mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-08-11 00:42:48 +00:00
5a2b3c25aa
LiteLLM construction computed the real provider in `__new__` but never passed it into init, so `BaseLLM` silently defaulted every shared-path model to `openai`. Infer the provider from a `provider/model` prefix when none is supplied so groq, cohere, mistral, and the rest report themselves correctly to callers like the policy engine.