[Bug] github o1模型不支持流式，请求适配非流输出

[Zzz3626]

📦 部署环境

Docker

📌 软件版本

v1.36.46

💻 系统环境

Windows

🌐 浏览器

Edge

🐛 问题描述

{
"error": {
"code": "unsupported_value",
"type": "invalid_request_error",
"param": "stream",
"message": "Unsupported value: 'stream' does not support true with this model. Supported values are: false."
},
"endpoint": "https://models.inference.ai.azure.com/",
"provider": "github"
}

📷 复现步骤

No response

🚦 期望结果

No response

📝 补充信息

No response

[lobehubbot]

👀 @Zzz3626

Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible.
Please make sure you have given us as much context as possible.
非常感谢您提交 issue。我们会尽快调查此事，并尽快回复您。 请确保您已经提供了尽可能多的背景信息。

[dosubot]

I found a similar discussion regarding the issue of models not supporting streaming in the lobe-chat framework. The discussion is titled "调用chat的AI接口，传入stream为false,还是调用流式数据，或者返回报错" and it remains unsolved ^[1].

Regarding your issue, the error message indicates that the model you are using does not support streaming (stream: true). The lobe-chat framework handles such cases by returning an error message when a model does not support a requested feature like streaming. In your case, the error message specifies that the stream parameter is not supported with the value true for the model you are using ^[2].

To resolve this, you can set the stream parameter to false for models that do not support streaming. This adjustment should allow the model to process requests without attempting to use unsupported streaming features.

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}

[jiajiaxd]

#5110 似乎已经适配过了，但是仍然需要手动自定义添加o1模型（如下图）

如果自定义添加o1的话，就会复现本issue出现的问题
版本：v1.37.1

[lobehubbot]

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

---

#5110 seems to have been adapted, but you still need to manually add the o1 model (as shown below)

If o1 is added by customization, the problem of this issue will be reproduced.
Version: v1.37.1

[RS-Imagine]

同样能复现该报错。
另外，请考虑默认关闭GitHub提供商的模型获取，modelList: { showModelFetcher: true }, // I'm not sure if it is good to show the model fetcher, as remote list is not complete.