Commit Graph
9 Commits
Author SHA1 Message Date
Jamie Pine d35e6f0cc5 fix sample upload blocking the event loop and causing server timeouts
Move audio validation and saving to thread pool so librosa/ffmpeg decoding
doesn't block the async event loop. Combine validate + load into a single
pass to avoid decoding the file twice. Add 50 MB upload limit and chunked
reads to prevent unbounded memory allocation.

Closes #278
2026-03-16 23:29:18 -07:00
Jamie Pine f9e1aa153d handle client disconnects in SSE and streaming endpoints
Wrap SSE generators with BrokenPipeError/ConnectionResetError handling
so client disconnects during generation status polling, download progress,
or audio streaming don't produce unhandled Errno 32 errors.

Closes #248
2026-03-16 23:17:09 -07:00
Jamie Pine f1541701fb add model selection and expanded language support to /transcribe endpoint
Closes #233
2026-03-16 22:44:28 -07:00
James Pine 1526f2de26 about page + generation folder open and display 2026-03-16 10:14:47 -07:00
James Pine 4a8a9eac14 fix: docker frontend + docs cleanup 2026-03-16 05:28:05 -07:00
James Pine e9f63d6c57 reject model migration to subdirectory of source cache 2026-03-16 03:43:37 -07:00
James Pine 0d0b62ea93 address CodeRabbit review: fix 4 critical + 12 major issues
Critical:
- Remove dead backend.utils.validation PyInstaller hidden import
- Fix story_items table rebuild to preserve track/trim/version columns
- Guard cache migration against same source/destination path
- Fix regeneration audio overwrite (use random uuid suffix per take)

Major:
- Engine selector: validate language on Qwen switch, clear stale modelSize
- Sync language validation regex between profile create and generate (22 langs)
- Guard CUDA download against duplicate concurrent requests
- Only set model_size for engines that support multiple sizes
- Fix 404 swallowed by generic except in history export
- Validate audio_path before FileResponse in export-audio
- Transcription: stream uploads in 1MB chunks, use robust cache check,
  call complete_download() on Whisper download success
- Set clean version as default when effects chain validation fails
- Return explicit error when Windows port occupied by non-voicebox process
2026-03-16 03:12:01 -07:00
James Pine b3012ed10c move CRUD and service modules into services/, platform_detect into utils/
Move 9 business-logic modules from the backend root into services/:
channels, effects, history, profiles, stories, versions, export_import,
transcribe, tts. Move platform_detect.py into utils/.

Backend root now contains only infrastructure (app, main, config, server,
models, build_binary) and docs. All 94 routes verified.
2026-03-16 02:15:20 -07:00
James Pine 88536d27f7 extract routes from main.py into domain routers (Phase 4)
Split the 2,578-line main.py (90 routes) into 12 domain-specific router
modules under routes/. main.py is now a 45-line entry point.

New structure:
- app.py: FastAPI instance, CORS, startup/shutdown, safe_content_disposition
- routes/: health, profiles, channels, generations, history, transcription,
  stories, effects, audio, models, tasks, cuda
- services/cuda.py: moved from cuda_download.py

Also includes Phase 5 database/ package (from parallel agent):
- database/__init__.py re-exports all symbols for backward compat
- database/models.py, session.py, migrations.py, seed.py

All 90 routes verified registered and app imports cleanly.
2026-03-16 02:03:15 -07:00