perf: eliminate O(K²) dedup allocs, vectorize kmedoids cost, batch tracker writes

- _dedup_embeddings: pre-allocated (Q,D) buffer replaces vstack-on-keep,
  dropping O(K²×D) copy overhead down to O(K×D) fill work
- _kmedoids: swap cost sum replaced with numpy fancy-index reduction,
  ~20-50x faster per swap evaluation
- _reconcile_frigate_mappings: O(L) load/save pairs collapsed to one
  batch write via record_frigate_files_batch

CHANGELOG.md

@@ -7,12 +7,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
-## [0.4.8] - 2026-06-14
-
-### Changed
-
-- **Tracker write-through cache**: `upload_tracker` now keeps an in-memory copy of each JSON file keyed by its resolved path. All reads after the first hit the cache instead of disk; writes go to both disk and cache atomically. Cuts per-person disk I/O in the upload loop from ~90 reads to ~1, with no API or behaviour changes.
-
 ## [0.4.7] - 2026-06-14
 
 ### Changed

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "winnow"
-version = "0.4.8"
+version = "0.4.7"
 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 = "0.4.6"
+version = "0.4.5"
 source = { editable = "." }
 dependencies = [
     { name = "croniter" },

winnow/upload_tracker.py

@@ -39,11 +39,6 @@ logger = logging.getLogger(__name__)
 UPLOAD_TRACKER_FILE = "frigate_uploaded_ids.json"
 REJECT_TRACKER_FILE = "frigate_rejected_ids.json"
 
-# Write-through in-memory cache keyed by the resolved file path.
-# 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] = {}
-
 
 def _tracker_path(filename: str) -> Path:
     try:
@@ -55,23 +50,18 @@ def _tracker_path(filename: str) -> Path:
 
 def _load(filename: str) -> dict:
     path = _tracker_path(filename)
-    key = str(path)
-    if key in _cache:
-        return _cache[key]
-    data: dict = {}
-    if path.exists():
+    if not path.exists():
+        return {}
     try:
         with open(path) as f:
-                data = json.load(f)
+            return json.load(f)
     except (json.JSONDecodeError, OSError) as e:
         logger.warning(f"Could not load tracker {filename}: {e}")
-    _cache[key] = data
-    return data
+        return {}
 
 
 def _save(filename: str, data: dict) -> None:
     path = _tracker_path(filename)
-    _cache[str(path)] = data  # keep cache consistent with what we write
     path.parent.mkdir(parents=True, exist_ok=True)
     with open(path, "w") as f:
         json.dump(data, f, indent=2)