Commit History

  1. fix: move spaces import to top of app.py and trigger startup_report directly Running

    4dd9774
  2. fix: bind dummy worker to hidden Gradio button for HF ZeroGPU check and add class 38 to LabelRegistry

    f56867f
  3. fix: prevent ZeroGPU blocking call during app import to resolve 30min startup timeout

    be283bc

  1. fix: add HF ZeroGPU startup check bypass function in app.py

    2ec65b4
  2. fix: mount Gradio at root / and restore background model download & warmup task

    bdc8261
  3. fix: mount Gradio at /ui so FastAPI native router has full control of / and /api/v1/* routes

    0bfacff
  4. fix: add uvicorn.run entry point for HF space python process execution

    f27c8df
  5. perf: non-blocking async model warmup for instant boot and 200 OK health check

    8563384
  6. fix: mount Gradio at root for HF Space health check & REST API availability

    98f553f
  7. fix: switch HF space SDK to docker for direct FastAPI execution

    023ac94
  8. fix: mount gradio at /status to avoid /api route conflict

    38aeaed
  9. feat: launch uvicorn with full mounted app and add /api/v1/health route

    5b75e17
  10. feat: migrate full production detection service architecture with 8-model hub sync

    119c847
  11. feat: pre-warm and cache all 8 model files from Kaaado/agrovia-models

    71fb473
  12. feat: pre-warm all 5 models from Kaaado/agrovia-models and mount FastAPI endpoints

    49a9028
  13. fix: add @spaces.GPU wrapper to satisfy HF ZeroGPU watchdog

    3d986dd
  14. fix: use native Gradio launch with pre-warmed models

    6b30783
  15. fix: update sdk_version to 5.16.0 in README.md

    0530364
  16. fix: expose app ASGI entrypoint for HF space

    a59d412
  17. fix: add uvicorn server runner on port 7860 for HF Space

    3a2c0d1
  18. Deploy FastAPI detection engine with model caching

    60aaf91