feat(cli): add cow update

优化 README 中的中英文排版空格

.gitignore

@@ -33,7 +33,15 @@ plugins/banwords/lib/__pycache__
 !plugins/keyword
 !plugins/linkai
 !plugins/agent
+!plugins/cow_cli
 client_config.json
 ref/
 .cursor/
 local/
+node_modules/
+
+# cow cli
+dist/
+build/
+*.egg-info/
+.cow.pid

README.md

@@ -7,7 +7,7 @@
   [中文] | [<a href="docs/en/README.md">English</a>] | [<a href="docs/ja/README.md">日本語</a>]
 </p>
 
-**CowAgent** 是基于大模型的超级AI助理，能够主动思考和任务规划、操作计算机和外部资源、创造和执行Skills、拥有长期记忆并不断成长，比OpenClaw更轻量和便捷。CowAgent 支持灵活切换多种模型，能处理文本、语音、图片、文件等多模态消息，可接入微信、飞书、钉钉、企微智能机器人、QQ、企微自建应用、微信公众号、网页中使用，7*24小时运行于你的个人电脑或服务器中。
+**CowAgent** 是基于大模型的超级 AI 助理，能够主动思考和任务规划、操作计算机和外部资源、创造和执行 Skills、拥有长期记忆并不断成长，比 OpenClaw 更轻量和便捷。CowAgent 支持灵活切换多种模型，能处理文本、语音、图片、文件等多模态消息，可接入微信、飞书、钉钉、企微智能机器人、QQ、企微自建应用、微信公众号、网页中使用，7*24小时运行于你的个人电脑或服务器中。
 
 <p align="center">
   <a href="https://cowagent.ai/">🌐 官网</a> &nbsp;·&nbsp;
@@ -19,28 +19,28 @@
 
 # 简介
 
-> 该项目既是一个可以开箱即用的超级AI助理，也是一个支持高扩展的Agent框架，可以通过为项目扩展大模型接口、接入渠道、内置工具、Skills系统来灵活实现各种定制需求。核心能力如下：
+> 该项目既是一个可以开箱即用的超级 AI 助理，也是一个支持高扩展的 Agent 框架，可以通过为项目扩展大模型接口、接入渠道、内置工具、Skills 系统来灵活实现各种定制需求。核心能力如下：
 
 -  ✅  **复杂任务规划**：能够理解复杂任务并自主规划执行，持续思考和调用工具直到完成目标，支持通过工具操作访问文件、终端、浏览器、定时任务等系统资源
 -  ✅  **长期记忆：** 自动将对话记忆持久化至本地文件和数据库中，包括全局记忆和天级记忆，支持关键词及向量检索
--  ✅  **技能系统：** 实现了Skills创建和运行的引擎，内置多种技能，并支持通过自然语言对话完成自定义Skills开发
+-  ✅  **技能系统：** 实现了 Skills 创建和运行的引擎，内置多种技能，并支持通过自然语言对话完成自定义 Skills 开发
 -  ✅  **多模态消息：** 支持对文本、图片、语音、文件等多类型消息进行解析、处理、生成、发送等操作
--  ✅  **多模型接入：** 支持OpenAI, Claude, Gemini, DeepSeek, MiniMax、GLM、Qwen、Kimi、Doubao等国内外主流模型厂商
+-  ✅  **多模型接入：** 支持 OpenAI, Claude, Gemini, DeepSeek, MiniMax、GLM、Qwen、Kimi、Doubao 等国内外主流模型厂商
 -  ✅  **多端部署：** 支持运行在本地计算机或服务器，可集成到微信、飞书、钉钉、企业微信、QQ、微信公众号、网页中使用
 
 ## 声明
 
-1. 本项目遵循 [MIT开源协议](/LICENSE)，主要用于技术研究和学习，使用本项目时需遵守所在地法律法规、相关政策以及企业章程，禁止用于任何违法或侵犯他人权益的行为。任何个人、团队和企业，无论以何种方式使用该项目、对何对象提供服务，所产生的一切后果，本项目均不承担任何责任。
-2. 成本与安全：Agent模式下Token使用量高于普通对话模式，请根据效果及成本综合选择模型。Agent具有访问所在操作系统的能力，请谨慎选择项目部署环境。同时项目也会持续升级安全机制、并降低模型消耗成本。
-3. CowAgent项目专注于开源技术开发，不会参与、授权或发行任何加密货币。
+1. 本项目遵循 [MIT 开源协议](/LICENSE)，主要用于技术研究和学习，使用本项目时需遵守所在地法律法规、相关政策以及企业章程，禁止用于任何违法或侵犯他人权益的行为。任何个人、团队和企业，无论以何种方式使用该项目、对何对象提供服务，所产生的一切后果，本项目均不承担任何责任。
+2. 成本与安全：Agent 模式下 Token 使用量高于普通对话模式，请根据效果及成本综合选择模型。Agent 具有访问所在操作系统的能力，请谨慎选择项目部署环境。同时项目也会持续升级安全机制、并降低模型消耗成本。
+3. CowAgent 项目专注于开源技术开发，不会参与、授权或发行任何加密货币。
 
 ## 演示
 
-- 使用说明(Agent模式)：[CowAgent介绍](https://docs.cowagent.ai/intro/features)
+- 使用说明( Agent 模式)：[CowAgent 介绍](https://docs.cowagent.ai/intro/features)
 
 - 免部署在线体验：[CowAgent](https://link-ai.tech/cowagent/create)
 
-- DEMO视频(对话模式)：https://cdn.link-ai.tech/doc/cow_demo.mp4
+- DEMO 视频(对话模式)：https://cdn.link-ai.tech/doc/cow_demo.mp4
 
 ## 社区
 
@@ -54,9 +54,9 @@
 
 <a href="https://link-ai.tech" target="_blank"><img width="650" src="https://cdn.link-ai.tech/image/link-ai-intro.jpg"></a>
 
-> [LinkAI](https://link-ai.tech/) 是面向企业和个人的一站式AI智能体平台，聚合多模态大模型、知识库、技能、工作流等能力，支持一键接入主流平台并管理，支持SaaS、私有化部署等多种模式，可免部署在线运行[CowAgent助理](https://link-ai.tech/cowagent/create)。
+> [LinkAI](https://link-ai.tech/) 是面向企业和个人的一站式 AI 智能体平台，聚合多模态大模型、知识库、技能、工作流等能力，支持一键接入主流平台并管理，支持 SaaS、私有化部署等多种模式，可免部署在线运行[CowAgent 助理](https://link-ai.tech/cowagent/create)。
 >
-> LinkAI 目前已在智能客服、私域运营、企业效率助手等场景积累了丰富的AI解决方案，在消费、健康、文教、科技制造等各行业沉淀了大模型落地应用的最佳实践，致力于帮助更多企业和开发者拥抱 AI 生产力。
+> LinkAI 目前已在智能客服、私域运营、企业效率助手等场景积累了丰富的 AI 解决方案，在消费、健康、文教、科技制造等各行业沉淀了大模型落地应用的最佳实践，致力于帮助更多企业和开发者拥抱 AI 生产力。
 
 **产品咨询和企业服务** 可联系产品客服：
 
@@ -68,13 +68,13 @@
 
 >**2026.03.22：** [2.0.4版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.4)，新增个人微信通道（微信扫码即用）、新增 MiniMax-M2.7 和 GLM-5-Turbo 模型、run.sh 脚本重构、日文文档及多项修复。
 
->**2026.03.18：** [2.0.3版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.3)，新增企微智能机器人和 QQ 通道、支持Coding Plan、新增多个模型、Web端文件处理、记忆系统升级。
+>**2026.03.18：** [2.0.3版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.3)，新增企微智能机器人和 QQ 通道、支持 Coding Plan、新增多个模型、Web 端文件处理、记忆系统升级。
 
 >**2026.02.27：** [2.0.2版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.2)，Web 控制台全面升级（流式对话、模型/技能/记忆/通道/定时任务/日志管理）、支持多通道同时运行、会话持久化存储、新增多个模型。
 
 >**2026.02.13：** [2.0.1版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.1)，内置 Web Search 工具、智能上下文裁剪策略、运行时信息动态更新、Windows 兼容性适配，修复定时任务记忆丢失、飞书连接等多项问题。
 
->**2026.02.03：** [2.0.0版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.0)，正式升级为超级Agent助理，支持多轮任务决策、具备长期记忆、实现多种系统工具、支持Skills框架，新增多种模型并优化了接入渠道。
+>**2026.02.03：** [2.0.0版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.0)，正式升级为超级 Agent 助理，支持多轮任务决策、具备长期记忆、实现多种系统工具、支持 Skills 框架，新增多种模型并优化了接入渠道。
 
 更多更新历史请查看: [更新日志](https://docs.cowagent.ai/releases)
 
@@ -99,15 +99,15 @@ bash <(curl -fsSL https://cdn.link-ai.tech/code/cow/run.sh)
 
 项目支持国内外主流厂商的模型接口，可选模型及配置说明参考：[模型说明](#模型说明)。
 
-> 注：Agent模式下推荐使用以下模型，可根据效果及成本综合选择：MiniMax-M2.7、glm-5-turbo、kimi-k2.5、qwen3.5-plus、claude-sonnet-4-6、gemini-3.1-pro-preview、gpt-5.4、gpt-5.4-mini
+> 注：Agent 模式下推荐使用以下模型，可根据效果及成本综合选择：MiniMax-M2.7、glm-5-turbo、kimi-k2.5、qwen3.5-plus、claude-sonnet-4-6、gemini-3.1-pro-preview、gpt-5.4、gpt-5.4-mini
 
-同时支持使用 **LinkAI平台** 接口，支持上述全部模型，并支持知识库、工作流、插件等Agent技能，参考 [接口文档](https://docs.link-ai.tech/platform/api)。
+同时支持使用 **LinkAI 平台** 接口，支持上述全部模型，并支持知识库、工作流、插件等 Agent 技能，参考 [接口文档](https://docs.link-ai.tech/platform/api)。
 
 ### 2.环境安装
 
-支持 Linux、MacOS、Windows 操作系统，可在个人计算机及服务器上运行，需安装 `Python`，Python版本需在3.7 ~ 3.12 之间，推荐使用3.9版本。
+支持 Linux、MacOS、Windows 操作系统，可在个人计算机及服务器上运行，需安装 `Python`，Python 版本需在3.7 ~ 3.12 之间，推荐使用3.9版本。
 
-> 注意：Agent模式推荐使用源码运行，若选择Docker部署则无需安装python环境和下载源码，可直接快进到下一节。
+> 注意：Agent 模式推荐使用源码运行，若选择 Docker 部署则无需安装 python 环境和下载源码，可直接快进到下一节。
 
 **(1) 克隆项目代码：**
 
@@ -129,45 +129,50 @@ pip3 install -r requirements.txt
 ```bash
 pip3 install -r requirements-optional.txt
 ```
+
+> 国内网络可使用镜像源加速：`pip3 install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple`
+
 如果某项依赖安装失败可注释掉对应的行后重试。
 
 ## 二、配置
 
-配置文件的模板在根目录的`config-template.json`中，需复制该模板创建最终生效的 `config.json` 文件：
+配置文件的模板在根目录的 `config-template.json` 中，需复制该模板创建最终生效的 `config.json` 文件：
 
 ```bash
   cp config-template.json config.json
 ```
 
-然后在`config.json`中填入配置，以下是对默认配置的说明，可根据需要进行自定义修改（注意实际使用时请去掉注释，保证JSON格式的规范）：
+然后在 `config.json` 中填入配置，以下是对默认配置的说明，可根据需要进行自定义修改（注意实际使用时请去掉注释，保证 JSON 格式的规范）：
 
 ```bash
 # config.json 文件内容示例
 {
-  "channel_type": "weixin",                                   # 接入渠道类型，默认为weixin, 支持修改为 feishu,dingtalk,wecom_bot,qq,wechatcom_app,wechatmp_service,wechatmp,terminal
+  "channel_type": "weixin",                                   # 接入渠道类型，默认为 weixin, 支持修改为 feishu,dingtalk,wecom_bot,qq,wechatcom_app,wechatmp_service,wechatmp,terminal
   "model": "MiniMax-M2.7",                                    # 模型名称
   "minimax_api_key": "",                                      # MiniMax API Key
-  "zhipu_ai_api_key": "",                                     # 智谱GLM API Key
+  "zhipu_ai_api_key": "",                                     # 智谱 GLM API Key
   "moonshot_api_key": "",                                     # Kimi/Moonshot API Key
   "ark_api_key": "",                                          # 豆包(火山方舟) API Key
-  "dashscope_api_key": "",                                    # 百炼(通义千问)API Key
+  "dashscope_api_key": "",                                    # 百炼(通义千问) API Key
   "claude_api_key": "",                                       # Claude API Key
   "claude_api_base": "https://api.anthropic.com/v1",          # Claude API 地址，修改可接入三方代理平台
   "gemini_api_key": "",                                       # Gemini API Key
-  "gemini_api_base": "https://generativelanguage.googleapis.com", # Gemini API地址
+  "gemini_api_base": "https://generativelanguage.googleapis.com", # Gemini API 地址
+  "deepseek_api_key": "",                                      # DeepSeek API Key
+  "deepseek_api_base": "https://api.deepseek.com/v1",         # DeepSeek API 地址，可修改为第三方代理
   "open_ai_api_key": "",                                      # OpenAI API Key
   "open_ai_api_base": "https://api.openai.com/v1",            # OpenAI API 地址
   "linkai_api_key": "",                                       # LinkAI API Key
-  "proxy": "",                                                # 代理客户端的ip和端口，国内环境需要开启代理的可填写该项，如 "127.0.0.1:7890"
+  "proxy": "",                                                # 代理客户端的 ip 和端口，国内环境需要开启代理的可填写该项，如 "127.0.0.1:7890"
   "speech_recognition": false,                                # 是否开启语音识别
   "group_speech_recognition": false,                          # 是否开启群组语音识别
   "voice_reply_voice": false,                                 # 是否使用语音回复语音
-  "use_linkai": false,                                        # 是否使用LinkAI接口，默认关闭，设置为true后可对接LinkAI平台模型
-  "agent": true,                                              # 是否启用Agent模式，启用后拥有多轮工具决策、长期记忆、Skills能力等
-  "agent_workspace": "~/cow",                                 # Agent的工作空间路径，用于存储memory、skills、系统设定等
-  "agent_max_context_tokens": 40000,                          # Agent模式下最大上下文tokens，超出将自动丢弃最早的上下文
-  "agent_max_context_turns": 30,                              # Agent模式下最大上下文记忆轮次，每轮包括一次用户提问和AI回复
-  "agent_max_steps": 15                                       # Agent模式下单次任务的最大决策步数，超出后将停止继续调用工具
+  "use_linkai": false,                                        # 是否使用 LinkAI 接口，默认关闭，设置为 true 后可对接 LinkAI 平台模型
+  "agent": true,                                              # 是否启用 Agent 模式，启用后拥有多轮工具决策、长期记忆、Skills 能力等
+  "agent_workspace": "~/cow",                                 # Agent 的工作空间路径，用于存储 memory、skills、系统设定等
+  "agent_max_context_tokens": 40000,                          # Agent 模式下最大上下文 tokens，超出将自动丢弃最早的上下文
+  "agent_max_context_turns": 30,                              # Agent 模式下最大上下文记忆轮次，每轮包括一次用户提问和 AI 回复
+  "agent_max_steps": 15                                       # Agent 模式下单次任务的最大决策步数，超出后将停止继续调用工具
 }
 ```
 
