fix: v0.6.2 — structural tracker refactor, batch writes, multi-instance prep

- Drop flat list as primary storage; derive uploaded/rejected IDs from by_person
  (single source of truth). Legacy flat lists in existing files still read for
  backward compat. Removes dual-representation sync hazard.
- Add begin_batch/flush_batch: per-person upload loop now does 1 os.replace
  instead of N (one per mark_uploaded call). Benefit on slow storage.
- reset_all_people(): RESET_PERSON=* is now O(1) disk writes instead of O(P^2).
- blur_score_from_image inlines cv2.Laplacian directly, removing assess_quality
  call overhead and decoupling from the full quality pipeline.

CHANGELOG.md

@@ -7,6 +7,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.6.2] - 2026-06-16
+
+### Changed
+
+- **Flat `uploaded_asset_ids` / `rejected_asset_ids` lists dropped as primary storage**: asset IDs are now derived on read from `by_person` entries, which are the single source of truth. The legacy flat lists in existing tracker files are still read (union) so no assets become re-eligible after upgrading. New writes no longer maintain the flat lists. This removes the dual-representation sync hazard and paves the way for multi-instance support (per-instance `by_person` keying in a future release).
+
+- **Tracker writes batched per person**: `mark_uploaded` calls inside the per-person upload loop are now accumulated in memory (`begin_batch`) and flushed in a single `os.replace` write at the end of each person's loop (`flush_batch`), reducing N tracker writes per person to 1. Benefits users on slow storage (NAS, SD card, spinning disks).
+
+- **`RESET_PERSON=*` is now O(1) disk writes**: replaced the per-person `reset_person` loop with `reset_all_people()`, which makes one Frigate API call per person for file deletion and then clears both tracker files in two writes. Previously it was O(P²) iterations and 2P writes.
+
+- **`blur_score_from_image` inlines Laplacian computation**: replaced the `assess_quality()` call (which ran grayscale, exposure, and confidence checks whose results were discarded) with a direct `cv2.Laplacian` computation. The function is now self-contained and does not silently inherit future costs added to the full quality pipeline.
+
 ## [0.6.1] - 2026-06-16
 
 ### Fixed

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "winnow"
-version = "0.6.1"
+version = "0.6.2"
 description = "Selects diverse, high-quality photos from Immich as training data for Frigate face recognition."
 license = "AGPL-3.0-or-later"
 requires-python = ">=3.13"

uv.lock

@@ -862,7 +862,7 @@ wheels = [
 
 [[package]]
 name = "winnow"
-version = "0.6.0"
+version = "0.6.1"
 source = { editable = "." }
 dependencies = [
     { name = "croniter" },

winnow/cli.py

@@ -12,7 +12,7 @@ from .executor import execute_jobs, upload_to_frigate
 from .immich_api import get_immich_version, get_people, merge_people
 from .jobs import _show_preview, auto_configure, interactive_configure
 from .log_config import console, setup_logging
-from .upload_tracker import find_by_crop_dimension, get_person_summary, reset_person
+from .upload_tracker import find_by_crop_dimension, get_person_summary, reset_all_people, reset_person
 
 logger = logging.getLogger(__name__)
 
@@ -207,8 +207,7 @@ def main() -> None:
                         "and will be reset along with everyone else.[/yellow]"
                     )
                 if names:
-                    for name in names:
-                        reset_person(name)
+                    reset_all_people()
                     rprint(f"[bold yellow]Reset tracking data for all {len(names)} people.[/bold yellow]")
                 else:
                     rprint("[dim]No tracking data to reset.[/dim]")

winnow/executor.py

@@ -34,6 +34,8 @@ from .upload_tracker import (
     has_frigate_scores,
     mark_rejected,
     mark_uploaded,
+    begin_batch,
+    flush_batch,
     remove_frigate_file,
     remove_frigate_files_batch,
 )
@@ -364,6 +366,7 @@ def upload_to_frigate(jobs: list[dict]) -> None:
             min_quality_score_for_slot: float | None = None
             person_has_fscores: bool = has_frigate_scores(name)
 
