[Bug]使用推理模型在思考过程较长时，会被截断

[jung233]

📦 Platform

Vercel

📦 Deploymenet mode

server db(lobe-chat-database image)

📌 Version

1.51.3

💻 Operating System

Windows

🌐 Browser

Chrome

🐛 Bug Description

使用Deepseek R1回答较长问题时，会出现思考一半直接中止输出（使用腾讯云 OpenAI兼容接口，服务器模式）。使用XXXStudio本地客户端未出现该问题

📷 Recurrence Steps

No response

🚦 Expected Behavior

No response

📝 Additional Information

No response

[lobehubbot]

👀 @jung233

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。