From 229611b4c3eb7ecc4619dc5ac7d76bd55654c8b9 Mon Sep 17 00:00:00 2001
From: dtoro <d.toro.v@pm.me>
Date: Fri, 10 Apr 2026 10:48:19 +0200
Subject: [PATCH] fix: face clusters write photo_tags, raise detection
 threshold to 0.7

- recluster_faces now writes photo_tags rows for each face cluster so
  the tag count and tag_ids filter work (previously count was always 0)
- Old cluster tags and photo_tags are cleaned up before re-clustering
- Raise face detection threshold from 0.4 to 0.7 to reduce false
  positives (was detecting dog faces as people)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 backend/app/config.py       |  2 +-
 backend/app/tasks/vision.py | 64 ++++++++++++++++++++++++++-----------
 mulita.yml                  |  2 +-
 3 files changed, 47 insertions(+), 21 deletions(-)

diff --git a/backend/app/config.py b/backend/app/config.py
index 6ad7ae8..0128606 100644
--- a/backend/app/config.py
+++ b/backend/app/config.py
@@ -50,7 +50,7 @@ class FacesSettings(BaseModel):
     """YuNet + SFace face detection/recognition settings"""
     enabled: bool = True
     min_face_size: int = 40
-    recognition_threshold: float = 0.4
+    recognition_threshold: float = 0.7
     cluster_eps: float = 0.35
 
 class VisionSettings(BaseModel):
diff --git a/backend/app/tasks/vision.py b/backend/app/tasks/vision.py
index ac4df17..5ac29a6 100644
--- a/backend/app/tasks/vision.py
+++ b/backend/app/tasks/vision.py
@@ -294,9 +294,11 @@ def recluster_faces():
         return {'status': 'skipped', 'reason': 'faces disabled'}
 
     from app.models.face_embedding import FaceEmbedding
-    from app.models.tags import Tag
+    from app.models.tags import Tag, photo_tags
     from app.services.vision.clustering import cluster_faces
 
+    source_name = "vision:sface"
+
     session = _get_sync_session()
     try:
         face_rows = session.execute(
@@ -310,37 +312,61 @@ def recluster_faces():
         embeddings = np.array([f.vector for f in face_rows], dtype=np.float32)
         labels = cluster_faces(embeddings, eps=settings.vision.faces.cluster_eps)
 
+        # Clean up old face_cluster tags and their photo_tags
+        old_cluster_tags = session.execute(
+            select(Tag).where(Tag.kind == 'face_cluster', Tag.source == source_name)
+        ).scalars().all()
+        for old_tag in old_cluster_tags:
+            session.execute(
+                delete(photo_tags).where(
+                    photo_tags.c.tag_id == old_tag.id,
+                    photo_tags.c.source == source_name,
+                )
+            )
+            session.delete(old_tag)
+        session.flush()
+
+        # Build new clusters
         cluster_tag_map: dict[int, str] = {}
-        source_name = "vision:sface"
+        # Track which photos belong to which cluster
+        cluster_photos: dict[int, set[str]] = {}
 
         for i, label in enumerate(labels):
             if label == -1:
                 face_rows[i].cluster_id = None
                 continue
 
+            if label not in cluster_photos:
+                cluster_photos[label] = set()
+            cluster_photos[label].add(face_rows[i].photo_id)
+
             if label not in cluster_tag_map:
                 cluster_name = f"Person {label + 1}"
-                tag = session.execute(
-                    select(Tag).where(
-                        Tag.kind == 'face_cluster',
-                        Tag.source == source_name,
-                        Tag.name == cluster_name,
-                    )
-                ).scalar_one_or_none()
-
-                if not tag:
-                    tag = Tag(
-                        name=cluster_name,
-                        kind='face_cluster',
-                        source=source_name,
-                        representative_photo_id=face_rows[i].photo_id,
-                    )
-                    session.add(tag)
-                    session.flush()
+                tag = Tag(
+                    name=cluster_name,
+                    kind='face_cluster',
+                    source=source_name,
+                    representative_photo_id=face_rows[i].photo_id,
+                )
+                session.add(tag)
+                session.flush()
                 cluster_tag_map[label] = tag.id
 
             face_rows[i].cluster_id = cluster_tag_map[label]
 
+        # Write photo_tags associations so the tag count and tag_ids
+        # filter work for face clusters
+        for label, photo_ids in cluster_photos.items():
+            tag_id = cluster_tag_map[label]
+            for pid in photo_ids:
+                session.execute(
+                    photo_tags.insert().values(
+                        photo_id=pid,
+                        tag_id=tag_id,
+                        source=source_name,
+                    )
+                )
+
         session.commit()
     finally:
         session.close()
diff --git a/mulita.yml b/mulita.yml
index 265ad75..a5dcd80 100644
--- a/mulita.yml
+++ b/mulita.yml
@@ -44,6 +44,6 @@ vision:
   faces:
     enabled: true
     min_face_size: 40
-    recognition_threshold: 0.4
+    recognition_threshold: 0.7
     cluster_eps: 0.35
   worker_concurrency: 2