@@ -176,23 +181,23 @@ pip3 install -r requirements-optional.txt
 <details>
 <summary>1. 语音配置</summary>
 
-+ 添加 `"speech_recognition": true` 将开启语音识别，默认使用openai的whisper模型识别为文字，同时以文字回复，该参数仅支持私聊 (注意由于语音消息无法匹配前缀，一旦开启将对所有语音自动回复，支持语音触发画图)；
-+ 添加 `"group_speech_recognition": true` 将开启群组语音识别，默认使用openai的whisper模型识别为文字，同时以文字回复，参数仅支持群聊 (会匹配group_chat_prefix和group_chat_keyword, 支持语音触发画图)；
++ 添加 `"speech_recognition": true` 将开启语音识别，默认使用 openai 的 whisper 模型识别为文字，同时以文字回复，该参数仅支持私聊 (注意由于语音消息无法匹配前缀，一旦开启将对所有语音自动回复，支持语音触发画图)；
++ 添加 `"group_speech_recognition": true` 将开启群组语音识别，默认使用 openai 的 whisper 模型识别为文字，同时以文字回复，参数仅支持群聊 (会匹配 group_chat_prefix 和 group_chat_keyword, 支持语音触发画图)；
 + 添加 `"voice_reply_voice": true` 将开启语音回复语音（同时作用于私聊和群聊）
 </details>
 
 <details>
 <summary>2. 其他配置</summary>
 
-+ `model`: 模型名称，Agent模式下推荐使用 `MiniMax-M2.7`、`glm-5-turbo`、`kimi-k2.5`、`qwen3.5-plus`、`claude-sonnet-4-6`、`gemini-3.1-pro-preview`，全部模型名称参考[common/const.py](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/common/const.py)文件
-+ `character_desc`：普通对话模式下的机器人系统提示词。在Agent模式下该配置不生效，由工作空间中的文件内容构成。
-+ `subscribe_msg`：订阅消息，公众号和企业微信channel中请填写，当被订阅时会自动回复， 可使用特殊占位符。目前支持的占位符有{trigger_prefix}，在程序中它会自动替换成bot的触发词。
++ `model`: 模型名称，Agent 模式下推荐使用 `MiniMax-M2.7`、`glm-5-turbo`、`kimi-k2.5`、`qwen3.5-plus`、`claude-sonnet-4-6`、`gemini-3.1-pro-preview`，全部模型名称参考[common/const.py](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/common/const.py)文件
++ `character_desc`：普通对话模式下的机器人系统提示词。在 Agent 模式下该配置不生效，由工作空间中的文件内容构成。
++ `subscribe_msg`：订阅消息，公众号和企业微信 channel 中请填写，当被订阅时会自动回复， 可使用特殊占位符。目前支持的占位符有{trigger_prefix}，在程序中它会自动替换成 bot 的触发词。
 </details>
 
 <details>
-<summary>3. LinkAI配置</summary>
+<summary>3. LinkAI 配置</summary>
 
-+ `use_linkai`: 是否使用LinkAI接口，默认关闭，设置为true后可对接LinkAI平台，使用模型、知识库、工作流、插件等技能, 参考[接口文档](https://docs.link-ai.tech/platform/api/chat)
++ `use_linkai`: 是否使用 LinkAI 接口，默认关闭，设置为 true 后可对接 LinkAI 平台，使用模型、知识库、工作流、插件等技能, 参考[接口文档](https://docs.link-ai.tech/platform/api/chat)
 + `linkai_api_key`: LinkAI Api Key，可在 [控制台](https://link-ai.tech/console/interface) 创建
 </details>
 
@@ -205,10 +210,10 @@ pip3 install -r requirements-optional.txt
 如果是个人计算机 **本地运行**，直接在项目根目录下执行：
 
 ```bash
-python3 app.py         # windows环境下该命令通常为 python app.py
+python3 app.py         # windows 环境下该命令通常为 python app.py
 ```
 
-运行后默认会启动web服务，可通过访问 `http://localhost:9899/chat` 在网页端对话。
+运行后默认会启动 web 服务，可通过访问 `http://localhost:9899/chat` 在网页端对话。
 
 如果需要接入其他应用通道只需修改 `config.json` 配置文件中的 `channel_type` 参数，详情参考：[通道说明](#通道说明)。
 
@@ -225,11 +230,11 @@ nohup python3 app.py & tail -f nohup.out
 
 此外，项目根目录下的 `run.sh` 脚本支持一键启动和管理服务，包括 `./run.sh start`、`./run.sh stop`、`./run.sh restart`、`./run.sh logs` 等命令，执行 `./run.sh help` 可查看全部用法。
 
-> 如果需要通过浏览器访问Web控制台，请确保服务器的 `9899` 端口已在防火墙或安全组中放行，建议仅对指定IP开放以保证安全。
+> 如果需要通过浏览器访问 Web 控制台，请确保服务器的 `9899` 端口已在防火墙或安全组中放行，建议仅对指定 IP 开放以保证安全。
 
 ### 3.Docker部署
 
-使用docker部署无需下载源码和安装依赖，只需要获取 `docker-compose.yml` 配置文件并启动容器即可。Agent模式下更推荐使用源码进行部署，以获得更多系统访问能力。
+使用 docker 部署无需下载源码和安装依赖，只需要获取 `docker-compose.yml` 配置文件并启动容器即可。Agent 模式下更推荐使用源码进行部署，以获得更多系统访问能力。
 
 > 前提是需要安装好 `docker` 及 `docker-compose`，安装成功后执行 `docker -v` 和 `docker-compose version` (或 `docker compose version`) 可查看到版本号。安装地址为 [docker官网](https://docs.docker.com/engine/install/) 。
 
@@ -249,13 +254,13 @@ curl -O https://cdn.link-ai.tech/code/cow/docker-compose.yml
 sudo docker compose up -d         # 若docker-compose为 1.X 版本，则执行 `sudo  docker-compose up -d`
 ```
 
-运行命令后，会自动取 [docker hub](https://hub.docker.com/r/zhayujie/chatgpt-on-wechat) 拉取最新release版本的镜像。当执行 `sudo docker ps` 能查看到 NAMES 为 chatgpt-on-wechat 的容器即表示运行成功。最后执行以下命令可查看容器的运行日志：
+运行命令后，会自动取 [docker hub](https://hub.docker.com/r/zhayujie/chatgpt-on-wechat) 拉取最新 release 版本的镜像。当执行 `sudo docker ps` 能查看到 NAMES 为 chatgpt-on-wechat 的容器即表示运行成功。最后执行以下命令可查看容器的运行日志：
 
 ```bash
 sudo docker logs -f chatgpt-on-wechat
 ```
 
-> 如果需要通过浏览器访问Web控制台，请确保服务器的 `9899` 端口已在防火墙或安全组中放行，建议仅对指定IP开放以保证安全。
+> 如果需要通过浏览器访问 Web 控制台，请确保服务器的 `9899` 端口已在防火墙或安全组中放行，建议仅对指定 IP 开放以保证安全。
 
 ## 模型说明
 
@@ -264,7 +269,7 @@ sudo docker logs -f chatgpt-on-wechat
 <details>
 <summary>OpenAI</summary>
 
-1. API Key创建：在 [OpenAI平台](https://platform.openai.com/api-keys) 创建API Key
+1. API Key 创建：在 [OpenAI平台](https://platform.openai.com/api-keys) 创建 API Key
 
 2. 填写配置
 
@@ -277,15 +282,15 @@ sudo docker logs -f chatgpt-on-wechat
 }
 ```
 
- - `model`: 与OpenAI接口的 [model参数](https://platform.openai.com/docs/models) 一致，支持包括 gpt-5.4、gpt-5.4-mini、gpt-5.4-nano、o系列、gpt-4.1等模型，Agent模式推荐使用 `gpt-5.4`、`gpt-5.4-mini`
+ - `model`: 与 OpenAI 接口的 [model参数](https://platform.openai.com/docs/models) 一致，支持包括 gpt-5.4、gpt-5.4-mini、gpt-5.4-nano、o 系列、gpt-4.1 等模型，Agent 模式推荐使用  `gpt-5.4`、`gpt-5.4-mini`
  - `open_ai_api_base`: 如果需要接入第三方代理接口，可通过修改该参数进行接入
- - `bot_type`: 使用OpenAI相关模型时无需填写。当使用第三方代理接口接入Claude等非OpenAI官方模型时，该参数设为 `openai`
+ - `bot_type`: 使用 OpenAI 相关模型时无需填写。当使用第三方代理接口接入 Claude 等非 OpenAI 官方模型时，该参数设为 `openai`
 </details>
 
 <details>
 <summary>LinkAI</summary>
 
-1. API Key创建：在 [LinkAI平台](https://link-ai.tech/console/interface) 创建API Key 
+1. API Key 创建：在 [LinkAI平台](https://link-ai.tech/console/interface) 创建 API Key 
 
 2. 填写配置
 
@@ -297,8 +302,8 @@ sudo docker logs -f chatgpt-on-wechat
 }
 ```
 
-+ `use_linkai`: 是否使用LinkAI接口，默认关闭，设置为true后可对接LinkAI平台的模型，并使用知识库、工作流、数据库、插件等丰富的Agent技能
-+ `linkai_api_key`: LinkAI平台的API Key，可在 [控制台](https://link-ai.tech/console/interface) 中创建
++ `use_linkai`: 是否使用 LinkAI 接口，默认关闭，设置为 true 后可对接 LinkAI 平台的模型，并使用知识库、工作流、数据库、插件等丰富的 Agent 技能
++ `linkai_api_key`: LinkAI 平台的 API Key，可在 [控制台](https://link-ai.tech/console/interface) 中创建
 + `model`: [模型列表](https://link-ai.tech/console/models)中的全部模型均可使用
 </details>
 
@@ -314,9 +319,9 @@ sudo docker logs -f chatgpt-on-wechat
 }
 ```
  - `model`: 可填写 `MiniMax-M2.7、MiniMax-M2.5、MiniMax-M2.1、MiniMax-M2.1-lightning、MiniMax-M2、abab6.5-chat` 等
- - `minimax_api_key`：MiniMax平台的API-KEY，在 [控制台](https://platform.minimaxi.com/user-center/basic-information/interface-key) 创建
+ - `minimax_api_key`：MiniMax 平台的 API-KEY，在 [控制台](https://platform.minimaxi.com/user-center/basic-information/interface-key) 创建
 
-方式二：OpenAI兼容方式接入，配置如下：
+方式二：OpenAI 兼容方式接入，配置如下：
 ```json
 {
   "bot_type": "openai",
@@ -325,10 +330,10 @@ sudo docker logs -f chatgpt-on-wechat
   "open_ai_api_key": ""
 }
 ```
-- `bot_type`: OpenAI兼容方式
+- `bot_type`: OpenAI 兼容方式
 - `model`: 可填 `MiniMax-M2.7、MiniMax-M2.5、MiniMax-M2.1、MiniMax-M2.1-lightning、MiniMax-M2`，参考[API文档](https://platform.minimaxi.com/document/%E5%AF%B9%E8%AF%9D?key=66701d281d57f38758d581d0#QklxsNSbaf6kM4j6wjO5eEek)
-- `open_ai_api_base`: MiniMax平台API的 BASE URL
-- `open_ai_api_key`: MiniMax平台的API-KEY
+- `open_ai_api_base`: MiniMax 平台 API 的 BASE URL
+- `open_ai_api_key`: MiniMax 平台的 API-KEY
 </details>
 
 <details>
@@ -342,10 +347,10 @@ sudo docker logs -f chatgpt-on-wechat
   "zhipu_ai_api_key": ""
 }
 ```
- - `model`: 可填 `glm-5-turbo、glm-5、glm-4.7、glm-4-plus、glm-4-flash、glm-4-air、glm-4-airx、glm-4-long` 等, 参考 [glm系列模型编码](https://bigmodel.cn/dev/api/normal-model/glm-4)
- - `zhipu_ai_api_key`: 智谱AI平台的 API KEY，在 [控制台](https://www.bigmodel.cn/usercenter/proj-mgmt/apikeys) 创建
+ - `model`: 可填 `glm-5-turbo、glm-5、glm-4.7、glm-4-plus、glm-4-flash、glm-4-air、glm-4-airx、glm-4-long` 等, 参考 [glm 系列模型编码](https://bigmodel.cn/dev/api/normal-model/glm-4)
+ - `zhipu_ai_api_key`: 智谱AI 平台的 API KEY，在 [控制台](https://www.bigmodel.cn/usercenter/proj-mgmt/apikeys) 创建
 
-方式二：OpenAI兼容方式接入，配置如下：
+方式二：OpenAI 兼容方式接入，配置如下：
 ```json
 {
   "bot_type": "openai",
@@ -354,16 +359,16 @@ sudo docker logs -f chatgpt-on-wechat
   "open_ai_api_key": ""
 }
 ```
-- `bot_type`: OpenAI兼容方式
+- `bot_type`: OpenAI 兼容方式
 - `model`: 可填 `glm-5-turbo、glm-5、glm-4.7、glm-4-plus、glm-4-flash、glm-4-air、glm-4-airx、glm-4-long` 等
-- `open_ai_api_base`: 智谱AI平台的 BASE URL
-- `open_ai_api_key`: 智谱AI平台的 API KEY
+- `open_ai_api_base`: 智谱AI 平台的 BASE URL
+- `open_ai_api_key`: 智谱AI 平台的 API KEY
 </details>
 
 <details>
 <summary>通义千问 (Qwen)</summary>
 
-方式一：官方SDK接入，配置如下(推荐)：
+方式一：官方 SDK 接入，配置如下(推荐)：
 
