release: merge dev → main for 0.4.1

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

CHANGELOG.md

@@ -7,6 +7,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.4.1] - 2026-06-13
+
+### Fixed
+
+- **`RESET_PERSON` no longer creates duplicate Frigate files**: previously, resetting a person only wiped the local tracker — existing Frigate training files were left as unmanaged orphans, causing the next run to upload a full new batch on top of them. `reset_person` now deletes all winnow-managed files for that person from Frigate before clearing the tracker. Manually-added Frigate files are unaffected.
+- **No spurious warning when `FRIGATE_URL` is unset and `RESET_PERSON` is used**: the deletion step is now skipped silently at info level rather than logging a misleading "could not delete" warning.
+
 ## [0.4.0] - 2026-06-13
 
 ### Added

README.md

@@ -11,6 +11,8 @@
 
 Frigate's face recognition is only as good as its training data — and the key quality metric is **diversity**, not volume. A hundred photos from the same week teach the model one lighting condition. What you need is a spread: different years, different angles, different lighting, different contexts. Your photo library already has that data. winnow finds and delivers the right subset automatically.
 
+> **winnow only touches files it uploaded.** Faces added to Frigate manually through its UI are never deleted, replaced, or modified — not by quality replacement, not by `RESET_PERSON`, not by stale cleanup. If you have a curated training set you want to keep, it is safe.
+
 ---
 
 ## How It Works
@@ -222,7 +224,7 @@ In scheduled mode the process (and loaded models) stays resident between runs. T
 | :--- | :--- | :--- |
 | `DRY_RUN` | `false` | Preview selection without downloading or uploading |
 | `RETRY_REJECTED` | `false` | Re-attempt assets previously rejected by Frigate |
-| `RESET_PERSON` | *(unset)* | Clear upload and rejection history for one person by name |
+| `RESET_PERSON` | *(unset)* | Clear upload history for one person and delete their winnow-managed Frigate training files so the next run starts fresh. Manually added Frigate files are never touched |
 
 ### Scheduling
 

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "winnow"
-version = "0.4.0"
+version = "0.4.1"
 description = "Selects diverse, high-quality photos from Immich as training data for Frigate face recognition and object classification."
 license = "AGPL-3.0-or-later"
 requires-python = ">=3.13"

uv.lock

@@ -2348,7 +2348,7 @@ wheels = [
 
 [[package]]
 name = "winnow"
-version = "0.3.3"
+version = "0.4.0"
 source = { editable = "." }
 dependencies = [
     { name = "croniter" },

winnow/executor.py

@@ -13,7 +13,12 @@ from rich import print as rprint
 from rich.progress import BarColumn, Progress, SpinnerColumn, TaskProgressColumn, TextColumn
 
 from .config import Config, get_headers
-from .frigate_api import delete_frigate_person_files, get_all_frigate_person_files, get_frigate_person_files, recognize_face
+from .frigate_api import (
+    delete_frigate_person_files,
+    get_all_frigate_person_files,
+    get_frigate_person_files,
+    recognize_face,
+)
 from .image_processing import process_face_mode, process_full_mode, process_object_mode
 from .immich_api import fetch_face_data, fetch_full_image
 from .log_config import console
@@ -395,6 +400,7 @@ def upload_to_frigate(jobs: list[dict]) -> None:
             actually_uploaded: list[tuple[str, str | None]] = []
             failed_deletes: set[str] = set()
             min_quality_score_for_slot: float | None = None
+            person_has_fscores: bool = has_frigate_scores(name)
 
             for fname in person_files:
                 fpath = os.path.join(person_dir, fname)
@@ -427,9 +433,9 @@ def upload_to_frigate(jobs: list[dict]) -> None:
                 # handles this conservatively by skipping that candidate until the next run.
                 pre_fscore: float | None = None
                 if Config.ENABLE_FRIGATE_SCORES and pre_run_count > 0:
-                    if not at_cap or has_frigate_scores(name):
+                    if not at_cap or person_has_fscores:
                         _result = recognize_face(fpath)
-                        if _result is not None and _result[0] == name:
+                        if _result is not None and (_result[0] or "").casefold() == name.casefold():
                             pre_fscore = _result[1]
 
                 # Ceiling check: skip if the existing training set already covers this
@@ -450,7 +456,7 @@ def upload_to_frigate(jobs: list[dict]) -> None:
                         progress.advance(upload_task)
                         continue
 
