AJ Isaacs 174db1e5db feat: per-model failure tracking to avoid unnecessary full restarts ...

Individual model probe failures are now tracked separately from router
health failures. Models get a grace period after loading, and persistently
failing models are unloaded and put in cooldown rather than triggering a
full service restart. Only router-level health failures cause restarts.

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

2026-02-08 12:09:07 -05:00

12 KiB

Raw Permalink Blame History

View Raw