[Bug]deepseekv4昨天晚上好像改了什么东西报错了

[lq-259]

What happened / 发生了什么

使用dsv4对话报错，24号中午还正常，晚上就出现问题了看qq群其他群友也有同样的问题

Reproduce / 如何复现？

使用deepseekv4官方api通过bot进行对话，webchat似乎没问题

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

debian uv安装的最新版

OS

Windows

Logs / 报错日志

2026-04-25 02:02:25.140] [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 "/root/.local/share/uv/tools/astrbot/lib/python3.12/site-packages/astrbot/core/agent/runners/tool_loop_agent_runner.py", line 510, in _iter_llm_responses_with_fallback
async for attempt in retrying:
File "/root/.local/share/uv/tools/astrbot/lib/python3.12/site-packages/tenacity/asyncio/init.py", line 170, in anext
do = await self.iter(retry_state=self._retry_state)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/tools/astrbot/lib/python3.12/site-packages/tenacity/asyncio/init.py", line 157, in iter
result = await action(retry_state)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/tools/astrbot/lib/python3.12/site-packages/tenacity/_utils.py", line 111, in inner
return call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/tools/astrbot/lib/python3.12/site-packages/tenacity/init.py", line 393, in
self._add_action_func(lambda rs: rs.outcome.result())
^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 449, in result
return self.__get_result()
^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result
raise self._exception
File "/root/.local/share/uv/tools/astrbot/lib/python3.12/site-packages/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 "/root/.local/share/uv/tools/astrbot/lib/python3.12/site-packages/astrbot/core/agent/runners/tool_loop_agent_runner.py", line 477, in _iter_llm_responses
yield await self.provider.text_chat(**payload)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/tools/astrbot/lib/python3.12/site-packages/astrbot/core/provider/sources/openai_source.py", line 1165, in text_chat
) = await self._handle_api_error(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/tools/astrbot/lib/python3.12/site-packages/astrbot/core/provider/sources/openai_source.py", line 1111, in _handle_api_error
raise e
File "/root/.local/share/uv/tools/astrbot/lib/python3.12/site-packages/astrbot/core/provider/sources/openai_source.py", line 1153, in text_chat
llm_response = await self._query(payloads, func_tool)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/tools/astrbot/lib/python3.12/site-packages/astrbot/core/provider/sources/openai_source.py", line 572, in _query
completion = await self.client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/tools/astrbot/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 2714, in create
return await self._post(
^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/tools/astrbot/lib/python3.12/site-packages/openai/_base_client.py", line 1913, in post
return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.local/share/uv/tools/astrbot/lib/python3.12/site-packages/openai/_base_client.py", line 1698, 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'}}
[2026-04-25 02:02:25.171] [Core] [WARN] [v4.23.5] [runners.tool_loop_agent_runner:492]: Switched from deepseek/deepseek-v4-flash to fallback chat provider: openai/gpt-5.4

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 @lq-259! I'm Dosu and I’m helping the AstrBot team.

这个问题已经被定位到了。DeepSeek API 近期要求在多轮对话中，assistant 消息里的 reasoning_content 必须回传给 API，但 AstrBot 在流式模式下的消息过滤逻辑（_query_stream）缺少对 reasoning_content 的保留检查，导致含有推理内容但无普通 content 的消息被错误地过滤掉了 [1]。

好消息是 PR #7759 已于 4 月 24 日提交，正是修复你遇到的这个问题。 该 PR 的主要改动包括：

1. 将消息过滤逻辑抽取为 _clean_assistant_messages_for_chat_completion() 共享方法，同时应用于 _query 和 _query_stream 两条代码路径 [2]
2. 过滤时新增对 reasoning_content 的检查，避免仅含推理内容的消息被误删
3. 流式模式下正确累积 reasoning_content 并保留到最终响应中

临时解决方案：在 PR 合并并发版之前，可以尝试关闭流式输出（streaming），非流式路径的过滤逻辑相对完整，可能可以绕过此问题 [3]。也可以手动将 PR #7759 的改动应用到本地安装。

To reply, just mention @dosu.

---

Share context across your team and agents. Try Dosu.

[Soulter]

试一下 /new 有没有用

[lq-259]

试一下 /new 有没有用

新开和清理历史应该都是有用的，但是切换成其他模型再切回来似乎依然会这样

[Hola-Gracias]

非流式路径也会遇到这个问题

即使把本体修了也有这个问题

大概找到问题所在了，可能是因为astrbot_plugin_livingmemory这个插件的fake_tool_call模式的问题