Behavision: face recognition for retail, edge to head office

Five components that ship as one product:

- behavision/  the recognition engine. RTSP ingest, YuNet detection, IoU
               tracking, ArcFace embeddings, a FAISS/SQLite gallery, and a
               FastAPI dashboard. Identity is decided once per TRACK from an
               average of at least three embeddings, never per frame.
- agent/       the Go edge agent: supervises the engine, holds a durable
               spool, and drains it to MQTT. Nothing is acked before the
               broker confirms.
- desktop/     the shop PC application (Wails + React + tray).
- server/      the cloud API, MQTT consumer, reports and assistant.
- web/         platform.loyaly.ai, the head-office app, embedded in the
               server binary.

The gallery stores 512-float embeddings and timestamps - no images unless
`app.store_faces` is switched on. Those embeddings are biometric personal
data under GDPR and India's DPDP: template inversion reconstructs a
recognisable face from an ArcFace vector, so data/behavision.db is treated
as a biometric database and DELETE /api/visitors/{id} is a real erasure.

CLAUDE.md carries the reasoning behind every non-obvious decision here,
including the ones that were measured and the ones that were wrong first.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HViLj9gYNRtSr7YVZmW5sn

tests/test_detector_concurrency.py

@@ -0,0 +1,55 @@
+"""cv2.FaceDetectorYN caches its input size and is not thread-safe, so camera
+workers must not share one. Skipped when the model is absent, matching the
+faiss-optional pattern in test_index.py — the suite stays runnable with no
+models installed."""
+import threading
+from pathlib import Path
+
+import numpy as np
+import pytest
+
+from behavision.config import Config
+from behavision.detection import YUNET_FILENAME, FaceDetector
+
+MODELS = Path(__file__).resolve().parent.parent / "models"
+pytestmark = pytest.mark.skipif(not (MODELS / YUNET_FILENAME).exists(),
+                                reason="YuNet model not installed")
+
+
+def _detector():
+    d = Config().detection
+    return FaceDetector(MODELS, d.score_threshold, d.nms_threshold,
+                        d.max_faces, d.min_face_px)
+
+
+def _hammer(det, size, errors, n=40):
+    w, h = size
+    frame = np.zeros((h, w, 3), dtype=np.uint8)
+    for _ in range(n):
+        try:
+            det.detect(frame)
+        except Exception as exc:  # noqa: BLE001 - cv2 raises on size mismatch
+            errors.append(exc)
+            return
+
+
+def _race(det_a, det_b):
+    errors = []
+    threads = [threading.Thread(target=_hammer, args=(det_a, (1280, 720), errors)),
+               threading.Thread(target=_hammer, args=(det_b, (640, 480), errors))]
+    for t in threads:
+        t.start()
+    for t in threads:
+        t.join()
+    return errors
+
+
+def test_a_shared_detector_really_does_race():
+    """Guards the premise: if this ever stops failing, the test below is
+    proving nothing and the per-camera split can be revisited."""
+    shared = _detector()
+    assert _race(shared, shared), "expected a shared detector to race"
+
+
+def test_per_camera_detectors_do_not_race():
+    assert _race(_detector(), _detector()) == []