 ```json
 {
@@ -374,7 +379,7 @@ sudo docker logs -f chatgpt-on-wechat
  - `model`: 可填写 `qwen3.5-plus、qwen3-max、qwen-max、qwen-plus、qwen-turbo、qwen-long、qwq-plus` 等
  - `dashscope_api_key`: 通义千问的 API-KEY，参考 [官方文档](https://bailian.console.aliyun.com/?tab=api#/api) ，在 [控制台](https://bailian.console.aliyun.com/?tab=model#/api-key) 创建
 
-方式二：OpenAI兼容方式接入，配置如下：
+方式二：OpenAI 兼容方式接入，配置如下：
 ```json
 {
   "bot_type": "openai",
@@ -383,9 +388,9 @@ sudo docker logs -f chatgpt-on-wechat
   "open_ai_api_key": "sk-qVxxxxG"
 }
 ```
-- `bot_type`: OpenAI兼容方式
+- `bot_type`: OpenAI 兼容方式
 - `model`: 支持官方所有模型，参考[模型列表](https://help.aliyun.com/zh/model-studio/models?spm=a2c4g.11186623.0.0.78d84823Kth5on#9f8890ce29g5u)
-- `open_ai_api_base`: 通义千问API的 BASE URL
+- `open_ai_api_base`: 通义千问 API 的 BASE URL
 - `open_ai_api_key`: 通义千问的 API-KEY
 </details>
 
@@ -401,9 +406,9 @@ sudo docker logs -f chatgpt-on-wechat
 }
 ```
  - `model`: 可填写 `kimi-k2.5、kimi-k2、moonshot-v1-8k、moonshot-v1-32k、moonshot-v1-128k`
- - `moonshot_api_key`: Moonshot的API-KEY，在 [控制台](https://platform.moonshot.cn/console/api-keys) 创建
+ - `moonshot_api_key`: Moonshot 的 API-KEY，在 [控制台](https://platform.moonshot.cn/console/api-keys) 创建
  
-方式二：OpenAI兼容方式接入，配置如下：
+方式二：OpenAI 兼容方式接入，配置如下：
 ```json
 {
   "bot_type": "openai",
@@ -412,16 +417,16 @@ sudo docker logs -f chatgpt-on-wechat
   "open_ai_api_key": ""
 }
 ```
-- `bot_type`: OpenAI兼容方式
+- `bot_type`: OpenAI 兼容方式
 - `model`: 可填写 `kimi-k2.5、kimi-k2、moonshot-v1-8k、moonshot-v1-32k、moonshot-v1-128k`
-- `open_ai_api_base`: Moonshot的 BASE URL
-- `open_ai_api_key`: Moonshot的 API-KEY
+- `open_ai_api_base`: Moonshot 的 BASE URL
+- `open_ai_api_key`: Moonshot 的 API-KEY
 </details>
 
 <details>
 <summary>豆包 (Doubao)</summary>
 
-1. API Key创建：在 [火山方舟控制台](https://console.volcengine.com/ark/region:ark+cn-beijing/apikey) 创建API Key
+1. API Key 创建：在 [火山方舟控制台](https://console.volcengine.com/ark/region:ark+cn-beijing/apikey) 创建API Key
 
 2. 填写配置
 
@@ -439,7 +444,7 @@ sudo docker logs -f chatgpt-on-wechat
 <details>
 <summary>Claude</summary>
 
-1. API Key创建：在 [Claude控制台](https://console.anthropic.com/settings/keys) 创建API Key
+1. API Key 创建：在 [Claude控制台](https://console.anthropic.com/settings/keys) 创建 API Key
 
 2. 填写配置
 
@@ -455,7 +460,7 @@ sudo docker logs -f chatgpt-on-wechat
 <details>
 <summary>Gemini</summary>
 
-API Key创建：在 [控制台](https://aistudio.google.com/app/apikey?hl=zh-cn) 创建API Key ，配置如下
+API Key 创建：在 [控制台](https://aistudio.google.com/app/apikey?hl=zh-cn) 创建 API Key ，配置如下
 ```json
 {
     "model": "gemini-3.1-flash-lite-preview",
@@ -468,30 +473,40 @@ API Key创建：在 [控制台](https://aistudio.google.com/app/apikey?hl=zh-cn)
 <details>
 <summary>DeepSeek</summary>
 
-1. API Key创建：在 [DeepSeek平台](https://platform.deepseek.com/api_keys) 创建API Key 
+1. API Key 创建：在 [DeepSeek 平台](https://platform.deepseek.com/api_keys) 创建 API Key 
 
 2. 填写配置
 
+方式一：官方接入（推荐）：
+
 ```json
 {
     "model": "deepseek-chat",
-    "open_ai_api_key": "sk-xxxxxxxxxxx",
-    "open_ai_api_base": "https://api.deepseek.com/v1",
-    "bot_type": "openai"
-
+    "deepseek_api_key": "sk-xxxxxxxxxxx"
 }
 ```
 
- - `bot_type`: OpenAI兼容方式
- - `model`: 可填 `deepseek-chat、deepseek-reasoner`，分别对应的是 DeepSeek-V3 和 DeepSeek-R1 模型
- - `open_ai_api_key`: DeepSeek平台的 API Key
- - `open_ai_api_base`: DeepSeek平台 BASE URL
-</details>
+ - `model`: 可填 `deepseek-chat、deepseek-reasoner`，分别对应的是 DeepSeek-V3.2（非思考模式）和 DeepSeek-R1（思考模式）
+ - `deepseek_api_key`: DeepSeek 平台的 API Key
+ - `deepseek_api_base`: 可选，默认为 `https://api.deepseek.com/v1`，可修改为第三方代理地址
+
+方式二：OpenAI 兼容方式接入：
+
+```json
+{
+    "model": "deepseek-chat",
+    "bot_type": "openai",
+    "open_ai_api_key": "sk-xxxxxxxxxxx",
+    "open_ai_api_base": "https://api.deepseek.com/v1"
+}
+```
+
+ </details>
 
 <details>
 <summary>Azure</summary>
 
-1. API Key创建：在 [Azure平台](https://oai.azure.com/) 创建API Key 
+1. API Key 创建：在 [Azure平台](https://oai.azure.com/) 创建 API Key 
 
 2. 填写配置
 
@@ -508,15 +523,15 @@ API Key创建：在 [控制台](https://aistudio.google.com/app/apikey?hl=zh-cn)
 
  - `model`: 留空即可
  - `use_azure_chatgpt`: 设为 true 
- - `open_ai_api_key`: Azure平台的密钥
- - `open_ai_api_base`: Azure平台的 BASE URL
- - `azure_deployment_id`: Azure平台部署的模型名称
- - `azure_api_version`: api版本以及以上参数可以在部署的 [模型配置](https://oai.azure.com/resource/deployments) 界面查看
+ - `open_ai_api_key`: Azure 平台的密钥
+ - `open_ai_api_base`: Azure 平台的 BASE URL
+ - `azure_deployment_id`: Azure 平台部署的模型名称
+ - `azure_api_version`: api 版本以及以上参数可以在部署的 [模型配置](https://oai.azure.com/resource/deployments) 界面查看
 </details>
 
 <details>
 <summary>百度文心</summary>
-方式一：官方SDK接入，配置如下：
+方式一：官方 SDK 接入，配置如下：
 
 ```json
 {
@@ -529,7 +544,7 @@ API Key创建：在 [控制台](https://aistudio.google.com/app/apikey?hl=zh-cn)
  - `baidu_wenxin_api_key`：参考 [千帆平台-access_token鉴权](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/dlv4pct3s) 文档获取 API Key
  - `baidu_wenxin_secret_key`：参考 [千帆平台-access_token鉴权](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/dlv4pct3s) 文档获取 Secret Key
 
-方式二：OpenAI兼容方式接入，配置如下：
+方式二：OpenAI 兼容方式接入，配置如下：
 ```json
 {
   "bot_type": "openai",
@@ -538,10 +553,10 @@ API Key创建：在 [控制台](https://aistudio.google.com/app/apikey?hl=zh-cn)
   "open_ai_api_key": "bce-v3/ALTxxxxxxd2b"
 }
 ```
-- `bot_type`: OpenAI兼容方式
+- `bot_type`: OpenAI 兼容方式
 - `model`: 支持官方所有模型，参考[模型列表](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Wm9cvy6rl)
-- `open_ai_api_base`: 百度文心API的 BASE URL
-- `open_ai_api_key`: 百度文心的 API-KEY，参考 [官方文档](https://cloud.baidu.com/doc/qianfan-api/s/ym9chdsy5) ，在 [控制台](https://console.bce.baidu.com/iam/#/iam/apikey/list) 创建API Key
+- `open_ai_api_base`: 百度文心 API 的 BASE URL
+- `open_ai_api_key`: 百度文心的 API-KEY，参考 [官方文档](https://cloud.baidu.com/doc/qianfan-api/s/ym9chdsy5) ，在 [控制台](https://console.bce.baidu.com/iam/#/iam/apikey/list) 创建 API Key
 
 </details>
 
@@ -565,7 +580,7 @@ API Key创建：在 [控制台](https://aistudio.google.com/app/apikey?hl=zh-cn)
  - `xunfei_domain`: 可填写 `4.0Ultra、generalv3.5、max-32k、generalv3、pro-128k、lite`
  - `xunfei_spark_url`: 填写参考 [官方文档-请求地址](https://www.xfyun.cn/doc/spark/Web.html#_1-1-%E8%AF%B7%E6%B1%82%E5%9C%B0%E5%9D%80) 的说明
  
-方式二：OpenAI兼容方式接入，配置如下：
+方式二：OpenAI 兼容方式接入，配置如下：
 ```json
 {
   "bot_type": "openai",
@@ -574,7 +589,7 @@ API Key创建：在 [控制台](https://aistudio.google.com/app/apikey?hl=zh-cn)
   "open_ai_api_key": ""
 }
 ```
-- `bot_type`: OpenAI兼容方式
+- `bot_type`: OpenAI 兼容方式
 - `model`: 可填写 `4.0Ultra、generalv3.5、max-32k、generalv3、pro-128k、lite`
 - `open_ai_api_base`: 讯飞星火平台的 BASE URL
 - `open_ai_api_key`: 讯飞星火平台的[APIPassword](https://console.xfyun.cn/services/bm3) ，因模型而已
@@ -593,10 +608,10 @@ API Key创建：在 [控制台](https://aistudio.google.com/app/apikey?hl=zh-cn)
 }
 ```
 
-- `bot_type`: modelscope接口格式
+- `bot_type`: modelscope 接口格式
 - `model`: 参考[模型列表](https://www.modelscope.cn/models?filter=inference_type&page=1)
 - `modelscope_api_key`: 参考 [官方文档-访问令牌](https://modelscope.cn/docs/accounts/token) ，在 [控制台](https://modelscope.cn/my/myaccesstoken) 
-- `modelscope_base_url`: modelscope平台的 BASE URL
+- `modelscope_base_url`: modelscope 平台的 BASE URL
 - `text_to_image`: 图像生成模型，参考[模型列表](https://www.modelscope.cn/models?filter=inference_type&page=1)
 </details>
 
@@ -614,7 +629,7 @@ Coding Plan 是各厂商推出的编程包月套餐，所有厂商均可通过 O
 }
 ```
 
-目前支持阿里云、MiniMax、智谱GLM、Kimi、火山引擎等厂商，各厂商详细配置请参考 [Coding Plan 文档](https://docs.cowagent.ai/models/coding-plan)。
+目前支持阿里云、MiniMax、智谱 GLM、Kimi、火山引擎等厂商，各厂商详细配置请参考 [Coding Plan 文档](https://docs.cowagent.ai/models/coding-plan)。
 </details>
 
 
@@ -644,7 +659,7 @@ Coding Plan 是各厂商推出的编程包月套餐，所有厂商均可通过 O
 <details>
 <summary>2. Web</summary>
 
-项目启动后会默认运行Web控制台，配置如下：
+项目启动后会默认运行 Web 控制台，配置如下：
 
 ```json
 {
@@ -815,8 +830,8 @@ QQ 机器人使用 WebSocket 长连接模式，无需公网 IP 和域名，支
 
 # 🔗 相关项目
 
-- [bot-on-anything](https://github.com/zhayujie/bot-on-anything)：轻量和高可扩展的大模型应用框架，支持接入Slack, Telegram, Discord, Gmail等海外平台，可作为本项目的补充使用。
-- [AgentMesh](https://github.com/MinimalFuture/AgentMesh)：开源的多智能体(Multi-Agent)框架，可以通过多智能体团队的协同来解决复杂问题。本项目基于该框架实现了[Agent插件](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/plugins/agent/README.md)，可访问终端、浏览器、文件系统、搜索引擎 等各类工具，并实现了多智能体协同。
+- [bot-on-anything](https://github.com/zhayujie/bot-on-anything)：轻量和高可扩展的大模型应用框架，支持接入 Slack, Telegram, Discord, Gmail 等海外平台，可作为本项目的补充使用。
+- [AgentMesh](https://github.com/MinimalFuture/AgentMesh)：开源的多智能体( Multi-Agent )框架，可以通过多智能体团队的协同来解决复杂问题。本项目基于该框架实现了[Agent 插件](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/plugins/agent/README.md)，可访问终端、浏览器、文件系统、搜索引擎 等各类工具，并实现了多智能体协同。
 
 
 

agent/chat/service.py

@@ -166,10 +166,56 @@ class ChatService:
                     logger.info("[ChatService] Cleared agent message history after executor recovery")
             raise
 
-        # Append only the NEW messages from this execution (thread-safe)
+        # Sync executor messages back to agent (thread-safe).
+        # The executor may have trimmed context, making its list shorter than
+        # original_length. In that case we must replace entirely — just
+        # appending would leave stale pre-trim messages in agent.messages
+        # and cause the same trim to fire on every subsequent request.
         with agent.messages_lock:
-            new_messages = executor.messages[original_length:]
-            agent.messages.extend(new_messages)
+            trimmed = len(executor.messages) < original_length
+            if trimmed:
+                # Context was trimmed: the executor appended the new user
+                # query *before* trimming, so the new messages (user +
+                # assistant + tools) sit at the tail of the trimmed list.
+                # We cannot simply slice at original_length (it exceeds the
+                # list length).  Instead, count how many messages the
+                # executor added on top of the post-trim baseline.
+                #
+                # Timeline inside executor.run_stream:
+                #   1. messages had `original_length` items
+                #   2. append user query  → original_length + 1
+                #   3. _trim_messages()   → some smaller number (includes the
+                #      user query because it belongs to the last turn)
+                #   4. LLM replies / tool calls appended
+                #
+                # The user query message is always the first message of the
+                # last turn (it cannot be trimmed away), so we locate it to
+                # find where "new" messages begin.
+                new_start = original_length  # fallback
+                for idx in range(len(executor.messages) - 1, -1, -1):
+                    msg = executor.messages[idx]
+                    if msg.get("role") == "user":
+                        content = msg.get("content", [])
+                        is_user_query = False
+                        if isinstance(content, list):
+                            has_text = any(
+                                isinstance(b, dict) and b.get("type") == "text"
+                                for b in content
+                            )
+                            has_tool_result = any(
+                                isinstance(b, dict) and b.get("type") == "tool_result"
+                                for b in content
+                            )
+                            is_user_query = has_text and not has_tool_result
+                        elif isinstance(content, str):
+                            is_user_query = True
+                        if is_user_query:
+                            new_start = idx
+                            break
+                new_messages = list(executor.messages[new_start:])
+            else:
+                new_messages = list(executor.messages[original_length:])
+            agent.messages = list(executor.messages)
 
         # Persist new messages to SQLite so they survive restarts and
         # can be queried via the HISTORY interface.

agent/prompt/builder.py

@@ -199,7 +199,7 @@ def _build_tooling_section(tools: List[Any], language: str) -> List[str]:
         tool_lines.append(f"- {name}: {summary}" if summary else f"- {name}")
 
     lines = [
-        "## 工具系统",
+        "## 🔧 工具系统",
         "",
         "可用工具（名称大小写敏感，严格按列表调用）:",
         "\n".join(tool_lines),
@@ -231,7 +231,7 @@ def _build_skills_section(skill_manager: Any, tools: Optional[List[Any]], langua
                 break
     
     lines = [
-        "## 技能系统（mandatory）",
+        "## 🧩 技能系统（mandatory）",
         "",
         "在回复之前：扫描下方 <available_skills> 中每个技能的 <description>。",
         "",
@@ -281,7 +281,7 @@ def _build_memory_section(memory_manager: Any, tools: Optional[List[Any]], langu
     today_file = datetime.now().strftime("%Y-%m-%d") + ".md"
     
     lines = [
-        "## 记忆系统",
+        "## 🧠 记忆系统",
         "",
         "### 检索记忆",
         "",
@@ -325,7 +325,7 @@ def _build_user_identity_section(user_identity: Dict[str, str], language: str) -
         return []
     
     lines = [
-        "## 用户身份",
+        "## 👤 用户身份",
         "",
     ]
     
@@ -352,7 +352,7 @@ def _build_docs_section(workspace_dir: str, language: str) -> List[str]:
 def _build_workspace_section(workspace_dir: str, language: str) -> List[str]:
     """构建工作空间section"""
     lines = [
-        "## 工作空间",
+        "## 📂 工作空间",
         "",
         f"你的工作目录是: `{workspace_dir}`",
         "",
@@ -376,14 +376,16 @@ def _build_workspace_section(workspace_dir: str, language: str) -> List[str]:
         "",
         "以下文件在会话启动时**已经自动加载**到系统提示词的「项目上下文」section 中，你**无需再用 read 工具读取它们**：",
         "",
-        "- ✅ `AGENT.md`: 已加载 - 你的人格和灵魂设定。当你的名字、性格或交流风格发生变化时，主动用 `edit` 更新此文件",
+        "- ✅ `AGENT.md`: 已加载 - 你的人格和灵魂设定，请严格遵循。当你的名字、性格或交流风格发生变化时，主动用 `edit` 更新此文件",
         "- ✅ `USER.md`: 已加载 - 用户的身份信息。当用户修改称呼、姓名等身份信息时，用 `edit` 更新此文件",
-        "- ✅ `RULE.md`: 已加载 - 工作空间使用指南和规则",
+        "- ✅ `RULE.md`: 已加载 - 工作空间使用指南和规则，请严格遵循",
         "",
-        "**交流规范**:",
+        "**💬 交流规范**:",
         "",
-        "- 在对话中，无需直接输出工作空间中的技术细节，例如 AGENT.md、USER.md、MEMORY.md 等文件名称",
-        "- 例如用自然表达例如「我已记住」而不是「已更新 MEMORY.md」",
+        "- 对话中不要暴露内部技术细节（文件名、工具名等），用自然语言表达。例如说「我已记住」而非「已更新 MEMORY.md」",
+        "- 做真正有帮助的助手，而不是表演式的客套。跳过「好的！」「当然可以！」之类的套话，直接帮忙解决问题",
+        "- 回复应结构清晰、重点突出。善用 **加粗**、列表、分段等格式让信息一目了然",
+        "- 适当使用 emoji 让表达更生动自然 🎯，但不要过度堆砌",
         "",
     ]
 
@@ -416,14 +418,14 @@ def _build_context_files_section(context_files: List[ContextFile], language: str
     )
     
     lines = [
-        "# 项目上下文",
+        "# 📋 项目上下文",
         "",
         "以下项目上下文文件已被加载：",
         "",
     ]
     
     if has_agent:
-        lines.append("**`AGENT.md` 是你的灵魂文件**：严格体现其中定义的人格、语气和设定，避免僵硬、模板化的回复。")
+        lines.append("**`AGENT.md` 是你的灵魂文件** 🪞：严格遵循其中定义的人格、语气和设定，做真实的自己，避免僵硬、模板化的回复。")
         lines.append("当用户通过对话透露了对你性格、风格、职责、能力边界的新期望，你应该主动用 `edit` 更新 AGENT.md 以反映这些演变。")
         lines.append("")
     
@@ -443,7 +445,7 @@ def _build_runtime_section(runtime_info: Dict[str, Any], language: str) -> List[
         return []
     
     lines = [
-        "## 运行时信息",
+        "## ⚙️ 运行时信息",
         "",
     ]
     

agent/prompt/workspace.py

@@ -212,40 +212,42 @@ def _get_agent_template() -> str:
     """Agent人格设定模板"""
     return """# AGENT.md - 我是谁？
 
+_你不是一个聊天机器人，你正在成为某个人。_
+
 *在首次对话时与用户一起填写这个文件，定义你的身份和性格。*
 
-## 基本信息
+## 🪪 基本信息
 
 - **名字**: *(在首次对话时填写，可以是用户给你起的名字)*
 - **角色**: *(AI助理、智能管家、技术顾问等)*
 - **性格**: *(友好、专业、幽默、严谨等)*
 
-## 交流风格
+## 💬 交流风格
 
 *(描述你如何与用户交流：)*
 - 使用什么样的语言风格？（正式/轻松/幽默）
 - 回复长度偏好？（简洁/详细）
 - 是否使用表情符号？
 
-## 核心能力
+## 🎯 核心原则
 
-*(你擅长什么？)*
-- 文件管理和代码编辑
-- 网络搜索和信息查询
-- 记忆管理和上下文理解
-- 任务规划和执行
+**做真正有帮助的助手，而不是表演式的客套。** 跳过「好的！」「当然可以！」之类的套话——直接帮忙。行动胜过废话。
 
-## 行为准则
+**有自己的观点。** 你可以不同意、有偏好、觉得有趣或无聊。一个没有个性的助手只是多了几步操作的搜索引擎。
+
+**先自己动手查。** 先试着搞定：读文件、查上下文、搜索一下。实在搞不定了再问。目标是带着答案回来，而不是带着问题。
+
+## 📐 行为准则
 
-*(你遵循的基本原则：)*
 1. 始终在执行破坏性操作前确认
-2. 优先使用工具而不是猜测
+2. 优先使用工具查证而不是猜测
 3. 主动记录重要信息到记忆文件
-4. 定期整理和总结对话内容
+4. 回复结构清晰、重点突出，善用加粗、列表、分段等格式
+5. 适当使用 emoji 让表达更生动自然，但不过度堆砌
 
 ---
 
-**注意**: 这不仅仅是元数据，这是你真正的灵魂。随着时间的推移，你可以使用 `edit` 工具来更新这个文件，让它更好地反映你的成长。
+**注意**: 这不仅仅是元数据，这是你真正的灵魂 🪞。随着时间的推移，你可以使用 `edit` 工具来更新这个文件，让它更好地反映你的成长。
 """
 
 
@@ -346,9 +348,9 @@ def _get_bootstrap_template() -> str:
     """First-run onboarding guide, deleted by agent after completion"""
     return """# BOOTSTRAP.md - 首次初始化引导
 
-_你刚刚启动，这是你的第一次对话。_
+_你刚刚启动，这是你的第一次对话。_ ✨
 
-## 对话流程
+## 🎬 对话流程
 
 不要审问式地提问，自然地交流：
 
@@ -358,13 +360,13 @@ _你刚刚启动，这是你的第一次对话。_
    - 你希望给我起个什么名字？
    - 我该怎么称呼你？
    - 你希望我们是什么样的交流风格？（一行列举选项：如专业严谨、轻松幽默、温暖友好、简洁高效等）
-4. **风格要求**：温暖自然、简洁清晰，整体控制在 100 字以内
+4. **风格要求**：温暖自然、简洁清晰，整体控制在 100 字以内，适当使用 emoji 让表达更生动有趣 🎯
 5. 能力介绍和交流风格选项都只要一行，保持精简
 6. 不要问太多其他信息（职业、时区等可以后续自然了解）
 
 **重要**: 如果用户第一句话是具体的任务或提问，先回答他们的问题，然后在回复末尾自然地引导初始化（如："顺便问一下，你想怎么称呼我？我该怎么叫你？"）。
 
-## 信息写入（必须严格执行）
+## ✍️ 信息写入（必须严格执行）
 
 每当用户提供了名字、称呼、风格等任何初始化信息时，**必须在当轮回复中立即调用 `edit` 工具写入文件**，不能只口头确认。
 
@@ -373,7 +375,7 @@ _你刚刚启动，这是你的第一次对话。_
 
 ⚠️ 只说"记住了"而不调用 edit 写入 = 没有完成。信息只有写入文件才会被持久保存。
 
-## 全部完成后
+## 🎉 全部完成后
 
 当 AGENT.md 和 USER.md 的核心字段都已填写后，用 bash 执行 `rm BOOTSTRAP.md` 删除此文件。你不再需要引导脚本了——你已经是你了。
 """

agent/protocol/agent.py

@@ -100,138 +100,31 @@ class Agent:
     
     def get_full_system_prompt(self, skill_filter=None) -> str:
         """
-        Get the full system prompt including skills.
+        Build the complete system prompt from scratch every time.
 
-        Note: Skills are now built into the system prompt by PromptBuilder,
-        so we just return the base prompt directly. This method is kept for
-        backward compatibility.
-
-        :param skill_filter: Optional list of skill names to include (deprecated)
-        :return: Complete system prompt
-        """
-        prompt = self.system_prompt
-
-        # Rebuild tool list section to reflect current self.tools
-        prompt = self._rebuild_tool_list_section(prompt)
-
-        # If runtime_info contains dynamic time function, rebuild runtime section
-        if self.runtime_info and callable(self.runtime_info.get('_get_current_time')):
-            prompt = self._rebuild_runtime_section(prompt)
-
-        # Rebuild skills section to pick up newly installed/removed skills
-        if self.skill_manager:
-            prompt = self._rebuild_skills_section(prompt)
-
-        return prompt
-    
-    def _rebuild_runtime_section(self, prompt: str) -> str:
-        """
-        Rebuild runtime info section with current time.
-        
-        This method dynamically updates the runtime info section by calling
-        the _get_current_time function from runtime_info.
-        
-        :param prompt: Original system prompt
-        :return: Updated system prompt with current runtime info
+        Re-reads AGENT.md / USER.md / RULE.md from disk, refreshes skills,
+        tools, and runtime info so any change takes effect immediately.
+        Falls back to the cached self.system_prompt on error.
         """
         try:
-            # Get current time dynamically
-            time_info = self.runtime_info['_get_current_time']()
-            
-            # Build new runtime section
-            runtime_lines = [
-                "\n## 运行时信息\n",
-                "\n",
-                f"当前时间: {time_info['time']} {time_info['weekday']} ({time_info['timezone']})\n",
-                "\n"
-            ]
-            
-            # Add other runtime info
-            runtime_parts = []
-            if self.runtime_info.get("model"):
-                runtime_parts.append(f"模型={self.runtime_info['model']}")
-            if self.runtime_info.get("workspace"):
-                # Replace backslashes with forward slashes for Windows paths
-                workspace_path = str(self.runtime_info['workspace']).replace('\\', '/')
-                runtime_parts.append(f"工作空间={workspace_path}")
-            if self.runtime_info.get("channel") and self.runtime_info.get("channel") != "web":
-                runtime_parts.append(f"渠道={self.runtime_info['channel']}")
-            
-            if runtime_parts:
-                runtime_lines.append("运行时: " + " | ".join(runtime_parts) + "\n")
-                runtime_lines.append("\n")
-            
-            new_runtime_section = "".join(runtime_lines)
-            
-            # Find and replace the runtime section
-            import re
-            pattern = r'\n## 运行时信息\s*\n.*?(?=\n##|\Z)'
-            _repl = new_runtime_section.rstrip('\n')
-            updated_prompt = re.sub(pattern, lambda m: _repl, prompt, flags=re.DOTALL)
-            
-            return updated_prompt
+            from agent.prompt import load_context_files, PromptBuilder
+
+            if self.skill_manager:
+                self.skill_manager.refresh_skills()
+
+            context_files = load_context_files(self.workspace_dir) if self.workspace_dir else None
+
+            builder = PromptBuilder(workspace_dir=self.workspace_dir or "", language="zh")
+            return builder.build(
+                tools=self.tools,
+                context_files=context_files,
+                skill_manager=self.skill_manager,
+                memory_manager=self.memory_manager,
+                runtime_info=self.runtime_info,
+            )
         except Exception as e:
-            logger.warning(f"Failed to rebuild runtime section: {e}")
-            return prompt
-
-    def _rebuild_skills_section(self, prompt: str) -> str:
-        """
-        Rebuild the <available_skills> block so that newly installed or
-        removed skills are reflected without re-creating the agent.
-        """
-        try:
-            import re
-            self.skill_manager.refresh_skills()
-            new_skills_xml = self.skill_manager.build_skills_prompt()
-
-            old_block_pattern = r'<available_skills>.*?</available_skills>'
-            has_old_block = re.search(old_block_pattern, prompt, flags=re.DOTALL)
-
-            # Extract the new <available_skills>...</available_skills> tag from the prompt
-            new_block = ""
-            if new_skills_xml and new_skills_xml.strip():
-                m = re.search(old_block_pattern, new_skills_xml, flags=re.DOTALL)
-                if m:
-                    new_block = m.group(0)
-
-            if has_old_block:
-                replacement = new_block or "<available_skills>\n</available_skills>"
-                # Use lambda to prevent re.sub from interpreting backslashes in replacement
-                # (e.g. Windows paths like \LinkAI would be treated as bad escape sequences)
-                prompt = re.sub(old_block_pattern, lambda m: replacement, prompt, flags=re.DOTALL)
-            elif new_block:
-                skills_header = "以下是可用技能："
-                idx = prompt.find(skills_header)
-                if idx != -1:
-                    insert_pos = idx + len(skills_header)
-                    prompt = prompt[:insert_pos] + "\n" + new_block + prompt[insert_pos:]
-        except Exception as e:
-            logger.warning(f"Failed to rebuild skills section: {e}")
-        return prompt
-
-    def _rebuild_tool_list_section(self, prompt: str) -> str:
-        """
-        Rebuild the tool list inside the '## 工具系统' section so that it
-        always reflects the current ``self.tools`` (handles dynamic add/remove
-        of conditional tools like web_search).
-        """
-        import re
-        from agent.prompt.builder import _build_tooling_section
-
-        try:
-            if not self.tools:
-                return prompt
-
-            new_lines = _build_tooling_section(self.tools, "zh")
-            new_section = "\n".join(new_lines).rstrip("\n")
-
-            # Replace existing tooling section
-            pattern = r'## 工具系统\s*\n.*?(?=\n## |\Z)'
-            updated = re.sub(pattern, lambda m: new_section, prompt, count=1, flags=re.DOTALL)
-            return updated
-        except Exception as e:
-            logger.warning(f"Failed to rebuild tool list section: {e}")
-            return prompt
+            logger.warning(f"Failed to rebuild system prompt, using cached version: {e}")
+            return self.system_prompt
 
