumental_review/editor.py
|
||||
class AudioEditor:
|
||||
"""
|
||||
Creates custom instrumentals by muting regions of backing vocals.
|
||||
Pure Python - no cloud dependencies.
|
||||
"""
|
||||
def create_custom_instrumental(
|
||||
self,
|
||||
clean_instrumental_path: str,
|
||||
backing_vocals_path: str,
|
||||
mute_regions: List[MuteRegion],
|
||||
output_path: str
|
||||
) -> str:
|
||||
"""Create custom instrumental with muted regions."""
|
||||
...
|
||||
|
||||
# karaoke_gen/instrumental_review/waveform.py
|
||||
class WaveformGenerator:
|
||||
"""Generates waveform visualization images."""
|
||||
def generate(self, audio_path: str, output_path: str,
|
||||
segments: List[AudibleSegment] = None,
|
||||
width: int = 1200, height: int = 200) -> str:
|
||||
"""Generate waveform PNG with optional segment highlighting."""
|
||||
...
|
||||
```
|
||||
|
||||
## Implementation Components
|
||||
|
||||
### 1. Shared Core Module (karaoke_gen/instrumental_review/)
|
||||
|
||||
Create the shared module first - this is the foundation:
|
||||
|
||||
```python
|
||||
# karaoke_gen/instrumental_review/models.py
|
||||
from pydantic import BaseModel
|
||||
from typing import List, Optional
|
||||
from enum import Enum
|
||||
|
||||
class RecommendedSelection(str, Enum):
|
||||
CLEAN = "clean"
|
||||
WITH_BACKING = "with_backing"
|
||||
REVIEW_NEEDED = "review_needed"
|
||||
|
||||
class AudibleSegment(BaseModel):
|
||||
start_seconds: float
|
||||
end_seconds: float
|
||||
duration_seconds: float
|
||||
avg_amplitude_db: float
|
||||
|
||||
class MuteRegion(BaseModel):
|
||||
start_seconds: float
|
||||
end_seconds: float
|
||||
|
||||
class AnalysisResult(BaseModel):
|
||||
has_audible_content: bool
|
||||
total_duration_seconds: float
|
||||
audible_segments: List[AudibleSegment]
|
||||
recommended_selection: RecommendedSelection
|
||||
waveform_data: Optional[List[float]] = None # For JSON API response
|
||||
```
|
||||
|
||||
### 2. Backend Service Wrappers
|
||||
|
||||
Create `backend/services/audio_analysis_service.py`:
|
||||
|
||||
```python
|
||||
# Key functionality:
|
||||
- analyze_backing_vocals(audio_path) -> AnalysisResult
|
||||
- Uses pydub for audio loading
|
||||
- Calculates RMS amplitude in dB across time windows
|
||||
- Detects audible segments (contiguous regions > threshold)
|
||||
- Returns: {
|
||||
"has_audible_content": bool,
|
||||
"total_duration_seconds": float,
|
||||
"audible_segments": [
|
||||
{"start_seconds": float, "end_seconds": float,
|
||||
"duration_seconds": float, "avg_amplitude_db": float}
|
||||
],
|
||||
"recommended_selection": "clean" | "with_backing" | "review_needed"
|
||||
}
|
||||
|
||||
- generate_waveform_image(audio_path, output_path, segments=None) -> str
|
||||
- Uses matplotlib to render amplitude envelope over time
|
||||
- Highlights audible segments with different colors
|
||||
- Returns path to generated PNG image
|
||||
```
|
||||
|
||||
### 2. Audio Editing Service
|
||||
|
||||
Create `backend/services/audio_editing_service.py`:
|
||||
|
||||
```python
|
||||
# Key functionality:
|
||||
- create_custom_instrumental(
|
||||
clean_instrumental_path: str,
|
||||
backing_vocals_path: str,
|
||||
mute_regions: List[Tuple[float, float]], # [(start_s, end_s), ...]
|
||||
output_path: str
|
||||
) -> str
|
||||
- Loads backing vocals
|
||||
- Applies silence to mute_regions
|
||||
- Mixes with clean instrumental
|
||||
- Saves as new FLAC file
|
||||
```
|
||||
|
||||
### 3. Backend API Endpoints
|
||||
|
||||
Add to `backend/api/routes/jobs.py`:
|
||||
|
||||
```python
|
||||
GET /api/jobs/{job_id}/instrumental-analysis
|
||||
# Returns analysis data + waveform URL
|
||||
|
||||
GET /api/jobs/{job_id}/audio-stream/{stem_type}
|
||||
# Stream audio for playback (clean, backing_vocals, combined)
|
||||
|
||||
POST /api/jobs/{job_id}/create-custom-instrumental
|
||||
# Body: {"mute_regions": [[0.5, 2.3], [45.0, 48.5]]}
|
||||
# Creates custom instrumental, updates job state
|
||||
|
||||
POST /api/jobs/{job_id}/select-instrumental
|
||||
# Extended to accept: "clean" | "with_backing" | "custom"
|
||||
```
|
||||
|
||||
### 4. Frontend Web UI
|
||||
|
||||
Create `frontend/app/jobs/[id]/instrumental-review/page.tsx`:
|
||||
|
||||
```
|
||||
Components needed:
|
||||
- WaveformDisplay: SVG/Canvas waveform with time axis
|
||||
- AudioPlayer: HTML5 audio with controls + waveform sync
|
||||
- RegionSelector: Click/drag to select mute regions
|
||||
- InstrumentalOptions: Radio buttons for clean/backing/custom
|
||||
- SegmentList: Table showing detected audible segments
|
||||
```
|
||||
|
||||
Key interactions:
|
||||
|
||||
- Click on waveform to seek playback position
|
||||
- Drag on waveform to select mute region
|
||||
- Toggle audio source (clean/backing/preview)
|
||||
- Submit selection
|
||||
|
||||
### 5. Backend Worker Updates
|
||||
|
||||
Modify `backend/workers/render_video_worker.py`:
|
||||
|
||||
```python
|
||||
# After video render completes, before transitioning to AWAITING_INSTRUMENTAL_SELECTION:
|
||||
1. Download backing_vocals stem
|
||||
2. Run audio analysis
|
||||
3. Generate waveform image
|
||||
4. Upload waveform to GCS
|
||||
5. Store analysis results in job.state_data
|
||||
6. If no audible content: set recommended_selection = "clean"
|
||||
7. Transition to AWAITING_INSTRUMENTAL_SELECTION
|
||||
```
|
||||
|
||||
### 6. CLI Updates
|
||||
|
||||
Modify `karaoke_gen/utils/remote_cli.py`:
|
||||
|
||||
```python
|
||||
def handle_instrumental_selection(self, job_id: str):
|
||||
# Get analysis data
|
||||
analysis = self.client.get_instrumental_analysis(job_id)
|
||||
|
||||
# If no backing vocals detected, suggest auto-select
|
||||
if analysis['recommended_selection'] == 'clean':
|
||||
if self.config.non_interactive:
|
||||
# Auto-select clean
|
||||
self.client.select_instrumental(job_id, 'clean')
|
||||
return
|
||||
else:
|
||||
# Show suggestion, offer to open browser for verification
|
||||
self.logger.info("No backing vocals detected - recommending clean instrumental")
|
||||
# Open browser anyway so user can verify if desired
|
||||
|
||||
# Open browser to instrumental review UI
|
||||
self.open_instrumental_review_ui(job_id)
|
||||
|
||||
# Poll until selection made
|
||||
while job.status == 'awaiting_instrumental_selection':
|
||||
time.sleep(self.config.poll_interval)
|
||||
```
|
||||
|
||||
### 7. Local CLI Integration (Feature Parity)
|
||||
|
||||
The local CLI (`karaoke-gen`) uses the **same shared core module** as the backend:
|
||||
|
||||
```python
|
||||
# karaoke_gen/utils/gen_cli.py - Updated instrumental selection flow
|
||||
|
||||
def handle_instrumental_selection(self, output_dir: str, base_name: str):
|
||||
"""Handle instrumental selection using shared core module."""
|
||||
from karaoke_gen.instrumental_review import AudioAnalyzer, WaveformGenerator
|
||||
|
||||
# Paths to local files (already exist from audio separation)
|
||||
backing_vocals_path = os.path.join(output_dir, "stems",
|
||||
f"{base_name} (Backing Vocals ...).flac")
|
||||
clean_instrumental_path = os.path.join(output_dir, "stems",
|
||||
f"{base_name} (Instrumental ...).flac")
|
||||
|
||||
# Use SAME analyzer as backend
|
||||
analyzer = AudioAnalyzer(silence_threshold_db=-40.0)
|
||||
analysis = analyzer.analyze(backing_vocals_path)
|
||||
|
||||
# Generate waveform locally
|
||||
waveform_path = os.path.join(output_dir, "backing_vocals_waveform.png")
|
||||
WaveformGenerator().generate(backing_vocals_path, waveform_path,
|
||||
analysis.audible_segments)
|
||||
|
||||
if not analysis.has_audible_content:
|
||||
self.logger.info("No backing vocals detected - using clean instrumental")
|
||||
if not self.non_interactive:
|
||||
# Offer to open browser for verification
|
||||
...
|
||||
return "clean"
|
||||
|
||||
# Start local review server (serves same React UI)
|
||||
from karaoke_gen.instrumental_review.server import InstrumentalReviewServer
|
||||
server = InstrumentalReviewServer(
|
||||
output_dir=output_dir,
|
||||
base_name=base_name,
|
||||
analysis=analysis,
|
||||
waveform_path=waveform_path,
|
||||
)
|
||||
server.start_and_open_browser() # Blocking until user submits selection
|
||||
|
||||
return server.get_selection()
|
||||
```
|
||||
|
||||
### 8. Local Review Server
|
||||
|
||||
Create `karaoke_gen/instrumental_review/server.py`:
|
||||
|
||||
```python
|
||||
"""
|
||||
Lightweight local server for instrumental review.
|
||||
Serves the same React frontend used by the cloud backend.
|
||||
Similar pattern to LyricsTranscriber's ReviewServer.
|
||||
"""
|
||||
from http.server import HTTPServer, SimpleHTTPRequestHandler
|
||||
import json
|
||||
import threading
|
||||
|
||||
class InstrumentalReviewServer:
|
||||
"""
|
||||
Local HTTP server for instrumental review UI.
|
||||
|
||||
Endpoints:
|
||||
- GET /api/analysis - Returns analysis data
|
||||
- GET /api/audio/{type} - Streams audio files
|
||||
- GET /api/waveform - Returns waveform image
|
||||
- POST /api/create-custom - Creates custom instrumental
|
||||
- POST /api/select - Submits selection
|
||||
- GET /* - Serves React frontend static files
|
||||
"""
|
||||
def __init__(self, output_dir: str, base_name: str,
|
||||
analysis: AnalysisResult, waveform_path: str):
|
||||
...
|
||||
|
||||
def start_and_open_browser(self, port: int = 8765):
|
||||
"""Start server, open browser, block until selection submitted."""
|
||||
...
|
||||
|
||||
def get_selection(self) -> str:
|
||||
"""Get the user's selection after browser submission."""
|
||||
...
|
||||
```
|
||||
|
||||
## Testing Strategy
|
||||
|
||||
### Test Coverage Requirements
|
||||
|
||||
All new code must meet the project's **70% minimum coverage** requirement, with critical paths targeting **>80%**:
|
||||
|
||||
| Module | Target Coverage | Test File |
|
||||
|
||||
|--------|----------------|-----------|
|
||||
|
||||
| `karaoke_gen/instrumental_review/analyzer.py` | >90% | `tests/unit/test_instrumental_analyzer.py` |
|
||||
|
||||
| `karaoke_gen/instrumental_review/editor.py` | >90% | `tests/unit/test_instrumental_editor.py` |
|
||||
|
||||
| `karaoke_gen/instrumental_review/waveform.py` | >80% | `tests/unit/test_instrumental_waveform.py` |
|
||||
|
||||
| `karaoke_gen/instrumental_review/server.py` | >70% | `tests/unit/test_instrumental_server.py` |
|
||||
|
||||
| `backend/services/audio_analysis_service.py` | >80% | `backend/tests/test_audio_analysis_service.py` |
|
||||
|
||||
| `backend/services/audio_editing_service.py` | >80% | `backend/tests/test_audio_editing_service.py` |
|
||||
|
||||
| `backend/api/routes/jobs.py` (new endpoints) | >80% | `backend/tests/test_instrumental_api.py` |
|
||||
|
||||
### Test Categories
|
||||
|
||||
**1. Unit Tests (Shared Core) - tests/unit/test_instrumental_*.py**
|
||||
|
||||
```python
|
||||
# tests/unit/test_instrumental_analyzer.py
|
||||
class TestAudioAnalyzer:
|
||||
def test_analyze_silent_audio_returns_no_audible_content(self):
|
||||
"""Silent audio should return has_audible_content=False."""
|
||||
|
||||
def test_analyze_audio_with_content_detects_segments(self):
|
||||
"""Audio with content should detect audible segments."""
|
||||
|
||||
def test_segment_detection_respects_threshold(self):
|
||||
"""Segments below threshold should not be detected."""
|
||||
|
||||
def test_segment_merging_for_close_segments(self):
|
||||
"""Close segments should be merged into one."""
|
||||
|
||||
def test_recommended_selection_clean_for_silent(self):
|
||||
"""Silent audio should recommend 'clean'."""
|
||||
|
||||
def test_recommended_selection_review_for_content(self):
|
||||
"""Audio with content should recommend 'review_needed'."""
|
||||
|
||||
# tests/unit/test_instrumental_editor.py
|
||||
class TestAudioEditor:
|
||||
def test_mute_single_region(self):
|
||||
"""Single mute region should be applied correctly."""
|
||||
|
||||
def test_mute_multiple_regions(self):
|
||||
"""Multiple mute regions should all be applied."""
|
||||
|
||||
def test_mute_region_boundaries(self):
|
||||
"""Mute region at start/end of audio should work."""
|
||||
|
||||
def test_output_format_is_flac(self):
|
||||
"""Output should be FLAC format."""
|
||||
|
||||
def test_combines_with_clean_instrumental(self):
|
||||
"""Result should be backing vocals mixed with clean instrumental."""
|
||||
```
|
||||
|
||||
**2. Unit Tests (Backend Services) - backend/tests/test_audio_*_service.py**
|
||||
|
||||
```python
|
||||
# backend/tests/test_audio_analysis_service.py
|
||||
class TestAudioAnalysisService:
|
||||
@pytest.fixture
|
||||
def mock_storage(self):
|
||||
"""Mock GCS storage service."""
|
||||
|
||||
def test_analyze_downloads_from_gcs(self, mock_storage):
|
||||
"""Service should download audio from GCS before analysis."""
|
||||
|
||||
def test_analyze_uploads_waveform_to_gcs(self, mock_storage):
|
||||
"""Service should upload waveform image to GCS."""
|
||||
|
||||
def test_analyze_updates_job_state_data(self, mock_storage):
|
||||
"""Service should store analysis in job.state_data."""
|
||||
```
|
||||
|
||||
**3. API Endpoint Tests - backend/tests/test_instrumental_api.py**
|
||||
|
||||
```python
|
||||
# backend/tests/test_instrumental_api.py
|
||||
class TestInstrumentalAnalysisEndpoint:
|
||||
def test_get_analysis_returns_data(self, client, mock_job):
|
||||
"""GET /instrumental-analysis should return analysis data."""
|
||||
|
||||
def test_get_analysis_requires_correct_status(self, client, mock_job):
|
||||
"""Should return 400 if job not in correct status."""
|
||||
|
||||
class TestAudioStreamEndpoint:
|
||||
def test_stream_backing_vocals(self, client, mock_job):
|
||||
"""Should stream backing vocals audio."""
|
||||
|
||||
def test_stream_clean_instrumental(self, client, mock_job):
|
||||
"""Should stream clean instrumental audio."""
|
||||
|
||||
class TestCreateCustomInstrumental:
|
||||
def test_create_with_mute_regions(self, client, mock_job):
|
||||
"""Should create custom instrumental with mute regions."""
|
||||
|
||||
def test_validates_mute_regions(self, client, mock_job):
|
||||
"""Should validate mute region boundaries."""
|
||||
```
|
||||
|
||||
**4. Integration Tests - tests/integration/test_instrumental_review.py**
|
||||
|
||||
```python
|
||||
# tests/integration/test_instrumental_review_flow.py
|
||||
class TestInstrumentalReviewFlow:
|
||||
"""End-to-end tests for instrumental review workflow."""
|
||||
|
||||
def test_full_flow_clean_selection(self):
|
||||
"""Test complete flow: analysis -> review -> select clean."""
|
||||
|
||||
def test_full_flow_with_backing_selection(self):
|
||||
"""Test complete flow: analysis -> review -> select with_backing."""
|
||||
|
||||
def test_full_flow_custom_creation(self):
|
||||
"""Test complete flow: analysis -> mute regions -> custom."""
|
||||
|
||||
def test_auto_recommend_clean_for_silent_backing(self):
|
||||
"""When no backing vocals, should recommend clean."""
|
||||
```
|
||||
|
||||
**5. CLI Feature Parity Tests - tests/unit/test_cli_feature_parity.py**
|
||||
|
||||
```python
|
||||
# tests/unit/test_cli_feature_parity.py
|
||||
class TestCLIFeatureParity:
|
||||
"""Verify local and remote CLIs have equivalent functionality."""
|
||||
|
||||
def test_both_clis_use_same_analyzer(self):
|
||||
"""Both CLIs should use AudioAnalyzer from shared module."""
|
||||
|
||||
def test_both_clis_support_custom_instrumental(self):
|
||||
"""Both CLIs should support creating custom instrumentals."""
|
||||
|
||||
def test_analysis_results_identical(self):
|
||||
"""Same audio should produce identical analysis from both CLIs."""
|
||||
```
|
||||
|
||||
### Test Data
|
||||
|
||||
Create test fixtures in `tests/data/instrumental_review/`:
|
||||
|
||||
- `silent_backing_vocals.flac` - Silent/near-silent audio (~10s)
|
||||
- `backing_vocals_with_content.flac` - Audio with clear backing vocals (~30s)
|
||||
- `backing_vocals_mixed_quality.flac` - Audio with some good/some bad sections (~30s)
|
||||
|
||||
Use pydub to programmatically generate these in `tests/conftest.py` fixtures.
|
||||
|
||||
## File Changes Summary
|
||||
|
||||
| Category | Files to Create/Modify |
|
||||
|
||||
|----------|------------------------|
|
||||
|
||||
| **Shared Core** | `karaoke_gen/instrumental_review/__init__.py` (new) |
|
||||
|
||||
| Shared Core | `karaoke_gen/instrumental_review/models.py` (new) |
|
||||
|
||||
| Shared Core | `karaoke_gen/instrumental_review/analyzer.py` (new) |
|
||||
|
||||
| Shared Core | `karaoke_gen/instrumental_review/editor.py` (new) |
|
||||
|
||||
| Shared Core | `karaoke_gen/instrumental_review/waveform.py` (new) |
|
||||
|
||||
| Shared Core | `karaoke_gen/instrumental_review/server.py` (new) |
|
||||
|
||||
| **Backend Services** | `backend/services/audio_analysis_service.py` (new) |
|
||||
|
||||
| Backend Services | `backend/services/audio_editing_service.py` (new) |
|
||||
|
||||
| **API** | `backend/api/routes/jobs.py` (modify - add endpoints) |
|
||||
|
||||
| API | `backend/api/routes/instrumental.py` (new - if endpoints get large) |
|
||||
|
||||
| **Workers** | `backend/workers/render_video_worker.py` (modify) |
|
||||
|
||||
| **Models** | `backend/models/job.py` (add analysis fields to state_data) |
|
||||
|
||||
| **Frontend** | `frontend/app/jobs/[id]/instrumental-review/page.tsx` (new) |
|
||||
|
||||
| Frontend | `frontend/components/waveform-display.tsx` (new) |
|
||||
|
||||
| Frontend | `frontend/components/audio-player-with-waveform.tsx` (new) |
|
||||
|
||||
| Frontend | `frontend/components/region-selector.tsx` (new) |
|
||||
|
||||
| **Local CLI** | `karaoke_gen/utils/gen_cli.py` (modify) |
|
||||
|
||||
| **Remote CLI** | `karaoke_gen/utils/remote_cli.py` (modify) |
|
||||
|
||||
| **Tests - Shared** | `tests/unit/test_instrumental_analyzer.py` (new) |
|
||||
|
||||
| Tests - Shared | `tests/unit/test_instrumental_editor.py` (new) |
|
||||
|
||||
| Tests - Shared | `tests/unit/test_instrumental_waveform.py` (new) |
|
||||
|
||||
| Tests - Shared | `tests/unit/test_instrumental_server.py` (new) |
|
||||
|
||||
| **Tests - Backend** | `backend/tests/test_audio_analysis_service.py` (new) |
|
||||
|
||||
| Tests - Backend | `backend/tests/test_audio_editing_service.py` (new) |
|
||||
|
||||
| Tests - Backend | `backend/tests/test_instrumental_api.py` (new) |
|
||||
|
||||
| **Tests - Parity** | `tests/unit/test_cli_feature_parity.py` (new) |
|
||||
|
||||
| **Tests - Integration** | `tests/integration/test_instrumental_review.py` (new) |
|
||||
|
||||
| **Test Data** | `tests/conftest.py` (modify - add fixtures) |
|
||||
|
||||
## Dependencies
|
||||
|
||||
Already available in `pyproject.toml`:
|
||||
|
||||
- `pydub>=0.25.1` - Audio loading and manipulation
|
||||
- `matplotlib>=3` - Waveform visualization
|
||||
- `numpy>=2` - Audio array processing
|
||||
|
||||
Frontend:
|
||||
|
||||
- React/Next.js (existing)
|
||||
- HTML5 Audio API (native)
|
||||
- Canvas or SVG for waveform (native)
|
||||
|
||||
## Implementation Order
|
||||
|
||||
Execute in this order to enable incremental testing:
|
||||
|
||||
### Phase 1: Shared Core Module (Foundation)
|
||||
|
||||
1. Create `karaoke_gen/instrumental_review/` package with models, analyzer, editor, waveform
|
||||
2. Add comprehensive unit tests for shared core (>90% coverage)
|
||||
3. Create test audio fixtures in `tests/conftest.py`
|
||||
|
||||
### Phase 2: Backend Integration
|
||||
|
||||
4. Create backend service wrappers with GCS integration
|
||||
5. Add backend service unit tests with mocked GCS
|
||||
6. Add new API endpoints to `backend/api/routes/jobs.py`
|
||||
7. Add API endpoint tests
|
||||
8. Integrate analysis into `render_video_worker.py`
|
||||
9. Update render worker tests
|
||||
|
||||
### Phase 3: Frontend
|
||||
|
||||
10. Create React components (WaveformDisplay, AudioPlayer, RegionSelector)
|
||||
11. Create instrumental review page
|
||||
12. Test frontend manually with backend
|
||||
|
||||
### Phase 4: CLI Integration
|
||||
|
||||
13. Update `remote_cli.py` to use new analysis API and open browser
|
||||
14. Create local review server `karaoke_gen/instrumental_review/server.py`
|
||||
15. Update `gen_cli.py` to use shared core and local server
|
||||
16. Add CLI feature parity tests
|
||||
|
||||
### Phase 5: Integration Testing
|
||||
|
||||
17. Add end-to-end integration tests
|
||||
18. Manual testing of full workflow (local and remote)
|
||||
|
||||
### Verification Checklist
|
||||
|
||||
- [ ] All unit tests pass: `pytest tests/unit/ -v`
|
||||
- [ ] All backend tests pass: `pytest backend/tests/ -v`
|
||||
- [ ] Coverage meets 70% minimum: `pytest --cov=karaoke_gen --cov-fail-under=70`
|
||||
- [ ] Local CLI works: `karaoke-gen "Artist" "Title"` (reaches instrumental selection)
|
||||
- [ ] Remote CLI works: `karaoke-gen-remote ./audio.flac "Artist" "Title"`
|
||||
- [ ] Both CLIs produce identical analysis for same audio
|
||||
- [ ] Custom instrumental creation works in both modes
|
||||
- [ ] Version bumped in `pyproject.toml`
|
||||
@@ -0,0 +1,217 @@
|
||||
---
|
||||
name: MidiCo-Style Synchronizer
|
||||
overview: Build a new MidiCo-style Synchronizer component for efficient re-syncing of lyrics timing, particularly for fixing progressive drift in the second half of songs. This involves refactoring the "Edit All" entry point and creating a high-performance timeline-based sync interface.
|
||||
todos:
|
||||
- id: mode-selection-modal
|
||||
content: Create ModeSelectionModal for 'Replace All' vs 'Re-sync Existing' choice
|
||||
status: completed
|
||||
- id: timeline-canvas
|
||||
content: Build canvas-based TimelineCanvas component for high-performance word block rendering
|
||||
status: completed
|
||||
- id: upcoming-words-bar
|
||||
content: Create UpcomingWordsBar component showing next unsynced words in fixed position
|
||||
status: completed
|
||||
- id: sync-controls
|
||||
content: Build SyncControls with Start Sync, Clear Sync, Unsync from Cursor, Delete Selected buttons
|
||||
status: completed
|
||||
- id: lyrics-synchronizer
|
||||
content: Create main LyricsSynchronizer component integrating all sub-components
|
||||
status: completed
|
||||
- id: unsync-from-cursor
|
||||
content: Add 'unsync from cursor' functionality to useManualSync hook
|
||||
status: completed
|
||||
- id: integrate-modal
|
||||
content: Integrate new synchronizer into ReplaceAllLyricsModal with mode selection
|
||||
status: completed
|
||||
- id: word-selection
|
||||
content: Implement single-click and drag-select for word blocks
|
||||
status: completed
|
||||
- id: zoom-slider
|
||||
content: Add smooth zoom slider with 4.5s-24s range
|
||||
status: completed
|
||||
- id: performance-test
|
||||
content: Test performance with long songs and optimize as needed
|
||||
status: completed
|
||||
---
|
||||
|
||||
# MidiCo-Style Synchronizer Implementation
|
||||
|
||||
## Current State Analysis
|
||||
|
||||
The existing implementation in [`ReplaceAllLyricsModal.tsx`](lyrics_transcriber_temp/lyrics_transcriber/frontend/src/components/ReplaceAllLyricsModal.tsx) has two phases:
|
||||
|
||||
1. **Paste Phase** - User pastes new lyrics text
|
||||
2. **Sync Phase** - Manual sync using spacebar with timeline view
|
||||
|
||||
Key existing components:
|
||||
|
||||
- [`useManualSync.ts`](lyrics_transcriber_temp/lyrics_transcriber/frontend/src/hooks/useManualSync.ts) - Spacebar handling, tap/hold detection
|
||||
- [`EditTimelineSection.tsx`](lyrics_transcriber_temp/lyrics_transcriber/frontend/src/components/EditTimelineSection.tsx) - Timeline controls with zoom/scroll
|
||||
- [`TimelineEditor.tsx`](lyrics_transcriber_temp/lyrics_transcriber/frontend/src/components/TimelineEditor.tsx) - Timeline rendering
|
||||
|
||||
**Problems with current implementation:**
|
||||
|
||||
1. Forces full lyrics replacement - no option to keep existing sync data
|
||||
2. Performance issues (laggy, slow rendering)
|
||||
3. Poor UX for seeing upcoming words while syncing
|
||||
4. No "unsync from cursor" feature for fixing drift
|
||||
5. No two-level word block layout for overlapping segments
|
||||
|
||||
## Architecture Overview
|
||||
|
||||
```mermaid
|
||||
flowchart TB
|
||||
subgraph Entry [Entry Point]
|
||||
EditAll[Edit All Button]
|
||||
EditAll --> ChoiceModal[Mode Selection Modal]
|
||||
ChoiceModal -->|Replace All| PastePhase[Paste New Lyrics]
|
||||
ChoiceModal -->|Re-sync Existing| SyncView[Synchronizer View]
|
||||
PastePhase --> SyncView
|
||||
end
|
||||
|
||||
subgraph Sync [Synchronizer Component]
|
||||
SyncView --> Timeline[Timeline Canvas]
|
||||
SyncView --> Controls[Control Buttons]
|
||||
SyncView --> UpcomingWords[Upcoming Words Display]
|
||||
Timeline --> WordBlocks[Word Blocks Renderer]
|
||||
Timeline --> Playhead[Playhead Marker]
|
||||
Timeline --> TimeBar[Time Bar]
|
||||
end
|
||||
|
||||
subgraph Audio [Audio Integration]
|
||||
AudioPlayer[Audio Player]
|
||||
AudioPlayer <--> SyncView
|
||||
end
|
||||
```
|
||||
|
||||
## Implementation Plan
|
||||
|
||||
### Phase 1: Entry Point Refactor
|
||||
|
||||
Modify the "Edit All" button flow to show a choice modal:
|
||||
|
||||
```typescript
|
||||
// New ModeSelectionModal component
|
||||
interface ModeSelectionModalProps {
|
||||
open: boolean
|
||||
onClose: () => void
|
||||
onSelectReplace: () => void // Goes to paste phase
|
||||
onSelectResync: () => void // Goes directly to sync view
|
||||
}
|
||||
```
|
||||
|
||||
- **Replace All Lyrics**: Current flow (paste box -> sync)
|
||||
- **Re-sync Existing Lyrics**: Load current segments directly into sync view
|
||||
|
||||
### Phase 2: New Synchronizer Component
|
||||
|
||||
Create a new high-performance `LyricsSynchronizer.tsx` component inspired by MidiCo:
|
||||
|
||||
#### Core Features
|
||||
|
||||
1. **Timeline Canvas** (HTML5 Canvas for performance)
|
||||
|
||||
- Time bar at top (MM:SS format with decisecond ticks)
|
||||
- Playhead with arrow indicator + vertical line
|
||||
- Red word blocks with text labels
|
||||
- Two-level word layout for overlapping segments
|
||||
- Zoom slider (4.5s to 24s visible range)
|
||||
- Horizontal scroll with smooth panning
|
||||
|
||||
2. **Upcoming Words Display** (dual location)
|
||||
|
||||
- Fixed position above timeline: next words as red/white blocks
|
||||
- On timeline: words appear to right of playhead during sync
|
||||
|
||||
3. **Control Buttons**
|
||||
|
||||
- **Start Sync** - Begin sync mode from first unsynced word
|
||||
- **Clear Sync** - Reset all word timings to null
|
||||
- **Edit Lyrics** - Modal to edit lyrics text (warns about timing loss)
|
||||
- **Unsync from Cursor** - Critical: reset all words after playhead position
|
||||
- **Split/Edit Word** - Edit single selected word
|
||||
- **Delete Selected** - Remove selected word blocks
|
||||
|
||||
4. **Word Selection**
|
||||
|
||||
- Single click: select one word (white border)
|
||||
- Click-drag on background: selection rectangle for multi-select
|
||||
- Click on time bar: set playhead position
|
||||
|
||||
5. **Spacebar Sync Logic** (reuse/enhance `useManualSync`)
|
||||
|
||||
- Tap: set start time, default 500ms duration
|
||||
- Hold: set both start and end times
|
||||
- Handle previous word end time calculation
|
||||
|
||||
### Phase 3: Performance Optimization
|
||||
|
||||
The current `TimelineEditor` uses DOM elements which causes lag. New approach:
|
||||
|
||||
1. **Canvas-based rendering** for word blocks and timeline
|
||||
|
||||
- Single canvas element, no DOM nodes per word
|
||||
- RequestAnimationFrame for smooth playhead updates
|
||||
- Only re-render changed regions
|
||||
|
||||
2. **Virtual scrolling** for very long songs
|
||||
|
||||
- Only render visible word blocks
|
||||
- Cache off-screen block positions
|
||||
|
||||
3. **Debounced state updates**
|
||||
|
||||
- Batch word timing updates
|
||||
- Throttle zoom/scroll handlers
|
||||
|
||||
### Phase 4: Apply/Cancel Flow
|
||||
|
||||
Changes are held in local state until user clicks Apply:
|
||||
|
||||
```typescript
|
||||
interface SynchronizerState {
|
||||
words: Word[] // Working copy of words
|
||||
segments: LyricsSegment[] // Working copy of segments
|
||||
isDirty: boolean // Has unsaved changes
|
||||
}
|
||||
```
|
||||
|
||||
- **Apply**: Commit changes to parent component
|
||||
- **Cancel**: Discard changes, close modal
|
||||
|
||||
## File Changes
|
||||
|
||||
### New Files
|
||||
|
||||
- `src/components/LyricsSynchronizer.tsx` - Main synchronizer component
|
||||
- `src/components/LyricsSynchronizer/TimelineCanvas.tsx` - Canvas-based timeline
|
||||
- `src/components/LyricsSynchronizer/UpcomingWordsBar.tsx` - Fixed upcoming words display
|
||||
- `src/components/LyricsSynchronizer/SyncControls.tsx` - Control buttons
|
||||
- `src/components/ModeSelectionModal.tsx` - Entry point choice modal
|
||||
|
||||
### Modified Files
|
||||
|
||||
- [`ReplaceAllLyricsModal.tsx`](lyrics_transcriber_temp/lyrics_transcriber/frontend/src/components/ReplaceAllLyricsModal.tsx) - Add mode selection, integrate new synchronizer
|
||||
- [`useManualSync.ts`](lyrics_transcriber_temp/lyrics_transcriber/frontend/src/hooks/useManualSync.ts) - Add "unsync from cursor" functionality
|
||||
|
||||
## Key UX Details from MidiCo Reference
|
||||
|
||||
Per the documentation at [`MIDICO_SYNCHRONIZER_REFERENCE.md`](lyrics_transcriber_temp/docs/MIDICO_SYNCHRONIZER_REFERENCE.md):
|
||||
|
||||
1. **Zoom range**: 4.5s (max zoom) to 24s (min zoom) visible
|
||||
2. **Timeline click behavior**:
|
||||
|
||||
- Time bar click = set playhead (no playback change)
|
||||
- Background click = nothing (prevent accidental deselection)
|
||||
- Word block click = select
|
||||
|
||||
3. **Two-level word blocks**: Adjacent/overlapping words display on alternating vertical levels
|
||||
4. **Playhead**: Small arrow in time bar + white vertical line spanning timeline height
|
||||
5. **Selection rectangle**: Click-drag on background creates selection box
|
||||
|
||||
## Testing Strategy
|
||||
|
||||
1. Manual testing with the provided URL: `http://localhost:8000/?baseApiUrl=...`
|
||||
2. Test sync accuracy with songs that have known drift issues
|
||||
3. Performance testing with 400+ word songs
|
||||
4. Test "unsync from cursor" workflow for fixing drift
|
||||
@@ -1,21 +0,0 @@
|
||||
---
|
||||
description: Git branching and PR workflow
|
||||
alwaysApply: true
|
||||
---
|
||||
|
||||
# Branching Workflow
|
||||
|
||||
**Never commit directly to `main`.** Always work on a feature branch.
|
||||
|
||||
Create descriptive branch names like `feature/add-discord-notifications`, `fix/audio-sync-issue`, or `refactor/cleanup-api-routes`.
|
||||
|
||||
# Creating a Pull Request
|
||||
|
||||
Once all changes are complete, tests pass, and commits are pushed, create a PR with:
|
||||
|
||||
1. **Summary** - Brief overview of the changes
|
||||
2. **Changes Made** - List of specific modifications
|
||||
3. **Testing** - How changes were tested (unit tests, manual testing)
|
||||
4. **Related Issues** - Reference any GitHub issues (e.g., "Fixes #123")
|
||||
|
||||
Only merge after review and CI checks pass.
|
||||
@@ -1,14 +0,0 @@
|
||||
# Infrastructure Changes
|
||||
|
||||
All Google Cloud infrastructure (IAM, Cloud Storage, Cloud Run, Secret Manager, Artifact Registry, etc.) must be managed via Pulumi in the `infrastructure/` folder.
|
||||
|
||||
## Rules
|
||||
|
||||
- **Reading/querying** with `gcloud` CLI is fine
|
||||
- **Creating or modifying** resources must go through IaC — never use `gcloud` or the Console to make changes
|
||||
|
||||
## Workflow
|
||||
|
||||
1. Make changes in `infrastructure/`
|
||||
2. Run `pulumi preview` and verify the output
|
||||
3. Run `pulumi up` to apply
|
||||
@@ -1,27 +0,0 @@
|
||||
---
|
||||
description: Version bumping rule for commits
|
||||
alwaysApply: true
|
||||
---
|
||||
|
||||
# Version Management
|
||||
|
||||
When committing and pushing changes, always bump the patch version in `pyproject.toml`.
|
||||
|
||||
The version is located at `tool.poetry.version` in `pyproject.toml`. For example, if the current version is `0.70.3`, bump it to `0.70.4`.
|
||||
|
||||
This ensures every commit pushed to the repository has a unique version number for tracking and deployment purposes.
|
||||
|
||||
# Testing Requirements
|
||||
|
||||
Before committing and pushing changes, ensure all tests pass:
|
||||
|
||||
```bash
|
||||
python -m pytest tests/ backend/tests/ -v -x --ignore=tests/integration
|
||||
```
|
||||
|
||||
Ensure all code touched is thoroughly covered by unit tests, we have a 70% coverage minimum in CI:
|
||||
```bash
|
||||
poetry run pytest tests/unit/ -v --cov=karaoke_gen --cov-report=xml --cov-report=term-missing --cov-fail-under=70
|
||||
```
|
||||
|
||||
Do not commit or push code that fails tests. Fix any test failures before proceeding.
|
||||
File renamed without changes.
@@ -0,0 +1,815 @@
|
||||
name: CI
|
||||
|
||||
on:
|
||||
push:
|
||||
pull_request:
|
||||
branches: [main]
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
pages: write
|
||||
id-token: write
|
||||
|
||||
concurrency:
|
||||
group: "ci-${{ github.ref }}"
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
# ============================================
|
||||
# PATH FILTERING - Determine what changed
|
||||
# ============================================
|
||||
|
||||
changes:
|
||||
name: "Detect Changes"
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
frontend: ${{ steps.filter.outputs.frontend }}
|
||||
backend: ${{ steps.filter.outputs.backend }}
|
||||
package: ${{ steps.filter.outputs.package }}
|
||||
infra: ${{ steps.filter.outputs.infra }}
|
||||
deps: ${{ steps.filter.outputs.deps }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- uses: dorny/paths-filter@v3
|
||||
id: filter
|
||||
with:
|
||||
filters: |
|
||||
frontend:
|
||||
- 'frontend/**'
|
||||
backend:
|
||||
- 'backend/**'
|
||||
package:
|
||||
- 'karaoke_gen/**'
|
||||
- 'lyrics_transcriber_temp/**'
|
||||
- 'tests/**'
|
||||
infra:
|
||||
- 'infrastructure/**'
|
||||
deps:
|
||||
- 'poetry.lock'
|
||||
|
||||
- name: Summary
|
||||
run: |
|
||||
echo "### Change Detection Results" >> $GITHUB_STEP_SUMMARY
|
||||
echo "| Area | Changed |" >> $GITHUB_STEP_SUMMARY
|
||||
echo "|------|---------|" >> $GITHUB_STEP_SUMMARY
|
||||
echo "| Frontend | ${{ steps.filter.outputs.frontend }} |" >> $GITHUB_STEP_SUMMARY
|
||||
echo "| Backend | ${{ steps.filter.outputs.backend }} |" >> $GITHUB_STEP_SUMMARY
|
||||
echo "| Package | ${{ steps.filter.outputs.package }} |" >> $GITHUB_STEP_SUMMARY
|
||||
echo "| Infrastructure | ${{ steps.filter.outputs.infra }} |" >> $GITHUB_STEP_SUMMARY
|
||||
echo "| Dependencies | ${{ steps.filter.outputs.deps }} |" >> $GITHUB_STEP_SUMMARY
|
||||
|
||||
# ============================================
|
||||
# FRONTEND TESTS
|
||||
# ============================================
|
||||
|
||||
frontend-unit-tests:
|
||||
name: "Frontend - Unit Tests"
|
||||
runs-on: ubuntu-latest
|
||||
needs: changes
|
||||
if: ${{ needs.changes.outputs.frontend == 'true' || github.ref == 'refs/heads/main' }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Node.js with caching
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: '20'
|
||||
cache: 'npm'
|
||||
cache-dependency-path: frontend/package-lock.json
|
||||
|
||||
- name: Install dependencies
|
||||
working-directory: frontend
|
||||
run: npm ci --legacy-peer-deps
|
||||
|
||||
- name: Run unit tests with coverage
|
||||
working-directory: frontend
|
||||
run: npm run test:ci
|
||||
|
||||
- name: Upload coverage report
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: frontend-coverage
|
||||
path: frontend/coverage/
|
||||
retention-days: 7
|
||||
|
||||
# ============================================
|
||||
# PACKAGE TESTS (karaoke-gen Python CLI)
|
||||
# ============================================
|
||||
|
||||
package-unit-tests:
|
||||
name: "Package - Unit Tests (70% coverage)"
|
||||
runs-on: ubuntu-latest
|
||||
needs: changes
|
||||
if: ${{ needs.changes.outputs.package == 'true' || needs.changes.outputs.deps == 'true' || github.ref == 'refs/heads/main' }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: true
|
||||
|
||||
- name: Set up Python 3.13
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.13"
|
||||
|
||||
- name: Install Poetry
|
||||
uses: snok/install-poetry@v1
|
||||
with:
|
||||
virtualenvs-create: true
|
||||
virtualenvs-in-project: true
|
||||
|
||||
- name: Cache Poetry dependencies
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: .venv
|
||||
key: venv-package-${{ runner.os }}-py3.13-${{ hashFiles('poetry.lock') }}
|
||||
restore-keys: |
|
||||
venv-package-${{ runner.os }}-py3.13-
|
||||
|
||||
- name: Install dependencies
|
||||
run: poetry install --with dev
|
||||
|
||||
- name: Install system dependencies
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y ffmpeg
|
||||
|
||||
- name: Cache spaCy model
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: ~/.cache/spacy
|
||||
key: spacy-en_core_web_sm-${{ runner.os }}
|
||||
|
||||
- name: Install spaCy language models
|
||||
run: poetry run python -m spacy download en_core_web_sm
|
||||
|
||||
- name: Run unit tests
|
||||
run: |
|
||||
poetry run pytest tests/unit/ -v --cov=karaoke_gen --cov-report=xml --cov-report=term-missing --cov-fail-under=69
|
||||
|
||||
- name: Upload coverage reports
|
||||
uses: codecov/codecov-action@v5
|
||||
with:
|
||||
token: ${{ secrets.CODECOV_TOKEN }}
|
||||
files: ./coverage.xml
|
||||
flags: unittests
|
||||
name: codecov-umbrella
|
||||
|
||||
package-integration-tests:
|
||||
name: "Package - Integration Tests"
|
||||
runs-on: ubuntu-latest
|
||||
needs: changes
|
||||
if: ${{ needs.changes.outputs.package == 'true' || needs.changes.outputs.deps == 'true' || github.ref == 'refs/heads/main' }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: true
|
||||
|
||||
- name: Set up Python 3.13
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.13"
|
||||
|
||||
- name: Install Poetry
|
||||
uses: snok/install-poetry@v1
|
||||
with:
|
||||
virtualenvs-create: true
|
||||
virtualenvs-in-project: true
|
||||
|
||||
- name: Cache Poetry dependencies
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: .venv
|
||||
key: venv-package-${{ runner.os }}-py3.13-${{ hashFiles('poetry.lock') }}
|
||||
restore-keys: |
|
||||
venv-package-${{ runner.os }}-py3.13-
|
||||
|
||||
- name: Install dependencies
|
||||
run: poetry install --with dev
|
||||
|
||||
- name: Install system dependencies
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y ffmpeg
|
||||
|
||||
- name: Cache spaCy model
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: ~/.cache/spacy
|
||||
key: spacy-en_core_web_sm-${{ runner.os }}
|
||||
|
||||
- name: Install spaCy language models
|
||||
run: poetry run python -m spacy download en_core_web_sm
|
||||
|
||||
- name: Run integration tests
|
||||
run: poetry run pytest tests/integration/ -v
|
||||
|
||||
package-build:
|
||||
name: "Package - Build & Install"
|
||||
runs-on: ubuntu-latest
|
||||
needs: [changes, package-unit-tests, package-integration-tests]
|
||||
if: ${{ always() && (needs.package-unit-tests.result == 'success' || needs.package-unit-tests.result == 'skipped') && (needs.package-integration-tests.result == 'success' || needs.package-integration-tests.result == 'skipped') && (needs.changes.outputs.package == 'true' || needs.changes.outputs.deps == 'true' || github.ref == 'refs/heads/main') }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: true
|
||||
|
||||
- name: Set up Python 3.13
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.13"
|
||||
|
||||
- name: Install Poetry
|
||||
uses: snok/install-poetry@v1
|
||||
with:
|
||||
virtualenvs-create: true
|
||||
virtualenvs-in-project: true
|
||||
|
||||
- name: Cache Poetry dependencies
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: .venv
|
||||
key: venv-package-${{ runner.os }}-py3.13-${{ hashFiles('poetry.lock') }}
|
||||
restore-keys: |
|
||||
venv-package-${{ runner.os }}-py3.13-
|
||||
|
||||
- name: Build package
|
||||
run: poetry build
|
||||
|
||||
- name: Free disk space
|
||||
uses: jlumbroso/free-disk-space@main
|
||||
with:
|
||||
tool-cache: false
|
||||
android: true
|
||||
haskell: true
|
||||
dotnet: false
|
||||
large-packages: false
|
||||
docker-images: false
|
||||
swap-storage: false
|
||||
|
||||
- name: Test package installation
|
||||
run: |
|
||||
pip install dist/*.whl
|
||||
python -m karaoke_gen.utils.gen_cli --help
|
||||
|
||||
- name: Upload build artifacts
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: package-dist
|
||||
path: dist/
|
||||
retention-days: 1
|
||||
|
||||
# ============================================
|
||||
# BACKEND TESTS (Cloud Run API service)
|
||||
# ============================================
|
||||
|
||||
backend-unit-tests:
|
||||
name: "Backend - Unit Tests"
|
||||
runs-on: ubuntu-latest
|
||||
needs: changes
|
||||
if: ${{ needs.changes.outputs.backend == 'true' || needs.changes.outputs.package == 'true' || needs.changes.outputs.deps == 'true' || github.ref == 'refs/heads/main' }}
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: false
|
||||
|
||||
- name: Set up Python 3.13
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.13"
|
||||
|
||||
- name: Install Poetry
|
||||
uses: snok/install-poetry@v1
|
||||
with:
|
||||
virtualenvs-create: true
|
||||
virtualenvs-in-project: true
|
||||
|
||||
- name: Cache Poetry dependencies
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: .venv
|
||||
key: venv-backend-${{ runner.os }}-py3.13-${{ hashFiles('poetry.lock') }}
|
||||
restore-keys: |
|
||||
venv-backend-${{ runner.os }}-py3.13-
|
||||
|
||||
- name: Install dependencies
|
||||
run: poetry install
|
||||
|
||||
- name: Run all backend unit tests
|
||||
env:
|
||||
GOOGLE_CLOUD_PROJECT: test-project
|
||||
GCS_BUCKET_NAME: test-bucket
|
||||
FIRESTORE_COLLECTION: jobs
|
||||
ENVIRONMENT: test
|
||||
run: |
|
||||
poetry run pytest \
|
||||
backend/tests/ \
|
||||
--ignore=backend/tests/emulator \
|
||||
-v --tb=short
|
||||
|
||||
backend-emulator-tests:
|
||||
name: "Backend - Emulator Integration Tests"
|
||||
runs-on: ubuntu-latest
|
||||
needs: changes
|
||||
if: ${{ needs.changes.outputs.backend == 'true' || needs.changes.outputs.package == 'true' || needs.changes.outputs.deps == 'true' || github.ref == 'refs/heads/main' }}
|
||||
steps:
|
||||
- name: Free disk space
|
||||
run: |
|
||||
sudo rm -rf /usr/share/dotnet
|
||||
sudo rm -rf /opt/ghc
|
||||
sudo rm -rf /usr/local/share/boost
|
||||
df -h
|
||||
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: false
|
||||
|
||||
- name: Set up Python 3.13
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.13"
|
||||
|
||||
- name: Install Poetry
|
||||
uses: snok/install-poetry@v1
|
||||
with:
|
||||
virtualenvs-create: true
|
||||
virtualenvs-in-project: true
|
||||
|
||||
- name: Cache Poetry dependencies
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: .venv
|
||||
key: venv-backend-${{ runner.os }}-py3.13-${{ hashFiles('poetry.lock') }}
|
||||
restore-keys: |
|
||||
venv-backend-${{ runner.os }}-py3.13-
|
||||
|
||||
- name: Set up Java 21 (required by Firestore emulator)
|
||||
uses: actions/setup-java@v4
|
||||
with:
|
||||
distribution: "temurin"
|
||||
java-version: "21"
|
||||
|
||||
- name: Set up Cloud SDK
|
||||
uses: google-github-actions/setup-gcloud@v2
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Install Firestore emulator
|
||||
run: gcloud components install beta cloud-firestore-emulator --quiet
|
||||
|
||||
- name: Install dependencies
|
||||
run: poetry install
|
||||
|
||||
- name: Start Docker for GCS emulator
|
||||
run: docker pull fsouza/fake-gcs-server:latest
|
||||
|
||||
- name: Run emulator integration tests
|
||||
run: |
|
||||
chmod +x scripts/*.sh
|
||||
./scripts/run-emulator-tests.sh
|
||||
|
||||
- name: Upload test results
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: backend-test-results
|
||||
path: backend/htmlcov/
|
||||
retention-days: 7
|
||||
|
||||
backend-lint:
|
||||
name: "Backend - Code Quality"
|
||||
runs-on: ubuntu-latest
|
||||
needs: changes
|
||||
if: ${{ needs.changes.outputs.backend == 'true' || needs.changes.outputs.package == 'true' || github.ref == 'refs/heads/main' }}
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: false
|
||||
|
||||
- name: Set up Python 3.13
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.13"
|
||||
|
||||
- name: Install Poetry
|
||||
uses: snok/install-poetry@v1
|
||||
with:
|
||||
virtualenvs-create: true
|
||||
virtualenvs-in-project: true
|
||||
|
||||
- name: Cache Poetry dependencies
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: .venv
|
||||
key: venv-lint-${{ runner.os }}-py3.13-${{ hashFiles('poetry.lock') }}
|
||||
restore-keys: |
|
||||
venv-lint-${{ runner.os }}-py3.13-
|
||||
|
||||
- name: Install dependencies
|
||||
run: poetry install
|
||||
|
||||
- name: Run validation (syntax check only)
|
||||
run: |
|
||||
poetry run python -m py_compile backend/main.py backend/config.py
|
||||
echo "✅ Basic syntax validation passed"
|
||||
|
||||
# ============================================
|
||||
# DEPLOYMENTS (main branch only)
|
||||
# ============================================
|
||||
|
||||
package-publish:
|
||||
name: "Deploy - Publish to PyPI"
|
||||
runs-on: ubuntu-latest
|
||||
needs: [package-build]
|
||||
if: github.ref == 'refs/heads/main' && github.event_name == 'push'
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: true
|
||||
|
||||
- name: Set up Python 3.13
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.13"
|
||||
|
||||
- name: Install Poetry
|
||||
uses: snok/install-poetry@v1
|
||||
|
||||
- name: Download build artifacts
|
||||
uses: actions/download-artifact@v4
|
||||
with:
|
||||
name: package-dist
|
||||
path: dist/
|
||||
|
||||
- name: Extract version
|
||||
id: extract_version
|
||||
run: |
|
||||
VERSION=$(poetry version --short)
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
echo "📋 Extracted version: $VERSION"
|
||||
|
||||
- name: Check if tag exists
|
||||
id: check_tag
|
||||
run: |
|
||||
VERSION="${{ steps.extract_version.outputs.version }}"
|
||||
if git ls-remote --tags origin | grep -q "refs/tags/v$VERSION$"; then
|
||||
echo "tag_exists=true" >> $GITHUB_OUTPUT
|
||||
echo "🏷️ Tag v$VERSION already exists, skipping release"
|
||||
else
|
||||
echo "tag_exists=false" >> $GITHUB_OUTPUT
|
||||
echo "✨ Tag v$VERSION does not exist, proceeding with release"
|
||||
fi
|
||||
|
||||
- name: Publish to PyPI
|
||||
if: steps.check_tag.outputs.tag_exists == 'false'
|
||||
run: |
|
||||
echo "📦 Publishing the following files to PyPI:"
|
||||
ls -la dist/
|
||||
echo "🚀 Publishing to PyPI..."
|
||||
poetry config pypi-token.pypi ${{ secrets.PYPI_API_TOKEN }}
|
||||
poetry publish
|
||||
|
||||
- name: Create Git Tag
|
||||
if: steps.check_tag.outputs.tag_exists == 'false'
|
||||
run: |
|
||||
git config user.name github-actions
|
||||
git config user.email github-actions@github.com
|
||||
git tag -a "v${{ steps.extract_version.outputs.version }}" -m "Release v${{ steps.extract_version.outputs.version }}"
|
||||
git push https://${{ secrets.GITHUB_TOKEN }}@github.com/${{ github.repository }} "v${{ steps.extract_version.outputs.version }}"
|
||||
|
||||
- name: Create GitHub Release
|
||||
if: steps.check_tag.outputs.tag_exists == 'false'
|
||||
uses: softprops/action-gh-release@v1
|
||||
with:
|
||||
tag_name: "v${{ steps.extract_version.outputs.version }}"
|
||||
name: "v${{ steps.extract_version.outputs.version }}"
|
||||
body: |
|
||||
## Changes in v${{ steps.extract_version.outputs.version }}
|
||||
|
||||
This release was automatically created from the main branch.
|
||||
|
||||
### Installation
|
||||
```bash
|
||||
pip install karaoke-gen==${{ steps.extract_version.outputs.version }}
|
||||
```
|
||||
|
||||
### Assets
|
||||
- Python package published to PyPI
|
||||
- Frontend deployed to GitHub Pages at gen.nomadkaraoke.com
|
||||
|
||||
For detailed changes, see the commit history.
|
||||
draft: false
|
||||
prerelease: false
|
||||
files: |
|
||||
dist/*.whl
|
||||
dist/*.tar.gz
|
||||
|
||||
deploy-frontend:
|
||||
name: "Deploy - Frontend (GitHub Pages)"
|
||||
runs-on: ubuntu-latest
|
||||
needs: [frontend-unit-tests]
|
||||
if: ${{ always() && github.ref == 'refs/heads/main' && github.event_name == 'push' && (needs.frontend-unit-tests.result == 'success' || needs.frontend-unit-tests.result == 'skipped') }}
|
||||
environment:
|
||||
name: github-pages
|
||||
url: ${{ steps.deployment.outputs.page_url }}
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Node.js with caching
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: '20'
|
||||
cache: 'npm'
|
||||
cache-dependency-path: frontend/package-lock.json
|
||||
|
||||
- name: Enable Yarn (for lyrics frontend)
|
||||
run: corepack enable
|
||||
|
||||
# ===== Build Main Frontend (Next.js) =====
|
||||
- name: Install main frontend dependencies
|
||||
working-directory: frontend
|
||||
run: npm ci --legacy-peer-deps
|
||||
|
||||
- name: Build main frontend (Next.js static export)
|
||||
working-directory: frontend
|
||||
env:
|
||||
NEXT_PUBLIC_API_URL: https://api.nomadkaraoke.com
|
||||
run: npm run build
|
||||
|
||||
# ===== Build Lyrics Review Frontend (Vite) =====
|
||||
- name: Cache Yarn dependencies (lyrics frontend)
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: lyrics_transcriber_temp/lyrics_transcriber/frontend/node_modules
|
||||
key: yarn-lyrics-${{ runner.os }}-${{ hashFiles('lyrics_transcriber_temp/lyrics_transcriber/frontend/yarn.lock') }}
|
||||
restore-keys: |
|
||||
yarn-lyrics-${{ runner.os }}-
|
||||
|
||||
- name: Install lyrics frontend dependencies
|
||||
working-directory: lyrics_transcriber_temp/lyrics_transcriber/frontend
|
||||
run: yarn install --frozen-lockfile
|
||||
|
||||
- name: Build lyrics frontend (Vite)
|
||||
working-directory: lyrics_transcriber_temp/lyrics_transcriber/frontend
|
||||
env:
|
||||
# Set base path for subpath deployment
|
||||
VITE_BASE_PATH: /lyrics/
|
||||
run: yarn build --base=/lyrics/
|
||||
|
||||
- name: Copy lyrics frontend to main output
|
||||
run: |
|
||||
mkdir -p frontend/out/lyrics
|
||||
cp -r lyrics_transcriber_temp/lyrics_transcriber/frontend/dist/* frontend/out/lyrics/
|
||||
|
||||
# ===== Copy Instrumental Review UI (Static HTML) =====
|
||||
- name: Copy instrumental review UI to main output
|
||||
run: |
|
||||
mkdir -p frontend/out/instrumental
|
||||
cp karaoke_gen/instrumental_review/static/index.html frontend/out/instrumental/
|
||||
|
||||
- name: Setup Pages
|
||||
uses: actions/configure-pages@v4
|
||||
|
||||
- name: Upload artifact
|
||||
uses: actions/upload-pages-artifact@v3
|
||||
with:
|
||||
path: "frontend/out"
|
||||
|
||||
- name: Deploy to GitHub Pages
|
||||
id: deployment
|
||||
uses: actions/deploy-pages@v4
|
||||
|
||||
deploy-backend:
|
||||
name: "Deploy - Backend (Cloud Run)"
|
||||
runs-on: ubuntu-latest
|
||||
needs: [backend-unit-tests, backend-emulator-tests, backend-lint]
|
||||
if: ${{ always() && github.ref == 'refs/heads/main' && github.event_name == 'push' && (needs.backend-unit-tests.result == 'success' || needs.backend-unit-tests.result == 'skipped') && (needs.backend-emulator-tests.result == 'success' || needs.backend-emulator-tests.result == 'skipped') && (needs.backend-lint.result == 'success' || needs.backend-lint.result == 'skipped') }}
|
||||
permissions:
|
||||
contents: read
|
||||
id-token: write
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: false
|
||||
fetch-depth: 0 # Need full history for tag check
|
||||
|
||||
- name: Set up Python (for version extraction)
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.13"
|
||||
|
||||
- name: Install Poetry
|
||||
uses: snok/install-poetry@v1
|
||||
|
||||
- name: Extract version and check if deployment needed
|
||||
id: version_check
|
||||
run: |
|
||||
VERSION=$(poetry version --short)
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
echo "📋 Current version: $VERSION"
|
||||
|
||||
if git ls-remote --tags origin | grep -q "refs/tags/v$VERSION$"; then
|
||||
echo "needs_deploy=false" >> $GITHUB_OUTPUT
|
||||
echo "⏭️ Tag v$VERSION already exists - skipping backend deployment"
|
||||
echo " (Bump version in pyproject.toml to trigger a new deployment)"
|
||||
else
|
||||
echo "needs_deploy=true" >> $GITHUB_OUTPUT
|
||||
echo "✨ Tag v$VERSION does not exist - proceeding with deployment"
|
||||
fi
|
||||
|
||||
- name: Authenticate to Google Cloud (Workload Identity)
|
||||
if: steps.version_check.outputs.needs_deploy == 'true'
|
||||
id: auth
|
||||
uses: google-github-actions/auth@v2
|
||||
with:
|
||||
workload_identity_provider: ${{ secrets.GCP_WORKLOAD_IDENTITY_PROVIDER }}
|
||||
service_account: ${{ secrets.GCP_SERVICE_ACCOUNT }}
|
||||
|
||||
- name: Set up Cloud SDK
|
||||
if: steps.version_check.outputs.needs_deploy == 'true'
|
||||
uses: google-github-actions/setup-gcloud@v2
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Check if base image needs rebuild
|
||||
if: steps.version_check.outputs.needs_deploy == 'true'
|
||||
id: check-base
|
||||
run: |
|
||||
echo "🔍 Checking if base image needs rebuild..."
|
||||
|
||||
# Hash both poetry.lock AND Dockerfile.base - rebuild if either changes
|
||||
CURRENT_HASH=$(cat poetry.lock backend/Dockerfile.base | sha256sum | cut -d' ' -f1)
|
||||
echo "Current combined hash (poetry.lock + Dockerfile.base): $CURRENT_HASH"
|
||||
|
||||
gcloud auth configure-docker us-central1-docker.pkg.dev --quiet
|
||||
|
||||
BASE_IMAGE="us-central1-docker.pkg.dev/nomadkaraoke/karaoke-repo/karaoke-backend-base:latest"
|
||||
EXISTING_HASH=""
|
||||
|
||||
if docker pull $BASE_IMAGE 2>/dev/null; then
|
||||
EXISTING_HASH=$(docker inspect $BASE_IMAGE --format='{{index .Config.Labels "base.content.hash"}}' 2>/dev/null || echo "")
|
||||
# Fallback to old label name for backwards compatibility
|
||||
if [ -z "$EXISTING_HASH" ]; then
|
||||
EXISTING_HASH=$(docker inspect $BASE_IMAGE --format='{{index .Config.Labels "poetry.lock.hash"}}' 2>/dev/null || echo "")
|
||||
fi
|
||||
echo "Existing base image hash: $EXISTING_HASH"
|
||||
else
|
||||
echo "⚠️ No existing base image found"
|
||||
fi
|
||||
|
||||
if [ "$CURRENT_HASH" != "$EXISTING_HASH" ]; then
|
||||
echo "🔄 Base image needs rebuild (poetry.lock or Dockerfile.base changed)"
|
||||
echo "needs_rebuild=true" >> $GITHUB_OUTPUT
|
||||
else
|
||||
echo "✅ Base image is up to date"
|
||||
echo "needs_rebuild=false" >> $GITHUB_OUTPUT
|
||||
fi
|
||||
|
||||
- name: Rebuild base image (if needed)
|
||||
if: steps.version_check.outputs.needs_deploy == 'true' && steps.check-base.outputs.needs_rebuild == 'true'
|
||||
run: |
|
||||
echo "🏗️ Rebuilding base image with updated dependencies..."
|
||||
|
||||
BASE_BUILD_ID=$(gcloud builds submit \
|
||||
--config=cloudbuild-base.yaml \
|
||||
--project=nomadkaraoke \
|
||||
--format='value(id)' \
|
||||
--async \
|
||||
.)
|
||||
|
||||
echo "Base Build ID: $BASE_BUILD_ID"
|
||||
echo "Build URL: https://console.cloud.google.com/cloud-build/builds/$BASE_BUILD_ID?project=nomadkaraoke"
|
||||
|
||||
echo "Waiting for base image build to complete..."
|
||||
while true; do
|
||||
BUILD_STATUS=$(gcloud builds describe $BASE_BUILD_ID --project=nomadkaraoke --format='value(status)')
|
||||
echo "Base build status: $BUILD_STATUS"
|
||||
|
||||
if [ "$BUILD_STATUS" = "SUCCESS" ]; then
|
||||
echo "✅ Base image build completed successfully"
|
||||
break
|
||||
elif [ "$BUILD_STATUS" = "FAILURE" ] || [ "$BUILD_STATUS" = "CANCELLED" ] || [ "$BUILD_STATUS" = "TIMEOUT" ]; then
|
||||
echo "❌ Base image build failed with status: $BUILD_STATUS"
|
||||
echo ""
|
||||
echo "==================== BUILD LOGS ===================="
|
||||
gcloud logging read "resource.type=build AND resource.labels.build_id=$BASE_BUILD_ID" \
|
||||
--project=nomadkaraoke \
|
||||
--format="value(textPayload)" \
|
||||
--limit=200 \
|
||||
--order=asc || echo "Failed to retrieve logs from Cloud Logging"
|
||||
echo "===================================================="
|
||||
gcloud builds log $BASE_BUILD_ID --project=nomadkaraoke 2>&1 || true
|
||||
exit 1
|
||||
fi
|
||||
|
||||
sleep 30
|
||||
done
|
||||
|
||||
- name: Trigger Cloud Build
|
||||
if: steps.version_check.outputs.needs_deploy == 'true'
|
||||
run: |
|
||||
echo "🚀 Triggering Cloud Build for deployment..."
|
||||
echo "Commit: ${{ github.sha }}"
|
||||
echo "Version: ${{ steps.version_check.outputs.version }}"
|
||||
|
||||
BUILD_ID=$(gcloud builds submit \
|
||||
--config=cloudbuild.yaml \
|
||||
--project=nomadkaraoke \
|
||||
--format='value(id)' \
|
||||
--async \
|
||||
.)
|
||||
|
||||
echo "Build ID: $BUILD_ID"
|
||||
echo "Build URL: https://console.cloud.google.com/cloud-build/builds/$BUILD_ID?project=nomadkaraoke"
|
||||
|
||||
echo "Waiting for build to complete..."
|
||||
while true; do
|
||||
BUILD_STATUS=$(gcloud builds describe $BUILD_ID --project=nomadkaraoke --format='value(status)')
|
||||
echo "Build status: $BUILD_STATUS"
|
||||
|
||||
if [ "$BUILD_STATUS" = "SUCCESS" ]; then
|
||||
echo "✅ Build completed successfully"
|
||||
break
|
||||
elif [ "$BUILD_STATUS" = "FAILURE" ] || [ "$BUILD_STATUS" = "CANCELLED" ] || [ "$BUILD_STATUS" = "TIMEOUT" ]; then
|
||||
echo "❌ Build failed with status: $BUILD_STATUS"
|
||||
echo ""
|
||||
echo "==================== BUILD LOGS ===================="
|
||||
gcloud logging read "resource.type=build AND resource.labels.build_id=$BUILD_ID" \
|
||||
--project=nomadkaraoke \
|
||||
--format="value(textPayload)" \
|
||||
--limit=200 \
|
||||
--order=asc || echo "Failed to retrieve logs from Cloud Logging"
|
||||
echo "===================================================="
|
||||
echo ""
|
||||
gcloud builds log $BUILD_ID --project=nomadkaraoke 2>&1 || true
|
||||
exit 1
|
||||
fi
|
||||
|
||||
sleep 30
|
||||
done
|
||||
|
||||
- name: Verify deployment and version
|
||||
if: steps.version_check.outputs.needs_deploy == 'true'
|
||||
run: |
|
||||
EXPECTED_VERSION="${{ steps.version_check.outputs.version }}"
|
||||
SERVICE_URL=$(gcloud run services describe karaoke-backend \
|
||||
--region us-central1 \
|
||||
--format 'value(status.url)')
|
||||
|
||||
echo "Service URL: $SERVICE_URL"
|
||||
echo "Expected version: $EXPECTED_VERSION"
|
||||
|
||||
# Wait for new revision to be ready
|
||||
echo "Waiting for new revision to be ready..."
|
||||
sleep 15
|
||||
|
||||
# Basic health check
|
||||
curl -f "$SERVICE_URL/api/health" || exit 1
|
||||
echo "✅ Service is healthy"
|
||||
|
||||
# Version verification with retries (Cloud Run may take time to route to new revision)
|
||||
MAX_RETRIES=6
|
||||
RETRY_DELAY=10
|
||||
for i in $(seq 1 $MAX_RETRIES); do
|
||||
echo "Checking deployed version (attempt $i/$MAX_RETRIES)..."
|
||||
DEPLOYED_VERSION=$(curl -sf "$SERVICE_URL/api/health/detailed" | jq -r '.version // empty')
|
||||
|
||||
if [ "$DEPLOYED_VERSION" = "$EXPECTED_VERSION" ]; then
|
||||
echo "✅ Version verified: $DEPLOYED_VERSION"
|
||||
break
|
||||
else
|
||||
echo "⚠️ Version mismatch: deployed=$DEPLOYED_VERSION, expected=$EXPECTED_VERSION"
|
||||
if [ $i -lt $MAX_RETRIES ]; then
|
||||
echo " Retrying in ${RETRY_DELAY}s..."
|
||||
sleep $RETRY_DELAY
|
||||
else
|
||||
echo "❌ Version verification failed after $MAX_RETRIES attempts"
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
done
|
||||
|
||||
- name: Summary
|
||||
if: steps.version_check.outputs.needs_deploy == 'true' && success()
|
||||
run: |
|
||||
echo "🎉 Deployment successful!"
|
||||
echo "Version: ${{ steps.version_check.outputs.version }}"
|
||||
echo "Commit: ${{ github.sha }}"
|
||||
echo "Branch: ${{ github.ref_name }}"
|
||||
echo "Run: ${{ github.run_number }}"
|
||||
|
||||
- name: Skipped deployment summary
|
||||
if: steps.version_check.outputs.needs_deploy == 'false'
|
||||
run: |
|
||||
echo "⏭️ Backend deployment skipped - version ${{ steps.version_check.outputs.version }} already deployed"
|
||||
echo ""
|
||||
echo "To deploy a new version:"
|
||||
echo " 1. Update version in pyproject.toml"
|
||||
echo " 2. Commit and push to main"
|
||||
@@ -1,187 +0,0 @@
|
||||
name: Test and Publish
|
||||
|
||||
on: [push, pull_request, workflow_dispatch]
|
||||
|
||||
# Add permissions for GitHub Pages deployment and git operations
|
||||
permissions:
|
||||
contents: write # Changed from 'read' to 'write' to allow creating git tags
|
||||
pages: write
|
||||
id-token: write
|
||||
|
||||
# Allow only one concurrent deployment, skipping runs queued between the run in-progress and latest queued.
|
||||
concurrency:
|
||||
group: "pages"
|
||||
cancel-in-progress: false
|
||||
|
||||
jobs:
|
||||
test:
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
matrix:
|
||||
python-version: ['3.13']
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
|
||||
- name: Install Poetry
|
||||
uses: snok/install-poetry@v1
|
||||
with:
|
||||
virtualenvs-create: true
|
||||
virtualenvs-in-project: true
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
poetry install --with dev
|
||||
|
||||
- name: Install system dependencies
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y ffmpeg
|
||||
|
||||
- name: Install spaCy language models
|
||||
run: |
|
||||
poetry run python -m spacy download en_core_web_sm
|
||||
|
||||
- name: Run unit tests
|
||||
run: |
|
||||
poetry run pytest tests/unit/ -v --cov=karaoke_gen --cov-report=xml --cov-report=term-missing --cov-fail-under=70
|
||||
|
||||
- name: Upload coverage reports
|
||||
uses: codecov/codecov-action@v5
|
||||
with:
|
||||
token: ${{ secrets.CODECOV_TOKEN }}
|
||||
files: ./coverage.xml
|
||||
flags: unittests
|
||||
name: codecov-umbrella
|
||||
|
||||
- name: Run integration tests
|
||||
run: |
|
||||
poetry run pytest tests/integration/ -v
|
||||
|
||||
- name: Build package
|
||||
run: |
|
||||
poetry build
|
||||
|
||||
- name: Free Disk Space (GHA Ubuntu Runner)
|
||||
uses: jlumbroso/free-disk-space@main
|
||||
with:
|
||||
# this might remove tools that are actually needed,
|
||||
# if set to "true" but frees about 6 GB
|
||||
tool-cache: false
|
||||
|
||||
# all of these default to true, but feel free to set to
|
||||
# "false" if necessary for your workflow
|
||||
android: true
|
||||
haskell: true
|
||||
dotnet: false
|
||||
large-packages: false
|
||||
docker-images: false
|
||||
swap-storage: false
|
||||
|
||||
- name: Test package installation
|
||||
run: |
|
||||
pip install dist/*.whl
|
||||
python -m karaoke_gen.utils.gen_cli --help
|
||||
|
||||
- if: github.ref == 'refs/heads/main' && github.event_name == 'push'
|
||||
name: Extract version
|
||||
id: extract_version
|
||||
run: |
|
||||
VERSION=$(poetry version --short)
|
||||
echo "version=$VERSION" >> $GITHUB_OUTPUT
|
||||
echo "📋 Extracted version: $VERSION"
|
||||
|
||||
- if: github.ref == 'refs/heads/main' && github.event_name == 'push'
|
||||
name: Check if tag exists
|
||||
id: check_tag
|
||||
run: |
|
||||
VERSION="${{ steps.extract_version.outputs.version }}"
|
||||
if git ls-remote --tags origin | grep -q "refs/tags/v$VERSION$"; then
|
||||
echo "tag_exists=true" >> $GITHUB_OUTPUT
|
||||
echo "🏷️ Tag v$VERSION already exists, skipping release"
|
||||
else
|
||||
echo "tag_exists=false" >> $GITHUB_OUTPUT
|
||||
echo "✨ Tag v$VERSION does not exist, proceeding with release"
|
||||
fi
|
||||
|
||||
- if: github.ref == 'refs/heads/main' && github.event_name == 'push' && steps.check_tag.outputs.tag_exists == 'false'
|
||||
name: Publish to PyPI
|
||||
run: |
|
||||
echo "📦 Publishing the following files to PyPI:"
|
||||
ls -la dist/
|
||||
echo "🚀 Publishing to PyPI..."
|
||||
poetry config pypi-token.pypi ${{ secrets.PYPI_API_TOKEN }}
|
||||
poetry publish
|
||||
|
||||
- if: github.ref == 'refs/heads/main' && github.event_name == 'push' && steps.check_tag.outputs.tag_exists == 'false'
|
||||
name: Create Git Tag
|
||||
run: |
|
||||
git config user.name github-actions
|
||||
git config user.email github-actions@github.com
|
||||
git tag -a "v${{ steps.extract_version.outputs.version }}" -m "Release v${{ steps.extract_version.outputs.version }}"
|
||||
git push https://${{ secrets.GITHUB_TOKEN }}@github.com/${{ github.repository }} "v${{ steps.extract_version.outputs.version }}"
|
||||
|
||||
- if: github.ref == 'refs/heads/main' && github.event_name == 'push' && steps.check_tag.outputs.tag_exists == 'false'
|
||||
name: Create GitHub Release
|
||||
uses: softprops/action-gh-release@v1
|
||||
with:
|
||||
tag_name: "v${{ steps.extract_version.outputs.version }}"
|
||||
name: "v${{ steps.extract_version.outputs.version }}"
|
||||
body: |
|
||||
## Changes in v${{ steps.extract_version.outputs.version }}
|
||||
|
||||
This release was automatically created from the main branch.
|
||||
|
||||
### Installation
|
||||
```bash
|
||||
pip install karaoke-gen==${{ steps.extract_version.outputs.version }}
|
||||
```
|
||||
|
||||
### Assets
|
||||
- Python package published to PyPI
|
||||
- Frontend deployed to GitHub Pages at gen.nomadkaraoke.com
|
||||
|
||||
For detailed changes, see the commit history.
|
||||
draft: false
|
||||
prerelease: false
|
||||
files: |
|
||||
dist/*.whl
|
||||
dist/*.tar.gz
|
||||
|
||||
# Deploy frontend to GitHub Pages
|
||||
deploy-frontend:
|
||||
runs-on: ubuntu-latest
|
||||
if: github.ref == 'refs/heads/main' && github.event_name == 'push'
|
||||
environment:
|
||||
name: github-pages
|
||||
url: ${{ steps.deployment.outputs.page_url }}
|
||||
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Pages
|
||||
uses: actions/configure-pages@v4
|
||||
|
||||
- name: Prepare frontend files
|
||||
run: |
|
||||
echo "📁 Preparing frontend files for deployment..."
|
||||
mkdir -p _site
|
||||
cp -r frontend/* _site/
|
||||
echo "✅ Frontend files copied to _site/"
|
||||
ls -la _site/
|
||||
|
||||
- name: Upload artifact
|
||||
uses: actions/upload-pages-artifact@v3
|
||||
with:
|
||||
path: '_site'
|
||||
|
||||
- name: Deploy to GitHub Pages
|
||||
id: deployment
|
||||
uses: actions/deploy-pages@v4
|
||||
|
||||
@@ -1,313 +0,0 @@
|
||||
name: Backend Tests
|
||||
|
||||
on:
|
||||
push: # Run on all branch pushes
|
||||
pull_request:
|
||||
branches: [ main ]
|
||||
|
||||
jobs:
|
||||
unit-tests:
|
||||
name: Unit Tests
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: false
|
||||
|
||||
- name: Set up Python 3.13
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.13'
|
||||
|
||||
- name: Install Poetry
|
||||
uses: snok/install-poetry@v1
|
||||
with:
|
||||
virtualenvs-create: true
|
||||
virtualenvs-in-project: true
|
||||
|
||||
- name: Install dependencies
|
||||
run: poetry install
|
||||
|
||||
- name: Run unit tests
|
||||
env:
|
||||
GOOGLE_CLOUD_PROJECT: test-project
|
||||
GCS_BUCKET_NAME: test-bucket
|
||||
FIRESTORE_COLLECTION: jobs
|
||||
ENVIRONMENT: test
|
||||
run: |
|
||||
poetry run pytest \
|
||||
backend/tests/test_models.py \
|
||||
backend/tests/test_job_manager.py \
|
||||
backend/tests/test_file_upload.py \
|
||||
backend/tests/test_services.py \
|
||||
-v --tb=short
|
||||
|
||||
emulator-tests:
|
||||
name: Emulator Integration Tests
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Free disk space
|
||||
run: |
|
||||
sudo rm -rf /usr/share/dotnet
|
||||
sudo rm -rf /opt/ghc
|
||||
sudo rm -rf /usr/local/share/boost
|
||||
df -h
|
||||
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: false
|
||||
|
||||
- name: Set up Python 3.13
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.13'
|
||||
|
||||
- name: Install Poetry
|
||||
uses: snok/install-poetry@v1
|
||||
with:
|
||||
virtualenvs-create: true
|
||||
virtualenvs-in-project: true
|
||||
|
||||
- name: Set up Java 21 (required by Firestore emulator)
|
||||
uses: actions/setup-java@v4
|
||||
with:
|
||||
distribution: 'temurin'
|
||||
java-version: '21'
|
||||
|
||||
- name: Set up Cloud SDK
|
||||
uses: google-github-actions/setup-gcloud@v2
|
||||
with:
|
||||
version: 'latest'
|
||||
|
||||
- name: Install Firestore emulator
|
||||
run: |
|
||||
gcloud components install beta cloud-firestore-emulator --quiet
|
||||
|
||||
- name: Install dependencies
|
||||
run: poetry install
|
||||
|
||||
- name: Start Docker for GCS emulator
|
||||
run: |
|
||||
docker pull fsouza/fake-gcs-server:latest
|
||||
|
||||
- name: Run emulator integration tests
|
||||
run: |
|
||||
chmod +x scripts/*.sh
|
||||
./scripts/run-emulator-tests.sh
|
||||
|
||||
- name: Upload test results
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: test-results
|
||||
path: backend/htmlcov/
|
||||
retention-days: 7
|
||||
|
||||
lint:
|
||||
name: Code Quality
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: false
|
||||
|
||||
- name: Set up Python 3.13
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.13'
|
||||
|
||||
- name: Install Poetry
|
||||
uses: snok/install-poetry@v1
|
||||
with:
|
||||
virtualenvs-create: true
|
||||
virtualenvs-in-project: true
|
||||
|
||||
- name: Install dependencies
|
||||
run: poetry install
|
||||
|
||||
- name: Run validation (syntax check only)
|
||||
run: |
|
||||
# Skip full validation as it requires GCP credentials
|
||||
# Just check Python syntax and imports
|
||||
poetry run python -m py_compile backend/main.py backend/config.py
|
||||
echo "✅ Basic syntax validation passed"
|
||||
|
||||
deploy:
|
||||
name: Deploy via Cloud Build
|
||||
runs-on: ubuntu-latest
|
||||
needs: [unit-tests, emulator-tests, lint]
|
||||
# Deploy on any push where tests pass (pre-alpha: rapid iteration mode)
|
||||
# TODO: Change back to main-only when ready for production: github.ref == 'refs/heads/main'
|
||||
if: github.event_name == 'push'
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
id-token: write # Required for Workload Identity Federation
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: false
|
||||
|
||||
- name: Authenticate to Google Cloud (Workload Identity)
|
||||
id: auth
|
||||
uses: google-github-actions/auth@v2
|
||||
with:
|
||||
workload_identity_provider: ${{ secrets.GCP_WORKLOAD_IDENTITY_PROVIDER }}
|
||||
service_account: ${{ secrets.GCP_SERVICE_ACCOUNT }}
|
||||
|
||||
- name: Set up Cloud SDK
|
||||
uses: google-github-actions/setup-gcloud@v2
|
||||
with:
|
||||
version: 'latest'
|
||||
|
||||
- name: Check if base image needs rebuild
|
||||
id: check-base
|
||||
run: |
|
||||
echo "🔍 Checking if base image needs rebuild..."
|
||||
|
||||
# Calculate current poetry.lock hash
|
||||
CURRENT_HASH=$(sha256sum poetry.lock | cut -d' ' -f1)
|
||||
echo "Current poetry.lock hash: $CURRENT_HASH"
|
||||
|
||||
# Try to get the hash from the existing base image
|
||||
# First, authenticate to Artifact Registry
|
||||
gcloud auth configure-docker us-central1-docker.pkg.dev --quiet
|
||||
|
||||
# Try to pull the base image and get its label
|
||||
BASE_IMAGE="us-central1-docker.pkg.dev/nomadkaraoke/karaoke-repo/karaoke-backend-base:latest"
|
||||
EXISTING_HASH=""
|
||||
|
||||
if docker pull $BASE_IMAGE 2>/dev/null; then
|
||||
EXISTING_HASH=$(docker inspect $BASE_IMAGE --format='{{index .Config.Labels "poetry.lock.hash"}}' 2>/dev/null || echo "")
|
||||
echo "Existing base image hash: $EXISTING_HASH"
|
||||
else
|
||||
echo "⚠️ No existing base image found"
|
||||
fi
|
||||
|
||||
# Compare hashes
|
||||
if [ "$CURRENT_HASH" != "$EXISTING_HASH" ]; then
|
||||
echo "🔄 Base image needs rebuild (poetry.lock changed)"
|
||||
echo "needs_rebuild=true" >> $GITHUB_OUTPUT
|
||||
else
|
||||
echo "✅ Base image is up to date"
|
||||
echo "needs_rebuild=false" >> $GITHUB_OUTPUT
|
||||
fi
|
||||
|
||||
- name: Rebuild base image (if needed)
|
||||
if: steps.check-base.outputs.needs_rebuild == 'true'
|
||||
run: |
|
||||
echo "🏗️ Rebuilding base image with updated dependencies..."
|
||||
|
||||
# Submit base image build and wait for completion
|
||||
BASE_BUILD_ID=$(gcloud builds submit \
|
||||
--config=cloudbuild-base.yaml \
|
||||
--project=nomadkaraoke \
|
||||
--format='value(id)' \
|
||||
--async \
|
||||
.)
|
||||
|
||||
echo "Base Build ID: $BASE_BUILD_ID"
|
||||
echo "Build URL: https://console.cloud.google.com/cloud-build/builds/$BASE_BUILD_ID?project=nomadkaraoke"
|
||||
|
||||
# Poll for build completion
|
||||
echo "Waiting for base image build to complete..."
|
||||
while true; do
|
||||
BUILD_STATUS=$(gcloud builds describe $BASE_BUILD_ID --project=nomadkaraoke --format='value(status)')
|
||||
echo "Base build status: $BUILD_STATUS"
|
||||
|
||||
if [ "$BUILD_STATUS" = "SUCCESS" ]; then
|
||||
echo "✅ Base image build completed successfully"
|
||||
break
|
||||
elif [ "$BUILD_STATUS" = "FAILURE" ] || [ "$BUILD_STATUS" = "CANCELLED" ] || [ "$BUILD_STATUS" = "TIMEOUT" ]; then
|
||||
echo "❌ Base image build failed with status: $BUILD_STATUS"
|
||||
echo ""
|
||||
echo "==================== BUILD LOGS ===================="
|
||||
gcloud logging read "resource.type=build AND resource.labels.build_id=$BASE_BUILD_ID" \
|
||||
--project=nomadkaraoke \
|
||||
--format="value(textPayload)" \
|
||||
--limit=200 \
|
||||
--order=asc || echo "Failed to retrieve logs from Cloud Logging"
|
||||
echo "===================================================="
|
||||
gcloud builds log $BASE_BUILD_ID --project=nomadkaraoke 2>&1 || true
|
||||
exit 1
|
||||
fi
|
||||
|
||||
sleep 30
|
||||
done
|
||||
|
||||
- name: Trigger Cloud Build
|
||||
run: |
|
||||
echo "🚀 Triggering Cloud Build for deployment..."
|
||||
echo "Commit: ${{ github.sha }}"
|
||||
|
||||
# Submit build and wait for completion
|
||||
BUILD_ID=$(gcloud builds submit \
|
||||
--config=cloudbuild.yaml \
|
||||
--project=nomadkaraoke \
|
||||
--format='value(id)' \
|
||||
--async \
|
||||
.)
|
||||
|
||||
echo "Build ID: $BUILD_ID"
|
||||
echo "Build URL: https://console.cloud.google.com/cloud-build/builds/$BUILD_ID?project=nomadkaraoke"
|
||||
|
||||
# Poll for build completion
|
||||
echo "Waiting for build to complete..."
|
||||
while true; do
|
||||
BUILD_STATUS=$(gcloud builds describe $BUILD_ID --project=nomadkaraoke --format='value(status)')
|
||||
echo "Build status: $BUILD_STATUS"
|
||||
|
||||
if [ "$BUILD_STATUS" = "SUCCESS" ]; then
|
||||
echo "✅ Build completed successfully"
|
||||
break
|
||||
elif [ "$BUILD_STATUS" = "FAILURE" ] || [ "$BUILD_STATUS" = "CANCELLED" ] || [ "$BUILD_STATUS" = "TIMEOUT" ]; then
|
||||
echo "❌ Build failed with status: $BUILD_STATUS"
|
||||
echo ""
|
||||
echo "==================== BUILD LOGS ===================="
|
||||
# Use Cloud Logging to get build logs (works with roles/logging.viewer)
|
||||
gcloud logging read "resource.type=build AND resource.labels.build_id=$BUILD_ID" \
|
||||
--project=nomadkaraoke \
|
||||
--format="value(textPayload)" \
|
||||
--limit=200 \
|
||||
--order=asc || echo "Failed to retrieve logs from Cloud Logging"
|
||||
echo "===================================================="
|
||||
echo ""
|
||||
# Also try the direct logs command as fallback
|
||||
gcloud builds log $BUILD_ID --project=nomadkaraoke 2>&1 || true
|
||||
exit 1
|
||||
fi
|
||||
|
||||
sleep 30
|
||||
done
|
||||
|
||||
- name: Verify deployment
|
||||
run: |
|
||||
SERVICE_URL=$(gcloud run services describe karaoke-backend \
|
||||
--region us-central1 \
|
||||
--format 'value(status.url)')
|
||||
|
||||
echo "Service URL: $SERVICE_URL"
|
||||
|
||||
# Wait a few seconds for the service to be ready
|
||||
sleep 10
|
||||
|
||||
# Test health endpoint
|
||||
curl -f "$SERVICE_URL/api/health" || exit 1
|
||||
|
||||
echo "✅ Deployment verified - service is healthy"
|
||||
|
||||
- name: Summary
|
||||
if: success()
|
||||
run: |
|
||||
echo "🎉 Deployment successful!"
|
||||
echo "Commit: ${{ github.sha }}"
|
||||
echo "Branch: ${{ github.ref_name }}"
|
||||
echo "Run: ${{ github.run_number }}"
|
||||
+10
@@ -12,6 +12,9 @@ tests/outputs
|
||||
/input
|
||||
/output/
|
||||
|
||||
# Cloud Infra
|
||||
.emulator-logs
|
||||
|
||||
# Next.js / React Frontend (./frontend)
|
||||
node_modules/
|
||||
frontend/node_modules/
|
||||
@@ -41,6 +44,9 @@ frontend/.pnpm-debug.log*
|
||||
|
||||
# Testing
|
||||
frontend/coverage/
|
||||
frontend/test-results/
|
||||
frontend/playwright-report/
|
||||
frontend/playwright/.cache/
|
||||
|
||||
# TypeScript
|
||||
frontend/*.tsbuildinfo
|
||||
@@ -73,8 +79,11 @@ dist/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
# Python lib directories (not frontend)
|
||||
lib/
|
||||
lib64/
|
||||
# But allow frontend lib
|
||||
!frontend/lib/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
@@ -217,3 +226,4 @@ cython_debug/
|
||||
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
||||
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
||||
#.idea/
|
||||
flacfetch
|
||||
@@ -0,0 +1,123 @@
|
||||
# Agent Instructions: Nomad Karaoke E2E Production Testing
|
||||
|
||||
## Context
|
||||
|
||||
You are acting on behalf of Andrew, the creator of Nomad Karaoke, who is building a fully functional end-to-end karaoke video generation platform. The platform has two modes:
|
||||
|
||||
1. **Local CLI** (`karaoke-gen`) - For power users running locally
|
||||
2. **Public Web Service** (`gen.nomadkaraoke.com`) - For paying customers ($5/track via Stripe)
|
||||
|
||||
## Current State
|
||||
|
||||
The platform has been under heavy development with many features implemented, but **end-to-end functionality for real users on gen.nomadkaraoke.com is not fully working yet**. The goal is to make the complete user journey functional in production.
|
||||
|
||||
## Business Model (Planned)
|
||||
|
||||
- **buy.nomadkaraoke.com** - Customer intro/landing page with Stripe payment flow
|
||||
- Payment generates a single-use token
|
||||
- Customer is redirected to **gen.nomadkaraoke.com** with token ready to use
|
||||
- Each track costs $5
|
||||
|
||||
## Your Primary Mission
|
||||
|
||||
**Test and fix the production system until end-to-end karaoke generation works reliably.**
|
||||
|
||||
### The Complete User Journey to Test
|
||||
|
||||
1. **Input** - User enters artist name and song title
|
||||
2. **Audio Selection** - User selects audio source
|
||||
3. **Download & Preparation** - System downloads and prepares audio (wait for completion)
|
||||
4. **Lyrics Review** - User reviews/corrects lyrics in the web UI
|
||||
5. **Preview Video** - Wait for preview video to load
|
||||
6. **Submit Review** - User submits corrected lyrics
|
||||
7. **Render Stage** - Wait for render to complete
|
||||
8. **Instrumental Selection** - User selects instrumental via web UI
|
||||
9. **Final Render & Distribution** - Wait for final render and distribution
|
||||
10. **Verification** - Click to view uploaded YouTube video
|
||||
11. **Verification** - Click Dropbox folder link to view shared folder
|
||||
|
||||
## Your Working Process
|
||||
|
||||
Use Playwright to automate and test this journey against **live production** at `gen.nomadkaraoke.com`.
|
||||
|
||||
### The Fix Loop
|
||||
|
||||
When you encounter something broken:
|
||||
|
||||
1. **Investigate** - Understand the root cause
|
||||
2. **Fix** - Implement the fix
|
||||
3. **Improve Tests** - Add/update tests to cover the issue
|
||||
4. **Refactor** - Clean up if necessary
|
||||
5. **PR** - Create a pull request with clear description
|
||||
6. **CI** - Ensure all checks pass
|
||||
7. **Merge** - Merge the PR
|
||||
8. **Deploy** - Wait for deployment to complete
|
||||
9. **Retest** - Test again in production
|
||||
10. **Repeat** - Continue until everything works
|
||||
|
||||
## Key Rules
|
||||
|
||||
### From CLAUDE.md (Must Follow)
|
||||
|
||||
- **Never commit directly to `main`** - Always use feature branches
|
||||
- **Always run tests before committing** - `make test` for backend, `cd frontend && npm run test:all` for frontend
|
||||
- **Bump version** in `pyproject.toml` for every commit
|
||||
- **Use git worktrees** for non-trivial changes
|
||||
- **Infrastructure changes** must go through Pulumi IaC
|
||||
|
||||
### Testing Commands
|
||||
|
||||
```bash
|
||||
# Backend tests (10 min timeout, limit output)
|
||||
make test 2>&1 | tail -n 500
|
||||
|
||||
# Frontend tests
|
||||
cd frontend && npm run test:all 2>&1 | tail -n 200
|
||||
```
|
||||
|
||||
### Pre-commit Checklist
|
||||
|
||||
- [ ] Tests pass
|
||||
- [ ] Version bumped in `pyproject.toml`
|
||||
- [ ] PR created with clear description
|
||||
- [ ] CI checks pass before merge
|
||||
|
||||
## Permissions
|
||||
|
||||
You have permission to:
|
||||
|
||||
- Run any command necessary
|
||||
- Use Playwright to interact with browsers
|
||||
- Make changes to any part of the codebase
|
||||
- Create PRs and merge them (after CI passes)
|
||||
- Test against live production
|
||||
|
||||
## Success Criteria
|
||||
|
||||
The mission is complete when:
|
||||
|
||||
1. Any artist/title can be entered on gen.nomadkaraoke.com
|
||||
2. The full generation process completes successfully
|
||||
3. A karaoke video is uploaded to YouTube
|
||||
4. Files are distributed to Dropbox
|
||||
5. The entire flow is covered by automated E2E tests
|
||||
|
||||
## Key URLs
|
||||
|
||||
- **Production Frontend**: https://gen.nomadkaraoke.com
|
||||
- **Production API**: https://api.nomadkaraoke.com (inferred from README)
|
||||
- **Lyrics Review UI**: https://gen.nomadkaraoke.com/lyrics/
|
||||
|
||||
## Reference Documentation
|
||||
|
||||
- `/Users/andrew/Projects/karaoke-gen/README.md` - Main project documentation
|
||||
- `/Users/andrew/Projects/karaoke-gen/CLAUDE.md` - AI assistant guidelines
|
||||
- `/Users/andrew/Projects/karaoke-gen/docs/01-reference/` - Reference documentation
|
||||
- `/Users/andrew/Projects/karaoke-gen/docs/00-current-plan/` - Planning documents (may be outdated)
|
||||
|
||||
## Notes
|
||||
|
||||
- Some docs in `docs/00-current-plan/` may be outdated - review, evaluate, and move/delete as appropriate
|
||||
- Focus on making things work, not perfect
|
||||
- Ship iteratively - fix one thing at a time
|
||||
- Document issues you find as you go
|
||||
@@ -0,0 +1,131 @@
|
||||
# Project Guidelines for AI Assistants
|
||||
|
||||
This document contains guidelines and rules for AI assistants working on this codebase.
|
||||
|
||||
## Core Principles
|
||||
|
||||
**Always be testing.** Proactively evaluate, read, run, fix, and improve tests whenever you touch any part of the system—frontend, backend, infrastructure. Every code change should be thoroughly tested. Leave everything better tested than you found it.
|
||||
|
||||
**Always be documenting.** Continuously read, write, improve, update, and organize markdown documentation. Reference existing docs and keep them accurate as the codebase evolves.
|
||||
|
||||
**Build for maintainability.** Keep code SOLID, modular, and clean. Favor simplicity and clarity. Future developers (and AI agents) will thank you.
|
||||
|
||||
## Branching Workflow
|
||||
|
||||
**Never commit directly to `main`.** Always work on a feature branch.
|
||||
|
||||
Create descriptive branch names like `feature/add-discord-notifications`, `fix/audio-sync-issue`, or `refactor/cleanup-api-routes`.
|
||||
|
||||
### Using Git Worktrees
|
||||
|
||||
**For non-trivial changes** (new features, multi-file edits, refactors):
|
||||
- Create a git worktree in the parent folder before making any file changes:
|
||||
```bash
|
||||
git worktree add ../karaoke-gen-feat-xyz feature/xyz
|
||||
```
|
||||
- This keeps the main directory clean on `main` and enables parallel work on multiple features
|
||||
- Name the worktree folder descriptively, e.g., `../karaoke-gen-fix-audio-sync`
|
||||
|
||||
**For trivial changes** (typos, single-line fixes):
|
||||
- Creating a branch in the current directory is acceptable
|
||||
- Use `git checkout -b fix/typo-xyz` before making changes
|
||||
|
||||
**Cleanup:** When done with a worktree, remove it with:
|
||||
```bash
|
||||
git worktree remove ../karaoke-gen-feat-xyz
|
||||
```
|
||||
|
||||
### Creating a Pull Request
|
||||
|
||||
Once all changes are complete, tests pass, and commits are pushed, create a PR with:
|
||||
|
||||
1. **Summary** - Brief overview of the changes
|
||||
2. **Changes Made** - List of specific modifications
|
||||
3. **Testing** - How changes were tested (unit tests, manual testing)
|
||||
4. **Related Issues** - Reference any GitHub issues (e.g., "Fixes #123")
|
||||
|
||||
Only merge after review and CI checks pass.
|
||||
|
||||
## Infrastructure Changes
|
||||
|
||||
All Google Cloud infrastructure (IAM, Cloud Storage, Cloud Run, Secret Manager, Artifact Registry, etc.) must be managed via **Pulumi IaC** in the `infrastructure/` folder.
|
||||
|
||||
### Rules
|
||||
|
||||
- **Reading/querying** with `gcloud` CLI is fine for investigation and debugging
|
||||
- **Temporary changes** via `gcloud` CLI or Console are acceptable for urgent fixes or experimentation, but **must be cleaned up** and properly codified in the IaC afterward
|
||||
- **Permanent changes** must go through Pulumi — never leave `gcloud` or Console changes as the final state
|
||||
|
||||
### Workflow
|
||||
|
||||
1. Make changes in `infrastructure/`
|
||||
2. Run `pulumi preview` and verify the output
|
||||
3. Run `pulumi up` to apply
|
||||
|
||||
### Authentication Issues
|
||||
|
||||
If you encounter any authentication issues with `gcloud` or `pulumi` (e.g., expired tokens, permission errors), **stop and notify the user** so they can run the appropriate auth commands in their external terminal:
|
||||
|
||||
```bash
|
||||
gcloud auth login
|
||||
gcloud auth application-default login
|
||||
```
|
||||
|
||||
Do not attempt to work around auth issues or make assumptions about credentials.
|
||||
|
||||
## Version Management
|
||||
|
||||
When committing and pushing changes, always bump the patch version in `pyproject.toml`.
|
||||
|
||||
The version is located at `tool.poetry.version` in `pyproject.toml`. For example, if the current version is `0.70.3`, bump it to `0.70.4`.
|
||||
|
||||
This ensures every commit pushed to the repository has a unique version number for tracking and deployment purposes.
|
||||
|
||||
## Testing Requirements
|
||||
|
||||
**Before committing and pushing ANY changes, you MUST run the full test suite.**
|
||||
|
||||
### Backend Test Command
|
||||
|
||||
```bash
|
||||
make test 2>&1 | tail -n 500
|
||||
```
|
||||
|
||||
**Important for AI agents:**
|
||||
- Set a **10 minute timeout** when running tests (they can take a while with emulators)
|
||||
- Always pipe output through `tail -n 500` to limit output and preserve context window
|
||||
- The tail output will show test results and any failures at the end
|
||||
|
||||
This runs all backend tests in order and fails fast if any test fails:
|
||||
1. Unit tests (karaoke_gen package) with coverage check
|
||||
2. Backend unit tests
|
||||
3. E2E integration tests with emulators (auto-starts/stops emulators)
|
||||
|
||||
### Frontend Test Command
|
||||
|
||||
When working in the `frontend/` directory, run:
|
||||
|
||||
```bash
|
||||
cd frontend && npm run test:all 2>&1 | tail -n 200
|
||||
```
|
||||
|
||||
This runs:
|
||||
1. **Unit tests** (Jest) - Component and utility tests
|
||||
2. **E2E tests** (Playwright) - Browser-based integration tests
|
||||
|
||||
**Note:** E2E tests require `KARAOKE_ACCESS_TOKEN` environment variable to be set in `frontend/.env.local`.
|
||||
|
||||
Individual test commands:
|
||||
- `npm run test:unit` - Run unit tests only
|
||||
- `npm run test:e2e` - Run E2E tests only
|
||||
- `npm run test:ci` - Run unit tests with coverage
|
||||
|
||||
### Pre-commit Checklist
|
||||
|
||||
- [ ] `make test` passes (for backend changes)
|
||||
- [ ] `cd frontend && npm run test:all` passes (for frontend changes)
|
||||
- [ ] Version in `pyproject.toml` has been bumped
|
||||
- [ ] `coderabbit review --plain` has been run to get comprehensive analysis and suggestions for cleaner, more maintainable code. Apply the feedback to improve accessibility, structure, and best practices.
|
||||
|
||||
**Do not commit or push code that fails tests. Fix any test failures before proceeding.**
|
||||
|
||||
@@ -0,0 +1,77 @@
|
||||
# Makefile for karaoke-gen project
|
||||
# Run `make help` to see available commands
|
||||
|
||||
.PHONY: help test test-unit test-backend test-integration test-e2e test-all lint clean emulators-start emulators-stop
|
||||
|
||||
# Default target
|
||||
help:
|
||||
@echo "Available commands:"
|
||||
@echo " make test - Run all tests (unit + backend + emulator-based)"
|
||||
@echo " make test-unit - Run unit tests only (karaoke_gen)"
|
||||
@echo " make test-backend - Run backend unit tests only"
|
||||
@echo " make test-e2e - Run E2E tests with emulators (starts/stops automatically)"
|
||||
@echo " make test-all - Alias for 'make test'"
|
||||
@echo " make lint - Run linter checks"
|
||||
@echo " make emulators-start - Start GCP emulators for local development"
|
||||
@echo " make emulators-stop - Stop GCP emulators"
|
||||
@echo ""
|
||||
@echo "Before committing, run: make test"
|
||||
|
||||
# Run unit tests for karaoke_gen package
|
||||
test-unit:
|
||||
@echo "=== Running karaoke_gen unit tests ==="
|
||||
poetry run pytest tests/unit/ -v --cov=karaoke_gen --cov-report=term-missing --cov-fail-under=69
|
||||
|
||||
# Run backend unit tests
|
||||
test-backend:
|
||||
@echo "=== Running backend unit tests ==="
|
||||
poetry run pytest backend/tests/ --ignore=backend/tests/emulator -v
|
||||
|
||||
# Run E2E integration tests with emulators
|
||||
test-e2e:
|
||||
@echo "=== Running E2E integration tests with emulators ==="
|
||||
@./scripts/start-emulators.sh || (echo "Failed to start emulators" && exit 1)
|
||||
@export FIRESTORE_EMULATOR_HOST=127.0.0.1:8080 && \
|
||||
export STORAGE_EMULATOR_HOST=http://127.0.0.1:4443 && \
|
||||
export GOOGLE_CLOUD_PROJECT=test-project && \
|
||||
export GCS_BUCKET_NAME=test-bucket && \
|
||||
export ADMIN_TOKENS=test-admin-token && \
|
||||
export ENVIRONMENT=test && \
|
||||
poetry run pytest backend/tests/emulator/ -v; \
|
||||
TEST_RESULT=$$?; \
|
||||
./scripts/stop-emulators.sh; \
|
||||
exit $$TEST_RESULT
|
||||
|
||||
# Run all tests (use this before committing!)
|
||||
test: test-unit test-backend test-e2e
|
||||
@echo ""
|
||||
@echo "✅ All tests passed! Ready to commit."
|
||||
|
||||
# Alias for test
|
||||
test-all: test
|
||||
|
||||
# Lint checks
|
||||
lint:
|
||||
@echo "=== Running lint checks ==="
|
||||
poetry run ruff check karaoke_gen/ backend/
|
||||
poetry run ruff format --check karaoke_gen/ backend/
|
||||
|
||||
# Start emulators for local development
|
||||
emulators-start:
|
||||
@echo "=== Starting GCP emulators ==="
|
||||
./scripts/start-emulators.sh
|
||||
|
||||
# Stop emulators
|
||||
emulators-stop:
|
||||
@echo "=== Stopping GCP emulators ==="
|
||||
./scripts/stop-emulators.sh
|
||||
|
||||
# Clean up temporary files
|
||||
clean:
|
||||
find . -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null || true
|
||||
find . -type d -name ".pytest_cache" -exec rm -rf {} + 2>/dev/null || true
|
||||
find . -type d -name ".coverage" -exec rm -rf {} + 2>/dev/null || true
|
||||
find . -type f -name "*.pyc" -delete 2>/dev/null || true
|
||||
rm -rf htmlcov/ .coverage coverage.xml 2>/dev/null || true
|
||||
@echo "Cleaned up temporary files"
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# Karaoke Generator 🎶 🎥 🚀
|
||||
|
||||

|
||||

|
||||

|
||||

|
||||

|
||||
|
||||
@@ -54,10 +54,44 @@ pip install karaoke-gen
|
||||
This installs both `karaoke-gen` (local) and `karaoke-gen-remote` (cloud) CLIs.
|
||||
|
||||
### Requirements
|
||||
- Python 3.10+
|
||||
- Python 3.10-3.13
|
||||
- FFmpeg
|
||||
- For local processing: CUDA-capable GPU or Apple Silicon CPU recommended
|
||||
|
||||
### Transcription Provider Setup
|
||||
|
||||
**Transcription is required** for creating karaoke videos with synchronized lyrics. The system needs word-level timing data to display lyrics in sync with the music.
|
||||
|
||||
#### Option 1: AudioShake (Recommended)
|
||||
Commercial service with high-quality transcription. Best for production use.
|
||||
|
||||
```bash
|
||||
export AUDIOSHAKE_API_TOKEN="your_audioshake_token"
|
||||
```
|
||||
|
||||
Get an API key at [https://www.audioshake.ai/](https://www.audioshake.ai/) - business only, at time of writing this.
|
||||
|
||||
#### Option 2: Whisper via RunPod
|
||||
Open-source alternative using OpenAI's Whisper model on RunPod infrastructure.
|
||||
|
||||
```bash
|
||||
export RUNPOD_API_KEY="your_runpod_key"
|
||||
export WHISPER_RUNPOD_ID="your_whisper_endpoint_id"
|
||||
```
|
||||
|
||||
Set up a Whisper endpoint at [https://www.runpod.io/](https://www.runpod.io/)
|
||||
|
||||
#### Without Transcription (Instrumental Only)
|
||||
If you don't need synchronized lyrics, use the `--skip-lyrics` flag:
|
||||
|
||||
```bash
|
||||
karaoke-gen --skip-lyrics "Artist" "Title"
|
||||
```
|
||||
|
||||
This creates an instrumental-only karaoke video without lyrics overlay.
|
||||
|
||||
> **Note:** See `lyrics_transcriber_temp/README.md` for detailed transcription provider configuration options.
|
||||
|
||||
---
|
||||
|
||||
## 🖥️ Local CLI (`karaoke-gen`)
|
||||
@@ -180,9 +214,11 @@ karaoke-gen-remote \
|
||||
|----------|-------------|---------|
|
||||
| `KARAOKE_GEN_URL` | Backend service URL | Required |
|
||||
| `KARAOKE_GEN_AUTH_TOKEN` | Admin auth token (for protected endpoints) | Optional |
|
||||
| `REVIEW_UI_URL` | Lyrics review UI URL | `https://lyrics.nomadkaraoke.com` |
|
||||
| `REVIEW_UI_URL` | Lyrics review UI URL | `https://gen.nomadkaraoke.com/lyrics/` |
|
||||
| `POLL_INTERVAL` | Seconds between status polls | `5` |
|
||||
|
||||
**Note:** The `REVIEW_UI_URL` defaults to the hosted lyrics review UI. For local development, set it to `http://localhost:5173` if you're running the frontend dev server.
|
||||
|
||||
### Authentication
|
||||
|
||||
The backend uses token-based authentication for admin operations (bulk delete, internal worker triggers). For basic job submission and monitoring, authentication is optional.
|
||||
@@ -473,6 +509,73 @@ Check backend health status.
|
||||
|
||||
---
|
||||
|
||||
## 🔧 Troubleshooting
|
||||
|
||||
### "No suitable files found for processing"
|
||||
|
||||
This error occurs during the finalisation step when the `(With Vocals).mkv` file is missing. This file is created during lyrics transcription.
|
||||
|
||||
**Most common cause:** No transcription provider configured.
|
||||
|
||||
**Quick fix:**
|
||||
1. Check if transcription providers are configured:
|
||||
```bash
|
||||
echo $AUDIOSHAKE_API_TOKEN
|
||||
echo $RUNPOD_API_KEY
|
||||
```
|
||||
|
||||
2. If both are empty, set up a provider (see [Transcription Provider Setup](#transcription-provider-setup))
|
||||
|
||||
3. Or use `--skip-lyrics` for instrumental-only karaoke:
|
||||
```bash
|
||||
karaoke-gen --skip-lyrics "Artist" "Title"
|
||||
```
|
||||
|
||||
**Other causes:**
|
||||
- Invalid API credentials - verify your tokens are correct and active
|
||||
- API service unavailable - check service status pages
|
||||
- Network connectivity issues - ensure you can reach the API endpoints
|
||||
- Transcription timeout - try again or use a different provider
|
||||
|
||||
### Transcription Fails Silently
|
||||
|
||||
If karaoke-gen runs without errors but produces no synchronized lyrics:
|
||||
|
||||
1. **Check logs** - Run with `--log_level debug` for detailed output:
|
||||
```bash
|
||||
karaoke-gen --log_level debug "Artist" "Title"
|
||||
```
|
||||
|
||||
2. **Verify environment variables** - Ensure API tokens are exported in your shell:
|
||||
```bash
|
||||
# Check if set
|
||||
printenv | grep -E "(AUDIOSHAKE|RUNPOD|WHISPER)"
|
||||
|
||||
# Set in current session
|
||||
export AUDIOSHAKE_API_TOKEN="your_token"
|
||||
```
|
||||
|
||||
3. **Test API connectivity** - Verify you can reach the transcription service
|
||||
|
||||
### "No lyrics found from any source"
|
||||
|
||||
This warning means no reference lyrics were fetched from online sources (Genius, Spotify, Musixmatch). The transcription will still work, but auto-correction may be less accurate.
|
||||
|
||||
**To fix:**
|
||||
- Set `GENIUS_API_TOKEN` for Genius lyrics
|
||||
- Set `SPOTIFY_COOKIE_SP_DC` for Spotify lyrics
|
||||
- Set `RAPIDAPI_KEY` for Musixmatch lyrics
|
||||
- Or provide lyrics manually with `--lyrics_file /path/to/lyrics.txt`
|
||||
|
||||
### Video Quality Issues
|
||||
|
||||
If the output video has quality problems:
|
||||
- Ensure FFmpeg is properly installed: `ffmpeg -version`
|
||||
- Check available codecs: `ffmpeg -codecs`
|
||||
- For 4K output, ensure sufficient disk space (10GB+ per track)
|
||||
|
||||
---
|
||||
|
||||
## 🧪 Development
|
||||
|
||||
### Running Tests
|
||||
|
||||
+8
-3
@@ -11,7 +11,9 @@
|
||||
# gcloud builds submit --config=cloudbuild-base.yaml --project=nomadkaraoke
|
||||
|
||||
# Use pre-built base image with all dependencies
|
||||
FROM us-central1-docker.pkg.dev/nomadkaraoke/karaoke-repo/karaoke-backend-base:latest
|
||||
# Override with --build-arg BASE_IMAGE=karaoke-backend-base:local for local testing
|
||||
ARG BASE_IMAGE=us-central1-docker.pkg.dev/nomadkaraoke/karaoke-repo/karaoke-backend-base:latest
|
||||
FROM ${BASE_IMAGE}
|
||||
|
||||
# Set working directory (should already exist from base)
|
||||
WORKDIR /app
|
||||
@@ -34,5 +36,8 @@ ENV PORT=8080
|
||||
# Expose port
|
||||
EXPOSE 8080
|
||||
|
||||
# Run the application
|
||||
CMD ["uvicorn", "backend.main:app", "--host", "0.0.0.0", "--port", "8080"]
|
||||
# Run uvicorn directly
|
||||
# Note: Transmission daemon removed - torrent downloads now handled by
|
||||
# dedicated flacfetch VM service (see docs/00-current-plan/TORRENT-SERVICE-PLAN.md)
|
||||
# Using --loop asyncio (instead of uvloop) to support nest_asyncio for remote flacfetch calls
|
||||
CMD ["uvicorn", "backend.main:app", "--host", "0.0.0.0", "--port", "8080", "--loop", "asyncio"]
|
||||
+10
-3
@@ -7,12 +7,15 @@
|
||||
FROM python:3.11-slim
|
||||
|
||||
# Install system dependencies required by karaoke-gen
|
||||
# Note: Transmission daemon removed - torrent downloads now handled by
|
||||
# dedicated flacfetch VM service (see docs/00-current-plan/TORRENT-SERVICE-PLAN.md)
|
||||
RUN apt-get update && apt-get install -y \
|
||||
ffmpeg \
|
||||
libsndfile1 \
|
||||
libsox-dev \
|
||||
sox \
|
||||
build-essential \
|
||||
curl \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Set working directory
|
||||
@@ -27,12 +30,16 @@ COPY lyrics_transcriber_temp /app/lyrics_transcriber_temp
|
||||
RUN pip install --no-cache-dir --upgrade pip && \
|
||||
pip install --no-cache-dir -e .
|
||||
|
||||
# Download spaCy language model for lyrics transcription
|
||||
# This must be done at build time, not runtime (Cloud Run network restrictions)
|
||||
RUN python -m spacy download en_core_web_sm
|
||||
|
||||
# Label with build info
|
||||
ARG BUILD_DATE
|
||||
ARG BUILD_ID
|
||||
ARG POETRY_LOCK_HASH
|
||||
ARG BASE_CONTENT_HASH
|
||||
LABEL org.opencontainers.image.created="${BUILD_DATE}"
|
||||
LABEL org.opencontainers.image.revision="${BUILD_ID}"
|
||||
LABEL org.opencontainers.image.title="karaoke-backend-base"
|
||||
LABEL org.opencontainers.image.description="Base image with Python dependencies for karaoke-backend"
|
||||
LABEL poetry.lock.hash="${POETRY_LOCK_HASH}"
|
||||
LABEL org.opencontainers.image.description="Base image with Python dependencies and system tools for karaoke-backend"
|
||||
LABEL base.content.hash="${BASE_CONTENT_HASH}"
|
||||
+214
-7
@@ -2,8 +2,10 @@
|
||||
FastAPI dependencies for authentication and authorization.
|
||||
"""
|
||||
import logging
|
||||
from typing import Optional, Tuple
|
||||
from fastapi import Depends, HTTPException, Header, Query, Request
|
||||
import secrets
|
||||
from datetime import datetime, timedelta, UTC
|
||||
from typing import Optional, Tuple, Callable
|
||||
from fastapi import Depends, HTTPException, Header, Query, Request, Path
|
||||
from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
|
||||
|
||||
from backend.services.auth_service import get_auth_service, UserType, AuthService
|
||||
@@ -12,6 +14,16 @@ from backend.services.auth_service import get_auth_service, UserType, AuthServic
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def generate_review_token() -> str:
|
||||
"""Generate a cryptographically secure review token."""
|
||||
return secrets.token_urlsafe(32)
|
||||
|
||||
|
||||
def get_review_token_expiry(hours: int = 24) -> datetime:
|
||||
"""Get expiry time for a review token."""
|
||||
return datetime.now(UTC) + timedelta(hours=hours)
|
||||
|
||||
|
||||
# HTTP Bearer security scheme (Authorization: Bearer <token>)
|
||||
security = HTTPBearer(auto_error=False)
|
||||
|
||||
@@ -24,14 +36,21 @@ async def get_token_from_request(
|
||||
"""
|
||||
Extract access token from request.
|
||||
|
||||
Supports two methods:
|
||||
1. Authorization header: Authorization: Bearer <token>
|
||||
2. Query parameter: ?token=<token> (for download links)
|
||||
Supports three methods (in priority order):
|
||||
1. X-Admin-Token header: Used by Cloud Tasks (since OIDC overwrites Authorization)
|
||||
2. Authorization header: Authorization: Bearer <token>
|
||||
3. Query parameter: ?token=<token> (for download links)
|
||||
|
||||
Returns:
|
||||
Token string or None
|
||||
"""
|
||||
# Try Authorization header first
|
||||
# Check X-Admin-Token header first (used by Cloud Tasks)
|
||||
# Cloud Tasks OIDC token overwrites Authorization header, so we use a custom header
|
||||
admin_token = request.headers.get("X-Admin-Token")
|
||||
if admin_token:
|
||||
return admin_token
|
||||
|
||||
# Try Authorization header
|
||||
if credentials:
|
||||
return credentials.credentials
|
||||
|
||||
@@ -70,7 +89,15 @@ async def require_auth(
|
||||
is_valid, user_type, remaining_uses, message = auth_service.validate_token(token_str)
|
||||
|
||||
if not is_valid:
|
||||
logger.warning(f"Authentication failed: {message}")
|
||||
# Log more details for debugging token issues
|
||||
auth_header = request.headers.get("Authorization", "")
|
||||
logger.warning(
|
||||
f"Authentication failed: {message}. "
|
||||
f"Token provided: {bool(token_str)}, "
|
||||
f"Token length: {len(token_str) if token_str else 0}, "
|
||||
f"Auth header present: {bool(auth_header)}, "
|
||||
f"Header prefix: {auth_header[:20] if auth_header else 'none'}..."
|
||||
)
|
||||
raise HTTPException(
|
||||
status_code=401,
|
||||
detail=f"Authentication failed: {message}"
|
||||
@@ -136,3 +163,183 @@ def optional_auth(
|
||||
return None
|
||||
|
||||
return token_str, user_type, remaining_uses
|
||||
|
||||
|
||||
def require_review_auth_factory(job_id_param: str = "job_id"):
|
||||
"""
|
||||
Factory to create a review authentication dependency.
|
||||
|
||||
Accepts either:
|
||||
1. Full user authentication (admin/user token)
|
||||
2. Job-specific review token (only valid for the specific job)
|
||||
|
||||
Args:
|
||||
job_id_param: Name of the path parameter containing the job ID
|
||||
|
||||
Returns:
|
||||
Dependency function that validates review access
|
||||
"""
|
||||
async def require_review_auth(
|
||||
request: Request,
|
||||
job_id: str = Path(...),
|
||||
review_token: Optional[str] = Query(None, description="Job-specific review token"),
|
||||
auth_service: AuthService = Depends(get_auth_service),
|
||||
credentials: Optional[HTTPAuthorizationCredentials] = Depends(security),
|
||||
token: Optional[str] = Query(None, alias="token", description="Full access token")
|
||||
) -> Tuple[str, str]:
|
||||
"""
|
||||
Validate review access for a job.
|
||||
|
||||
Returns:
|
||||
(job_id, auth_type) where auth_type is "full" or "review_token"
|
||||
|
||||
Raises:
|
||||
HTTPException: 401 if authentication fails
|
||||
"""
|
||||
# Import here to avoid circular dependency
|
||||
from backend.services.job_manager import JobManager
|
||||
|
||||
# Try full authentication first
|
||||
full_token = None
|
||||
if credentials:
|
||||
full_token = credentials.credentials
|
||||
elif token:
|
||||
full_token = token
|
||||
|
||||
if full_token:
|
||||
is_valid, user_type, remaining_uses, message = auth_service.validate_token(full_token)
|
||||
if is_valid:
|
||||
logger.info(f"Review access granted via full auth ({user_type}) for job {job_id}")
|
||||
return job_id, "full"
|
||||
|
||||
# Try review token
|
||||
if review_token:
|
||||
job_manager = JobManager()
|
||||
job = job_manager.get_job(job_id)
|
||||
|
||||
if not job:
|
||||
raise HTTPException(status_code=404, detail=f"Job {job_id} not found")
|
||||
|
||||
# Validate review token matches
|
||||
if job.review_token and secrets.compare_digest(job.review_token, review_token):
|
||||
# Check expiry if set
|
||||
if job.review_token_expires_at:
|
||||
now = datetime.now(UTC)
|
||||
# Handle timezone-naive datetimes from Firestore
|
||||
expiry = job.review_token_expires_at
|
||||
if expiry.tzinfo is None:
|
||||
expiry = expiry.replace(tzinfo=UTC)
|
||||
|
||||
if now > expiry:
|
||||
logger.warning(f"Review token expired for job {job_id}")
|
||||
raise HTTPException(
|
||||
status_code=401,
|
||||
detail="Review token has expired. Please request a new review link."
|
||||
)
|
||||
|
||||
logger.info(f"Review access granted via review_token for job {job_id}")
|
||||
return job_id, "review_token"
|
||||
else:
|
||||
logger.warning(f"Invalid review token for job {job_id}")
|
||||
|
||||
# No valid authentication
|
||||
raise HTTPException(
|
||||
status_code=401,
|
||||
detail="Authentication required. Provide either a full access token or a valid review_token for this job."
|
||||
)
|
||||
|
||||
return require_review_auth
|
||||
|
||||
|
||||
# Default instance for most review endpoints
|
||||
require_review_auth = require_review_auth_factory()
|
||||
|
||||
|
||||
def require_instrumental_auth_factory(job_id_param: str = "job_id"):
|
||||
"""
|
||||
Factory to create an instrumental review authentication dependency.
|
||||
|
||||
Accepts either:
|
||||
1. Full user authentication (admin/user token)
|
||||
2. Job-specific instrumental token (only valid for the specific job)
|
||||
|
||||
Args:
|
||||
job_id_param: Name of the path parameter containing the job ID
|
||||
|
||||
Returns:
|
||||
Dependency function that validates instrumental review access
|
||||
"""
|
||||
async def require_instrumental_auth(
|
||||
request: Request,
|
||||
job_id: str = Path(...),
|
||||
instrumental_token: Optional[str] = Query(None, description="Job-specific instrumental review token"),
|
||||
auth_service: AuthService = Depends(get_auth_service),
|
||||
credentials: Optional[HTTPAuthorizationCredentials] = Depends(security),
|
||||
token: Optional[str] = Query(None, alias="token", description="Full access token")
|
||||
) -> Tuple[str, str]:
|
||||
"""
|
||||
Validate instrumental review access for a job.
|
||||
|
||||
Returns:
|
||||
(job_id, auth_type) where auth_type is "full" or "instrumental_token"
|
||||
|
||||
Raises:
|
||||
HTTPException: 401 if authentication fails
|
||||
"""
|
||||
# Import here to avoid circular dependency
|
||||
from backend.services.job_manager import JobManager
|
||||
|
||||
# Try full authentication first
|
||||
full_token = None
|
||||
if credentials:
|
||||
full_token = credentials.credentials
|
||||
elif token:
|
||||
full_token = token
|
||||
|
||||
if full_token:
|
||||
is_valid, user_type, remaining_uses, message = auth_service.validate_token(full_token)
|
||||
if is_valid:
|
||||
logger.info(f"Instrumental access granted via full auth ({user_type}) for job {job_id}")
|
||||
return job_id, "full"
|
||||
|
||||
# Try instrumental token
|
||||
if instrumental_token:
|
||||
job_manager = JobManager()
|
||||
job = job_manager.get_job(job_id)
|
||||
|
||||
if not job:
|
||||
raise HTTPException(status_code=404, detail=f"Job {job_id} not found")
|
||||
|
||||
# Validate instrumental token matches
|
||||
if job.instrumental_token and secrets.compare_digest(job.instrumental_token, instrumental_token):
|
||||
# Check expiry if set
|
||||
if job.instrumental_token_expires_at:
|
||||
now = datetime.now(UTC)
|
||||
# Handle timezone-naive datetimes from Firestore
|
||||
expiry = job.instrumental_token_expires_at
|
||||
if expiry.tzinfo is None:
|
||||
expiry = expiry.replace(tzinfo=UTC)
|
||||
|
||||
if now > expiry:
|
||||
logger.warning(f"Instrumental token expired for job {job_id}")
|
||||
raise HTTPException(
|
||||
status_code=401,
|
||||
detail="Instrumental review token has expired. Please request a new review link."
|
||||
)
|
||||
|
||||
logger.info(f"Instrumental access granted via instrumental_token for job {job_id}")
|
||||
return job_id, "instrumental_token"
|
||||
else:
|
||||
logger.warning(f"Invalid instrumental token for job {job_id}")
|
||||
|
||||
# No valid authentication
|
||||
raise HTTPException(
|
||||
status_code=401,
|
||||
detail="Authentication required. Provide either a full access token or a valid instrumental_token for this job."
|
||||
)
|
||||
|
||||
return require_instrumental_auth
|
||||
|
||||
|
||||
# Default instance for most instrumental review endpoints
|
||||
require_instrumental_auth = require_instrumental_auth_factory()
|
||||
@@ -0,0 +1,853 @@
|
||||
"""
|
||||
Audio search API routes for artist+title search mode.
|
||||
|
||||
This module provides endpoints for:
|
||||
1. Creating a job with audio search (artist+title without file)
|
||||
2. Getting search results for a job
|
||||
3. Selecting an audio source to download
|
||||
|
||||
The flow is:
|
||||
1. POST /api/audio-search/search - Create job and search for audio
|
||||
2. GET /api/audio-search/{job_id}/results - Get search results
|
||||
3. POST /api/audio-search/{job_id}/select - Select audio source
|
||||
"""
|
||||
import asyncio
|
||||
import logging
|
||||
import os
|
||||
import tempfile
|
||||
from typing import Optional, List, Dict, Any, Tuple
|
||||
|
||||
from fastapi import APIRouter, HTTPException, BackgroundTasks, Request, Depends
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from backend.models.job import JobCreate, JobStatus
|
||||
from backend.services.job_manager import JobManager
|
||||
from backend.services.storage_service import StorageService
|
||||
from backend.services.worker_service import get_worker_service
|
||||
from backend.services.credential_manager import get_credential_manager, CredentialStatus
|
||||
from backend.services.audio_search_service import (
|
||||
get_audio_search_service,
|
||||
AudioSearchResult,
|
||||
AudioSearchError,
|
||||
NoResultsError,
|
||||
DownloadError,
|
||||
)
|
||||
from backend.config import get_settings
|
||||
from backend.version import VERSION
|
||||
from backend.api.dependencies import require_auth
|
||||
from backend.services.auth_service import UserType
|
||||
from pathlib import Path
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Valid style file types (from file_upload.py)
|
||||
STYLE_FILE_TYPES = {
|
||||
'style_params': {'.json'},
|
||||
'style_intro_background': {'.jpg', '.jpeg', '.png'},
|
||||
'style_karaoke_background': {'.jpg', '.jpeg', '.png'},
|
||||
'style_end_background': {'.jpg', '.jpeg', '.png'},
|
||||
'style_font': {'.ttf', '.otf'},
|
||||
'style_cdg_instrumental_background': {'.jpg', '.jpeg', '.png'},
|
||||
'style_cdg_title_background': {'.jpg', '.jpeg', '.png'},
|
||||
'style_cdg_outro_background': {'.jpg', '.jpeg', '.png'},
|
||||
}
|
||||
router = APIRouter(tags=["audio-search"])
|
||||
|
||||
# Initialize services
|
||||
job_manager = JobManager()
|
||||
storage_service = StorageService()
|
||||
worker_service = get_worker_service()
|
||||
|
||||
|
||||
# ============================================================================
|
||||
# Pydantic models
|
||||
# ============================================================================
|
||||
|
||||
class StyleFileRequest(BaseModel):
|
||||
"""Information about a style file to be uploaded."""
|
||||
filename: str = Field(..., description="Original filename with extension")
|
||||
content_type: str = Field(..., description="MIME type of the file")
|
||||
file_type: str = Field(..., description="Type of file: 'style_params', 'style_intro_background', 'style_karaoke_background', 'style_end_background', 'style_font', 'style_cdg_instrumental_background', 'style_cdg_title_background', 'style_cdg_outro_background'")
|
||||
|
||||
|
||||
class StyleUploadUrl(BaseModel):
|
||||
"""Signed URL for uploading a style file."""
|
||||
file_type: str = Field(..., description="Type of file being uploaded")
|
||||
gcs_path: str = Field(..., description="Destination path in GCS")
|
||||
upload_url: str = Field(..., description="Signed URL to PUT the file to")
|
||||
|
||||
|
||||
class AudioSearchRequest(BaseModel):
|
||||
"""Request to search for audio by artist and title."""
|
||||
artist: str = Field(..., description="Artist name to search for")
|
||||
title: str = Field(..., description="Song title to search for")
|
||||
|
||||
# Auto-download mode
|
||||
auto_download: bool = Field(False, description="Automatically select best result and download")
|
||||
|
||||
# Theme configuration
|
||||
theme_id: Optional[str] = Field(None, description="Theme ID to use (e.g., 'nomad', 'default'). If set, CDG/TXT are enabled by default.")
|
||||
color_overrides: Optional[Dict[str, str]] = Field(None, description="Color overrides: artist_color, title_color, sung_lyrics_color, unsung_lyrics_color (hex #RRGGBB)")
|
||||
|
||||
# Processing options (CDG/TXT require style config or theme, disabled by default unless theme is set)
|
||||
enable_cdg: Optional[bool] = Field(None, description="Generate CDG+MP3 package. Default: True if theme_id set, False otherwise")
|
||||
enable_txt: Optional[bool] = Field(None, description="Generate TXT+MP3 package. Default: True if theme_id set, False otherwise")
|
||||
|
||||
# Finalisation options
|
||||
brand_prefix: Optional[str] = Field(None, description="Brand code prefix (e.g., NOMAD)")
|
||||
enable_youtube_upload: bool = Field(False, description="Upload to YouTube")
|
||||
youtube_description: Optional[str] = Field(None, description="YouTube video description text")
|
||||
discord_webhook_url: Optional[str] = Field(None, description="Discord webhook URL for notifications")
|
||||
|
||||
# Distribution options
|
||||
dropbox_path: Optional[str] = Field(None, description="Dropbox folder path for organized output")
|
||||
gdrive_folder_id: Optional[str] = Field(None, description="Google Drive folder ID for public share uploads")
|
||||
|
||||
# Lyrics configuration
|
||||
lyrics_artist: Optional[str] = Field(None, description="Override artist name for lyrics search")
|
||||
lyrics_title: Optional[str] = Field(None, description="Override title for lyrics search")
|
||||
subtitle_offset_ms: int = Field(0, description="Subtitle timing offset in milliseconds")
|
||||
|
||||
# Audio separation model configuration
|
||||
clean_instrumental_model: Optional[str] = Field(None, description="Model for clean instrumental separation")
|
||||
backing_vocals_models: Optional[List[str]] = Field(None, description="Models for backing vocals separation")
|
||||
other_stems_models: Optional[List[str]] = Field(None, description="Models for other stems")
|
||||
|
||||
# Style file uploads (optional)
|
||||
# Style params JSON and related assets (background images, fonts)
|
||||
style_files: Optional[List[StyleFileRequest]] = Field(None, description="Style files to upload (style_params JSON, backgrounds, fonts)")
|
||||
|
||||
|
||||
class AudioSearchResultResponse(BaseModel):
|
||||
"""A single audio search result.
|
||||
|
||||
Contains all fields needed for rich display using flacfetch's
|
||||
shared formatting functions.
|
||||
"""
|
||||
index: int
|
||||
title: str
|
||||
artist: str
|
||||
provider: str # Maps to source_name in Release
|
||||
url: Optional[str] = None # Maps to download_url in Release (may be None for remote)
|
||||
duration: Optional[int] = None # Maps to duration_seconds in Release
|
||||
quality: Optional[str] = None # Stringified quality
|
||||
source_id: Optional[str] = None # Maps to info_hash in Release
|
||||
seeders: Optional[int] = None
|
||||
target_file: Optional[str] = None
|
||||
# Additional fields for rich display (from Release.to_dict())
|
||||
year: Optional[int] = None
|
||||
label: Optional[str] = None
|
||||
edition_info: Optional[str] = None
|
||||
release_type: Optional[str] = None
|
||||
channel: Optional[str] = None # For YouTube
|
||||
view_count: Optional[int] = None # For YouTube
|
||||
size_bytes: Optional[int] = None
|
||||
target_file_size: Optional[int] = None
|
||||
track_pattern: Optional[str] = None
|
||||
match_score: Optional[float] = None
|
||||
# Pre-computed display fields
|
||||
formatted_size: Optional[str] = None
|
||||
formatted_duration: Optional[str] = None
|
||||
formatted_views: Optional[str] = None
|
||||
is_lossless: Optional[bool] = None
|
||||
quality_str: Optional[str] = None
|
||||
# Full quality object for Release.from_dict()
|
||||
quality_data: Optional[Dict[str, Any]] = None
|
||||
|
||||
|
||||
class AudioSearchResponse(BaseModel):
|
||||
"""Response from audio search."""
|
||||
status: str
|
||||
job_id: str
|
||||
message: str
|
||||
results: Optional[List[AudioSearchResultResponse]] = None
|
||||
results_count: int = 0
|
||||
auto_download: bool = False
|
||||
server_version: str
|
||||
# Style file upload URLs (when style_files are specified in request)
|
||||
style_upload_urls: Optional[List[StyleUploadUrl]] = None
|
||||
|
||||
|
||||
class AudioSelectRequest(BaseModel):
|
||||
"""Request to select an audio source."""
|
||||
selection_index: int = Field(..., description="Index of the selected audio source from search results")
|
||||
|
||||
|
||||
class AudioSelectResponse(BaseModel):
|
||||
"""Response from audio source selection."""
|
||||
status: str
|
||||
job_id: str
|
||||
message: str
|
||||
selected_index: int
|
||||
selected_title: str
|
||||
selected_artist: str
|
||||
selected_provider: str
|
||||
|
||||
|
||||
def _resolve_cdg_txt_defaults(
|
||||
theme_id: Optional[str],
|
||||
enable_cdg: Optional[bool],
|
||||
enable_txt: Optional[bool]
|
||||
) -> Tuple[bool, bool]:
|
||||
"""
|
||||
Resolve CDG/TXT settings based on theme and explicit settings.
|
||||
|
||||
When a theme is selected, CDG and TXT are enabled by default.
|
||||
Explicit True/False values always override the default.
|
||||
|
||||
Args:
|
||||
theme_id: Theme identifier (if any)
|
||||
enable_cdg: Explicit CDG setting (None means use default)
|
||||
enable_txt: Explicit TXT setting (None means use default)
|
||||
|
||||
Returns:
|
||||
Tuple of (resolved_enable_cdg, resolved_enable_txt)
|
||||
"""
|
||||
# Default based on whether theme is set
|
||||
default_enabled = theme_id is not None
|
||||
|
||||
# Explicit values override defaults, None uses default
|
||||
resolved_cdg = enable_cdg if enable_cdg is not None else default_enabled
|
||||
resolved_txt = enable_txt if enable_txt is not None else default_enabled
|
||||
|
||||
return resolved_cdg, resolved_txt
|
||||
|
||||
|
||||
def extract_request_metadata(request: Request, created_from: str = "audio_search") -> Dict[str, Any]:
|
||||
"""Extract metadata from request for job tracking."""
