Skip to content

[Bug] mimo-v2.5适配问题 #8267

@redshirmp

Description

@redshirmp

What happened / 发生了什么

检查了配置。is_reasoning_model: true 已开启,但 astrbot 调用 mimo-v2.5 时可能未正确传递 reasoning_content 参数。
这属于 astrbot 框架层面的兼容性问题。建议:
查看 astrbot 是否有针对推理模型的配置项
或暂时关闭 is_reasoning_model 测试
导致可以正常群聊发消息而无法私聊?

Reproduce / 如何复现?

从deepseek模型换到mimo-v2.5,
并且在配置界面增添了
"enable_thinking": false,
"thinking": {"type": "disabled"}用于关闭思考模式
给mimo-v2.5关闭思考模式后出现私聊bot机器人回报code:400错误。
群聊反而没事

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

Astr V4.25.0 windows NapCat

OS

Windows

Logs / 报错日志

[2026-05-20 22:30:14.438] [Core]
[INFO]
[core.event_bus:61]: [default] [艾薇拉(aiocqhttp)] 红虾嗷/1592499417: ?
[2026-05-20 22:30:14.460] [Core]
[INFO]
[astrbot_plugin_angel_memory.main:248]: [事件人格] 会话ID=艾薇拉:FriendMessage:1592499417 当前人格=大小姐
[2026-05-20 22:30:14.460] [Core]
[INFO]
[core.initialization_manager:215]: ✅ 系统等待完成:准备就绪(异步)
[2026-05-20 22:30:14.461] [Core]
[INFO]
[services.retrieval_service:67]: 🧠 灵魂回忆深度: 7 (E=0.0)
[2026-05-20 22:30:15.215] [Core]
[WARN]
[v4.25.0] [runners.tool_loop_agent_runner:555]: Chat Model xiaomimimo/mimo-v2.5 request error: Error code: 400 - {'error': {'code': '400', 'message': 'Param Incorrect', 'param': 'The reasoning_content in the thinking mode must be passed back to the API.', 'type': ''}}
Traceback (most recent call last):
File "\?\D:\AstrBot\backend\app\astrbot\core\agent\runners\tool_loop_agent_runner.py", line 510, in iter_llm_responses_with_fallback
async for attempt in retrying:
File "D:\AstrBot\backend\python\Lib\site-packages\tenacity\asyncio_init
.py", line 170, in anext
do = await self.iter(retry_state=self.retry_state)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AstrBot\backend\python\Lib\site-packages\tenacity\asyncio_init
.py", line 157, in iter
result = await action(retry_state)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AstrBot\backend\python\Lib\site-packages\tenacity_utils.py", line 111, in inner
return call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "D:\AstrBot\backend\python\Lib\site-packages\tenacity_init_.py", line 393, in
self._add_action_func(lambda rs: rs.outcome.result())
^^^^^^^^^^^^^^^^^^^
File "D:\AstrBot\backend\python\Lib\concurrent\futures_base.py", line 449, in result
return self.__get_result()
^^^^^^^^^^^^^^^^^^^
File "D:\AstrBot\backend\python\Lib\concurrent\futures_base.py", line 401, in __get_result
raise self._exception
File "\?\D:\AstrBot\backend\app\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 "\?\D:\AstrBot\backend\app\astrbot\core\agent\runners\tool_loop_agent_runner.py", line 477, in _iter_llm_responses
yield await self.provider.text_chat(**payload)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "\?\D:\AstrBot\backend\app\astrbot\core\provider\sources\openai_source.py", line 1217, in text_chat
) = await self._handle_api_error(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "\?\D:\AstrBot\backend\app\astrbot\core\provider\sources\openai_source.py", line 1163, in _handle_api_error
raise e
File "\?\D:\AstrBot\backend\app\astrbot\core\provider\sources\openai_source.py", line 1205, in text_chat
llm_response = await self._query(payloads, func_tool)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "\?\D:\AstrBot\backend\app\astrbot\core\provider\sources\openai_source.py", line 596, in _query
completion = await self.client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AstrBot\backend\python\Lib\site-packages\openai\resources\chat\completions\completions.py", line 2739, in create
return await self._post(
^^^^^^^^^^^^^^^^^
File "D:\AstrBot\backend\python\Lib\site-packages\openai_base_client.py", line 1931, in post
return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\AstrBot\backend\python\Lib\site-packages\openai_base_client.py", line 1716, in request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'code': '400', 'message': 'Param Incorrect', 'param': 'The reasoning_content in the thinking mode must be passed back to the API.', 'type': ''}}
[2026-05-20 22:30:15.231] [Core]
[INFO]
[respond.stage:183]: Prepare to send - 红虾嗷/1592499417: LLM 响应错误: All chat models failed: BadRequestError: Error code: 400 - {'error': {'code': '400', 'message': 'Param Incorrect', 'param': 'The reasoning_content in the thinking mode must be passed back to the API.', 'type': ''}}
[2026-05-20 22:30:15.376] [Core]
[INFO]
[core.angel_heart_context:546]: AngelHeart[艾薇拉:FriendMessage:1592499417]: 状态更新: 观测中 -> 观测中 (AI回复完成,进入观测中)
[2026-05-20 22:30:15.376] [Core]
[INFO]
[astrbot_plugin_angel_heart.main:588]: AngelHeart[艾薇拉:FriendMessage:1592499417]: 任务处理完成,已在消息发送后释放处理锁。

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

  • Yes!

Code of Conduct

Metadata

Metadata

Assignees

No one assigned

    Labels

    area:providerThe bug / feature is about AI Provider, Models, LLM Agent, LLM Agent Runner.bugSomething isn't workingpriority: p1

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions