feat: trace-level matching, health watcher/worker status, timezone config

scripts/face_landmark_qc.py

@@ -2,23 +2,30 @@
 """
 Face landmark QC: verify eyes/nose are within face bounding box.
 Flags faces in DB where landmarks don't match the bbox.
-Usage: python3 face_landmark_qc.py <file_uuid> [--threshold 0.5] [--fix]
+Usage: python3 face_landmark_qc.py <file_uuid> [--threshold 0.5] [--apply]
 """
-import sys, json, psycopg2, argparse
+import sys, json, psycopg2, argparse, os
 
 parser = argparse.ArgumentParser()
 parser.add_argument("uuid")
 parser.add_argument("--threshold", "-t", type=float, default=0.5,
     help="Fraction of landmark points that must be inside bbox (default: 0.5)")
-parser.add_argument("--fix", action="store_true", help="Update face_detections QC flag in DB")
+parser.add_argument("--apply", action="store_true",
+    help="Write qc_ok to face_detections.metadata in DB")
+parser.add_argument("--schema", default="dev",
+    help="DB schema (default: dev)")
 args = parser.parse_args()
 
 UUID = args.uuid
 THRESHOLD = args.threshold
-FACE_PATH = f"/Users/accusys/momentry/output_dev/{UUID}.face.json"
+SCHEMA = args.schema
+OUTPUT_DIR = os.environ.get("MOMENTRY_OUTPUT_DIR", f"/Users/accusys/momentry/output_dev")
+FACE_PATH = f"{OUTPUT_DIR}/{UUID}.face.json"
 
 print(f"=== Face Landmark QC ===")
 print(f"UUID: {UUID}")
+print(f"Schema: {SCHEMA}")
+print(f"Face file: {FACE_PATH}")
 print(f"Threshold: {THRESHOLD * 100:.0f}% points must be inside bbox")
 
 # Load face.json
@@ -29,8 +36,7 @@ total_faces = 0
 faces_with_lm = 0
 good_faces = 0
 bad_faces = 0
-bad_frame_ids = set()
-bad_face_details = []
+qc_results = []  # list of (frame, face_idx, qc_ok, x, y, w, h)
 
 # Build frame lookup for fast access
 frame_map = {}
@@ -42,13 +48,22 @@ for frame_num, frm in frame_map.items():
         total_faces += 1
         lm = face.get('landmarks')
         if not lm:
+            bbox = face.get('bbox', {})
+            qc_results.append((frame_num, fi, False, bbox.get('x'), bbox.get('y'),
+                               bbox.get('width'), bbox.get('height')))
+            bad_faces += 1
             continue
         faces_with_lm += 1
 
-        x, y, w, h = face['x'], face['y'], face['width'], face['height']
+        bbox = face.get('bbox', {})
+        x, y, w, h = bbox.get('x'), bbox.get('y'), bbox.get('width'), bbox.get('height')
+        if None in (x, y, w, h):
+            qc_results.append((frame_num, fi, False, x, y, w, h))
+            bad_faces += 1
+            continue
         inside_pts = 0
         total_pts = 0
-        eye_nose_inside = 0  # at least one point from each eye+nose inside
+        eye_nose_inside = 0
 
         for lm_type in ['left_eye', 'right_eye', 'nose']:
             points = lm.get(lm_type, [])
@@ -63,53 +78,39 @@ for frame_num, frm in frame_map.items():
                 eye_nose_inside += 1
 
         ratio = inside_pts / max(1, total_pts)
+        qc_ok = (ratio >= THRESHOLD and eye_nose_inside >= 2)
 
-        if ratio >= THRESHOLD and eye_nose_inside >= 2:
+        qc_results.append((frame_num, fi, qc_ok, x, y, w, h))
+        if qc_ok:
             good_faces += 1
         else:
             bad_faces += 1
-            bad_frame_ids.add(frame_num)
-            bad_face_details.append({
-                'frame': frame_num,
-                'face_idx': fi,
-                'bbox': [x, y, w, h],
-                'inside_pts': inside_pts,
-                'total_pts': total_pts,
-                'ratio': ratio,
-                'eye_nose_ok': eye_nose_inside,
-            })
 
 print(f"\nTotal faces: {total_faces:,}")
 print(f"Faces with landmarks: {faces_with_lm:,}")
 print(f"✅ Good (≥{THRESHOLD*100:.0f}% inside + ≥2 features): {good_faces:,}")
-print(f"❌ Bad: {bad_faces:,}")
+print(f"❌ Bad (no eyes or insufficient landmarks): {bad_faces:,}")
 print(f"Quality pass rate: {100 * good_faces / max(1, faces_with_lm):.1f}%")
 
-print(f"\nBad faces in {len(bad_frame_ids)} unique frames")
-
-# Show sample bad faces
-print(f"\nSample bad faces:")
-for bf in sorted(bad_face_details, key=lambda b: b['ratio'])[:5]:
-    print(f"  frame={bf['frame']}, bbox={bf['bbox']}, {bf['inside_pts']}/{bf['total_pts']} inside ({bf['ratio']*100:.0f}%), eye/nose={bf['eye_nose_ok']}/3")
-
-# Show sample good faces
-print(f"\nSample good faces:")
-good_details = []
-for frame_num, frm in frame_map.items():
-    for face in frm.get('faces', []):
-        lm = face.get('landmarks')
-        if not lm:
-            continue
-        x, y, w, h = face['x'], face['y'], face['width'], face['height']
-        inside = sum(1 for pts in lm.values() for pt in pts
-            if (x <= pt[0] <= x + w) and (y <= pt[1] <= y + h))
-        total = sum(len(pts) for pts in lm.values())
-        if inside / max(1, total) >= THRESHOLD:
-            good_details.append((frame_num, x, y, w, h, inside, total))
-            if len(good_details) >= 5:
-                break
-    if len(good_details) >= 5:
-        break
-
-for g in good_details:
-    print(f"  frame={g[0]}, bbox=[{g[1]},{g[2]},{g[3]},{g[4]}], {g[5]}/{g[6]} inside ({100*g[5]/max(1,g[6]):.0f}%)")
+# Apply mode: write qc_ok to face_detections.metadata
+if args.apply:
+    print(f"\n=== Applying QC results to {SCHEMA}.face_detections ===")
+    db_url = os.environ.get("DATABASE_URL", "postgres://accusys@localhost:5432/momentry")
+    conn = psycopg2.connect(db_url)
+    cur = conn.cursor()
+    updated = 0
+    for frame_num, fi, qc_ok, x, y, w, h in qc_results:
+        qc_str = "true" if qc_ok else "false"
+        cur.execute(
+            f"UPDATE {SCHEMA}.face_detections "
+            f"SET metadata = jsonb_set(COALESCE(metadata, '{{}}'::jsonb), '{{qc_ok}}', '\"{qc_str}\"'::jsonb) "
+            f"WHERE file_uuid = %s AND frame_number = %s AND x = %s AND y = %s AND width = %s AND height = %s",
+            (UUID, frame_num, x, y, w, h)
+        )
+        if cur.rowcount > 0:
+            updated += 1
+    conn.commit()
+    cur.close()
+    conn.close()
+    print(f"Updated {updated} rows in {SCHEMA}.face_detections")
+    print(f"Skipped {len(qc_results) - updated} rows (no matching face_detections row)")