Files
winnow/scheduler.py
T
flanandClaude Sonnet 4.6 af8bae1c45 fix: embedding cache key mismatch, scheduler path/exception, log handler leak
embeddings.py: face embedding cache used 'immich' for lookup but
'insightface' for storage, so the cache was never hit for locally-
computed embeddings. Unified to 'insightface'/'siglip' throughout.
This affects all users since ENABLE_CACHE now defaults to true.

scheduler.py: INSIGHTFACE_HOME=/models/.insightface was having
'.insightface' appended again, making buffalo_l check always report
'will download'. Also catch BaseException (not just Exception) so a
SystemExit from a library call can't silently kill all future runs.

log_config.py: handlers.clear() abandoned open FileHandler fds on
each scheduled main() call. Close each handler properly before removal.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-12 15:10:44 +00:00

53 lines
1.6 KiB
Python

#!/usr/bin/env python3
import logging
import os
import sys
import time
from pathlib import Path
try:
from croniter import croniter
except ImportError:
print("croniter not installed. Run: uv add croniter")
sys.exit(1)
# Imported at module level so models loaded during the first run stay
# resident in memory across all subsequent scheduled runs.
from winnow.cli import main
SCHEDULE = os.environ["CRON_SCHEDULE"]
MODELS_DIR = os.environ.get("HF_HOME", "/models/huggingface")
INSIGHTFACE_HOME = os.environ.get("INSIGHTFACE_HOME", "/models/.insightface")
logger = logging.getLogger(__name__)
def check_models() -> None:
buffalo = Path(INSIGHTFACE_HOME) / "models" / "buffalo_l"
hf_hub = Path(MODELS_DIR) / "hub"
if not buffalo.exists():
print(" InsightFace Buffalo_L not found — will download on first run", flush=True)
if not (hf_hub.exists() and any(hf_hub.iterdir())):
print(" HuggingFace models not found — will download on first run", flush=True)
NOW = time.time()
cron = croniter(SCHEDULE, NOW)
next_run = cron.get_next(float)
while True:
now = time.time()
if now >= next_run:
print(f"\n[{time.strftime('%Y-%m-%d %H:%M:%S')}] Starting winnow run...", flush=True)
check_models()
try:
main()
print("winnow run complete", flush=True)
except KeyboardInterrupt:
raise
except BaseException as e:
logger.error(f"winnow run failed: {e}", exc_info=True)
print(f"winnow run failed: {e}", flush=True)
next_run = cron.get_next(float)
time.sleep(60)