video-accessibility/backend/app/services
michael c512bdc184 feat: use AD VTT pause points instead of Gemini video analysis
Optimize the accessible video workflow by eliminating the dedicated
Gemini video analysis call for pause point estimation. Instead:

- Use AD VTT cue start times as initial pause points for Whisper refinement
- Add user-selectable accessible video method (pause_insert/overlay) at QC approval
- Add bulk approval API endpoint with method selection
- Add method selector UI to QCDetail page
- Add bulk approval modal to QCList for jobs with accessible video

Benefits:
- Eliminates expensive Gemini API call with video upload
- Faster workflow (~5-15 seconds saved per job)
- Cost savings on Gemini video analysis
- User control over accessible video integration method

Backend changes:
- Add accessible_video_method to RequestedOutputs and ApproveSourceRequest
- Add POST /jobs/bulk/approve endpoint
- Replace Gemini call with _build_placements_from_ad_vtt() helper
- Mark analyze_accessible_video_placement() as deprecated

Frontend changes:
- Add method selector radio buttons to QCDetail
- Add bulk approval modal with method selection to QCList
- Update API client and React Query hooks

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-03 19:05:45 -06:00
..
__pycache__ better tts config for worker 2025-10-08 18:47:28 -05:00
audit_logger.py initial commit 2025-08-24 16:28:33 -05:00
emailer.py initial commit 2025-08-24 16:28:33 -05:00
ffmpeg_http_service.py feat: add Cloud Run HTTP services for Whisper and FFmpeg 2026-01-02 10:12:50 -06:00
gcs.py initial commit 2025-08-24 16:28:33 -05:00
gemini.py feat: use AD VTT pause points instead of Gemini video analysis 2026-01-03 19:05:45 -06:00
gemini_tts.py feat: add TTS_FAILED status and robust error handling for TTS synthesis 2025-12-30 14:26:07 -06:00
microsoft_auth.py added MSAL microsoft authentication 2025-10-10 09:19:39 -05:00
secrets_manager.py initial commit 2025-08-24 16:28:33 -05:00
tts.py feat: add accessible video (MP4 with embedded audio descriptions) 2025-12-26 11:06:41 -06:00
validation.py feat: add accessible video validation, remove AI confidence check 2025-12-26 16:41:57 -06:00
video_renderer.py fix: prevent event loop closed error in video renderer Cloud Run calls 2026-01-03 08:44:27 -06:00
vtt_retimer.py fix: rewrite VTT retiming algorithm to prevent captions during AD segments 2025-12-30 09:01:03 -06:00
websocket.py wrote docker files and deployment instructions 2025-10-08 16:00:12 -05:00
websocket_publisher.py wrote docker files and deployment instructions 2025-10-08 16:00:12 -05:00
whisper_http_service.py feat: add Cloud Run HTTP services for Whisper and FFmpeg 2026-01-02 10:12:50 -06:00
whisper_service.py feat: add Cloud Run HTTP services for Whisper and FFmpeg 2026-01-02 10:12:50 -06:00