Files
karaoke-gen/backend/config.py
T
Andrew Beveridge ☄️andClaude ae85ec0a09 feat: Move worker logs to Firestore subcollection to avoid 1MB limit (#195)
## Summary

Move `worker_logs` from embedded array in job documents to a Firestore
subcollection (`jobs/{job_id}/logs`) to avoid the 1MB document size
limit. This fixes job failures when logs exceed the limit during
long-running operations like video encoding.

**Problem:** Job `501258e1` failed when logs reached 1.26MB (2,547 log
entries), representing 98.6% of the maximum document size.

## Changes

### New Files
- `backend/models/worker_log.py` - WorkerLogEntry dataclass with factory
methods, serialization (to_dict, to_legacy_dict, from_dict)
- `backend/tests/test_worker_log_subcollection.py` - 24 unit tests
- `backend/tests/emulator/test_worker_logs_subcollection.py` - 11
integration tests using Firestore emulator

### Modified Files
- `backend/services/firestore_service.py` - Added subcollection methods
(append, get, count, delete)
- `backend/services/job_manager.py` - Use subcollection with fallback to
legacy embedded arrays
- `backend/api/routes/jobs.py` - Updated logs endpoint to use new
methods
- `backend/config.py` - Added `USE_LOG_SUBCOLLECTION` feature flag
(default: true)
- `infrastructure/__main__.py` - Added TTL policy (30 days) and
composite index for logs subcollection
- `pyproject.toml` - Version bump 0.89.6 → 0.90.0

### Documentation
- `docs/README.md` - Added to Recent Changes
- `docs/ARCHITECTURE.md` - Added logs subcollection to Firestore
Collections table
- `docs/LESSONS-LEARNED.md` - Added "Firestore Document 1MB Limit with
Embedded Arrays" section

## Testing

- [x] 24 unit tests pass
(`backend/tests/test_worker_log_subcollection.py`)
- [x] 11 emulator integration tests pass
(`backend/tests/emulator/test_worker_logs_subcollection.py`)
- [x] All 68 existing emulator tests pass

## Review

- [x] CodeRabbit CLI review completed locally
- [x] Review feedback addressed (timestamp formatting fix)

## Rollback Plan

Set `USE_LOG_SUBCOLLECTION=false` environment variable and redeploy. New
logs will go back to embedded array; subcollection logs will remain but
won't be read.

@coderabbitai ignore

---
🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude <noreply@anthropic.com>
2026-01-04 20:14:25 -05:00

