feat: OCR independent chunks + TMDb seed with file_uuid

- Rule 1 now creates OCR-only chunks instead of merging into ASRX
- generate_seed_embeddings.py supports --file-uuid parameter
- get_seeds() filters by file_uuid
- identity_matcher.py uses file_uuid for seed matching
- Push QDRANT_API_KEY to Python subprocesses
- Face clustering uses frame+bbox matching instead of face_id
- Portal uses JWT authentication
- FilesView filter logic fixed

scripts/face_clustering_processor.py

@@ -104,9 +104,14 @@ def main():
     print(f"[FACE_CLUSTER] Loading embeddings from Qdrant for {UUID}...")
     try:
         import requests
-        qdrant_url = "http://localhost:6333"
+        qdrant_url = os.environ.get("QDRANT_URL", "http://localhost:6333")
+        qdrant_api_key = os.environ.get("QDRANT_API_KEY", "")
         collection = "_faces"
         
+        headers = {}
+        if qdrant_api_key:
+            headers["api-key"] = qdrant_api_key
+        
         # Query all embeddings for this file_uuid
         response = requests.post(
             f"{qdrant_url}/collections/{collection}/points/scroll",
@@ -118,7 +123,8 @@ def main():
                 },
                 "limit": 10000,
                 "with_vector": True
-            }
+            },
+            headers=headers
         )
         
         if response.status_code == 200:
@@ -140,22 +146,57 @@ def main():
         print(f"[FACE_CLUSTER] Failed to load embeddings from Qdrant: {e}")
         embedding_map = {}
 
-    # Use embeddings from Qdrant or face.json
+    # Use embeddings from Qdrant - match by frame + bbox
     embeddings = []
     face_refs = []
 
     print(f"🔍 Collecting face embeddings for {UUID}...")
 
+    # Build a lookup: (frame, bbox_center) -> embedding
+    # Use frame number and approximate bbox center for matching
+    qdrant_by_frame = {}
+    for point in points:
+        payload = point.get("payload", {})
+        frame = payload.get("frame")
+        bbox = payload.get("bbox", {})
+        vector = point.get("vector")
+        if frame is not None and vector:
+            # Use frame + bbox center as key
+            cx = bbox.get("x", 0) + bbox.get("width", 0) // 2
+            cy = bbox.get("y", 0) + bbox.get("height", 0) // 2
+            key = (frame, cx, cy)
+            if key not in qdrant_by_frame:
+                qdrant_by_frame[key] = vector
+
+    print(f"[FACE_CLUSTER] Built Qdrant lookup with {len(qdrant_by_frame)} entries")
+
     for frame_idx, frame_obj in enumerate(frames_list):
+        frame_num = frame_obj.get("frame", frame_idx)
         faces = frame_obj.get("faces", [])
         if not faces:
             continue
 
         for face_idx, face in enumerate(faces):
-            face_id = face.get("face_id")
-            if face_id and face_id in embedding_map:
-                embeddings.append(embedding_map[face_id])
-                face_refs.append({"frame_idx": frame_idx, "face_idx": face_idx, "face_id": face_id})
+            x = face.get("x", 0)
+            y = face.get("y", 0)
+            w = face.get("width", 0)
+            h = face.get("height", 0)
+            cx = x + w // 2
+            cy = y + h // 2
+
+            # Try exact match first
+            key = (frame_num, cx, cy)
+            if key in qdrant_by_frame:
+                embeddings.append(qdrant_by_frame[key])
+                face_refs.append({"frame_idx": frame_idx, "face_idx": face_idx})
+                continue
+
+            # Try approximate match (within 50 pixels)
+            for (qf, qx, qy), vec in qdrant_by_frame.items():
+                if qf == frame_num and abs(qx - cx) < 50 and abs(qy - cy) < 50:
+                    embeddings.append(vec)
+                    face_refs.append({"frame_idx": frame_idx, "face_idx": face_idx})
+                    break
 
     if not embeddings:
         print("❌ No embeddings found in Qdrant.")