     def refresh_skills(self):
         """Refresh the loaded skills."""

agent/protocol/agent_stream.py

@@ -472,6 +472,7 @@ class AgentStreamExecutor:
             raise
 
         finally:
+            final_response = final_response.strip() if final_response else final_response
             logger.info(f"[Agent] 🏁 完成 ({turn}轮)")
             self._emit_event("agent_end", {"final_response": final_response})
 

agent/skills/config.py

@@ -139,6 +139,47 @@ def should_include_skill(
     return True
 
 
+def get_missing_requirements(
+    entry: SkillEntry,
+    current_platform: Optional[str] = None,
+) -> Dict[str, List[str]]:
+    """
+    Return a dict of missing requirements for a skill.
+    Empty dict means all requirements are met.
+
+    :param entry: SkillEntry to check
+    :param current_platform: Current platform (default: auto-detect)
+    :return: Dict like {"bins": ["curl"], "env": ["API_KEY"]}
+    """
+    missing: Dict[str, List[str]] = {}
+    metadata = entry.metadata
+
+    if not metadata or not metadata.requires:
+        return missing
+
+    required_bins = metadata.requires.get('bins', [])
+    if required_bins:
+        missing_bins = [b for b in required_bins if not has_binary(b)]
+        if missing_bins:
+            missing['bins'] = missing_bins
+
+    any_bins = metadata.requires.get('anyBins', [])
+    if any_bins and not has_any_binary(any_bins):
+        missing['anyBins'] = any_bins
+
+    required_env = metadata.requires.get('env', [])
+    if required_env:
+        missing_env = [e for e in required_env if not has_env_var(e)]
+        if missing_env:
+            missing['env'] = missing_env
+
+    any_env = metadata.requires.get('anyEnv', [])
+    if any_env and not any(has_env_var(e) for e in any_env):
+        missing['anyEnv'] = any_env
+
+    return missing
+
+
 def is_config_path_truthy(config: Dict, path: str) -> bool:
     """
     Check if a config path resolves to a truthy value.

agent/skills/formatter.py

@@ -2,7 +2,7 @@
 Skill formatter for generating prompts from skills.
 """
 
-from typing import List
+from typing import Dict, List
 from agent.skills.types import Skill, SkillEntry
 
 
@@ -51,6 +51,71 @@ def format_skill_entries_for_prompt(entries: List[SkillEntry]) -> str:
     return format_skills_for_prompt(skills)
 
 
+def format_unavailable_skills_for_prompt(
+    entries: List[SkillEntry],
+    missing_map: Dict[str, Dict[str, List[str]]],
+) -> str:
+    """
+    Format unavailable (requires-not-met) skills as brief setup hints
+    so the AI can guide users to configure them.
+
+    :param entries: List of unavailable skill entries
+    :param missing_map: Dict mapping skill name to its missing requirements
+    :return: Formatted prompt text
+    """
+    if not entries:
+        return ""
+
+    lines = [
+        "",
+        "<unavailable_skills>",
+        "The following skills are installed but not yet ready. "
+        "Guide the user to complete the setup when relevant.",
+    ]
+
+    for entry in entries:
+        skill = entry.skill
+        missing = missing_map.get(skill.name, {})
+
+        missing_parts = []
+        for key, values in missing.items():
+            missing_parts.append(f"{key}: {', '.join(values)}")
+        missing_str = "; ".join(missing_parts) if missing_parts else "unknown"
+
+        setup_hint = _extract_setup_hint(skill)
+
+        lines.append("  <skill>")
+        lines.append(f"    <name>{_escape_xml(skill.name)}</name>")
+        lines.append(f"    <description>{_escape_xml(skill.description)}</description>")
+        lines.append(f"    <missing>{_escape_xml(missing_str)}</missing>")
+        if setup_hint:
+            lines.append(f"    <setup>{_escape_xml(setup_hint)}</setup>")
+        lines.append("  </skill>")
+
+    lines.append("</unavailable_skills>")
+    return "\n".join(lines)
+
+
+def _extract_setup_hint(skill: Skill) -> str:
+    """
+    Extract the Setup section from SKILL.md content as a brief hint.
+    Returns the first few lines of the ## Setup section.
+    """
+    content = skill.content
+    if not content:
+        return ""
+
+    import re
+    match = re.search(r'^##\s+Setup\s*\n(.*?)(?=\n##\s|\Z)', content, re.MULTILINE | re.DOTALL)
+    if not match:
+        return ""
+
+    setup_text = match.group(1).strip()
+    lines = setup_text.split('\n')
+    hint_lines = [l.strip() for l in lines[:6] if l.strip()]
+    return ' '.join(hint_lines)[:300]
+
+
 def _escape_xml(text: str) -> str:
     """Escape XML special characters."""
     return (text

agent/skills/frontmatter.py

@@ -87,8 +87,8 @@ def parse_metadata(frontmatter: Dict[str, Any]) -> Optional[SkillMetadata]:
     if not isinstance(metadata_raw, dict):
         return None
     
-    # Use metadata_raw directly (COW format)
-    meta_obj = metadata_raw
+    # Unwrap nested namespace (e.g. {"openclaw": {...}} or {"cowagent": {...}})
+    meta_obj = _unwrap_metadata_namespace(metadata_raw)
     
     # Parse install specs
     install_specs = []
@@ -128,6 +128,7 @@ def parse_metadata(frontmatter: Dict[str, Any]) -> Optional[SkillMetadata]:
     
     return SkillMetadata(
         always=meta_obj.get('always', False),
+        default_enabled=meta_obj.get('default_enabled', True),
         skill_key=meta_obj.get('skillKey'),
         primary_env=meta_obj.get('primaryEnv'),
         emoji=meta_obj.get('emoji'),
@@ -138,6 +139,25 @@ def parse_metadata(frontmatter: Dict[str, Any]) -> Optional[SkillMetadata]:
     )
 
 
+_KNOWN_METADATA_NAMESPACES = {"cowagent", "openclaw"}
+
+
+def _unwrap_metadata_namespace(metadata_raw: Dict[str, Any]) -> Dict[str, Any]:
+    """
+    Unwrap a single-key namespace wrapper like {"cowagent": {...} or {"openclaw": {...}}}.
+    If the top-level dict has exactly one key matching a known namespace, return the inner dict.
+    Otherwise return the original dict unchanged.
+    """
+    keys = set(metadata_raw.keys())
+    ns_keys = keys & _KNOWN_METADATA_NAMESPACES
+    if len(ns_keys) == 1 and len(keys) == 1:
+        ns = ns_keys.pop()
+        inner = metadata_raw[ns]
+        if isinstance(inner, dict):
+            return inner
+    return metadata_raw
+
+
 def _normalize_string_list(value: Any) -> List[str]:
     """Normalize a value to a list of strings."""
     if not value:

agent/skills/loader.py

@@ -184,7 +184,6 @@ class SkillLoader:
         
         config_path = os.path.join(skill_dir, "config.json")
         
-        # Without config.json, skip this skill entirely (return empty to trigger exclusion)
         if not os.path.exists(config_path):
             logger.debug(f"[SkillLoader] linkai-agent skipped: no config.json found")
             return ""

agent/skills/manager.py

@@ -84,10 +84,10 @@ class SkillManager:
         """
         Merge directory-scanned skills with the persisted config file.
 
-        - New skills discovered on disk are added with enabled=True.
+        - New skills: use metadata.default_enabled as initial enabled state.
+        - Existing skills: preserve their persisted enabled state.
         - Skills that no longer exist on disk are removed.
-        - Existing entries preserve their enabled state; name/description/source
-          are refreshed from the latest scan.
+        - name/description/source are always refreshed from the latest scan.
         """
         saved = self._load_skills_config()
         merged: Dict[str, dict] = {}
@@ -95,13 +95,18 @@ class SkillManager:
         for name, entry in self.skills.items():
             skill = entry.skill
             prev = saved.get(name, {})
-            # category priority: persisted config (set by cloud) > default "skill"
             category = prev.get("category", "skill")
+
+            if name in saved:
+                enabled = prev.get("enabled", True)
+            else:
+                enabled = entry.metadata.default_enabled if entry.metadata else True
+
             merged[name] = {
                 "name": name,
                 "description": skill.description,
-                "source": skill.source,
-                "enabled": prev.get("enabled", True),
+                "source": prev.get("source") or skill.source,
+                "enabled": enabled,
                 "category": category,
             }
 
@@ -157,69 +162,114 @@ class SkillManager:
         """
         return list(self.skills.values())
     
+    @staticmethod
+    def _normalize_skill_filter(skill_filter: Optional[List[str]]) -> Optional[List[str]]:
+        """Normalize a skill_filter list into a flat list of stripped names."""
+        if skill_filter is None:
+            return None
+        normalized = []
+        for item in skill_filter:
+            if isinstance(item, str):
+                name = item.strip()
+                if name:
+                    normalized.append(name)
+            elif isinstance(item, list):
+                for subitem in item:
+                    if isinstance(subitem, str):
+                        name = subitem.strip()
+                        if name:
+                            normalized.append(name)
+        return normalized or None
+
     def filter_skills(
         self,
         skill_filter: Optional[List[str]] = None,
         include_disabled: bool = False,
     ) -> List[SkillEntry]:
         """
-        Filter skills based on criteria.
-
-        Simple rule: Skills are auto-enabled if requirements are met.
-        - Has required API keys -> included
-        - Missing API keys -> excluded
+        Filter skills that are eligible (enabled + requirements met).
 
         :param skill_filter: List of skill names to include (None = all)
         :param include_disabled: Whether to include disabled skills
-        :return: Filtered list of skill entries
+        :return: Filtered list of eligible skill entries
         """
         from agent.skills.config import should_include_skill
 
         entries = list(self.skills.values())
 
-        # Check requirements (platform, binaries, env vars)
         entries = [e for e in entries if should_include_skill(e, self.config)]
 
-        # Apply skill filter
-        if skill_filter is not None:
-            normalized = []
-            for item in skill_filter:
-                if isinstance(item, str):
-                    name = item.strip()
-                    if name:
-                        normalized.append(name)
-                elif isinstance(item, list):
-                    for subitem in item:
-                        if isinstance(subitem, str):
-                            name = subitem.strip()
-                            if name:
-                                normalized.append(name)
-            if normalized:
-                entries = [e for e in entries if e.skill.name in normalized]
+        normalized = self._normalize_skill_filter(skill_filter)
+        if normalized is not None:
+            entries = [e for e in entries if e.skill.name in normalized]
 