-                    using_fscore = has_frigate_scores(name) and Config.ENABLE_FRIGATE_SCORES
+                    using_fscore = person_has_fscores and Config.ENABLE_FRIGATE_SCORES
                     if using_fscore:
                         candidate_score = pre_fscore
                         if candidate_score is None:
@@ -476,8 +482,10 @@ def upload_to_frigate(jobs: list[dict]) -> None:
                         )
                         if delete_frigate_person_files(name, [target_frigate_file]):
                             remove_frigate_file(name, target_frigate_file)
+                            person_has_fscores = has_frigate_scores(name)
                             effective_count -= 1
-                            min_quality_score_for_slot = None  # clear any blur-mode slot floor — Frigate uses a different score metric
+                            # clear any blur-mode slot floor — Frigate uses a different score metric
+                            min_quality_score_for_slot = None
                         else:
                             logger.warning(f"Failed to delete {target_frigate_file} for {name}, skipping replacement")
                             failed_deletes.add(target_frigate_file)
@@ -507,6 +515,7 @@ def upload_to_frigate(jobs: list[dict]) -> None:
                         )
                         if delete_frigate_person_files(name, [target_frigate_file]):
                             remove_frigate_file(name, target_frigate_file)
+                            person_has_fscores = has_frigate_scores(name)
                             effective_count -= 1
                             min_quality_score_for_slot = score_map.get(fname)
                         else:
@@ -538,6 +547,8 @@ def upload_to_frigate(jobs: list[dict]) -> None:
                                     crop_dims=dims_map.get(fname),
                                     frigate_score=pre_fscore,
                                 )
+                                if pre_fscore is not None:
+                                    person_has_fscores = True
                                 actually_uploaded.append((fname, asset_id))
 
                             break

winnow/frigate_api.py

@@ -22,24 +22,6 @@ def _get_faces_data() -> dict | None:
         return None
 
 
-def get_frigate_face_counts() -> dict[str, int] | None:
-    """Return {person_name: training_image_count} from Frigate's train directory.
-
-    Returns None if FRIGATE_URL is not set or the API is unreachable, so callers
-    can distinguish "API unavailable" from "person has 0 images."
-    """
-    data = _get_faces_data()
-    if data is None:
-        return None
-    # Response: {person_name: [file, ...], "train": [...], ...}
-    # "train" is a flat pending list, not a person — skip it.
-    return {
-        name: len(files)
-        for name, files in data.items()
-        if name != "train" and isinstance(files, list)
-    }
-
-
 def get_all_frigate_person_files() -> dict[str, list[str]] | None:
     """Return {person_name: [filename, ...]} for every person in Frigate.
 
@@ -49,6 +31,8 @@ def get_all_frigate_person_files() -> dict[str, list[str]] | None:
     data = _get_faces_data()
     if data is None:
         return None
+    # Response: {person_name: [file, ...], "train": [...], ...}
+    # "train" is a flat pending list, not a person — skip it.
     return {
         name: files
         for name, files in data.items()
@@ -56,6 +40,18 @@ def get_all_frigate_person_files() -> dict[str, list[str]] | None:
     }
 
 
+def get_frigate_face_counts() -> dict[str, int] | None:
+    """Return {person_name: training_image_count} from Frigate's train directory.
+
+    Returns None if FRIGATE_URL is not set or the API is unreachable, so callers
+    can distinguish "API unavailable" from "person has 0 images."
+    """
+    all_files = get_all_frigate_person_files()
+    if all_files is None:
+        return None
+    return {name: len(files) for name, files in all_files.items()}
+
+
 def get_frigate_person_files(person_name: str) -> list[str] | None:
     """Return the list of training filenames for a person in Frigate.
 

winnow/upload_tracker.py

@@ -29,8 +29,11 @@ Frigate's UI are never mapped here and are never touched by quality replacement.
 
 import json
 import logging
+import os
 from pathlib import Path
 
+from .frigate_api import delete_frigate_person_files
+
 logger = logging.getLogger(__name__)
 
 UPLOAD_TRACKER_FILE = "frigate_uploaded_ids.json"
@@ -167,7 +170,9 @@ def remove_frigate_file(person_name: str, frigate_filename: str) -> None:
     data = _load(UPLOAD_TRACKER_FILE)
     by_person = data.get("by_person", {})
     entry = _migrate_entry(by_person.get(person_name, {}))
-    entry["frigate_files"].pop(frigate_filename, None)
+    asset_id = entry["frigate_files"].pop(frigate_filename, None)
+    if asset_id:
+        entry["frigate_scores"].pop(asset_id, None)
     by_person[person_name] = entry
     _save(UPLOAD_TRACKER_FILE, data)
     logger.debug(f"Removed Frigate file mapping {frigate_filename} ({person_name})")
@@ -204,6 +209,22 @@ def has_frigate_scores(person_name: str) -> bool:
     return any(asset_id in frigate_scores for asset_id in frigate_files.values())
 
