fix: face detection — use OpenCV FaceDetectorYN and full-res originals

- Rewrite faces.py to use cv2.FaceDetectorYN instead of raw ONNX
  (handles multi-scale anchor decoding and NMS internally)
- Load original photo files at up to 4000px for face detection instead
  of 240px thumbnails — faces were too small to detect at thumbnail res
- Falls back to thumbnail if original is unavailable

Tested: 33 faces extracted from 13 photos, clustered into 1 person.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

backend/app/tasks/vision.py

@@ -206,6 +206,42 @@ def detect_objects(photo_id: str):
     return {'status': 'success', 'photo_id': photo_id, 'objects': len(detections)}
 
 
+def _load_original(photo_id: str) -> np.ndarray | None:
+    """Load the original photo file as an RGB numpy array, resized to
+    max 1280px on the longest edge for face detection."""
+    from sqlalchemy import create_engine, select as sa_select, text as sa_text
+    from app.models import Photo
+
+    session = _get_sync_session()
+    try:
+        photo = session.execute(
+            sa_select(Photo).where(Photo.id == photo_id)
+        ).scalar_one_or_none()
+        if not photo or not photo.filepath:
+            return None
+        filepath = photo.filepath
+    finally:
+        session.close()
+
+    if not Path(filepath).exists():
+        logger.warning("Original file not found: %s", filepath)
+        return None
+
+    try:
+        img = Image.open(filepath).convert("RGB")
+        # Cap at 4000px on longest edge to avoid OOM, but keep as large
+        # as possible for face detection accuracy
+        max_dim = 4000
+        w, h = img.size
+        if max(w, h) > max_dim:
+            scale = max_dim / max(w, h)
+            img = img.resize((int(w * scale), int(h * scale)), Image.BICUBIC)
+        return np.array(img)
+    except Exception as e:
+        logger.warning("Failed to load original %s: %s", filepath, e)
+        return None
+
+
 @shared_task(name='extract_faces', queue='vision')
 def extract_faces(photo_id: str):
     """Detect faces and store recognition embeddings. Clustering is
@@ -213,9 +249,13 @@ def extract_faces(photo_id: str):
     if not settings.vision.enabled or not settings.vision.faces.enabled:
         return {'status': 'skipped', 'reason': 'faces disabled'}
 
-    image = _load_thumb(photo_id, "large")  # 1280px for better face detection
+    # Use original file for face detection — thumbnails are often too
+    # small (240px) for reliable face detection.
+    image = _load_original(photo_id)
     if image is None:
-        return {'status': 'error', 'message': 'thumbnail not found'}
+        image = _load_thumb(photo_id, "large")
+    if image is None:
+        return {'status': 'error', 'message': 'no image available'}
 
     from app.services.vision.registry import registry
     face_proc = registry.get_face_processor()