Files
winnow/scheduler.py
T
flan 2e08504682 fix: audit hardening — input validation, error handling, and robustness (#25)
* fix: audit hardening — input validation, error handling, and robustness

- immich_api: guard person["id"] with .get() + early return on missing field
- immich_api: include page number in pagination exception log
- immich_api: validate faces response is a list before indexing
- executor: wrap Image.open() in try/except for non-image HTTP responses
- executor: strip leading 'v' from Frigate version before parsing (v0.16.0 was misread)
- config: wrap FRIGATE_SCORE_CEILING float() parse in try/except with warning
- config: warn when both DATA_DIR and legacy CWD config files exist simultaneously
- scheduler: wrap PID file write in try/except so /tmp failures don't crash startup
- scheduler: clamp sleep to 60s max to bound recovery time after NTP clock jumps
- frigate_api: log unexpected non-list type in get_frigate_person_files at DEBUG

* fix: LIMIT env var crash and symlink guard on person output dir

- jobs: wrap int(LIMIT) parse in try/except — bad value (e.g. "30.5", "all")
  now logs a warning and falls back to the default instead of crashing
- executor: check for symlink before shutil.rmtree on person_dir — prevents
  following a symlink out of OUTPUT_DIR on a shared volume

* chore: bump version to 0.5.3
2026-06-14 19:39:35 -04:00

64 lines
2.0 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
logger = logging.getLogger(__name__)
def _check_models() -> None:
insightface_home = os.environ.get("INSIGHTFACE_HOME", "/models/.insightface")
buffalo = Path(insightface_home) / "models" / "buffalo_l"
if not buffalo.exists():
print(" InsightFace Buffalo_L not found — will download on first run", flush=True)
def _run_scheduler() -> None:
schedule = os.environ.get("CRON_SCHEDULE")
if not schedule:
print("Error: CRON_SCHEDULE environment variable is required.", flush=True)
sys.exit(1)
try:
Path("/tmp/winnow.pid").write_text(str(os.getpid()))
except OSError as e:
print(f"Warning: could not write PID file: {e}", flush=True)
now = time.time()
cron = croniter(schedule, now)
next_run = cron.get_next(float)
print(f"Next run: {time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(next_run))}", flush=True)
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 Exception as e:
logger.error("winnow run failed: %s", e, exc_info=True)
print(f"winnow run failed: {e}", flush=True)
next_run = cron.get_next(float)
print(f"Next run: {time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(next_run))}", flush=True)
time.sleep(min(60, max(1, next_run - time.time())))
if __name__ == "__main__":
_run_scheduler()