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(security): handle query parameters in HMAC signature and default API key fallback

    790c991
  2. fix: add HF ZeroGPU startup check bypass function in app.py

    2ec65b4
  3. feat: pre-download all 8 AI models on boot via huggingface_hub SDK

    5fc4228
  4. fix: use hf_hub_download SDK and validate >1MB binary size to prevent text-pointer segfaults

    04d56e6
  5. fix: pin numpy<2.0.0 to prevent ONNXRuntime C++ segfault on Linux container

    8bf0de8
  6. fix: mount Gradio at root / and restore background model download & warmup task

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

    0bfacff
  8. fix: report status healthy when models_ready is True for Hugging Face health check probe

    38d3256
  9. fix: pre-warm models synchronously during lifespan startup to guarantee zero-downtime container readiness

    d055536
  10. fix: harden health check exception handling and fix cnn_loaded state calculation

    69af453
  11. fix: use streamed chunk download with User-Agent header for HF Hub model binaries

    3982649
  12. fix: add safe fallback to yolo_service for missing ONNX models during warmup

    d2d1629
  13. perf: prioritize fast and limited model download and warmup on boot

    bc9c615
  14. fix: use direct HF resolve download to guarantee binary model files without pointer file corruption

    29ea819
  15. perf: optimize model_loader manifest to download essential ONNX models for rapid boot

    34ce6c6
  16. perf: refine warmup to pre-warm primary production models within RAM budget

    9f53731
  17. fix: export environment variables in app/__init__.py for module resolution

    66c5614
  18. perf: reuse existing ONNX sessions across modes pointing to identical model paths

    ad22f50
  19. fix: enforce explicit CPUExecutionProvider to prevent CUDA device discovery segfaults on HF CPU space

    0c272c4
  20. fix: add 1.0s timeout to DB and Redis checks in health endpoint to prevent proxy 503 timeouts

    cd69f93
  21. fix: add hf_xet dependency to requirements.txt for fast HF Hub model downloading

    e6e248e
  22. fix: set relative data/ model default paths in config.py for portable environment execution

    379216b
  23. fix: remove non-ASCII unicode characters from print calls in model_loader.py

    22edca0
  24. fix: add uvicorn.run entry point for HF space python process execution

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

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

    98f553f
  27. fix: add root GET / health response route for HF ingress proxy

    b8299ee
  28. fix: switch HF space SDK to docker for direct FastAPI execution

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

    38aeaed
  30. fix: safe redis connection check and graceful fallback

    586a69a
  31. fix: default rate_limiter to memory:// when local redis is used

    c229cda
  32. feat: launch uvicorn with full mounted app and add /api/v1/health route

    5b75e17
  33. fix: in-memory fallback for rate limiter when redis is unreachable

    827e99a
  34. fix: valid HF metadata colorTo value

    a3c0dfd
  35. feat: migrate full production detection service architecture with 8-model hub sync

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

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

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

    3d986dd
  39. fix: set valid colorTo in README.md

    47fbd60
  40. fix: use native Gradio launch with pre-warmed models

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

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

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

    3a2c0d1
  44. fix: remove tflite-runtime requirement for Python 3.12 compatibility

    5c57507
  45. Deploy FastAPI detection engine with model caching

    60aaf91
  46. initial commit

    Verified signature
    11988af