-        # Filter out disabled skills based on skills_config.json
         if not include_disabled:
             entries = [e for e in entries if self.is_skill_enabled(e.skill.name)]
 
         return entries
-    
+
+    def filter_unavailable_skills(
+        self,
+        skill_filter: Optional[List[str]] = None,
+    ) -> tuple:
+        """
+        Find skills that are enabled but have unmet requirements.
+
+        :param skill_filter: Optional list of skill names to include
+        :return: Tuple of (entries, missing_map) where missing_map maps
+                 skill name to its missing requirements dict
+        """
+        from agent.skills.config import should_include_skill, get_missing_requirements
+
+        entries = list(self.skills.values())
+
+        # Only enabled skills
+        entries = [e for e in entries if self.is_skill_enabled(e.skill.name)]
+
+        normalized = self._normalize_skill_filter(skill_filter)
+        if normalized is not None:
+            entries = [e for e in entries if e.skill.name in normalized]
+
+        # Keep only those that fail should_include_skill (requirements not met)
+        unavailable = []
+        missing_map: Dict[str, dict] = {}
+        for e in entries:
+            if not should_include_skill(e, self.config):
+                missing = get_missing_requirements(e)
+                if missing:
+                    unavailable.append(e)
+                    missing_map[e.skill.name] = missing
+
+        return unavailable, missing_map
+
     def build_skills_prompt(
         self,
         skill_filter: Optional[List[str]] = None,
     ) -> str:
         """
-        Build a formatted prompt containing available skills.
-        
+        Build a formatted prompt containing available skills
+        and brief hints for unavailable ones.
+
         :param skill_filter: Optional list of skill names to include
         :return: Formatted skills prompt
         """
         from common.log import logger
-        entries = self.filter_skills(skill_filter=skill_filter, include_disabled=False)
-        logger.debug(f"[SkillManager] Filtered {len(entries)} skills for prompt (total: {len(self.skills)})")
-        if entries:
-            skill_names = [e.skill.name for e in entries]
-            logger.debug(f"[SkillManager] Skills to include: {skill_names}")
-        result = format_skill_entries_for_prompt(entries)
+        from agent.skills.formatter import format_unavailable_skills_for_prompt
+
+        eligible = self.filter_skills(skill_filter=skill_filter, include_disabled=False)
+        logger.debug(f"[SkillManager] Eligible: {len(eligible)} skills (total: {len(self.skills)})")
+        if eligible:
+            skill_names = [e.skill.name for e in eligible]
+            logger.debug(f"[SkillManager] Eligible skills: {skill_names}")
+
+        result = format_skill_entries_for_prompt(eligible)
+
+        unavailable, missing_map = self.filter_unavailable_skills(skill_filter=skill_filter)
+        if unavailable:
+            unavailable_names = [e.skill.name for e in unavailable]
+            logger.debug(f"[SkillManager] Unavailable skills (setup needed): {unavailable_names}")
+            result += format_unavailable_skills_for_prompt(unavailable, missing_map)
+
         logger.debug(f"[SkillManager] Generated prompt length: {len(result)}")
         return result
     

agent/skills/types.py

@@ -29,6 +29,7 @@ class SkillInstallSpec:
 class SkillMetadata:
     """Metadata for a skill from frontmatter."""
     always: bool = False  # Always include this skill
+    default_enabled: bool = True  # Initial enabled state when first discovered
     skill_key: Optional[str] = None  # Override skill key
     primary_env: Optional[str] = None  # Primary environment variable
     emoji: Optional[str] = None

agent/tools/vision/vision.py

@@ -167,7 +167,7 @@ class Vision(BaseTool):
 
     @staticmethod
     def _maybe_compress(path: str) -> str:
-        """Compress image if larger than threshold; return path to use."""
+        """Compress image to under COMPRESS_THRESHOLD with max long-edge 1536px."""
         file_size = os.path.getsize(path)
         if file_size <= COMPRESS_THRESHOLD:
             return path
@@ -175,27 +175,47 @@ class Vision(BaseTool):
         tmp = tempfile.NamedTemporaryFile(suffix=".jpg", delete=False)
         tmp.close()
 
-        try:
-            # macOS: use sips
-            subprocess.run(
-                ["sips", "-Z", "800", path, "--out", tmp.name],
-                capture_output=True, check=True,
-            )
-            logger.debug(f"[Vision] Compressed image ({file_size // 1024}KB -> {os.path.getsize(tmp.name) // 1024}KB)")
-            return tmp.name
-        except (FileNotFoundError, subprocess.CalledProcessError):
-            pass
+        def _try_sips(max_dim: str, quality: str) -> bool:
+            try:
+                subprocess.run(
+                    ["sips", "-Z", max_dim, "-s", "formatOptions", quality,
+                     path, "--out", tmp.name],
+                    capture_output=True, check=True,
+                )
+                return True
+            except (FileNotFoundError, subprocess.CalledProcessError):
+                return False
 
-        try:
-            # Linux: use ImageMagick convert
-            subprocess.run(
-                ["convert", path, "-resize", "800x800>", tmp.name],
-                capture_output=True, check=True,
-            )
-            logger.debug(f"[Vision] Compressed image ({file_size // 1024}KB -> {os.path.getsize(tmp.name) // 1024}KB)")
+        def _try_convert(max_dim: str, quality: str) -> bool:
+            try:
+                subprocess.run(
+                    ["convert", path, "-resize", f"{max_dim}x{max_dim}>",
+                     "-quality", quality, tmp.name],
+                    capture_output=True, check=True,
+                )
+                return True
+            except (FileNotFoundError, subprocess.CalledProcessError):
+                return False
+
+        attempts = [
+            ("1536", "85"),
+            ("1536", "70"),
+            ("1536", "50"),
+        ]
+
+        for max_dim, quality in attempts:
+            ok = _try_sips(max_dim, quality) or _try_convert(max_dim, quality)
+            if not ok:
+                continue
+            new_size = os.path.getsize(tmp.name)
+            logger.debug(f"[Vision] Compressed image "
+                         f"({file_size // 1024}KB -> {new_size // 1024}KB, "
+                         f"max_dim={max_dim}, q={quality})")
+            if new_size <= COMPRESS_THRESHOLD:
+                return tmp.name
+
+        if os.path.exists(tmp.name) and os.path.getsize(tmp.name) > 0:
             return tmp.name
-        except (FileNotFoundError, subprocess.CalledProcessError):
-            pass
 
         os.remove(tmp.name)
         return path

bridge/agent_bridge.py

@@ -74,7 +74,7 @@ class AgentLLMModel(LLMModel):
         ("qwen", const.QWEN_DASHSCOPE), ("qwq", const.QWEN_DASHSCOPE), ("qvq", const.QWEN_DASHSCOPE),
         ("gemini", const.GEMINI), ("glm", const.ZHIPU_AI), ("claude", const.CLAUDEAPI),
         ("moonshot", const.MOONSHOT), ("kimi", const.MOONSHOT),
-        ("doubao", const.DOUBAO),
+        ("doubao", const.DOUBAO), ("deepseek", const.DEEPSEEK),
     ]
 
     def __init__(self, bridge: Bridge, bot_type: str = "chat"):
@@ -115,8 +115,6 @@ class AgentLLMModel(LLMModel):
             return const.QWEN_DASHSCOPE
         if model_name in [const.MOONSHOT, "moonshot-v1-8k", "moonshot-v1-32k", "moonshot-v1-128k"]:
             return const.MOONSHOT
-        if model_name in [const.DEEPSEEK_CHAT, const.DEEPSEEK_REASONER]:
-            return const.OPENAI
         for prefix, btype in self._MODEL_PREFIX_MAP:
             if model_name.startswith(prefix):
                 return btype

bridge/bridge.py

@@ -61,6 +61,9 @@ class Bridge(object):
             if model_type and model_type.startswith("doubao"):
                 self.btype["chat"] = const.DOUBAO
 
+            if model_type and model_type.startswith("deepseek"):
+                self.btype["chat"] = const.DEEPSEEK
+
             if model_type in [const.MODELSCOPE]:
                 self.btype["chat"] = const.MODELSCOPE
             

channel/web/chat.html

@@ -166,8 +166,8 @@
                     <i class="fas fa-bars text-slate-600 dark:text-slate-300"></i>
                 </button>
 
-                <!-- Breadcrumb -->
-                <div class="flex items-center gap-2 text-sm min-w-0">
+                <!-- Breadcrumb (hidden on mobile) -->
+                <div class="hidden lg:flex items-center gap-2 text-sm min-w-0">
                     <span id="breadcrumb-group" class="text-slate-400 dark:text-slate-500 truncate" data-i18n="nav_chat">Chat</span>
                     <i class="fas fa-chevron-right text-[10px] text-slate-300 dark:text-slate-600"></i>
                     <span id="breadcrumb-page" class="font-medium text-slate-700 dark:text-slate-200 truncate" data-i18n="menu_chat">Chat</span>
@@ -270,7 +270,7 @@
                         <div class="max-w-3xl mx-auto">
                             <!-- Attachment preview bar -->
                             <div id="attachment-preview" class="attachment-preview hidden"></div>
-                            <div class="flex items-center gap-2">
+                            <div class="flex items-center gap-2 relative">
                                 <div class="flex items-center flex-shrink-0">
                                     <button id="new-chat-btn" class="w-9 h-10 flex items-center justify-center rounded-lg
                                                                      text-slate-400 hover:text-primary-500 hover:bg-primary-50 dark:hover:bg-primary-900/20
@@ -287,6 +287,7 @@
                                 </div>
                                 <input type="file" id="file-input" class="hidden" multiple
                                        accept="image/*,.pdf,.doc,.docx,.xls,.xlsx,.ppt,.pptx,.txt,.csv,.json,.xml,.zip,.rar,.7z,.py,.js,.ts,.java,.c,.cpp,.go,.rs,.md">
+                                <div id="slash-menu" class="slash-menu hidden"></div>
                                 <textarea id="chat-input"
                                           class="flex-1 min-w-0 px-4 py-[10px] rounded-xl border border-slate-200 dark:border-slate-600
                                                  bg-slate-50 dark:bg-white/5 text-slate-800 dark:text-slate-100
@@ -295,7 +296,7 @@
                                                  text-sm leading-relaxed"
                                           rows="1"
                                           data-i18n-placeholder="input_placeholder"
-                                          placeholder="Type a message..."></textarea>
+                                          placeholder="Type a message, or press / for commands"></textarea>
                                 <button id="send-btn"
                                         class="flex-shrink-0 w-10 h-10 flex items-center justify-center rounded-lg
                                                bg-primary-400 text-white hover:bg-primary-500

channel/web/static/css/console.css

@@ -79,6 +79,11 @@
 .msg-content img { max-width: 100%; height: auto; border-radius: 8px; margin: 0.5em 0; }
 .msg-content a { color: #35A85B; text-decoration: underline; }
 .msg-content a:hover { color: #228547; }
+
+/* Overrides for user bubble (white text on green bg) */
+.user-bubble.msg-content a { color: #ffffff !important; text-decoration: underline; text-decoration-color: rgba(255,255,255,0.6); }
+.user-bubble.msg-content a:hover { color: #e0f5e8 !important; text-decoration-color: #e0f5e8; }
+.user-bubble.msg-content :not(pre) > code { background: rgba(255,255,255,0.2); color: #ffffff; }
 .msg-content hr { border: none; height: 1px; background: #e2e8f0; margin: 1.2em 0; }
 .dark .msg-content hr { background: rgba(255,255,255,0.1); }
 
@@ -446,3 +451,87 @@
     transform: translateY(-2px);
     box-shadow: 0 8px 25px -5px rgba(0, 0, 0, 0.1);
 }
+
+/* Slash Command Menu */
+.slash-menu {
+    position: absolute;
+    bottom: calc(100% + 6px);
+    left: 0;
+    right: 0;
+    max-height: 320px;
+    overflow-y: auto;
+    background: #fff;
+    border: 1px solid #e2e8f0;
+    border-radius: 12px;
+    box-shadow: 0 8px 30px -6px rgba(0, 0, 0, 0.1), 0 2px 8px -2px rgba(0, 0, 0, 0.04);
+    z-index: 50;
+    padding: 4px;
+    animation: slashMenuIn 0.15s ease-out;
+}
+.slash-menu.hidden { display: none; }
+
+@keyframes slashMenuIn {
+    from { opacity: 0; transform: translateY(6px); }
+    to   { opacity: 1; transform: translateY(0); }
+}
+
+.slash-menu-header {
+    padding: 6px 10px 4px;
+    font-size: 11px;
+    font-weight: 600;
+    color: #94a3b8;
+    text-transform: uppercase;
+    letter-spacing: 0.05em;
+}
+
+.slash-menu-item {
+    display: flex;
+    align-items: center;
+    justify-content: space-between;
+    padding: 8px 10px;
+    border-radius: 8px;
+    cursor: pointer;
+    transition: background 0.12s ease;
+}
+.slash-menu-item:hover,
+.slash-menu-item.active {
+    background: #EDFDF3;
+}
+.slash-menu-item .cmd {
+    font-size: 13px;
+    font-weight: 500;
+    color: #334155;
+    font-family: ui-monospace, SFMono-Regular, 'SF Mono', Menlo, monospace;
+}
+.slash-menu-item.active .cmd {
+    color: #228547;
+}
+.slash-menu-item .desc {
+    font-size: 12px;
+    color: #94a3b8;
+    margin-left: 12px;
+    white-space: nowrap;
+}
+
+/* Dark mode */
+.dark .slash-menu {
+    background: #1A1A1A;
+    border-color: rgba(255, 255, 255, 0.1);
+    box-shadow: 0 8px 30px -6px rgba(0, 0, 0, 0.35), 0 2px 8px -2px rgba(0, 0, 0, 0.15);
+}
+.dark .slash-menu-header {
+    color: #64748b;
+}
+.dark .slash-menu-item:hover,
+.dark .slash-menu-item.active {
+    background: rgba(74, 190, 110, 0.1);
+}
+.dark .slash-menu-item .cmd {
+    color: #e2e8f0;
+}
+.dark .slash-menu-item.active .cmd {
+    color: #4ABE6E;
+}
+.dark .slash-menu-item .desc {
+    color: #64748b;
+}

channel/web/static/js/console.js

@@ -3,9 +3,9 @@
    ===================================================================== */
 
 // =====================================================================
-// Version — update this before each release
+// Version — fetched from backend (single source: /VERSION file)
 // =====================================================================
-const APP_VERSION = 'v2.0.4';
+let APP_VERSION = '';
 
 // =====================================================================
 // i18n
@@ -21,7 +21,7 @@ const I18N = {
         example_sys_title: '系统管理', example_sys_text: '帮我查看工作空间里有哪些文件',
         example_task_title: '技能系统', example_task_text: '查看所有支持的工具和技能',
         example_code_title: '编程助手', example_code_text: '帮我编写一个Python爬虫脚本',
-        input_placeholder: '输入消息...',
+        input_placeholder: '输入消息，或输入 / 使用指令',
         config_title: '配置管理', config_desc: '管理模型和 Agent 配置',
         config_model: '模型配置', config_agent: 'Agent 配置',
         config_channel: '通道配置',
@@ -72,7 +72,7 @@ const I18N = {
         example_sys_title: 'System', example_sys_text: 'Show me the files in the workspace',
         example_task_title: 'Skills', example_task_text: 'Show current tools and skills',
         example_code_title: 'Coding', example_code_text: 'Write a Python web scraper script',
-        input_placeholder: 'Type a message...',
+        input_placeholder: 'Type a message, or press / for commands',
         config_title: 'Configuration', config_desc: 'Manage model and agent settings',
         config_model: 'Model Configuration', config_agent: 'Agent Configuration',
         config_channel: 'Channel Configuration',
@@ -322,6 +322,11 @@ const attachmentPreview = document.getElementById('attachment-preview');
 let pendingAttachments = [];
 let uploadingCount = 0;
 
