3 Commits

Include renames

Author	SHA1	Message	Date
andrew	0efcfa45b8	feat: DO-gated manual batch mode (auto default, office-only switches)	2026-09-24 15:45:12 +07:00
andrew	12b70a3431	refactor: consolidate counting config through src/config_loader ... - config.yaml gains counting.max_reid_frames (200) + debounce_frames (8); CountingConfig + parsing + pinned-value test added - predict.py load_zones() delegates to read_zone_polygons() (geometry only); legacy zones.json knob reads removed (config.yaml is canonical) - run_prediction wires 5 more live knobs from cfg.counting.* (entry/exit overlap, tolerance_missing_frames, max_reid_frames, debounce_frames) - delete deprecated src/config.py (v3 keys) + tests/test_config.py; src/main.py bridges onto unified config so the deprecated entrypoint keeps working - 8 never-read globals (JARAK_ABSORBSI_GHOST, CAMERA_NOISE_DEADBAND, ...) left untouched — flagged for Phase 2 dead-code cleanup Verified: pytest 21 passed; full pipeline runs on synthetic video (engines load, 30 frames, clean finish).	2026-09-17 12:59:54 +07:00
andrew	2d9c66cbb6	feat: unified config.yaml with extensible model presets (A-D data-driven, E/F ready) ... - config.yaml canonical for stream/models/counting/batch/output/camera - models.modes hold engines+class filters only; conf/iou/min_bbox in detection_params - predict.py derives tracker roles structurally (no per-mode branching) - dashboard mode switch validates + persists atomically to config.yaml - .env keeps secrets/deployment only; zones.json geometry; tracker.yaml hyperparams - batch_mode.json keeps manual/auto batch mode; legacy model_mode ignored w/ warning - src/detection+tracking gain iou param (default 0.7 = no behavior change)	2026-09-17 11:44:45 +07:00