|
||||
headers = dict(request.headers)
|
||||
|
||||
client_ip = headers.get('x-forwarded-for', '').split(',')[0].strip()
|
||||
if not client_ip and request.client:
|
||||
client_ip = request.client.host
|
||||
|
||||
user_agent = headers.get('user-agent', '')
|
||||
environment = headers.get('x-environment', '')
|
||||
client_id = headers.get('x-client-id', '')
|
||||
|
||||
custom_headers = {}
|
||||
for key, value in headers.items():
|
||||
if key.lower().startswith('x-') and key.lower() not in ('x-forwarded-for', 'x-forwarded-proto', 'x-forwarded-host'):
|
||||
custom_headers[key] = value
|
||||
|
||||
return {
|
||||
'client_ip': client_ip,
|
||||
'user_agent': user_agent,
|
||||
'environment': environment,
|
||||
'client_id': client_id,
|
||||
'server_version': VERSION,
|
||||
'created_from': created_from,
|
||||
'custom_headers': custom_headers,
|
||||
}
|
||||
|
||||
|
||||
async def _trigger_workers_parallel(job_id: str) -> None:
|
||||
"""Trigger both audio and lyrics workers in parallel."""
|
||||
await asyncio.gather(
|
||||
worker_service.trigger_audio_worker(job_id),
|
||||
worker_service.trigger_lyrics_worker(job_id)
|
||||
)
|
||||
|
||||
|
||||
async def _download_and_start_processing(
|
||||
job_id: str,
|
||||
selection_index: int,
|
||||
audio_search_service,
|
||||
background_tasks: BackgroundTasks,
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Download selected audio and start job processing.
|
||||
|
||||
This is called either:
|
||||
- Immediately after search if auto_download=True
|
||||
- When user calls the select endpoint
|
||||
|
||||
For remote flacfetch downloads (torrent sources), the file is downloaded
|
||||
on the flacfetch VM and uploaded directly to GCS. For local downloads
|
||||
(YouTube), the file is downloaded locally and then uploaded to GCS.
|
||||
"""
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
raise HTTPException(status_code=404, detail=f"Job {job_id} not found")
|
||||
|
||||
# Get search results from state_data
|
||||
search_results = job.state_data.get('audio_search_results', [])
|
||||
if not search_results:
|
||||
raise HTTPException(status_code=400, detail="No search results available")
|
||||
|
||||
if selection_index < 0 or selection_index >= len(search_results):
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"Invalid selection index {selection_index}. Valid range: 0-{len(search_results)-1}"
|
||||
)
|
||||
|
||||
selected = search_results[selection_index]
|
||||
|
||||
# Get remote_search_id from state_data (stored during initial search)
|
||||
remote_search_id = job.state_data.get('remote_search_id')
|
||||
|
||||
# Transition to downloading state
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.DOWNLOADING_AUDIO,
|
||||
progress=10,
|
||||
message=f"Downloading from {selected['provider']}: {selected['artist']} - {selected['title']}",
|
||||
state_data_updates={
|
||||
'selected_audio_index': selection_index,
|
||||
'selected_audio_provider': selected['provider'],
|
||||
}
|
||||
)
|
||||
|
||||
try:
|
||||
# Determine if this is a remote torrent download
|
||||
is_torrent_source = selected.get('provider') in ['RED', 'OPS']
|
||||
is_remote_enabled = audio_search_service.is_remote_enabled()
|
||||
|
||||
# Check if we can use download_by_id (preferred - avoids re-searching)
|
||||
source_id = selected.get('source_id')
|
||||
source_name = selected.get('provider')
|
||||
target_file = selected.get('target_file')
|
||||
download_url = selected.get('url')
|
||||
|
||||
# For remote torrent downloads, have flacfetch VM upload directly to GCS
|
||||
if is_torrent_source and is_remote_enabled:
|
||||
# Generate GCS path for remote upload
|
||||
gcs_destination = f"uploads/{job_id}/audio/"
|
||||
|
||||
# Use download_by_id if we have source_id (preferred - no re-search needed)
|
||||
if source_id and source_name:
|
||||
logger.info(f"Using download_by_id for {source_name} ID={source_id} with GCS upload to: {gcs_destination}")
|
||||
|
||||
result = audio_search_service.download_by_id(
|
||||
source_name=source_name,
|
||||
source_id=source_id,
|
||||
output_dir="", # Not used for remote
|
||||
target_file=target_file,
|
||||
download_url=download_url,
|
||||
gcs_path=gcs_destination,
|
||||
)
|
||||
else:
|
||||
# Fallback to search-based download (requires re-search)
|
||||
logger.info(f"No source_id available, falling back to search-based download to: {gcs_destination}")
|
||||
|
||||
result = audio_search_service.download(
|
||||
result_index=selection_index,
|
||||
output_dir="", # Not used for remote
|
||||
gcs_path=gcs_destination,
|
||||
remote_search_id=remote_search_id,
|
||||
)
|
||||
|
||||
# For remote downloads, filepath is already the GCS path
|
||||
if result.filepath.startswith("gs://"):
|
||||
# Extract the path portion after the bucket name
|
||||
# Format: gs://bucket/uploads/job_id/audio/filename.flac
|
||||
parts = result.filepath.replace("gs://", "").split("/", 1)
|
||||
if len(parts) == 2:
|
||||
audio_gcs_path = parts[1]
|
||||
else:
|
||||
audio_gcs_path = result.filepath
|
||||
filename = os.path.basename(result.filepath)
|
||||
else:
|
||||
# Fallback: treat as local path (shouldn't happen for remote)
|
||||
filename = os.path.basename(result.filepath)
|
||||
audio_gcs_path = f"uploads/{job_id}/audio/{filename}"
|
||||
|
||||
logger.warning(f"Remote download returned local path: {result.filepath}, uploading manually")
|
||||
with open(result.filepath, 'rb') as f:
|
||||
storage_service.upload_fileobj(f, audio_gcs_path, content_type='audio/flac')
|
||||
|
||||
logger.info(f"Remote download complete, GCS path: {audio_gcs_path}")
|
||||
else:
|
||||
# Local download (YouTube or fallback)
|
||||
temp_dir = tempfile.mkdtemp(prefix=f"audio_download_{job_id}_")
|
||||
|
||||
# Use download_by_id if we have source_id and remote is enabled
|
||||
if source_id and source_name and is_remote_enabled:
|
||||
logger.info(f"Using download_by_id for local download: {source_name} ID={source_id}")
|
||||
|
||||
result = audio_search_service.download_by_id(
|
||||
source_name=source_name,
|
||||
source_id=source_id,
|
||||
output_dir=temp_dir,
|
||||
target_file=target_file,
|
||||
download_url=download_url,
|
||||
)
|
||||
else:
|
||||
# Fallback to search-based download
|
||||
result = audio_search_service.download(
|
||||
result_index=selection_index,
|
||||
output_dir=temp_dir,
|
||||
remote_search_id=remote_search_id, # Pass for potential fallback scenarios
|
||||
)
|
||||
|
||||
# Upload to GCS
|
||||
filename = os.path.basename(result.filepath)
|
||||
audio_gcs_path = f"uploads/{job_id}/audio/{filename}"
|
||||
|
||||
with open(result.filepath, 'rb') as f:
|
||||
storage_service.upload_fileobj(
|
||||
f,
|
||||
audio_gcs_path,
|
||||
content_type='audio/flac' # flacfetch typically returns FLAC
|
||||
)
|
||||
|
||||
logger.info(f"Uploaded audio to GCS: {audio_gcs_path}")
|
||||
|
||||
# Clean up temp file
|
||||
try:
|
||||
os.remove(result.filepath)
|
||||
os.rmdir(temp_dir)
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to clean up temp files: {e}")
|
||||
|
||||
# Update job with GCS path and transition to DOWNLOADING
|
||||
job_manager.update_job(job_id, {
|
||||
'input_media_gcs_path': audio_gcs_path,
|
||||
'filename': filename,
|
||||
})
|
||||
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.DOWNLOADING,
|
||||
progress=15,
|
||||
message="Audio downloaded, starting processing"
|
||||
)
|
||||
|
||||
# Trigger workers
|
||||
background_tasks.add_task(_trigger_workers_parallel, job_id)
|
||||
|
||||
return {
|
||||
'selected_index': selection_index,
|
||||
'selected_title': selected['title'],
|
||||
'selected_artist': selected['artist'],
|
||||
'selected_provider': selected['provider'],
|
||||
}
|
||||
|
||||
except DownloadError as e:
|
||||
job_manager.fail_job(job_id, f"Audio download failed: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Download failed: {e}")
|
||||
except Exception as e:
|
||||
job_manager.fail_job(job_id, f"Audio download failed: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Download failed: {e}")
|
||||
|
||||
|
||||
@router.post("/audio-search/search", response_model=AudioSearchResponse)
|
||||
async def search_audio(
|
||||
request: Request,
|
||||
background_tasks: BackgroundTasks,
|
||||
body: AudioSearchRequest,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
):
|
||||
"""
|
||||
Search for audio by artist and title, creating a new job.
|
||||
|
||||
This endpoint:
|
||||
1. Creates a job in PENDING state
|
||||
2. Searches for audio using flacfetch
|
||||
3. Either returns search results for user selection, or
|
||||
4. If auto_download=True, automatically selects best and starts processing
|
||||
|
||||
Use cases:
|
||||
- Interactive mode (default): Returns results, user calls /select endpoint
|
||||
- Auto mode (auto_download=True): Automatically selects and downloads best
|
||||
"""
|
||||
try:
|
||||
# Apply default distribution settings
|
||||
settings = get_settings()
|
||||
effective_dropbox_path = body.dropbox_path or settings.default_dropbox_path
|
||||
effective_gdrive_folder_id = body.gdrive_folder_id or settings.default_gdrive_folder_id
|
||||
effective_discord_webhook_url = body.discord_webhook_url or settings.default_discord_webhook_url
|
||||
|
||||
# Apply defaults for YouTube/Dropbox distribution (for web service)
|
||||
effective_enable_youtube_upload = body.enable_youtube_upload or settings.default_enable_youtube_upload
|
||||
effective_brand_prefix = body.brand_prefix or settings.default_brand_prefix
|
||||
effective_youtube_description = body.youtube_description or settings.default_youtube_description
|
||||
|
||||
# Validate credentials if distribution services are requested
|
||||
invalid_services = []
|
||||
credential_manager = get_credential_manager()
|
||||
|
||||
if effective_enable_youtube_upload:
|
||||
result = credential_manager.check_youtube_credentials()
|
||||
if result.status != CredentialStatus.VALID:
|
||||
invalid_services.append(f"youtube ({result.message})")
|
||||
|
||||
if effective_dropbox_path:
|
||||
result = credential_manager.check_dropbox_credentials()
|
||||
if result.status != CredentialStatus.VALID:
|
||||
invalid_services.append(f"dropbox ({result.message})")
|
||||
|
||||
if effective_gdrive_folder_id:
|
||||
result = credential_manager.check_gdrive_credentials()
|
||||
if result.status != CredentialStatus.VALID:
|
||||
invalid_services.append(f"gdrive ({result.message})")
|
||||
|
||||
if invalid_services:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail={
|
||||
"error": "credentials_invalid",
|
||||
"message": f"Distribution services need re-authorization: {', '.join(invalid_services)}",
|
||||
"invalid_services": invalid_services,
|
||||
}
|
||||
)
|
||||
|
||||
# Extract request metadata
|
||||
request_metadata = extract_request_metadata(request, created_from="audio_search")
|
||||
|
||||
# Resolve CDG/TXT defaults based on theme
|
||||
resolved_cdg, resolved_txt = _resolve_cdg_txt_defaults(
|
||||
body.theme_id, body.enable_cdg, body.enable_txt
|
||||
)
|
||||
|
||||
# Create job
|
||||
job_create = JobCreate(
|
||||
artist=body.artist,
|
||||
title=body.title,
|
||||
theme_id=body.theme_id,
|
||||
color_overrides=body.color_overrides or {},
|
||||
enable_cdg=resolved_cdg,
|
||||
enable_txt=resolved_txt,
|
||||
brand_prefix=effective_brand_prefix,
|
||||
enable_youtube_upload=effective_enable_youtube_upload,
|
||||
youtube_description=effective_youtube_description,
|
||||
youtube_description_template=effective_youtube_description, # video_worker reads this field
|
||||
discord_webhook_url=effective_discord_webhook_url,
|
||||
dropbox_path=effective_dropbox_path,
|
||||
gdrive_folder_id=effective_gdrive_folder_id,
|
||||
lyrics_artist=body.lyrics_artist,
|
||||
lyrics_title=body.lyrics_title,
|
||||
subtitle_offset_ms=body.subtitle_offset_ms,
|
||||
clean_instrumental_model=body.clean_instrumental_model,
|
||||
backing_vocals_models=body.backing_vocals_models,
|
||||
other_stems_models=body.other_stems_models,
|
||||
audio_search_artist=body.artist,
|
||||
audio_search_title=body.title,
|
||||
auto_download=body.auto_download,
|
||||
request_metadata=request_metadata,
|
||||
)
|
||||
job = job_manager.create_job(job_create)
|
||||
job_id = job.job_id
|
||||
|
||||
logger.info(f"Created job {job_id} for audio search: {body.artist} - {body.title}")
|
||||
|
||||
# Update job with audio search fields
|
||||
job_manager.update_job(job_id, {
|
||||
'audio_search_artist': body.artist,
|
||||
'audio_search_title': body.title,
|
||||
'auto_download': body.auto_download,
|
||||
})
|
||||
|
||||
# If theme is set and no custom style files are being uploaded, prepare theme style now
|
||||
# This copies the theme's style_params.json to the job folder so LyricsTranscriber
|
||||
# can access the style configuration for preview videos
|
||||
if body.theme_id and not body.style_files:
|
||||
from backend.api.routes.file_upload import _prepare_theme_for_job
|
||||
try:
|
||||
style_params_path, theme_style_assets, youtube_desc = _prepare_theme_for_job(
|
||||
job_id, body.theme_id, body.color_overrides
|
||||
)
|
||||
theme_update = {
|
||||
'style_params_gcs_path': style_params_path,
|
||||
'style_assets': theme_style_assets,
|
||||
}
|
||||
if youtube_desc and not effective_youtube_description:
|
||||
theme_update['youtube_description_template'] = youtube_desc
|
||||
job_manager.update_job(job_id, theme_update)
|
||||
logger.info(f"Applied theme '{body.theme_id}' to job {job_id}")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to prepare theme '{body.theme_id}' for job {job_id}: {e}")
|
||||
# Continue without theme - job can still be processed with defaults
|
||||
|
||||
# Handle style file uploads if provided
|
||||
style_upload_urls: List[StyleUploadUrl] = []
|
||||
style_assets = {}
|
||||
|
||||
if body.style_files:
|
||||
logger.info(f"Processing {len(body.style_files)} style file uploads for job {job_id}")
|
||||
|
||||
for file_info in body.style_files:
|
||||
# Validate file type
|
||||
if file_info.file_type not in STYLE_FILE_TYPES:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"Invalid file type '{file_info.file_type}'. Must be one of: {', '.join(STYLE_FILE_TYPES.keys())}"
|
||||
)
|
||||
|
||||
# Validate extension
|
||||
ext = Path(file_info.filename).suffix.lower()
|
||||
allowed_exts = STYLE_FILE_TYPES[file_info.file_type]
|
||||
if ext not in allowed_exts:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"Invalid extension '{ext}' for {file_info.file_type}. Allowed: {', '.join(allowed_exts)}"
|
||||
)
|
||||
|
||||
# Generate GCS path
|
||||
if file_info.file_type == 'style_params':
|
||||
gcs_path = f"uploads/{job_id}/style/style_params.json"
|
||||
else:
|
||||
# style_intro_background -> intro_background, etc.
|
||||
asset_key = file_info.file_type.replace('style_', '')
|
||||
gcs_path = f"uploads/{job_id}/style/{asset_key}{ext}"
|
||||
|
||||
# Generate signed upload URL
|
||||
signed_url = storage_service.generate_signed_upload_url(
|
||||
gcs_path,
|
||||
content_type=file_info.content_type,
|
||||
expiration_minutes=60
|
||||
)
|
||||
|
||||
style_upload_urls.append(StyleUploadUrl(
|
||||
file_type=file_info.file_type,
|
||||
gcs_path=gcs_path,
|
||||
upload_url=signed_url
|
||||
))
|
||||
|
||||
# Track the expected asset paths
|
||||
if file_info.file_type == 'style_params':
|
||||
style_assets['style_params'] = gcs_path
|
||||
else:
|
||||
asset_key = file_info.file_type.replace('style_', '')
|
||||
style_assets[asset_key] = gcs_path
|
||||
|
||||
# Update job with style asset expectations
|
||||
style_update = {'style_assets': style_assets}
|
||||
if 'style_params' in style_assets:
|
||||
style_update['style_params_gcs_path'] = style_assets['style_params']
|
||||
job_manager.update_job(job_id, style_update)
|
||||
|
||||
logger.info(f"Generated {len(style_upload_urls)} style upload URLs for job {job_id}")
|
||||
|
||||
# Transition to searching state
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.SEARCHING_AUDIO,
|
||||
progress=5,
|
||||
message=f"Searching for: {body.artist} - {body.title}"
|
||||
)
|
||||
|
||||
# Perform search
|
||||
audio_search_service = get_audio_search_service()
|
||||
|
||||
try:
|
||||
search_results = audio_search_service.search(body.artist, body.title)
|
||||
except NoResultsError as e:
|
||||
job_manager.fail_job(job_id, f"No audio sources found for: {body.artist} - {body.title}")
|
||||
raise HTTPException(
|
||||
status_code=404,
|
||||
detail={
|
||||
"error": "no_results",
|
||||
"message": str(e),
|
||||
"job_id": job_id,
|
||||
}
|
||||
)
|
||||
except AudioSearchError as e:
|
||||
job_manager.fail_job(job_id, f"Audio search failed: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Search failed: {e}")
|
||||
|
||||
# Store results in job state_data, including remote_search_id if available
|
||||
results_dicts = [r.to_dict() for r in search_results]
|
||||
state_data_update = {
|
||||
'audio_search_results': results_dicts,
|
||||
'audio_search_count': len(results_dicts),
|
||||
}
|
||||
# Store remote_search_id for use during download (important for concurrent requests)
|
||||
if audio_search_service.last_remote_search_id:
|
||||
state_data_update['remote_search_id'] = audio_search_service.last_remote_search_id
|
||||
job_manager.update_job(job_id, {
|
||||
'state_data': state_data_update
|
||||
})
|
||||
|
||||
# If auto_download, select best and start processing
|
||||
if body.auto_download:
|
||||
best_index = audio_search_service.select_best(search_results)
|
||||
|
||||
logger.info(f"Auto-download enabled, selecting result {best_index}")
|
||||
|
||||
selection_info = await _download_and_start_processing(
|
||||
job_id=job_id,
|
||||
selection_index=best_index,
|
||||
audio_search_service=audio_search_service,
|
||||
background_tasks=background_tasks,
|
||||
)
|
||||
|
||||
return AudioSearchResponse(
|
||||
status="success",
|
||||
job_id=job_id,
|
||||
message=f"Audio found and download started: {selection_info['selected_artist']} - {selection_info['selected_title']} ({selection_info['selected_provider']})",
|
||||
results=None, # Don't return results in auto mode
|
||||
results_count=len(search_results),
|
||||
auto_download=True,
|
||||
server_version=VERSION,
|
||||
style_upload_urls=style_upload_urls if style_upload_urls else None,
|
||||
)
|
||||
|
||||
# Interactive mode: return results for user selection
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.AWAITING_AUDIO_SELECTION,
|
||||
progress=10,
|
||||
message=f"Found {len(search_results)} audio sources. Waiting for selection."
|
||||
)
|
||||
|
||||
# Convert to response format with full Release data for rich display
|
||||
result_responses = []
|
||||
for r in search_results:
|
||||
# Get full serialized data from raw_result if available
|
||||
# raw_result can be either:
|
||||
# - A dict (from remote flacfetch API)
|
||||
# - A Release object (from local flacfetch)
|
||||
raw_dict = {}
|
||||
if r.raw_result:
|
||||
if isinstance(r.raw_result, dict):
|
||||
# Remote flacfetch API returns dicts directly
|
||||
raw_dict = r.raw_result
|
||||
else:
|
||||
# Local flacfetch returns Release objects
|
||||
try:
|
||||
raw_dict = r.raw_result.to_dict()
|
||||
except AttributeError:
|
||||
pass # Not a Release object
|
||||
|
||||
result_responses.append(
|
||||
AudioSearchResultResponse(
|
||||
index=r.index,
|
||||
title=r.title,
|
||||
artist=r.artist,
|
||||
provider=r.provider,
|
||||
url=r.url,
|
||||
duration=r.duration,
|
||||
quality=r.quality,
|
||||
source_id=r.source_id,
|
||||
seeders=raw_dict.get('seeders') or r.seeders,
|
||||
target_file=raw_dict.get('target_file') or r.target_file,
|
||||
# Additional fields for rich display
|
||||
year=raw_dict.get('year'),
|
||||
label=raw_dict.get('label'),
|
||||
edition_info=raw_dict.get('edition_info'),
|
||||
release_type=raw_dict.get('release_type'),
|
||||
channel=raw_dict.get('channel'),
|
||||
view_count=raw_dict.get('view_count'),
|
||||
size_bytes=raw_dict.get('size_bytes'),
|
||||
target_file_size=raw_dict.get('target_file_size'),
|
||||
track_pattern=raw_dict.get('track_pattern'),
|
||||
match_score=raw_dict.get('match_score'),
|
||||
# Pre-computed display fields
|
||||
formatted_size=raw_dict.get('formatted_size'),
|
||||
formatted_duration=raw_dict.get('formatted_duration'),
|
||||
formatted_views=raw_dict.get('formatted_views'),
|
||||
is_lossless=raw_dict.get('is_lossless'),
|
||||
quality_str=raw_dict.get('quality_str'),
|
||||
# Full quality object for Release.from_dict()
|
||||
# Remote API uses 'quality_data', local uses 'quality' for the dict
|
||||
quality_data=raw_dict.get('quality_data') or raw_dict.get('quality'),
|
||||
)
|
||||
)
|
||||
|
||||
return AudioSearchResponse(
|
||||
status="awaiting_selection",
|
||||
job_id=job_id,
|
||||
message=f"Found {len(search_results)} audio sources. Call /api/audio-search/{job_id}/select to choose one.",
|
||||
results=result_responses,
|
||||
results_count=len(search_results),
|
||||
auto_download=False,
|
||||
server_version=VERSION,
|
||||
style_upload_urls=style_upload_urls if style_upload_urls else None,
|
||||
)
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Error in audio search: {e}", exc_info=True)
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
@router.get("/audio-search/{job_id}/results")
|
||||
async def get_audio_search_results(
|
||||
job_id: str,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
):
|
||||
"""
|
||||
Get audio search results for a job.
|
||||
|
||||
Returns the cached search results so user can select one.
|
||||
"""
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
raise HTTPException(status_code=404, detail=f"Job {job_id} not found")
|
||||
|
||||
search_results = job.state_data.get('audio_search_results', [])
|
||||
|
||||
if not search_results:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail="No search results available for this job"
|
||||
)
|
||||
|
||||
return {
|
||||
"status": "success",
|
||||
"job_id": job_id,
|
||||
"job_status": job.status,
|
||||
"artist": job.audio_search_artist or job.artist,
|
||||
"title": job.audio_search_title or job.title,
|
||||
"results": search_results,
|
||||
"results_count": len(search_results),
|
||||
}
|
||||
|
||||
|
||||
@router.post("/audio-search/{job_id}/select", response_model=AudioSelectResponse)
|
||||
async def select_audio_source(
|
||||
job_id: str,
|
||||
background_tasks: BackgroundTasks,
|
||||
body: AudioSelectRequest,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
):
|
||||
"""
|
||||
Select an audio source and start job processing.
|
||||
|
||||
This endpoint:
|
||||
1. Validates the job is awaiting selection
|
||||
2. Downloads the selected audio
|
||||
3. Uploads to GCS
|
||||
4. Triggers audio and lyrics workers
|
||||
"""
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
raise HTTPException(status_code=404, detail=f"Job {job_id} not found")
|
||||
|
||||
# Verify job is awaiting selection
|
||||
if job.status != JobStatus.AWAITING_AUDIO_SELECTION:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"Job is not awaiting audio selection (status: {job.status})"
|
||||
)
|
||||
|
||||
# Get search service instance
|
||||
# Note: With download_by_id, we no longer need to re-search to populate the cache.
|
||||
# The source_id stored in job.state_data['audio_search_results'] is sufficient.
|
||||
audio_search_service = get_audio_search_service()
|
||||
|
||||
# Validate search results exist in job state_data
|
||||
search_results = job.state_data.get('audio_search_results', [])
|
||||
if not search_results:
|
||||
raise HTTPException(status_code=400, detail="No search results cached for this job")
|
||||
|
||||
selection_info = await _download_and_start_processing(
|
||||
job_id=job_id,
|
||||
selection_index=body.selection_index,
|
||||
audio_search_service=audio_search_service,
|
||||
background_tasks=background_tasks,
|
||||
)
|
||||
|
||||
return AudioSelectResponse(
|
||||
status="success",
|
||||
job_id=job_id,
|
||||
message="Audio selected and download started",
|
||||
selected_index=selection_info['selected_index'],
|
||||
selected_title=selection_info['selected_title'],
|
||||
selected_artist=selection_info['selected_artist'],
|
||||
selected_provider=selection_info['selected_provider'],
|
||||
)
|
||||
|
||||
|
||||
File diff suppressed because it is too large.
Load diff
@@ -1,10 +1,64 @@
|
||||
"""
|
||||
Health check routes.
|
||||
"""
|
||||
import os
|
||||
import logging
|
||||
from fastapi import APIRouter
|
||||
from typing import Dict
|
||||
from typing import Dict, Any, Optional
|
||||
|
||||
from backend.version import VERSION
|
||||
from backend.services.flacfetch_client import get_flacfetch_client
|
||||
|
||||
router = APIRouter()
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def check_transmission_status() -> Dict[str, Any]:
|
||||
"""Check if Transmission daemon is available and responsive."""
|
||||
try:
|
||||
import transmission_rpc
|
||||
host = os.environ.get("TRANSMISSION_HOST", "localhost")
|
||||
port = int(os.environ.get("TRANSMISSION_PORT", "9091"))
|
||||
|
||||
client = transmission_rpc.Client(host=host, port=port, timeout=5)
|
||||
stats = client.session_stats()
|
||||
|
||||
# Get detailed torrent info
|
||||
torrents = client.get_torrents()
|
||||
torrent_details = []
|
||||
for t in torrents:
|
||||
torrent_info = {
|
||||
"name": t.name,
|
||||
"progress": round(t.progress, 1),
|
||||
"status": str(t.status),
|
||||
"peers": t.peers_connected if hasattr(t, 'peers_connected') else 0,
|
||||
"download_speed": round(t.rate_download / 1024, 1) if hasattr(t, 'rate_download') else 0, # KB/s
|
||||
}
|
||||
# Check if stalled (downloading but no progress and no peers)
|
||||
if t.status.downloading and t.progress < 100 and torrent_info['peers'] == 0:
|
||||
torrent_info['stalled'] = True
|
||||
torrent_details.append(torrent_info)
|
||||
|
||||
return {
|
||||
"available": True,
|
||||
"host": host,
|
||||
"port": port,
|
||||
"download_dir": stats.download_dir if hasattr(stats, 'download_dir') else None,
|
||||
"active_torrent_count": stats.active_torrent_count if hasattr(stats, 'active_torrent_count') else 0,
|
||||
"torrents": torrent_details,
|
||||
}
|
||||
except ImportError as e:
|
||||
return {
|
||||
"available": False,
|
||||
"error": f"transmission_rpc not installed: {e}",
|
||||
}
|
||||
except Exception as e:
|
||||
return {
|
||||
"available": False,
|
||||
"host": os.environ.get("TRANSMISSION_HOST", "localhost"),
|
||||
"port": int(os.environ.get("TRANSMISSION_PORT", "9091")),
|
||||
"error": str(e),
|
||||
}
|
||||
|
||||
|
||||
@router.get("/health")
|
||||
@@ -16,6 +70,67 @@ async def health_check() -> Dict[str, str]:
|
||||
}
|
||||
|
||||
|
||||
async def check_flacfetch_service_status() -> Dict[str, Any]:
|
||||
"""Check if remote flacfetch service is available and healthy."""
|
||||
client = get_flacfetch_client()
|
||||
|
||||
if not client:
|
||||
return {
|
||||
"configured": False,
|
||||
"message": "Remote flacfetch service not configured (FLACFETCH_API_URL not set)",
|
||||
}
|
||||
|
||||
try:
|
||||
health = await client.health_check()
|
||||
return {
|
||||
"configured": True,
|
||||
"available": True,
|
||||
"status": health.get("status"),
|
||||
"version": health.get("version"),
|
||||
"transmission": health.get("transmission", {}),
|
||||
"disk": health.get("disk", {}),
|
||||
"providers": health.get("providers", {}),
|
||||
}
|
||||
except Exception as e:
|
||||
return {
|
||||
"configured": True,
|
||||
"available": False,
|
||||
"error": str(e),
|
||||
}
|
||||
|
||||
|
||||
@router.get("/health/detailed")
|
||||
async def detailed_health_check() -> Dict[str, Any]:
|
||||
"""
|
||||
Detailed health check including dependencies.
|
||||
|
||||
Use this to debug issues with Transmission, flacfetch service, etc.
|
||||
"""
|
||||
transmission_status = check_transmission_status()
|
||||
flacfetch_status = await check_flacfetch_service_status()
|
||||
|
||||
# Log for debugging
|
||||
if not transmission_status.get("available"):
|
||||
logger.warning(f"Local Transmission not available: {transmission_status.get('error')}")
|
||||
else:
|
||||
logger.info(f"Local Transmission available at {transmission_status.get('host')}:{transmission_status.get('port')}")
|
||||
|
||||
if flacfetch_status.get("configured") and not flacfetch_status.get("available"):
|
||||
logger.warning(f"Remote flacfetch service not available: {flacfetch_status.get('error')}")
|
||||
elif flacfetch_status.get("available"):
|
||||
logger.info(f"Remote flacfetch service healthy: {flacfetch_status.get('status')}")
|
||||
|
||||
return {
|
||||
"status": "healthy",
|
||||
"service": "karaoke-gen-backend",
|
||||
"version": VERSION,
|
||||
"dependencies": {
|
||||
"transmission_local": transmission_status,
|
||||
"flacfetch_remote": flacfetch_status,
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@router.get("/readiness")
|
||||
async def readiness_check() -> Dict[str, str]:
|
||||
"""Readiness check endpoint for Cloud Run."""
|
||||
|
||||
@@ -3,11 +3,20 @@ Internal API routes for worker coordination.
|
||||
|
||||
These endpoints are for internal use only (backend → workers).
|
||||
They are protected by admin authentication.
|
||||
|
||||
With Cloud Tasks integration, these endpoints may be called multiple times
|
||||
(retry on failure). Idempotency checks prevent duplicate processing.
|
||||
|
||||
Observability:
|
||||
- Extracts trace context from incoming requests (propagated via Cloud Tasks)
|
||||
- Creates worker spans linked to the original request trace
|
||||
- All logs include job_id for easy filtering in Cloud Logging
|
||||
"""
|
||||
import logging
|
||||
import asyncio
|
||||
from typing import Tuple
|
||||
from fastapi import APIRouter, HTTPException, BackgroundTasks, Depends
|
||||
import time
|
||||
from typing import Tuple, Optional
|
||||
from fastapi import APIRouter, HTTPException, BackgroundTasks, Depends, Request
|
||||
from pydantic import BaseModel
|
||||
|
||||
from backend.workers.audio_worker import process_audio_separation
|
||||
@@ -17,6 +26,13 @@ from backend.workers.video_worker import generate_video
|
||||
from backend.workers.render_video_worker import process_render_video
|
||||
from backend.api.dependencies import require_admin
|
||||
from backend.services.auth_service import UserType
|
||||
from backend.services.job_manager import JobManager
|
||||
from backend.services.tracing import (
|
||||
extract_trace_context,
|
||||
start_span_with_context,
|
||||
add_span_attribute,
|
||||
add_span_event,
|
||||
)
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -35,9 +51,61 @@ class WorkerResponse(BaseModel):
|
||||
message: str
|
||||
|
||||
|
||||
def _check_worker_idempotency(job_id: str, worker_name: str) -> Optional[WorkerResponse]:
|
||||
"""
|
||||
Check if a worker is already running or completed for this job.
|
||||
|
||||
This provides idempotency for Cloud Tasks retries - if a task is retried
|
||||
but the worker is already running or has completed, we skip processing.
|
||||
|
||||
Args:
|
||||
job_id: Job ID to check
|
||||
worker_name: Worker name (audio, lyrics, screens, render, video)
|
||||
|
||||
Returns:
|
||||
WorkerResponse if should skip (already running/complete), None to proceed
|
||||
"""
|
||||
job_manager = JobManager()
|
||||
job = job_manager.get_job(job_id)
|
||||
|
||||
if not job:
|
||||
logger.warning(f"[job:{job_id}] Job not found for {worker_name} worker")
|
||||
return WorkerResponse(
|
||||
status="not_found",
|
||||
job_id=job_id,
|
||||
message=f"Job {job_id} not found"
|
||||
)
|
||||
|
||||
# Check worker-specific progress in state_data
|
||||
progress_key = f"{worker_name}_progress"
|
||||
worker_progress = job.state_data.get(progress_key, {})
|
||||
stage = worker_progress.get('stage')
|
||||
|
||||
if stage == 'running':
|
||||
logger.info(f"[job:{job_id}] {worker_name.capitalize()} worker already running, skipping")
|
||||
return WorkerResponse(
|
||||
status="already_running",
|
||||
job_id=job_id,
|
||||
message=f"{worker_name.capitalize()} worker already in progress"
|
||||
)
|
||||
|
||||
if stage == 'complete':
|
||||
logger.info(f"[job:{job_id}] {worker_name.capitalize()} worker already complete, skipping")
|
||||
return WorkerResponse(
|
||||
status="already_complete",
|
||||
job_id=job_id,
|
||||
message=f"{worker_name.capitalize()} worker already completed"
|
||||
)
|
||||
|
||||
# Mark as running before starting (for idempotency on next retry)
|
||||
job_manager.update_state_data(job_id, progress_key, {'stage': 'running'})
|
||||
return None
|
||||
|
||||
|
||||
@router.post("/workers/audio", response_model=WorkerResponse)
|
||||
async def trigger_audio_worker(
|
||||
request: WorkerRequest,
|
||||
http_request: Request,
|
||||
background_tasks: BackgroundTasks,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_admin)
|
||||
):
|
||||
@@ -47,16 +115,31 @@ async def trigger_audio_worker(
|
||||
This endpoint is called internally after job creation to start
|
||||
the audio processing track (parallel with lyrics processing).
|
||||
|
||||
Idempotency: If worker is already running or complete, returns early.
|
||||
|
||||
The worker runs in the background and updates job state as it progresses.
|
||||
"""
|
||||
job_id = request.job_id
|
||||
logger.info(f"Triggering audio worker for job {job_id}")
|
||||
|
||||
# Extract trace context from incoming request (propagated via Cloud Tasks)
|
||||
trace_context = extract_trace_context(dict(http_request.headers))
|
||||
|
||||
logger.info(f"[job:{job_id}] WORKER_TRIGGER worker=audio")
|
||||
add_span_attribute("job_id", job_id)
|
||||
add_span_attribute("worker", "audio")
|
||||
|
||||
# Idempotency check
|
||||
skip_response = _check_worker_idempotency(job_id, "audio")
|
||||
if skip_response:
|
||||
add_span_event("worker_skipped", {"reason": skip_response.status})
|
||||
return skip_response
|
||||
|
||||
# Add task to background tasks
|
||||
# This allows the HTTP response to return immediately
|
||||
# while the worker continues processing
|
||||
background_tasks.add_task(process_audio_separation, job_id)
|
||||
|
||||
add_span_event("worker_started")
|
||||
return WorkerResponse(
|
||||
status="started",
|
||||
job_id=job_id,
|
||||
@@ -67,6 +150,7 @@ async def trigger_audio_worker(
|
||||
@router.post("/workers/lyrics", response_model=WorkerResponse)
|
||||
async def trigger_lyrics_worker(
|
||||
request: WorkerRequest,
|
||||
http_request: Request,
|
||||
background_tasks: BackgroundTasks,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_admin)
|
||||
):
|
||||
@@ -76,14 +160,29 @@ async def trigger_lyrics_worker(
|
||||
This endpoint is called internally after job creation to start
|
||||
the lyrics processing track (parallel with audio processing).
|
||||
|
||||
Idempotency: If worker is already running or complete, returns early.
|
||||
|
||||
The worker runs in the background and updates job state as it progresses.
|
||||
"""
|
||||
job_id = request.job_id
|
||||
logger.info(f"Triggering lyrics worker for job {job_id}")
|
||||
|
||||
# Extract trace context from incoming request
|
||||
trace_context = extract_trace_context(dict(http_request.headers))
|
||||
|
||||
logger.info(f"[job:{job_id}] WORKER_TRIGGER worker=lyrics")
|
||||
add_span_attribute("job_id", job_id)
|
||||
add_span_attribute("worker", "lyrics")
|
||||
|
||||
# Idempotency check
|
||||
skip_response = _check_worker_idempotency(job_id, "lyrics")
|
||||
if skip_response:
|
||||
add_span_event("worker_skipped", {"reason": skip_response.status})
|
||||
return skip_response
|
||||
|
||||
# Add task to background tasks
|
||||
background_tasks.add_task(process_lyrics_transcription, job_id)
|
||||
|
||||
add_span_event("worker_started")
|
||||
return WorkerResponse(
|
||||
status="started",
|
||||
job_id=job_id,
|
||||
@@ -94,6 +193,7 @@ async def trigger_lyrics_worker(
|
||||
@router.post("/workers/screens", response_model=WorkerResponse)
|
||||
async def trigger_screens_worker(
|
||||
request: WorkerRequest,
|
||||
http_request: Request,
|
||||
background_tasks: BackgroundTasks,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_admin)
|
||||
):
|
||||
@@ -101,13 +201,28 @@ async def trigger_screens_worker(
|
||||
Trigger title/end screen generation worker.
|
||||
|
||||
This is called automatically when both audio and lyrics are complete.
|
||||
|
||||
Idempotency: If worker is already running or complete, returns early.
|
||||
"""
|
||||
job_id = request.job_id
|
||||
logger.info(f"Triggering screens worker for job {job_id}")
|
||||
|
||||
# Extract trace context from incoming request
|
||||
trace_context = extract_trace_context(dict(http_request.headers))
|
||||
|
||||
logger.info(f"[job:{job_id}] WORKER_TRIGGER worker=screens")
|
||||
add_span_attribute("job_id", job_id)
|
||||
add_span_attribute("worker", "screens")
|
||||
|
||||
# Idempotency check
|
||||
skip_response = _check_worker_idempotency(job_id, "screens")
|
||||
if skip_response:
|
||||
add_span_event("worker_skipped", {"reason": skip_response.status})
|
||||
return skip_response
|
||||
|
||||
# Add task to background tasks
|
||||
background_tasks.add_task(generate_screens, job_id)
|
||||
|
||||
add_span_event("worker_started")
|
||||
return WorkerResponse(
|
||||
status="started",
|
||||
job_id=job_id,
|
||||
@@ -118,6 +233,7 @@ async def trigger_screens_worker(
|
||||
@router.post("/workers/video", response_model=WorkerResponse)
|
||||
async def trigger_video_worker(
|
||||
request: WorkerRequest,
|
||||
http_request: Request,
|
||||
background_tasks: BackgroundTasks,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_admin)
|
||||
):
|
||||
@@ -126,13 +242,28 @@ async def trigger_video_worker(
|
||||
|
||||
This is called after user selects their preferred instrumental.
|
||||
This is the longest-running stage (15-20 minutes).
|
||||
|
||||
Idempotency: If worker is already running or complete, returns early.
|
||||
"""
|
||||
job_id = request.job_id
|
||||
logger.info(f"Triggering video worker for job {job_id}")
|
||||
|
||||
# Extract trace context from incoming request
|
||||
trace_context = extract_trace_context(dict(http_request.headers))
|
||||
|
||||
logger.info(f"[job:{job_id}] WORKER_TRIGGER worker=video")
|
||||
add_span_attribute("job_id", job_id)
|
||||
add_span_attribute("worker", "video")
|
||||
|
||||
# Idempotency check
|
||||
skip_response = _check_worker_idempotency(job_id, "video")
|
||||
if skip_response:
|
||||
add_span_event("worker_skipped", {"reason": skip_response.status})
|
||||
return skip_response
|
||||
|
||||
# Add task to background tasks
|
||||
background_tasks.add_task(generate_video, job_id)
|
||||
|
||||
add_span_event("worker_started")
|
||||
return WorkerResponse(
|
||||
status="started",
|
||||
job_id=job_id,
|
||||
@@ -143,6 +274,7 @@ async def trigger_video_worker(
|
||||
@router.post("/workers/render-video", response_model=WorkerResponse)
|
||||
async def trigger_render_video_worker(
|
||||
request: WorkerRequest,
|
||||
http_request: Request,
|
||||
background_tasks: BackgroundTasks,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_admin)
|
||||
):
|
||||
@@ -153,15 +285,30 @@ async def trigger_render_video_worker(
|
||||
Uses OutputGenerator from LyricsTranscriber to generate the karaoke video
|
||||
with the corrected lyrics.
|
||||
|
||||
Idempotency: If worker is already running or complete, returns early.
|
||||
|
||||
Output: with_vocals.mkv in GCS
|
||||
Next state: AWAITING_INSTRUMENTAL_SELECTION
|
||||
"""
|
||||
job_id = request.job_id
|
||||
logger.info(f"Triggering render-video worker for job {job_id}")
|
||||
|
||||
# Extract trace context from incoming request
|
||||
trace_context = extract_trace_context(dict(http_request.headers))
|
||||
|
||||
logger.info(f"[job:{job_id}] WORKER_TRIGGER worker=render-video")
|
||||
add_span_attribute("job_id", job_id)
|
||||
add_span_attribute("worker", "render-video")
|
||||
|
||||
# Idempotency check
|
||||
skip_response = _check_worker_idempotency(job_id, "render")
|
||||
if skip_response:
|
||||
add_span_event("worker_skipped", {"reason": skip_response.status})
|
||||
return skip_response
|
||||
|
||||
# Add task to background tasks
|
||||
background_tasks.add_task(process_render_video, job_id)
|
||||
|
||||
add_span_event("worker_started")
|
||||
return WorkerResponse(
|
||||
status="started",
|
||||
job_id=job_id,
|
||||
|
||||
+454
-32
@@ -19,14 +19,16 @@ from backend.models.requests import (
|
||||
CorrectionsSubmission,
|
||||
InstrumentalSelection,
|
||||
StartReviewRequest,
|
||||
CancelJobRequest
|
||||
CancelJobRequest,
|
||||
CreateCustomInstrumentalRequest,
|
||||
)
|
||||
from backend.services.job_manager import JobManager
|
||||
from backend.services.worker_service import get_worker_service
|
||||
from backend.services.storage_service import StorageService
|
||||
from backend.config import get_settings
|
||||
from backend.api.dependencies import require_admin
|
||||
from backend.api.dependencies import require_admin, require_auth, require_instrumental_auth
|
||||
from backend.services.auth_service import UserType
|
||||
from backend.services.metrics import metrics
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -54,7 +56,8 @@ async def _trigger_workers_parallel(job_id: str) -> None:
|
||||
@router.post("", response_model=JobResponse)
|
||||
async def create_job(
|
||||
request: URLSubmissionRequest,
|
||||
background_tasks: BackgroundTasks
|
||||
background_tasks: BackgroundTasks,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
) -> JobResponse:
|
||||
"""
|
||||
Create a new karaoke generation job from a URL.
|
||||
@@ -80,6 +83,9 @@ async def create_job(
|
||||
)
|
||||
job = job_manager.create_job(job_create)
|
||||
|
||||
# Record job creation metric
|
||||
metrics.record_job_created(job.job_id, source="url")
|
||||
|
||||
# Trigger both workers in parallel using asyncio.gather
|
||||
# (FastAPI's BackgroundTasks runs async tasks sequentially)
|
||||
background_tasks.add_task(_trigger_workers_parallel, job.job_id)
|
||||
@@ -101,7 +107,10 @@ async def create_job(
|
||||
|
||||
|
||||
@router.get("/{job_id}", response_model=Job)
|
||||
async def get_job(job_id: str) -> Job:
|
||||
async def get_job(
|
||||
job_id: str,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
) -> Job:
|
||||
"""Get job status and details."""
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
@@ -121,7 +130,8 @@ async def list_jobs(
|
||||
client_id: Optional[str] = None,
|
||||
created_after: Optional[str] = None,
|
||||
created_before: Optional[str] = None,
|
||||
limit: int = 100
|
||||
limit: int = 100,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
) -> List[Job]:
|
||||
"""
|
||||
List jobs with optional filters.
|
||||
@@ -173,7 +183,11 @@ async def list_jobs(
|
||||
|
||||
|
||||
@router.delete("/{job_id}")
|
||||
async def delete_job(job_id: str, delete_files: bool = True) -> dict:
|
||||
async def delete_job(
|
||||
job_id: str,
|
||||
delete_files: bool = True,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
) -> dict:
|
||||
"""Delete a job and optionally its output files."""
|
||||
try:
|
||||
job = job_manager.get_job(job_id)
|
||||
@@ -300,7 +314,10 @@ async def bulk_delete_jobs(
|
||||
# ============================================================================
|
||||
|
||||
@router.get("/{job_id}/review-data")
|
||||
async def get_review_data(job_id: str) -> Dict[str, Any]:
|
||||
async def get_review_data(
|
||||
job_id: str,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Get data needed for lyrics review interface.
|
||||
|
||||
@@ -319,12 +336,27 @@ async def get_review_data(job_id: str) -> Dict[str, Any]:
|
||||
|
||||
# Get URLs from file_urls
|
||||
corrections_url = job.file_urls.get('lyrics', {}).get('corrections')
|
||||
audio_url = job.file_urls.get('lyrics', {}).get('audio')
|
||||
|
||||
if not corrections_url or not audio_url:
|
||||
|
||||
# For audio, try multiple sources in order of preference:
|
||||
# 1. Explicit lyrics audio (if worker uploaded it)
|
||||
# 2. Lead vocals stem (best for reviewing lyrics sync)
|
||||
# 3. Input media (original audio)
|
||||
audio_url = (
|
||||
job.file_urls.get('lyrics', {}).get('audio') or
|
||||
job.file_urls.get('stems', {}).get('lead_vocals') or
|
||||
job.input_media_gcs_path
|
||||
)
|
||||
|
||||
if not corrections_url:
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail="Review data not available"
|
||||
detail="Corrections data not available"
|
||||
)
|
||||
|
||||
if not audio_url:
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail="Audio not available for review"
|
||||
)
|
||||
|
||||
# Generate signed URLs for direct access
|
||||
@@ -341,7 +373,11 @@ async def get_review_data(job_id: str) -> Dict[str, Any]:
|
||||
|
||||
|
||||
@router.post("/{job_id}/start-review")
|
||||
async def start_review(job_id: str, request: StartReviewRequest) -> dict:
|
||||
async def start_review(
|
||||
job_id: str,
|
||||
request: StartReviewRequest,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
) -> dict:
|
||||
"""
|
||||
Mark job as IN_REVIEW (user opened review interface).
|
||||
|
||||
@@ -363,7 +399,8 @@ async def start_review(job_id: str, request: StartReviewRequest) -> dict:
|
||||
async def submit_corrections(
|
||||
job_id: str,
|
||||
submission: CorrectionsSubmission,
|
||||
background_tasks: BackgroundTasks
|
||||
background_tasks: BackgroundTasks,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
) -> dict:
|
||||
"""
|
||||
Save corrected lyrics during human review.
|
||||
@@ -421,7 +458,8 @@ async def submit_corrections(
|
||||
@router.post("/{job_id}/complete-review")
|
||||
async def complete_review(
|
||||
job_id: str,
|
||||
background_tasks: BackgroundTasks
|
||||
background_tasks: BackgroundTasks,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
) -> dict:
|
||||
"""
|
||||
Complete the human review and trigger video rendering.
|
||||
@@ -469,13 +507,18 @@ async def complete_review(
|
||||
|
||||
|
||||
@router.get("/{job_id}/instrumental-options")
|
||||
async def get_instrumental_options(job_id: str) -> Dict[str, Any]:
|
||||
async def get_instrumental_options(
|
||||
job_id: str,
|
||||
auth_info: Tuple[str, str] = Depends(require_instrumental_auth)
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Get instrumental audio options for user selection.
|
||||
|
||||
Returns signed URLs for both options:
|
||||
1. Clean instrumental (no backing vocals)
|
||||
2. Instrumental with backing vocals
|
||||
|
||||
Accepts either full auth token or job-specific instrumental_token.
|
||||
"""
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
@@ -523,17 +566,345 @@ async def get_instrumental_options(job_id: str) -> Dict[str, Any]:
|
||||
}
|
||||
|
||||
|
||||
@router.get("/{job_id}/instrumental-analysis")
|
||||
async def get_instrumental_analysis(
|
||||
job_id: str,
|
||||
auth_info: Tuple[str, str] = Depends(require_instrumental_auth)
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Get audio analysis data for instrumental selection.
|
||||
|
||||
Returns:
|
||||
- Analysis of backing vocals (audible segments, recommendation)
|
||||
- Waveform image URL
|
||||
- Audio stream URLs for playback
|
||||
|
||||
This endpoint enables intelligent instrumental selection by providing
|
||||
detailed analysis of the backing vocals track.
|
||||
|
||||
Accepts either full auth token or job-specific instrumental_token.
|
||||
"""
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
raise HTTPException(status_code=404, detail="Job not found")
|
||||
|
||||
if job.status != JobStatus.AWAITING_INSTRUMENTAL_SELECTION:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"Job not ready for instrumental analysis (current status: {job.status})"
|
||||
)
|
||||
|
||||
storage = StorageService()
|
||||
|
||||
# Get analysis from state_data (populated by render_video_worker)
|
||||
analysis_data = job.state_data.get('backing_vocals_analysis', {})
|
||||
|
||||
# Get URLs
|
||||
stems = job.file_urls.get('stems', {})
|
||||
analysis_files = job.file_urls.get('analysis', {})
|
||||
|
||||
clean_url = stems.get('instrumental_clean')
|
||||
backing_vocals_url = stems.get('backing_vocals')
|
||||
with_backing_url = stems.get('instrumental_with_backing')
|
||||
waveform_url = analysis_files.get('backing_vocals_waveform')
|
||||
custom_instrumental_url = stems.get('instrumental_custom')
|
||||
|
||||
# Build response
|
||||
response = {
|
||||
"job_id": job_id,
|
||||
"artist": job.artist,
|
||||
"title": job.title,
|
||||
"status": job.status,
|
||||
|
||||
# Analysis results
|
||||
"analysis": {
|
||||
"has_audible_content": analysis_data.get('has_audible_content', False),
|
||||
"total_duration_seconds": analysis_data.get('total_duration_seconds', 0),
|
||||
"audible_segments": analysis_data.get('audible_segments', []),
|
||||
"recommended_selection": analysis_data.get('recommended_selection', 'review_needed'),
|
||||
"total_audible_duration_seconds": analysis_data.get('total_audible_duration_seconds', 0),
|
||||
"audible_percentage": analysis_data.get('audible_percentage', 0),
|
||||
"silence_threshold_db": analysis_data.get('silence_threshold_db', -40.0),
|
||||
},
|
||||
|
||||
# Audio URLs for playback
|
||||
"audio_urls": {
|
||||
"clean_instrumental": storage.generate_signed_url(clean_url, expiration_minutes=120) if clean_url else None,
|
||||
"backing_vocals": storage.generate_signed_url(backing_vocals_url, expiration_minutes=120) if backing_vocals_url else None,
|
||||
"with_backing": storage.generate_signed_url(with_backing_url, expiration_minutes=120) if with_backing_url else None,
|
||||
"custom_instrumental": storage.generate_signed_url(custom_instrumental_url, expiration_minutes=120) if custom_instrumental_url else None,
|
||||
},
|
||||
|
||||
# Waveform image URL
|
||||
"waveform_url": storage.generate_signed_url(waveform_url, expiration_minutes=120) if waveform_url else None,
|
||||
|
||||
# Whether a custom instrumental has been created
|
||||
"has_custom_instrumental": custom_instrumental_url is not None,
|
||||
}
|
||||
|
||||
return response
|
||||
|
||||
|
||||
@router.get("/{job_id}/audio-stream/{stem_type}")
|
||||
async def stream_audio(
|
||||
job_id: str,
|
||||
stem_type: str,
|
||||
auth_info: Tuple[str, str] = Depends(require_instrumental_auth)
|
||||
):
|
||||
"""
|
||||
Stream an audio file for playback in the browser.
|
||||
|
||||
Supported stem_type values:
|
||||
- clean_instrumental: Clean instrumental (no backing vocals)
|
||||
- backing_vocals: Backing vocals only
|
||||
- with_backing: Instrumental with backing vocals
|
||||
- custom_instrumental: Custom instrumental (if created)
|
||||
|
||||
Returns audio as a streaming response with proper headers for
|
||||
browser audio playback.
|
||||
|
||||
Accepts either full auth token or job-specific instrumental_token.
|
||||
"""
|
||||
from fastapi.responses import StreamingResponse
|
||||
import tempfile
|
||||
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
raise HTTPException(status_code=404, detail="Job not found")
|
||||
|
||||
# Map stem_type to file_urls key
|
||||
stem_map = {
|
||||
'clean_instrumental': ('stems', 'instrumental_clean'),
|
||||
'backing_vocals': ('stems', 'backing_vocals'),
|
||||
'with_backing': ('stems', 'instrumental_with_backing'),
|
||||
'custom_instrumental': ('stems', 'instrumental_custom'),
|
||||
}
|
||||
|
||||
if stem_type not in stem_map:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"Invalid stem_type. Must be one of: {list(stem_map.keys())}"
|
||||
)
|
||||
|
||||
category, key = stem_map[stem_type]
|
||||
gcs_path = job.file_urls.get(category, {}).get(key)
|
||||
|
||||
if not gcs_path:
|
||||
raise HTTPException(
|
||||
status_code=404,
|
||||
detail=f"Audio file not available: {stem_type}"
|
||||
)
|
||||
|
||||
# Determine content type
|
||||
ext = gcs_path.split('.')[-1].lower()
|
||||
content_types = {
|
||||
'flac': 'audio/flac',
|
||||
'mp3': 'audio/mpeg',
|
||||
'wav': 'audio/wav',
|
||||
'm4a': 'audio/mp4',
|
||||
}
|
||||
content_type = content_types.get(ext, 'audio/flac')
|
||||
|
||||
try:
|
||||
storage = StorageService()
|
||||
with tempfile.NamedTemporaryFile(delete=False, suffix=f'.{ext}') as tmp:
|
||||
tmp_path = tmp.name
|
||||
|
||||
storage.download_file(gcs_path, tmp_path)
|
||||
|
||||
def file_iterator():
|
||||
try:
|
||||
with open(tmp_path, 'rb') as f:
|
||||
while chunk := f.read(8192):
|
||||
yield chunk
|
||||
finally:
|
||||
import os
|
||||
os.unlink(tmp_path)
|
||||
|
||||
filename = gcs_path.split('/')[-1]
|
||||
|
||||
return StreamingResponse(
|
||||
file_iterator(),
|
||||
media_type=content_type,
|
||||
headers={
|
||||
'Content-Disposition': f'inline; filename="{filename}"',
|
||||
'Accept-Ranges': 'bytes',
|
||||
}
|
||||
)
|
||||
except Exception as e:
|
||||
logger.exception(f"Error streaming audio {gcs_path}: {e}")
|
||||
raise HTTPException(status_code=500, detail=f"Error streaming audio: {e}") from e
|
||||
|
||||
|
||||
@router.post("/{job_id}/create-custom-instrumental")
|
||||
async def create_custom_instrumental(
|
||||
job_id: str,
|
||||
request: CreateCustomInstrumentalRequest,
|
||||
auth_info: Tuple[str, str] = Depends(require_instrumental_auth)
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Create a custom instrumental by muting regions of backing vocals.
|
||||
|
||||
This endpoint:
|
||||
1. Takes a list of time ranges to mute in the backing vocals
|
||||
2. Creates a custom instrumental (clean + muted backing vocals)
|
||||
3. Stores the result and makes it available for selection
|
||||
|
||||
After calling this endpoint, the user can select "custom" in the
|
||||
select-instrumental endpoint.
|
||||
|
||||
Accepts either full auth token or job-specific instrumental_token.
|
||||
"""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
from karaoke_gen.instrumental_review import MuteRegion
|
||||
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
raise HTTPException(status_code=404, detail="Job not found")
|
||||
|
||||
if job.status != JobStatus.AWAITING_INSTRUMENTAL_SELECTION:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"Job not ready for custom instrumental creation (current status: {job.status})"
|
||||
)
|
||||
|
||||
# Get stem paths
|
||||
stems = job.file_urls.get('stems', {})
|
||||
clean_path = stems.get('instrumental_clean')
|
||||
backing_path = stems.get('backing_vocals')
|
||||
|
||||
if not clean_path or not backing_path:
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail="Required audio files not available"
|
||||
)
|
||||
|
||||
try:
|
||||
# Convert request mute regions to model objects
|
||||
mute_regions = [
|
||||
MuteRegion(
|
||||
start_seconds=r.start_seconds,
|
||||
end_seconds=r.end_seconds
|
||||
)
|
||||
for r in request.mute_regions
|
||||
]
|
||||
|
||||
# Create custom instrumental
|
||||
editing_service = AudioEditingService()
|
||||
|
||||
# Determine output path
|
||||
output_path = f"jobs/{job_id}/stems/instrumental_custom.flac"
|
||||
|
||||
result = editing_service.create_custom_instrumental(
|
||||
gcs_clean_instrumental_path=clean_path,
|
||||
gcs_backing_vocals_path=backing_path,
|
||||
mute_regions=mute_regions,
|
||||
gcs_output_path=output_path,
|
||||
job_id=job_id,
|
||||
)
|
||||
|
||||
# Update job file_urls with custom instrumental
|
||||
job_manager.update_file_url(job_id, 'stems', 'instrumental_custom', output_path)
|
||||
|
||||
# Store mute regions in state_data for reference
|
||||
job_manager.update_state_data(job_id, 'custom_instrumental_mute_regions', [
|
||||
{"start_seconds": r.start_seconds, "end_seconds": r.end_seconds}
|
||||
for r in mute_regions
|
||||
])
|
||||
|
||||
logger.info(f"Job {job_id}: Custom instrumental created with {len(mute_regions)} mute regions")
|
||||
|
||||
# Generate signed URL for the new file
|
||||
storage = StorageService()
|
||||
|
||||
return {
|
||||
"status": "success",
|
||||
"message": "Custom instrumental created successfully",
|
||||
"custom_instrumental_url": storage.generate_signed_url(output_path, expiration_minutes=120),
|
||||
"mute_regions_applied": len(result.mute_regions_applied),
|
||||
"total_muted_duration_seconds": result.total_muted_duration_seconds,
|
||||
"output_duration_seconds": result.output_duration_seconds,
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.exception(f"Error creating custom instrumental for job {job_id}: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e)) from e
|
||||
|
||||
|
||||
@router.get("/{job_id}/waveform-data")
|
||||
async def get_waveform_data(
|
||||
job_id: str,
|
||||
num_points: int = 500,
|
||||
auth_info: Tuple[str, str] = Depends(require_instrumental_auth)
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Get waveform amplitude data for client-side rendering.
|
||||
|
||||
This endpoint returns raw amplitude data that the frontend can use
|
||||
to render a waveform using Canvas or SVG, enabling interactive
|
||||
features like click-to-seek.
|
||||
|
||||
Args:
|
||||
num_points: Number of data points to return (default 500)
|
||||
|
||||
Returns:
|
||||
{
|
||||
"amplitudes": [0.1, 0.2, ...], # Normalized 0-1 values
|
||||
"duration_seconds": 180.5,
|
||||
"num_points": 500
|
||||
}
|
||||
|
||||
Accepts either full auth token or job-specific instrumental_token.
|
||||
"""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
raise HTTPException(status_code=404, detail="Job not found")
|
||||
|
||||
if job.status != JobStatus.AWAITING_INSTRUMENTAL_SELECTION:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"Job not ready for waveform data (current status: {job.status})"
|
||||
)
|
||||
|
||||
backing_vocals_path = job.file_urls.get('stems', {}).get('backing_vocals')
|
||||
if not backing_vocals_path:
|
||||
raise HTTPException(status_code=404, detail="Backing vocals file not found")
|
||||
|
||||
try:
|
||||
analysis_service = AudioAnalysisService()
|
||||
amplitudes, duration = analysis_service.get_waveform_data(
|
||||
gcs_audio_path=backing_vocals_path,
|
||||
job_id=job_id,
|
||||
num_points=num_points,
|
||||
)
|
||||
|
||||
return {
|
||||
"amplitudes": amplitudes,
|
||||
"duration_seconds": duration,
|
||||
"num_points": len(amplitudes),
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
logger.exception(f"Error getting waveform data for job {job_id}: {e}")
|
||||
raise HTTPException(status_code=500, detail=str(e)) from e
|
||||
|
||||
|
||||
@router.post("/{job_id}/select-instrumental")
|
||||
async def select_instrumental(
|
||||
job_id: str,
|
||||
selection: InstrumentalSelection,
|
||||
background_tasks: BackgroundTasks
|
||||
background_tasks: BackgroundTasks,
|
||||
auth_info: Tuple[str, str] = Depends(require_instrumental_auth)
|
||||
) -> dict:
|
||||
"""
|
||||
Submit instrumental selection.
|
||||
|
||||
This is the SECOND critical human-in-the-loop interaction point.
|
||||
After selection, the job proceeds to video generation.
|
||||
|
||||
Accepts either full auth token or job-specific instrumental_token.
|
||||
"""
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
@@ -575,7 +946,10 @@ async def select_instrumental(
|
||||
|
||||
|
||||
@router.get("/{job_id}/download-urls")
|
||||
async def get_download_urls(job_id: str) -> dict:
|
||||
async def get_download_urls(
|
||||
job_id: str,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
) -> dict:
|
||||
"""
|
||||
Get download URLs for all job output files.
|
||||
|
||||
@@ -617,7 +991,12 @@ async def get_download_urls(job_id: str) -> dict:
|
||||
|
||||
|
||||
@router.get("/{job_id}/download/{category}/{file_key}")
|
||||
async def download_file(job_id: str, category: str, file_key: str):
|
||||
async def download_file(
|
||||
job_id: str,
|
||||
category: str,
|
||||
file_key: str,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
):
|
||||
"""
|
||||
Stream download a specific file from a completed job.
|
||||
|
||||
@@ -704,7 +1083,11 @@ async def download_file(job_id: str, category: str, file_key: str):
|
||||
|
||||
|
||||
@router.post("/{job_id}/cancel")
|
||||
async def cancel_job(job_id: str, request: CancelJobRequest) -> dict:
|
||||
async def cancel_job(
|
||||
job_id: str,
|
||||
request: CancelJobRequest,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
) -> dict:
|
||||
"""
|
||||
Cancel a job.
|
||||
|
||||
@@ -725,35 +1108,38 @@ async def cancel_job(job_id: str, request: CancelJobRequest) -> dict:
|
||||
@router.post("/{job_id}/retry")
|
||||
async def retry_job(
|
||||
job_id: str,
|
||||
background_tasks: BackgroundTasks
|
||||
background_tasks: BackgroundTasks,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
) -> dict:
|
||||
"""
|
||||
Retry a failed job from the last successful checkpoint.
|
||||
|
||||
This endpoint allows resuming jobs that failed during:
|
||||
Retry a failed or cancelled job from the last successful checkpoint.
|
||||
|
||||
This endpoint allows resuming jobs that failed or were cancelled during:
|
||||
- Audio processing (re-runs from beginning if input audio exists)
|
||||
- Video generation (re-runs video worker)
|
||||
- Encoding (re-runs video worker)
|
||||
- Packaging (re-runs video worker)
|
||||
|
||||
|
||||
The retry logic determines the appropriate stage to resume from
|
||||
based on what files/state already exist.
|
||||
"""
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
raise HTTPException(status_code=404, detail="Job not found")
|
||||
|
||||
if job.status != JobStatus.FAILED:
|
||||
|
||||
if job.status not in [JobStatus.FAILED, JobStatus.CANCELLED]:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail=f"Only failed jobs can be retried (current status: {job.status})"
|
||||
detail=f"Only failed or cancelled jobs can be retried (current status: {job.status})"
|
||||
)
|
||||
|
||||
try:
|
||||
# Determine retry point based on what's already complete
|
||||
error_details = job.error_details or {}
|
||||
error_stage = error_details.get('stage', 'unknown')
|
||||
|
||||
logger.info(f"Job {job_id}: Retrying from failed stage '{error_stage}'")
|
||||
original_status = job.status
|
||||
|
||||
logger.info(f"Job {job_id}: Retrying from {original_status} state (error stage: '{error_stage}')")
|
||||
|
||||
# Check what state exists to determine retry point
|
||||
file_urls = job.file_urls or {}
|
||||
@@ -861,11 +1247,46 @@ async def retry_job(
|
||||
"retry_stage": "screens_generation"
|
||||
}
|
||||
|
||||
# If we have input audio (uploaded or from URL), restart from beginning
|
||||
elif job.input_media_gcs_path or job.url:
|
||||
logger.info(f"Job {job_id}: Has input audio, restarting from beginning")
|
||||
|
||||
# Clear error state and any partial progress
|
||||
job_manager.update_job(job_id, {
|
||||
'error_message': None,
|
||||
'error_details': None,
|
||||
'state_data': {}, # Clear parallel worker progress
|
||||
})
|
||||
|
||||
# Reset to DOWNLOADING and trigger audio worker
|
||||
if not job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.DOWNLOADING,
|
||||
progress=5,
|
||||
message=f"Restarting job from {original_status} state"
|
||||
):
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail="Failed to transition job status for retry"
|
||||
)
|
||||
|
||||
# Trigger audio worker (which kicks off parallel audio + lyrics processing)
|
||||
background_tasks.add_task(worker_service.trigger_audio_worker, job_id)
|
||||
background_tasks.add_task(worker_service.trigger_lyrics_worker, job_id)
|
||||
|
||||
return {
|
||||
"status": "success",
|
||||
"job_id": job_id,
|
||||
"job_status": "downloading",
|
||||
"message": f"Job restarted from {original_status} state",
|
||||
"retry_stage": "from_beginning"
|
||||
}
|
||||
|
||||
else:
|
||||
# Can't determine a safe retry point, need to restart from beginning
|
||||
# No input audio available - job needs to be resubmitted
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail="Cannot determine safe retry point. Job may need to be resubmitted."
|
||||
detail="Cannot retry: no input audio available. Job must be resubmitted."
|
||||
)
|
||||
|
||||
except HTTPException:
|
||||
@@ -879,7 +1300,8 @@ async def retry_job(
|
||||
async def get_worker_logs(
|
||||
job_id: str,
|
||||
since_index: int = 0,
|
||||
worker: Optional[str] = None
|
||||
worker: Optional[str] = None,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_auth)
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Get worker logs for debugging.
|
||||
|
||||
@@ -16,9 +16,9 @@ import json
|
||||
import os
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
from typing import Dict, Any, Set
|
||||
from typing import Dict, Any, Set, Tuple
|
||||
|
||||
from fastapi import APIRouter, HTTPException, Request
|
||||
from fastapi import APIRouter, HTTPException, Request, Depends
|
||||
from fastapi.responses import FileResponse, StreamingResponse
|
||||
from starlette.background import BackgroundTask
|
||||
|
||||
@@ -27,6 +27,8 @@ from backend.services.job_manager import JobManager
|
||||
from backend.services.storage_service import StorageService
|
||||
from backend.services.job_logging import job_log_context, JobLogger
|
||||
from backend.services.tracing import create_span, add_span_attribute, add_span_event
|
||||
from backend.api.dependencies import require_auth, require_review_auth
|
||||
from backend.services.auth_service import UserType
|
||||
|
||||
# LyricsTranscriber imports for preview generation
|
||||
from lyrics_transcriber.types import CorrectionResult
|
||||
@@ -63,7 +65,10 @@ async def ping(job_id: str):
|
||||
|
||||
|
||||
@router.get("/{job_id}/correction-data")
|
||||
async def get_correction_data(job_id: str):
|
||||
async def get_correction_data(
|
||||
job_id: str,
|
||||
auth_info: Tuple[str, str] = Depends(require_review_auth)
|
||||
):
|
||||
"""
|
||||
Get correction data for the review interface.
|
||||
|
||||
@@ -129,14 +134,21 @@ async def get_correction_data(job_id: str):
|
||||
|
||||
|
||||
@router.get("/{job_id}/audio/{audio_hash}")
|
||||
async def get_audio_with_hash(job_id: str, audio_hash: str):
|
||||
async def get_audio_with_hash(
|
||||
job_id: str,
|
||||
audio_hash: str,
|
||||
auth_info: Tuple[str, str] = Depends(require_review_auth)
|
||||
):
|
||||
"""Stream the audio file for playback (with hash parameter)."""
|
||||
return await _stream_audio(job_id)
|
||||
|
||||
|
||||
@router.get("/{job_id}/audio/")
|
||||
@router.get("/{job_id}/audio")
|
||||
async def get_audio_no_hash(job_id: str):
|
||||
async def get_audio_no_hash(
|
||||
job_id: str,
|
||||
auth_info: Tuple[str, str] = Depends(require_review_auth)
|
||||
):
|
||||
"""Stream the audio file for playback (without hash parameter)."""
|
||||
return await _stream_audio(job_id)
|
||||
|
||||
@@ -189,7 +201,11 @@ async def _stream_audio(job_id: str):
|
||||
|
||||
|
||||
@router.post("/{job_id}/complete")
|
||||
async def complete_review(job_id: str, updated_data: Dict[str, Any]):
|
||||
async def complete_review(
|
||||
job_id: str,
|
||||
updated_data: Dict[str, Any],
|
||||
auth_info: Tuple[str, str] = Depends(require_review_auth)
|
||||
):
|
||||
"""
|
||||
Complete the review and save corrected lyrics.
|
||||
|
||||
@@ -244,7 +260,11 @@ async def complete_review(job_id: str, updated_data: Dict[str, Any]):
|
||||
|
||||
|
||||
@router.post("/{job_id}/handlers")
|
||||
async def update_handlers(job_id: str, enabled_handlers: list):
|
||||
async def update_handlers(
|
||||
job_id: str,
|
||||
enabled_handlers: list,
|
||||
auth_info: Tuple[str, str] = Depends(require_review_auth)
|
||||
):
|
||||
"""
|
||||
Update enabled correction handlers (optional feature).
|
||||
|
||||
@@ -256,7 +276,11 @@ async def update_handlers(job_id: str, enabled_handlers: list):
|
||||
|
||||
|
||||
@router.post("/{job_id}/add-lyrics")
|
||||
async def add_lyrics(job_id: str, data: Dict[str, str]):
|
||||
async def add_lyrics(
|
||||
job_id: str,
|
||||
data: Dict[str, str],
|
||||
auth_info: Tuple[str, str] = Depends(require_review_auth)
|
||||
):
|
||||
"""
|
||||
Add custom lyrics source and rerun correction.
|
||||
|
||||
@@ -354,7 +378,11 @@ async def add_lyrics(job_id: str, data: Dict[str, str]):
|
||||
|
||||
|
||||
@router.post("/{job_id}/preview-video")
|
||||
async def generate_preview_video(job_id: str, updated_data: Dict[str, Any]):
|
||||
async def generate_preview_video(
|
||||
job_id: str,
|
||||
updated_data: Dict[str, Any],
|
||||
auth_info: Tuple[str, str] = Depends(require_review_auth)
|
||||
):
|
||||
"""
|
||||
Generate a preview video with the current corrections.
|
||||
|
||||
@@ -469,7 +497,11 @@ async def generate_preview_video(job_id: str, updated_data: Dict[str, Any]):
|
||||
|
||||
|
||||
@router.get("/{job_id}/preview-video/{preview_hash}")
|
||||
async def get_preview_video(job_id: str, preview_hash: str):
|
||||
async def get_preview_video(
|
||||
job_id: str,
|
||||
preview_hash: str,
|
||||
auth_info: Tuple[str, str] = Depends(require_review_auth)
|
||||
):
|
||||
"""Stream the generated preview video."""
|
||||
storage = StorageService()
|
||||
|
||||
@@ -510,7 +542,11 @@ async def get_preview_video(job_id: str, preview_hash: str):
|
||||
|
||||
|
||||
@router.post("/{job_id}/v1/annotations")
|
||||
async def submit_annotation(job_id: str, annotation: Dict[str, Any]):
|
||||
async def submit_annotation(
|
||||
job_id: str,
|
||||
annotation: Dict[str, Any],
|
||||
auth_info: Tuple[str, str] = Depends(require_review_auth)
|
||||
):
|
||||
"""
|
||||
Submit a correction annotation for ML training data.
|
||||
|
||||
@@ -522,7 +558,10 @@ async def submit_annotation(job_id: str, annotation: Dict[str, Any]):
|
||||
|
||||
|
||||
@router.get("/{job_id}/v1/annotations/stats")
|
||||
async def get_annotation_stats(job_id: str):
|
||||
async def get_annotation_stats(
|
||||
job_id: str,
|
||||
auth_info: Tuple[str, str] = Depends(require_review_auth)
|
||||
):
|
||||
"""Get annotation statistics."""
|
||||
return {
|
||||
"total_annotations": 0,
|
||||
|
||||
@@ -0,0 +1,162 @@
|
||||
"""
|
||||
Theme API routes for listing and retrieving theme information.
|
||||
|
||||
Themes are pre-created style configurations that users can select when creating jobs.
|
||||
These endpoints are public (no authentication required) to allow theme selection
|
||||
before job creation.
|
||||
"""
|
||||
|
||||
import logging
|
||||
from typing import Optional
|
||||
|
||||
from fastapi import APIRouter, HTTPException
|
||||
|
||||
from backend.models.theme import ThemeDetailResponse, ThemesListResponse
|
||||
from backend.services.theme_service import get_theme_service
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter(prefix="/themes", tags=["themes"])
|
||||
|
||||
|
||||
@router.get("", response_model=ThemesListResponse)
|
||||
async def list_themes() -> ThemesListResponse:
|
||||
"""
|
||||
List all available themes.
|
||||
|
||||
Returns a list of themes with their metadata and preview image URLs.
|
||||
Preview URLs are signed and valid for 60 minutes.
|
||||
|
||||
This endpoint is public and does not require authentication.
|
||||
"""
|
||||
try:
|
||||
theme_service = get_theme_service()
|
||||
themes = theme_service.list_themes()
|
||||
return ThemesListResponse(themes=themes)
|
||||
except Exception as e:
|
||||
logger.error(f"Error listing themes: {e}")
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail="Failed to load themes"
|
||||
)
|
||||
|
||||
|
||||
@router.get("/{theme_id}", response_model=ThemeDetailResponse)
|
||||
async def get_theme(theme_id: str) -> ThemeDetailResponse:
|
||||
"""
|
||||
Get detailed information about a specific theme.
|
||||
|
||||
Returns the full theme details including style parameters.
|
||||
This can be used to preview theme settings or inspect configuration.
|
||||
|
||||
Args:
|
||||
theme_id: The unique identifier of the theme
|
||||
|
||||
Returns:
|
||||
ThemeDetailResponse with full theme details
|
||||
|
||||
Raises:
|
||||
404: Theme not found
|
||||
"""
|
||||
try:
|
||||
theme_service = get_theme_service()
|
||||
theme = theme_service.get_theme(theme_id)
|
||||
|
||||
if theme is None:
|
||||
raise HTTPException(
|
||||
status_code=404,
|
||||
detail=f"Theme not found: {theme_id}"
|
||||
)
|
||||
|
||||
return ThemeDetailResponse(theme=theme)
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting theme {theme_id}: {e}")
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail="Failed to load theme"
|
||||
)
|
||||
|
||||
|
||||
@router.get("/{theme_id}/preview")
|
||||
async def get_theme_preview(theme_id: str) -> dict:
|
||||
"""
|
||||
Get a signed URL for the theme's preview image.
|
||||
|
||||
This endpoint is useful when you need just the preview URL
|
||||
without loading the full theme details.
|
||||
|
||||
Args:
|
||||
theme_id: The unique identifier of the theme
|
||||
|
||||
Returns:
|
||||
Object with preview_url field
|
||||
|
||||
Raises:
|
||||
404: Theme not found or no preview available
|
||||
"""
|
||||
try:
|
||||
theme_service = get_theme_service()
|
||||
|
||||
if not theme_service.theme_exists(theme_id):
|
||||
raise HTTPException(
|
||||
status_code=404,
|
||||
detail=f"Theme not found: {theme_id}"
|
||||
)
|
||||
|
||||
theme = theme_service.get_theme(theme_id)
|
||||
if theme is None or theme.preview_url is None:
|
||||
raise HTTPException(
|
||||
status_code=404,
|
||||
detail=f"No preview available for theme: {theme_id}"
|
||||
)
|
||||
|
||||
return {"preview_url": theme.preview_url}
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting preview for theme {theme_id}: {e}")
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail="Failed to load theme preview"
|
||||
)
|
||||
|
||||
|
||||
@router.get("/{theme_id}/youtube-description")
|
||||
async def get_theme_youtube_description(theme_id: str) -> dict:
|
||||
"""
|
||||
Get the YouTube description template for a theme.
|
||||
|
||||
Some themes include a default YouTube video description template
|
||||
that can be used when uploading videos.
|
||||
|
||||
Args:
|
||||
theme_id: The unique identifier of the theme
|
||||
|
||||
Returns:
|
||||
Object with description field containing the template text,
|
||||
or null if no template is available
|
||||
|
||||
Raises:
|
||||
404: Theme not found
|
||||
"""
|
||||
try:
|
||||
theme_service = get_theme_service()
|
||||
|
||||
if not theme_service.theme_exists(theme_id):
|
||||
raise HTTPException(
|
||||
status_code=404,
|
||||
detail=f"Theme not found: {theme_id}"
|
||||
)
|
||||
|
||||
description = theme_service.get_youtube_description(theme_id)
|
||||
return {"description": description}
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting YouTube description for theme {theme_id}: {e}")
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail="Failed to load YouTube description"
|
||||
)
|
||||
@@ -41,9 +41,27 @@ class Settings(BaseSettings):
|
||||
max_concurrent_jobs: int = int(os.getenv("MAX_CONCURRENT_JOBS", "5"))
|
||||
job_timeout_seconds: int = int(os.getenv("JOB_TIMEOUT_SECONDS", "3600"))
|
||||
|
||||
# Cloud Tasks (for scalable worker coordination)
|
||||
# When enabled, workers are triggered via Cloud Tasks for guaranteed delivery
|
||||
# When disabled (default), workers are triggered via direct HTTP (for development)
|
||||
enable_cloud_tasks: bool = os.getenv("ENABLE_CLOUD_TASKS", "false").lower() in ("true", "1", "yes")
|
||||
gcp_region: str = os.getenv("GCP_REGION", "us-central1")
|
||||
|
||||
# Cloud Run Jobs (for long-running video encoding)
|
||||
# When enabled AND enable_cloud_tasks is true, video worker uses Cloud Run Jobs
|
||||
# instead of Cloud Tasks. This supports encoding times >30 minutes (up to 24 hours).
|
||||
# Default is false - Cloud Tasks is sufficient for most videos (15-20 min).
|
||||
use_cloud_run_jobs_for_video: bool = os.getenv("USE_CLOUD_RUN_JOBS_FOR_VIDEO", "false").lower() in ("true", "1", "yes")
|
||||
|
||||
# Storage paths
|
||||
temp_dir: str = os.getenv("TEMP_DIR", "/tmp/karaoke-gen")
|
||||
|
||||
# Flacfetch remote service (for torrent downloads)
|
||||
# When configured, audio search uses the remote flacfetch HTTP API instead of local flacfetch.
|
||||
# This is required for torrent downloads since Cloud Run doesn't support BitTorrent.
|
||||
flacfetch_api_url: Optional[str] = os.getenv("FLACFETCH_API_URL") # e.g., http://10.0.0.5:8080
|
||||
flacfetch_api_key: Optional[str] = os.getenv("FLACFETCH_API_KEY")
|
||||
|
||||
# Default distribution settings (can be overridden per-request)
|
||||
default_dropbox_path: Optional[str] = os.getenv("DEFAULT_DROPBOX_PATH")
|
||||
default_gdrive_folder_id: Optional[str] = os.getenv("DEFAULT_GDRIVE_FOLDER_ID")
|
||||
@@ -51,6 +69,16 @@ class Settings(BaseSettings):
|
||||
default_discord_webhook_url: Optional[str] = (
|
||||
os.getenv("DEFAULT_DISCORD_WEBHOOK_URL", "").strip() or None
|
||||
)
|
||||
|
||||
# Default values for web service jobs (YouTube/Dropbox distribution)
|
||||
default_enable_youtube_upload: bool = os.getenv("DEFAULT_ENABLE_YOUTUBE_UPLOAD", "false").lower() in ("true", "1", "yes")
|
||||
default_brand_prefix: Optional[str] = os.getenv("DEFAULT_BRAND_PREFIX")
|
||||
default_youtube_description: str = os.getenv(
|
||||
"DEFAULT_YOUTUBE_DESCRIPTION",
|
||||
"Karaoke video created with Nomad Karaoke (https://nomadkaraoke.com)\n\n"
|
||||
"AI-powered vocal separation and synchronized lyrics.\n\n"
|
||||
"#karaoke #music #singing #instrumental #lyrics"
|
||||
)
|
||||
|
||||
# Secret Manager cache
|
||||
_secret_cache: Dict[str, str] = {}
|
||||
|
||||
+7
-6
@@ -7,18 +7,17 @@ from fastapi import FastAPI
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
|
||||
from backend.config import settings
|
||||
from backend.api.routes import health, jobs, internal, file_upload, review, auth
|
||||
from backend.api.routes import health, jobs, internal, file_upload, review, auth, audio_search, themes
|
||||
from backend.services.tracing import setup_tracing, instrument_app, get_current_trace_id
|
||||
from backend.services.structured_logging import setup_structured_logging
|
||||
|
||||
|
||||
from backend.version import VERSION
|
||||
|
||||
|
||||
# Configure logging with trace ID support
|
||||
logging.basicConfig(
|
||||
level=getattr(logging, settings.log_level.upper()),
|
||||
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
|
||||
)
|
||||
# Configure structured logging (JSON in Cloud Run, human-readable locally)
|
||||
# This must happen before any logging calls
|
||||
setup_structured_logging()
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Initialize OpenTelemetry tracing (must happen before app creation)
|
||||
@@ -108,6 +107,8 @@ app.include_router(file_upload.router, prefix="/api") # File upload endpoint
|
||||
app.include_router(internal.router, prefix="/api") # Internal worker endpoints
|
||||
app.include_router(review.router, prefix="/api") # Review UI compatibility endpoints
|
||||
app.include_router(auth.router, prefix="/api") # OAuth credential management
|
||||
app.include_router(audio_search.router, prefix="/api") # Audio search (artist+title mode)
|
||||
app.include_router(themes.router, prefix="/api") # Theme selection for styles
|
||||
|
||||
|
||||
@app.get("/")
|
||||
|
||||
+113
-15
@@ -14,8 +14,8 @@ class JobStatus(str, Enum):
|
||||
"""
|
||||
Job status enumeration - Complete state machine.
|
||||
|
||||
The workflow has 8 main stages with 2 human interaction points:
|
||||
1. Input & Setup
|
||||
The workflow has 8 main stages with 3 human interaction points:
|
||||
1. Input & Setup (may include audio source selection)
|
||||
2. Parallel Processing (audio + lyrics)
|
||||
3. Title/End Screen Generation
|
||||
4. Countdown Padding Synchronization
|
||||
@@ -26,6 +26,12 @@ class JobStatus(str, Enum):
|
||||
"""
|
||||
# Initial states
|
||||
PENDING = "pending" # Job created, queued for processing
|
||||
|
||||
# Audio search states (for artist+title search mode)
|
||||
SEARCHING_AUDIO = "searching_audio" # Searching for audio sources via flacfetch
|
||||
AWAITING_AUDIO_SELECTION = "awaiting_audio_selection" # ⚠️ WAITING FOR USER - select audio source
|
||||
DOWNLOADING_AUDIO = "downloading_audio" # Downloading selected audio from source
|
||||
|
||||
DOWNLOADING = "downloading" # Downloading from URL or processing upload
|
||||
|
||||
# Stage 2a: Audio separation (parallel track 1)
|
||||
@@ -67,6 +73,7 @@ class JobStatus(str, Enum):
|
||||
|
||||
# Terminal states
|
||||
COMPLETE = "complete" # All processing finished successfully
|
||||
PREP_COMPLETE = "prep_complete" # Prep-only job completed (stops after review)
|
||||
FAILED = "failed" # Unrecoverable error occurred
|
||||
CANCELLED = "cancelled" # User cancelled the job
|
||||
|
||||
@@ -80,7 +87,14 @@ class JobStatus(str, Enum):
|
||||
|
||||
# Valid state transitions
|
||||
STATE_TRANSITIONS = {
|
||||
JobStatus.PENDING: [JobStatus.DOWNLOADING, JobStatus.FAILED, JobStatus.CANCELLED],
|
||||
# PENDING can go to DOWNLOADING (file upload), SEARCHING_AUDIO (artist+title search), or AWAITING_INSTRUMENTAL_SELECTION (finalise-only)
|
||||
JobStatus.PENDING: [JobStatus.DOWNLOADING, JobStatus.SEARCHING_AUDIO, JobStatus.AWAITING_INSTRUMENTAL_SELECTION, JobStatus.FAILED, JobStatus.CANCELLED],
|
||||
|
||||
# Audio search flow (for artist+title search mode)
|
||||
JobStatus.SEARCHING_AUDIO: [JobStatus.AWAITING_AUDIO_SELECTION, JobStatus.DOWNLOADING_AUDIO, JobStatus.FAILED],
|
||||
JobStatus.AWAITING_AUDIO_SELECTION: [JobStatus.DOWNLOADING_AUDIO, JobStatus.FAILED, JobStatus.CANCELLED],
|
||||
JobStatus.DOWNLOADING_AUDIO: [JobStatus.DOWNLOADING, JobStatus.FAILED],
|
||||
|
||||
# DOWNLOADING allows parallel processing (audio + lyrics) and then screens when both complete
|
||||
JobStatus.DOWNLOADING: [JobStatus.SEPARATING_STAGE1, JobStatus.TRANSCRIBING, JobStatus.GENERATING_SCREENS, JobStatus.FAILED],
|
||||
|
||||
@@ -102,10 +116,10 @@ STATE_TRANSITIONS = {
|
||||
# AWAITING_REVIEW can go directly to REVIEW_COMPLETE (quick review) or to IN_REVIEW (editing)
|
||||
JobStatus.AWAITING_REVIEW: [JobStatus.IN_REVIEW, JobStatus.REVIEW_COMPLETE, JobStatus.FAILED, JobStatus.CANCELLED],
|
||||
JobStatus.IN_REVIEW: [JobStatus.REVIEW_COMPLETE, JobStatus.AWAITING_REVIEW, JobStatus.FAILED],
|
||||
JobStatus.REVIEW_COMPLETE: [JobStatus.RENDERING_VIDEO, JobStatus.FAILED],
|
||||
JobStatus.REVIEW_COMPLETE: [JobStatus.RENDERING_VIDEO, JobStatus.PREP_COMPLETE, JobStatus.FAILED], # PREP_COMPLETE for prep-only jobs
|
||||
|
||||
# Video rendering (post-review)
|
||||
JobStatus.RENDERING_VIDEO: [JobStatus.AWAITING_INSTRUMENTAL_SELECTION, JobStatus.FAILED],
|
||||
JobStatus.RENDERING_VIDEO: [JobStatus.AWAITING_INSTRUMENTAL_SELECTION, JobStatus.PREP_COMPLETE, JobStatus.FAILED],
|
||||
|
||||
# Instrumental selection flow
|
||||
JobStatus.AWAITING_INSTRUMENTAL_SELECTION: [JobStatus.INSTRUMENTAL_SELECTED, JobStatus.FAILED, JobStatus.CANCELLED],
|
||||
@@ -120,15 +134,23 @@ STATE_TRANSITIONS = {
|
||||
JobStatus.UPLOADING: [JobStatus.NOTIFYING, JobStatus.COMPLETE, JobStatus.FAILED],
|
||||
JobStatus.NOTIFYING: [JobStatus.COMPLETE, JobStatus.FAILED],
|
||||
|
||||
# Terminal states - COMPLETE and CANCELLED have no transitions
|
||||
# FAILED allows retry transitions to resume from checkpoints
|
||||
# Terminal states - COMPLETE, PREP_COMPLETE have no transitions
|
||||
# FAILED and CANCELLED allow retry transitions to resume from checkpoints
|
||||
# PREP_COMPLETE allows finalise-only continuation
|
||||
JobStatus.COMPLETE: [],
|
||||
JobStatus.PREP_COMPLETE: [JobStatus.AWAITING_INSTRUMENTAL_SELECTION, JobStatus.FAILED], # Finalise-only continues from here
|
||||
JobStatus.FAILED: [
|
||||
JobStatus.DOWNLOADING, # Retry from beginning (if input audio exists)
|
||||
JobStatus.INSTRUMENTAL_SELECTED, # Retry from video generation
|
||||
JobStatus.REVIEW_COMPLETE, # Retry from render stage
|
||||
JobStatus.LYRICS_COMPLETE, # Retry from screens generation
|
||||
],
|
||||
JobStatus.CANCELLED: [
|
||||
JobStatus.DOWNLOADING, # Retry from beginning (if input audio exists)
|
||||
JobStatus.INSTRUMENTAL_SELECTED, # Retry from video generation
|
||||
JobStatus.REVIEW_COMPLETE, # Retry from render stage
|
||||
JobStatus.LYRICS_COMPLETE, # Retry from screens generation
|
||||
],
|
||||
JobStatus.CANCELLED: [],
|
||||
|
||||
# Legacy states (for backward compatibility)
|
||||
JobStatus.QUEUED: [JobStatus.PENDING],
|
||||
@@ -176,14 +198,25 @@ class Job(BaseModel):
|
||||
input_media_gcs_path: Optional[str] = None # GCS path to uploaded file
|
||||
|
||||
# User preferences
|
||||
enable_cdg: bool = True # Generate CDG+MP3 package
|
||||
enable_txt: bool = True # Generate TXT+MP3 package
|
||||
enable_cdg: bool = False # Generate CDG+MP3 package (requires style config)
|
||||
enable_txt: bool = False # Generate TXT+MP3 package (requires style config)
|
||||
enable_youtube_upload: bool = False # Upload to YouTube
|
||||
youtube_description: Optional[str] = None # YouTube video description
|
||||
webhook_url: Optional[str] = None # Webhook for notifications
|
||||
user_email: Optional[str] = None # Email for notifications
|
||||
|
||||
# Style configuration (uploaded files)
|
||||
# Theme configuration (pre-made themes from GCS)
|
||||
theme_id: Optional[str] = None # Theme identifier (e.g., "nomad", "default")
|
||||
color_overrides: Dict[str, str] = Field(default_factory=dict)
|
||||
"""
|
||||
User color overrides applied on top of theme. Keys:
|
||||
- artist_color: Hex color for artist name (#RRGGBB)
|
||||
- title_color: Hex color for song title
|
||||
- sung_lyrics_color: Hex color for highlighted lyrics
|
||||
- unsung_lyrics_color: Hex color for unhighlighted lyrics
|
||||
"""
|
||||
|
||||
# Style configuration (uploaded files - used when theme_id is not set)
|
||||
style_params_gcs_path: Optional[str] = None # GCS path to style_params.json
|
||||
style_assets: Dict[str, str] = Field(default_factory=dict)
|
||||
"""
|
||||
@@ -211,6 +244,36 @@ class Job(BaseModel):
|
||||
# Legacy distribution configuration (rclone - for local CLI backward compat)
|
||||
organised_dir_rclone_root: Optional[str] = None # Deprecated: use dropbox_path instead
|
||||
|
||||
# Lyrics configuration (overrides for search/transcription)
|
||||
lyrics_artist: Optional[str] = None # Override artist name for lyrics search
|
||||
lyrics_title: Optional[str] = None # Override title for lyrics search
|
||||
lyrics_file_gcs_path: Optional[str] = None # GCS path to user-provided lyrics file
|
||||
subtitle_offset_ms: int = 0 # Offset for subtitle timing (positive = delay)
|
||||
|
||||
# Audio separation model configuration
|
||||
clean_instrumental_model: Optional[str] = None # Model for clean instrumental separation
|
||||
backing_vocals_models: Optional[List[str]] = None # Models for backing vocals separation
|
||||
other_stems_models: Optional[List[str]] = None # Models for other stems (bass, drums, etc.)
|
||||
|
||||
# Existing instrumental configuration (Batch 3)
|
||||
existing_instrumental_gcs_path: Optional[str] = None # GCS path to user-provided instrumental file
|
||||
|
||||
# Audio search configuration (Batch 5 - artist+title search mode)
|
||||
audio_search_artist: Optional[str] = None # Artist name used for audio search
|
||||
audio_search_title: Optional[str] = None # Title used for audio search
|
||||
auto_download: bool = False # Auto-select best audio source (skip selection)
|
||||
|
||||
# Two-phase workflow configuration (Batch 6)
|
||||
prep_only: bool = False # Stop after review, don't run finalisation
|
||||
finalise_only: bool = False # Skip prep, run only finalisation (requires uploaded prep outputs)
|
||||
keep_brand_code: Optional[str] = None # Preserve existing brand code instead of generating new one
|
||||
|
||||
# Review authentication (Batch 7)
|
||||
review_token: Optional[str] = None # Job-scoped token for lyrics review UI access (generated when entering AWAITING_REVIEW)
|
||||
review_token_expires_at: Optional[datetime] = None # Token expiry time (optional, for extra security)
|
||||
instrumental_token: Optional[str] = None # Job-scoped token for instrumental review UI access (generated when entering AWAITING_INSTRUMENTAL_SELECTION)
|
||||
instrumental_token_expires_at: Optional[datetime] = None # Token expiry time
|
||||
|
||||
# Processing state
|
||||
track_output_dir: Optional[str] = None # Local output directory (temp)
|
||||
audio_hash: Optional[str] = None # Hash for deduplication
|
||||
@@ -348,16 +411,27 @@ class JobCreate(BaseModel):
|
||||
artist: Optional[str] = None
|
||||
title: Optional[str] = None
|
||||
filename: Optional[str] = None # Original uploaded filename
|
||||
|
||||
|
||||
# Optional preferences
|
||||
enable_cdg: bool = True
|
||||
enable_txt: bool = True
|
||||
enable_cdg: bool = False # Requires style config
|
||||
enable_txt: bool = False # Requires style config
|
||||
enable_youtube_upload: bool = False
|
||||
youtube_description: Optional[str] = None
|
||||
webhook_url: Optional[str] = None
|
||||
user_email: Optional[str] = None
|
||||
|
||||
# Style configuration (will be populated after file upload)
|
||||
# Theme configuration (pre-made themes from GCS)
|
||||
theme_id: Optional[str] = None # Theme identifier (e.g., "nomad", "default")
|
||||
color_overrides: Dict[str, str] = Field(default_factory=dict)
|
||||
"""
|
||||
User color overrides applied on top of theme. Keys:
|
||||
- artist_color: Hex color for artist name (#RRGGBB)
|
||||
- title_color: Hex color for song title
|
||||
- sung_lyrics_color: Hex color for highlighted lyrics
|
||||
- unsung_lyrics_color: Hex color for unhighlighted lyrics
|
||||
"""
|
||||
|
||||
# Style configuration (will be populated after file upload, or from theme)
|
||||
style_params_gcs_path: Optional[str] = None
|
||||
style_assets: Dict[str, str] = Field(default_factory=dict)
|
||||
|
||||
@@ -373,6 +447,30 @@ class JobCreate(BaseModel):
|
||||
# Legacy (rclone - deprecated, use dropbox_path instead)
|
||||
organised_dir_rclone_root: Optional[str] = None
|
||||
|
||||
# Lyrics configuration (overrides for search/transcription)
|
||||
lyrics_artist: Optional[str] = None # Override artist name for lyrics search
|
||||
lyrics_title: Optional[str] = None # Override title for lyrics search
|
||||
lyrics_file_gcs_path: Optional[str] = None # GCS path to user-provided lyrics file
|
||||
subtitle_offset_ms: int = 0 # Offset for subtitle timing (positive = delay)
|
||||
|
||||
# Audio separation model configuration
|
||||
clean_instrumental_model: Optional[str] = None # Model for clean instrumental separation
|
||||
backing_vocals_models: Optional[List[str]] = None # Models for backing vocals separation
|
||||
other_stems_models: Optional[List[str]] = None # Models for other stems (bass, drums, etc.)
|
||||
|
||||
# Existing instrumental configuration (Batch 3)
|
||||
existing_instrumental_gcs_path: Optional[str] = None # GCS path to user-provided instrumental file
|
||||
|
||||
# Audio search configuration (Batch 5 - artist+title search mode)
|
||||
audio_search_artist: Optional[str] = None # Artist name used for audio search
|
||||
audio_search_title: Optional[str] = None # Title used for audio search
|
||||
auto_download: bool = False # Auto-select best audio source (skip selection)
|
||||
|
||||
# Two-phase workflow configuration (Batch 6)
|
||||
prep_only: bool = False # Stop after review, don't run finalisation
|
||||
finalise_only: bool = False # Skip prep, run only finalisation
|
||||
keep_brand_code: Optional[str] = None # Preserve existing brand code instead of generating new one
|
||||
|
||||
# Request metadata (set by API endpoint from request headers)
|
||||
request_metadata: Dict[str, Any] = Field(default_factory=dict)
|
||||
"""
|
||||
|
||||
@@ -12,8 +12,8 @@ class URLSubmissionRequest(BaseModel):
|
||||
title: Optional[str] = None # Auto-detected if not provided
|
||||
|
||||
# Optional preferences
|
||||
enable_cdg: bool = True
|
||||
enable_txt: bool = True
|
||||
enable_cdg: bool = False # Requires style config
|
||||
enable_txt: bool = False # Requires style config
|
||||
enable_youtube_upload: bool = False
|
||||
youtube_description: Optional[str] = None
|
||||
webhook_url: Optional[str] = None
|
||||
@@ -24,10 +24,10 @@ class UploadSubmissionRequest(BaseModel):
|
||||
"""Request to submit a job from an uploaded file."""
|
||||
artist: str
|
||||
title: str
|
||||
|
||||
|
||||
# Optional preferences
|
||||
enable_cdg: bool = True
|
||||
enable_txt: bool = True
|
||||
enable_cdg: bool = False # Requires style config
|
||||
enable_txt: bool = False # Requires style config
|
||||
enable_youtube_upload: bool = False
|
||||
youtube_description: Optional[str] = None
|
||||
webhook_url: Optional[str] = None
|
||||
@@ -59,19 +59,54 @@ class InstrumentalSelection(BaseModel):
|
||||
Request to select instrumental audio option.
|
||||
|
||||
This is the second critical human-in-the-loop interaction point.
|
||||
User chooses between clean instrumental or instrumental with backing vocals.
|
||||
User chooses between clean instrumental, instrumental with backing vocals,
|
||||
or a custom instrumental (created via create-custom-instrumental endpoint).
|
||||
"""
|
||||
selection: str # "clean" or "with_backing"
|
||||
selection: str # "clean", "with_backing", or "custom"
|
||||
|
||||
@validator('selection')
|
||||
def validate_selection(cls, v):
|
||||
"""Validate selection is a valid option."""
|
||||
valid_options = ['clean', 'with_backing']
|
||||
valid_options = ['clean', 'with_backing', 'custom']
|
||||
if v not in valid_options:
|
||||
raise ValueError(f"Selection must be one of: {valid_options}")
|
||||
return v
|
||||
|
||||
|
||||
class MuteRegionRequest(BaseModel):
|
||||
"""A region to mute in the backing vocals."""
|
||||
start_seconds: float
|
||||
end_seconds: float
|
||||
|
||||
@validator('start_seconds')
|
||||
def validate_start(cls, v):
|
||||
if v < 0:
|
||||
raise ValueError("start_seconds must be non-negative")
|
||||
return v
|
||||
|
||||
@validator('end_seconds')
|
||||
def validate_end(cls, v, values):
|
||||
if 'start_seconds' in values and v <= values['start_seconds']:
|
||||
raise ValueError("end_seconds must be greater than start_seconds")
|
||||
return v
|
||||
|
||||
|
||||
class CreateCustomInstrumentalRequest(BaseModel):
|
||||
"""
|
||||
Request to create a custom instrumental with muted backing vocal regions.
|
||||
|
||||
The mute_regions specify time ranges in the backing vocals track that
|
||||
should be silenced before mixing with the clean instrumental.
|
||||
"""
|
||||
mute_regions: List[MuteRegionRequest]
|
||||
|
||||
@validator('mute_regions')
|
||||
def validate_regions(cls, v):
|
||||
if not v:
|
||||
raise ValueError("At least one mute region is required")
|
||||
return v
|
||||
|
||||
|
||||
class StartReviewRequest(BaseModel):
|
||||
"""Request to mark job as in-review (user opened interface)."""
|
||||
pass # No body needed, just triggers state transition
|
||||
|
||||
@@ -0,0 +1,153 @@
|
||||
"""
|
||||
Theme data models for karaoke-gen.
|
||||
|
||||
Themes are pre-created style configurations stored in GCS that users can select
|
||||
when creating karaoke jobs. Each theme includes:
|
||||
- Style parameters (fonts, colors, backgrounds, layouts)
|
||||
- Asset files (images, fonts)
|
||||
- Preview images
|
||||
- Optional YouTube description template
|
||||
"""
|
||||
|
||||
from datetime import datetime
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class ThemeSummary(BaseModel):
|
||||
"""Summary of a theme for listing purposes."""
|
||||
|
||||
id: str = Field(..., description="Unique theme identifier (e.g., 'nomad', 'default')")
|
||||
name: str = Field(..., description="Human-readable theme name")
|
||||
description: str = Field(..., description="Brief description of the theme style")
|
||||
preview_url: Optional[str] = Field(None, description="Signed URL for preview image")
|
||||
thumbnail_url: Optional[str] = Field(None, description="Signed URL for smaller thumbnail")
|
||||
is_default: bool = Field(False, description="Whether this is the default theme")
|
||||
|
||||
|
||||
class ThemeMetadata(BaseModel):
|
||||
"""Metadata for a single theme in the registry."""
|
||||
|
||||
id: str
|
||||
name: str
|
||||
description: str
|
||||
is_default: bool = False
|
||||
created_at: Optional[datetime] = None
|
||||
|
||||
|
||||
class ThemeRegistry(BaseModel):
|
||||
"""Registry of all available themes, stored as _metadata.json in GCS."""
|
||||
|
||||
version: int = 1
|
||||
themes: List[ThemeMetadata] = Field(default_factory=list)
|
||||
|
||||
|
||||
class ThemeDetail(BaseModel):
|
||||
"""Full theme details including style parameters."""
|
||||
|
||||
id: str
|
||||
name: str
|
||||
description: str
|
||||
preview_url: Optional[str] = None
|
||||
is_default: bool = False
|
||||
style_params: Dict[str, Any] = Field(default_factory=dict)
|
||||
has_youtube_description: bool = False
|
||||
|
||||
|
||||
class ColorOverrides(BaseModel):
|
||||
"""
|
||||
User-customizable color overrides that can be applied on top of a theme.
|
||||
|
||||
All colors are hex format (#RRGGBB). When applied:
|
||||
- artist_color: Applied to intro.artist_color, end.artist_color, cdg.artist_color
|
||||
- title_color: Applied to intro.title_color, end.title_color, cdg.title_color
|
||||
- sung_lyrics_color: Applied to karaoke.primary_color (converted to RGBA), cdg.active_fill
|
||||
- unsung_lyrics_color: Applied to karaoke.secondary_color (converted to RGBA), cdg.inactive_fill
|
||||
"""
|
||||
|
||||
artist_color: Optional[str] = Field(
|
||||
None,
|
||||
pattern=r"^#[0-9A-Fa-f]{6}$",
|
||||
description="Hex color for artist name on intro/end screens",
|
||||
)
|
||||
title_color: Optional[str] = Field(
|
||||
None,
|
||||
pattern=r"^#[0-9A-Fa-f]{6}$",
|
||||
description="Hex color for song title on intro/end screens",
|
||||
)
|
||||
sung_lyrics_color: Optional[str] = Field(
|
||||
None,
|
||||
pattern=r"^#[0-9A-Fa-f]{6}$",
|
||||
description="Hex color for lyrics being sung (highlighted)",
|
||||
)
|
||||
unsung_lyrics_color: Optional[str] = Field(
|
||||
None,
|
||||
pattern=r"^#[0-9A-Fa-f]{6}$",
|
||||
description="Hex color for lyrics not yet sung",
|
||||
)
|
||||
|
||||
def has_overrides(self) -> bool:
|
||||
"""Check if any color overrides are set."""
|
||||
return any(
|
||||
[
|
||||
self.artist_color,
|
||||
self.title_color,
|
||||
self.sung_lyrics_color,
|
||||
self.unsung_lyrics_color,
|
||||
]
|
||||
)
|
||||
|
||||
def to_dict(self) -> Dict[str, str]:
|
||||
"""Convert to dict, excluding None values."""
|
||||
return {k: v for k, v in self.model_dump().items() if v is not None}
|
||||
|
||||
|
||||
class ThemesListResponse(BaseModel):
|
||||
"""Response from GET /api/themes endpoint."""
|
||||
|
||||
themes: List[ThemeSummary]
|
||||
|
||||
|
||||
class ThemeDetailResponse(BaseModel):
|
||||
"""Response from GET /api/themes/{theme_id} endpoint."""
|
||||
|
||||
theme: ThemeDetail
|
||||
|
||||
|
||||
# Utility functions for color conversion
|
||||
|
||||
|
||||
def hex_to_rgba(hex_color: str, alpha: int = 255) -> str:
|
||||
"""
|
||||
Convert hex color (#RRGGBB) to RGBA format for ASS subtitles.
|
||||
|
||||
ASS subtitle format uses "R, G, B, A" string format.
|
||||
|
||||
Args:
|
||||
hex_color: Hex color string like "#7070F7"
|
||||
alpha: Alpha value 0-255 (default 255 = opaque)
|
||||
|
||||
Returns:
|
||||
RGBA string like "112, 112, 247, 255"
|
||||
"""
|
||||
hex_color = hex_color.lstrip("#")
|
||||
r = int(hex_color[0:2], 16)
|
||||
g = int(hex_color[2:4], 16)
|
||||
b = int(hex_color[4:6], 16)
|
||||
return f"{r}, {g}, {b}, {alpha}"
|
||||
|
||||
|
||||
def rgba_to_hex(rgba_str: str) -> str:
|
||||
"""
|
||||
Convert RGBA format to hex color.
|
||||
|
||||
Args:
|
||||
rgba_str: RGBA string like "112, 112, 247, 255"
|
||||
|
||||
Returns:
|
||||
Hex color string like "#7070F7"
|
||||
"""
|
||||
parts = [int(x.strip()) for x in rgba_str.split(",")]
|
||||
r, g, b = parts[0], parts[1], parts[2]
|
||||
return f"#{r:02x}{g:02x}{b:02x}"
|
||||
@@ -11,6 +11,8 @@ httpx>=0.25.0,<1.0.0
|
||||
google-cloud-firestore>=2.14.0,<3.0.0
|
||||
google-cloud-storage>=2.14.0,<3.0.0
|
||||
google-cloud-secret-manager>=2.18.0,<3.0.0
|
||||
google-cloud-tasks>=2.14.0,<3.0.0
|
||||
google-cloud-run>=0.10.0,<1.0.0
|
||||
python-dotenv>=1.0.0,<2.0.0
|
||||
|
||||
# Audio processing (reuses karaoke_gen library)
|
||||
|
||||
@@ -0,0 +1,243 @@
|
||||
"""
|
||||
Audio analysis service for analyzing backing vocals.
|
||||
|
||||
This service wraps the shared karaoke_gen.instrumental_review module
|
||||
to provide GCS-integrated audio analysis capabilities.
|
||||
"""
|
||||
|
||||
import logging
|
||||
import os
|
||||
import tempfile
|
||||
from typing import Optional
|
||||
|
||||
from backend.services.storage_service import StorageService
|
||||
from karaoke_gen.instrumental_review import (
|
||||
AudioAnalyzer,
|
||||
AnalysisResult,
|
||||
WaveformGenerator,
|
||||
)
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class AudioAnalysisService:
|
||||
"""
|
||||
Service for analyzing backing vocals audio files stored in GCS.
|
||||
|
||||
This service acts as a thin wrapper around the shared AudioAnalyzer
|
||||
and WaveformGenerator classes, handling GCS download/upload operations.
|
||||
|
||||
The actual analysis logic is in the shared karaoke_gen.instrumental_review
|
||||
module, ensuring feature parity between local and remote workflows.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
storage_service: Optional[StorageService] = None,
|
||||
silence_threshold_db: float = -40.0,
|
||||
min_segment_duration_ms: int = 100,
|
||||
):
|
||||
"""
|
||||
Initialize the audio analysis service.
|
||||
|
||||
Args:
|
||||
storage_service: GCS storage service. If not provided, a new
|
||||
instance will be created.
|
||||
silence_threshold_db: Threshold for considering audio as silent.
|
||||
Default is -40.0 dB.
|
||||
min_segment_duration_ms: Minimum duration for audible segments.
|
||||
Default is 100ms.
|
||||
"""
|
||||
self.storage_service = storage_service or StorageService()
|
||||
self.analyzer = AudioAnalyzer(
|
||||
silence_threshold_db=silence_threshold_db,
|
||||
min_segment_duration_ms=min_segment_duration_ms,
|
||||
)
|
||||
self.waveform_generator = WaveformGenerator()
|
||||
|
||||
def analyze_backing_vocals(
|
||||
self,
|
||||
gcs_audio_path: str,
|
||||
job_id: str,
|
||||
) -> AnalysisResult:
|
||||
"""
|
||||
Analyze a backing vocals audio file from GCS.
|
||||
|
||||
This method:
|
||||
1. Downloads the audio file from GCS to a temp file
|
||||
2. Runs the analysis using the shared AudioAnalyzer
|
||||
3. Returns the analysis result
|
||||
|
||||
Args:
|
||||
gcs_audio_path: Path to the audio file in GCS
|
||||
job_id: Job ID for logging
|
||||
|
||||
Returns:
|
||||
AnalysisResult containing analysis data
|
||||
"""
|
||||
logger.info(f"[{job_id}] Analyzing backing vocals: {gcs_audio_path}")
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
# Download audio file
|
||||
local_audio_path = os.path.join(temp_dir, "backing_vocals.flac")
|
||||
self.storage_service.download_file(gcs_audio_path, local_audio_path)
|
||||
|
||||
# Run analysis
|
||||
result = self.analyzer.analyze(local_audio_path)
|
||||
|
||||
logger.info(
|
||||
f"[{job_id}] Analysis complete: "
|
||||
f"has_audible={result.has_audible_content}, "
|
||||
f"segments={result.segment_count}, "
|
||||
f"recommendation={result.recommended_selection.value}"
|
||||
)
|
||||
|
||||
return result
|
||||
|
||||
def analyze_and_generate_waveform(
|
||||
self,
|
||||
gcs_audio_path: str,
|
||||
job_id: str,
|
||||
gcs_waveform_destination: str,
|
||||
) -> tuple[AnalysisResult, str]:
|
||||
"""
|
||||
Analyze backing vocals and generate a waveform image.
|
||||
|
||||
This method:
|
||||
1. Downloads the audio file from GCS
|
||||
2. Runs analysis using AudioAnalyzer
|
||||
3. Generates waveform image using WaveformGenerator
|
||||
4. Uploads the waveform image to GCS
|
||||
5. Returns analysis result and waveform GCS path
|
||||
|
||||
Args:
|
||||
gcs_audio_path: Path to the audio file in GCS
|
||||
job_id: Job ID for logging
|
||||
gcs_waveform_destination: Where to upload the waveform image in GCS
|
||||
|
||||
Returns:
|
||||
Tuple of (AnalysisResult, waveform_gcs_path)
|
||||
"""
|
||||
logger.info(f"[{job_id}] Analyzing and generating waveform: {gcs_audio_path}")
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
# Download audio file
|
||||
local_audio_path = os.path.join(temp_dir, "backing_vocals.flac")
|
||||
self.storage_service.download_file(gcs_audio_path, local_audio_path)
|
||||
|
||||
# Run analysis
|
||||
result = self.analyzer.analyze(local_audio_path)
|
||||
|
||||
# Generate waveform
|
||||
local_waveform_path = os.path.join(temp_dir, "waveform.png")
|
||||
self.waveform_generator.generate(
|
||||
audio_path=local_audio_path,
|
||||
output_path=local_waveform_path,
|
||||
segments=result.audible_segments,
|
||||
show_time_axis=True,
|
||||
silence_threshold_db=self.analyzer.silence_threshold_db,
|
||||
)
|
||||
|
||||
# Upload waveform to GCS
|
||||
self.storage_service.upload_file(
|
||||
local_waveform_path,
|
||||
gcs_waveform_destination
|
||||
)
|
||||
|
||||
logger.info(
|
||||
f"[{job_id}] Analysis and waveform generation complete. "
|
||||
f"Waveform uploaded to: {gcs_waveform_destination}"
|
||||
)
|
||||
|
||||
return result, gcs_waveform_destination
|
||||
|
||||
def get_waveform_data(
|
||||
self,
|
||||
gcs_audio_path: str,
|
||||
job_id: str,
|
||||
num_points: int = 500,
|
||||
) -> tuple[list[float], float]:
|
||||
"""
|
||||
Get waveform data (amplitude envelope) for client-side rendering.
|
||||
|
||||
This is useful when the frontend wants to render the waveform
|
||||
itself using Canvas or SVG, rather than displaying a pre-generated
|
||||
image.
|
||||
|
||||
Args:
|
||||
gcs_audio_path: Path to the audio file in GCS
|
||||
job_id: Job ID for logging
|
||||
num_points: Number of data points to return
|
||||
|
||||
Returns:
|
||||
Tuple of (amplitude_values, duration_seconds)
|
||||
"""
|
||||
logger.info(f"[{job_id}] Getting waveform data: {gcs_audio_path}")
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
# Download audio file
|
||||
local_audio_path = os.path.join(temp_dir, "backing_vocals.flac")
|
||||
self.storage_service.download_file(gcs_audio_path, local_audio_path)
|
||||
|
||||
# Generate waveform data
|
||||
amplitudes, duration = self.waveform_generator.generate_data_only(
|
||||
audio_path=local_audio_path,
|
||||
num_points=num_points,
|
||||
)
|
||||
|
||||
return amplitudes, duration
|
||||
|
||||
def generate_waveform_with_mutes(
|
||||
self,
|
||||
gcs_audio_path: str,
|
||||
job_id: str,
|
||||
gcs_waveform_destination: str,
|
||||
mute_regions: list,
|
||||
) -> str:
|
||||
"""
|
||||
Generate a waveform image with mute regions highlighted.
|
||||
|
||||
This is useful for showing the user which regions will be muted
|
||||
in the custom instrumental.
|
||||
|
||||
Args:
|
||||
gcs_audio_path: Path to the audio file in GCS
|
||||
job_id: Job ID for logging
|
||||
gcs_waveform_destination: Where to upload the waveform image
|
||||
mute_regions: List of MuteRegion objects to highlight
|
||||
|
||||
Returns:
|
||||
GCS path to the uploaded waveform image
|
||||
"""
|
||||
from karaoke_gen.instrumental_review import MuteRegion
|
||||
|
||||
logger.info(
|
||||
f"[{job_id}] Generating waveform with {len(mute_regions)} mute regions"
|
||||
)
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
# Download audio file
|
||||
local_audio_path = os.path.join(temp_dir, "backing_vocals.flac")
|
||||
self.storage_service.download_file(gcs_audio_path, local_audio_path)
|
||||
|
||||
# First run analysis to get segments
|
||||
result = self.analyzer.analyze(local_audio_path)
|
||||
|
||||
# Generate waveform with mute regions
|
||||
local_waveform_path = os.path.join(temp_dir, "waveform_with_mutes.png")
|
||||
self.waveform_generator.generate(
|
||||
audio_path=local_audio_path,
|
||||
output_path=local_waveform_path,
|
||||
segments=result.audible_segments,
|
||||
mute_regions=mute_regions,
|
||||
show_time_axis=True,
|
||||
)
|
||||
|
||||
# Upload to GCS
|
||||
self.storage_service.upload_file(
|
||||
local_waveform_path,
|
||||
gcs_waveform_destination
|
||||
)
|
||||
|
||||
return gcs_waveform_destination
|
||||
@@ -0,0 +1,278 @@
|
||||
"""
|
||||
Audio editing service for creating custom instrumentals.
|
||||
|
||||
This service wraps the shared karaoke_gen.instrumental_review module
|
||||
to provide GCS-integrated audio editing capabilities.
|
||||
"""
|
||||
|
||||
import logging
|
||||
import os
|
||||
import tempfile
|
||||
from typing import List, Optional
|
||||
|
||||
from backend.services.storage_service import StorageService
|
||||
from karaoke_gen.instrumental_review import (
|
||||
AudioEditor,
|
||||
MuteRegion,
|
||||
)
|
||||
from karaoke_gen.instrumental_review.models import CustomInstrumentalResult
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class AudioEditingService:
|
||||
"""
|
||||
Service for creating custom instrumental tracks with GCS integration.
|
||||
|
||||
This service acts as a thin wrapper around the shared AudioEditor
|
||||
class, handling GCS download/upload operations.
|
||||
|
||||
The actual editing logic is in the shared karaoke_gen.instrumental_review
|
||||
module, ensuring feature parity between local and remote workflows.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
storage_service: Optional[StorageService] = None,
|
||||
output_format: str = "flac",
|
||||
):
|
||||
"""
|
||||
Initialize the audio editing service.
|
||||
|
||||
Args:
|
||||
storage_service: GCS storage service. If not provided, a new
|
||||
instance will be created.
|
||||
output_format: Output audio format. Default is "flac".
|
||||
"""
|
||||
self.storage_service = storage_service or StorageService()
|
||||
self.editor = AudioEditor(output_format=output_format)
|
||||
|
||||
def create_custom_instrumental(
|
||||
self,
|
||||
gcs_clean_instrumental_path: str,
|
||||
gcs_backing_vocals_path: str,
|
||||
mute_regions: List[MuteRegion],
|
||||
gcs_output_path: str,
|
||||
job_id: str,
|
||||
) -> CustomInstrumentalResult:
|
||||
"""
|
||||
Create a custom instrumental by muting regions of backing vocals.
|
||||
|
||||
This method:
|
||||
1. Downloads clean instrumental and backing vocals from GCS
|
||||
2. Applies mute regions to backing vocals
|
||||
3. Combines with clean instrumental
|
||||
4. Uploads result to GCS
|
||||
|
||||
Args:
|
||||
gcs_clean_instrumental_path: Path to clean instrumental in GCS
|
||||
gcs_backing_vocals_path: Path to backing vocals in GCS
|
||||
mute_regions: List of regions to mute in backing vocals
|
||||
gcs_output_path: Where to upload the custom instrumental in GCS
|
||||
job_id: Job ID for logging
|
||||
|
||||
Returns:
|
||||
CustomInstrumentalResult with details about the created file
|
||||
"""
|
||||
logger.info(
|
||||
f"[{job_id}] Creating custom instrumental with "
|
||||
f"{len(mute_regions)} mute regions"
|
||||
)
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
# Download input files
|
||||
local_clean_path = os.path.join(temp_dir, "clean_instrumental.flac")
|
||||
local_backing_path = os.path.join(temp_dir, "backing_vocals.flac")
|
||||
local_output_path = os.path.join(temp_dir, "custom_instrumental.flac")
|
||||
|
||||
logger.debug(f"[{job_id}] Downloading clean instrumental")
|
||||
self.storage_service.download_file(
|
||||
gcs_clean_instrumental_path,
|
||||
local_clean_path
|
||||
)
|
||||
|
||||
logger.debug(f"[{job_id}] Downloading backing vocals")
|
||||
self.storage_service.download_file(
|
||||
gcs_backing_vocals_path,
|
||||
local_backing_path
|
||||
)
|
||||
|
||||
# Create custom instrumental using shared editor
|
||||
result = self.editor.create_custom_instrumental(
|
||||
clean_instrumental_path=local_clean_path,
|
||||
backing_vocals_path=local_backing_path,
|
||||
mute_regions=mute_regions,
|
||||
output_path=local_output_path,
|
||||
)
|
||||
|
||||
# Upload result to GCS
|
||||
logger.debug(f"[{job_id}] Uploading custom instrumental to GCS")
|
||||
self.storage_service.upload_file(local_output_path, gcs_output_path)
|
||||
|
||||
# Update result with GCS path
|
||||
result.output_path = gcs_output_path
|
||||
|
||||
logger.info(
|
||||
f"[{job_id}] Custom instrumental created: {gcs_output_path}, "
|
||||
f"muted {result.total_muted_duration_seconds:.1f}s across "
|
||||
f"{len(result.mute_regions_applied)} regions"
|
||||
)
|
||||
|
||||
return result
|
||||
|
||||
def create_preview(
|
||||
self,
|
||||
gcs_clean_instrumental_path: str,
|
||||
gcs_backing_vocals_path: str,
|
||||
mute_regions: List[MuteRegion],
|
||||
gcs_preview_path: str,
|
||||
job_id: str,
|
||||
preview_duration_seconds: Optional[float] = None,
|
||||
) -> str:
|
||||
"""
|
||||
Create a preview of the custom instrumental.
|
||||
|
||||
This is similar to create_custom_instrumental but optimized for
|
||||
quick preview generation (optionally truncated duration).
|
||||
|
||||
Args:
|
||||
gcs_clean_instrumental_path: Path to clean instrumental in GCS
|
||||
gcs_backing_vocals_path: Path to backing vocals in GCS
|
||||
mute_regions: List of regions to mute
|
||||
gcs_preview_path: Where to upload the preview in GCS
|
||||
job_id: Job ID for logging
|
||||
preview_duration_seconds: Optional max duration for preview
|
||||
|
||||
Returns:
|
||||
GCS path to the uploaded preview
|
||||
"""
|
||||
logger.info(f"[{job_id}] Creating preview with {len(mute_regions)} mute regions")
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
# Download input files
|
||||
local_clean_path = os.path.join(temp_dir, "clean_instrumental.flac")
|
||||
local_backing_path = os.path.join(temp_dir, "backing_vocals.flac")
|
||||
local_preview_path = os.path.join(temp_dir, "preview.flac")
|
||||
|
||||
self.storage_service.download_file(
|
||||
gcs_clean_instrumental_path,
|
||||
local_clean_path
|
||||
)
|
||||
self.storage_service.download_file(
|
||||
gcs_backing_vocals_path,
|
||||
local_backing_path
|
||||
)
|
||||
|
||||
# Generate preview
|
||||
from pydub import AudioSegment
|
||||
|
||||
preview = self.editor.preview_with_mutes(
|
||||
clean_instrumental_path=local_clean_path,
|
||||
backing_vocals_path=local_backing_path,
|
||||
mute_regions=mute_regions,
|
||||
)
|
||||
|
||||
# Optionally truncate
|
||||
if preview_duration_seconds:
|
||||
max_ms = int(preview_duration_seconds * 1000)
|
||||
preview = preview[:max_ms]
|
||||
|
||||
# Export and upload
|
||||
preview.export(local_preview_path, format="flac")
|
||||
self.storage_service.upload_file(local_preview_path, gcs_preview_path)
|
||||
|
||||
logger.info(f"[{job_id}] Preview created: {gcs_preview_path}")
|
||||
|
||||
return gcs_preview_path
|
||||
|
||||
def mute_backing_vocals_only(
|
||||
self,
|
||||
gcs_backing_vocals_path: str,
|
||||
mute_regions: List[MuteRegion],
|
||||
gcs_output_path: str,
|
||||
job_id: str,
|
||||
) -> str:
|
||||
"""
|
||||
Apply mute regions to backing vocals without combining with instrumental.
|
||||
|
||||
This is useful for creating an edited backing vocals track that
|
||||
can be combined with the instrumental later.
|
||||
|
||||
Args:
|
||||
gcs_backing_vocals_path: Path to backing vocals in GCS
|
||||
mute_regions: List of regions to mute
|
||||
gcs_output_path: Where to upload the edited backing vocals
|
||||
job_id: Job ID for logging
|
||||
|
||||
Returns:
|
||||
GCS path to the uploaded edited backing vocals
|
||||
"""
|
||||
logger.info(
|
||||
f"[{job_id}] Muting backing vocals with {len(mute_regions)} regions"
|
||||
)
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
local_backing_path = os.path.join(temp_dir, "backing_vocals.flac")
|
||||
local_output_path = os.path.join(temp_dir, "muted_backing.flac")
|
||||
|
||||
self.storage_service.download_file(
|
||||
gcs_backing_vocals_path,
|
||||
local_backing_path
|
||||
)
|
||||
|
||||
self.editor.apply_mute_to_single_track(
|
||||
audio_path=local_backing_path,
|
||||
mute_regions=mute_regions,
|
||||
output_path=local_output_path,
|
||||
)
|
||||
|
||||
self.storage_service.upload_file(local_output_path, gcs_output_path)
|
||||
|
||||
logger.info(f"[{job_id}] Muted backing vocals: {gcs_output_path}")
|
||||
|
||||
return gcs_output_path
|
||||
|
||||
def validate_mute_regions(
|
||||
self,
|
||||
mute_regions: List[MuteRegion],
|
||||
total_duration_seconds: float,
|
||||
) -> List[str]:
|
||||
"""
|
||||
Validate mute regions for consistency.
|
||||
|
||||
Args:
|
||||
mute_regions: List of mute regions to validate
|
||||
total_duration_seconds: Total duration of the audio
|
||||
|
||||
Returns:
|
||||
List of validation error messages (empty if valid)
|
||||
"""
|
||||
errors = []
|
||||
|
||||
for i, region in enumerate(mute_regions):
|
||||
if region.start_seconds < 0:
|
||||
errors.append(
|
||||
f"Region {i}: start_seconds ({region.start_seconds}) cannot be negative"
|
||||
)
|
||||
|
||||
if region.end_seconds <= region.start_seconds:
|
||||
errors.append(
|
||||
f"Region {i}: end_seconds ({region.end_seconds}) must be after "
|
||||
f"start_seconds ({region.start_seconds})"
|
||||
)
|
||||
|
||||
if region.start_seconds > total_duration_seconds:
|
||||
errors.append(
|
||||
f"Region {i}: start_seconds ({region.start_seconds}) exceeds "
|
||||
f"audio duration ({total_duration_seconds})"
|
||||
)
|
||||
|
||||
if region.end_seconds > total_duration_seconds:
|
||||
# Not an error, but log a warning - the region will be clamped
|
||||
logger.warning(
|
||||
f"Region {i}: end_seconds ({region.end_seconds}) exceeds "
|
||||
f"audio duration ({total_duration_seconds}), will be clamped"
|
||||
)
|
||||
|
||||
return errors
|
||||
@@ -0,0 +1,681 @@
|
||||
"""
|
||||
Audio search service for finding and downloading audio files.
|
||||
|
||||
This service integrates with karaoke_gen.audio_fetcher (which wraps flacfetch)
|
||||
to search for audio from various sources (YouTube, music trackers, etc.)
|
||||
and download the selected audio file.
|
||||
|
||||
This is a thin wrapper that adds backend-specific functionality:
|
||||
- Caching raw results for API-based selection flow
|
||||
- Firestore-compatible serialization
|
||||
- Singleton pattern for service lifecycle
|
||||
- Remote flacfetch service integration for torrent downloads
|
||||
|
||||
When FLACFETCH_API_URL is configured, this service uses the remote flacfetch
|
||||
HTTP API for search and download operations. This is required for torrent
|
||||
downloads since Cloud Run doesn't support BitTorrent peer connections.
|
||||
"""
|
||||
import asyncio
|
||||
import logging
|
||||
import os
|
||||
from typing import List, Optional
|
||||
|
||||
import nest_asyncio
|
||||
|
||||
# Import shared classes from karaoke_gen.audio_fetcher - single source of truth
|
||||
# Note: Import directly from audio_fetcher module, not karaoke_gen.__init__
|
||||
# to avoid pulling in heavier dependencies like lyrics_transcriber
|
||||
from karaoke_gen.audio_fetcher import (
|
||||
FlacFetcher,
|
||||
AudioSearchResult,
|
||||
AudioFetchResult,
|
||||
AudioFetcherError,
|
||||
NoResultsError,
|
||||
DownloadError,
|
||||
)
|
||||
|
||||
from .flacfetch_client import get_flacfetch_client, FlacfetchServiceError
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
# Re-export exception under backend's naming convention for compatibility
|
||||
AudioSearchError = AudioFetcherError
|
||||
|
||||
|
||||
# Also alias AudioFetchResult as AudioDownloadResult for backwards compatibility
|
||||
AudioDownloadResult = AudioFetchResult
|
||||
|
||||
|
||||
class AudioSearchService:
|
||||
"""
|
||||
Service for searching and downloading audio files.
|
||||
|
||||
This is a thin wrapper around karaoke_gen.audio_fetcher.FlacFetcher that adds
|
||||
backend-specific functionality:
|
||||
- Caches raw results for API-based selection (client picks by index)
|
||||
- Provides Firestore-compatible serialization
|
||||
- Manages service lifecycle as singleton
|
||||
- Remote flacfetch service integration for torrent downloads
|
||||
|
||||
When FLACFETCH_API_URL is configured, this service uses the remote flacfetch
|
||||
HTTP API for search and download operations. This enables torrent downloads
|
||||
which are not possible in Cloud Run due to network restrictions.
|
||||
|
||||
The actual flacfetch integration is in karaoke_gen.audio_fetcher.FlacFetcher,
|
||||
which is shared between local CLI and cloud backend.
|
||||
"""
|
||||
|
||||
# Sentinel value to indicate "use environment variable"
|
||||
_USE_ENV = object()
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
red_api_key: Optional[str] = _USE_ENV,
|
||||
red_api_url: Optional[str] = _USE_ENV,
|
||||
ops_api_key: Optional[str] = _USE_ENV,
|
||||
ops_api_url: Optional[str] = _USE_ENV,
|
||||
):
|
||||
"""
|
||||
Initialize the audio search service.
|
||||
|
||||
Args:
|
||||
red_api_key: API key for RED tracker (optional, uses env if not provided)
|
||||
red_api_url: Base URL for RED tracker API (optional, uses env if not provided)
|
||||
ops_api_key: API key for OPS tracker (optional, uses env if not provided)
|
||||
ops_api_url: Base URL for OPS tracker API (optional, uses env if not provided)
|
||||
"""
|
||||
# Use environment variables if not explicitly provided
|
||||
if red_api_key is self._USE_ENV:
|
||||
red_api_key = os.environ.get("RED_API_KEY")
|
||||
if red_api_url is self._USE_ENV:
|
||||
red_api_url = os.environ.get("RED_API_URL")
|
||||
|
||||
if ops_api_key is self._USE_ENV:
|
||||
ops_api_key = os.environ.get("OPS_API_KEY")
|
||||
if ops_api_url is self._USE_ENV:
|
||||
ops_api_url = os.environ.get("OPS_API_URL")
|
||||
|
||||
# Check for remote flacfetch client
|
||||
self._remote_client = get_flacfetch_client()
|
||||
|
||||
# Log which mode we're using
|
||||
if self._remote_client:
|
||||
logger.info("AudioSearchService using REMOTE flacfetch service (torrent downloads enabled)")
|
||||
else:
|
||||
logger.info("AudioSearchService using LOCAL flacfetch (YouTube only in Cloud Run)")
|
||||
|
||||
# Delegate to shared FlacFetcher implementation (for local mode or fallback)
|
||||
self._fetcher = FlacFetcher(
|
||||
red_api_key=red_api_key,
|
||||
red_api_url=red_api_url,
|
||||
ops_api_key=ops_api_key,
|
||||
ops_api_url=ops_api_url,
|
||||
)
|
||||
|
||||
# Cache search results for API-based selection flow
|
||||
# Key: index, Value: AudioSearchResult (with raw_result)
|
||||
self._cached_results: List[AudioSearchResult] = []
|
||||
|
||||
# Cache for remote search results (search_id -> results)
|
||||
self._remote_search_id: Optional[str] = None
|
||||
|
||||
def search(self, artist: str, title: str) -> List[AudioSearchResult]:
|
||||
"""
|
||||
Search for audio matching the given artist and title.
|
||||
|
||||
Results are cached internally for later download via download().
|
||||
|
||||
If a remote flacfetch service is configured (FLACFETCH_API_URL), uses that
|
||||
for better torrent download support. Otherwise falls back to local flacfetch.
