-
-
Notifications
You must be signed in to change notification settings - Fork 2.2k
[Bug] 模型使用小米的mimo V2.5模型后主动消息回复的插件无法回复 #8173
Copy link
Copy link
Open
Labels
area:providerThe bug / feature is about AI Provider, Models, LLM Agent, LLM Agent Runner.The bug / feature is about AI Provider, Models, LLM Agent, LLM Agent Runner.bugSomething isn't workingSomething isn't workingfeature:pluginThe bug / feature is about AstrBot plugin system.The bug / feature is about AstrBot plugin system.plugin-cate:automationScheduled reminders, notifications, subscriptions, and proactive messages.(only startswith [Plugin])Scheduled reminders, notifications, subscriptions, and proactive messages.(only startswith [Plugin])
Description
Metadata
Metadata
Assignees
Labels
area:providerThe bug / feature is about AI Provider, Models, LLM Agent, LLM Agent Runner.The bug / feature is about AI Provider, Models, LLM Agent, LLM Agent Runner.bugSomething isn't workingSomething isn't workingfeature:pluginThe bug / feature is about AstrBot plugin system.The bug / feature is about AstrBot plugin system.plugin-cate:automationScheduled reminders, notifications, subscriptions, and proactive messages.(only startswith [Plugin])Scheduled reminders, notifications, subscriptions, and proactive messages.(only startswith [Plugin])
What happened / 发生了什么
使用主动消息 (Proactive Chat)插件（https://github.com/DBJD-CR/astrbot_plugin_proactive_chat），配置默认对话模型为小米的mimo V2.5，主动触发或到点触发主动消息恢复，无法发送回复信息，基于小米之前发公告说强制要回传reasoning_content，可能是相关的问题
Reproduce / 如何复现？
使用主动消息 (Proactive Chat)插件（https://github.com/DBJD-CR/astrbot_plugin_proactive_chat），配置默认对话模型为小米的mimo V2.5，主动触发或到点触发主动消息恢复，无法发送回复信息
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
astrbot docker部署，V4.24.4版本，使用小米的token plan中的mimo V2.5
OS
Linux
Logs / 报错日志
[2026-05-13 16:16:45.047] [Plug]
[INFO]
[core.chat_flow:194]: [主动消息] 开始生成第 1 次主动消息喵，当前未回复次数: 0 次喵。
[2026-05-13 16:16:45.367] [Plug]
[INFO]
[core.llm_adapter:633]: [主动消息] 使用默认人格设定喵
[2026-05-13 16:16:45.468] [Plug]
[INFO]
[core.llm_adapter:532]: [主动消息] 上下文注入来源：混合模式，读取到对话历史 267 条，平台流水原始记录 20 条，注入上下文 20 条，平台流水上下文长度 1166 字，最终提供给模型的上下文共 268 条喵。
[2026-05-13 16:16:45.476] [Plug]
[INFO]
[core.llm_adapter:665]: [主动消息] 上下文与人格设定已准备完成喵。
[2026-05-13 16:16:46.711] [Plug]
[ERRO]
[v4.24.4] [core.llm_adapter:752]: [主动消息] 使用新 API 调用 LLM 失败喵: 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': ''}}
[2026-05-13 16:16:46.713] [Plug]
[INFO]
[core.llm_adapter:753]: [主动消息] 错误类型喵: BadRequestError
[2026-05-13 16:16:46.715] [Plug]
[INFO]
[core.llm_adapter:754]: [主动消息] 错误详情喵: 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': ''}}
[2026-05-13 16:16:47.605] [Plug]
[ERRO]
[v4.24.4] [core.llm_adapter:794]: [主动消息] 传统 API 回退也失败喵: 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': ''}}
[2026-05-13 16:16:47.607] [Plug]
[INFO]
[core.llm_adapter:795]: [主动消息] 回退错误类型喵: BadRequestError
[2026-05-13 16:16:47.608] [Plug]
[ERRO]
[v4.24.4] [core.llm_adapter:798]: [主动消息] 呜喵？！LLM调用完全失败，将重新调度任务喵。
Are you willing to submit a PR? / 你愿意提交 PR 吗？
Code of Conduct