- Remove ';' from command-injection pattern — semicolons are common in French
and other European languages, not a shell injection risk in JSON context
- Skip security pattern scanning for free-text fields (captions_vtt,
audio_description_vtt, notes, etc.) — natural language always generates
false positives against injection regexes
- Add GET/HEAD to GCS CORS config so browsers can load signed VTT URLs
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- New services/cost_tracker.py: sync httpx preflight()/record() + async wrappers;
BudgetExceeded exception; no-op when COST_TRACKER_BASE_URL is empty
- Preflight budget check added before ingestion (Gemini), per-language translation
(video-native + traditional), and per-language TTS dispatch
- _record_gemini_usage and _record_tts_cost now call cost_tracker directly;
removes broken asyncio.get_event_loop() hack from sync Celery worker
- Fix: _cost_ctx now threaded into extract_accessibility_targeted (video-native path)
- Fix: user_id/cost_project_id now propagated through dispatch_language_tts →
synthesize_cue_task.s() and the rerender_accessible_video.py re-render path
- Remove oliver-cost-tracker SDK dependency (was commented-out/never installed)
- Drop cost_tracker_outbox_path setting and get_cost_tracker() factory
- Update COST_TRACKER_BASE_URL default to optical-dev.oliver.solutions in
.env.prod.example, docker-compose.yml, and all Cloud Run service yamls
- Cloud Run yamls use Secret Manager ref (cost-tracker-api-key) for the API key
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- FFmpeg: Enable CPU throttling to reduce idle costs
- Whisper: Keep CPU throttling disabled (model loading needs full CPU)
- Remove readinessProbe (requires BETA launch stage)
- Both services scale to zero when idle for cost savings
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Changed cpu-throttling from "false" to "true" for both services.
This reduces costs when instances are idle between requests:
- Idle CPU billed at ~10% of active rate instead of 100%
- Instances still scale to zero after ~15 min of no traffic
Trade-off: Slightly slower response when resuming from throttled state,
but startup-cpu-boost is still enabled to mitigate cold starts.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Migrate CPU-intensive workloads to Cloud Run for autoscaling:
- Add Whisper HTTP service (FastAPI) with /transcribe endpoint
- Add FFmpeg HTTP service (FastAPI) with /encode, /probe, /extract-frame, etc.
- Add Dockerfiles for both services (8 vCPU, 32GB RAM, Gen2)
- Add Cloud Build config for CI/CD deployment
- Add Cloud Run service YAML configs with scale-to-zero
- Update whisper_transcribe.py to call Cloud Run when WHISPER_SERVICE_URL set
- Update video_renderer.py to call Cloud Run when FFMPEG_SERVICE_URL set
- Update whisper_service.py for Cloud Run compatibility (no settings dependency)
- Add ffmpeg_service_url and whisper_service_url to config.py
Services scale 0→N based on request load, falling back to local
execution when service URLs are not configured (hybrid mode).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Break out TTS synthesis into a dedicated Celery worker (tts queue) with
concurrency=8 for parallel processing. Each AD cue is now synthesized as
a separate task, enabling up to 8 cues to be processed simultaneously.
Key changes:
- Add tts_synthesis.py with synthesize_cue_task for per-cue synthesis
- Refactor translate_and_synthesize.py to dispatch cue tasks in parallel
- Add tts-worker service to docker-compose.yml (concurrency=8)
- Add Cloud Run service config for production deployment
Benefits:
- Parallel synthesis even for single jobs (e.g., 50 cues → 8 concurrent)
- Natural rate limiting across multiple concurrent jobs
- Fault tolerance with per-cue retries and GCS persistence
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Medium model is faster and uses less memory (~1.5GB vs ~3GB)
while still providing good multilingual transcription quality.
Updated in:
- config.py
- docker-compose.yml
- whisper-worker-service.yaml
- cloudbuild.yaml
- Dockerfile (pre-download)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Environment variables were overriding config.py with 'base' model.
Updated defaults in:
- docker-compose.yml
- whisper-worker-service.yaml
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements word-level speech analysis using faster-whisper to refine
AD pause points. Gemini's timestamps are snapped to natural speech gaps
(sentence/phrase boundaries) to prevent pauses mid-word.
Key changes:
- Add WhisperService for transcription and gap detection
- Add dedicated Celery task routed to 'whisper' queue
- Integrate refinement into render_accessible_video task
- Cache Whisper transcripts in MongoDB for reuse across languages
- Add dedicated whisper-worker with concurrency=1 to prevent OOM
Configuration:
- Uses faster-whisper 'base' model (multilingual, ~145MB)
- 5-second search window after Gemini's recommended point
- Falls back to original timestamp if no gap found
Infrastructure:
- New Docker stage: whisper-worker
- New Cloud Run service: accessible-video-whisper-worker
- Updated docker-compose.yml with whisper-worker service
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