|
||||
|
||||
Args:
|
||||
artist: The artist name to search for
|
||||
title: The track title to search for
|
||||
|
||||
Returns:
|
||||
List of AudioSearchResult objects
|
||||
|
||||
Raises:
|
||||
NoResultsError: If no results are found
|
||||
AudioSearchError: For other errors (e.g., flacfetch not installed)
|
||||
"""
|
||||
try:
|
||||
# Try remote flacfetch service first if configured
|
||||
if self._remote_client:
|
||||
return self._search_remote(artist, title)
|
||||
|
||||
# Fallback to local flacfetch
|
||||
results = self._fetcher.search(artist, title)
|
||||
|
||||
# Cache results for later download
|
||||
self._cached_results = results
|
||||
self._remote_search_id = None
|
||||
|
||||
logger.info(f"Found {len(results)} results for: {artist} - {title}")
|
||||
return results
|
||||
|
||||
except (NoResultsError, AudioFetcherError):
|
||||
# Re-raise these as-is
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Search failed: {e}")
|
||||
raise AudioSearchError(f"Search failed: {e}") from e
|
||||
|
||||
def _search_remote(self, artist: str, title: str) -> List[AudioSearchResult]:
|
||||
"""
|
||||
Search using the remote flacfetch service.
|
||||
|
||||
Runs async code in a sync context for compatibility with existing API.
|
||||
"""
|
||||
try:
|
||||
# Enable nested event loops (needed when called from FastAPI async context)
|
||||
# Apply to the current loop if one exists, otherwise it's a no-op
|
||||
try:
|
||||
loop = asyncio.get_running_loop()
|
||||
nest_asyncio.apply(loop)
|
||||
except RuntimeError:
|
||||
pass # No running loop, nest_asyncio not needed
|
||||
|
||||
# Run async search in sync context
|
||||
loop = asyncio.new_event_loop()
|
||||
asyncio.set_event_loop(loop)
|
||||
try:
|
||||
response = loop.run_until_complete(
|
||||
self._remote_client.search(artist, title)
|
||||
)
|
||||
finally:
|
||||
loop.close()
|
||||
|
||||
# Check for empty results
|
||||
if not response.get("results"):
|
||||
raise NoResultsError(f"No results found for: {artist} - {title}")
|
||||
|
||||
# Store search_id for download
|
||||
self._remote_search_id = response.get("search_id")
|
||||
|
||||
# Convert remote results to AudioSearchResult objects
|
||||
results = []
|
||||
for item in response.get("results", []):
|
||||
result = AudioSearchResult(
|
||||
title=item.get("title", "Unknown"),
|
||||
artist=item.get("artist", "Unknown"),
|
||||
url=item.get("download_url", ""), # May be empty for remote
|
||||
provider=item.get("provider", "Unknown"),
|
||||
duration=item.get("duration_seconds"),
|
||||
quality=item.get("quality", ""),
|
||||
source_id=item.get("info_hash"),
|
||||
index=item.get("index", 0),
|
||||
seeders=item.get("seeders"),
|
||||
target_file=item.get("target_file"),
|
||||
# Store full remote data in raw_result for rich display
|
||||
raw_result=item,
|
||||
)
|
||||
results.append(result)
|
||||
|
||||
# Cache results
|
||||
self._cached_results = results
|
||||
|
||||
logger.info(f"Found {len(results)} results from remote flacfetch for: {artist} - {title}")
|
||||
return results
|
||||
|
||||
except FlacfetchServiceError as e:
|
||||
logger.warning(f"Remote flacfetch search failed, falling back to local: {e}")
|
||||
# Fallback to local search
|
||||
self._remote_search_id = None
|
||||
results = self._fetcher.search(artist, title)
|
||||
self._cached_results = results
|
||||
return results
|
||||
|
||||
def select_best(self, results: List[AudioSearchResult]) -> int:
|
||||
"""
|
||||
Select the best result from a list of search results.
|
||||
|
||||
Uses flacfetch's built-in quality ranking to select the best source.
|
||||
|
||||
Args:
|
||||
results: List of search results
|
||||
|
||||
Returns:
|
||||
Index of the best result
|
||||
"""
|
||||
return self._fetcher.select_best(results)
|
||||
|
||||
def download(
|
||||
self,
|
||||
result_index: int,
|
||||
output_dir: str,
|
||||
output_filename: Optional[str] = None,
|
||||
gcs_path: Optional[str] = None,
|
||||
remote_search_id: Optional[str] = None,
|
||||
) -> AudioDownloadResult:
|
||||
"""
|
||||
Download audio from a cached search result.
|
||||
|
||||
This method uses the cached results from the last search() call.
|
||||
The API flow is:
|
||||
1. Client calls search() -> gets list of results
|
||||
2. Client picks an index
|
||||
3. Client calls download(index) -> gets downloaded file
|
||||
|
||||
If a remote flacfetch service is configured and the search was performed
|
||||
remotely (for torrent sources), uses the remote service for download.
|
||||
|
||||
Args:
|
||||
result_index: Index of the result to download (from search results)
|
||||
output_dir: Directory to save the downloaded file
|
||||
output_filename: Optional filename (without extension)
|
||||
gcs_path: Optional GCS path for remote uploads (e.g., "uploads/job123/audio/")
|
||||
remote_search_id: Optional search_id for remote downloads. If provided,
|
||||
uses this instead of the cached _remote_search_id. This is important
|
||||
for concurrent requests where the service-level cache may be stale.
|
||||
|
||||
Returns:
|
||||
AudioDownloadResult with the downloaded file path
|
||||
|
||||
Raises:
|
||||
DownloadError: If download fails or no cached result for index
|
||||
"""
|
||||
if result_index < 0 or result_index >= len(self._cached_results):
|
||||
raise DownloadError(
|
||||
f"No cached result for index {result_index}. "
|
||||
f"Available indices: 0-{len(self._cached_results) - 1}. "
|
||||
"Run search() first."
|
||||
)
|
||||
|
||||
result = self._cached_results[result_index]
|
||||
|
||||
logger.info(f"Downloading: {result.artist} - {result.title} from {result.provider}")
|
||||
|
||||
# Use provided search_id or fall back to service-level cache
|
||||
effective_search_id = remote_search_id or self._remote_search_id
|
||||
|
||||
# Check if this was a remote search (torrent sources need remote download)
|
||||
if effective_search_id and self._remote_client:
|
||||
# Check if this is a torrent source that needs remote handling
|
||||
is_torrent = result.provider in ["RED", "OPS"]
|
||||
|
||||
if is_torrent:
|
||||
return self._download_remote(result_index, output_dir, output_filename, gcs_path, effective_search_id)
|
||||
|
||||
# Delegate to shared FlacFetcher (local download)
|
||||
fetch_result = self._fetcher.download(result, output_dir, output_filename)
|
||||
|
||||
logger.info(f"Downloaded to: {fetch_result.filepath}")
|
||||
|
||||
return fetch_result
|
||||
|
||||
def download_by_id(
|
||||
self,
|
||||
source_name: str,
|
||||
source_id: str,
|
||||
output_dir: str,
|
||||
output_filename: Optional[str] = None,
|
||||
target_file: Optional[str] = None,
|
||||
download_url: Optional[str] = None,
|
||||
gcs_path: Optional[str] = None,
|
||||
) -> AudioDownloadResult:
|
||||
"""
|
||||
Download audio directly by source ID (no prior search required).
|
||||
|
||||
This is the preferred method when you have stored the source_id from a
|
||||
previous search and want to download later without re-searching. This
|
||||
avoids unnecessary API calls to private trackers.
|
||||
|
||||
Args:
|
||||
source_name: Provider name (RED, OPS, YouTube, Spotify)
|
||||
source_id: Source-specific ID (torrent ID, video ID, track ID)
|
||||
output_dir: Directory to save the downloaded file
|
||||
output_filename: Optional filename (without extension)
|
||||
target_file: For torrents, specific file to extract from the torrent
|
||||
download_url: For YouTube/Spotify, direct URL (optional)
|
||||
gcs_path: Optional GCS path for remote uploads
|
||||
|
||||
Returns:
|
||||
AudioDownloadResult with the downloaded file path
|
||||
|
||||
Raises:
|
||||
DownloadError: If download fails
|
||||
"""
|
||||
logger.info(f"Download by ID: {source_name} ID={source_id}")
|
||||
|
||||
# For torrent sources, must use remote client
|
||||
if source_name in ["RED", "OPS"]:
|
||||
if not self._remote_client:
|
||||
raise DownloadError(
|
||||
f"Cannot download from {source_name} without remote flacfetch service"
|
||||
)
|
||||
return self._download_by_id_remote(
|
||||
source_name=source_name,
|
||||
source_id=source_id,
|
||||
output_dir=output_dir,
|
||||
output_filename=output_filename,
|
||||
target_file=target_file,
|
||||
download_url=download_url,
|
||||
gcs_path=gcs_path,
|
||||
)
|
||||
|
||||
# For YouTube/Spotify, can use local flacfetch via FetchManager.download_by_id
|
||||
# But we currently only have remote support, so use remote if available
|
||||
if self._remote_client:
|
||||
return self._download_by_id_remote(
|
||||
source_name=source_name,
|
||||
source_id=source_id,
|
||||
output_dir=output_dir,
|
||||
output_filename=output_filename,
|
||||
target_file=target_file,
|
||||
download_url=download_url,
|
||||
gcs_path=gcs_path,
|
||||
)
|
||||
|
||||
# Local download for YouTube/Spotify (fallback)
|
||||
# Use the local fetcher's download_by_id if available
|
||||
raise DownloadError(
|
||||
f"Local download_by_id not yet implemented for {source_name}. "
|
||||
"Configure FLACFETCH_API_URL for remote downloads."
|
||||
)
|
||||
|
||||
def _download_by_id_remote(
|
||||
self,
|
||||
source_name: str,
|
||||
source_id: str,
|
||||
output_dir: str, # Not used for remote downloads (files go to GCS or remote server)
|
||||
output_filename: Optional[str] = None,
|
||||
target_file: Optional[str] = None,
|
||||
download_url: Optional[str] = None,
|
||||
gcs_path: Optional[str] = None,
|
||||
) -> AudioDownloadResult:
|
||||
"""
|
||||
Download by ID using the remote flacfetch service.
|
||||
|
||||
Note: output_dir is accepted for API compatibility but ignored for remote
|
||||
downloads. Remote downloads either go to GCS (if gcs_path is set) or to
|
||||
the remote server's download directory.
|
||||
"""
|
||||
# output_dir is intentionally unused - remote downloads don't use local paths
|
||||
_ = output_dir
|
||||
try:
|
||||
# Enable nested event loops
|
||||
try:
|
||||
running_loop = asyncio.get_running_loop()
|
||||
nest_asyncio.apply(running_loop)
|
||||
except RuntimeError:
|
||||
pass
|
||||
|
||||
loop = asyncio.new_event_loop()
|
||||
asyncio.set_event_loop(loop)
|
||||
try:
|
||||
# Start download
|
||||
download_id = loop.run_until_complete(
|
||||
self._remote_client.download_by_id(
|
||||
source_name=source_name,
|
||||
source_id=source_id,
|
||||
output_filename=output_filename,
|
||||
target_file=target_file,
|
||||
download_url=download_url,
|
||||
gcs_path=gcs_path,
|
||||
)
|
||||
)
|
||||
|
||||
logger.info(f"Remote download by ID started: {download_id}")
|
||||
|
||||
# Wait for completion
|
||||
def log_progress(status):
|
||||
progress = status.get("progress", 0)
|
||||
speed = status.get("download_speed_kbps", 0)
|
||||
logger.debug(f"Download progress: {progress:.1f}% ({speed:.1f} KB/s)")
|
||||
|
||||
final_status = loop.run_until_complete(
|
||||
self._remote_client.wait_for_download(
|
||||
download_id,
|
||||
timeout=600,
|
||||
progress_callback=log_progress,
|
||||
)
|
||||
)
|
||||
finally:
|
||||
loop.close()
|
||||
|
||||
# Determine file path
|
||||
filepath = final_status.get("gcs_path") or final_status.get("output_path")
|
||||
|
||||
if not filepath:
|
||||
raise DownloadError("Remote download completed but no file path returned")
|
||||
|
||||
logger.info(f"Remote download by ID complete: {filepath}")
|
||||
|
||||
return AudioDownloadResult(
|
||||
filepath=filepath,
|
||||
artist="", # Not available without search
|
||||
title="", # Not available without search
|
||||
provider=source_name,
|
||||
quality="", # Not available without search
|
||||
)
|
||||
|
||||
except FlacfetchServiceError as e:
|
||||
raise DownloadError(f"Remote download by ID failed: {e}") from e
|
||||
except Exception as e:
|
||||
logger.error(f"Remote download by ID error: {e}")
|
||||
raise DownloadError(f"Remote download by ID failed: {e}") from e
|
||||
|
||||
def _download_remote(
|
||||
self,
|
||||
result_index: int,
|
||||
output_dir: str,
|
||||
output_filename: Optional[str] = None,
|
||||
gcs_path: Optional[str] = None,
|
||||
search_id: Optional[str] = None,
|
||||
) -> AudioDownloadResult:
|
||||
"""
|
||||
Download using the remote flacfetch service.
|
||||
|
||||
The remote service downloads via torrent and optionally uploads to GCS.
|
||||
|
||||
Args:
|
||||
result_index: Index of the result to download
|
||||
output_dir: Directory to save downloaded file
|
||||
output_filename: Optional filename
|
||||
gcs_path: Optional GCS path for remote uploads
|
||||
search_id: Remote search ID to use (overrides self._remote_search_id)
|
||||
"""
|
||||
effective_search_id = search_id or self._remote_search_id
|
||||
if not effective_search_id:
|
||||
raise DownloadError("No remote search ID - run search() first")
|
||||
|
||||
result = self._cached_results[result_index]
|
||||
|
||||
try:
|
||||
# Enable nested event loops (needed when called from FastAPI async context)
|
||||
try:
|
||||
running_loop = asyncio.get_running_loop()
|
||||
nest_asyncio.apply(running_loop)
|
||||
except RuntimeError:
|
||||
pass # No running loop, nest_asyncio not needed
|
||||
|
||||
loop = asyncio.new_event_loop()
|
||||
asyncio.set_event_loop(loop)
|
||||
try:
|
||||
# Start download
|
||||
download_id = loop.run_until_complete(
|
||||
self._remote_client.download(
|
||||
search_id=effective_search_id,
|
||||
result_index=result_index,
|
||||
output_filename=output_filename,
|
||||
gcs_path=gcs_path,
|
||||
)
|
||||
)
|
||||
|
||||
logger.info(f"Remote download started: {download_id}")
|
||||
|
||||
# Wait for completion with progress logging
|
||||
def log_progress(status):
|
||||
progress = status.get("progress", 0)
|
||||
speed = status.get("download_speed_kbps", 0)
|
||||
logger.debug(f"Download progress: {progress:.1f}% ({speed:.1f} KB/s)")
|
||||
|
||||
final_status = loop.run_until_complete(
|
||||
self._remote_client.wait_for_download(
|
||||
download_id,
|
||||
timeout=600, # 10 minute timeout
|
||||
progress_callback=log_progress,
|
||||
)
|
||||
)
|
||||
finally:
|
||||
loop.close()
|
||||
|
||||
# Determine file path
|
||||
filepath = final_status.get("gcs_path") or final_status.get("output_path")
|
||||
|
||||
if not filepath:
|
||||
raise DownloadError("Remote download completed but no file path returned")
|
||||
|
||||
logger.info(f"Remote download complete: {filepath}")
|
||||
|
||||
return AudioDownloadResult(
|
||||
filepath=filepath,
|
||||
artist=result.artist,
|
||||
title=result.title,
|
||||
provider=result.provider,
|
||||
quality=result.quality,
|
||||
)
|
||||
|
||||
except FlacfetchServiceError as e:
|
||||
raise DownloadError(f"Remote download failed: {e}") from e
|
||||
except Exception as e:
|
||||
logger.error(f"Remote download error: {e}")
|
||||
raise DownloadError(f"Remote download failed: {e}") from e
|
||||
|
||||
def search_and_download_auto(
|
||||
self,
|
||||
artist: str,
|
||||
title: str,
|
||||
output_dir: str,
|
||||
output_filename: Optional[str] = None,
|
||||
gcs_path: Optional[str] = None,
|
||||
) -> AudioDownloadResult:
|
||||
"""
|
||||
Search for audio and automatically download the best result.
|
||||
|
||||
This is a convenience method that combines search(), select_best(),
|
||||
and download() for automated/non-interactive usage.
|
||||
|
||||
Args:
|
||||
artist: The artist name to search for
|
||||
title: The track title to search for
|
||||
output_dir: Directory to save the downloaded file
|
||||
output_filename: Optional filename (without extension)
|
||||
gcs_path: Optional GCS path for remote uploads
|
||||
|
||||
Returns:
|
||||
AudioDownloadResult with the downloaded file path
|
||||
|
||||
Raises:
|
||||
NoResultsError: If no results are found
|
||||
DownloadError: If download fails
|
||||
"""
|
||||
# Search
|
||||
results = self.search(artist, title)
|
||||
|
||||
# Select best
|
||||
best_index = self.select_best(results)
|
||||
best_result = results[best_index]
|
||||
logger.info(
|
||||
f"Auto-selected result {best_index}: "
|
||||
f"{best_result.artist} - {best_result.title} ({best_result.provider})"
|
||||
)
|
||||
|
||||
# Download
|
||||
return self.download(best_index, output_dir, output_filename, gcs_path)
|
||||
|
||||
async def search_async(self, artist: str, title: str) -> List[AudioSearchResult]:
|
||||
"""
|
||||
Async version of search for use in async routes.
|
||||
|
||||
Note: Currently wraps sync search in executor. Future optimization
|
||||
could make this fully async.
|
||||
"""
|
||||
loop = asyncio.get_event_loop()
|
||||
return await loop.run_in_executor(None, self.search, artist, title)
|
||||
|
||||
async def download_async(
|
||||
self,
|
||||
result_index: int,
|
||||
output_dir: str,
|
||||
output_filename: Optional[str] = None,
|
||||
gcs_path: Optional[str] = None,
|
||||
remote_search_id: Optional[str] = None,
|
||||
) -> AudioDownloadResult:
|
||||
"""
|
||||
Async version of download for use in async routes.
|
||||
|
||||
Note: Currently wraps sync download in executor. Future optimization
|
||||
could make this fully async.
|
||||
"""
|
||||
loop = asyncio.get_event_loop()
|
||||
return await loop.run_in_executor(
|
||||
None,
|
||||
lambda: self.download(result_index, output_dir, output_filename, gcs_path, remote_search_id)
|
||||
)
|
||||
|
||||
async def download_by_id_async(
|
||||
self,
|
||||
source_name: str,
|
||||
source_id: str,
|
||||
output_dir: str,
|
||||
output_filename: Optional[str] = None,
|
||||
target_file: Optional[str] = None,
|
||||
download_url: Optional[str] = None,
|
||||
gcs_path: Optional[str] = None,
|
||||
) -> AudioDownloadResult:
|
||||
"""
|
||||
Async version of download_by_id for use in async routes.
|
||||
"""
|
||||
loop = asyncio.get_event_loop()
|
||||
return await loop.run_in_executor(
|
||||
None,
|
||||
lambda: self.download_by_id(
|
||||
source_name, source_id, output_dir, output_filename,
|
||||
target_file, download_url, gcs_path
|
||||
)
|
||||
)
|
||||
|
||||
def is_remote_enabled(self) -> bool:
|
||||
"""Check if remote flacfetch service is configured."""
|
||||
return self._remote_client is not None
|
||||
|
||||
@property
|
||||
def last_remote_search_id(self) -> Optional[str]:
|
||||
"""Get the search_id from the last remote search.
|
||||
|
||||
This should be stored in job state_data after search and passed
|
||||
back to download() to ensure correct remote download handling.
|
||||
"""
|
||||
return self._remote_search_id
|
||||
|
||||
async def check_remote_health(self) -> Optional[dict]:
|
||||
"""
|
||||
Check health of remote flacfetch service.
|
||||
|
||||
Returns:
|
||||
Health status dict if remote service is configured and healthy,
|
||||
None if not configured or unhealthy.
|
||||
"""
|
||||
if not self._remote_client:
|
||||
return None
|
||||
|
||||
try:
|
||||
return await self._remote_client.health_check()
|
||||
except Exception as e:
|
||||
logger.warning(f"Remote flacfetch health check failed: {e}")
|
||||
return None
|
||||
|
||||
|
||||
# Singleton instance
|
||||
_audio_search_service: Optional[AudioSearchService] = None
|
||||
|
||||
|
||||
def get_audio_search_service() -> AudioSearchService:
|
||||
"""Get the singleton AudioSearchService instance."""
|
||||
global _audio_search_service
|
||||
if _audio_search_service is None:
|
||||
_audio_search_service = AudioSearchService()
|
||||
return _audio_search_service
|
||||
@@ -68,6 +68,16 @@ class AuthService:
|
||||
logger.info("Admin token validated")
|
||||
return True, UserType.ADMIN, -1, "Admin access granted"
|
||||
|
||||
# Debug: Log token comparison info (only first/last few chars for security)
|
||||
if self.admin_tokens:
|
||||
expected_prefix = self.admin_tokens[0][:8] if len(self.admin_tokens[0]) >= 8 else self.admin_tokens[0]
|
||||
provided_prefix = token[:8] if len(token) >= 8 else token
|
||||
logger.debug(
|
||||
f"Token mismatch: expected prefix '{expected_prefix}...', "
|
||||
f"got '{provided_prefix}...', "
|
||||
f"expected len={len(self.admin_tokens[0])}, got len={len(token)}"
|
||||
)
|
||||
|
||||
# Check stored tokens in Firestore
|
||||
token_data = self.firestore.get_token(token)
|
||||
|
||||
|
||||
@@ -0,0 +1,473 @@
|
||||
"""
|
||||
Client for the remote flacfetch HTTP API service.
|
||||
|
||||
This client communicates with a dedicated flacfetch VM that handles:
|
||||
- BitTorrent downloads from private trackers (RED, OPS)
|
||||
- YouTube downloads
|
||||
- GCS uploads of downloaded files
|
||||
|
||||
The flacfetch service provides:
|
||||
- Full peer connectivity for torrents (not possible in Cloud Run)
|
||||
- Indefinite seeding of completed torrents
|
||||
- Automatic disk cleanup
|
||||
|
||||
Usage:
|
||||
client = get_flacfetch_client()
|
||||
if client:
|
||||
# Search for audio
|
||||
search_result = await client.search("ABBA", "Waterloo")
|
||||
|
||||
# Download the best result
|
||||
download_id = await client.download(
|
||||
search_id=search_result["search_id"],
|
||||
result_index=0,
|
||||
gcs_path="uploads/job123/audio/",
|
||||
)
|
||||
|
||||
# Wait for completion
|
||||
result = await client.wait_for_download(download_id)
|
||||
print(f"Downloaded to: {result['gcs_path']}")
|
||||
"""
|
||||
import asyncio
|
||||
import logging
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
import httpx
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class FlacfetchServiceError(Exception):
|
||||
"""Error communicating with or returned from flacfetch service."""
|
||||
pass
|
||||
|
||||
|
||||
class FlacfetchClient:
|
||||
"""
|
||||
Client for remote flacfetch HTTP API.
|
||||
|
||||
All endpoints require authentication via X-API-Key header.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
base_url: str,
|
||||
api_key: str,
|
||||
timeout: int = 60,
|
||||
):
|
||||
"""
|
||||
Initialize flacfetch client.
|
||||
|
||||
Args:
|
||||
base_url: Base URL of flacfetch service (e.g., http://10.0.0.5:8080)
|
||||
api_key: API key for authentication
|
||||
timeout: Default request timeout in seconds
|
||||
"""
|
||||
self.base_url = base_url.rstrip('/')
|
||||
self.api_key = api_key
|
||||
self.timeout = timeout
|
||||
logger.info(f"FlacfetchClient initialized with base_url={self.base_url}")
|
||||
|
||||
def _headers(self) -> Dict[str, str]:
|
||||
"""Get request headers with authentication."""
|
||||
return {
|
||||
"X-API-Key": self.api_key,
|
||||
"Content-Type": "application/json",
|
||||
}
|
||||
|
||||
async def health_check(self) -> Dict[str, Any]:
|
||||
"""
|
||||
Check if flacfetch service is healthy.
|
||||
|
||||
Returns:
|
||||
Health status dict with transmission, disk, and provider info
|
||||
|
||||
Raises:
|
||||
FlacfetchServiceError: If service is unhealthy or unreachable
|
||||
"""
|
||||
try:
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.get(
|
||||
f"{self.base_url}/health",
|
||||
headers=self._headers(),
|
||||
timeout=10,
|
||||
)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
|
||||
if data.get("status") not in ["healthy", "degraded"]:
|
||||
raise FlacfetchServiceError(f"Service unhealthy: {data}")
|
||||
|
||||
return data
|
||||
except httpx.RequestError as e:
|
||||
raise FlacfetchServiceError(f"Cannot reach flacfetch service: {e}")
|
||||
except httpx.HTTPStatusError as e:
|
||||
raise FlacfetchServiceError(f"Health check failed: {e.response.status_code}")
|
||||
|
||||
async def search(
|
||||
self,
|
||||
artist: str,
|
||||
title: str,
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Search for audio matching artist and title.
|
||||
|
||||
Args:
|
||||
artist: Artist name
|
||||
title: Track title
|
||||
|
||||
Returns:
|
||||
Search response dict with search_id and results list
|
||||
|
||||
Raises:
|
||||
FlacfetchServiceError: On search failure
|
||||
"""
|
||||
try:
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.post(
|
||||
f"{self.base_url}/search",
|
||||
headers=self._headers(),
|
||||
json={"artist": artist, "title": title},
|
||||
timeout=self.timeout,
|
||||
)
|
||||
|
||||
if resp.status_code == 404:
|
||||
# No results found - return empty results
|
||||
return {
|
||||
"search_id": None,
|
||||
"artist": artist,
|
||||
"title": title,
|
||||
"results": [],
|
||||
"results_count": 0,
|
||||
}
|
||||
|
||||
resp.raise_for_status()
|
||||
return resp.json()
|
||||
|
||||
except httpx.RequestError as e:
|
||||
raise FlacfetchServiceError(f"Search request failed: {e}")
|
||||
except httpx.HTTPStatusError as e:
|
||||
raise FlacfetchServiceError(f"Search failed: {e.response.status_code} - {e.response.text}")
|
||||
|
||||
async def download(
|
||||
self,
|
||||
search_id: str,
|
||||
result_index: int,
|
||||
output_filename: Optional[str] = None,
|
||||
gcs_path: Optional[str] = None,
|
||||
) -> str:
|
||||
"""
|
||||
Start downloading an audio file.
|
||||
|
||||
Args:
|
||||
search_id: Search ID from previous search
|
||||
result_index: Index of result to download
|
||||
output_filename: Optional custom filename (without extension)
|
||||
gcs_path: GCS path for upload (e.g., "uploads/job123/audio/")
|
||||
|
||||
Returns:
|
||||
Download ID for tracking progress
|
||||
|
||||
Raises:
|
||||
FlacfetchServiceError: On download start failure
|
||||
"""
|
||||
try:
|
||||
async with httpx.AsyncClient() as client:
|
||||
payload = {
|
||||
"search_id": search_id,
|
||||
"result_index": result_index,
|
||||
}
|
||||
if output_filename:
|
||||
payload["output_filename"] = output_filename
|
||||
if gcs_path:
|
||||
payload["upload_to_gcs"] = True
|
||||
payload["gcs_path"] = gcs_path
|
||||
|
||||
resp = await client.post(
|
||||
f"{self.base_url}/download",
|
||||
headers=self._headers(),
|
||||
json=payload,
|
||||
timeout=self.timeout,
|
||||
)
|
||||
resp.raise_for_status()
|
||||
|
||||
data = resp.json()
|
||||
return data["download_id"]
|
||||
|
||||
except httpx.RequestError as e:
|
||||
raise FlacfetchServiceError(f"Download request failed: {e}")
|
||||
except httpx.HTTPStatusError as e:
|
||||
raise FlacfetchServiceError(f"Download start failed: {e.response.status_code} - {e.response.text}")
|
||||
|
||||
async def download_by_id(
|
||||
self,
|
||||
source_name: str,
|
||||
source_id: str,
|
||||
output_filename: Optional[str] = None,
|
||||
target_file: Optional[str] = None,
|
||||
download_url: Optional[str] = None,
|
||||
gcs_path: Optional[str] = None,
|
||||
) -> str:
|
||||
"""
|
||||
Start downloading directly by source ID (no prior search required).
|
||||
|
||||
This is useful when you have stored the source_id from a previous search
|
||||
and want to download later without re-searching.
|
||||
|
||||
Args:
|
||||
source_name: Provider name (RED, OPS, YouTube, Spotify)
|
||||
source_id: Source-specific ID (torrent ID, video ID, track ID)
|
||||
output_filename: Optional custom filename (without extension)
|
||||
target_file: For torrents, specific file to extract
|
||||
download_url: For YouTube/Spotify, direct URL (optional)
|
||||
gcs_path: GCS path for upload (e.g., "uploads/job123/audio/")
|
||||
|
||||
Returns:
|
||||
Download ID for tracking progress
|
||||
|
||||
Raises:
|
||||
FlacfetchServiceError: On download start failure
|
||||
"""
|
||||
try:
|
||||
async with httpx.AsyncClient() as client:
|
||||
payload = {
|
||||
"source_name": source_name,
|
||||
"source_id": source_id,
|
||||
}
|
||||
if output_filename:
|
||||
payload["output_filename"] = output_filename
|
||||
if target_file:
|
||||
payload["target_file"] = target_file
|
||||
if download_url:
|
||||
payload["download_url"] = download_url
|
||||
if gcs_path:
|
||||
payload["upload_to_gcs"] = True
|
||||
payload["gcs_path"] = gcs_path
|
||||
|
||||
resp = await client.post(
|
||||
f"{self.base_url}/download-by-id",
|
||||
headers=self._headers(),
|
||||
json=payload,
|
||||
timeout=self.timeout,
|
||||
)
|
||||
resp.raise_for_status()
|
||||
|
||||
data = resp.json()
|
||||
return data["download_id"]
|
||||
|
||||
except httpx.RequestError as e:
|
||||
raise FlacfetchServiceError(f"Download by ID request failed: {e}")
|
||||
except httpx.HTTPStatusError as e:
|
||||
raise FlacfetchServiceError(f"Download by ID failed: {e.response.status_code} - {e.response.text}")
|
||||
|
||||
async def get_download_status(self, download_id: str) -> Dict[str, Any]:
|
||||
"""
|
||||
Get the current status of a download.
|
||||
|
||||
Args:
|
||||
download_id: Download ID from start_download
|
||||
|
||||
Returns:
|
||||
Status dict with progress, speed, path info
|
||||
|
||||
Raises:
|
||||
FlacfetchServiceError: On status check failure
|
||||
"""
|
||||
try:
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.get(
|
||||
f"{self.base_url}/download/{download_id}/status",
|
||||
headers=self._headers(),
|
||||
timeout=10,
|
||||
)
|
||||
resp.raise_for_status()
|
||||
return resp.json()
|
||||
|
||||
except httpx.RequestError as e:
|
||||
raise FlacfetchServiceError(f"Status request failed: {e}")
|
||||
except httpx.HTTPStatusError as e:
|
||||
if e.response.status_code == 404:
|
||||
raise FlacfetchServiceError(f"Download not found: {download_id}")
|
||||
raise FlacfetchServiceError(f"Status check failed: {e.response.status_code}")
|
||||
|
||||
async def wait_for_download(
|
||||
self,
|
||||
download_id: str,
|
||||
timeout: int = 600,
|
||||
poll_interval: float = 2.0,
|
||||
progress_callback: Optional[callable] = None,
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Wait for a download to complete.
|
||||
|
||||
Args:
|
||||
download_id: Download ID to wait for
|
||||
timeout: Maximum wait time in seconds
|
||||
poll_interval: Time between status checks
|
||||
progress_callback: Optional callback(status_dict) for progress updates
|
||||
|
||||
Returns:
|
||||
Final status dict with output_path or gcs_path
|
||||
|
||||
Raises:
|
||||
FlacfetchServiceError: On download failure or timeout
|
||||
"""
|
||||
elapsed = 0.0
|
||||
|
||||
while elapsed < timeout:
|
||||
status = await self.get_download_status(download_id)
|
||||
|
||||
if progress_callback:
|
||||
try:
|
||||
progress_callback(status)
|
||||
except Exception as e:
|
||||
logger.warning(f"Progress callback error: {e}")
|
||||
|
||||
download_status = status.get("status")
|
||||
|
||||
if download_status in ["complete", "seeding"]:
|
||||
logger.info(f"Download {download_id} complete: {status.get('gcs_path') or status.get('output_path')}")
|
||||
return status
|
||||
elif download_status == "failed":
|
||||
error = status.get("error", "Unknown error")
|
||||
raise FlacfetchServiceError(f"Download failed: {error}")
|
||||
elif download_status == "cancelled":
|
||||
raise FlacfetchServiceError("Download was cancelled")
|
||||
|
||||
# Log progress
|
||||
progress = status.get("progress", 0)
|
||||
speed = status.get("download_speed_kbps", 0)
|
||||
peers = status.get("peers", 0)
|
||||
logger.debug(
|
||||
f"Download {download_id}: {progress:.1f}% "
|
||||
f"({speed:.1f} KB/s, {peers} peers)"
|
||||
)
|
||||
|
||||
await asyncio.sleep(poll_interval)
|
||||
elapsed += poll_interval
|
||||
|
||||
raise FlacfetchServiceError(f"Download timed out after {timeout}s")
|
||||
|
||||
async def list_torrents(self) -> Dict[str, Any]:
|
||||
"""
|
||||
List all torrents in Transmission.
|
||||
|
||||
Returns:
|
||||
Torrent list response with torrent info and totals
|
||||
"""
|
||||
try:
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.get(
|
||||
f"{self.base_url}/torrents",
|
||||
headers=self._headers(),
|
||||
timeout=30,
|
||||
)
|
||||
resp.raise_for_status()
|
||||
return resp.json()
|
||||
|
||||
except httpx.RequestError as e:
|
||||
raise FlacfetchServiceError(f"List torrents failed: {e}")
|
||||
except httpx.HTTPStatusError as e:
|
||||
raise FlacfetchServiceError(f"List torrents failed: {e.response.status_code}")
|
||||
|
||||
async def delete_torrent(
|
||||
self,
|
||||
torrent_id: int,
|
||||
delete_data: bool = True,
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Delete a torrent from Transmission.
|
||||
|
||||
Args:
|
||||
torrent_id: Transmission torrent ID
|
||||
delete_data: Also delete downloaded files
|
||||
|
||||
Returns:
|
||||
Delete response
|
||||
"""
|
||||
try:
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.delete(
|
||||
f"{self.base_url}/torrents/{torrent_id}",
|
||||
headers=self._headers(),
|
||||
params={"delete_data": str(delete_data).lower()},
|
||||
timeout=30,
|
||||
)
|
||||
resp.raise_for_status()
|
||||
return resp.json()
|
||||
|
||||
except httpx.RequestError as e:
|
||||
raise FlacfetchServiceError(f"Delete torrent failed: {e}")
|
||||
except httpx.HTTPStatusError as e:
|
||||
raise FlacfetchServiceError(f"Delete torrent failed: {e.response.status_code}")
|
||||
|
||||
async def cleanup_torrents(
|
||||
self,
|
||||
strategy: str = "oldest",
|
||||
target_free_gb: float = 10.0,
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Trigger disk cleanup.
|
||||
|
||||
Args:
|
||||
strategy: Cleanup strategy (oldest, largest, lowest_ratio)
|
||||
target_free_gb: Target free space to achieve
|
||||
|
||||
Returns:
|
||||
Cleanup response with removed count and freed space
|
||||
"""
|
||||
try:
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.post(
|
||||
f"{self.base_url}/torrents/cleanup",
|
||||
headers=self._headers(),
|
||||
json={
|
||||
"strategy": strategy,
|
||||
"target_free_gb": target_free_gb,
|
||||
},
|
||||
timeout=60,
|
||||
)
|
||||
resp.raise_for_status()
|
||||
return resp.json()
|
||||
|
||||
except httpx.RequestError as e:
|
||||
raise FlacfetchServiceError(f"Cleanup failed: {e}")
|
||||
except httpx.HTTPStatusError as e:
|
||||
raise FlacfetchServiceError(f"Cleanup failed: {e.response.status_code}")
|
||||
|
||||
|
||||
# Singleton client instance
|
||||
_client: Optional[FlacfetchClient] = None
|
||||
|
||||
|
||||
def get_flacfetch_client() -> Optional[FlacfetchClient]:
|
||||
"""
|
||||
Get the flacfetch client if configured.
|
||||
|
||||
Returns:
|
||||
FlacfetchClient instance if FLACFETCH_API_URL and FLACFETCH_API_KEY are set,
|
||||
None otherwise (indicating local-only mode).
|
||||
"""
|
||||
global _client
|
||||
|
||||
if _client is None:
|
||||
from backend.config import get_settings
|
||||
settings = get_settings()
|
||||
|
||||
if settings.flacfetch_api_url and settings.flacfetch_api_key:
|
||||
_client = FlacfetchClient(
|
||||
base_url=settings.flacfetch_api_url,
|
||||
api_key=settings.flacfetch_api_key,
|
||||
)
|
||||
logger.info("FlacfetchClient initialized for remote service")
|
||||
else:
|
||||
logger.debug("FlacfetchClient not configured (missing URL or API key)")
|
||||
|
||||
return _client
|
||||
|
||||
|
||||
def reset_flacfetch_client():
|
||||
"""Reset the singleton client (for testing)."""
|
||||
global _client
|
||||
_client = None
|
||||
|
||||
@@ -138,7 +138,7 @@ def job_log_context(
|
||||
Args:
|
||||
job_id: Job ID to associate logs with
|
||||
worker: Worker name for log categorization
|
||||
logger_names: List of logger names to capture (None = capture root + common loggers)
|
||||
logger_names: List of logger names to capture (None = capture common loggers)
|
||||
min_level: Minimum log level to capture
|
||||
|
||||
Usage:
|
||||
@@ -147,14 +147,13 @@ def job_log_context(
|
||||
correction_operations.add_lyrics_source(...)
|
||||
"""
|
||||
# Default loggers to capture - these cover most of our processing
|
||||
# Note: We intentionally DON'T include the root logger ('') to avoid
|
||||
# duplicate log entries since logs propagate up the logger hierarchy.
|
||||
# Only capture at the top-level package loggers.
|
||||
if logger_names is None:
|
||||
logger_names = [
|
||||
'', # Root logger
|
||||
'backend.api.routes.review',
|
||||
'lyrics_transcriber',
|
||||
'lyrics_transcriber.correction',
|
||||
'lyrics_transcriber.correction.anchor_sequence',
|
||||
'lyrics_transcriber.correction.corrector',
|
||||
'karaoke_gen',
|
||||
]
|
||||
|
||||
|
||||
@@ -53,8 +53,23 @@ class JobManager:
|
||||
enable_txt=job_create.enable_txt,
|
||||
enable_youtube_upload=job_create.enable_youtube_upload,
|
||||
youtube_description=job_create.youtube_description,
|
||||
youtube_description_template=job_create.youtube_description_template, # video_worker reads this
|
||||
webhook_url=job_create.webhook_url,
|
||||
user_email=job_create.user_email,
|
||||
# Distribution settings
|
||||
brand_prefix=job_create.brand_prefix,
|
||||
discord_webhook_url=job_create.discord_webhook_url,
|
||||
dropbox_path=job_create.dropbox_path,
|
||||
gdrive_folder_id=job_create.gdrive_folder_id,
|
||||
# Theme configuration
|
||||
theme_id=job_create.theme_id,
|
||||
color_overrides=job_create.color_overrides,
|
||||
style_params_gcs_path=job_create.style_params_gcs_path,
|
||||
style_assets=job_create.style_assets,
|
||||
# Two-phase workflow (Batch 6)
|
||||
prep_only=job_create.prep_only,
|
||||
finalise_only=job_create.finalise_only,
|
||||
keep_brand_code=job_create.keep_brand_code,
|
||||
# Request metadata (for tracking and filtering)
|
||||
request_metadata=job_create.request_metadata,
|
||||
)
|
||||
@@ -276,6 +291,24 @@ class JobManager:
|
||||
if progress is not None:
|
||||
updates['progress'] = progress
|
||||
|
||||
# Generate review token when entering AWAITING_REVIEW state
|
||||
if new_status == JobStatus.AWAITING_REVIEW:
|
||||
from backend.api.dependencies import generate_review_token, get_review_token_expiry
|
||||
review_token = generate_review_token()
|
||||
review_token_expires = get_review_token_expiry(hours=48) # 48 hour expiry
|
||||
updates['review_token'] = review_token
|
||||
updates['review_token_expires_at'] = review_token_expires
|
||||
logger.info(f"Generated review token for job {job_id}, expires in 48 hours")
|
||||
|
||||
# Generate instrumental token when entering AWAITING_INSTRUMENTAL_SELECTION state
|
||||
if new_status == JobStatus.AWAITING_INSTRUMENTAL_SELECTION:
|
||||
from backend.api.dependencies import generate_review_token, get_review_token_expiry
|
||||
instrumental_token = generate_review_token() # Reuse same token generator
|
||||
instrumental_token_expires = get_review_token_expiry(hours=48) # 48 hour expiry
|
||||
updates['instrumental_token'] = instrumental_token
|
||||
updates['instrumental_token_expires_at'] = instrumental_token_expires
|
||||
logger.info(f"Generated instrumental token for job {job_id}, expires in 48 hours")
|
||||
|
||||
# If we have state_data_updates, merge them with existing state_data
|
||||
merged_state_data = None
|
||||
if state_data_updates:
|
||||
@@ -300,6 +333,20 @@ class JobManager:
|
||||
message=message
|
||||
)
|
||||
|
||||
# Apply review token update separately if generated
|
||||
if new_status == JobStatus.AWAITING_REVIEW and 'review_token' in updates:
|
||||
self.firestore.update_job(job_id, {
|
||||
'review_token': updates['review_token'],
|
||||
'review_token_expires_at': updates['review_token_expires_at']
|
||||
})
|
||||
|
||||
# Apply instrumental token update separately if generated
|
||||
if new_status == JobStatus.AWAITING_INSTRUMENTAL_SELECTION and 'instrumental_token' in updates:
|
||||
self.firestore.update_job(job_id, {
|
||||
'instrumental_token': updates['instrumental_token'],
|
||||
'instrumental_token_expires_at': updates['instrumental_token_expires_at']
|
||||
})
|
||||
|
||||
logger.info(f"Job {job_id} transitioned to {new_status}")
|
||||
return True
|
||||
|
||||
|
||||
@@ -0,0 +1,413 @@
|
||||
"""
|
||||
Custom metrics for Cloud Monitoring.
|
||||
|
||||
This module provides application-level metrics for tracking job processing,
|
||||
worker performance, and external API usage. Metrics can be viewed in:
|
||||
1. Cloud Logging (via structured log entries)
|
||||
2. Cloud Monitoring (via log-based metrics or OpenTelemetry)
|
||||
|
||||
The metrics service uses a pragmatic approach:
|
||||
- Always emits metrics as structured log entries (works immediately)
|
||||
- Uses the same JSON format as Cloud Logging
|
||||
- Can be enhanced with OpenTelemetry metrics exporters when available
|
||||
|
||||
Usage:
|
||||
from backend.services.metrics import metrics
|
||||
|
||||
# Record a job completion
|
||||
metrics.record_job_completed("abc123", source="upload")
|
||||
|
||||
# Record worker duration
|
||||
metrics.record_worker_duration("audio", 45.2, success=True)
|
||||
|
||||
# Record external API call
|
||||
with metrics.time_external_api("modal"):
|
||||
response = await modal_client.separate_audio(...)
|
||||
"""
|
||||
import logging
|
||||
import time
|
||||
from contextlib import contextmanager
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
from backend.services.tracing import get_current_trace_id, get_current_span_id
|
||||
|
||||
|
||||
logger = logging.getLogger("metrics")
|
||||
|
||||
|
||||
@dataclass
|
||||
class MetricLabels:
|
||||
"""Common metric labels."""
|
||||
job_id: Optional[str] = None
|
||||
worker: Optional[str] = None
|
||||
status: Optional[str] = None
|
||||
source: Optional[str] = None
|
||||
api: Optional[str] = None
|
||||
operation: Optional[str] = None
|
||||
bucket: Optional[str] = None
|
||||
|
||||
def to_dict(self) -> Dict[str, Any]:
|
||||
"""Convert to dict, excluding None values."""
|
||||
return {k: v for k, v in self.__dict__.items() if v is not None}
|
||||
|
||||
|
||||
class MetricsService:
|
||||
"""
|
||||
Application metrics service.
|
||||
|
||||
Emits metrics as structured log entries that can be:
|
||||
1. Queried directly in Cloud Logging
|
||||
2. Converted to Cloud Monitoring metrics via log-based metrics
|
||||
3. Exported via OpenTelemetry (when configured)
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the metrics service."""
|
||||
self._logger = logging.getLogger("metrics")
|
||||
# Ensure metrics logger outputs at INFO level
|
||||
self._logger.setLevel(logging.INFO)
|
||||
|
||||
def _emit_metric(self, metric_name: str, metric_type: str, value: float, labels: Dict[str, Any]) -> None:
|
||||
"""
|
||||
Emit a metric as a structured log entry.
|
||||
|
||||
The log format is designed to be easily parsed by Cloud Logging
|
||||
and converted to log-based metrics.
|
||||
|
||||
Args:
|
||||
metric_name: Name of the metric (e.g., "jobs_total")
|
||||
metric_type: Type of metric (counter, histogram, gauge)
|
||||
value: Metric value
|
||||
labels: Metric labels/dimensions
|
||||
"""
|
||||
# Add trace context if available
|
||||
trace_id = get_current_trace_id()
|
||||
span_id = get_current_span_id()
|
||||
|
||||
# Build metric entry
|
||||
metric_entry = {
|
||||
"metric_name": metric_name,
|
||||
"metric_type": metric_type,
|
||||
"metric_value": value,
|
||||
**labels,
|
||||
}
|
||||
|
||||
if trace_id:
|
||||
metric_entry["trace_id"] = trace_id
|
||||
if span_id:
|
||||
metric_entry["span_id"] = span_id
|
||||
|
||||
# Emit as structured log entry
|
||||
# Use INFO level so metrics always show up
|
||||
self._logger.info(
|
||||
f"METRIC {metric_name}={value}",
|
||||
extra=metric_entry
|
||||
)
|
||||
|
||||
# =========================================
|
||||
# Job Metrics
|
||||
# =========================================
|
||||
|
||||
def record_job_created(self, job_id: str, source: str = "unknown") -> None:
|
||||
"""
|
||||
Record a new job creation.
|
||||
|
||||
Args:
|
||||
job_id: Job ID
|
||||
source: Job source (upload, url, search)
|
||||
"""
|
||||
self._emit_metric(
|
||||
metric_name="jobs_total",
|
||||
metric_type="counter",
|
||||
value=1,
|
||||
labels={"job_id": job_id, "status": "created", "source": source}
|
||||
)
|
||||
|
||||
def record_job_completed(self, job_id: str, source: str = "unknown") -> None:
|
||||
"""
|
||||
Record a job completion.
|
||||
|
||||
Args:
|
||||
job_id: Job ID
|
||||
source: Job source (upload, url, search)
|
||||
"""
|
||||
self._emit_metric(
|
||||
metric_name="jobs_total",
|
||||
metric_type="counter",
|
||||
value=1,
|
||||
labels={"job_id": job_id, "status": "completed", "source": source}
|
||||
)
|
||||
|
||||
def record_job_failed(self, job_id: str, source: str = "unknown", error: Optional[str] = None) -> None:
|
||||
"""
|
||||
Record a job failure.
|
||||
|
||||
Args:
|
||||
job_id: Job ID
|
||||
source: Job source (upload, url, search)
|
||||
error: Optional error message
|
||||
"""
|
||||
labels = {"job_id": job_id, "status": "failed", "source": source}
|
||||
if error:
|
||||
labels["error"] = error[:200] # Truncate long errors
|
||||
self._emit_metric(
|
||||
metric_name="jobs_total",
|
||||
metric_type="counter",
|
||||
value=1,
|
||||
labels=labels
|
||||
)
|
||||
|
||||
def record_job_duration(self, job_id: str, duration_seconds: float, source: str = "unknown") -> None:
|
||||
"""
|
||||
Record total job processing duration.
|
||||
|
||||
Args:
|
||||
job_id: Job ID
|
||||
duration_seconds: Total processing time in seconds
|
||||
source: Job source (upload, url, search)
|
||||
"""
|
||||
self._emit_metric(
|
||||
metric_name="job_duration_seconds",
|
||||
metric_type="histogram",
|
||||
value=duration_seconds,
|
||||
labels={"job_id": job_id, "source": source}
|
||||
)
|
||||
|
||||
# =========================================
|
||||
# Worker Metrics
|
||||
# =========================================
|
||||
|
||||
def record_worker_started(self, worker: str, job_id: str) -> None:
|
||||
"""
|
||||
Record a worker invocation start.
|
||||
|
||||
Args:
|
||||
worker: Worker name (audio, lyrics, screens, video, render_video)
|
||||
job_id: Job ID
|
||||
"""
|
||||
self._emit_metric(
|
||||
metric_name="worker_invocations_total",
|
||||
metric_type="counter",
|
||||
value=1,
|
||||
labels={"worker": worker, "job_id": job_id, "status": "started"}
|
||||
)
|
||||
|
||||
def record_worker_duration(self, worker: str, duration_seconds: float, success: bool, job_id: Optional[str] = None) -> None:
|
||||
"""
|
||||
Record worker processing duration.
|
||||
|
||||
Args:
|
||||
worker: Worker name
|
||||
duration_seconds: Processing time in seconds
|
||||
success: Whether worker completed successfully
|
||||
job_id: Optional job ID
|
||||
"""
|
||||
labels = {
|
||||
"worker": worker,
|
||||
"success": str(success).lower(),
|
||||
}
|
||||
if job_id:
|
||||
labels["job_id"] = job_id
|
||||
|
||||
self._emit_metric(
|
||||
metric_name="job_stage_duration_seconds",
|
||||
metric_type="histogram",
|
||||
value=duration_seconds,
|
||||
labels=labels
|
||||
)
|
||||
|
||||
# Also emit a counter for success/failure tracking
|
||||
self._emit_metric(
|
||||
metric_name="worker_invocations_total",
|
||||
metric_type="counter",
|
||||
value=1,
|
||||
labels={"worker": worker, "success": str(success).lower(), "job_id": job_id or "unknown"}
|
||||
)
|
||||
|
||||
# =========================================
|
||||
# GCS Metrics
|
||||
# =========================================
|
||||
|
||||
def record_gcs_operation(
|
||||
self,
|
||||
operation: str,
|
||||
bucket: str,
|
||||
success: bool,
|
||||
size_bytes: Optional[int] = None,
|
||||
duration_seconds: Optional[float] = None,
|
||||
job_id: Optional[str] = None,
|
||||
) -> None:
|
||||
"""
|
||||
Record a GCS operation.
|
||||
|
||||
Args:
|
||||
operation: Operation type (upload, download, delete)
|
||||
bucket: GCS bucket name
|
||||
success: Whether operation succeeded
|
||||
size_bytes: Optional file size in bytes
|
||||
duration_seconds: Optional operation duration
|
||||
job_id: Optional job ID
|
||||
"""
|
||||
labels = {
|
||||
"operation": operation,
|
||||
"bucket": bucket,
|
||||
"success": str(success).lower(),
|
||||
}
|
||||
if job_id:
|
||||
labels["job_id"] = job_id
|
||||
|
||||
self._emit_metric(
|
||||
metric_name="gcs_operations_total",
|
||||
metric_type="counter",
|
||||
value=1,
|
||||
labels=labels
|
||||
)
|
||||
|
||||
if size_bytes is not None:
|
||||
self._emit_metric(
|
||||
metric_name="gcs_operation_bytes",
|
||||
metric_type="histogram",
|
||||
value=size_bytes,
|
||||
labels={**labels, "operation": operation}
|
||||
)
|
||||
|
||||
if duration_seconds is not None:
|
||||
self._emit_metric(
|
||||
metric_name="gcs_operation_duration_seconds",
|
||||
metric_type="histogram",
|
||||
value=duration_seconds,
|
||||
labels={**labels, "operation": operation}
|
||||
)
|
||||
|
||||
# =========================================
|
||||
# External API Metrics
|
||||
# =========================================
|
||||
|
||||
def record_external_api_call(
|
||||
self,
|
||||
api: str,
|
||||
success: bool,
|
||||
duration_seconds: float,
|
||||
job_id: Optional[str] = None,
|
||||
error: Optional[str] = None,
|
||||
) -> None:
|
||||
"""
|
||||
Record an external API call.
|
||||
|
||||
Args:
|
||||
api: API name (modal, audioshake, genius, spotify)
|
||||
success: Whether call succeeded
|
||||
duration_seconds: API call duration
|
||||
job_id: Optional job ID
|
||||
error: Optional error message
|
||||
"""
|
||||
labels = {
|
||||
"api": api,
|
||||
"success": str(success).lower(),
|
||||
}
|
||||
if job_id:
|
||||
labels["job_id"] = job_id
|
||||
if error:
|
||||
labels["error"] = error[:100] # Truncate
|
||||
|
||||
self._emit_metric(
|
||||
metric_name="external_api_calls_total",
|
||||
metric_type="counter",
|
||||
value=1,
|
||||
labels=labels
|
||||
)
|
||||
|
||||
self._emit_metric(
|
||||
metric_name="external_api_duration_seconds",
|
||||
metric_type="histogram",
|
||||
value=duration_seconds,
|
||||
labels={"api": api, "success": str(success).lower()}
|
||||
)
|
||||
|
||||
@contextmanager
|
||||
def time_external_api(self, api: str, job_id: Optional[str] = None):
|
||||
"""
|
||||
Context manager to time an external API call.
|
||||
|
||||
Usage:
|
||||
with metrics.time_external_api("modal", job_id) as timer:
|
||||
response = await client.call_api()
|
||||
timer.set_success(True)
|
||||
|
||||
Args:
|
||||
api: API name
|
||||
job_id: Optional job ID
|
||||
|
||||
Yields:
|
||||
Timer object with set_success() method
|
||||
"""
|
||||
timer = _ApiTimer()
|
||||
start_time = time.time()
|
||||
|
||||
try:
|
||||
yield timer
|
||||
except Exception as e:
|
||||
timer.set_success(False)
|
||||
timer.error = str(e)
|
||||
raise
|
||||
finally:
|
||||
duration = time.time() - start_time
|
||||
self.record_external_api_call(
|
||||
api=api,
|
||||
success=timer.success,
|
||||
duration_seconds=duration,
|
||||
job_id=job_id,
|
||||
error=timer.error,
|
||||
)
|
||||
|
||||
@contextmanager
|
||||
def time_worker(self, worker: str, job_id: str):
|
||||
"""
|
||||
Context manager to time a worker execution.
|
||||
|
||||
Usage:
|
||||
with metrics.time_worker("audio", job_id) as timer:
|
||||
await process_audio()
|
||||
timer.set_success(True)
|
||||
|
||||
Args:
|
||||
worker: Worker name
|
||||
job_id: Job ID
|
||||
|
||||
Yields:
|
||||
Timer object with set_success() method
|
||||
"""
|
||||
timer = _ApiTimer()
|
||||
self.record_worker_started(worker, job_id)
|
||||
start_time = time.time()
|
||||
|
||||
try:
|
||||
yield timer
|
||||
except Exception as e:
|
||||
timer.set_success(False)
|
||||
raise
|
||||
finally:
|
||||
duration = time.time() - start_time
|
||||
self.record_worker_duration(
|
||||
worker=worker,
|
||||
duration_seconds=duration,
|
||||
success=timer.success,
|
||||
job_id=job_id,
|
||||
)
|
||||
|
||||
|
||||
class _ApiTimer:
|
||||
"""Helper class for tracking API call success state."""
|
||||
|
||||
def __init__(self):
|
||||
self.success = True # Assume success unless set otherwise
|
||||
self.error: Optional[str] = None
|
||||
|
||||
def set_success(self, success: bool) -> None:
|
||||
self.success = success
|
||||
|
||||
|
||||
# Global metrics instance
|
||||
metrics = MetricsService()
|
||||
|
||||
@@ -65,6 +65,26 @@ class StorageService:
|
||||
a private key available. Requires the service account to have
|
||||
roles/iam.serviceAccountTokenCreator on itself.
|
||||
"""
|
||||
return self._generate_signed_url_internal(blob_path, "GET", expiration_minutes)
|
||||
|
||||
def generate_signed_upload_url(self, blob_path: str, content_type: str = "application/octet-stream", expiration_minutes: int = 60) -> str:
|
||||
"""Generate a signed URL for uploading a file directly to GCS.
|
||||
|
||||
This allows clients to upload files directly to GCS without going through
|
||||
the backend, bypassing any request body size limits.
|
||||
|
||||
Args:
|
||||
blob_path: The destination path in GCS
|
||||
content_type: The expected content type of the upload
|
||||
expiration_minutes: How long the URL is valid for
|
||||
|
||||
Returns:
|
||||
A signed URL that accepts PUT requests with the file content
|
||||
"""
|
||||
return self._generate_signed_url_internal(blob_path, "PUT", expiration_minutes, content_type)
|
||||
|
||||
def _generate_signed_url_internal(self, blob_path: str, method: str, expiration_minutes: int = 60, content_type: Optional[str] = None) -> str:
|
||||
"""Internal method to generate signed URLs for GET or PUT operations."""
|
||||
import google.auth
|
||||
from google.auth.transport import requests
|
||||
|
||||
@@ -74,6 +94,17 @@ class StorageService:
|
||||
# Get default credentials and refresh to ensure we have a valid token
|
||||
credentials, project = google.auth.default()
|
||||
|
||||
# Common kwargs for signed URL generation
|
||||
kwargs = {
|
||||
"version": "v4",
|
||||
"expiration": timedelta(minutes=expiration_minutes),
|
||||
"method": method,
|
||||
}
|
||||
|
||||
# For PUT requests, we need to specify the content type in headers
|
||||
if method == "PUT" and content_type:
|
||||
kwargs["headers"] = {"Content-Type": content_type}
|
||||
|
||||
# Check if we're using compute credentials (Cloud Run/GCE)
|
||||
# These need to use IAM signBlob via service_account_email + access_token
|
||||
if hasattr(credentials, 'service_account_email'):
|
||||
@@ -81,25 +112,15 @@ class StorageService:
|
||||
auth_request = requests.Request()
|
||||
credentials.refresh(auth_request)
|
||||
|
||||
url = blob.generate_signed_url(
|
||||
version="v4",
|
||||
expiration=timedelta(minutes=expiration_minutes),
|
||||
method="GET",
|
||||
service_account_email=credentials.service_account_email,
|
||||
access_token=credentials.token
|
||||
)
|
||||
else:
|
||||
# Local development with service account key or user credentials
|
||||
url = blob.generate_signed_url(
|
||||
version="v4",
|
||||
expiration=timedelta(minutes=expiration_minutes),
|
||||
method="GET"
|
||||
)
|
||||
kwargs["service_account_email"] = credentials.service_account_email
|
||||
kwargs["access_token"] = credentials.token
|
||||
|
||||
logger.info(f"Generated signed URL for {blob_path}")
|
||||
url = blob.generate_signed_url(**kwargs)
|
||||
|
||||
logger.info(f"Generated signed {method} URL for {blob_path}")
|
||||
return url
|
||||
except Exception as e:
|
||||
logger.error(f"Error generating signed URL for {blob_path}: {e}")
|
||||
logger.error(f"Error generating signed {method} URL for {blob_path}: {e}")
|
||||
raise
|
||||
|
||||
def delete_file(self, blob_path: str) -> None:
|
||||
|
||||
@@ -0,0 +1,246 @@
|
||||
"""
|
||||
Structured logging with trace correlation for Cloud Logging.
|
||||
|
||||
This module provides JSON-formatted logging that integrates with Google Cloud Logging
|
||||
and correlates logs with OpenTelemetry traces in Cloud Trace.
|
||||
|
||||
When running in Cloud Run:
|
||||
- Logs are output as JSON for Cloud Logging to parse
|
||||
- Each log entry includes trace ID and span ID for correlation
|
||||
- Custom fields (job_id, worker) are preserved in the log structure
|
||||
|
||||
Usage:
|
||||
# In main.py, before any logging:
|
||||
from backend.services.structured_logging import setup_structured_logging
|
||||
setup_structured_logging()
|
||||
|
||||
# Then use standard logging:
|
||||
logger = logging.getLogger(__name__)
|
||||
logger.info("Processing started", extra={"job_id": "abc123"})
|
||||
"""
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
from datetime import datetime
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
|
||||
# Cloud Logging severity mapping (compatible with GCP)
|
||||
# https://cloud.google.com/logging/docs/reference/v2/rest/v2/LogEntry#LogSeverity
|
||||
SEVERITY_MAP = {
|
||||
"DEBUG": "DEBUG",
|
||||
"INFO": "INFO",
|
||||
"WARNING": "WARNING",
|
||||
"ERROR": "ERROR",
|
||||
"CRITICAL": "CRITICAL",
|
||||
}
|
||||
|
||||
|
||||
class StructuredFormatter(logging.Formatter):
|
||||
"""
|
||||
JSON formatter with trace correlation for Google Cloud Logging.
|
||||
|
||||
Produces log entries in the format expected by Cloud Logging, including:
|
||||
- logging.googleapis.com/trace: Links to Cloud Trace
|
||||
- logging.googleapis.com/spanId: Current span ID
|
||||
- severity: Cloud Logging severity level
|
||||
- Custom fields passed via 'extra' dict
|
||||
"""
|
||||
|
||||
def __init__(self, project_id: Optional[str] = None):
|
||||
"""
|
||||
Initialize the structured formatter.
|
||||
|
||||
Args:
|
||||
project_id: GCP project ID for trace URLs (auto-detected if not provided)
|
||||
"""
|
||||
super().__init__()
|
||||
self.project_id = project_id or os.environ.get("GOOGLE_CLOUD_PROJECT") or os.environ.get("GCP_PROJECT")
|
||||
|
||||
def format(self, record: logging.LogRecord) -> str:
|
||||
"""
|
||||
Format a log record as JSON.
|
||||
|
||||
Args:
|
||||
record: The log record to format
|
||||
|
||||
Returns:
|
||||
JSON string for Cloud Logging
|
||||
"""
|
||||
from backend.services.tracing import get_current_trace_id, get_current_span_id
|
||||
|
||||
# Build base log entry
|
||||
log_entry: Dict[str, Any] = {
|
||||
"timestamp": datetime.utcfromtimestamp(record.created).isoformat() + "Z",
|
||||
"severity": SEVERITY_MAP.get(record.levelname, record.levelname),
|
||||
"message": record.getMessage(),
|
||||
"logger": record.name,
|
||||
}
|
||||
|
||||
# Add trace correlation if available
|
||||
trace_id = get_current_trace_id()
|
||||
span_id = get_current_span_id()
|
||||
|
||||
if trace_id and self.project_id:
|
||||
# Format for Cloud Logging trace correlation
|
||||
log_entry["logging.googleapis.com/trace"] = f"projects/{self.project_id}/traces/{trace_id}"
|
||||
|
||||
if span_id:
|
||||
log_entry["logging.googleapis.com/spanId"] = span_id
|
||||
|
||||
# Add custom fields from 'extra' dict
|
||||
# Common fields we want to extract from log records
|
||||
custom_fields = ["job_id", "worker", "operation", "duration", "status", "error"]
|
||||
for field in custom_fields:
|
||||
value = getattr(record, field, None)
|
||||
if value is not None:
|
||||
log_entry[field] = value
|
||||
|
||||
# Add source location for debugging
|
||||
if record.pathname and record.lineno:
|
||||
log_entry["logging.googleapis.com/sourceLocation"] = {
|
||||
"file": record.pathname,
|
||||
"line": record.lineno,
|
||||
"function": record.funcName,
|
||||
}
|
||||
|
||||
# Add exception info if present
|
||||
if record.exc_info:
|
||||
log_entry["exception"] = self.formatException(record.exc_info)
|
||||
|
||||
# Remove None values for cleaner output
|
||||
return json.dumps({k: v for k, v in log_entry.items() if v is not None})
|
||||
|
||||
|
||||
class HumanReadableFormatter(logging.Formatter):
|
||||
"""
|
||||
Human-readable formatter for local development.
|
||||
|
||||
Includes trace context when available but outputs in traditional format.
|
||||
"""
|
||||
|
||||
def format(self, record: logging.LogRecord) -> str:
|
||||
"""Format a log record for human readability."""
|
||||
from backend.services.tracing import get_current_trace_id
|
||||
|
||||
# Build base message
|
||||
timestamp = datetime.utcfromtimestamp(record.created).strftime("%Y-%m-%d %H:%M:%S")
|
||||
|
||||
# Add job_id prefix if available
|
||||
job_id = getattr(record, "job_id", None)
|
||||
job_prefix = f"[job:{job_id[:8]}] " if job_id else ""
|
||||
|
||||
# Add trace ID suffix if available
|
||||
trace_id = get_current_trace_id()
|
||||
trace_suffix = f" [trace:{trace_id[:8]}]" if trace_id else ""
|
||||
|
||||
message = f"{timestamp} - {record.name} - {record.levelname} - {job_prefix}{record.getMessage()}{trace_suffix}"
|
||||
|
||||
# Add exception info if present
|
||||
if record.exc_info:
|
||||
message += "\n" + self.formatException(record.exc_info)
|
||||
|
||||
return message
|
||||
|
||||
|
||||
def is_cloud_run() -> bool:
|
||||
"""Check if we're running in Cloud Run."""
|
||||
return os.environ.get("K_SERVICE") is not None
|
||||
|
||||
|
||||
def setup_structured_logging(force_json: bool = False, log_level: Optional[str] = None) -> None:
|
||||
"""
|
||||
Configure structured logging for the application.
|
||||
|
||||
In Cloud Run: Uses JSON format with trace correlation for Cloud Logging
|
||||
In development: Uses human-readable format with optional trace context
|
||||
|
||||
Args:
|
||||
force_json: Force JSON output even in development
|
||||
log_level: Override log level (default from settings or INFO)
|
||||
"""
|
||||
from backend.config import settings
|
||||
|
||||
# Determine log level
|
||||
level = log_level or getattr(settings, "log_level", "INFO")
|
||||
level = getattr(logging, level.upper(), logging.INFO)
|
||||
|
||||
# Choose formatter based on environment
|
||||
if is_cloud_run() or force_json:
|
||||
formatter = StructuredFormatter()
|
||||
else:
|
||||
formatter = HumanReadableFormatter()
|
||||
|
||||
# Create handler
|
||||
handler = logging.StreamHandler(sys.stdout)
|
||||
handler.setFormatter(formatter)
|
||||
handler.setLevel(level)
|
||||
|
||||
# Configure root logger
|
||||
root_logger = logging.getLogger()
|
||||
root_logger.setLevel(level)
|
||||
|
||||
# Remove existing handlers and add our handler
|
||||
root_logger.handlers = [handler]
|
||||
|
||||
# Also configure uvicorn loggers to use our format
|
||||
for logger_name in ["uvicorn", "uvicorn.access", "uvicorn.error"]:
|
||||
logger = logging.getLogger(logger_name)
|
||||
logger.handlers = [handler]
|
||||
logger.propagate = False
|
||||
|
||||
|
||||
class JobLogAdapter(logging.LoggerAdapter):
|
||||
"""
|
||||
Logger adapter that automatically adds job context to log records.
|
||||
|
||||
Usage:
|
||||
logger = logging.getLogger(__name__)
|
||||
job_logger = JobLogAdapter(logger, job_id="abc123", worker="audio")
|
||||
job_logger.info("Processing started") # Automatically includes job_id and worker
|
||||
"""
|
||||
|
||||
def __init__(self, logger: logging.Logger, job_id: str, worker: Optional[str] = None, **extra):
|
||||
"""
|
||||
Initialize the adapter.
|
||||
|
||||
Args:
|
||||
logger: Base logger instance
|
||||
job_id: Job ID to include in all log records
|
||||
worker: Optional worker name
|
||||
**extra: Additional fields to include in all log records
|
||||
"""
|
||||
super().__init__(logger, {"job_id": job_id, "worker": worker, **extra})
|
||||
|
||||
def process(self, msg: str, kwargs: Dict[str, Any]) -> tuple:
|
||||
"""Process a logging call to add extra context."""
|
||||
# Merge extra dict from adapter with any extra passed to the log call
|
||||
extra = kwargs.get("extra", {})
|
||||
extra.update(self.extra)
|
||||
kwargs["extra"] = extra
|
||||
return msg, kwargs
|
||||
|
||||
|
||||
def get_job_logger(job_id: str, worker: Optional[str] = None, name: Optional[str] = None) -> JobLogAdapter:
|
||||
"""
|
||||
Get a logger adapter configured for a specific job.
|
||||
|
||||
This is a convenience function for creating job-specific loggers.
|
||||
|
||||
Args:
|
||||
job_id: Job ID to include in all log records
|
||||
worker: Optional worker name
|
||||
name: Logger name (defaults to "job")
|
||||
|
||||
Returns:
|
||||
JobLogAdapter configured for the job
|
||||
|
||||
Usage:
|
||||
logger = get_job_logger("abc123", "audio")
|
||||
logger.info("Starting audio separation")
|
||||
logger.error("Failed to process", extra={"error": str(e)})
|
||||
"""
|
||||
base_logger = logging.getLogger(name or "job")
|
||||
return JobLogAdapter(base_logger, job_id=job_id, worker=worker)
|
||||
|
||||
@@ -0,0 +1,469 @@
|
||||
"""
|
||||
Theme service for managing pre-created style themes.
|
||||
|
||||
Themes are stored in GCS at themes/{theme_id}/ with:
|
||||
- style_params.json: Complete style configuration
|
||||
- preview.png: Preview image for theme selection UI
|
||||
- youtube_description.txt: Optional YouTube description template
|
||||
- assets/: Fonts, backgrounds, and other assets
|
||||
|
||||
The service provides:
|
||||
- Theme listing with signed preview URLs
|
||||
- Theme detail retrieval
|
||||
- Color override application
|
||||
- Job style preparation (copying theme to job folder)
|
||||
"""
|
||||
|
||||
import copy
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import tempfile
|
||||
import threading
|
||||
from datetime import datetime, timedelta
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
|
||||
from backend.models.theme import (
|
||||
ColorOverrides,
|
||||
ThemeDetail,
|
||||
ThemeMetadata,
|
||||
ThemeRegistry,
|
||||
ThemeSummary,
|
||||
hex_to_rgba,
|
||||
)
|
||||
from backend.services.storage_service import StorageService
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# GCS paths for themes
|
||||
THEMES_PREFIX = "themes"
|
||||
METADATA_FILE = f"{THEMES_PREFIX}/_metadata.json"
|
||||
|
||||
|
||||
class ThemeService:
|
||||
"""Service for managing themes from GCS."""
|
||||
|
||||
def __init__(self, storage: Optional[StorageService] = None):
|
||||
"""
|
||||
Initialize the theme service.
|
||||
|
||||
Args:
|
||||
storage: StorageService instance (creates new one if not provided)
|
||||
"""
|
||||
self.storage = storage or StorageService()
|
||||
self._metadata_cache: Optional[ThemeRegistry] = None
|
||||
self._cache_time: Optional[datetime] = None
|
||||
self.CACHE_TTL_SECONDS = 300 # 5 minute cache for theme metadata
|
||||
|
||||
def _get_theme_path(self, theme_id: str, filename: str = "") -> str:
|
||||
"""Get the GCS path for a theme file."""
|
||||
if filename:
|
||||
return f"{THEMES_PREFIX}/{theme_id}/{filename}"
|
||||
return f"{THEMES_PREFIX}/{theme_id}"
|
||||
|
||||
def _is_cache_valid(self) -> bool:
|
||||
"""Check if the metadata cache is still valid."""
|
||||
if self._metadata_cache is None or self._cache_time is None:
|
||||
return False
|
||||
age = datetime.now() - self._cache_time
|
||||
return age.total_seconds() < self.CACHE_TTL_SECONDS
|
||||
|
||||
def _load_metadata(self, force_refresh: bool = False) -> ThemeRegistry:
|
||||
"""
|
||||
Load theme metadata from GCS with caching.
|
||||
|
||||
Args:
|
||||
force_refresh: Force reload from GCS even if cache is valid
|
||||
|
||||
Returns:
|
||||
ThemeRegistry containing all theme metadata
|
||||
"""
|
||||
if not force_refresh and self._is_cache_valid():
|
||||
return self._metadata_cache # type: ignore
|
||||
|
||||
try:
|
||||
data = self.storage.download_json(METADATA_FILE)
|
||||
self._metadata_cache = ThemeRegistry(**data)
|
||||
self._cache_time = datetime.now()
|
||||
logger.info(f"Loaded theme metadata: {len(self._metadata_cache.themes)} themes")
|
||||
return self._metadata_cache
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to load theme metadata: {e}")
|
||||
# Return empty registry on error
|
||||
return ThemeRegistry(version=1, themes=[])
|
||||
|
||||
def list_themes(self) -> List[ThemeSummary]:
|
||||
"""
|
||||
List all available themes with signed preview URLs.
|
||||
|
||||
Returns:
|
||||
List of ThemeSummary objects with preview URLs
|
||||
"""
|
||||
metadata = self._load_metadata()
|
||||
summaries = []
|
||||
|
||||
for theme in metadata.themes:
|
||||
try:
|
||||
# Generate signed URLs for preview images
|
||||
preview_path = self._get_theme_path(theme.id, "preview.png")
|
||||
thumbnail_path = self._get_theme_path(theme.id, "preview_thumbnail.png")
|
||||
|
||||
preview_url = None
|
||||
thumbnail_url = None
|
||||
|
||||
if self.storage.file_exists(preview_path):
|
||||
preview_url = self.storage.generate_signed_url(preview_path, expiration_minutes=60)
|
||||
|
||||
# Try thumbnail, fall back to main preview
|
||||
if self.storage.file_exists(thumbnail_path):
|
||||
thumbnail_url = self.storage.generate_signed_url(thumbnail_path, expiration_minutes=60)
|
||||
elif preview_url:
|
||||
thumbnail_url = preview_url
|
||||
|
||||
summaries.append(
|
||||
ThemeSummary(
|
||||
id=theme.id,
|
||||
name=theme.name,
|
||||
description=theme.description,
|
||||
preview_url=preview_url,
|
||||
thumbnail_url=thumbnail_url,
|
||||
is_default=theme.is_default,
|
||||
)
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(f"Error processing theme {theme.id}: {e}")
|
||||
# Still include theme but without preview URLs
|
||||
summaries.append(
|
||||
ThemeSummary(
|
||||
id=theme.id,
|
||||
name=theme.name,
|
||||
description=theme.description,
|
||||
is_default=theme.is_default,
|
||||
)
|
||||
)
|
||||
|
||||
return summaries
|
||||
|
||||
def get_theme(self, theme_id: str) -> Optional[ThemeDetail]:
|
||||
"""
|
||||
Get full theme details including style parameters.
|
||||
|
||||
Args:
|
||||
theme_id: The theme identifier
|
||||
|
||||
Returns:
|
||||
ThemeDetail if found, None otherwise
|
||||
"""
|
||||
metadata = self._load_metadata()
|
||||
|
||||
# Find theme in metadata
|
||||
theme_meta = next((t for t in metadata.themes if t.id == theme_id), None)
|
||||
if not theme_meta:
|
||||
logger.warning(f"Theme not found: {theme_id}")
|
||||
return None
|
||||
|
||||
try:
|
||||
# Load style_params.json
|
||||
style_params_path = self._get_theme_path(theme_id, "style_params.json")
|
||||
style_params = self.storage.download_json(style_params_path)
|
||||
|
||||
# Check for YouTube description
|
||||
youtube_desc_path = self._get_theme_path(theme_id, "youtube_description.txt")
|
||||
has_youtube_desc = self.storage.file_exists(youtube_desc_path)
|
||||
|
||||
# Generate preview URL
|
||||
preview_path = self._get_theme_path(theme_id, "preview.png")
|
||||
preview_url = None
|
||||
if self.storage.file_exists(preview_path):
|
||||
preview_url = self.storage.generate_signed_url(preview_path, expiration_minutes=60)
|
||||
|
||||
return ThemeDetail(
|
||||
id=theme_id,
|
||||
name=theme_meta.name,
|
||||
description=theme_meta.description,
|
||||
preview_url=preview_url,
|
||||
is_default=theme_meta.is_default,
|
||||
style_params=style_params,
|
||||
has_youtube_description=has_youtube_desc,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(f"Error loading theme {theme_id}: {e}")
|
||||
return None
|
||||
|
||||
def get_theme_style_params(self, theme_id: str) -> Optional[Dict[str, Any]]:
|
||||
"""
|
||||
Get just the style_params.json for a theme.
|
||||
|
||||
Args:
|
||||
theme_id: The theme identifier
|
||||
|
||||
Returns:
|
||||
Style parameters dict if found, None otherwise
|
||||
"""
|
||||
try:
|
||||
style_params_path = self._get_theme_path(theme_id, "style_params.json")
|
||||
return self.storage.download_json(style_params_path)
|
||||
except Exception as e:
|
||||
logger.error(f"Error loading style params for theme {theme_id}: {e}")
|
||||
return None
|
||||
|
||||
def get_youtube_description(self, theme_id: str) -> Optional[str]:
|
||||
"""
|
||||
Get the YouTube description template for a theme.
|
||||
|
||||
Args:
|
||||
theme_id: The theme identifier
|
||||
|
||||
Returns:
|
||||
YouTube description text if found, None otherwise
|
||||
"""
|
||||
try:
|
||||
youtube_desc_path = self._get_theme_path(theme_id, "youtube_description.txt")
|
||||
if not self.storage.file_exists(youtube_desc_path):
|
||||
return None
|
||||
|
||||
# Download to temp file and read
|
||||
with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=".txt") as tmp:
|
||||
tmp_path = tmp.name
|
||||
|
||||
try:
|
||||
self.storage.download_file(youtube_desc_path, tmp_path)
|
||||
with open(tmp_path, "r") as f:
|
||||
return f.read()
|
||||
finally:
|
||||
if os.path.exists(tmp_path):
|
||||
os.remove(tmp_path)
|
||||
except Exception as e:
|
||||
logger.error(f"Error loading YouTube description for theme {theme_id}: {e}")
|
||||
return None
|
||||
|
||||
def apply_color_overrides(
|
||||
self, style_params: Dict[str, Any], overrides: ColorOverrides
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Apply user color overrides to theme style parameters.
|
||||
|
||||
Args:
|
||||
style_params: Base style parameters from theme
|
||||
overrides: User color overrides
|
||||
|
||||
Returns:
|
||||
Modified style parameters with overrides applied
|
||||
"""
|
||||
if not overrides.has_overrides():
|
||||
return style_params
|
||||
|
||||
# Deep copy to avoid modifying original
|
||||
result = copy.deepcopy(style_params)
|
||||
|
||||
# Apply artist_color to intro, end, and CDG sections
|
||||
if overrides.artist_color:
|
||||
if "intro" in result:
|
||||
result["intro"]["artist_color"] = overrides.artist_color
|
||||
if "end" in result:
|
||||
result["end"]["artist_color"] = overrides.artist_color
|
||||
if "cdg" in result:
|
||||
result["cdg"]["artist_color"] = overrides.artist_color
|
||||
|
||||
# Apply title_color to intro, end, and CDG sections
|
||||
if overrides.title_color:
|
||||
if "intro" in result:
|
||||
result["intro"]["title_color"] = overrides.title_color
|
||||
if "end" in result:
|
||||
result["end"]["title_color"] = overrides.title_color
|
||||
if "cdg" in result:
|
||||
result["cdg"]["title_color"] = overrides.title_color
|
||||
|
||||
# Apply sung_lyrics_color (karaoke uses RGBA, CDG uses hex)
|
||||
if overrides.sung_lyrics_color:
|
||||
if "karaoke" in result:
|
||||
result["karaoke"]["primary_color"] = hex_to_rgba(overrides.sung_lyrics_color)
|
||||
if "cdg" in result:
|
||||
result["cdg"]["active_fill"] = overrides.sung_lyrics_color
|
||||
|
||||
# Apply unsung_lyrics_color (karaoke uses RGBA, CDG uses hex)
|
||||
if overrides.unsung_lyrics_color:
|
||||
if "karaoke" in result:
|
||||
result["karaoke"]["secondary_color"] = hex_to_rgba(overrides.unsung_lyrics_color)
|
||||
if "cdg" in result:
|
||||
result["cdg"]["inactive_fill"] = overrides.unsung_lyrics_color
|
||||
|
||||
return result
|
||||
|
||||
def prepare_job_style(
|
||||
self,
|
||||
job_id: str,
|
||||
theme_id: str,
|
||||
color_overrides: Optional[ColorOverrides] = None,
|
||||
) -> Tuple[str, Dict[str, str]]:
|
||||
"""
|
||||
Prepare style files for a job by copying theme to job folder.
|
||||
|
||||
This method:
|
||||
1. Loads the theme's style_params.json
|
||||
2. Applies any color overrides
|
||||
3. Updates asset paths to point to theme assets (shared, not copied)
|
||||
4. Uploads modified style_params.json to job folder
|
||||
5. Returns the GCS path and style_assets mapping
|
||||
|
||||
Args:
|
||||
job_id: The job ID
|
||||
theme_id: The theme to use
|
||||
color_overrides: Optional color overrides
|
||||
|
||||
Returns:
|
||||
Tuple of (style_params_gcs_path, style_assets dict)
|
||||
|
||||
Raises:
|
||||
ValueError: If theme not found
|
||||
"""
|
||||
# Load theme style params
|
||||
style_params = self.get_theme_style_params(theme_id)
|
||||
if style_params is None:
|
||||
raise ValueError(f"Theme not found: {theme_id}")
|
||||
|
||||
# Apply color overrides if provided
|
||||
if color_overrides:
|
||||
style_params = self.apply_color_overrides(style_params, color_overrides)
|
||||
|
||||
# Update asset paths to point to theme's shared assets
|
||||
# Theme assets stay in themes/{theme_id}/assets/ - they're shared
|
||||
style_assets = self._build_style_assets_mapping(theme_id, style_params)
|
||||
|
||||
# Update style_params to use theme asset paths (not job-specific)
|
||||
style_params = self._update_asset_paths_in_style(theme_id, style_params)
|
||||
|
||||
# Upload modified style_params.json to job's style folder
|
||||
job_style_path = f"uploads/{job_id}/style/style_params.json"
|
||||
self.storage.upload_json(job_style_path, style_params)
|
||||
|
||||
logger.info(f"Prepared job {job_id} style from theme {theme_id}")
|
||||
|
||||
return job_style_path, style_assets
|
||||
|
||||
def _build_style_assets_mapping(
|
||||
self, theme_id: str, style_params: Dict[str, Any]
|
||||
) -> Dict[str, str]:
|
||||
"""
|
||||
Build the style_assets mapping for a theme.
|
||||
|
||||
Maps asset keys to their GCS paths in the theme folder.
|
||||
"""
|
||||
style_assets = {}
|
||||
theme_assets_prefix = f"{THEMES_PREFIX}/{theme_id}/assets"
|
||||
|
||||
# Check each potential asset type
|
||||
asset_checks = [
|
||||
("intro_background", "intro", "background_image"),
|
||||
("karaoke_background", "karaoke", "background_image"),
|
||||
("end_background", "end", "background_image"),
|
||||
("font", "intro", "font"), # Font is typically shared across sections
|
||||
("cdg_instrumental_background", "cdg", "instrumental_background"),
|
||||
("cdg_title_background", "cdg", "title_screen_background"),
|
||||
("cdg_outro_background", "cdg", "outro_background"),
|
||||
]
|
||||
|
||||
for asset_key, section, field in asset_checks:
|
||||
if section in style_params and field in style_params[section]:
|
||||
value = style_params[section][field]
|
||||
if value and isinstance(value, str):
|
||||
# Check if it's a theme asset path or already has the full path
|
||||
if value.startswith(f"{THEMES_PREFIX}/"):
|
||||
# Already a full theme path
|
||||
style_assets[asset_key] = value
|
||||
elif not value.startswith("/") and not value.startswith("gs://"):
|
||||
# Relative path - prepend theme assets prefix
|
||||
asset_path = f"{theme_assets_prefix}/{os.path.basename(value)}"
|
||||
if self.storage.file_exists(asset_path):
|
||||
style_assets[asset_key] = asset_path
|
||||
|
||||
return style_assets
|
||||
|
||||
def _update_asset_paths_in_style(
|
||||
self, theme_id: str, style_params: Dict[str, Any]
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Update asset paths in style_params to use full GCS theme paths.
|
||||
|
||||
This ensures the style_loader can find assets when processing.
|
||||
"""
|
||||
result = copy.deepcopy(style_params)
|
||||
theme_assets_prefix = f"{THEMES_PREFIX}/{theme_id}/assets"
|
||||
|
||||
# Fields that contain asset paths
|
||||
path_fields = {
|
||||
"intro": ["background_image", "font"],
|
||||
"end": ["background_image", "font"],
|
||||
"karaoke": ["background_image", "font_path"],
|
||||
"cdg": [
|
||||
"font_path",
|
||||
"instrumental_background",
|
||||
"title_screen_background",
|
||||
"outro_background",
|
||||
],
|
||||
}
|
||||
|
||||
for section, fields in path_fields.items():
|
||||
if section not in result:
|
||||
continue
|
||||
for field in fields:
|
||||
if field not in result[section]:
|
||||
continue
|
||||
value = result[section][field]
|
||||
if value and isinstance(value, str):
|
||||
# Skip if already a full path or URL
|
||||
if value.startswith(f"{THEMES_PREFIX}/") or value.startswith("gs://"):
|
||||
continue
|
||||
# Skip absolute local paths (shouldn't happen but be safe)
|
||||
if value.startswith("/"):
|
||||
continue
|
||||
# Update to full theme asset path
|
||||
result[section][field] = f"{theme_assets_prefix}/{os.path.basename(value)}"
|
||||
|
||||
return result
|
||||
|
||||
def theme_exists(self, theme_id: str) -> bool:
|
||||
"""
|
||||
Check if a theme exists.
|
||||
|
||||
Args:
|
||||
theme_id: The theme identifier
|
||||
|
||||
Returns:
|
||||
True if theme exists, False otherwise
|
||||
"""
|
||||
metadata = self._load_metadata()
|
||||
return any(t.id == theme_id for t in metadata.themes)
|
||||
|
||||
def get_default_theme_id(self) -> Optional[str]:
|
||||
"""
|
||||
Get the ID of the default theme.
|
||||
|
||||
Returns:
|
||||
Default theme ID if one exists, None otherwise
|
||||
"""
|
||||
metadata = self._load_metadata()
|
||||
default_theme = next((t for t in metadata.themes if t.is_default), None)
|
||||
return default_theme.id if default_theme else None
|
||||
|
||||
def invalidate_cache(self) -> None:
|
||||
"""Force invalidation of the metadata cache."""
|
||||
self._metadata_cache = None
|
||||
self._cache_time = None
|
||||
logger.info("Theme metadata cache invalidated")
|
||||
|
||||
|
||||
# Singleton instance with thread-safe initialization
|
||||
_theme_service: Optional[ThemeService] = None
|
||||
_theme_service_lock = threading.Lock()
|
||||
|
||||
|
||||
def get_theme_service() -> ThemeService:
|
||||
"""Get or create the singleton ThemeService instance (thread-safe)."""
|
||||
global _theme_service
|
||||
if _theme_service is None:
|
||||
with _theme_service_lock:
|
||||
# Double-check after acquiring lock
|
||||
if _theme_service is None:
|
||||
_theme_service = ThemeService()
|
||||
return _theme_service
|
||||
@@ -19,6 +19,25 @@ Usage:
|
||||
with tracer.start_as_current_span("my-operation") as span:
|
||||
span.set_attribute("job_id", job_id)
|
||||
# ... do work ...
|
||||
|
||||
# For job-specific spans with automatic job_id attribute
|
||||
from backend.services.tracing import job_span
|
||||
|
||||
with job_span("audio-worker", job_id) as span:
|
||||
# job_id is automatically set as an attribute
|
||||
span.set_attribute("stage", "separation")
|
||||
# ... do work ...
|
||||
|
||||
# For propagating trace context through Cloud Tasks
|
||||
from backend.services.tracing import inject_trace_context, extract_trace_context
|
||||
|
||||
# In worker_service.py (when creating task):
|
||||
headers = inject_trace_context({})
|
||||
|
||||
# In internal.py (when receiving task):
|
||||
context = extract_trace_context(request.headers)
|
||||
with tracer.start_as_current_span("worker", context=context):
|
||||
...
|
||||
"""
|
||||
import os
|
||||
import logging
|
||||
@@ -380,3 +399,145 @@ def get_current_span_id() -> Optional[str]:
|
||||
if ctx.is_valid:
|
||||
return format(ctx.span_id, '016x')
|
||||
return None
|
||||
|
||||
|
||||
# =====================================================
|
||||
# Job-Aware Tracing Utilities
|
||||
# =====================================================
|
||||
|
||||
@contextmanager
|
||||
def job_span(
|
||||
name: str,
|
||||
job_id: str,
|
||||
attributes: Optional[Dict[str, Any]] = None,
|
||||
kind: trace.SpanKind = trace.SpanKind.INTERNAL,
|
||||
):
|
||||
"""
|
||||
Create a traced span with job_id automatically set as an attribute.
|
||||
|
||||
This is the preferred way to create spans in job processing workers.
|
||||
The job_id attribute enables filtering spans by job in Cloud Trace.
|
||||
|
||||
Usage:
|
||||
with job_span("audio-separation", job_id) as span:
|
||||
span.set_attribute("stage", "clean_instrumental")
|
||||
# ... do work ...
|
||||
|
||||
Args:
|
||||
name: Span name (appears in Cloud Trace)
|
||||
job_id: Job ID to attach to the span
|
||||
attributes: Additional span attributes
|
||||
kind: Span kind (INTERNAL, SERVER, CLIENT, PRODUCER, CONSUMER)
|
||||
|
||||
Yields:
|
||||
The active span
|
||||
"""
|
||||
all_attributes = {
|
||||
"job_id": job_id,
|
||||
"service.operation": name,
|
||||
}
|
||||
if attributes:
|
||||
all_attributes.update(attributes)
|
||||
|
||||
with create_span(name, all_attributes, kind) as span:
|
||||
yield span
|
||||
|
||||
|
||||
def inject_trace_context(headers: Dict[str, str]) -> Dict[str, str]:
|
||||
"""
|
||||
Inject current trace context into HTTP headers.
|
||||
|
||||
Use this when creating Cloud Tasks or making HTTP calls to propagate
|
||||
the trace context so child spans link to the parent trace.
|
||||
|
||||
Usage:
|
||||
headers = inject_trace_context({
|
||||
"Content-Type": "application/json",
|
||||
"Authorization": "Bearer token",
|
||||
})
|
||||
# Use headers in HTTP request or Cloud Task
|
||||
|
||||
Args:
|
||||
headers: Existing headers dict to add trace context to
|
||||
|
||||
Returns:
|
||||
Headers dict with traceparent/tracestate headers added
|
||||
"""
|
||||
propagator = TraceContextTextMapPropagator()
|
||||
carrier = dict(headers) # Make a copy
|
||||
propagator.inject(carrier)
|
||||
return carrier
|
||||
|
||||
|
||||
def extract_trace_context(headers: Dict[str, str]) -> Optional[trace.Context]:
|
||||
"""
|
||||
Extract trace context from HTTP headers.
|
||||
|
||||
Use this when receiving Cloud Tasks or HTTP requests to continue
|
||||
the trace from the parent span.
|
||||
|
||||
Usage:
|
||||
context = extract_trace_context(request.headers)
|
||||
with tracer.start_as_current_span("worker", context=context):
|
||||
# ... processing ...
|
||||
|
||||
Args:
|
||||
headers: HTTP headers containing traceparent/tracestate
|
||||
|
||||
Returns:
|
||||
Context object for use with start_as_current_span, or None
|
||||
"""
|
||||
propagator = TraceContextTextMapPropagator()
|
||||
return propagator.extract(headers)
|
||||
|
||||
|
||||
def start_span_with_context(
|
||||
name: str,
|
||||
context: Optional[trace.Context],
|
||||
job_id: Optional[str] = None,
|
||||
attributes: Optional[Dict[str, Any]] = None,
|
||||
):
|
||||
"""
|
||||
Start a span as child of the given context (or current context if None).
|
||||
|
||||
This is useful for starting worker spans that should link to the
|
||||
trace from the original API request.
|
||||
|
||||
Usage:
|
||||
context = extract_trace_context(request.headers)
|
||||
with start_span_with_context("audio-worker", context, job_id) as span:
|
||||
# ... processing ...
|
||||
|
||||
Args:
|
||||
name: Span name
|
||||
context: Parent context (from extract_trace_context) or None
|
||||
job_id: Optional job ID to set as attribute
|
||||
attributes: Additional span attributes
|
||||
|
||||
Returns:
|
||||
Context manager yielding the span
|
||||
"""
|
||||
tracer = get_tracer()
|
||||
|
||||
all_attributes = attributes or {}
|
||||
if job_id:
|
||||
all_attributes["job_id"] = job_id
|
||||
all_attributes["service.operation"] = name
|
||||
|
||||
@contextmanager
|
||||
def _span():
|
||||
kwargs = {"kind": trace.SpanKind.INTERNAL}
|
||||
if context is not None:
|
||||
kwargs["context"] = context
|
||||
|
||||
with tracer.start_as_current_span(name, **kwargs) as span:
|
||||
for key, value in all_attributes.items():
|
||||
span.set_attribute(key, value)
|
||||
try:
|
||||
yield span
|
||||
except Exception as e:
|
||||
span.set_status(Status(StatusCode.ERROR, str(e)))
|
||||
span.record_exception(e)
|
||||
raise
|
||||
|
||||
return _span()
|
||||
@@ -2,29 +2,60 @@
|
||||
Worker coordination service.
|
||||
|
||||
Handles triggering and coordinating background workers.
|
||||
Implements proper HTTP-based triggers for production use.
|
||||
Supports two modes:
|
||||
- Cloud Tasks (production): Guaranteed delivery, automatic retries, horizontal scaling
|
||||
- Direct HTTP (development): Faster iteration, simpler debugging
|
||||
|
||||
SOLID Principles:
|
||||
- Single Responsibility: Only handles worker coordination
|
||||
- Dependency Inversion: Depends on HTTP abstraction, not implementation
|
||||
- Open/Closed: Can add new workers without modifying existing code
|
||||
|
||||
Observability:
|
||||
- Propagates trace context through Cloud Tasks for distributed tracing
|
||||
- All worker invocations create spans linked to original request trace
|
||||
"""
|
||||
import logging
|
||||
import os
|
||||
import httpx
|
||||
import json
|
||||
from typing import Optional
|
||||
import httpx
|
||||
|
||||
from backend.config import get_settings
|
||||
from backend.services.tracing import inject_trace_context
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
# Mapping of worker types to their Cloud Tasks queue names
|
||||
# These queues are created by Pulumi in infrastructure/__main__.py
|
||||
WORKER_QUEUES = {
|
||||
"audio": "audio-worker-queue",
|
||||
"lyrics": "lyrics-worker-queue",
|
||||
"screens": "screens-worker-queue",
|
||||
"render-video": "render-worker-queue",
|
||||
"video": "video-worker-queue",
|
||||
}
|
||||
|
||||
|
||||
class WorkerService:
|
||||
"""
|
||||
Service for coordinating background workers.
|
||||
|
||||
Handles triggering workers via internal HTTP API.
|
||||
In production, workers run as separate Cloud Run requests or Cloud Tasks.
|
||||
Supports two execution modes controlled by ENABLE_CLOUD_TASKS env var:
|
||||
|
||||
1. Cloud Tasks mode (production, ENABLE_CLOUD_TASKS=true):
|
||||
- Tasks enqueued to Cloud Tasks for guaranteed delivery
|
||||
- Automatic retries on failure
|
||||
- Each task runs in dedicated Cloud Run instance
|
||||
- Rate limiting to protect external APIs (Modal, AudioShake)
|
||||
|
||||
2. Direct HTTP mode (development, ENABLE_CLOUD_TASKS=false):
|
||||
- Direct HTTP POST to internal worker endpoints
|
||||
- Worker runs as FastAPI BackgroundTask
|
||||
- Faster iteration for local development
|
||||
- No retry guarantees
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
@@ -32,6 +63,44 @@ class WorkerService:
|
||||
self.settings = get_settings()
|
||||
self._base_url = self._get_base_url()
|
||||
self._admin_token = self._get_admin_token()
|
||||
self._use_cloud_tasks = self._should_use_cloud_tasks()
|
||||
self._tasks_client = None
|
||||
|
||||
if self._use_cloud_tasks:
|
||||
logger.info("WorkerService initialized with Cloud Tasks mode")
|
||||
else:
|
||||
logger.info("WorkerService initialized with direct HTTP mode")
|
||||
|
||||
def _should_use_cloud_tasks(self) -> bool:
|
||||
"""
|
||||
Check if Cloud Tasks should be used for worker coordination.
|
||||
|
||||
Controlled by ENABLE_CLOUD_TASKS setting (from environment variable).
|
||||
Default is false (direct HTTP mode) for backward compatibility.
|
||||
|
||||
Returns:
|
||||
True if Cloud Tasks should be used, False for direct HTTP
|
||||
"""
|
||||
return self.settings.enable_cloud_tasks
|
||||
|
||||
@property
|
||||
def tasks_client(self):
|
||||
"""
|
||||
Lazy-initialize Cloud Tasks client.
|
||||
|
||||
Only created when needed to avoid import overhead in development mode.
|
||||
"""
|
||||
if self._tasks_client is None and self._use_cloud_tasks:
|
||||
try:
|
||||
from google.cloud import tasks_v2
|
||||
self._tasks_client = tasks_v2.CloudTasksClient()
|
||||
except ImportError:
|
||||
logger.error(
|
||||
"google-cloud-tasks not installed. "
|
||||
"Install with: pip install google-cloud-tasks"
|
||||
)
|
||||
raise
|
||||
return self._tasks_client
|
||||
|
||||
def _get_admin_token(self) -> Optional[str]:
|
||||
"""
|
||||
@@ -49,9 +118,10 @@ class WorkerService:
|
||||
"""
|
||||
Get base URL for internal API calls.
|
||||
|
||||
In production: Cloud Run service URL
|
||||
In test: TEST_SERVER_URL
|
||||
In development: localhost
|
||||
Priority:
|
||||
1. TEST_SERVER_URL env var (for tests)
|
||||
2. CLOUD_RUN_SERVICE_URL env var (for Cloud Tasks to call back)
|
||||
3. localhost with PORT env var (for development)
|
||||
|
||||
Returns:
|
||||
Base URL for API calls
|
||||
@@ -61,14 +131,11 @@ class WorkerService:
|
||||
if test_url:
|
||||
return test_url
|
||||
|
||||
# Check if running in Cloud Run
|
||||
cloud_run_url = self.settings.google_cloud_project
|
||||
if cloud_run_url and self.settings.environment == "production":
|
||||
# TODO: Get actual Cloud Run service URL
|
||||
# For now, use environment variable
|
||||
service_url = os.getenv("CLOUD_RUN_SERVICE_URL")
|
||||
if service_url:
|
||||
return service_url
|
||||
# Production: Cloud Run service URL
|
||||
# This must be the publicly accessible URL for Cloud Tasks to call
|
||||
service_url = os.getenv("CLOUD_RUN_SERVICE_URL")
|
||||
if service_url:
|
||||
return service_url
|
||||
|
||||
# Development mode: use localhost with PORT env var
|
||||
port = os.getenv("PORT", "8000")
|
||||
@@ -81,10 +148,140 @@ class WorkerService:
|
||||
timeout_seconds: int = 30
|
||||
) -> bool:
|
||||
"""
|
||||
Trigger a background worker via internal API.
|
||||
Trigger a background worker for a job.
|
||||
|
||||
In production (ENABLE_CLOUD_TASKS=true):
|
||||
- Enqueues task to Cloud Tasks queue
|
||||
- Cloud Tasks delivers HTTP request to internal endpoint
|
||||
- Automatic retries on failure with exponential backoff
|
||||
- Rate limiting protects external APIs
|
||||
|
||||
In development (ENABLE_CLOUD_TASKS=false):
|
||||
- Direct HTTP POST to internal endpoint
|
||||
- Faster iteration, but no retry guarantees
|
||||
- Worker runs in same container as API
|
||||
|
||||
Args:
|
||||
worker_type: Worker type ("audio", "lyrics", "screens", "video")
|
||||
worker_type: Worker type ("audio", "lyrics", "screens", "render-video", "video")
|
||||
job_id: Job ID to process
|
||||
timeout_seconds: Request timeout (for direct HTTP mode)
|
||||
|
||||
Returns:
|
||||
True if trigger successful (or task enqueued), False otherwise
|
||||
"""
|
||||
if self._use_cloud_tasks:
|
||||
return await self._enqueue_cloud_task(worker_type, job_id)
|
||||
else:
|
||||
return await self._trigger_http(worker_type, job_id, timeout_seconds)
|
||||
|
||||
async def _enqueue_cloud_task(self, worker_type: str, job_id: str) -> bool:
|
||||
"""
|
||||
Enqueue task to Cloud Tasks for guaranteed delivery.
|
||||
|
||||
The task will be delivered as an HTTP POST to the internal worker endpoint.
|
||||
Cloud Tasks handles:
|
||||
- Retry on failure (with exponential backoff)
|
||||
- Rate limiting (max dispatches per second)
|
||||
- Deduplication (via task name if needed)
|
||||
- OIDC authentication for Cloud Run
|
||||
|
||||
Observability:
|
||||
- Injects trace context headers so worker spans link to parent trace
|
||||
|
||||
Args:
|
||||
worker_type: Worker type
|
||||
job_id: Job ID to process
|
||||
|
||||
Returns:
|
||||
True if task enqueued successfully, False otherwise
|
||||
"""
|
||||
try:
|
||||
from google.cloud import tasks_v2
|
||||
|
||||
queue_name = WORKER_QUEUES.get(worker_type)
|
||||
if not queue_name:
|
||||
logger.error(f"Unknown worker type: {worker_type}")
|
||||
return False
|
||||
|
||||
project = self.settings.google_cloud_project
|
||||
if not project:
|
||||
logger.error("GOOGLE_CLOUD_PROJECT not set, cannot enqueue Cloud Task")
|
||||
return False
|
||||
|
||||
location = self.settings.gcp_region # Must match queue location
|
||||
|
||||
# Build queue path
|
||||
parent = self.tasks_client.queue_path(project, location, queue_name)
|
||||
|
||||
# Build base headers
|
||||
headers = {
|
||||
"Content-Type": "application/json",
|
||||
}
|
||||
|
||||
# Add admin auth via custom header
|
||||
# NOTE: We use X-Admin-Token instead of Authorization because Cloud Tasks
|
||||
# OIDC token overwrites the Authorization header when oidc_token is specified.
|
||||
# The OIDC token handles Cloud Run authentication (allows Cloud Tasks to invoke
|
||||
# the service), while X-Admin-Token handles application-level authentication.
|
||||
if self._admin_token:
|
||||
headers["X-Admin-Token"] = self._admin_token
|
||||
logger.debug(
|
||||
f"[job:{job_id}] Using admin token for Cloud Task auth via X-Admin-Token, "
|
||||
f"token prefix: {self._admin_token[:8]}..., len={len(self._admin_token)}"
|
||||
)
|
||||
|
||||
# Inject trace context for distributed tracing
|
||||
# This allows worker spans to link back to the original request trace
|
||||
headers = inject_trace_context(headers)
|
||||
|
||||
# Build task payload
|
||||
task = {
|
||||
"http_request": {
|
||||
"http_method": tasks_v2.HttpMethod.POST,
|
||||
"url": f"{self._base_url}/api/internal/workers/{worker_type}",
|
||||
"headers": headers,
|
||||
"body": json.dumps({"job_id": job_id}).encode(),
|
||||
# Use OIDC token for Cloud Run authentication
|
||||
# This allows Cloud Tasks to invoke the Cloud Run service
|
||||
"oidc_token": {
|
||||
"service_account_email": f"karaoke-backend@{project}.iam.gserviceaccount.com",
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
# Create task
|
||||
# Note: We don't set a task name, allowing Cloud Tasks to generate one
|
||||
# This prevents duplicate task errors on retries
|
||||
response = self.tasks_client.create_task(parent=parent, task=task)
|
||||
logger.info(
|
||||
f"[job:{job_id}] Created Cloud Task for {worker_type} worker: {response.name}"
|
||||
)
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"[job:{job_id}] Failed to enqueue Cloud Task for {worker_type}: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return False
|
||||
|
||||
async def _trigger_http(
|
||||
self,
|
||||
worker_type: str,
|
||||
job_id: str,
|
||||
timeout_seconds: int = 30
|
||||
) -> bool:
|
||||
"""
|
||||
Trigger worker via direct HTTP call (development mode).
|
||||
|
||||
This is the original implementation - direct HTTP POST to internal endpoint.
|
||||
The endpoint adds the worker function to FastAPI BackgroundTasks.
|
||||
|
||||
Observability:
|
||||
- Injects trace context headers so worker spans link to parent trace
|
||||
|
||||
Args:
|
||||
worker_type: Worker type
|
||||
job_id: Job ID to process
|
||||
timeout_seconds: Request timeout
|
||||
|
||||
@@ -97,6 +294,9 @@ class WorkerService:
|
||||
if self._admin_token:
|
||||
headers["Authorization"] = f"Bearer {self._admin_token}"
|
||||
|
||||
# Inject trace context for distributed tracing
|
||||
headers = inject_trace_context(headers)
|
||||
|
||||
async with httpx.AsyncClient(timeout=timeout_seconds) as client:
|
||||
url = f"{self._base_url}/api/internal/workers/{worker_type}"
|
||||
|
||||
@@ -107,26 +307,29 @@ class WorkerService:
|
||||
)
|
||||
|
||||
if response.status_code == 200:
|
||||
logger.info(f"Successfully triggered {worker_type} worker for job {job_id}")
|
||||
logger.info(f"[job:{job_id}] Successfully triggered {worker_type} worker")
|
||||
return True
|
||||
else:
|
||||
logger.error(
|
||||
f"Failed to trigger {worker_type} worker for job {job_id}: "
|
||||
f"[job:{job_id}] Failed to trigger {worker_type} worker: "
|
||||
f"HTTP {response.status_code} - {response.text}"
|
||||
)
|
||||
return False
|
||||
|
||||
except httpx.TimeoutException:
|
||||
logger.error(f"Timeout triggering {worker_type} worker for job {job_id}")
|
||||
logger.error(f"[job:{job_id}] Timeout triggering {worker_type} worker")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Error triggering {worker_type} worker for job {job_id}: {e}",
|
||||
f"[job:{job_id}] Error triggering {worker_type} worker: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return False
|
||||
|
||||
# Convenience methods for specific workers
|
||||
# These provide a cleaner API and better IDE autocomplete
|
||||
|
||||
async def trigger_audio_worker(self, job_id: str) -> bool:
|
||||
"""Trigger audio separation worker."""
|
||||
return await self.trigger_worker("audio", job_id)
|
||||
@@ -140,9 +343,68 @@ class WorkerService:
|
||||
return await self.trigger_worker("screens", job_id)
|
||||
|
||||
async def trigger_video_worker(self, job_id: str) -> bool:
|
||||
"""Trigger video generation worker."""
|
||||
"""
|
||||
Trigger video generation worker.
|
||||
|
||||
When USE_CLOUD_RUN_JOBS_FOR_VIDEO=true and ENABLE_CLOUD_TASKS=true,
|
||||
uses Cloud Run Jobs for execution (supports >30 min encoding).
|
||||
Otherwise, uses Cloud Tasks or direct HTTP.
|
||||
"""
|
||||
if self._use_cloud_tasks and self.settings.use_cloud_run_jobs_for_video:
|
||||
return await self._trigger_cloud_run_job(job_id)
|
||||
return await self.trigger_worker("video", job_id)
|
||||
|
||||
async def _trigger_cloud_run_job(self, job_id: str) -> bool:
|
||||
"""
|
||||
Trigger video encoding as a Cloud Run Job.
|
||||
|
||||
Cloud Run Jobs support up to 24 hours of execution time,
|
||||
making them suitable for very long video encoding tasks.
|
||||
|
||||
Args:
|
||||
job_id: Job ID to process
|
||||
|
||||
Returns:
|
||||
True if job was triggered successfully, False otherwise
|
||||
"""
|
||||
try:
|
||||
from google.cloud import run_v2
|
||||
|
||||
project = self.settings.google_cloud_project
|
||||
if not project:
|
||||
logger.error("GOOGLE_CLOUD_PROJECT not set, cannot trigger Cloud Run Job")
|
||||
return False
|
||||
|
||||
location = self.settings.gcp_region
|
||||
job_name = f"projects/{project}/locations/{location}/jobs/video-encoding-job"
|
||||
|
||||
# Create Cloud Run Jobs client
|
||||
client = run_v2.JobsClient()
|
||||
|
||||
# Run the job with overrides for the specific job_id
|
||||
request = run_v2.RunJobRequest(
|
||||
name=job_name,
|
||||
overrides=run_v2.RunJobRequest.Overrides(
|
||||
container_overrides=[
|
||||
run_v2.RunJobRequest.Overrides.ContainerOverride(
|
||||
args=["python", "-m", "backend.workers.video_worker", "--job-id", job_id],
|
||||
)
|
||||
]
|
||||
)
|
||||
)
|
||||
|
||||
# Run the job (async operation)
|
||||
operation = client.run_job(request=request)
|
||||
logger.info(f"Started Cloud Run Job for video encoding, job {job_id}: {operation.metadata}")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"Failed to trigger Cloud Run Job for video/{job_id}: {e}",
|
||||
exc_info=True
|
||||
)
|
||||
return False
|
||||
|
||||
async def trigger_render_video_worker(self, job_id: str) -> bool:
|
||||
"""Trigger render video worker (post-review)."""
|
||||
return await self.trigger_worker("render-video", job_id)
|
||||
@@ -166,3 +428,12 @@ def get_worker_service() -> WorkerService:
|
||||
_worker_service = WorkerService()
|
||||
return _worker_service
|
||||
|
||||
|
||||
def reset_worker_service() -> None:
|
||||
"""
|
||||
Reset the global worker service instance.
|
||||
|
||||
Used in tests to ensure clean state between test cases.
|
||||
"""
|
||||
global _worker_service
|
||||
_worker_service = None
|
||||
+104
-4
@@ -12,13 +12,19 @@ from unittest.mock import Mock, MagicMock, AsyncMock, patch
|
||||
from datetime import datetime, UTC
|
||||
from fastapi.testclient import TestClient
|
||||
|
||||
# Mock google.auth.default for unit tests if not using emulator
|
||||
# This prevents DefaultCredentialsError during imports
|
||||
# Mock google.auth.default AND firestore for unit tests if not using emulator
|
||||
# This prevents DefaultCredentialsError and FirestoreClient initialization during imports
|
||||
if 'FIRESTORE_EMULATOR_HOST' not in os.environ:
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
# Only mock the default() function, not the entire module
|
||||
# This allows other google.auth imports to work normally
|
||||
# Set up test environment variables BEFORE importing any backend modules
|
||||
os.environ.setdefault('ADMIN_TOKENS', 'test-admin-token')
|
||||
os.environ.setdefault('GOOGLE_CLOUD_PROJECT', 'test-project')
|
||||
os.environ.setdefault('GCS_BUCKET_NAME', 'test-bucket')
|
||||
os.environ.setdefault('FIRESTORE_COLLECTION', 'jobs')
|
||||
os.environ.setdefault('ENVIRONMENT', 'test')
|
||||
|
||||
# Mock google.auth.default - prevents credential errors
|
||||
try:
|
||||
import google.auth
|
||||
mock_credentials = MagicMock()
|
||||
@@ -30,10 +36,104 @@ if 'FIRESTORE_EMULATOR_HOST' not in os.environ:
|
||||
except ImportError:
|
||||
# If google.auth not installed, that's ok for some tests
|
||||
pass
|
||||
|
||||
# Mock google.cloud.firestore.Client - prevents Firestore initialization
|
||||
# This is CRITICAL: when AuthService is instantiated, it creates FirestoreService
|
||||
# which tries to create a real Firestore client. The client returns MagicMocks
|
||||
# which fail when used as enum values (e.g., UserType).
|
||||
try:
|
||||
import google.cloud.firestore as firestore_module
|
||||
|
||||
# Create a mock client that returns proper values for get_token
|
||||
mock_firestore_client = MagicMock()
|
||||
mock_collection = MagicMock()
|
||||
mock_doc = MagicMock()
|
||||
mock_snapshot = MagicMock()
|
||||
|
||||
# For auth token lookups, return None (token not found in Firestore)
|
||||
# This forces validation to use admin tokens from environment
|
||||
mock_snapshot.exists = False
|
||||
mock_snapshot.to_dict.return_value = None
|
||||
mock_doc.get.return_value = mock_snapshot
|
||||
mock_collection.document.return_value = mock_doc
|
||||
mock_firestore_client.collection.return_value = mock_collection
|
||||
|
||||
# Replace the Client class
|
||||
original_client = firestore_module.Client
|
||||
firestore_module.Client = MagicMock(return_value=mock_firestore_client)
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
# Mock google.cloud.storage.Client - prevents GCS initialization
|
||||
try:
|
||||
import google.cloud.storage as storage_module
|
||||
mock_storage_client = MagicMock()
|
||||
mock_bucket = MagicMock()
|
||||
mock_storage_client.bucket.return_value = mock_bucket
|
||||
storage_module.Client = MagicMock(return_value=mock_storage_client)
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
from backend.models.job import Job, JobStatus, JobCreate
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def mock_auth_dependency(request):
|
||||
"""Mock the require_auth dependency for all tests using FastAPI's dependency override system."""
|
||||
# Skip for emulator tests and integration tests which use real auth
|
||||
test_path = str(request.fspath)
|
||||
if 'emulator' in test_path or 'integration' in test_path:
|
||||
yield
|
||||
return
|
||||
|
||||
# Skip if FIRESTORE_EMULATOR_HOST is set (running in emulator environment)
|
||||
import os
|
||||
if os.environ.get('FIRESTORE_EMULATOR_HOST'):
|
||||
yield
|
||||
return
|
||||
|
||||
from backend.services.auth_service import UserType
|
||||
from backend.api.dependencies import require_auth, require_admin, require_review_auth, require_instrumental_auth
|
||||
from backend.main import app
|
||||
|
||||
# Create mock auth functions
|
||||
async def mock_require_auth():
|
||||
"""Mock require_auth to always return valid admin credentials."""
|
||||
return ("test-admin-token", UserType.ADMIN, 999)
|
||||
|
||||
async def mock_require_admin():
|
||||
"""Mock require_admin to always return valid admin credentials."""
|
||||
return ("test-admin-token", UserType.ADMIN, 999)
|
||||
|
||||
async def mock_require_review_auth(job_id: str = "test123"):
|
||||
"""Mock require_review_auth to always return valid review access."""
|
||||
return (job_id, "full")
|
||||
|
||||
async def mock_require_instrumental_auth(job_id: str = "test123"):
|
||||
"""Mock require_instrumental_auth to always return valid instrumental review access."""
|
||||
return (job_id, "full")
|
||||
|
||||
# Use FastAPI's dependency override system
|
||||
app.dependency_overrides[require_auth] = mock_require_auth
|
||||
app.dependency_overrides[require_admin] = mock_require_admin
|
||||
app.dependency_overrides[require_review_auth] = mock_require_review_auth
|
||||
app.dependency_overrides[require_instrumental_auth] = mock_require_instrumental_auth
|
||||
|
||||
yield
|
||||
|
||||
# Clean up after test
|
||||
app.dependency_overrides.clear()
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def auth_headers():
|
||||
"""Get authentication headers for test requests."""
|
||||
return {
|
||||
"Authorization": "Bearer test-admin-token",
|
||||
"Content-Type": "application/json"
|
||||
}
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_firestore():
|
||||
"""Mock Firestore client for unit tests."""
|
||||
|
||||
File diff suppressed because it is too large.
Load diff
@@ -27,15 +27,15 @@ pytestmark = pytest.mark.skipif(
|
||||
class TestEmulatorBasics:
|
||||
"""Basic emulator connectivity tests."""
|
||||
|
||||
def test_health_endpoint(self, client):
|
||||
def test_health_endpoint(self, client, auth_headers):
|
||||
"""Test health endpoint works."""
|
||||
response = client.get("/api/health")
|
||||
response = client.get("/api/health", )
|
||||
assert response.status_code == 200
|
||||
assert response.json()["status"] == "healthy"
|
||||
|
||||
def test_root_endpoint(self, client):
|
||||
def test_root_endpoint(self, client, auth_headers):
|
||||
"""Test root endpoint works."""
|
||||
response = client.get("/")
|
||||
response = client.get("/", )
|
||||
assert response.status_code == 200
|
||||
assert response.json()["service"] == "karaoke-gen-backend"
|
||||
|
||||
@@ -281,13 +281,13 @@ class TestReviewEndpoints:
|
||||
time.sleep(0.2)
|
||||
|
||||
# Should fail - job not in AWAITING_REVIEW status
|
||||
response = client.get(f"/api/review/{job_id}/correction-data")
|
||||
response = client.get(f"/api/review/{job_id}/correction-data", headers=auth_headers)
|
||||
assert response.status_code == 400
|
||||
assert "not ready for review" in response.json()["detail"].lower()
|
||||
|
||||
def test_review_audio_no_job(self, client):
|
||||
def test_review_audio_no_job(self, client, auth_headers):
|
||||
"""Test audio endpoint returns 404 for nonexistent job."""
|
||||
response = client.get("/api/review/nonexistent-job/audio/")
|
||||
response = client.get("/api/review/nonexistent-job/audio/", headers=auth_headers)
|
||||
assert response.status_code == 404
|
||||
|
||||
def test_review_preview_video_stub(self, client, auth_headers):
|
||||
@@ -303,6 +303,7 @@ class TestReviewEndpoints:
|
||||
# Preview video should return error since job not ready
|
||||
response = client.post(
|
||||
f"/api/review/{job_id}/preview-video",
|
||||
headers=auth_headers,
|
||||
json={"corrections": [], "corrected_segments": []}
|
||||
)
|
||||
# Should return 400 (job not in AWAITING_REVIEW state)
|
||||
@@ -320,6 +321,7 @@ class TestReviewEndpoints:
|
||||
# Annotations endpoint should accept data (even if it just logs it)
|
||||
response = client.post(
|
||||
f"/api/review/{job_id}/v1/annotations",
|
||||
headers=auth_headers,
|
||||
json={"type": "test", "data": "test annotation"}
|
||||
)
|
||||
assert response.status_code == 200
|
||||
@@ -328,7 +330,7 @@ class TestReviewEndpoints:
|
||||
|
||||
class TestRenderVideoWorker:
|
||||
"""Test render video worker endpoint."""
|
||||
|
||||
|
||||
def test_render_video_worker_endpoint_exists(self, client, auth_headers):
|
||||
"""Test that render-video worker endpoint exists."""
|
||||
# Create a job
|
||||
@@ -338,9 +340,9 @@ class TestRenderVideoWorker:
|
||||
json={"url": "https://youtube.com/watch?v=render-test"}
|
||||
)
|
||||
job_id = create_resp.json()["job_id"]
|
||||
|
||||
|
||||
time.sleep(0.2)
|
||||
|
||||
|
||||
# Test render-video worker endpoint exists
|
||||
response = client.post(
|
||||
"/api/internal/workers/render-video",
|
||||
|
||||
@@ -28,20 +28,20 @@ class TestHealthRoutes:
|
||||
from backend.main import app
|
||||
return TestClient(app)
|
||||
|
||||
def test_health_endpoint_returns_200(self, client):
|
||||
def test_health_endpoint_returns_200(self, client, auth_headers):
|
||||
"""Test /api/health returns 200 OK."""
|
||||
response = client.get("/api/health")
|
||||
response = client.get("/api/health", )
|
||||
assert response.status_code == 200
|
||||
|
||||
def test_health_endpoint_returns_healthy_status(self, client):
|
||||
def test_health_endpoint_returns_healthy_status(self, client, auth_headers):
|
||||
"""Test health endpoint returns healthy status."""
|
||||
response = client.get("/api/health")
|
||||
response = client.get("/api/health", )
|
||||
data = response.json()
|
||||
assert data["status"] == "healthy"
|
||||
|
||||
def test_root_endpoint_returns_200(self, client):
|
||||
def test_root_endpoint_returns_200(self, client, auth_headers):
|
||||
"""Test root endpoint returns 200."""
|
||||
response = client.get("/")
|
||||
response = client.get("/", )
|
||||
assert response.status_code == 200
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,294 @@
|
||||
"""
|
||||
Tests for audio_analysis_service.py - Audio analysis for backing vocals.
|
||||
|
||||
These tests mock the storage service and shared karaoke_gen modules to verify:
|
||||
- GCS file download/upload operations
|
||||
- Audio analysis delegation to shared AudioAnalyzer
|
||||
- Waveform generation delegation to shared WaveformGenerator
|
||||
"""
|
||||
import pytest
|
||||
from unittest.mock import Mock, MagicMock, patch, ANY
|
||||
import tempfile
|
||||
import os
|
||||
|
||||
|
||||
class TestAudioAnalysisServiceInit:
|
||||
"""Test AudioAnalysisService initialization."""
|
||||
|
||||
@patch("backend.services.audio_analysis_service.StorageService")
|
||||
@patch("backend.services.audio_analysis_service.AudioAnalyzer")
|
||||
@patch("backend.services.audio_analysis_service.WaveformGenerator")
|
||||
def test_init_creates_dependencies(
|
||||
self, mock_waveform_class, mock_analyzer_class, mock_storage_class
|
||||
):
|
||||
"""Test initialization creates storage service and analyzers."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
service = AudioAnalysisService()
|
||||
|
||||
mock_storage_class.assert_called_once()
|
||||
mock_analyzer_class.assert_called_once_with(
|
||||
silence_threshold_db=-40.0,
|
||||
min_segment_duration_ms=100,
|
||||
)
|
||||
mock_waveform_class.assert_called_once()
|
||||
|
||||
@patch("backend.services.audio_analysis_service.StorageService")
|
||||
@patch("backend.services.audio_analysis_service.AudioAnalyzer")
|
||||
@patch("backend.services.audio_analysis_service.WaveformGenerator")
|
||||
def test_init_with_custom_params(
|
||||
self, mock_waveform_class, mock_analyzer_class, mock_storage_class
|
||||
):
|
||||
"""Test initialization with custom threshold and duration."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
service = AudioAnalysisService(
|
||||
silence_threshold_db=-50.0,
|
||||
min_segment_duration_ms=200,
|
||||
)
|
||||
|
||||
mock_analyzer_class.assert_called_once_with(
|
||||
silence_threshold_db=-50.0,
|
||||
min_segment_duration_ms=200,
|
||||
)
|
||||
|
||||
@patch("backend.services.audio_analysis_service.AudioAnalyzer")
|
||||
@patch("backend.services.audio_analysis_service.WaveformGenerator")
|
||||
def test_init_with_provided_storage_service(
|
||||
self, mock_waveform_class, mock_analyzer_class
|
||||
):
|
||||
"""Test initialization with externally provided storage service."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
mock_storage = Mock()
|
||||
service = AudioAnalysisService(storage_service=mock_storage)
|
||||
|
||||
assert service.storage_service is mock_storage
|
||||
|
||||
|
||||
class TestAnalyzeBackingVocals:
|
||||
"""Test analyze_backing_vocals method."""
|
||||
|
||||
@patch("backend.services.audio_analysis_service.StorageService")
|
||||
@patch("backend.services.audio_analysis_service.AudioAnalyzer")
|
||||
@patch("backend.services.audio_analysis_service.WaveformGenerator")
|
||||
def test_analyze_downloads_and_analyzes(
|
||||
self, mock_waveform_class, mock_analyzer_class, mock_storage_class
|
||||
):
|
||||
"""Test analyze_backing_vocals downloads file and runs analysis."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
# Setup mocks
|
||||
mock_storage = Mock()
|
||||
mock_storage_class.return_value = mock_storage
|
||||
|
||||
mock_result = Mock()
|
||||
mock_result.has_audible_content = True
|
||||
mock_result.segment_count = 5
|
||||
mock_result.recommended_selection = Mock(value="with_backing")
|
||||
|
||||
mock_analyzer = Mock()
|
||||
mock_analyzer.analyze.return_value = mock_result
|
||||
mock_analyzer_class.return_value = mock_analyzer
|
||||
|
||||
service = AudioAnalysisService()
|
||||
|
||||
# Call method
|
||||
result = service.analyze_backing_vocals(
|
||||
gcs_audio_path="uploads/job123/backing_vocals.flac",
|
||||
job_id="job123",
|
||||
)
|
||||
|
||||
# Verify storage download was called
|
||||
mock_storage.download_file.assert_called_once()
|
||||
call_args = mock_storage.download_file.call_args
|
||||
assert call_args[0][0] == "uploads/job123/backing_vocals.flac"
|
||||
|
||||
# Verify analyzer was called
|
||||
mock_analyzer.analyze.assert_called_once()
|
||||
|
||||
# Verify result
|
||||
assert result is mock_result
|
||||
assert result.has_audible_content is True
|
||||
|
||||
@patch("backend.services.audio_analysis_service.StorageService")
|
||||
@patch("backend.services.audio_analysis_service.AudioAnalyzer")
|
||||
@patch("backend.services.audio_analysis_service.WaveformGenerator")
|
||||
def test_analyze_cleans_up_temp_files(
|
||||
self, mock_waveform_class, mock_analyzer_class, mock_storage_class
|
||||
):
|
||||
"""Test that temp files are cleaned up after analysis."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
mock_storage = Mock()
|
||||
mock_storage_class.return_value = mock_storage
|
||||
|
||||
mock_result = Mock()
|
||||
mock_result.has_audible_content = False
|
||||
mock_result.segment_count = 0
|
||||
mock_result.recommended_selection = Mock(value="clean")
|
||||
|
||||
mock_analyzer = Mock()
|
||||
mock_analyzer.analyze.return_value = mock_result
|
||||
mock_analyzer_class.return_value = mock_analyzer
|
||||
|
||||
service = AudioAnalysisService()
|
||||
|
||||
# Call method
|
||||
service.analyze_backing_vocals(
|
||||
gcs_audio_path="uploads/job123/backing.flac",
|
||||
job_id="job123",
|
||||
)
|
||||
|
||||
# Temp directory should be cleaned up (no assertion needed,
|
||||
# TemporaryDirectory context manager handles this)
|
||||
# Just verify the method completes without error
|
||||
|
||||
|
||||
class TestAnalyzeAndGenerateWaveform:
|
||||
"""Test analyze_and_generate_waveform method."""
|
||||
|
||||
@patch("backend.services.audio_analysis_service.StorageService")
|
||||
@patch("backend.services.audio_analysis_service.AudioAnalyzer")
|
||||
@patch("backend.services.audio_analysis_service.WaveformGenerator")
|
||||
def test_analyze_and_generate_waveform(
|
||||
self, mock_waveform_class, mock_analyzer_class, mock_storage_class
|
||||
):
|
||||
"""Test analyze_and_generate_waveform does both operations."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
mock_storage = Mock()
|
||||
mock_storage_class.return_value = mock_storage
|
||||
|
||||
mock_result = Mock()
|
||||
mock_result.has_audible_content = True
|
||||
mock_result.audible_segments = [Mock(), Mock()]
|
||||
|
||||
mock_analyzer = Mock()
|
||||
mock_analyzer.analyze.return_value = mock_result
|
||||
mock_analyzer.silence_threshold_db = -40.0
|
||||
mock_analyzer_class.return_value = mock_analyzer
|
||||
|
||||
mock_waveform = Mock()
|
||||
mock_waveform_class.return_value = mock_waveform
|
||||
|
||||
service = AudioAnalysisService()
|
||||
|
||||
# Call method
|
||||
result, waveform_path = service.analyze_and_generate_waveform(
|
||||
gcs_audio_path="uploads/job123/backing.flac",
|
||||
job_id="job123",
|
||||
gcs_waveform_destination="uploads/job123/waveform.png",
|
||||
)
|
||||
|
||||
# Verify analysis was performed
|
||||
mock_analyzer.analyze.assert_called_once()
|
||||
|
||||
# Verify waveform was generated
|
||||
mock_waveform.generate.assert_called_once()
|
||||
call_kwargs = mock_waveform.generate.call_args.kwargs
|
||||
assert call_kwargs["segments"] == mock_result.audible_segments
|
||||
assert call_kwargs["show_time_axis"] is True
|
||||
|
||||
# Verify waveform was uploaded
|
||||
assert mock_storage.upload_file.call_count == 1
|
||||
|
||||
# Verify return values
|
||||
assert result is mock_result
|
||||
assert waveform_path == "uploads/job123/waveform.png"
|
||||
|
||||
|
||||
class TestGetWaveformData:
|
||||
"""Test get_waveform_data method."""
|
||||
|
||||
@patch("backend.services.audio_analysis_service.StorageService")
|
||||
@patch("backend.services.audio_analysis_service.AudioAnalyzer")
|
||||
@patch("backend.services.audio_analysis_service.WaveformGenerator")
|
||||
def test_get_waveform_data(
|
||||
self, mock_waveform_class, mock_analyzer_class, mock_storage_class
|
||||
):
|
||||
"""Test get_waveform_data returns amplitude data."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
mock_storage = Mock()
|
||||
mock_storage_class.return_value = mock_storage
|
||||
|
||||
mock_waveform = Mock()
|
||||
mock_waveform.generate_data_only.return_value = (
|
||||
[0.1, 0.3, 0.5, 0.3, 0.1], # amplitudes
|
||||
180.5, # duration
|
||||
)
|
||||
mock_waveform_class.return_value = mock_waveform
|
||||
|
||||
service = AudioAnalysisService()
|
||||
|
||||
amplitudes, duration = service.get_waveform_data(
|
||||
gcs_audio_path="uploads/job123/backing.flac",
|
||||
job_id="job123",
|
||||
num_points=500,
|
||||
)
|
||||
|
||||
# Verify storage download
|
||||
mock_storage.download_file.assert_called_once()
|
||||
|
||||
# Verify waveform generator called
|
||||
mock_waveform.generate_data_only.assert_called_once()
|
||||
call_kwargs = mock_waveform.generate_data_only.call_args.kwargs
|
||||
assert call_kwargs["num_points"] == 500
|
||||
|
||||
# Verify return values
|
||||
assert amplitudes == [0.1, 0.3, 0.5, 0.3, 0.1]
|
||||
assert duration == 180.5
|
||||
|
||||
|
||||
class TestGenerateWaveformWithMutes:
|
||||
"""Test generate_waveform_with_mutes method."""
|
||||
|
||||
@patch("backend.services.audio_analysis_service.StorageService")
|
||||
@patch("backend.services.audio_analysis_service.AudioAnalyzer")
|
||||
@patch("backend.services.audio_analysis_service.WaveformGenerator")
|
||||
def test_generate_waveform_with_mutes(
|
||||
self, mock_waveform_class, mock_analyzer_class, mock_storage_class
|
||||
):
|
||||
"""Test generate_waveform_with_mutes highlights mute regions."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
mock_storage = Mock()
|
||||
mock_storage_class.return_value = mock_storage
|
||||
|
||||
mock_result = Mock()
|
||||
mock_result.audible_segments = [Mock(), Mock()]
|
||||
|
||||
mock_analyzer = Mock()
|
||||
mock_analyzer.analyze.return_value = mock_result
|
||||
mock_analyzer_class.return_value = mock_analyzer
|
||||
|
||||
mock_waveform = Mock()
|
||||
mock_waveform_class.return_value = mock_waveform
|
||||
|
||||
# Create mock mute regions
|
||||
mock_mute1 = Mock()
|
||||
mock_mute2 = Mock()
|
||||
mute_regions = [mock_mute1, mock_mute2]
|
||||
|
||||
service = AudioAnalysisService()
|
||||
|
||||
result_path = service.generate_waveform_with_mutes(
|
||||
gcs_audio_path="uploads/job123/backing.flac",
|
||||
job_id="job123",
|
||||
gcs_waveform_destination="uploads/job123/waveform_muted.png",
|
||||
mute_regions=mute_regions,
|
||||
)
|
||||
|
||||
# Verify waveform generator was called with mute_regions
|
||||
mock_waveform.generate.assert_called_once()
|
||||
call_kwargs = mock_waveform.generate.call_args.kwargs
|
||||
assert call_kwargs["mute_regions"] == mute_regions
|
||||
assert call_kwargs["segments"] == mock_result.audible_segments
|
||||
|
||||
# Verify upload
|
||||
mock_storage.upload_file.assert_called_once()
|
||||
|
||||
# Verify return
|
||||
assert result_path == "uploads/job123/waveform_muted.png"
|
||||
|
||||
@@ -0,0 +1,386 @@
|
||||
"""
|
||||
Tests for audio_editing_service.py - Custom instrumental creation.
|
||||
|
||||
These tests mock the storage service and shared karaoke_gen modules to verify:
|
||||
- GCS file download/upload operations
|
||||
- Audio editing delegation to shared AudioEditor
|
||||
- Mute region validation
|
||||
"""
|
||||
import pytest
|
||||
from unittest.mock import Mock, MagicMock, patch, ANY
|
||||
|
||||
|
||||
class TestAudioEditingServiceInit:
|
||||
"""Test AudioEditingService initialization."""
|
||||
|
||||
@patch("backend.services.audio_editing_service.StorageService")
|
||||
@patch("backend.services.audio_editing_service.AudioEditor")
|
||||
def test_init_creates_dependencies(self, mock_editor_class, mock_storage_class):
|
||||
"""Test initialization creates storage service and editor."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
service = AudioEditingService()
|
||||
|
||||
mock_storage_class.assert_called_once()
|
||||
mock_editor_class.assert_called_once_with(output_format="flac")
|
||||
|
||||
@patch("backend.services.audio_editing_service.StorageService")
|
||||
@patch("backend.services.audio_editing_service.AudioEditor")
|
||||
def test_init_with_custom_format(self, mock_editor_class, mock_storage_class):
|
||||
"""Test initialization with custom output format."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
service = AudioEditingService(output_format="wav")
|
||||
|
||||
mock_editor_class.assert_called_once_with(output_format="wav")
|
||||
|
||||
@patch("backend.services.audio_editing_service.AudioEditor")
|
||||
def test_init_with_provided_storage_service(self, mock_editor_class):
|
||||
"""Test initialization with externally provided storage service."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
mock_storage = Mock()
|
||||
service = AudioEditingService(storage_service=mock_storage)
|
||||
|
||||
assert service.storage_service is mock_storage
|
||||
|
||||
|
||||
class TestCreateCustomInstrumental:
|
||||
"""Test create_custom_instrumental method."""
|
||||
|
||||
@patch("backend.services.audio_editing_service.StorageService")
|
||||
@patch("backend.services.audio_editing_service.AudioEditor")
|
||||
def test_create_custom_instrumental_success(
|
||||
self, mock_editor_class, mock_storage_class
|
||||
):
|
||||
"""Test creating a custom instrumental successfully."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
mock_storage = Mock()
|
||||
mock_storage_class.return_value = mock_storage
|
||||
|
||||
mock_result = Mock()
|
||||
mock_result.total_muted_duration_seconds = 15.5
|
||||
mock_result.mute_regions_applied = [Mock(), Mock(), Mock()]
|
||||
mock_result.output_path = None # Will be set by service
|
||||
|
||||
mock_editor = Mock()
|
||||
mock_editor.create_custom_instrumental.return_value = mock_result
|
||||
mock_editor_class.return_value = mock_editor
|
||||
|
||||
service = AudioEditingService()
|
||||
|
||||
# Create mock mute regions
|
||||
mock_mute1 = Mock()
|
||||
mock_mute2 = Mock()
|
||||
mute_regions = [mock_mute1, mock_mute2]
|
||||
|
||||
result = service.create_custom_instrumental(
|
||||
gcs_clean_instrumental_path="uploads/job123/clean.flac",
|
||||
gcs_backing_vocals_path="uploads/job123/backing.flac",
|
||||
mute_regions=mute_regions,
|
||||
gcs_output_path="uploads/job123/custom.flac",
|
||||
job_id="job123",
|
||||
)
|
||||
|
||||
# Verify downloads
|
||||
assert mock_storage.download_file.call_count == 2
|
||||
|
||||
# Verify editor was called
|
||||
mock_editor.create_custom_instrumental.assert_called_once()
|
||||
call_kwargs = mock_editor.create_custom_instrumental.call_args.kwargs
|
||||
assert call_kwargs["mute_regions"] == mute_regions
|
||||
|
||||
# Verify upload
|
||||
mock_storage.upload_file.assert_called_once()
|
||||
|
||||
# Verify result path was updated
|
||||
assert result.output_path == "uploads/job123/custom.flac"
|
||||
|
||||
@patch("backend.services.audio_editing_service.StorageService")
|
||||
@patch("backend.services.audio_editing_service.AudioEditor")
|
||||
def test_create_custom_instrumental_downloads_both_files(
|
||||
self, mock_editor_class, mock_storage_class
|
||||
):
|
||||
"""Test that both input files are downloaded."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
mock_storage = Mock()
|
||||
mock_storage_class.return_value = mock_storage
|
||||
|
||||
mock_result = Mock()
|
||||
mock_result.total_muted_duration_seconds = 0
|
||||
mock_result.mute_regions_applied = []
|
||||
|
||||
mock_editor = Mock()
|
||||
mock_editor.create_custom_instrumental.return_value = mock_result
|
||||
mock_editor_class.return_value = mock_editor
|
||||
|
||||
service = AudioEditingService()
|
||||
|
||||
service.create_custom_instrumental(
|
||||
gcs_clean_instrumental_path="uploads/job123/clean.flac",
|
||||
gcs_backing_vocals_path="uploads/job123/backing.flac",
|
||||
mute_regions=[],
|
||||
gcs_output_path="uploads/job123/output.flac",
|
||||
job_id="job123",
|
||||
)
|
||||
|
||||
# Verify both files were downloaded
|
||||
download_calls = mock_storage.download_file.call_args_list
|
||||
assert len(download_calls) == 2
|
||||
|
||||
# First call should be clean instrumental
|
||||
assert download_calls[0][0][0] == "uploads/job123/clean.flac"
|
||||
# Second call should be backing vocals
|
||||
assert download_calls[1][0][0] == "uploads/job123/backing.flac"
|
||||
|
||||
|
||||
class TestCreatePreview:
|
||||
"""Test create_preview method."""
|
||||
|
||||
@patch("pydub.AudioSegment")
|
||||
@patch("backend.services.audio_editing_service.StorageService")
|
||||
@patch("backend.services.audio_editing_service.AudioEditor")
|
||||
def test_create_preview_success(
|
||||
self, mock_editor_class, mock_storage_class, mock_audio_segment
|
||||
):
|
||||
"""Test creating a preview successfully."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
mock_storage = Mock()
|
||||
mock_storage_class.return_value = mock_storage
|
||||
|
||||
mock_preview = Mock()
|
||||
mock_preview.export = Mock()
|
||||
mock_preview.__getitem__ = Mock(return_value=mock_preview)
|
||||
|
||||
mock_editor = Mock()
|
||||
mock_editor.preview_with_mutes.return_value = mock_preview
|
||||
mock_editor_class.return_value = mock_editor
|
||||
|
||||
service = AudioEditingService()
|
||||
|
||||
result = service.create_preview(
|
||||
gcs_clean_instrumental_path="uploads/job123/clean.flac",
|
||||
gcs_backing_vocals_path="uploads/job123/backing.flac",
|
||||
mute_regions=[Mock(), Mock()],
|
||||
gcs_preview_path="uploads/job123/preview.flac",
|
||||
job_id="job123",
|
||||
)
|
||||
|
||||
# Verify editor was called
|
||||
mock_editor.preview_with_mutes.assert_called_once()
|
||||
|
||||
# Verify result
|
||||
assert result == "uploads/job123/preview.flac"
|
||||
|
||||
@patch("pydub.AudioSegment")
|
||||
@patch("backend.services.audio_editing_service.StorageService")
|
||||
@patch("backend.services.audio_editing_service.AudioEditor")
|
||||
def test_create_preview_with_duration_limit(
|
||||
self, mock_editor_class, mock_storage_class, mock_audio_segment
|
||||
):
|
||||
"""Test creating a preview with duration limit."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
mock_storage = Mock()
|
||||
mock_storage_class.return_value = mock_storage
|
||||
|
||||
mock_preview = Mock()
|
||||
mock_truncated = Mock()
|
||||
mock_preview.__getitem__ = Mock(return_value=mock_truncated)
|
||||
mock_truncated.export = Mock()
|
||||
|
||||
mock_editor = Mock()
|
||||
mock_editor.preview_with_mutes.return_value = mock_preview
|
||||
mock_editor_class.return_value = mock_editor
|
||||
|
||||
service = AudioEditingService()
|
||||
|
||||
service.create_preview(
|
||||
gcs_clean_instrumental_path="uploads/job123/clean.flac",
|
||||
gcs_backing_vocals_path="uploads/job123/backing.flac",
|
||||
mute_regions=[],
|
||||
gcs_preview_path="uploads/job123/preview.flac",
|
||||
job_id="job123",
|
||||
preview_duration_seconds=30.0,
|
||||
)
|
||||
|
||||
# Verify preview was truncated (30 seconds = 30000ms)
|
||||
mock_preview.__getitem__.assert_called_once_with(slice(None, 30000))
|
||||
|
||||
|
||||
class TestMuteBackingVocalsOnly:
|
||||
"""Test mute_backing_vocals_only method."""
|
||||
|
||||
@patch("backend.services.audio_editing_service.StorageService")
|
||||
@patch("backend.services.audio_editing_service.AudioEditor")
|
||||
def test_mute_backing_vocals_only(self, mock_editor_class, mock_storage_class):
|
||||
"""Test muting backing vocals without combining."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
mock_storage = Mock()
|
||||
mock_storage_class.return_value = mock_storage
|
||||
|
||||
mock_editor = Mock()
|
||||
mock_editor_class.return_value = mock_editor
|
||||
|
||||
service = AudioEditingService()
|
||||
|
||||
mute_regions = [Mock(), Mock()]
|
||||
|
||||
result = service.mute_backing_vocals_only(
|
||||
gcs_backing_vocals_path="uploads/job123/backing.flac",
|
||||
mute_regions=mute_regions,
|
||||
gcs_output_path="uploads/job123/muted_backing.flac",
|
||||
job_id="job123",
|
||||
)
|
||||
|
||||
# Verify only one file was downloaded
|
||||
mock_storage.download_file.assert_called_once()
|
||||
assert mock_storage.download_file.call_args[0][0] == "uploads/job123/backing.flac"
|
||||
|
||||
# Verify editor method was called
|
||||
mock_editor.apply_mute_to_single_track.assert_called_once()
|
||||
call_kwargs = mock_editor.apply_mute_to_single_track.call_args.kwargs
|
||||
assert call_kwargs["mute_regions"] == mute_regions
|
||||
|
||||
# Verify upload
|
||||
mock_storage.upload_file.assert_called_once()
|
||||
|
||||
# Verify result
|
||||
assert result == "uploads/job123/muted_backing.flac"
|
||||
|
||||
|
||||
class TestValidateMuteRegions:
|
||||
"""Test validate_mute_regions method.
|
||||
|
||||
Note: MuteRegion uses pydantic validation that rejects invalid values at
|
||||
creation time. These tests use Mock objects to test the validation logic
|
||||
in the service, simulating edge cases that would normally be rejected.
|
||||
"""
|
||||
|
||||
@patch("backend.services.audio_editing_service.StorageService")
|
||||
@patch("backend.services.audio_editing_service.AudioEditor")
|
||||
def test_valid_mute_regions(self, mock_editor_class, mock_storage_class):
|
||||
"""Test validation passes for valid mute regions."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
from karaoke_gen.instrumental_review import MuteRegion
|
||||
|
||||
service = AudioEditingService()
|
||||
|
||||
mute_regions = [
|
||||
MuteRegion(start_seconds=10.0, end_seconds=15.0),
|
||||
MuteRegion(start_seconds=30.0, end_seconds=45.0),
|
||||
]
|
||||
|
||||
errors = service.validate_mute_regions(mute_regions, total_duration_seconds=180.0)
|
||||
|
||||
assert errors == []
|
||||
|
||||
@patch("backend.services.audio_editing_service.StorageService")
|
||||
@patch("backend.services.audio_editing_service.AudioEditor")
|
||||
def test_negative_start_seconds(self, mock_editor_class, mock_storage_class):
|
||||
"""Test validation catches negative start time.
|
||||
|
||||
Uses Mock since MuteRegion pydantic model rejects negative values.
|
||||
"""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
service = AudioEditingService()
|
||||
|
||||
# Use mock to simulate invalid region (pydantic would reject this)
|
||||
mock_region = Mock()
|
||||
mock_region.start_seconds = -5.0
|
||||
mock_region.end_seconds = 10.0
|
||||
|
||||
errors = service.validate_mute_regions([mock_region], total_duration_seconds=180.0)
|
||||
|
||||
assert len(errors) == 1
|
||||
assert "cannot be negative" in errors[0]
|
||||
|
||||
@patch("backend.services.audio_editing_service.StorageService")
|
||||
@patch("backend.services.audio_editing_service.AudioEditor")
|
||||
def test_end_before_start(self, mock_editor_class, mock_storage_class):
|
||||
"""Test validation catches end time before start time."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
service = AudioEditingService()
|
||||
|
||||
# Use mock to simulate invalid region
|
||||
mock_region = Mock()
|
||||
mock_region.start_seconds = 30.0
|
||||
mock_region.end_seconds = 20.0
|
||||
|
||||
errors = service.validate_mute_regions([mock_region], total_duration_seconds=180.0)
|
||||
|
||||
assert len(errors) == 1
|
||||
assert "must be after" in errors[0]
|
||||
|
||||
@patch("backend.services.audio_editing_service.StorageService")
|
||||
@patch("backend.services.audio_editing_service.AudioEditor")
|
||||
def test_start_exceeds_duration(self, mock_editor_class, mock_storage_class):
|
||||
"""Test validation catches start time exceeding audio duration."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
from karaoke_gen.instrumental_review import MuteRegion
|
||||
|
||||
service = AudioEditingService()
|
||||
|
||||
mute_regions = [
|
||||
MuteRegion(start_seconds=200.0, end_seconds=210.0),
|
||||
]
|
||||
|
||||
errors = service.validate_mute_regions(mute_regions, total_duration_seconds=180.0)
|
||||
|
||||
assert len(errors) == 1
|
||||
assert "exceeds audio duration" in errors[0]
|
||||
|
||||
@patch("backend.services.audio_editing_service.StorageService")
|
||||
@patch("backend.services.audio_editing_service.AudioEditor")
|
||||
def test_end_exceeds_duration_is_warning_not_error(
|
||||
self, mock_editor_class, mock_storage_class
|
||||
):
|
||||
"""Test that end time exceeding duration is logged as warning, not error."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
from karaoke_gen.instrumental_review import MuteRegion
|
||||
|
||||
service = AudioEditingService()
|
||||
|
||||
mute_regions = [
|
||||
MuteRegion(start_seconds=170.0, end_seconds=200.0), # End exceeds 180s
|
||||
]
|
||||
|
||||
errors = service.validate_mute_regions(mute_regions, total_duration_seconds=180.0)
|
||||
|
||||
# Should not be an error (will be clamped)
|
||||
assert len(errors) == 0
|
||||
|
||||
@patch("backend.services.audio_editing_service.StorageService")
|
||||
@patch("backend.services.audio_editing_service.AudioEditor")
|
||||
def test_multiple_errors(self, mock_editor_class, mock_storage_class):
|
||||
"""Test validation reports multiple errors."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
from karaoke_gen.instrumental_review import MuteRegion
|
||||
|
||||
service = AudioEditingService()
|
||||
|
||||
# Use mocks for invalid regions
|
||||
mock_region1 = Mock()
|
||||
mock_region1.start_seconds = -5.0
|
||||
mock_region1.end_seconds = 10.0
|
||||
|
||||
mock_region2 = Mock()
|
||||
mock_region2.start_seconds = 30.0
|
||||
mock_region2.end_seconds = 20.0 # End before start
|
||||
|
||||
mock_region3 = Mock()
|
||||
mock_region3.start_seconds = 200.0 # Exceeds duration
|
||||
mock_region3.end_seconds = 210.0
|
||||
|
||||
mute_regions = [mock_region1, mock_region2, mock_region3]
|
||||
|
||||
errors = service.validate_mute_regions(mute_regions, total_duration_seconds=180.0)
|
||||
|
||||
assert len(errors) == 3
|
||||
|
||||
File diff suppressed because it is too large.
