release: v0.5.15 — fix cache regression and structural cleanup

- cache.py: fix np.save extension bug from v0.5.13 — tmp path used
  final+".tmp" (abc.npy.tmp) but np.save auto-appends .npy to paths not
  ending in .npy, writing to abc.npy.tmp.npy instead; os.replace then
  raised FileNotFoundError silently, making every cache write a no-op
  and leaking *.npy.tmp.npy files. Fixed by inserting .tmp before .npy:
  tmp = final[:-4] + ".tmp.npy"

- config.py: remove str(default) round-trip in _getenv_int/_getenv_float
  — use raw = os.getenv(name); return default if raw is None else int(raw)
  so a future float default can't cause a spurious "not a valid integer"
  warning and return the wrong type

- executor.py: consolidate 4 progress.remove_task calls into one
  try/finally around the per-job body; continue inside try/finally
  executes the finally before the next iteration, making the invariant
  structurally enforced rather than relying on discipline across 4 sites

CHANGELOG.md

@@ -7,6 +7,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.5.15] - 2026-06-15
+
+### Fixed
+
+- **Embedding cache writes were silently no-ops since v0.5.13**: the atomic-write path used `tmp = final + ".tmp"` where `final` ends in `.npy` (e.g. `abc.npy`), producing a tmp path of `abc.npy.tmp`. `np.save` auto-appends `.npy` to paths not already ending in `.npy`, so it wrote to `abc.npy.tmp.npy` instead. The subsequent `os.replace("abc.npy.tmp", "abc.npy")` then raised `FileNotFoundError` (caught silently at DEBUG), meaning no cache entry was ever committed and leaked `*.npy.tmp.npy` files accumulated on disk. The fix inserts `.tmp` before the `.npy` extension: `tmp = final[:-4] + ".tmp.npy"` so `np.save` sees a path already ending in `.npy` and does not re-append.
+
+- **`_getenv_int`/`_getenv_float` no longer route the default through `str()` conversion**: the previous form `os.getenv(name, str(default))` converted the default to a string so it could be fed through `int()`/`float()` — an unnecessary round-trip that would cause `_getenv_int("FOO", 4.0)` to log a spurious "not a valid integer" warning and return the float. The helpers now use `raw = os.getenv(name); return default if raw is None else int(raw)`, passing the typed default through directly.
+
+- **`execute_jobs` progress task now removed via `try/finally`**: `progress.remove_task(job_task)` was duplicated in three early-exit paths (ValueError, symlink TOCTOU, OSError) plus once at normal completion. The entire per-job body is now wrapped in `try/finally: progress.remove_task(job_task)`; the three inner `continue` statements trigger the `finally` automatically before advancing to the next job, making the invariant structurally impossible to violate by a future code path.
+
 ## [0.5.14] - 2026-06-15
 
 ### Fixed

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "winnow"
-version = "0.5.14"
+version = "0.5.15"
 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"

winnow/cache.py

@@ -83,7 +83,9 @@ class EmbeddingCache:
         """Store an embedding in the cache."""
         self._ensure_dir()
         final = self._path(asset_id, model)
-        tmp = final + ".tmp"
+        # Insert .tmp before .npy so np.save doesn't auto-append another .npy extension
+        # (np.save appends .npy to paths that don't already end in .npy).
+        tmp = final[:-4] + ".tmp.npy"
         try:
             np.save(tmp, embedding)
             os.replace(tmp, final)

winnow/config.py

@@ -13,20 +13,24 @@ _LEGACY_CONFIG_FILE = Path(".immich_config.json")  # pre-v0.6: lived in process
 
 
 def _getenv_int(name: str, default: int) -> int:
-    val = os.getenv(name, str(default))
+    raw = os.getenv(name)
+    if raw is None:
+        return default
     try:
-        return int(val)
+        return int(raw)
     except ValueError:
-        logging.warning("%s=%r is not a valid integer — using default %s", name, val, default)
+        logging.warning("%s=%r is not a valid integer — using default %s", name, raw, default)
         return default
 
 
 def _getenv_float(name: str, default: float) -> float:
-    val = os.getenv(name, str(default))
+    raw = os.getenv(name)
+    if raw is None:
+        return default
     try:
-        return float(val)
+        return float(raw)
     except ValueError:
-        logging.warning("%s=%r is not a valid float — using default %s", name, val, default)
+        logging.warning("%s=%r is not a valid float — using default %s", name, raw, default)
         return default
 
 

winnow/executor.py

@@ -101,18 +101,17 @@ def execute_jobs(jobs: list[dict]) -> None:
             name = person["name"]
 
             job_task = progress.add_task(f"Processing {name}...", total=len(assets))
+            try:
                 try:
                     person_dir = _safe_person_dir(Config.OUTPUT_DIR, name)
                 except ValueError as e:
                     logger.error(str(e))
-                progress.remove_task(job_task)
                     continue
                 # Face crops are transient (uploaded then discarded); wipe before each run.
                 # A symlink could appear here via a TOCTOU race after _safe_person_dir
                 # returned — writing through it would land crops outside output_dir.
                 if os.path.islink(person_dir):
                     logger.error("person_dir %s became a symlink after path check — skipping job", person_dir)
-                progress.remove_task(job_task)
                     continue
                 try:
                     if os.path.isdir(person_dir):
@@ -120,7 +119,6 @@ def execute_jobs(jobs: list[dict]) -> None:
                     os.makedirs(person_dir, exist_ok=True)
                 except OSError as e:
                     logger.error("Failed to prepare output dir for %s: %s", name, e)
-                progress.remove_task(job_task)
                     continue
 
                 # Track filename → asset_id, filename → confidence score, filename → crop dims
@@ -209,11 +207,11 @@ def execute_jobs(jobs: list[dict]) -> None:
                 job["score_map"] = score_map
                 job["dims_map"] = dims_map
 
-            progress.remove_task(job_task)
-
                 # Log how many images were actually saved vs selected
                 if count < len(assets):
                     logger.info("%s: saved %s/%s selected images", name, count, len(assets))
+            finally:
+                progress.remove_task(job_task)
 
 
 def upload_to_frigate(jobs: list[dict]) -> None: