gpt5 参数设置不支持

cm, err := openai.NewChatModel(context.Background(), &openai.ChatModelConfig{
BaseURL: "",
APIKey: "",
Model: "gpt-5",
ReasoningEffort: openai.ReasoningEffortLevelLow,
ByAzure: func() bool {
return os.Getenv("OPENAI_BY_AZURE") == "true"
}(),
})
使用gpt5 endpoint 过程中发现有些参数不能设置 ：ReasoningEffort: openai.ReasoningEffortLevelLow,Temperature 等。
报错如下：[NodeRunError] error, status code: 400, status: 400 Bad Request, message: %!s(), body: {"message":"UnsupportedParamsError: azure does not support parameters: ['reasoning_effort'], for model=gpt-5. To drop these, set `drop_params=True`. \n If you want to use these params dynamically send allowed_openai_params=['reasoning_effort'] in your request.. Received Model Group=gpt-5\nAvailable Model Group Fallbacks=None","type":"None","param":null,"code":"400"

Start by reproducing the example through openai.NewChatModel with ChatModelConfig, using the reported gpt-5 and Azure settings. Trace how ReasoningEffort and Temperature are converted into the request, then compare the behavior with the reported 400 response. Done should be defined as an agreed handling of unsupported parameters, verified with a regression test or documented reproduction.

Written by the indexing model from the issue text.