fix: ASRX duplication, TKG edges, trace ingest, and add pipeline progress publishing

- ASRX handler no longer stores duplicate 'asr' pre_chunks
- Pre_chunks storage made idempotent (delete-before-insert)
- Rule 1 + trace_ingest changed to query 'asrx' not 'asr'
- Trace chunks removed (dynamic from TKG/Qdrant)
- TKG scroll_face_points fixed: trace_id >= 1 (not == 1)
- TKG AsrxSegmentEntry: start/end -> start_time/end_time (match ASRX JSON)
- Unregister error handling: log instead of silent discard
- Add publish_pipeline_progress calls at each pipeline stage
  (processors, rule1, face_trace, identity_agent, TKG, rule2, completion)

scripts/face_clustering_processor.py

@@ -14,13 +14,9 @@ from sklearn.cluster import AgglomerativeClustering
 
 sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
 
-try:
-    from deepface import DeepFace
-
-    HAS_DEEPFACE = True
-except ImportError:
-    print("❌ DeepFace not found. Run: pip install deepface")
-    sys.exit(1)
+# Use FaceNet embeddings from face.json instead of DeepFace
+HAS_DEEPFACE = False
+print("[FACE_CLUSTER] Using FaceNet embeddings from face.json (DeepFace not required)")
 
 # 設定
 UUID = os.getenv("UUID", "quick_preview")
@@ -104,53 +100,69 @@ def main():
         print("❌ No frames in JSON.")
         return
 
-    cap = cv2.VideoCapture(VIDEO_PATH)
+    # Get embeddings from Qdrant
+    print(f"[FACE_CLUSTER] Loading embeddings from Qdrant for {UUID}...")
+    try:
+        import requests
+        qdrant_url = "http://localhost:6333"
+        collection = "_faces"
+        
+        # Query all embeddings for this file_uuid
+        response = requests.post(
+            f"{qdrant_url}/collections/{collection}/points/scroll",
+            json={
+                "filter": {
+                    "must": [
+                        {"key": "file_uuid", "match": {"value": UUID}}
+                    ]
+                },
+                "limit": 10000,
+                "with_vector": True
+            }
+        )
+        
+        if response.status_code == 200:
+            result = response.json()
+            points = result.get("result", {}).get("points", [])
+            print(f"[FACE_CLUSTER] Loaded {len(points)} embeddings from Qdrant")
+            
+            # Build face_id -> embedding map
+            embedding_map = {}
+            for point in points:
+                face_id = point.get("payload", {}).get("face_id")
+                vector = point.get("vector")
+                if face_id and vector:
+                    embedding_map[face_id] = vector
+        else:
+            print(f"[FACE_CLUSTER] Qdrant query failed: {response.status_code}")
+            embedding_map = {}
+    except Exception as e:
+        print(f"[FACE_CLUSTER] Failed to load embeddings from Qdrant: {e}")
+        embedding_map = {}
+
+    # Use embeddings from Qdrant or face.json
     embeddings = []
     face_refs = []
 
-    print(f"🔍 Extracting face embeddings from {UUID}...")
+    print(f"🔍 Collecting face embeddings for {UUID}...")
 
     for frame_idx, frame_obj in enumerate(frames_list):
-        ts = frame_obj.get("timestamp")
         faces = frame_obj.get("faces", [])
         if not faces:
             continue
 
-        if ts is not None:
-            cap.set(cv2.CAP_PROP_POS_MSEC, ts * 1000)
-
-        ret, frame = cap.read()
-        if not ret:
-            continue
-
         for face_idx, face in enumerate(faces):
-            x, y, w, h = face["x"], face["y"], face["width"], face["height"]
-            margin = 5
-            crop = frame[
-                max(0, y - margin) : y + h + margin, max(0, x - margin) : x + w + margin
-            ]
-
-            if crop is None or crop.size == 0:
-                continue
-
-            try:
-                res = DeepFace.represent(
-                    img_path=crop, model_name="ArcFace", enforce_detection=False
-                )
-                if res and "embedding" in res[0]:
-                    embeddings.append(res[0]["embedding"])
-                    face_refs.append({"frame_idx": frame_idx, "face_idx": face_idx})
-            except Exception:
-                pass
-
-    cap.release()
+            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})
 
     if not embeddings:
-        print("❌ No embeddings extracted.")
+        print("❌ No embeddings found in Qdrant.")
         return
 
     embeddings = np.array(embeddings)
-    print(f"✅ Extracted {len(embeddings)} face embeddings.")
+    print(f"✅ Collected {len(embeddings)} face embeddings from Qdrant.")
 
     # 2. 聚類
     print(f"🧠 Clustering {len(embeddings)} faces...")