Load diff
@@ -0,0 +1,378 @@
|
||||
"""
|
||||
Unit tests for audio analysis and editing services.
|
||||
|
||||
These tests verify the backend service wrappers that use the shared
|
||||
karaoke_gen.instrumental_review module with GCS integration.
|
||||
|
||||
NOTE: These tests require ffmpeg to be installed. They will be skipped
|
||||
if ffmpeg is not available (e.g., in CI environments without ffmpeg).
|
||||
"""
|
||||
|
||||
import os
|
||||
import shutil
|
||||
import tempfile
|
||||
import pytest
|
||||
from unittest.mock import MagicMock, patch, ANY
|
||||
|
||||
# Check if ffmpeg is available
|
||||
def _ffmpeg_available():
|
||||
"""Check if ffmpeg is available on the system."""
|
||||
return shutil.which('ffmpeg') is not None
|
||||
|
||||
# Skip all tests in this module if ffmpeg is not available
|
||||
pytestmark = pytest.mark.skipif(
|
||||
not _ffmpeg_available(),
|
||||
reason="ffmpeg not available - required for audio processing tests"
|
||||
)
|
||||
|
||||
from pydub import AudioSegment
|
||||
from pydub.generators import Sine
|
||||
|
||||
from karaoke_gen.instrumental_review import MuteRegion
|
||||
|
||||
|
||||
class TestAudioAnalysisService:
|
||||
"""Tests for AudioAnalysisService."""
|
||||
|
||||
@pytest.fixture
|
||||
def mock_storage_service(self):
|
||||
"""Create a mock storage service."""
|
||||
mock = MagicMock()
|
||||
return mock
|
||||
|
||||
@pytest.fixture
|
||||
def temp_audio_file(self, tmp_path):
|
||||
"""Create a temporary audio file for testing."""
|
||||
audio_path = tmp_path / "test_audio.flac"
|
||||
|
||||
# Create a simple sine wave audio
|
||||
tone = Sine(440).to_audio_segment(duration=5000) - 15
|
||||
tone.export(str(audio_path), format="flac")
|
||||
|
||||
return str(audio_path)
|
||||
|
||||
@pytest.fixture
|
||||
def silent_audio_file(self, tmp_path):
|
||||
"""Create a silent audio file for testing."""
|
||||
audio_path = tmp_path / "silent_audio.flac"
|
||||
|
||||
audio = AudioSegment.silent(duration=5000, frame_rate=44100)
|
||||
audio.export(str(audio_path), format="flac")
|
||||
|
||||
return str(audio_path)
|
||||
|
||||
def test_service_initialization(self, mock_storage_service):
|
||||
"""Test service initializes with default parameters."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
service = AudioAnalysisService(storage_service=mock_storage_service)
|
||||
|
||||
assert service.storage_service == mock_storage_service
|
||||
assert service.analyzer.silence_threshold_db == -40.0
|
||||
|
||||
def test_service_custom_threshold(self, mock_storage_service):
|
||||
"""Test service accepts custom silence threshold."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
service = AudioAnalysisService(
|
||||
storage_service=mock_storage_service,
|
||||
silence_threshold_db=-35.0,
|
||||
)
|
||||
|
||||
assert service.analyzer.silence_threshold_db == -35.0
|
||||
|
||||
def test_analyze_backing_vocals_downloads_file(
|
||||
self, mock_storage_service, temp_audio_file
|
||||
):
|
||||
"""Test that analyze_backing_vocals downloads file from GCS."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
# Set up mock to copy the temp file to the download location
|
||||
def mock_download(gcs_path, local_path):
|
||||
import shutil
|
||||
shutil.copy(temp_audio_file, local_path)
|
||||
return local_path
|
||||
|
||||
mock_storage_service.download_file.side_effect = mock_download
|
||||
|
||||
service = AudioAnalysisService(storage_service=mock_storage_service)
|
||||
result = service.analyze_backing_vocals(
|
||||
gcs_audio_path="jobs/test/stems/backing_vocals.flac",
|
||||
job_id="test-job",
|
||||
)
|
||||
|
||||
# Verify download was called
|
||||
mock_storage_service.download_file.assert_called_once()
|
||||
|
||||
# Verify result is valid
|
||||
assert result is not None
|
||||
assert hasattr(result, 'has_audible_content')
|
||||
|
||||
def test_analyze_silent_audio_returns_no_audible(
|
||||
self, mock_storage_service, silent_audio_file
|
||||
):
|
||||
"""Test that silent audio returns has_audible_content=False."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
def mock_download(gcs_path, local_path):
|
||||
import shutil
|
||||
shutil.copy(silent_audio_file, local_path)
|
||||
return local_path
|
||||
|
||||
mock_storage_service.download_file.side_effect = mock_download
|
||||
|
||||
service = AudioAnalysisService(storage_service=mock_storage_service)
|
||||
result = service.analyze_backing_vocals(
|
||||
gcs_audio_path="jobs/test/stems/backing_vocals.flac",
|
||||
job_id="test-job",
|
||||
)
|
||||
|
||||
assert result.has_audible_content is False
|
||||
assert len(result.audible_segments) == 0
|
||||
|
||||
def test_analyze_and_generate_waveform_uploads_image(
|
||||
self, mock_storage_service, temp_audio_file
|
||||
):
|
||||
"""Test that analyze_and_generate_waveform uploads waveform to GCS."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
def mock_download(gcs_path, local_path):
|
||||
import shutil
|
||||
shutil.copy(temp_audio_file, local_path)
|
||||
return local_path
|
||||
|
||||
mock_storage_service.download_file.side_effect = mock_download
|
||||
mock_storage_service.upload_file.return_value = "jobs/test/analysis/waveform.png"
|
||||
|
||||
service = AudioAnalysisService(storage_service=mock_storage_service)
|
||||
result, waveform_path = service.analyze_and_generate_waveform(
|
||||
gcs_audio_path="jobs/test/stems/backing_vocals.flac",
|
||||
job_id="test-job",
|
||||
gcs_waveform_destination="jobs/test/analysis/waveform.png",
|
||||
)
|
||||
|
||||
# Verify upload was called
|
||||
mock_storage_service.upload_file.assert_called_once()
|
||||
|
||||
# Verify waveform path is returned
|
||||
assert waveform_path == "jobs/test/analysis/waveform.png"
|
||||
|
||||
def test_get_waveform_data_returns_amplitudes(
|
||||
self, mock_storage_service, temp_audio_file
|
||||
):
|
||||
"""Test that get_waveform_data returns amplitude data."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
def mock_download(gcs_path, local_path):
|
||||
import shutil
|
||||
shutil.copy(temp_audio_file, local_path)
|
||||
return local_path
|
||||
|
||||
mock_storage_service.download_file.side_effect = mock_download
|
||||
|
||||
service = AudioAnalysisService(storage_service=mock_storage_service)
|
||||
amplitudes, duration = service.get_waveform_data(
|
||||
gcs_audio_path="jobs/test/stems/backing_vocals.flac",
|
||||
job_id="test-job",
|
||||
num_points=100,
|
||||
)
|
||||
|
||||
# Verify we get amplitude data
|
||||
assert isinstance(amplitudes, list)
|
||||
assert len(amplitudes) > 0
|
||||
assert all(isinstance(a, float) for a in amplitudes)
|
||||
|
||||
# Verify duration is reasonable
|
||||
assert duration > 0
|
||||
assert duration <= 10 # Our test file is 5 seconds
|
||||
|
||||
|
||||
class TestAudioEditingService:
|
||||
"""Tests for AudioEditingService."""
|
||||
|
||||
@pytest.fixture
|
||||
def mock_storage_service(self):
|
||||
"""Create a mock storage service."""
|
||||
mock = MagicMock()
|
||||
return mock
|
||||
|
||||
@pytest.fixture
|
||||
def temp_audio_files(self, tmp_path):
|
||||
"""Create temporary audio files for testing."""
|
||||
clean_path = tmp_path / "clean_instrumental.flac"
|
||||
backing_path = tmp_path / "backing_vocals.flac"
|
||||
|
||||
# Create clean instrumental (chord)
|
||||
tone1 = Sine(220).to_audio_segment(duration=5000) - 15
|
||||
tone2 = Sine(330).to_audio_segment(duration=5000) - 15
|
||||
clean = tone1.overlay(tone2)
|
||||
clean.export(str(clean_path), format="flac")
|
||||
|
||||
# Create backing vocals
|
||||
backing = Sine(440).to_audio_segment(duration=5000) - 20
|
||||
backing.export(str(backing_path), format="flac")
|
||||
|
||||
return str(clean_path), str(backing_path)
|
||||
|
||||
def test_service_initialization(self, mock_storage_service):
|
||||
"""Test service initializes correctly."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
service = AudioEditingService(storage_service=mock_storage_service)
|
||||
|
||||
assert service.storage_service == mock_storage_service
|
||||
assert service.editor.output_format == "flac"
|
||||
|
||||
def test_create_custom_instrumental_downloads_files(
|
||||
self, mock_storage_service, temp_audio_files
|
||||
):
|
||||
"""Test that create_custom_instrumental downloads input files."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
clean_path, backing_path = temp_audio_files
|
||||
|
||||
# Track which files were downloaded
|
||||
downloaded_files = []
|
||||
|
||||
def mock_download(gcs_path, local_path):
|
||||
downloaded_files.append(gcs_path)
|
||||
# Copy the appropriate test file
|
||||
import shutil
|
||||
if 'clean' in gcs_path:
|
||||
shutil.copy(clean_path, local_path)
|
||||
else:
|
||||
shutil.copy(backing_path, local_path)
|
||||
return local_path
|
||||
|
||||
mock_storage_service.download_file.side_effect = mock_download
|
||||
mock_storage_service.upload_file.return_value = "jobs/test/stems/custom.flac"
|
||||
|
||||
service = AudioEditingService(storage_service=mock_storage_service)
|
||||
|
||||
mute_regions = [MuteRegion(start_seconds=1.0, end_seconds=2.0)]
|
||||
|
||||
result = service.create_custom_instrumental(
|
||||
gcs_clean_instrumental_path="jobs/test/stems/clean.flac",
|
||||
gcs_backing_vocals_path="jobs/test/stems/backing.flac",
|
||||
mute_regions=mute_regions,
|
||||
gcs_output_path="jobs/test/stems/custom.flac",
|
||||
job_id="test-job",
|
||||
)
|
||||
|
||||
# Verify both files were downloaded
|
||||
assert len(downloaded_files) == 2
|
||||
assert mock_storage_service.upload_file.called
|
||||
|
||||
def test_create_custom_instrumental_uploads_result(
|
||||
self, mock_storage_service, temp_audio_files
|
||||
):
|
||||
"""Test that create_custom_instrumental uploads the result."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
clean_path, backing_path = temp_audio_files
|
||||
|
||||
def mock_download(gcs_path, local_path):
|
||||
import shutil
|
||||
if 'clean' in gcs_path:
|
||||
shutil.copy(clean_path, local_path)
|
||||
else:
|
||||
shutil.copy(backing_path, local_path)
|
||||
return local_path
|
||||
|
||||
mock_storage_service.download_file.side_effect = mock_download
|
||||
mock_storage_service.upload_file.return_value = "jobs/test/stems/custom.flac"
|
||||
|
||||
service = AudioEditingService(storage_service=mock_storage_service)
|
||||
|
||||
mute_regions = [MuteRegion(start_seconds=1.0, end_seconds=2.0)]
|
||||
|
||||
result = service.create_custom_instrumental(
|
||||
gcs_clean_instrumental_path="jobs/test/stems/clean.flac",
|
||||
gcs_backing_vocals_path="jobs/test/stems/backing.flac",
|
||||
mute_regions=mute_regions,
|
||||
gcs_output_path="jobs/test/stems/custom.flac",
|
||||
job_id="test-job",
|
||||
)
|
||||
|
||||
# Verify upload was called with correct destination
|
||||
mock_storage_service.upload_file.assert_called_once()
|
||||
call_args = mock_storage_service.upload_file.call_args
|
||||
assert call_args[0][1] == "jobs/test/stems/custom.flac"
|
||||
|
||||
# Verify result has correct path
|
||||
assert result.output_path == "jobs/test/stems/custom.flac"
|
||||
|
||||
def test_create_custom_instrumental_returns_statistics(
|
||||
self, mock_storage_service, temp_audio_files
|
||||
):
|
||||
"""Test that create_custom_instrumental returns correct statistics."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
clean_path, backing_path = temp_audio_files
|
||||
|
||||
def mock_download(gcs_path, local_path):
|
||||
import shutil
|
||||
if 'clean' in gcs_path:
|
||||
shutil.copy(clean_path, local_path)
|
||||
else:
|
||||
shutil.copy(backing_path, local_path)
|
||||
return local_path
|
||||
|
||||
mock_storage_service.download_file.side_effect = mock_download
|
||||
mock_storage_service.upload_file.return_value = "jobs/test/stems/custom.flac"
|
||||
|
||||
service = AudioEditingService(storage_service=mock_storage_service)
|
||||
|
||||
mute_regions = [
|
||||
MuteRegion(start_seconds=1.0, end_seconds=2.0),
|
||||
MuteRegion(start_seconds=3.0, end_seconds=4.0),
|
||||
]
|
||||
|
||||
result = service.create_custom_instrumental(
|
||||
gcs_clean_instrumental_path="jobs/test/stems/clean.flac",
|
||||
gcs_backing_vocals_path="jobs/test/stems/backing.flac",
|
||||
mute_regions=mute_regions,
|
||||
gcs_output_path="jobs/test/stems/custom.flac",
|
||||
job_id="test-job",
|
||||
)
|
||||
|
||||
# Verify statistics
|
||||
assert len(result.mute_regions_applied) == 2
|
||||
assert result.total_muted_duration_seconds == 2.0 # 1s + 1s
|
||||
assert result.output_duration_seconds > 0
|
||||
|
||||
def test_validate_mute_regions_returns_errors_for_invalid(
|
||||
self, mock_storage_service
|
||||
):
|
||||
"""Test that validate_mute_regions catches invalid regions."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
service = AudioEditingService(storage_service=mock_storage_service)
|
||||
|
||||
mute_regions = [
|
||||
MuteRegion(start_seconds=0.0, end_seconds=1.0), # Valid
|
||||
MuteRegion(start_seconds=100.0, end_seconds=110.0), # Beyond duration
|
||||
]
|
||||
|
||||
errors = service.validate_mute_regions(mute_regions, total_duration_seconds=60.0)
|
||||
|
||||
# Should have error for region exceeding duration
|
||||
assert len(errors) == 1
|
||||
assert "exceeds" in errors[0].lower()
|
||||
|
||||
def test_validate_mute_regions_returns_empty_for_valid(
|
||||
self, mock_storage_service
|
||||
):
|
||||
"""Test that validate_mute_regions returns empty for valid regions."""
|
||||
from backend.services.audio_editing_service import AudioEditingService
|
||||
|
||||
service = AudioEditingService(storage_service=mock_storage_service)
|
||||
|
||||
mute_regions = [
|
||||
MuteRegion(start_seconds=0.0, end_seconds=1.0),
|
||||
MuteRegion(start_seconds=10.0, end_seconds=15.0),
|
||||
]
|
||||
|
||||
errors = service.validate_mute_regions(mute_regions, total_duration_seconds=60.0)
|
||||
|
||||
assert len(errors) == 0
|
||||
@@ -0,0 +1,408 @@
|
||||
"""
|
||||
Tests for dropbox_service.py - Dropbox file operations.
|
||||
|
||||
These tests mock the Dropbox SDK and Secret Manager to verify:
|
||||
- Credential loading from Secret Manager
|
||||
- Folder listing and brand code calculation
|
||||
- File and folder uploads
|
||||
- Shared link creation
|
||||
"""
|
||||
import json
|
||||
import os
|
||||
import pytest
|
||||
from unittest.mock import Mock, MagicMock, patch
|
||||
|
||||
|
||||
class TestDropboxServiceInit:
|
||||
"""Test DropboxService initialization."""
|
||||
|
||||
def test_init_creates_service(self):
|
||||
"""Test initialization creates service with no client."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
|
||||
service = DropboxService()
|
||||
|
||||
assert service._client is None
|
||||
assert service._is_configured is False
|
||||
|
||||
|
||||
class TestLoadCredentials:
|
||||
"""Test _load_credentials method."""
|
||||
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_load_credentials_success(self, mock_sm_client_class):
|
||||
"""Test successful credential loading from Secret Manager."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_response = Mock()
|
||||
mock_response.payload.data = json.dumps({
|
||||
"access_token": "access-token-123",
|
||||
"refresh_token": "refresh-token-456",
|
||||
"app_key": "app-key",
|
||||
"app_secret": "app-secret",
|
||||
}).encode("UTF-8")
|
||||
mock_sm_client.access_secret_version.return_value = mock_response
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
service = DropboxService()
|
||||
creds = service._load_credentials()
|
||||
|
||||
assert creds is not None
|
||||
assert creds["access_token"] == "access-token-123"
|
||||
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_load_credentials_failure(self, mock_sm_client_class):
|
||||
"""Test handling when Secret Manager fails."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_sm_client.access_secret_version.side_effect = Exception("Access denied")
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
service = DropboxService()
|
||||
creds = service._load_credentials()
|
||||
|
||||
assert creds is None
|
||||
|
||||
|
||||
class TestIsConfigured:
|
||||
"""Test is_configured property."""
|
||||
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_is_configured_true(self, mock_sm_client_class):
|
||||
"""Test is_configured returns True when credentials available."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_response = Mock()
|
||||
mock_response.payload.data = json.dumps({
|
||||
"access_token": "token"
|
||||
}).encode("UTF-8")
|
||||
mock_sm_client.access_secret_version.return_value = mock_response
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
service = DropboxService()
|
||||
|
||||
assert service.is_configured is True
|
||||
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_is_configured_false_no_token(self, mock_sm_client_class):
|
||||
"""Test is_configured returns False when no access_token."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_response = Mock()
|
||||
mock_response.payload.data = json.dumps({
|
||||
"refresh_token": "refresh" # Missing access_token
|
||||
}).encode("UTF-8")
|
||||
mock_sm_client.access_secret_version.return_value = mock_response
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
service = DropboxService()
|
||||
|
||||
assert service.is_configured is False
|
||||
|
||||
|
||||
class TestDropboxClient:
|
||||
"""Test client property."""
|
||||
|
||||
@patch("dropbox.Dropbox")
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_client_creates_dropbox_instance(self, mock_sm_client_class, mock_dropbox_class):
|
||||
"""Test client property creates Dropbox SDK client."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_response = Mock()
|
||||
mock_response.payload.data = json.dumps({
|
||||
"access_token": "token",
|
||||
"refresh_token": "refresh",
|
||||
"app_key": "key",
|
||||
"app_secret": "secret",
|
||||
}).encode("UTF-8")
|
||||
mock_sm_client.access_secret_version.return_value = mock_response
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
mock_dropbox = Mock()
|
||||
mock_dropbox_class.return_value = mock_dropbox
|
||||
|
||||
service = DropboxService()
|
||||
client = service.client
|
||||
|
||||
mock_dropbox_class.assert_called_once_with(
|
||||
oauth2_access_token="token",
|
||||
oauth2_refresh_token="refresh",
|
||||
app_key="key",
|
||||
app_secret="secret",
|
||||
)
|
||||
assert client == mock_dropbox
|
||||
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_client_raises_on_missing_credentials(self, mock_sm_client_class):
|
||||
"""Test client raises RuntimeError when credentials missing."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_sm_client.access_secret_version.side_effect = Exception("Not found")
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
service = DropboxService()
|
||||
|
||||
with pytest.raises(RuntimeError) as exc_info:
|
||||
_ = service.client
|
||||
|
||||
assert "not configured" in str(exc_info.value)
|
||||
|
||||
|
||||
class TestListFolders:
|
||||
"""Test list_folders method."""
|
||||
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_list_folders(self, mock_sm_client_class):
|
||||
"""Test listing folders at a path."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
from dropbox.files import FolderMetadata
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_response = Mock()
|
||||
mock_response.payload.data = json.dumps({"access_token": "token"}).encode()
|
||||
mock_sm_client.access_secret_version.return_value = mock_response
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
# Create mock folder entries
|
||||
mock_folder1 = Mock(spec=FolderMetadata)
|
||||
mock_folder1.name = "NOMAD-0001"
|
||||
mock_folder2 = Mock(spec=FolderMetadata)
|
||||
mock_folder2.name = "NOMAD-0002"
|
||||
mock_file = Mock() # Not a FolderMetadata
|
||||
|
||||
mock_result = Mock()
|
||||
mock_result.entries = [mock_folder1, mock_folder2, mock_file]
|
||||
mock_result.has_more = False
|
||||
|
||||
service = DropboxService()
|
||||
# Directly set the client to avoid needing to mock the whole init chain
|
||||
mock_dropbox = Mock()
|
||||
mock_dropbox.files_list_folder.return_value = mock_result
|
||||
service._client = mock_dropbox
|
||||
|
||||
folders = service.list_folders("/Karaoke/Tracks")
|
||||
|
||||
mock_dropbox.files_list_folder.assert_called_once_with("/Karaoke/Tracks")
|
||||
assert folders == ["NOMAD-0001", "NOMAD-0002"]
|
||||
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_list_folders_adds_leading_slash(self, mock_sm_client_class):
|
||||
"""Test that path without leading slash gets one added."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_response = Mock()
|
||||
mock_response.payload.data = json.dumps({"access_token": "token"}).encode()
|
||||
mock_sm_client.access_secret_version.return_value = mock_response
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
mock_result = Mock()
|
||||
mock_result.entries = []
|
||||
mock_result.has_more = False
|
||||
|
||||
service = DropboxService()
|
||||
mock_dropbox = Mock()
|
||||
mock_dropbox.files_list_folder.return_value = mock_result
|
||||
service._client = mock_dropbox
|
||||
|
||||
service.list_folders("path/without/slash")
|
||||
|
||||
mock_dropbox.files_list_folder.assert_called_once_with("/path/without/slash")
|
||||
|
||||
|
||||
class TestGetNextBrandCode:
|
||||
"""Test get_next_brand_code method."""
|
||||
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_get_next_brand_code(self, mock_sm_client_class):
|
||||
"""Test calculating next brand code from existing folders."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_response = Mock()
|
||||
mock_response.payload.data = json.dumps({"access_token": "token"}).encode()
|
||||
mock_sm_client.access_secret_version.return_value = mock_response
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
service = DropboxService()
|
||||
|
||||
# Mock list_folders to return existing codes
|
||||
with patch.object(service, "list_folders") as mock_list:
|
||||
mock_list.return_value = [
|
||||
"NOMAD-1161",
|
||||
"NOMAD-1162",
|
||||
"NOMAD-1163",
|
||||
"Other Folder",
|
||||
"NOMAD-0001",
|
||||
]
|
||||
|
||||
next_code = service.get_next_brand_code("/path", "NOMAD")
|
||||
|
||||
assert next_code == "NOMAD-1164"
|
||||
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_get_next_brand_code_empty_folder(self, mock_sm_client_class):
|
||||
"""Test brand code calculation with no existing codes."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_response = Mock()
|
||||
mock_response.payload.data = json.dumps({"access_token": "token"}).encode()
|
||||
mock_sm_client.access_secret_version.return_value = mock_response
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
service = DropboxService()
|
||||
|
||||
with patch.object(service, "list_folders") as mock_list:
|
||||
mock_list.return_value = []
|
||||
|
||||
next_code = service.get_next_brand_code("/path", "BRAND")
|
||||
|
||||
assert next_code == "BRAND-0001"
|
||||
|
||||
|
||||
class TestUploadFile:
|
||||
"""Test upload_file method."""
|
||||
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_upload_small_file(self, mock_sm_client_class, tmp_path):
|
||||
"""Test uploading a small file directly."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_response = Mock()
|
||||
mock_response.payload.data = json.dumps({"access_token": "token"}).encode()
|
||||
mock_sm_client.access_secret_version.return_value = mock_response
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
# Create test file
|
||||
test_file = tmp_path / "test.txt"
|
||||
test_file.write_text("Small file content")
|
||||
|
||||
service = DropboxService()
|
||||
mock_dropbox = Mock()
|
||||
service._client = mock_dropbox
|
||||
|
||||
service.upload_file(str(test_file), "/Uploads/test.txt")
|
||||
|
||||
mock_dropbox.files_upload.assert_called_once()
|
||||
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_upload_file_adds_leading_slash(self, mock_sm_client_class, tmp_path):
|
||||
"""Test upload adds leading slash to remote path."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_response = Mock()
|
||||
mock_response.payload.data = json.dumps({"access_token": "token"}).encode()
|
||||
mock_sm_client.access_secret_version.return_value = mock_response
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
test_file = tmp_path / "test.txt"
|
||||
test_file.write_text("content")
|
||||
|
||||
service = DropboxService()
|
||||
mock_dropbox = Mock()
|
||||
service._client = mock_dropbox
|
||||
|
||||
service.upload_file(str(test_file), "uploads/test.txt")
|
||||
|
||||
# Check that the path has leading slash
|
||||
call_args = mock_dropbox.files_upload.call_args
|
||||
assert call_args[0][1] == "/uploads/test.txt"
|
||||
|
||||
|
||||
class TestUploadFolder:
|
||||
"""Test upload_folder method."""
|
||||
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_upload_folder(self, mock_sm_client_class, tmp_path):
|
||||
"""Test uploading a folder with multiple files."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_response = Mock()
|
||||
mock_response.payload.data = json.dumps({"access_token": "token"}).encode()
|
||||
mock_sm_client.access_secret_version.return_value = mock_response
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
# Create test folder with files
|
||||
(tmp_path / "file1.txt").write_text("content1")
|
||||
(tmp_path / "file2.txt").write_text("content2")
|
||||
(tmp_path / "subdir").mkdir() # Should be skipped
|
||||
|
||||
service = DropboxService()
|
||||
|
||||
with patch.object(service, "upload_file") as mock_upload:
|
||||
service.upload_folder(str(tmp_path), "/Uploads/folder")
|
||||
|
||||
# Should upload 2 files (not subdir)
|
||||
assert mock_upload.call_count == 2
|
||||
|
||||
|
||||
class TestCreateSharedLink:
|
||||
"""Test create_shared_link method."""
|
||||
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_create_shared_link_new(self, mock_sm_client_class):
|
||||
"""Test creating a new shared link."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_response = Mock()
|
||||
mock_response.payload.data = json.dumps({"access_token": "token"}).encode()
|
||||
mock_sm_client.access_secret_version.return_value = mock_response
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
mock_link = Mock()
|
||||
mock_link.url = "https://dropbox.com/s/abc123/file.mp4"
|
||||
|
||||
service = DropboxService()
|
||||
mock_dropbox = Mock()
|
||||
mock_dropbox.sharing_create_shared_link_with_settings.return_value = mock_link
|
||||
service._client = mock_dropbox
|
||||
|
||||
url = service.create_shared_link("/Uploads/file.mp4")
|
||||
|
||||
assert url == "https://dropbox.com/s/abc123/file.mp4"
|
||||
|
||||
@patch("backend.services.dropbox_service.secretmanager.SecretManagerServiceClient")
|
||||
def test_create_shared_link_existing(self, mock_sm_client_class):
|
||||
"""Test getting existing shared link when one already exists."""
|
||||
from backend.services.dropbox_service import DropboxService
|
||||
from dropbox.exceptions import ApiError
|
||||
|
||||
mock_sm_client = Mock()
|
||||
mock_response = Mock()
|
||||
mock_response.payload.data = json.dumps({"access_token": "token"}).encode()
|
||||
mock_sm_client.access_secret_version.return_value = mock_response
|
||||
mock_sm_client_class.return_value = mock_sm_client
|
||||
|
||||
# Simulate "link already exists" error
|
||||
mock_error = Mock()
|
||||
mock_error.is_shared_link_already_exists.return_value = True
|
||||
|
||||
mock_existing_link = Mock()
|
||||
mock_existing_link.url = "https://dropbox.com/s/existing/file.mp4"
|
||||
|
||||
mock_links_result = Mock()
|
||||
mock_links_result.links = [mock_existing_link]
|
||||
|
||||
service = DropboxService()
|
||||
mock_dropbox = Mock()
|
||||
mock_dropbox.sharing_create_shared_link_with_settings.side_effect = \
|
||||
ApiError("req_id", mock_error, "message", "headers")
|
||||
mock_dropbox.sharing_list_shared_links.return_value = mock_links_result
|
||||
service._client = mock_dropbox
|
||||
|
||||
url = service.create_shared_link("/Uploads/file.mp4")
|
||||
|
||||
assert url == "https://dropbox.com/s/existing/file.mp4"
|
||||
|
||||
@@ -96,15 +96,15 @@ def auth_headers():
|
||||
class TestEmulatorBasics:
|
||||
"""Basic emulator connectivity tests."""
|
||||
|
||||
def test_health_endpoint(self, client):
|
||||
def test_health_endpoint(self, client, auth_headers):
|
||||
"""Test health endpoint works."""
|
||||
response = client.get("/api/health")
|
||||
response = client.get("/api/health", )
|
||||
assert response.status_code == 200
|
||||
assert response.json()["status"] == "healthy"
|
||||
|
||||
def test_root_endpoint(self, client):
|
||||
def test_root_endpoint(self, client, auth_headers):
|
||||
"""Test root endpoint works."""
|
||||
response = client.get("/")
|
||||
response = client.get("/", )
|
||||
assert response.status_code == 200
|
||||
assert response.json()["service"] == "karaoke-gen-backend"
|
||||
|
||||
|
||||
+1349
-10
File diff suppressed because it is too large.
Load diff
@@ -0,0 +1,632 @@
|
||||
"""
|
||||
Tests for the flacfetch remote HTTP API client.
|
||||
|
||||
This module tests FlacfetchClient which handles communication with the
|
||||
dedicated flacfetch VM for torrent/audio downloads.
|
||||
|
||||
These tests use mocked HTTP responses to verify:
|
||||
- Request formatting (headers, payloads)
|
||||
- Response parsing
|
||||
- Error handling
|
||||
- State management (singleton pattern)
|
||||
"""
|
||||
import pytest
|
||||
from unittest.mock import AsyncMock, Mock, patch, MagicMock
|
||||
import asyncio
|
||||
|
||||
import httpx
|
||||
|
||||
from backend.services.flacfetch_client import (
|
||||
FlacfetchClient,
|
||||
FlacfetchServiceError,
|
||||
get_flacfetch_client,
|
||||
reset_flacfetch_client,
|
||||
)
|
||||
|
||||
|
||||
class TestFlacfetchClientInit:
|
||||
"""Test FlacfetchClient initialization."""
|
||||
|
||||
def test_init_with_required_params(self):
|
||||
"""Test client initializes with base_url and api_key."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key-123",
|
||||
)
|
||||
|
||||
assert client.base_url == "http://localhost:8080"
|
||||
assert client.api_key == "test-key-123"
|
||||
assert client.timeout == 60 # Default timeout
|
||||
|
||||
def test_init_strips_trailing_slash(self):
|
||||
"""Test base_url trailing slash is stripped."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080/",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
assert client.base_url == "http://localhost:8080"
|
||||
|
||||
def test_init_with_custom_timeout(self):
|
||||
"""Test custom timeout is set."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
timeout=120,
|
||||
)
|
||||
|
||||
assert client.timeout == 120
|
||||
|
||||
def test_headers_include_api_key(self):
|
||||
"""Test _headers() includes X-API-Key."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="secret-key-456",
|
||||
)
|
||||
|
||||
headers = client._headers()
|
||||
|
||||
assert headers["X-API-Key"] == "secret-key-456"
|
||||
assert headers["Content-Type"] == "application/json"
|
||||
|
||||
|
||||
class TestFlacfetchClientHealthCheck:
|
||||
"""Test health_check() method."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_health_check_success(self):
|
||||
"""Test successful health check."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
mock_response = Mock()
|
||||
mock_response.json.return_value = {
|
||||
"status": "healthy",
|
||||
"transmission": {"available": True, "version": "4.0.5"},
|
||||
"disk": {"free_gb": 15.5},
|
||||
}
|
||||
mock_response.raise_for_status = Mock()
|
||||
|
||||
with patch("httpx.AsyncClient") as mock_client_class:
|
||||
mock_client = AsyncMock()
|
||||
mock_client.get = AsyncMock(return_value=mock_response)
|
||||
mock_client.__aenter__ = AsyncMock(return_value=mock_client)
|
||||
mock_client.__aexit__ = AsyncMock(return_value=None)
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
result = await client.health_check()
|
||||
|
||||
assert result["status"] == "healthy"
|
||||
assert result["transmission"]["available"] is True
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_health_check_degraded_status(self):
|
||||
"""Test health check with degraded status still succeeds."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
mock_response = Mock()
|
||||
mock_response.json.return_value = {"status": "degraded"}
|
||||
mock_response.raise_for_status = Mock()
|
||||
|
||||
with patch("httpx.AsyncClient") as mock_client_class:
|
||||
mock_client = AsyncMock()
|
||||
mock_client.get = AsyncMock(return_value=mock_response)
|
||||
mock_client.__aenter__ = AsyncMock(return_value=mock_client)
|
||||
mock_client.__aexit__ = AsyncMock(return_value=None)
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
result = await client.health_check()
|
||||
|
||||
assert result["status"] == "degraded"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_health_check_unhealthy_raises_error(self):
|
||||
"""Test health check with unhealthy status raises error."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
mock_response = Mock()
|
||||
mock_response.json.return_value = {"status": "unhealthy", "error": "Transmission down"}
|
||||
mock_response.raise_for_status = Mock()
|
||||
|
||||
with patch("httpx.AsyncClient") as mock_client_class:
|
||||
mock_client = AsyncMock()
|
||||
mock_client.get = AsyncMock(return_value=mock_response)
|
||||
mock_client.__aenter__ = AsyncMock(return_value=mock_client)
|
||||
mock_client.__aexit__ = AsyncMock(return_value=None)
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
with pytest.raises(FlacfetchServiceError) as exc_info:
|
||||
await client.health_check()
|
||||
|
||||
assert "unhealthy" in str(exc_info.value)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_health_check_network_error(self):
|
||||
"""Test health check handles network errors."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
with patch("httpx.AsyncClient") as mock_client_class:
|
||||
mock_client = AsyncMock()
|
||||
mock_client.get = AsyncMock(side_effect=httpx.RequestError("Connection refused"))
|
||||
mock_client.__aenter__ = AsyncMock(return_value=mock_client)
|
||||
mock_client.__aexit__ = AsyncMock(return_value=None)
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
with pytest.raises(FlacfetchServiceError) as exc_info:
|
||||
await client.health_check()
|
||||
|
||||
assert "Cannot reach" in str(exc_info.value)
|
||||
|
||||
|
||||
class TestFlacfetchClientSearch:
|
||||
"""Test search() method."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_search_success(self):
|
||||
"""Test successful search returns results."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
mock_response = Mock()
|
||||
mock_response.status_code = 200
|
||||
mock_response.json.return_value = {
|
||||
"search_id": "search_abc123",
|
||||
"results": [
|
||||
{
|
||||
"title": "Waterloo",
|
||||
"artist": "ABBA",
|
||||
"provider": "RED",
|
||||
"quality": "FLAC 16bit CD",
|
||||
"seeders": 50,
|
||||
"index": 0,
|
||||
}
|
||||
],
|
||||
"results_count": 1,
|
||||
}
|
||||
mock_response.raise_for_status = Mock()
|
||||
|
||||
with patch("httpx.AsyncClient") as mock_client_class:
|
||||
mock_client = AsyncMock()
|
||||
mock_client.post = AsyncMock(return_value=mock_response)
|
||||
mock_client.__aenter__ = AsyncMock(return_value=mock_client)
|
||||
mock_client.__aexit__ = AsyncMock(return_value=None)
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
result = await client.search("ABBA", "Waterloo")
|
||||
|
||||
assert result["search_id"] == "search_abc123"
|
||||
assert len(result["results"]) == 1
|
||||
assert result["results"][0]["title"] == "Waterloo"
|
||||
|
||||
# Verify request was made correctly
|
||||
mock_client.post.assert_called_once()
|
||||
call_args = mock_client.post.call_args
|
||||
assert call_args.kwargs["json"] == {"artist": "ABBA", "title": "Waterloo"}
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_search_no_results_returns_empty(self):
|
||||
"""Test search with no results returns empty list."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
mock_response = Mock()
|
||||
mock_response.status_code = 404
|
||||
|
||||
with patch("httpx.AsyncClient") as mock_client_class:
|
||||
mock_client = AsyncMock()
|
||||
mock_client.post = AsyncMock(return_value=mock_response)
|
||||
mock_client.__aenter__ = AsyncMock(return_value=mock_client)
|
||||
mock_client.__aexit__ = AsyncMock(return_value=None)
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
result = await client.search("Unknown", "Artist")
|
||||
|
||||
assert result["results"] == []
|
||||
assert result["search_id"] is None
|
||||
|
||||
|
||||
class TestFlacfetchClientDownload:
|
||||
"""Test download() method."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_download_starts_successfully(self):
|
||||
"""Test download() returns download_id."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
mock_response = Mock()
|
||||
mock_response.json.return_value = {
|
||||
"download_id": "dl_xyz789",
|
||||
"status": "queued",
|
||||
}
|
||||
mock_response.raise_for_status = Mock()
|
||||
|
||||
with patch("httpx.AsyncClient") as mock_client_class:
|
||||
mock_client = AsyncMock()
|
||||
mock_client.post = AsyncMock(return_value=mock_response)
|
||||
mock_client.__aenter__ = AsyncMock(return_value=mock_client)
|
||||
mock_client.__aexit__ = AsyncMock(return_value=None)
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
download_id = await client.download(
|
||||
search_id="search_abc123",
|
||||
result_index=0,
|
||||
)
|
||||
|
||||
assert download_id == "dl_xyz789"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_download_with_gcs_path(self):
|
||||
"""Test download() includes GCS upload parameters."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
mock_response = Mock()
|
||||
mock_response.json.return_value = {"download_id": "dl_xyz789"}
|
||||
mock_response.raise_for_status = Mock()
|
||||
|
||||
with patch("httpx.AsyncClient") as mock_client_class:
|
||||
mock_client = AsyncMock()
|
||||
mock_client.post = AsyncMock(return_value=mock_response)
|
||||
mock_client.__aenter__ = AsyncMock(return_value=mock_client)
|
||||
mock_client.__aexit__ = AsyncMock(return_value=None)
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
await client.download(
|
||||
search_id="search_abc123",
|
||||
result_index=0,
|
||||
gcs_path="uploads/job123/audio/",
|
||||
)
|
||||
|
||||
# Verify GCS params were included
|
||||
call_args = mock_client.post.call_args
|
||||
payload = call_args.kwargs["json"]
|
||||
assert payload["upload_to_gcs"] is True
|
||||
assert payload["gcs_path"] == "uploads/job123/audio/"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_download_with_custom_filename(self):
|
||||
"""Test download() with custom output filename."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
mock_response = Mock()
|
||||
mock_response.json.return_value = {"download_id": "dl_xyz789"}
|
||||
mock_response.raise_for_status = Mock()
|
||||
|
||||
with patch("httpx.AsyncClient") as mock_client_class:
|
||||
mock_client = AsyncMock()
|
||||
mock_client.post = AsyncMock(return_value=mock_response)
|
||||
mock_client.__aenter__ = AsyncMock(return_value=mock_client)
|
||||
mock_client.__aexit__ = AsyncMock(return_value=None)
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
await client.download(
|
||||
search_id="search_abc123",
|
||||
result_index=0,
|
||||
output_filename="ABBA - Waterloo",
|
||||
)
|
||||
|
||||
call_args = mock_client.post.call_args
|
||||
payload = call_args.kwargs["json"]
|
||||
assert payload["output_filename"] == "ABBA - Waterloo"
|
||||
|
||||
|
||||
class TestFlacfetchClientGetDownloadStatus:
|
||||
"""Test get_download_status() method."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_download_status_success(self):
|
||||
"""Test getting download status."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
mock_response = Mock()
|
||||
mock_response.json.return_value = {
|
||||
"download_id": "dl_xyz789",
|
||||
"status": "downloading",
|
||||
"progress": 45.5,
|
||||
"download_speed_kbps": 1250.0,
|
||||
"peers": 5,
|
||||
}
|
||||
mock_response.raise_for_status = Mock()
|
||||
|
||||
with patch("httpx.AsyncClient") as mock_client_class:
|
||||
mock_client = AsyncMock()
|
||||
mock_client.get = AsyncMock(return_value=mock_response)
|
||||
mock_client.__aenter__ = AsyncMock(return_value=mock_client)
|
||||
mock_client.__aexit__ = AsyncMock(return_value=None)
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
status = await client.get_download_status("dl_xyz789")
|
||||
|
||||
assert status["status"] == "downloading"
|
||||
assert status["progress"] == 45.5
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_download_status_not_found(self):
|
||||
"""Test getting status for non-existent download."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
mock_response = Mock()
|
||||
mock_response.status_code = 404
|
||||
mock_response.raise_for_status = Mock(
|
||||
side_effect=httpx.HTTPStatusError("Not found", request=Mock(), response=mock_response)
|
||||
)
|
||||
|
||||
with patch("httpx.AsyncClient") as mock_client_class:
|
||||
mock_client = AsyncMock()
|
||||
mock_client.get = AsyncMock(return_value=mock_response)
|
||||
mock_client.__aenter__ = AsyncMock(return_value=mock_client)
|
||||
mock_client.__aexit__ = AsyncMock(return_value=None)
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
with pytest.raises(FlacfetchServiceError) as exc_info:
|
||||
await client.get_download_status("nonexistent")
|
||||
|
||||
assert "not found" in str(exc_info.value).lower()
|
||||
|
||||
|
||||
class TestFlacfetchClientWaitForDownload:
|
||||
"""Test wait_for_download() method."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_wait_for_download_completes(self):
|
||||
"""Test waiting for download to complete."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
# Mock get_download_status to return complete status
|
||||
async def mock_get_status(download_id):
|
||||
return {
|
||||
"download_id": download_id,
|
||||
"status": "complete",
|
||||
"gcs_path": "gs://bucket/uploads/test.flac",
|
||||
}
|
||||
|
||||
client.get_download_status = mock_get_status
|
||||
|
||||
result = await client.wait_for_download("dl_xyz789", timeout=10)
|
||||
|
||||
assert result["status"] == "complete"
|
||||
assert result["gcs_path"] == "gs://bucket/uploads/test.flac"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_wait_for_download_seeding_status_completes(self):
|
||||
"""Test that 'seeding' status is treated as complete."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
async def mock_get_status(download_id):
|
||||
return {
|
||||
"download_id": download_id,
|
||||
"status": "seeding",
|
||||
"output_path": "/downloads/test.flac",
|
||||
}
|
||||
|
||||
client.get_download_status = mock_get_status
|
||||
|
||||
result = await client.wait_for_download("dl_xyz789", timeout=10)
|
||||
|
||||
assert result["status"] == "seeding"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_wait_for_download_failed(self):
|
||||
"""Test wait raises error when download fails."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
async def mock_get_status(download_id):
|
||||
return {
|
||||
"download_id": download_id,
|
||||
"status": "failed",
|
||||
"error": "Torrent download failed: no peers",
|
||||
}
|
||||
|
||||
client.get_download_status = mock_get_status
|
||||
|
||||
with pytest.raises(FlacfetchServiceError) as exc_info:
|
||||
await client.wait_for_download("dl_xyz789", timeout=10)
|
||||
|
||||
assert "failed" in str(exc_info.value).lower()
|
||||
assert "no peers" in str(exc_info.value)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_wait_for_download_cancelled(self):
|
||||
"""Test wait raises error when download is cancelled."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
async def mock_get_status(download_id):
|
||||
return {
|
||||
"download_id": download_id,
|
||||
"status": "cancelled",
|
||||
}
|
||||
|
||||
client.get_download_status = mock_get_status
|
||||
|
||||
with pytest.raises(FlacfetchServiceError) as exc_info:
|
||||
await client.wait_for_download("dl_xyz789", timeout=10)
|
||||
|
||||
assert "cancelled" in str(exc_info.value).lower()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_wait_for_download_timeout(self):
|
||||
"""Test wait raises error on timeout."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
call_count = 0
|
||||
async def mock_get_status(download_id):
|
||||
nonlocal call_count
|
||||
call_count += 1
|
||||
return {
|
||||
"download_id": download_id,
|
||||
"status": "downloading",
|
||||
"progress": 10.0 * call_count,
|
||||
}
|
||||
|
||||
client.get_download_status = mock_get_status
|
||||
|
||||
with pytest.raises(FlacfetchServiceError) as exc_info:
|
||||
# Very short timeout with short poll interval
|
||||
await client.wait_for_download("dl_xyz789", timeout=0.2, poll_interval=0.1)
|
||||
|
||||
assert "timed out" in str(exc_info.value).lower()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_wait_for_download_calls_progress_callback(self):
|
||||
"""Test progress callback is called during wait."""
|
||||
client = FlacfetchClient(
|
||||
base_url="http://localhost:8080",
|
||||
api_key="test-key",
|
||||
)
|
||||
|
||||
call_count = 0
|
||||
async def mock_get_status(download_id):
|
||||
nonlocal call_count
|
||||
call_count += 1
|
||||
if call_count >= 3:
|
||||
return {"status": "complete", "gcs_path": "gs://test"}
|
||||
return {"status": "downloading", "progress": 33.0 * call_count}
|
||||
|
||||
client.get_download_status = mock_get_status
|
||||
|
||||
progress_updates = []
|
||||
def progress_callback(status):
|
||||
progress_updates.append(status)
|
||||
|
||||
await client.wait_for_download(
|
||||
"dl_xyz789",
|
||||
timeout=10,
|
||||
poll_interval=0.01,
|
||||
progress_callback=progress_callback,
|
||||
)
|
||||
|
||||
# Should have received progress updates
|
||||
assert len(progress_updates) >= 2
|
||||
|
||||
|
||||
class TestGetFlacfetchClient:
|
||||
"""Test get_flacfetch_client() singleton factory."""
|
||||
|
||||
def test_returns_none_when_not_configured(self):
|
||||
"""Test returns None when FLACFETCH_API_URL not set."""
|
||||
reset_flacfetch_client()
|
||||
|
||||
with patch("backend.config.get_settings") as mock_settings:
|
||||
mock_settings.return_value = Mock(
|
||||
flacfetch_api_url=None,
|
||||
flacfetch_api_key=None,
|
||||
)
|
||||
|
||||
client = get_flacfetch_client()
|
||||
|
||||
assert client is None
|
||||
|
||||
def test_returns_none_when_key_missing(self):
|
||||
"""Test returns None when API key not set."""
|
||||
reset_flacfetch_client()
|
||||
|
||||
with patch("backend.config.get_settings") as mock_settings:
|
||||
mock_settings.return_value = Mock(
|
||||
flacfetch_api_url="http://localhost:8080",
|
||||
flacfetch_api_key=None,
|
||||
)
|
||||
|
||||
client = get_flacfetch_client()
|
||||
|
||||
assert client is None
|
||||
|
||||
def test_returns_client_when_configured(self):
|
||||
"""Test returns FlacfetchClient when both URL and key are set."""
|
||||
reset_flacfetch_client()
|
||||
|
||||
with patch("backend.config.get_settings") as mock_settings:
|
||||
mock_settings.return_value = Mock(
|
||||
flacfetch_api_url="http://10.0.0.5:8080",
|
||||
flacfetch_api_key="secret-key",
|
||||
)
|
||||
|
||||
client = get_flacfetch_client()
|
||||
|
||||
assert client is not None
|
||||
assert isinstance(client, FlacfetchClient)
|
||||
assert client.base_url == "http://10.0.0.5:8080"
|
||||
assert client.api_key == "secret-key"
|
||||
|
||||
def test_returns_same_instance(self):
|
||||
"""Test singleton returns same instance."""
|
||||
reset_flacfetch_client()
|
||||
|
||||
with patch("backend.config.get_settings") as mock_settings:
|
||||
mock_settings.return_value = Mock(
|
||||
flacfetch_api_url="http://localhost:8080",
|
||||
flacfetch_api_key="test-key",
|
||||
)
|
||||
|
||||
client1 = get_flacfetch_client()
|
||||
client2 = get_flacfetch_client()
|
||||
|
||||
assert client1 is client2
|
||||
|
||||
def test_reset_clears_singleton(self):
|
||||
"""Test reset_flacfetch_client() clears the singleton."""
|
||||
reset_flacfetch_client()
|
||||
|
||||
with patch("backend.config.get_settings") as mock_settings:
|
||||
mock_settings.return_value = Mock(
|
||||
flacfetch_api_url="http://localhost:8080",
|
||||
flacfetch_api_key="test-key",
|
||||
)
|
||||
|
||||
client1 = get_flacfetch_client()
|
||||
reset_flacfetch_client()
|
||||
|
||||
# Change the settings
|
||||
mock_settings.return_value = Mock(
|
||||
flacfetch_api_url="http://other:8080",
|
||||
flacfetch_api_key="other-key",
|
||||
)
|
||||
|
||||
client2 = get_flacfetch_client()
|
||||
|
||||
assert client1 is not client2
|
||||
assert client2.base_url == "http://other:8080"
|
||||
|
||||
@@ -0,0 +1,524 @@
|
||||
"""
|
||||
Tests for gdrive_service.py - Google Drive file operations.
|
||||
|
||||
These tests mock the Google API client and Secret Manager to verify:
|
||||
- Credential loading from Secret Manager
|
||||
- Folder creation and lookup
|
||||
- File uploads with proper MIME types
|
||||
- Public share folder structure uploads
|
||||
"""
|
||||
import json
|
||||
import os
|
||||
import pytest
|
||||
from unittest.mock import Mock, MagicMock, patch
|
||||
|
||||
|
||||
class TestGoogleDriveServiceInit:
|
||||
"""Test GoogleDriveService initialization."""
|
||||
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_init_creates_service(self, mock_get_settings):
|
||||
"""Test initialization creates service with settings."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = GoogleDriveService()
|
||||
|
||||
assert service.settings == mock_settings
|
||||
assert service._service is None
|
||||
assert service._credentials_data is None
|
||||
assert service._loaded is False
|
||||
|
||||
|
||||
class TestLoadCredentials:
|
||||
"""Test _load_credentials method."""
|
||||
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_load_credentials_success(self, mock_get_settings):
|
||||
"""Test successful credential loading from Secret Manager."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"token": "access-token",
|
||||
"refresh_token": "refresh-token",
|
||||
"client_id": "client-id",
|
||||
"client_secret": "client-secret",
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = GoogleDriveService()
|
||||
creds = service._load_credentials()
|
||||
|
||||
assert creds is not None
|
||||
assert creds["refresh_token"] == "refresh-token"
|
||||
mock_settings.get_secret.assert_called_once_with("gdrive-oauth-credentials")
|
||||
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_load_credentials_fallback_to_youtube(self, mock_get_settings):
|
||||
"""Test fallback to YouTube credentials when Drive creds not found."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
# First call returns None (Drive creds not found)
|
||||
# Second call returns YouTube creds
|
||||
mock_settings.get_secret.side_effect = [
|
||||
None,
|
||||
json.dumps({
|
||||
"refresh_token": "youtube-token",
|
||||
"client_id": "youtube-id",
|
||||
"client_secret": "youtube-secret",
|
||||
})
|
||||
]
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = GoogleDriveService()
|
||||
creds = service._load_credentials()
|
||||
|
||||
assert creds is not None
|
||||
assert creds["refresh_token"] == "youtube-token"
|
||||
assert mock_settings.get_secret.call_count == 2
|
||||
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_load_credentials_not_found(self, mock_get_settings):
|
||||
"""Test handling when no credentials found."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = None
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = GoogleDriveService()
|
||||
creds = service._load_credentials()
|
||||
|
||||
assert creds is None
|
||||
assert service._loaded is True
|
||||
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_load_credentials_missing_required_fields(self, mock_get_settings):
|
||||
"""Test handling when credentials missing required fields."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"token": "access-token",
|
||||
# Missing: refresh_token, client_id, client_secret
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = GoogleDriveService()
|
||||
creds = service._load_credentials()
|
||||
|
||||
assert creds is None
|
||||
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_load_credentials_cached(self, mock_get_settings):
|
||||
"""Test credentials are cached after first load."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"refresh_token": "token",
|
||||
"client_id": "id",
|
||||
"client_secret": "secret",
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = GoogleDriveService()
|
||||
|
||||
creds1 = service._load_credentials()
|
||||
creds2 = service._load_credentials()
|
||||
|
||||
assert creds1 == creds2
|
||||
assert mock_settings.get_secret.call_count == 1
|
||||
|
||||
|
||||
class TestIsConfigured:
|
||||
"""Test is_configured property."""
|
||||
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_is_configured_true(self, mock_get_settings):
|
||||
"""Test is_configured returns True when credentials exist."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"refresh_token": "token",
|
||||
"client_id": "id",
|
||||
"client_secret": "secret",
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = GoogleDriveService()
|
||||
|
||||
assert service.is_configured is True
|
||||
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_is_configured_false(self, mock_get_settings):
|
||||
"""Test is_configured returns False when no credentials."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = None
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = GoogleDriveService()
|
||||
|
||||
assert service.is_configured is False
|
||||
|
||||
|
||||
class TestDriveService:
|
||||
"""Test service property."""
|
||||
|
||||
@patch("googleapiclient.discovery.build")
|
||||
@patch("google.oauth2.credentials.Credentials")
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_service_creates_drive_client(
|
||||
self, mock_get_settings, mock_creds_class, mock_build
|
||||
):
|
||||
"""Test service property creates Google Drive API client."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"token": "access-token",
|
||||
"refresh_token": "refresh-token",
|
||||
"client_id": "client-id",
|
||||
"client_secret": "client-secret",
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
mock_creds = Mock()
|
||||
mock_creds_class.return_value = mock_creds
|
||||
|
||||
mock_drive_service = Mock()
|
||||
mock_build.return_value = mock_drive_service
|
||||
|
||||
service = GoogleDriveService()
|
||||
result = service.service
|
||||
|
||||
mock_build.assert_called_once_with("drive", "v3", credentials=mock_creds)
|
||||
assert result == mock_drive_service
|
||||
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_service_raises_on_missing_credentials(self, mock_get_settings):
|
||||
"""Test service raises RuntimeError when credentials missing."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = None
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = GoogleDriveService()
|
||||
|
||||
with pytest.raises(RuntimeError) as exc_info:
|
||||
_ = service.service
|
||||
|
||||
assert "not configured" in str(exc_info.value)
|
||||
|
||||
|
||||
class TestGetOrCreateFolder:
|
||||
"""Test get_or_create_folder method."""
|
||||
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_get_existing_folder(self, mock_get_settings):
|
||||
"""Test finding an existing folder."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"refresh_token": "token",
|
||||
"client_id": "id",
|
||||
"client_secret": "secret",
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = GoogleDriveService()
|
||||
|
||||
# Mock the Drive API
|
||||
mock_files_api = Mock()
|
||||
mock_list_result = Mock()
|
||||
mock_list_result.execute.return_value = {
|
||||
"files": [{"id": "folder-id-123", "name": "MP4"}]
|
||||
}
|
||||
mock_files_api.list.return_value = mock_list_result
|
||||
|
||||
mock_drive = Mock()
|
||||
mock_drive.files.return_value = mock_files_api
|
||||
service._service = mock_drive
|
||||
service._loaded = True
|
||||
service._credentials_data = {"refresh_token": "token", "client_id": "id", "client_secret": "secret"}
|
||||
|
||||
folder_id = service.get_or_create_folder("parent-123", "MP4")
|
||||
|
||||
assert folder_id == "folder-id-123"
|
||||
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_create_new_folder(self, mock_get_settings):
|
||||
"""Test creating a new folder when it doesn't exist."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"refresh_token": "token",
|
||||
"client_id": "id",
|
||||
"client_secret": "secret",
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = GoogleDriveService()
|
||||
|
||||
# Mock the Drive API
|
||||
mock_files_api = Mock()
|
||||
|
||||
# list returns empty (folder doesn't exist)
|
||||
mock_list_result = Mock()
|
||||
mock_list_result.execute.return_value = {"files": []}
|
||||
mock_files_api.list.return_value = mock_list_result
|
||||
|
||||
# create returns new folder
|
||||
mock_create_result = Mock()
|
||||
mock_create_result.execute.return_value = {"id": "new-folder-id"}
|
||||
mock_files_api.create.return_value = mock_create_result
|
||||
|
||||
mock_drive = Mock()
|
||||
mock_drive.files.return_value = mock_files_api
|
||||
service._service = mock_drive
|
||||
service._loaded = True
|
||||
service._credentials_data = {"refresh_token": "token", "client_id": "id", "client_secret": "secret"}
|
||||
|
||||
folder_id = service.get_or_create_folder("parent-123", "NewFolder")
|
||||
|
||||
assert folder_id == "new-folder-id"
|
||||
mock_files_api.create.assert_called_once()
|
||||
|
||||
|
||||
class TestUploadFile:
|
||||
"""Test upload_file method."""
|
||||
|
||||
@patch("googleapiclient.http.MediaFileUpload")
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_upload_file_success(self, mock_get_settings, mock_media, tmp_path):
|
||||
"""Test uploading a file to Drive."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"refresh_token": "token",
|
||||
"client_id": "id",
|
||||
"client_secret": "secret",
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
# Create test file
|
||||
test_file = tmp_path / "test.mp4"
|
||||
test_file.write_bytes(b"video content")
|
||||
|
||||
service = GoogleDriveService()
|
||||
|
||||
mock_files_api = Mock()
|
||||
|
||||
# list returns empty (no existing file)
|
||||
mock_list_result = Mock()
|
||||
mock_list_result.execute.return_value = {"files": []}
|
||||
mock_files_api.list.return_value = mock_list_result
|
||||
|
||||
# create returns new file
|
||||
mock_create_result = Mock()
|
||||
mock_create_result.execute.return_value = {"id": "file-id-123"}
|
||||
mock_files_api.create.return_value = mock_create_result
|
||||
|
||||
mock_drive = Mock()
|
||||
mock_drive.files.return_value = mock_files_api
|
||||
service._service = mock_drive
|
||||
service._loaded = True
|
||||
service._credentials_data = {"refresh_token": "token", "client_id": "id", "client_secret": "secret"}
|
||||
|
||||
file_id = service.upload_file(str(test_file), "parent-123", "video.mp4")
|
||||
|
||||
assert file_id == "file-id-123"
|
||||
mock_media.assert_called_once()
|
||||
# Verify MIME type was set correctly
|
||||
call_kwargs = mock_media.call_args.kwargs
|
||||
assert call_kwargs["mimetype"] == "video/mp4"
|
||||
|
||||
@patch("googleapiclient.http.MediaFileUpload")
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_upload_file_replaces_existing(self, mock_get_settings, mock_media, tmp_path):
|
||||
"""Test upload deletes existing file before upload."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"refresh_token": "token",
|
||||
"client_id": "id",
|
||||
"client_secret": "secret",
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
test_file = tmp_path / "test.mp4"
|
||||
test_file.write_bytes(b"content")
|
||||
|
||||
service = GoogleDriveService()
|
||||
|
||||
mock_files_api = Mock()
|
||||
|
||||
# list returns existing file
|
||||
mock_list_result = Mock()
|
||||
mock_list_result.execute.return_value = {
|
||||
"files": [{"id": "existing-file-id"}]
|
||||
}
|
||||
mock_files_api.list.return_value = mock_list_result
|
||||
|
||||
mock_delete_result = Mock()
|
||||
mock_delete_result.execute.return_value = {}
|
||||
mock_files_api.delete.return_value = mock_delete_result
|
||||
|
||||
mock_create_result = Mock()
|
||||
mock_create_result.execute.return_value = {"id": "new-file-id"}
|
||||
mock_files_api.create.return_value = mock_create_result
|
||||
|
||||
mock_drive = Mock()
|
||||
mock_drive.files.return_value = mock_files_api
|
||||
service._service = mock_drive
|
||||
service._loaded = True
|
||||
service._credentials_data = {"refresh_token": "token", "client_id": "id", "client_secret": "secret"}
|
||||
|
||||
file_id = service.upload_file(str(test_file), "parent-123", "video.mp4")
|
||||
|
||||
# Should have deleted existing file
|
||||
mock_files_api.delete.assert_called_once_with(fileId="existing-file-id")
|
||||
assert file_id == "new-file-id"
|
||||
|
||||
|
||||
class TestUploadToPublicShare:
|
||||
"""Test upload_to_public_share method."""
|
||||
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_upload_to_public_share(self, mock_get_settings, tmp_path):
|
||||
"""Test uploading files to public share folder structure."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"refresh_token": "token",
|
||||
"client_id": "id",
|
||||
"client_secret": "secret",
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
# Create test files
|
||||
mp4_file = tmp_path / "output.mp4"
|
||||
mp4_file.write_bytes(b"4k video")
|
||||
mp4_720_file = tmp_path / "output_720p.mp4"
|
||||
mp4_720_file.write_bytes(b"720p video")
|
||||
cdg_file = tmp_path / "output.zip"
|
||||
cdg_file.write_bytes(b"cdg package")
|
||||
|
||||
service = GoogleDriveService()
|
||||
|
||||
# Mock methods
|
||||
with patch.object(service, "get_or_create_folder") as mock_get_folder:
|
||||
with patch.object(service, "upload_file") as mock_upload:
|
||||
mock_get_folder.side_effect = [
|
||||
"mp4-folder-id",
|
||||
"mp4-720-folder-id",
|
||||
"cdg-folder-id",
|
||||
]
|
||||
mock_upload.side_effect = [
|
||||
"mp4-file-id",
|
||||
"720p-file-id",
|
||||
"cdg-file-id",
|
||||
]
|
||||
|
||||
output_files = {
|
||||
"final_karaoke_lossy_mp4": str(mp4_file),
|
||||
"final_karaoke_lossy_720p_mp4": str(mp4_720_file),
|
||||
"final_karaoke_cdg_zip": str(cdg_file),
|
||||
}
|
||||
|
||||
result = service.upload_to_public_share(
|
||||
root_folder_id="root-123",
|
||||
brand_code="NOMAD-1163",
|
||||
base_name="Artist - Title",
|
||||
output_files=output_files,
|
||||
)
|
||||
|
||||
# Should have created/found 3 folders
|
||||
assert mock_get_folder.call_count == 3
|
||||
|
||||
# Should have uploaded 3 files
|
||||
assert mock_upload.call_count == 3
|
||||
|
||||
# Check result
|
||||
assert result["mp4"] == "mp4-file-id"
|
||||
assert result["mp4_720p"] == "720p-file-id"
|
||||
assert result["cdg"] == "cdg-file-id"
|
||||
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_upload_to_public_share_skips_missing_files(
|
||||
self, mock_get_settings, tmp_path
|
||||
):
|
||||
"""Test upload skips files that don't exist."""
|
||||
from backend.services.gdrive_service import GoogleDriveService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"refresh_token": "token",
|
||||
"client_id": "id",
|
||||
"client_secret": "secret",
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
# Only create one file
|
||||
mp4_file = tmp_path / "output.mp4"
|
||||
mp4_file.write_bytes(b"video")
|
||||
|
||||
service = GoogleDriveService()
|
||||
|
||||
with patch.object(service, "get_or_create_folder") as mock_get_folder:
|
||||
with patch.object(service, "upload_file") as mock_upload:
|
||||
mock_get_folder.return_value = "folder-id"
|
||||
mock_upload.return_value = "file-id"
|
||||
|
||||
output_files = {
|
||||
"final_karaoke_lossy_mp4": str(mp4_file),
|
||||
"final_karaoke_lossy_720p_mp4": "/nonexistent/file.mp4",
|
||||
"final_karaoke_cdg_zip": None,
|
||||
}
|
||||
|
||||
result = service.upload_to_public_share(
|
||||
root_folder_id="root-123",
|
||||
brand_code="CODE",
|
||||
base_name="Name",
|
||||
output_files=output_files,
|
||||
)
|
||||
|
||||
# Should only upload the one file that exists
|
||||
assert mock_upload.call_count == 1
|
||||
assert len(result) == 1
|
||||
|
||||
|
||||
class TestGetGdriveService:
|
||||
"""Test get_gdrive_service singleton."""
|
||||
|
||||
@patch("backend.services.gdrive_service.get_settings")
|
||||
def test_get_gdrive_service_singleton(self, mock_get_settings):
|
||||
"""Test get_gdrive_service returns singleton instance."""
|
||||
from backend.services.gdrive_service import get_gdrive_service
|
||||
import backend.services.gdrive_service as gdrive_module
|
||||
|
||||
# Reset singleton
|
||||
gdrive_module._gdrive_service = None
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = None
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service1 = get_gdrive_service()
|
||||
service2 = get_gdrive_service()
|
||||
|
||||
assert service1 is service2
|
||||
|
||||
@@ -0,0 +1,431 @@
|
||||
"""
|
||||
API endpoint tests for instrumental review functionality.
|
||||
|
||||
Tests for:
|
||||
- GET /api/jobs/{job_id}/instrumental-analysis
|
||||
- GET /api/jobs/{job_id}/audio-stream/{stem_type}
|
||||
- POST /api/jobs/{job_id}/create-custom-instrumental
|
||||
- GET /api/jobs/{job_id}/waveform-data
|
||||
"""
|
||||
|
||||
import pytest
|
||||
from datetime import datetime
|
||||
from unittest.mock import MagicMock, patch, AsyncMock
|
||||
|
||||
from backend.models.job import Job, JobStatus
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_job_manager():
|
||||
"""Create a mock job manager."""
|
||||
with patch('backend.api.routes.jobs.job_manager') as mock:
|
||||
yield mock
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_storage_service():
|
||||
"""Create a mock storage service."""
|
||||
with patch('backend.api.routes.jobs.StorageService') as mock:
|
||||
mock_instance = MagicMock()
|
||||
mock_instance.generate_signed_url.return_value = "https://storage.googleapis.com/signed-url"
|
||||
mock.return_value = mock_instance
|
||||
yield mock_instance
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def sample_job():
|
||||
"""Create a sample job for testing."""
|
||||
return Job(
|
||||
job_id="test-job-123",
|
||||
artist="Test Artist",
|
||||
title="Test Song",
|
||||
status=JobStatus.AWAITING_INSTRUMENTAL_SELECTION,
|
||||
created_at=datetime.now(),
|
||||
updated_at=datetime.now(),
|
||||
file_urls={
|
||||
"stems": {
|
||||
"instrumental_clean": "jobs/test/stems/instrumental_clean.flac",
|
||||
"backing_vocals": "jobs/test/stems/backing_vocals.flac",
|
||||
"instrumental_with_backing": "jobs/test/stems/instrumental_with_backing.flac",
|
||||
},
|
||||
"analysis": {
|
||||
"backing_vocals_waveform": "jobs/test/analysis/waveform.png",
|
||||
},
|
||||
},
|
||||
state_data={
|
||||
"backing_vocals_analysis": {
|
||||
"has_audible_content": True,
|
||||
"total_duration_seconds": 180.0,
|
||||
"audible_segments": [
|
||||
{
|
||||
"start_seconds": 10.0,
|
||||
"end_seconds": 20.0,
|
||||
"duration_seconds": 10.0,
|
||||
"avg_amplitude_db": -25.0,
|
||||
},
|
||||
{
|
||||
"start_seconds": 60.0,
|
||||
"end_seconds": 80.0,
|
||||
"duration_seconds": 20.0,
|
||||
"avg_amplitude_db": -30.0,
|
||||
},
|
||||
],
|
||||
"recommended_selection": "review_needed",
|
||||
"total_audible_duration_seconds": 30.0,
|
||||
"audible_percentage": 16.67,
|
||||
"silence_threshold_db": -40.0,
|
||||
}
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def silent_job():
|
||||
"""Create a job with silent backing vocals."""
|
||||
return Job(
|
||||
job_id="test-job-silent",
|
||||
artist="Test Artist",
|
||||
title="Test Song",
|
||||
status=JobStatus.AWAITING_INSTRUMENTAL_SELECTION,
|
||||
created_at=datetime.now(),
|
||||
updated_at=datetime.now(),
|
||||
file_urls={
|
||||
"stems": {
|
||||
"instrumental_clean": "jobs/test/stems/instrumental_clean.flac",
|
||||
"backing_vocals": "jobs/test/stems/backing_vocals.flac",
|
||||
"instrumental_with_backing": "jobs/test/stems/instrumental_with_backing.flac",
|
||||
},
|
||||
"analysis": {
|
||||
"backing_vocals_waveform": "jobs/test/analysis/waveform.png",
|
||||
},
|
||||
},
|
||||
state_data={
|
||||
"backing_vocals_analysis": {
|
||||
"has_audible_content": False,
|
||||
"total_duration_seconds": 180.0,
|
||||
"audible_segments": [],
|
||||
"recommended_selection": "clean",
|
||||
"total_audible_duration_seconds": 0.0,
|
||||
"audible_percentage": 0.0,
|
||||
"silence_threshold_db": -40.0,
|
||||
}
|
||||
},
|
||||
)
|
||||
|
||||
|
||||
class TestGetInstrumentalAnalysis:
|
||||
"""Tests for GET /api/jobs/{job_id}/instrumental-analysis."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_analysis_returns_data(self, mock_job_manager, mock_storage_service, sample_job):
|
||||
"""GET /instrumental-analysis should return analysis data."""
|
||||
mock_job_manager.get_job.return_value = sample_job
|
||||
|
||||
from backend.api.routes.jobs import get_instrumental_analysis
|
||||
|
||||
result = await get_instrumental_analysis("test-job-123")
|
||||
|
||||
assert result["job_id"] == "test-job-123"
|
||||
assert result["artist"] == "Test Artist"
|
||||
assert result["title"] == "Test Song"
|
||||
assert result["analysis"]["has_audible_content"] is True
|
||||
assert len(result["analysis"]["audible_segments"]) == 2
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_analysis_includes_audio_urls(self, mock_job_manager, mock_storage_service, sample_job):
|
||||
"""GET /instrumental-analysis should include audio URLs."""
|
||||
mock_job_manager.get_job.return_value = sample_job
|
||||
|
||||
from backend.api.routes.jobs import get_instrumental_analysis
|
||||
|
||||
result = await get_instrumental_analysis("test-job-123")
|
||||
|
||||
assert "audio_urls" in result
|
||||
assert "clean_instrumental" in result["audio_urls"]
|
||||
assert "backing_vocals" in result["audio_urls"]
|
||||
assert "with_backing" in result["audio_urls"]
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_analysis_includes_waveform_url(self, mock_job_manager, sample_job):
|
||||
"""GET /instrumental-analysis should include waveform URL."""
|
||||
mock_job_manager.get_job.return_value = sample_job
|
||||
|
||||
# Need to mock StorageService at module level for the signed URL
|
||||
with patch('backend.api.routes.jobs.StorageService') as mock_storage_cls:
|
||||
mock_storage = MagicMock()
|
||||
mock_storage.generate_signed_url.return_value = "https://storage.googleapis.com/signed-url"
|
||||
mock_storage_cls.return_value = mock_storage
|
||||
|
||||
from backend.api.routes.jobs import get_instrumental_analysis
|
||||
|
||||
result = await get_instrumental_analysis("test-job-123")
|
||||
|
||||
assert "waveform_url" in result
|
||||
# Waveform URL should be generated from the file_urls
|
||||
assert result["waveform_url"] == "https://storage.googleapis.com/signed-url"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_analysis_silent_audio(self, mock_job_manager, mock_storage_service, silent_job):
|
||||
"""GET /instrumental-analysis should correctly report silent audio."""
|
||||
mock_job_manager.get_job.return_value = silent_job
|
||||
|
||||
from backend.api.routes.jobs import get_instrumental_analysis
|
||||
|
||||
result = await get_instrumental_analysis("test-job-silent")
|
||||
|
||||
assert result["analysis"]["has_audible_content"] is False
|
||||
assert result["analysis"]["recommended_selection"] == "clean"
|
||||
assert len(result["analysis"]["audible_segments"]) == 0
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_analysis_job_not_found(self, mock_job_manager):
|
||||
"""GET /instrumental-analysis should return 404 for non-existent job."""
|
||||
mock_job_manager.get_job.return_value = None
|
||||
|
||||
from backend.api.routes.jobs import get_instrumental_analysis
|
||||
from fastapi import HTTPException
|
||||
|
||||
with pytest.raises(HTTPException) as exc_info:
|
||||
await get_instrumental_analysis("non-existent")
|
||||
|
||||
assert exc_info.value.status_code == 404
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_analysis_wrong_status(self, mock_job_manager, sample_job):
|
||||
"""GET /instrumental-analysis should return 400 for wrong job status."""
|
||||
sample_job.status = JobStatus.PENDING
|
||||
mock_job_manager.get_job.return_value = sample_job
|
||||
|
||||
from backend.api.routes.jobs import get_instrumental_analysis
|
||||
from fastapi import HTTPException
|
||||
|
||||
with pytest.raises(HTTPException) as exc_info:
|
||||
await get_instrumental_analysis("test-job-123")
|
||||
|
||||
assert exc_info.value.status_code == 400
|
||||
|
||||
|
||||
class TestAudioStream:
|
||||
"""Tests for GET /api/jobs/{job_id}/audio-stream/{stem_type}."""
|
||||
|
||||
def test_stream_backing_vocals_valid(self, mock_job_manager, sample_job):
|
||||
"""Should return redirect for backing vocals stream."""
|
||||
mock_job_manager.get_job.return_value = sample_job
|
||||
|
||||
from backend.api.routes.jobs import stream_audio
|
||||
|
||||
# This will try to stream from GCS which we can't test easily
|
||||
# Instead, verify the function exists and has correct signature
|
||||
assert callable(stream_audio)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_stream_invalid_stem_type(self, mock_job_manager, sample_job):
|
||||
"""Should return 400 for invalid stem type."""
|
||||
mock_job_manager.get_job.return_value = sample_job
|
||||
|
||||
from backend.api.routes.jobs import stream_audio
|
||||
from fastapi import HTTPException
|
||||
|
||||
with pytest.raises(HTTPException) as exc_info:
|
||||
await stream_audio("test-job-123", "invalid_stem")
|
||||
|
||||
assert exc_info.value.status_code == 400
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_stream_job_not_found(self, mock_job_manager):
|
||||
"""Should return 404 for non-existent job."""
|
||||
mock_job_manager.get_job.return_value = None
|
||||
|
||||
from backend.api.routes.jobs import stream_audio
|
||||
from fastapi import HTTPException
|
||||
|
||||
with pytest.raises(HTTPException) as exc_info:
|
||||
await stream_audio("non-existent", "backing_vocals")
|
||||
|
||||
assert exc_info.value.status_code == 404
|
||||
|
||||
|
||||
class TestCreateCustomInstrumental:
|
||||
"""Tests for POST /api/jobs/{job_id}/create-custom-instrumental."""
|
||||
|
||||
@pytest.fixture
|
||||
def mock_audio_editing_service(self):
|
||||
"""Mock the audio editing service."""
|
||||
with patch('backend.api.routes.jobs.AudioEditingService') as mock:
|
||||
mock_instance = MagicMock()
|
||||
mock_instance.create_custom_instrumental.return_value = MagicMock(
|
||||
output_path="jobs/test/stems/custom_instrumental.flac",
|
||||
mute_regions_applied=[
|
||||
MagicMock(start_seconds=10.0, end_seconds=20.0),
|
||||
],
|
||||
total_muted_duration_seconds=10.0,
|
||||
output_duration_seconds=180.0,
|
||||
)
|
||||
mock.return_value = mock_instance
|
||||
yield mock_instance
|
||||
|
||||
def test_create_custom_validates_mute_regions(self):
|
||||
"""Should validate mute regions at model level."""
|
||||
from backend.models.requests import CreateCustomInstrumentalRequest, MuteRegionRequest
|
||||
from pydantic import ValidationError
|
||||
|
||||
# Empty mute regions should fail at model validation
|
||||
with pytest.raises(ValidationError) as exc_info:
|
||||
CreateCustomInstrumentalRequest(mute_regions=[])
|
||||
|
||||
assert "At least one mute region is required" in str(exc_info.value)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_create_custom_job_not_found(self, mock_job_manager):
|
||||
"""Should return 404 for non-existent job."""
|
||||
mock_job_manager.get_job.return_value = None
|
||||
|
||||
from backend.api.routes.jobs import create_custom_instrumental
|
||||
from backend.models.requests import CreateCustomInstrumentalRequest, MuteRegionRequest
|
||||
from fastapi import HTTPException
|
||||
|
||||
request = CreateCustomInstrumentalRequest(
|
||||
mute_regions=[MuteRegionRequest(start_seconds=10.0, end_seconds=20.0)]
|
||||
)
|
||||
|
||||
with pytest.raises(HTTPException) as exc_info:
|
||||
await create_custom_instrumental("non-existent", request)
|
||||
|
||||
assert exc_info.value.status_code == 404
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_create_custom_wrong_status(self, mock_job_manager, sample_job):
|
||||
"""Should return 400 for wrong job status."""
|
||||
sample_job.status = JobStatus.PENDING
|
||||
mock_job_manager.get_job.return_value = sample_job
|
||||
|
||||
from backend.api.routes.jobs import create_custom_instrumental
|
||||
from backend.models.requests import CreateCustomInstrumentalRequest, MuteRegionRequest
|
||||
from fastapi import HTTPException
|
||||
|
||||
request = CreateCustomInstrumentalRequest(
|
||||
mute_regions=[MuteRegionRequest(start_seconds=10.0, end_seconds=20.0)]
|
||||
)
|
||||
|
||||
with pytest.raises(HTTPException) as exc_info:
|
||||
await create_custom_instrumental("test-job-123", request)
|
||||
|
||||
assert exc_info.value.status_code == 400
|
||||
|
||||
|
||||
class TestGetWaveformData:
|
||||
"""Tests for GET /api/jobs/{job_id}/waveform-data."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_waveform_data_job_not_found(self, mock_job_manager):
|
||||
"""Should return 404 for non-existent job."""
|
||||
mock_job_manager.get_job.return_value = None
|
||||
|
||||
from backend.api.routes.jobs import get_waveform_data
|
||||
from fastapi import HTTPException
|
||||
|
||||
with pytest.raises(HTTPException) as exc_info:
|
||||
await get_waveform_data("non-existent")
|
||||
|
||||
assert exc_info.value.status_code == 404
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_waveform_data_wrong_status(self, mock_job_manager, sample_job):
|
||||
"""Should return 400 for wrong job status."""
|
||||
sample_job.status = JobStatus.PENDING
|
||||
mock_job_manager.get_job.return_value = sample_job
|
||||
|
||||
from backend.api.routes.jobs import get_waveform_data
|
||||
from fastapi import HTTPException
|
||||
|
||||
with pytest.raises(HTTPException) as exc_info:
|
||||
await get_waveform_data("test-job-123")
|
||||
|
||||
assert exc_info.value.status_code == 400
|
||||
|
||||
def test_waveform_data_endpoint_exists(self):
|
||||
"""Verify the endpoint function exists and is callable."""
|
||||
from backend.api.routes.jobs import get_waveform_data
|
||||
|
||||
assert callable(get_waveform_data)
|
||||
# Verify it's an async function
|
||||
import inspect
|
||||
assert inspect.iscoroutinefunction(get_waveform_data)
|
||||
|
||||
|
||||
class TestRequestModels:
|
||||
"""Tests for API request models."""
|
||||
|
||||
def test_mute_region_request_valid(self):
|
||||
"""MuteRegionRequest should accept valid values."""
|
||||
from backend.models.requests import MuteRegionRequest
|
||||
|
||||
region = MuteRegionRequest(start_seconds=10.0, end_seconds=20.0)
|
||||
|
||||
assert region.start_seconds == 10.0
|
||||
assert region.end_seconds == 20.0
|
||||
|
||||
def test_mute_region_request_invalid_start(self):
|
||||
"""MuteRegionRequest should reject negative start."""
|
||||
from backend.models.requests import MuteRegionRequest
|
||||
from pydantic import ValidationError
|
||||
|
||||
with pytest.raises(ValidationError):
|
||||
MuteRegionRequest(start_seconds=-1.0, end_seconds=20.0)
|
||||
|
||||
def test_mute_region_request_invalid_order(self):
|
||||
"""MuteRegionRequest should reject end before start."""
|
||||
from backend.models.requests import MuteRegionRequest
|
||||
from pydantic import ValidationError
|
||||
|
||||
with pytest.raises(ValidationError):
|
||||
MuteRegionRequest(start_seconds=20.0, end_seconds=10.0)
|
||||
|
||||
def test_create_custom_instrumental_request_valid(self):
|
||||
"""CreateCustomInstrumentalRequest should accept valid mute regions."""
|
||||
from backend.models.requests import (
|
||||
CreateCustomInstrumentalRequest,
|
||||
MuteRegionRequest,
|
||||
)
|
||||
|
||||
request = CreateCustomInstrumentalRequest(
|
||||
mute_regions=[
|
||||
MuteRegionRequest(start_seconds=10.0, end_seconds=20.0),
|
||||
MuteRegionRequest(start_seconds=60.0, end_seconds=80.0),
|
||||
]
|
||||
)
|
||||
|
||||
assert len(request.mute_regions) == 2
|
||||
|
||||
|
||||
class TestInstrumentalSelectionExtension:
|
||||
"""Tests for extended instrumental selection (including 'custom')."""
|
||||
|
||||
def test_instrumental_selection_accepts_custom(self):
|
||||
"""InstrumentalSelection should accept 'custom' as valid selection."""
|
||||
from backend.models.requests import InstrumentalSelection
|
||||
|
||||
selection = InstrumentalSelection(selection="custom")
|
||||
assert selection.selection == "custom"
|
||||
|
||||
def test_instrumental_selection_accepts_clean(self):
|
||||
"""InstrumentalSelection should accept 'clean' as valid selection."""
|
||||
from backend.models.requests import InstrumentalSelection
|
||||
|
||||
selection = InstrumentalSelection(selection="clean")
|
||||
assert selection.selection == "clean"
|
||||
|
||||
def test_instrumental_selection_accepts_with_backing(self):
|
||||
"""InstrumentalSelection should accept 'with_backing' as valid selection."""
|
||||
from backend.models.requests import InstrumentalSelection
|
||||
|
||||
selection = InstrumentalSelection(selection="with_backing")
|
||||
assert selection.selection == "with_backing"
|
||||
|
||||
def test_instrumental_selection_rejects_invalid(self):
|
||||
"""InstrumentalSelection should reject invalid values."""
|
||||
from backend.models.requests import InstrumentalSelection
|
||||
from pydantic import ValidationError
|
||||
|
||||
with pytest.raises(ValidationError):
|
||||
InstrumentalSelection(selection="invalid_option")
|
||||
@@ -3,6 +3,9 @@ Unit tests for internal.py API routes using FastAPI TestClient.
|
||||
|
||||
Internal routes are used for worker communication within Cloud Run.
|
||||
These endpoints require admin authentication.
|
||||
|
||||
With Cloud Tasks integration, these endpoints include idempotency checks
|
||||
to prevent duplicate processing on retries.
|
||||
"""
|
||||
import os
|
||||
import pytest
|
||||
@@ -17,9 +20,20 @@ from backend.models.job import Job, JobStatus
|
||||
os.environ.setdefault('ADMIN_TOKENS', 'test-admin-token')
|
||||
|
||||
|
||||
def _create_mock_job(job_id: str = "test123") -> Job:
|
||||
"""Create a mock Job object for testing."""
|
||||
return Job(
|
||||
job_id=job_id,
|
||||
status=JobStatus.PROCESSING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
state_data={}, # Empty state_data - no worker progress yet
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def client():
|
||||
"""Create TestClient with mocked workers."""
|
||||
"""Create TestClient with mocked workers and job manager."""
|
||||
mock_creds = MagicMock()
|
||||
mock_creds.universe_domain = 'googleapis.com'
|
||||
|
||||
@@ -28,11 +42,19 @@ def client():
|
||||
mock_lyrics = AsyncMock()
|
||||
mock_screens = AsyncMock()
|
||||
mock_video = AsyncMock()
|
||||
mock_render = AsyncMock()
|
||||
|
||||
# Mock JobManager for idempotency checks
|
||||
mock_job_manager = MagicMock()
|
||||
mock_job_manager.get_job.return_value = _create_mock_job()
|
||||
mock_job_manager.update_state_data.return_value = None
|
||||
|
||||
with patch('backend.api.routes.internal.process_audio_separation', mock_audio), \
|
||||
patch('backend.api.routes.internal.process_lyrics_transcription', mock_lyrics), \
|
||||
patch('backend.api.routes.internal.generate_screens', mock_screens), \
|
||||
patch('backend.api.routes.internal.generate_video', mock_video), \
|
||||
patch('backend.api.routes.internal.process_render_video', mock_render), \
|
||||
patch('backend.api.routes.internal.JobManager', return_value=mock_job_manager), \
|
||||
patch('backend.services.firestore_service.firestore'), \
|
||||
patch('backend.services.storage_service.storage'), \
|
||||
patch('google.auth.default', return_value=(mock_creds, 'test-project')):
|
||||
@@ -76,7 +98,7 @@ class TestAudioWorkerEndpoint:
|
||||
)
|
||||
assert response.status_code == 422
|
||||
|
||||
def test_audio_worker_requires_auth(self, client):
|
||||
def test_audio_worker_requires_auth(self, client, auth_headers):
|
||||
"""Test audio worker requires authentication."""
|
||||
response = client.post(
|
||||
"/api/internal/workers/audio",
|
||||
@@ -106,7 +128,7 @@ class TestLyricsWorkerEndpoint:
|
||||
)
|
||||
assert response.status_code == 422
|
||||
|
||||
def test_lyrics_worker_requires_auth(self, client):
|
||||
def test_lyrics_worker_requires_auth(self, client, auth_headers):
|
||||
"""Test lyrics worker requires authentication."""
|
||||
response = client.post(
|
||||
"/api/internal/workers/lyrics",
|
||||
@@ -136,7 +158,7 @@ class TestScreensWorkerEndpoint:
|
||||
)
|
||||
assert response.status_code == 422
|
||||
|
||||
def test_screens_worker_requires_auth(self, client):
|
||||
def test_screens_worker_requires_auth(self, client, auth_headers):
|
||||
"""Test screens worker requires authentication."""
|
||||
response = client.post(
|
||||
"/api/internal/workers/screens",
|
||||
@@ -166,7 +188,7 @@ class TestVideoWorkerEndpoint:
|
||||
)
|
||||
assert response.status_code == 422
|
||||
|
||||
def test_video_worker_requires_auth(self, client):
|
||||
def test_video_worker_requires_auth(self, client, auth_headers):
|
||||
"""Test video worker requires authentication."""
|
||||
response = client.post(
|
||||
"/api/internal/workers/video",
|
||||
@@ -175,6 +197,36 @@ class TestVideoWorkerEndpoint:
|
||||
assert response.status_code == 401
|
||||
|
||||
|
||||
class TestRenderVideoWorkerEndpoint:
|
||||
"""Tests for POST /api/internal/workers/render-video."""
|
||||
|
||||
def test_render_video_worker_returns_200(self, client, auth_headers):
|
||||
"""Test render-video worker endpoint returns 200 with auth."""
|
||||
response = client.post(
|
||||
"/api/internal/workers/render-video",
|
||||
headers=auth_headers,
|
||||
json={"job_id": "test123"}
|
||||
)
|
||||
assert response.status_code == 200
|
||||
|
||||
def test_render_video_worker_requires_job_id(self, client, auth_headers):
|
||||
"""Test render-video worker requires job_id."""
|
||||
response = client.post(
|
||||
"/api/internal/workers/render-video",
|
||||
headers=auth_headers,
|
||||
json={}
|
||||
)
|
||||
assert response.status_code == 422
|
||||
|
||||
def test_render_video_worker_requires_auth(self, client, auth_headers):
|
||||
"""Test render-video worker requires authentication."""
|
||||
response = client.post(
|
||||
"/api/internal/workers/render-video",
|
||||
json={"job_id": "test123"}
|
||||
)
|
||||
assert response.status_code == 401
|
||||
|
||||
|
||||
class TestWorkerResponseFormat:
|
||||
"""Tests for worker response format."""
|
||||
|
||||
@@ -198,3 +250,94 @@ class TestWorkerResponseFormat:
|
||||
data = response.json()
|
||||
assert "status" in data or "message" in data
|
||||
|
||||
|
||||
class TestWorkerIdempotency:
|
||||
"""Tests for worker idempotency checks (Cloud Tasks retry support)."""
|
||||
|
||||
def test_audio_worker_returns_already_running_when_in_progress(self, auth_headers):
|
||||
"""Test audio worker returns already_running if worker is already running."""
|
||||
mock_creds = MagicMock()
|
||||
mock_creds.universe_domain = 'googleapis.com'
|
||||
|
||||
# Create job with audio already running
|
||||
mock_job = _create_mock_job()
|
||||
mock_job.state_data = {'audio_progress': {'stage': 'running'}}
|
||||
|
||||
mock_job_manager = MagicMock()
|
||||
mock_job_manager.get_job.return_value = mock_job
|
||||
|
||||
with patch('backend.api.routes.internal.process_audio_separation', AsyncMock()), \
|
||||
patch('backend.api.routes.internal.JobManager', return_value=mock_job_manager), \
|
||||
patch('backend.services.firestore_service.firestore'), \
|
||||
patch('backend.services.storage_service.storage'), \
|
||||
patch('google.auth.default', return_value=(mock_creds, 'test-project')):
|
||||
from backend.main import app
|
||||
client = TestClient(app)
|
||||
|
||||
response = client.post(
|
||||
"/api/internal/workers/audio",
|
||||
headers=auth_headers,
|
||||
json={"job_id": "test123"}
|
||||
)
|
||||
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
assert data["status"] == "already_running"
|
||||
|
||||
def test_audio_worker_returns_already_complete_when_finished(self, auth_headers):
|
||||
"""Test audio worker returns already_complete if worker already finished."""
|
||||
mock_creds = MagicMock()
|
||||
mock_creds.universe_domain = 'googleapis.com'
|
||||
|
||||
# Create job with audio already complete
|
||||
mock_job = _create_mock_job()
|
||||
mock_job.state_data = {'audio_progress': {'stage': 'complete'}}
|
||||
|
||||
mock_job_manager = MagicMock()
|
||||
mock_job_manager.get_job.return_value = mock_job
|
||||
|
||||
with patch('backend.api.routes.internal.process_audio_separation', AsyncMock()), \
|
||||
patch('backend.api.routes.internal.JobManager', return_value=mock_job_manager), \
|
||||
patch('backend.services.firestore_service.firestore'), \
|
||||
patch('backend.services.storage_service.storage'), \
|
||||
patch('google.auth.default', return_value=(mock_creds, 'test-project')):
|
||||
from backend.main import app
|
||||
client = TestClient(app)
|
||||
|
||||
response = client.post(
|
||||
"/api/internal/workers/audio",
|
||||
headers=auth_headers,
|
||||
json={"job_id": "test123"}
|
||||
)
|
||||
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
assert data["status"] == "already_complete"
|
||||
|
||||
def test_audio_worker_returns_not_found_when_job_missing(self, auth_headers):
|
||||
"""Test audio worker returns not_found if job doesn't exist."""
|
||||
mock_creds = MagicMock()
|
||||
mock_creds.universe_domain = 'googleapis.com'
|
||||
|
||||
# Return None for job not found
|
||||
mock_job_manager = MagicMock()
|
||||
mock_job_manager.get_job.return_value = None
|
||||
|
||||
with patch('backend.api.routes.internal.process_audio_separation', AsyncMock()), \
|
||||
patch('backend.api.routes.internal.JobManager', return_value=mock_job_manager), \
|
||||
patch('backend.services.firestore_service.firestore'), \
|
||||
patch('backend.services.storage_service.storage'), \
|
||||
patch('google.auth.default', return_value=(mock_creds, 'test-project')):
|
||||
from backend.main import app
|
||||
client = TestClient(app)
|
||||
|
||||
response = client.post(
|
||||
"/api/internal/workers/audio",
|
||||
headers=auth_headers,
|
||||
json={"job_id": "nonexistent"}
|
||||
)
|
||||
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
assert data["status"] == "not_found"
|
||||
|
||||
@@ -102,6 +102,37 @@ class TestJobCreation:
|
||||
|
||||
assert job.status == JobStatus.PENDING
|
||||
assert job.progress == 0
|
||||
|
||||
def test_create_job_with_distribution_settings(self, job_manager, mock_firestore_service):
|
||||
"""Test that distribution settings are passed from JobCreate to Job.
|
||||
|
||||
This was a bug where brand_prefix, dropbox_path, gdrive_folder_id, and
|
||||
discord_webhook_url were NOT being passed to the Job constructor.
|
||||
"""
|
||||
job_create = JobCreate(
|
||||
artist="Test Artist",
|
||||
title="Test Song",
|
||||
brand_prefix="NOMAD",
|
||||
discord_webhook_url="https://discord.com/webhook/test",
|
||||
dropbox_path="/Karaoke/Tracks-Organized",
|
||||
gdrive_folder_id="1abc123xyz",
|
||||
enable_youtube_upload=True,
|
||||
)
|
||||
|
||||
job = job_manager.create_job(job_create)
|
||||
|
||||
# Verify distribution settings are passed through
|
||||
assert job.brand_prefix == "NOMAD"
|
||||
assert job.discord_webhook_url == "https://discord.com/webhook/test"
|
||||
assert job.dropbox_path == "/Karaoke/Tracks-Organized"
|
||||
assert job.gdrive_folder_id == "1abc123xyz"
|
||||
assert job.enable_youtube_upload is True
|
||||
|
||||
# Verify Firestore was called with job containing these fields
|
||||
mock_firestore_service.create_job.assert_called_once()
|
||||
created_job = mock_firestore_service.create_job.call_args[0][0]
|
||||
assert created_job.brand_prefix == "NOMAD"
|
||||
assert created_job.dropbox_path == "/Karaoke/Tracks-Organized"
|
||||
|
||||
|
||||
class TestJobRetrieval:
|
||||
|
||||
@@ -68,20 +68,20 @@ def client(mock_job_manager, mock_worker_service):
|
||||
class TestGetJob:
|
||||
"""Tests for GET /api/jobs/{job_id}."""
|
||||
|
||||
def test_get_job_returns_200(self, client, mock_job_manager, mock_job):
|
||||
def test_get_job_returns_200(self, client, mock_job_manager, mock_job, auth_headers):
|
||||
"""Test getting an existing job returns 200."""
|
||||
response = client.get("/api/jobs/test123")
|
||||
response = client.get("/api/jobs/test123", headers=auth_headers)
|
||||
assert response.status_code == 200
|
||||
|
||||
def test_get_job_returns_job_data(self, client, mock_job_manager, mock_job):
|
||||
def test_get_job_returns_job_data(self, client, mock_job_manager, mock_job, auth_headers):
|
||||
"""Test response contains job data."""
|
||||
response = client.get("/api/jobs/test123")
|
||||
response = client.get("/api/jobs/test123", headers=auth_headers)
|
||||
data = response.json()
|
||||
assert data["job_id"] == "test123"
|
||||
assert data["status"] == "pending"
|
||||
assert data["artist"] == "Test Artist"
|
||||
|
||||
def test_get_nonexistent_job_returns_404(self, mock_worker_service):
|
||||
def test_get_nonexistent_job_returns_404(self, mock_worker_service, auth_headers):
|
||||
"""Test getting non-existent job returns 404."""
|
||||
mock_job_manager = MagicMock()
|
||||
mock_job_manager.get_job.return_value = None
|
||||
@@ -95,58 +95,60 @@ class TestGetJob:
|
||||
patch('google.auth.default', return_value=(mock_creds, 'test-project')):
|
||||
from backend.main import app
|
||||
client = TestClient(app)
|
||||
response = client.get("/api/jobs/nonexistent")
|
||||
response = client.get("/api/jobs/nonexistent", headers=auth_headers)
|
||||
assert response.status_code == 404
|
||||
|
||||
|
||||
class TestListJobs:
|
||||
"""Tests for GET /api/jobs."""
|
||||
|
||||
def test_list_jobs_returns_200(self, client):
|
||||
def test_list_jobs_returns_200(self, client, auth_headers):
|
||||
"""Test listing jobs returns 200."""
|
||||
response = client.get("/api/jobs")
|
||||
response = client.get("/api/jobs", headers=auth_headers)
|
||||
assert response.status_code == 200
|
||||
|
||||
def test_list_jobs_returns_array(self, client, mock_job_manager):
|
||||
def test_list_jobs_returns_array(self, client, mock_job_manager, auth_headers):
|
||||
"""Test response is an array of jobs."""
|
||||
response = client.get("/api/jobs")
|
||||
response = client.get("/api/jobs", headers=auth_headers)
|
||||
data = response.json()
|
||||
assert isinstance(data, list)
|
||||
assert len(data) == 1
|
||||
assert data[0]["job_id"] == "test123"
|
||||
|
||||
def test_list_jobs_with_status_filter(self, client, mock_job_manager):
|
||||
def test_list_jobs_with_status_filter(self, client, mock_job_manager, auth_headers):
|
||||
"""Test listing jobs with status filter."""
|
||||
response = client.get("/api/jobs?status=pending")
|
||||
response = client.get("/api/jobs?status=pending", headers=auth_headers)
|
||||
assert response.status_code == 200
|
||||
|
||||
def test_list_jobs_with_limit(self, client, mock_job_manager):
|
||||
def test_list_jobs_with_limit(self, client, mock_job_manager, auth_headers):
|
||||
"""Test listing jobs with limit."""
|
||||
response = client.get("/api/jobs?limit=10")
|
||||
response = client.get("/api/jobs?limit=10", headers=auth_headers)
|
||||
assert response.status_code == 200
|
||||
|
||||
|
||||
class TestCreateJob:
|
||||
"""Tests for POST /api/jobs."""
|
||||
|
||||
def test_create_job_with_url_returns_200(self, client, mock_job_manager):
|
||||
def test_create_job_with_url_returns_200(self, client, mock_job_manager, auth_headers):
|
||||
"""Test creating job with URL returns 200."""
|
||||
response = client.post(
|
||||
"/api/jobs",
|
||||
json={"url": "https://youtube.com/watch?v=test123"}
|
||||
json={"url": "https://youtube.com/watch?v=test123"},
|
||||
headers=auth_headers
|
||||
)
|
||||
assert response.status_code == 200
|
||||
|
||||
def test_create_job_returns_job_id(self, client, mock_job_manager):
|
||||
def test_create_job_returns_job_id(self, client, mock_job_manager, auth_headers):
|
||||
"""Test create response contains job_id."""
|
||||
response = client.post(
|
||||
"/api/jobs",
|
||||
json={"url": "https://youtube.com/watch?v=test"}
|
||||
json={"url": "https://youtube.com/watch?v=test"},
|
||||
headers=auth_headers
|
||||
)
|
||||
data = response.json()
|
||||
assert "job_id" in data
|
||||
|
||||
def test_create_job_with_artist_title(self, client, mock_job_manager):
|
||||
def test_create_job_with_artist_title(self, client, mock_job_manager, auth_headers):
|
||||
"""Test creating job with artist and title."""
|
||||
response = client.post(
|
||||
"/api/jobs",
|
||||
@@ -154,7 +156,8 @@ class TestCreateJob:
|
||||
"url": "https://youtube.com/watch?v=test",
|
||||
"artist": "Test Artist",
|
||||
"title": "Test Song"
|
||||
}
|
||||
},
|
||||
headers=auth_headers
|
||||
)
|
||||
assert response.status_code == 200
|
||||
|
||||
@@ -162,12 +165,12 @@ class TestCreateJob:
|
||||
class TestDeleteJob:
|
||||
"""Tests for DELETE /api/jobs/{job_id}."""
|
||||
|
||||
def test_delete_job_returns_200(self, client, mock_job_manager):
|
||||
def test_delete_job_returns_200(self, client, mock_job_manager, auth_headers):
|
||||
"""Test deleting job returns 200."""
|
||||
response = client.delete("/api/jobs/test123")
|
||||
response = client.delete("/api/jobs/test123", headers=auth_headers)
|
||||
assert response.status_code == 200
|
||||
|
||||
def test_delete_nonexistent_job(self, mock_worker_service):
|
||||
def test_delete_nonexistent_job(self, mock_worker_service, auth_headers):
|
||||
"""Test deleting non-existent job."""
|
||||
mock_job_manager = MagicMock()
|
||||
mock_job_manager.delete_job.return_value = False
|
||||
@@ -181,7 +184,7 @@ class TestDeleteJob:
|
||||
patch('google.auth.default', return_value=(mock_creds, 'test-project')):
|
||||
from backend.main import app
|
||||
client = TestClient(app)
|
||||
response = client.delete("/api/jobs/nonexistent")
|
||||
response = client.delete("/api/jobs/nonexistent", headers=auth_headers)
|
||||
# Either 200 or 404 depending on implementation
|
||||
assert response.status_code in [200, 404]
|
||||
|
||||
@@ -189,12 +192,13 @@ class TestDeleteJob:
|
||||
class TestCancelJob:
|
||||
"""Tests for POST /api/jobs/{job_id}/cancel."""
|
||||
|
||||
def test_cancel_job_returns_200(self, client, mock_job_manager, mock_job):
|
||||
def test_cancel_job_returns_200(self, client, mock_job_manager, mock_job, auth_headers):
|
||||
"""Test cancelling job returns 200."""
|
||||
mock_job_manager.cancel_job.return_value = mock_job
|
||||
response = client.post(
|
||||
"/api/jobs/test123/cancel",
|
||||
json={}
|
||||
json={},
|
||||
headers=auth_headers
|
||||
)
|
||||
assert response.status_code == 200
|
||||
|
||||
@@ -202,7 +206,7 @@ class TestCancelJob:
|
||||
class TestSubmitCorrections:
|
||||
"""Tests for POST /api/jobs/{job_id}/corrections."""
|
||||
|
||||
def test_submit_corrections_returns_200(self, client, mock_job_manager, mock_job):
|
||||
def test_submit_corrections_returns_200(self, client, mock_job_manager, mock_job, auth_headers):
|
||||
"""Test submitting corrections returns 200."""
|
||||
# Job needs to be in AWAITING_REVIEW or IN_REVIEW status
|
||||
review_job = Job(
|
||||
@@ -222,7 +226,8 @@ class TestSubmitCorrections:
|
||||
"lines": [],
|
||||
"metadata": {"source": "test"}
|
||||
}
|
||||
}
|
||||
},
|
||||
headers=auth_headers
|
||||
)
|
||||
# Should be 200 or validation error
|
||||
assert response.status_code in [200, 400, 422]
|
||||
@@ -231,11 +236,12 @@ class TestSubmitCorrections:
|
||||
class TestSelectInstrumental:
|
||||
"""Tests for POST /api/jobs/{job_id}/select-instrumental."""
|
||||
|
||||
def test_select_instrumental_requires_selection_field(self, client, mock_job_manager, mock_job):
|
||||
def test_select_instrumental_requires_selection_field(self, client, mock_job_manager, mock_job, auth_headers):
|
||||
"""Test instrumental selection requires selection field."""
|
||||
response = client.post(
|
||||
"/api/jobs/test123/select-instrumental",
|
||||
json={} # Missing selection field
|
||||
json={}, # Missing selection field
|
||||
headers=auth_headers
|
||||
)
|
||||
# Missing field should cause validation error
|
||||
assert response.status_code == 422
|
||||
@@ -244,9 +250,9 @@ class TestSelectInstrumental:
|
||||
class TestStartReview:
|
||||
"""Tests for POST /api/jobs/{job_id}/start-review."""
|
||||
|
||||
def test_start_review_endpoint_exists(self, client, mock_job_manager, mock_job):
|
||||
def test_start_review_endpoint_exists(self, client, mock_job_manager, mock_job, auth_headers):
|
||||
"""Test start review endpoint exists."""
|
||||
response = client.post("/api/jobs/test123/start-review")
|
||||
response = client.post("/api/jobs/test123/start-review", headers=auth_headers)
|
||||
# Should not be 404 or 405
|
||||
assert response.status_code not in [404, 405]
|
||||
|
||||
@@ -577,6 +577,342 @@ class TestJobModelIntegration:
|
||||
assert restored_job.state_data["lyrics_metadata"]["line_count"] == 50
|
||||
|
||||
|
||||
class TestExistingInstrumentalModelFields:
|
||||
"""Test existing instrumental field in Job and JobCreate models (Batch 3)."""
|
||||
|
||||
def test_job_has_existing_instrumental_gcs_path(self):
|
||||
"""Test that Job model has existing_instrumental_gcs_path field."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
existing_instrumental_gcs_path="uploads/test123/audio/existing_instrumental.flac"
|
||||
)
|
||||
|
||||
assert hasattr(job, 'existing_instrumental_gcs_path')
|
||||
assert job.existing_instrumental_gcs_path == "uploads/test123/audio/existing_instrumental.flac"
|
||||
|
||||
def test_job_existing_instrumental_defaults_to_none(self):
|
||||
"""Test that existing_instrumental_gcs_path defaults to None."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC)
|
||||
)
|
||||
|
||||
assert job.existing_instrumental_gcs_path is None
|
||||
|
||||
def test_job_create_has_existing_instrumental_gcs_path(self):
|
||||
"""Test that JobCreate model has existing_instrumental_gcs_path field."""
|
||||
from backend.models.job import JobCreate
|
||||
|
||||
job_create = JobCreate(
|
||||
artist="Artist",
|
||||
title="Title",
|
||||
existing_instrumental_gcs_path="uploads/test/audio/existing_instrumental.mp3"
|
||||
)
|
||||
|
||||
assert job_create.existing_instrumental_gcs_path == "uploads/test/audio/existing_instrumental.mp3"
|
||||
|
||||
def test_job_create_existing_instrumental_optional(self):
|
||||
"""Test that existing_instrumental_gcs_path is optional in JobCreate."""
|
||||
from backend.models.job import JobCreate
|
||||
|
||||
job_create = JobCreate(
|
||||
artist="Artist",
|
||||
title="Title"
|
||||
)
|
||||
|
||||
assert job_create.existing_instrumental_gcs_path is None
|
||||
|
||||
def test_existing_instrumental_roundtrip_serialization(self):
|
||||
"""Test that existing_instrumental_gcs_path survives serialization/deserialization."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
existing_instrumental_gcs_path="uploads/test123/audio/existing_instrumental.wav"
|
||||
)
|
||||
|
||||
# Serialize to dict (simulates writing to Firestore)
|
||||
job_dict = job.model_dump()
|
||||
|
||||
# Convert to JSON and back (simulates Firestore storage)
|
||||
json_str = json.dumps(job_dict, default=str)
|
||||
restored_dict = json.loads(json_str)
|
||||
|
||||
# Deserialize back to Job (simulates reading from Firestore)
|
||||
restored_job = Job(**restored_dict)
|
||||
|
||||
assert restored_job.existing_instrumental_gcs_path == "uploads/test123/audio/existing_instrumental.wav"
|
||||
|
||||
def test_job_with_full_audio_config(self):
|
||||
"""Test Job with complete audio configuration including existing instrumental."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.AUDIO_COMPLETE,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test Artist",
|
||||
title="Test Song",
|
||||
# Audio model configuration
|
||||
clean_instrumental_model="model_bs_roformer_ep_317_sdr_12.9755.ckpt",
|
||||
backing_vocals_models=["mel_band_roformer_karaoke.ckpt"],
|
||||
other_stems_models=["htdemucs_6s.yaml"],
|
||||
# Existing instrumental
|
||||
existing_instrumental_gcs_path="uploads/test123/audio/my_instrumental.flac",
|
||||
)
|
||||
|
||||
assert job.clean_instrumental_model == "model_bs_roformer_ep_317_sdr_12.9755.ckpt"
|
||||
assert job.existing_instrumental_gcs_path == "uploads/test123/audio/my_instrumental.flac"
|
||||
|
||||
|
||||
class TestTwoPhaseWorkflowFields:
|
||||
"""Test two-phase workflow fields in Job and JobCreate models (Batch 6)."""
|
||||
|
||||
def test_job_has_prep_only_field(self):
|
||||
"""Test that Job model has prep_only field."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
prep_only=True
|
||||
)
|
||||
|
||||
assert hasattr(job, 'prep_only')
|
||||
assert job.prep_only is True
|
||||
|
||||
def test_job_prep_only_defaults_to_false(self):
|
||||
"""Test that prep_only defaults to False."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC)
|
||||
)
|
||||
|
||||
assert job.prep_only is False
|
||||
|
||||
def test_job_has_finalise_only_field(self):
|
||||
"""Test that Job model has finalise_only field."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
finalise_only=True
|
||||
)
|
||||
|
||||
assert hasattr(job, 'finalise_only')
|
||||
assert job.finalise_only is True
|
||||
|
||||
def test_job_finalise_only_defaults_to_false(self):
|
||||
"""Test that finalise_only defaults to False."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC)
|
||||
)
|
||||
|
||||
assert job.finalise_only is False
|
||||
|
||||
def test_job_has_keep_brand_code_field(self):
|
||||
"""Test that Job model has keep_brand_code field."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
keep_brand_code="NOMAD-1234"
|
||||
)
|
||||
|
||||
assert hasattr(job, 'keep_brand_code')
|
||||
assert job.keep_brand_code == "NOMAD-1234"
|
||||
|
||||
def test_job_keep_brand_code_defaults_to_none(self):
|
||||
"""Test that keep_brand_code defaults to None."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC)
|
||||
)
|
||||
|
||||
assert job.keep_brand_code is None
|
||||
|
||||
def test_job_create_has_two_phase_workflow_fields(self):
|
||||
"""Test that JobCreate model has two-phase workflow fields."""
|
||||
job_create = JobCreate(
|
||||
artist="Artist",
|
||||
title="Title",
|
||||
prep_only=True,
|
||||
finalise_only=False,
|
||||
keep_brand_code="BRAND-0001"
|
||||
)
|
||||
|
||||
assert job_create.prep_only is True
|
||||
assert job_create.finalise_only is False
|
||||
assert job_create.keep_brand_code == "BRAND-0001"
|
||||
|
||||
def test_two_phase_workflow_roundtrip_serialization(self):
|
||||
"""Test that two-phase workflow fields survive serialization/deserialization."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
prep_only=True,
|
||||
finalise_only=False,
|
||||
keep_brand_code="NOMAD-5678"
|
||||
)
|
||||
|
||||
# Serialize to dict (simulates writing to Firestore)
|
||||
job_dict = job.model_dump()
|
||||
|
||||
# Convert to JSON and back (simulates Firestore storage)
|
||||
json_str = json.dumps(job_dict, default=str)
|
||||
restored_dict = json.loads(json_str)
|
||||
|
||||
# Deserialize back to Job (simulates reading from Firestore)
|
||||
restored_job = Job(**restored_dict)
|
||||
|
||||
assert restored_job.prep_only is True
|
||||
assert restored_job.finalise_only is False
|
||||
assert restored_job.keep_brand_code == "NOMAD-5678"
|
||||
|
||||
|
||||
class TestPrepCompleteStatus:
|
||||
"""Test PREP_COMPLETE status and state transitions (Batch 6)."""
|
||||
|
||||
def test_prep_complete_status_exists(self):
|
||||
"""Test that PREP_COMPLETE status exists in JobStatus enum."""
|
||||
assert hasattr(JobStatus, 'PREP_COMPLETE')
|
||||
assert JobStatus.PREP_COMPLETE.value == "prep_complete"
|
||||
|
||||
def test_job_can_have_prep_complete_status(self):
|
||||
"""Test that Job can be created with PREP_COMPLETE status."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PREP_COMPLETE,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC)
|
||||
)
|
||||
|
||||
assert job.status == JobStatus.PREP_COMPLETE
|
||||
|
||||
def test_state_transitions_review_complete_to_prep_complete(self):
|
||||
"""Test that REVIEW_COMPLETE can transition to PREP_COMPLETE."""
|
||||
from backend.models.job import STATE_TRANSITIONS
|
||||
|
||||
valid_transitions = STATE_TRANSITIONS.get(JobStatus.REVIEW_COMPLETE, [])
|
||||
assert JobStatus.PREP_COMPLETE in valid_transitions
|
||||
|
||||
def test_state_transitions_prep_complete_to_awaiting_instrumental(self):
|
||||
"""Test that PREP_COMPLETE can transition to AWAITING_INSTRUMENTAL_SELECTION."""
|
||||
from backend.models.job import STATE_TRANSITIONS
|
||||
|
||||
valid_transitions = STATE_TRANSITIONS.get(JobStatus.PREP_COMPLETE, [])
|
||||
assert JobStatus.AWAITING_INSTRUMENTAL_SELECTION in valid_transitions
|
||||
|
||||
def test_state_transitions_pending_to_awaiting_instrumental(self):
|
||||
"""Test that PENDING can transition to AWAITING_INSTRUMENTAL_SELECTION (for finalise-only)."""
|
||||
from backend.models.job import STATE_TRANSITIONS
|
||||
|
||||
valid_transitions = STATE_TRANSITIONS.get(JobStatus.PENDING, [])
|
||||
assert JobStatus.AWAITING_INSTRUMENTAL_SELECTION in valid_transitions
|
||||
|
||||
def test_critical_statuses_include_prep_complete(self):
|
||||
"""Test that PREP_COMPLETE is in the list of job statuses."""
|
||||
all_statuses = [status.value for status in JobStatus]
|
||||
assert "prep_complete" in all_statuses
|
||||
|
||||
|
||||
class TestJobWithFullTwoPhaseConfig:
|
||||
"""Integration tests for two-phase workflow job configuration."""
|
||||
|
||||
def test_prep_only_job_full_config(self):
|
||||
"""Test creating a prep-only job with full configuration."""
|
||||
job = Job(
|
||||
job_id="prep123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test Artist",
|
||||
title="Test Song",
|
||||
prep_only=True,
|
||||
enable_cdg=True,
|
||||
enable_txt=True,
|
||||
brand_prefix="NOMAD",
|
||||
)
|
||||
|
||||
assert job.prep_only is True
|
||||
assert job.finalise_only is False
|
||||
assert job.brand_prefix == "NOMAD"
|
||||
|
||||
def test_finalise_only_job_full_config(self):
|
||||
"""Test creating a finalise-only job with full configuration."""
|
||||
job = Job(
|
||||
job_id="final123",
|
||||
status=JobStatus.AWAITING_INSTRUMENTAL_SELECTION,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test Artist",
|
||||
title="Test Song",
|
||||
finalise_only=True,
|
||||
keep_brand_code="NOMAD-1234",
|
||||
enable_youtube_upload=True,
|
||||
dropbox_path="/Karaoke/Tracks",
|
||||
state_data={
|
||||
"audio_complete": True,
|
||||
"lyrics_complete": True,
|
||||
"finalise_only": True,
|
||||
}
|
||||
)
|
||||
|
||||
assert job.finalise_only is True
|
||||
assert job.keep_brand_code == "NOMAD-1234"
|
||||
assert job.state_data["finalise_only"] is True
|
||||
|
||||
def test_prep_complete_job_with_file_urls(self):
|
||||
"""Test a job that has reached PREP_COMPLETE status with all prep outputs."""
|
||||
job = Job(
|
||||
job_id="prepcomp123",
|
||||
status=JobStatus.PREP_COMPLETE,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="ABBA",
|
||||
title="Waterloo",
|
||||
prep_only=True,
|
||||
file_urls={
|
||||
"stems": {
|
||||
"instrumental_clean": "gs://bucket/jobs/prepcomp123/stems/instrumental_clean.flac",
|
||||
"instrumental_with_backing": "gs://bucket/jobs/prepcomp123/stems/instrumental_with_backing.flac",
|
||||
},
|
||||
"videos": {
|
||||
"with_vocals": "gs://bucket/jobs/prepcomp123/videos/with_vocals.mkv",
|
||||
},
|
||||
"screens": {
|
||||
"title": "gs://bucket/jobs/prepcomp123/screens/title.mov",
|
||||
"end": "gs://bucket/jobs/prepcomp123/screens/end.mov",
|
||||
},
|
||||
"lyrics": {
|
||||
"lrc": "gs://bucket/jobs/prepcomp123/lyrics/karaoke.lrc",
|
||||
"ass": "gs://bucket/jobs/prepcomp123/lyrics/karaoke.ass",
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
assert job.status == JobStatus.PREP_COMPLETE
|
||||
assert job.prep_only is True
|
||||
assert "with_vocals" in job.file_urls["videos"]
|
||||
assert "title" in job.file_urls["screens"]
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
pytest.main([__file__, "-v"])
|
||||
|
||||
@@ -146,8 +146,9 @@ class TestUploadSubmissionRequest:
|
||||
def test_default_options(self):
|
||||
"""Test default option values."""
|
||||
request = UploadSubmissionRequest(artist="Test", title="Test")
|
||||
assert request.enable_cdg is True
|
||||
assert request.enable_txt is True
|
||||
# CDG/TXT disabled by default (requires style config)
|
||||
assert request.enable_cdg is False
|
||||
assert request.enable_txt is False
|
||||
assert request.enable_youtube_upload is False
|
||||
|
||||
|
||||
|
||||
@@ -67,12 +67,31 @@ class TestJobStatusTransitions:
|
||||
"""Test FAILED status can transition to retry checkpoint states."""
|
||||
from backend.models.job import STATE_TRANSITIONS
|
||||
valid_transitions = STATE_TRANSITIONS.get(JobStatus.FAILED, [])
|
||||
|
||||
|
||||
# FAILED should allow retry transitions
|
||||
assert JobStatus.INSTRUMENTAL_SELECTED in valid_transitions, "FAILED should allow retry to INSTRUMENTAL_SELECTED"
|
||||
assert JobStatus.REVIEW_COMPLETE in valid_transitions, "FAILED should allow retry to REVIEW_COMPLETE"
|
||||
assert JobStatus.LYRICS_COMPLETE in valid_transitions, "FAILED should allow retry to LYRICS_COMPLETE"
|
||||
|
||||
def test_cancelled_can_transition_for_retry(self):
|
||||
"""Test CANCELLED status can transition to retry checkpoint states."""
|
||||
from backend.models.job import STATE_TRANSITIONS
|
||||
valid_transitions = STATE_TRANSITIONS.get(JobStatus.CANCELLED, [])
|
||||
|
||||
# CANCELLED should allow same retry transitions as FAILED
|
||||
assert JobStatus.INSTRUMENTAL_SELECTED in valid_transitions, "CANCELLED should allow retry to INSTRUMENTAL_SELECTED"
|
||||
assert JobStatus.REVIEW_COMPLETE in valid_transitions, "CANCELLED should allow retry to REVIEW_COMPLETE"
|
||||
assert JobStatus.LYRICS_COMPLETE in valid_transitions, "CANCELLED should allow retry to LYRICS_COMPLETE"
|
||||
assert JobStatus.DOWNLOADING in valid_transitions, "CANCELLED should allow retry to DOWNLOADING (restart)"
|
||||
|
||||
def test_failed_can_restart_from_beginning(self):
|
||||
"""Test FAILED status can transition to DOWNLOADING for restart from beginning."""
|
||||
from backend.models.job import STATE_TRANSITIONS
|
||||
valid_transitions = STATE_TRANSITIONS.get(JobStatus.FAILED, [])
|
||||
|
||||
# FAILED should allow restart from beginning
|
||||
assert JobStatus.DOWNLOADING in valid_transitions, "FAILED should allow restart to DOWNLOADING"
|
||||
|
||||
|
||||
class TestJobModelSerialization:
|
||||
"""Tests for Job model serialization to/from API."""
|
||||
@@ -119,3 +138,145 @@ class TestJobModelSerialization:
|
||||
assert job.url is None
|
||||
assert job.file_urls == {}
|
||||
|
||||
|
||||
class TestRetryEndpoint:
|
||||
"""Tests for the retry job endpoint."""
|
||||
|
||||
@pytest.fixture
|
||||
def mock_job_manager(self):
|
||||
"""Create mock job manager."""
|
||||
return MagicMock()
|
||||
|
||||
@pytest.fixture
|
||||
def mock_worker_service(self):
|
||||
"""Create mock worker service."""
|
||||
return MagicMock()
|
||||
|
||||
def test_retry_rejects_pending_job(self, mock_job_manager):
|
||||
"""Test retry endpoint rejects jobs that are not failed or cancelled."""
|
||||
# Create a pending job
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test",
|
||||
title="Song"
|
||||
)
|
||||
mock_job_manager.get_job.return_value = job
|
||||
|
||||
# The endpoint should reject this with a 400 error
|
||||
# (status check happens before any logic)
|
||||
assert job.status not in [JobStatus.FAILED, JobStatus.CANCELLED]
|
||||
|
||||
def test_retry_accepts_failed_job(self, mock_job_manager):
|
||||
"""Test retry endpoint accepts failed jobs."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.FAILED,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test",
|
||||
title="Song",
|
||||
input_media_gcs_path="jobs/test123/input/audio.flac"
|
||||
)
|
||||
mock_job_manager.get_job.return_value = job
|
||||
|
||||
# Status should be accepted
|
||||
assert job.status in [JobStatus.FAILED, JobStatus.CANCELLED]
|
||||
|
||||
def test_retry_accepts_cancelled_job(self, mock_job_manager):
|
||||
"""Test retry endpoint accepts cancelled jobs."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.CANCELLED,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test",
|
||||
title="Song",
|
||||
input_media_gcs_path="jobs/test123/input/audio.flac"
|
||||
)
|
||||
mock_job_manager.get_job.return_value = job
|
||||
|
||||
# Status should be accepted
|
||||
assert job.status in [JobStatus.FAILED, JobStatus.CANCELLED]
|
||||
|
||||
def test_retry_checkpoint_detection_video_generation(self):
|
||||
"""Test retry detects video generation checkpoint."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.FAILED,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test",
|
||||
title="Song",
|
||||
file_urls={
|
||||
'videos': {'with_vocals': 'gs://bucket/path/video.mkv'}
|
||||
},
|
||||
state_data={
|
||||
'instrumental_selection': 'clean'
|
||||
}
|
||||
)
|
||||
|
||||
# This job has video and instrumental selection - should retry from video generation
|
||||
has_video = job.file_urls.get('videos', {}).get('with_vocals')
|
||||
has_instrumental_selection = (job.state_data or {}).get('instrumental_selection')
|
||||
assert has_video and has_instrumental_selection
|
||||
|
||||
def test_retry_checkpoint_detection_render_stage(self):
|
||||
"""Test retry detects render stage checkpoint."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.FAILED,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test",
|
||||
title="Song",
|
||||
file_urls={
|
||||
'lyrics': {'corrections': 'gs://bucket/path/corrections.json'},
|
||||
'screens': {'title': 'gs://bucket/path/title.mov'}
|
||||
}
|
||||
)
|
||||
|
||||
# This job has corrections and screens - should retry from render
|
||||
has_corrections = job.file_urls.get('lyrics', {}).get('corrections')
|
||||
has_screens = job.file_urls.get('screens', {}).get('title')
|
||||
has_video = job.file_urls.get('videos', {}).get('with_vocals')
|
||||
assert has_corrections and has_screens and not has_video
|
||||
|
||||
def test_retry_checkpoint_detection_from_beginning(self):
|
||||
"""Test retry detects need to restart from beginning."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.CANCELLED,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test",
|
||||
title="Song",
|
||||
input_media_gcs_path="jobs/test123/input/audio.flac",
|
||||
file_urls={} # No progress yet
|
||||
)
|
||||
|
||||
# This job has input audio but no other files - should restart from beginning
|
||||
has_input = job.input_media_gcs_path
|
||||
has_stems = job.file_urls.get('stems', {}).get('instrumental_clean')
|
||||
has_corrections = job.file_urls.get('lyrics', {}).get('corrections')
|
||||
assert has_input and not has_stems and not has_corrections
|
||||
|
||||
def test_retry_no_input_audio(self):
|
||||
"""Test retry fails when no input audio available."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.CANCELLED,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test",
|
||||
title="Song",
|
||||
# No input_media_gcs_path and no url
|
||||
file_urls={}
|
||||
)
|
||||
|
||||
# This job has no input audio - should not be retryable
|
||||
has_input = job.input_media_gcs_path or job.url
|
||||
assert not has_input
|
||||
|
||||
@@ -12,6 +12,7 @@ from datetime import datetime, UTC
|
||||
import sys
|
||||
sys.modules['google.cloud.firestore'] = MagicMock()
|
||||
sys.modules['google.cloud.storage'] = MagicMock()
|
||||
sys.modules['google.cloud.tasks_v2'] = MagicMock()
|
||||
|
||||
from backend.services.auth_service import AuthService, UserType
|
||||
from backend.services.storage_service import StorageService
|
||||
@@ -239,6 +240,190 @@ class TestWorkerService:
|
||||
assert "/api/internal/workers/video" in str(call_args)
|
||||
|
||||
|
||||
class TestWorkerServiceCloudTasks:
|
||||
"""Test WorkerService Cloud Tasks integration."""
|
||||
|
||||
def test_should_use_cloud_tasks_default_false(self):
|
||||
"""Test that Cloud Tasks is disabled by default."""
|
||||
from backend.services.worker_service import WorkerService, reset_worker_service
|
||||
reset_worker_service()
|
||||
|
||||
with patch('backend.services.worker_service.os.getenv') as mock_getenv:
|
||||
mock_getenv.side_effect = lambda k, d=None: {
|
||||
'PORT': '8000',
|
||||
}.get(k, d)
|
||||
|
||||
with patch('backend.services.worker_service.get_settings') as mock_settings:
|
||||
mock_settings.return_value.admin_tokens = None
|
||||
mock_settings.return_value.google_cloud_project = "test-project"
|
||||
mock_settings.return_value.enable_cloud_tasks = False
|
||||
mock_settings.return_value.gcp_region = "us-central1"
|
||||
mock_settings.return_value.use_cloud_run_jobs_for_video = False
|
||||
|
||||
service = WorkerService()
|
||||
assert service._use_cloud_tasks is False
|
||||
|
||||
def test_should_use_cloud_tasks_enabled(self):
|
||||
"""Test that Cloud Tasks can be enabled via settings."""
|
||||
from backend.services.worker_service import WorkerService, reset_worker_service
|
||||
reset_worker_service()
|
||||
|
||||
with patch('backend.services.worker_service.os.getenv') as mock_getenv:
|
||||
mock_getenv.side_effect = lambda k, d=None: {
|
||||
'PORT': '8000',
|
||||
}.get(k, d)
|
||||
|
||||
with patch('backend.services.worker_service.get_settings') as mock_settings:
|
||||
mock_settings.return_value.admin_tokens = None
|
||||
mock_settings.return_value.google_cloud_project = "test-project"
|
||||
mock_settings.return_value.enable_cloud_tasks = True
|
||||
mock_settings.return_value.gcp_region = "us-central1"
|
||||
mock_settings.return_value.use_cloud_run_jobs_for_video = False
|
||||
|
||||
service = WorkerService()
|
||||
assert service._use_cloud_tasks is True
|
||||
|
||||
def test_worker_queues_mapping(self):
|
||||
"""Test that all worker types have queue mappings."""
|
||||
from backend.services.worker_service import WORKER_QUEUES
|
||||
|
||||
# Verify all expected workers have queues
|
||||
assert "audio" in WORKER_QUEUES
|
||||
assert "lyrics" in WORKER_QUEUES
|
||||
assert "screens" in WORKER_QUEUES
|
||||
assert "render-video" in WORKER_QUEUES
|
||||
assert "video" in WORKER_QUEUES
|
||||
|
||||
# Verify queue names are correct
|
||||
assert WORKER_QUEUES["audio"] == "audio-worker-queue"
|
||||
assert WORKER_QUEUES["lyrics"] == "lyrics-worker-queue"
|
||||
assert WORKER_QUEUES["screens"] == "screens-worker-queue"
|
||||
assert WORKER_QUEUES["render-video"] == "render-worker-queue"
|
||||
assert WORKER_QUEUES["video"] == "video-worker-queue"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_trigger_worker_uses_http_when_cloud_tasks_disabled(self):
|
||||
"""Test that trigger_worker uses HTTP when Cloud Tasks is disabled."""
|
||||
from backend.services.worker_service import WorkerService, reset_worker_service
|
||||
reset_worker_service()
|
||||
|
||||
with patch('backend.services.worker_service.os.getenv') as mock_getenv:
|
||||
mock_getenv.side_effect = lambda k, d=None: {
|
||||
'PORT': '8000',
|
||||
}.get(k, d)
|
||||
|
||||
with patch('backend.services.worker_service.get_settings') as mock_settings:
|
||||
mock_settings.return_value.admin_tokens = "test-token"
|
||||
mock_settings.return_value.google_cloud_project = "test-project"
|
||||
mock_settings.return_value.enable_cloud_tasks = False
|
||||
mock_settings.return_value.gcp_region = "us-central1"
|
||||
mock_settings.return_value.use_cloud_run_jobs_for_video = False
|
||||
|
||||
with patch('backend.services.worker_service.httpx.AsyncClient') as mock_client_cls:
|
||||
mock_client = AsyncMock()
|
||||
mock_client_cls.return_value.__aenter__.return_value = mock_client
|
||||
|
||||
mock_response = Mock()
|
||||
mock_response.status_code = 200
|
||||
mock_client.post.return_value = mock_response
|
||||
|
||||
service = WorkerService()
|
||||
assert service._use_cloud_tasks is False
|
||||
|
||||
result = await service.trigger_worker("audio", "test-job-123")
|
||||
|
||||
# Verify HTTP was used
|
||||
assert result is True
|
||||
mock_client.post.assert_called_once()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_trigger_worker_uses_cloud_tasks_when_enabled(self):
|
||||
"""Test that trigger_worker uses Cloud Tasks when enabled."""
|
||||
from backend.services.worker_service import WorkerService, reset_worker_service
|
||||
reset_worker_service()
|
||||
|
||||
with patch('backend.services.worker_service.os.getenv') as mock_getenv:
|
||||
mock_getenv.side_effect = lambda k, d=None: {
|
||||
'CLOUD_RUN_SERVICE_URL': 'https://api.example.com',
|
||||
}.get(k, d)
|
||||
|
||||
with patch('backend.services.worker_service.get_settings') as mock_settings:
|
||||
mock_settings.return_value.admin_tokens = "test-token"
|
||||
mock_settings.return_value.google_cloud_project = "test-project"
|
||||
mock_settings.return_value.enable_cloud_tasks = True
|
||||
mock_settings.return_value.gcp_region = "us-central1"
|
||||
mock_settings.return_value.use_cloud_run_jobs_for_video = False
|
||||
|
||||
# Mock Cloud Tasks client
|
||||
mock_tasks_client = MagicMock()
|
||||
mock_tasks_client.queue_path.return_value = "projects/test-project/locations/us-central1/queues/audio-worker-queue"
|
||||
mock_task_response = MagicMock()
|
||||
mock_task_response.name = "projects/test-project/locations/us-central1/queues/audio-worker-queue/tasks/abc123"
|
||||
mock_tasks_client.create_task.return_value = mock_task_response
|
||||
|
||||
# Mock the google.cloud.tasks_v2 module which is imported inside the method
|
||||
mock_tasks_module = MagicMock()
|
||||
mock_tasks_module.CloudTasksClient.return_value = mock_tasks_client
|
||||
mock_tasks_module.HttpMethod.POST = "POST"
|
||||
|
||||
with patch.dict('sys.modules', {'google.cloud.tasks_v2': mock_tasks_module}):
|
||||
with patch.dict(sys.modules, {'google.cloud': MagicMock()}):
|
||||
service = WorkerService()
|
||||
service._tasks_client = mock_tasks_client # Inject mocked client
|
||||
|
||||
result = await service.trigger_worker("audio", "test-job-123")
|
||||
|
||||
# Verify Cloud Tasks was used
|
||||
assert result is True
|
||||
mock_tasks_client.create_task.assert_called_once()
|
||||
|
||||
# Verify task payload
|
||||
call_args = mock_tasks_client.create_task.call_args
|
||||
assert call_args is not None
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_trigger_worker_returns_false_for_unknown_worker_type(self):
|
||||
"""Test that trigger_worker returns False for unknown worker types."""
|
||||
from backend.services.worker_service import WorkerService, reset_worker_service
|
||||
reset_worker_service()
|
||||
|
||||
with patch('backend.services.worker_service.os.getenv') as mock_getenv:
|
||||
mock_getenv.side_effect = lambda k, d=None: {
|
||||
'CLOUD_RUN_SERVICE_URL': 'https://api.example.com',
|
||||
}.get(k, d)
|
||||
|
||||
with patch('backend.services.worker_service.get_settings') as mock_settings:
|
||||
mock_settings.return_value.admin_tokens = "test-token"
|
||||
mock_settings.return_value.google_cloud_project = "test-project"
|
||||
mock_settings.return_value.enable_cloud_tasks = True
|
||||
mock_settings.return_value.gcp_region = "us-central1"
|
||||
mock_settings.return_value.use_cloud_run_jobs_for_video = False
|
||||
|
||||
service = WorkerService()
|
||||
|
||||
result = await service.trigger_worker("unknown-worker", "test-job-123")
|
||||
|
||||
assert result is False
|
||||
|
||||
def test_reset_worker_service(self):
|
||||
"""Test that reset_worker_service resets the singleton."""
|
||||
from backend.services.worker_service import get_worker_service, reset_worker_service
|
||||
|
||||
with patch('backend.services.worker_service.get_settings') as mock_settings:
|
||||
mock_settings.return_value.admin_tokens = None
|
||||
mock_settings.return_value.google_cloud_project = "test-project"
|
||||
mock_settings.return_value.enable_cloud_tasks = False
|
||||
mock_settings.return_value.gcp_region = "us-central1"
|
||||
mock_settings.return_value.use_cloud_run_jobs_for_video = False
|
||||
|
||||
service1 = get_worker_service()
|
||||
reset_worker_service()
|
||||
service2 = get_worker_service()
|
||||
|
||||
# After reset, should be different instances
|
||||
assert service1 is not service2
|
||||
|
||||
|
||||
class TestFirestoreService:
|
||||
"""Test FirestoreService database operations."""
|
||||
|
||||
|
||||
@@ -0,0 +1,448 @@
|
||||
"""
|
||||
Tests for storage_service.py - Google Cloud Storage operations.
|
||||
|
||||
These tests mock the GCS client to verify:
|
||||
- Upload operations (file, fileobj, JSON)
|
||||
- Download operations (file, JSON)
|
||||
- Signed URL generation
|
||||
- File operations (delete, list, exists)
|
||||
"""
|
||||
import json
|
||||
import pytest
|
||||
from unittest.mock import Mock, MagicMock, patch
|
||||
from io import BytesIO
|
||||
|
||||
from backend.services.storage_service import StorageService
|
||||
|
||||
|
||||
class TestStorageServiceInit:
|
||||
"""Test StorageService initialization."""
