Merge pull request #42 from sudolulo/fix/frigate-500-permanent-rejection

fix: Frigate 500 permanent rejection + 13 correctness bugs

CHANGELOG.md

@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Changed
+
+- **`MAX_AUTO_IMAGES` default lowered from 20 to 5** — existing users who have not set this variable and already have more than 5 winnow-managed images in Frigate will find themselves at cap on the next run. With `QUALITY_REPLACEMENT=true` (the default), winnow will attempt to swap weaker images rather than uploading new ones. Set `MAX_AUTO_IMAGES=20` to restore the previous behaviour.
+
 ## [0.6.5] - 2026-06-17
 
 ### Added

README.md

@@ -187,7 +187,7 @@ In scheduled mode the process (and loaded models) stays resident between runs. T
 
 | Variable | Default | Description |
 | :--- | :--- | :--- |
-| `MAX_AUTO_IMAGES` | `20` | Maximum training images per person in Frigate |
+| `MAX_AUTO_IMAGES` | `5` | Maximum training images per person in Frigate |
 | `QUALITY_REPLACEMENT` | `true` | When at cap, swap a weaker tracked image for a better candidate. With Frigate scoring active, targets the most redundant image (highest pre-upload recognize score); otherwise uses blur score. Never touches manually added Frigate files. Set `false` to skip people at cap |
 
 #### Advanced Tuning *(calibrated — do not adjust)*

compose.yml

@@ -31,7 +31,7 @@ services:
       # - USE_FULL_RESOLUTION=true    # Use full-res images vs thumbnails (default: true)
       # - MIN_CONFIDENCE=0.7          # Minimum face detection confidence (default: 0.7)
       # - BLUR_THRESHOLD=100.0        # Laplacian blur threshold; lower = accept more blur (default: 100.0)
-      # - MAX_AUTO_IMAGES=80          # Hard cap on auto-diversity selection (default: 20)
+      # - MAX_AUTO_IMAGES=80          # Hard cap on auto-diversity selection (default: 5)
 
       # ── Caching & Models ──────────────────────────────────────────────────
       # - FORCE_CPU=true              # Disable GPU, fall back to CPU

scheduler.py

@@ -49,11 +49,12 @@ def _run_scheduler() -> None:
             try:
                 main()
                 print("winnow run complete", flush=True)
-            except KeyboardInterrupt:
+            except (KeyboardInterrupt, SystemExit):
                 raise
             except Exception as e:
                 logger.error("winnow run failed: %s", e, exc_info=True)
                 print(f"winnow run failed: {e}", flush=True)
+            cron = croniter(schedule, time.time())
             next_run = cron.get_next(float)
             print(f"Next run: {time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(next_run))}", flush=True)
         time.sleep(min(60, max(1, next_run - time.time())))

tests/test_config.py

@@ -21,7 +21,7 @@ def test_config_loads_defaults(monkeypatch):
     assert cfg.MIN_FACE_COUNT == 3
     assert cfg.BLUR_THRESHOLD == 120.0
     assert cfg.MIN_CONFIDENCE == 0.7
-    assert cfg.MAX_AUTO_IMAGES == 20
+    assert cfg.MAX_AUTO_IMAGES == 5
     assert cfg.QUALITY_REPLACEMENT is True
     assert cfg.FACE_MARGIN == 0.15
     assert cfg.USE_FULL_RESOLUTION is True

winnow/config.py

@@ -127,12 +127,15 @@ class _Config:
         self.API_KEY = os.getenv("API_KEY")
         self.OUTPUT_DIR = os.getenv("OUTPUT_DIR", "./frigate_train")
         self.YEARS_FILTER = _getenv_int("YEARS_FILTER", 10)
+        if self.YEARS_FILTER < 0:
+            logging.warning("YEARS_FILTER=%s is negative — using default 10", self.YEARS_FILTER)
+            self.YEARS_FILTER = 10
         self.MIN_FACE_WIDTH = _getenv_int("MIN_FACE_WIDTH", 90)
         self.MIN_FACE_COUNT = _getenv_int("MIN_FACE_COUNT", 3)
         self.MERGE_DUPLICATE_PEOPLE = _getenv_bool("MERGE_DUPLICATE_PEOPLE", False)
         self.BLUR_THRESHOLD = _getenv_float("BLUR_THRESHOLD", 120.0)
         self.MIN_CONFIDENCE = _getenv_float("MIN_CONFIDENCE", 0.7)
-        self.MAX_AUTO_IMAGES = _getenv_int("MAX_AUTO_IMAGES", 20)
+        self.MAX_AUTO_IMAGES = _getenv_int("MAX_AUTO_IMAGES", 5)
         self.QUALITY_REPLACEMENT = _getenv_bool("QUALITY_REPLACEMENT", True)
         self.FRIGATE_SCORE_CEILING = _getenv_optional_float("FRIGATE_SCORE_CEILING")
         self.ENABLE_FRIGATE_SCORES = _getenv_bool("ENABLE_FRIGATE_SCORES", True)

winnow/embeddings.py

@@ -107,7 +107,6 @@ def get_insightface_app():
     global _insightface_app, _insightface_loaded
     if _insightface_loaded:
         return _insightface_app
-    _insightface_loaded = True
 
     ctx_id = -1
     insightface_home = os.environ.get("INSIGHTFACE_HOME", os.path.expanduser("~/.insightface"))
@@ -172,10 +171,12 @@ def get_insightface_app():
             _insightface_app.prepare(ctx_id=ctx_id, det_size=(640, 640))
 
         logger.info("InsightFace Buffalo_L: ready on %s (%.1fs)", device_str, time.time() - t0)
+        _insightface_loaded = True
         return _insightface_app
 
     except ImportError:
         logger.error("InsightFace not installed!")
+        _insightface_loaded = True
         return None
     except Exception as e:
         logger.error("Failed to load InsightFace: %s", e)
@@ -193,9 +194,11 @@ def get_insightface_app():
                     )
                     _insightface_app.prepare(ctx_id=-1, det_size=(640, 640))
                 logger.info("InsightFace Buffalo_L: ready on CPU (fallback, %.1fs)", time.time() - t0)
+                _insightface_loaded = True
                 return _insightface_app
             except Exception as ex:
                 logger.error("InsightFace CPU fallback failed: %s", ex)
+        _insightface_loaded = True
         return None
 
 

winnow/executor.py

@@ -186,11 +186,10 @@ def execute_jobs(jobs: list[dict]) -> None:
                             saved = process_face_mode(
                                 img, asset, person, person_dir, count, insightface_app=insightface_app
                             )
-                            if saved:
+                            if isinstance(saved, tuple):
                                 filename = f"{count}.jpg"
                                 asset_map[filename] = asset["id"]
                                 score_map[filename] = asset.get("quality_score")
-                                if isinstance(saved, tuple):
                                 dims_map[filename] = saved
                                 # Time-spread path: compute blur score from the downloaded
                                 # image. Capped at 1440px via blur_score_from_image() so the
@@ -202,8 +201,9 @@ def execute_jobs(jobs: list[dict]) -> None:
 
                                 count += 1
                             else:
+                                reason = saved if isinstance(saved, str) else "no usable face data"
                                 progress.console.print(
-                                    f"[yellow]Skipped {asset['id']} (no usable face data)[/yellow]"
+                                    f"[yellow]Skipped {asset['id']} ({reason})[/yellow]"
                                 )
                     except Exception as e:
                         logger.error("Failed to process asset %s: %s", asset.get("id", "<unknown>"), e)
@@ -384,9 +384,9 @@ def upload_to_frigate(jobs: list[dict]) -> None:
                     # freed slot isn't filled with something worse than what we removed.
                     if min_quality_score_for_slot is not None:
                         file_score = score_map.get(fname)
-                        if file_score is not None and file_score <= min_quality_score_for_slot:
+                        if file_score is not None and file_score < min_quality_score_for_slot:
                             progress.console.print(
-                                f"    [dim]⏭  {fname}: score {file_score:.3f} ≤ freed slot floor"
+                                f"    [dim]⏭  {fname}: score {file_score:.3f} < freed slot floor"
                                 f" {min_quality_score_for_slot:.3f}, skipping[/dim]"
                             )
                             progress.advance(upload_task)
@@ -566,13 +566,14 @@ def upload_to_frigate(jobs: list[dict]) -> None:
                                     error_detail = resp.json().get("message", full_body[:100])
                                 except Exception:
                                     error_detail = full_body[:100]
-                                if resp.status_code == 400:
+                                if resp.status_code in (400, 500):
                                     progress.console.print(f"      [dim]{error_detail}[/dim]")
                                 else:
                                     logger.debug("%s HTTP %s: %s", fname, resp.status_code, error_detail)
                                 _is_permanent = (
                                     (resp.status_code == 400 and "face" in full_body.lower())
                                     or resp.status_code == 422
+                                    or (resp.status_code == 500 and "could not process" in full_body.lower())
                                 )
                                 if _is_permanent:
                                     asset_id = asset_map.get(fname)