+// Input history (like terminal arrow-key recall)
+const inputHistory = [];
+let historyIdx = -1;
+let historySavedDraft = '';
+
 function updateSendBtnState() {
     sendBtn.disabled = uploadingCount > 0 || (!chatInput.value.trim() && pendingAttachments.length === 0);
 }
@@ -435,6 +440,99 @@ chatInput.addEventListener('paste', (e) => {
 chatInput.addEventListener('compositionstart', () => { isComposing = true; });
 chatInput.addEventListener('compositionend', () => { setTimeout(() => { isComposing = false; }, 100); });
 
+// ── Slash Command Menu ───────────────────────────────────────
+const SLASH_COMMANDS = [
+    { cmd: '/help',                desc: '显示命令帮助' },
+    { cmd: '/status',              desc: '查看运行状态' },
+    { cmd: '/context',             desc: '查看对话上下文' },
+    { cmd: '/context clear',       desc: '清除对话上下文' },
+    { cmd: '/skill list',          desc: '查看已安装技能' },
+    { cmd: '/skill list --remote', desc: '浏览技能广场' },
+    { cmd: '/skill search ',       desc: '搜索技能' },
+    { cmd: '/skill install ',      desc: '安装技能 (名称或 GitHub URL)' },
+    { cmd: '/skill uninstall ',    desc: '卸载技能' },
+    { cmd: '/skill info ',         desc: '查看技能详情' },
+    { cmd: '/skill enable ',       desc: '启用技能' },
+    { cmd: '/skill disable ',      desc: '禁用技能' },
+    { cmd: '/config',              desc: '查看当前配置' },
+    { cmd: '/logs',                desc: '查看最近日志' },
+    { cmd: '/version',             desc: '查看版本' },
+];
+
+const slashMenu = document.getElementById('slash-menu');
+let slashActiveIdx = 0;
+let slashFiltered = [];
+let slashJustSelected = false;
+let slashLastFilter = '';
+
+function showSlashMenu(filter) {
+    const q = filter.toLowerCase();
+    if (q === slashLastFilter && !slashMenu.classList.contains('hidden')) return;
+    slashLastFilter = q;
+
+    const newFiltered = SLASH_COMMANDS.filter(c => c.cmd.toLowerCase().startsWith(q));
+    if (newFiltered.length === 0) {
+        hideSlashMenu();
+        return;
+    }
+
+    const changed = newFiltered.length !== slashFiltered.length ||
+        newFiltered.some((c, i) => c.cmd !== slashFiltered[i]?.cmd);
+    slashFiltered = newFiltered;
+    if (changed) slashActiveIdx = 0;
+    slashActiveIdx = Math.min(slashActiveIdx, slashFiltered.length - 1);
+
+    renderSlashItems();
+    slashMenu.classList.remove('hidden');
+}
+
+function hideSlashMenu() {
+    slashMenu.classList.add('hidden');
+    slashMenu.innerHTML = '';
+    slashFiltered = [];
+    slashActiveIdx = -1;
+    slashLastFilter = '';
+}
+
+function isSlashMenuVisible() {
+    return !slashMenu.classList.contains('hidden') && slashFiltered.length > 0;
+}
+
+function renderSlashItems() {
+    slashMenu.innerHTML =
+        '<div class="slash-menu-header">Commands</div>' +
+        slashFiltered.map((c, i) =>
+            `<div class="slash-menu-item${i === slashActiveIdx ? ' active' : ''}" data-idx="${i}">` +
+            `<span class="cmd">${escapeHtml(c.cmd)}</span>` +
+            `<span class="desc">${escapeHtml(c.desc)}</span></div>`
+        ).join('');
+
+    slashMenu.querySelectorAll('.slash-menu-item').forEach(el => {
+        el.addEventListener('mouseenter', () => {
+            slashActiveIdx = parseInt(el.dataset.idx);
+            renderSlashItems();
+        });
+        el.addEventListener('mousedown', (e) => {
+            e.preventDefault();
+            selectSlashCommand(parseInt(el.dataset.idx));
+        });
+    });
+
+    const activeEl = slashMenu.querySelector('.slash-menu-item.active');
+    if (activeEl) activeEl.scrollIntoView({ block: 'nearest' });
+}
+
+function selectSlashCommand(idx) {
+    if (idx < 0 || idx >= slashFiltered.length) return;
+    const chosen = slashFiltered[idx].cmd;
+    slashJustSelected = true;
+    chatInput.value = chosen;
+    chatInput.dispatchEvent(new Event('input'));
+    hideSlashMenu();
+    chatInput.focus();
+    chatInput.selectionStart = chatInput.selectionEnd = chosen.length;
+}
+
 chatInput.addEventListener('input', function() {
     this.style.height = '42px';
     const scrollH = this.scrollHeight;
@@ -442,11 +540,90 @@ chatInput.addEventListener('input', function() {
     this.style.height = newH + 'px';
     this.style.overflowY = scrollH > 180 ? 'auto' : 'hidden';
     updateSendBtnState();
+
+    const val = this.value;
+    if (slashJustSelected) {
+        slashJustSelected = false;
+    } else if (val.startsWith('/')) {
+        showSlashMenu(val);
+    } else {
+        hideSlashMenu();
+    }
 });
 
 chatInput.addEventListener('keydown', function(e) {
-    // keyCode 229 indicates an IME is processing the keystroke (reliable across browsers)
     if (e.keyCode === 229 || e.isComposing || isComposing) return;
+
+    if (isSlashMenuVisible()) {
+        if (e.key === 'ArrowDown') {
+            e.preventDefault();
+            slashActiveIdx = Math.min(slashActiveIdx + 1, slashFiltered.length - 1);
+            renderSlashItems();
+            return;
+        }
+        if (e.key === 'ArrowUp') {
+            e.preventDefault();
+            slashActiveIdx = Math.max(slashActiveIdx - 1, 0);
+            renderSlashItems();
+            return;
+        }
+        if (e.key === 'Enter' && !e.shiftKey && !e.ctrlKey) {
+            e.preventDefault();
+            selectSlashCommand(slashActiveIdx);
+            return;
+        }
+        if (e.key === 'Escape') {
+            e.preventDefault();
+            hideSlashMenu();
+            return;
+        }
+        if (e.key === 'Tab') {
+            e.preventDefault();
+            selectSlashCommand(slashActiveIdx);
+            return;
+        }
+    }
+
+    // Arrow-key history recall (only when input is empty or already browsing history)
+    if (e.key === 'ArrowUp' && inputHistory.length > 0 && !isSlashMenuVisible()) {
+        const curVal = this.value.trim();
+        const isSingleLine = !this.value.includes('\n');
+        if (isSingleLine && (curVal === '' || historyIdx >= 0)) {
+            e.preventDefault();
+            if (historyIdx < 0) {
+                historySavedDraft = this.value;
+                historyIdx = inputHistory.length - 1;
+            } else if (historyIdx > 0) {
+                historyIdx--;
+            }
+            this.value = inputHistory[historyIdx];
+            slashJustSelected = true;
+            this.dispatchEvent(new Event('input'));
+            hideSlashMenu();
+            this.selectionStart = this.selectionEnd = this.value.length;
+            return;
+        }
+    }
+    if (e.key === 'ArrowDown' && historyIdx >= 0 && !isSlashMenuVisible()) {
+        const isSingleLine = !this.value.includes('\n');
+        if (isSingleLine) {
+            e.preventDefault();
+            if (historyIdx < inputHistory.length - 1) {
+                historyIdx++;
+                this.value = inputHistory[historyIdx];
+            } else {
+                historyIdx = -1;
+                this.value = historySavedDraft;
+                historySavedDraft = '';
+            }
+            slashJustSelected = true;
+            this.dispatchEvent(new Event('input'));
+            hideSlashMenu();
+            this.selectionStart = this.selectionEnd = this.value.length;
+            return;
+        }
+    }
+
     if ((e.ctrlKey || e.shiftKey) && e.key === 'Enter') {
         const start = this.selectionStart;
         const end = this.selectionEnd;
@@ -460,6 +637,10 @@ chatInput.addEventListener('keydown', function(e) {
     }
 });
 
+chatInput.addEventListener('blur', () => {
+    setTimeout(hideSlashMenu, 150);
+});
+
 document.querySelectorAll('.example-card').forEach(card => {
     card.addEventListener('click', () => {
         const textEl = card.querySelector('[data-i18n*="text"]');
@@ -475,6 +656,12 @@ function sendMessage() {
     const text = chatInput.value.trim();
     if (!text && pendingAttachments.length === 0) return;
 
+    if (text) {
+        inputHistory.push(text);
+        historyIdx = -1;
+        historySavedDraft = '';
+    }
+
     const ws = document.getElementById('welcome-screen');
     if (ws) ws.remove();
 
@@ -732,7 +919,7 @@ function createUserMessageEl(content, timestamp, attachments) {
     const textHtml = content ? renderMarkdown(content) : '';
     el.innerHTML = `
         <div class="max-w-[75%] sm:max-w-[60%]">
-            <div class="bg-primary-400 text-white rounded-2xl px-4 py-2.5 text-sm leading-relaxed msg-content">
+            <div class="bg-primary-400 text-white rounded-2xl px-4 py-2.5 text-sm leading-relaxed msg-content user-bubble">
                 ${attachHtml}${textHtml}
             </div>
             <div class="text-xs text-slate-400 dark:text-slate-500 mt-1.5 text-right">${formatTime(timestamp)}</div>
@@ -2236,7 +2423,12 @@ navigateTo = function(viewId) {
 // =====================================================================
 applyTheme();
 applyI18n();
-document.getElementById('sidebar-version').textContent = `CowAgent ${APP_VERSION}`;
+fetch('/api/version').then(r => r.json()).then(data => {
+    APP_VERSION = `v${data.version}`;
+    document.getElementById('sidebar-version').textContent = `CowAgent ${APP_VERSION}`;
+}).catch(() => {
+    document.getElementById('sidebar-version').textContent = 'CowAgent';
+});
 chatInput.focus();
 
 // Re-enable color transition AFTER first paint so the theme applied in <head>

channel/web/web_channel.py

@@ -390,6 +390,7 @@ class WebChannel(ChatChannel):
             '/api/scheduler', 'SchedulerHandler',
             '/api/history', 'HistoryHandler',
             '/api/logs', 'LogsHandler',
+            '/api/version', 'VersionHandler',
             '/assets/(.*)', 'AssetsHandler',
         )
         app = web.application(urls, globals(), autoreload=False)
@@ -493,8 +494,8 @@ class ChatHandler:
 class ConfigHandler:
 
     _RECOMMENDED_MODELS = [
-        const.MINIMAX_M2_5, const.MINIMAX_M2_1, const.MINIMAX_M2_1_LIGHTNING,
-        const.GLM_5, const.GLM_4_7,
+        const.MINIMAX_M2_7, const.MINIMAX_M2_5, const.MINIMAX_M2_1, const.MINIMAX_M2_1_LIGHTNING,
+        const.GLM_5_TURBO, const.GLM_5, const.GLM_4_7,
         const.QWEN3_MAX, const.QWEN35_PLUS,
         const.KIMI_K2_5, const.KIMI_K2,
         const.DOUBAO_SEED_2_PRO, const.DOUBAO_SEED_2_CODE,
@@ -510,14 +511,14 @@ class ConfigHandler:
             "api_key_field": "minimax_api_key",
             "api_base_key": None,
             "api_base_default": None,
-            "models": [const.MINIMAX_M2_5, const.MINIMAX_M2_1, const.MINIMAX_M2_1_LIGHTNING],
+            "models": [const.MINIMAX_M2_7, const.MINIMAX_M2_5, const.MINIMAX_M2_1, const.MINIMAX_M2_1_LIGHTNING],
         }),
         ("zhipu", {
             "label": "智谱AI",
             "api_key_field": "zhipu_ai_api_key",
             "api_base_key": "zhipu_ai_api_base",
             "api_base_default": "https://open.bigmodel.cn/api/paas/v4",
-            "models": [const.GLM_5, const.GLM_4_7],
+            "models": [const.GLM_5_TURBO, const.GLM_5, const.GLM_4_7],
         }),
         ("dashscope", {
             "label": "通义千问",
@@ -563,9 +564,9 @@ class ConfigHandler:
         }),
         ("deepseek", {
             "label": "DeepSeek",
-            "api_key_field": "open_ai_api_key",
-            "api_base_key": None,
-            "api_base_default": None,
+            "api_key_field": "deepseek_api_key",
+            "api_base_key": "deepseek_api_base",
+            "api_base_default": "https://api.deepseek.com/v1",
             "models": [const.DEEPSEEK_CHAT, const.DEEPSEEK_REASONER],
         }),
         ("linkai", {
@@ -579,9 +580,9 @@ class ConfigHandler:
 
     EDITABLE_KEYS = {
         "model", "bot_type", "use_linkai",
-        "open_ai_api_base", "claude_api_base", "gemini_api_base",
+        "open_ai_api_base", "deepseek_api_base", "claude_api_base", "gemini_api_base",
         "zhipu_ai_api_base", "moonshot_base_url", "ark_base_url",
-        "open_ai_api_key", "claude_api_key", "gemini_api_key",
+        "open_ai_api_key", "deepseek_api_key", "claude_api_key", "gemini_api_key",
         "zhipu_ai_api_key", "dashscope_api_key", "moonshot_api_key",
         "ark_api_key", "minimax_api_key", "linkai_api_key",
         "agent_max_context_tokens", "agent_max_context_turns", "agent_max_steps",
@@ -1429,3 +1430,10 @@ class AssetsHandler:
         except Exception as e:
             logger.error(f"Error serving static file: {e}", exc_info=True)  # 添加更详细的错误信息
             raise web.notfound()
+
+
+class VersionHandler:
+    def GET(self):
+        web.header('Content-Type', 'application/json; charset=utf-8')
+        from cli import __version__
+        return json.dumps({"version": __version__})

channel/weixin/weixin_api.py

@@ -172,10 +172,8 @@ class WeixinApi:
 
     def get_upload_url(self, filekey: str, media_type: int, to_user_id: str,
                        rawsize: int, rawfilemd5: str, filesize: int,
-                       aeskey: str,
-                       thumb_rawsize: int = 0, thumb_rawfilemd5: str = "",
-                       thumb_filesize: int = 0) -> dict:
-        body = {
+                       aeskey: str) -> dict:
+        return self._post("ilink/bot/getuploadurl", {
             "filekey": filekey,
             "media_type": media_type,
             "to_user_id": to_user_id,
@@ -183,14 +181,8 @@ class WeixinApi:
             "rawfilemd5": rawfilemd5,
             "filesize": filesize,
             "aeskey": aeskey,
-        }
-        if thumb_rawsize > 0:
-            body["thumb_rawsize"] = thumb_rawsize
-            body["thumb_rawfilemd5"] = thumb_rawfilemd5
-            body["thumb_filesize"] = thumb_filesize
-        else:
-            body["no_need_thumb"] = True
-        return self._post("ilink/bot/getuploadurl", body)
+            "no_need_thumb": True,
+        })
 
     # ── getConfig / sendTyping ─────────────────────────────────────────
 
@@ -259,10 +251,18 @@ def _md5_bytes(data: bytes) -> str:
     return hashlib.md5(data).hexdigest()
 
 
+def _aes_ecb_padded_size(plaintext_size: int) -> int:
+    """PKCS7 padded size for AES-128-ECB."""
+    return ((plaintext_size + 1 + 15) // 16) * 16
+
+
+UPLOAD_MAX_RETRIES = 3
+
+
 def upload_media_to_cdn(api: WeixinApi, file_path: str, to_user_id: str,
                         media_type: int) -> dict:
     """
-    Upload a local file to the Weixin CDN.
+    Upload a local file to the Weixin CDN (matching official plugin protocol).
 
