[Bug] 通过火山引擎（字节跳动）api接入的DeepseekR1没有思考过程，Deepseek官方的api展示的markdown格式有问题

[JoesephChan]

📦 部署方式

官方安装包

📌 软件版本

v2.15.8

💻 系统环境

Windows

📌 系统版本

10

🌐 浏览器

Edge

📌 浏览器版本

/

🐛 问题描述

通过火山引擎（字节跳动）api接入的DeepseekR1没有思考过程，粗略看了下源码应该是没写think部分；Deepseek官方的api展示的markdown格式有问题，无论是V3还是R1（chat和reasoner）都无法准确显示markdow，会吞掉/n。

📷 复现步骤

No response

🚦 期望结果

No response

📝 补充信息

No response

[Issues-translate-bot]

Bot detected the issue body's language is not English, translate it automatically.

---

Title: [Bug] DeepseekR1 connected through Volcano Engine (ByteDance) API has no thinking process, and there is a problem with the markdown format displayed by Deepseek official API

📦 Deployment method

Official installation package

📌 Software version

v2.15.8

💻 System environment

Windows

📌 System version

10

🌐 Browser

Edge

📌 Browser version

/

🐛 Question description

DeepseekR1, which is connected through the Volcano Engine (ByteDance) API, has no thinking process. I have a rough look at the source code and it should not have written the think part; there is a problem with the markdown format displayed by Deepseek's official API, whether it is V3 or R1 (chat and reasoner) No markdow can be displayed accurately, and it will swallow /n.

📷 Reproduction steps

No response

🚦 Expected results

No response

📝 Supplementary information

No response

[sanbei101]

#6122

[Issues-translate-bot]

Bot detected the issue body's language is not English, translate it automatically.

---

#6122

[theores]

#6122

这不是同一个问题，楼主说的使用字节跳动、腾讯云的deepseek api接入时，没有显示思考过程。

[Issues-translate-bot]

Bot detected the issue body's language is not English, translate it automatically.

---

#6122

This is not the same problem. The poster said that when using ByteDance and Tencent Cloud's deepseek API access, there is no reflection process.

[bestsanmao]

#6204

[Issues-translate-bot]

Bot detected the issue body's language is not English, translate it automatically.

---

#6204

[TianRandai111]

我调用的就是阿里云的deepseek ，nestgpt用官网最新的代码， CUSTOM_MODELS=-all,+deepseek-r1@DeepSeek ，就可以了

[Issues-translate-bot]

Bot detected the issue body's language is not English, translate it automatically.

---

What I call is Alibaba Cloud's deepseek. nestgpt uses the latest code on the official website, CUSTOM_MODELS=-all,+deepseek-r1@DeepSeek, and that's fine.

[bestsanmao]

#6204 这个pr已经可以了
管理还没合并进main

[JoesephChan]

还有一个是Deepseek官方的API返回的内容输出为Markdown时/n会被吞掉，但查看响应时发现是有返回换行符的；用其他的大模型就没有Markdown格式的问题。

[Issues-translate-bot]

Bot detected the issue body's language is not English, translate it automatically.

---

Another thing is that when the content returned by Deepseek's official API is Markdown, /n will be swallowed, but when viewing the response, it is found that there is a newline return; there is no problem with Markdown format when using other big models.

[bestsanmao]

还有一个是Deepseek官方的API返回的内容输出为Markdown时/n会被吞掉，但查看响应时发现是有返回换行符的；用其他的大模型就没有Markdown格式的问题。

已在 #6204 中修复（还没合并到main）

[Issues-translate-bot]

Bot detected the issue body's language is not English, translate it automatically.

---

Another thing is that when the content returned by Deepseek official API is Markdown, /n will be swallowed, but when viewing the response, it is found that there is a newline return; there is no problem with Markdown format when using other big models.

Fixed in #6204 (not merged to main yet)