winnow/frigate_api.py

@@ -146,8 +146,10 @@ def delete_frigate_person_files(person_name: str, filenames: list[str]) -> bool:
     Returns True on success, False if unreachable or the request fails.
     """
     frigate_url = _get_frigate_url()
-    if not frigate_url or not filenames:
+    if not frigate_url:
         return False
+    if not filenames:
+        return True
     from urllib.parse import quote
     encoded_name = quote(person_name, safe="")
     try:

winnow/image_processing.py

@@ -48,6 +48,8 @@ def align_face(img: Image.Image, landmarks: list[list[float]] | np.ndarray) -> I
         if lm.shape != (5, 2):
             logger.debug("Invalid landmark shape: %s, expected (5, 2)", lm.shape)
             return None
+        with warnings.catch_warnings():
+            warnings.filterwarnings("ignore", message=".*estimate.*is deprecated", category=FutureWarning)
             aligned = norm_crop(img_np, lm)
         return Image.fromarray(aligned)
     except ImportError:
@@ -66,10 +68,11 @@ def process_face_mode(
     count: int,
     min_width: int | None = None,
     insightface_app=None,
-) -> tuple[int, int] | None:
+) -> tuple[int, int] | str:
     """Crop face based on Immich metadata and save to output directory.
 
-    Returns (width, height) of the saved crop, or None if no crop was saved.
+    Returns (width, height) of the saved crop, or a skip-reason string if the
+    face was filtered out.
     When insightface_app is provided and ENABLE_FACE_ALIGNMENT is True,
     re-detects the face in the Immich bbox region using InsightFace to get
     precise landmarks for a proper 112x112 aligned crop. Falls back to
@@ -89,7 +92,7 @@ def process_face_mode(
 
     if not face_info:
         logger.debug("No face info for %s in asset %s", person.get("name"), asset.get("id"))
-        return None
+        return "no face metadata"
 
     img_w, img_h = img.size
     meta_w = face_info.get("imageWidth") or 0
@@ -108,7 +111,7 @@ def process_face_mode(
     face_w, face_h = x2 - x1, y2 - y1
     if face_w < min_width or face_h < min_width:
         logger.debug("Face too small (%.1fx%.1f)", face_w, face_h)
-        return None
+        return f"face too small ({face_w:.0f}x{face_h:.0f}px, min {min_width}px)"
 
     # Re-detect face with InsightFace for landmark-based alignment.
     # Immich's /api/faces endpoint does not include landmarks, so the

winnow/immich_api.py

@@ -134,7 +134,7 @@ def fetch_all_assets(person: dict) -> tuple[list[dict], int]:
             # Immich ≥2.x returns {"assets": {"items": [...]}};
             # earlier versions returned {"assets": [...]} directly.
             if isinstance(page_assets, dict):
-                page_assets = page_assets.get("items", [])
+                page_assets = page_assets.get("items") or []
 
             page_count = len(page_assets)  # raw count for termination check before filtering
 
@@ -303,7 +303,7 @@ def filter_recent_assets(assets: list[dict], years: int | None = None) -> list[d
                 recent.append(asset)
             else:
                 skipped += 1
-        except ValueError:
+        except (ValueError, TypeError):
             bad_timestamp += 1
             continue
 

winnow/jobs.py

@@ -86,7 +86,11 @@ def _resolve_strategy(strategy: str, has_embedding: bool) -> tuple[int | str, st
         "standard": (30, "smart"),
         "broad": (100, "smart"),
     }
-    return strategy_map.get(strategy, ("auto", "smart"))
+    result = strategy_map.get(strategy)
+    if result is None:
+        logger.warning("Unrecognised STRATEGY=%r — falling back to auto", strategy)
+        return ("auto", "smart")
+    return result
 
 
 def _perform_selection(
@@ -244,13 +248,13 @@ def auto_configure(people: list[dict]) -> list[dict]:
         return []
 
     strategy = os.environ.get("STRATEGY", "auto")
-    skip = [s.strip() for s in os.environ.get("SKIP_PEOPLE", "").split(",") if s.strip()]
+    skip = {s.strip().casefold() for s in os.environ.get("SKIP_PEOPLE", "").split(",") if s.strip()}
-    only = [s.strip() for s in os.environ.get("ONLY_PEOPLE", "").split(",") if s.strip()]
+    only = {s.strip().casefold() for s in os.environ.get("ONLY_PEOPLE", "").split(",") if s.strip()}
 
     if only:
-        valid_people = [p for p in valid_people if p["name"] in only]
+        valid_people = [p for p in valid_people if p["name"].casefold() in only]
     if skip:
-        valid_people = [p for p in valid_people if p["name"] not in skip]
+        valid_people = [p for p in valid_people if p["name"].casefold() not in skip]
 
     min_face_count = Config.MIN_FACE_COUNT