mirror of
https://github.com/nomadkaraoke/karaoke-gen.git
synced 2026-11-20 13:07:57 +09:00
## Problem The daily E2E Stage 2 failed on 2026-10-17 (run #216) and 2026-10-18 (#217). When a customer finishes review **before** stem separation does, `video-encoding-job` fails its prerequisites (`Missing instrumental: instrumental_clean`) 3× within seconds. The job then sits at `instrumental_selected` ("Starting final encode") forever: it's never marked failed, nothing alerts, and separation finishing doesn't re-trigger the encode. The race became common when the GPU image's unpinned `pip install "audio-separator[gpu]"` picked up **0.47.0** on the 10-17 rebuild. On L4, the mel-band RoFormer **karaoke** models run 3–5× slower than on 0.44.2, so total separation went from ~5 to ~10–16 min: | model (~3-min track) | 0.44.2 | 0.47.0 | |---|---|---| | karaoke_aufr33_viperx | ~25s | 75s | | karaoke_gabox_v2 | ~26s | 149s | | karaoke_becruily | ~27s | 157s | | instrumental fv7z / resurrection | ~50–60s | ~62s | The model YAMLs still say `num_overlap: 8, batch_size: 1`, so this isn't the #299 YAML-defaults change; the cause is somewhere in 0.45–0.47's RoFormer inference changes. That root cause is tracked separately. ## Fix - **Pin** `audio-separator[gpu]==0.44.2` in `backend/Dockerfile.gpu-base` (`ARG AUDIO_SEPARATOR_VERSION`). Changing this file triggers the GPU base image rebuild in CI. - **Video worker parks instead of failing.** When the selected stem is missing *and* separation is still running (`audio_complete` false, valid status), it sets `state_data.video_waiting_for_stems`, puts a user-visible message ("Waiting for audio separation to finish; the final video starts automatically") and exits 0, so Cloud Run doesn't retry. It re-checks after parking, and an atomic Firestore test-and-clear (`claim_job_state_flag`) means exactly one of the video worker and the audio worker proceeds if the stems land mid-park. - **Audio worker resumes it.** After `mark_audio_complete`, `resume_video_if_waiting_for_stems` re-triggers a parked encode. The fake-workers pipeline does the same, so the local stack matches prod. - **Backstop in `recover_stuck_jobs`.** `instrumental_selected` for more than 10 min with the stem present → re-trigger the video worker (covers a lost resume or lost dispatch). More than 60 min with separation never finishing → `mark_job_failed` (`stage=video_waiting_for_stems`), so the job fails loudly. Jobs older than 24h are never revived. (No jobs are in `instrumental_selected` in prod right now.) ## Testing - New `backend/tests/test_video_waits_for_stems.py` (16 tests): pending detection (including that a wrong status never parks), park / continue / claim-race outcomes, and resume (flag claimed / no flag / job moved on). - `test_recover_stuck_jobs_repark.py`: 5 new sweep tests (re-trigger, fresh, still separating, never-ready → fail, >24h ignored). - Full `backend/tests` (excluding emulator): 6455 passed. - Local CodeRabbit review: 0 findings. ## Verify after deploy - The GPU job logs `Separator version 0.44.2`, and karaoke-model separation is back to ~20–30s. - The next daily E2E Stage 2 passes. @coderabbitai ignore 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_019pmG2XAgtUguEJWLFpkKHN Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
205 lines
6.9 KiB
TOML
205 lines
6.9 KiB
TOML
[tool.poetry]
|
|
name = "karaoke-gen"
|
|
version = "0.278.11"
|
|
description = "Generate karaoke videos with synchronized lyrics. Handles the entire process from downloading audio and lyrics to creating the final video with title screens."
|
|
authors = ["Andrew Beveridge <andrew@beveridge.uk>"]
|
|
license = "MIT"
|
|
readme = "README.md"
|
|
packages = [
|
|
{ include = "karaoke_gen" },
|
|
{ include = "backend" }
|
|
]
|
|
include = [
|
|
# The Next.js static export is generated at build time and gitignored (see #876).
|
|
# Poetry's plain-string include respects .gitignore and would DROP a gitignored
|
|
# path from the wheel; the dict form with an explicit `format` overrides .gitignore
|
|
# so the built frontend is still bundled (needed for the CLI local-review UI).
|
|
# Wheel-only: the sdist would balloon past PyPI's 10 GB cap, so bundle in the wheel only.
|
|
{ path = "karaoke_gen/nextjs_frontend/out/**/*", format = ["wheel"] },
|
|
"karaoke_gen/lyrics_transcriber/output/fonts/*",
|
|
"karaoke_gen/lyrics_transcriber/output/cdgmaker/images/*",
|
|
"karaoke_gen/lyrics_transcriber/output/cdgmaker/transitions/*",
|
|
# Skip/include lists for the YouTube description backfill worker (must ship in
|
|
# the Cloud Run image so the scheduled worker can read them).
|
|
"backend/data/youtube_backfill/*.txt"
|
|
]
|
|
homepage = "https://github.com/nomadkaraoke/karaoke-gen"
|
|
repository = "https://github.com/nomadkaraoke/karaoke-gen"
|
|
documentation = "https://github.com/nomadkaraoke/karaoke-gen/blob/main/README.md"
|
|
|
|
[tool.poetry.dependencies]
|
|
python = ">=3.10,<3.14"
|
|
torch = ">=2.7"
|
|
requests = ">=2"
|
|
beautifulsoup4 = ">=4"
|
|
flacfetch = ">=0.9.0"
|
|
lyricsgenius = ">=3"
|
|
fetch-lyrics-from-genius = ">=0.1"
|
|
pillow = ">=10.1"
|
|
pyinstaller = ">=6.3"
|
|
google-api-python-client = "2.193.0"
|
|
google-auth = "2.49.1"
|
|
google-auth-oauthlib = "1.3.0"
|
|
google-auth-httplib2 = "0.3.0"
|
|
thefuzz = ">=0.22"
|
|
numpy = ">=2"
|
|
audio-separator = { version = ">=0.43.0", extras = ["cpu"] }
|
|
lyrics-converter = ">=0.2.1"
|
|
# lyrics_transcriber is now a subpackage of karaoke_gen (karaoke_gen/lyrics_transcriber/)
|
|
# Dependencies from vendored lyrics_transcriber:
|
|
mutagen = ">=1.47" # For LRCLIB provider to get track duration for better matching
|
|
python-slugify = ">=8"
|
|
syrics = ">=0"
|
|
karaoke-lyrics-processor = ">=0.6"
|
|
dropbox = ">=12"
|
|
spacy = ">=3.8.7"
|
|
srsly = ">=2.5.1"
|
|
tqdm = ">=4.67"
|
|
python-levenshtein = ">=0.26"
|
|
transformers = ">=4.47"
|
|
metaphone = ">=0.6"
|
|
nltk = ">=3.9"
|
|
spacy-syllables = ">=3"
|
|
syllables = ">=1"
|
|
fonttools = ">=4.55"
|
|
ollama = ">=0.4.7"
|
|
shortuuid = ">=1.0.13"
|
|
nest-asyncio = ">=1.5"
|
|
openai = ">=1.63.2"
|
|
langgraph = ">=0.2.0"
|
|
langchain = ">=0.3.0"
|
|
langchain-core = ">=0.3.0"
|
|
langchain-openai = ">=0.2.0"
|
|
langchain-anthropic = ">=0.2.0"
|
|
anthropic = ">=0.109.0" # direct dep: auto-correct structured outputs (output_config)
|
|
langchain-ollama = ">=0.2.0"
|
|
langchain-google-genai = ">=2.0.0"
|
|
langfuse = ">=3.0.0"
|
|
jiwer = ">=3.0.0"
|
|
kbputils = "^0.0.16"
|
|
attrs = ">=24.2.0"
|
|
cattrs = ">=24.1.2"
|
|
toml = ">=0.10"
|
|
argparse = ">=1.4.0"
|
|
psutil = "^7.0.0"
|
|
pyperclip = "*"
|
|
pytest-asyncio = "*"
|
|
ffmpeg-python = "^0.2.0"
|
|
python-multipart = "^0.0.20"
|
|
python-docx = ">=1.1.0"
|
|
yt-dlp = ">=2024.0.0"
|
|
matplotlib = ">=3"
|
|
# Backend API dependencies
|
|
fastapi = ">=0.104.0"
|
|
uvicorn = { version = ">=0.24.0", extras = ["standard"] }
|
|
pydantic = ">=2.5.0"
|
|
pydantic-settings = ">=2.1.0"
|
|
httpx = ">=0.25.0"
|
|
tenacity = "^8.2.0" # Retry logic for external service calls
|
|
google-cloud-firestore = "2.26.0"
|
|
google-cloud-compute = "^1.0.0"
|
|
google-cloud-storage = "3.10.1"
|
|
google-cloud-secret-manager = "2.26.0"
|
|
google-cloud-monitoring = "2.29.1" # Cloud Monitoring for YouTube API quota metrics
|
|
google-cloud-tasks = "2.21.0" # Cloud Tasks for worker coordination (Phase 1 scalability)
