fix: bugs and code quality in embeddings, jobs, diversity, config

- embeddings: initialize ctx_id=-1 before try block so the except
  handler cannot NameError; move insightface_home out of try for the
  same reason
- embeddings: replace contextlib.redirect_stdout/stderr (Python-level
  only) with fd-level dup2 suppression — actually silences C extension
  noise from InsightFace during model loading
- jobs: fix frigate_count==0 falling through `or` chain; use explicit
  `is not None` check so a real zero is not treated as missing data
- diversity: thread person_id through select_diverse_assets →
  _select_by_embedding → _get_face_bbox / _get_face_confidence /
  _crop_face_from_thumbnail so group-photo assets embed the target
  person's face rather than whichever person is listed first
- config: replace type() hack for ConfigManager with a proper class

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

winnow/config.py

@@ -161,7 +161,12 @@ class _ConfigAccessor:
 
 
 Config = _ConfigAccessor()
-ConfigManager = type("ConfigManager", (), {"get": staticmethod(lambda: _Config())})
+
+
+class ConfigManager:
+    @staticmethod
+    def get() -> _Config:
+        return _Config()
 
 
 def get_headers() -> dict[str, str]:

winnow/diversity.py

@@ -29,6 +29,7 @@ def select_diverse_assets(
     entity_name: str,
     selection_mode: str = "smart",
     entity_type: str = "face",
+    person_id: str | None = None,
     progress_callback=None,
 ) -> list:
     """
@@ -59,7 +60,7 @@ def select_diverse_assets(
         return _select_time_spread(assets, limit)
 
     try:
-        return _select_by_embedding(assets, limit, entity_type, progress_callback)
+        return _select_by_embedding(assets, limit, entity_type, person_id, progress_callback)
     except Exception as e:
         logger.error(f"Smart Diversity failed: {e}. Falling back to time spread.")
         return _select_time_spread(assets, limit)
@@ -80,9 +81,11 @@ def _fetch_thumbnail(asset_id: str, timeout: int = 10) -> Image.Image | None:
         return None
 
 
-def _get_face_bbox(asset: dict) -> tuple[float, float, float, float] | None:
-    """Extract face bounding box from asset metadata if available."""
+def _get_face_bbox(asset: dict, person_id: str | None = None) -> tuple[float, float, float, float] | None:
+    """Extract face bounding box from asset metadata for the given person."""
     for person in asset.get("people", []):
+        if person_id and person.get("id") != person_id:
+            continue
         faces = person.get("faces", [])
         if faces:
             f = faces[0]
@@ -95,9 +98,11 @@ def _get_face_bbox(asset: dict) -> tuple[float, float, float, float] | None:
     return None
 
 
-def _get_face_confidence(asset: dict) -> float | None:
-    """Extract face detection confidence from asset metadata if available."""
+def _get_face_confidence(asset: dict, person_id: str | None = None) -> float | None:
+    """Extract face detection confidence from asset metadata for the given person."""
     for person in asset.get("people", []):
+        if person_id and person.get("id") != person_id:
+            continue
         faces = person.get("faces", [])
         if faces:
             return faces[0].get("score") or faces[0].get("confidence")
@@ -108,6 +113,7 @@ def _crop_face_from_thumbnail(
     img: Image.Image,
     asset: dict,
     margin: float = 0.25,
+    person_id: str | None = None,
 ) -> Image.Image | None:
     """Crop the face region from a thumbnail using Immich bbox metadata.
 
@@ -118,11 +124,12 @@ def _crop_face_from_thumbnail(
         img: Full preview thumbnail
         asset: Asset dict with people/faces metadata
         margin: Extra margin around the bbox (fraction, default 25%)
+        person_id: If provided, only crop from this person's face data.
 
     Returns:
         Cropped face PIL image, or None if no face metadata available
     """
-    bbox = _get_face_bbox(asset)
+    bbox = _get_face_bbox(asset, person_id=person_id)
     if bbox is None:
         return None
 
@@ -169,6 +176,7 @@ def _select_by_embedding(
     assets: list,
     limit: int | str,
     entity_type: str,
+    person_id: str | None = None,
     progress_callback=None,
 ) -> list:
     """Select assets using embedding-based cluster-aware FPS.
@@ -217,11 +225,11 @@ def _select_by_embedding(
         if img is None:
             continue
 
-        confidence = _get_face_confidence(asset)
+        confidence = _get_face_confidence(asset, person_id=person_id)
 
         # Quality gate: filter before expensive embedding computation
         if entity_type == "face":
-            face_bbox = _get_face_bbox(asset)
+            face_bbox = _get_face_bbox(asset, person_id=person_id)
             quality = assess_quality(
                 img,
                 face_bbox=face_bbox,
@@ -236,7 +244,7 @@ def _select_by_embedding(
                 continue
 
             # Crop the target person's face before embedding
-            face_crop = _crop_face_from_thumbnail(img, asset)
+            face_crop = _crop_face_from_thumbnail(img, asset, person_id=person_id)
             embed_img = face_crop if face_crop is not None else img
         else:
             embed_img = img

winnow/embeddings.py

@@ -6,11 +6,11 @@ Unified embedding interface for faces and objects.
 - Caching: Disk-based cache avoids recomputation on reruns
 """
 
-import contextlib
 import importlib
 import logging
 import os
 import warnings
+from contextlib import contextmanager
 
 import cv2
 import numpy as np
@@ -20,6 +20,24 @@ from .cache import get_cache
 
 logger = logging.getLogger(__name__)
 
