fix: store_traced_faces — embed from DB, UPDATE not INSERT, dedup

scripts/store_traced_faces.py

@@ -48,10 +48,25 @@ def run_face_tracker(face_json_path: str, traced_json_path: str) -> str:
         frames_dict = {}
         for frame in face_data["frames"]:
             fnum = str(frame["frame"])
+            faces = []
+            for f in frame.get("faces", []):
+                bbox = f.get("bbox", f)
+                face = {
+                    "x": bbox.get("x", f.get("x", 0)),
+                    "y": bbox.get("y", f.get("y", 0)),
+                    "width": bbox.get("width", f.get("width", 0)),
+                    "height": bbox.get("height", f.get("height", 0)),
+                    "confidence": f.get("confidence", 0.0),
+                }
+                if "landmarks" in f:
+                    face["landmarks"] = f["landmarks"]
+                if "embedding" in f:
+                    face["embedding"] = f["embedding"]
+                faces.append(face)
             frames_dict[fnum] = {
                 "frame_number": frame["frame"],
                 "time_seconds": frame.get("timestamp", 0),
-                "faces": frame.get("faces", []),
+                "faces": faces,
             }
         face_data["frames"] = frames_dict
         # Preserve metadata (fps needed by face_tracker)
@@ -63,6 +78,41 @@ def run_face_tracker(face_json_path: str, traced_json_path: str) -> str:
 
     print(f"[TRACE] Processing {len(face_data.get('frames', {}))} frames")
     
+    # Load embeddings from DB for the face tracker
+    file_uuid = face_json_path.split("/")[-1].replace(".face.json", "").replace("_traced.json", "")
+    try:
+        conn = get_conn()
+        cur = conn.cursor()
+        cur.execute(f"""
+            SELECT frame_number, x, y, width, height, embedding
+            FROM {SCHEMA}.face_detections
+            WHERE file_uuid = %s AND embedding IS NOT NULL
+        """, (file_uuid,))
+        emb_rows = cur.fetchall()
+        conn.close()
+        # Build lookup: frame_number → list of (bbox, embedding)
+        emb_map = {}
+        for fn, x, y, w, h, emb in emb_rows:
+            emb_map.setdefault(fn, []).append(((x, y, w, h), emb))
+        print(f"[TRACE] Loaded {len(emb_rows)} embeddings from DB")
+        
+        # Attach embeddings to face data
+        attached = 0
+        for fnum_str, frm_data in face_data.get("frames", {}).items():
+            fnum = int(fnum_str)
+            for face in frm_data.get("faces", []):
+                x, y, w, h = face.get("x", 0), face.get("y", 0), face.get("width", 0), face.get("height", 0)
+                candidates = emb_map.get(fnum, [])
+                # Find matching embedding by bbox proximity
+                for (ex, ey, ew, eh), emb in candidates:
+                    if abs(x - ex) < 10 and abs(y - ey) < 10 and abs(w - ew) < 10 and abs(h - eh) < 10:
+                        face["embedding"] = emb
+                        attached += 1
+                        break
+        print(f"[TRACE] Attached {attached} embeddings to faces")
+    except Exception as e:
+        print(f"[TRACE] WARNING: Could not load embeddings: {e}")
+    
     # Load cut boundaries from cut.json (same directory as face.json)
     cut_boundaries = None
     cuts_path = face_json_path.replace("_traced.json", ".cut.json").replace(".face.json", ".cut.json")
@@ -121,20 +171,18 @@ def store_traced_faces(file_uuid: str, traced_json_path: str, schema: str = SCHE
             try:
                 cur.execute(
                     f"""
-                    INSERT INTO {schema}.face_detections
+                    UPDATE {schema}.face_detections
-                        (file_uuid, frame_number, face_id, trace_id,
+                    SET trace_id = %s
-                         x, y, width, height, confidence, embedding)
+                    WHERE file_uuid = %s AND frame_number = %s
-                    VALUES (%s, %s, %s, %s,
+                      AND x = %s AND y = %s AND width = %s AND height = %s
-                            %s, %s, %s, %s, %s, %s)
-                    ON CONFLICT DO NOTHING
                     """,
                     (
-                        file_uuid, frame_num, face_id, trace_id,
+                        trace_id,
-                        x, y, w, h, confidence,
+                        file_uuid, frame_num, x, y, w, h,
-                        embed_vec,
                     ),
                 )
-                total_stored += 1
+                if cur.rowcount > 0:
+                    total_stored += 1
             except Exception as e:
                 print(f"[TRACE] Error storing face at frame {frame_num}: {e}")
                 conn.rollback()