- Updated the autopilot state to reflect the current task status as in progress.
- Refactored the inference module to streamline model downloading and conversion processes, replacing the download_model method with a more efficient load_source method.
- Introduced asynchronous model building in the inference module to enhance performance during model conversion.
- Enhanced the engine factory to include a new method for building and caching models, improving error handling and logging during the upload process.
- Added calibration cache handling in the Jetson TensorRT engine for better resource management.
Made-with: Cursor
- Added Jetson-specific deployment instructions to `deploy_scripts.md`, detailing prerequisites and service management.
- Updated `deploy_status_report.md` to reflect the completion of the AZ-180 cycle and the readiness of Jetson support.
- Removed outdated task documentation for Jetson Orin Nano support from the todo list.
Made-with: Cursor
- Dockerfile.jetson: JetPack 6.x L4T base image (aarch64), TensorRT and PyCUDA from apt
- requirements-jetson.txt: derived from requirements.txt, no pip tensorrt/pycuda
- docker-compose.jetson.yml: runtime: nvidia for NVIDIA Container Runtime
- tensorrt_engine.pyx: convert_from_source accepts optional calib_cache_path; INT8 used when cache present, FP16 fallback; get_engine_filename encodes precision suffix to avoid engine cache confusion
- inference.pyx: init_ai tries INT8 engine then FP16 on lookup; downloads calibration cache before conversion thread; passes cache path through to convert_from_source
- constants_inf: add INT8_CALIB_CACHE_FILE constant
- Unit tests for AC-3 (INT8 flag set when cache provided) and AC-4 (FP16 when no cache)
Made-with: Cursor
- Pin all deps; h11==0.16.0 (CVE-2025-43859), python-multipart>=1.3.1 (CVE-2026-28356), PyJWT==2.12.1
- Add HMAC JWT verification (require_auth FastAPI dependency, JWT_SECRET-gated)
- Fix TokenManager._refresh() to use ADMIN_API_URL instead of ANNOTATIONS_URL
- Rename POST /detect → POST /detect/image (image-only, rejects video files)
- Replace global SSE stream with per-job SSE: GET /detect/{media_id} with event replay buffer
- Apply require_auth to all 4 protected endpoints
- Fix on_annotation/on_status closure to use mutable current_id for correct post-upload event routing
- Add non-root appuser to Dockerfile and Dockerfile.gpu
- Add JWT_SECRET to e2e/docker-compose.test.yml and run-tests.sh
- Update all e2e tests and unit tests for new endpoints and HMAC token signing
- 64/64 tests pass
Made-with: Cursor
- Update autopilot state to step 14 (Deploy) with status in progress.
- Mark step 12 (Security Audit) and step 13 (Performance Test) as skipped due to previous cycle completion.
- Update deployment status report date to 2026-04-01 and add notes on the implementation and testing of the `POST /detect/video` endpoint.
- Emphasize the need to address security findings before production deployment.
Made-with: Cursor
- Add tests/test_az178_realvideo_streaming.py: integration test that validates
frame decoding begins while upload is still in progress using a real video fixture
- Add conftest.py: pytest plugin for per-test duration reporting
- Update e2e tests (async_sse, performance, security, streaming_video_upload, video)
and run-tests.sh for updated test suite
- Move AZ-178 task to done/; add data/ to .gitignore (StreamingBuffer temp files)
- Update autopilot state to step 12 (Security Audit) for new feature cycle
Made-with: Cursor
- Added `/detect/video` endpoint for true streaming video detection, allowing inference to start as upload bytes arrive.
- Introduced `run_detect_video_stream` method in the inference module to handle video processing from a file-like object.
- Updated media hashing to include a new function for computing hashes directly from files with minimal I/O.
- Enhanced documentation to reflect changes in video processing and API behavior.
Made-with: Cursor
- Changed the current step from "Refactor" to "Implement" in the autopilot state, indicating a transition to the next phase of development.
- Updated the dependencies table to reflect the completion of 11 tasks and the addition of 4 new tasks related to the distributed architecture.
- Removed outdated task documentation for AZ-173, AZ-174, AZ-175, and AZ-176 as they are now obsolete following the architectural changes.
- Enhanced the execution order for new tasks, organizing them into batches based on dependencies.
These updates aim to align the project documentation with the current development phase and improve clarity on task management moving forward.
- Introduced `AIAvailabilityStatus` class to manage the availability status of AI models, including methods for setting status and logging messages.
- Added `AIRecognitionConfig` class to encapsulate configuration parameters for AI recognition, with a static method for creating instances from dictionaries.
- Implemented enums for AI availability states to enhance clarity and maintainability.
- Updated related Cython files to support the new classes and ensure proper type handling.
These changes aim to improve the structure and functionality of the AI model management system, facilitating better status tracking and configuration handling.
- Modified the health endpoint to return "None" for AI availability when inference is not initialized, improving clarity on system status.
- Enhanced the test documentation to include handling of skipped tests, emphasizing the need for investigation before proceeding.
- Updated test assertions to ensure proper execution order and prevent premature engine initialization.
- Refactored test cases to streamline performance testing and improve readability, removing unnecessary complexity.
These changes aim to enhance the robustness of the health check and improve the overall testing framework.
- Added Cython generated files to .gitignore to prevent unnecessary tracking.
- Updated paths in `inference.c` and `coreml_engine.c` to reflect the correct virtual environment.
- Revised the execution environment documentation to clarify hardware dependency checks and local execution instructions, ensuring accurate guidance for users.
- Removed outdated Docker suitability checks and streamlined the assessment process for test execution environments.
- Updated the `Inference` class to replace the `get_onnx_engine_bytes` method with `download_model`, allowing for dynamic model loading based on a specified filename.
- Modified the `convert_and_upload_model` method to accept `source_bytes` instead of `onnx_engine_bytes`, enhancing flexibility in model conversion.
- Introduced a new property `engine_name` to the `Inference` class for better access to engine details.
- Adjusted the `AIRecognitionConfig` structure to include a new method pointer `from_dict`, improving configuration handling.
- Updated various test cases to reflect changes in model paths and timeout settings, ensuring consistency and reliability in testing.
Oleksandr Bezdieniezhnykh