A community member reported a bug in the AgentRunner.from_llm function, where it does not properly test for fine-tuned models, leading to the ReActAgent being automatically used even when the fine-tuned model is an OpenAI model. Another community member suggested that this sounds like an easy pull request to fix, but noted they have a lot of other things going on, so a pull request from the original reporter would be very helpful.
AgentRunner.from_llmhas a bug. In the is_function_calling_model you are not testing for finetuned models. Which leads to the ReActAgent being automatically used, even if your finetuned model is an OpenAI one. @Logan M
