[Bug] deepseek-v4-flash 思考模式多轮对话报 400：The `reasoning_content` in the thinking mode must be passed back to the API.

[LWDJD]

What happened / 发生了什么

在更新了v4.23.5之后，使用“deepseek-v4-flash”模型ID时会返回400报错，但降级到旧模型ID “deepseek-reasoner”后可以正常使用。

Reproduce / 如何复现？

使用v4.23.5版本，添加OpenAI格式的DeepSeek模型提供商，选择使用“deepseek-v4-flash”模型ID，我在自定义请求体参数中添加了{"reasoning_effort":"max"}，不过这个自定义请求体参数可能没有什么影响。

AstrBot version, deployment method (e.g., Windows Docker Desktop deployment), provider used, and messaging platform used. / AstrBot 版本、部署方式（如 Windows Docker Desktop 部署）、使用的提供商、使用的消息平台适配器

v4.23.5
Linux Docker
DeepSeek(OpenAI API)
QQ Bot(官方)

OS

Linux

Logs / 报错日志

[2026-04-27 07:18:06.512] [Core] [WARN] [v4.23.5] [runners.tool_loop_agent_runner:555]: Chat Model deepseek/deepseek-v4-flash request error: Error code: 400 - {'error': {'message': 'The reasoning_content in the thinking mode must be passed back to the API.', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_request_error'}}
Traceback (most recent call last):
File "/AstrBot/astrbot/core/agent/runners/tool_loop_agent_runner.py", line 510, in _iter_llm_responses_with_fallback
async for attempt in retrying:
File "/usr/local/lib/python3.12/site-packages/tenacity/asyncio/init.py", line 170, in anext
do = await self.iter(retry_state=self._retry_state)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/tenacity/asyncio/init.py", line 157, in iter
result = await action(retry_state)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/tenacity/_utils.py", line 111, in inner
return call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/tenacity/init.py", line 393, in
self._add_action_func(lambda rs: rs.outcome.result())
^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/concurrent/futures/_base.py", line 449, in result
return self.__get_result()
^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result
raise self._exception
File "/AstrBot/astrbot/core/agent/runners/tool_loop_agent_runner.py", line 514, in _iter_llm_responses_with_fallback
async for resp in self._iter_llm_responses(
File "/AstrBot/astrbot/core/agent/runners/tool_loop_agent_runner.py", line 477, in _iter_llm_responses
yield await self.provider.text_chat(**payload)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/AstrBot/astrbot/core/provider/sources/openai_source.py", line 1165, in text_chat
) = await self._handle_api_error(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/AstrBot/astrbot/core/provider/sources/openai_source.py", line 1111, in _handle_api_error
raise e
File "/AstrBot/astrbot/core/provider/sources/openai_source.py", line 1153, in text_chat
llm_response = await self._query(payloads, func_tool)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/AstrBot/astrbot/core/provider/sources/openai_source.py", line 572, in _query
completion = await self.client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 2700, in create
return await self._post(
^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/openai/_base_client.py", line 1884, in post
return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/openai/_base_client.py", line 1669, in request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': 'The reasoning_content in the thinking mode must be passed back to the API.', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_request_error'}}
[2026-04-27 07:18:06.532] [Core] [WARN] [v4.23.5] [runners.tool_loop_agent_runner:492]: Switched from deepseek/deepseek-v4-flash to fallback chat provider: deepseek/deepseek-reasoner

Are you willing to submit a PR? / 你愿意提交 PR 吗？

• Yes!

Code of Conduct

• I have read and agree to abide by the project's Code of Conduct。

[dosubot]

Hi @LWDJD! I'm Dosu and I’m helping the AstrBot team.

这是一个已知的重复问题，与 #7782 和 #7798 相同 [1] [2]。

原因：DeepSeek API 要求多轮对话中 assistant 消息的 reasoning_content 必须原样回传，但 AstrBot 的 Message 类缺少该字段，导致构建历史消息时推理内容丢失。

修复进展：PR #7759 已提交修复，但尚未合并 [1]。此外社区讨论中还发现 fallback 到其他模型再切回 DeepSeek 时也会因"脏历史"触发同样的错误，需要额外的 sanitizer 逻辑 [2]。

临时解决：使用 /new 清除对话历史后重新开始对话，或暂时降级使用 deepseek-reasoner 模型 ID（你已经发现这个方法有效）。

To reply, just mention @dosu.

---

Docs are dead. Just use Dosu.

[daniel5u]

#7823 已经修复了