|
|
google-cloud-run = "0.15.0" # Cloud Run Jobs for long-running video encoding (Phase 2 scalability)
|
|
google-cloud-logging = ">=3.9.0" # Cloud Logging for error monitoring
|
|
python-dotenv = ">=1.0.0"
|
|
pydub = ">=0.25.1"
|
|
# Google / Apple ID-token verification (JWKS) for mobile sign-in
|
|
pyjwt = { version = ">=2.8.0", extras = ["crypto"] }
|
|
# Payment and email services
|
|
stripe = "^14.1.0"
|
|
email-validator = ">=2.0.0" # For Pydantic EmailStr validation
|
|
# Web Push notifications
|
|
pywebpush = ">=2.0.0"
|
|
# OpenTelemetry for distributed tracing
|
|
opentelemetry-api = ">=1.20.0"
|
|
opentelemetry-sdk = ">=1.20.0"
|
|
opentelemetry-instrumentation-fastapi = ">=0.41b0"
|
|
opentelemetry-instrumentation-httpx = ">=0.41b0"
|
|
opentelemetry-instrumentation-logging = ">=0.41b0"
|
|
opentelemetry-exporter-gcp-trace = ">=1.6.0"
|
|
opentelemetry-resourcedetector-gcp = ">=1.6.0a0"
|
|
# Optional: Local Whisper transcription (install with: pip install karaoke-gen[local-whisper])
|
|
whisper-timestamped = { version = ">=1.15.0", optional = true }
|
|
aiohttp = "^3.13.2"
|
|
|
|
[tool.poetry.group.dev.dependencies]
|
|
black = ">=23"
|
|
poetry = "*"
|
|
pytest = ">=7.0"
|
|
pytest-cov = ">=4.0"
|
|
pytest-mock = ">=3.10"
|
|
pytest-asyncio = "*"
|
|
|
|
# Make dev dependencies available as optional extras for pip install
|
|
# These need to be declared as optional dependencies first
|
|
[tool.poetry.dependencies.black]
|
|
version = ">=23"
|
|
optional = true
|
|
|
|
[tool.poetry.dependencies.pytest]
|
|
version = ">=7.0"
|
|
optional = true
|
|
|
|
[tool.poetry.dependencies.pytest-cov]
|
|
version = ">=4.0"
|
|
optional = true
|
|
|
|
[tool.poetry.dependencies.pytest-mock]
|
|
version = ">=3.10"
|
|
optional = true
|
|
|
|
[tool.poetry.extras]
|
|
# Local Whisper transcription support - optional, heavy dependencies
|
|
# Install with: pip install karaoke-gen[local-whisper]
|
|
# For CPU-only installation (recommended for systems without GPU):
|
|
# pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu
|
|
# pip install karaoke-gen[local-whisper]
|
|
local-whisper = ["whisper-timestamped"]
|
|
|
|
# Development/testing dependencies (pytest-asyncio is already a main dependency)
|
|
# Install with: pip install -e ".[dev]" or pip install -e ".[local-whisper,dev]"
|
|
dev = ["black", "pytest", "pytest-cov", "pytest-mock"]
|
|
|
|
[tool.poetry.scripts]
|
|
karaoke-gen = 'karaoke_gen.utils.gen_cli:main'
|
|
karaoke-gen-remote = 'karaoke_gen.utils.remote_cli:main'
|
|
karaoke-bulk = 'karaoke_gen.utils.bulk_cli:main'
|
|
|
|
[tool.black]
|
|
line-length = 140
|
|
|
|
[build-system]
|
|
requires = ["poetry-core"]
|
|
build-backend = "poetry.core.masonry.api"
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests/unit", "tests/integration", "backend/tests"]
|
|
python_files = ["test_*.py"]
|
|
addopts = [
|
|
"--asyncio-mode=auto",
|
|
"-v",
|
|
"--tb=short",
|
|
]
|
|
markers = [
|
|
"slow: marks tests as slow (deselect with '-m \"not slow\"')",
|
|
"integration: marks tests as integration tests",
|
|
"asyncio: mark test as async",
|
|
"emulator: marks tests requiring GCP emulators",
|
|
]
|
|
filterwarnings = [
|
|
"ignore::DeprecationWarning",
|
|
"ignore:'audioop' is deprecated:DeprecationWarning",
|
|
"ignore::RuntimeWarning",
|
|
"ignore::UserWarning",
|
|
]
|
|
|
|
[tool.coverage.run]
|
|
# Exclude lyrics_transcriber subpackage from coverage since it was a separate vendored package
|
|
# with its own test suite - including it in karaoke_gen coverage would unfairly lower the percentage
|
|
omit = [
|
|
"karaoke_gen/lyrics_transcriber/*",
|
|
]
|