+
+@contextmanager
+def _suppress_output():
+    """Suppress stdout/stderr at the file-descriptor level, silencing C extension noise."""
+    devnull_fd = os.open(os.devnull, os.O_WRONLY)
+    saved_out, saved_err = os.dup(1), os.dup(2)
+    try:
+        os.dup2(devnull_fd, 1)
+        os.dup2(devnull_fd, 2)
+        yield
+    finally:
+        os.dup2(saved_out, 1)
+        os.dup2(saved_err, 2)
+        os.close(devnull_fd)
+        os.close(saved_out)
+        os.close(saved_err)
+
+
 # Lazy-loaded singletons
 _insightface_app = None
 _insightface_loaded = False
@@ -70,6 +88,8 @@ def get_insightface_app():
     # Preload CUDA/cuDNN DLLs BEFORE any ORT InferenceSession is created
     _preload_cuda_libs()
 
+    ctx_id = -1
+    insightface_home = os.environ.get("INSIGHTFACE_HOME", os.path.expanduser("~/.insightface"))
     try:
         import onnxruntime as ort
         from insightface.app import FaceAnalysis
@@ -78,7 +98,6 @@ def get_insightface_app():
         providers = [p for p in ort.get_available_providers() if p != "TensorrtExecutionProvider"]
         logger.info(f"Available ONNX providers: {providers}")
 
-        # Determine device: 0 for GPU, -1 for CPU
         gpu_providers = {
             "CUDAExecutionProvider",
             "ROCmExecutionProvider",
@@ -90,9 +109,7 @@ def get_insightface_app():
         device_str = "GPU" if ctx_id >= 0 else "CPU"
         logger.info(f"Loading InsightFace Buffalo_L on {device_str} (ctx_id={ctx_id})...")
 
-        # Suppress C-level output during model loading
-        with open(os.devnull, "w") as devnull, contextlib.redirect_stdout(devnull), contextlib.redirect_stderr(devnull):
-            insightface_home = os.environ.get("INSIGHTFACE_HOME", os.path.expanduser("~/.insightface"))
+        with _suppress_output():
             _insightface_app = FaceAnalysis(name="buffalo_l", root=insightface_home, providers=providers)
             _insightface_app.prepare(ctx_id=ctx_id, det_size=(640, 640))
 
@@ -103,7 +120,6 @@ def get_insightface_app():
         return None
     except Exception as e:
         logger.error(f"Failed to load InsightFace: {e}")
-        # Retry on CPU if GPU failed
         if ctx_id == 0:
             logger.warning("Retrying InsightFace on CPU...")
             try:

winnow/jobs.py

@@ -81,7 +81,9 @@ def _resolve_strategy(strategy: str, has_embedding: bool) -> tuple[int | str, st
     return strategy_map.get(strategy, ("auto", "smart"))
 
 
-def _perform_selection(assets: list, limit: int | str, name: str, selection_mode: str, entity_type: str) -> list:
+def _perform_selection(
+    assets: list, limit: int | str, name: str, selection_mode: str, entity_type: str, person_id: str | None = None
+) -> list:
     """Run diversity selection with progress display."""
     if selection_mode == "smart":
         model_display = "InsightFace (face embeddings)" if entity_type == "face" else "SigLIP (visual embeddings)"
@@ -104,6 +106,7 @@ def _perform_selection(assets: list, limit: int | str, name: str, selection_mode
                 name,
                 selection_mode=selection_mode,
                 entity_type=entity_type,
+                person_id=person_id,
                 progress_callback=lambda c, t: progress.update(task, completed=c, total=t),
             )
 
@@ -113,7 +116,9 @@ def _perform_selection(assets: list, limit: int | str, name: str, selection_mode
 
     rprint(f"\n[cyan]Using time-spread selection for {limit} images...[/cyan]")
     with console.status(f"[bold]Selecting {limit} images evenly distributed over time...[/bold]"):
-        selected = select_diverse_assets(assets, limit, name, selection_mode="time", entity_type=entity_type)
+        selected = select_diverse_assets(
+            assets, limit, name, selection_mode="time", entity_type=entity_type, person_id=person_id
+        )
     rprint(f"  [green]Selected {len(selected)} images using time spread.[/green]")
     return selected
 
@@ -167,7 +172,9 @@ def _configure_person(person: dict, people: list[dict]) -> dict | None:
         return None
 
     # Perform selection
-    selected_assets = _perform_selection(recent_assets, limit, name, selection_mode, entity_type)
+    selected_assets = _perform_selection(
+        recent_assets, limit, name, selection_mode, entity_type, person_id=person["id"]
+    )
 
     rprint(f"  [green]Queued {len(selected_assets)} images for {name}.[/green]")
     return {"person": person, "assets": selected_assets, "limit": len(selected_assets), "config": config}
@@ -276,10 +283,8 @@ def auto_configure(people: list[dict]) -> list[dict]:
         if frigate_counts is not None:
             already_uploaded = frigate_counts.get(name, 0)
         else:
-            already_uploaded = (
-                person_summary.get("frigate_count")
-                or person_summary.get("uploaded", 0)
-            )
+            fc = person_summary.get("frigate_count")
+            already_uploaded = fc if fc is not None else person_summary.get("uploaded", 0)
         capacity = Config.MAX_AUTO_IMAGES - already_uploaded
         if capacity <= 0:
             rprint(
@@ -301,7 +306,9 @@ def auto_configure(people: list[dict]) -> list[dict]:
         if selection_mode == "skip":
             continue
 
-        selected_assets = _perform_selection(recent_assets, limit, name, selection_mode, entity_type)
+        selected_assets = _perform_selection(
+            recent_assets, limit, name, selection_mode, entity_type, person_id=person["id"]
+        )
 
         if selected_assets:
             rprint(f"  [green]Queued {len(selected_assets)} images for {name}.[/green]")