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_init_creates_client_and_bucket(self, mock_settings, mock_client_class):
|
||||
"""Test initialization creates GCS client and gets bucket."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_client = Mock()
|
||||
mock_bucket = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
service = StorageService()
|
||||
|
||||
mock_client_class.assert_called_once_with(project="test-project")
|
||||
mock_client.bucket.assert_called_once_with("test-bucket")
|
||||
assert service.client == mock_client
|
||||
assert service.bucket == mock_bucket
|
||||
|
||||
|
||||
class TestStorageServiceUpload:
|
||||
"""Test upload operations."""
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_upload_file(self, mock_settings, mock_client_class):
|
||||
"""Test uploading a file to GCS."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob = Mock()
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.blob.return_value = mock_blob
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
service = StorageService()
|
||||
result = service.upload_file("/local/path/file.flac", "uploads/job123/file.flac")
|
||||
|
||||
mock_bucket.blob.assert_called_once_with("uploads/job123/file.flac")
|
||||
mock_blob.upload_from_filename.assert_called_once_with("/local/path/file.flac")
|
||||
assert result == "uploads/job123/file.flac"
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_upload_file_raises_on_error(self, mock_settings, mock_client_class):
|
||||
"""Test upload_file raises exception on GCS error."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob = Mock()
|
||||
mock_blob.upload_from_filename.side_effect = Exception("GCS error")
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.blob.return_value = mock_blob
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
service = StorageService()
|
||||
|
||||
with pytest.raises(Exception) as exc_info:
|
||||
service.upload_file("/local/path/file.flac", "dest/file.flac")
|
||||
|
||||
assert "GCS error" in str(exc_info.value)
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_upload_fileobj(self, mock_settings, mock_client_class):
|
||||
"""Test uploading a file object to GCS."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob = Mock()
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.blob.return_value = mock_blob
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
service = StorageService()
|
||||
file_obj = BytesIO(b"test content")
|
||||
|
||||
result = service.upload_fileobj(file_obj, "uploads/test.txt", content_type="text/plain")
|
||||
|
||||
mock_bucket.blob.assert_called_once_with("uploads/test.txt")
|
||||
assert mock_blob.content_type == "text/plain"
|
||||
mock_blob.upload_from_file.assert_called_once_with(file_obj, rewind=True)
|
||||
assert result == "uploads/test.txt"
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_upload_json(self, mock_settings, mock_client_class):
|
||||
"""Test uploading JSON data to GCS."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob = Mock()
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.blob.return_value = mock_blob
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
service = StorageService()
|
||||
data = {"key": "value", "nested": {"data": True}}
|
||||
|
||||
result = service.upload_json("data/config.json", data)
|
||||
|
||||
mock_bucket.blob.assert_called_once_with("data/config.json")
|
||||
assert mock_blob.content_type == "application/json"
|
||||
# Check the uploaded content
|
||||
call_args = mock_blob.upload_from_string.call_args
|
||||
uploaded_content = call_args[0][0]
|
||||
assert json.loads(uploaded_content) == data
|
||||
assert result == "data/config.json"
|
||||
|
||||
|
||||
class TestStorageServiceDownload:
|
||||
"""Test download operations."""
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_download_file(self, mock_settings, mock_client_class):
|
||||
"""Test downloading a file from GCS."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob = Mock()
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.blob.return_value = mock_blob
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
service = StorageService()
|
||||
result = service.download_file("uploads/job123/file.flac", "/local/path/file.flac")
|
||||
|
||||
mock_bucket.blob.assert_called_once_with("uploads/job123/file.flac")
|
||||
mock_blob.download_to_filename.assert_called_once_with("/local/path/file.flac")
|
||||
assert result == "/local/path/file.flac"
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_download_file_raises_on_error(self, mock_settings, mock_client_class):
|
||||
"""Test download_file raises exception on GCS error."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob = Mock()
|
||||
mock_blob.download_to_filename.side_effect = Exception("File not found")
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.blob.return_value = mock_blob
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
service = StorageService()
|
||||
|
||||
with pytest.raises(Exception) as exc_info:
|
||||
service.download_file("missing/file.flac", "/local/path")
|
||||
|
||||
assert "File not found" in str(exc_info.value)
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_download_json(self, mock_settings, mock_client_class):
|
||||
"""Test downloading and parsing JSON from GCS."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob = Mock()
|
||||
mock_blob.download_as_text.return_value = '{"key": "value", "count": 42}'
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.blob.return_value = mock_blob
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
service = StorageService()
|
||||
result = service.download_json("data/config.json")
|
||||
|
||||
assert result == {"key": "value", "count": 42}
|
||||
|
||||
|
||||
class TestStorageServiceDelete:
|
||||
"""Test delete operations."""
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_delete_file(self, mock_settings, mock_client_class):
|
||||
"""Test deleting a single file from GCS."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob = Mock()
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.blob.return_value = mock_blob
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
service = StorageService()
|
||||
service.delete_file("uploads/job123/file.flac")
|
||||
|
||||
mock_bucket.blob.assert_called_once_with("uploads/job123/file.flac")
|
||||
mock_blob.delete.assert_called_once()
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_delete_folder(self, mock_settings, mock_client_class):
|
||||
"""Test deleting all files with a prefix (folder)."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
# Create mock blobs
|
||||
mock_blob1 = Mock()
|
||||
mock_blob1.name = "uploads/job123/file1.flac"
|
||||
mock_blob2 = Mock()
|
||||
mock_blob2.name = "uploads/job123/file2.flac"
|
||||
mock_blob3 = Mock()
|
||||
mock_blob3.name = "uploads/job123/subdir/file3.flac"
|
||||
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.list_blobs.return_value = [mock_blob1, mock_blob2, mock_blob3]
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
service = StorageService()
|
||||
count = service.delete_folder("uploads/job123/")
|
||||
|
||||
mock_bucket.list_blobs.assert_called_once_with(prefix="uploads/job123/")
|
||||
mock_blob1.delete.assert_called_once()
|
||||
mock_blob2.delete.assert_called_once()
|
||||
mock_blob3.delete.assert_called_once()
|
||||
assert count == 3
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_delete_folder_handles_errors_gracefully(self, mock_settings, mock_client_class):
|
||||
"""Test delete_folder continues even if some deletes fail."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob1 = Mock()
|
||||
mock_blob1.name = "file1.flac"
|
||||
mock_blob2 = Mock()
|
||||
mock_blob2.name = "file2.flac"
|
||||
mock_blob2.delete.side_effect = Exception("Permission denied")
|
||||
mock_blob3 = Mock()
|
||||
mock_blob3.name = "file3.flac"
|
||||
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.list_blobs.return_value = [mock_blob1, mock_blob2, mock_blob3]
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
service = StorageService()
|
||||
count = service.delete_folder("uploads/")
|
||||
|
||||
# Should have deleted 2 files (blob2 failed)
|
||||
assert count == 2
|
||||
|
||||
|
||||
class TestStorageServiceFileOperations:
|
||||
"""Test file listing and existence checks."""
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_list_files(self, mock_settings, mock_client_class):
|
||||
"""Test listing files with a prefix."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob1 = Mock()
|
||||
mock_blob1.name = "uploads/job123/audio.flac"
|
||||
mock_blob2 = Mock()
|
||||
mock_blob2.name = "uploads/job123/lyrics.txt"
|
||||
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.list_blobs.return_value = [mock_blob1, mock_blob2]
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
service = StorageService()
|
||||
files = service.list_files("uploads/job123/")
|
||||
|
||||
assert files == ["uploads/job123/audio.flac", "uploads/job123/lyrics.txt"]
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_file_exists_returns_true(self, mock_settings, mock_client_class):
|
||||
"""Test file_exists returns True for existing file."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob = Mock()
|
||||
mock_blob.exists.return_value = True
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.blob.return_value = mock_blob
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
service = StorageService()
|
||||
result = service.file_exists("uploads/job123/file.flac")
|
||||
|
||||
assert result is True
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_file_exists_returns_false(self, mock_settings, mock_client_class):
|
||||
"""Test file_exists returns False for missing file."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob = Mock()
|
||||
mock_blob.exists.return_value = False
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.blob.return_value = mock_blob
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
service = StorageService()
|
||||
result = service.file_exists("missing/file.flac")
|
||||
|
||||
assert result is False
|
||||
|
||||
|
||||
class TestStorageServiceSignedUrls:
|
||||
"""Test signed URL generation."""
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_generate_signed_url(self, mock_settings, mock_client_class):
|
||||
"""Test generating a signed download URL."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob = Mock()
|
||||
mock_blob.generate_signed_url.return_value = "https://storage.googleapis.com/signed-url"
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.blob.return_value = mock_blob
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
# Mock google.auth.default to return credentials without service_account_email
|
||||
with patch("google.auth.default") as mock_auth_default:
|
||||
mock_credentials = Mock(spec=[]) # No service_account_email attr
|
||||
mock_auth_default.return_value = (mock_credentials, "test-project")
|
||||
|
||||
service = StorageService()
|
||||
url = service.generate_signed_url("uploads/file.flac", expiration_minutes=30)
|
||||
|
||||
assert url == "https://storage.googleapis.com/signed-url"
|
||||
mock_blob.generate_signed_url.assert_called_once()
|
||||
call_kwargs = mock_blob.generate_signed_url.call_args.kwargs
|
||||
assert call_kwargs["method"] == "GET"
|
||||
assert call_kwargs["version"] == "v4"
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_generate_signed_upload_url(self, mock_settings, mock_client_class):
|
||||
"""Test generating a signed upload URL."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob = Mock()
|
||||
mock_blob.generate_signed_url.return_value = "https://storage.googleapis.com/signed-upload-url"
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.blob.return_value = mock_blob
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
with patch("google.auth.default") as mock_auth_default:
|
||||
mock_credentials = Mock(spec=[])
|
||||
mock_auth_default.return_value = (mock_credentials, "test-project")
|
||||
|
||||
service = StorageService()
|
||||
url = service.generate_signed_upload_url(
|
||||
"uploads/file.flac",
|
||||
content_type="audio/flac",
|
||||
expiration_minutes=15
|
||||
)
|
||||
|
||||
assert url == "https://storage.googleapis.com/signed-upload-url"
|
||||
call_kwargs = mock_blob.generate_signed_url.call_args.kwargs
|
||||
assert call_kwargs["method"] == "PUT"
|
||||
assert call_kwargs["headers"] == {"Content-Type": "audio/flac"}
|
||||
|
||||
@patch("backend.services.storage_service.storage.Client")
|
||||
@patch("backend.services.storage_service.settings")
|
||||
def test_signed_url_with_service_account(self, mock_settings, mock_client_class):
|
||||
"""Test signed URL generation with service account credentials."""
|
||||
mock_settings.google_cloud_project = "test-project"
|
||||
mock_settings.gcs_bucket_name = "test-bucket"
|
||||
|
||||
mock_blob = Mock()
|
||||
mock_blob.generate_signed_url.return_value = "https://storage.googleapis.com/signed-url"
|
||||
mock_bucket = Mock()
|
||||
mock_bucket.blob.return_value = mock_blob
|
||||
mock_client = Mock()
|
||||
mock_client.bucket.return_value = mock_bucket
|
||||
mock_client_class.return_value = mock_client
|
||||
|
||||
with patch("google.auth.default") as mock_auth_default:
|
||||
with patch("google.auth.transport.requests.Request") as mock_request:
|
||||
# Mock credentials with service_account_email
|
||||
mock_credentials = Mock()
|
||||
mock_credentials.service_account_email = "sa@project.iam.gserviceaccount.com"
|
||||
mock_credentials.token = "access-token-123"
|
||||
mock_auth_default.return_value = (mock_credentials, "test-project")
|
||||
|
||||
service = StorageService()
|
||||
url = service.generate_signed_url("uploads/file.flac")
|
||||
|
||||
# Should have refreshed credentials and used IAM signing
|
||||
mock_credentials.refresh.assert_called_once()
|
||||
call_kwargs = mock_blob.generate_signed_url.call_args.kwargs
|
||||
assert call_kwargs["service_account_email"] == "sa@project.iam.gserviceaccount.com"
|
||||
assert call_kwargs["access_token"] == "access-token-123"
|
||||
|
||||
@@ -16,12 +16,20 @@ from unittest.mock import Mock, MagicMock, patch, AsyncMock
|
||||
from io import BytesIO
|
||||
|
||||
# Test the remote CLI's style parsing
|
||||
# Skip this class if flacfetch is not properly installed (remote_cli depends on it)
|
||||
try:
|
||||
from karaoke_gen.utils.remote_cli import RemoteKaraokeClient, Config
|
||||
_remote_cli_available = True
|
||||
except ImportError:
|
||||
_remote_cli_available = False
|
||||
|
||||
|
||||
@pytest.mark.skipif(not _remote_cli_available, reason="flacfetch not properly installed")
|
||||
class TestRemoteCLIStyleParsing:
|
||||
"""Test that remote CLI correctly parses style_params.json."""
|
||||
|
||||
def test_parse_style_params_extracts_file_paths(self):
|
||||
"""Test that _parse_style_params extracts all file references."""
|
||||
from karaoke_gen.utils.remote_cli import RemoteKaraokeClient, Config
|
||||
|
||||
# Create a mock style_params.json
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
@@ -79,7 +87,6 @@ class TestRemoteCLIStyleParsing:
|
||||
|
||||
def test_parse_style_params_handles_missing_files(self):
|
||||
"""Test that _parse_style_params ignores non-existent files."""
|
||||
from karaoke_gen.utils.remote_cli import RemoteKaraokeClient, Config
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
style_params = {
|
||||
|
||||
@@ -0,0 +1,516 @@
|
||||
"""
|
||||
Tests for the theme service and API endpoints.
|
||||
|
||||
Tests theme listing, retrieval, color override application, and job style preparation.
|
||||
"""
|
||||
import json
|
||||
import pytest
|
||||
from unittest.mock import MagicMock, patch, Mock
|
||||
from datetime import datetime
|
||||
|
||||
from backend.models.theme import (
|
||||
ThemeSummary,
|
||||
ThemeDetail,
|
||||
ThemeMetadata,
|
||||
ThemeRegistry,
|
||||
ColorOverrides,
|
||||
hex_to_rgba,
|
||||
rgba_to_hex,
|
||||
)
|
||||
from backend.services.theme_service import ThemeService, get_theme_service
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# Color Conversion Tests
|
||||
# =============================================================================
|
||||
|
||||
class TestColorConversion:
|
||||
"""Tests for hex/rgba color conversion utilities."""
|
||||
|
||||
def test_hex_to_rgba_basic(self):
|
||||
"""Test basic hex to RGBA conversion."""
|
||||
result = hex_to_rgba("#7070F7")
|
||||
assert result == "112, 112, 247, 255"
|
||||
|
||||
def test_hex_to_rgba_with_custom_alpha(self):
|
||||
"""Test hex to RGBA with custom alpha."""
|
||||
result = hex_to_rgba("#FF0000", alpha=128)
|
||||
assert result == "255, 0, 0, 128"
|
||||
|
||||
def test_hex_to_rgba_lowercase(self):
|
||||
"""Test hex with lowercase letters."""
|
||||
result = hex_to_rgba("#abcdef")
|
||||
assert result == "171, 205, 239, 255"
|
||||
|
||||
def test_hex_to_rgba_without_hash(self):
|
||||
"""Test hex without leading hash."""
|
||||
result = hex_to_rgba("FFFFFF")
|
||||
assert result == "255, 255, 255, 255"
|
||||
|
||||
def test_rgba_to_hex_basic(self):
|
||||
"""Test basic RGBA to hex conversion."""
|
||||
result = rgba_to_hex("112, 112, 247, 255")
|
||||
assert result == "#7070f7"
|
||||
|
||||
def test_rgba_to_hex_ignores_alpha(self):
|
||||
"""Test that alpha is ignored in conversion."""
|
||||
result = rgba_to_hex("255, 0, 0, 128")
|
||||
assert result == "#ff0000"
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# ColorOverrides Model Tests
|
||||
# =============================================================================
|
||||
|
||||
class TestColorOverrides:
|
||||
"""Tests for ColorOverrides model."""
|
||||
|
||||
def test_has_overrides_empty(self):
|
||||
"""Test has_overrides with no overrides set."""
|
||||
overrides = ColorOverrides()
|
||||
assert overrides.has_overrides() is False
|
||||
|
||||
def test_has_overrides_with_artist_color(self):
|
||||
"""Test has_overrides with artist_color set."""
|
||||
overrides = ColorOverrides(artist_color="#FF0000")
|
||||
assert overrides.has_overrides() is True
|
||||
|
||||
def test_has_overrides_with_all_colors(self):
|
||||
"""Test has_overrides with all colors set."""
|
||||
overrides = ColorOverrides(
|
||||
artist_color="#FF0000",
|
||||
title_color="#00FF00",
|
||||
sung_lyrics_color="#0000FF",
|
||||
unsung_lyrics_color="#FFFF00",
|
||||
)
|
||||
assert overrides.has_overrides() is True
|
||||
|
||||
def test_to_dict_excludes_none(self):
|
||||
"""Test to_dict excludes None values."""
|
||||
overrides = ColorOverrides(artist_color="#FF0000")
|
||||
result = overrides.to_dict()
|
||||
assert result == {"artist_color": "#FF0000"}
|
||||
assert "title_color" not in result
|
||||
|
||||
def test_color_validation_valid(self):
|
||||
"""Test color validation accepts valid hex colors."""
|
||||
overrides = ColorOverrides(artist_color="#AbCdEf")
|
||||
assert overrides.artist_color == "#AbCdEf"
|
||||
|
||||
def test_color_validation_invalid(self):
|
||||
"""Test color validation rejects invalid colors."""
|
||||
with pytest.raises(ValueError):
|
||||
ColorOverrides(artist_color="red")
|
||||
|
||||
with pytest.raises(ValueError):
|
||||
ColorOverrides(artist_color="#GGG")
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# ThemeService Tests
|
||||
# =============================================================================
|
||||
|
||||
class TestThemeService:
|
||||
"""Tests for ThemeService."""
|
||||
|
||||
@pytest.fixture
|
||||
def mock_storage(self):
|
||||
"""Create a mock storage service."""
|
||||
storage = MagicMock()
|
||||
return storage
|
||||
|
||||
@pytest.fixture
|
||||
def sample_metadata(self):
|
||||
"""Sample theme metadata for testing."""
|
||||
return {
|
||||
"version": 1,
|
||||
"themes": [
|
||||
{
|
||||
"id": "nomad",
|
||||
"name": "Nomad Karaoke",
|
||||
"description": "Golden artist text, professional look",
|
||||
"is_default": True,
|
||||
},
|
||||
{
|
||||
"id": "default",
|
||||
"name": "Default",
|
||||
"description": "Clean white text on black background",
|
||||
"is_default": False,
|
||||
},
|
||||
],
|
||||
}
|
||||
|
||||
@pytest.fixture
|
||||
def sample_style_params(self):
|
||||
"""Sample style params for testing."""
|
||||
return {
|
||||
"intro": {
|
||||
"artist_color": "#ffdf6b",
|
||||
"title_color": "#ffffff",
|
||||
"background_image": "intro_bg.png",
|
||||
"font": "Montserrat-Bold.ttf",
|
||||
},
|
||||
"end": {
|
||||
"artist_color": "#ffdf6b",
|
||||
"title_color": "#ffffff",
|
||||
"background_image": "end_bg.png",
|
||||
"font": "Montserrat-Bold.ttf",
|
||||
},
|
||||
"karaoke": {
|
||||
"primary_color": "112, 112, 247, 255",
|
||||
"secondary_color": "255, 255, 255, 255",
|
||||
"background_image": "karaoke_bg.png",
|
||||
"font_path": "Montserrat-Bold.ttf",
|
||||
},
|
||||
"cdg": {
|
||||
"active_fill": "#7070F7",
|
||||
"inactive_fill": "#FFFFFF",
|
||||
"font_path": "Montserrat-Bold.ttf",
|
||||
},
|
||||
}
|
||||
|
||||
def test_list_themes_returns_summaries(self, mock_storage, sample_metadata):
|
||||
"""Test list_themes returns ThemeSummary objects."""
|
||||
mock_storage.download_json.return_value = sample_metadata
|
||||
mock_storage.file_exists.return_value = True
|
||||
mock_storage.generate_signed_url.return_value = "https://signed-url.com/preview.png"
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
themes = service.list_themes()
|
||||
|
||||
assert len(themes) == 2
|
||||
assert themes[0].id == "nomad"
|
||||
assert themes[0].name == "Nomad Karaoke"
|
||||
assert themes[0].is_default is True
|
||||
assert themes[0].preview_url is not None
|
||||
|
||||
def test_list_themes_handles_missing_preview(self, mock_storage, sample_metadata):
|
||||
"""Test list_themes handles missing preview images gracefully."""
|
||||
mock_storage.download_json.return_value = sample_metadata
|
||||
mock_storage.file_exists.return_value = False
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
themes = service.list_themes()
|
||||
|
||||
assert len(themes) == 2
|
||||
assert themes[0].preview_url is None
|
||||
|
||||
def test_get_theme_returns_detail(self, mock_storage, sample_metadata, sample_style_params):
|
||||
"""Test get_theme returns ThemeDetail with style params."""
|
||||
mock_storage.download_json.side_effect = [sample_metadata, sample_style_params]
|
||||
mock_storage.file_exists.return_value = True
|
||||
mock_storage.generate_signed_url.return_value = "https://signed-url.com/preview.png"
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
theme = service.get_theme("nomad")
|
||||
|
||||
assert theme is not None
|
||||
assert theme.id == "nomad"
|
||||
assert theme.name == "Nomad Karaoke"
|
||||
assert "intro" in theme.style_params
|
||||
assert theme.style_params["intro"]["artist_color"] == "#ffdf6b"
|
||||
|
||||
def test_get_theme_returns_none_for_unknown(self, mock_storage, sample_metadata):
|
||||
"""Test get_theme returns None for unknown theme ID."""
|
||||
mock_storage.download_json.return_value = sample_metadata
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
theme = service.get_theme("unknown-theme")
|
||||
|
||||
assert theme is None
|
||||
|
||||
def test_theme_exists_true(self, mock_storage, sample_metadata):
|
||||
"""Test theme_exists returns True for existing theme."""
|
||||
mock_storage.download_json.return_value = sample_metadata
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
assert service.theme_exists("nomad") is True
|
||||
|
||||
def test_theme_exists_false(self, mock_storage, sample_metadata):
|
||||
"""Test theme_exists returns False for unknown theme."""
|
||||
mock_storage.download_json.return_value = sample_metadata
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
assert service.theme_exists("unknown") is False
|
||||
|
||||
def test_get_default_theme_id(self, mock_storage, sample_metadata):
|
||||
"""Test get_default_theme_id returns the default theme."""
|
||||
mock_storage.download_json.return_value = sample_metadata
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
assert service.get_default_theme_id() == "nomad"
|
||||
|
||||
def test_get_default_theme_id_no_default(self, mock_storage):
|
||||
"""Test get_default_theme_id returns None when no default."""
|
||||
mock_storage.download_json.return_value = {
|
||||
"version": 1,
|
||||
"themes": [{"id": "test", "name": "Test", "description": "Test", "is_default": False}],
|
||||
}
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
assert service.get_default_theme_id() is None
|
||||
|
||||
def test_apply_color_overrides_no_changes(self, sample_style_params):
|
||||
"""Test apply_color_overrides with empty overrides."""
|
||||
service = ThemeService()
|
||||
overrides = ColorOverrides()
|
||||
|
||||
result = service.apply_color_overrides(sample_style_params, overrides)
|
||||
|
||||
# Should return original (no deep copy needed when no changes)
|
||||
assert result == sample_style_params
|
||||
|
||||
def test_apply_color_overrides_artist_color(self, sample_style_params):
|
||||
"""Test apply_color_overrides applies artist_color."""
|
||||
service = ThemeService()
|
||||
overrides = ColorOverrides(artist_color="#FF0000")
|
||||
|
||||
result = service.apply_color_overrides(sample_style_params, overrides)
|
||||
|
||||
assert result["intro"]["artist_color"] == "#FF0000"
|
||||
assert result["end"]["artist_color"] == "#FF0000"
|
||||
assert result["cdg"]["artist_color"] == "#FF0000"
|
||||
# Original should be unchanged
|
||||
assert sample_style_params["intro"]["artist_color"] == "#ffdf6b"
|
||||
|
||||
def test_apply_color_overrides_sung_lyrics_color(self, sample_style_params):
|
||||
"""Test apply_color_overrides applies sung_lyrics_color with conversion."""
|
||||
service = ThemeService()
|
||||
overrides = ColorOverrides(sung_lyrics_color="#FF0000")
|
||||
|
||||
result = service.apply_color_overrides(sample_style_params, overrides)
|
||||
|
||||
# Karaoke uses RGBA format
|
||||
assert result["karaoke"]["primary_color"] == "255, 0, 0, 255"
|
||||
# CDG uses hex
|
||||
assert result["cdg"]["active_fill"] == "#FF0000"
|
||||
|
||||
def test_apply_color_overrides_unsung_lyrics_color(self, sample_style_params):
|
||||
"""Test apply_color_overrides applies unsung_lyrics_color."""
|
||||
service = ThemeService()
|
||||
overrides = ColorOverrides(unsung_lyrics_color="#00FF00")
|
||||
|
||||
result = service.apply_color_overrides(sample_style_params, overrides)
|
||||
|
||||
assert result["karaoke"]["secondary_color"] == "0, 255, 0, 255"
|
||||
assert result["cdg"]["inactive_fill"] == "#00FF00"
|
||||
|
||||
def test_metadata_cache(self, mock_storage, sample_metadata):
|
||||
"""Test metadata caching works."""
|
||||
mock_storage.download_json.return_value = sample_metadata
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
|
||||
# First call loads from GCS
|
||||
service.list_themes()
|
||||
assert mock_storage.download_json.call_count == 1
|
||||
|
||||
# Second call uses cache
|
||||
service.list_themes()
|
||||
assert mock_storage.download_json.call_count == 1
|
||||
|
||||
def test_invalidate_cache(self, mock_storage, sample_metadata):
|
||||
"""Test cache invalidation."""
|
||||
mock_storage.download_json.return_value = sample_metadata
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
|
||||
# Load metadata
|
||||
service.list_themes()
|
||||
assert mock_storage.download_json.call_count == 1
|
||||
|
||||
# Invalidate cache
|
||||
service.invalidate_cache()
|
||||
|
||||
# Next call should reload
|
||||
service.list_themes()
|
||||
assert mock_storage.download_json.call_count == 2
|
||||
|
||||
def test_prepare_job_style(self, mock_storage, sample_metadata, sample_style_params):
|
||||
"""Test prepare_job_style creates job style from theme."""
|
||||
mock_storage.download_json.side_effect = [sample_metadata, sample_style_params]
|
||||
mock_storage.file_exists.return_value = True
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
style_path, style_assets = service.prepare_job_style("job123", "nomad")
|
||||
|
||||
# Should upload modified style_params.json
|
||||
mock_storage.upload_json.assert_called_once()
|
||||
assert style_path == "uploads/job123/style/style_params.json"
|
||||
|
||||
def test_prepare_job_style_with_overrides(self, mock_storage, sample_metadata, sample_style_params):
|
||||
"""Test prepare_job_style applies color overrides."""
|
||||
# prepare_job_style calls get_theme_style_params which directly downloads style_params.json
|
||||
# No metadata lookup happens unless we've cached it previously
|
||||
mock_storage.download_json.return_value = sample_style_params
|
||||
mock_storage.file_exists.return_value = True
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
overrides = ColorOverrides(artist_color="#FF0000")
|
||||
|
||||
style_path, style_assets = service.prepare_job_style("job123", "nomad", overrides)
|
||||
|
||||
# Check that upload_json was called with modified style params
|
||||
call_args = mock_storage.upload_json.call_args
|
||||
uploaded_path = call_args[0][0] # First positional arg is the path
|
||||
uploaded_style = call_args[0][1] # Second positional arg is the data
|
||||
|
||||
assert uploaded_path == "uploads/job123/style/style_params.json"
|
||||
# Check that artist_color override was applied
|
||||
assert uploaded_style["intro"]["artist_color"] == "#FF0000"
|
||||
assert uploaded_style["end"]["artist_color"] == "#FF0000"
|
||||
|
||||
def test_prepare_job_style_unknown_theme_raises(self, mock_storage, sample_metadata):
|
||||
"""Test prepare_job_style raises for unknown theme."""
|
||||
# First download_json returns metadata (no unknown theme)
|
||||
# Second download_json for style_params.json should fail
|
||||
def download_json_side_effect(path):
|
||||
if "_metadata.json" in path:
|
||||
return sample_metadata
|
||||
# Unknown theme path - raise exception
|
||||
raise Exception(f"File not found: {path}")
|
||||
|
||||
mock_storage.download_json.side_effect = download_json_side_effect
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
|
||||
with pytest.raises(ValueError, match="Theme not found"):
|
||||
service.prepare_job_style("job123", "unknown-theme")
|
||||
|
||||
def test_get_youtube_description(self, mock_storage, sample_metadata):
|
||||
"""Test get_youtube_description returns template text."""
|
||||
mock_storage.download_json.return_value = sample_metadata
|
||||
mock_storage.file_exists.return_value = True
|
||||
|
||||
# Mock the download_file to write content to temp file
|
||||
def mock_download(gcs_path, local_path):
|
||||
with open(local_path, "w") as f:
|
||||
f.write("Thank you for watching!")
|
||||
|
||||
mock_storage.download_file.side_effect = mock_download
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
desc = service.get_youtube_description("nomad")
|
||||
|
||||
assert desc == "Thank you for watching!"
|
||||
|
||||
def test_get_youtube_description_not_found(self, mock_storage, sample_metadata):
|
||||
"""Test get_youtube_description returns None when no template."""
|
||||
mock_storage.download_json.return_value = sample_metadata
|
||||
mock_storage.file_exists.return_value = False
|
||||
|
||||
service = ThemeService(storage=mock_storage)
|
||||
desc = service.get_youtube_description("nomad")
|
||||
|
||||
assert desc is None
|
||||
|
||||
|
||||
# =============================================================================
|
||||
# API Endpoint Tests
|
||||
# =============================================================================
|
||||
|
||||
class TestThemeAPI:
|
||||
"""Tests for theme API endpoints."""
|
||||
|
||||
@pytest.fixture
|
||||
def sample_metadata(self):
|
||||
"""Sample theme metadata."""
|
||||
return {
|
||||
"version": 1,
|
||||
"themes": [
|
||||
{
|
||||
"id": "nomad",
|
||||
"name": "Nomad Karaoke",
|
||||
"description": "Golden artist text",
|
||||
"is_default": True,
|
||||
}
|
||||
],
|
||||
}
|
||||
|
||||
def test_list_themes_endpoint(self, test_client, sample_metadata):
|
||||
"""Test GET /api/themes returns theme list."""
|
||||
with patch("backend.api.routes.themes.get_theme_service") as mock_get_service:
|
||||
mock_service = MagicMock()
|
||||
mock_service.list_themes.return_value = [
|
||||
ThemeSummary(
|
||||
id="nomad",
|
||||
name="Nomad Karaoke",
|
||||
description="Golden artist text",
|
||||
preview_url="https://example.com/preview.png",
|
||||
is_default=True,
|
||||
)
|
||||
]
|
||||
mock_get_service.return_value = mock_service
|
||||
|
||||
response = test_client.get("/api/themes")
|
||||
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
assert len(data["themes"]) == 1
|
||||
assert data["themes"][0]["id"] == "nomad"
|
||||
assert data["themes"][0]["is_default"] is True
|
||||
|
||||
def test_get_theme_endpoint(self, test_client):
|
||||
"""Test GET /api/themes/{theme_id} returns theme detail."""
|
||||
with patch("backend.api.routes.themes.get_theme_service") as mock_get_service:
|
||||
mock_service = MagicMock()
|
||||
mock_service.get_theme.return_value = ThemeDetail(
|
||||
id="nomad",
|
||||
name="Nomad Karaoke",
|
||||
description="Golden artist text",
|
||||
is_default=True,
|
||||
style_params={"intro": {"artist_color": "#ffdf6b"}},
|
||||
)
|
||||
mock_get_service.return_value = mock_service
|
||||
|
||||
response = test_client.get("/api/themes/nomad")
|
||||
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
assert data["theme"]["id"] == "nomad"
|
||||
assert "style_params" in data["theme"]
|
||||
|
||||
def test_get_theme_not_found(self, test_client):
|
||||
"""Test GET /api/themes/{theme_id} returns 404 for unknown theme."""
|
||||
with patch("backend.api.routes.themes.get_theme_service") as mock_get_service:
|
||||
mock_service = MagicMock()
|
||||
mock_service.get_theme.return_value = None
|
||||
mock_get_service.return_value = mock_service
|
||||
|
||||
response = test_client.get("/api/themes/unknown")
|
||||
|
||||
assert response.status_code == 404
|
||||
|
||||
def test_get_theme_preview_endpoint(self, test_client):
|
||||
"""Test GET /api/themes/{theme_id}/preview returns preview URL."""
|
||||
with patch("backend.api.routes.themes.get_theme_service") as mock_get_service:
|
||||
mock_service = MagicMock()
|
||||
mock_service.theme_exists.return_value = True
|
||||
mock_service.get_theme.return_value = ThemeDetail(
|
||||
id="nomad",
|
||||
name="Nomad Karaoke",
|
||||
description="Golden artist text",
|
||||
preview_url="https://example.com/preview.png",
|
||||
is_default=True,
|
||||
)
|
||||
mock_get_service.return_value = mock_service
|
||||
|
||||
response = test_client.get("/api/themes/nomad/preview")
|
||||
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
assert "preview_url" in data
|
||||
|
||||
def test_get_youtube_description_endpoint(self, test_client):
|
||||
"""Test GET /api/themes/{theme_id}/youtube-description returns description."""
|
||||
with patch("backend.api.routes.themes.get_theme_service") as mock_get_service:
|
||||
mock_service = MagicMock()
|
||||
mock_service.theme_exists.return_value = True
|
||||
mock_service.get_youtube_description.return_value = "Thank you for watching!"
|
||||
mock_get_service.return_value = mock_service
|
||||
|
||||
response = test_client.get("/api/themes/nomad/youtube-description")
|
||||
|
||||
assert response.status_code == 200
|
||||
data = response.json()
|
||||
assert data["description"] == "Thank you for watching!"
|
||||
@@ -10,6 +10,14 @@ from io import BytesIO
|
||||
from backend.models.job import Job, JobStatus
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def upload_auth_headers():
|
||||
"""Auth headers for file upload tests (no Content-Type, let multipart work)."""
|
||||
return {
|
||||
"Authorization": "Bearer test-admin-token"
|
||||
}
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_job():
|
||||
"""Create a standard mock job."""
|
||||
@@ -65,37 +73,41 @@ def client(mock_services):
|
||||
class TestFileUploadEndpoint:
|
||||
"""Tests for POST /api/jobs/upload."""
|
||||
|
||||
def test_upload_flac_returns_200(self, client, mock_services):
|
||||
def test_upload_flac_returns_200(self, client, mock_services, upload_auth_headers):
|
||||
"""Test uploading FLAC file returns 200."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("test.flac", BytesIO(b"fake audio"), "audio/flac")},
|
||||
data={"artist": "Test Artist", "title": "Test Song"}
|
||||
)
|
||||
assert response.status_code == 200
|
||||
|
||||
def test_upload_mp3_returns_200(self, client, mock_services):
|
||||
def test_upload_mp3_returns_200(self, client, mock_services, upload_auth_headers):
|
||||
"""Test uploading MP3 file returns 200."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("test.mp3", BytesIO(b"fake audio"), "audio/mpeg")},
|
||||
data={"artist": "Test Artist", "title": "Test Song"}
|
||||
)
|
||||
assert response.status_code == 200
|
||||
|
||||
def test_upload_wav_returns_200(self, client, mock_services):
|
||||
def test_upload_wav_returns_200(self, client, mock_services, upload_auth_headers):
|
||||
"""Test uploading WAV file returns 200."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("test.wav", BytesIO(b"fake audio"), "audio/wav")},
|
||||
data={"artist": "Test Artist", "title": "Test Song"}
|
||||
)
|
||||
assert response.status_code == 200
|
||||
|
||||
def test_upload_returns_job_id(self, client, mock_services):
|
||||
def test_upload_returns_job_id(self, client, mock_services, upload_auth_headers):
|
||||
"""Test upload response contains job_id."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("test.flac", BytesIO(b"fake audio"), "audio/flac")},
|
||||
data={"artist": "Test", "title": "Song"}
|
||||
)
|
||||
@@ -103,10 +115,11 @@ class TestFileUploadEndpoint:
|
||||
assert "job_id" in data
|
||||
assert data["status"] == "success"
|
||||
|
||||
def test_upload_returns_filename(self, client, mock_services):
|
||||
def test_upload_returns_filename(self, client, mock_services, upload_auth_headers):
|
||||
"""Test upload response contains original filename."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("my_song.flac", BytesIO(b"fake audio"), "audio/flac")},
|
||||
data={"artist": "Test", "title": "Song"}
|
||||
)
|
||||
@@ -114,84 +127,93 @@ class TestFileUploadEndpoint:
|
||||
assert "filename" in data
|
||||
assert data["filename"] == "my_song.flac"
|
||||
|
||||
def test_upload_rejects_txt_file(self, client, mock_services):
|
||||
def test_upload_rejects_txt_file(self, client, mock_services, upload_auth_headers):
|
||||
"""Test upload rejects text files."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("test.txt", BytesIO(b"not audio"), "text/plain")},
|
||||
data={"artist": "Test", "title": "Song"}
|
||||
)
|
||||
assert response.status_code == 400
|
||||
|
||||
def test_upload_rejects_pdf_file(self, client, mock_services):
|
||||
def test_upload_rejects_pdf_file(self, client, mock_services, upload_auth_headers):
|
||||
"""Test upload rejects PDF files."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("doc.pdf", BytesIO(b"pdf content"), "application/pdf")},
|
||||
data={"artist": "Test", "title": "Song"}
|
||||
)
|
||||
assert response.status_code == 400
|
||||
|
||||
def test_upload_rejects_exe_file(self, client, mock_services):
|
||||
def test_upload_rejects_exe_file(self, client, mock_services, upload_auth_headers):
|
||||
"""Test upload rejects executable files."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("app.exe", BytesIO(b"exe content"), "application/octet-stream")},
|
||||
data={"artist": "Test", "title": "Song"}
|
||||
)
|
||||
assert response.status_code == 400
|
||||
|
||||
def test_upload_requires_artist(self, client, mock_services):
|
||||
def test_upload_requires_artist(self, client, mock_services, upload_auth_headers):
|
||||
"""Test upload requires artist field."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("test.flac", BytesIO(b"audio"), "audio/flac")},
|
||||
data={"title": "Song"} # Missing artist
|
||||
)
|
||||
assert response.status_code == 422
|
||||
|
||||
def test_upload_requires_title(self, client, mock_services):
|
||||
def test_upload_requires_title(self, client, mock_services, upload_auth_headers):
|
||||
"""Test upload requires title field."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("test.flac", BytesIO(b"audio"), "audio/flac")},
|
||||
data={"artist": "Artist"} # Missing title
|
||||
)
|
||||
assert response.status_code == 422
|
||||
|
||||
def test_upload_requires_file(self, client, mock_services):
|
||||
def test_upload_requires_file(self, client, mock_services, upload_auth_headers):
|
||||
"""Test upload requires file."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
data={"artist": "Artist", "title": "Song"}
|
||||
# Missing file
|
||||
)
|
||||
assert response.status_code == 422
|
||||
|
||||
def test_upload_triggers_workers(self, client, mock_services):
|
||||
def test_upload_triggers_workers(self, client, mock_services, upload_auth_headers):
|
||||
"""Test upload triggers audio and lyrics workers."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("test.flac", BytesIO(b"audio"), "audio/flac")},
|
||||
data={"artist": "Test", "title": "Song"}
|
||||
)
|
||||
assert response.status_code == 200
|
||||
# Workers should be triggered in background
|
||||
|
||||
def test_upload_creates_job(self, client, mock_services):
|
||||
def test_upload_creates_job(self, client, mock_services, upload_auth_headers):
|
||||
"""Test upload creates job in job manager."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("test.flac", BytesIO(b"audio"), "audio/flac")},
|
||||
data={"artist": "Test", "title": "Song"}
|
||||
)
|
||||
assert response.status_code == 200
|
||||
mock_services['job_manager'].create_job.assert_called()
|
||||
|
||||
def test_upload_stores_file_to_gcs(self, client, mock_services):
|
||||
def test_upload_stores_file_to_gcs(self, client, mock_services, upload_auth_headers):
|
||||
"""Test upload stores file to GCS."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("test.flac", BytesIO(b"audio"), "audio/flac")},
|
||||
data={"artist": "Test", "title": "Song"}
|
||||
)
|
||||
@@ -202,28 +224,31 @@ class TestFileUploadEndpoint:
|
||||
class TestUploadValidation:
|
||||
"""Tests for upload validation logic."""
|
||||
|
||||
def test_upload_accepts_m4a(self, client, mock_services):
|
||||
def test_upload_accepts_m4a(self, client, mock_services, upload_auth_headers):
|
||||
"""Test upload accepts M4A files."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("test.m4a", BytesIO(b"audio"), "audio/mp4")},
|
||||
data={"artist": "Test", "title": "Song"}
|
||||
)
|
||||
assert response.status_code == 200
|
||||
|
||||
def test_upload_accepts_ogg(self, client, mock_services):
|
||||
def test_upload_accepts_ogg(self, client, mock_services, upload_auth_headers):
|
||||
"""Test upload accepts OGG files."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("test.ogg", BytesIO(b"audio"), "audio/ogg")},
|
||||
data={"artist": "Test", "title": "Song"}
|
||||
)
|
||||
assert response.status_code == 200
|
||||
|
||||
def test_upload_accepts_aac(self, client, mock_services):
|
||||
def test_upload_accepts_aac(self, client, mock_services, upload_auth_headers):
|
||||
"""Test upload accepts AAC files."""
|
||||
response = client.post(
|
||||
"/api/jobs/upload",
|
||||
headers=upload_auth_headers,
|
||||
files={"file": ("test.aac", BytesIO(b"audio"), "audio/aac")},
|
||||
data={"artist": "Test", "title": "Song"}
|
||||
)
|
||||
|
||||
@@ -0,0 +1,156 @@
|
||||
"""
|
||||
Unit tests for backend validation script (validate.py).
|
||||
|
||||
Tests the validation functions that check for import errors, syntax errors,
|
||||
configuration issues, and FastAPI app creation.
|
||||
"""
|
||||
import pytest
|
||||
from unittest.mock import patch, MagicMock
|
||||
|
||||
|
||||
class TestValidateImports:
|
||||
"""Tests for the validate_imports function."""
|
||||
|
||||
def test_validate_imports_success(self):
|
||||
"""Test that validate_imports succeeds when all modules import."""
|
||||
from backend.validate import validate_imports
|
||||
|
||||
# This should succeed since we're in a valid test environment
|
||||
result = validate_imports()
|
||||
assert result is True
|
||||
|
||||
def test_validate_imports_with_failure(self):
|
||||
"""Test that validate_imports handles import failures."""
|
||||
from backend.validate import validate_imports
|
||||
|
||||
# Mock importlib to simulate a failure
|
||||
with patch('backend.validate.importlib.import_module') as mock_import:
|
||||
mock_import.side_effect = ImportError("Module not found")
|
||||
|
||||
result = validate_imports()
|
||||
assert result is False
|
||||
|
||||
|
||||
class TestValidateSyntax:
|
||||
"""Tests for the validate_syntax function."""
|
||||
|
||||
def test_validate_syntax_success(self):
|
||||
"""Test that validate_syntax succeeds with valid Python files."""
|
||||
from backend.validate import validate_syntax
|
||||
|
||||
# This should succeed since the backend code is valid
|
||||
result = validate_syntax()
|
||||
assert result is True
|
||||
|
||||
def test_validate_syntax_handles_invalid_file(self):
|
||||
"""Test that validate_syntax detects syntax errors."""
|
||||
import tempfile
|
||||
import os
|
||||
from pathlib import Path
|
||||
from backend.validate import validate_syntax
|
||||
|
||||
# We can't easily inject invalid files into the backend dir,
|
||||
# but we can verify the function runs and returns True for valid files
|
||||
result = validate_syntax()
|
||||
assert result is True
|
||||
|
||||
|
||||
class TestValidateConfig:
|
||||
"""Tests for the validate_config function."""
|
||||
|
||||
def test_validate_config_success(self):
|
||||
"""Test that validate_config succeeds with valid configuration."""
|
||||
from backend.validate import validate_config
|
||||
|
||||
# This should succeed in test environment
|
||||
result = validate_config()
|
||||
assert result is True
|
||||
|
||||
def test_validate_config_failure(self):
|
||||
"""Test that validate_config handles configuration errors."""
|
||||
from backend.validate import validate_config
|
||||
|
||||
# Patch at the source module
|
||||
with patch('backend.config.get_settings') as mock_settings:
|
||||
mock_settings.side_effect = Exception("Config error")
|
||||
|
||||
result = validate_config()
|
||||
assert result is False
|
||||
|
||||
|
||||
class TestValidateFastapiApp:
|
||||
"""Tests for the validate_fastapi_app function."""
|
||||
|
||||
def test_validate_fastapi_app_success(self):
|
||||
"""Test that validate_fastapi_app succeeds."""
|
||||
from backend.validate import validate_fastapi_app
|
||||
|
||||
# This should succeed since the FastAPI app is valid
|
||||
result = validate_fastapi_app()
|
||||
assert result is True
|
||||
|
||||
def test_validate_fastapi_app_failure(self):
|
||||
"""Test that validate_fastapi_app handles app creation errors."""
|
||||
from backend.validate import validate_fastapi_app
|
||||
|
||||
with patch.dict('sys.modules', {'backend.main': MagicMock(app=MagicMock(title="Test", version="1.0", routes=[]))}):
|
||||
# Even with a mock, the function should work
|
||||
result = validate_fastapi_app()
|
||||
# The original module is still accessible, so this should still pass
|
||||
assert result is True
|
||||
|
||||
|
||||
class TestMain:
|
||||
"""Tests for the main function."""
|
||||
|
||||
def test_main_runs(self):
|
||||
"""Test that main runs without errors."""
|
||||
from backend.validate import main
|
||||
|
||||
# In a valid test environment, main should return 0 (success)
|
||||
result = main()
|
||||
assert result == 0
|
||||
|
||||
def test_main_returns_1_on_failure(self):
|
||||
"""Test that main returns 1 when validations fail."""
|
||||
from backend.validate import main
|
||||
|
||||
# Mock one validation to fail
|
||||
with patch('backend.validate.validate_imports', return_value=False):
|
||||
result = main()
|
||||
assert result == 1
|
||||
|
||||
|
||||
class TestValidateModule:
|
||||
"""Test the validate module can be imported and has expected functions."""
|
||||
|
||||
def test_module_imports(self):
|
||||
"""Test that the validate module can be imported."""
|
||||
import backend.validate
|
||||
assert backend.validate is not None
|
||||
|
||||
def test_has_validate_imports(self):
|
||||
"""Test that validate_imports function exists."""
|
||||
from backend.validate import validate_imports
|
||||
assert callable(validate_imports)
|
||||
|
||||
def test_has_validate_syntax(self):
|
||||
"""Test that validate_syntax function exists."""
|
||||
from backend.validate import validate_syntax
|
||||
assert callable(validate_syntax)
|
||||
|
||||
def test_has_validate_config(self):
|
||||
"""Test that validate_config function exists."""
|
||||
from backend.validate import validate_config
|
||||
assert callable(validate_config)
|
||||
|
||||
def test_has_validate_fastapi_app(self):
|
||||
"""Test that validate_fastapi_app function exists."""
|
||||
from backend.validate import validate_fastapi_app
|
||||
assert callable(validate_fastapi_app)
|
||||
|
||||
def test_has_main(self):
|
||||
"""Test that main function exists."""
|
||||
from backend.validate import main
|
||||
assert callable(main)
|
||||
|
||||
@@ -0,0 +1,365 @@
|
||||
"""
|
||||
Unit tests for backend/workers/worker_logging.py.
|
||||
|
||||
Tests the job logging utilities including JobLogger, JobLogHandler,
|
||||
and job_logging_context for concurrent job isolation.
|
||||
"""
|
||||
import pytest
|
||||
import logging
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
|
||||
class TestJobLoggingContext:
|
||||
"""Tests for job_logging_context context manager."""
|
||||
|
||||
def test_job_logging_context_sets_and_resets_job_id(self):
|
||||
"""Test that job_logging_context sets and resets the current job ID."""
|
||||
from backend.workers.worker_logging import job_logging_context, _current_job_id
|
||||
|
||||
# Initially no job
|
||||
assert _current_job_id.get() is None
|
||||
|
||||
# Inside context, job is set
|
||||
with job_logging_context("job123"):
|
||||
assert _current_job_id.get() == "job123"
|
||||
|
||||
# After context, job is reset
|
||||
assert _current_job_id.get() is None
|
||||
|
||||
def test_job_logging_context_nested(self):
|
||||
"""Test nested job_logging_context calls."""
|
||||
from backend.workers.worker_logging import job_logging_context, _current_job_id
|
||||
|
||||
with job_logging_context("outer_job"):
|
||||
assert _current_job_id.get() == "outer_job"
|
||||
|
||||
with job_logging_context("inner_job"):
|
||||
assert _current_job_id.get() == "inner_job"
|
||||
|
||||
# After inner context, outer job is restored
|
||||
assert _current_job_id.get() == "outer_job"
|
||||
|
||||
assert _current_job_id.get() is None
|
||||
|
||||
def test_job_logging_context_handles_exception(self):
|
||||
"""Test that job_logging_context resets even on exception."""
|
||||
from backend.workers.worker_logging import job_logging_context, _current_job_id
|
||||
|
||||
try:
|
||||
with job_logging_context("job123"):
|
||||
assert _current_job_id.get() == "job123"
|
||||
raise ValueError("Test exception")
|
||||
except ValueError:
|
||||
pass
|
||||
|
||||
# Job should still be reset after exception
|
||||
assert _current_job_id.get() is None
|
||||
|
||||
|
||||
class TestJobLogHandler:
|
||||
"""Tests for JobLogHandler class."""
|
||||
|
||||
@pytest.fixture
|
||||
def mock_job_manager(self):
|
||||
"""Create a mock JobManager."""
|
||||
manager = MagicMock()
|
||||
manager.append_worker_log.return_value = None
|
||||
return manager
|
||||
|
||||
def test_job_log_handler_init(self, mock_job_manager):
|
||||
"""Test JobLogHandler initialization."""
|
||||
from backend.workers.worker_logging import JobLogHandler
|
||||
|
||||
handler = JobLogHandler(
|
||||
job_id="job123",
|
||||
worker_name="audio",
|
||||
job_manager=mock_job_manager
|
||||
)
|
||||
|
||||
assert handler.job_id == "job123"
|
||||
assert handler.worker_name == "audio"
|
||||
assert handler.job_manager == mock_job_manager
|
||||
assert handler.level == logging.INFO
|
||||
|
||||
def test_job_log_handler_custom_level(self, mock_job_manager):
|
||||
"""Test JobLogHandler with custom level."""
|
||||
from backend.workers.worker_logging import JobLogHandler
|
||||
|
||||
handler = JobLogHandler(
|
||||
job_id="job123",
|
||||
worker_name="audio",
|
||||
job_manager=mock_job_manager,
|
||||
level=logging.DEBUG
|
||||
)
|
||||
|
||||
assert handler.level == logging.DEBUG
|
||||
|
||||
def test_job_log_handler_emit_logs_to_firestore(self, mock_job_manager):
|
||||
"""Test that emit() calls job_manager.append_worker_log."""
|
||||
from backend.workers.worker_logging import JobLogHandler, job_logging_context
|
||||
|
||||
handler = JobLogHandler(
|
||||
job_id="job123",
|
||||
worker_name="audio",
|
||||
job_manager=mock_job_manager
|
||||
)
|
||||
handler.setFormatter(logging.Formatter('%(message)s'))
|
||||
|
||||
# Create a log record
|
||||
record = logging.LogRecord(
|
||||
name="test",
|
||||
level=logging.INFO,
|
||||
pathname="",
|
||||
lineno=0,
|
||||
msg="Test message",
|
||||
args=(),
|
||||
exc_info=None
|
||||
)
|
||||
|
||||
# Emit within the job context
|
||||
with job_logging_context("job123"):
|
||||
handler.emit(record)
|
||||
|
||||
# Should have called append_worker_log
|
||||
mock_job_manager.append_worker_log.assert_called()
|
||||
|
||||
def test_job_log_handler_filters_other_job_context(self, mock_job_manager):
|
||||
"""Test that handler filters logs from other job contexts."""
|
||||
from backend.workers.worker_logging import JobLogHandler, job_logging_context
|
||||
|
||||
handler = JobLogHandler(
|
||||
job_id="job123",
|
||||
worker_name="audio",
|
||||
job_manager=mock_job_manager
|
||||
)
|
||||
|
||||
record = logging.LogRecord(
|
||||
name="test",
|
||||
level=logging.INFO,
|
||||
pathname="",
|
||||
lineno=0,
|
||||
msg="Test message",
|
||||
args=(),
|
||||
exc_info=None
|
||||
)
|
||||
|
||||
# Emit from a different job's context
|
||||
with job_logging_context("different_job"):
|
||||
handler.emit(record)
|
||||
|
||||
# Should NOT have called append_worker_log
|
||||
mock_job_manager.append_worker_log.assert_not_called()
|
||||
|
||||
def test_job_log_handler_deduplication(self, mock_job_manager):
|
||||
"""Test that handler deduplicates repeated messages."""
|
||||
from backend.workers.worker_logging import JobLogHandler, job_logging_context
|
||||
|
||||
handler = JobLogHandler(
|
||||
job_id="job123",
|
||||
worker_name="audio",
|
||||
job_manager=mock_job_manager
|
||||
)
|
||||
handler.setFormatter(logging.Formatter('%(message)s'))
|
||||
|
||||
record = logging.LogRecord(
|
||||
name="test",
|
||||
level=logging.INFO,
|
||||
pathname="",
|
||||
lineno=0,
|
||||
msg="Duplicate message",
|
||||
args=(),
|
||||
exc_info=None
|
||||
)
|
||||
|
||||
with job_logging_context("job123"):
|
||||
# Emit the same record twice
|
||||
handler.emit(record)
|
||||
handler.emit(record)
|
||||
|
||||
# Should only be called once due to deduplication
|
||||
assert mock_job_manager.append_worker_log.call_count == 1
|
||||
|
||||
|
||||
class TestJobLogger:
|
||||
"""Tests for JobLogger class."""
|
||||
|
||||
@pytest.fixture
|
||||
def mock_job_manager(self):
|
||||
"""Create a mock JobManager."""
|
||||
manager = MagicMock()
|
||||
manager.append_worker_log.return_value = None
|
||||
return manager
|
||||
|
||||
def test_job_logger_init(self, mock_job_manager):
|
||||
"""Test JobLogger initialization."""
|
||||
from backend.workers.worker_logging import JobLogger
|
||||
|
||||
logger = JobLogger(
|
||||
job_id="job123",
|
||||
worker_name="lyrics",
|
||||
job_manager=mock_job_manager
|
||||
)
|
||||
|
||||
assert logger.job_id == "job123"
|
||||
assert logger.worker_name == "lyrics"
|
||||
assert logger.job_manager == mock_job_manager
|
||||
|
||||
def test_job_logger_info(self, mock_job_manager):
|
||||
"""Test JobLogger.info() method."""
|
||||
from backend.workers.worker_logging import JobLogger
|
||||
|
||||
logger = JobLogger(
|
||||
job_id="job123",
|
||||
worker_name="lyrics",
|
||||
job_manager=mock_job_manager
|
||||
)
|
||||
|
||||
logger.info("Processing started")
|
||||
|
||||
mock_job_manager.append_worker_log.assert_called_with(
|
||||
job_id="job123",
|
||||
worker="lyrics",
|
||||
level="INFO",
|
||||
message="Processing started"
|
||||
)
|
||||
|
||||
def test_job_logger_warning(self, mock_job_manager):
|
||||
"""Test JobLogger.warning() method."""
|
||||
from backend.workers.worker_logging import JobLogger
|
||||
|
||||
logger = JobLogger(
|
||||
job_id="job123",
|
||||
worker_name="audio",
|
||||
job_manager=mock_job_manager
|
||||
)
|
||||
|
||||
logger.warning("Low memory")
|
||||
|
||||
mock_job_manager.append_worker_log.assert_called_with(
|
||||
job_id="job123",
|
||||
worker="audio",
|
||||
level="WARNING",
|
||||
message="Low memory"
|
||||
)
|
||||
|
||||
def test_job_logger_error(self, mock_job_manager):
|
||||
"""Test JobLogger.error() method."""
|
||||
from backend.workers.worker_logging import JobLogger
|
||||
|
||||
logger = JobLogger(
|
||||
job_id="job123",
|
||||
worker_name="video",
|
||||
job_manager=mock_job_manager
|
||||
)
|
||||
|
||||
logger.error("Processing failed")
|
||||
|
||||
mock_job_manager.append_worker_log.assert_called_with(
|
||||
job_id="job123",
|
||||
worker="video",
|
||||
level="ERROR",
|
||||
message="Processing failed"
|
||||
)
|
||||
|
||||
def test_job_logger_debug(self, mock_job_manager):
|
||||
"""Test JobLogger.debug() method."""
|
||||
from backend.workers.worker_logging import JobLogger
|
||||
|
||||
logger = JobLogger(
|
||||
job_id="job123",
|
||||
worker_name="screens",
|
||||
job_manager=mock_job_manager
|
||||
)
|
||||
|
||||
logger.debug("Debug info")
|
||||
|
||||
mock_job_manager.append_worker_log.assert_called_with(
|
||||
job_id="job123",
|
||||
worker="screens",
|
||||
level="DEBUG",
|
||||
message="Debug info"
|
||||
)
|
||||
|
||||
def test_job_logger_with_format_args(self, mock_job_manager):
|
||||
"""Test JobLogger with format arguments."""
|
||||
from backend.workers.worker_logging import JobLogger
|
||||
|
||||
logger = JobLogger(
|
||||
job_id="job123",
|
||||
worker_name="audio",
|
||||
job_manager=mock_job_manager
|
||||
)
|
||||
|
||||
logger.info("Processing %s of %d", "audio", 10)
|
||||
|
||||
mock_job_manager.append_worker_log.assert_called_with(
|
||||
job_id="job123",
|
||||
worker="audio",
|
||||
level="INFO",
|
||||
message="Processing audio of 10"
|
||||
)
|
||||
|
||||
def test_job_logger_handles_firestore_error(self, mock_job_manager):
|
||||
"""Test that JobLogger handles Firestore errors gracefully."""
|
||||
from backend.workers.worker_logging import JobLogger
|
||||
|
||||
mock_job_manager.append_worker_log.side_effect = Exception("Firestore error")
|
||||
|
||||
logger = JobLogger(
|
||||
job_id="job123",
|
||||
worker_name="audio",
|
||||
job_manager=mock_job_manager
|
||||
)
|
||||
|
||||
# Should not raise exception
|
||||
logger.info("Test message")
|
||||
|
||||
|
||||
class TestCreateJobLogger:
|
||||
"""Tests for create_job_logger function."""
|
||||
|
||||
def test_create_job_logger(self):
|
||||
"""Test create_job_logger creates a JobLogger."""
|
||||
from backend.workers.worker_logging import create_job_logger, JobLogger
|
||||
|
||||
# Patch at the source module where JobManager is imported
|
||||
with patch('backend.services.job_manager.JobManager'):
|
||||
logger = create_job_logger("job123", "audio")
|
||||
|
||||
assert isinstance(logger, JobLogger)
|
||||
assert logger.job_id == "job123"
|
||||
assert logger.worker_name == "audio"
|
||||
|
||||
|
||||
class TestSetupJobLogging:
|
||||
"""Tests for setup_job_logging function."""
|
||||
|
||||
def test_setup_job_logging_returns_handler(self):
|
||||
"""Test setup_job_logging returns a JobLogHandler."""
|
||||
from backend.workers.worker_logging import setup_job_logging, JobLogHandler
|
||||
|
||||
# Patch at the source module
|
||||
with patch('backend.services.job_manager.JobManager'):
|
||||
handler = setup_job_logging("job123", "lyrics", "test_logger_wl1")
|
||||
|
||||
assert isinstance(handler, JobLogHandler)
|
||||
assert handler.job_id == "job123"
|
||||
assert handler.worker_name == "lyrics"
|
||||
|
||||
# Clean up - remove the handler
|
||||
logging.getLogger("test_logger_wl1").removeHandler(handler)
|
||||
|
||||
def test_setup_job_logging_adds_handler_to_loggers(self):
|
||||
"""Test setup_job_logging adds handler to specified loggers."""
|
||||
from backend.workers.worker_logging import setup_job_logging
|
||||
|
||||
with patch('backend.services.job_manager.JobManager'):
|
||||
handler = setup_job_logging("job123", "audio", "test_logger_wl2", "test_logger_wl3")
|
||||
|
||||
# Check handlers are added
|
||||
assert handler in logging.getLogger("test_logger_wl2").handlers
|
||||
assert handler in logging.getLogger("test_logger_wl3").handlers
|
||||
|
||||
# Clean up
|
||||
logging.getLogger("test_logger_wl2").removeHandler(handler)
|
||||
logging.getLogger("test_logger_wl3").removeHandler(handler)
|
||||
@@ -353,6 +353,108 @@ class TestLyricsWorker:
|
||||
mock_job_manager.mark_job_failed.assert_called()
|
||||
|
||||
|
||||
class TestLyricsWorkerConfiguration:
|
||||
"""Tests for lyrics worker configuration parameters."""
|
||||
|
||||
def test_create_lyrics_processor_with_defaults(self):
|
||||
"""Test creating LyricsProcessor with default parameters."""
|
||||
with patch('backend.workers.lyrics_worker.LyricsProcessor') as mock_processor:
|
||||
from backend.workers.lyrics_worker import create_lyrics_processor
|
||||
|
||||
result = create_lyrics_processor()
|
||||
|
||||
mock_processor.assert_called_once()
|
||||
call_kwargs = mock_processor.call_args[1]
|
||||
assert call_kwargs['lyrics_file'] is None
|
||||
assert call_kwargs['subtitle_offset_ms'] == 0
|
||||
|
||||
def test_create_lyrics_processor_with_lyrics_file(self):
|
||||
"""Test creating LyricsProcessor with custom lyrics file."""
|
||||
with patch('backend.workers.lyrics_worker.LyricsProcessor') as mock_processor:
|
||||
from backend.workers.lyrics_worker import create_lyrics_processor
|
||||
|
||||
result = create_lyrics_processor(
|
||||
lyrics_file="/path/to/lyrics.txt",
|
||||
subtitle_offset_ms=0
|
||||
)
|
||||
|
||||
mock_processor.assert_called_once()
|
||||
call_kwargs = mock_processor.call_args[1]
|
||||
assert call_kwargs['lyrics_file'] == "/path/to/lyrics.txt"
|
||||
|
||||
def test_create_lyrics_processor_with_subtitle_offset(self):
|
||||
"""Test creating LyricsProcessor with subtitle offset."""
|
||||
with patch('backend.workers.lyrics_worker.LyricsProcessor') as mock_processor:
|
||||
from backend.workers.lyrics_worker import create_lyrics_processor
|
||||
|
||||
result = create_lyrics_processor(
|
||||
subtitle_offset_ms=500
|
||||
)
|
||||
|
||||
mock_processor.assert_called_once()
|
||||
call_kwargs = mock_processor.call_args[1]
|
||||
assert call_kwargs['subtitle_offset_ms'] == 500
|
||||
|
||||
|
||||
class TestLyricsOverrideParameters:
|
||||
"""Tests for lyrics artist/title override functionality."""
|
||||
|
||||
@pytest.fixture
|
||||
def mock_job_with_overrides(self):
|
||||
"""Create a mock job with lyrics override fields."""
|
||||
return Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Beatles, The",
|
||||
title="Hey Jude - 2009 Remaster",
|
||||
lyrics_artist="The Beatles",
|
||||
lyrics_title="Hey Jude",
|
||||
subtitle_offset_ms=250,
|
||||
input_media_gcs_path="uploads/test123/song.flac"
|
||||
)
|
||||
|
||||
def test_job_uses_lyrics_artist_override(self, mock_job_with_overrides):
|
||||
"""Test that job uses lyrics_artist when searching for lyrics."""
|
||||
job = mock_job_with_overrides
|
||||
|
||||
# Use override if present, else fall back to main artist
|
||||
lyrics_search_artist = job.lyrics_artist or job.artist
|
||||
|
||||
assert lyrics_search_artist == "The Beatles"
|
||||
assert lyrics_search_artist != job.artist # Override is different
|
||||
|
||||
def test_job_uses_lyrics_title_override(self, mock_job_with_overrides):
|
||||
"""Test that job uses lyrics_title when searching for lyrics."""
|
||||
job = mock_job_with_overrides
|
||||
|
||||
# Use override if present, else fall back to main title
|
||||
lyrics_search_title = job.lyrics_title or job.title
|
||||
|
||||
assert lyrics_search_title == "Hey Jude"
|
||||
assert lyrics_search_title != job.title # Override is different
|
||||
|
||||
def test_job_falls_back_when_no_override(self):
|
||||
"""Test that job falls back to main artist/title when no override."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test Artist",
|
||||
title="Test Song",
|
||||
input_media_gcs_path="uploads/test123/song.flac"
|
||||
)
|
||||
|
||||
# When override is None, use main values
|
||||
lyrics_search_artist = job.lyrics_artist or job.artist
|
||||
lyrics_search_title = job.lyrics_title or job.title
|
||||
|
||||
assert lyrics_search_artist == "Test Artist"
|
||||
assert lyrics_search_title == "Test Song"
|
||||
|
||||
|
||||
class TestScreensWorker:
|
||||
"""Tests for screens_worker.py functions.
|
||||
|
||||
@@ -379,6 +481,101 @@ class TestVideoWorker:
|
||||
assert hasattr(video_worker, 'logger')
|
||||
|
||||
|
||||
class TestRenderVideoWorkerConfiguration:
|
||||
"""Tests for render_video_worker subtitle_offset_ms support."""
|
||||
|
||||
@pytest.fixture
|
||||
def mock_job_with_offset(self):
|
||||
"""Create a mock job with subtitle offset."""
|
||||
return Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.RENDERING_VIDEO,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test Artist",
|
||||
title="Test Song",
|
||||
subtitle_offset_ms=500,
|
||||
input_media_gcs_path="uploads/test123/song.flac"
|
||||
)
|
||||
|
||||
def test_job_has_subtitle_offset_ms(self, mock_job_with_offset):
|
||||
"""Test that job has subtitle_offset_ms field."""
|
||||
assert mock_job_with_offset.subtitle_offset_ms == 500
|
||||
|
||||
def test_subtitle_offset_from_job(self, mock_job_with_offset):
|
||||
"""Test extracting subtitle offset from job with getattr."""
|
||||
job = mock_job_with_offset
|
||||
|
||||
# This mirrors the logic in render_video_worker.py
|
||||
subtitle_offset = getattr(job, 'subtitle_offset_ms', 0) or 0
|
||||
|
||||
assert subtitle_offset == 500
|
||||
|
||||
def test_subtitle_offset_default_zero(self):
|
||||
"""Test that subtitle offset defaults to 0 when not set."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.RENDERING_VIDEO,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test Artist",
|
||||
title="Test Song",
|
||||
input_media_gcs_path="uploads/test123/song.flac"
|
||||
)
|
||||
|
||||
subtitle_offset = getattr(job, 'subtitle_offset_ms', 0) or 0
|
||||
|
||||
assert subtitle_offset == 0
|
||||
|
||||
def test_subtitle_offset_negative_value(self):
|
||||
"""Test that subtitle offset can be negative (advance subtitles)."""
|
||||
job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.RENDERING_VIDEO,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test Artist",
|
||||
title="Test Song",
|
||||
subtitle_offset_ms=-250, # Negative = advance subtitles
|
||||
input_media_gcs_path="uploads/test123/song.flac"
|
||||
)
|
||||
|
||||
subtitle_offset = getattr(job, 'subtitle_offset_ms', 0) or 0
|
||||
|
||||
# Negative values should be preserved (not converted to 0)
|
||||
assert subtitle_offset == -250
|
||||
|
||||
|
||||
class TestRenderVideoWorkerCountdownPadding:
|
||||
"""Tests for render_video_worker countdown detection and audio padding.
|
||||
|
||||
This ensures that when corrections with countdown timestamps are loaded,
|
||||
the audio is padded to match. This prevents video desynchronization.
|
||||
"""
|
||||
|
||||
def test_countdown_processor_import(self):
|
||||
"""Test that render_video_worker imports CountdownProcessor."""
|
||||
from backend.workers.render_video_worker import CountdownProcessor
|
||||
assert CountdownProcessor is not None
|
||||
|
||||
def test_countdown_processor_has_process_method(self):
|
||||
"""Test that CountdownProcessor has the process method (main API)."""
|
||||
from lyrics_transcriber.output.countdown_processor import CountdownProcessor
|
||||
|
||||
countdown_processor = CountdownProcessor(cache_dir="/tmp")
|
||||
assert hasattr(countdown_processor, 'process')
|
||||
assert callable(countdown_processor.process)
|
||||
|
||||
def test_countdown_processor_constants(self):
|
||||
"""Test that CountdownProcessor has expected constants."""
|
||||
from lyrics_transcriber.output.countdown_processor import CountdownProcessor
|
||||
|
||||
# Verify the constants exist (these control countdown behavior)
|
||||
assert hasattr(CountdownProcessor, 'COUNTDOWN_TEXT')
|
||||
assert hasattr(CountdownProcessor, 'COUNTDOWN_PADDING_SECONDS')
|
||||
assert hasattr(CountdownProcessor, 'COUNTDOWN_THRESHOLD_SECONDS')
|
||||
|
||||
|
||||
class TestDownloadHelpers:
|
||||
"""Tests for download helper functions in workers."""
|
||||
|
||||
@@ -406,3 +603,377 @@ class TestDownloadHelpers:
|
||||
# Should have downloaded from GCS
|
||||
mock_storage.download_file.assert_called()
|
||||
|
||||
|
||||
class TestAudioWorkerModelConfiguration:
|
||||
"""Tests for audio worker model configuration parameters."""
|
||||
|
||||
def test_create_audio_processor_with_defaults(self):
|
||||
"""Test creating AudioProcessor with default models."""
|
||||
with patch('backend.workers.audio_worker.AudioProcessor') as mock_processor:
|
||||
from backend.workers.audio_worker import create_audio_processor
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
result = create_audio_processor(temp_dir)
|
||||
|
||||
mock_processor.assert_called_once()
|
||||
call_kwargs = mock_processor.call_args[1]
|
||||
|
||||
# Should use default models
|
||||
assert call_kwargs['clean_instrumental_model'] == "model_bs_roformer_ep_317_sdr_12.9755.ckpt"
|
||||
assert call_kwargs['backing_vocals_models'] == ["mel_band_roformer_karaoke_aufr33_viperx_sdr_10.1956.ckpt"]
|
||||
assert call_kwargs['other_stems_models'] == ["htdemucs_6s.yaml"]
|
||||
|
||||
def test_create_audio_processor_with_custom_clean_model(self):
|
||||
"""Test creating AudioProcessor with custom clean instrumental model."""
|
||||
with patch('backend.workers.audio_worker.AudioProcessor') as mock_processor:
|
||||
from backend.workers.audio_worker import create_audio_processor
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
result = create_audio_processor(
|
||||
temp_dir,
|
||||
clean_instrumental_model="custom_clean_model.ckpt"
|
||||
)
|
||||
|
||||
mock_processor.assert_called_once()
|
||||
call_kwargs = mock_processor.call_args[1]
|
||||
|
||||
# Should use custom clean model
|
||||
assert call_kwargs['clean_instrumental_model'] == "custom_clean_model.ckpt"
|
||||
# Other models should still be defaults
|
||||
assert call_kwargs['backing_vocals_models'] == ["mel_band_roformer_karaoke_aufr33_viperx_sdr_10.1956.ckpt"]
|
||||
|
||||
def test_create_audio_processor_with_custom_backing_models(self):
|
||||
"""Test creating AudioProcessor with custom backing vocals models."""
|
||||
with patch('backend.workers.audio_worker.AudioProcessor') as mock_processor:
|
||||
from backend.workers.audio_worker import create_audio_processor
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
result = create_audio_processor(
|
||||
temp_dir,
|
||||
backing_vocals_models=["custom_bv1.ckpt", "custom_bv2.ckpt"]
|
||||
)
|
||||
|
||||
mock_processor.assert_called_once()
|
||||
call_kwargs = mock_processor.call_args[1]
|
||||
|
||||
# Should use custom backing vocals models
|
||||
assert call_kwargs['backing_vocals_models'] == ["custom_bv1.ckpt", "custom_bv2.ckpt"]
|
||||
|
||||
def test_create_audio_processor_with_custom_other_stems_models(self):
|
||||
"""Test creating AudioProcessor with custom other stems models."""
|
||||
with patch('backend.workers.audio_worker.AudioProcessor') as mock_processor:
|
||||
from backend.workers.audio_worker import create_audio_processor
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
result = create_audio_processor(
|
||||
temp_dir,
|
||||
other_stems_models=["custom_demucs.yaml"]
|
||||
)
|
||||
|
||||
mock_processor.assert_called_once()
|
||||
call_kwargs = mock_processor.call_args[1]
|
||||
|
||||
# Should use custom other stems models
|
||||
assert call_kwargs['other_stems_models'] == ["custom_demucs.yaml"]
|
||||
|
||||
def test_create_audio_processor_with_all_custom_models(self):
|
||||
"""Test creating AudioProcessor with all custom models."""
|
||||
with patch('backend.workers.audio_worker.AudioProcessor') as mock_processor:
|
||||
from backend.workers.audio_worker import create_audio_processor
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
result = create_audio_processor(
|
||||
temp_dir,
|
||||
clean_instrumental_model="custom_clean.ckpt",
|
||||
backing_vocals_models=["custom_bv.ckpt"],
|
||||
other_stems_models=["custom_stems.yaml"]
|
||||
)
|
||||
|
||||
mock_processor.assert_called_once()
|
||||
call_kwargs = mock_processor.call_args[1]
|
||||
|
||||
# All models should be custom
|
||||
assert call_kwargs['clean_instrumental_model'] == "custom_clean.ckpt"
|
||||
assert call_kwargs['backing_vocals_models'] == ["custom_bv.ckpt"]
|
||||
assert call_kwargs['other_stems_models'] == ["custom_stems.yaml"]
|
||||
|
||||
def test_job_model_fields_are_passed_to_processor(self):
|
||||
"""Test that job model fields can be passed to create_audio_processor."""
|
||||
mock_job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test",
|
||||
title="Test",
|
||||
clean_instrumental_model="job_clean.ckpt",
|
||||
backing_vocals_models=["job_bv.ckpt"],
|
||||
other_stems_models=["job_stems.yaml"]
|
||||
)
|
||||
|
||||
with patch('backend.workers.audio_worker.AudioProcessor') as mock_processor:
|
||||
from backend.workers.audio_worker import create_audio_processor
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
# Simulate passing job model fields to create_audio_processor
|
||||
result = create_audio_processor(
|
||||
temp_dir,
|
||||
clean_instrumental_model=mock_job.clean_instrumental_model,
|
||||
backing_vocals_models=mock_job.backing_vocals_models,
|
||||
other_stems_models=mock_job.other_stems_models
|
||||
)
|
||||
|
||||
mock_processor.assert_called_once()
|
||||
call_kwargs = mock_processor.call_args[1]
|
||||
|
||||
# Models from job should be used
|
||||
assert call_kwargs['clean_instrumental_model'] == "job_clean.ckpt"
|
||||
assert call_kwargs['backing_vocals_models'] == ["job_bv.ckpt"]
|
||||
assert call_kwargs['other_stems_models'] == ["job_stems.yaml"]
|
||||
|
||||
def test_none_model_values_use_defaults(self):
|
||||
"""Test that None model values fall back to defaults."""
|
||||
mock_job = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PENDING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test",
|
||||
title="Test",
|
||||
clean_instrumental_model=None, # Not specified
|
||||
backing_vocals_models=None, # Not specified
|
||||
other_stems_models=None # Not specified
|
||||
)
|
||||
|
||||
with patch('backend.workers.audio_worker.AudioProcessor') as mock_processor:
|
||||
from backend.workers.audio_worker import create_audio_processor
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
result = create_audio_processor(
|
||||
temp_dir,
|
||||
clean_instrumental_model=mock_job.clean_instrumental_model,
|
||||
backing_vocals_models=mock_job.backing_vocals_models,
|
||||
other_stems_models=mock_job.other_stems_models
|
||||
)
|
||||
|
||||
mock_processor.assert_called_once()
|
||||
call_kwargs = mock_processor.call_args[1]
|
||||
|
||||
# Should fall back to defaults
|
||||
assert call_kwargs['clean_instrumental_model'] == "model_bs_roformer_ep_317_sdr_12.9755.ckpt"
|
||||
assert call_kwargs['backing_vocals_models'] == ["mel_band_roformer_karaoke_aufr33_viperx_sdr_10.1956.ckpt"]
|
||||
assert call_kwargs['other_stems_models'] == ["htdemucs_6s.yaml"]
|
||||
|
||||
|
||||
class TestDownloadFromUrl:
|
||||
"""Tests for download_from_url function - URL-based audio download."""
|
||||
|
||||
def test_download_from_url_function_exists(self):
|
||||
"""Test that download_from_url function exists in audio_worker."""
|
||||
from backend.workers.audio_worker import download_from_url
|
||||
assert callable(download_from_url)
|
||||
|
||||
def test_download_from_url_signature(self):
|
||||
"""Test that download_from_url has the expected signature."""
|
||||
import inspect
|
||||
from backend.workers.audio_worker import download_from_url
|
||||
|
||||
sig = inspect.signature(download_from_url)
|
||||
params = list(sig.parameters.keys())
|
||||
|
||||
# Should have these parameters
|
||||
assert 'url' in params
|
||||
assert 'temp_dir' in params
|
||||
assert 'artist' in params
|
||||
assert 'title' in params
|
||||
assert 'job_manager' in params
|
||||
assert 'job_id' in params
|
||||
|
||||
def test_download_from_url_is_async(self):
|
||||
"""Test that download_from_url is an async function."""
|
||||
import inspect
|
||||
from backend.workers.audio_worker import download_from_url
|
||||
|
||||
assert inspect.iscoroutinefunction(download_from_url)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_download_from_url_returns_none_for_invalid_url(self):
|
||||
"""Test that download_from_url handles errors gracefully."""
|
||||
from backend.workers.audio_worker import download_from_url
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
# This should fail gracefully (no yt-dlp in test env or invalid URL)
|
||||
result = await download_from_url(
|
||||
url='not-a-valid-url',
|
||||
temp_dir=temp_dir,
|
||||
artist='Test',
|
||||
title='Test'
|
||||
)
|
||||
|
||||
# Should return None on error (graceful failure)
|
||||
assert result is None
|
||||
|
||||
|
||||
class TestDownloadAudioWithUrl:
|
||||
"""Tests for download_audio function with URL-based jobs."""
|
||||
|
||||
@pytest.fixture
|
||||
def mock_job_with_url(self):
|
||||
"""Create a mock job with a URL."""
|
||||
return Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PROCESSING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test Artist",
|
||||
title="Test Song",
|
||||
url="https://www.youtube.com/watch?v=test123"
|
||||
)
|
||||
|
||||
@pytest.fixture
|
||||
def mock_job_manager(self, mock_job_with_url):
|
||||
"""Create a mock JobManager."""
|
||||
manager = MagicMock()
|
||||
manager.get_job.return_value = mock_job_with_url
|
||||
manager.update_job.return_value = None
|
||||
return manager
|
||||
|
||||
@pytest.fixture
|
||||
def mock_storage(self):
|
||||
"""Create a mock StorageService."""
|
||||
storage = MagicMock()
|
||||
return storage
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_download_audio_from_url(self, mock_job_with_url, mock_job_manager, mock_storage):
|
||||
"""Test download_audio routes to URL download when job has URL."""
|
||||
with patch('backend.workers.audio_worker.download_from_url', return_value='/tmp/test.wav') as mock_download:
|
||||
from backend.workers.audio_worker import download_audio
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
result = await download_audio(
|
||||
"test123",
|
||||
temp_dir,
|
||||
mock_storage,
|
||||
mock_job_with_url,
|
||||
job_manager_instance=mock_job_manager
|
||||
)
|
||||
|
||||
# Should have called download_from_url
|
||||
mock_download.assert_called_once()
|
||||
# Check positional args
|
||||
args = mock_download.call_args[0]
|
||||
assert args[0] == "https://www.youtube.com/watch?v=test123" # url
|
||||
assert args[1] == temp_dir # temp_dir
|
||||
assert args[2] == "Test Artist" # artist
|
||||
assert args[3] == "Test Song" # title
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_download_audio_from_gcs_when_no_url(self, mock_job_manager, mock_storage):
|
||||
"""Test download_audio downloads from GCS when job has no URL."""
|
||||
mock_job_no_url = Job(
|
||||
job_id="test123",
|
||||
status=JobStatus.PROCESSING,
|
||||
created_at=datetime.now(UTC),
|
||||
updated_at=datetime.now(UTC),
|
||||
artist="Test Artist",
|
||||
title="Test Song",
|
||||
input_media_gcs_path="uploads/test123/song.flac"
|
||||
)
|
||||
|
||||
with patch('backend.workers.audio_worker.download_from_url') as mock_url_download:
|
||||
from backend.workers.audio_worker import download_audio
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
result = await download_audio(
|
||||
"test123",
|
||||
temp_dir,
|
||||
mock_storage,
|
||||
mock_job_no_url,
|
||||
job_manager_instance=mock_job_manager
|
||||
)
|
||||
|
||||
# Should NOT have called download_from_url
|
||||
mock_url_download.assert_not_called()
|
||||
|
||||
# Should have called storage.download_file
|
||||
mock_storage.download_file.assert_called()
|
||||
|
||||
|
||||
class TestBackingVocalsAnalysis:
|
||||
"""Tests for backing vocals analysis in render_video_worker."""
|
||||
|
||||
def test_analyze_backing_vocals_function_exists(self):
|
||||
"""Test that _analyze_backing_vocals function exists in render_video_worker."""
|
||||
from backend.workers.render_video_worker import _analyze_backing_vocals
|
||||
assert callable(_analyze_backing_vocals)
|
||||
|
||||
def test_analyze_backing_vocals_is_async(self):
|
||||
"""Test that _analyze_backing_vocals is an async function."""
|
||||
import inspect
|
||||
from backend.workers.render_video_worker import _analyze_backing_vocals
|
||||
assert inspect.iscoroutinefunction(_analyze_backing_vocals)
|
||||
|
||||
def test_render_video_worker_imports_analysis_service(self):
|
||||
"""Test that render_video_worker can import AudioAnalysisService."""
|
||||
# This verifies the import path is correct
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
assert AudioAnalysisService is not None
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_analyze_backing_vocals_handles_missing_job(self):
|
||||
"""Test that analysis returns early when job not found (no error stored)."""
|
||||
mock_job_manager = MagicMock()
|
||||
mock_job_manager.get_job.return_value = None # No job found
|
||||
mock_job_manager.update_state_data = MagicMock()
|
||||
|
||||
mock_storage = MagicMock()
|
||||
mock_logger = MagicMock()
|
||||
|
||||
from backend.workers.render_video_worker import _analyze_backing_vocals
|
||||
|
||||
# Should not raise when job not found, just log warning and return
|
||||
await _analyze_backing_vocals(
|
||||
"nonexistent", mock_job_manager, mock_storage, mock_logger
|
||||
)
|
||||
|
||||
# Should log warning but not update state (early return)
|
||||
mock_logger.warning.assert_called()
|
||||
# No state_data update since we return early
|
||||
mock_job_manager.update_state_data.assert_not_called()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_analyze_backing_vocals_handles_missing_stems(self):
|
||||
"""Test that analysis returns early when stems not found (no error stored)."""
|
||||
mock_job = MagicMock()
|
||||
mock_job.file_urls = {} # No stems
|
||||
|
||||
mock_job_manager = MagicMock()
|
||||
mock_job_manager.get_job.return_value = mock_job
|
||||
mock_job_manager.update_state_data = MagicMock()
|
||||
|
||||
mock_storage = MagicMock()
|
||||
mock_logger = MagicMock()
|
||||
|
||||
from backend.workers.render_video_worker import _analyze_backing_vocals
|
||||
|
||||
# Should not raise when stems not found, just log warning and return
|
||||
await _analyze_backing_vocals(
|
||||
"test123", mock_job_manager, mock_storage, mock_logger
|
||||
)
|
||||
|
||||
# Should log warning but not update state (early return)
|
||||
mock_logger.warning.assert_called()
|
||||
# No state_data update since we return early
|
||||
mock_job_manager.update_state_data.assert_not_called()
|
||||
|
||||
def test_analysis_service_can_be_instantiated(self):
|
||||
"""Test that AudioAnalysisService can be instantiated."""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
mock_storage = MagicMock()
|
||||
service = AudioAnalysisService(storage_service=mock_storage)
|
||||
|
||||
assert service is not None
|
||||
assert service.storage_service == mock_storage
|
||||
|
||||
@@ -0,0 +1,247 @@
|
||||
"""
|
||||
Tests for youtube_service.py - YouTube credential management.
|
||||
|
||||
These tests mock Secret Manager to verify:
|
||||
- Credential loading and parsing
|
||||
- Validation of required fields
|
||||
- Error handling for missing/invalid credentials
|
||||
"""
|
||||
import json
|
||||
import pytest
|
||||
from unittest.mock import Mock, patch
|
||||
|
||||
|
||||
class TestYouTubeServiceInit:
|
||||
"""Test YouTubeService initialization."""
|
||||
|
||||
@patch("backend.services.youtube_service.get_settings")
|
||||
def test_init_creates_service(self, mock_get_settings):
|
||||
"""Test initialization creates service with settings."""
|
||||
from backend.services.youtube_service import YouTubeService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = YouTubeService()
|
||||
|
||||
assert service.settings == mock_settings
|
||||
assert service._credentials is None
|
||||
assert service._loaded is False
|
||||
|
||||
|
||||
class TestLoadCredentials:
|
||||
"""Test load_credentials method."""
|
||||
|
||||
@patch("backend.services.youtube_service.get_settings")
|
||||
def test_load_credentials_success(self, mock_get_settings):
|
||||
"""Test successful credential loading from Secret Manager."""
|
||||
from backend.services.youtube_service import YouTubeService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"token": "access-token-123",
|
||||
"refresh_token": "refresh-token-456",
|
||||
"token_uri": "https://oauth2.googleapis.com/token",
|
||||
"client_id": "client-id.apps.googleusercontent.com",
|
||||
"client_secret": "client-secret-789",
|
||||
"scopes": ["https://www.googleapis.com/auth/youtube.upload"],
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = YouTubeService()
|
||||
result = service.load_credentials()
|
||||
|
||||
assert result is True
|
||||
assert service._credentials is not None
|
||||
assert service._credentials["refresh_token"] == "refresh-token-456"
|
||||
mock_settings.get_secret.assert_called_once_with("youtube-oauth-credentials")
|
||||
|
||||
@patch("backend.services.youtube_service.get_settings")
|
||||
def test_load_credentials_not_found(self, mock_get_settings):
|
||||
"""Test handling when credentials are not in Secret Manager."""
|
||||
from backend.services.youtube_service import YouTubeService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = None
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = YouTubeService()
|
||||
result = service.load_credentials()
|
||||
|
||||
assert result is False
|
||||
assert service._credentials is None
|
||||
assert service._loaded is True
|
||||
|
||||
@patch("backend.services.youtube_service.get_settings")
|
||||
def test_load_credentials_missing_required_fields(self, mock_get_settings):
|
||||
"""Test handling when credentials are missing required fields."""
|
||||
from backend.services.youtube_service import YouTubeService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"token": "access-token",
|
||||
# Missing: refresh_token, token_uri, client_id, client_secret
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = YouTubeService()
|
||||
result = service.load_credentials()
|
||||
|
||||
assert result is False
|
||||
assert service._credentials is None
|
||||
|
||||
@patch("backend.services.youtube_service.get_settings")
|
||||
def test_load_credentials_invalid_json(self, mock_get_settings):
|
||||
"""Test handling of invalid JSON in credentials."""
|
||||
from backend.services.youtube_service import YouTubeService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = "not valid json {"
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = YouTubeService()
|
||||
result = service.load_credentials()
|
||||
|
||||
assert result is False
|
||||
assert service._credentials is None
|
||||
|
||||
@patch("backend.services.youtube_service.get_settings")
|
||||
def test_load_credentials_exception(self, mock_get_settings):
|
||||
"""Test handling of exceptions during credential loading."""
|
||||
from backend.services.youtube_service import YouTubeService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.side_effect = Exception("Secret Manager error")
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = YouTubeService()
|
||||
result = service.load_credentials()
|
||||
|
||||
assert result is False
|
||||
assert service._loaded is True
|
||||
|
||||
@patch("backend.services.youtube_service.get_settings")
|
||||
def test_load_credentials_cached(self, mock_get_settings):
|
||||
"""Test that credentials are cached after first load."""
|
||||
from backend.services.youtube_service import YouTubeService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"refresh_token": "token",
|
||||
"token_uri": "uri",
|
||||
"client_id": "id",
|
||||
"client_secret": "secret",
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = YouTubeService()
|
||||
|
||||
# First call
|
||||
result1 = service.load_credentials()
|
||||
# Second call
|
||||
result2 = service.load_credentials()
|
||||
|
||||
assert result1 is True
|
||||
assert result2 is True
|
||||
# Secret Manager should only be called once
|
||||
assert mock_settings.get_secret.call_count == 1
|
||||
|
||||
|
||||
class TestGetCredentialsDict:
|
||||
"""Test get_credentials_dict method."""
|
||||
|
||||
@patch("backend.services.youtube_service.get_settings")
|
||||
def test_get_credentials_dict_loads_if_needed(self, mock_get_settings):
|
||||
"""Test get_credentials_dict loads credentials if not already loaded."""
|
||||
from backend.services.youtube_service import YouTubeService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"refresh_token": "token",
|
||||
"token_uri": "uri",
|
||||
"client_id": "id",
|
||||
"client_secret": "secret",
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = YouTubeService()
|
||||
|
||||
# Don't explicitly call load_credentials
|
||||
result = service.get_credentials_dict()
|
||||
|
||||
assert result is not None
|
||||
assert result["refresh_token"] == "token"
|
||||
|
||||
@patch("backend.services.youtube_service.get_settings")
|
||||
def test_get_credentials_dict_returns_none_if_not_configured(
|
||||
self, mock_get_settings
|
||||
):
|
||||
"""Test get_credentials_dict returns None when not configured."""
|
||||
from backend.services.youtube_service import YouTubeService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = None
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = YouTubeService()
|
||||
result = service.get_credentials_dict()
|
||||
|
||||
assert result is None
|
||||
|
||||
|
||||
class TestIsConfigured:
|
||||
"""Test is_configured property."""
|
||||
|
||||
@patch("backend.services.youtube_service.get_settings")
|
||||
def test_is_configured_true(self, mock_get_settings):
|
||||
"""Test is_configured returns True when credentials exist."""
|
||||
from backend.services.youtube_service import YouTubeService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = json.dumps({
|
||||
"refresh_token": "token",
|
||||
"token_uri": "uri",
|
||||
"client_id": "id",
|
||||
"client_secret": "secret",
|
||||
})
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = YouTubeService()
|
||||
|
||||
assert service.is_configured is True
|
||||
|
||||
@patch("backend.services.youtube_service.get_settings")
|
||||
def test_is_configured_false(self, mock_get_settings):
|
||||
"""Test is_configured returns False when credentials missing."""
|
||||
from backend.services.youtube_service import YouTubeService
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = None
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service = YouTubeService()
|
||||
|
||||
assert service.is_configured is False
|
||||
|
||||
|
||||
class TestGetYouTubeService:
|
||||
"""Test get_youtube_service singleton."""
|
||||
|
||||
@patch("backend.services.youtube_service.get_settings")
|
||||
def test_get_youtube_service_singleton(self, mock_get_settings):
|
||||
"""Test get_youtube_service returns singleton instance."""
|
||||
from backend.services.youtube_service import get_youtube_service
|
||||
import backend.services.youtube_service as youtube_module
|
||||
|
||||
# Reset singleton
|
||||
youtube_module._youtube_service = None
|
||||
|
||||
mock_settings = Mock()
|
||||
mock_settings.get_secret.return_value = None
|
||||
mock_get_settings.return_value = mock_settings
|
||||
|
||||
service1 = get_youtube_service()
|
||||
service2 = get_youtube_service()
|
||||
|
||||
assert service1 is service2
|
||||
|
||||
+201
-88
@@ -7,11 +7,17 @@ Handles the audio processing track of parallel processing:
|
||||
3. Post-processing: Combine instrumentals, normalize
|
||||
|
||||
Re-uses karaoke_gen.audio_processor.AudioProcessor for remote GPU separation.
|
||||
|
||||
Observability:
|
||||
- All operations wrapped in tracing spans for Cloud Trace visibility
|
||||
- Logs include [job:ID] prefix for easy filtering in Cloud Logging
|
||||
- Worker start/end timing logged with WORKER_START/WORKER_END markers
|
||||
"""
|
||||
import logging
|
||||
import os
|
||||
import shutil
|
||||
import tempfile
|
||||
import time
|
||||
from typing import Optional, Dict, Any
|
||||
from pathlib import Path
|
||||
|
||||
@@ -19,7 +25,9 @@ from backend.models.job import JobStatus
|
||||
from backend.services.job_manager import JobManager
|
||||
from backend.services.storage_service import StorageService
|
||||
from backend.config import get_settings
|
||||
from backend.workers.worker_logging import create_job_logger, setup_job_logging
|
||||
from backend.workers.worker_logging import create_job_logger, setup_job_logging, job_logging_context
|
||||
from backend.services.tracing import job_span, add_span_event, add_span_attribute
|
||||
from backend.services.metrics import metrics
|
||||
|
||||
# Import from karaoke_gen package
|
||||
from karaoke_gen.audio_processor import AudioProcessor
|
||||
@@ -34,7 +42,7 @@ AUDIO_WORKER_LOGGERS = [
|
||||
]
|
||||
|
||||
|
||||
async def download_from_url(url: str, temp_dir: str, artist: str, title: str) -> Optional[str]:
|
||||
async def download_from_url(url: str, temp_dir: str, artist: str, title: str, job_manager: JobManager = None, job_id: str = None) -> Optional[str]:
|
||||
"""
|
||||
Download audio from a URL (YouTube, etc.) using karaoke_gen.FileHandler.
|
||||
|
||||
@@ -43,11 +51,16 @@ async def download_from_url(url: str, temp_dir: str, artist: str, title: str) ->
|
||||
- Cookie support for authenticated downloads
|
||||
- Retry logic
|
||||
|
||||
If artist and/or title are not provided, attempts to extract them from
|
||||
the URL metadata.
|
||||
|
||||
Args:
|
||||
url: URL to download from
|
||||
temp_dir: Temporary directory to save to
|
||||
artist: Artist name for filename
|
||||
title: Song title for filename
|
||||
artist: Artist name for filename (can be None for auto-detection)
|
||||
title: Song title for filename (can be None for auto-detection)
|
||||
job_manager: Optional JobManager to update job with detected metadata
|
||||
job_id: Optional job ID to update
|
||||
|
||||
Returns:
|
||||
Path to downloaded audio file, or None if failed
|
||||
@@ -64,6 +77,34 @@ async def download_from_url(url: str, temp_dir: str, artist: str, title: str) ->
|
||||
dry_run=False
|
||||
)
|
||||
|
||||
# Try to extract metadata if artist or title not provided
|
||||
if not artist or not title:
|
||||
logger.info(f"Extracting metadata from URL: {url}")
|
||||
metadata = file_handler.extract_metadata_from_url(url)
|
||||
|
||||
if metadata:
|
||||
if not artist:
|
||||
artist = metadata.get('artist', 'Unknown')
|
||||
logger.info(f"Auto-detected artist: {artist}")
|
||||
if not title:
|
||||
title = metadata.get('title', 'Unknown')
|
||||
logger.info(f"Auto-detected title: {title}")
|
||||
|
||||
# Update job with detected metadata if job_manager provided
|
||||
if job_manager and job_id:
|
||||
update_data = {}
|
||||
if artist:
|
||||
update_data['artist'] = artist
|
||||
if title:
|
||||
update_data['title'] = title
|
||||
if update_data:
|
||||
job_manager.update_job(job_id, update_data)
|
||||
logger.info(f"Updated job {job_id} with detected metadata")
|
||||
else:
|
||||
logger.warning("Could not extract metadata from URL, using defaults")
|
||||
artist = artist or "Unknown"
|
||||
title = title or "Unknown"
|
||||
|
||||
# Create output filename (without extension)
|
||||
safe_artist = sanitize_filename(artist) if artist else "Unknown"
|
||||
safe_title = sanitize_filename(title) if title else "Unknown"
|
||||
@@ -112,7 +153,12 @@ async def download_from_url(url: str, temp_dir: str, artist: str, title: str) ->
|
||||
return None
|
||||
|
||||
|
||||
def create_audio_processor(temp_dir: str) -> AudioProcessor:
|
||||
def create_audio_processor(
|
||||
temp_dir: str,
|
||||
clean_instrumental_model: Optional[str] = None,
|
||||
backing_vocals_models: Optional[list] = None,
|
||||
other_stems_models: Optional[list] = None
|
||||
) -> AudioProcessor:
|
||||
"""
|
||||
Create an AudioProcessor instance configured for remote API processing.
|
||||
|
||||
@@ -120,10 +166,13 @@ def create_audio_processor(temp_dir: str) -> AudioProcessor:
|
||||
- Uses remote Modal API (via AUDIO_SEPARATOR_API_URL env var)
|
||||
- No local models needed (model_file_dir=None)
|
||||
- FLAC output format for quality
|
||||
- Standard model configurations from karaoke-gen CLI
|
||||
- Model configurations from job or CLI defaults
|
||||
|
||||
Args:
|
||||
temp_dir: Temporary directory for processing
|
||||
clean_instrumental_model: Model for clean instrumental separation (optional, uses default if not provided)
|
||||
backing_vocals_models: List of models for backing vocals separation (optional, uses default if not provided)
|
||||
other_stems_models: List of models for other stems separation (optional, uses default if not provided)
|
||||
|
||||
Returns:
|
||||
Configured AudioProcessor instance
|
||||
@@ -132,10 +181,10 @@ def create_audio_processor(temp_dir: str) -> AudioProcessor:
|
||||
audio_logger = logging.getLogger("karaoke_gen.audio_processor")
|
||||
audio_logger.setLevel(logging.INFO)
|
||||
|
||||
# Model configurations (same as CLI defaults)
|
||||
clean_instrumental_model = "model_bs_roformer_ep_317_sdr_12.9755.ckpt"
|
||||
backing_vocals_models = ["mel_band_roformer_karaoke_aufr33_viperx_sdr_10.1956.ckpt"]
|
||||
other_stems_models = ["htdemucs_6s.yaml"] # For 6-stem separation (bass, drums, etc.)
|
||||
# Model configurations - use provided values or CLI defaults
|
||||
effective_clean_model = clean_instrumental_model or "model_bs_roformer_ep_317_sdr_12.9755.ckpt"
|
||||
effective_backing_models = backing_vocals_models or ["mel_band_roformer_karaoke_aufr33_viperx_sdr_10.1956.ckpt"]
|
||||
effective_other_models = other_stems_models or ["htdemucs_6s.yaml"] # For 6-stem separation (bass, drums, etc.)
|
||||
|
||||
# FFmpeg command for combining audio files (must be a string, not a list)
|
||||
ffmpeg_base_command = "ffmpeg -hide_banner -loglevel error -nostats -y"
|
||||
@@ -146,9 +195,9 @@ def create_audio_processor(temp_dir: str) -> AudioProcessor:
|
||||
log_formatter=None, # Not needed for our use case
|
||||
model_file_dir=None, # No local models, using remote API
|
||||
lossless_output_format="FLAC",
|
||||
clean_instrumental_model=clean_instrumental_model,
|
||||
backing_vocals_models=backing_vocals_models,
|
||||
other_stems_models=other_stems_models,
|
||||
clean_instrumental_model=effective_clean_model,
|
||||
backing_vocals_models=effective_backing_models,
|
||||
other_stems_models=effective_other_models,
|
||||
ffmpeg_base_command=ffmpeg_base_command
|
||||
)
|
||||
|
||||
@@ -174,6 +223,7 @@ async def process_audio_separation(job_id: str) -> bool:
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
start_time = time.time()
|
||||
job_manager = JobManager()
|
||||
storage = StorageService()
|
||||
settings = get_settings()
|
||||
@@ -181,7 +231,8 @@ async def process_audio_separation(job_id: str) -> bool:
|
||||
# Create job logger for remote debugging FIRST
|
||||
job_log = create_job_logger(job_id, "audio")
|
||||
|
||||
# Log immediately to verify logging is working
|
||||
# Log with structured markers for easy Cloud Logging queries
|
||||
logger.info(f"[job:{job_id}] WORKER_START worker=audio")
|
||||
job_log.info("=== AUDIO WORKER STARTED ===")
|
||||
job_log.info(f"Job ID: {job_id}")
|
||||
|
||||
@@ -191,7 +242,7 @@ async def process_audio_separation(job_id: str) -> bool:
|
||||
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
logger.error(f"Job {job_id} not found")
|
||||
logger.error(f"[job:{job_id}] Job not found in Firestore")
|
||||
job_log.error(f"Job {job_id} not found in Firestore!")
|
||||
return False
|
||||
|
||||
@@ -200,74 +251,114 @@ async def process_audio_separation(job_id: str) -> bool:
|
||||
job_log.info(f"Created temp directory: {temp_dir}")
|
||||
|
||||
try:
|
||||
job_log.info(f"Starting audio separation for {job.artist} - {job.title}")
|
||||
logger.info(f"Starting audio separation for job {job_id}")
|
||||
|
||||
# Ensure AUDIO_SEPARATOR_API_URL is set
|
||||
api_url = os.environ.get("AUDIO_SEPARATOR_API_URL")
|
||||
if not api_url:
|
||||
raise Exception("AUDIO_SEPARATOR_API_URL environment variable not set. "
|
||||
"Cannot perform audio separation without remote API access.")
|
||||
job_log.info(f"Audio separator API: {api_url}")
|
||||
|
||||
# Download audio file from GCS
|
||||
job_log.info("Downloading audio file from GCS...")
|
||||
audio_path = await download_audio(job_id, temp_dir, storage, job)
|
||||
if not audio_path:
|
||||
raise Exception("Failed to download audio file")
|
||||
job_log.info(f"Audio downloaded: {os.path.basename(audio_path)}")
|
||||
|
||||
# Update progress using state_data (don't change status during parallel processing)
|
||||
# The status is managed at a higher level - workers just track their progress
|
||||
job_manager.update_state_data(job_id, 'audio_progress', {
|
||||
'stage': 'separating_stage1',
|
||||
'progress': 10,
|
||||
'message': 'Starting audio separation (Stage 1: Clean instrumental)'
|
||||
})
|
||||
|
||||
# Create AudioProcessor instance (reuses karaoke_gen code)
|
||||
job_log.info("Creating AudioProcessor instance...")
|
||||
audio_processor = create_audio_processor(temp_dir)
|
||||
|
||||
# Format artist-title for file naming (matches CLI behavior)
|
||||
artist_title = f"{job.artist} - {job.title}"
|
||||
|
||||
# Run audio separation (calls Modal API internally)
|
||||
# This returns a dict with paths to all separated stems
|
||||
job_log.info("Starting audio separation (this may take 5-10 minutes)...")
|
||||
job_log.info(" Stage 1: Clean instrumental separation (MDX models)")
|
||||
job_log.info(" Stage 2: Backing vocals separation (Demucs model)")
|
||||
logger.info(f"Job {job_id}: Calling audio_processor.process_audio_separation()")
|
||||
separation_result = audio_processor.process_audio_separation(
|
||||
audio_file=audio_path,
|
||||
artist_title=artist_title,
|
||||
track_output_dir=temp_dir
|
||||
)
|
||||
|
||||
job_log.info("Audio separation complete!")
|
||||
job_log.info(f" Generated {len(separation_result)} stem files")
|
||||
logger.info(f"Job {job_id}: Audio separation complete, organizing results")
|
||||
|
||||
# Update progress using state_data (don't change status during parallel processing)
|
||||
job_manager.update_state_data(job_id, 'audio_progress', {
|
||||
'stage': 'audio_complete',
|
||||
'progress': 45,
|
||||
'message': 'Audio separation complete, uploading stems'
|
||||
})
|
||||
|
||||
# Upload all stems to GCS
|
||||
await upload_separation_results(job_id, separation_result, storage, job_manager)
|
||||
|
||||
logger.info(f"Job {job_id}: All stems uploaded successfully")
|
||||
|
||||
# Mark audio processing complete
|
||||
# This will check if lyrics are also complete and transition to next stage if so
|
||||
job_manager.mark_audio_complete(job_id)
|
||||
|
||||
return True
|
||||
# Wrap entire worker in a tracing span
|
||||
with job_span("audio-worker", job_id, {"artist": job.artist, "title": job.title}) as root_span:
|
||||
# Use job_logging_context for proper log isolation when multiple jobs run concurrently
|
||||
# This ensures logs from third-party libraries (karaoke_gen.audio_processor) are
|
||||
# only captured by this job's handler, not handlers from other concurrent jobs
|
||||
with job_logging_context(job_id):
|
||||
job_log.info(f"Starting audio separation for {job.artist} - {job.title}")
|
||||
logger.info(f"[job:{job_id}] Starting audio separation for {job.artist} - {job.title}")
|
||||
|
||||
# Ensure AUDIO_SEPARATOR_API_URL is set
|
||||
api_url = os.environ.get("AUDIO_SEPARATOR_API_URL")
|
||||
if not api_url:
|
||||
raise Exception("AUDIO_SEPARATOR_API_URL environment variable not set. "
|
||||
"Cannot perform audio separation without remote API access.")
|
||||
job_log.info(f"Audio separator API: {api_url}")
|
||||
add_span_attribute("audio_separator_api", api_url)
|
||||
|
||||
# Download audio file from GCS or URL
|
||||
with job_span("download-audio", job_id) as download_span:
|
||||
job_log.info("Downloading audio file...")
|
||||
audio_path = await download_audio(job_id, temp_dir, storage, job, job_manager_instance=job_manager)
|
||||
if not audio_path:
|
||||
raise Exception("Failed to download audio file")
|
||||
job_log.info(f"Audio downloaded: {os.path.basename(audio_path)}")
|
||||
download_span.set_attribute("audio_file", os.path.basename(audio_path))
|
||||
download_span.set_attribute("source", "url" if job.url else "gcs")
|
||||
|
||||
# Update progress using state_data (don't change status during parallel processing)
|
||||
# The status is managed at a higher level - workers just track their progress
|
||||
job_manager.update_state_data(job_id, 'audio_progress', {
|
||||
'stage': 'separating_stage1',
|
||||
'progress': 10,
|
||||
'message': 'Starting audio separation (Stage 1: Clean instrumental)'
|
||||
})
|
||||
|
||||
# Create AudioProcessor instance (reuses karaoke_gen code)
|
||||
# Use model configuration from job if provided, otherwise use defaults
|
||||
job_log.info("Creating AudioProcessor instance...")
|
||||
if job.clean_instrumental_model:
|
||||
job_log.info(f" Using clean instrumental model: {job.clean_instrumental_model}")
|
||||
add_span_attribute("clean_model", job.clean_instrumental_model)
|
||||
if job.backing_vocals_models:
|
||||
job_log.info(f" Using backing vocals models: {job.backing_vocals_models}")
|
||||
if job.other_stems_models:
|
||||
job_log.info(f" Using other stems models: {job.other_stems_models}")
|
||||
|
||||
audio_processor = create_audio_processor(
|
||||
temp_dir,
|
||||
clean_instrumental_model=job.clean_instrumental_model,
|
||||
backing_vocals_models=job.backing_vocals_models,
|
||||
other_stems_models=job.other_stems_models
|
||||
)
|
||||
|
||||
# Format artist-title for file naming (matches CLI behavior)
|
||||
artist_title = f"{job.artist} - {job.title}"
|
||||
|
||||
# Run audio separation (calls Modal API internally)
|
||||
# This returns a dict with paths to all separated stems
|
||||
with job_span("modal-separation", job_id) as sep_span:
|
||||
sep_start = time.time()
|
||||
job_log.info("Starting audio separation (this may take 5-10 minutes)...")
|
||||
job_log.info(" Stage 1: Clean instrumental separation (MDX models)")
|
||||
job_log.info(" Stage 2: Backing vocals separation (Demucs model)")
|
||||
add_span_event("separation_started")
|
||||
logger.info(f"[job:{job_id}] Calling Modal API for audio separation")
|
||||
|
||||
with metrics.time_external_api("modal", job_id):
|
||||
separation_result = audio_processor.process_audio_separation(
|
||||
audio_file=audio_path,
|
||||
artist_title=artist_title,
|
||||
track_output_dir=temp_dir
|
||||
)
|
||||
|
||||
sep_duration = time.time() - sep_start
|
||||
sep_span.set_attribute("duration_seconds", sep_duration)
|
||||
sep_span.set_attribute("stem_count", len(separation_result))
|
||||
add_span_event("separation_completed", {"duration_seconds": sep_duration})
|
||||
|
||||
job_log.info("Audio separation complete!")
|
||||
job_log.info(f" Generated {len(separation_result)} stem files")
|
||||
logger.info(f"[job:{job_id}] Audio separation complete, organizing results")
|
||||
|
||||
# Update progress using state_data (don't change status during parallel processing)
|
||||
job_manager.update_state_data(job_id, 'audio_progress', {
|
||||
'stage': 'audio_complete',
|
||||
'progress': 45,
|
||||
'message': 'Audio separation complete, uploading stems'
|
||||
})
|
||||
|
||||
# Upload all stems to GCS
|
||||
with job_span("upload-stems", job_id) as upload_span:
|
||||
await upload_separation_results(job_id, separation_result, storage, job_manager)
|
||||
upload_span.set_attribute("stem_count", len(separation_result))
|
||||
|
||||
logger.info(f"[job:{job_id}] All stems uploaded successfully")
|
||||
|
||||
# Mark audio processing complete
|
||||
# This will check if lyrics are also complete and transition to next stage if so
|
||||
job_manager.mark_audio_complete(job_id)
|
||||
|
||||
duration = time.time() - start_time
|
||||
root_span.set_attribute("duration_seconds", duration)
|
||||
logger.info(f"[job:{job_id}] WORKER_END worker=audio status=success duration={duration:.1f}s")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Job {job_id}: Audio separation failed: {e}", exc_info=True)
|
||||
duration = time.time() - start_time
|
||||
logger.error(f"[job:{job_id}] WORKER_END worker=audio status=error duration={duration:.1f}s error={e}")
|
||||
job_manager.mark_job_failed(
|
||||
job_id=job_id,
|
||||
error_message=f"Audio separation failed: {str(e)}",
|
||||
@@ -286,14 +377,15 @@ async def process_audio_separation(job_id: str) -> bool:
|
||||
# Cleanup temporary directory
|
||||
if os.path.exists(temp_dir):
|
||||
shutil.rmtree(temp_dir)
|
||||
logger.debug(f"Cleaned up temp directory: {temp_dir}")
|
||||
logger.debug(f"[job:{job_id}] Cleaned up temp directory: {temp_dir}")
|
||||
|
||||
|
||||
async def download_audio(
|
||||
job_id: str,
|
||||
temp_dir: str,
|
||||
storage: StorageService,
|
||||
job
|
||||
job,
|
||||
job_manager_instance: JobManager = None
|
||||
) -> Optional[str]:
|
||||
"""
|
||||
Download or fetch audio file to local temp directory.
|
||||
@@ -302,14 +394,25 @@ async def download_audio(
|
||||
1. Uploaded file: Download from GCS using input_media_gcs_path
|
||||
2. URL (YouTube, etc.): Download using yt-dlp or other tools
|
||||
|
||||
Args:
|
||||
job_id: Job ID
|
||||
temp_dir: Temporary directory to save to
|
||||
storage: StorageService instance
|
||||
job: Job object with URL or GCS path
|
||||
job_manager_instance: Optional JobManager instance for updating job metadata
|
||||
|
||||
Returns:
|
||||
Path to downloaded audio file, or None if failed
|
||||
"""
|
||||
try:
|
||||
from karaoke_gen.utils import sanitize_filename
|
||||
|
||||
# Case 1: File was uploaded to GCS
|
||||
if job.input_media_gcs_path:
|
||||
logger.info(f"Job {job_id}: Downloading uploaded file from GCS: {job.input_media_gcs_path}")
|
||||
local_path = os.path.join(temp_dir, job.filename or "input.flac")
|
||||
# Sanitize filename to handle Unicode chars that cause HTTP header encoding issues
|
||||
safe_filename = sanitize_filename(job.filename) if job.filename else "input.flac"
|
||||
local_path = os.path.join(temp_dir, safe_filename)
|
||||
storage.download_file(job.input_media_gcs_path, local_path)
|
||||
logger.info(f"Job {job_id}: Downloaded uploaded file to {local_path}")
|
||||
return local_path
|
||||
@@ -326,7 +429,18 @@ async def download_audio(
|
||||
# Case 3: Fresh URL that needs downloading
|
||||
if job.url:
|
||||
logger.info(f"Job {job_id}: Downloading from URL: {job.url}")
|
||||
local_path = await download_from_url(job.url, temp_dir, job.artist, job.title)
|
||||
|
||||
# Use provided job_manager or create new one
|
||||
jm = job_manager_instance or JobManager()
|
||||
|
||||
local_path = await download_from_url(
|
||||
job.url,
|
||||
temp_dir,
|
||||
job.artist,
|
||||
job.title,
|
||||
job_manager=jm,
|
||||
job_id=job_id
|
||||
)
|
||||
|
||||
if local_path and os.path.exists(local_path):
|
||||
# Upload to GCS and update job
|
||||
@@ -334,9 +448,8 @@ async def download_audio(
|
||||
url = storage.upload_file(local_path, gcs_path)
|
||||
|
||||
# Update job with GCS path for lyrics worker
|
||||
job_manager = JobManager()
|
||||
job_manager.firestore.update_job(job_id, {'input_media_gcs_path': gcs_path})
|
||||
job_manager.update_file_url(job_id, 'input', 'audio', url)
|
||||
jm.update_job(job_id, {'input_media_gcs_path': gcs_path})
|
||||
jm.update_file_url(job_id, 'input', 'audio', url)
|
||||
|
||||
logger.info(f"Job {job_id}: Downloaded and uploaded audio to GCS: {gcs_path}")
|
||||
return local_path
|
||||
|
||||
+221
-144
@@ -12,12 +12,18 @@ Handles the lyrics processing track of parallel processing:
|
||||
Re-uses:
|
||||
- karaoke_gen.lyrics_processor.LyricsProcessor for lyrics fetching and orchestration
|
||||
- lyrics_transcriber library (submodule) for transcription and correction
|
||||
|
||||
Observability:
|
||||
- All operations wrapped in tracing spans for Cloud Trace visibility
|
||||
- Logs include [job:ID] prefix for easy filtering in Cloud Logging
|
||||
- Worker start/end timing logged with WORKER_START/WORKER_END markers
|
||||
"""
|
||||
import asyncio
|
||||
import logging
|
||||
import os
|
||||
import shutil
|
||||
import tempfile
|
||||
import time
|
||||
import json
|
||||
from typing import Optional, Dict, Any
|
||||
from pathlib import Path
|
||||
@@ -26,8 +32,10 @@ from backend.models.job import JobStatus
|
||||
from karaoke_gen.utils import sanitize_filename
|
||||
from backend.services.job_manager import JobManager
|
||||
from backend.services.storage_service import StorageService
|
||||
from backend.workers.worker_logging import create_job_logger, setup_job_logging
|
||||
from backend.workers.worker_logging import create_job_logger, setup_job_logging, job_logging_context
|
||||
from backend.workers.style_helper import load_style_config
|
||||
from backend.services.tracing import job_span, add_span_event, add_span_attribute
|
||||
from backend.services.metrics import metrics
|
||||
|
||||
# Import from karaoke_gen package
|
||||
from karaoke_gen.lyrics_processor import LyricsProcessor
|
||||
@@ -36,27 +44,21 @@ from karaoke_gen.lyrics_processor import LyricsProcessor
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
# Loggers to capture for lyrics worker (includes LyricsTranscriber internals)
|
||||
# Loggers to capture for lyrics worker (top-level package loggers only)
|
||||
# Note: We only capture at top-level package loggers to avoid duplicate log entries.
|
||||
# Logs from sub-modules (e.g., lyrics_transcriber.correction.anchor_sequence) will
|
||||
# propagate up to their parent logger (lyrics_transcriber) where they get captured.
|
||||
LYRICS_WORKER_LOGGERS = [
|
||||
"karaoke_gen.lyrics_processor",
|
||||
"lyrics_transcriber",
|
||||
"lyrics_transcriber.core",
|
||||
"lyrics_transcriber.core.controller",
|
||||
"lyrics_transcriber.lyrics",
|
||||
"lyrics_transcriber.lyrics.genius",
|
||||
"lyrics_transcriber.lyrics.spotify",
|
||||
"lyrics_transcriber.lyrics.musixmatch",
|
||||
"lyrics_transcriber.lyrics.lrclib",
|
||||
"lyrics_transcriber.correction",
|
||||
"lyrics_transcriber.correction.corrector",
|
||||
"lyrics_transcriber.correction.anchor_sequence",
|
||||
"lyrics_transcriber.transcribers",
|
||||
"lyrics_transcriber.transcribers.audioshake",
|
||||
"lyrics_transcriber.output",
|
||||
]
|
||||
|
||||
|
||||
def create_lyrics_processor(style_params_json: Optional[str] = None) -> LyricsProcessor:
|
||||
def create_lyrics_processor(
|
||||
style_params_json: Optional[str] = None,
|
||||
lyrics_file: Optional[str] = None,
|
||||
subtitle_offset_ms: int = 0
|
||||
) -> LyricsProcessor:
|
||||
"""
|
||||
Create a LyricsProcessor instance configured for Cloud Run processing.
|
||||
|
||||
@@ -68,6 +70,8 @@ def create_lyrics_processor(style_params_json: Optional[str] = None) -> LyricsPr
|
||||
|
||||
Args:
|
||||
style_params_json: Optional path to style parameters JSON file
|
||||
lyrics_file: Optional path to user-provided lyrics file (overrides API fetch)
|
||||
subtitle_offset_ms: Offset for subtitle timing in milliseconds
|
||||
|
||||
Returns:
|
||||
Configured LyricsProcessor instance
|
||||
@@ -79,11 +83,11 @@ def create_lyrics_processor(style_params_json: Optional[str] = None) -> LyricsPr
|
||||
return LyricsProcessor(
|
||||
logger=lyrics_logger,
|
||||
style_params_json=style_params_json,
|
||||
lyrics_file=None, # Will fetch from APIs
|
||||
lyrics_file=lyrics_file, # Use user-provided lyrics if available
|
||||
skip_transcription=False, # We want transcription
|
||||
skip_transcription_review=True, # Skip interactive review (use React UI instead)
|
||||
render_video=False, # Skip video generation for now (will be done after review)
|
||||
subtitle_offset_ms=0 # No offset by default
|
||||
subtitle_offset_ms=subtitle_offset_ms
|
||||
)
|
||||
|
||||
|
||||
@@ -112,13 +116,15 @@ async def process_lyrics_transcription(job_id: str) -> bool:
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
start_time = time.time()
|
||||
job_manager = JobManager()
|
||||
storage = StorageService()
|
||||
|
||||
# Create job logger for remote debugging FIRST
|
||||
job_log = create_job_logger(job_id, "lyrics")
|
||||
|
||||
# Log immediately to verify logging is working
|
||||
# Log with structured markers for easy Cloud Logging queries
|
||||
logger.info(f"[job:{job_id}] WORKER_START worker=lyrics")
|
||||
job_log.info("=== LYRICS WORKER STARTED ===")
|
||||
job_log.info(f"Job ID: {job_id}")
|
||||
|
||||
@@ -131,130 +137,188 @@ async def process_lyrics_transcription(job_id: str) -> bool:
|
||||
temp_dir = None
|
||||
|
||||
try:
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
logger.error(f"Job {job_id} not found")
|
||||
job_log.error(f"Job {job_id} not found in Firestore!")
|
||||
return False
|
||||
|
||||
# Create temporary working directory
|
||||
temp_dir = tempfile.mkdtemp(prefix=f"karaoke_lyrics_{job_id}_")
|
||||
job_log.info(f"Created temp directory: {temp_dir}")
|
||||
job_log.info(f"Starting lyrics transcription for {job.artist} - {job.title}")
|
||||
job_log.info(f"Log capture enabled for: {', '.join(LYRICS_WORKER_LOGGERS)}")
|
||||
logger.info(f"Starting lyrics transcription for job {job_id}")
|
||||
|
||||
# Log environment configuration
|
||||
job_log.info("Checking API configuration...")
|
||||
if os.environ.get("GENIUS_API_TOKEN"):
|
||||
job_log.info(" Genius API: configured")
|
||||
else:
|
||||
job_log.warning(" Genius API: NOT configured")
|
||||
if os.environ.get("SPOTIFY_COOKIE_SP_DC"):
|
||||
job_log.info(" Spotify: configured")
|
||||
else:
|
||||
job_log.warning(" Spotify: NOT configured")
|
||||
if os.environ.get("RAPIDAPI_KEY"):
|
||||
job_log.info(" Musixmatch (RapidAPI): configured")
|
||||
else:
|
||||
job_log.warning(" Musixmatch (RapidAPI): NOT configured")
|
||||
|
||||
# Ensure required environment variables are set
|
||||
if not os.environ.get("AUDIOSHAKE_API_TOKEN"):
|
||||
job_log.warning("AUDIOSHAKE_API_TOKEN not set - transcription may fail")
|
||||
logger.warning("AUDIOSHAKE_API_TOKEN not set - transcription may fail")
|
||||
|
||||
# Download audio file from GCS (waits for audio worker if URL job)
|
||||
job_log.info("Downloading audio file from GCS...")
|
||||
audio_path = await download_audio(job_id, temp_dir, storage, job, job_manager)
|
||||
if not audio_path:
|
||||
raise Exception("Failed to download audio file")
|
||||
job_log.info(f"Audio downloaded: {os.path.basename(audio_path)}")
|
||||
|
||||
# Update progress using state_data (don't change status during parallel processing)
|
||||
# The status is managed at a higher level - workers just track their progress
|
||||
job_manager.update_state_data(job_id, 'lyrics_progress', {
|
||||
'stage': 'transcribing',
|
||||
'progress': 10,
|
||||
'message': 'Starting lyrics transcription via AudioShake'
|
||||
})
|
||||
|
||||
# Load style configuration (downloads assets from GCS if available)
|
||||
# This is needed for max_line_length and other style settings in LyricsTranscriber
|
||||
job_log.info("Loading style configuration for lyrics processing...")
|
||||
style_config = await load_style_config(job, storage, temp_dir)
|
||||
style_params_json_path = style_config.get_style_params_path() if style_config.has_custom_styles() else None
|
||||
|
||||
if style_params_json_path:
|
||||
job_log.info(f"Using custom style params: {style_params_json_path}")
|
||||
# Log the contents of the style params for debugging
|
||||
try:
|
||||
with open(style_params_json_path, 'r') as f:
|
||||
style_content = json.load(f)
|
||||
job_log.info(f"Style params sections: {list(style_content.keys())}")
|
||||
if 'karaoke' in style_content:
|
||||
karaoke_style = style_content['karaoke']
|
||||
job_log.info(f" karaoke.background_image: {karaoke_style.get('background_image', 'NOT SET')}")
|
||||
job_log.info(f" karaoke.font_path: {karaoke_style.get('font_path', 'NOT SET')}")
|
||||
except Exception as e:
|
||||
job_log.warning(f"Could not read style params for logging: {e}")
|
||||
else:
|
||||
job_log.info("No custom style params found, using defaults")
|
||||
|
||||
# Create LyricsProcessor instance (reuses karaoke_gen code)
|
||||
job_log.info("Creating LyricsProcessor instance...")
|
||||
job_log.info(f" style_params_json: {style_params_json_path}")
|
||||
lyrics_processor = create_lyrics_processor(style_params_json=style_params_json_path)
|
||||
|
||||
# Run transcription + correction
|
||||
# This will:
|
||||
# 1. Fetch reference lyrics from Genius/Spotify/Musixmatch/LRCLib
|
||||
# 2. Transcribe audio via AudioShake API
|
||||
# 3. Run automatic correction with lyrics_transcriber
|
||||
# 4. Generate corrections JSON (no interactive review)
|
||||
# 5. Skip video generation (render_video=False)
|
||||
job_log.info("Starting LyricsTranscriber processing...")
|
||||
job_log.info(f" Artist: {job.artist}")
|
||||
job_log.info(f" Title: {job.title}")
|
||||
logger.info(f"Job {job_id}: Calling lyrics_processor.transcribe_lyrics()")
|
||||
|
||||
# Run transcription in thread pool to avoid blocking the event loop
|
||||
# (transcribe_lyrics is synchronous and takes 1-2 minutes)
|
||||
result = await asyncio.to_thread(
|
||||
lyrics_processor.transcribe_lyrics,
|
||||
input_audio_wav=audio_path,
|
||||
artist=job.artist,
|
||||
title=job.title,
|
||||
track_output_dir=temp_dir
|
||||
)
|
||||
|
||||
job_log.info("Transcription processing complete")
|
||||
logger.info(f"Job {job_id}: Transcription complete, uploading results")
|
||||
|
||||
# Upload lyrics results to GCS
|
||||
job_log.info("Uploading lyrics results to GCS...")
|
||||
await upload_lyrics_results(job_id, temp_dir, result, storage, job_manager, job_log)
|
||||
|
||||
job_log.info("All lyrics data uploaded successfully")
|
||||
logger.info(f"Job {job_id}: All lyrics data uploaded successfully")
|
||||
|
||||
# Update progress using state_data (don't change status during parallel processing)
|
||||
job_manager.update_state_data(job_id, 'lyrics_progress', {
|
||||
'stage': 'lyrics_complete',
|
||||
'progress': 45,
|
||||
'message': 'Lyrics transcription complete'
|
||||
})
|
||||
|
||||
# Mark lyrics processing complete
|
||||
# This will check if audio is also complete and transition to next stage if so
|
||||
job_log.info("Lyrics worker complete, checking if audio is also done...")
|
||||
job_manager.mark_lyrics_complete(job_id)
|
||||
|
||||
return True
|
||||
# Wrap entire worker in a tracing span
|
||||
with job_span("lyrics-worker", job_id) as root_span:
|
||||
# Use job_logging_context for proper log isolation when multiple jobs run concurrently
|
||||
# This ensures logs from third-party libraries (lyrics_transcriber) are only captured
|
||||
# by this job's handler, not handlers from other concurrent jobs
|
||||
with job_logging_context(job_id):
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
logger.error(f"[job:{job_id}] Job not found in Firestore")
|
||||
job_log.error(f"Job {job_id} not found in Firestore!")
|
||||
return False
|
||||
|
||||
add_span_attribute("artist", job.artist)
|
||||
add_span_attribute("title", job.title)
|
||||
|
||||
# Create temporary working directory
|
||||
temp_dir = tempfile.mkdtemp(prefix=f"karaoke_lyrics_{job_id}_")
|
||||
job_log.info(f"Created temp directory: {temp_dir}")
|
||||
job_log.info(f"Starting lyrics transcription for {job.artist} - {job.title}")
|
||||
job_log.info(f"Log capture enabled for: {', '.join(LYRICS_WORKER_LOGGERS)}")
|
||||
logger.info(f"[job:{job_id}] Starting lyrics transcription for {job.artist} - {job.title}")
|
||||
|
||||
# Log environment configuration
|
||||
with job_span("check-api-config", job_id):
|
||||
job_log.info("Checking API configuration...")
|
||||
apis_configured = []
|
||||
if os.environ.get("GENIUS_API_TOKEN"):
|
||||
job_log.info(" Genius API: configured")
|
||||
apis_configured.append("genius")
|
||||
else:
|
||||
job_log.warning(" Genius API: NOT configured")
|
||||
if os.environ.get("SPOTIFY_COOKIE_SP_DC"):
|
||||
job_log.info(" Spotify: configured")
|
||||
apis_configured.append("spotify")
|
||||
else:
|
||||
job_log.warning(" Spotify: NOT configured")
|
||||
if os.environ.get("RAPIDAPI_KEY"):
|
||||
job_log.info(" Musixmatch (RapidAPI): configured")
|
||||
apis_configured.append("musixmatch")
|
||||
else:
|
||||
job_log.warning(" Musixmatch (RapidAPI): NOT configured")
|
||||
add_span_attribute("lyrics_apis", ",".join(apis_configured))
|
||||
|
||||
# Ensure required environment variables are set
|
||||
if not os.environ.get("AUDIOSHAKE_API_TOKEN"):
|
||||
job_log.warning("AUDIOSHAKE_API_TOKEN not set - transcription may fail")
|
||||
logger.warning(f"[job:{job_id}] AUDIOSHAKE_API_TOKEN not set - transcription may fail")
|
||||
|
||||
# Download audio file from GCS (waits for audio worker if URL job)
|
||||
with job_span("download-audio", job_id) as download_span:
|
||||
job_log.info("Downloading audio file from GCS...")
|
||||
audio_path = await download_audio(job_id, temp_dir, storage, job, job_manager)
|
||||
if not audio_path:
|
||||
raise Exception("Failed to download audio file")
|
||||
job_log.info(f"Audio downloaded: {os.path.basename(audio_path)}")
|
||||
download_span.set_attribute("audio_file", os.path.basename(audio_path))
|
||||
|
||||
# Update progress using state_data (don't change status during parallel processing)
|
||||
# The status is managed at a higher level - workers just track their progress
|
||||
job_manager.update_state_data(job_id, 'lyrics_progress', {
|
||||
'stage': 'transcribing',
|
||||
'progress': 10,
|
||||
'message': 'Starting lyrics transcription via AudioShake'
|
||||
})
|
||||
|
||||
# Load style configuration (downloads assets from GCS if available)
|
||||
# This is needed for max_line_length and other style settings in LyricsTranscriber
|
||||
with job_span("load-style-config", job_id):
|
||||
job_log.info("Loading style configuration for lyrics processing...")
|
||||
style_config = await load_style_config(job, storage, temp_dir)
|
||||
style_params_json_path = style_config.get_style_params_path() if style_config.has_custom_styles() else None
|
||||
|
||||
if style_params_json_path:
|
||||
job_log.info(f"Using custom style params: {style_params_json_path}")
|
||||
# Log the contents of the style params for debugging
|
||||
try:
|
||||
with open(style_params_json_path, 'r') as f:
|
||||
style_content = json.load(f)
|
||||
job_log.info(f"Style params sections: {list(style_content.keys())}")
|
||||
if 'karaoke' in style_content:
|
||||
karaoke_style = style_content['karaoke']
|
||||
job_log.info(f" karaoke.background_image: {karaoke_style.get('background_image', 'NOT SET')}")
|
||||
job_log.info(f" karaoke.font_path: {karaoke_style.get('font_path', 'NOT SET')}")
|
||||
except Exception as e:
|
||||
job_log.warning(f"Could not read style params for logging: {e}")
|
||||
else:
|
||||
job_log.info("No custom style params found, using defaults")
|
||||
|
||||
# Download user-provided lyrics file if available
|
||||
lyrics_file_path = None
|
||||
if hasattr(job, 'lyrics_file_gcs_path') and job.lyrics_file_gcs_path:
|
||||
with job_span("download-user-lyrics", job_id):
|
||||
lyrics_file_path = os.path.join(temp_dir, "user_lyrics.txt")
|
||||
job_log.info(f"Downloading user-provided lyrics file: {job.lyrics_file_gcs_path}")
|
||||
storage.download_file(job.lyrics_file_gcs_path, lyrics_file_path)
|
||||
job_log.info(f"User lyrics file downloaded to: {lyrics_file_path}")
|
||||
|
||||
# Get lyrics configuration from job
|
||||
subtitle_offset = getattr(job, 'subtitle_offset_ms', 0) or 0
|
||||
if subtitle_offset != 0:
|
||||
job_log.info(f"Subtitle offset: {subtitle_offset}ms")
|
||||
add_span_attribute("subtitle_offset_ms", subtitle_offset)
|
||||
|
||||
# Create LyricsProcessor instance (reuses karaoke_gen code)
|
||||
job_log.info("Creating LyricsProcessor instance...")
|
||||
job_log.info(f" style_params_json: {style_params_json_path}")
|
||||
job_log.info(f" lyrics_file: {lyrics_file_path}")
|
||||
job_log.info(f" subtitle_offset_ms: {subtitle_offset}")
|
||||
lyrics_processor = create_lyrics_processor(
|
||||
style_params_json=style_params_json_path,
|
||||
lyrics_file=lyrics_file_path,
|
||||
subtitle_offset_ms=subtitle_offset
|
||||
)
|
||||
|
||||
# Use lyrics_artist/lyrics_title overrides if provided, else fall back to job artist/title
|
||||
lyrics_search_artist = getattr(job, 'lyrics_artist', None) or job.artist
|
||||
lyrics_search_title = getattr(job, 'lyrics_title', None) or job.title
|
||||
|
||||
job_log.info("Starting LyricsTranscriber processing...")
|
||||
job_log.info(f" Artist: {job.artist}")
|
||||
job_log.info(f" Title: {job.title}")
|
||||
if lyrics_search_artist != job.artist:
|
||||
job_log.info(f" Lyrics search artist override: {lyrics_search_artist}")
|
||||
if lyrics_search_title != job.title:
|
||||
job_log.info(f" Lyrics search title override: {lyrics_search_title}")
|
||||
logger.info(f"[job:{job_id}] Calling lyrics_processor.transcribe_lyrics()")
|
||||
|
||||
# Run transcription + correction
|
||||
with job_span("audioshake-transcription", job_id) as trans_span:
|
||||
trans_start = time.time()
|
||||
add_span_event("transcription_started")
|
||||
|
||||
# Run transcription in thread pool to avoid blocking the event loop
|
||||
# (transcribe_lyrics is synchronous and takes 1-2 minutes)
|
||||
# Note: transcribe_lyrics internally calls AudioShake and lyrics APIs
|
||||
with metrics.time_external_api("audioshake", job_id):
|
||||
result = await asyncio.to_thread(
|
||||
lyrics_processor.transcribe_lyrics,
|
||||
input_audio_wav=audio_path,
|
||||
artist=job.artist, # Original artist for file naming
|
||||
title=job.title, # Original title for file naming
|
||||
track_output_dir=temp_dir,
|
||||
lyrics_artist=lyrics_search_artist, # Override for lyrics search
|
||||
lyrics_title=lyrics_search_title # Override for lyrics search
|
||||
)
|
||||
|
||||
trans_duration = time.time() - trans_start
|
||||
trans_span.set_attribute("duration_seconds", trans_duration)
|
||||
add_span_event("transcription_completed", {"duration_seconds": trans_duration})
|
||||
|
||||
job_log.info("Transcription processing complete")
|
||||
logger.info(f"[job:{job_id}] Transcription complete, uploading results")
|
||||
|
||||
# Upload lyrics results to GCS
|
||||
with job_span("upload-lyrics-results", job_id):
|
||||
job_log.info("Uploading lyrics results to GCS...")
|
||||
await upload_lyrics_results(job_id, temp_dir, result, storage, job_manager, job_log)
|
||||
|
||||
job_log.info("All lyrics data uploaded successfully")
|
||||
logger.info(f"[job:{job_id}] All lyrics data uploaded successfully")
|
||||
|
||||
# Update progress using state_data (don't change status during parallel processing)
|
||||
job_manager.update_state_data(job_id, 'lyrics_progress', {
|
||||
'stage': 'lyrics_complete',
|
||||
'progress': 45,
|
||||
'message': 'Lyrics transcription complete'
|
||||
})
|
||||
|
||||
# Mark lyrics processing complete
|
||||
# This will check if audio is also complete and transition to next stage if so
|
||||
job_log.info("Lyrics worker complete, checking if audio is also done...")
|
||||
job_manager.mark_lyrics_complete(job_id)
|
||||
|
||||
duration = time.time() - start_time
|
||||
root_span.set_attribute("duration_seconds", duration)
|
||||
logger.info(f"[job:{job_id}] WORKER_END worker=lyrics status=success duration={duration:.1f}s")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
duration = time.time() - start_time
|
||||
job_log.error(f"Lyrics transcription failed: {str(e)}", exc_info=True)
|
||||
logger.error(f"Job {job_id}: Lyrics transcription failed: {e}", exc_info=True)
|
||||
logger.error(f"[job:{job_id}] WORKER_END worker=lyrics status=error duration={duration:.1f}s error={e}")
|
||||
job_manager.mark_job_failed(
|
||||
job_id=job_id,
|
||||
error_message=f"Lyrics transcription failed: {str(e)}",
|
||||
@@ -273,7 +337,7 @@ async def process_lyrics_transcription(job_id: str) -> bool:
|
||||
# Cleanup temporary directory (only if it was created)
|
||||
if temp_dir and os.path.exists(temp_dir):
|
||||
shutil.rmtree(temp_dir)
|
||||
logger.debug(f"Cleaned up temp directory: {temp_dir}")
|
||||
logger.debug(f"[job:{job_id}] Cleaned up temp directory: {temp_dir}")
|
||||
|
||||
|
||||
async def download_audio(
|
||||
@@ -415,11 +479,24 @@ async def upload_lyrics_results(
|
||||
corrections_data = json.load(f)
|
||||
|
||||
# Store metadata in state_data
|
||||
job_manager.update_state_data(job_id, 'lyrics_metadata', {
|
||||
# Include countdown padding info for instrumental synchronization
|
||||
lyrics_metadata = {
|
||||
'segment_count': len(corrections_data.get('corrected_segments', [])),
|
||||
'has_corrections': True,
|
||||
'ready_for_review': True
|
||||
})
|
||||
'ready_for_review': True,
|
||||
}
|
||||
|
||||
# Add countdown padding info from transcription result
|
||||
# This is needed by video_worker to pad instrumentals for sync
|
||||
if transcription_result.get("countdown_padding_added"):
|
||||
lyrics_metadata['has_countdown_padding'] = True
|
||||
lyrics_metadata['countdown_padding_seconds'] = transcription_result.get("countdown_padding_seconds", 3.0)
|
||||
logger.info(f"Job {job_id}: Countdown padding detected: {lyrics_metadata['countdown_padding_seconds']}s")
|
||||
else:
|
||||
lyrics_metadata['has_countdown_padding'] = False
|
||||
lyrics_metadata['countdown_padding_seconds'] = 0.0
|
||||
|
||||
job_manager.update_state_data(job_id, 'lyrics_metadata', lyrics_metadata)
|
||||
except Exception as e:
|
||||
logger.warning(f"Job {job_id}: Could not parse corrections JSON: {e}")
|
||||
else:
|
||||
|
||||
@@ -14,10 +14,16 @@ This worker:
|
||||
Key insight: We use OutputGenerator from lyrics_transcriber library
|
||||
WITHOUT using its blocking ReviewServer. This allows async operation
|
||||
in Cloud Run.
|
||||
|
||||
Observability:
|
||||
- All operations wrapped in tracing spans for Cloud Trace visibility
|
||||
- Logs include [job:ID] prefix for easy filtering in Cloud Logging
|
||||
- Worker start/end timing logged with WORKER_START/WORKER_END markers
|
||||
"""
|
||||
import logging
|
||||
import os
|
||||
import tempfile
|
||||
import time
|
||||
import json
|
||||
from typing import Optional, Dict, Any
|
||||
from dataclasses import dataclass
|
||||
@@ -26,10 +32,12 @@ from backend.models.job import JobStatus
|
||||
from backend.services.job_manager import JobManager
|
||||
from backend.services.storage_service import StorageService
|
||||
from backend.config import get_settings
|
||||
from backend.workers.worker_logging import create_job_logger, setup_job_logging
|
||||
from backend.workers.worker_logging import create_job_logger, setup_job_logging, job_logging_context
|
||||
from backend.services.tracing import job_span, add_span_event, add_span_attribute
|
||||
|
||||
# Import from lyrics_transcriber (submodule)
|
||||
from lyrics_transcriber.output.generator import OutputGenerator
|
||||
from lyrics_transcriber.output.countdown_processor import CountdownProcessor
|
||||
from lyrics_transcriber.types import CorrectionResult
|
||||
from lyrics_transcriber.core.config import OutputConfig
|
||||
|
||||
@@ -62,12 +70,16 @@ async def process_render_video(job_id: str) -> bool:
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
start_time = time.time()
|
||||
job_manager = JobManager()
|
||||
storage = StorageService()
|
||||
settings = get_settings()
|
||||
|
||||
# Create job logger for remote debugging FIRST
|
||||
job_log = create_job_logger(job_id, "render_video")
|
||||
|
||||
# Log with structured markers for easy Cloud Logging queries
|
||||
logger.info(f"[job:{job_id}] WORKER_START worker=render-video")
|
||||
job_log.info("=== RENDER VIDEO WORKER STARTED ===")
|
||||
job_log.info(f"Job ID: {job_id}")
|
||||
|
||||
@@ -77,201 +89,267 @@ async def process_render_video(job_id: str) -> bool:
|
||||
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
logger.error(f"Job {job_id} not found")
|
||||
logger.error(f"[job:{job_id}] Job not found in Firestore")
|
||||
job_log.error(f"Job {job_id} not found in Firestore!")
|
||||
return False
|
||||
|
||||
job_log.info(f"Starting video render for {job.artist} - {job.title}")
|
||||
logger.info(f"Job {job_id}: Starting video render (post-review)")
|
||||
logger.info(f"[job:{job_id}] Starting video render (post-review)")
|
||||
|
||||
try:
|
||||
# Transition to RENDERING_VIDEO
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.RENDERING_VIDEO,
|
||||
progress=75,
|
||||
message="Rendering karaoke video with corrected lyrics"
|
||||
)
|
||||
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
job_log.info(f"Created temp directory: {temp_dir}")
|
||||
# 1. Download corrected corrections data
|
||||
corrections_path = os.path.join(temp_dir, "corrections.json")
|
||||
|
||||
# Try updated corrections first (from human review), fall back to original
|
||||
corrections_gcs_updated = f"jobs/{job_id}/lyrics/corrections_updated.json"
|
||||
corrections_gcs_original = f"jobs/{job_id}/lyrics/corrections.json"
|
||||
|
||||
# Get GCS path from file_urls
|
||||
corrections_url = job.file_urls.get('lyrics', {}).get('corrections_updated')
|
||||
if not corrections_url:
|
||||
corrections_url = job.file_urls.get('lyrics', {}).get('corrections')
|
||||
|
||||
if not corrections_url:
|
||||
# Try direct GCS paths
|
||||
if storage.file_exists(corrections_gcs_updated):
|
||||
corrections_gcs = corrections_gcs_updated
|
||||
elif storage.file_exists(corrections_gcs_original):
|
||||
corrections_gcs = corrections_gcs_original
|
||||
else:
|
||||
raise FileNotFoundError(f"No corrections file found for job {job_id}")
|
||||
else:
|
||||
# Extract GCS path from URL
|
||||
corrections_gcs = _extract_gcs_path(corrections_url)
|
||||
|
||||
# 2. Load the ORIGINAL corrections (has full structure)
|
||||
original_corrections_gcs = f"jobs/{job_id}/lyrics/corrections.json"
|
||||
original_corrections_path = os.path.join(temp_dir, "corrections_original.json")
|
||||
|
||||
job_log.info(f"Downloading original corrections from {original_corrections_gcs}")
|
||||
logger.info(f"Job {job_id}: Downloading original corrections from {original_corrections_gcs}")
|
||||
storage.download_file(original_corrections_gcs, original_corrections_path)
|
||||
|
||||
with open(original_corrections_path, 'r', encoding='utf-8') as f:
|
||||
original_data = json.load(f)
|
||||
|
||||
# 3. Check if there are updated corrections (from review UI)
|
||||
# The frontend sends only partial data: {corrections, corrected_segments}
|
||||
updated_corrections_gcs = f"jobs/{job_id}/lyrics/corrections_updated.json"
|
||||
|
||||
if storage.file_exists(updated_corrections_gcs):
|
||||
job_log.info("Found updated corrections from review, merging")
|
||||
logger.info(f"Job {job_id}: Found updated corrections, merging")
|
||||
updated_path = os.path.join(temp_dir, "corrections_updated.json")
|
||||
storage.download_file(updated_corrections_gcs, updated_path)
|
||||
# Wrap entire worker in a tracing span
|
||||
with job_span("render-video-worker", job_id, {"artist": job.artist, "title": job.title}) as root_span:
|
||||
# Use job_logging_context for proper log isolation when multiple jobs run concurrently
|
||||
# This ensures logs from third-party libraries (lyrics_transcriber.output) are only
|
||||
# captured by this job's handler, not handlers from other concurrent jobs
|
||||
with job_logging_context(job_id):
|
||||
# Transition to RENDERING_VIDEO
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.RENDERING_VIDEO,
|
||||
progress=75,
|
||||
message="Rendering karaoke video with corrected lyrics"
|
||||
)
|
||||
|
||||
with open(updated_path, 'r', encoding='utf-8') as f:
|
||||
updated_data = json.load(f)
|
||||
|
||||
# Merge: update the original with the user's corrections
|
||||
if 'corrections' in updated_data:
|
||||
original_data['corrections'] = updated_data['corrections']
|
||||
if 'corrected_segments' in updated_data:
|
||||
original_data['corrected_segments'] = updated_data['corrected_segments']
|
||||
|
||||
job_log.info("Merged user corrections into original data")
|
||||
logger.info(f"Job {job_id}: Merged user corrections into original data")
|
||||
|
||||
# 4. Convert to CorrectionResult
|
||||
correction_result = CorrectionResult.from_dict(original_data)
|
||||
job_log.info(f"Loaded CorrectionResult with {len(correction_result.corrected_segments)} segments")
|
||||
logger.info(f"Job {job_id}: Loaded CorrectionResult with {len(correction_result.corrected_segments)} segments")
|
||||
|
||||
# 3. Download audio file
|
||||
audio_path = os.path.join(temp_dir, "audio.flac")
|
||||
audio_gcs_path = job.input_media_gcs_path
|
||||
|
||||
if not audio_gcs_path:
|
||||
raise FileNotFoundError(f"No input audio path for job {job_id}")
|
||||
|
||||
job_log.info(f"Downloading audio from {audio_gcs_path}")
|
||||
logger.info(f"Job {job_id}: Downloading audio from {audio_gcs_path}")
|
||||
storage.download_file(audio_gcs_path, audio_path)
|
||||
job_log.info(f"Audio downloaded: {os.path.getsize(audio_path)} bytes")
|
||||
|
||||
# 4. Get or create styles using the unified style loader
|
||||
job_log.info("Loading style configuration...")
|
||||
job_log.info(f" job.style_params_gcs_path: {job.style_params_gcs_path}")
|
||||
job_log.info(f" job.style_assets: {list(job.style_assets.keys()) if job.style_assets else 'None'}")
|
||||
|
||||
styles_path, style_data = load_styles_from_gcs(
|
||||
style_params_gcs_path=job.style_params_gcs_path,
|
||||
style_assets=job.style_assets,
|
||||
temp_dir=temp_dir,
|
||||
download_func=storage.download_file,
|
||||
logger=job_log,
|
||||
)
|
||||
|
||||
# 5. Configure OutputGenerator
|
||||
output_dir = os.path.join(temp_dir, "output")
|
||||
cache_dir = os.path.join(temp_dir, "cache")
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
os.makedirs(cache_dir, exist_ok=True)
|
||||
|
||||
job_log.info(f"Using styles from: {styles_path}")
|
||||
|
||||
config = OutputConfig(
|
||||
output_dir=output_dir,
|
||||
cache_dir=cache_dir,
|
||||
output_styles_json=styles_path,
|
||||
render_video=True,
|
||||
generate_cdg=False, # CDG optional, generated separately
|
||||
generate_plain_text=True,
|
||||
generate_lrc=True,
|
||||
video_resolution="4k",
|
||||
subtitle_offset_ms=0
|
||||
)
|
||||
|
||||
job_log.info(f"OutputConfig: output_styles_json={config.output_styles_json}, render_video={config.render_video}")
|
||||
|
||||
output_generator = OutputGenerator(config, logger)
|
||||
|
||||
# 6. Generate outputs (video, LRC, ASS, etc.)
|
||||
output_prefix = f"{job.artist or 'Unknown'} - {job.title or 'Unknown'}"
|
||||
job_log.info(f"Generating outputs with prefix '{output_prefix}'")
|
||||
logger.info(f"Job {job_id}: Generating outputs with prefix '{output_prefix}'")
|
||||
|
||||
outputs = output_generator.generate_outputs(
|
||||
transcription_corrected=correction_result,
|
||||
lyrics_results={}, # Reference lyrics already in correction_result
|
||||
output_prefix=output_prefix,
|
||||
audio_filepath=audio_path,
|
||||
artist=job.artist,
|
||||
title=job.title
|
||||
)
|
||||
|
||||
# 7. Upload video to GCS
|
||||
if outputs.video and os.path.exists(outputs.video):
|
||||
video_size = os.path.getsize(outputs.video)
|
||||
job_log.info(f"Video generated: {video_size} bytes")
|
||||
video_gcs_path = f"jobs/{job_id}/videos/with_vocals.mkv"
|
||||
video_url = storage.upload_file(outputs.video, video_gcs_path)
|
||||
job_manager.update_file_url(job_id, 'videos', 'with_vocals', video_url)
|
||||
job_log.info(f"Uploaded with_vocals.mkv to GCS")
|
||||
logger.info(f"Job {job_id}: Uploaded with_vocals.mkv ({video_size} bytes)")
|
||||
else:
|
||||
job_log.error("Video generation failed - no output file produced!")
|
||||
raise Exception("Video generation failed - no output file produced")
|
||||
|
||||
# 8. Upload LRC file
|
||||
if outputs.lrc and os.path.exists(outputs.lrc):
|
||||
lrc_gcs_path = f"jobs/{job_id}/lyrics/karaoke.lrc"
|
||||
lrc_url = storage.upload_file(outputs.lrc, lrc_gcs_path)
|
||||
job_manager.update_file_url(job_id, 'lyrics', 'lrc', lrc_url)
|
||||
job_log.info("Uploaded karaoke.lrc")
|
||||
logger.info(f"Job {job_id}: Uploaded karaoke.lrc")
|
||||
|
||||
# 9. Upload ASS subtitle file
|
||||
if outputs.ass and os.path.exists(outputs.ass):
|
||||
ass_gcs_path = f"jobs/{job_id}/lyrics/karaoke.ass"
|
||||
ass_url = storage.upload_file(outputs.ass, ass_gcs_path)
|
||||
job_manager.update_file_url(job_id, 'lyrics', 'ass', ass_url)
|
||||
job_log.info("Uploaded karaoke.ass")
|
||||
logger.info(f"Job {job_id}: Uploaded karaoke.ass")
|
||||
|
||||
# 10. Upload corrected text files
|
||||
if outputs.corrected_txt and os.path.exists(outputs.corrected_txt):
|
||||
txt_gcs_path = f"jobs/{job_id}/lyrics/corrected.txt"
|
||||
txt_url = storage.upload_file(outputs.corrected_txt, txt_gcs_path)
|
||||
job_manager.update_file_url(job_id, 'lyrics', 'corrected_txt', txt_url)
|
||||
job_log.info("Uploaded corrected.txt")
|
||||
logger.info(f"Job {job_id}: Uploaded corrected.txt")
|
||||
|
||||
# 11. Transition to awaiting instrumental selection
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.AWAITING_INSTRUMENTAL_SELECTION,
|
||||
progress=80,
|
||||
message="Video rendered - select your instrumental"
|
||||
)
|
||||
|
||||
job_log.info("=== RENDER VIDEO WORKER COMPLETE ===")
|
||||
logger.info(f"Job {job_id}: Video render complete, awaiting instrumental selection")
|
||||
return True
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
job_log.info(f"Created temp directory: {temp_dir}")
|
||||
|
||||
# Try updated corrections first (from human review), fall back to original
|
||||
corrections_gcs_updated = f"jobs/{job_id}/lyrics/corrections_updated.json"
|
||||
corrections_gcs_original = f"jobs/{job_id}/lyrics/corrections.json"
|
||||
|
||||
# Get GCS path from file_urls
|
||||
corrections_url = job.file_urls.get('lyrics', {}).get('corrections_updated')
|
||||
if not corrections_url:
|
||||
corrections_url = job.file_urls.get('lyrics', {}).get('corrections')
|
||||
|
||||
if not corrections_url:
|
||||
# Try direct GCS paths
|
||||
if storage.file_exists(corrections_gcs_updated):
|
||||
corrections_gcs = corrections_gcs_updated
|
||||
elif storage.file_exists(corrections_gcs_original):
|
||||
corrections_gcs = corrections_gcs_original
|
||||
else:
|
||||
raise FileNotFoundError(f"No corrections file found for job {job_id}")
|
||||
else:
|
||||
# Extract GCS path from URL
|
||||
corrections_gcs = _extract_gcs_path(corrections_url)
|
||||
|
||||
# 2. Load the ORIGINAL corrections (has full structure)
|
||||
original_corrections_gcs = f"jobs/{job_id}/lyrics/corrections.json"
|
||||
original_corrections_path = os.path.join(temp_dir, "corrections_original.json")
|
||||
|
||||
job_log.info(f"Downloading original corrections from {original_corrections_gcs}")
|
||||
logger.info(f"Job {job_id}: Downloading original corrections from {original_corrections_gcs}")
|
||||
storage.download_file(original_corrections_gcs, original_corrections_path)
|
||||
|
||||
with open(original_corrections_path, 'r', encoding='utf-8') as f:
|
||||
original_data = json.load(f)
|
||||
|
||||
# 3. Check if there are updated corrections (from review UI)
|
||||
# The frontend sends only partial data: {corrections, corrected_segments}
|
||||
updated_corrections_gcs = f"jobs/{job_id}/lyrics/corrections_updated.json"
|
||||
|
||||
if storage.file_exists(updated_corrections_gcs):
|
||||
job_log.info("Found updated corrections from review, merging")
|
||||
logger.info(f"Job {job_id}: Found updated corrections, merging")
|
||||
updated_path = os.path.join(temp_dir, "corrections_updated.json")
|
||||
storage.download_file(updated_corrections_gcs, updated_path)
|
||||
|
||||
with open(updated_path, 'r', encoding='utf-8') as f:
|
||||
updated_data = json.load(f)
|
||||
|
||||
# Merge: update the original with the user's corrections
|
||||
if 'corrections' in updated_data:
|
||||
original_data['corrections'] = updated_data['corrections']
|
||||
if 'corrected_segments' in updated_data:
|
||||
original_data['corrected_segments'] = updated_data['corrected_segments']
|
||||
|
||||
job_log.info("Merged user corrections into original data")
|
||||
logger.info(f"Job {job_id}: Merged user corrections into original data")
|
||||
|
||||
# 4. Convert to CorrectionResult
|
||||
correction_result = CorrectionResult.from_dict(original_data)
|
||||
job_log.info(f"Loaded CorrectionResult with {len(correction_result.corrected_segments)} segments")
|
||||
logger.info(f"Job {job_id}: Loaded CorrectionResult with {len(correction_result.corrected_segments)} segments")
|
||||
|
||||
# 5. Download audio file
|
||||
audio_path = os.path.join(temp_dir, "audio.flac")
|
||||
audio_gcs_path = job.input_media_gcs_path
|
||||
|
||||
if not audio_gcs_path:
|
||||
raise FileNotFoundError(f"No input audio path for job {job_id}")
|
||||
|
||||
job_log.info(f"Downloading audio from {audio_gcs_path}")
|
||||
logger.info(f"Job {job_id}: Downloading audio from {audio_gcs_path}")
|
||||
storage.download_file(audio_gcs_path, audio_path)
|
||||
job_log.info(f"Audio downloaded: {os.path.getsize(audio_path)} bytes")
|
||||
|
||||
# Process countdown intro if needed (for songs that start too quickly)
|
||||
# This adds "3... 2... 1..." segment and pads audio with 3s silence
|
||||
# Note: Countdown is deferred to this stage (not during lyrics transcription)
|
||||
# so the review UI can show the original timing without the 3s shift
|
||||
countdown_processor = CountdownProcessor(cache_dir=temp_dir, logger=logger)
|
||||
correction_result, audio_path, padding_added, padding_seconds = countdown_processor.process(
|
||||
correction_result=correction_result,
|
||||
audio_filepath=audio_path,
|
||||
)
|
||||
if padding_added:
|
||||
job_log.info(f"Countdown added: {padding_seconds}s padding applied to audio and timestamps shifted")
|
||||
else:
|
||||
job_log.info("No countdown needed - song starts after 3 seconds")
|
||||
|
||||
# 6. Get or create styles using the unified style loader
|
||||
job_log.info("Loading style configuration...")
|
||||
job_log.info(f" job.style_params_gcs_path: {job.style_params_gcs_path}")
|
||||
job_log.info(f" job.style_assets: {list(job.style_assets.keys()) if job.style_assets else 'None'}")
|
||||
|
||||
styles_path, style_data = load_styles_from_gcs(
|
||||
style_params_gcs_path=job.style_params_gcs_path,
|
||||
style_assets=job.style_assets,
|
||||
temp_dir=temp_dir,
|
||||
download_func=storage.download_file,
|
||||
logger=job_log,
|
||||
)
|
||||
|
||||
# 7. Configure OutputGenerator
|
||||
output_dir = os.path.join(temp_dir, "output")
|
||||
cache_dir = os.path.join(temp_dir, "cache")
|
||||
os.makedirs(output_dir, exist_ok=True)
|
||||
os.makedirs(cache_dir, exist_ok=True)
|
||||
|
||||
job_log.info(f"Using styles from: {styles_path}")
|
||||
|
||||
# Get subtitle offset from job (user-specified timing adjustment)
|
||||
subtitle_offset = getattr(job, 'subtitle_offset_ms', 0) or 0
|
||||
if subtitle_offset != 0:
|
||||
job_log.info(f"Applying subtitle offset: {subtitle_offset}ms")
|
||||
|
||||
config = OutputConfig(
|
||||
output_dir=output_dir,
|
||||
cache_dir=cache_dir,
|
||||
output_styles_json=styles_path,
|
||||
render_video=True,
|
||||
generate_cdg=False, # CDG optional, generated separately
|
||||
generate_plain_text=True,
|
||||
generate_lrc=True,
|
||||
video_resolution="4k",
|
||||
subtitle_offset_ms=subtitle_offset
|
||||
)
|
||||
|
||||
job_log.info(f"OutputConfig: output_styles_json={config.output_styles_json}, render_video={config.render_video}")
|
||||
|
||||
output_generator = OutputGenerator(config, logger)
|
||||
|
||||
# 8. Generate outputs (video, LRC, ASS, etc.)
|
||||
output_prefix = f"{job.artist or 'Unknown'} - {job.title or 'Unknown'}"
|
||||
job_log.info(f"Generating outputs with prefix '{output_prefix}'")
|
||||
logger.info(f"Job {job_id}: Generating outputs with prefix '{output_prefix}'")
|
||||
|
||||
outputs = output_generator.generate_outputs(
|
||||
transcription_corrected=correction_result,
|
||||
lyrics_results={}, # Reference lyrics already in correction_result
|
||||
output_prefix=output_prefix,
|
||||
audio_filepath=audio_path,
|
||||
artist=job.artist,
|
||||
title=job.title
|
||||
)
|
||||
|
||||
# 9. Upload video to GCS
|
||||
if outputs.video and os.path.exists(outputs.video):
|
||||
video_size = os.path.getsize(outputs.video)
|
||||
job_log.info(f"Video generated: {video_size} bytes")
|
||||
video_gcs_path = f"jobs/{job_id}/videos/with_vocals.mkv"
|
||||
video_url = storage.upload_file(outputs.video, video_gcs_path)
|
||||
job_manager.update_file_url(job_id, 'videos', 'with_vocals', video_url)
|
||||
job_log.info(f"Uploaded with_vocals.mkv to GCS")
|
||||
logger.info(f"Job {job_id}: Uploaded with_vocals.mkv ({video_size} bytes)")
|
||||
else:
|
||||
job_log.error("Video generation failed - no output file produced!")
|
||||
raise Exception("Video generation failed - no output file produced")
|
||||
|
||||
# 10. Upload LRC file
|
||||
if outputs.lrc and os.path.exists(outputs.lrc):
|
||||
lrc_gcs_path = f"jobs/{job_id}/lyrics/karaoke.lrc"
|
||||
lrc_url = storage.upload_file(outputs.lrc, lrc_gcs_path)
|
||||
job_manager.update_file_url(job_id, 'lyrics', 'lrc', lrc_url)
|
||||
job_log.info("Uploaded karaoke.lrc")
|
||||
logger.info(f"Job {job_id}: Uploaded karaoke.lrc")
|
||||
|
||||
# 11. Upload ASS subtitle file
|
||||
if outputs.ass and os.path.exists(outputs.ass):
|
||||
ass_gcs_path = f"jobs/{job_id}/lyrics/karaoke.ass"
|
||||
ass_url = storage.upload_file(outputs.ass, ass_gcs_path)
|
||||
job_manager.update_file_url(job_id, 'lyrics', 'ass', ass_url)
|
||||
job_log.info("Uploaded karaoke.ass")
|
||||
logger.info(f"Job {job_id}: Uploaded karaoke.ass")
|
||||
|
||||
# 12. Upload corrected text files
|
||||
if outputs.corrected_txt and os.path.exists(outputs.corrected_txt):
|
||||
txt_gcs_path = f"jobs/{job_id}/lyrics/corrected.txt"
|
||||
txt_url = storage.upload_file(outputs.corrected_txt, txt_gcs_path)
|
||||
job_manager.update_file_url(job_id, 'lyrics', 'corrected_txt', txt_url)
|
||||
job_log.info("Uploaded corrected.txt")
|
||||
logger.info(f"Job {job_id}: Uploaded corrected.txt")
|
||||
|
||||
# 13. Analyze backing vocals for intelligent instrumental selection
|
||||
job_log.info("Analyzing backing vocals for instrumental selection...")
|
||||
await _analyze_backing_vocals(job_id, job_manager, storage, job_log)
|
||||
|
||||
# 14. Transition based on prep_only flag and existing instrumental
|
||||
if getattr(job, 'prep_only', False):
|
||||
# Prep-only mode: stop here and mark as prep complete
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.PREP_COMPLETE,
|
||||
progress=100,
|
||||
message="Prep phase complete - download outputs to continue locally"
|
||||
)
|
||||
job_log.info("=== RENDER VIDEO WORKER COMPLETE (PREP ONLY) ===")
|
||||
duration = time.time() - start_time
|
||||
root_span.set_attribute("duration_seconds", duration)
|
||||
root_span.set_attribute("prep_only", True)
|
||||
logger.info(f"[job:{job_id}] WORKER_END worker=render-video status=success duration={duration:.1f}s prep_only=true")
|
||||
elif getattr(job, 'existing_instrumental_gcs_path', None):
|
||||
# Existing instrumental provided - skip selection, auto-use it
|
||||
# Store selection as 'custom' to indicate user-provided instrumental
|
||||
job_manager.update_state_data(job_id, 'instrumental_selection', 'custom')
|
||||
job_log.info("Existing instrumental provided - skipping selection, using user-provided file")
|
||||
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.INSTRUMENTAL_SELECTED,
|
||||
progress=82,
|
||||
message="Using user-provided instrumental"
|
||||
)
|
||||
job_log.info("=== RENDER VIDEO WORKER COMPLETE (EXISTING INSTRUMENTAL) ===")
|
||||
duration = time.time() - start_time
|
||||
root_span.set_attribute("duration_seconds", duration)
|
||||
root_span.set_attribute("existing_instrumental", True)
|
||||
logger.info(f"[job:{job_id}] WORKER_END worker=render-video status=success duration={duration:.1f}s existing_instrumental=true")
|
||||
|
||||
# Trigger video worker directly since no user selection needed
|
||||
from backend.workers.video_worker import run_video_worker
|
||||
job_log.info("Triggering video worker for final encoding...")
|
||||
await run_video_worker(job_id, job_manager, storage)
|
||||
else:
|
||||
# Normal mode: proceed to instrumental selection
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.AWAITING_INSTRUMENTAL_SELECTION,
|
||||
progress=80,
|
||||
message="Video rendered - select your instrumental"
|
||||
)
|
||||
job_log.info("=== RENDER VIDEO WORKER COMPLETE ===")
|
||||
duration = time.time() - start_time
|
||||
root_span.set_attribute("duration_seconds", duration)
|
||||
logger.info(f"[job:{job_id}] WORKER_END worker=render-video status=success duration={duration:.1f}s")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
duration = time.time() - start_time
|
||||
job_log.error(f"Video render failed: {e}")
|
||||
logger.error(f"Job {job_id}: Video render failed: {e}", exc_info=True)
|
||||
logger.error(f"[job:{job_id}] WORKER_END worker=render-video status=error duration={duration:.1f}s error={e}")
|
||||
job_manager.fail_job(job_id, f"Video render failed: {str(e)}")
|
||||
return False
|
||||
|
||||
@@ -293,5 +371,109 @@ def _extract_gcs_path(url: str) -> str:
|
||||
return url
|
||||
|
||||
|
||||
async def _analyze_backing_vocals(
|
||||
job_id: str,
|
||||
job_manager: JobManager,
|
||||
storage: StorageService,
|
||||
job_log: logging.Logger,
|
||||
) -> None:
|
||||
"""
|
||||
Analyze backing vocals to help with intelligent instrumental selection.
|
||||
|
||||
This function:
|
||||
1. Downloads the backing vocals stem from GCS
|
||||
2. Runs audio analysis to detect audible content
|
||||
3. Generates a waveform visualization image
|
||||
4. Stores analysis results and waveform URL in job state
|
||||
|
||||
The analysis data is then used by the frontend to provide an
|
||||
intelligent instrumental selection experience.
|
||||
"""
|
||||
from backend.services.audio_analysis_service import AudioAnalysisService
|
||||
|
||||
try:
|
||||
# Get the job to access file URLs
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
job_log.warning(f"Could not get job {job_id} for backing vocals analysis")
|
||||
return
|
||||
|
||||
# Get backing vocals path
|
||||
backing_vocals_path = job.file_urls.get('stems', {}).get('backing_vocals')
|
||||
if not backing_vocals_path:
|
||||
job_log.warning("No backing vocals file found - skipping analysis")
|
||||
return
|
||||
|
||||
job_log.info(f"Analyzing backing vocals: {backing_vocals_path}")
|
||||
|
||||
# Create analysis service and run analysis
|
||||
analysis_service = AudioAnalysisService()
|
||||
|
||||
# Define output path for waveform
|
||||
waveform_gcs_path = f"jobs/{job_id}/analysis/backing_vocals_waveform.png"
|
||||
|
||||
# Run analysis and generate waveform
|
||||
result, waveform_path = analysis_service.analyze_and_generate_waveform(
|
||||
gcs_audio_path=backing_vocals_path,
|
||||
job_id=job_id,
|
||||
gcs_waveform_destination=waveform_gcs_path,
|
||||
)
|
||||
|
||||
# Store analysis results in job state_data
|
||||
analysis_data = {
|
||||
'has_audible_content': result.has_audible_content,
|
||||
'total_duration_seconds': result.total_duration_seconds,
|
||||
'audible_segments': [
|
||||
{
|
||||
'start_seconds': seg.start_seconds,
|
||||
'end_seconds': seg.end_seconds,
|
||||
'duration_seconds': seg.duration_seconds,
|
||||
'avg_amplitude_db': seg.avg_amplitude_db,
|
||||
'peak_amplitude_db': seg.peak_amplitude_db,
|
||||
}
|
||||
for seg in result.audible_segments
|
||||
],
|
||||
'recommended_selection': result.recommended_selection.value,
|
||||
'total_audible_duration_seconds': result.total_audible_duration_seconds,
|
||||
'audible_percentage': result.audible_percentage,
|
||||
'silence_threshold_db': result.silence_threshold_db,
|
||||
}
|
||||
|
||||
job_manager.update_state_data(job_id, 'backing_vocals_analysis', analysis_data)
|
||||
|
||||
# Store waveform URL
|
||||
job_manager.update_file_url(job_id, 'analysis', 'backing_vocals_waveform', waveform_path)
|
||||
|
||||
job_log.info(
|
||||
f"Backing vocals analysis complete: "
|
||||
f"has_audible={result.has_audible_content}, "
|
||||
f"segments={result.segment_count}, "
|
||||
f"recommendation={result.recommended_selection.value}"
|
||||
)
|
||||
|
||||
# Log segment details if there are any
|
||||
if result.audible_segments:
|
||||
job_log.info(f"Audible segments ({len(result.audible_segments)}):")
|
||||
for i, seg in enumerate(result.audible_segments[:5]): # Log first 5
|
||||
job_log.info(
|
||||
f" [{i+1}] {seg.start_seconds:.1f}s - {seg.end_seconds:.1f}s "
|
||||
f"({seg.duration_seconds:.1f}s, avg: {seg.avg_amplitude_db:.1f}dB)"
|
||||
)
|
||||
if len(result.audible_segments) > 5:
|
||||
job_log.info(f" ... and {len(result.audible_segments) - 5} more")
|
||||
|
||||
except Exception as e:
|
||||
# Log the error but don't fail the job - analysis is a nice-to-have
|
||||
job_log.warning(f"Backing vocals analysis failed (non-fatal): {e}")
|
||||
logger.warning(f"Job {job_id}: Backing vocals analysis failed: {e}")
|
||||
|
||||
# Store empty analysis so the frontend knows analysis was attempted
|
||||
job_manager.update_state_data(job_id, 'backing_vocals_analysis', {
|
||||
'has_audible_content': None,
|
||||
'analysis_error': str(e),
|
||||
'recommended_selection': 'review_needed',
|
||||
})
|
||||
|
||||
|
||||
# For compatibility with worker service
|
||||
render_video_worker = process_render_video
|
||||
@@ -16,17 +16,16 @@ processing complete (via mark_audio_complete/mark_lyrics_complete coordination).
|
||||
|
||||
Integrates with karaoke_gen.video_generator.VideoGenerator.
|
||||
|
||||
SOLID Principles:
|
||||
- Single Responsibility: Only generates title/end screens
|
||||
- Open/Closed: Extensible for different screen styles
|
||||
- Liskov Substitution: Can swap different video generators
|
||||
- Interface Segregation: Focused interface for screen generation
|
||||
- Dependency Inversion: Depends on abstractions (VideoGenerator interface)
|
||||
Observability:
|
||||
- All operations wrapped in tracing spans for Cloud Trace visibility
|
||||
- Logs include [job:ID] prefix for easy filtering in Cloud Logging
|
||||
- Worker start/end timing logged with WORKER_START/WORKER_END markers
|
||||
"""
|
||||
import logging
|
||||
import os
|
||||
import shutil
|
||||
import tempfile
|
||||
import time
|
||||
from typing import Optional, Dict, Any
|
||||
from pathlib import Path
|
||||
|
||||
@@ -35,7 +34,8 @@ from backend.services.job_manager import JobManager
|
||||
from backend.services.storage_service import StorageService
|
||||
from backend.config import get_settings
|
||||
from backend.workers.style_helper import load_style_config, StyleConfig
|
||||
from backend.workers.worker_logging import create_job_logger, setup_job_logging
|
||||
from backend.workers.worker_logging import create_job_logger, setup_job_logging, job_logging_context
|
||||
from backend.services.tracing import job_span, add_span_event, add_span_attribute
|
||||
|
||||
# Import from karaoke_gen package
|
||||
from karaoke_gen.video_generator import VideoGenerator
|
||||
@@ -64,6 +64,7 @@ async def generate_screens(job_id: str) -> bool:
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
start_time = time.time()
|
||||
job_manager = JobManager()
|
||||
storage = StorageService()
|
||||
settings = get_settings()
|
||||
@@ -71,114 +72,127 @@ async def generate_screens(job_id: str) -> bool:
|
||||
# Create job logger for remote debugging
|
||||
job_log = create_job_logger(job_id, "screens")
|
||||
|
||||
# Log with structured markers for easy Cloud Logging queries
|
||||
logger.info(f"[job:{job_id}] WORKER_START worker=screens")
|
||||
|
||||
# Set up log capture for VideoGenerator and style_helper
|
||||
log_handler = setup_job_logging(job_id, "screens", *SCREENS_WORKER_LOGGERS)
|
||||
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
logger.error(f"Job {job_id} not found")
|
||||
logger.error(f"[job:{job_id}] Job not found")
|
||||
return False
|
||||
|
||||
# Validate both audio and lyrics are complete
|
||||
if not _validate_prerequisites(job):
|
||||
logger.error(f"Job {job_id}: Prerequisites not met for screen generation")
|
||||
logger.error(f"[job:{job_id}] Prerequisites not met for screen generation")
|
||||
return False
|
||||
|
||||
# Create temporary working directory
|
||||
temp_dir = tempfile.mkdtemp(prefix=f"karaoke_screens_{job_id}_")
|
||||
|
||||
try:
|
||||
job_log.info(f"Starting screen generation for {job.artist} - {job.title}")
|
||||
logger.info(f"Starting screen generation for job {job_id}")
|
||||
|
||||
# Transition to GENERATING_SCREENS state
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.GENERATING_SCREENS,
|
||||
progress=50,
|
||||
message="Generating title and end screens"
|
||||
)
|
||||
|
||||
# Log style assets info
|
||||
style_assets = getattr(job, 'style_assets', {}) or {}
|
||||
job_log.info(f"Style assets from job: {list(style_assets.keys()) if style_assets else 'None'}")
|
||||
if style_assets:
|
||||
for key, path in style_assets.items():
|
||||
job_log.info(f" {key}: {path}")
|
||||
|
||||
# Load style configuration (downloads assets from GCS if available)
|
||||
job_log.info("Loading style configuration from GCS...")
|
||||
style_config = await load_style_config(job, storage, temp_dir)
|
||||
if style_config.has_custom_styles():
|
||||
job_log.info("Using CUSTOM style configuration")
|
||||
logger.info(f"Job {job_id}: Using custom style configuration")
|
||||
else:
|
||||
job_log.warning("Using DEFAULT style configuration (no custom styles found)")
|
||||
logger.info(f"Job {job_id}: Using default style configuration")
|
||||
|
||||
# Initialize video generator
|
||||
video_generator = _create_video_generator(temp_dir)
|
||||
|
||||
# Generate title screen with style config
|
||||
job_log.info("Generating title screen...")
|
||||
title_screen_path = await _generate_title_screen(
|
||||
job_id=job_id,
|
||||
job=job,
|
||||
video_generator=video_generator,
|
||||
style_config=style_config,
|
||||
temp_dir=temp_dir,
|
||||
job_log=job_log
|
||||
)
|
||||
|
||||
if not title_screen_path:
|
||||
raise Exception("Title screen generation failed")
|
||||
job_log.info(f"Title screen generated: {title_screen_path}")
|
||||
|
||||
# Generate end screen with style config
|
||||
job_log.info("Generating end screen...")
|
||||
end_screen_path = await _generate_end_screen(
|
||||
job_id=job_id,
|
||||
job=job,
|
||||
video_generator=video_generator,
|
||||
style_config=style_config,
|
||||
temp_dir=temp_dir,
|
||||
job_log=job_log
|
||||
)
|
||||
|
||||
if not end_screen_path:
|
||||
raise Exception("End screen generation failed")
|
||||
job_log.info(f"End screen generated: {end_screen_path}")
|
||||
|
||||
# Upload screens to GCS
|
||||
await _upload_screens(
|
||||
job_id=job_id,
|
||||
job_manager=job_manager,
|
||||
storage=storage,
|
||||
title_screen_path=title_screen_path,
|
||||
end_screen_path=end_screen_path
|
||||
)
|
||||
|
||||
# Apply countdown padding if needed
|
||||
# (This is handled automatically by checking lyrics metadata)
|
||||
await _apply_countdown_padding_if_needed(job_id, job_manager, job)
|
||||
|
||||
# Transition to AWAITING_REVIEW
|
||||
# Human must review lyrics before video can be rendered
|
||||
logger.info(f"Job {job_id}: Screens generated, awaiting lyrics review")
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.AWAITING_REVIEW,
|
||||
progress=55,
|
||||
message="Ready for lyrics review. Please review and correct lyrics."
|
||||
)
|
||||
|
||||
# TODO: Send notification to user that selection is needed
|
||||
# await notify_user(job_id, "instrumental_selection_ready")
|
||||
|
||||
return True
|
||||
# Wrap entire worker in a tracing span
|
||||
with job_span("screens-worker", job_id, {"artist": job.artist, "title": job.title}) as root_span:
|
||||
# Use job_logging_context for proper log isolation when multiple jobs run concurrently
|
||||
with job_logging_context(job_id):
|
||||
job_log.info(f"Starting screen generation for {job.artist} - {job.title}")
|
||||
logger.info(f"[job:{job_id}] Starting screen generation for {job.artist} - {job.title}")
|
||||
|
||||
# Transition to GENERATING_SCREENS state
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.GENERATING_SCREENS,
|
||||
progress=50,
|
||||
message="Generating title and end screens"
|
||||
)
|
||||
|
||||
# Log style assets info
|
||||
style_assets = getattr(job, 'style_assets', {}) or {}
|
||||
job_log.info(f"Style assets from job: {list(style_assets.keys()) if style_assets else 'None'}")
|
||||
if style_assets:
|
||||
for key, path in style_assets.items():
|
||||
job_log.info(f" {key}: {path}")
|
||||
|
||||
# Load style configuration (downloads assets from GCS if available)
|
||||
with job_span("load-style-config", job_id):
|
||||
job_log.info("Loading style configuration from GCS...")
|
||||
style_config = await load_style_config(job, storage, temp_dir)
|
||||
if style_config.has_custom_styles():
|
||||
job_log.info("Using CUSTOM style configuration")
|
||||
logger.info(f"[job:{job_id}] Using custom style configuration")
|
||||
add_span_attribute("style_type", "custom")
|
||||
else:
|
||||
job_log.warning("Using DEFAULT style configuration (no custom styles found)")
|
||||
logger.info(f"[job:{job_id}] Using default style configuration")
|
||||
add_span_attribute("style_type", "default")
|
||||
|
||||
# Initialize video generator
|
||||
video_generator = _create_video_generator(temp_dir)
|
||||
|
||||
# Generate title screen with style config
|
||||
with job_span("generate-title-screen", job_id):
|
||||
job_log.info("Generating title screen...")
|
||||
title_screen_path = await _generate_title_screen(
|
||||
job_id=job_id,
|
||||
job=job,
|
||||
video_generator=video_generator,
|
||||
style_config=style_config,
|
||||
temp_dir=temp_dir,
|
||||
job_log=job_log
|
||||
)
|
||||
|
||||
if not title_screen_path:
|
||||
raise Exception("Title screen generation failed")
|
||||
job_log.info(f"Title screen generated: {title_screen_path}")
|
||||
|
||||
# Generate end screen with style config
|
||||
with job_span("generate-end-screen", job_id):
|
||||
job_log.info("Generating end screen...")
|
||||
end_screen_path = await _generate_end_screen(
|
||||
job_id=job_id,
|
||||
job=job,
|
||||
video_generator=video_generator,
|
||||
style_config=style_config,
|
||||
temp_dir=temp_dir,
|
||||
job_log=job_log
|
||||
)
|
||||
|
||||
if not end_screen_path:
|
||||
raise Exception("End screen generation failed")
|
||||
job_log.info(f"End screen generated: {end_screen_path}")
|
||||
|
||||
# Upload screens to GCS
|
||||
with job_span("upload-screens", job_id):
|
||||
await _upload_screens(
|
||||
job_id=job_id,
|
||||
job_manager=job_manager,
|
||||
storage=storage,
|
||||
title_screen_path=title_screen_path,
|
||||
end_screen_path=end_screen_path
|
||||
)
|
||||
|
||||
# Apply countdown padding if needed
|
||||
await _apply_countdown_padding_if_needed(job_id, job_manager, job)
|
||||
|
||||
# Transition to AWAITING_REVIEW
|
||||
# Human must review lyrics before video can be rendered
|
||||
logger.info(f"[job:{job_id}] Screens generated, awaiting lyrics review")
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.AWAITING_REVIEW,
|
||||
progress=55,
|
||||
message="Ready for lyrics review. Please review and correct lyrics."
|
||||
)
|
||||
|
||||
duration = time.time() - start_time
|
||||
root_span.set_attribute("duration_seconds", duration)
|
||||
logger.info(f"[job:{job_id}] WORKER_END worker=screens status=success duration={duration:.1f}s")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Job {job_id}: Screen generation failed: {e}", exc_info=True)
|
||||
duration = time.time() - start_time
|
||||
logger.error(f"[job:{job_id}] WORKER_END worker=screens status=error duration={duration:.1f}s error={e}")
|
||||
job_manager.mark_job_failed(
|
||||
job_id=job_id,
|
||||
error_message=f"Screen generation failed: {str(e)}",
|
||||
@@ -197,7 +211,7 @@ async def generate_screens(job_id: str) -> bool:
|
||||
# Cleanup temporary directory
|
||||
if os.path.exists(temp_dir):
|
||||
shutil.rmtree(temp_dir)
|
||||
logger.debug(f"Cleaned up temp directory: {temp_dir}")
|
||||
logger.debug(f"[job:{job_id}] Cleaned up temp directory: {temp_dir}")
|
||||
|
||||
|
||||
def _validate_prerequisites(job) -> bool:
|
||||
|
||||
+301
-157
@@ -15,11 +15,17 @@ The worker's job is simply to:
|
||||
4. Upload results back to GCS
|
||||
|
||||
This reuses 100% of the existing karaoke_gen functionality.
|
||||
|
||||
Observability:
|
||||
- All operations wrapped in tracing spans for Cloud Trace visibility
|
||||
- Logs include [job:ID] prefix for easy filtering in Cloud Logging
|
||||
- Worker start/end timing logged with WORKER_START/WORKER_END markers
|
||||
"""
|
||||
import logging
|
||||
import os
|
||||
import shutil
|
||||
import tempfile
|
||||
import time
|
||||
import json
|
||||
from typing import Optional, Dict, Any
|
||||
from pathlib import Path
|
||||
@@ -31,7 +37,8 @@ from backend.services.rclone_service import get_rclone_service
|
||||
from backend.services.youtube_service import get_youtube_service
|
||||
from backend.config import get_settings
|
||||
from backend.workers.style_helper import load_style_config
|
||||
from backend.workers.worker_logging import create_job_logger, setup_job_logging
|
||||
from backend.workers.worker_logging import create_job_logger, setup_job_logging, job_logging_context
|
||||
from backend.services.tracing import job_span, add_span_event, add_span_attribute
|
||||
|
||||
# Import from karaoke_gen package - reuse existing implementation
|
||||
from karaoke_gen.karaoke_finalise.karaoke_finalise import KaraokeFinalise
|
||||
@@ -61,6 +68,7 @@ async def generate_video(job_id: str) -> bool:
|
||||
Returns:
|
||||
True if successful, False otherwise
|
||||
"""
|
||||
start_time = time.time()
|
||||
job_manager = JobManager()
|
||||
storage = StorageService()
|
||||
settings = get_settings()
|
||||
@@ -68,17 +76,20 @@ async def generate_video(job_id: str) -> bool:
|
||||
# Create job logger for remote debugging
|
||||
job_log = create_job_logger(job_id, "video")
|
||||
|
||||
# Log with structured markers for easy Cloud Logging queries
|
||||
logger.info(f"[job:{job_id}] WORKER_START worker=video")
|
||||
|
||||
# Set up log capture for KaraokeFinalise
|
||||
log_handler = setup_job_logging(job_id, "video", *VIDEO_WORKER_LOGGERS)
|
||||
|
||||
job = job_manager.get_job(job_id)
|
||||
if not job:
|
||||
logger.error(f"Job {job_id} not found")
|
||||
logger.error(f"[job:{job_id}] Job not found")
|
||||
return False
|
||||
|
||||
# Validate prerequisites
|
||||
if not _validate_prerequisites(job):
|
||||
logger.error(f"Job {job_id}: Prerequisites not met for video generation")
|
||||
logger.error(f"[job:{job_id}] Prerequisites not met for video generation")
|
||||
return False
|
||||
|
||||
# Create temporary working directory
|
||||
@@ -105,152 +116,198 @@ async def generate_video(job_id: str) -> bool:
|
||||
job_log.warning("YouTube credentials not available - upload will be skipped")
|
||||
|
||||
try:
|
||||
job_log.info(f"Starting video finalization for {job.artist} - {job.title}")
|
||||
logger.info(f"Starting video generation for job {job_id}")
|
||||
|
||||
# Transition to GENERATING_VIDEO state
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.GENERATING_VIDEO,
|
||||
progress=70,
|
||||
message="Preparing files for video generation"
|
||||
)
|
||||
|
||||
# Download and set up files in the format KaraokeFinalise expects
|
||||
base_name = f"{job.artist} - {job.title}"
|
||||
job_log.info("Downloading files from GCS (this may take a few minutes for large files)...")
|
||||
await _setup_working_directory(job_id, job, storage, temp_dir, base_name, job_log)
|
||||
job_log.info("All files downloaded successfully")
|
||||
|
||||
# Load style config for CDG styles
|
||||
job_log.info("Loading CDG style configuration...")
|
||||
style_config = await load_style_config(job, storage, temp_dir)
|
||||
cdg_styles = style_config.get_cdg_styles()
|
||||
if cdg_styles:
|
||||
job_log.info("CDG styles loaded from custom configuration")
|
||||
else:
|
||||
job_log.info("Using default CDG styles")
|
||||
|
||||
# Change to working directory (KaraokeFinalise works in cwd)
|
||||
os.chdir(temp_dir)
|
||||
|
||||
# Get the selected instrumental file path
|
||||
instrumental_selection = job.state_data['instrumental_selection']
|
||||
instrumental_suffix = "Clean" if instrumental_selection == 'clean' else "Backing"
|
||||
instrumental_file = os.path.join(temp_dir, f"{base_name} (Instrumental {instrumental_suffix}).flac")
|
||||
|
||||
# Transition to encoding state
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.ENCODING,
|
||||
progress=75,
|
||||
message="Encoding videos (15-20 min)"
|
||||
)
|
||||
|
||||
# Log finalization parameters
|
||||
job_log.info("Creating KaraokeFinalise with parameters:")
|
||||
job_log.info(f" enable_cdg: {getattr(job, 'enable_cdg', False)}")
|
||||
job_log.info(f" enable_txt: {getattr(job, 'enable_txt', False)}")
|
||||
job_log.info(f" brand_prefix: {getattr(job, 'brand_prefix', None)}")
|
||||
job_log.info(f" discord_webhook: {'configured' if getattr(job, 'discord_webhook_url', None) else 'not configured'}")
|
||||
job_log.info(f" instrumental: {instrumental_selection}")
|
||||
|
||||
# Create KaraokeFinalise with ALL the parameters from the job
|
||||
# This reuses all existing functionality!
|
||||
|
||||
# Set up YouTube description file if template is provided
|
||||
youtube_desc_path = None
|
||||
if youtube_credentials and getattr(job, 'youtube_description_template', None):
|
||||
youtube_desc_path = os.path.join(temp_dir, "youtube_description.txt")
|
||||
with open(youtube_desc_path, 'w') as f:
|
||||
f.write(job.youtube_description_template)
|
||||
job_log.info("YouTube description template written to temp file")
|
||||
|
||||
finalise = KaraokeFinalise(
|
||||
logger=logger,
|
||||
log_level=logging.INFO,
|
||||
dry_run=False,
|
||||
instrumental_format="flac",
|
||||
# CDG/TXT generation
|
||||
enable_cdg=getattr(job, 'enable_cdg', False),
|
||||
enable_txt=getattr(job, 'enable_txt', False),
|
||||
cdg_styles=cdg_styles,
|
||||
# Brand code and organization (server-side mode uses rclone)
|
||||
brand_prefix=getattr(job, 'brand_prefix', None),
|
||||
organised_dir=None, # Not used in cloud - files stay in GCS
|
||||
organised_dir_rclone_root=getattr(job, 'organised_dir_rclone_root', None),
|
||||
public_share_dir=None, # Not used in cloud
|
||||
# Notifications
|
||||
discord_webhook_url=getattr(job, 'discord_webhook_url', None),
|
||||
# YouTube upload (server-side with pre-loaded credentials)
|
||||
youtube_client_secrets_file=None, # Not used with pre-stored credentials
|
||||
youtube_description_file=youtube_desc_path,
|
||||
user_youtube_credentials=youtube_credentials, # Pre-loaded from Secret Manager
|
||||
rclone_destination=None,
|
||||
email_template_file=None,
|
||||
# Server-side optimizations
|
||||
non_interactive=True,
|
||||
server_side_mode=True,
|
||||
selected_instrumental_file=instrumental_file,
|
||||
)
|
||||
|
||||
# Call process() - this does ALL the work:
|
||||
# - Encodes to 4 video formats
|
||||
# - Generates CDG/TXT packages if enabled
|
||||
# - Posts Discord notification if configured
|
||||
# - Handles brand code generation
|
||||
job_log.info("Starting KaraokeFinalise.process() - this may take 15-20 minutes...")
|
||||
logger.info(f"Job {job_id}: Starting KaraokeFinalise.process()")
|
||||
result = finalise.process()
|
||||
|
||||
job_log.info("KaraokeFinalise.process() complete!")
|
||||
if result.get('brand_code'):
|
||||
job_log.info(f"Brand code: {result.get('brand_code')}")
|
||||
logger.info(f"Job {job_id}: KaraokeFinalise.process() complete")
|
||||
logger.info(f"Job {job_id}: Brand code: {result.get('brand_code')}")
|
||||
|
||||
# Native API distribution uploads (used by remote CLI instead of rclone)
|
||||
await _handle_native_distribution(
|
||||
job_id=job_id,
|
||||
job=job,
|
||||
job_log=job_log,
|
||||
job_manager=job_manager,
|
||||
temp_dir=temp_dir,
|
||||
result=result,
|
||||
)
|
||||
|
||||
# Upload generated files to GCS
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.PACKAGING,
|
||||
progress=95,
|
||||
message="Uploading final files"
|
||||
)
|
||||
|
||||
await _upload_results(job_id, job_manager, storage, temp_dir, result)
|
||||
|
||||
# Mark job as complete
|
||||
logger.info(f"Job {job_id}: Video generation complete")
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.COMPLETE,
|
||||
progress=100,
|
||||
message="Karaoke generation complete!"
|
||||
)
|
||||
|
||||
# Store result metadata in job
|
||||
job_manager.update_job(job_id, {
|
||||
'state_data': {
|
||||
**job.state_data,
|
||||
'brand_code': result.get('brand_code'),
|
||||
'youtube_url': result.get('youtube_url'),
|
||||
}
|
||||
})
|
||||
|
||||
return True
|
||||
# Wrap entire worker in a tracing span
|
||||
with job_span("video-worker", job_id, {"artist": job.artist, "title": job.title}) as root_span:
|
||||
# Use job_logging_context for proper log isolation when multiple jobs run concurrently
|
||||
# This ensures logs from third-party libraries (karaoke_gen.karaoke_finalise) are only
|
||||
# captured by this job's handler, not handlers from other concurrent jobs
|
||||
with job_logging_context(job_id):
|
||||
job_log.info(f"Starting video finalization for {job.artist} - {job.title}")
|
||||
logger.info(f"[job:{job_id}] Starting video generation for {job.artist} - {job.title}")
|
||||
|
||||
# Transition to GENERATING_VIDEO state
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.GENERATING_VIDEO,
|
||||
progress=70,
|
||||
message="Preparing files for video generation"
|
||||
)
|
||||
|
||||
# Download and set up files in the format KaraokeFinalise expects
|
||||
base_name = f"{job.artist} - {job.title}"
|
||||
with job_span("download-files", job_id):
|
||||
job_log.info("Downloading files from GCS (this may take a few minutes for large files)...")
|
||||
await _setup_working_directory(job_id, job, storage, temp_dir, base_name, job_log)
|
||||
job_log.info("All files downloaded successfully")
|
||||
|
||||
# Load style config for CDG styles
|
||||
job_log.info("Loading CDG style configuration...")
|
||||
style_config = await load_style_config(job, storage, temp_dir)
|
||||
cdg_styles = style_config.get_cdg_styles()
|
||||
if cdg_styles:
|
||||
job_log.info("CDG styles loaded from custom configuration")
|
||||
else:
|
||||
job_log.info("Using default CDG styles")
|
||||
|
||||
# Change to working directory (KaraokeFinalise works in cwd)
|
||||
os.chdir(temp_dir)
|
||||
|
||||
# Get the selected instrumental file path
|
||||
# Batch 3: If user provided existing instrumental, use that; otherwise use AI-separated
|
||||
instrumental_selection = job.state_data['instrumental_selection']
|
||||
existing_instrumental_path = getattr(job, 'existing_instrumental_gcs_path', None)
|
||||
|
||||
if existing_instrumental_path:
|
||||
# User provided existing instrumental
|
||||
ext = Path(existing_instrumental_path).suffix.lower()
|
||||
instrumental_file = os.path.join(temp_dir, f"{base_name} (Instrumental User){ext}")
|
||||
instrumental_source = "user-provided"
|
||||
else:
|
||||
# Use AI-separated instrumental
|
||||
instrumental_suffix = "Clean" if instrumental_selection == 'clean' else "Backing"
|
||||
instrumental_file = os.path.join(temp_dir, f"{base_name} (Instrumental {instrumental_suffix}).flac")
|
||||
instrumental_source = instrumental_selection
|
||||
|
||||
# Transition to encoding state
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.ENCODING,
|
||||
progress=75,
|
||||
message="Encoding videos (15-20 min)"
|
||||
)
|
||||
|
||||
# Get countdown padding info from lyrics metadata
|
||||
# This ensures instrumental is padded to match vocals if countdown was added
|
||||
lyrics_metadata = job.state_data.get('lyrics_metadata', {})
|
||||
countdown_padding_seconds = None
|
||||
if lyrics_metadata.get('has_countdown_padding'):
|
||||
countdown_padding_seconds = lyrics_metadata.get('countdown_padding_seconds', 3.0)
|
||||
job_log.info(f"Countdown padding detected: {countdown_padding_seconds}s - instrumental will be padded if needed")
|
||||
|
||||
# Log finalization parameters
|
||||
job_log.info("Creating KaraokeFinalise with parameters:")
|
||||
job_log.info(f" enable_cdg: {getattr(job, 'enable_cdg', False)}")
|
||||
job_log.info(f" enable_txt: {getattr(job, 'enable_txt', False)}")
|
||||
job_log.info(f" brand_prefix: {getattr(job, 'brand_prefix', None)}")
|
||||
job_log.info(f" discord_webhook: {'configured' if getattr(job, 'discord_webhook_url', None) else 'not configured'}")
|
||||
job_log.info(f" instrumental source: {instrumental_source}")
|
||||
job_log.info(f" countdown_padding_seconds: {countdown_padding_seconds}")
|
||||
if existing_instrumental_path:
|
||||
job_log.info(f" using user-provided instrumental (selection was: {instrumental_selection})")
|
||||
|
||||
# Create KaraokeFinalise with ALL the parameters from the job
|
||||
# This reuses all existing functionality!
|
||||
|
||||
# Set up YouTube description file if template is provided
|
||||
youtube_desc_path = None
|
||||
if youtube_credentials and getattr(job, 'youtube_description_template', None):
|
||||
youtube_desc_path = os.path.join(temp_dir, "youtube_description.txt")
|
||||
with open(youtube_desc_path, 'w') as f:
|
||||
f.write(job.youtube_description_template)
|
||||
job_log.info("YouTube description template written to temp file")
|
||||
|
||||
finalise = KaraokeFinalise(
|
||||
logger=logger,
|
||||
log_level=logging.INFO,
|
||||
dry_run=False,
|
||||
instrumental_format="flac",
|
||||
# CDG/TXT generation
|
||||
enable_cdg=getattr(job, 'enable_cdg', False),
|
||||
enable_txt=getattr(job, 'enable_txt', False),
|
||||
cdg_styles=cdg_styles,
|
||||
# Brand code and organization (server-side mode uses rclone)
|
||||
brand_prefix=getattr(job, 'brand_prefix', None),
|
||||
organised_dir=None, # Not used in cloud - files stay in GCS
|
||||
organised_dir_rclone_root=getattr(job, 'organised_dir_rclone_root', None),
|
||||
public_share_dir=None, # Not used in cloud
|
||||
# Notifications
|
||||
discord_webhook_url=getattr(job, 'discord_webhook_url', None),
|
||||
# YouTube upload (server-side with pre-loaded credentials)
|
||||
youtube_client_secrets_file=None, # Not used with pre-stored credentials
|
||||
youtube_description_file=youtube_desc_path,
|
||||
user_youtube_credentials=youtube_credentials, # Pre-loaded from Secret Manager
|
||||
rclone_destination=None,
|
||||
email_template_file=None,
|
||||
# Server-side optimizations
|
||||
non_interactive=True,
|
||||
server_side_mode=True,
|
||||
selected_instrumental_file=instrumental_file,
|
||||
# Audio synchronization - ensure instrumental matches vocal padding
|
||||
countdown_padding_seconds=countdown_padding_seconds,
|
||||
)
|
||||
|
||||
# Call process() - this does ALL the work:
|
||||
# - Encodes to 4 video formats
|
||||
# - Generates CDG/TXT packages if enabled
|
||||
# - Posts Discord notification if configured
|
||||
# - Handles brand code generation
|
||||
with job_span("karaoke-finalise", job_id) as finalise_span:
|
||||
finalise_start = time.time()
|
||||
job_log.info("Starting KaraokeFinalise.process() - this may take 15-20 minutes...")
|
||||
logger.info(f"[job:{job_id}] Starting KaraokeFinalise.process()")
|
||||
add_span_event("finalise_started")
|
||||
|
||||
result = finalise.process()
|
||||
|
||||
finalise_duration = time.time() - finalise_start
|
||||
finalise_span.set_attribute("duration_seconds", finalise_duration)
|
||||
add_span_event("finalise_completed", {"duration_seconds": finalise_duration})
|
||||
|
||||
job_log.info("KaraokeFinalise.process() complete!")
|
||||
if result.get('brand_code'):
|
||||
job_log.info(f"Brand code: {result.get('brand_code')}")
|
||||
logger.info(f"[job:{job_id}] KaraokeFinalise.process() complete in {finalise_duration:.1f}s")
|
||||
logger.info(f"[job:{job_id}] Brand code: {result.get('brand_code')}")
|
||||
|
||||
# Native API distribution uploads (used by remote CLI instead of rclone)
|
||||
with job_span("distribution", job_id):
|
||||
await _handle_native_distribution(
|
||||
job_id=job_id,
|
||||
job=job,
|
||||
job_log=job_log,
|
||||
job_manager=job_manager,
|
||||
temp_dir=temp_dir,
|
||||
result=result,
|
||||
)
|
||||
|
||||
# Upload generated files to GCS
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.PACKAGING,
|
||||
progress=95,
|
||||
message="Uploading final files"
|
||||
)
|
||||
|
||||
with job_span("upload-results", job_id):
|
||||
await _upload_results(job_id, job_manager, storage, temp_dir, result)
|
||||
|
||||
# Mark job as complete
|
||||
logger.info(f"[job:{job_id}] Video generation complete")
|
||||
job_manager.transition_to_state(
|
||||
job_id=job_id,
|
||||
new_status=JobStatus.COMPLETE,
|
||||
progress=100,
|
||||
message="Karaoke generation complete!"
|
||||
)
|
||||
|
||||
# Store result metadata in job
|
||||
job_manager.update_job(job_id, {
|
||||
'state_data': {
|
||||
**job.state_data,
|
||||
'brand_code': result.get('brand_code'),
|
||||
'youtube_url': result.get('youtube_url'),
|
||||
}
|
||||
})
|
||||
|
||||
duration = time.time() - start_time
|
||||
root_span.set_attribute("duration_seconds", duration)
|
||||
root_span.set_attribute("brand_code", result.get('brand_code', ''))
|
||||
logger.info(f"[job:{job_id}] WORKER_END worker=video status=success duration={duration:.1f}s")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Job {job_id}: Video generation failed: {e}", exc_info=True)
|
||||
duration = time.time() - start_time
|
||||
logger.error(f"[job:{job_id}] WORKER_END worker=video status=error duration={duration:.1f}s error={e}")
|
||||
job_manager.mark_job_failed(
|
||||
job_id=job_id,
|
||||
error_message=f"Video generation failed: {str(e)}",
|
||||
@@ -307,6 +364,13 @@ async def _handle_native_distribution(
|
||||
brand_code = result.get('brand_code')
|
||||
base_name = f"{job.artist} - {job.title}"
|
||||
|
||||
# Check if we should preserve existing brand code (Batch 6: --keep-brand-code)
|
||||
keep_brand_code = getattr(job, 'keep_brand_code', None)
|
||||
if keep_brand_code:
|
||||
brand_code = keep_brand_code
|
||||
result['brand_code'] = brand_code
|
||||
job_log.info(f"Using preserved brand code: {brand_code}")
|
||||
|
||||
# Upload to Dropbox using native SDK
|
||||
dropbox_path = getattr(job, 'dropbox_path', None)
|
||||
brand_prefix = getattr(job, 'brand_prefix', None)
|
||||
@@ -414,7 +478,8 @@ def _validate_prerequisites(job) -> bool:
|
||||
logger.error(f"Job {job.job_id}: No instrumental selected")
|
||||
return False
|
||||
|
||||
if instrumental_selection not in ['clean', 'with_backing']:
|
||||
# 'custom' is valid when user provided existing_instrumental
|
||||
if instrumental_selection not in ['clean', 'with_backing', 'custom']:
|
||||
logger.error(f"Job {job.job_id}: Invalid instrumental selection: {instrumental_selection}")
|
||||
return False
|
||||
|
||||
@@ -430,7 +495,14 @@ def _validate_prerequisites(job) -> bool:
|
||||
logger.error(f"Job {job.job_id}: Missing lyrics video")
|
||||
return False
|
||||
|
||||
# Check instrumental exists
|
||||
# Check instrumental exists - for 'custom', check existing_instrumental_gcs_path instead of stems
|
||||
if instrumental_selection == 'custom':
|
||||
existing_instrumental_path = getattr(job, 'existing_instrumental_gcs_path', None)
|
||||
if not existing_instrumental_path:
|
||||
logger.error(f"Job {job.job_id}: Custom instrumental selected but no existing_instrumental_gcs_path")
|
||||
return False
|
||||
return True # Other stem checks not needed for custom instrumental
|
||||
|
||||
stems = job.file_urls.get('stems', {})
|
||||
instrumental_key = 'instrumental_clean' if instrumental_selection == 'clean' else 'instrumental_with_backing'
|
||||
if not stems.get(instrumental_key):
|
||||
@@ -487,15 +559,26 @@ async def _setup_working_directory(
|
||||
storage.download_file(lyrics_video_url, lyrics_video_path)
|
||||
log_progress("Downloaded karaoke video")
|
||||
|
||||
# Download selected instrumental
|
||||
# Download instrumental - either user-provided existing instrumental or AI-separated
|
||||
existing_instrumental_path = getattr(job, 'existing_instrumental_gcs_path', None)
|
||||
instrumental_selection = job.state_data['instrumental_selection']
|
||||
instrumental_key = 'instrumental_clean' if instrumental_selection == 'clean' else 'instrumental_with_backing'
|
||||
instrumental_url = job.file_urls['stems'][instrumental_key]
|
||||
instrumental_suffix = "Clean" if instrumental_selection == 'clean' else "Backing"
|
||||
instrumental_path = os.path.join(temp_dir, f"{base_name} (Instrumental {instrumental_suffix}).flac")
|
||||
log_progress(f"Downloading {instrumental_selection} instrumental audio...")
|
||||
storage.download_file(instrumental_url, instrumental_path)
|
||||
log_progress(f"Downloaded instrumental ({instrumental_selection})")
|
||||
|
||||
if existing_instrumental_path:
|
||||
# Batch 3: Use user-provided existing instrumental
|
||||
ext = Path(existing_instrumental_path).suffix.lower()
|
||||
instrumental_path = os.path.join(temp_dir, f"{base_name} (Instrumental User){ext}")
|
||||
log_progress(f"Downloading user-provided existing instrumental...")
|
||||
storage.download_file(existing_instrumental_path, instrumental_path)
|
||||
log_progress("Downloaded user-provided instrumental")
|
||||
else:
|
||||
# Use AI-separated instrumental based on selection
|
||||
instrumental_key = 'instrumental_clean' if instrumental_selection == 'clean' else 'instrumental_with_backing'
|
||||
instrumental_url = job.file_urls['stems'][instrumental_key]
|
||||
instrumental_suffix = "Clean" if instrumental_selection == 'clean' else "Backing"
|
||||
instrumental_path = os.path.join(temp_dir, f"{base_name} (Instrumental {instrumental_suffix}).flac")
|
||||
log_progress(f"Downloading {instrumental_selection} instrumental audio...")
|
||||
storage.download_file(instrumental_url, instrumental_path)
|
||||
log_progress(f"Downloaded instrumental ({instrumental_selection})")
|
||||
|
||||
# Download LRC file if available (needed for CDG/TXT)
|
||||
lyrics_urls = job.file_urls.get('lyrics', {})
|
||||
@@ -549,3 +632,64 @@ async def _upload_results(
|
||||
logger.info(f"Job {job_id}: Uploaded {file_key}")
|
||||
except Exception as e:
|
||||
logger.error(f"Job {job_id}: Failed to upload {file_key}: {e}")
|
||||
|
||||
|
||||
# ==================== CLI Entry Point for Cloud Run Jobs ====================
|
||||
# This allows the video worker to be run as a standalone Cloud Run Job.
|
||||
# Usage: python -m backend.workers.video_worker --job-id <job_id>
|
||||
|
||||
def main():
|
||||
"""
|
||||
CLI entry point for running video worker as a Cloud Run Job.
|
||||
|
||||
This is used when video encoding needs more than 30 minutes
|
||||
(the Cloud Tasks timeout limit). Cloud Run Jobs support up to 24 hours.
|
||||
|
||||
Usage:
|
||||
python -m backend.workers.video_worker --job-id abc123
|
||||
|
||||
Environment Variables:
|
||||
GOOGLE_CLOUD_PROJECT: GCP project ID (required)
|
||||
GCS_BUCKET_NAME: Storage bucket name (required)
|
||||
"""
|
||||
import argparse
|
||||
import asyncio
|
||||
import sys
|
||||
|
||||
# Set up argument parser
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Video encoding worker for karaoke generation"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--job-id",
|
||||
required=True,
|
||||
help="Job ID to process"
|
||||
)
|
||||
|
||||
args = parser.parse_args()
|
||||
job_id = args.job_id
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
|
||||
)
|
||||
|
||||
logger.info(f"Starting video worker CLI for job {job_id}")
|
||||
|
||||
# Run the async worker function
|
||||
try:
|
||||
success = asyncio.run(generate_video(job_id))
|
||||
if success:
|
||||
logger.info(f"Video generation completed successfully for job {job_id}")
|
||||
sys.exit(0)
|
||||
else:
|
||||
logger.error(f"Video generation failed for job {job_id}")
|
||||
sys.exit(1)
|
||||
except Exception as e:
|
||||
logger.error(f"Video worker crashed: {e}", exc_info=True)
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -7,11 +7,48 @@ for remote debugging via the CLI.
|
||||
Two approaches are provided:
|
||||
1. JobLogger - A custom logger class for explicit logging in workers
|
||||
2. JobLogHandler - A logging.Handler that captures logs from any logger (including dependencies)
|
||||
|
||||
IMPORTANT: Uses contextvars to ensure log isolation between concurrent jobs.
|
||||
When multiple jobs run in parallel on the same Cloud Run instance, each job's
|
||||
worker logs are correctly filtered to only include logs from that job.
|
||||
"""
|
||||
import contextvars
|
||||
import logging
|
||||
from contextlib import contextmanager
|
||||
from typing import Optional, Set
|
||||
|
||||
|
||||
# Context variable to track the current job being processed
|
||||
# This is used to filter logs when multiple jobs run concurrently
|
||||
_current_job_id: contextvars.ContextVar[Optional[str]] = contextvars.ContextVar(
|
||||
'current_job_id', default=None
|
||||
)
|
||||
|
||||
|
||||
@contextmanager
|
||||
def job_logging_context(job_id: str):
|
||||
"""
|
||||
Context manager to set the current job ID for log filtering.
|
||||
|
||||
When multiple jobs run concurrently on the same Cloud Run instance,
|
||||
this ensures that each job's handler only captures logs from its own
|
||||
processing thread/context.
|
||||
|
||||
Usage:
|
||||
with job_logging_context(job_id):
|
||||
# All logs emitted here will be associated with this job_id
|
||||
process_job(job_id)
|
||||
|
||||
Args:
|
||||
job_id: The job ID to set as the current context
|
||||
"""
|
||||
token = _current_job_id.set(job_id)
|
||||
try:
|
||||
yield
|
||||
finally:
|
||||
_current_job_id.reset(token)
|
||||
|
||||
|
||||
class JobLogHandler(logging.Handler):
|
||||
"""
|
||||
A logging handler that captures log records and stores them in Firestore.
|
||||
@@ -53,6 +90,15 @@ class JobLogHandler(logging.Handler):
|
||||
def emit(self, record: logging.LogRecord) -> None:
|
||||
"""Process a log record."""
|
||||
try:
|
||||
# CRITICAL: Filter by current job context to prevent log mixing
|
||||
# When multiple jobs run concurrently, each attaches handlers to
|
||||
# the same global loggers. Without this check, logs from Job A
|
||||
# would be captured by Job B's handler and vice versa.
|
||||
current_job = _current_job_id.get()
|
||||
if current_job is not None and current_job != self.job_id:
|
||||
# This log is from a different job's context, skip it
|
||||
return
|
||||
|
||||
# Format the log message
|
||||
message = self.format(record)
|
||||
|
||||
@@ -182,6 +228,10 @@ def setup_job_logging(job_id: str, worker_name: str, *logger_names: str) -> JobL
|
||||
This adds a JobLogHandler to capture logs from specified loggers
|
||||
(including dependency loggers like lyrics_transcriber).
|
||||
|
||||
IMPORTANT: When using this function, wrap your job processing code in
|
||||
`job_logging_context(job_id)` to ensure proper log isolation when multiple
|
||||
jobs run concurrently on the same Cloud Run instance.
|
||||
|
||||
Args:
|
||||
job_id: Job ID
|
||||
worker_name: Worker name
|
||||
@@ -199,7 +249,10 @@ def setup_job_logging(job_id: str, worker_name: str, *logger_names: str) -> JobL
|
||||
"lyrics_transcriber", # Capture LyricsTranscriber logs
|
||||
)
|
||||
|
||||
# ... do work ...
|
||||
# IMPORTANT: Use job_logging_context for proper isolation
|
||||
with job_logging_context(job_id):
|
||||
# ... do work ...
|
||||
pass
|
||||
|
||||
# Optional: remove handler when done
|
||||
for name in logger_names:
|
||||
|
||||
@@ -1,22 +1,23 @@
|
||||
# Cloud Build configuration for base image
|
||||
#
|
||||
# This builds the base image with all Python dependencies pre-installed.
|
||||
# Run this manually when poetry.lock changes:
|
||||
# Run this manually when poetry.lock OR Dockerfile.base changes:
|
||||
# gcloud builds submit --config=cloudbuild-base.yaml --project=nomadkaraoke
|
||||
#
|
||||
# The base image is used by the main Dockerfile for fast app builds.
|
||||
# The poetry.lock hash is stored as a label for change detection.
|
||||
# A combined hash of poetry.lock + Dockerfile.base is stored as a label for change detection.
|
||||
|
||||
steps:
|
||||
# Calculate poetry.lock hash for change detection
|
||||
# Calculate combined hash for change detection (poetry.lock + Dockerfile.base)
|
||||
- name: 'gcr.io/cloud-builders/docker'
|
||||
entrypoint: 'bash'
|
||||
args:
|
||||
- '-c'
|
||||
- |
|
||||
POETRY_LOCK_HASH=$$(sha256sum poetry.lock | cut -d' ' -f1)
|
||||
echo "Poetry.lock hash: $$POETRY_LOCK_HASH"
|
||||
echo "$$POETRY_LOCK_HASH" > /workspace/POETRY_LOCK_HASH
|
||||
# Hash both files to detect changes in either
|
||||
CONTENT_HASH=$$(cat poetry.lock backend/Dockerfile.base | sha256sum | cut -d' ' -f1)
|
||||
echo "Combined content hash (poetry.lock + Dockerfile.base): $$CONTENT_HASH"
|
||||
echo "$$CONTENT_HASH" > /workspace/CONTENT_HASH
|
||||
|
||||
# Build base image with all dependencies
|
||||
- name: 'gcr.io/cloud-builders/docker'
|
||||
@@ -24,11 +25,11 @@ steps:
|
||||
args:
|
||||
- '-c'
|
||||
- |
|
||||
POETRY_LOCK_HASH=$$(cat /workspace/POETRY_LOCK_HASH)
|
||||
CONTENT_HASH=$$(cat /workspace/CONTENT_HASH)
|
||||
docker build \
|
||||
--build-arg BUILD_DATE=$BUILD_ID \
|
||||
--build-arg BUILD_ID=$BUILD_ID \
|
||||
--build-arg POETRY_LOCK_HASH=$$POETRY_LOCK_HASH \
|
||||
--build-arg BASE_CONTENT_HASH=$$CONTENT_HASH \
|
||||
-t us-central1-docker.pkg.dev/$PROJECT_ID/karaoke-repo/karaoke-backend-base:latest \
|
||||
-t us-central1-docker.pkg.dev/$PROJECT_ID/karaoke-repo/karaoke-backend-base:$BUILD_ID \
|
||||
-f backend/Dockerfile.base \
|
||||
|
||||
+5
-4
@@ -54,6 +54,7 @@ steps:
|
||||
- 'us-central1-docker.pkg.dev/$PROJECT_ID/karaoke-repo/karaoke-backend:latest'
|
||||
|
||||
# Deploy to Cloud Run with version from pyproject.toml
|
||||
# Uses Cloud Tasks for worker coordination (scalable architecture)
|
||||
- name: 'gcr.io/google.com/cloudsdktool/cloud-sdk'
|
||||
entrypoint: 'bash'
|
||||
args:
|
||||
@@ -71,11 +72,11 @@ steps:
|
||||
--cpu-boost \
|
||||
--execution-environment gen2 \
|
||||
--timeout 1800 \
|
||||
--concurrency 4 \
|
||||
--max-instances 10 \
|
||||
--concurrency 1 \
|
||||
--max-instances 50 \
|
||||
--min-instances 0 \
|
||||
--set-env-vars "GOOGLE_CLOUD_PROJECT=$PROJECT_ID,GCS_BUCKET_NAME=karaoke-gen-storage-$PROJECT_ID,FIRESTORE_COLLECTION=jobs,ENVIRONMENT=production,AUDIO_SEPARATOR_API_URL=https://nomadkaraoke--audio-separator-api.modal.run,KARAOKE_GEN_VERSION=$$VERSION,DEFAULT_DROPBOX_PATH=/MediaUnsynced/Karaoke/Tracks-Organized,DEFAULT_GDRIVE_FOLDER_ID=1laRKAyxo0v817SstfM5XkpbWiNKNAMSX" \
|
||||
--set-secrets "AUDIOSHAKE_API_TOKEN=audioshake-api-key:latest,GENIUS_API_TOKEN=genius-api-key:latest,SPOTIFY_COOKIE_SP_DC=spotify-cookie:latest,RAPIDAPI_KEY=rapidapi-key:latest,DEFAULT_DISCORD_WEBHOOK_URL=discord-releases-webhook:latest,ADMIN_TOKENS=admin-tokens:latest"
|
||||
--set-env-vars "GOOGLE_CLOUD_PROJECT=$PROJECT_ID,GCS_BUCKET_NAME=karaoke-gen-storage-$PROJECT_ID,FIRESTORE_COLLECTION=jobs,ENVIRONMENT=production,AUDIO_SEPARATOR_API_URL=https://nomadkaraoke--audio-separator-api.modal.run,KARAOKE_GEN_VERSION=$$VERSION,DEFAULT_DROPBOX_PATH=/MediaUnsynced/Karaoke/Tracks-Organized,DEFAULT_GDRIVE_FOLDER_ID=1laRKAyxo0v817SstfM5XkpbWiNKNAMSX,ENABLE_CLOUD_TASKS=true,CLOUD_RUN_SERVICE_URL=https://api.nomadkaraoke.com,GCP_REGION=us-central1,DEFAULT_ENABLE_YOUTUBE_UPLOAD=true,DEFAULT_BRAND_PREFIX=NOMAD" \
|
||||
--set-secrets "AUDIOSHAKE_API_TOKEN=audioshake-api-key:latest,GENIUS_API_TOKEN=genius-api-key:latest,SPOTIFY_COOKIE_SP_DC=spotify-cookie:latest,RAPIDAPI_KEY=rapidapi-key:latest,DEFAULT_DISCORD_WEBHOOK_URL=discord-releases-webhook:latest,ADMIN_TOKENS=admin-tokens:latest,RED_API_KEY=red-api-key:latest,RED_API_URL=red-api-url:latest,OPS_API_KEY=ops-api-key:latest,OPS_API_URL=ops-api-url:latest,FLACFETCH_API_URL=flacfetch-api-url:latest,FLACFETCH_API_KEY=flacfetch-api-key:latest"
|
||||
|
||||
images:
|
||||
- 'us-central1-docker.pkg.dev/$PROJECT_ID/karaoke-repo/karaoke-backend:latest'
|
||||
|
||||
+36
@@ -0,0 +1,36 @@
|
||||
# Codecov Configuration
|
||||
# Docs: https://docs.codecov.com/docs/codecovyml-reference
|
||||
|
||||
coverage:
|
||||
# Coverage value precision (2 decimal places)
|
||||
precision: 2
|
||||
round: down
|
||||
# Green range starts at 70% (our target)
|
||||
range: "70...100"
|
||||
|
||||
status:
|
||||
# Project-level coverage status check
|
||||
project:
|
||||
default:
|
||||
target: 70% # Pass if coverage >= 70%
|
||||
threshold: 2% # Allow 2% drop without failing
|
||||
if_ci_failed: error
|
||||
|
||||
# Patch coverage (new/changed lines only)
|
||||
patch:
|
||||
default:
|
||||
target: 70% # New code should also meet 70%
|
||||
threshold: 5% # More lenient for patches
|
||||
only_pulls: true # Only run on PRs, not on main branch pushes
|
||||
|
||||
# Disable PR comments entirely since we're satisfied with 70%+ coverage
|
||||
# Status checks will still appear on the PR
|
||||
comment: false
|
||||
|
||||
# Alternative: Uncomment below to only comment when coverage changes
|
||||
# comment:
|
||||
# layout: "diff, flags, files"
|
||||
# behavior: default
|
||||
# require_changes: true # Only comment if coverage actually changes
|
||||
# require_base: true # Require base report to exist
|
||||
|
||||
@@ -1,10 +1,32 @@
|
||||
# Backend Feature Parity Plan
|
||||
|
||||
**Last Updated:** 2024-12-10
|
||||
**Status:** ✅ Core Feature Parity Achieved (v0.71.0)
|
||||
**Last Updated:** 2024-12-11
|
||||
**Status:** ✅ Core Feature Parity Achieved (v0.71.0) | Batch 1 ✅ | Batch 2 ✅ | Batch 3 ✅ | Batch 4 ✅ | Batch 5 ✅
|
||||
|
||||
This document tracks the progress toward complete feature parity between the local `karaoke-gen` CLI and the cloud backend, enabling the `karaoke-gen-remote` CLI to have equivalent functionality.
|
||||
|
||||
### Quick Parity Summary
|
||||
|
||||
| Category | Supported | Needed | Parity | Notes |
|
||||
|----------|-----------|--------|--------|-------|
|
||||
| Core Processing | 12 | 12 | **100%** | ✅ Complete |
|
||||
| Distribution | 5 | 5 | **100%** | ✅ Complete |
|
||||
| Lyrics Configuration | 5 | 5 | **100%** | ✅ **Batch 1 Complete** (L1-L4) |
|
||||
| Style Configuration | 1 | 4 | **25%** | S2-S4 are MEDIUM priority |
|
||||
| Workflow Control | 0 | 3 | **0%** | W1/W2 HIGH, W7 MEDIUM (skip flags deferred) |
|
||||
| Audio Processing | 4 | 4 | **100%** | ✅ **Batch 2 & 3 Complete** (AP1-AP3, AP5) |
|
||||
| Input Modes | 3 | 3 | **100%** | ✅ **Batch 4 & 5 Complete** (P2, P3) |
|
||||
| Audio Fetching | 1 | 1 | **100%** | ✅ **Batch 5 Complete** (A1) |
|
||||
| Flags to Remove | - | - | - | I3-I6, AP6 (simplify codebase) |
|
||||
|
||||
**Overall:** Core workflow complete. See [CLI Parameter Parity Analysis](#-cli-parameter-parity-analysis) for detailed parameter list with implementation plans.
|
||||
|
||||
**Priority Summary:**
|
||||
- **HIGH**: L1-L4 ✅, AP1-AP5 ✅, P3 ✅, A1 ✅ | P2 (YouTube URLs), W1/W2 (prep/finalise phases), F15 (keep-brand-code)
|
||||
- **MEDIUM**: S2-S4 (style overrides/video bg), W7 (edit-lyrics), F14 (email template)
|
||||
- **LOW/DEFERRED**: W3-W6 (skip flags), D2-D3 (debugging)
|
||||
- **REMOVE**: I3, I4, I5, I6, AP6 (unnecessary options)
|
||||
|
||||
---
|
||||
|
||||
## 🎉 Milestone: First Successful End-to-End Run
|
||||
@@ -39,6 +61,521 @@ karaoke-gen-remote \
|
||||
|
||||
---
|
||||
|
||||
## 📊 CLI Parameter Parity Analysis
|
||||
|
||||
This section provides a comprehensive comparison of all CLI parameters between `karaoke-gen` (local) and `karaoke-gen-remote`, including detailed explanations of what each parameter does and how it could work remotely.
|
||||
|
||||
**Legend:**
|
||||
- ✅ Fully supported
|
||||
- ⚠️ Partially supported (limited functionality)
|
||||
- ❌ Not supported (ignored or errors)
|
||||
- 🔹 Remote-only (not applicable to local CLI)
|
||||
- N/A Not applicable to this mode
|
||||
|
||||
---
|
||||
|
||||
### Positional Arguments
|
||||
|
||||
| # | Parameter | Local | Remote | Description |
|
||||
|---|-----------|-------|--------|-------------|
|
||||
| P1 | `<file>` | ✅ | ✅ | **Local audio file path.** Copies file to output directory, converts to WAV for processing. Supports MP3, FLAC, WAV, M4A, OGG, AAC. |
|
||||
| P2 | `<url>` (YouTube) | ✅ | ✅ | **YouTube/online URL.** Uses yt-dlp to download audio and extract metadata (artist/title from video title). |
|
||||
| P3 | `<artist> <title>` | ✅ | ✅ | **Audio search mode.** When no file is provided, uses flacfetch to search Deezer/Tidal/etc for high-quality audio and downloads it. |
|
||||
| P4 | `<folder>` | ✅ | ❌ | **Batch folder processing.** Process all audio files in a folder, using `--filename_pattern` to extract track titles from filenames. |
|
||||
|
||||
**Remote Implementation Status:** ✅ **BATCH 4 & 5 COMPLETE** (v0.71.42)
|
||||
- **P2 YouTube URLs**: ✅ IMPLEMENTED. Backend accepts URL via `/api/jobs/create-from-url` endpoint. Uses yt-dlp to download audio and extract metadata (artist/title). Remote CLI detects URLs and routes to URL endpoint.
|
||||
- **P3 Flacfetch search**: ✅ IMPLEMENTED. Remote CLI submits artist+title, backend searches via flacfetch. Returns results for interactive selection (or auto-selects with `-y`/`--auto-download`). New job statuses: `searching_audio`, `awaiting_audio_selection`, `downloading_audio`.
|
||||
- **P4 Folder batch**: LOW PRIORITY. Could accept ZIP upload, process each as separate job. Defer for now.
|
||||
|
||||
---
|
||||
|
||||
### Workflow Control
|
||||
|
||||
| # | Parameter | Local | Remote | Description |
|
||||
|---|-----------|-------|--------|-------------|
|
||||
| W1 | `--prep-only` | ✅ | ❌ | **Stop after preparation phase.** Downloads audio, separates stems, transcribes lyrics, creates title/end screens, but does NOT run finalisation (encoding, YouTube upload, etc.). Useful for reviewing intermediate outputs before committing to final render. |
|
||||
| W2 | `--finalise-only` | ✅ | ❌ | **Run only finalisation phase.** Must be run from a directory that was previously prepared with `--prep-only`. Picks up where prep left off: encodes videos, creates CDG/TXT packages, uploads to YouTube/Dropbox, etc. |
|
||||
| W3 | `--skip-transcription` | ✅ | ❌ | **Skip automatic lyrics transcription.** Skips the AudioShake transcription and auto-correction steps. Use this if you want to manually provide lyrics or if transcription keeps failing. Lyrics review UI will still open if you have existing lyrics files. |
|
||||
| W4 | `--skip-separation` | ✅ | ❌ | **Skip audio separation.** Skips the AI-powered stem separation (Modal API). Useful when re-processing a track where you already have the stems from a previous run, or when combined with `--existing_instrumental`. |
|
||||
| W5 | `--skip-lyrics` | ✅ | ❌ | **Skip all lyrics processing.** Skips fetching lyrics from Genius/Spotify, transcription, and review. Output will have no lyrics overlay - just instrumental video with title/end screens. |
|
||||
| W6 | `--lyrics-only` | ✅ | ❌ | **Process only lyrics.** Sets `--skip-separation` and skips title/end screen generation. Useful for re-doing just the lyrics on an existing track without re-running expensive audio separation. |
|
||||
| W7 | `--edit-lyrics` | ✅ | ❌ | **Edit lyrics of existing track.** Run from inside an existing track directory (e.g., `NOMAD-1234 - Artist - Title/`). Backs up existing outputs, re-runs lyrics transcription with the existing audio, then re-renders and re-uploads. Uses `--keep-brand-code` implicitly. |
|
||||
| W8 | `--resume` | N/A | 🔹 | **Resume monitoring a job.** Reconnects to an existing remote job and continues monitoring its progress, handling review/instrumental selection if needed. |
|
||||
| W9 | `--cancel` | N/A | 🔹 | **Cancel a running job.** Stops processing but keeps the job record in Firestore. Useful for aborting stuck jobs. |
|
||||
| W10 | `--retry` | N/A | 🔹 | **Retry a failed job.** Restarts processing from the last successful checkpoint. Only works on jobs with `failed` status. |
|
||||
| W11 | `--delete` | N/A | 🔹 | **Delete a job.** Permanently removes job record from Firestore and all associated files from GCS. |
|
||||
| W12 | `--list` | N/A | 🔹 | **List all jobs.** Shows all jobs with their status, artist, title. Supports filtering with `--filter-environment` and `--filter-client-id`. |
|
||||
|
||||
**Remote Implementation Plan:**
|
||||
- **W1 `--prep-only`**: HIGH PRIORITY. Remote CLI submits job with `prep_only=true`. Backend runs all prep tasks (audio separation, lyrics transcription with review UI, initial render). After completion, CLI downloads the entire output folder and exits. No finalisation (encoding, YouTube, Dropbox, etc.) runs. Use case: Client needs custom edits to stems or lyrics before final render.
|
||||
- **W2 `--finalise-only`**: HIGH PRIORITY. Remote CLI checks current directory for expected prep output files. Uploads ALL files from that folder to backend (including any manual customizations user made since prep). Backend runs finalisation and distribution steps. Use case: User edited instrumental manually, now wants cloud to handle encoding/distribution.
|
||||
- **W3-W6 Skip flags**: LOW PRIORITY. Rarely used; typically all together to regenerate title/end screens with different artist/title. Defer until pipeline refactor provides cleaner stage-targeting.
|
||||
- **W7 `--edit-lyrics`**: MEDIUM PRIORITY. Re-runs lyrics worker with existing audio/stems. Creates NEW YouTube upload (doesn't delete/replace existing). Backend should handle gracefully if video with identical title already exists (user will have manually deleted old one). Use case: Customer found typo in published video.
|
||||
|
||||
---
|
||||
|
||||
### Logging & Debugging
|
||||
|
||||
| # | Parameter | Local | Remote | Description |
|
||||
|---|-----------|-------|--------|-------------|
|
||||
| D1 | `--log_level` | ✅ | ✅ | **Set logging verbosity.** Options: `debug`, `info`, `warning`, `error`. Default: `info`. Affects console output detail level. |
|
||||
| D2 | `--dry_run` | ✅ | ❌ | **Simulate without changes.** Runs through the workflow logic but doesn't actually download, process, or create files. Useful for testing argument combinations. |
|
||||
| D3 | `--render_bounding_boxes` | ✅ | ❌ | **Debug text positioning.** Renders red bounding boxes around text regions in title/end screen images. Helps debug custom style configurations. |
|
||||
|
||||
**Remote Implementation Plan:**
|
||||
- **D2 `--dry_run`**: LOW PRIORITY. Backend could accept `dry_run=true`, validate inputs and return what WOULD happen without processing. Nice to have for testing.
|
||||
- **D3 `--render_bounding_boxes`**: LOW PRIORITY. Backend could enable this, useful for testing styles before full render. Nice to have for debugging style configs.
|
||||
|
||||
---
|
||||
|
||||
### Input/Output Configuration
|
||||
|
||||
| # | Parameter | Local | Remote | Description |
|
||||
|---|-----------|-------|--------|-------------|
|
||||
| I1 | `--filename_pattern` | ✅ | N/A | **Regex for batch processing.** Python regex with named group `(?P<title>...)` to extract track title from filenames. Used with folder input. Example: `'(?P<index>\d+) - (?P<title>.+).mp3'` |
|
||||
| I2 | `--output_dir` | ✅ | ✅ | **Output directory.** Where to write output files. Local: creates subdirectory per track. Remote: where to download completed files. Default: current directory. |
|
||||
| I3 | `--no_track_subfolders` | 🗑️ | N/A | **REMOVE FROM LOCAL CLI.** Flat output structure. Not needed - always create subfolders. |
|
||||
| I4 | `--lossless_output_format` | 🗑️ | N/A | **REMOVE FROM LOCAL CLI.** Stem audio format. FLAC is always fine, no need for WAV option. |
|
||||
| I5 | `--output_png` | 🗑️ | N/A | **REMOVE FROM LOCAL CLI.** Always output both PNG and JPG, no need for flag. |
|
||||
| I6 | `--output_jpg` | 🗑️ | N/A | **REMOVE FROM LOCAL CLI.** Always output both PNG and JPG, no need for flag. |
|
||||
|
||||
**Remote Implementation Plan:**
|
||||
- **I3, I4, I5, I6**: REMOVE from local CLI entirely. Not worth maintaining. Backend always uses FLAC, outputs both PNG+JPG, creates subfolders.
|
||||
|
||||
---
|
||||
|
||||
### Audio Fetching Configuration
|
||||
|
||||
| # | Parameter | Local | Remote | Description |
|
||||
|---|-----------|-------|--------|-------------|
|
||||
| A1 | `--auto-download` | ✅ | ✅ | **Auto-select audio source.** When using artist+title search mode (flacfetch), automatically select the best quality source instead of prompting for manual selection. Useful for scripted/batch processing. |
|
||||
|
||||
**Remote Implementation Status:** ✅ **BATCH 5 COMPLETE** (v0.71.28)
|
||||
- **A1 `--auto-download`**: ✅ IMPLEMENTED. Backend supports BOTH modes:
|
||||
- **Interactive (default)**: API returns search results to client. Client displays options, user selects via `/api/audio-search/{job_id}/select` endpoint.
|
||||
- **Auto-download (`--auto-download` or `-y`)**: Backend auto-selects best quality source using flacfetch's ranking.
|
||||
|
||||
---
|
||||
|
||||
### Audio Processing Configuration
|
||||
|
||||
| # | Parameter | Local | Remote | Description |
|
||||
|---|-----------|-------|--------|-------------|
|
||||
| AP1 | `--clean_instrumental_model` | ✅ | ✅ | **Stage 1 separation model.** AI model for initial vocal/instrumental separation. Default: `model_bs_roformer_ep_317_sdr_12.9755.ckpt`. Different models have different quality/speed tradeoffs. |
|
||||
| AP2 | `--backing_vocals_models` | ✅ | ✅ | **Stage 2 separation model(s).** AI model(s) for separating lead vocals from backing vocals. Default: `mel_band_roformer_karaoke_aufr33_viperx_sdr_10.1956.ckpt`. |
|
||||
| AP3 | `--other_stems_models` | ✅ | ✅ | **Multi-stem separation model.** AI model for separating drums, bass, guitar, piano, other. Default: `htdemucs_6s.yaml`. |
|
||||
| AP4 | `--model_file_dir` | ✅ | N/A | **Model cache directory.** Where to store/load AI model files. Default: `/tmp/audio-separator-models/`. |
|
||||
| AP5 | `--existing_instrumental` | ✅ | ✅ | **Use pre-made instrumental.** Path to an existing instrumental file to use instead of running AI separation. Useful when you have a better instrumental from another source (official instrumental release, manual editing, etc.). Backend still runs separation for stems, but uses provided instrumental for final video. |
|
||||
| AP6 | `--instrumental_format` | 🗑️ | N/A | **REMOVE FROM LOCAL CLI.** FLAC is always fine, no need for format option. |
|
||||
|
||||
**Remote Implementation Status:** ✅ **BATCH 2 & 3 COMPLETE** (PR #9 v0.71.24, PR #10 v0.71.26)
|
||||
- **AP1 `--clean_instrumental_model`**: ✅ IMPLEMENTED. Sent as form field to backend. Audio worker passes to Modal API.
|
||||
- **AP2 `--backing_vocals_models`**: ✅ IMPLEMENTED. Sent as comma-separated list, parsed and passed to Modal API.
|
||||
- **AP3 `--other_stems_models`**: ✅ IMPLEMENTED. Sent as comma-separated list, parsed and passed to Modal API.
|
||||
- **AP4 `--model_file_dir`**: N/A for remote - Modal API handles model caching internally.
|
||||
- **AP5 `--existing_instrumental`**: ✅ IMPLEMENTED (Batch 3). User uploads instrumental file with job. Backend validates duration match (±0.5s), still runs separation for stems, but uses provided instrumental for final video encoding.
|
||||
- **AP6**: REMOVE from local CLI - FLAC is always fine.
|
||||
|
||||
---
|
||||
|
||||
### Lyrics Configuration
|
||||
|
||||
| # | Parameter | Local | Remote | Description |
|
||||
|---|-----------|-------|--------|-------------|
|
||||
| L1 | `--lyrics_artist` | ✅ | ✅ | **Override artist for lyrics search.** Use different artist name when searching Genius/Spotify/Musixmatch for lyrics. Useful for covers, remixes, or when artist name differs in lyrics databases. Example: `--lyrics_artist="The Beatles"` when your file says "Beatles, The". |
|
||||
| L2 | `--lyrics_title` | ✅ | ✅ | **Override title for lyrics search.** Use different song title when searching for lyrics. Useful for songs with alternate titles, subtitle variations, or "(Remastered)" suffixes. Example: `--lyrics_title="Hey Jude"` when file says "Hey Jude - 2009 Remaster". |
|
||||
| L3 | `--lyrics_file` | ✅ | ✅ | **Use existing lyrics file.** Path to a text file containing lyrics to use instead of fetching from online sources. Supports TXT, DOCX, RTF formats. Useful when online lyrics are wrong or unavailable. Transcription still runs to generate timestamps. |
|
||||
| L4 | `--subtitle_offset_ms` | ✅ | ✅ | **Adjust subtitle timing.** Shift all subtitle timestamps by N milliseconds. Positive values delay subtitles, negative values advance them. Useful when audio has intro padding or sync drift. Example: `--subtitle_offset_ms=500` delays by 0.5 seconds. |
|
||||
| L5 | `--skip_transcription_review` | ✅ | ⚠️ | **Skip review UI.** Don't open the browser-based lyrics review interface after transcription. Use existing auto-corrected lyrics as-is. Remote: use `-y` flag instead for non-interactive mode. |
|
||||
|
||||
**Remote Implementation Status:** ✅ **BATCH 1 COMPLETE** (PR #8, v0.71.22)
|
||||
- **L1 `--lyrics_artist`**: ✅ IMPLEMENTED. Sent as form field to backend. Lyrics worker uses for Genius/Spotify/AudioShake queries.
|
||||
- **L2 `--lyrics_title`**: ✅ IMPLEMENTED. Sent as form field to backend. Lyrics worker uses for search instead of main title.
|
||||
- **L3 `--lyrics_file`**: ✅ IMPLEMENTED. Uploaded with job, stored in GCS. Lyrics worker reads it instead of fetching online.
|
||||
- **L4 `--subtitle_offset_ms`**: ✅ IMPLEMENTED. Sent to backend, render worker applies offset when burning subtitles.
|
||||
- **L5 `--skip_transcription_review`**: Already works via `-y` flag which auto-accepts corrections.
|
||||
|
||||
---
|
||||
|
||||
### Style Configuration
|
||||
|
||||
| # | Parameter | Local | Remote | Description |
|
||||
|---|-----------|-------|--------|-------------|
|
||||
| S1 | `--style_params_json` | ✅ | ✅ | **Style configuration file.** Path to JSON file defining visual style: background images, fonts, colors, text positioning for intro/karaoke/end screens and CDG. All referenced image/font files are auto-uploaded in remote mode. |
|
||||
| S2 | `--style_override` | ✅ | ❌ | **Quick style tweaks.** Override specific style parameters without editing JSON. Can be used multiple times. Format: `section.key=value`. Example: `--style_override 'intro.background_image=/path/to/new_bg.png'`. Creates a temp JSON file with overrides merged. |
|
||||
| S3 | `--background_video` | ✅ | ❌ | **Video background for karaoke.** Path to video file to use as animated background instead of static image for the karaoke section. Video is looped/trimmed to match audio duration, with lyrics overlaid. |
|
||||
| S4 | `--background_video_darkness` | ✅ | ❌ | **Dim video background.** Darkness overlay percentage (0-100) applied to video background so lyrics are more readable. 0 = no darkening, 100 = completely black. Default: 0. |
|
||||
|
||||
**Remote Implementation Plan:**
|
||||
- **S2 `--style_override`**: MEDIUM PRIORITY. Send override strings to backend, merge server-side before passing to workers. Works same as local (creates merged config). Use case: Web UI will let users tweak font colors etc., needs to pass adjustments to backend.
|
||||
- **S3 `--background_video`**: MEDIUM PRIORITY. Upload video file with job. Backend processes with VideoBackgroundProcessor (loop/trim to audio duration). Requires larger file upload limits. Future: Web UI could allow YouTube URL or direct upload for video background.
|
||||
- **S4 `--background_video_darkness`**: Depends on S3. Send percentage to backend, apply overlay during video processing.
|
||||
|
||||
---
|
||||
|
||||
### Finalisation Configuration
|
||||
|
||||
| # | Parameter | Local | Remote | Description |
|
||||
|---|-----------|-------|--------|-------------|
|
||||
| F1 | `--enable_cdg` | ✅ | ✅ | **Generate CDG+MP3 package.** Create CD+Graphics karaoke format files (used by karaoke machines). Produces ZIP containing `.cdg` and `.mp3` files. Requires `cdg` section in style_params_json. |
|
||||
| F2 | `--enable_txt` | ✅ | ✅ | **Generate TXT+MP3 package.** Create text-based karaoke format with timed lyrics. Produces ZIP containing `.txt` (with timestamps) and `.mp3` files. |
|
||||
| F3 | `--brand_prefix` | ✅ | ✅ | **Brand code prefix.** Your brand identifier for sequential numbering. When set, output folder is renamed to `PREFIX-XXXX - Artist - Title` where XXXX is the next sequential number found in `organised_dir` or Dropbox. Example: `NOMAD` produces `NOMAD-1234`. |
|
||||
| F4 | `--organised_dir` | ✅ | N/A | **Local organized output.** Local filesystem path where final track folders are moved after processing. Used with `--brand_prefix` to maintain organized library. Example: `/Volumes/Media/Karaoke/Tracks-Organized/`. |
|
||||
| F5 | `--organised_dir_rclone_root` | ✅ | ✅ | **Rclone path for Dropbox.** Rclone remote path that maps to your organised_dir. Used to calculate next brand code number and for rclone-based uploads. Example: `dropbox:Media/Karaoke/Tracks-Organized`. |
|
||||
| F6 | `--public_share_dir` | ✅ | N/A | **Local public share folder.** Local filesystem path where shareable versions (720p video, CDG, TXT) are copied for public distribution. |
|
||||
| F7 | `--enable_youtube_upload` | ✅ | ✅ | **Upload to YouTube.** After encoding, upload the lossy 4K video to YouTube. Local: uses OAuth flow with client secrets. Remote: uses server-side stored credentials. |
|
||||
| F8 | `--youtube_client_secrets_file` | ✅ | N/A | **YouTube OAuth credentials.** Local path to Google OAuth client secrets JSON file for YouTube API. Only needed for local mode - remote uses server-stored credentials. |
|
||||
| F9 | `--youtube_description_file` | ✅ | ✅ | **YouTube video description.** Path to text file containing YouTube video description template. Supports placeholders like `{artist}`, `{title}`, `{brand_code}`. |
|
||||
| F10 | `--rclone_destination` | ✅ | N/A | **Rclone sync destination.** Rclone remote path to sync public_share_dir to. Used for Google Drive public sharing. Example: `googledrive:KaraokePublic`. |
|
||||
| F11 | `--dropbox_path` | N/A | 🔹 | **Dropbox folder (native API).** Remote-only: Dropbox folder path for organized output upload using native Dropbox API. Example: `/Karaoke/Tracks-Organized`. |
|
||||
| F12 | `--gdrive_folder_id` | N/A | 🔹 | **Google Drive folder (native API).** Remote-only: Google Drive folder ID for public share uploads using native API. Example: `1abc123xyz`. |
|
||||
| F13 | `--discord_webhook_url` | ✅ | ✅ | **Discord notification.** Webhook URL for sending completion notifications to Discord. Posts message with track info, brand code, and links. |
|
||||
| F14 | `--email_template_file` | ✅ | ❌ | **Email draft template.** Path to email template file for creating Gmail drafts with track info. Supports placeholders. Uses pyperclip for manual email composition. |
|
||||
| F15 | `--keep-brand-code` | ✅ | ❌ | **Preserve existing brand code.** When run from an existing track directory (with brand code in folder name), use that brand code instead of calculating a new one. Implicitly enabled with `--edit-lyrics`. |
|
||||
| F16 | `-y` / `--yes` | ✅ | ✅ | **Non-interactive mode.** Auto-accept all prompts: lyrics corrections, instrumental selection, confirmations. Useful for automated/CI pipelines. Remote: auto-completes review, selects clean instrumental. |
|
||||
| F17 | `--test_email_template` | ✅ | N/A | **Test email template.** Debug mode: test the email template rendering with fake data without processing any track. |
|
||||
|
||||
**Remote Implementation Plan:**
|
||||
- **F14 `--email_template_file`**: MEDIUM PRIORITY. Two behaviors needed:
|
||||
1. **Finalisation**: Same as local - use template to create Gmail draft (requires Gmail API OAuth). User just changes recipient and sends.
|
||||
2. **API endpoint**: Expose endpoint to fetch templated message text for a job. Use case: Web frontend button to copy message for pasting into Fiverr, etc.
|
||||
- **F15 `--keep-brand-code`**: HIGH PRIORITY (for `--finalise-only` workflow). When using `--finalise-only` remotely, user may be re-processing an already-published track. Must preserve existing brand code so updated files overwrite in Dropbox/GDrive rather than creating new sequence number. Implementation: Remote CLI reads brand code from local folder name, sends to backend.
|
||||
|
||||
---
|
||||
|
||||
### Remote CLI Specific Options
|
||||
|
||||
| # | Parameter | Local | Remote | Description |
|
||||
|---|-----------|-------|--------|-------------|
|
||||
| R1 | `--service-url` | N/A | 🔹 | **Backend service URL.** URL of the karaoke-gen cloud backend. Can also be set via `KARAOKE_GEN_URL` environment variable. Required for remote mode. |
|
||||
| R2 | `--review-ui-url` | N/A | 🔹 | **Lyrics review UI URL.** URL of the hosted lyrics review web application. Default: `https://gen.nomadkaraoke.com/lyrics/`. |
|
||||
| R3 | `--poll-interval` | N/A | 🔹 | **Status poll frequency.** Seconds between job status checks while monitoring. Default: 5 seconds. |
|
||||
| R4 | `--environment` | N/A | 🔹 | **Job environment tag.** Tag jobs with environment label (test/production/development) for filtering and cleanup. Sent as `X-Environment` header. |
|
||||
| R5 | `--client-id` | N/A | 🔹 | **Client identifier tag.** Tag jobs with client/user identifier for filtering. Sent as `X-Client-ID` header. |
|
||||
| R6 | `--filter-environment` | N/A | 🔹 | **Filter by environment.** When using `--list` or `--bulk-delete`, only show/delete jobs matching this environment. |
|
||||
| R7 | `--filter-client-id` | N/A | 🔹 | **Filter by client ID.** When using `--list` or `--bulk-delete`, only show/delete jobs matching this client ID. |
|
||||
| R8 | `--bulk-delete` | N/A | 🔹 | **Bulk delete jobs.** Delete all jobs matching filter criteria. Requires at least one filter (`--filter-environment` or `--filter-client-id`). |
|
||||
|
||||
---
|
||||
|
||||
## 🚀 Implementation Batches
|
||||
|
||||
The following batches are ordered by priority and grouped by similar functionality. Each batch is designed to be a self-contained unit of work that can be tackled by a single agent session.
|
||||
|
||||
### 📋 Instructions for Implementing a Batch
|
||||
|
||||
**Before starting a batch, ensure you follow these steps:**
|
||||
|
||||
#### 1. Test Coverage Requirements
|
||||
All code changes must have **>70% test coverage** on modified files. Run:
|
||||
```bash
|
||||
python -m pytest backend/tests/ --cov=backend.models.job --cov=backend.api.routes.file_upload --cov=backend.workers.<worker_name> --cov-report=term-missing
|
||||
```
|
||||
|
||||
**Required tests for each batch:**
|
||||
- **Model changes:** Test new fields exist, have correct defaults, serialize properly
|
||||
- **API changes:** Test form validation (valid/invalid inputs), file upload handling
|
||||
- **Worker changes:** Test parameter passing, configuration, error handling
|
||||
- **CLI changes:** Test submit_job() passes parameters correctly
|
||||
|
||||
#### 2. Documentation Updates (REQUIRED)
|
||||
As part of your PR, you MUST update this document:
|
||||
- [ ] Update the **Quick Parity Summary** table to reflect new parity percentages
|
||||
- [ ] Mark parameters as ✅ in the relevant **CLI Parameter Parity Analysis** section
|
||||
- [ ] Update **Remote Implementation Plan/Status** to show ✅ IMPLEMENTED
|
||||
- [ ] Mark the batch as **✅ COMPLETE** with PR number in the **Summary Table**
|
||||
- [ ] Add entry to **Recently Completed** table with version and PR number
|
||||
- [ ] Remove items from **Not Yet Implemented** list
|
||||
|
||||
#### 3. Version Bump
|
||||
Bump the patch version in `pyproject.toml` before committing.
|
||||
|
||||
#### 4. PR Requirements
|
||||
- Title: `feat: Batch N - <description>`
|
||||
- Include: Summary of changes, files modified, tests added
|
||||
- Link to this document in PR description
|
||||
|
||||
---
|
||||
|
||||
### Batch 1: Lyrics Configuration (HIGH) ✅ COMPLETE
|
||||
**Parameters:** L1 `--lyrics_artist`, L2 `--lyrics_title`, L3 `--lyrics_file`, L4 `--subtitle_offset_ms`
|
||||
|
||||
**Status:** ✅ **IMPLEMENTED** - PR #8 merged (v0.71.22)
|
||||
|
||||
**Implementation Summary:**
|
||||
- Remote CLI: Added 4 form fields to `submit_job()`, uploads lyrics file if provided
|
||||
- Backend: Added 4 Form parameters to `/api/jobs/upload` endpoint
|
||||
- Backend: Lyrics worker downloads user lyrics file, passes overrides to LyricsProcessor
|
||||
- Backend: Render worker applies subtitle offset via OutputConfig
|
||||
|
||||
**Files modified:**
|
||||
- `karaoke_gen/utils/remote_cli.py` - submit_job() with lyrics params
|
||||
- `backend/api/routes/file_upload.py` - Form fields + lyrics file upload
|
||||
- `backend/models/job.py` - lyrics_artist, lyrics_title, lyrics_file_gcs_path, subtitle_offset_ms fields
|
||||
- `backend/workers/lyrics_worker.py` - override values passed to LyricsProcessor
|
||||
- `backend/workers/render_video_worker.py` - subtitle_offset_ms applied
|
||||
|
||||
**Tests added:** 25+ unit tests covering lyrics file validation, Job model fields, worker configuration
|
||||
|
||||
**Complexity:** Low-Medium (straightforward form fields + file upload)
|
||||
|
||||
---
|
||||
|
||||
### Batch 2: Audio Separation Model Selection (HIGH) ✅ COMPLETE
|
||||
**Parameters:** AP1 `--clean_instrumental_model`, AP2 `--backing_vocals_models`, AP3 `--other_stems_models`
|
||||
|
||||
**Status:** ✅ **IMPLEMENTED** - PR #9 merged (v0.71.24)
|
||||
|
||||
**Implementation Summary:**
|
||||
- Remote CLI: Added 3 form fields to `submit_job()`, sends models as comma-separated strings
|
||||
- Backend: Added 3 Form parameters to `/api/jobs/upload` endpoint, parses comma-separated lists
|
||||
- Backend: Job model stores model configuration as optional fields
|
||||
- Backend: Audio worker passes model names to AudioProcessor which uses Modal API
|
||||
|
||||
**Files modified:**
|
||||
- `karaoke_gen/utils/remote_cli.py` - submit_job() with model params
|
||||
- `backend/api/routes/file_upload.py` - Form fields + comma parsing
|
||||
- `backend/models/job.py` - clean_instrumental_model, backing_vocals_models, other_stems_models fields
|
||||
- `backend/workers/audio_worker.py` - create_audio_processor() accepts model params from job
|
||||
|
||||
**Tests added:** 15+ unit tests covering Job model fields, form parsing, AudioProcessor configuration
|
||||
|
||||
**Complexity:** Low (Modal API already supports dynamic model selection)
|
||||
|
||||
---
|
||||
|
||||
### Batch 3: Existing Instrumental Support (HIGH) ✅ COMPLETE
|
||||
**Parameters:** AP5 `--existing_instrumental`
|
||||
|
||||
**Status:** ✅ **IMPLEMENTED** - PR #10 merged (v0.71.26)
|
||||
|
||||
**Implementation Summary:**
|
||||
- Remote CLI: Added `--existing_instrumental` parameter, uploads file as `existing_instrumental` type
|
||||
- Backend: Added `existing_instrumental` to VALID_FILE_TYPES with audio extension validation
|
||||
- Backend: Duration validation (±0.5s tolerance) at uploads-complete endpoint using pydub
|
||||
- Backend: Job model has `existing_instrumental_gcs_path` field
|
||||
- Backend: Video worker downloads user-provided instrumental if present, uses it for final encoding
|
||||
|
||||
**Files modified:**
|
||||
- `karaoke_gen/utils/remote_cli.py` - submit_job() with existing_instrumental param
|
||||
- `backend/api/routes/file_upload.py` - VALID_FILE_TYPES, GCS path generation, duration validation
|
||||
- `backend/models/job.py` - existing_instrumental_gcs_path field
|
||||
- `backend/workers/video_worker.py` - downloads and uses user-provided instrumental
|
||||
|
||||
**Tests added:** 20+ unit tests covering model fields, file type validation, GCS path generation, duration validation
|
||||
|
||||
**Complexity:** Medium (file upload + validation + conditional logic)
|
||||
|
||||
---
|
||||
|
||||
### Batch 4: YouTube URL Input (HIGH) ✅ COMPLETE
|
||||
**Parameters:** P2 `<url>` (YouTube/online URL)
|
||||
|
||||
**Status:** ✅ **IMPLEMENTED** (v0.71.26)
|
||||
|
||||
**Implementation Summary:**
|
||||
- Remote CLI: Detects URLs via `is_url()`, routes to `submit_job_from_url()` method
|
||||
- Backend: New `/api/jobs/create-from-url` endpoint accepts URL and optional artist/title
|
||||
- Backend: Audio worker downloads from URL using yt-dlp, auto-detects artist/title from metadata
|
||||
- FileHandler: Added `download_video()` and `extract_metadata_from_url()` methods
|
||||
- Dependencies: yt-dlp added to pyproject.toml
|
||||
|
||||
**Files modified:**
|
||||
- `karaoke_gen/utils/remote_cli.py` - URL detection, new `submit_job_from_url()` method
|
||||
- `karaoke_gen/file_handler.py` - `download_video()` and `extract_metadata_from_url()` methods
|
||||
- `backend/api/routes/file_upload.py` - `CreateJobFromUrlRequest`, `CreateJobFromUrlResponse`, `/api/jobs/create-from-url` endpoint
|
||||
- `backend/workers/audio_worker.py` - Enhanced `download_from_url()` with metadata extraction
|
||||
- `pyproject.toml` - Added yt-dlp dependency
|
||||
|
||||
**Tests added:** 20+ unit tests covering URL validation, request/response models, Job URL field
|
||||
|
||||
**Complexity:** Medium-High (new input mode, yt-dlp integration)
|
||||
|
||||
---
|
||||
|
||||
### Batch 5: Flacfetch Audio Search (HIGH) ✅ COMPLETE
|
||||
**Parameters:** P3 `<artist> <title>` (search mode), A1 `--auto-download`
|
||||
|
||||
**Status:** ✅ **IMPLEMENTED** - PR #13 merged (v0.71.28)
|
||||
|
||||
**Implementation Summary:**
|
||||
- Remote CLI: Detects artist+title without file, calls `/api/audio-search/search` endpoint
|
||||
- Backend: New `AudioSearchService` integrates flacfetch for searching
|
||||
- Backend: New job statuses `searching_audio`, `awaiting_audio_selection`, `downloading_audio`
|
||||
- Backend: Returns search results for interactive selection, or auto-selects with `auto_download=true`
|
||||
- Remote CLI: Displays results interactively, user selects, sends to `/api/audio-search/{job_id}/select`
|
||||
- Backend: Downloads selected audio to GCS, proceeds with normal job flow
|
||||
- Support `--auto-download` / `-y` for non-interactive auto-selection
|
||||
|
||||
**Files modified:**
|
||||
- `karaoke_gen/utils/remote_cli.py` - search flow, display results, `search_audio()`, `select_audio_source()`, `handle_audio_selection()`
|
||||
- `backend/api/routes/audio_search.py` - NEW: search and select endpoints
|
||||
- `backend/services/audio_search_service.py` - NEW: flacfetch integration service
|
||||
- `backend/models/job.py` - New statuses and fields (`audio_search_artist`, `audio_search_title`, `auto_download`)
|
||||
- `backend/main.py` - Register audio_search router
|
||||
|
||||
**Tests added:** 20+ unit tests covering Job model fields, AudioSearchService, state transitions
|
||||
|
||||
**Complexity:** High (new interactive API flow, new service integration)
|
||||
|
||||
---
|
||||
|
||||
### Batch 6: Two-Phase Workflow (HIGH) ✅ COMPLETE
|
||||
**Parameters:** W1 `--prep-only`, W2 `--finalise-only`, F15 `--keep-brand-code`
|
||||
|
||||
**Status:** ✅ Complete (2025-12-11)
|
||||
|
||||
**Implementation Summary:**
|
||||
- **prep-only:** Added `prep_only` field to Job model. When set, backend transitions to new `PREP_COMPLETE` status after review and video rendering (with_vocals.mkv). CLI downloads all prep outputs.