167 lines
7.5 KiB
Python

"""
Configuration management for the karaoke generation backend.
"""
import os
import logging
from typing import Optional, Dict
from pydantic_settings import BaseSettings
from google.cloud import secretmanager
logger = logging.getLogger(__name__)
class Settings(BaseSettings):
"""Application settings."""
# Google Cloud
google_cloud_project: str = os.getenv("GOOGLE_CLOUD_PROJECT", "")
gcs_bucket_name: str = os.getenv("GCS_BUCKET_NAME", "karaoke-gen-storage")
gcs_temp_bucket: str = os.getenv("GCS_TEMP_BUCKET", "karaoke-gen-temp")
gcs_output_bucket: str = os.getenv("GCS_OUTPUT_BUCKET", "karaoke-gen-outputs")
firestore_collection: str = os.getenv("FIRESTORE_COLLECTION", "jobs")
# Audio Separator API (for GPU processing)
audio_separator_api_url: Optional[str] = os.getenv("AUDIO_SEPARATOR_API_URL")
# External APIs (can be set via env or Secret Manager)
audioshake_api_key: Optional[str] = os.getenv("AUDIOSHAKE_API_KEY")
genius_api_key: Optional[str] = os.getenv("GENIUS_API_KEY")
spotify_cookie: Optional[str] = os.getenv("SPOTIFY_COOKIE_SP_DC")
rapidapi_key: Optional[str] = os.getenv("RAPIDAPI_KEY")
# Authentication
admin_tokens: Optional[str] = os.getenv("ADMIN_TOKENS") # Comma-separated list
# Application
environment: str = os.getenv("ENVIRONMENT", "development")
log_level: str = os.getenv("LOG_LEVEL", "INFO")
# Processing
max_concurrent_jobs: int = int(os.getenv("MAX_CONCURRENT_JOBS", "5"))
job_timeout_seconds: int = int(os.getenv("JOB_TIMEOUT_SECONDS", "3600"))
# Agentic AI Correction (for lyrics correction via LLM)
# When enabled, uses Gemini via Vertex AI for intelligent lyrics correction
use_agentic_ai: bool = os.getenv("USE_AGENTIC_AI", "true").lower() in ("true", "1", "yes")
agentic_ai_model: str = os.getenv("AGENTIC_AI_MODEL", "vertexai/gemini-3-flash-preview")
# Timeout for agentic correction in seconds. If correction takes longer, abort and
# use uncorrected transcription - human review will fix any issues.
agentic_correction_timeout_seconds: int = int(os.getenv("AGENTIC_CORRECTION_TIMEOUT_SECONDS", "180"))
# 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")
# GCE Encoding Worker (for high-performance video encoding)
# When enabled, video encoding is offloaded to a dedicated C4 GCE instance
# with faster CPU (Intel Granite Rapids 3.9 GHz) instead of Cloud Run.
# This provides 2-3x faster encoding times for CPU-bound FFmpeg libx264 encoding.
use_gce_encoding: bool = os.getenv("USE_GCE_ENCODING", "false").lower() in ("true", "1", "yes")
encoding_worker_url: Optional[str] = os.getenv("ENCODING_WORKER_URL") # e.g., http://136.119.50.148:8080
encoding_worker_api_key: Optional[str] = os.getenv("ENCODING_WORKER_API_KEY")
# Storage paths
temp_dir: str = os.getenv("TEMP_DIR", "/tmp/karaoke-gen")
# Worker logs storage mode
# When enabled, worker logs are stored in a Firestore subcollection (jobs/{job_id}/logs)
# instead of an embedded array. This avoids the 1MB document size limit.
# Default is true for new deployments.
use_log_subcollection: bool = os.getenv("USE_LOG_SUBCOLLECTION", "true").lower() in ("true", "1", "yes")
# 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")
# Strip whitespace/newlines from webhook URL - common issue when env vars are set with trailing newlines
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] = {}
class Config:
env_file = ".env"
case_sensitive = False
def get_secret(self, secret_id: str) -> Optional[str]:
"""
Get a secret from Google Secret Manager.
Caches secrets in memory to avoid repeated API calls.
Falls back to environment variables if Secret Manager unavailable.
Args:
secret_id: Secret name (e.g., "audioshake-api-key")
Returns:
Secret value or None if not found
"""
# Check cache first
if secret_id in self._secret_cache:
return self._secret_cache[secret_id]
# Check environment variable (development mode)
env_var = secret_id.upper().replace('-', '_')
env_value = os.getenv(env_var)
if env_value:
logger.debug(f"Using {secret_id} from environment variable")
self._secret_cache[secret_id] = env_value
return env_value
# Try Secret Manager (production mode)
if not self.google_cloud_project:
logger.warning(f"Cannot fetch secret {secret_id}: No GCP project configured")
return None
try:
client = secretmanager.SecretManagerServiceClient()
name = f"projects/{self.google_cloud_project}/secrets/{secret_id}/versions/latest"
response = client.access_secret_version(request={"name": name})
# Strip whitespace/newlines - common issue when secrets are created with trailing newlines
secret_value = response.payload.data.decode('UTF-8').strip()
# Cache it
self._secret_cache[secret_id] = secret_value
logger.info(f"Loaded secret {secret_id} from Secret Manager")
return secret_value
except Exception as e:
logger.error(f"Failed to load secret {secret_id} from Secret Manager: {e}")
return None
# Global settings instance
settings = Settings()
def get_settings() -> Settings:
"""Get the global settings instance."""
return settings