 
+def _pick_mapped_file(
+    person_name: str, score_key: str, *, highest: bool, exclude: set[str] | None = None
+) -> tuple[str, str, float] | None:
+    data = _load(UPLOAD_TRACKER_FILE)
+    entry = _migrate_entry(data.get("by_person", {}).get(person_name, {}))
+    scores = entry.get(score_key, {})
+    candidates = [
+        (ff, asset_id, scores[asset_id])
+        for ff, asset_id in entry.get("frigate_files", {}).items()
+        if (exclude is None or ff not in exclude) and asset_id in scores
+    ]
+    if not candidates:
+        return None
+    return max(candidates, key=lambda x: x[2]) if highest else min(candidates, key=lambda x: x[2])
+
+
 def get_lowest_quality_mapped_file(
     person_name: str, exclude: set[str] | None = None
 ) -> tuple[str, str, float] | None:
@@ -213,21 +234,7 @@ def get_lowest_quality_mapped_file(
     Used for quality replacement when no Frigate scores are available.
     Pass `exclude` to skip files that failed to delete this run.
     """
-    data = _load(UPLOAD_TRACKER_FILE)
-    entry = _migrate_entry(data.get("by_person", {}).get(person_name, {}))
-    frigate_files = entry.get("frigate_files", {})
-    blur_scores = entry.get("scores", {})
-
-    candidates = [
-        (ff, asset_id, blur_scores[asset_id])
-        for ff, asset_id in frigate_files.items()
-        if (exclude is None or ff not in exclude)
-        and asset_id in blur_scores
-    ]
-
-    if not candidates:
-        return None
-    return min(candidates, key=lambda x: x[2])
+    return _pick_mapped_file(person_name, "scores", highest=False, exclude=exclude)
 
 
 def get_most_redundant_mapped_file(
@@ -240,21 +247,7 @@ def get_most_redundant_mapped_file(
     = the most redundant file and therefore the best replacement target.
     Pass `exclude` to skip files that failed to delete this run.
     """
-    data = _load(UPLOAD_TRACKER_FILE)
-    entry = _migrate_entry(data.get("by_person", {}).get(person_name, {}))
-    frigate_files = entry.get("frigate_files", {})
-    frigate_scores = entry.get("frigate_scores", {})
-
-    candidates = [
-        (ff, asset_id, frigate_scores[asset_id])
-        for ff, asset_id in frigate_files.items()
-        if (exclude is None or ff not in exclude)
-        and asset_id in frigate_scores
-    ]
-
-    if not candidates:
-        return None
-    return max(candidates, key=lambda x: x[2])
+    return _pick_mapped_file(person_name, "frigate_scores", highest=True, exclude=exclude)
 
 
 def get_frigate_filename_for_asset(person_name: str, asset_id: str) -> str | None:
@@ -307,19 +300,41 @@ def update_frigate_count(person_name: str, count: int) -> None:
 
 
 def reset_person(person_name: str) -> None:
-    """Remove all uploaded and rejected records for a given person."""
-    for filename in (UPLOAD_TRACKER_FILE, REJECT_TRACKER_FILE):
-        data = _load(filename)
+    """Remove all uploaded and rejected records for a given person.
+
+    Also deletes winnow-managed Frigate training files so the next run starts
+    clean rather than uploading on top of orphaned files. Manually-added Frigate
+    files (not in frigate_files) are never touched. Proceeds with tracker reset
+    even if Frigate is unreachable.
+    """
+    upload_data = _load(UPLOAD_TRACKER_FILE)
+    entry = _migrate_entry(upload_data.get("by_person", {}).get(person_name, {}))
+    frigate_filenames = list(entry.get("frigate_files", {}).keys())
+    if frigate_filenames:
+        if not os.environ.get("FRIGATE_URL", "").strip():
+            logger.info(f"FRIGATE_URL not set — skipping Frigate file deletion for {person_name}")
+        elif delete_frigate_person_files(person_name, frigate_filenames):
+            logger.info(f"Deleted {len(frigate_filenames)} Frigate file(s) for {person_name}")
+        else:
+            logger.warning(f"Could not delete Frigate files for {person_name} — tracker reset proceeding anyway")
+
+    changed = False
+    tracker_files = ((UPLOAD_TRACKER_FILE, upload_data), (REJECT_TRACKER_FILE, _load(REJECT_TRACKER_FILE)))
+    for filename, data in tracker_files:
         flat_key = _flat_key(filename)
         by_person = data.get("by_person", {})
-        entry = by_person.pop(person_name, None)
-        if entry is not None:
-            person_ids = set(_get_ids(entry))
+        tracker_entry = by_person.pop(person_name, None)
+        if tracker_entry is not None:
+            person_ids = set(_get_ids(tracker_entry))
             flat = set(data.get(flat_key, [])) - person_ids
             data[flat_key] = sorted(flat)
             data["by_person"] = by_person
             _save(filename, data)
-    logger.info(f"Reset tracking data for {person_name}")
+            changed = True
+    if changed:
+        logger.info(f"Reset tracking data for {person_name}")
+    else:
+        logger.debug(f"reset_person: no tracking data found for {person_name}")
 
 
 def get_person_summary() -> dict[str, dict]: