service-update-alerts/update_monitor
Jeena 86268107fa classifier: Add fallback model for transient LLM failures
The 26b model occasionally hangs or fails outright on the local Ollama
box, which used to drop every such update into 'manual' for no good
reason. Retry the same prompt with a smaller model before giving up,
and surface both errors when even the fallback fails.

OLLAMA_FALLBACK_MODEL is new config, see .env.sample.
2026-10-06 22:10:07 +09:00
..
__init__.py feat: Add AI-driven auto-update & restructure into package 2026-04-09 12:49:57 +00:00
__main__.py feat: Add AI-driven auto-update & restructure into package 2026-04-09 12:49:57 +00:00
checker.py classifier: Point at gemma4:26b and retry transient fetches 2026-09-14 05:37:37 +00:00
classifier.py classifier: Add fallback model for transient LLM failures 2026-10-06 22:10:07 +09:00
comparator.py feat: Add AI-driven auto-update & restructure into package 2026-04-09 12:49:57 +00:00
extractor.py feat: Add AI-driven auto-update & restructure into package 2026-04-09 12:49:57 +00:00
fetcher.py feat: Add AI-driven auto-update & restructure into package 2026-04-09 12:49:57 +00:00
loader.py feat: Add AI-driven auto-update & restructure into package 2026-04-09 12:49:57 +00:00
models.py feat: Add AI-driven auto-update & restructure into package 2026-04-09 12:49:57 +00:00
notifier.py feat: Add AI-driven auto-update & restructure into package 2026-04-09 12:49:57 +00:00
updater.py feat: Add AI-driven auto-update & restructure into package 2026-04-09 12:49:57 +00:00