video-accessibility/backend/app/tasks
michael e44210ea64 feat: auto-rewrite TTS cues that fail synthesis
When TTS synthesis fails after 3 retries, the system now:
- Sends problematic cue text to Gemini for TTS-safe rewriting
- Updates the VTT file in GCS with rewritten text
- Retries TTS synthesis with the new text
- Records successful rewrites in job.tts_rewrites field

UI changes:
- JobDetail shows amber caution box with original/rewritten text
- JobsList shows warning icon next to jobs with rewrites
- Error display clarifies text shown is "after rewrite attempt"

Files changed:
- backend/app/models/job.py: Add tts_rewrites field
- backend/app/prompts/gemini_tts_rewrite.md: New prompt template
- backend/app/services/gemini.py: Add rewrite_tts_cue method
- backend/app/tasks/tts_synthesis.py: Add VTT update utilities
- backend/app/tasks/translate_and_synthesize.py: Rewrite+retry logic
- frontend/src/types/api.ts: Add TTSRewriteItem type
- frontend/src/routes/jobs/JobDetail.tsx: Caution display
- frontend/src/routes/jobs/JobsList.tsx: Warning indicator

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-05 14:42:50 -06:00
..
__pycache__ removed mongodb change stream monitoring, added global websockets monitoring for notifications, broke symmetry between toasts and persistent notifications (and refined which notifications get sent and how) 2025-08-25 15:48:18 -05:00
__init__.py feat: add dedicated TTS worker with parallel per-cue synthesis 2025-12-30 14:23:11 -06:00
ffmpeg_operations.py feat: add dedicated ffmpeg queue to prevent server overload 2025-12-26 17:56:23 -06:00
ingest_and_ai.py fix: broadcast WebSocket updates for ingesting and ai_processing status 2025-12-27 07:38:25 -06:00
notify.py added websockets for live job status updates with toast notifications on job list page 2025-08-24 19:41:23 -05:00
render_accessible_video.py feat: use AD VTT pause points instead of Gemini video analysis 2026-01-03 19:05:45 -06:00
translate_and_synthesize.py feat: auto-rewrite TTS cues that fail synthesis 2026-01-05 14:42:50 -06:00
tts_synthesis.py feat: auto-rewrite TTS cues that fail synthesis 2026-01-05 14:42:50 -06:00
whisper_transcribe.py fix: add authentication for Cloud Run service calls 2026-01-02 11:41:07 -06:00