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

src/api/agent_api.rs

@@ -56,12 +56,17 @@ async fn translate_text(
         "temperature": 0.1
     });
 
-    let response = LLM_CLIENT.post(llm_url).json(&body).send().await.map_err(|e| {
-        (
-            StatusCode::INTERNAL_SERVER_ERROR,
-            format!("Failed to call LLM: {}", e),
-        )
-    })?;
+    let response = LLM_CLIENT
+        .post(llm_url)
+        .json(&body)
+        .send()
+        .await
+        .map_err(|e| {
+            (
+                StatusCode::INTERNAL_SERVER_ERROR,
+                format!("Failed to call LLM: {}", e),
+            )
+        })?;
 
     let llm_resp: serde_json::Value = response.json().await.map_err(|e| {
         (