fix: INSIGHTFACE_HOME path, entrypoint, caching default, CRON_SCHEDULE opt-in

- Dockerfile: ENV INSIGHTFACE_HOME=/models → /models/.insightface to
  match compose.yml and .env.example; the old value caused InsightFace
  to store models at /models/models/buffalo_l (double-appended subdir)
- entrypoint.sh: use /app/.venv/bin/winnow (installed entry point)
  instead of python -m winnow.cli
- config.py: ENABLE_CACHE default false → true; embedding cache is
  always beneficial in practice; users can opt out with ENABLE_CACHE=false
- compose.yml: comment out CRON_SCHEDULE so scheduling is opt-in;
  flip ENABLE_CACHE to commented opt-out to reflect new default
- README.md: update ENABLE_CACHE default documentation to true
- tests/test_config.py: update default assertion to match

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

Dockerfile

@@ -71,7 +71,7 @@ RUN groupadd -g 568 apps && useradd -u 568 -g apps -m -s /bin/bash appuser \
 
 WORKDIR /app
 USER appuser
-ENV HF_HOME=/models/huggingface INSIGHTFACE_HOME=/models
+ENV HF_HOME=/models/huggingface INSIGHTFACE_HOME=/models/.insightface
 
 HEALTHCHECK CMD test -f /app/entrypoint.sh || exit 1
 ENTRYPOINT ["tini", "--", "/app/entrypoint.sh"]

README.md

@@ -192,7 +192,7 @@ The first run after a fresh install downloads the embedding models (~1-2 GB). Su
 | Variable | Default | Description |
 | :--- | :--- | :--- |
 | `FORCE_CPU` | `false` | Disable GPU — fall back to CPU for embedding computation |
-| `ENABLE_CACHE` | `false` | Cache computed embeddings to disk (speeds up re-runs on the same library) |
+| `ENABLE_CACHE` | `true` | Cache computed embeddings to disk (speeds up re-runs on the same library) |
 | `CACHE_DIR` | `.if_cache` | Path for embedding cache and upload tracker files |
 | `HF_HOME` | *(system)* | HuggingFace model cache location (SigLIP) |
 | `INSIGHTFACE_HOME` | *(system)* | InsightFace model cache location (Buffalo_L) |

compose.yml

@@ -35,7 +35,7 @@ services:
 
       # ── Caching & Models ──────────────────────────────────────────────────
       - FORCE_CPU=false
-      - ENABLE_CACHE=true
+      # - ENABLE_CACHE=false          # Disable embedding cache (default: true)
       - CACHE_DIR=/app/.if_cache
       - HF_HOME=/models/huggingface
       - INSIGHTFACE_HOME=/models/.insightface
@@ -47,10 +47,9 @@ services:
 
       # ── Scheduling ────────────────────────────────────────────────────────
       # Cron expression (unset = run once and exit)
-      # Every Sunday at 3 AM:
+      # - CRON_SCHEDULE=0 3 * * 0    # Every Sunday at 3 AM
-      - CRON_SCHEDULE=0 3 * * 0
+      # - CRON_SCHEDULE=0 3 1 * *    # First of every month
-      # - CRON_SCHEDULE=0 3 1 * *
+      # - CRON_SCHEDULE=*/30 * * * * # Every 30 minutes
-      # - CRON_SCHEDULE=*/30 * * * *
     volumes:
       # Replace with absolute paths on your host, e.g. /opt/winnow/models
       - /path/to/winnow/models:/models

entrypoint.sh

@@ -4,7 +4,7 @@ export PYTHONUNBUFFERED=1
 
 # 1. Run the job immediately on startup
 echo "▶ Running on startup..."
-/app/.venv/bin/python -m winnow.cli
+/app/.venv/bin/winnow
 
 # 2. If a schedule exists, start the scheduler
 if [ -n "${CRON_SCHEDULE:-}" ]; then

tests/test_config.py

@@ -25,7 +25,7 @@ def test_config_loads_defaults(monkeypatch):
     assert cfg.FACE_MARGIN == 0.15
     assert cfg.USE_FULL_RESOLUTION is True
     assert cfg.ENABLE_FACE_ALIGNMENT is True
-    assert cfg.ENABLE_CACHE is False
+    assert cfg.ENABLE_CACHE is True
 
     _Config.reset()
 

winnow/config.py

@@ -39,8 +39,7 @@ class _Config:
     USE_FULL_RESOLUTION: bool = True
     ENABLE_FACE_ALIGNMENT: bool = True
 
-    # Caching (opt-in to avoid unexpected files)
+    ENABLE_CACHE: bool = True
-    ENABLE_CACHE: bool = False
     CACHE_DIR: str = ".if_cache"
 
     def __new__(cls) -> "_Config":
@@ -64,7 +63,7 @@ class _Config:
         self.FACE_MARGIN = float(os.getenv("FACE_MARGIN", "0.15"))
         self.USE_FULL_RESOLUTION = os.getenv("USE_FULL_RESOLUTION", "true").lower() in ("true", "1", "yes")
         self.ENABLE_FACE_ALIGNMENT = os.getenv("ENABLE_FACE_ALIGNMENT", "true").lower() in ("true", "1", "yes")
-        self.ENABLE_CACHE = os.getenv("ENABLE_CACHE", "false").lower() in ("true", "1", "yes")
+        self.ENABLE_CACHE = os.getenv("ENABLE_CACHE", "true").lower() in ("true", "1", "yes")
         self.CACHE_DIR = os.getenv("CACHE_DIR", ".if_cache")
 
         # Fall back to config file for non-sensitive values (API_KEY not stored here)