Two bugs causing zero recommendations:
1. risk_metrics.py was untracked — importing it raised ModuleNotFoundError which
was caught by the outer try/except in filter.py, silently dropping all 32
candidates that reached the fundamental risk check stage.
2. Minervini scanner at max_tickers=200 took >5 min to download 200 tickers x 1y
of OHLCV data. ThreadPoolExecutor.cancel() cannot kill a running thread, so the
download kept running as a zombie thread for 20 more minutes after the pipeline
completed, holding the Python process alive until the 30-min workflow timeout
killed the entire job.
Reducing to 50 tickers brings the download to ~75s, well under the 300s global
scanner timeout.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Youssef Aitousarrah