feat: Phase 2.6 edges migration to Qdrant (TKG-only architecture)

Phase 2.6.1: co_occurrence_edges migration
- build_co_occurrence_edges_from_qdrant()
- Qdrant embeddings → frame grouping → YOLO objects
- Result: 6679 edges (vs 6701 PostgreSQL)

Phase 2.6.2: face_face_edges migration
- build_face_face_edges_from_qdrant()
- Qdrant embeddings → frame grouping → face pairs
- mutual_gaze detection preserved
- Result: 6 edges (exact match)

Phase 2.6.3: speaker_face_edges migration
- build_speaker_face_edges_from_qdrant()
- Qdrant embeddings → trace_id frame ranges
- SPEAKS_AS edge creation

Architecture:
- All edges use Qdrant payload (no face_detections queries)
- PostgreSQL fallback for empty Qdrant
- Estimated 3.6x performance improvement

Testing:
- Playground (3003): ✓ All Phase 2.6 logs verified
- Edge counts: ✓ Close match with PostgreSQL
- Fallback: ✓ Working

Docs:
- docs_v1.0/DESIGN/TKG_PHASE2_6_EDGES_MIGRATION.md
- docs_v1.0/M4_workspace/2026-06-21_phase2_6_test.md

scripts/asrx_processor.py

@@ -228,7 +228,21 @@ def process_asrx(video_path: str, output_path: str, uuid: str = "",
         # Stage 1: Audio Track Preprocessing
         tmp_dir, audio_input = _shared_audio_setup(video_path)
 
-        # Stage 2: SelfASRXFixed 7-step pipeline
+        # Stage 2: Load ASR segments for time alignment (if available)
+        asr_segments = None
+        asr_path = (output_path.replace(".asrx.json", ".asr.json")
+                    if output_path else "")
+        if asr_path and os.path.exists(asr_path):
+            try:
+                with open(asr_path) as f:
+                    asr_data = json.load(f)
+                asr_segments = asr_data.get("segments", [])
+                if asr_segments:
+                    print(f"[ASRX] Loaded {len(asr_segments)} ASR segments from {asr_path}")
+            except Exception as e:
+                print(f"[ASRX] Failed to load ASR segments: {e}")
+
+        # Stage 3: SelfASRXFixed 7-step pipeline
         from asrx_self.main_fixed import SelfASRXFixed
 
         if publisher:
@@ -239,6 +253,9 @@ def process_asrx(video_path: str, output_path: str, uuid: str = "",
         if publisher:
             publisher.info("asrx", "ASRX_TRANSCRIBING")
 
+        if asr_segments:
+            print(f"[ASRX] Using {len(asr_segments)} ASR segments for diarization", file=sys.stderr)
+
         result = asrx.process(
             audio_input,
             output_path=None,
@@ -246,6 +263,7 @@ def process_asrx(video_path: str, output_path: str, uuid: str = "",
             max_speakers=10,
             quality_threshold=0.85,
             checkpoint_path=checkpoint_path,
+            asr_segments=asr_segments,
         )
 
         if "error" in result: