video-accessibility/backend/app/tasks
Vadym Samoilenko 2e8a8dc287 feat: add brand context, ethics guidelines, and improved AD prompt rules
- Add brand_context field (job model, API, frontend form) so clients can
  list brand names present in their video; Gemini uses these names instead
  of generic descriptors (e.g. "Sellotape" not "sticky tape")
- Add ethical guidelines section to both Gemini prompts covering
  person-first language, consistent race/gender description only when
  plot-relevant, no guessing at unconfirmed identity
- Revamp audio description rules: priority ordering (essential →
  high-priority → time-permitting), pre-teaching placement, no cinematic
  jargon, succinct style replacing the former "20% longer" instruction
- Thread brand_context through full stack: routes → job doc → ingest
  task → translate task → both Gemini prompt templates

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-18 14:46:09 +00:00
..
__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 fix: register rerender_accessible_video task with Celery worker 2026-01-11 10:12:50 -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 feat: add brand context, ethics guidelines, and improved AD prompt rules 2026-03-18 14:46:09 +00:00
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: add QC accessible video review and editing capabilities 2026-01-11 08:32:27 -06:00
rerender_accessible_video.py fix: clear stale pause points when AD VTT is re-uploaded 2026-03-09 17:07:55 +00:00
translate_and_synthesize.py feat: add brand context, ethics guidelines, and improved AD prompt rules 2026-03-18 14:46:09 +00:00
tts_synthesis.py feat: add ElevenLabs voice selection to frontend and backend 2026-03-03 13:58:56 +00:00
whisper_transcribe.py fix: add authentication for Cloud Run service calls 2026-01-02 11:41:07 -06:00