Any idea why the tool calling fails first, but then runs normally? 13:49:17:788 [LOG] Model request started (attempt #1, chatgpt-4o-latest, openai) 13:49:17:935 [LOG] Model request started (attempt #2, gpt-4o-2024-08-06, azure-openai, eastus) 13:49:17:935 [WARN] Model request failed (attempt #1, reason: (tools is not supported in this model. For a list of supported models, refer to https://platform.openai.com/docs/guides/function-calling#models-supporting-function-calling.)) 13:49:18:558 [WARN] Model request taking too long (attempt #1, started 769.17ms ago) 13:49:18:558 [LOG] Model request started (attempt #3, gpt-4o-2024-05-13, azure-openai, eastus2) 13:49:19:287 [LOG] Model called tool: TestTool({"param1":"..."})

chat-gpt-4o latest doesn't supports tool, so please use another model instead.

Oh I wasn't aware of that, I thought that would work with all 4o models and latest would just pick the latest automatically instead of manually choosing one. Thanks for the hint. It seems like gpt-4o-2024-08-06 is the default one in this case.