+            begin_batch(UPLOAD_TRACKER_FILE)
             for fname in person_files:
                 fpath = os.path.join(person_dir, fname)
 
@@ -590,6 +593,8 @@ def upload_to_frigate(jobs: list[dict]) -> None:
                     " was not filled this run — will be available next run"
                 )
 
+            flush_batch(UPLOAD_TRACKER_FILE)
+
             # Batch-map Frigate filenames to asset IDs now that all uploads are done.
             if actually_uploaded and not _skip_reconcile:
                 reconcile_frigate_mappings(name, known_frigate_files_at_start, actually_uploaded)

winnow/quality.py

@@ -154,7 +154,8 @@ def blur_score_from_image(img: Image.Image, max_dim: int = 1440) -> float | None
         if score_img.width > max_dim or score_img.height > max_dim:
             score_img = score_img.copy()
             score_img.thumbnail((max_dim, max_dim), Image.LANCZOS)
-        return float(assess_quality(score_img).blur_score)
+        gray = cv2.cvtColor(np.array(score_img), cv2.COLOR_RGB2GRAY)
+        return float(cv2.Laplacian(gray, cv2.CV_64F).var())
     except Exception as exc:
         logger.debug("blur_score_from_image failed: %s", exc)
         return None

winnow/upload_tracker.py

@@ -43,6 +43,7 @@ REJECT_TRACKER_FILE = "frigate_rejected_ids.json"
 # Reduces per-call JSON reads from O(calls) to O(1) after the first load.
 # Keyed by full path so tests with isolated tmp dirs never share entries.
 _cache: dict[str, dict] = {}
+_deferred: set[str] = set()  # paths whose disk writes are batched until flush_batch()
 
 
 def _tracker_path(filename: str) -> Path:
@@ -69,28 +70,48 @@ def _load(filename: str) -> dict:
     return data
 
 
-def _save(filename: str, data: dict) -> None:
-    path = _tracker_path(filename)
+def _write_to_disk(path: Path, data: dict) -> None:
     path.parent.mkdir(parents=True, exist_ok=True)
     tmp = path.with_suffix(".tmp")
     try:
         with open(tmp, "w") as f:
             json.dump(data, f, indent=2)
         os.replace(tmp, path)
-        _cache[str(path)] = data  # update only after the file is safely on disk
     except Exception:
         tmp.unlink(missing_ok=True)
         raise
 
 
+def _save(filename: str, data: dict) -> None:
+    path = _tracker_path(filename)
+    key = str(path)
+    if key in _deferred:
+        _cache[key] = data  # accumulate in cache; disk write deferred until flush_batch()
+        return
+    _write_to_disk(path, data)
+    _cache[key] = data  # update cache only after successful write
+
+
+def begin_batch(filename: str) -> None:
+    """Defer tracker disk writes for filename. All _save calls accumulate in the
+    in-memory cache until flush_batch() is called. Use around per-person upload loops
+    to reduce N writes to 1."""
+    _deferred.add(str(_tracker_path(filename)))
+
+
+def flush_batch(filename: str) -> None:
+    """Write the accumulated cache state for filename to disk."""
+    path = _tracker_path(filename)
+    key = str(path)
+    _deferred.discard(key)
+    if key in _cache:
+        _write_to_disk(path, _cache[key])
+
+
 def _flat_key(filename: str) -> str:
     return "uploaded_asset_ids" if filename == UPLOAD_TRACKER_FILE else "rejected_asset_ids"
 
 
-def _load_flat(filename: str) -> set[str]:
-    return set(_load(filename).get(_flat_key(filename), []))
-
-
 def _get_ids(entry: list | dict) -> list[str]:
     """Extract asset_ids from either the old list format or the new dict format."""
     if isinstance(entry, list):
@@ -121,10 +142,6 @@ def _mark(
     frigate_score: float | None = None,
 ) -> None:
     data = _load(filename)
-    flat_key = _flat_key(filename)
-    flat = set(data.get(flat_key, []))
-    flat.add(asset_id)
-    data[flat_key] = sorted(flat)
     if person_name:
         by_person = data.setdefault("by_person", {})
         entry = _migrate_entry(by_person.get(person_name, {}))
@@ -144,11 +161,21 @@ def _mark(
 # ── Public API ────────────────────────────────────────────────────────────────
 
 def load_uploaded_ids() -> set[str]:
-    return _load_flat(UPLOAD_TRACKER_FILE)
+    """Return all asset IDs recorded as uploaded. Derives from by_person (primary)
+    plus any legacy flat list still present in old tracker files."""
+    data = _load(UPLOAD_TRACKER_FILE)
+    ids = {aid for e in data.get("by_person", {}).values() for aid in _get_ids(e)}
+    ids.update(data.get("uploaded_asset_ids", []))  # backward compat with pre-0.6.1 files
+    return ids
 
 
 def load_rejected_ids() -> set[str]:
-    return _load_flat(REJECT_TRACKER_FILE)
+    """Return all asset IDs recorded as rejected. Derives from by_person (primary)
+    plus any legacy flat list still present in old tracker files."""
+    data = _load(REJECT_TRACKER_FILE)
+    ids = {aid for e in data.get("by_person", {}).values() for aid in _get_ids(e)}
+    ids.update(data.get("rejected_asset_ids", []))  # backward compat with pre-0.6.1 files
+    return ids
 
 
 def mark_uploaded(
@@ -327,6 +354,29 @@ def update_frigate_count(person_name: str, count: int) -> None:
     _save(UPLOAD_TRACKER_FILE, data)
 
 
+def reset_all_people() -> None:
+    """Reset all tracking data in two writes (O(P) Frigate API calls, O(1) disk writes).
+
+    Preferred over calling reset_person() in a loop when RESET_PERSON=* — that
+    approach is O(P²) because each call rebuilds the flat list from all remaining entries.
+    """
+    upload_data = _load(UPLOAD_TRACKER_FILE)
+    for person_name, raw_entry in upload_data.get("by_person", {}).items():
+        entry = _migrate_entry(raw_entry)
+        frigate_filenames = list(entry.get("frigate_files", {}).keys())
+        if not frigate_filenames:
+            continue
+        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")
+    _save(UPLOAD_TRACKER_FILE, {})
+    _save(REJECT_TRACKER_FILE, {})
+    logger.info("Reset all tracking data")
+
+
 def reset_person(person_name: str) -> None:
     """Remove all uploaded and rejected records for a given person.
 
@@ -347,18 +397,15 @@ def reset_person(person_name: str) -> None:
             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)
+    for filename in (UPLOAD_TRACKER_FILE, REJECT_TRACKER_FILE):
+        data = upload_data if filename == UPLOAD_TRACKER_FILE else _load(REJECT_TRACKER_FILE)
         by_person = data.get("by_person", {})
         tracker_entry = by_person.pop(person_name, None)
         if tracker_entry is not None:
-            # Rebuild from remaining entries rather than subtracting, so IDs that
-            # appear under another person aren't incorrectly removed from the flat list.
-            remaining_ids: set[str] = set()
-            for other_entry in by_person.values():
-                remaining_ids.update(_get_ids(other_entry))
-            data[flat_key] = sorted(remaining_ids)
+            flat_key = _flat_key(filename)
+            person_ids = set(_get_ids(tracker_entry))
+            if person_ids and flat_key in data:
+                data[flat_key] = sorted(set(data[flat_key]) - person_ids)
             data["by_person"] = by_person
             _save(filename, data)
             changed = True