Abhimanyu Kapur a80f85692b fix(ui): drop max_tokens from the auto-router connection probe ... max_tokens=1 makes reasoning models (o1/o3/...) return a 400 "max_tokens reached" because reasoning tokens count against the cap, so a reachable reasoning tier showed a false failure in Test Connection. Live-verified: o3 400s with the cap and succeeds without it. Extract the request shape into a pure buildModelGroupTestRequest and cover it with a test asserting the chat body carries no max_tokens (or max_completion_tokens), so this regression is caught in unit tests instead of only against a live reasoning model.		2026-07-11 16:43:36 -07:00
..
litellm-dashboard	fix(ui): drop max_tokens from the auto-router connection probe	2026-07-11 16:43:36 -07:00
Dockerfile	feat: add componentized proxy deployment with gateway, backend, ui, and migrations (#27557)	2026-05-16 09:25:17 -07:00
nginx.conf	feat: add componentized proxy deployment with gateway, backend, ui, and migrations (#27557)	2026-05-16 09:25:17 -07:00