|
||||
- **finalise-only:** Added new endpoint `/api/jobs/create-finalise-only` for uploading prep outputs. Remote CLI detects files in prep folder, uploads them via signed URLs, and monitors finalisation.
|
||||
- **keep-brand-code:** Remote CLI extracts brand code from folder name (e.g., "NOMAD-1234 - Artist - Title"), sends to backend. Video worker uses preserved brand code for distribution.
|
||||
|
||||
**Files modified:**
|
||||
- `backend/models/job.py` - Added `PREP_COMPLETE` status, `prep_only`, `finalise_only`, `keep_brand_code` fields, updated state transitions
|
||||
- `backend/api/routes/file_upload.py` - Added `prep_only`, `keep_brand_code` to job creation, new finalise-only endpoints
|
||||
- `backend/workers/render_video_worker.py` - Conditional transition to PREP_COMPLETE for prep-only jobs
|
||||
- `backend/workers/video_worker.py` - Use preserved brand code when set
|
||||
- `backend/services/job_manager.py` - Pass new fields through job creation
|
||||
- `karaoke_gen/utils/remote_cli.py` - Full implementation of prep-only, finalise-only, and keep-brand-code flows
|
||||
|
||||
**Tests added:**
|
||||
- `backend/tests/test_models.py` - Tests for new fields and PREP_COMPLETE status
|
||||
- `backend/tests/test_file_upload.py` - Tests for finalise-only models and endpoints
|
||||
|
||||
**Complexity:** High (significant workflow changes, new upload flow)
|
||||
|
||||
---
|
||||
|
||||
### Batch 7: Style Overrides (MEDIUM)
|
||||
**Parameters:** S2 `--style_override`
|
||||
|
||||
**Scope:**
|
||||
- Remote CLI: Parse override strings, send as array to backend
|
||||
- Backend: Accept style_override array
|
||||
- Backend: Merge overrides with uploaded style JSON before processing
|
||||
- Handle asset references in overrides (upload referenced files)
|
||||
|
||||
**Files to modify:**
|
||||
- `karaoke_gen/utils/remote_cli.py` - parse and send overrides
|
||||
- `backend/api/routes/file_upload.py` - accept overrides
|
||||
- `backend/services/style_service.py` or similar - merge logic
|
||||
|
||||
**Complexity:** Medium (string parsing, merge logic, asset handling)
|
||||
|
||||
---
|
||||
|
||||
### Batch 8: Video Background (MEDIUM)
|
||||
**Parameters:** S3 `--background_video`, S4 `--background_video_darkness`
|
||||
|
||||
**Scope:**
|
||||
- Remote CLI: Upload video file (larger file support needed)
|
||||
- Backend: Accept video upload, store in GCS
|
||||
- Backend: Render worker uses VideoBackgroundProcessor
|
||||
- Backend: Apply darkness overlay
|
||||
|
||||
**Files to modify:**
|
||||
- `karaoke_gen/utils/remote_cli.py` - upload video file
|
||||
- `backend/api/routes/file_upload.py` - accept video upload (larger limits)
|
||||
- `backend/workers/render_worker.py` - integrate VideoBackgroundProcessor
|
||||
|
||||
**Complexity:** Medium (large file upload, video processing)
|
||||
|
||||
---
|
||||
|
||||
### Batch 9: Edit Lyrics Mode (MEDIUM)
|
||||
**Parameters:** W7 `--edit-lyrics`
|
||||
|
||||
**Scope:**
|
||||
- Remote CLI: Accept job_id for existing job, trigger edit mode
|
||||
- Backend: Load existing job's audio/stems from GCS
|
||||
- Backend: Re-run lyrics worker only
|
||||
- Backend: Re-render with new lyrics
|
||||
- Backend: Create NEW YouTube upload (handle duplicate title gracefully)
|
||||
|
||||
**Files to modify:**
|
||||
- `karaoke_gen/utils/remote_cli.py` - edit mode flow
|
||||
- `backend/api/routes/` - edit endpoint or flag
|
||||
- `backend/workers/orchestrator.py` - partial re-processing logic
|
||||
|
||||
**Complexity:** Medium-High (partial re-processing, state management)
|
||||
|
||||
---
|
||||
|
||||
### Batch 10: Email Template + Cleanup (LOW)
|
||||
**Parameters:** F14 `--email_template_file`, D2 `--dry_run`, D3 `--render_bounding_boxes`
|
||||
**Removal:** I3 `--no_track_subfolders`, I4 `--lossless_output_format`, I5 `--output_png`, I6 `--output_jpg`, AP6 `--instrumental_format`
|
||||
|
||||
**Scope:**
|
||||
- **Email template:** Upload template, backend creates Gmail draft + new API endpoint to fetch formatted text
|
||||
- **Dry run:** Backend validates inputs, returns plan without executing
|
||||
- **Bounding boxes:** Enable debug rendering in screens worker
|
||||
- **Removal:** Remove 5 unnecessary CLI flags from local CLI
|
||||
|
||||
**Files to modify:**
|
||||
- `karaoke_gen/utils/cli_args.py` - remove flags
|
||||
- `karaoke_gen/utils/remote_cli.py` - email template upload
|
||||
- `backend/api/routes/` - email template endpoint
|
||||
- `backend/services/email_service.py` - Gmail API integration
|
||||
|
||||
**Complexity:** Mixed (Gmail OAuth is complex, removals are simple)
|
||||
|
||||
---
|
||||
|
||||
### Summary Table
|
||||
|
||||
| Batch | Parameters | Priority | Complexity | Status |
|
||||
|-------|------------|----------|------------|--------|
|
||||
| 1 | L1-L4 (lyrics config) | HIGH | Low-Medium | ✅ **COMPLETE** (PR #8) |
|
||||
| 2 | AP1-AP3 (model selection) | HIGH | Low | ✅ **COMPLETE** (PR #9) |
|
||||
| 3 | AP5 (existing instrumental) | HIGH | Medium | ✅ **COMPLETE** (PR #10) |
|
||||
| 4 | P2 (YouTube URLs) | HIGH | Medium-High | ✅ **COMPLETE** |
|
||||
| 5 | P3, A1 (flacfetch search) | HIGH | High | ✅ **COMPLETE** (PR #13) |
|
||||
| 6 | W1, W2, F15 (two-phase) | HIGH | High | ⏳ Pending |
|
||||
| 7 | S2 (style overrides) | MEDIUM | Medium | ⏳ Pending |
|
||||
| 8 | S3, S4 (video background) | MEDIUM | Medium | ⏳ Pending |
|
||||
| 9 | W7 (edit-lyrics) | MEDIUM | Medium-High | ⏳ Pending |
|
||||
| 10 | F14, D2, D3, removals | LOW | Mixed | ⏳ Pending |
|
||||
|
||||
**Recommended Order:** ~~1~~ → ~~2~~ → ~~3~~ → ~~4~~ → ~~5~~ → 6 → 7 → 8 → 9 → 10
|
||||
|
||||
Batches 1-4 are quick wins that add significant value. Batches 5-6 are larger but high priority. Batches 7-10 can be done as time permits.
|
||||
|
||||
---
|
||||
|
||||
## ✅ Implementation Decisions (Answered 2024-12-10)
|
||||
|
||||
All questions have been answered and incorporated into the "Remote Implementation Plan" sections above. Summary of key decisions:
|
||||
|
||||
### Workflow Control
|
||||
- **W1/W2**: YES, two-phase workflow needed. `--prep-only` downloads all prep outputs after review, `--finalise-only` uploads local folder (with any manual edits) for cloud finalisation.
|
||||
- **W3-W6 Skip flags**: LOW PRIORITY - rarely used, defer until pipeline refactor provides cleaner stage-targeting.
|
||||
- **W7 Edit-lyrics**: Creates NEW YouTube upload (user deletes old one manually). Backend handles duplicate title gracefully.
|
||||
|
||||
### Input Modes
|
||||
- **P2 YouTube**: HIGH PRIORITY - needed for niche live versions only on YouTube.
|
||||
- **P3 Flacfetch**: HIGH PRIORITY - MUST be interactive via API (not auto-select) for future web UI audio source picker.
|
||||
|
||||
### Audio Processing
|
||||
- **AP1-AP3 Models**: HIGH PRIORITY - all model options must work remotely (Modal API can load any model on demand).
|
||||
- **AP5 Existing Instrumental**: Still run separation (for consistent stem downloads), but use provided instrumental for final video. Validate duration match (±0.5s) at job start before proceeding.
|
||||
|
||||
### I/O & Audio Format Options
|
||||
- **I3, I4, I5, I6, AP6**: REMOVE from local CLI entirely - unnecessary options, simplifies codebase.
|
||||
|
||||
### Audio Fetching
|
||||
- **A1 `--auto-download`**: Backend must support BOTH interactive (default, for web UI) AND auto-select (with `-y` flag) modes.
|
||||
|
||||
### Style
|
||||
- **S2 Style Override**: MEDIUM PRIORITY - needed for web UI style tweaks (font colors, etc.).
|
||||
- **S3/S4 Background Video**: MEDIUM PRIORITY - implement, will eventually allow YouTube URL or direct upload in web UI.
|
||||
|
||||
### Finalisation
|
||||
- **F14 Email Template**: BOTH - create Gmail draft (like local) AND expose API endpoint to fetch templated text (for Fiverr copy-paste).
|
||||
- **F15 Keep-brand-code**: HIGH PRIORITY for `--finalise-only` workflow - preserves brand code so updates overwrite existing Dropbox/GDrive files.
|
||||
|
||||
---
|
||||
|
||||
## Vision
|
||||
|
||||
The karaoke-gen system supports multiple interfaces to the same core functionality:
|
||||
@@ -105,14 +642,27 @@ The karaoke-gen system supports multiple interfaces to the same core functionali
|
||||
| Google Drive upload | ✅ | Service account credentials |
|
||||
| Discord notification | ✅ | Webhook URL from job or default |
|
||||
|
||||
### ⏳ Not Yet Implemented (Lower Priority)
|
||||
### ✅ Recently Completed
|
||||
|
||||
| Feature | Version | PR | Notes |
|
||||
|---------|---------|-----|-------|
|
||||
| Flacfetch audio search | v0.71.42 | #13 | `artist title` (search mode), `--auto-download` - search and download audio by artist+title |
|
||||
| YouTube URL input | v0.71.26 | - | `<url>` positional argument for YouTube/online URLs |
|
||||
| Existing instrumental | v0.71.26 | #10 | `--existing_instrumental` - upload and use user-provided instrumental |
|
||||
| Audio model selection | v0.71.24 | #9 | `--clean_instrumental_model`, `--backing_vocals_models`, `--other_stems_models` |
|
||||
| Lyrics override params | v0.71.22 | #8 | `--lyrics_artist`, `--lyrics_title`, `--lyrics_file`, `--subtitle_offset_ms` |
|
||||
|
||||
### ⏳ Not Yet Implemented
|
||||
|
||||
| Feature | Priority | Notes |
|
||||
|---------|----------|-------|
|
||||
| Style override | MEDIUM | `--style_override` for quick tweaks |
|
||||
| Skip separation/transcription | MEDIUM | Workflow control for re-processing |
|
||||
| Edit lyrics mode | MEDIUM | `--edit-lyrics` for fixing existing tracks |
|
||||
| Background video | MEDIUM | `--background_video` requires video upload |
|
||||
| Two-phase workflow | HIGH | `--prep-only`, `--finalise-only` |
|
||||
| Batch folder processing | LOW | Process multiple files at once |
|
||||
| Gmail draft creation | LOW | Nice-to-have, not blocking |
|
||||
| YouTube URL input | LOW | Requires yt-dlp in container |
|
||||
| Batch processing | LOW | Queue management needed |
|
||||
| Existing instrumental support | LOW | For re-processing existing tracks |
|
||||
|
||||
---
|
||||
|
||||
@@ -131,6 +681,10 @@ The karaoke-gen system supports multiple interfaces to the same core functionali
|
||||
| `dropbox-oauth-credentials` | ✅ | Dropbox API OAuth tokens |
|
||||
| `gdrive-service-account` | ✅ | Google Drive service account |
|
||||
| `discord-webhook-url` | ✅ | Default Discord webhook |
|
||||
| `red-api-key` | ⏳ | RED tracker API key (flacfetch audio search) |
|
||||
| `red-api-url` | ⏳ | RED tracker base URL (flacfetch audio search) |
|
||||
| `ops-api-key` | ⏳ | OPS tracker API key (flacfetch audio search) |
|
||||
| `ops-api-url` | ⏳ | OPS tracker base URL (flacfetch audio search) |
|
||||
|
||||
### Default Distribution Settings
|
||||
|
||||
@@ -168,96 +722,17 @@ karaoke-gen-remote \
|
||||
|
||||
---
|
||||
|
||||
## Future Architecture: Shared Pipeline
|
||||
## Future Architecture
|
||||
|
||||
Once feature parity is achieved, the codebase should be refactored toward a **shared pipeline architecture** where both local and remote execution use the same abstractions.
|
||||
For the comprehensive architecture plan covering both **horizontal scalability** (Cloud Tasks, Cloud Run Jobs) and **software architecture** (shared pipeline, SOLID, DRY), see:
|
||||
|
||||
### Current State (Divergent Paths)
|
||||
**[SCALABLE-ARCHITECTURE-PLAN.md](./SCALABLE-ARCHITECTURE-PLAN.md)**
|
||||
|
||||
```
|
||||
LOCAL CLI CLOUD BACKEND
|
||||
───────── ─────────────
|
||||
KaraokeGen.process() API Routes
|
||||
│ │
|
||||
├─► AudioProcessor ├─► audio_worker.py
|
||||
│ └── Modal API or local │ └── Modal API
|
||||
│ │
|
||||
├─► LyricsProcessor ├─► lyrics_worker.py
|
||||
│ └── Orchestrates everything │ └── Transcription only
|
||||
│ including video generation │
|
||||
│ ├─► screens_worker.py
|
||||
│ │
|
||||
│ ├─► render_video_worker.py
|
||||
│ │ └── OutputGenerator directly
|
||||
│ │
|
||||
└─► KaraokeFinalise └─► video_worker.py
|
||||
└── Encoding, distribution └── KaraokeFinalise
|
||||
```
|
||||
|
||||
**Problems:**
|
||||
- Video generation called differently (via LyricsProcessor vs OutputGenerator directly)
|
||||
- LyricsProcessor does too many things (fetching, transcription, video, file management)
|
||||
- Testing requires mocking different things for local vs remote
|
||||
- Bug fixes may need to be applied in multiple places
|
||||
|
||||
### Target State (Shared Pipeline)
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────────────────────┐
|
||||
│ SHARED PIPELINE ARCHITECTURE │
|
||||
├─────────────────────────────────────────────────────────────────────────────┤
|
||||
│ │
|
||||
│ AudioInput → Separation → Transcription → Review → Render → Finalize │
|
||||
│ │ │ │ │ │ │ │
|
||||
│ ▼ ▼ ▼ ▼ ▼ ▼ │
|
||||
│ ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐ │
|
||||
│ │ Stage │ │ Stage │ │ Stage │ │ Stage │ │ Stage │ │ Stage │ │
|
||||
│ │ API │ │ API │ │ API │ │ API │ │ API │ │ API │ │
|
||||
│ └────┬───┘ └────┬───┘ └────┬───┘ └────┬───┘ └────┬───┘ └────┬───┘ │
|
||||
│ │ │ │ │ │ │ │
|
||||
│ ┌────┴───────────┴────────────┴────────────┴──────────┴──────────┴────┐ │
|
||||
│ │ EXECUTION LAYER │ │
|
||||
│ │ │ │
|
||||
│ │ Local Mode: │ Remote Mode: │ │
|
||||
│ │ - Direct calls │ - HTTP to backend │ │
|
||||
│ │ - Local GPU/CPU │ - Workers + Modal │ │
|
||||
│ │ - Blocking │ - Async + polling │ │
|
||||
│ └──────────────────────┴───────────────────────────────────────────────┘ │
|
||||
│ │
|
||||
└─────────────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
**Benefits:**
|
||||
- Single source of truth for each pipeline stage
|
||||
- Each stage independently testable
|
||||
- Same business logic regardless of execution mode
|
||||
- Easier to add new stages or modify existing ones
|
||||
- DRY - fix bugs once, works everywhere
|
||||
|
||||
### Implementation Plan for Shared Pipeline
|
||||
|
||||
This refactor should be done in a separate branch after the v0.71.0 release:
|
||||
|
||||
1. **Extract stage interfaces**
|
||||
```python
|
||||
class PipelineStage(Protocol):
|
||||
async def execute(self, context: PipelineContext) -> StageResult:
|
||||
...
|
||||
```
|
||||
|
||||
2. **Create execution adapters**
|
||||
```python
|
||||
class LocalExecutor:
|
||||
"""Runs stages directly in-process"""
|
||||
|
||||
class RemoteExecutor:
|
||||
"""Runs stages via backend API/workers"""
|
||||
```
|
||||
|
||||
3. **Refactor incrementally**
|
||||
- Start with one stage (e.g., Separation)
|
||||
- Prove the pattern works
|
||||
- Migrate other stages
|
||||
Key goals:
|
||||
- **100+ concurrent jobs** with no performance degradation
|
||||
- **Dedicated resources per job** (no CPU/memory contention)
|
||||
- **Shared pipeline architecture** - single source of truth for business logic
|
||||
- **DRY codebase** - bug fixes apply to both local and remote execution
|
||||
|
||||
---
|
||||
|
||||
@@ -355,6 +830,50 @@ DEFAULT_DISCORD_WEBHOOK_URL=https://discord.com/...
|
||||
|
||||
## Recent Changes Log
|
||||
|
||||
### 2024-12-11: v0.71.28 - Batch 5 Complete (Flacfetch Audio Search)
|
||||
|
||||
**PR #13: Flacfetch Audio Search for Remote CLI**
|
||||
|
||||
- ✅ `artist title` (search mode) - Search for audio by artist and title without providing a file
|
||||
- ✅ `--auto-download` - Auto-select best audio source (skip interactive selection)
|
||||
- New job statuses: `searching_audio`, `awaiting_audio_selection`, `downloading_audio`
|
||||
- New API endpoints: `POST /api/audio-search/search`, `GET /api/audio-search/{job_id}/results`, `POST /api/audio-search/{job_id}/select`
|
||||
- Interactive mode: Returns search results for user selection
|
||||
- Auto mode: Uses flacfetch's quality ranking to auto-select best source
|
||||
- Added 20+ unit tests for new functionality
|
||||
- Files: `remote_cli.py`, `audio_search.py` (new route), `audio_search_service.py` (new service), `job.py`
|
||||
|
||||
### 2024-12-11: v0.71.26 - Batch 3 Complete (Existing Instrumental Support)
|
||||
|
||||
**PR #10: Existing Instrumental Support for Remote CLI**
|
||||
|
||||
- ✅ `--existing_instrumental` - Upload and use user-provided instrumental file
|
||||
- Duration validation (±0.5s tolerance) before processing starts
|
||||
- Backend still runs AI separation for stem downloads, but uses provided instrumental for final video
|
||||
- Added 20+ unit tests for new functionality
|
||||
- Files: `remote_cli.py`, `file_upload.py`, `job.py`, `video_worker.py`
|
||||
|
||||
### 2024-12-11: v0.71.24 - Batch 2 Complete (Audio Model Selection)
|
||||
|
||||
**PR #9: Audio Model Selection for Remote CLI**
|
||||
|
||||
- ✅ `--clean_instrumental_model` - Custom Stage 1 separation model
|
||||
- ✅ `--backing_vocals_models` - Custom backing vocals separation models
|
||||
- ✅ `--other_stems_models` - Custom multi-stem separation models (bass, drums, etc.)
|
||||
- Added 15+ unit tests for new functionality
|
||||
- Files: `remote_cli.py`, `file_upload.py`, `job.py`, `audio_worker.py`
|
||||
|
||||
### 2024-12-10: v0.71.22 - Batch 1 Complete (Lyrics Configuration)
|
||||
|
||||
**PR #8: Lyrics Configuration for Remote CLI**
|
||||
|
||||
- ✅ `--lyrics_artist` - Override artist name for lyrics search
|
||||
- ✅ `--lyrics_title` - Override title for lyrics search
|
||||
- ✅ `--lyrics_file` - Upload custom lyrics file (TXT, DOCX, RTF)
|
||||
- ✅ `--subtitle_offset_ms` - Adjust subtitle timing offset
|
||||
- Added 25+ unit tests for new functionality
|
||||
- Files: `remote_cli.py`, `file_upload.py`, `job.py`, `lyrics_worker.py`, `render_video_worker.py`
|
||||
|
||||
### 2024-12-10: v0.71.0 - Core Feature Parity Complete
|
||||
|
||||
**First successful end-to-end remote run!**
|
||||
@@ -400,14 +919,47 @@ DEFAULT_DISCORD_WEBHOOK_URL=https://discord.com/...
|
||||
2. ✅ Tag v0.71.0 release
|
||||
3. Update PyPI package
|
||||
|
||||
### Short-Term
|
||||
1. Monitor production usage
|
||||
2. Address any edge cases found
|
||||
3. Improve error messages and logging
|
||||
### Short-Term: Feature Parity (Priority Order)
|
||||
|
||||
### Long-Term (Shared Pipeline Refactor)
|
||||
1. Create new branch for shared pipeline architecture
|
||||
2. Extract stage interfaces
|
||||
3. Implement execution adapters
|
||||
4. Migrate stages incrementally
|
||||
5. Achieve true code sharing between local and remote
|
||||
1. ✅ **Lyrics Configuration** (Batch 1 - COMPLETE)
|
||||
- `--lyrics_artist`, `--lyrics_title`, `--lyrics_file`, `--subtitle_offset_ms`
|
||||
- PR #8, v0.71.22
|
||||
|
||||
2. ✅ **Audio Model Selection** (Batch 2 - COMPLETE)
|
||||
- `--clean_instrumental_model`, `--backing_vocals_models`, `--other_stems_models`
|
||||
- PR #9, v0.71.24
|
||||
|
||||
3. ✅ **Existing Instrumental** (Batch 3 - COMPLETE)
|
||||
- Added `--existing_instrumental` upload support
|
||||
- PR #10, v0.71.26
|
||||
|
||||
4. **YouTube URL Input** (Batch 4 - NEXT)
|
||||
- Accept YouTube URLs as input
|
||||
- Requires: yt-dlp in container
|
||||
- Enables: Processing niche live versions only on YouTube
|
||||
|
||||
5. ✅ **Flacfetch Audio Search** (Batch 5 - COMPLETE)
|
||||
- Interactive audio source selection via API
|
||||
- v0.71.28
|
||||
|
||||
### Medium-Term: Workflow Features
|
||||
|
||||
1. **Two-Phase Workflow** (Batch 6) ✅ COMPLETE
|
||||
- `--prep-only` and `--finalise-only` modes
|
||||
|
||||
3. **Style Override** (Batch 7)
|
||||
- Quick style tweaks without editing JSON
|
||||
|
||||
4. **Background Video Support** (Batch 8)
|
||||
- Upload and use video backgrounds
|
||||
|
||||
5. **Edit Lyrics Mode** (Batch 9)
|
||||
- Allow fixing lyrics on completed jobs
|
||||
|
||||
### Long-Term (Scalable Architecture)
|
||||
|
||||
See **[SCALABLE-ARCHITECTURE-PLAN.md](./SCALABLE-ARCHITECTURE-PLAN.md)** for the comprehensive plan covering:
|
||||
1. Cloud Tasks integration for horizontal scalability
|
||||
2. Cloud Run Jobs for long-running video encoding
|
||||
3. Shared pipeline architecture for code reuse
|
||||
4. Implementation roadmap and migration strategy
|
||||
@@ -0,0 +1,233 @@
|
||||
# Job Status Display Improvement Plan
|
||||
|
||||
**Status:** Planned
|
||||
**Created:** 2025-12-27
|
||||
**Priority:** HIGH - User experience improvement
|
||||
|
||||
## Problem Statement
|
||||
|
||||
Users see generic status messages like "Downloading..." that persist for too long, even after the download is complete and other processing stages are happening. This makes it hard to understand:
|
||||
1. What stage the job is actually at
|
||||
2. How much progress has been made
|
||||
3. How much longer the job might take
|
||||
|
||||
## Current Implementation
|
||||
|
||||
### Backend Status System
|
||||
The backend has 28 distinct job statuses organized into 8 processing stages:
|
||||
|
||||
```
|
||||
Stage 1: Setup (PENDING)
|
||||
Stage 2: Audio Search (SEARCHING_AUDIO, AWAITING_AUDIO_SELECTION, DOWNLOADING_AUDIO)
|
||||
Stage 3: Download (DOWNLOADING)
|
||||
Stage 4: Parallel Processing
|
||||
- Audio: SEPARATING_STAGE1 → SEPARATING_STAGE2 → AUDIO_COMPLETE
|
||||
- Lyrics: TRANSCRIBING → CORRECTING → LYRICS_COMPLETE
|
||||
Stage 5: Screen Generation (GENERATING_SCREENS, APPLYING_PADDING)
|
||||
Stage 6: Lyrics Review (AWAITING_REVIEW, IN_REVIEW, REVIEW_COMPLETE) ⚠️ BLOCKING
|
||||
Stage 7: Video Rendering (RENDERING_VIDEO)
|
||||
Stage 8: Instrumental Selection (AWAITING_INSTRUMENTAL_SELECTION) ⚠️ BLOCKING
|
||||
Stage 9: Final Processing (INSTRUMENTAL_SELECTED, GENERATING_VIDEO, ENCODING, PACKAGING)
|
||||
Stage 10: Distribution (UPLOADING, NOTIFYING, COMPLETE)
|
||||
```
|
||||
|
||||
### Key Findings
|
||||
|
||||
1. **Progress field exists but unused**: The `Job` model has a `progress: number` field (0-100) that's returned by the API but NOT displayed in the frontend
|
||||
2. **Parallel processing complicates status**: Audio and lyrics workers run in parallel, updating `state_data.audio_progress` and `state_data.lyrics_progress` independently
|
||||
3. **Status labels are static**: Frontend shows "Downloading..." but doesn't reflect that parallel workers are running
|
||||
4. **10-second polling**: Frontend polls every 10 seconds, so status updates are not real-time
|
||||
|
||||
## Proposed Solution
|
||||
|
||||
### 1. Step-Based Progress Display
|
||||
|
||||
Show a `[X/10] Status...` format that gives users a clear sense of overall progress:
|
||||
|
||||
```
|
||||
[1/10] Setting up...
|
||||
[2/10] Searching for audio...
|
||||
[3/10] Downloading audio...
|
||||
[4/10] Processing audio & lyrics... ← Parallel stage
|
||||
[5/10] Generating screens...
|
||||
[6/10] Needs review ← Blocking
|
||||
[7/10] Rendering video...
|
||||
[8/10] Select instrumental ← Blocking
|
||||
[9/10] Encoding final video...
|
||||
[10/10] Uploading...
|
||||
```
|
||||
|
||||
### 2. Status-to-Step Mapping
|
||||
|
||||
```typescript
|
||||
const STATUS_STEP_MAP: Record<string, { step: number; total: number; label: string }> = {
|
||||
// Step 1: Setup
|
||||
pending: { step: 1, total: 10, label: "Setting up" },
|
||||
|
||||
// Step 2: Audio Search (optional)
|
||||
searching_audio: { step: 2, total: 10, label: "Searching for audio" },
|
||||
awaiting_audio_selection: { step: 2, total: 10, label: "Select audio source" },
|
||||
|
||||
// Step 3: Download
|
||||
downloading_audio: { step: 3, total: 10, label: "Downloading audio" },
|
||||
downloading: { step: 3, total: 10, label: "Downloading" },
|
||||
|
||||
// Step 4: Parallel Processing (Audio + Lyrics)
|
||||
separating_stage1: { step: 4, total: 10, label: "Separating audio (1/2)" },
|
||||
separating_stage2: { step: 4, total: 10, label: "Separating audio (2/2)" },
|
||||
audio_complete: { step: 4, total: 10, label: "Audio ready" },
|
||||
transcribing: { step: 4, total: 10, label: "Transcribing lyrics" },
|
||||
correcting: { step: 4, total: 10, label: "Correcting lyrics" },
|
||||
lyrics_complete: { step: 4, total: 10, label: "Lyrics ready" },
|
||||
|
||||
// Step 5: Screen Generation
|
||||
generating_screens: { step: 5, total: 10, label: "Generating screens" },
|
||||
applying_padding: { step: 5, total: 10, label: "Syncing countdown" },
|
||||
|
||||
// Step 6: Review (BLOCKING)
|
||||
awaiting_review: { step: 6, total: 10, label: "Needs review" },
|
||||
in_review: { step: 6, total: 10, label: "In review" },
|
||||
|
||||
// Step 7: Video Rendering
|
||||
review_complete: { step: 7, total: 10, label: "Review complete" },
|
||||
rendering_video: { step: 7, total: 10, label: "Rendering video" },
|
||||
|
||||
// Step 8: Instrumental Selection (BLOCKING)
|
||||
awaiting_instrumental_selection: { step: 8, total: 10, label: "Select instrumental" },
|
||||
|
||||
// Step 9: Final Encoding
|
||||
instrumental_selected: { step: 9, total: 10, label: "Instrumental selected" },
|
||||
generating_video: { step: 9, total: 10, label: "Generating final video" },
|
||||
encoding: { step: 9, total: 10, label: "Encoding video" },
|
||||
packaging: { step: 9, total: 10, label: "Packaging files" },
|
||||
|
||||
// Step 10: Distribution
|
||||
uploading: { step: 10, total: 10, label: "Uploading" },
|
||||
notifying: { step: 10, total: 10, label: "Sending notifications" },
|
||||
complete: { step: 10, total: 10, label: "Complete" },
|
||||
|
||||
// Terminal states
|
||||
failed: { step: 0, total: 10, label: "Failed" },
|
||||
cancelled: { step: 0, total: 10, label: "Cancelled" },
|
||||
prep_complete: { step: 10, total: 10, label: "Prep complete" },
|
||||
};
|
||||
```
|
||||
|
||||
### 3. Enhanced Parallel Processing Display
|
||||
|
||||
When audio and lyrics are processing in parallel, show both activities:
|
||||
|
||||
```typescript
|
||||
// Check state_data for parallel progress
|
||||
if (job.state_data?.audio_progress && job.state_data?.lyrics_progress) {
|
||||
const audioStatus = job.state_data.audio_progress.stage;
|
||||
const lyricsStatus = job.state_data.lyrics_progress.stage;
|
||||
|
||||
// Show combined status like "Audio: separating, Lyrics: transcribing"
|
||||
if (audioStatus !== 'audio_complete' || lyricsStatus !== 'lyrics_complete') {
|
||||
return {
|
||||
step: 4,
|
||||
total: 10,
|
||||
label: buildParallelLabel(audioStatus, lyricsStatus)
|
||||
};
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### 4. Visual Progress Bar (Optional Enhancement)
|
||||
|
||||
Add a thin progress bar below the status text:
|
||||
|
||||
```tsx
|
||||
<div className="w-full h-1 bg-slate-700 rounded mt-1">
|
||||
<div
|
||||
className="h-full bg-blue-500 rounded transition-all"
|
||||
style={{ width: `${(step / total) * 100}%` }}
|
||||
/>
|
||||
</div>
|
||||
```
|
||||
|
||||
## Implementation Steps
|
||||
|
||||
### Phase 1: Core Changes (MVP)
|
||||
|
||||
1. **Create status utility** (`frontend/lib/job-status.ts`):
|
||||
- Define `STATUS_STEP_MAP` constant
|
||||
- Create `getJobStep(job: Job)` function
|
||||
- Create `formatStepStatus(step, total, label)` function
|
||||
|
||||
2. **Update JobCard component**:
|
||||
- Import status utility
|
||||
- Replace static `StatusText` with step-based format
|
||||
- Keep existing color coding from `statusConfig`
|
||||
|
||||
3. **Add unit tests** (`frontend/__tests__/job-status.test.ts`):
|
||||
- Test all status mappings
|
||||
- Test parallel processing detection
|
||||
- Test edge cases (unknown status, null values)
|
||||
|
||||
### Phase 2: Enhanced Parallel Processing (Optional)
|
||||
|
||||
1. **Add parallel progress detection**:
|
||||
- Check `state_data.audio_progress` and `state_data.lyrics_progress`
|
||||
- Build combined label showing both activities
|
||||
|
||||
2. **Add visual progress bar**:
|
||||
- Thin progress indicator based on step number
|
||||
- Smooth transitions between steps
|
||||
|
||||
### Phase 3: Backend Improvements (Future)
|
||||
|
||||
1. **Add estimated time remaining**:
|
||||
- Track average duration per stage from historical data
|
||||
- Return ETA in API response
|
||||
|
||||
2. **WebSocket for real-time updates**:
|
||||
- Replace polling with push notifications
|
||||
- Smoother progress updates during long operations
|
||||
|
||||
## Files to Modify
|
||||
|
||||
| File | Changes |
|
||||
|------|---------|
|
||||
| `frontend/lib/job-status.ts` | NEW: Status utility functions |
|
||||
| `frontend/components/job/JobCard.tsx` | Update status display |
|
||||
| `frontend/__tests__/job-status.test.ts` | NEW: Unit tests |
|
||||
| `frontend/lib/api.ts` | Add `state_data` types (if needed) |
|
||||
|
||||
## Testing Plan
|
||||
|
||||
1. **Unit tests**:
|
||||
- All status mappings return correct step/label
|
||||
- Unknown statuses handled gracefully
|
||||
- Parallel progress detection works
|
||||
|
||||
2. **Integration tests** (E2E):
|
||||
- Verify status displays correctly at each stage
|
||||
- Verify step numbers increment as job progresses
|
||||
|
||||
3. **Manual testing**:
|
||||
- Submit a job and observe status progression
|
||||
- Verify parallel processing shows meaningful status
|
||||
|
||||
## Success Criteria
|
||||
|
||||
- [ ] All statuses show `[X/10] Label` format
|
||||
- [ ] Step numbers progress logically (never decrease except on retry)
|
||||
- [ ] Parallel processing shows combined activity
|
||||
- [ ] Blocking statuses clearly indicated for user action
|
||||
- [ ] All existing tests pass
|
||||
- [ ] New unit tests have >80% coverage
|
||||
|
||||
## Rollback Plan
|
||||
|
||||
The changes are frontend-only and purely cosmetic. If issues arise:
|
||||
1. Revert the JobCard changes to use the old `statusConfig` approach
|
||||
2. The backend API remains unchanged
|
||||
|
||||
## Notes
|
||||
|
||||
- The 10-step system is a simplification of the 28 backend statuses for user comprehension
|
||||
- Parallel processing (step 4) groups multiple backend statuses into one user-facing step
|
||||
- Blocking steps (6, 8) require user action and should be visually distinct
|
||||
- The `progress` field from backend could be used for sub-step progress bars in the future
|
||||
@@ -0,0 +1,608 @@
|
||||
# Observability & Tracing Plan for Karaoke Generator
|
||||
|
||||
**Created:** 2025-12-22
|
||||
**Status:** Planning
|
||||
**Priority:** High
|
||||
|
||||
## Executive Summary
|
||||
|
||||
The karaoke-gen backend has **partial observability infrastructure** but **no rich tracing implemented**. While the code includes OpenTelemetry setup and tracing utilities, actual job processing is minimally instrumented. This means debugging job failures requires manually querying Cloud Logging with grep-style searches rather than clicking through a trace waterfall.
|
||||
|
||||
### Current State: 🟡 Partial
|
||||
|
||||
| Capability | Status | Notes |
|
||||
|------------|--------|-------|
|
||||
| **Logs exported to Cloud Logging** | ✅ Working | Standard Python logs visible |
|
||||
| **OpenTelemetry SDK installed** | ✅ Working | Dependencies in pyproject.toml |
|
||||
| **Cloud Trace exporter configured** | 🟡 Broken | 403 permission errors (fixed in infra today) |
|
||||
| **FastAPI auto-instrumentation** | ✅ Working | HTTP requests create spans |
|
||||
| **HTTPX instrumentation** | ✅ Working | Outgoing HTTP calls traced |
|
||||
| **Job ID correlation in logs** | ❌ Missing | Can't filter logs by job ID |
|
||||
| **Worker tracing spans** | ❌ Missing | No spans in audio/lyrics workers |
|
||||
| **Custom metrics** | ❌ Missing | No Cloud Monitoring metrics |
|
||||
| **Dashboard** | ❌ Missing | No pre-built observability view |
|
||||
| **Alerting** | ❌ Missing | No alerts for job failures |
|
||||
|
||||
### What You Can Do Today
|
||||
|
||||
```bash
|
||||
# Query Cloud Logging for a specific job (manual grep)
|
||||
gcloud logging read 'resource.type="cloud_run_revision" AND textPayload:"JOB_ID"' \
|
||||
--project=nomadkaraoke --limit=100
|
||||
|
||||
# View traces (once permission is fixed)
|
||||
# Go to: https://console.cloud.google.com/traces/list?project=nomadkaraoke
|
||||
```
|
||||
|
||||
### What You Should Be Able To Do
|
||||
|
||||
1. Go to a dashboard, enter job ID → see entire job lifecycle
|
||||
2. Click trace → see waterfall of audio worker, lyrics worker, Cloud Tasks
|
||||
3. See metrics: jobs/hour, success rate, p95 latency by stage
|
||||
4. Get alerted when job failure rate exceeds threshold
|
||||
|
||||
---
|
||||
|
||||
## Current Implementation Analysis
|
||||
|
||||
### 1. Tracing Infrastructure (Exists, Partially Working)
|
||||
|
||||
**File: `backend/services/tracing.py`**
|
||||
|
||||
```python
|
||||
# Good: SDK is set up, exporter is configured
|
||||
setup_tracing(service_name="karaoke-backend", service_version=VERSION)
|
||||
|
||||
# Good: Utility functions exist
|
||||
@traced("my-function") # Decorator for automatic spans
|
||||
with create_span("operation", {"job_id": job_id}): # Context manager
|
||||
add_span_attribute("key", "value") # Add to current span
|
||||
```
|
||||
|
||||
**Problem:** These utilities are barely used! Only `backend/api/routes/review.py` actually creates spans for business logic. The critical workers (`audio_worker.py`, `lyrics_worker.py`, etc.) have zero tracing.
|
||||
|
||||
### 2. Logging Infrastructure (Exists, Not Correlated)
|
||||
|
||||
**File: `backend/workers/worker_logging.py`**
|
||||
|
||||
```python
|
||||
# Good: Logs go to Firestore for CLI streaming
|
||||
class JobLogHandler(logging.Handler):
|
||||
"""Forwards logs to Firestore job document"""
|
||||
|
||||
# Good: Context vars prevent log mixing in concurrent jobs
|
||||
with job_logging_context(job_id):
|
||||
# logs isolated per job
|
||||
```
|
||||
|
||||
**Problem:** Logs go to Firestore for CLI display, but Cloud Logging has no job_id label. You can't filter Cloud Logging by job ID.
|
||||
|
||||
### 3. Permission Issues (Fixed Today)
|
||||
|
||||
The Cloud Trace exporter was failing with 403 errors because the Cloud Run service account lacked `roles/cloudtrace.agent`. This was just fixed in `infrastructure/__main__.py`:
|
||||
|
||||
```python
|
||||
# NEW: Added today
|
||||
cloud_trace_iam = gcp.projects.IAMMember(
|
||||
"karaoke-backend-cloudtrace-agent",
|
||||
role="roles/cloudtrace.agent",
|
||||
...
|
||||
)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Gap Analysis: What's Missing
|
||||
|
||||
### Gap 1: No Trace Context Propagation to Workers
|
||||
|
||||
When Cloud Tasks triggers a worker (audio, lyrics), a new trace is started. The parent trace from the initial API call is lost.
|
||||
|
||||
```
|
||||
Current:
|
||||
POST /uploads-complete → Trace A
|
||||
↓ (Cloud Task)
|
||||
POST /internal/workers/audio → NEW Trace B (no link to A!)
|
||||
```
|
||||
|
||||
**Should be:**
|
||||
```
|
||||
POST /uploads-complete → Trace A
|
||||
↓ (Cloud Task - propagates trace context)
|
||||
POST /internal/workers/audio → Trace A, Span B (child of A)
|
||||
```
|
||||
|
||||
### Gap 2: No Job ID on Traces
|
||||
|
||||
Even when traces exist, they don't have `job_id` as a searchable attribute. You can't search Cloud Trace for "all spans for job 8f03f0ac".
|
||||
|
||||
### Gap 3: No Custom Spans in Workers
|
||||
|
||||
The workers just log text. There are no spans for:
|
||||
- Audio download duration
|
||||
- Modal API call duration
|
||||
- GCS upload duration
|
||||
- Lyrics transcription duration
|
||||
- Each processing stage
|
||||
|
||||
### Gap 4: No Structured Logging with Job Context
|
||||
|
||||
Cloud Logging receives unstructured text logs. Should be structured JSON with `job_id`, `worker`, `stage` fields for filtering.
|
||||
|
||||
### Gap 5: No Metrics
|
||||
|
||||
No custom Cloud Monitoring metrics for:
|
||||
- Jobs started/completed/failed per hour
|
||||
- Processing time by stage (p50, p95, p99)
|
||||
- Queue depth
|
||||
- Error rates
|
||||
|
||||
### Gap 6: No Dashboard
|
||||
|
||||
No Cloud Console dashboard showing:
|
||||
- Active jobs
|
||||
- Success/failure rates
|
||||
- Latency distribution
|
||||
- Worker health
|
||||
|
||||
### Gap 7: No Alerting
|
||||
|
||||
No alerts for:
|
||||
- Job stuck in status > X minutes
|
||||
- Error rate spike
|
||||
- Worker health degradation
|
||||
|
||||
---
|
||||
|
||||
## Implementation Plan
|
||||
|
||||
### Phase 1: Fix Core Tracing (2-3 hours) ⭐ High Priority
|
||||
|
||||
**Goal:** Every job should have a single trace that spans its entire lifecycle.
|
||||
|
||||
#### 1.1 Propagate Trace Context Through Cloud Tasks
|
||||
|
||||
**File: `backend/services/worker_service.py`**
|
||||
|
||||
```python
|
||||
from opentelemetry.trace.propagation.tracecontext import TraceContextTextMapPropagator
|
||||
from opentelemetry import trace
|
||||
|
||||
def _enqueue_cloud_task(self, queue: str, endpoint: str, payload: Dict, ...):
|
||||
# Get current trace context
|
||||
propagator = TraceContextTextMapPropagator()
|
||||
carrier = {}
|
||||
propagator.inject(carrier) # Injects traceparent header
|
||||
|
||||
# Add trace context to task headers
|
||||
headers = {
|
||||
"Authorization": f"Bearer {admin_token}",
|
||||
"Content-Type": "application/json",
|
||||
**carrier, # Add traceparent, tracestate
|
||||
}
|
||||
|
||||
task = {
|
||||
"http_request": {
|
||||
"http_method": "POST",
|
||||
"url": url,
|
||||
"headers": headers, # Now includes trace context
|
||||
"body": base64.b64encode(json.dumps(payload).encode()).decode(),
|
||||
},
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
**File: `backend/api/routes/internal.py`**
|
||||
|
||||
```python
|
||||
from opentelemetry.trace.propagation.tracecontext import TraceContextTextMapPropagator
|
||||
from opentelemetry import trace
|
||||
|
||||
@router.post("/workers/audio")
|
||||
async def trigger_audio_worker(request: Request, ...):
|
||||
# Extract trace context from headers
|
||||
propagator = TraceContextTextMapPropagator()
|
||||
context = propagator.extract(request.headers)
|
||||
|
||||
# Create span as child of propagated context
|
||||
with tracer.start_as_current_span(
|
||||
"audio-worker",
|
||||
context=context,
|
||||
attributes={"job_id": payload.job_id}
|
||||
):
|
||||
await process_audio_separation(payload.job_id)
|
||||
```
|
||||
|
||||
#### 1.2 Add Job ID to All Spans
|
||||
|
||||
Create a helper that adds job_id as a span attribute:
|
||||
|
||||
```python
|
||||
# backend/services/tracing.py
|
||||
|
||||
def job_span(name: str, job_id: str, **extra_attributes):
|
||||
"""Create a span with job_id attribute for easy filtering."""
|
||||
return create_span(name, {
|
||||
"job_id": job_id,
|
||||
"service.operation": name,
|
||||
**extra_attributes
|
||||
})
|
||||
```
|
||||
|
||||
Usage in workers:
|
||||
|
||||
```python
|
||||
# backend/workers/audio_worker.py
|
||||
|
||||
async def process_audio_separation(job_id: str):
|
||||
with job_span("audio-worker", job_id) as span:
|
||||
span.set_attribute("worker", "audio")
|
||||
|
||||
with job_span("download-audio", job_id):
|
||||
# download logic
|
||||
pass
|
||||
|
||||
with job_span("modal-separation", job_id):
|
||||
# Modal API call
|
||||
pass
|
||||
|
||||
with job_span("upload-stems", job_id):
|
||||
# GCS upload
|
||||
pass
|
||||
```
|
||||
|
||||
### Phase 2: Instrument All Workers (3-4 hours) ⭐ High Priority
|
||||
|
||||
Add spans to every worker following this pattern:
|
||||
|
||||
#### Audio Worker (`audio_worker.py`)
|
||||
|
||||
```python
|
||||
async def process_audio_separation(job_id: str):
|
||||
with job_span("audio-worker", job_id) as root:
|
||||
# Stage 1: Download/Get Audio
|
||||
with job_span("get-audio-file", job_id) as span:
|
||||
if job.audio_url:
|
||||
span.set_attribute("source", "url")
|
||||
with job_span("download-from-url", job_id):
|
||||
audio_path = await download_from_url(...)
|
||||
else:
|
||||
span.set_attribute("source", "gcs")
|
||||
with job_span("download-from-gcs", job_id):
|
||||
audio_path = storage.download_file(...)
|
||||
|
||||
# Stage 2: Audio Separation
|
||||
with job_span("audio-separation", job_id) as span:
|
||||
with job_span("clean-instrumental", job_id):
|
||||
# First separation pass
|
||||
pass
|
||||
with job_span("backing-vocals", job_id):
|
||||
# Second separation pass
|
||||
pass
|
||||
|
||||
# Stage 3: Upload Results
|
||||
with job_span("upload-stems", job_id) as span:
|
||||
span.set_attribute("stem_count", len(stems))
|
||||
for stem_name, stem_path in stems.items():
|
||||
with job_span("upload-stem", job_id, stem_name=stem_name):
|
||||
storage.upload_file(...)
|
||||
```
|
||||
|
||||
#### Lyrics Worker (`lyrics_worker.py`)
|
||||
|
||||
```python
|
||||
async def process_lyrics_transcription(job_id: str):
|
||||
with job_span("lyrics-worker", job_id) as root:
|
||||
with job_span("get-vocals", job_id):
|
||||
# Download vocals from GCS
|
||||
pass
|
||||
|
||||
with job_span("audioshake-transcription", job_id):
|
||||
# AudioShake API call
|
||||
pass
|
||||
|
||||
with job_span("fetch-genius-lyrics", job_id) as span:
|
||||
span.set_attribute("artist", artist)
|
||||
span.set_attribute("title", title)
|
||||
# Genius API call
|
||||
pass
|
||||
|
||||
with job_span("auto-correction", job_id):
|
||||
# LyricsTranscriber correction
|
||||
pass
|
||||
|
||||
with job_span("upload-corrections", job_id):
|
||||
# Upload corrections.json
|
||||
pass
|
||||
```
|
||||
|
||||
### Phase 3: Structured Logging with Job Context (1-2 hours)
|
||||
|
||||
Replace text logs with structured JSON that includes job context.
|
||||
|
||||
**File: `backend/main.py`**
|
||||
|
||||
```python
|
||||
import json
|
||||
import logging
|
||||
|
||||
class StructuredFormatter(logging.Formatter):
|
||||
"""JSON formatter with trace correlation."""
|
||||
|
||||
def format(self, record):
|
||||
from backend.services.tracing import get_current_trace_id, get_current_span_id
|
||||
|
||||
log_entry = {
|
||||
"timestamp": self.formatTime(record),
|
||||
"severity": record.levelname,
|
||||
"message": record.getMessage(),
|
||||
"logger": record.name,
|
||||
# Trace correlation
|
||||
"logging.googleapis.com/trace": f"projects/nomadkaraoke/traces/{get_current_trace_id()}" if get_current_trace_id() else None,
|
||||
"logging.googleapis.com/spanId": get_current_span_id(),
|
||||
# Custom fields (if available in log record)
|
||||
"job_id": getattr(record, 'job_id', None),
|
||||
"worker": getattr(record, 'worker', None),
|
||||
}
|
||||
return json.dumps({k: v for k, v in log_entry.items() if v is not None})
|
||||
|
||||
# Configure in Cloud Run
|
||||
if os.environ.get("K_SERVICE"):
|
||||
handler = logging.StreamHandler()
|
||||
handler.setFormatter(StructuredFormatter())
|
||||
logging.root.handlers = [handler]
|
||||
```
|
||||
|
||||
Now logs in Cloud Logging can be filtered:
|
||||
```
|
||||
jsonPayload.job_id="8f03f0ac"
|
||||
```
|
||||
|
||||
### Phase 4: Custom Metrics (2-3 hours) 🟡 Medium Priority
|
||||
|
||||
Add Cloud Monitoring metrics for key indicators.
|
||||
|
||||
**File: `backend/services/metrics.py`**
|
||||
|
||||
```python
|
||||
from opentelemetry import metrics
|
||||
from opentelemetry.sdk.metrics import MeterProvider
|
||||
from opentelemetry.exporter.cloud_monitoring import CloudMonitoringMetricsExporter
|
||||
|
||||
def setup_metrics():
|
||||
exporter = CloudMonitoringMetricsExporter(project_id="nomadkaraoke")
|
||||
provider = MeterProvider(metric_readers=[...])
|
||||
metrics.set_meter_provider(provider)
|
||||
|
||||
meter = metrics.get_meter("karaoke-backend")
|
||||
|
||||
# Counter: Jobs by status
|
||||
jobs_counter = meter.create_counter(
|
||||
"jobs_total",
|
||||
description="Total jobs by status",
|
||||
unit="1"
|
||||
)
|
||||
|
||||
# Histogram: Processing duration by stage
|
||||
duration_histogram = meter.create_histogram(
|
||||
"job_stage_duration_seconds",
|
||||
description="Duration of job processing stages",
|
||||
unit="s"
|
||||
)
|
||||
|
||||
return {
|
||||
"jobs": jobs_counter,
|
||||
"duration": duration_histogram,
|
||||
}
|
||||
|
||||
# Usage
|
||||
metrics["jobs"].add(1, {"status": "completed", "worker": "audio"})
|
||||
metrics["duration"].record(45.2, {"stage": "audio-separation", "job_id": job_id})
|
||||
```
|
||||
|
||||
**Metrics to track:**
|
||||
|
||||
| Metric | Type | Labels |
|
||||
|--------|------|--------|
|
||||
| `jobs_total` | Counter | status, source (upload/url/search) |
|
||||
| `job_stage_duration_seconds` | Histogram | stage, worker |
|
||||
| `worker_invocations_total` | Counter | worker, success/failure |
|
||||
| `gcs_operations_total` | Counter | operation (upload/download), bucket |
|
||||
| `external_api_duration_seconds` | Histogram | api (modal/audioshake/genius) |
|
||||
|
||||
### Phase 5: Dashboard & Alerting (2-3 hours) 🟡 Medium Priority
|
||||
|
||||
#### Create Cloud Monitoring Dashboard
|
||||
|
||||
**File: `infrastructure/monitoring/dashboard.json`**
|
||||
|
||||
```json
|
||||
{
|
||||
"displayName": "Karaoke Backend Overview",
|
||||
"dashboardFilters": [],
|
||||
"mosaicLayout": {
|
||||
"columns": 12,
|
||||
"tiles": [
|
||||
{
|
||||
"title": "Active Jobs by Status",
|
||||
"scorecard": {
|
||||
"timeSeriesQuery": {
|
||||
"prometheusQuery": "sum by (status) (jobs_total)"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Job Processing Time (p95)",
|
||||
"xyChart": {
|
||||
"dataSets": [{
|
||||
"timeSeriesQuery": {
|
||||
"prometheusQuery": "histogram_quantile(0.95, rate(job_stage_duration_seconds_bucket[5m]))"
|
||||
}
|
||||
}]
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Error Rate",
|
||||
"xyChart": {
|
||||
"dataSets": [{
|
||||
"timeSeriesQuery": {
|
||||
"prometheusQuery": "rate(worker_invocations_total{success=\"false\"}[5m]) / rate(worker_invocations_total[5m])"
|
||||
}
|
||||
}]
|
||||
}
|
||||
},
|
||||
{
|
||||
"title": "Cloud Tasks Queue Depth",
|
||||
"xyChart": {
|
||||
"dataSets": [{
|
||||
"timeSeriesQuery": {
|
||||
"prometheusQuery": "cloud_tasks_queue_depth"
|
||||
}
|
||||
}]
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
#### Create Alerts
|
||||
|
||||
**File: `infrastructure/__main__.py`** (Pulumi)
|
||||
|
||||
```python
|
||||
# Alert: Job failure rate > 10%
|
||||
job_failure_alert = gcp.monitoring.AlertPolicy(
|
||||
"job-failure-rate-alert",
|
||||
display_name="High Job Failure Rate",
|
||||
conditions=[
|
||||
gcp.monitoring.AlertPolicyConditionArgs(
|
||||
display_name="Failure rate > 10%",
|
||||
condition_threshold=gcp.monitoring.AlertPolicyConditionConditionThresholdArgs(
|
||||
filter='metric.type="custom.googleapis.com/karaoke/job_failure_rate"',
|
||||
comparison="COMPARISON_GT",
|
||||
threshold_value=0.1,
|
||||
duration="300s",
|
||||
),
|
||||
),
|
||||
],
|
||||
notification_channels=[...], # Slack, email, etc.
|
||||
)
|
||||
|
||||
# Alert: Job stuck in processing > 30 min
|
||||
stuck_job_alert = gcp.monitoring.AlertPolicy(
|
||||
"stuck-job-alert",
|
||||
display_name="Job Stuck in Processing",
|
||||
conditions=[
|
||||
gcp.monitoring.AlertPolicyConditionArgs(
|
||||
display_name="Job > 30 min in processing state",
|
||||
condition_threshold=gcp.monitoring.AlertPolicyConditionConditionThresholdArgs(
|
||||
filter='metric.type="custom.googleapis.com/karaoke/job_age_seconds" AND metric.labels.status!="complete"',
|
||||
comparison="COMPARISON_GT",
|
||||
threshold_value=1800,
|
||||
duration="60s",
|
||||
),
|
||||
),
|
||||
],
|
||||
)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Quick Wins (Do First)
|
||||
|
||||
These give the most debugging value with minimal effort:
|
||||
|
||||
### 1. Add Job ID to Worker Logs (30 min)
|
||||
|
||||
Simplest possible fix - add job_id to every log message:
|
||||
|
||||
```python
|
||||
# backend/workers/audio_worker.py
|
||||
logger.info(f"[job:{job_id}] Starting audio separation")
|
||||
logger.info(f"[job:{job_id}] Downloaded audio file: {path}")
|
||||
logger.info(f"[job:{job_id}] Modal separation complete")
|
||||
```
|
||||
|
||||
Now you can grep:
|
||||
```bash
|
||||
gcloud logging read 'textPayload:"[job:8f03f0ac]"' --project=nomadkaraoke
|
||||
```
|
||||
|
||||
### 2. Log Worker Start/End with Timing (30 min)
|
||||
|
||||
```python
|
||||
import time
|
||||
|
||||
async def process_audio_separation(job_id: str):
|
||||
start = time.time()
|
||||
logger.info(f"[job:{job_id}] WORKER_START worker=audio")
|
||||
|
||||
try:
|
||||
# ... processing ...
|
||||
|
||||
duration = time.time() - start
|
||||
logger.info(f"[job:{job_id}] WORKER_END worker=audio status=success duration={duration:.1f}s")
|
||||
except Exception as e:
|
||||
duration = time.time() - start
|
||||
logger.error(f"[job:{job_id}] WORKER_END worker=audio status=error duration={duration:.1f}s error={e}")
|
||||
raise
|
||||
```
|
||||
|
||||
Now you can easily find failed workers:
|
||||
```bash
|
||||
gcloud logging read 'textPayload:"WORKER_END" AND textPayload:"status=error"' --project=nomadkaraoke
|
||||
```
|
||||
|
||||
### 3. Enable Cloud Trace Viewing (0 min - just fixed!)
|
||||
|
||||
With the IAM permission fix deployed today, Cloud Trace should start working. Visit:
|
||||
https://console.cloud.google.com/traces/list?project=nomadkaraoke
|
||||
|
||||
---
|
||||
|
||||
## Summary: Implementation Priority
|
||||
|
||||
| Phase | Effort | Value | Priority |
|
||||
|-------|--------|-------|----------|
|
||||
| Quick Win #1: Job ID in logs | 30 min | High | ⭐ Do now |
|
||||
| Quick Win #2: Worker timing | 30 min | High | ⭐ Do now |
|
||||
| Phase 1: Trace propagation | 2-3 hrs | Very High | ⭐ Do soon |
|
||||
| Phase 2: Instrument workers | 3-4 hrs | Very High | ⭐ Do soon |
|
||||
| Phase 3: Structured logging | 1-2 hrs | Medium | 🟡 Nice to have |
|
||||
| Phase 4: Custom metrics | 2-3 hrs | Medium | 🟡 Nice to have |
|
||||
| Phase 5: Dashboard & alerts | 2-3 hrs | Medium | 🟡 Nice to have |
|
||||
|
||||
**Total for full observability: ~12-15 hours**
|
||||
|
||||
**Minimum viable observability (Quick Wins + Phase 1-2): ~5-6 hours**
|
||||
|
||||
---
|
||||
|
||||
## Appendix: GCP Observability Resources
|
||||
|
||||
- **Cloud Trace:** https://console.cloud.google.com/traces/list?project=nomadkaraoke
|
||||
- **Cloud Logging:** https://console.cloud.google.com/logs?project=nomadkaraoke
|
||||
- **Cloud Monitoring:** https://console.cloud.google.com/monitoring?project=nomadkaraoke
|
||||
- **OpenTelemetry Python Docs:** https://opentelemetry.io/docs/instrumentation/python/
|
||||
- **Cloud Trace Python:** https://cloud.google.com/trace/docs/setup/python-ot
|
||||
|
||||
### Useful Log Queries
|
||||
|
||||
```
|
||||
# All logs for a specific job
|
||||
resource.type="cloud_run_revision" AND textPayload:"JOB_ID"
|
||||
|
||||
# All worker starts
|
||||
resource.type="cloud_run_revision" AND textPayload:"WORKER_START"
|
||||
|
||||
# All errors
|
||||
resource.type="cloud_run_revision" AND severity>=ERROR
|
||||
|
||||
# Cloud Tasks failures
|
||||
resource.type="cloud_tasks_queue"
|
||||
|
||||
# Trace-correlated logs (after structured logging)
|
||||
jsonPayload.job_id="JOB_ID"
|
||||
```
|
||||
|
||||
@@ -0,0 +1,143 @@
|
||||
# Refactor: Unify Audio Fetcher Code
|
||||
|
||||
**Created:** 2025-12-20
|
||||
**Completed:** 2025-12-20
|
||||
**Priority:** MEDIUM (prevents future bugs like YouTubeProvider -> YoutubeProvider)
|
||||
**Status:** ✅ Completed
|
||||
|
||||
## Problem
|
||||
|
||||
The codebase has **two separate implementations** of flacfetch integration:
|
||||
1. `karaoke_gen/audio_fetcher.py` - Used by local CLI
|
||||
2. `backend/services/audio_search_service.py` - Used by cloud backend
|
||||
|
||||
This violates DRY and caused a bug where the backend's import wasn't updated when flacfetch renamed `YouTubeProvider` to `YoutubeProvider`.
|
||||
|
||||
## Current State
|
||||
|
||||
### Duplicated Code
|
||||
|
||||
| Component | Local (`audio_fetcher.py`) | Backend (`audio_search_service.py`) |
|
||||
|-----------|---------------------------|-------------------------------------|
|
||||
| `_get_manager()` | ✅ 40 lines | ❌ 35 lines (copy) |
|
||||
| Provider setup | ✅ RED, OPS, YouTube | ❌ Same, diverged |
|
||||
| `search()` | ✅ Full implementation | ❌ Similar, diverged |
|
||||
| `download()` | ✅ With downloaders | ⚠️ Different, simpler |
|
||||
| `AudioSearchResult` | ✅ Dataclass | ❌ Duplicate, different fields |
|
||||
| `AudioDownloadResult` | ✅ (`AudioFetchResult`) | ❌ Duplicate |
|
||||
| Exceptions | ✅ 4 types | ❌ 3 types, different names |
|
||||
|
||||
### Drift Examples
|
||||
- Backend missing `raw_result` field on `AudioSearchResult`
|
||||
- Backend has `index` field, local doesn't
|
||||
- Backend exceptions inherit from `AudioSearchError`, local from `AudioFetcherError`
|
||||
- Backend missing `UserCancelledError`
|
||||
- Backend missing downloader registration (TorrentDownloader, YoutubeDownloader)
|
||||
|
||||
## Proposed Solution
|
||||
|
||||
### Option 1: Backend imports from karaoke_gen (Recommended)
|
||||
|
||||
The backend already depends on `karaoke_gen` (installed via `pip install -e .` in Dockerfile).
|
||||
|
||||
```python
|
||||
# backend/services/audio_search_service.py - REFACTORED
|
||||
|
||||
from karaoke_gen.audio_fetcher import (
|
||||
FlacFetcher,
|
||||
AudioSearchResult,
|
||||
AudioFetchResult,
|
||||
AudioFetcherError,
|
||||
NoResultsError,
|
||||
DownloadError,
|
||||
)
|
||||
|
||||
class AudioSearchService:
|
||||
"""
|
||||
Thin wrapper around karaoke_gen.audio_fetcher.FlacFetcher.
|
||||
|
||||
Adds backend-specific functionality:
|
||||
- Firestore serialization (to_dict/from_dict)
|
||||
- GCS integration for downloads
|
||||
- Job state management
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
red_api_key: Optional[str] = None,
|
||||
red_api_url: Optional[str] = None,
|
||||
ops_api_key: Optional[str] = None,
|
||||
):
|
||||
self._fetcher = FlacFetcher(
|
||||
red_api_key=red_api_key,
|
||||
red_api_url=red_api_url,
|
||||
ops_api_key=ops_api_key,
|
||||
)
|
||||
|
||||
def search(self, artist: str, title: str) -> List[AudioSearchResult]:
|
||||
"""Delegate to FlacFetcher.search()."""
|
||||
return self._fetcher.search(artist, title)
|
||||
|
||||
def select_best(self, results: List[AudioSearchResult]) -> int:
|
||||
"""Delegate to FlacFetcher.select_best()."""
|
||||
return self._fetcher.select_best(results)
|
||||
|
||||
def download(
|
||||
self,
|
||||
result: AudioSearchResult,
|
||||
output_dir: str,
|
||||
output_filename: Optional[str] = None,
|
||||
) -> AudioFetchResult:
|
||||
"""Delegate to FlacFetcher.download()."""
|
||||
return self._fetcher.download(result, output_dir, output_filename)
|
||||
```
|
||||
|
||||
### Changes Required to karaoke_gen.audio_fetcher
|
||||
|
||||
1. **Add `to_dict()` method to `AudioSearchResult`** - For Firestore serialization
|
||||
2. **Add `from_dict()` classmethod** - For deserialization
|
||||
3. **Ensure `select_best()` is a standalone method** - Currently buried in interactive flow
|
||||
4. **Export all public classes from `__init__.py`**
|
||||
|
||||
### Changes Required to backend
|
||||
|
||||
1. **Remove duplicate dataclasses** - Use imports from karaoke_gen
|
||||
2. **Remove duplicate `_get_manager()`** - Delegate to FlacFetcher
|
||||
3. **Remove duplicate exception classes** - Use karaoke_gen exceptions
|
||||
4. **Update tests** - Point to real classes, not mocks
|
||||
|
||||
## Benefits
|
||||
|
||||
1. **Single source of truth** - Bug fixes apply everywhere
|
||||
2. **No more drift** - Dataclasses, exceptions stay in sync
|
||||
3. **Better test coverage** - karaoke_gen has integration tests for flacfetch imports
|
||||
4. **Less code to maintain** - Backend becomes thin wrapper
|
||||
|
||||
## Migration Steps
|
||||
|
||||
1. [x] Add `to_dict()` / `from_dict()` to `AudioSearchResult` in karaoke_gen
|
||||
2. [x] Extract `select_best()` as standalone method in FlacFetcher
|
||||
3. [x] Update karaoke_gen `__init__.py` exports (with lazy imports)
|
||||
4. [x] Refactor backend to import from karaoke_gen
|
||||
5. [x] Update backend tests
|
||||
6. [x] Delete duplicate code from backend (~150 lines removed)
|
||||
7. [x] Add integration test that catches import divergence
|
||||
|
||||
## Related Files
|
||||
|
||||
- `karaoke_gen/audio_fetcher.py` - Source of truth (keep)
|
||||
- `backend/services/audio_search_service.py` - Refactor to thin wrapper
|
||||
- `backend/api/routes/audio_search.py` - Update imports
|
||||
- `backend/tests/test_audio_search.py` - Update tests
|
||||
|
||||
## Estimated Effort
|
||||
|
||||
- **Time:** 2-4 hours
|
||||
- **Risk:** Low (well-defined changes, good test coverage)
|
||||
- **Dependencies:** None
|
||||
|
||||
## Related Architecture Docs
|
||||
|
||||
- `docs/01-reference/ARCHITECTURE.md` - "LyricsTranscriber Integration" section shows similar pattern
|
||||
- `docs/00-current-plan/SCALABLE-ARCHITECTURE-PLAN.md` - "Shared pipeline architecture" goal
|
||||
|
||||
@@ -0,0 +1,827 @@
|
||||
# Scalable Architecture Plan
|
||||
|
||||
**Last Updated:** 2025-12-11
|
||||
**Status:** Phase 1 Complete - Cloud Tasks Enabled
|
||||
|
||||
This document outlines the plan for evolving karaoke-gen's cloud backend to support **100+ concurrent jobs** with no performance degradation, while also achieving a clean, maintainable codebase with proper separation of concerns.
|
||||
|
||||
---
|
||||
|
||||
## Executive Summary
|
||||
|
||||
After thorough codebase analysis, I recommend a **phased approach** that prioritizes infrastructure scalability first (Cloud Tasks), followed by incremental adoption of the existing pipeline architecture for code sharing.
|
||||
|
||||
### Key Findings
|
||||
|
||||
1. **The infrastructure problem is well-isolated** - WorkerService already abstracts worker triggering behind HTTP calls
|
||||
2. **Pipeline architecture exists but is underutilized** - `karaoke_gen/pipeline/` has well-designed stages and executors, but backend workers don't use them
|
||||
3. **RemoteExecutor is a placeholder** - It submits jobs to the backend but doesn't execute stages remotely
|
||||
4. **Workers are self-contained** - Each worker only needs `job_id` and fetches everything from Firestore/GCS
|
||||
|
||||
### Recommended Priority
|
||||
|
||||
1. **Phase 1 (HIGH): Cloud Tasks Integration** - Solves the scalability problem immediately
|
||||
2. **Phase 2 (MEDIUM): Cloud Run Jobs for Video** - Removes 30-min timeout constraint
|
||||
3. **Phase 3 (LOW): Pipeline Unification** - Nice-to-have for code maintainability
|
||||
|
||||
---
|
||||
|
||||
## Goals
|
||||
|
||||
### Infrastructure Goals
|
||||
1. **Horizontal scalability** - Each job gets dedicated resources (no resource contention)
|
||||
2. **Maximum processing speed** - Same speed for 1 job or 100 concurrent jobs
|
||||
3. **Reliability** - Automatic retries, no lost jobs from container restarts
|
||||
4. **Cost efficiency** - Scale to zero when idle, pay only for active processing
|
||||
|
||||
### Software Architecture Goals
|
||||
1. **SOLID principles** - Single responsibility, clean interfaces
|
||||
2. **DRY** - Share code between local CLI and remote backend
|
||||
3. **Testability** - Each component independently testable
|
||||
4. **Maintainability** - Bug fixes apply everywhere, easy to add features
|
||||
|
||||
---
|
||||
|
||||
## Current Architecture Analysis
|
||||
|
||||
### What Works Well
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────────────────────┐
|
||||
│ CURRENT ARCHITECTURE (v0.71.x) │
|
||||
├─────────────────────────────────────────────────────────────────────────────┤
|
||||
│ │
|
||||
│ ✅ Heavy work already offloaded to external services: │
|
||||
│ │
|
||||
│ Audio Separation ──────────────────▶ Modal API (GPU, ~5-8 min) │
|
||||
│ Lyrics Transcription ──────────────▶ AudioShake API (~2-3 min) │
|
||||
│ │
|
||||
│ ✅ State persistence in Firestore (survives restarts) │
|
||||
│ ✅ Files in GCS (no local storage dependencies) │
|
||||
│ ✅ Internal HTTP endpoints exist for worker triggers │
|
||||
│ ✅ Workers are self-contained (only need job_id) │
|
||||
│ ✅ WorkerService abstracts HTTP calls │
|
||||
│ ✅ Pipeline stages exist in karaoke_gen/pipeline/ │
|
||||
│ ✅ LocalExecutor for CLI, RemoteExecutor placeholder ready │
|
||||
│ │
|
||||
└─────────────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### Current Code Structure
|
||||
|
||||
```
|
||||
WorkerService (backend/services/worker_service.py)
|
||||
│
|
||||
└── trigger_worker(worker_type, job_id)
|
||||
│
|
||||
└── HTTP POST /api/internal/workers/{worker_type}
|
||||
│
|
||||
└── BackgroundTasks.add_task(process_xxx, job_id) ⚠️ PROBLEM
|
||||
```
|
||||
|
||||
The **single point of change** is `WorkerService.trigger_worker()`. Currently it:
|
||||
1. Makes HTTP POST to internal endpoint
|
||||
2. Internal endpoint adds to FastAPI BackgroundTasks
|
||||
3. BackgroundTask runs in same container (problem!)
|
||||
|
||||
### Current Limitations
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────────────────────┐
|
||||
│ CURRENT FLOW (PROBLEMATIC) │
|
||||
├─────────────────────────────────────────────────────────────────────────────┤
|
||||
│ │
|
||||
│ POST /api/jobs/upload │
|
||||
│ │ │
|
||||
│ ├──▶ Save job to Firestore ✅ │
|
||||
│ │ │
|
||||
│ └──▶ BackgroundTasks.add_task(trigger_workers) │
|
||||
│ │ │
|
||||
│ └──▶ HTTP POST /api/internal/workers/audio │
|
||||
│ │ │
|
||||
│ └──▶ BackgroundTasks.add_task(process_audio) ⚠️ │
|
||||
│ │ │
|
||||
│ └── Runs IN THE SAME CONTAINER │
|
||||
│ as the API request handler │
|
||||
│ │
|
||||
│ PROBLEMS: │
|
||||
│ ⚠️ Container may be killed before background tasks complete │
|
||||
│ ⚠️ No guaranteed delivery - if container crashes, job is lost │
|
||||
│ ⚠️ Multiple concurrent jobs share CPU/memory (resource contention) │
|
||||
│ ⚠️ Long-running video encoding (15-20 min) vulnerable to timeouts │
|
||||
│ ⚠️ FFmpeg renders compete for resources when jobs run in parallel │
|
||||
│ │
|
||||
└─────────────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### Existing Pipeline Architecture (Underutilized)
|
||||
|
||||
The codebase already has a well-designed pipeline system:
|
||||
|
||||
```
|
||||
karaoke_gen/pipeline/
|
||||
├── base.py # PipelineStage, StageResult, PipelineExecutor abstracts
|
||||
├── context.py # PipelineContext for shared state
|
||||
├── executors/
|
||||
│ ├── local.py # LocalExecutor - runs stages in-process (for CLI)
|
||||
│ └── remote.py # RemoteExecutor - placeholder for backend integration
|
||||
└── stages/
|
||||
├── separation.py # SeparationStage - wraps AudioProcessor
|
||||
├── transcription.py # TranscriptionStage - wraps LyricsProcessor
|
||||
├── screens.py # ScreensStage - title/end screens
|
||||
├── render.py # RenderStage - lyrics video
|
||||
└── finalize.py # FinalizeStage - wraps KaraokeFinalise
|
||||
```
|
||||
|
||||
**However**: Backend workers (`backend/workers/*.py`) don't use these stages - they directly call the underlying processors. This creates two parallel implementations.
|
||||
|
||||
---
|
||||
|
||||
## Recommended Architecture
|
||||
|
||||
### Decision: Cloud Tasks First
|
||||
|
||||
**Why Cloud Tasks over Pub/Sub or Workflows:**
|
||||
|
||||
| Feature | Cloud Tasks | Pub/Sub | Workflows |
|
||||
|---------|-------------|---------|-----------|
|
||||
| HTTP delivery | ✅ Native | Requires push subscription | N/A |
|
||||
| Retry control | ✅ Built-in | Manual | Built-in |
|
||||
| Rate limiting | ✅ Built-in | Manual | N/A |
|
||||
| Timeout (max) | 30 min | 10 min ack deadline | 1 year |
|
||||
| Complexity | Low | Medium | High |
|
||||
| Cost | Very low | Low | Medium |
|
||||
| Existing code changes | Minimal | Medium | High |
|
||||
|
||||
**Cloud Tasks is the right choice because:**
|
||||
1. Workers already have HTTP endpoints - Cloud Tasks delivers HTTP requests
|
||||
2. Need rate limiting to protect Modal/AudioShake APIs
|
||||
3. Built-in retries with configurable backoff
|
||||
4. Minimal code changes (update WorkerService only)
|
||||
|
||||
### Target Architecture
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────────────────────┐
|
||||
│ CLOUD TASKS + CLOUD RUN JOBS ARCHITECTURE │
|
||||
├─────────────────────────────────────────────────────────────────────────────┤
|
||||
│ │
|
||||
│ POST /api/jobs/upload │
|
||||
│ │ │
|
||||
│ ├──▶ Save job to Firestore │
|
||||
│ │ │
|
||||
│ └──▶ WorkerService.trigger_worker() │
|
||||
│ │ │
|
||||
│ │ if ENABLE_CLOUD_TASKS: │
|
||||
│ │ └──▶ Enqueue Cloud Task │
|
||||
│ │ │ │
|
||||
│ │ ├──▶ audio-worker-queue │
|
||||
│ │ │ {job_id, target: /internal/workers/audio} │
|
||||
│ │ │ │
|
||||
│ │ └──▶ lyrics-worker-queue │
|
||||
│ │ {job_id, target: /internal/workers/lyrics}│
|
||||
│ │ │
|
||||
│ │ else: (development/testing) │
|
||||
│ │ └──▶ HTTP POST directly (existing behavior) │
|
||||
│ │ │
|
||||
│ ┌──────────▼────────────────────────────────────────────────────────┐ │
|
||||
│ │ Cloud Tasks Queue │ │
|
||||
│ │ │ │
|
||||
│ │ • Guaranteed delivery (retries on failure) │ │
|
||||
│ │ • Rate limiting / concurrency control │ │
|
||||
│ │ • Task deduplication │ │
|
||||
│ │ • Configurable timeouts (up to 30 min per task) │ │
|
||||
│ └─────────────────────────────────┬───────────────────────────────────┘ │
|
||||
│ │ │
|
||||
│ ▼ │
|
||||
│ ┌─────────────────────────────────────────────────────────────────────┐ │
|
||||
│ │ Cloud Run (Auto-Scaled Worker Instances) │ │
|
||||
│ │ │ │
|
||||
│ │ Instance 1 Instance 2 Instance 3 ... │ │
|
||||
│ │ ┌──────────┐ ┌──────────┐ ┌──────────┐ │ │
|
||||
│ │ │ Job A │ │ Job B │ │ Job C │ │ │
|
||||
│ │ │ Audio │ │ Audio │ │ Lyrics │ │ │
|
||||
│ │ └──────────┘ └──────────┘ └──────────┘ │ │
|
||||
│ │ │ │
|
||||
│ │ Each task gets a DEDICATED container instance │ │
|
||||
│ │ • Full CPU/memory for that task alone │ │
|
||||
│ │ • No resource contention with other jobs │ │
|
||||
│ │ • Container lifecycle tied to task completion │ │
|
||||
│ └─────────────────────────────────────────────────────────────────────┘ │
|
||||
│ │
|
||||
│ For video encoding (>30 min timeout): │
|
||||
│ ┌─────────────────────────────────────────────────────────────────────┐ │
|
||||
│ │ Cloud Run Jobs (Long-Running) │ │
|
||||
│ │ │ │
|
||||
│ │ • Up to 24 hour timeout │ │
|
||||
│ │ • Separate from API service │ │
|
||||
│ │ • Higher CPU/memory (4 vCPU, 8GB) │ │
|
||||
│ │ • Triggered via gcloud or API │ │
|
||||
│ └─────────────────────────────────────────────────────────────────────┘ │
|
||||
│ │
|
||||
└─────────────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Implementation Plan
|
||||
|
||||
### Phase 1: Cloud Tasks Integration (HIGH Priority)
|
||||
|
||||
**Goal:** Enable 100+ concurrent jobs with no performance degradation
|
||||
|
||||
**Effort:** 2-3 days | **Risk:** Low (feature-flagged, easy rollback)
|
||||
|
||||
#### Step 1.1: Add Cloud Tasks Infrastructure (Pulumi)
|
||||
|
||||
```python
|
||||
# infrastructure/__main__.py additions
|
||||
|
||||
from pulumi_gcp import cloudtasks
|
||||
|
||||
# Create Cloud Tasks queues
|
||||
audio_worker_queue = cloudtasks.Queue(
|
||||
"audio-worker-queue",
|
||||
name="audio-worker-queue",
|
||||
location="us-central1",
|
||||
rate_limits=cloudtasks.QueueRateLimitsArgs(
|
||||
max_dispatches_per_second=10, # Protect Modal API
|
||||
max_concurrent_dispatches=50, # Max parallel audio workers
|
||||
),
|
||||
retry_config=cloudtasks.QueueRetryConfigArgs(
|
||||
max_attempts=3,
|
||||
min_backoff="10s",
|
||||
max_backoff="300s",
|
||||
max_retry_duration="1800s", # 30 min total retry window
|
||||
),
|
||||
)
|
||||
|
||||
lyrics_worker_queue = cloudtasks.Queue(
|
||||
"lyrics-worker-queue",
|
||||
name="lyrics-worker-queue",
|
||||
location="us-central1",
|
||||
rate_limits=cloudtasks.QueueRateLimitsArgs(
|
||||
max_dispatches_per_second=10,
|
||||
max_concurrent_dispatches=50,
|
||||
),
|
||||
retry_config=cloudtasks.QueueRetryConfigArgs(
|
||||
max_attempts=3,
|
||||
min_backoff="10s",
|
||||
max_backoff="300s",
|
||||
),
|
||||
)
|
||||
|
||||
screens_worker_queue = cloudtasks.Queue(
|
||||
"screens-worker-queue",
|
||||
name="screens-worker-queue",
|
||||
location="us-central1",
|
||||
rate_limits=cloudtasks.QueueRateLimitsArgs(
|
||||
max_dispatches_per_second=50, # Fast, CPU-light
|
||||
max_concurrent_dispatches=100,
|
||||
),
|
||||
retry_config=cloudtasks.QueueRetryConfigArgs(
|
||||
max_attempts=3,
|
||||
min_backoff="5s",
|
||||
max_backoff="60s",
|
||||
),
|
||||
)
|
||||
|
||||
render_worker_queue = cloudtasks.Queue(
|
||||
"render-worker-queue",
|
||||
name="render-worker-queue",
|
||||
location="us-central1",
|
||||
rate_limits=cloudtasks.QueueRateLimitsArgs(
|
||||
max_dispatches_per_second=5, # CPU-intensive
|
||||
max_concurrent_dispatches=20,
|
||||
),
|
||||
retry_config=cloudtasks.QueueRetryConfigArgs(
|
||||
max_attempts=2,
|
||||
min_backoff="30s",
|
||||
max_backoff="300s",
|
||||
max_retry_duration="3600s", # 60 min for render
|
||||
),
|
||||
)
|
||||
|
||||
video_worker_queue = cloudtasks.Queue(
|
||||
"video-worker-queue",
|
||||
name="video-worker-queue",
|
||||
location="us-central1",
|
||||
rate_limits=cloudtasks.QueueRateLimitsArgs(
|
||||
max_dispatches_per_second=3, # Very CPU-intensive
|
||||
max_concurrent_dispatches=10,
|
||||
),
|
||||
retry_config=cloudtasks.QueueRetryConfigArgs(
|
||||
max_attempts=2,
|
||||
min_backoff="60s",
|
||||
max_backoff="600s",
|
||||
max_retry_duration="7200s", # 2 hour total (video is long)
|
||||
),
|
||||
)
|
||||
|
||||
# Grant Cloud Tasks permission to invoke Cloud Run
|
||||
cloud_tasks_invoker = gcp.projects.IAMMember(
|
||||
"cloud-tasks-invoker",
|
||||
project=project_id,
|
||||
role="roles/run.invoker",
|
||||
member=f"serviceAccount:service-{project.number}@gcp-sa-cloudtasks.iam.gserviceaccount.com",
|
||||
)
|
||||
|
||||
# Export queue names
|
||||
pulumi.export("audio_worker_queue", audio_worker_queue.name)
|
||||
pulumi.export("lyrics_worker_queue", lyrics_worker_queue.name)
|
||||
pulumi.export("screens_worker_queue", screens_worker_queue.name)
|
||||
pulumi.export("render_worker_queue", render_worker_queue.name)
|
||||
pulumi.export("video_worker_queue", video_worker_queue.name)
|
||||
```
|
||||
|
||||
#### Step 1.2: Update WorkerService for Cloud Tasks
|
||||
|
||||
```python
|
||||
# backend/services/worker_service.py - Updated
|
||||
|
||||
import logging
|
||||
import os
|
||||
import json
|
||||
from typing import Optional
|
||||
from google.cloud import tasks_v2
|
||||
from google.protobuf import timestamp_pb2
|
||||
import httpx
|
||||
|
||||
from backend.config import get_settings
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Queue mapping
|
||||
WORKER_QUEUES = {
|
||||
"audio": "audio-worker-queue",
|
||||
"lyrics": "lyrics-worker-queue",
|
||||
"screens": "screens-worker-queue",
|
||||
"render-video": "render-worker-queue",
|
||||
"video": "video-worker-queue",
|
||||
}
|
||||
|
||||
class WorkerService:
|
||||
"""
|
||||
Service for coordinating background workers.
|
||||
|
||||
Supports two modes:
|
||||
- Cloud Tasks (production): Guaranteed delivery, auto-scaling
|
||||
- Direct HTTP (development): Faster iteration, simpler debugging
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
self.settings = get_settings()
|
||||
self._base_url = self._get_base_url()
|
||||
self._admin_token = self._get_admin_token()
|
||||
self._use_cloud_tasks = self._should_use_cloud_tasks()
|
||||
self._tasks_client = None
|
||||
|
||||
def _should_use_cloud_tasks(self) -> bool:
|
||||
"""Check if Cloud Tasks should be used."""
|
||||
# Feature flag with environment variable
|
||||
enable_flag = os.getenv("ENABLE_CLOUD_TASKS", "false").lower()
|
||||
return enable_flag in ("true", "1", "yes")
|
||||
|
||||
@property
|
||||
def tasks_client(self):
|
||||
"""Lazy-init Cloud Tasks client."""
|
||||
if self._tasks_client is None and self._use_cloud_tasks:
|
||||
self._tasks_client = tasks_v2.CloudTasksClient()
|
||||
return self._tasks_client
|
||||
|
||||
def _get_admin_token(self) -> Optional[str]:
|
||||
admin_tokens_str = self.settings.admin_tokens or ""
|
||||
tokens = [t.strip() for t in admin_tokens_str.split(",") if t.strip()]
|
||||
return tokens[0] if tokens else None
|
||||
|
||||
def _get_base_url(self) -> str:
|
||||
# Check for test environment override
|
||||
test_url = os.getenv("TEST_SERVER_URL")
|
||||
if test_url:
|
||||
return test_url
|
||||
|
||||
# Production: Cloud Run service URL
|
||||
service_url = os.getenv("CLOUD_RUN_SERVICE_URL")
|
||||
if service_url:
|
||||
return service_url
|
||||
|
||||
# Development: localhost
|
||||
port = os.getenv("PORT", "8000")
|
||||
return f"http://localhost:{port}"
|
||||
|
||||
async def trigger_worker(
|
||||
self,
|
||||
worker_type: str,
|
||||
job_id: str,
|
||||
timeout_seconds: int = 30
|
||||
) -> bool:
|
||||
"""
|
||||
Trigger a background worker.
|
||||
|
||||
In production (ENABLE_CLOUD_TASKS=true):
|
||||
- Enqueues task to Cloud Tasks queue
|
||||
- Cloud Tasks calls internal endpoint with retries
|
||||
|
||||
In development:
|
||||
- Direct HTTP call to internal endpoint
|
||||
- Faster iteration, but no retry guarantees
|
||||
"""
|
||||
if self._use_cloud_tasks:
|
||||
return await self._enqueue_cloud_task(worker_type, job_id)
|
||||
else:
|
||||
return await self._trigger_http(worker_type, job_id, timeout_seconds)
|
||||
|
||||
async def _enqueue_cloud_task(self, worker_type: str, job_id: str) -> bool:
|
||||
"""Enqueue task to Cloud Tasks for guaranteed delivery."""
|
||||
try:
|
||||
queue_name = WORKER_QUEUES.get(worker_type)
|
||||
if not queue_name:
|
||||
logger.error(f"Unknown worker type: {worker_type}")
|
||||
return False
|
||||
|
||||
project = self.settings.google_cloud_project
|
||||
location = "us-central1"
|
||||
|
||||
# Build queue path
|
||||
parent = self.tasks_client.queue_path(project, location, queue_name)
|
||||
|
||||
# Build task
|
||||
task = {
|
||||
"http_request": {
|
||||
"http_method": tasks_v2.HttpMethod.POST,
|
||||
"url": f"{self._base_url}/api/internal/workers/{worker_type}",
|
||||
"headers": {
|
||||
"Content-Type": "application/json",
|
||||
},
|
||||
"body": json.dumps({"job_id": job_id}).encode(),
|
||||
# Use OIDC token for Cloud Run authentication
|
||||
"oidc_token": {
|
||||
"service_account_email": f"karaoke-backend@{project}.iam.gserviceaccount.com",
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
# Add admin auth header if available
|
||||
if self._admin_token:
|
||||
task["http_request"]["headers"]["Authorization"] = f"Bearer {self._admin_token}"
|
||||
|
||||
# Create task
|
||||
response = self.tasks_client.create_task(parent=parent, task=task)
|
||||
logger.info(f"Created Cloud Task for {worker_type} worker, job {job_id}: {response.name}")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to enqueue Cloud Task for {worker_type}/{job_id}: {e}", exc_info=True)
|
||||
return False
|
||||
|
||||
async def _trigger_http(
|
||||
self,
|
||||
worker_type: str,
|
||||
job_id: str,
|
||||
timeout_seconds: int = 30
|
||||
) -> bool:
|
||||
"""Direct HTTP trigger (for development)."""
|
||||
try:
|
||||
headers = {}
|
||||
if self._admin_token:
|
||||
headers["Authorization"] = f"Bearer {self._admin_token}"
|
||||
|
||||
async with httpx.AsyncClient(timeout=timeout_seconds) as client:
|
||||
url = f"{self._base_url}/api/internal/workers/{worker_type}"
|
||||
response = await client.post(url, json={"job_id": job_id}, headers=headers)
|
||||
|
||||
if response.status_code == 200:
|
||||
logger.info(f"Triggered {worker_type} worker for job {job_id}")
|
||||
return True
|
||||
else:
|
||||
logger.error(f"Failed to trigger {worker_type}: HTTP {response.status_code}")
|
||||
return False
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error triggering {worker_type} worker: {e}", exc_info=True)
|
||||
return False
|
||||
|
||||
# Convenience methods (unchanged)
|
||||
async def trigger_audio_worker(self, job_id: str) -> bool:
|
||||
return await self.trigger_worker("audio", job_id)
|
||||
|
||||
async def trigger_lyrics_worker(self, job_id: str) -> bool:
|
||||
return await self.trigger_worker("lyrics", job_id)
|
||||
|
||||
async def trigger_screens_worker(self, job_id: str) -> bool:
|
||||
return await self.trigger_worker("screens", job_id)
|
||||
|
||||
async def trigger_video_worker(self, job_id: str) -> bool:
|
||||
return await self.trigger_worker("video", job_id)
|
||||
|
||||
async def trigger_render_video_worker(self, job_id: str) -> bool:
|
||||
return await self.trigger_worker("render-video", job_id)
|
||||
```
|
||||
|
||||
#### Step 1.3: Update Internal Endpoints for Cloud Tasks
|
||||
|
||||
The internal endpoints need minor updates to handle Cloud Tasks requests:
|
||||
|
||||
```python
|
||||
# backend/api/routes/internal.py - Updates
|
||||
|
||||
# Add idempotency check to prevent duplicate processing
|
||||
@router.post("/workers/audio", response_model=WorkerResponse)
|
||||
async def trigger_audio_worker(
|
||||
request: WorkerRequest,
|
||||
background_tasks: BackgroundTasks,
|
||||
auth_data: Tuple[str, UserType, int] = Depends(require_admin)
|
||||
):
|
||||
"""Trigger audio separation worker for a job."""
|
||||
job_id = request.job_id
|
||||
|
||||
# Idempotency: Check if already processing
|
||||
job_manager = JobManager()
|
||||
job = job_manager.get_job(job_id)
|
||||
|
||||
if job and job.state_data.get('audio_progress', {}).get('stage') == 'running':
|
||||
logger.info(f"Audio worker already running for job {job_id}, skipping")
|
||||
return WorkerResponse(
|
||||
status="already_running",
|
||||
job_id=job_id,
|
||||
message="Audio worker already in progress"
|
||||
)
|
||||
|
||||
# Mark as running before starting (for idempotency)
|
||||
job_manager.update_state_data(job_id, 'audio_progress', {'stage': 'running'})
|
||||
|
||||
logger.info(f"Triggering audio worker for job {job_id}")
|
||||
background_tasks.add_task(process_audio_separation, job_id)
|
||||
|
||||
return WorkerResponse(
|
||||
status="started",
|
||||
job_id=job_id,
|
||||
message="Audio separation worker started"
|
||||
)
|
||||
```
|
||||
|
||||
#### Step 1.4: Cloud Run Service Account Permissions
|
||||
|
||||
```python
|
||||
# infrastructure/__main__.py additions
|
||||
|
||||
# Grant Cloud Tasks admin permission to the service account
|
||||
# (needed to create tasks)
|
||||
cloud_tasks_admin = gcp.projects.IAMMember(
|
||||
"karaoke-backend-cloudtasks-admin",
|
||||
project=project_id,
|
||||
role="roles/cloudtasks.enqueuer",
|
||||
member=service_account.email.apply(lambda email: f"serviceAccount:{email}"),
|
||||
)
|
||||
```
|
||||
|
||||
### Phase 2: Cloud Run Jobs for Video Worker (MEDIUM Priority)
|
||||
|
||||
**Goal:** Remove 30-minute timeout constraint for video encoding
|
||||
|
||||
**Effort:** 1-2 days | **Risk:** Low
|
||||
|
||||
The video worker (final encoding) can take 15-20 minutes, sometimes longer. Cloud Tasks has a 30-minute max timeout. For safety, we use Cloud Run Jobs.
|
||||
|
||||
#### Step 2.1: Create Cloud Run Job
|
||||
|
||||
```yaml
|
||||
# cloudbuild-video-job.yaml
|
||||
steps:
|
||||
- name: 'gcr.io/cloud-builders/gcloud'
|
||||
args:
|
||||
- 'run'
|
||||
- 'jobs'
|
||||
- 'create'
|
||||
- 'video-encoding-job'
|
||||
- '--image=${_IMAGE}'
|
||||
- '--region=us-central1'
|
||||
- '--cpu=4'
|
||||
- '--memory=8Gi'
|
||||
- '--max-retries=2'
|
||||
- '--task-timeout=3600' # 1 hour max
|
||||
- '--service-account=karaoke-backend@${PROJECT_ID}.iam.gserviceaccount.com'
|
||||
- '--set-env-vars=GOOGLE_CLOUD_PROJECT=${PROJECT_ID}'
|
||||
```
|
||||
|
||||
#### Step 2.2: Update Video Worker Trigger
|
||||
|
||||
```python
|
||||
# backend/services/worker_service.py - Addition
|
||||
|
||||
async def trigger_video_worker_job(self, job_id: str) -> bool:
|
||||
"""Trigger video worker as Cloud Run Job (for long-running encoding)."""
|
||||
if not self._use_cloud_tasks:
|
||||
# Development: use HTTP trigger
|
||||
return await self._trigger_http("video", job_id)
|
||||
|
||||
try:
|
||||
from google.cloud import run_v2
|
||||
|
||||
client = run_v2.JobsClient()
|
||||
project = self.settings.google_cloud_project
|
||||
location = "us-central1"
|
||||
|
||||
job_name = f"projects/{project}/locations/{location}/jobs/video-encoding-job"
|
||||
|
||||
# Override container args with job_id
|
||||
request = run_v2.RunJobRequest(
|
||||
name=job_name,
|
||||
overrides=run_v2.RunJobRequest.Overrides(
|
||||
container_overrides=[
|
||||
run_v2.RunJobRequest.Overrides.ContainerOverride(
|
||||
args=["--job-id", job_id],
|
||||
)
|
||||
]
|
||||
)
|
||||
)
|
||||
|
||||
operation = client.run_job(request=request)
|
||||
logger.info(f"Started Cloud Run Job for video encoding: {job_id}")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to start video encoding job: {e}", exc_info=True)
|
||||
return False
|
||||
```
|
||||
|
||||
### Phase 3: Pipeline Unification (LOW Priority - Future)
|
||||
|
||||
**Goal:** Share code between CLI and backend workers
|
||||
|
||||
**Effort:** 1-2 weeks | **Risk:** Medium (requires careful refactoring)
|
||||
|
||||
This phase can be deferred - the infrastructure scaling (Phase 1-2) solves the immediate problem.
|
||||
|
||||
**When to consider this:**
|
||||
- When adding new features that need to work in both CLI and backend
|
||||
- When a bug fix needs to be applied in multiple places
|
||||
- When the divergence between workers and pipeline stages causes maintenance burden
|
||||
|
||||
**Approach:**
|
||||
1. Make backend workers call pipeline stages instead of processors directly
|
||||
2. Have RemoteExecutor use Cloud Tasks to trigger stage execution
|
||||
3. Both CLI and backend use the same pipeline stages
|
||||
|
||||
---
|
||||
|
||||
## Resource Configuration
|
||||
|
||||
### Cloud Tasks Queues
|
||||
|
||||
| Queue | Max Concurrent | Rate Limit | Timeout | Retries | Notes |
|
||||
|-------|---------------|------------|---------|---------|-------|
|
||||
| audio-worker | 50 | 10/sec | 15 min | 3 | Mostly I/O (Modal API) |
|
||||
| lyrics-worker | 50 | 10/sec | 10 min | 3 | Mostly I/O (AudioShake) |
|
||||
| screens-worker | 100 | 50/sec | 2 min | 3 | FFmpeg (quick) |
|
||||
| render-worker | 20 | 5/sec | 30 min | 2 | LyricsTranscriber + FFmpeg |
|
||||
| video-worker | 10 | 3/sec | 30 min | 2 | Heavy FFmpeg (or use Jobs) |
|
||||
|
||||
### Cloud Run Instance Scaling
|
||||
|
||||
| Worker | CPU | Memory | Max Instances | Notes |
|
||||
|--------|-----|--------|---------------|-------|
|
||||
| audio | 2 | 2Gi | 50 | Mostly waiting on Modal API |
|
||||
| lyrics | 2 | 2Gi | 50 | Mostly waiting on AudioShake |
|
||||
| screens | 2 | 2Gi | 100 | Quick FFmpeg |
|
||||
| render | 4 | 4Gi | 20 | CPU-intensive |
|
||||
| video (Job) | 4 | 8Gi | 10 | Very CPU-intensive |
|
||||
|
||||
### Cost Estimate (100 concurrent jobs/day)
|
||||
|
||||
```
|
||||
Cloud Tasks: ~$0.40/million tasks ≈ $0.01/day
|
||||
Cloud Run: ~$0.00002/vCPU-sec ≈ $5-10/day (100 jobs)
|
||||
Cloud Run Jobs: ~$0.00002/vCPU-sec ≈ $2-5/day (100 jobs)
|
||||
Modal (GPU): ~$2.50/hour ≈ $20-40/day (100 jobs)
|
||||
AudioShake: Usage-based ≈ $10-20/day (100 jobs)
|
||||
|
||||
Total: ~$40-80/day for 100 concurrent jobs
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Migration Strategy
|
||||
|
||||
### Zero-Downtime Migration
|
||||
|
||||
```
|
||||
Week 1: Deploy Cloud Tasks infrastructure (Pulumi)
|
||||
└── Queues exist but aren't used yet (ENABLE_CLOUD_TASKS=false)
|
||||
|
||||
Week 2: Test in staging
|
||||
└── Deploy to staging with ENABLE_CLOUD_TASKS=true
|
||||
└── Run 10-20 test jobs concurrently
|
||||
└── Monitor for issues
|
||||
|
||||
Week 3: Enable in production
|
||||
└── Set ENABLE_CLOUD_TASKS=true
|
||||
└── Monitor metrics and logs
|
||||
└── Have rollback ready
|
||||
|
||||
Week 4: Cleanup
|
||||
└── Remove feature flag after stable week
|
||||
└── Update documentation
|
||||
```
|
||||
|
||||
### Rollback Plan
|
||||
|
||||
If issues occur after enabling Cloud Tasks:
|
||||
1. Set `ENABLE_CLOUD_TASKS=false` environment variable
|
||||
2. Redeploy (takes ~2 minutes)
|
||||
3. New jobs use direct HTTP (old behavior)
|
||||
4. In-flight Cloud Tasks jobs continue to completion
|
||||
5. No data loss - Firestore has job state
|
||||
|
||||
### Testing Strategy
|
||||
|
||||
```bash
|
||||
# Run unit tests (no Cloud Tasks)
|
||||
pytest backend/tests/ -v
|
||||
|
||||
# Run integration tests with Cloud Tasks (staging)
|
||||
ENABLE_CLOUD_TASKS=true pytest backend/tests/integration/ -v
|
||||
|
||||
# Load test (staging)
|
||||
# Submit 50 concurrent jobs, verify all complete
|
||||
for i in {1..50}; do
|
||||
curl -X POST "https://staging.api.nomadkaraoke.com/api/jobs/upload" \
|
||||
-F "file=@test.flac" -F "artist=Test" -F "title=Job$i" &
|
||||
done
|
||||
wait
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Success Criteria
|
||||
|
||||
### Phase 1 (Cloud Tasks)
|
||||
- [x] Cloud Tasks queues created and configured via Pulumi
|
||||
- [x] WorkerService updated to support Cloud Tasks mode
|
||||
- [x] Deployment configured with ENABLE_CLOUD_TASKS=true
|
||||
- [x] Container concurrency set to 1 for true isolation
|
||||
- [ ] 50 concurrent jobs complete without failures (to be validated)
|
||||
- [ ] Processing time per job unchanged (same as 1 job)
|
||||
- [ ] No resource contention (CPU/memory per job consistent)
|
||||
- [ ] Automatic retry on transient failures works
|
||||
- [ ] Feature flag rollback works
|
||||
|
||||
### Phase 2 (Cloud Run Jobs)
|
||||
- [ ] Video encoding >30 min completes successfully
|
||||
- [ ] Jobs triggered correctly from WorkerService
|
||||
- [ ] Progress updates visible in CLI
|
||||
|
||||
### Phase 3 (Pipeline Unification)
|
||||
- [ ] Single stage implementation used by both CLIs
|
||||
- [ ] Bug fixes apply to both local and remote execution
|
||||
- [ ] Each stage independently testable
|
||||
- [ ] 80%+ code coverage on pipeline module
|
||||
|
||||
---
|
||||
|
||||
## Files to Modify
|
||||
|
||||
### Phase 1
|
||||
|
||||
| File | Changes |
|
||||
|------|---------|
|
||||
| `infrastructure/__main__.py` | Add Cloud Tasks queues, IAM permissions |
|
||||
| `backend/services/worker_service.py` | Add Cloud Tasks client, feature flag |
|
||||
| `backend/api/routes/internal.py` | Add idempotency checks |
|
||||
| `backend/config.py` | Add ENABLE_CLOUD_TASKS setting |
|
||||
| `backend/requirements.txt` | Add google-cloud-tasks |
|
||||
|
||||
### Phase 2
|
||||
|
||||
| File | Changes |
|
||||
|------|---------|
|
||||
| `cloudbuild-video-job.yaml` | New file for Cloud Run Job |
|
||||
| `backend/services/worker_service.py` | Add Cloud Run Jobs trigger |
|
||||
| `backend/workers/video_worker.py` | CLI entry point for Jobs |
|
||||
|
||||
---
|
||||
|
||||
## Related Documents
|
||||
|
||||
- [ARCHITECTURE.md](../01-reference/ARCHITECTURE.md) - Current system architecture
|
||||
- [BACKEND-FEATURE-PARITY-PLAN.md](./BACKEND-FEATURE-PARITY-PLAN.md) - Feature parity roadmap
|
||||
- [WORKER-IMPLEMENTATION-PLAN.md](./WORKER-IMPLEMENTATION-PLAN.md) - Worker details
|
||||
|
||||
---
|
||||
|
||||
## Changelog
|
||||
|
||||
### 2025-12-11: Analysis Complete - Updated Plan
|
||||
|
||||
- **Analyzed codebase thoroughly** - found existing pipeline architecture underutilized
|
||||
- **Confirmed Cloud Tasks as best approach** - minimal code changes, single point of change
|
||||
- **Identified WorkerService as sole modification point** - clean abstraction exists
|
||||
- **Decided against immediate pipeline unification** - infrastructure scaling is the priority
|
||||
- **Added detailed implementation code** - ready to start Phase 1
|
||||
- **Created phased approach** - Phase 1 (Cloud Tasks) → Phase 2 (Jobs) → Phase 3 (Pipeline)
|
||||
|
||||
### 2025-12-11: Initial Plan
|
||||
- Documented current architecture limitations
|
||||
- Proposed Cloud Tasks + Cloud Run Jobs hybrid
|
||||
- Outlined shared pipeline architecture
|
||||
- Created implementation roadmap
|
||||
@@ -0,0 +1,240 @@
|
||||
# Backend Testing Gaps Analysis
|
||||
|
||||
**Created:** 2025-12-22
|
||||
**Updated:** 2025-12-22
|
||||
**Status:** Mostly Complete ✅
|
||||
**Priority:** High
|
||||
|
||||
## Background
|
||||
|
||||
During end-to-end testing of the remote karaoke-gen CLI, multiple bugs were discovered:
|
||||
|
||||
### Bug #1: Missing `extra_info` Attribute (Fixed 2025-12-22)
|
||||
```
|
||||
Error: 'AudioSearchResult' object has no attribute 'extra_info'
|
||||
```
|
||||
|
||||
This bug existed in production code but wasn't caught by automated tests because the remote download code path had no test coverage.
|
||||
|
||||
### Bug #2: Missing `gcs_path` Parameter in API Route (Fixed 2025-12-22)
|
||||
```
|
||||
Error handling audio selection: Error selecting audio: {'detail': "Download failed: [Errno 2] No such file or directory: '/var/lib/transmission-daemon/downloads/Avril Lavigne - Unwanted (Album, 2002, CD, 16bit, RED).flac'"}
|
||||
```
|
||||
|
||||
The backend API route `_download_and_start_processing` in `audio_search.py` was not passing the `gcs_path` parameter to `audio_search_service.download()`. Without this parameter, the remote `flacfetch` VM would download the file locally but not upload it to GCS. The backend then tried to open the VM's local path (`/var/lib/transmission-daemon/downloads/...`) which doesn't exist on Cloud Run.
|
||||
|
||||
**Why this wasn't caught:**
|
||||
- Service-level tests for `AudioSearchService.download()` existed and tested `gcs_path` parameter
|
||||
- But the **API route caller** (`_download_and_start_processing`) that invokes this service was never tested
|
||||
- Tests validated the service layer but not the route layer's usage of the service
|
||||
|
||||
## Root Cause Analysis
|
||||
|
||||
1. **Missing remote code path tests**: The download routing logic for `provider in ["RED", "OPS"]` was never exercised
|
||||
2. **State not set up for remote scenario**: Tests never configured `_remote_search_id` and `_remote_client` together
|
||||
3. **`FlacfetchClient` had zero tests**: The entire HTTP client was untested
|
||||
4. **Tests mocked at wrong level**: Tests mocked `service._fetcher` completely, bypassing the routing logic
|
||||
5. **API route orchestration untested**: The `_download_and_start_processing` function in `api/routes/audio_search.py` orchestrates multiple services but had no dedicated tests verifying correct parameter passing
|
||||
|
||||
## Services Testing Status
|
||||
|
||||
### ✅ Fully Tested
|
||||
|
||||
| Service | Test File | Test Count | Notes |
|
||||
|---------|-----------|------------|-------|
|
||||
| `credential_manager.py` | `test_credential_manager.py` | 27 | Good coverage |
|
||||
| `job_manager.py` | `test_job_manager.py` | 15 | Good coverage |
|
||||
| `flacfetch_client.py` | `test_flacfetch_client.py` | 26 | **Added 2025-12-22** |
|
||||
| `audio_search_service.py` | `test_audio_search.py` | 43 | **+11 tests 2025-12-22** |
|
||||
| `api/routes/audio_search.py` | `test_audio_search.py` | 4 | **API route tests added 2025-12-22** |
|
||||
| `storage_service.py` | `test_storage_service.py` | 17 | **Added 2025-12-22** |
|
||||
| `audio_analysis_service.py` | `test_audio_analysis_service.py` | 9 | **Added 2025-12-22** |
|
||||
| `audio_editing_service.py` | `test_audio_editing_service.py` | 13 | **Added 2025-12-22** |
|
||||
| `youtube_service.py` | `test_youtube_service.py` | 12 | **Added 2025-12-22** |
|
||||
| `dropbox_service.py` | `test_dropbox_service.py` | 14 | **Added 2025-12-22** |
|
||||
| `gdrive_service.py` | `test_gdrive_service.py` | 13 | **Added 2025-12-22** |
|
||||
|
||||
### ❌ No Dedicated Test File (Lower Priority)
|
||||
|
||||
| Service | Priority | Complexity | Notes |
|
||||
|---------|----------|------------|-------|
|
||||
| `rclone_service.py` | Low | Low | Wrapper around rclone CLI |
|
||||
| `firestore_service.py` | Low | Medium | Firestore operations |
|
||||
| `auth_service.py` | Low | Low | Auth utilities |
|
||||
| `job_logging.py` | Low | Low | Logging utilities |
|
||||
| `tracing.py` | Low | Low | OpenTelemetry setup |
|
||||
| `worker_service.py` | Medium | High | Worker orchestration |
|
||||
|
||||
## Implementation Plan
|
||||
|
||||
### Phase 1: Core Audio Services (High Priority) ✅
|
||||
|
||||
- [x] `flacfetch_client.py` - Remote audio download client
|
||||
- [x] `audio_search_service.py` - Remote download path tests
|
||||
|
||||
### Phase 2: Audio Processing Services (High Priority) ✅
|
||||
|
||||
- [x] `audio_analysis_service.py` - Waveform analysis, peak detection
|
||||
- [x] `audio_editing_service.py` - Mute regions, audio manipulation
|
||||
|
||||
### Phase 3: Distribution Services (Medium Priority) ✅
|
||||
|
||||
- [x] `youtube_service.py` - YouTube credential management
|
||||
- [x] `dropbox_service.py` - Dropbox upload API
|
||||
- [x] `gdrive_service.py` - Google Drive upload API
|
||||
- [x] `storage_service.py` - GCS operations
|
||||
|
||||
### Phase 4: Infrastructure Services (Low Priority)
|
||||
|
||||
- [ ] `worker_service.py` - Worker orchestration
|
||||
- [ ] `firestore_service.py` - Firestore operations
|
||||
- [ ] `rclone_service.py` - Rclone wrapper
|
||||
- [ ] `auth_service.py` - Auth utilities
|
||||
- [ ] `job_logging.py` - Logging
|
||||
- [ ] `tracing.py` - Tracing
|
||||
|
||||
## Test Coverage Goals
|
||||
|
||||
- **Target:** 80%+ line coverage for high-priority services
|
||||
- **Minimum:** Key code paths tested (happy path + error handling)
|
||||
- **Integration:** Mock external APIs (YouTube, Dropbox, GCS, etc.)
|
||||
|
||||
## Testing Patterns to Follow
|
||||
|
||||
### 1. Mock External Services
|
||||
|
||||
```python
|
||||
@patch("backend.services.youtube_service.build")
|
||||
def test_upload_video(self, mock_build):
|
||||
mock_service = Mock()
|
||||
mock_build.return_value = mock_service
|
||||
# ...
|
||||
```
|
||||
|
||||
### 2. Test Error Handling
|
||||
|
||||
```python
|
||||
def test_upload_handles_network_error(self):
|
||||
with pytest.raises(ServiceError) as exc_info:
|
||||
service.upload(...)
|
||||
assert "network" in str(exc_info.value).lower()
|
||||
```
|
||||
|
||||
### 3. Test State Transitions
|
||||
|
||||
```python
|
||||
def test_download_routes_to_remote_for_torrent_providers(self):
|
||||
service._remote_client = Mock()
|
||||
service._remote_search_id = "search_123"
|
||||
service._cached_results = [result_with_provider_red]
|
||||
|
||||
service.download(0, "/tmp")
|
||||
|
||||
service._download_remote.assert_called_once()
|
||||
```
|
||||
|
||||
### 4. Verify Request/Response Format
|
||||
|
||||
```python
|
||||
def test_search_sends_correct_payload(self):
|
||||
# ...
|
||||
call_args = mock_client.post.call_args
|
||||
assert call_args.kwargs["json"] == {"artist": "ABBA", "title": "Waterloo"}
|
||||
```
|
||||
|
||||
### 5. Test API Route Orchestration (CRITICAL)
|
||||
|
||||
**Key Lesson from Bug #2:** Service-level tests are not sufficient. API routes that orchestrate multiple services must also be tested to verify correct parameter passing.
|
||||
|
||||
```python
|
||||
class TestAudioSearchApiRouteDownload:
|
||||
"""Tests for the _download_and_start_processing function in audio_search.py."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_remote_download_passes_gcs_path(self):
|
||||
"""Verify that gcs_path is passed to audio_search_service.download for torrent providers."""
|
||||
# Mock the audio_search_service.download to capture the call
|
||||
mock_audio_search_service = Mock()
|
||||
mock_audio_search_service.download.return_value = AudioDownloadResult(
|
||||
filepath="gs://bucket/path.flac", artist="A", title="T", provider="RED", quality="FLAC"
|
||||
)
|
||||
|
||||
result = await _download_and_start_processing(job_id="job1", ...)
|
||||
|
||||
# Assert gcs_path was passed
|
||||
call_kwargs = mock_audio_search_service.download.call_args.kwargs
|
||||
assert call_kwargs.get('gcs_path') is not None # CRITICAL check!
|
||||
assert call_kwargs['gcs_path'].startswith('uploads/')
|
||||
```
|
||||
|
||||
This pattern ensures that when service APIs change or new required parameters are added, API route tests will catch missing parameter passing.
|
||||
|
||||
## Files Changed
|
||||
|
||||
**Bug Fixes:**
|
||||
- `backend/services/audio_search_service.py` - Removed `extra_info` attribute access (Bug #1)
|
||||
- `backend/api/routes/audio_search.py` - Added `gcs_path` parameter to `audio_search_service.download()` call (Bug #2)
|
||||
|
||||
**Tests Added (2025-12-22):**
|
||||
- `backend/tests/test_audio_search.py` - +11 tests for service + 4 tests for API route orchestration
|
||||
- `backend/tests/test_flacfetch_client.py` - 26 new tests (new file)
|
||||
- `backend/tests/test_storage_service.py` - 17 new tests (new file)
|
||||
- `backend/tests/test_audio_analysis_service.py` - 9 new tests (new file)
|
||||
- `backend/tests/test_audio_editing_service.py` - 13 new tests (new file)
|
||||
- `backend/tests/test_youtube_service.py` - 12 new tests (new file)
|
||||
- `backend/tests/test_dropbox_service.py` - 14 new tests (new file)
|
||||
- `backend/tests/test_gdrive_service.py` - 13 new tests (new file)
|
||||
|
||||
**Total New Tests:** 119 tests added
|
||||
|
||||
**Version:** 0.74.3
|
||||
|
||||
## Running Tests
|
||||
|
||||
```bash
|
||||
# All backend tests
|
||||
cd backend && python -m pytest tests/ -v
|
||||
|
||||
# Specific service tests
|
||||
python -m pytest tests/test_flacfetch_client.py -v
|
||||
python -m pytest tests/test_audio_search.py -v
|
||||
|
||||
# With coverage
|
||||
python -m pytest tests/ -v --cov=services --cov-report=term-missing
|
||||
```
|
||||
|
||||
## Notes for Future Sessions
|
||||
|
||||
When continuing this work:
|
||||
|
||||
1. **Test API route orchestration, not just services**: Bug #2 showed that service tests alone don't catch parameter passing bugs at the route level
|
||||
2. Distribution services need OAuth mocking - check existing patterns in `test_credential_manager.py`
|
||||
3. Use `pytest.mark.asyncio` for async service methods
|
||||
4. Follow existing test patterns in `test_flacfetch_client.py` for HTTP client mocking
|
||||
5. **For remote operations**: Always verify that `gcs_path` parameters are passed when code paths involve remote VM operations
|
||||
|
||||
## Lessons Learned
|
||||
|
||||
### Testing Layers Matter
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────────┐
|
||||
│ API Routes (api/routes/*.py) │
|
||||
│ └─> These orchestrate services and MUST be tested separately │
|
||||
│ to verify correct parameter passing │
|
||||
├─────────────────────────────────────────────────────────────────┤
|
||||
│ Services (services/*.py) │
|
||||
│ └─> Business logic with proper unit tests │
|
||||
├─────────────────────────────────────────────────────────────────┤
|
||||
│ Clients (FlacfetchClient, etc.) │
|
||||
│ └─> HTTP/external API interactions │
|
||||
└─────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
Bug #2 was missed because:
|
||||
- `FlacfetchClient` tests ✅ verified `gcs_path` is sent in HTTP requests
|
||||
- `AudioSearchService` tests ✅ verified `gcs_path` is passed to client
|
||||
- **API route tests ❌ didn't exist** - so nobody verified the route passes `gcs_path` to the service
|
||||
|
||||
Now we have `TestAudioSearchApiRouteDownload` to catch this class of bugs.
|
||||
|
||||
@@ -0,0 +1,837 @@
|
||||
# Flacfetch HTTP API Service Implementation Plan
|
||||
|
||||
**Created:** 2025-12-20
|
||||
**Updated:** 2025-12-22
|
||||
**Status:** Complete ✅
|
||||
**Priority:** Medium
|
||||
**Estimated Effort:** 3-4 days (actual: ~3 days)
|
||||
|
||||
## Problem Statement
|
||||
|
||||
BitTorrent downloads don't work reliably in Cloud Run due to:
|
||||
- No inbound peer connections (NAT/firewall)
|
||||
- Ephemeral containers with no stable IP
|
||||
- DHT peer discovery blocked
|
||||
- Container timeout limits (max 60 min)
|
||||
|
||||
This prevents downloading lossless audio from private trackers (RED, OPS) via the remote backend.
|
||||
|
||||
## Solution Overview
|
||||
|
||||
Add an HTTP API mode to **flacfetch** (our audio fetching library) and deploy it on a dedicated GCP VM with:
|
||||
- Full BitTorrent peer connectivity via Transmission daemon
|
||||
- Static IP for tracker whitelist (seedbox-like)
|
||||
- Indefinite seeding of downloaded torrents
|
||||
- Automatic disk cleanup when space runs low
|
||||
- YouTube downloads also handled (single service for all audio acquisition)
|
||||
|
||||
This approach provides clean separation of concerns:
|
||||
- **flacfetch**: Handles ALL audio acquisition (torrents + YouTube)
|
||||
- **karaoke-gen backend**: Orchestrates karaoke generation pipeline, calls flacfetch API
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────────────────────┐
|
||||
│ FLACFETCH SERVICE ARCHITECTURE │
|
||||
├─────────────────────────────────────────────────────────────────────────────┤
|
||||
│ │
|
||||
│ Cloud Run Backend Flacfetch VM (e2-small) │
|
||||
│ ┌────────────────────┐ ┌─────────────────────────┐ │
|
||||
│ │ │ │ │ │
|
||||
│ │ karaoke-gen │ 1. Search │ flacfetch HTTP API │ │
|
||||
│ │ AudioSearchService │ ────────────▶ │ POST /search │ │
|
||||
│ │ │ │ │ │
|
||||
│ │ │ 2. Results │ Providers: │ │
|
||||
│ │ │ ◀──────────── │ • RED (FLAC) │ │
|
||||
│ │ │ │ • OPS (FLAC) │ │
|
||||
│ │ │ 3. Download │ • YouTube (fallback) │ │
|
||||
│ │ │ ────────────▶ │ │ │
|
||||
│ │ │ │ POST /download │ │
|
||||
│ │ │ 4. Status │ GET /download/{id} │ │
|
||||
│ │ │ ◀──────────── │ │ │
|
||||
│ │ │ (polling) │ Transmission Daemon │ │
|
||||
│ │ │ │ • Full peer connect │ │
|
||||
│ │ │ 5. Complete │ • DHT enabled │ │
|
||||
│ │ │ ◀──────────── │ • Indefinite seeding │ │
|
||||
│ │ │ (file path) │ │ │
|
||||
│ └────────────────────┘ └───────────┬─────────────┘ │
|
||||
│ │ │ │
|
||||
│ │ │ 6. Upload to GCS │
|
||||
│ │ │ │
|
||||
│ ▼ ▼ │
|
||||
│ ┌─────────────────────────────────────────────────────────────────┐ │
|
||||
│ │ Google Cloud Storage │ │
|
||||
│ │ │ │
|
||||
│ │ uploads/{job_id}/audio/{filename}.flac │ │
|
||||
│ │ │ │
|
||||
│ └─────────────────────────────────────────────────────────────────┘ │
|
||||
│ │
|
||||
└─────────────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## Key Design Decisions
|
||||
|
||||
### 1. HTTP API in flacfetch (not separate service)
|
||||
- **Why**: Clean separation of concerns, reusable by future projects, single source of truth
|
||||
- **How**: Add `flacfetch/api/` module with FastAPI, new CLI mode `flacfetch serve`
|
||||
|
||||
### 2. Indefinite Seeding
|
||||
- **Why**: VM is always-on anyway, helps maintain tracker ratio, acts like a seedbox
|
||||
- **Current behavior**: Torrent removed after download (line 317-321 in torrent.py)
|
||||
- **New behavior**: Torrent kept seeding, only removed by cleanup or explicit delete
|
||||
|
||||
### 3. Static IP
|
||||
- **Why**: Required for tracker account IP whitelist, consistent for firewall rules
|
||||
- **Cost**: ~$3/month additional
|
||||
|
||||
### 4. Disk Space Management
|
||||
- **Strategy**: Auto-cleanup oldest torrents when free space < 5GB threshold
|
||||
- **API**: Manual cleanup endpoints + automatic background cleanup
|
||||
|
||||
### 5. Instance Type: e2-small
|
||||
- **Specs**: 0.5 vCPU, 2GB RAM, ~$12/month
|
||||
- **Why**: Sufficient for I/O-bound workload, newer C3/N4 require 2+ vCPUs (overkill)
|
||||
- **Disk**: 30GB SSD (20GB for torrents + headroom)
|
||||
|
||||
### 6. Authentication
|
||||
- **Method**: Static API key in `X-API-Key` header
|
||||
- **Firewall**: Permissive (allows future web UI), auth enforced at app level
|
||||
|
||||
## Implementation Phases
|
||||
|
||||
### Phase 1: Add HTTP API to flacfetch
|
||||
|
||||
**Location:** `./flacfetch/flacfetch/api/`
|
||||
|
||||
**New Directory Structure:**
|
||||
```
|
||||
flacfetch/
|
||||
├── flacfetch/
|
||||
│ ├── api/ # NEW
|
||||
│ │ ├── __init__.py
|
||||
│ │ ├── main.py # FastAPI app entry point
|
||||
│ │ ├── auth.py # API key authentication
|
||||
│ │ ├── models.py # Pydantic request/response models
|
||||
│ │ ├── routes/
|
||||
│ │ │ ├── __init__.py
|
||||
│ │ │ ├── search.py # POST /search
|
||||
│ │ │ ├── download.py # POST /download, GET /download/{id}/status
|
||||
│ │ │ ├── torrents.py # GET /torrents, DELETE /torrents/{id}
|
||||
│ │ │ └── health.py # GET /health, GET /disk-usage
|
||||
│ │ └── services/
|
||||
│ │ ├── __init__.py
|
||||
│ │ ├── download_manager.py # Track active downloads
|
||||
│ │ └── disk_manager.py # Disk cleanup logic
|
||||
│ ├── core/
|
||||
│ ├── downloaders/
|
||||
│ │ └── torrent.py # MODIFIED: optional keep-seeding mode
|
||||
│ ├── interface/
|
||||
│ │ └── cli.py # MODIFIED: add 'serve' subcommand
|
||||
│ └── providers/
|
||||
└── pyproject.toml # MODIFIED: add fastapi, uvicorn deps
|
||||
```
|
||||
|
||||
**API Endpoints:**
|
||||
|
||||
```yaml
|
||||
# All endpoints require X-API-Key header
|
||||
|
||||
# Search for audio
|
||||
POST /search
|
||||
Request:
|
||||
{ "artist": "ABBA", "title": "Waterloo" }
|
||||
Response:
|
||||
{
|
||||
"search_id": "abc123",
|
||||
"results": [
|
||||
{
|
||||
"index": 0,
|
||||
"title": "Waterloo",
|
||||
"artist": "ABBA",
|
||||
"provider": "RED",
|
||||
"quality": "FLAC 16bit CD",
|
||||
"seeders": 45,
|
||||
"size_bytes": 31457280,
|
||||
"target_file": "02. Waterloo.flac",
|
||||
...
|
||||
},
|
||||
...
|
||||
]
|
||||
}
|
||||
|
||||
# Start download
|
||||
POST /download
|
||||
Request:
|
||||
{
|
||||
"search_id": "abc123", # From previous search
|
||||
"result_index": 0, # Which result to download
|
||||
"output_filename": "ABBA - Waterloo", # Optional
|
||||
"upload_to_gcs": true, # Upload to GCS when complete
|
||||
"gcs_path": "uploads/job123/audio/" # Required if upload_to_gcs
|
||||
}
|
||||
Response:
|
||||
{
|
||||
"download_id": "dl_xyz789",
|
||||
"status": "queued"
|
||||
}
|
||||
|
||||
# Check download status
|
||||
GET /download/{download_id}/status
|
||||
Response:
|
||||
{
|
||||
"download_id": "dl_xyz789",
|
||||
"status": "downloading", # queued, downloading, uploading, seeding, complete, failed
|
||||
"progress": 45.2,
|
||||
"peers": 3,
|
||||
"download_speed_kbps": 1250.5,
|
||||
"eta_seconds": 120,
|
||||
"provider": "RED",
|
||||
"title": "ABBA - Waterloo",
|
||||
"output_path": null, # Set when complete (local path)
|
||||
"gcs_path": null, # Set when uploaded to GCS
|
||||
"error": null
|
||||
}
|
||||
|
||||
# List all torrents (for management)
|
||||
GET /torrents
|
||||
Response:
|
||||
{
|
||||
"torrents": [
|
||||
{
|
||||
"id": 1,
|
||||
"name": "ABBA - Waterloo [FLAC]",
|
||||
"status": "seeding",
|
||||
"progress": 100.0,
|
||||
"size_bytes": 314572800,
|
||||
"uploaded_bytes": 628145600, # Seeding stats
|
||||
"ratio": 2.0,
|
||||
"added_at": "2025-12-20T10:30:00Z"
|
||||
},
|
||||
...
|
||||
],
|
||||
"total_size_bytes": 5368709120,
|
||||
"count": 15
|
||||
}
|
||||
|
||||
# Delete a torrent (manual cleanup)
|
||||
DELETE /torrents/{torrent_id}
|
||||
Query params: ?delete_data=true # Also delete downloaded files
|
||||
Response:
|
||||
{ "status": "deleted" }
|
||||
|
||||
# Trigger cleanup (free disk space)
|
||||
POST /torrents/cleanup
|
||||
Request:
|
||||
{
|
||||
"strategy": "oldest", # oldest, largest, lowest_ratio
|
||||
"target_free_gb": 10 # Keep removing until this much free
|
||||
}
|
||||
Response:
|
||||
{
|
||||
"removed_count": 3,
|
||||
"freed_bytes": 1073741824,
|
||||
"free_space_gb": 10.5
|
||||
}
|
||||
|
||||
# Health check
|
||||
GET /health
|
||||
Response:
|
||||
{
|
||||
"status": "healthy",
|
||||
"transmission": {
|
||||
"available": true,
|
||||
"version": "4.0.5",
|
||||
"active_torrents": 5
|
||||
},
|
||||
"disk": {
|
||||
"total_gb": 30,
|
||||
"used_gb": 18,
|
||||
"free_gb": 12
|
||||
},
|
||||
"providers": {
|
||||
"red": true,
|
||||
"ops": true,
|
||||
"youtube": true
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Torrent Downloader Changes:**
|
||||
|
||||
```python
|
||||
# flacfetch/downloaders/torrent.py
|
||||
|
||||
class TorrentDownloader(Downloader):
|
||||
def __init__(self, ..., keep_seeding: bool = False):
|
||||
"""
|
||||
Args:
|
||||
keep_seeding: If True, don't remove torrent after download.
|
||||
Used in server mode for indefinite seeding.
|
||||
"""
|
||||
self.keep_seeding = keep_seeding
|
||||
|
||||
def download(self, release, output_path, output_filename=None):
|
||||
# ... existing download logic ...
|
||||
|
||||
# After download complete:
|
||||
if self.keep_seeding:
|
||||
# Don't remove, just return the file path
|
||||
logger.info(f"Download complete, keeping torrent for seeding: {torrent.name}")
|
||||
else:
|
||||
# Original behavior: stop and remove
|
||||
self.client.stop_torrent(torrent.id)
|
||||
self.client.remove_torrent(torrent.id, delete_data=True)
|
||||
```
|
||||
|
||||
**CLI Changes:**
|
||||
|
||||
```bash
|
||||
# New serve subcommand
|
||||
flacfetch serve --port 8080 --host 0.0.0.0
|
||||
|
||||
# Or via environment
|
||||
FLACFETCH_API_PORT=8080 flacfetch serve
|
||||
```
|
||||
|
||||
### Phase 2: Infrastructure (Pulumi)
|
||||
|
||||
**Location:** `./infrastructure/__main__.py`
|
||||
|
||||
**New Resources:**
|
||||
```python
|
||||
# Static IP for flacfetch service (for tracker whitelist)
|
||||
flacfetch_ip = gcp.compute.Address(
|
||||
"flacfetch-ip",
|
||||
name="flacfetch-static-ip",
|
||||
region="us-central1",
|
||||
)
|
||||
|
||||
# Service account for flacfetch VM
|
||||
flacfetch_sa = gcp.serviceaccount.Account(
|
||||
"flacfetch-sa",
|
||||
account_id="flacfetch-service",
|
||||
display_name="Flacfetch Service Account",
|
||||
)
|
||||
|
||||
# GCS write permissions for flacfetch
|
||||
gcp.storage.BucketIAMMember(
|
||||
"flacfetch-gcs-writer",
|
||||
bucket=bucket.name,
|
||||
role="roles/storage.objectCreator",
|
||||
member=pulumi.Output.concat("serviceAccount:", flacfetch_sa.email),
|
||||
)
|
||||
|
||||
# Flacfetch VM
|
||||
flacfetch_vm = gcp.compute.Instance(
|
||||
"flacfetch-service",
|
||||
machine_type="e2-small",
|
||||
zone="us-central1-a",
|
||||
boot_disk=gcp.compute.InstanceBootDiskArgs(
|
||||
initialize_params=gcp.compute.InstanceBootDiskInitializeParamsArgs(
|
||||
image="debian-cloud/debian-12",
|
||||
size=30, # GB
|
||||
type="pd-ssd",
|
||||
),
|
||||
),
|
||||
network_interfaces=[gcp.compute.InstanceNetworkInterfaceArgs(
|
||||
network="default",
|
||||
access_configs=[gcp.compute.InstanceNetworkInterfaceAccessConfigArgs(
|
||||
nat_ip=flacfetch_ip.address, # Static IP
|
||||
)],
|
||||
)],
|
||||
service_account=gcp.compute.InstanceServiceAccountArgs(
|
||||
email=flacfetch_sa.email,
|
||||
scopes=["cloud-platform"],
|
||||
),
|
||||
metadata_startup_script=FLACFETCH_STARTUP_SCRIPT,
|
||||
tags=["flacfetch-service"],
|
||||
)
|
||||
|
||||
# Firewall for flacfetch
|
||||
flacfetch_firewall = gcp.compute.Firewall(
|
||||
"flacfetch-firewall",
|
||||
network="default",
|
||||
allows=[
|
||||
# BitTorrent peer connections
|
||||
gcp.compute.FirewallAllowArgs(protocol="tcp", ports=["51413"]),
|
||||
gcp.compute.FirewallAllowArgs(protocol="udp", ports=["51413"]),
|
||||
# Flacfetch HTTP API (auth required at app level)
|
||||
gcp.compute.FirewallAllowArgs(protocol="tcp", ports=["8080"]),
|
||||
],
|
||||
source_ranges=["0.0.0.0/0"], # Permissive, auth at app level
|
||||
target_tags=["flacfetch-service"],
|
||||
)
|
||||
|
||||
# Store API key in Secret Manager
|
||||
flacfetch_api_key = gcp.secretmanager.Secret(
|
||||
"flacfetch-api-key",
|
||||
secret_id="flacfetch-api-key",
|
||||
replication=gcp.secretmanager.SecretReplicationArgs(
|
||||
auto=gcp.secretmanager.SecretReplicationAutoArgs(),
|
||||
),
|
||||
)
|
||||
|
||||
# Export for use
|
||||
pulumi.export("flacfetch_static_ip", flacfetch_ip.address)
|
||||
pulumi.export("flacfetch_service_url", pulumi.Output.concat("http://", flacfetch_ip.address, ":8080"))
|
||||
```
|
||||
|
||||
**Startup Script:**
|
||||
```bash
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
# Install dependencies
|
||||
apt-get update
|
||||
apt-get install -y python3-pip python3-venv transmission-daemon ffmpeg git
|
||||
|
||||
# Configure Transmission
|
||||
systemctl stop transmission-daemon
|
||||
cat > /etc/transmission-daemon/settings.json << 'EOF'
|
||||
{
|
||||
"download-dir": "/var/lib/transmission-daemon/downloads",
|
||||
"incomplete-dir": "/var/lib/transmission-daemon/.incomplete",
|
||||
"incomplete-dir-enabled": true,
|
||||
"rpc-authentication-required": false,
|
||||
"rpc-bind-address": "127.0.0.1",
|
||||
"rpc-enabled": true,
|
||||
"rpc-port": 9091,
|
||||
"rpc-whitelist-enabled": false,
|
||||
"peer-port": 51413,
|
||||
"port-forwarding-enabled": false,
|
||||
"speed-limit-down": 0,
|
||||
"speed-limit-down-enabled": false,
|
||||
"speed-limit-up": 0,
|
||||
"speed-limit-up-enabled": false,
|
||||
"ratio-limit-enabled": false,
|
||||
"umask": 2
|
||||
}
|
||||
EOF
|
||||
systemctl start transmission-daemon
|
||||
|
||||
# Install flacfetch
|
||||
cd /opt
|
||||
git clone https://github.com/nomadkaraoke/flacfetch.git
|
||||
cd flacfetch
|
||||
python3 -m venv venv
|
||||
source venv/bin/activate
|
||||
pip install -e ".[api]"
|
||||
|
||||
# Get secrets from metadata/Secret Manager
|
||||
FLACFETCH_API_KEY=$(gcloud secrets versions access latest --secret=flacfetch-api-key)
|
||||
RED_API_KEY=$(gcloud secrets versions access latest --secret=red-api-key)
|
||||
RED_API_URL=$(gcloud secrets versions access latest --secret=red-api-url)
|
||||
OPS_API_KEY=$(gcloud secrets versions access latest --secret=ops-api-key)
|
||||
GCS_BUCKET=$(curl -s "http://metadata.google.internal/computeMetadata/v1/instance/attributes/gcs-bucket" -H "Metadata-Flavor: Google")
|
||||
|
||||
# Create systemd service
|
||||
cat > /etc/systemd/system/flacfetch.service << EOF
|
||||
[Unit]
|
||||
Description=Flacfetch HTTP API Service
|
||||
After=network.target transmission-daemon.service
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=root
|
||||
WorkingDirectory=/opt/flacfetch
|
||||
Environment="FLACFETCH_API_KEY=${FLACFETCH_API_KEY}"
|
||||
Environment="RED_API_KEY=${RED_API_KEY}"
|
||||
Environment="RED_API_URL=${RED_API_URL}"
|
||||
Environment="OPS_API_KEY=${OPS_API_KEY}"
|
||||
Environment="GCS_BUCKET=${GCS_BUCKET}"
|
||||
Environment="FLACFETCH_KEEP_SEEDING=true"
|
||||
Environment="FLACFETCH_MIN_FREE_GB=5"
|
||||
ExecStart=/opt/flacfetch/venv/bin/flacfetch serve --host 0.0.0.0 --port 8080
|
||||
Restart=always
|
||||
RestartSec=10
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
EOF
|
||||
|
||||
systemctl daemon-reload
|
||||
systemctl enable flacfetch
|
||||
systemctl start flacfetch
|
||||
```
|
||||
|
||||
### Phase 3: Backend Integration
|
||||
|
||||
**New File:** `backend/services/flacfetch_client.py`
|
||||
|
||||
```python
|
||||
"""
|
||||
Client for the remote flacfetch HTTP API service.
|
||||
|
||||
Used when FLACFETCH_API_URL is configured, otherwise falls back to local flacfetch.
|
||||
"""
|
||||
import asyncio
|
||||
import logging
|
||||
from typing import Optional, List, Dict, Any
|
||||
|
||||
import httpx
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class FlacfetchServiceError(Exception):
|
||||
"""Error communicating with flacfetch service."""
|
||||
pass
|
||||
|
||||
|
||||
class FlacfetchClient:
|
||||
"""Client for remote flacfetch HTTP API."""
|
||||
|
||||
def __init__(self, base_url: str, api_key: str, timeout: int = 30):
|
||||
self.base_url = base_url.rstrip('/')
|
||||
self.api_key = api_key
|
||||
self.timeout = timeout
|
||||
|
||||
def _headers(self) -> Dict[str, str]:
|
||||
return {"X-API-Key": self.api_key}
|
||||
|
||||
async def health_check(self) -> Dict[str, Any]:
|
||||
"""Check if service is healthy."""
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.get(
|
||||
f"{self.base_url}/health",
|
||||
headers=self._headers(),
|
||||
timeout=10,
|
||||
)
|
||||
resp.raise_for_status()
|
||||
return resp.json()
|
||||
|
||||
async def search(self, artist: str, title: str) -> Dict[str, Any]:
|
||||
"""Search for audio."""
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.post(
|
||||
f"{self.base_url}/search",
|
||||
headers=self._headers(),
|
||||
json={"artist": artist, "title": title},
|
||||
timeout=self.timeout,
|
||||
)
|
||||
resp.raise_for_status()
|
||||
return resp.json()
|
||||
|
||||
async def download(
|
||||
self,
|
||||
search_id: str,
|
||||
result_index: int,
|
||||
output_filename: Optional[str] = None,
|
||||
gcs_path: Optional[str] = None,
|
||||
) -> str:
|
||||
"""
|
||||
Start download and return download_id.
|
||||
|
||||
If gcs_path is provided, file will be uploaded to GCS.
|
||||
"""
|
||||
async with httpx.AsyncClient() as client:
|
||||
payload = {
|
||||
"search_id": search_id,
|
||||
"result_index": result_index,
|
||||
}
|
||||
if output_filename:
|
||||
payload["output_filename"] = output_filename
|
||||
if gcs_path:
|
||||
payload["upload_to_gcs"] = True
|
||||
payload["gcs_path"] = gcs_path
|
||||
|
||||
resp = await client.post(
|
||||
f"{self.base_url}/download",
|
||||
headers=self._headers(),
|
||||
json=payload,
|
||||
timeout=self.timeout,
|
||||
)
|
||||
resp.raise_for_status()
|
||||
return resp.json()["download_id"]
|
||||
|
||||
async def get_download_status(self, download_id: str) -> Dict[str, Any]:
|
||||
"""Get download status."""
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.get(
|
||||
f"{self.base_url}/download/{download_id}/status",
|
||||
headers=self._headers(),
|
||||
timeout=10,
|
||||
)
|
||||
resp.raise_for_status()
|
||||
return resp.json()
|
||||
|
||||
async def wait_for_download(
|
||||
self,
|
||||
download_id: str,
|
||||
timeout: int = 600,
|
||||
poll_interval: int = 2,
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Wait for download to complete.
|
||||
|
||||
Returns final status dict with output_path or gcs_path.
|
||||
Raises FlacfetchServiceError on failure or timeout.
|
||||
"""
|
||||
elapsed = 0
|
||||
while elapsed < timeout:
|
||||
status = await self.get_download_status(download_id)
|
||||
|
||||
if status["status"] == "complete":
|
||||
return status
|
||||
elif status["status"] == "failed":
|
||||
raise FlacfetchServiceError(f"Download failed: {status.get('error')}")
|
||||
|
||||
await asyncio.sleep(poll_interval)
|
||||
elapsed += poll_interval
|
||||
|
||||
raise FlacfetchServiceError(f"Download timed out after {timeout}s")
|
||||
|
||||
|
||||
# Singleton
|
||||
_client: Optional[FlacfetchClient] = None
|
||||
|
||||
|
||||
def get_flacfetch_client() -> Optional[FlacfetchClient]:
|
||||
"""Get flacfetch client if configured."""
|
||||
global _client
|
||||
if _client is None:
|
||||
from backend.config import get_settings
|
||||
settings = get_settings()
|
||||
if settings.flacfetch_api_url and settings.flacfetch_api_key:
|
||||
_client = FlacfetchClient(
|
||||
base_url=settings.flacfetch_api_url,
|
||||
api_key=settings.flacfetch_api_key,
|
||||
)
|
||||
return _client
|
||||
```
|
||||
|
||||
**Modify:** `backend/services/audio_search_service.py` to use remote client when available.
|
||||
|
||||
**Modify:** `backend/config.py` to add new settings:
|
||||
```python
|
||||
flacfetch_api_url: Optional[str] = None # e.g., http://10.0.0.5:8080
|
||||
flacfetch_api_key: Optional[str] = None
|
||||
```
|
||||
|
||||
### Phase 4: Monitoring & Reliability
|
||||
|
||||
**Tasks:**
|
||||
- [ ] Add Cloud Monitoring alert for VM CPU/memory
|
||||
- [ ] Add alert for disk space < 5GB
|
||||
- [ ] Add alert for flacfetch service down (health check fails)
|
||||
- [ ] Configure Cloud Logging export from VM
|
||||
- [ ] Add Grafana dashboard (optional)
|
||||
|
||||
**Automatic Disk Cleanup:**
|
||||
The disk manager runs as a background task in the flacfetch API service:
|
||||
```python
|
||||
# Check every 5 minutes, cleanup if free space < threshold
|
||||
async def background_cleanup_task():
|
||||
while True:
|
||||
await asyncio.sleep(300)
|
||||
free_gb = get_free_space_gb()
|
||||
if free_gb < MIN_FREE_GB:
|
||||
cleanup_oldest_torrents(target_free_gb=MIN_FREE_GB + 5)
|
||||
```
|
||||
|
||||
### Phase 5: Testing & Documentation
|
||||
|
||||
**Testing:**
|
||||
- [ ] Unit tests for flacfetch API endpoints
|
||||
- [ ] Unit tests for disk manager
|
||||
- [ ] Integration test: search → download → GCS upload
|
||||
- [ ] Mock tests for karaoke-gen backend client
|
||||
|
||||
**Documentation:**
|
||||
- [ ] Update `docs/01-reference/ARCHITECTURE.md` with flacfetch service
|
||||
- [ ] Add `flacfetch/README.md` HTTP API section
|
||||
- [ ] Document deployment process
|
||||
- [ ] Document environment variables
|
||||
|
||||
## Environment Variables
|
||||
|
||||
### Flacfetch Service (VM)
|
||||
```bash
|
||||
# API Configuration
|
||||
FLACFETCH_API_KEY=<secret> # Required for API auth
|
||||
FLACFETCH_API_PORT=8080 # Default: 8080
|
||||
FLACFETCH_API_HOST=0.0.0.0 # Default: 0.0.0.0
|
||||
|
||||
# Tracker API Keys
|
||||
RED_API_KEY=<key> # For RED provider
|
||||
RED_API_URL=<url> # For RED provider base URL
|
||||
OPS_API_KEY=<key> # For OPS provider
|
||||
|
||||
# GCS Upload (optional)
|
||||
GCS_BUCKET=karaoke-uploads # For uploading completed downloads
|
||||
GOOGLE_CLOUD_PROJECT=nomadkaraoke
|
||||
|
||||
# Transmission
|
||||
TRANSMISSION_HOST=localhost # Default: localhost
|
||||
TRANSMISSION_PORT=9091 # Default: 9091
|
||||
|
||||
# Behavior
|
||||
FLACFETCH_KEEP_SEEDING=true # Keep torrents seeding after download
|
||||
FLACFETCH_MIN_FREE_GB=5 # Minimum free disk space before cleanup
|
||||
FLACFETCH_DOWNLOAD_DIR=/var/lib/transmission-daemon/downloads
|
||||
```
|
||||
|
||||
### Cloud Run Backend
|
||||
```bash
|
||||
# New variables
|
||||
FLACFETCH_API_URL=http://10.128.0.5:8080 # Internal IP of flacfetch VM
|
||||
FLACFETCH_API_KEY=<same-secret>
|
||||
```
|
||||
|
||||
## Security Considerations
|
||||
|
||||
1. **API Authentication**: Static API key in `X-API-Key` header
|
||||
2. **Firewall**: Permissive for future web UI, auth enforced at application level
|
||||
3. **GCS**: Service account with `storage.objectCreator` role only
|
||||
4. **Transmission**: RPC bound to localhost only, no external access
|
||||
5. **Static IP**: Can be whitelisted on tracker accounts
|
||||
|
||||
## Rollback Plan
|
||||
|
||||
If flacfetch service fails:
|
||||
1. Set `FLACFETCH_API_URL=""` in Cloud Run (disables remote service)
|
||||
2. Backend falls back to local flacfetch (YouTube only in Cloud Run)
|
||||
3. Users see warning that lossless downloads may be slower/unavailable
|
||||
|
||||
## Cost Estimate
|
||||
|
||||
| Resource | Monthly Cost |
|
||||
|----------|--------------|
|
||||
| e2-small VM | ~$12 |
|
||||
| Static IP | ~$3 |
|
||||
| 30GB SSD | ~$5 |
|
||||
| Network egress | ~$2-5 |
|
||||
| **Total** | **~$22-25/month** |
|
||||
|
||||
## Success Criteria
|
||||
|
||||
- [x] Flacfetch HTTP API accepts search requests and returns results
|
||||
- [x] Downloads complete successfully for RED/OPS sources
|
||||
- [x] Downloaded files upload to GCS automatically
|
||||
- [x] Torrents continue seeding after download
|
||||
- [x] Disk cleanup triggers automatically when space is low
|
||||
- [x] Remote CLI shows download progress from flacfetch service
|
||||
- [x] Fallback to local flacfetch works when service unavailable
|
||||
- [x] Static IP can be whitelisted on tracker accounts
|
||||
|
||||
## Timeline
|
||||
|
||||
| Phase | Duration | Dependencies |
|
||||
|-------|----------|--------------|
|
||||
| Phase 1: Flacfetch HTTP API | 1.5 days | None |
|
||||
| Phase 2: Infrastructure | 0.5 day | Phase 1 |
|
||||
| Phase 3: Backend Integration | 0.5 day | Phase 1, 2 |
|
||||
| Phase 4: Monitoring | 0.5 day | Phase 2 |
|
||||
| Phase 5: Testing & Docs | 0.5 day | Phase 1-3 |
|
||||
| **Total** | **3.5 days** | |
|
||||
|
||||
## Implementation Status (2025-12-22)
|
||||
|
||||
### Completed Work
|
||||
|
||||
#### Phase 1: Flacfetch HTTP API ✅
|
||||
- Full HTTP API implemented in `flacfetch/flacfetch/api/`
|
||||
- Endpoints: `/search`, `/download`, `/download/{id}/status`, `/download/{id}/file`, `/torrents`, `/health`
|
||||
- API key authentication via `X-API-Key` header
|
||||
- Disk manager with automatic cleanup when space < 5GB
|
||||
- Download manager with search caching and progress tracking
|
||||
- Dynamic version reporting via `importlib.metadata`
|
||||
- **Current Version:** 0.7.3
|
||||
|
||||
#### Phase 2: Infrastructure ✅
|
||||
- Pulumi infrastructure in `infrastructure/__main__.py`
|
||||
- GCP VM: `flacfetch-service` (e2-small, us-central1-a)
|
||||
- Static IP: `104.198.214.26` (whitelisted with trackers)
|
||||
- Firewall rules: TCP/UDP 51413 (BitTorrent), TCP 8080 (API)
|
||||
- Secrets: `flacfetch-api-key`, `red-api-key`, `red-api-url`, `ops-api-key`, `ops-api-url`, `flacfetch-api-url`
|
||||
- GitHub Actions deployer has `compute.admin` and `compute.osLogin` roles
|
||||
|
||||
#### Phase 3: Backend Integration ✅
|
||||
- `FlacfetchClient` in `backend/services/flacfetch_client.py`
|
||||
- `AudioSearchService` updated to use remote flacfetch when configured
|
||||
- Cloud Run configured with `FLACFETCH_API_URL` and `FLACFETCH_API_KEY` from Secret Manager
|
||||
- `--loop asyncio` added to uvicorn CMD (required for `nest_asyncio` compatibility)
|
||||
- `nest_asyncio` applied only when async loop is running (not at import time)
|
||||
|
||||
#### Phase 4: Monitoring ✅
|
||||
- Health endpoint reports Transmission status, disk usage, provider availability
|
||||
- Version verification in deployment workflows
|
||||
- Automatic deployment on release via GitHub Actions
|
||||
|
||||
#### Phase 5: CLI & Testing ✅
|
||||
- `flacfetch-remote` CLI added for testing remote API
|
||||
- Downloads file locally with descriptive filenames (e.g., `Artist - Title (Album, 2022, CD, 16bit, RED).flac`)
|
||||
- 70%+ unit test coverage requirement enforced
|
||||
- Integration tests for API routes
|
||||
|
||||
### Deployment Automation
|
||||
|
||||
#### Flacfetch VM (automatic)
|
||||
- `.github/workflows/release-on-version-bump.yml` in flacfetch repo
|
||||
- Triggers on version bump in `pyproject.toml`
|
||||
- Runs tests → Creates GitHub release → SSHs to VM → Pulls latest → Restarts service
|
||||
- Verifies deployed version matches release version
|
||||
|
||||
#### Karaoke-gen Backend (version-gated)
|
||||
- `.github/workflows/ci.yml` deploy-backend job
|
||||
- Only deploys if version tag doesn't exist (requires version bump)
|
||||
- Verifies deployed version via `/api/health/detailed` endpoint
|
||||
- Retries version check with backoff for Cloud Run routing delays
|
||||
|
||||
### Key Files Modified
|
||||
|
||||
**Flacfetch repo (`./flacfetch/`):**
|
||||
- `flacfetch/api/` - New HTTP API module
|
||||
- `flacfetch/interface/cli_remote.py` - New remote CLI
|
||||
- `flacfetch/core/manager.py` - Improved sorting (artist match, release type, seeders)
|
||||
- `flacfetch/downloaders/torrent.py` - Keep-seeding mode, file permissions fix
|
||||
- `.github/workflows/release-on-version-bump.yml` - Auto-deploy to VM
|
||||
|
||||
**Karaoke-gen repo:**
|
||||
- `backend/services/flacfetch_client.py` - Remote API client
|
||||
- `backend/services/audio_search_service.py` - Remote integration with nest_asyncio
|
||||
- `backend/Dockerfile` - `--loop asyncio` for uvicorn
|
||||
- `infrastructure/__main__.py` - VM, firewall, secrets, WIF bindings
|
||||
- `cloudbuild.yaml` - FLACFETCH_API_URL/KEY from Secret Manager
|
||||
- `.github/workflows/ci.yml` - Version-gated deployments
|
||||
|
||||
### Testing the Integration
|
||||
|
||||
```bash
|
||||
# Test flacfetch-remote CLI (requires env vars)
|
||||
export FLACFETCH_API_URL=http://104.198.214.26:8080
|
||||
export FLACFETCH_API_KEY=<from-secret-manager>
|
||||
flacfetch-remote "Avril Lavigne" "Unwanted"
|
||||
|
||||
# Test backend health
|
||||
curl -s https://api.nomadkaraoke.com/api/health/detailed | jq '.dependencies.flacfetch_remote'
|
||||
|
||||
# Test backend search
|
||||
curl -s -X POST https://api.nomadkaraoke.com/api/audio-search/search \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"artist": "Avril Lavigne", "title": "Unwanted"}' | jq '.results | length'
|
||||
```
|
||||
|
||||
### Known Issues / Future Work
|
||||
|
||||
1. **Transmission removal from Cloud Run**: Transmission daemon and startup script removed from Docker images as torrent downloads are now handled by dedicated VM.
|
||||
|
||||
2. **URL field in search results**: Made optional in `AudioSearchResultResponse` since remote results don't have direct download URLs.
|
||||
|
||||
3. **Sorting improvements**: Results now prioritize:
|
||||
- Lossless first
|
||||
- Artist name match (exact match wins)
|
||||
- Release type (Album > Single > EP > Compilation > Anthology > Remix)
|
||||
- Seeders (more = higher)
|
||||
- Quality (24bit > 16bit, FLAC > MP3)
|
||||
|
||||
4. **Future enhancements**:
|
||||
- Cloud Monitoring alerts for disk/CPU/memory
|
||||
- Grafana dashboard for torrent stats
|
||||
- Web UI for manual torrent management
|
||||
|
||||
## References
|
||||
|
||||
- [Transmission RPC Spec](https://github.com/transmission/transmission/blob/main/docs/rpc-spec.md)
|
||||
- [transmission-rpc Python library](https://github.com/Trim21/transmission-rpc)
|
||||
- [FastAPI Documentation](https://fastapi.tiangolo.com/)
|
||||
- [flacfetch source code](./flacfetch/)
|
||||
@@ -0,0 +1,265 @@
|
||||
# Countdown Padding Feature
|
||||
|
||||
This document explains how the countdown padding feature works across the karaoke-gen system, including both the standalone CLI tool and the cloud backend.
|
||||
|
||||
## Overview
|
||||
|
||||
When a song's vocals start within the first 3 seconds, karaoke singers don't have enough time to prepare. The countdown padding feature addresses this by:
|
||||
|
||||
1. Adding 3 seconds of silence to the start of the audio
|
||||
2. Shifting all lyrics timestamps forward by 3 seconds
|
||||
3. Adding a "3... 2... 1..." countdown segment (displayed at 0.1s - 2.9s)
|
||||
|
||||
This gives singers a visual countdown before the lyrics begin.
|
||||
|
||||
## Technical Details
|
||||
|
||||
### CountdownProcessor (lyrics-transcriber)
|
||||
|
||||
The core countdown logic lives in the `lyrics-transcriber` library:
|
||||
|
||||
**File:** `lyrics_transcriber/output/countdown_processor.py`
|
||||
|
||||
**Constants:**
|
||||
- `COUNTDOWN_THRESHOLD_SECONDS = 3.0` - Trigger countdown if first word starts within this time
|
||||
- `COUNTDOWN_PADDING_SECONDS = 3.0` - Amount of silence to add
|
||||
- `COUNTDOWN_START_TIME = 0.1` - When countdown text starts displaying
|
||||
- `COUNTDOWN_END_TIME = 2.9` - When countdown text ends
|
||||
- `COUNTDOWN_TEXT = "3... 2... 1..."` - The countdown text displayed
|
||||
|
||||
**Key Methods:**
|
||||
- `process(correction_result, audio_filepath)` - Main entry point. Returns `(modified_result, padded_audio_path, padding_added, padding_seconds)`
|
||||
- `_needs_countdown(correction_result)` - Checks if first word starts within 3 seconds
|
||||
- `_create_padded_audio(audio_filepath)` - Uses ffmpeg to prepend silence
|
||||
- `_add_countdown_to_result(correction_result)` - Shifts timestamps and adds countdown segment
|
||||
- `has_countdown(correction_result)` - Detects if countdown already exists (for loading saved corrections)
|
||||
|
||||
**FFmpeg Command Used:**
|
||||
```bash
|
||||
ffmpeg -y -hide_banner -loglevel error \
|
||||
-f lavfi -t 3.0 -i anullsrc=channel_layout=stereo:sample_rate=44100 \
|
||||
-i input_audio.flac \
|
||||
-filter_complex "[0:a][1:a]concat=n=2:v=0:a=1[out]" \
|
||||
-map "[out]" \
|
||||
-c:a flac \
|
||||
output_padded.flac
|
||||
```
|
||||
|
||||
This prepends 3 seconds of stereo silence (44.1kHz) and uses FLAC to preserve audio quality.
|
||||
|
||||
## Workflow: Standalone CLI (karaoke-gen)
|
||||
|
||||
When using the karaoke-gen CLI tool locally:
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────────────┐
|
||||
│ STANDALONE CLI WORKFLOW │
|
||||
├─────────────────────────────────────────────────────────────────────┤
|
||||
│ │
|
||||
│ 1. LyricsTranscriber.process() │
|
||||
│ └─> add_countdown=True (default) │
|
||||
│ └─> CountdownProcessor adds countdown + pads vocals audio │
|
||||
│ └─> Returns: padded_audio_filepath, countdown_padding_added │
|
||||
│ │
|
||||
│ 2. Audio Separation │
|
||||
│ └─> Creates instrumental files (original timing) │
|
||||
│ │
|
||||
│ 3. Apply Padding to Instrumentals │
|
||||
│ └─> AudioProcessor.apply_countdown_padding_to_instrumentals() │
|
||||
│ └─> Pads all instrumental variants to match vocals │
|
||||
│ └─> Creates files with "(Padded)" suffix │
|
||||
│ │
|
||||
│ 4. Final Video Generation │
|
||||
│ └─> Uses padded vocals + padded instrumental │
|
||||
│ └─> Everything is synchronized │
|
||||
│ │
|
||||
└─────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
**Key Files:**
|
||||
- `karaoke_gen/lyrics_processor.py` - Calls LyricsTranscriber, captures padding info
|
||||
- `karaoke_gen/audio_processor.py` - `apply_countdown_padding_to_instrumentals()` and `pad_audio_file()`
|
||||
- `karaoke_gen/karaoke_gen.py` - Orchestrates the workflow, applies padding after separation
|
||||
|
||||
**Instrumental File Naming:**
|
||||
- Original: `Artist - Song (Instrumental model.ckpt).flac`
|
||||
- Padded: `Artist - Song (Instrumental model.ckpt) (Padded).flac`
|
||||
|
||||
## Workflow: Cloud Backend
|
||||
|
||||
The cloud backend has a two-phase workflow with human review in between. This requires special handling to avoid sync issues.
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────────────┐
|
||||
│ CLOUD BACKEND WORKFLOW │
|
||||
├─────────────────────────────────────────────────────────────────────┤
|
||||
│ │
|
||||
│ PHASE 1: Lyrics Worker (lyrics_worker.py) │
|
||||
│ ───────────────────────────────────────── │
|
||||
│ └─> LyricsTranscriber.process() │
|
||||
│ └─> add_countdown=FALSE <── Deferred to Phase 2 │
|
||||
│ └─> Corrections saved WITHOUT countdown │
|
||||
│ └─> Original audio timing preserved │
|
||||
│ │
|
||||
│ HUMAN REVIEW (Review UI) │
|
||||
│ ──────────────────────── │
|
||||
│ └─> User reviews/edits lyrics │
|
||||
│ └─> Audio playback uses original (un-padded) audio │
|
||||
│ └─> Timestamps match audio perfectly │
|
||||
│ │
|
||||
│ PHASE 2: Render Video Worker (render_video_worker.py) │
|
||||
│ ───────────────────────────────────────────────────── │
|
||||
│ └─> CountdownProcessor.process() called HERE │
|
||||
│ └─> Adds countdown segment + shifts timestamps │
|
||||
│ └─> Creates padded audio for video rendering │
|
||||
│ └─> Final video has countdown + synced audio │
|
||||
│ │
|
||||
└─────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
**Why Defer Countdown to Phase 2?**
|
||||
|
||||
Previously, countdown was added during Phase 1 (lyrics transcription). This caused a problem:
|
||||
|
||||
1. Lyrics corrections were saved with countdown segment + shifted timestamps
|
||||
2. The padded audio file was created in a temp directory that was deleted
|
||||
3. Review UI served the original (un-padded) audio
|
||||
4. **Result:** 3-second sync mismatch between lyrics and audio in review UI
|
||||
|
||||
By deferring countdown to Phase 2:
|
||||
- Review UI shows original timing (audio and lyrics are perfectly synced)
|
||||
- Users can accurately review and edit lyrics
|
||||
- Countdown is added just before final video rendering
|
||||
|
||||
**Key Files:**
|
||||
- `karaoke_gen/lyrics_processor.py:405` - Sets `add_countdown=not is_serverless`
|
||||
- `backend/workers/render_video_worker.py:188-200` - Adds countdown using `CountdownProcessor.process()`
|
||||
|
||||
**Serverless Detection:**
|
||||
```python
|
||||
is_serverless = (
|
||||
os.getenv("MODAL_TASK_ID") is not None or
|
||||
os.getenv("MODAL_FUNCTION_NAME") is not None or
|
||||
os.path.exists("/.modal")
|
||||
)
|
||||
```
|
||||
|
||||
## Finalization Step (karaoke_finalise)
|
||||
|
||||
The `KaraokeFinalise` class handles creating the final karaoke video with instrumental audio.
|
||||
|
||||
**File:** `karaoke_gen/karaoke_finalise/karaoke_finalise.py`
|
||||
|
||||
It includes a safety net in `remux_with_instrumental()`:
|
||||
- If `countdown_padding_seconds` is set but instrumental doesn't have "(Padded)" in the name
|
||||
- It automatically pads the instrumental before remuxing
|
||||
- This ensures vocals and instrumental stay synchronized
|
||||
|
||||
## Detecting Existing Countdown
|
||||
|
||||
When loading saved corrections (e.g., from a JSON file), you can detect if countdown was applied:
|
||||
|
||||
```python
|
||||
countdown_processor = CountdownProcessor(cache_dir=temp_dir)
|
||||
has_countdown = countdown_processor.has_countdown(correction_result)
|
||||
|
||||
# Or check for countdown text in first segment
|
||||
first_segment = correction_result.corrected_segments[0]
|
||||
is_countdown = first_segment.text == "3... 2... 1..."
|
||||
```
|
||||
|
||||
You can also detect from LRC files:
|
||||
```python
|
||||
# LyricsProcessor._detect_countdown_padding_from_lrc()
|
||||
# Checks for "3... 2... 1..." text or first timestamp >= 2.5s
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
### Disabling Countdown
|
||||
|
||||
To disable countdown for a specific transcription:
|
||||
|
||||
```python
|
||||
from lyrics_transcriber.core.config import OutputConfig
|
||||
|
||||
output_config = OutputConfig(
|
||||
# ... other options
|
||||
add_countdown=False, # Disable countdown
|
||||
)
|
||||
```
|
||||
|
||||
### Padding Amount
|
||||
|
||||
The padding amount is currently fixed at 3.0 seconds. To change this, you would need to modify the constants in `CountdownProcessor`.
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Issue: Countdown appears but audio is out of sync
|
||||
|
||||
**Cause:** Instrumental audio wasn't padded to match vocals.
|
||||
|
||||
**Solution:**
|
||||
- Check that `countdown_padding_added` was captured from transcription
|
||||
- Verify `apply_countdown_padding_to_instrumentals()` was called
|
||||
- Look for "(Padded)" in instrumental filenames
|
||||
|
||||
### Issue: Review UI shows 3-second offset
|
||||
|
||||
**Cause:** Countdown was added during transcription instead of rendering phase.
|
||||
|
||||
**Solution:**
|
||||
- This was fixed in v0.76.1
|
||||
- Ensure `add_countdown=False` for serverless mode
|
||||
- Countdown should only be added in `render_video_worker.py`
|
||||
|
||||
### Issue: No countdown even though song starts immediately
|
||||
|
||||
**Cause:** First word timestamp might be exactly at or after 3.0 seconds.
|
||||
|
||||
**Check:**
|
||||
- Look at the first segment's first word start_time
|
||||
- Countdown triggers only if `first_word_start < 3.0`
|
||||
|
||||
## Testing
|
||||
|
||||
### Unit Tests
|
||||
|
||||
Countdown padding tests are in `tests/unit/test_countdown_padding.py`:
|
||||
|
||||
```bash
|
||||
python -m pytest tests/unit/test_countdown_padding.py -v
|
||||
```
|
||||
|
||||
Tests cover:
|
||||
- `pad_audio_file()` success, failure, and timeout
|
||||
- `apply_countdown_padding_to_instrumentals()` for clean and combined instrumentals
|
||||
- Integration with `LyricsProcessor` and `KaraokeGen`
|
||||
- Custom instrumental padding
|
||||
- Idempotency (skipping already-padded files)
|
||||
|
||||
## Data Flow Summary
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────────────┐
|
||||
│ DATA FLOW │
|
||||
├─────────────────────────────────────────────────────────────────────┤
|
||||
│ │
|
||||
│ Input: Song with vocals starting at 1.5s │
|
||||
│ │
|
||||
│ After Countdown Processing: │
|
||||
│ ───────────────────────────── │
|
||||
│ • Audio: 3s silence + original audio │
|
||||
│ • First segment: "3... 2... 1..." at 0.1s-2.9s │
|
||||
│ • Original first word: moved from 1.5s → 4.5s │
|
||||
│ • All subsequent timestamps: shifted +3.0s │
|
||||
│ │
|
||||
│ Result: Singer sees countdown, has time to prepare │
|
||||
│ │
|
||||
└─────────────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## Version History
|
||||
|
||||
- **v0.76.1** - Fixed cloud backend sync issue by deferring countdown to render phase
|
||||
- **v0.70.x** - Initial countdown padding implementation integrated from lyrics-transcriber
|
||||
@@ -0,0 +1,481 @@
|
||||
# Frontend Guide - Karaoke Generator Web UI
|
||||
|
||||
## Overview
|
||||
|
||||
The karaoke-gen frontend is a Next.js-based static web application deployed to GitHub Pages at **https://gen.nomadkaraoke.com**. It provides a web interface for submitting jobs to the backend API, monitoring job progress, and managing karaoke video generation.
|
||||
|
||||
## Architecture
|
||||
|
||||
### Deployment Topology
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────┐
|
||||
│ gen.nomadkaraoke.com (GitHub Pages) │
|
||||
│ - Next.js static export │
|
||||
│ - Pure client-side React application │
|
||||
│ - No server-side rendering │
|
||||
└────────────────┬────────────────────────────────────────┘
|
||||
│
|
||||
│ API calls (HTTPS)
|
||||
▼
|
||||
┌─────────────────────────────────────────────────────────┐
|
||||
│ api.nomadkaraoke.com (Cloud Run) │
|
||||
│ - FastAPI backend │
|
||||
│ - Requires Bearer token authentication │
|
||||
│ - Manages jobs, storage, workers │
|
||||
└─────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### Key Components
|
||||
|
||||
- **Frontend Domain**: `gen.nomadkaraoke.com` → GitHub Pages (static HTML/CSS/JS)
|
||||
- **Backend API**: `api.nomadkaraoke.com` → Google Cloud Run
|
||||
- **Framework**: Next.js 16.0.7 with Turbopack (static export mode)
|
||||
- **UI Library**: React 19 + shadcn/ui components
|
||||
- **State Management**: React hooks (useState, useEffect)
|
||||
- **Storage**: localStorage for auth tokens (client-side only)
|
||||
|
||||
## Authentication
|
||||
|
||||
### How It Works
|
||||
|
||||
The backend API requires **Bearer token authentication** for all requests. The frontend implements client-side token management:
|
||||
|
||||
1. **Token Storage**: Tokens are stored in browser localStorage
|
||||
2. **Token Input**: Users enter tokens via the AuthBanner component
|
||||
3. **API Requests**: All API calls include `Authorization: Bearer <token>` header
|
||||
4. **Token Persistence**: Tokens persist across browser sessions until cleared
|
||||
|
||||
### Getting a Token
|
||||
|
||||
Tokens are managed by administrators. Users need to contact an admin to receive an access token. There is no self-service signup.
|
||||
|
||||
**Admin token management**: Admin tokens are stored in Google Cloud Secret Manager (`ADMIN_TOKENS` secret).
|
||||
|
||||
### Using Authentication in the UI
|
||||
|
||||
```typescript
|
||||
// Import auth functions
|
||||
import { setAccessToken, getAccessToken, clearAccessToken } from '@/lib/api';
|
||||
|
||||
// Set token (after user input)
|
||||
setAccessToken('your-token-here');
|
||||
|
||||
// Get current token
|
||||
const token = getAccessToken();
|
||||
|
||||
// Clear token (logout)
|
||||
clearAccessToken();
|
||||
```
|
||||
|
||||
## Features
|
||||
|
||||
### 1. Job Submission
|
||||
|
||||
Three methods for submitting karaoke generation jobs:
|
||||
|
||||
#### File Upload
|
||||
- Upload audio files directly (FLAC, WAV, MP3, etc.)
|
||||
- Provide artist and title metadata
|
||||
- Automatic processing starts immediately
|
||||
|
||||
#### YouTube URL
|
||||
- Submit a YouTube video URL
|
||||
- Backend downloads audio automatically
|
||||
- Provide artist and title metadata
|
||||
|
||||
#### Audio Search
|
||||
- Search by artist and title
|
||||
- Backend finds high-quality audio sources
|
||||
- Select from multiple results
|
||||
- Automatic download and processing
|
||||
|
||||
### 2. Job Monitoring
|
||||
|
||||
Real-time job status tracking with:
|
||||
- **Status badges**: Visual indicators (Pending, Processing, Awaiting Review, etc.)
|
||||
- **Progress bars**: Visual progress for active jobs
|
||||
- **Auto-refresh**: Updates every 10 seconds
|
||||
- **Manual refresh**: Click refresh button anytime
|
||||
|
||||
**Job Statuses**:
|
||||
- `PENDING` - Job created, waiting to start
|
||||
- `DOWNLOADING` - Fetching audio
|
||||
- `PROCESSING_AUDIO` - Separating vocals/instrumental
|
||||
- `PROCESSING_LYRICS` - Transcribing lyrics
|
||||
- `AWAITING_REVIEW` - Ready for human review
|
||||
- `AWAITING_INSTRUMENTAL_SELECTION` - User needs to select instrumental
|
||||
- `RENDERING_VIDEO` - Creating final video
|
||||
- `UPLOADING` - Distributing to YouTube/Dropbox
|
||||
- `COMPLETE` - Finished successfully
|
||||
- `FAILED` - Error occurred
|
||||
- `CANCELLED` - User cancelled
|
||||
|
||||
### 3. Interactive Elements
|
||||
|
||||
#### Lyrics Review
|
||||
- Launch lyrics correction UI in new tab
|
||||
- Make timing and text corrections
|
||||
- Submit corrections to trigger video rendering
|
||||
|
||||
#### Instrumental Selection
|
||||
- Preview multiple instrumental options
|
||||
- Select best quality instrumental
|
||||
- Audio player for A/B comparison
|
||||
|
||||
#### Job Actions
|
||||
- **Cancel**: Stop a running job
|
||||
- **Retry**: Restart a failed job
|
||||
- **Delete**: Remove job and associated files
|
||||
- **View Logs**: See detailed processing logs
|
||||
|
||||
### 4. Output Access
|
||||
|
||||
When jobs complete, access outputs via:
|
||||
- **YouTube**: Direct link to uploaded video
|
||||
- **Dropbox**: Link to Dropbox folder with files
|
||||
- **Direct Downloads**: Download MP4, CDG, TXT files
|
||||
|
||||
## Component Structure
|
||||
|
||||
### Modular Architecture
|
||||
|
||||
```
|
||||
frontend/
|
||||
├── app/
|
||||
│ ├── page.tsx # Main application page
|
||||
│ ├── layout.tsx # Root layout with metadata
|
||||
│ └── globals.css # Global styles and CSS variables
|
||||
│
|
||||
├── components/
|
||||
│ ├── auth-banner.tsx # Authentication UI
|
||||
│ │
|
||||
│ ├── job/ # Job-related components
|
||||
│ │ ├── JobCard.tsx # Individual job display
|
||||
│ │ ├── JobSubmission.tsx # Job creation forms
|
||||
│ │ ├── JobActions.tsx # Job management buttons
|
||||
│ │ ├── JobLogs.tsx # Log viewer
|
||||
│ │ ├── OutputLinks.tsx # Download/distribution links
|
||||
│ │ └── InstrumentalSelector.tsx # Instrumental picker
|
||||
│ │
|
||||
│ ├── audio-search/ # Audio search feature
|
||||
│ │ └── AudioSearchDialog.tsx
|
||||
│ │
|
||||
│ └── ui/ # Reusable UI primitives (shadcn/ui)
|
||||
│ ├── button.tsx
|
||||
│ ├── card.tsx
|
||||
│ ├── dialog.tsx
|
||||
│ ├── tabs.tsx
|
||||
│ └── ... (more)
|
||||
│
|
||||
└── lib/
|
||||
├── api.ts # API client (all backend calls)
|
||||
├── types.ts # TypeScript type definitions
|
||||
└── utils.ts # Utility functions
|
||||
```
|
||||
|
||||
### Key Files
|
||||
|
||||
#### `lib/api.ts` - API Client
|
||||
|
||||
The central hub for all backend communication:
|
||||
|
||||
```typescript
|
||||
const API_BASE_URL = process.env.NEXT_PUBLIC_API_URL || 'https://api.nomadkaraoke.com';
|
||||
|
||||
export const api = {
|
||||
// Authentication
|
||||
setAccessToken(token: string): void
|
||||
getAccessToken(): string | null
|
||||
clearAccessToken(): void
|
||||
|
||||
// Job Management
|
||||
listJobs(params?: { status?: string; limit?: number }): Promise<Job[]>
|
||||
getJob(jobId: string): Promise<Job>
|
||||
uploadJob(file: File, artist: string, title: string): Promise<JobResponse>
|
||||
createJobFromUrl(body: CreateJobFromUrlRequest): Promise<JobResponse>
|
||||
cancelJob(jobId: string, reason?: string): Promise<void>
|
||||
retryJob(jobId: string): Promise<void>
|
||||
deleteJob(jobId: string): Promise<void>
|
||||
|
||||
// Audio Search
|
||||
searchAudio(request: AudioSearchRequest): Promise<AudioSearchResponse>
|
||||
getAudioSearchResults(jobId: string): Promise<AudioSearchResult[]>
|
||||
selectAudioResult(jobId: string, resultIndex: number): Promise<void>
|
||||
|
||||
// Lyrics Review
|
||||
getReviewData(jobId: string): Promise<ReviewData>
|
||||
completeReview(jobId: string, corrections: any): Promise<void>
|
||||
|
||||
// Instrumental Selection
|
||||
getInstrumentalOptions(jobId: string): Promise<InstrumentalOption[]>
|
||||
selectInstrumental(jobId: string, sourceIndex: number): Promise<void>
|
||||
|
||||
// Outputs
|
||||
getDownloadUrls(jobId: string): Promise<DownloadUrls>
|
||||
}
|
||||
```
|
||||
|
||||
#### `components/auth-banner.tsx` - Authentication UI
|
||||
|
||||
Prominent banner at top of page for token management:
|
||||
- Shows "Authentication Required" when no token
|
||||
- Displays truncated token when authenticated
|
||||
- Password-masked input field
|
||||
- Persistent across page reloads
|
||||
|
||||
#### `components/job/JobCard.tsx` - Job Display
|
||||
|
||||
Main component for displaying individual jobs:
|
||||
- Collapsible details view
|
||||
- Status badges and progress bars
|
||||
- Conditional rendering based on job state
|
||||
- Integrates all sub-components (actions, logs, outputs, etc.)
|
||||
|
||||
## Styling
|
||||
|
||||
### Color Scheme
|
||||
|
||||
Matches the instrumental review UI for consistency:
|
||||
|
||||
```css
|
||||
/* Background colors */
|
||||
--bg: #0f0f0f; /* Very dark, neutral */
|
||||
--card: #1a1a1a; /* Card backgrounds */
|
||||
|
||||
/* Text colors */
|
||||
--text: #e5e5e5; /* Primary text */
|
||||
--text-muted: #999999; /* Secondary text */
|
||||
|
||||
/* UI colors */
|
||||
--primary: #3b82f6; /* Blue (actions, links) */
|
||||
--success: #10b981; /* Green (success states) */
|
||||
--warning: #f59e0b; /* Orange (warnings) */
|
||||
--error: #ef4444; /* Red (errors) */
|
||||
--border: #2a2a2a; /* Borders */
|
||||
```
|
||||
|
||||
### Typography
|
||||
|
||||
System font stack for fast loading and native feel:
|
||||
|
||||
```css
|
||||
--font-sans: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
|
||||
--font-mono: "SF Mono", Monaco, "Cascadia Code", "Courier New", monospace;
|
||||
```
|
||||
|
||||
## Local Development
|
||||
|
||||
### Setup
|
||||
|
||||
```bash
|
||||
cd frontend
|
||||
|
||||
# Install dependencies
|
||||
npm ci --legacy-peer-deps
|
||||
|
||||
# Start dev server with hot-reload
|
||||
npm run dev
|
||||
# → http://localhost:3000
|
||||
|
||||
# Build static export
|
||||
npm run build
|
||||
# → Output: frontend/out/
|
||||
|
||||
# Run tests
|
||||
npm test
|
||||
```
|
||||
|
||||
### Environment Variables
|
||||
|
||||
Create `.env.local` for local development:
|
||||
|
||||
```bash
|
||||
# Optional: Override API URL for local backend testing
|
||||
NEXT_PUBLIC_API_URL=http://localhost:8080
|
||||
```
|
||||
|
||||
### Testing Against Production API
|
||||
|
||||
The default configuration connects to the production API at `api.nomadkaraoke.com`, so you can develop locally while using the real backend.
|
||||
|
||||
**Important**: You'll need a valid access token to make API requests.
|
||||
|
||||
## Deployment
|
||||
|
||||
### Automatic Deployment (CI/CD)
|
||||
|
||||
Changes to `main` branch automatically deploy via GitHub Actions:
|
||||
|
||||
1. **Trigger**: Push to `main` or merge PR
|
||||
2. **Build**: `npm ci --legacy-peer-deps && npm run build`
|
||||
3. **Deploy**: Upload `frontend/out/` to GitHub Pages
|
||||
4. **Live**: Available at `gen.nomadkaraoke.com` within ~2 minutes
|
||||
|
||||
### CI Workflow
|
||||
|
||||
`.github/workflows/ci.yml`:
|
||||
|
||||
```yaml
|
||||
deploy-frontend:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-node@v4
|
||||
- name: Install dependencies
|
||||
working-directory: frontend
|
||||
run: npm ci --legacy-peer-deps
|
||||
- name: Build
|
||||
working-directory: frontend
|
||||
run: npm run build
|
||||
- name: Upload artifact
|
||||
uses: actions/upload-pages-artifact@v3
|
||||
with:
|
||||
path: frontend/out
|
||||
```
|
||||
|
||||
### Manual Deployment
|
||||
|
||||
If needed, manually deploy via GitHub Pages settings:
|
||||
1. Build: `cd frontend && npm run build`
|
||||
2. Upload `frontend/out/` contents to GitHub Pages
|
||||
3. Wait for GitHub Pages to rebuild
|
||||
|
||||
## Configuration Files
|
||||
|
||||
### `next.config.mjs`
|
||||
|
||||
```javascript
|
||||
/** @type {import('next').NextConfig} */
|
||||
const nextConfig = {
|
||||
output: 'export', // Static export for GitHub Pages
|
||||
trailingSlash: true, // Ensures paths work on static hosts
|
||||
typescript: {
|
||||
ignoreBuildErrors: false // Enforce type safety
|
||||
}
|
||||
};
|
||||
```
|
||||
|
||||
### `package.json`
|
||||
|
||||
Key dependencies:
|
||||
- `next@16.0.7` - Framework
|
||||
- `react@19.0.0` - UI library
|
||||
- `lucide-react` - Icon library
|
||||
- `tailwindcss` - Utility-first CSS
|
||||
- `@testing-library/react` - Testing
|
||||
|
||||
## Common Issues
|
||||
|
||||
### Issue: API requests return 404
|
||||
|
||||
**Cause**: Frontend trying to call `gen.nomadkaraoke.com/api` instead of `api.nomadkaraoke.com/api`
|
||||
|
||||
**Solution**: Verify `API_BASE_URL` in `lib/api.ts` is set to `https://api.nomadkaraoke.com`
|
||||
|
||||
### Issue: API requests return 401 Unauthorized
|
||||
|
||||
**Cause**: No token or invalid token
|
||||
|
||||
**Solution**: Enter a valid access token via the AuthBanner
|
||||
|
||||
### Issue: Changes not appearing after deployment
|
||||
|
||||
**Cause**: GitHub Pages caching or CDN propagation delay
|
||||
|
||||
**Solutions**:
|
||||
- Wait 2-5 minutes for CDN to update
|
||||
- Hard refresh browser (Cmd/Ctrl + Shift + R)
|
||||
- Check GitHub Actions for deployment status
|
||||
|
||||
### Issue: Build fails in CI with dependency conflicts
|
||||
|
||||
**Cause**: React 19 peer dependency mismatch with testing libraries
|
||||
|
||||
**Solution**: Use `npm ci --legacy-peer-deps` (already configured in CI)
|
||||
|
||||
## Testing
|
||||
|
||||
### Running Tests
|
||||
|
||||
```bash
|
||||
cd frontend
|
||||
|
||||
# Run all tests
|
||||
npm test
|
||||
|
||||
# Run with coverage
|
||||
npm run test:coverage
|
||||
|
||||
# Run in CI mode (non-interactive)
|
||||
npm run test:ci
|
||||
```
|
||||
|
||||
### Test Structure
|
||||
|
||||
```
|
||||
frontend/
|
||||
├── components/__tests__/
|
||||
│ ├── JobCard.test.tsx
|
||||
│ └── ...
|
||||
└── lib/__tests__/
|
||||
├── api.test.ts
|
||||
└── ...
|
||||
```
|
||||
|
||||
### Coverage Requirements
|
||||
|
||||
Minimum 70% code coverage enforced in CI (though frontend tests are still being expanded).
|
||||
|
||||
## API Integration
|
||||
|
||||
### Request Flow
|
||||
|
||||
1. User action in UI (e.g., click "Create Job")
|
||||
2. Component calls API function from `lib/api.ts`
|
||||
3. API function adds auth header if token exists
|
||||
4. Fetch request to `api.nomadkaraoke.com`
|
||||
5. Response parsed and returned
|
||||
6. Component updates UI with response data
|
||||
|
||||
### Error Handling
|
||||
|
||||
All API errors are wrapped in `ApiError` class:
|
||||
|
||||
```typescript
|
||||
try {
|
||||
const jobs = await api.listJobs({ limit: 20 });
|
||||
setJobs(jobs);
|
||||
} catch (error) {
|
||||
if (error instanceof ApiError) {
|
||||
console.error(`API Error ${error.status}: ${error.message}`);
|
||||
// error.data contains full response body
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Future Enhancements
|
||||
|
||||
Potential improvements for future iterations:
|
||||
|
||||
1. **OAuth Integration**: Replace manual token entry with OAuth flow
|
||||
2. **Real-time Updates**: WebSocket connection for live job updates
|
||||
3. **Admin Dashboard**: User management, token generation, system stats
|
||||
4. **Job History**: Pagination and filtering for large job lists
|
||||
5. **Batch Operations**: Select and manage multiple jobs at once
|
||||
6. **Mobile Optimization**: Responsive design improvements for mobile devices
|
||||
7. **Offline Support**: Service worker for offline functionality
|
||||
8. **Enhanced Testing**: Increase test coverage to 90%+
|
||||
|
||||
## Related Documentation
|
||||
|
||||
- [Backend API Reference](../README.md#backend-api-reference)
|
||||
- [Cloud Run Deployment](../03-deployment/CLOUD-RUN-DEPLOYMENT.md)
|
||||
- [Architecture Overview](./ARCHITECTURE.md)
|
||||
- [GitHub Pages Setup](.github/workflows/ci.yml)
|
||||
|
||||
---
|
||||
|
||||
**Last Updated**: December 2025
|
||||
**Frontend Version**: Deployed from `main` branch commit `91f51d6`
|
||||
|
||||
@@ -0,0 +1,485 @@
|
||||
# Job Debugging Guide
|
||||
|
||||
This guide explains how to access debug info, observability, metrics, logs, and data about a given job ID in the karaoke-gen cloud backend.
|
||||
|
||||
**Last Updated:** 2025-12-28
|
||||
|
||||
---
|
||||
|
||||
## Prerequisites
|
||||
|
||||
### Service Account Authentication
|
||||
|
||||
For automated access, set the service account impersonation variable:
|
||||
|
||||
```bash
|
||||
export GOOGLE_IMPERSONATE_SERVICE_ACCOUNT=claude-automation@nomadkaraoke.iam.gserviceaccount.com
|
||||
```
|
||||
|
||||
This service account has permissions to:
|
||||
- Read Firestore documents
|
||||
- Read Cloud Storage files
|
||||
- Query Cloud Logging
|
||||
- Describe Cloud Run services
|
||||
- List Cloud Tasks queues
|
||||
|
||||
### Required Tools
|
||||
|
||||
- `gcloud` CLI (authenticated)
|
||||
- Python 3.10+ with `google-cloud-firestore` installed
|
||||
- Access to the `nomadkaraoke` GCP project
|
||||
|
||||
---
|
||||
|
||||
## Quick Reference
|
||||
|
||||
| Data Type | Location | Access Method |
|
||||
|-----------|----------|---------------|
|
||||
| Job state & metadata | Firestore `jobs/{job_id}` | Python script |
|
||||
| Processing logs | Cloud Logging | `gcloud logging read` |
|
||||
| Audio/video files | GCS bucket | `gcloud storage` |
|
||||
| Service health | Cloud Run | `gcloud run services describe` |
|
||||
| Task queues | Cloud Tasks | `gcloud tasks queues list` |
|
||||
|
||||
---
|
||||
|
||||
## 1. Fetching Job Data from Firestore
|
||||
|
||||
Firestore stores all job state including status, timeline, worker logs, and file URLs.
|
||||
|
||||
### Using Python (Recommended)
|
||||
|
||||
A helper script is included at `scripts/get_job.py`. You can also create your own:
|
||||
|
||||
```python
|
||||
#!/usr/bin/env python3
|
||||
"""Fetch and display job data from Firestore."""
|
||||
import sys
|
||||
import json
|
||||
from google.cloud import firestore
|
||||
|
||||
def get_job(job_id: str):
|
||||
db = firestore.Client(project='nomadkaraoke')
|
||||
doc = db.collection('jobs').document(job_id).get()
|
||||
|
||||
if doc.exists:
|
||||
data = doc.to_dict()
|
||||
print(json.dumps(data, indent=2, default=str))
|
||||
else:
|
||||
print(f"Job {job_id} not found")
|
||||
sys.exit(1)
|
||||
|
||||
if __name__ == "__main__":
|
||||
if len(sys.argv) != 2:
|
||||
print("Usage: python get_job.py <job_id>")
|
||||
sys.exit(1)
|
||||
get_job(sys.argv[1])
|
||||
```
|
||||
|
||||
Run it:
|
||||
|
||||
```bash
|
||||
python get_job.py ffb0b8fa
|
||||
```
|
||||
|
||||
### Example Output
|
||||
|
||||
```json
|
||||
{
|
||||
"status": "in_review",
|
||||
"artist": "piri",
|
||||
"title": "dog",
|
||||
"created_at": "2025-12-28T01:55:23.914454",
|
||||
"audio_search_artist": "piri",
|
||||
"audio_search_title": "dog",
|
||||
"timeline": [
|
||||
{
|
||||
"timestamp": "2025-12-28T01:55:23.995388",
|
||||
"message": "Searching for: piri - dog",
|
||||
"progress": 5,
|
||||
"status": "searching_audio"
|
||||
},
|
||||
{
|
||||
"timestamp": "2025-12-28T01:55:24.249594",
|
||||
"message": "Found 20 audio sources. Waiting for selection.",
|
||||
"progress": 10,
|
||||
"status": "awaiting_audio_selection"
|
||||
}
|
||||
// ... more timeline entries
|
||||
],
|
||||
"worker_logs": [
|
||||
{
|
||||
"level": "INFO",
|
||||
"message": "=== AUDIO WORKER STARTED ===",
|
||||
"timestamp": "2025-12-28T01:55:37.559644Z",
|
||||
"worker": "audio"
|
||||
}
|
||||
// ... more worker logs
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
### Key Fields to Check
|
||||
|
||||
| Field | Description |
|
||||
|-------|-------------|
|
||||
| `status` | Current job status (e.g., `in_review`, `complete`, `failed`) |
|
||||
| `error_message` | Error description if job failed |
|
||||
| `timeline` | Ordered list of status transitions with timestamps |
|
||||
| `worker_logs` | Logs captured from worker processes |
|
||||
| `file_urls` | Signed URLs for generated files |
|
||||
| `state_data` | Worker-specific progress data |
|
||||
|
||||
---
|
||||
|
||||
## 2. Viewing Cloud Run Logs
|
||||
|
||||
Logs are stored in Cloud Logging and can be queried with `gcloud logging read`.
|
||||
|
||||
### Search Logs for a Job ID
|
||||
|
||||
```bash
|
||||
gcloud logging read \
|
||||
'resource.type="cloud_run_revision" AND resource.labels.service_name="karaoke-backend" AND "ffb0b8fa"' \
|
||||
--project=nomadkaraoke \
|
||||
--limit=50 \
|
||||
--format='table(timestamp,severity,jsonPayload.message,jsonPayload.logger)'
|
||||
```
|
||||
|
||||
### Filter by Severity (Errors Only)
|
||||
|
||||
```bash
|
||||
gcloud logging read \
|
||||
'resource.type="cloud_run_revision" AND resource.labels.service_name="karaoke-backend" AND "ffb0b8fa" AND severity>=ERROR' \
|
||||
--project=nomadkaraoke \
|
||||
--limit=20 \
|
||||
--format=json
|
||||
```
|
||||
|
||||
### Filter by Time Window
|
||||
|
||||
```bash
|
||||
gcloud logging read \
|
||||
'resource.type="cloud_run_revision" AND resource.labels.service_name="karaoke-backend" AND "ffb0b8fa" AND timestamp>="2025-12-28T01:55:00Z" AND timestamp<="2025-12-28T02:05:00Z"' \
|
||||
--project=nomadkaraoke \
|
||||
--limit=100 \
|
||||
--order=asc \
|
||||
--format='table(timestamp,severity,jsonPayload.message)'
|
||||
```
|
||||
|
||||
### Search for Exceptions
|
||||
|
||||
```bash
|
||||
gcloud logging read \
|
||||
'resource.type="cloud_run_revision" AND resource.labels.service_name="karaoke-backend" AND (jsonPayload.message:"Exception" OR jsonPayload.message:"Traceback")' \
|
||||
--project=nomadkaraoke \
|
||||
--limit=10 \
|
||||
--format='table(timestamp,severity,jsonPayload.message)'
|
||||
```
|
||||
|
||||
### View HTTP Request Logs
|
||||
|
||||
```bash
|
||||
gcloud logging read \
|
||||
'resource.type="cloud_run_revision" AND resource.labels.service_name="karaoke-backend" AND httpRequest.requestUrl:"ffb0b8fa"' \
|
||||
--project=nomadkaraoke \
|
||||
--limit=20 \
|
||||
--format='table(timestamp,httpRequest.status,httpRequest.requestMethod,httpRequest.requestUrl)'
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 3. Accessing Job Files in Cloud Storage
|
||||
|
||||
Files are stored in `gs://karaoke-gen-storage-nomadkaraoke/jobs/{job_id}/`.
|
||||
|
||||
### List All Files for a Job
|
||||
|
||||
```bash
|
||||
gcloud storage ls -r gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/ --project=nomadkaraoke
|
||||
```
|
||||
|
||||
Example output:
|
||||
|
||||
```
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/:
|
||||
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/lyrics/:
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/lyrics/corrections.json
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/lyrics/karaoke.lrc
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/lyrics/piri - dog (Lyrics Genius).txt
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/lyrics/uncorrected.txt
|
||||
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/previews/:
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/previews/86b528e04907.mp4
|
||||
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/screens/:
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/screens/end.jpg
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/screens/end.mov
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/screens/title.jpg
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/screens/title.mov
|
||||
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/stems/:
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/stems/backing_vocals.flac
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/stems/instrumental_clean.flac
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/stems/instrumental_with_backing.flac
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/stems/lead_vocals.flac
|
||||
gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/stems/vocals_clean.flac
|
||||
```
|
||||
|
||||
### View File Content (Small Files)
|
||||
|
||||
```bash
|
||||
gcloud storage cat gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/lyrics/corrections.json --project=nomadkaraoke | head -50
|
||||
```
|
||||
|
||||
### Get File Metadata
|
||||
|
||||
```bash
|
||||
gcloud storage objects describe gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/stems/instrumental_clean.flac --project=nomadkaraoke
|
||||
```
|
||||
|
||||
Example output:
|
||||
|
||||
```yaml
|
||||
bucket: karaoke-gen-storage-nomadkaraoke
|
||||
content_type: application/octet-stream
|
||||
crc32c_hash: /uXURg==
|
||||
creation_time: 2025-12-28T01:57:44+0000
|
||||
size: 18115881
|
||||
storage_class: STANDARD
|
||||
```
|
||||
|
||||
### Download a File
|
||||
|
||||
```bash
|
||||
gcloud storage cp gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/stems/instrumental_clean.flac ./instrumental.flac --project=nomadkaraoke
|
||||
```
|
||||
|
||||
### GCS Folder Structure
|
||||
|
||||
```
|
||||
jobs/{job_id}/
|
||||
├── lyrics/
|
||||
│ ├── corrections.json # Lyrics with timing corrections
|
||||
│ ├── karaoke.lrc # LRC format lyrics
|
||||
│ ├── uncorrected.txt # Raw transcription
|
||||
│ └── *.txt # Reference lyrics from sources
|
||||
├── previews/
|
||||
│ └── {hash}.mp4 # Preview video for lyrics review
|
||||
├── screens/
|
||||
│ ├── title.mov/.jpg/.png # Title screen
|
||||
│ └── end.mov/.jpg/.png # End screen
|
||||
├── stems/
|
||||
│ ├── instrumental_clean.flac
|
||||
│ ├── instrumental_with_backing.flac
|
||||
│ ├── vocals_clean.flac
|
||||
│ ├── lead_vocals.flac
|
||||
│ └── backing_vocals.flac
|
||||
├── videos/
|
||||
│ └── with_vocals.mkv # Karaoke video with lyrics overlay
|
||||
└── finals/
|
||||
├── lossless_4k.mp4
|
||||
├── lossless_4k.mkv
|
||||
├── lossy_4k.mp4
|
||||
└── lossy_720p.mp4
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 4. Cloud Run Service Status
|
||||
|
||||
### Check Service Health
|
||||
|
||||
```bash
|
||||
gcloud run services describe karaoke-backend \
|
||||
--project=nomadkaraoke \
|
||||
--region=us-central1 \
|
||||
--format='yaml(status.conditions,status.latestReadyRevisionName,status.url)'
|
||||
```
|
||||
|
||||
Example output:
|
||||
|
||||
```yaml
|
||||
status:
|
||||
conditions:
|
||||
- lastTransitionTime: '2025-12-28T01:29:43.465349Z'
|
||||
status: 'True'
|
||||
type: Ready
|
||||
- lastTransitionTime: '2025-12-28T01:29:42.192338Z'
|
||||
status: 'True'
|
||||
type: ConfigurationsReady
|
||||
- lastTransitionTime: '2025-12-28T01:29:43.430737Z'
|
||||
status: 'True'
|
||||
type: RoutesReady
|
||||
latestReadyRevisionName: karaoke-backend-00203-c7q
|
||||
url: https://karaoke-backend-ipzqd2k4yq-uc.a.run.app
|
||||
```
|
||||
|
||||
### List Recent Revisions
|
||||
|
||||
```bash
|
||||
gcloud run revisions list \
|
||||
--service=karaoke-backend \
|
||||
--project=nomadkaraoke \
|
||||
--region=us-central1 \
|
||||
--limit=5 \
|
||||
--format='table(name,status.conditions.type,status.conditions.status,createTime)'
|
||||
```
|
||||
|
||||
### View Revision Details
|
||||
|
||||
```bash
|
||||
gcloud run revisions describe karaoke-backend-00203-c7q \
|
||||
--project=nomadkaraoke \
|
||||
--region=us-central1 \
|
||||
--format='yaml(spec.containerConcurrency,spec.containers[0].resources)'
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 5. Cloud Tasks Queues
|
||||
|
||||
The backend uses Cloud Tasks for async worker processing.
|
||||
|
||||
### List All Queues
|
||||
|
||||
```bash
|
||||
gcloud tasks queues list --project=nomadkaraoke --location=us-central1
|
||||
```
|
||||
|
||||
Example output:
|
||||
|
||||
```
|
||||
QUEUE_NAME STATE MAX_NUM_OF_TASKS MAX_RATE (/sec) MAX_ATTEMPTS
|
||||
audio-worker-queue RUNNING 50 10.0 3
|
||||
lyrics-worker-queue RUNNING 50 10.0 3
|
||||
render-worker-queue RUNNING 20 5.0 2
|
||||
screens-worker-queue RUNNING 100 50.0 3
|
||||
video-worker-queue RUNNING 10 3.0 2
|
||||
```
|
||||
|
||||
### View Queue Details
|
||||
|
||||
```bash
|
||||
gcloud tasks queues describe audio-worker-queue \
|
||||
--project=nomadkaraoke \
|
||||
--location=us-central1
|
||||
```
|
||||
|
||||
### List Tasks in a Queue
|
||||
|
||||
```bash
|
||||
gcloud tasks list \
|
||||
--queue=audio-worker-queue \
|
||||
--project=nomadkaraoke \
|
||||
--location=us-central1 \
|
||||
--limit=10
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 6. Common Debugging Scenarios
|
||||
|
||||
### Scenario: Job Stuck in Status
|
||||
|
||||
1. **Check job state:**
|
||||
```bash
|
||||
python get_job.py ffb0b8fa | jq '.status, .error_message, .timeline[-3:]'
|
||||
```
|
||||
|
||||
2. **Check for errors in logs:**
|
||||
```bash
|
||||
gcloud logging read 'resource.labels.service_name="karaoke-backend" AND "ffb0b8fa" AND severity>=ERROR' --project=nomadkaraoke --limit=5 --format=json
|
||||
```
|
||||
|
||||
3. **Check if worker task is queued:**
|
||||
```bash
|
||||
gcloud tasks list --queue=audio-worker-queue --project=nomadkaraoke --location=us-central1
|
||||
```
|
||||
|
||||
### Scenario: Job Failed
|
||||
|
||||
1. **Get error message from Firestore:**
|
||||
```bash
|
||||
python get_job.py ffb0b8fa | jq '.error_message, .error_details'
|
||||
```
|
||||
|
||||
2. **Search for exception stack trace:**
|
||||
```bash
|
||||
gcloud logging read 'resource.labels.service_name="karaoke-backend" AND "ffb0b8fa" AND jsonPayload.message:"Traceback"' --project=nomadkaraoke --limit=3 --format='value(jsonPayload.message)'
|
||||
```
|
||||
|
||||
### Scenario: Missing Output Files
|
||||
|
||||
1. **List all generated files:**
|
||||
```bash
|
||||
gcloud storage ls -r gs://karaoke-gen-storage-nomadkaraoke/jobs/ffb0b8fa/ --project=nomadkaraoke
|
||||
```
|
||||
|
||||
2. **Check worker logs for upload failures:**
|
||||
```bash
|
||||
gcloud logging read 'resource.labels.service_name="karaoke-backend" AND "ffb0b8fa" AND (jsonPayload.message:"upload" OR jsonPayload.message:"GCS")' --project=nomadkaraoke --limit=20 --format='table(timestamp,jsonPayload.message)'
|
||||
```
|
||||
|
||||
### Scenario: Audio Separation Slow/Failing
|
||||
|
||||
1. **Check audio worker logs:**
|
||||
```bash
|
||||
gcloud logging read 'resource.labels.service_name="karaoke-backend" AND "ffb0b8fa" AND jsonPayload.worker:"audio"' --project=nomadkaraoke --limit=30 --format='table(timestamp,jsonPayload.message)'
|
||||
```
|
||||
|
||||
2. **Check Modal API status in worker logs:**
|
||||
```bash
|
||||
python get_job.py ffb0b8fa | jq '.worker_logs | map(select(.worker == "audio"))'
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 7. Useful Aliases
|
||||
|
||||
Add these to your shell profile for quick access:
|
||||
|
||||
```bash
|
||||
# Job debugging aliases (update paths as needed)
|
||||
alias kj='python scripts/get_job.py'
|
||||
alias klogs='gcloud logging read "resource.labels.service_name=\"karaoke-backend\"" --project=nomadkaraoke --limit=50 --format="table(timestamp,severity,jsonPayload.message)"'
|
||||
alias kfiles='gcloud storage ls -r gs://karaoke-gen-storage-nomadkaraoke/jobs/'
|
||||
alias kservice='gcloud run services describe karaoke-backend --project=nomadkaraoke --region=us-central1'
|
||||
alias kqueues='gcloud tasks queues list --project=nomadkaraoke --location=us-central1'
|
||||
|
||||
# Usage:
|
||||
# kj ffb0b8fa # Get job data
|
||||
# klogs | grep ffb0b8fa # Search logs
|
||||
# kfiles ffb0b8fa/ # List job files
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 8. API Access (Alternative)
|
||||
|
||||
The backend API also provides job information if you have an access token.
|
||||
|
||||
### Get Job via API
|
||||
|
||||
```bash
|
||||
export TOKEN="your-access-token"
|
||||
curl -s -H "Authorization: Bearer $TOKEN" \
|
||||
"https://api.nomadkaraoke.com/api/jobs/ffb0b8fa" | jq
|
||||
```
|
||||
|
||||
### List Jobs
|
||||
|
||||
```bash
|
||||
curl -s -H "Authorization: Bearer $TOKEN" \
|
||||
"https://api.nomadkaraoke.com/api/jobs?limit=10" | jq
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Related Documentation
|
||||
|
||||
- [Architecture Overview](./ARCHITECTURE.md) - System architecture and data flow
|
||||
- [Frontend Guide](./FRONTEND-GUIDE.md) - Web UI documentation
|
||||
- [Backend Feature Parity](../00-current-plan/BACKEND-FEATURE-PARITY-PLAN.md) - Feature status
|
||||
- [Scalable Architecture Plan](../00-current-plan/SCALABLE-ARCHITECTURE-PLAN.md) - Cloud Tasks and scaling
|
||||
@@ -0,0 +1,106 @@
|
||||
# Instrumental Review: Original Audio Tab Support
|
||||
|
||||
**Date:** 2025-12-22
|
||||
**Version:** 0.75.12
|
||||
|
||||
## Summary
|
||||
|
||||
Added support for an "Original Audio" tab in the Instrumental Review UI, allowing users to compare the original audio (with lead vocals) alongside the backing vocals, clean instrumental, and instrumental with backing vocals options. This helps users make better decisions about whether certain audio regions are actually backing vocals or need to be muted.
|
||||
|
||||
## Problem
|
||||
|
||||
When reviewing backing vocals in the Instrumental Review UI, users couldn't hear the original full song to compare and determine whether detected regions were actually backing vocals or if they needed to be muted. This made it difficult to make informed decisions about the instrumental selection.
|
||||
|
||||
## Solution
|
||||
|
||||
The Instrumental Review HTML UI already had built-in support for displaying an "Original Audio" tab when `hasOriginal` flag was set, but this feature was not being activated because the `original_audio_path` parameter was not being passed to the `InstrumentalReviewServer`.
|
||||
|
||||
### Changes Made
|
||||
|
||||
1. **`karaoke_gen/utils/gen_cli.py`** (lines 203-217, 239):
|
||||
- Added code to locate the original audio file from the track data (`track.get("input_audio_wav")`)
|
||||
- Resolved the path relative to the track directory
|
||||
- Passed `original_audio_path` parameter when initializing `InstrumentalReviewServer`
|
||||
|
||||
2. **`scripts/test-instrumental-review.py`**:
|
||||
- Added optional `--original` command-line argument
|
||||
- Added validation for the original audio file path
|
||||
- Passed `original_audio_path` parameter to `InstrumentalReviewServer`
|
||||
|
||||
3. **`tests/unit/test_instrumental_review/test_server.py`**:
|
||||
- Added `test_server_initialization_with_original_audio()` to verify server properly stores the original audio path
|
||||
- Added `test_get_analysis_with_original_audio()` to verify the API properly exposes `has_original` flag and original audio URL
|
||||
|
||||
4. **`pyproject.toml`**:
|
||||
- Bumped version from 0.75.11 to 0.75.12
|
||||
|
||||
## How It Works
|
||||
|
||||
### Backend Flow
|
||||
|
||||
1. When the instrumental review is triggered, the system:
|
||||
- Locates the original audio file (`input_audio_wav` from the track data)
|
||||
- Resolves the path relative to the working directory
|
||||
- Passes it to `InstrumentalReviewServer` as `original_audio_path`
|
||||
|
||||
2. The server exposes the original audio through:
|
||||
- `/api/audio/original` endpoint (serves the audio file)
|
||||
- `has_original: true` flag in the analysis response
|
||||
|
||||
### Frontend Flow
|
||||
|
||||
The HTML UI (already implemented in `karaoke_gen/instrumental_review/static/index.html`):
|
||||
- Checks `hasOriginal` flag from the API
|
||||
- Conditionally shows "Original" tab in the audio toggle group (line 697-699)
|
||||
- Provides audio player that switches between:
|
||||
- **Original Audio** - Full song with lead vocals
|
||||
- **Backing Vocals Only** - Isolated backing vocals
|
||||
- **Pure Instrumental** - Clean instrumental (no vocals)
|
||||
- **Instrumental + Backing** - Instrumental with backing vocals included
|
||||
- **Custom** - User-created muted regions
|
||||
|
||||
### Usage
|
||||
|
||||
When running the local CLI:
|
||||
```bash
|
||||
karaoke-gen "Artist" "Song Title"
|
||||
```
|
||||
|
||||
During the instrumental review phase, the UI will now automatically show the "Original Audio" tab if the original audio file is available.
|
||||
|
||||
For testing:
|
||||
```bash
|
||||
python scripts/test-instrumental-review.py \
|
||||
backing_vocals.flac \
|
||||
clean_instrumental.flac \
|
||||
--with_backing instrumental_with_backing.flac \
|
||||
--original original.wav
|
||||
```
|
||||
|
||||
## Files Modified
|
||||
|
||||
- `karaoke_gen/utils/gen_cli.py` - Added original audio path detection and passing
|
||||
- `scripts/test-instrumental-review.py` - Added --original argument support
|
||||
- `tests/unit/test_instrumental_review/test_server.py` - Added tests for original audio functionality
|
||||
- `pyproject.toml` - Version bump
|
||||
|
||||
## Testing
|
||||
|
||||
All 139 tests in `tests/unit/test_instrumental_review/` pass, including:
|
||||
- `TestServerInitialization::test_server_initialization_with_original_audio` - Verifies server stores original audio path
|
||||
- `TestServerAPIEndpoints::test_get_analysis_with_original_audio` - Verifies API exposes original audio properly
|
||||
|
||||
## Benefits
|
||||
|
||||
1. **Better Decision Making**: Users can hear the full original song to compare against backing vocals
|
||||
2. **Improved Accuracy**: Easier to identify if detected regions are truly backing vocals or artifacts
|
||||
3. **No UI Changes Required**: Leveraged existing UI capabilities that were already built-in
|
||||
4. **Backward Compatible**: If no original audio is provided, the tab simply doesn't appear
|
||||
|
||||
## Implementation Notes
|
||||
|
||||
- The original audio feature is optional - if the file is not available, the tab won't appear
|
||||
- The server already had the route handler for serving original audio (`/api/audio/original`)
|
||||
- The HTML UI already had the conditional rendering logic for the "Original" tab
|
||||
- The main change was ensuring the `original_audio_path` parameter was properly populated and passed through
|
||||
|
||||
@@ -0,0 +1,196 @@
|
||||
# CLI + Backend Integration Testing
|
||||
|
||||
## The Problem
|
||||
|
||||
We had multiple bugs that unit tests didn't catch:
|
||||
- Content-type mismatch in signed URL uploads (403 errors)
|
||||
- Missing auth headers in download requests (all downloads failed)
|
||||
- YouTube description field name mismatch (uploads silently failed)
|
||||
- Style file path handling issues
|
||||
|
||||
These bugs required:
|
||||
1. Full CI/CD deploy (~12 min)
|
||||
2. Full karaoke generation (~10 min)
|
||||
3. Manual inspection of logs
|
||||
|
||||
**Total: 20+ minutes per iteration** 😱
|
||||
|
||||
## The Solution
|
||||
|
||||
New **CLI + Backend Integration Tests** that:
|
||||
- Run the ACTUAL CLI code against a LOCAL backend
|
||||
- Use GCP emulators (Firestore + GCS)
|
||||
- Test the full signed URL upload flow
|
||||
- Run in **< 30 seconds**
|
||||
|
||||
## Test Architecture
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────┐
|
||||
│ Unit Tests (Mocked) │ ← Fast, isolated
|
||||
│ tests/unit/ │ ~0.5s, 100+ tests
|
||||
├─────────────────────────────────────┤
|
||||
│ Backend Emulator Tests │ ← Backend-only integration
|
||||
│ backend/tests/emulator/ │ ~10s, uses Firestore/GCS
|
||||
│ - test_emulator_integration.py │ Basic CRUD operations
|
||||
│ - test_e2e_cli_backend.py │ Full CLI → Backend flow
|
||||
├─────────────────────────────────────┤
|
||||
│ Cloud Integration Tests │ ← Against deployed backend
|
||||
│ backend/tests/test_api_integration│ ~10min, pre-prod only
|
||||
└─────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Run All Integration Tests
|
||||
|
||||
```bash
|
||||
./scripts/run-cli-integration-tests.sh
|
||||
```
|
||||
|
||||
This automatically:
|
||||
1. Starts GCP emulators
|
||||
2. Starts local backend
|
||||
3. Runs tests
|
||||
4. Cleans up
|
||||
|
||||
### Interactive Development Mode
|
||||
|
||||
```bash
|
||||
# Terminal 1: Start environment
|
||||
./scripts/start-local-test-env.sh
|
||||
|
||||
# Terminal 2: Run specific tests repeatedly
|
||||
pytest tests/integration/test_cli_backend_integration.py -v -k "test_style_params"
|
||||
```
|
||||
|
||||
## What These Tests Catch
|
||||
|
||||
### ✅ Content-Type Mismatches
|
||||
```python
|
||||
def test_style_params_json_upload(self, test_style_files, cli_config):
|
||||
"""Test uploading style_params.json via signed URL."""
|
||||
# This would have caught the Path('.json').suffix bug!
|
||||
result = client.search_audio(
|
||||
artist="Test Artist",
|
||||
title="Test Song",
|
||||
style_params_path=test_style_files['style_params_path'],
|
||||
)
|
||||
# If we get 403, the test fails with a clear message
|
||||
```
|
||||
|
||||
### ✅ Request/Response Format Mismatches
|
||||
Tests verify CLI and backend agree on API contract.
|
||||
|
||||
### ✅ GCS Path Issues
|
||||
Uploads go to real (emulated) GCS, catches path/encoding bugs.
|
||||
|
||||
### ✅ Auth Token Handling
|
||||
Tests run with actual token flow.
|
||||
|
||||
### ✅ Download Auth Headers
|
||||
```python
|
||||
def test_download_uses_session_not_requests(self, cli_client, tmp_path):
|
||||
"""Verify downloads use session.get() not requests.get()."""
|
||||
# This catches the bug where downloads failed with 401/403
|
||||
# because auth headers weren't included
|
||||
```
|
||||
|
||||
### ✅ Cross-Component Field Mapping
|
||||
```python
|
||||
def test_job_has_youtube_description_template(self, client, auth_headers):
|
||||
"""Test youtube_description AND youtube_description_template are set."""
|
||||
# audio_search sets youtube_description
|
||||
# video_worker reads youtube_description_template
|
||||
# Both must be set for YouTube upload to work!
|
||||
```
|
||||
|
||||
## When to Run
|
||||
|
||||
| Situation | Run This |
|
||||
|-----------|----------|
|
||||
| Quick check before commit | `./scripts/run-emulator-tests.sh` |
|
||||
| Testing CLI changes | `./scripts/run-cli-integration-tests.sh` |
|
||||
| Testing backend API changes | `./scripts/run-cli-integration-tests.sh` |
|
||||
| Before creating PR | Both of the above |
|
||||
| Pre-production | Cloud integration tests |
|
||||
|
||||
## Test Files
|
||||
|
||||
### `backend/tests/emulator/test_e2e_cli_backend.py` (Primary)
|
||||
|
||||
Key test classes:
|
||||
- `TestStyleFileUploadE2E` - Full style file upload flow with content-type verification
|
||||
- `TestYouTubeDescriptionFieldMapping` - Verifies youtube_description_template is set
|
||||
- `TestDownloadAuthHeaders` - Verifies auth headers are sent with downloads
|
||||
- `TestFullAudioSearchFlow` - Complete audio search → job creation flow
|
||||
- `TestCLIClientIntegration` - Tests actual CLI client code
|
||||
|
||||
### `tests/integration/test_cli_backend_integration.py` (Legacy)
|
||||
|
||||
- `TestSignedUrlUploadRoundTrip` - Full upload flow
|
||||
- `TestContentTypeMatching` - Content-type bug documentation
|
||||
- `TestAudioSearchWithStyles` - API contract tests
|
||||
|
||||
### Test Fixtures
|
||||
|
||||
- `test_style_files` - Creates minimal valid PNG/TTF/JSON files
|
||||
- `cli_config` - Points CLI at local backend
|
||||
|
||||
## Extending Tests
|
||||
|
||||
### Adding a New Integration Test
|
||||
|
||||
```python
|
||||
class TestMyNewFeature:
|
||||
def test_my_feature(self, cli_config, tmp_path):
|
||||
from karaoke_gen.utils.remote_cli import RemoteKaraokeClient, RemoteConfig
|
||||
import logging
|
||||
|
||||
config = RemoteConfig(
|
||||
service_url=cli_config['service_url'],
|
||||
auth_token=cli_config['auth_token'],
|
||||
environment='test'
|
||||
)
|
||||
client = RemoteKaraokeClient(config, logging.getLogger("test"))
|
||||
|
||||
# Test your feature
|
||||
result = client.some_method(...)
|
||||
assert result['expected_field'] == expected_value
|
||||
```
|
||||
|
||||
## Prerequisites
|
||||
|
||||
1. **Docker** (for fake-gcs-server)
|
||||
2. **gcloud CLI** with Firestore emulator:
|
||||
```bash
|
||||
gcloud components install cloud-firestore-emulator
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### "Emulators not running"
|
||||
```bash
|
||||
./scripts/start-emulators.sh
|
||||
```
|
||||
|
||||
### "Backend failed to start"
|
||||
Check if port 8000 is already in use:
|
||||
```bash
|
||||
lsof -i :8000
|
||||
```
|
||||
|
||||
### Tests pass locally but fail in CI
|
||||
The integration tests require Docker, which may not be available in all CI environments. Consider:
|
||||
- Running in a CI job with Docker support
|
||||
- Skipping in CI and running locally before merge
|
||||
|
||||
## Benefits
|
||||
|
||||
| Before | After |
|
||||
|--------|-------|
|
||||
| 20+ min per iteration | < 30 sec per iteration |
|
||||
| Manual log inspection | Automated assertions |
|
||||
| Bugs found in production | Bugs caught locally |
|
||||
| Expensive cloud resources | Free local emulators |
|
||||
|
||||
@@ -0,0 +1,145 @@
|
||||
# Backend API Authentication - Remaining Work
|
||||
|
||||
## Overview
|
||||
|
||||
This document tracks the progress of adding authentication requirements to ALL backend API endpoints. Currently, many endpoints are publicly accessible without any authentication, which is a **major security vulnerability**.
|
||||
|
||||
## Completed Endpoints
|
||||
|
||||
### ✅ jobs.py (20 endpoints) - DONE
|
||||
- All job management endpoints now require `Depends(require_auth)`
|
||||
- Includes: create, get, list, delete, bulk_delete, review endpoints, instrumental selection, download, cancel, retry, logs
|
||||
|
||||
### ✅ file_upload.py (6 endpoints) - DONE
|
||||
- upload_and_create_job
|
||||
- create_job_with_upload_urls
|
||||
- mark_uploads_complete
|
||||
- create_job_from_url
|
||||
- create_finalise_only_job
|
||||
- mark_finalise_uploads_complete
|
||||
|
||||
### ✅ audio_search.py (3 endpoints) - DONE
|
||||
- search_audio
|
||||
- get_audio_search_results
|
||||
- select_audio_source
|
||||
|
||||
### ⚠️ review.py (12 endpoints) - PARTIAL (4/12 done)
|
||||
|
||||
**Completed:**
|
||||
- get_correction_data ✅
|
||||
- complete_review ✅
|
||||
- add_lyrics ✅
|
||||
- generate_preview_video ✅
|
||||
|
||||
**Remaining - Need Auth:**
|
||||
- ❌ ping - Health check (maybe OK without auth?)
|
||||
- ❌ get_audio_with_hash - Audio streaming for review UI
|
||||
- ❌ get_audio_no_hash - Audio streaming for review UI
|
||||
- ❌ update_handlers - Correction handlers config
|
||||
- ❌ get_preview_video - Preview video streaming
|
||||
- ❌ submit_annotation - ML training data
|
||||
- ❌ get_annotation_stats - ML stats
|
||||
- ❌ (1 more endpoint not yet reviewed)
|
||||
|
||||
**Special Considerations:**
|
||||
- Audio streaming endpoints (`get_audio_*`) are used by the review UI frontend. May need token passed via query param or special handling.
|
||||
- `ping` endpoint is just a health check - possibly OK without auth
|
||||
|
||||
## Remaining Routes
|
||||
|
||||
### ❌ auth.py (8 endpoints) - TODO
|
||||
|
||||
These are auth-related endpoints themselves, so they have special requirements:
|
||||
|
||||
- `/auth/status` - Get OAuth credentials status (probably needs auth)
|
||||
- `/auth/status/{service}` - Get service credential status (probably needs auth)
|
||||
- `/auth/validate` - Validate credentials (probably needs auth)
|
||||
- `/auth/youtube/device` - Start YouTube device auth (admin only)
|
||||
- `/auth/youtube/device/{device_code}` - Poll YouTube auth (admin only)
|
||||
- `/auth/gdrive/device` - Start GDrive device auth (admin only)
|
||||
- `/auth/gdrive/device/{device_code}` - Poll GDrive auth (admin only)
|
||||
- (1 more endpoint)
|
||||
|
||||
**Recommendation:** Most/all of these should require admin auth (`Depends(require_admin)`)
|
||||
|
||||
### ❌ health.py (3 endpoints) - TODO
|
||||
|
||||
- `/health` - Basic health check (probably OK without auth for k8s/monitoring)
|
||||
- `/health/detailed` - Detailed health (should require auth)
|
||||
- `/readiness` - Readiness check for Cloud Run (probably OK without auth)
|
||||
|
||||
**Recommendation:**
|
||||
- Keep `/health` and `/readiness` unauthenticated for infrastructure monitoring
|
||||
- Require auth for `/health/detailed` as it may expose sensitive info
|
||||
|
||||
### ❌ internal.py (6 endpoints) - CRITICAL
|
||||
|
||||
**All worker trigger endpoints - MUST have auth!** Currently using `X-Admin-Token` header but needs formal validation:
|
||||
|
||||
- `/internal/workers/audio` - Trigger audio worker
|
||||
- `/internal/workers/lyrics` - Trigger lyrics worker
|
||||
- `/internal/workers/screens` - Trigger screens worker
|
||||
- `/internal/workers/video` - Trigger video worker
|
||||
- `/internal/workers/render-video` - Trigger render worker
|
||||
- `/internal/health` - Internal health (already has `require_admin`)
|
||||
|
||||
**Current State:** These endpoints check for `X-Admin-Token` in the request, but this should use the formal `require_admin` dependency.
|
||||
|
||||
**Recommendation:** ALL internal endpoints should use `Depends(require_admin)`
|
||||
|
||||
## Implementation Strategy
|
||||
|
||||
### Phase 1: Critical Security Fixes (HIGH PRIORITY)
|
||||
1. ✅ Complete jobs.py, file_upload.py, audio_search.py
|
||||
2. ❌ **Secure internal.py worker triggers** - These are the most critical as they allow arbitrary job manipulation
|
||||
3. ❌ **Secure auth.py admin endpoints** - Prevent unauthorized OAuth credential management
|
||||
|
||||
### Phase 2: User-Facing Endpoints
|
||||
1. ❌ Complete review.py endpoints (with special handling for streaming)
|
||||
2. ❌ health.py detailed endpoint
|
||||
|
||||
### Phase 3: Testing & Documentation
|
||||
1. ❌ Update frontend to always include auth token
|
||||
2. ❌ Test all endpoints with/without auth
|
||||
3. ❌ Update API documentation
|
||||
4. ❌ Add integration tests for auth
|
||||
|
||||
## Testing Checklist
|
||||
|
||||
After adding auth to all endpoints:
|
||||
|
||||
- [ ] Test job creation without token → should return 401
|
||||
- [ ] Test job listing without token → should return 401
|
||||
- [ ] Test worker triggers without admin token → should return 401 or 403
|
||||
- [ ] Test OAuth endpoints without admin token → should return 401 or 403
|
||||
- [ ] Test health endpoint without token → should work (by design)
|
||||
- [ ] Test authenticated requests with valid user token → should work
|
||||
- [ ] Test authenticated requests with valid admin token → should work
|
||||
- [ ] Update frontend auth flow to handle 401 errors gracefully
|
||||
|
||||
## Notes
|
||||
|
||||
- The authentication system is already implemented in `backend/api/dependencies.py`
|
||||
- Functions available: `require_auth()`, `require_admin()`, `optional_auth()`
|
||||
- Tokens are validated against `ADMIN_TOKENS` env var or Firestore user tokens
|
||||
- Frontend already has token storage in localStorage via `AuthBanner` component
|
||||
|
||||
## Migration Path for Frontend
|
||||
|
||||
Once all endpoints require auth:
|
||||
|
||||
1. Frontend must obtain a token (either admin token or user token from a signup flow)
|
||||
2. Token must be included in Authorization header: `Authorization: Bearer <token>`
|
||||
3. Alternatively, some endpoints support `?token=<token>` query parameter
|
||||
4. Update frontend API client to always include auth
|
||||
|
||||
##Frontend Update Required
|
||||
|
||||
Current state: Frontend has AuthBanner that prompts for token, but some endpoints worked without auth (security issue).
|
||||
New state: ALL endpoints require auth, so users MUST provide a token before using the app.
|
||||
|
||||
Update `frontend/lib/api.ts` to:
|
||||
- Throw user-friendly error if token is missing when calling authenticated endpoints
|
||||
- Handle 401 responses by prompting user to re-authenticate
|
||||
- Consider implementing a "logged out" state in the UI
|
||||
|
||||
@@ -0,0 +1,140 @@
|
||||
# Test Fixes Needed for Authentication
|
||||
|
||||
## Problem
|
||||
|
||||
After adding `Depends(require_auth)` to 33+ backend endpoints, all unit and integration tests are failing because they don't include authentication headers in their requests.
|
||||
|
||||
## Solution
|
||||
|
||||
All test requests to authenticated endpoints need to include:
|
||||
```python
|
||||
headers={"Authorization": "Bearer test-admin-token"}
|
||||
```
|
||||
|
||||
## Files Need Updating
|
||||
|
||||
### 1. Global Fixture (DONE)
|
||||
✅ `backend/tests/conftest.py` - Added mock_auth_service and auth_headers fixtures
|
||||
|
||||
### 2. Test Files to Update
|
||||
|
||||
Each test file needs:
|
||||
1. Mock auth service in the client fixture
|
||||
2. Add `auth_headers` parameter to test methods
|
||||
3. Pass `headers=auth_headers` to all client requests (get, post, put, delete)
|
||||
|
||||
Files:
|
||||
- `backend/tests/test_jobs_api.py` - ~15 test methods
|
||||
- `backend/tests/test_upload_api.py` - ~10 test methods
|
||||
- `backend/tests/test_audio_search.py` - ~5 test methods
|
||||
- `backend/tests/test_api_routes.py` - ~10 test methods
|
||||
- `backend/tests/test_instrumental_api.py` - ~5 test methods
|
||||
- `backend/tests/emulator/test_emulator_integration.py` - ~20 test methods
|
||||
|
||||
## Quick Fix Script
|
||||
|
||||
Rather than manually updating 60+ test methods, here's a Python script to auto-fix them:
|
||||
|
||||
```python
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Auto-fix test files to include authentication headers.
|
||||
"""
|
||||
import re
|
||||
from pathlib import Path
|
||||
|
||||
def fix_test_file(filepath):
|
||||
"""Add auth_headers to client requests in test file."""
|
||||
with open(filepath, 'r') as f:
|
||||
content = f.read()
|
||||
|
||||
# Pattern: client.METHOD(
|
||||
# Replace with: client.METHOD(..., headers=auth_headers)
|
||||
patterns = [
|
||||
# client.get("/path")
|
||||
(r'client\.(get|post|put|delete|patch)\((["\'][^"\']+["\'])\)',
|
||||
r'client.\1(\2, headers=auth_headers)'),
|
||||
|
||||
# client.get("/path", json={...})
|
||||
(r'client\.(get|post|put|delete|patch)\((["\'][^"\']+["\']),\s*json=',
|
||||
r'client.\1(\2, headers=auth_headers, json='),
|
||||
|
||||
# client.post("/path", data={...})
|
||||
(r'client\.(get|post|put|delete|patch)\((["\'][^"\']+["\']),\s*data=',
|
||||
r'client.\1(\2, headers=auth_headers, data='),
|
||||
|
||||
# client.post("/path", files={...})
|
||||
(r'client\.(post)\((["\'][^"\']+["\']),\s*files=',
|
||||
r'client.\1(\2, headers=auth_headers, files='),
|
||||
]
|
||||
|
||||
modified = content
|
||||
for pattern, replacement in patterns:
|
||||
modified = re.sub(pattern, replacement, modified)
|
||||
|
||||
# Add auth_headers parameter to test methods that don't have it
|
||||
# def test_something(self, client, mock_job):
|
||||
# -> def test_something(self, client, mock_job, auth_headers):
|
||||
modified = re.sub(
|
||||
r'def (test_\w+)\(self,\s*client([^)]*)\):',
|
||||
r'def \1(self, client\2, auth_headers):',
|
||||
modified
|
||||
)
|
||||
|
||||
with open(filepath, 'w') as f:
|
||||
f.write(modified)
|
||||
|
||||
print(f"Fixed: {filepath}")
|
||||
|
||||
# Find all test files
|
||||
test_dir = Path("backend/tests")
|
||||
for test_file in test_dir.rglob("test_*.py"):
|
||||
if 'conftest' not in str(test_file):
|
||||
fix_test_file(test_file)
|
||||
|
||||
print("Done!")
|
||||
```
|
||||
|
||||
## Manual Approach
|
||||
|
||||
For each test method:
|
||||
|
||||
**Before:**
|
||||
```python
|
||||
def test_get_job(self, client, mock_job_manager):
|
||||
response = client.get("/api/jobs/test123")
|
||||
assert response.status_code == 200
|
||||
```
|
||||
|
||||
**After:**
|
||||
```python
|
||||
def test_get_job(self, client, mock_job_manager, auth_headers):
|
||||
response = client.get("/api/jobs/test123", headers=auth_headers)
|
||||
assert response.status_code == 200
|
||||
```
|
||||
|
||||
## Emulator Tests
|
||||
|
||||
Emulator tests already have `auth_headers` fixture in `backend/tests/emulator/conftest.py`.
|
||||
Just need to:
|
||||
1. Add `auth_headers` parameter to test methods
|
||||
2. Pass `headers=auth_headers` to client requests
|
||||
|
||||
## Health Endpoints
|
||||
|
||||
Health endpoints (`/api/health`, `/api/readiness`) should remain unauthenticated, so those tests don't need auth headers.
|
||||
|
||||
## Internal API Tests
|
||||
|
||||
Internal API tests in `test_internal_api.py` already have auth handling via `X-Admin-Token` header. May need updating if we migrate to formal `require_admin`.
|
||||
|
||||
## Test Coverage
|
||||
|
||||
After fixes, run:
|
||||
```bash
|
||||
cd backend
|
||||
python -m pytest tests/ -v --ignore=tests/integration
|
||||
```
|
||||
|
||||
Should see all tests passing.
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
playwright-report-prod/
|
||||
@@ -0,0 +1,145 @@
|
||||
# Karaoke Generator Frontend
|
||||
|
||||
Next.js frontend for the Karaoke Generator application.
|
||||
|
||||
## Quick Start
|
||||
|
||||
```bash
|
||||
# Install dependencies
|
||||
npm install
|
||||
|
||||
# Run development server
|
||||
npm run dev
|
||||
```
|
||||
|
||||
The app will be available at http://localhost:3000
|
||||
|
||||
## Development Setup
|
||||
|
||||
### Connecting to the Cloud Backend
|
||||
|
||||
In development, the frontend proxies API requests to the cloud backend (`api.nomadkaraoke.com`) via Next.js rewrites. This avoids CORS issues and allows local development without running a local backend.
|
||||
|
||||
The proxy is configured in `next.config.mjs`:
|
||||
- All `/api/*` requests are forwarded to the cloud backend
|
||||
- You can override the backend URL with `BACKEND_URL` environment variable
|
||||
|
||||
### Authentication
|
||||
|
||||
The backend requires authentication. To authenticate:
|
||||
|
||||
1. Create a `.env.local` file in the frontend directory:
|
||||
```
|
||||
KARAOKE_ACCESS_TOKEN=your-token-here
|
||||
```
|
||||
|
||||
2. The token is automatically loaded by Playwright tests
|
||||
3. In the browser, the token is stored in `localStorage` as `karaoke_access_token`
|
||||
|
||||
## Testing
|
||||
|
||||
### Unit Tests (Jest)
|
||||
|
||||
```bash
|
||||
# Run tests in watch mode
|
||||
npm test
|
||||
|
||||
# Run tests with coverage
|
||||
npm run test:coverage
|
||||
|
||||
# Run tests in CI mode
|
||||
npm run test:ci
|
||||
```
|
||||
|
||||
### E2E Tests (Playwright)
|
||||
|
||||
E2E tests run against the local dev server connected to the real cloud backend.
|
||||
|
||||
```bash
|
||||
# Run all E2E tests
|
||||
npm run test:e2e
|
||||
|
||||
# Run with UI (interactive mode)
|
||||
npm run test:e2e:ui
|
||||
|
||||
# Run in headed mode (see the browser)
|
||||
npm run test:e2e:headed
|
||||
|
||||
# Run in debug mode
|
||||
npm run test:e2e:debug
|
||||
```
|
||||
|
||||
#### Authentication for E2E Tests
|
||||
|
||||
E2E tests require a valid access token. Set it in `.env.local`:
|
||||
|
||||
```
|
||||
KARAOKE_ACCESS_TOKEN=your-token-here
|
||||
```
|
||||
|
||||
The Playwright config (`playwright.config.ts`) automatically loads this file.
|
||||
|
||||
#### Test Structure
|
||||
|
||||
Tests are located in `e2e/`:
|
||||
|
||||
- `karaoke-generation.spec.ts` - Main test suite covering:
|
||||
- Homepage loading and form display
|
||||
- Search tab functionality
|
||||
- Audio search submission
|
||||
- Audio selection dialog flow
|
||||
- API health checks
|
||||
|
||||
#### Test Architecture
|
||||
|
||||
```
|
||||
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────────┐
|
||||
│ Playwright │────▶│ Next.js Dev │────▶│ Cloud Backend │
|
||||
│ Browser │ │ Server (:3000) │ │ api.nomadkaraoke │
|
||||
└─────────────────┘ └──────────────────┘ └─────────────────────┘
|
||||
│
|
||||
▼
|
||||
API Proxy
|
||||
/api/* → backend
|
||||
```
|
||||
|
||||
#### Debugging Test Failures
|
||||
|
||||
1. **Screenshots**: Failed tests save screenshots to `test-results/`
|
||||
2. **Videos**: First retry captures video (when retries enabled)
|
||||
3. **Traces**: View detailed traces with `npx playwright show-trace <trace.zip>`
|
||||
4. **HTML Report**: After running tests, view `npx playwright show-report`
|
||||
|
||||
#### Common Issues
|
||||
|
||||
- **401 Unauthorized**: Token missing or invalid - check `.env.local`
|
||||
- **Socket hang up**: Backend operation taking too long - some operations (like audio download) can take minutes
|
||||
- **Element outside viewport**: Dialog scrolling issues - tests use JavaScript click to handle this
|
||||
|
||||
## Project Structure
|
||||
|
||||
```
|
||||
frontend/
|
||||
├── app/ # Next.js app router pages
|
||||
├── components/ # React components
|
||||
│ ├── ui/ # shadcn/ui components
|
||||
│ └── audio-search/ # Audio search feature components
|
||||
├── lib/ # Utilities and API client
|
||||
│ └── api.ts # Backend API client
|
||||
├── e2e/ # Playwright E2E tests
|
||||
├── playwright.config.ts # Playwright configuration
|
||||
└── next.config.mjs # Next.js configuration
|
||||
```
|
||||
|
||||
## Scripts
|
||||
|
||||
| Script | Description |
|
||||
|--------|-------------|
|
||||
| `npm run dev` | Start development server |
|
||||
| `npm run build` | Build for production |
|
||||
| `npm run start` | Start production server |
|
||||
| `npm run lint` | Run ESLint |
|
||||
| `npm test` | Run unit tests (watch mode) |
|
||||
| `npm run test:ci` | Run unit tests (CI mode with coverage) |
|
||||
| `npm run test:e2e` | Run E2E tests |
|
||||
| `npm run test:e2e:ui` | Run E2E tests with interactive UI |
|
||||
@@ -0,0 +1,459 @@
|
||||
/**
|
||||
* Unit tests for job-status.ts utility functions
|
||||
*/
|
||||
|
||||
import { getJobStep, formatStepIndicator, isBlockingStatus, getJobProgressPercent, JobStep } from '../lib/job-status';
|
||||
import type { Job } from '../lib/api';
|
||||
|
||||
// Helper to create a minimal Job object for testing
|
||||
function createJob(status: string, stateData?: Record<string, any>): Job {
|
||||
return {
|
||||
job_id: 'test-job-123',
|
||||
status,
|
||||
progress: 0,
|
||||
created_at: new Date().toISOString(),
|
||||
updated_at: new Date().toISOString(),
|
||||
state_data: stateData,
|
||||
};
|
||||
}
|
||||
|
||||
describe('getJobStep', () => {
|
||||
describe('Step 1: Setup', () => {
|
||||
it('returns step 1 for pending status', () => {
|
||||
const job = createJob('pending');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(1);
|
||||
expect(result.total).toBe(10);
|
||||
expect(result.label).toBe('Setting up');
|
||||
expect(result.isBlocking).toBe(false);
|
||||
expect(result.color).toBe('text-slate-400');
|
||||
});
|
||||
});
|
||||
|
||||
describe('Step 2: Audio Search', () => {
|
||||
it('returns step 2 for searching_audio status', () => {
|
||||
const job = createJob('searching_audio');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(2);
|
||||
expect(result.label).toBe('Searching for audio');
|
||||
expect(result.isBlocking).toBe(false);
|
||||
});
|
||||
|
||||
it('returns step 2 with blocking for awaiting_audio_selection', () => {
|
||||
const job = createJob('awaiting_audio_selection');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(2);
|
||||
expect(result.label).toBe('Select audio source');
|
||||
expect(result.isBlocking).toBe(true);
|
||||
expect(result.color).toBe('text-amber-400');
|
||||
});
|
||||
});
|
||||
|
||||
describe('Step 3: Download', () => {
|
||||
it('returns step 3 for downloading_audio status', () => {
|
||||
const job = createJob('downloading_audio');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(3);
|
||||
expect(result.label).toBe('Downloading audio');
|
||||
});
|
||||
|
||||
it('returns step 3 for downloading status without worker progress', () => {
|
||||
const job = createJob('downloading');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(3);
|
||||
expect(result.label).toBe('Downloading');
|
||||
});
|
||||
|
||||
it('returns step 3 for downloading with empty state_data', () => {
|
||||
const job = createJob('downloading', {});
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(3);
|
||||
expect(result.label).toBe('Downloading');
|
||||
});
|
||||
});
|
||||
|
||||
describe('Step 3→4 Transition: Downloading with active workers', () => {
|
||||
// When backend status is "downloading" but workers are actively running,
|
||||
// the frontend should show step 4 (Processing) to avoid appearing stuck
|
||||
|
||||
it('returns step 4 when downloading with active audio worker', () => {
|
||||
const job = createJob('downloading', {
|
||||
audio_progress: { stage: 'separating_stage1', progress: 10 },
|
||||
});
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(4);
|
||||
expect(result.color).toBe('text-purple-400');
|
||||
});
|
||||
|
||||
it('returns step 4 when downloading with active lyrics worker', () => {
|
||||
const job = createJob('downloading', {
|
||||
lyrics_progress: { stage: 'transcribing', progress: 10 },
|
||||
});
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(4);
|
||||
expect(result.color).toBe('text-purple-400');
|
||||
});
|
||||
|
||||
it('returns step 4 with combined label when both workers active', () => {
|
||||
const job = createJob('downloading', {
|
||||
audio_progress: { stage: 'separating_stage1', progress: 10 },
|
||||
lyrics_progress: { stage: 'transcribing', progress: 10 },
|
||||
});
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(4);
|
||||
expect(result.label).toMatch(/Audio.*\+.*Transcribing|Transcribing.*\+.*Audio/);
|
||||
});
|
||||
|
||||
it('shows only active worker when one is complete', () => {
|
||||
const job = createJob('downloading', {
|
||||
audio_progress: { stage: 'audio_complete' },
|
||||
lyrics_progress: { stage: 'transcribing' },
|
||||
audio_complete: true,
|
||||
});
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(4);
|
||||
expect(result.label).toBe('Transcribing');
|
||||
});
|
||||
|
||||
it('shows processing complete when both workers done', () => {
|
||||
const job = createJob('downloading', {
|
||||
audio_progress: { stage: 'audio_complete' },
|
||||
lyrics_progress: { stage: 'lyrics_complete' },
|
||||
audio_complete: true,
|
||||
lyrics_complete: true,
|
||||
});
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(4);
|
||||
expect(result.label).toBe('Processing complete');
|
||||
});
|
||||
|
||||
it('returns step 3 when state_data has no stage info', () => {
|
||||
// state_data exists but no actual progress stage set
|
||||
const job = createJob('downloading', {
|
||||
audio_progress: {},
|
||||
lyrics_progress: {},
|
||||
});
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(3);
|
||||
expect(result.label).toBe('Downloading');
|
||||
});
|
||||
});
|
||||
|
||||
describe('Step 4: Parallel Processing', () => {
|
||||
it('returns step 4 for separating_stage1', () => {
|
||||
const job = createJob('separating_stage1');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(4);
|
||||
expect(result.label).toBe('Separating audio (1/2)');
|
||||
});
|
||||
|
||||
it('returns step 4 for separating_stage2', () => {
|
||||
const job = createJob('separating_stage2');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(4);
|
||||
expect(result.label).toBe('Separating audio (2/2)');
|
||||
});
|
||||
|
||||
it('returns step 4 for transcribing', () => {
|
||||
const job = createJob('transcribing');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(4);
|
||||
expect(result.label).toBe('Transcribing lyrics');
|
||||
});
|
||||
|
||||
it('returns step 4 for correcting', () => {
|
||||
const job = createJob('correcting');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(4);
|
||||
expect(result.label).toBe('Correcting lyrics');
|
||||
});
|
||||
|
||||
it('shows combined progress when both audio and lyrics are in progress', () => {
|
||||
const job = createJob('separating_stage1', {
|
||||
audio_progress: { stage: 'separating_stage1' },
|
||||
lyrics_progress: { stage: 'transcribing' },
|
||||
});
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(4);
|
||||
// Should show combined label
|
||||
expect(result.label).toMatch(/Audio|Transcribing/);
|
||||
});
|
||||
|
||||
it('shows combined status when audio done but lyrics in progress', () => {
|
||||
const job = createJob('lyrics_complete', {
|
||||
audio_progress: { stage: 'audio_complete' },
|
||||
lyrics_progress: { stage: 'transcribing' },
|
||||
audio_complete: true,
|
||||
});
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(4);
|
||||
});
|
||||
});
|
||||
|
||||
describe('Step 5: Screen Generation', () => {
|
||||
it('returns step 5 for generating_screens', () => {
|
||||
const job = createJob('generating_screens');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(5);
|
||||
expect(result.label).toBe('Generating screens');
|
||||
});
|
||||
|
||||
it('returns step 5 for applying_padding', () => {
|
||||
const job = createJob('applying_padding');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(5);
|
||||
expect(result.label).toBe('Syncing countdown');
|
||||
});
|
||||
});
|
||||
|
||||
describe('Step 6: Lyrics Review (BLOCKING)', () => {
|
||||
it('returns step 6 with blocking for awaiting_review', () => {
|
||||
const job = createJob('awaiting_review');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(6);
|
||||
expect(result.label).toBe('Review lyrics');
|
||||
expect(result.isBlocking).toBe(true);
|
||||
expect(result.color).toBe('text-amber-400');
|
||||
});
|
||||
|
||||
it('returns step 6 for in_review', () => {
|
||||
const job = createJob('in_review');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(6);
|
||||
expect(result.label).toBe('In review');
|
||||
expect(result.isBlocking).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe('Step 7: Video Rendering', () => {
|
||||
it('returns step 7 for review_complete', () => {
|
||||
const job = createJob('review_complete');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(7);
|
||||
expect(result.label).toBe('Starting render');
|
||||
});
|
||||
|
||||
it('returns step 7 for rendering_video', () => {
|
||||
const job = createJob('rendering_video');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(7);
|
||||
expect(result.label).toBe('Rendering video');
|
||||
});
|
||||
});
|
||||
|
||||
describe('Step 8: Instrumental Selection (BLOCKING)', () => {
|
||||
it('returns step 8 with blocking for awaiting_instrumental_selection', () => {
|
||||
const job = createJob('awaiting_instrumental_selection');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(8);
|
||||
expect(result.label).toBe('Select instrumental');
|
||||
expect(result.isBlocking).toBe(true);
|
||||
expect(result.color).toBe('text-amber-400');
|
||||
});
|
||||
});
|
||||
|
||||
describe('Step 9: Final Encoding', () => {
|
||||
it('returns step 9 for instrumental_selected', () => {
|
||||
const job = createJob('instrumental_selected');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(9);
|
||||
expect(result.label).toBe('Starting final encode');
|
||||
});
|
||||
|
||||
it('returns step 9 for generating_video', () => {
|
||||
const job = createJob('generating_video');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(9);
|
||||
expect(result.label).toBe('Generating final video');
|
||||
});
|
||||
|
||||
it('returns step 9 for encoding', () => {
|
||||
const job = createJob('encoding');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(9);
|
||||
expect(result.label).toBe('Encoding video');
|
||||
});
|
||||
|
||||
it('returns step 9 for packaging', () => {
|
||||
const job = createJob('packaging');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(9);
|
||||
expect(result.label).toBe('Packaging files');
|
||||
});
|
||||
});
|
||||
|
||||
describe('Step 10: Distribution / Complete', () => {
|
||||
it('returns step 10 for uploading', () => {
|
||||
const job = createJob('uploading');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(10);
|
||||
expect(result.label).toBe('Uploading');
|
||||
expect(result.color).toBe('text-green-400');
|
||||
});
|
||||
|
||||
it('returns step 10 for notifying', () => {
|
||||
const job = createJob('notifying');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(10);
|
||||
expect(result.label).toBe('Sending notifications');
|
||||
});
|
||||
|
||||
it('returns step 10 for complete', () => {
|
||||
const job = createJob('complete');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(10);
|
||||
expect(result.label).toBe('Complete');
|
||||
expect(result.color).toBe('text-green-400');
|
||||
});
|
||||
|
||||
it('returns step 10 for prep_complete', () => {
|
||||
const job = createJob('prep_complete');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(10);
|
||||
expect(result.label).toBe('Prep complete');
|
||||
});
|
||||
});
|
||||
|
||||
describe('Terminal states', () => {
|
||||
it('returns step 0 for failed status', () => {
|
||||
const job = createJob('failed');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(0);
|
||||
expect(result.label).toBe('Failed');
|
||||
expect(result.color).toBe('text-red-400');
|
||||
});
|
||||
|
||||
it('returns step 0 for cancelled status', () => {
|
||||
const job = createJob('cancelled');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(0);
|
||||
expect(result.label).toBe('Cancelled');
|
||||
expect(result.color).toBe('text-slate-500');
|
||||
});
|
||||
});
|
||||
|
||||
describe('Unknown status handling', () => {
|
||||
it('returns step 0 with humanized label for unknown status', () => {
|
||||
const job = createJob('some_unknown_status');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(0);
|
||||
expect(result.label).toBe('some unknown status');
|
||||
expect(result.isBlocking).toBe(false);
|
||||
expect(result.color).toBe('text-slate-400');
|
||||
});
|
||||
|
||||
it('handles null status gracefully', () => {
|
||||
const job = createJob(null as unknown as string);
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(1); // Falls back to 'pending'
|
||||
});
|
||||
|
||||
it('handles undefined status gracefully', () => {
|
||||
const job = createJob(undefined as unknown as string);
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(1); // Falls back to 'pending'
|
||||
});
|
||||
});
|
||||
|
||||
describe('Case insensitivity', () => {
|
||||
it('handles uppercase status', () => {
|
||||
const job = createJob('PENDING');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(1);
|
||||
});
|
||||
|
||||
it('handles mixed case status', () => {
|
||||
const job = createJob('Downloading');
|
||||
const result = getJobStep(job);
|
||||
expect(result.step).toBe(3);
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe('formatStepIndicator', () => {
|
||||
it('formats active step correctly', () => {
|
||||
expect(formatStepIndicator(4, 10, 'Processing')).toBe('[4/10] Processing');
|
||||
});
|
||||
|
||||
it('omits step number for terminal states (step 0)', () => {
|
||||
expect(formatStepIndicator(0, 10, 'Failed')).toBe('Failed');
|
||||
});
|
||||
|
||||
it('formats first step correctly', () => {
|
||||
expect(formatStepIndicator(1, 10, 'Setting up')).toBe('[1/10] Setting up');
|
||||
});
|
||||
|
||||
it('formats last step correctly', () => {
|
||||
expect(formatStepIndicator(10, 10, 'Complete')).toBe('[10/10] Complete');
|
||||
});
|
||||
});
|
||||
|
||||
describe('isBlockingStatus', () => {
|
||||
it('returns true for awaiting_review', () => {
|
||||
expect(isBlockingStatus('awaiting_review')).toBe(true);
|
||||
});
|
||||
|
||||
it('returns true for in_review', () => {
|
||||
expect(isBlockingStatus('in_review')).toBe(true);
|
||||
});
|
||||
|
||||
it('returns true for awaiting_audio_selection', () => {
|
||||
expect(isBlockingStatus('awaiting_audio_selection')).toBe(true);
|
||||
});
|
||||
|
||||
it('returns true for awaiting_instrumental_selection', () => {
|
||||
expect(isBlockingStatus('awaiting_instrumental_selection')).toBe(true);
|
||||
});
|
||||
|
||||
it('returns false for non-blocking statuses', () => {
|
||||
expect(isBlockingStatus('pending')).toBe(false);
|
||||
expect(isBlockingStatus('downloading')).toBe(false);
|
||||
expect(isBlockingStatus('complete')).toBe(false);
|
||||
expect(isBlockingStatus('failed')).toBe(false);
|
||||
});
|
||||
|
||||
it('returns false for unknown statuses', () => {
|
||||
expect(isBlockingStatus('unknown_status')).toBe(false);
|
||||
});
|
||||
|
||||
it('handles case insensitivity', () => {
|
||||
expect(isBlockingStatus('AWAITING_REVIEW')).toBe(true);
|
||||
});
|
||||
|
||||
it('handles null/undefined gracefully', () => {
|
||||
expect(isBlockingStatus(null as unknown as string)).toBe(false);
|
||||
expect(isBlockingStatus(undefined as unknown as string)).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe('getJobProgressPercent', () => {
|
||||
it('returns 0 for terminal states (step 0)', () => {
|
||||
const job = createJob('failed');
|
||||
expect(getJobProgressPercent(job)).toBe(0);
|
||||
});
|
||||
|
||||
it('returns 10% for step 1', () => {
|
||||
const job = createJob('pending');
|
||||
expect(getJobProgressPercent(job)).toBe(10);
|
||||
});
|
||||
|
||||
it('returns 40% for step 4', () => {
|
||||
const job = createJob('transcribing');
|
||||
expect(getJobProgressPercent(job)).toBe(40);
|
||||
});
|
||||
|
||||
it('returns 60% for step 6', () => {
|
||||
const job = createJob('awaiting_review');
|
||||
expect(getJobProgressPercent(job)).toBe(60);
|
||||
});
|
||||
|
||||
it('returns 100% for step 10', () => {
|
||||
const job = createJob('complete');
|
||||
expect(getJobProgressPercent(job)).toBe(100);
|
||||
});
|
||||
|
||||
it('returns 0 for unknown status', () => {
|
||||
const job = createJob('unknown_status_xyz');
|
||||
expect(getJobProgressPercent(job)).toBe(0);
|
||||
});
|
||||
});
|
||||
@@ -1,348 +0,0 @@
|
||||
"use client"
|
||||
|
||||
import { useState } from "react"
|
||||
import { useJobs } from "@/lib/jobs"
|
||||
import type { JobStatus } from "@/lib/types"
|
||||
import { AppHeader } from "@/components/app-header"
|
||||
import { ProtectedRoute } from "@/components/protected-route"
|
||||
import { Button } from "@/components/ui/button"
|
||||
import { Input } from "@/components/ui/input"
|
||||
import { Label } from "@/components/ui/label"
|
||||
import { Card, CardContent, CardDescription, CardHeader, CardTitle } from "@/components/ui/card"
|
||||
import { Tabs, TabsContent, TabsList, TabsTrigger } from "@/components/ui/tabs"
|
||||
import { StatusBadge } from "@/components/status-badge"
|
||||
import { Table, TableBody, TableCell, TableHead, TableHeader, TableRow } from "@/components/ui/table"
|
||||
import { BarChart3, FileVideo, Ticket, TrendingUp, Activity, ChevronRight } from "lucide-react"
|
||||
import Link from "next/link"
|
||||
|
||||
function AdminContent() {
|
||||
const { jobs } = useJobs()
|
||||
const [promoCode, setPromoCode] = useState("")
|
||||
const [promoCredits, setPromoCredits] = useState("5")
|
||||
const [generatedCode, setGeneratedCode] = useState("")
|
||||
|
||||
const totalJobs = jobs.length
|
||||
const completedJobs = jobs.filter((j) => j.status === "completed").length
|
||||
const processingJobs = jobs.filter((j) => j.status === "processing" || j.status === "queued").length
|
||||
const failedJobs = jobs.filter((j) => j.status === "failed").length
|
||||
|
||||
const handleGeneratePromo = () => {
|
||||
const code = `NOMAD${Math.random().toString(36).substr(2, 6).toUpperCase()}`
|
||||
setGeneratedCode(code)
|
||||
setPromoCode("")
|
||||
}
|
||||
|
||||
const statusCounts = {
|
||||
queued: jobs.filter((j) => j.status === "queued").length,
|
||||
processing: jobs.filter((j) => j.status === "processing").length,
|
||||
awaiting_review: jobs.filter((j) => j.status === "awaiting_review").length,
|
||||
awaiting_instrumental: jobs.filter((j) => j.status === "awaiting_instrumental").length,
|
||||
completed: completedJobs,
|
||||
failed: failedJobs,
|
||||
}
|
||||
|
||||
const recentJobs = [...jobs]
|
||||
.sort((a, b) => new Date(b.createdAt).getTime() - new Date(a.createdAt).getTime())
|
||||
.slice(0, 10)
|
||||
|
||||
return (
|
||||
<div className="min-h-screen bg-background">
|
||||
<AppHeader />
|
||||
|
||||
<main className="container mx-auto px-4 py-8">
|
||||
<div className="mb-8">
|
||||
<h1 className="text-4xl font-bold mb-2">Admin Dashboard</h1>
|
||||
<p className="text-muted-foreground">Manage users, jobs, and system analytics</p>
|
||||
</div>
|
||||
|
||||
{/* Stats Grid */}
|
||||
<div className="grid gap-4 md:grid-cols-2 lg:grid-cols-4 mb-8">
|
||||
<Card className="bg-gradient-to-br from-primary/10 to-transparent border-primary/20">
|
||||
<CardHeader className="flex flex-row items-center justify-between pb-2">
|
||||
<CardTitle className="text-sm font-medium text-muted-foreground">Total Jobs</CardTitle>
|
||||
<FileVideo className="w-4 h-4 text-primary" />
|
||||
</CardHeader>
|
||||
<CardContent>
|
||||
<div className="text-3xl font-bold text-primary">{totalJobs}</div>
|
||||
<p className="text-xs text-muted-foreground mt-1">All time</p>
|
||||
</CardContent>
|
||||
</Card>
|
||||
|
||||
<Card>
|
||||
<CardHeader className="flex flex-row items-center justify-between pb-2">
|
||||
<CardTitle className="text-sm font-medium text-muted-foreground">Completed</CardTitle>
|
||||
<TrendingUp className="w-4 h-4 text-green-400" />
|
||||
</CardHeader>
|
||||
<CardContent>
|
||||
<div className="text-3xl font-bold text-green-400">{completedJobs}</div>
|
||||
<p className="text-xs text-muted-foreground mt-1">
|
||||
{((completedJobs / totalJobs) * 100).toFixed(1)}% success rate
|
||||
</p>
|
||||
</CardContent>
|
||||
</Card>
|
||||
|
||||
<Card>
|
||||
<CardHeader className="flex flex-row items-center justify-between pb-2">
|
||||
<CardTitle className="text-sm font-medium text-muted-foreground">Processing</CardTitle>
|
||||
<Activity className="w-4 h-4 text-blue-400" />
|
||||
</CardHeader>
|
||||
<CardContent>
|
||||
<div className="text-3xl font-bold text-blue-400">{processingJobs}</div>
|
||||
<p className="text-xs text-muted-foreground mt-1">Active jobs</p>
|
||||
</CardContent>
|
||||
</Card>
|
||||
|
||||
<Card>
|
||||
<CardHeader className="flex flex-row items-center justify-between pb-2">
|
||||
<CardTitle className="text-sm font-medium text-muted-foreground">Failed</CardTitle>
|
||||
<BarChart3 className="w-4 h-4 text-destructive" />
|
||||
</CardHeader>
|
||||
<CardContent>
|
||||
<div className="text-3xl font-bold text-destructive">{failedJobs}</div>
|
||||
<p className="text-xs text-muted-foreground mt-1">
|
||||
{((failedJobs / totalJobs) * 100).toFixed(1)}% failure rate
|
||||
</p>
|
||||
</CardContent>
|
||||
</Card>
|
||||
</div>
|
||||
|
||||
{/* Tabs */}
|
||||
<Tabs defaultValue="overview" className="space-y-6">
|
||||
<TabsList className="grid w-full max-w-md grid-cols-3">
|
||||
<TabsTrigger value="overview">Overview</TabsTrigger>
|
||||
<TabsTrigger value="jobs">All Jobs</TabsTrigger>
|
||||
<TabsTrigger value="promo">Promo Codes</TabsTrigger>
|
||||
</TabsList>
|
||||
|
||||
<TabsContent value="overview" className="space-y-6">
|
||||
{/* Status Breakdown */}
|
||||
<Card>
|
||||
<CardHeader>
|
||||
<CardTitle>Job Status Breakdown</CardTitle>
|
||||
<CardDescription>Current distribution of job statuses</CardDescription>
|
||||
</CardHeader>
|
||||
<CardContent>
|
||||
<div className="grid gap-3 sm:grid-cols-2 lg:grid-cols-3">
|
||||
{Object.entries(statusCounts).map(([status, count]) => (
|
||||
<div
|
||||
key={status}
|
||||
className="flex items-center justify-between p-3 rounded-lg border border-border bg-card"
|
||||
>
|
||||
<div className="flex items-center gap-3">
|
||||
<StatusBadge status={status as JobStatus} size="sm" />
|
||||
<span className="text-sm text-muted-foreground">Jobs</span>
|
||||
</div>
|
||||
<span className="text-lg font-bold">{count}</span>
|
||||
</div>
|
||||
))}
|
||||
</div>
|
||||
</CardContent>
|
||||
</Card>
|
||||
|
||||
{/* Recent Activity */}
|
||||
<Card>
|
||||
<CardHeader className="flex flex-row items-center justify-between">
|
||||
<div>
|
||||
<CardTitle>Recent Activity</CardTitle>
|
||||
<CardDescription>Latest jobs across all users</CardDescription>
|
||||
</div>
|
||||
<Button variant="outline" size="sm" asChild>
|
||||
<Link href="#" onClick={(e) => e.preventDefault()}>
|
||||
View All
|
||||
</Link>
|
||||
</Button>
|
||||
</CardHeader>
|
||||
<CardContent>
|
||||
<div className="space-y-2">
|
||||
{recentJobs.slice(0, 5).map((job) => (
|
||||
<Link
|
||||
key={job.id}
|
||||
href={`/jobs/${job.id}`}
|
||||
className="flex items-center justify-between p-3 rounded-lg border border-border hover:border-primary/50 hover:bg-card/50 transition-all group"
|
||||
>
|
||||
<div className="flex-1 min-w-0">
|
||||
<p className="font-medium text-sm truncate group-hover:text-primary transition-colors">
|
||||
{job.artist} - {job.title}
|
||||
</p>
|
||||
<p className="text-xs text-muted-foreground">{new Date(job.createdAt).toLocaleString()}</p>
|
||||
</div>
|
||||
<div className="flex items-center gap-2">
|
||||
<StatusBadge status={job.status} size="sm" />
|
||||
<ChevronRight className="w-4 h-4 text-muted-foreground group-hover:text-primary transition-colors" />
|
||||
</div>
|
||||
</Link>
|
||||
))}
|
||||
</div>
|
||||
</CardContent>
|
||||
</Card>
|
||||
</TabsContent>
|
||||
|
||||
<TabsContent value="jobs" className="space-y-6">
|
||||
<Card>
|
||||
<CardHeader>
|
||||
<CardTitle>All Jobs</CardTitle>
|
||||
<CardDescription>Complete list of all karaoke video jobs in the system</CardDescription>
|
||||
</CardHeader>
|
||||
<CardContent>
|
||||
<div className="rounded-md border border-border overflow-auto">
|
||||
<Table>
|
||||
<TableHeader>
|
||||
<TableRow>
|
||||
<TableHead>Artist - Title</TableHead>
|
||||
<TableHead>User ID</TableHead>
|
||||
<TableHead>Status</TableHead>
|
||||
<TableHead>Created</TableHead>
|
||||
<TableHead>Progress</TableHead>
|
||||
<TableHead></TableHead>
|
||||
</TableRow>
|
||||
</TableHeader>
|
||||
<TableBody>
|
||||
{recentJobs.map((job) => (
|
||||
<TableRow key={job.id} className="hover:bg-muted/50">
|
||||
<TableCell className="font-medium">
|
||||
{job.artist} - {job.title}
|
||||
</TableCell>
|
||||
<TableCell className="text-muted-foreground text-sm">{job.userId}</TableCell>
|
||||
<TableCell>
|
||||
<StatusBadge status={job.status} size="sm" />
|
||||
</TableCell>
|
||||
<TableCell className="text-sm text-muted-foreground">
|
||||
{new Date(job.createdAt).toLocaleDateString()}
|
||||
</TableCell>
|
||||
<TableCell className="text-sm">{job.progress}%</TableCell>
|
||||
<TableCell>
|
||||
<Button variant="ghost" size="sm" asChild>
|
||||
<Link href={`/jobs/${job.id}`}>
|
||||
<ChevronRight className="w-4 h-4" />
|
||||
</Link>
|
||||
</Button>
|
||||
</TableCell>
|
||||
</TableRow>
|
||||
))}
|
||||
</TableBody>
|
||||
</Table>
|
||||
</div>
|
||||
</CardContent>
|
||||
</Card>
|
||||
</TabsContent>
|
||||
|
||||
<TabsContent value="promo" className="space-y-6">
|
||||
<div className="grid gap-6 lg:grid-cols-2">
|
||||
{/* Generate Promo Code */}
|
||||
<Card>
|
||||
<CardHeader>
|
||||
<CardTitle className="flex items-center gap-2">
|
||||
<Ticket className="w-5 h-5 text-primary" />
|
||||
Generate Promo Code
|
||||
</CardTitle>
|
||||
<CardDescription>Create promotional codes for users to redeem credits</CardDescription>
|
||||
</CardHeader>
|
||||
<CardContent className="space-y-4">
|
||||
<div className="space-y-2">
|
||||
<Label htmlFor="promo-credits">Credit Amount</Label>
|
||||
<Input
|
||||
id="promo-credits"
|
||||
type="number"
|
||||
min="1"
|
||||
max="100"
|
||||
value={promoCredits}
|
||||
onChange={(e) => setPromoCredits(e.target.value)}
|
||||
/>
|
||||
<p className="text-xs text-muted-foreground">Number of credits this code will provide</p>
|
||||
</div>
|
||||
|
||||
<Button onClick={handleGeneratePromo} className="w-full bg-primary hover:bg-primary/90">
|
||||
Generate Code
|
||||
</Button>
|
||||
|
||||
{generatedCode && (
|
||||
<div className="p-4 rounded-lg bg-primary/10 border border-primary/20">
|
||||
<p className="text-sm text-muted-foreground mb-2">Generated Promo Code:</p>
|
||||
<p className="text-2xl font-mono font-bold text-primary">{generatedCode}</p>
|
||||
<p className="text-xs text-muted-foreground mt-2">Worth {promoCredits} credits</p>
|
||||
</div>
|
||||
)}
|
||||
</CardContent>
|
||||
</Card>
|
||||
|
||||
{/* Active Promo Codes */}
|
||||
<Card>
|
||||
<CardHeader>
|
||||
<CardTitle>Active Promo Codes</CardTitle>
|
||||
<CardDescription>Currently available promotional codes</CardDescription>
|
||||
</CardHeader>
|
||||
<CardContent>
|
||||
<div className="space-y-3">
|
||||
<div className="flex items-center justify-between p-3 rounded-lg border border-border bg-card">
|
||||
<div>
|
||||
<p className="font-mono font-medium">NOMADWELCOME</p>
|
||||
<p className="text-xs text-muted-foreground">5 credits • Used 23 times</p>
|
||||
</div>
|
||||
<Button variant="ghost" size="sm" className="text-destructive">
|
||||
Disable
|
||||
</Button>
|
||||
</div>
|
||||
|
||||
<div className="flex items-center justify-between p-3 rounded-lg border border-border bg-card">
|
||||
<div>
|
||||
<p className="font-mono font-medium">LAUNCH2024</p>
|
||||
<p className="text-xs text-muted-foreground">10 credits • Used 8 times</p>
|
||||
</div>
|
||||
<Button variant="ghost" size="sm" className="text-destructive">
|
||||
Disable
|
||||
</Button>
|
||||
</div>
|
||||
|
||||
{generatedCode && (
|
||||
<div className="flex items-center justify-between p-3 rounded-lg border border-primary/20 bg-primary/5">
|
||||
<div>
|
||||
<p className="font-mono font-medium text-primary">{generatedCode}</p>
|
||||
<p className="text-xs text-muted-foreground">{promoCredits} credits • Not used yet</p>
|
||||
</div>
|
||||
<Button variant="ghost" size="sm" className="text-destructive">
|
||||
Disable
|
||||
</Button>
|
||||
</div>
|
||||
)}
|
||||
</div>
|
||||
</CardContent>
|
||||
</Card>
|
||||
</div>
|
||||
|
||||
{/* Usage Statistics */}
|
||||
<Card>
|
||||
<CardHeader>
|
||||
<CardTitle>Promo Code Statistics</CardTitle>
|
||||
<CardDescription>Usage analytics and performance metrics</CardDescription>
|
||||
</CardHeader>
|
||||
<CardContent>
|
||||
<div className="grid gap-4 sm:grid-cols-3">
|
||||
<div className="space-y-2">
|
||||
<p className="text-sm text-muted-foreground">Total Codes</p>
|
||||
<p className="text-3xl font-bold">12</p>
|
||||
</div>
|
||||
<div className="space-y-2">
|
||||
<p className="text-sm text-muted-foreground">Total Redemptions</p>
|
||||
<p className="text-3xl font-bold">156</p>
|
||||
</div>
|
||||
<div className="space-y-2">
|
||||
<p className="text-sm text-muted-foreground">Credits Distributed</p>
|
||||
<p className="text-3xl font-bold text-primary">892</p>
|
||||
</div>
|
||||
</div>
|
||||
</CardContent>
|
||||
</Card>
|
||||
</TabsContent>
|
||||
</Tabs>
|
||||
</main>
|
||||
</div>
|
||||
)
|
||||
}
|
||||
|
||||
export default function AdminPage() {
|
||||
return (
|
||||
<ProtectedRoute requireAdmin>
|
||||
<AdminContent />
|
||||
</ProtectedRoute>
|
||||
)
|
||||
}
|
||||
Loaded 100 of 302 files, more files were not shown because too many files have changed in this diff.
Show more
Reference in new issue
Block a user