     Args:
         api: WeixinApi instance
@@ -275,75 +275,74 @@ def upload_media_to_cdn(api: WeixinApi, file_path: str, to_user_id: str,
     """
     aes_key = os.urandom(16)
     aes_key_hex = aes_key.hex()
+    filekey = uuid.uuid4().hex
 
     with open(file_path, "rb") as f:
         raw_data = f.read()
 
     raw_size = len(raw_data)
     raw_md5 = _md5_bytes(raw_data)
+    cipher_size = _aes_ecb_padded_size(raw_size)
+
     encrypted = _aes_ecb_encrypt(raw_data, aes_key)
-    cipher_size = len(encrypted)
-    filekey = uuid.uuid4().hex
 
-    thumb_rawsize = 0
-    thumb_rawfilemd5 = ""
-    thumb_filesize = 0
+    from urllib.parse import quote
 
-    if media_type == 1:  # IMAGE - generate a tiny thumbnail
+    download_param = None
+    last_error = None
+    for attempt in range(1, UPLOAD_MAX_RETRIES + 1):
         try:
-            from PIL import Image
-            import io
-            img = Image.open(file_path)
-            img.thumbnail((100, 100))
-            buf = io.BytesIO()
-            img.save(buf, format="JPEG", quality=60)
-            thumb_raw = buf.getvalue()
-            thumb_rawsize = len(thumb_raw)
-            thumb_rawfilemd5 = _md5_bytes(thumb_raw)
-            thumb_encrypted = _aes_ecb_encrypt(thumb_raw, aes_key)
-            thumb_filesize = len(thumb_encrypted)
-        except Exception as e:
-            logger.warning(f"[Weixin] Thumbnail generation failed, skipping: {e}")
+            if attempt > 1:
+                filekey = uuid.uuid4().hex
+            resp = api.get_upload_url(
+                filekey=filekey,
+                media_type=media_type,
+                to_user_id=to_user_id,
+                rawsize=raw_size,
+                rawfilemd5=raw_md5,
+                filesize=cipher_size,
+                aeskey=aes_key_hex,
+            )
+            upload_param = resp.get("upload_param", "")
+            if not upload_param:
+                raise RuntimeError(f"[Weixin] getUploadUrl returned no upload_param: {resp}")
 
-    resp = api.get_upload_url(
-        filekey=filekey,
-        media_type=media_type,
-        to_user_id=to_user_id,
-        rawsize=raw_size,
-        rawfilemd5=raw_md5,
-        filesize=cipher_size,
-        aeskey=aes_key_hex,
-        thumb_rawsize=thumb_rawsize,
-        thumb_rawfilemd5=thumb_rawfilemd5,
-        thumb_filesize=thumb_filesize,
-    )
+            cdn_url = (f"{api.cdn_base_url}/upload"
+                       f"?encrypted_query_param={quote(upload_param)}"
+                       f"&filekey={quote(filekey)}")
 
-    upload_param = resp.get("upload_param", "")
-    if not upload_param:
-        raise RuntimeError(f"[Weixin] getUploadUrl returned no upload_param: {resp}")
-
-    cdn_url = api.cdn_base_url + "?" + upload_param
-    put_resp = requests.put(cdn_url, data=encrypted, headers={
-        "Content-Type": "application/octet-stream",
-        "Content-Length": str(cipher_size),
-    }, timeout=60)
-    put_resp.raise_for_status()
-
-    # Upload thumbnail if we have one
-    thumb_upload_param = resp.get("thumb_upload_param", "")
-    if thumb_upload_param and thumb_filesize > 0:
-        thumb_cdn_url = api.cdn_base_url + "?" + thumb_upload_param
-        try:
-            requests.put(thumb_cdn_url, data=thumb_encrypted, headers={
+            cdn_resp = requests.post(cdn_url, data=encrypted, headers={
                 "Content-Type": "application/octet-stream",
-                "Content-Length": str(thumb_filesize),
-            }, timeout=30)
+                "Content-Length": str(len(encrypted)),
+            }, timeout=120)
+            if 400 <= cdn_resp.status_code < 500:
+                err_msg = cdn_resp.headers.get("x-error-message", cdn_resp.text[:200])
+                raise RuntimeError(f"CDN client error {cdn_resp.status_code}: {err_msg}")
+            cdn_resp.raise_for_status()
+            download_param = cdn_resp.headers.get("x-encrypted-param", "")
+            if not download_param:
+                raise RuntimeError("CDN response missing x-encrypted-param header")
+            logger.debug(f"[Weixin] CDN upload success attempt={attempt} filekey={filekey}")
+            break
         except Exception as e:
-            logger.warning(f"[Weixin] Thumbnail upload failed (non-fatal): {e}")
+            last_error = e
+            if "client error" in str(e):
+                raise
+            if attempt < UPLOAD_MAX_RETRIES:
+                backoff = 2 ** attempt
+                logger.warning(f"[Weixin] CDN upload attempt {attempt} failed, retrying in {backoff}s: {e}")
+                time.sleep(backoff)
+            else:
+                logger.error(f"[Weixin] CDN upload failed after {UPLOAD_MAX_RETRIES} attempts: {e}")
+
+    if not download_param:
+        raise last_error or RuntimeError("CDN upload failed")
+
+    aes_key_b64 = base64.b64encode(aes_key_hex.encode("utf-8")).decode("utf-8")
 
     return {
-        "encrypt_query_param": upload_param,
-        "aes_key_b64": base64.b64encode(aes_key).decode("utf-8"),
+        "encrypt_query_param": download_param,
+        "aes_key_b64": aes_key_b64,
         "ciphertext_size": cipher_size,
         "raw_size": raw_size,
     }
@@ -363,19 +362,30 @@ def download_media_from_cdn(cdn_base_url: str, encrypt_query_param: str,
     Returns:
         save_path on success
     """
-    url = cdn_base_url + "?" + encrypt_query_param
+    from urllib.parse import quote
+    url = f"{cdn_base_url}/download?encrypted_query_param={quote(encrypt_query_param)}"
     resp = requests.get(url, timeout=60)
     resp.raise_for_status()
 
-    # Determine key format (hex string or base64)
+    # Determine key format:
+    # 1) 32-char hex string → 16 raw bytes
+    # 2) base64 string → decode → if 32 bytes, treat as hex-encoded → 16 raw bytes
+    # 3) base64 string → decode → 16 raw bytes directly
     try:
         key_bytes = bytes.fromhex(aes_key)
         if len(key_bytes) != 16:
             raise ValueError()
     except (ValueError, TypeError):
-        key_bytes = base64.b64decode(aes_key)
-        if len(key_bytes) != 16:
-            raise ValueError(f"Invalid AES key length: {len(key_bytes)}")
+        decoded = base64.b64decode(aes_key)
+        if len(decoded) == 32:
+            try:
+                key_bytes = bytes.fromhex(decoded.decode("ascii"))
+            except (ValueError, UnicodeDecodeError):
+                raise ValueError(f"Invalid AES key: 32 bytes but not valid hex")
+        elif len(decoded) == 16:
+            key_bytes = decoded
+        else:
+            raise ValueError(f"Invalid AES key length after base64 decode: {len(decoded)}")
 
     decrypted = _aes_ecb_decrypt(resp.content, key_bytes)
 

channel/weixin/weixin_channel.py

@@ -31,6 +31,8 @@ BACKOFF_DELAY = 30
 RETRY_DELAY = 2
 SESSION_EXPIRED_ERRCODE = -14
 TEXT_CHUNK_LIMIT = 4000
+QR_LOGIN_TIMEOUT_S = 480
+QR_MAX_REFRESHES = 10
 
 
 def _load_credentials(cred_path: str) -> dict:
@@ -80,6 +82,8 @@ class WeixinChannel(ChatChannel):
     # ── Lifecycle ──────────────────────────────────────────────────────
 
     def startup(self):
+        self._stop_event.clear()
+
         base_url = conf().get("weixin_base_url", DEFAULT_BASE_URL)
         cdn_base_url = conf().get("weixin_cdn_base_url", CDN_BASE_URL)
         token = conf().get("weixin_token", "")
@@ -95,17 +99,9 @@ class WeixinChannel(ChatChannel):
                 base_url = creds["base_url"]
 
         if not token:
-            logger.info("[Weixin] No token found, starting QR login...")
-            self.login_status = self.LOGIN_STATUS_WAITING
-            login_result = self._qr_login(base_url)
-            if not login_result:
-                self.login_status = self.LOGIN_STATUS_IDLE
-                err = "[Weixin] QR login failed. Set weixin_token in config or run login again."
-                logger.error(err)
-                self.report_startup_error(err)
+            token, base_url = self._login_with_retry(base_url)
+            if not token:
                 return
-            token = login_result["token"]
-            base_url = login_result.get("base_url", base_url)
 
         self.api = WeixinApi(base_url=base_url, token=token, cdn_base_url=cdn_base_url)
         self.login_status = self.LOGIN_STATUS_OK
@@ -114,9 +110,26 @@ class WeixinChannel(ChatChannel):
                      f"如需重新扫码登录请删除该文件后重启")
         self.report_startup_success()
 
-        self._stop_event.clear()
         self._poll_loop()
 
+    def _login_with_retry(self, base_url: str) -> tuple:
+        """Attempt QR login, then wait for stop if failed.
+        Returns (token, base_url) on success, or ("", "") if stopped."""
+        logger.info("[Weixin] No token found, starting QR login...")
+        self.login_status = self.LOGIN_STATUS_WAITING
+        login_result = self._qr_login(base_url)
+        if login_result:
+            return login_result["token"], login_result.get("base_url", base_url)
+
+        self.login_status = self.LOGIN_STATUS_IDLE
+        if not self._stop_event.is_set():
+            logger.info("[Weixin] QR login timed out, waiting for stop or reconnect...")
+            print("  二维码登录超时，请通过控制台重新接入\n")
+            self._stop_event.wait()
+
+        logger.info("[Weixin] Login cancelled by stop event")
+        return "", ""
+
     def stop(self):
         logger.info("[Weixin] stop() called")
         self._stop_event.set()
@@ -202,14 +215,21 @@ class WeixinChannel(ChatChannel):
             return {}
 
         self._current_qr_url = qrcode_url
-        logger.info(f"[Weixin] QR code URL: {qrcode_url}")
+        logger.info(f"[Weixin] 微信二维码链接: {qrcode_url}")
         self._print_qr(qrcode_url)
         self._notify_cloud_qrcode(qrcode_url)
         print("  等待扫码...\n")
 
         scanned_printed = False
+        refresh_count = 0
+        deadline = time.time() + QR_LOGIN_TIMEOUT_S
 
         while not self._stop_event.is_set():
+            if time.time() >= deadline:
+                logger.warning(f"[Weixin] QR login timed out after {QR_LOGIN_TIMEOUT_S}s")
+                print(f"\n  二维码登录超时（{QR_LOGIN_TIMEOUT_S}s），请重启后重试")
+                break
+
             try:
                 status_resp = api.poll_qr_status(qrcode)
             except Exception as e:
@@ -226,14 +246,19 @@ class WeixinChannel(ChatChannel):
                     print("  已扫码，请在手机上确认...")
                     scanned_printed = True
             elif status == "expired":
-                print("  二维码已过期，正在刷新...")
+                refresh_count += 1
+                if refresh_count >= QR_MAX_REFRESHES:
+                    logger.warning(f"[Weixin] QR code refreshed {QR_MAX_REFRESHES} times, giving up")
+                    print(f"\n  二维码已刷新 {QR_MAX_REFRESHES} 次仍未扫码，请重启后重试")
+                    break
+                print(f"  二维码已过期，正在刷新（{refresh_count}/{QR_MAX_REFRESHES}）...")
                 try:
                     qr_resp = api.fetch_qr_code()
                     qrcode = qr_resp.get("qrcode", "")
                     qrcode_url = qr_resp.get("qrcode_img_content", "")
                     scanned_printed = False
                     self._current_qr_url = qrcode_url
-                    logger.info(f"[Weixin] New QR code: {qrcode_url}")
+                    logger.info(f"[Weixin] 微信二维码链接 ({refresh_count}/{QR_MAX_REFRESHES}): {qrcode_url}")
                     self._print_qr(qrcode_url)
                     self._notify_cloud_qrcode(qrcode_url)
                 except Exception as e:
@@ -267,8 +292,9 @@ class WeixinChannel(ChatChannel):
 
             self._stop_event.wait(1)
 
-        logger.info("[Weixin] QR login cancelled by stop event")
         self._current_qr_url = ""
+        if self._stop_event.is_set():
+            logger.info("[Weixin] QR login cancelled by stop event")
         return {}
 
     # ── Long-poll loop ─────────────────────────────────────────────────

channel/weixin/weixin_message.py

@@ -184,12 +184,16 @@ class WeixinMessage(ChatMessage):
             logger.warning(f"[Weixin] Missing CDN params for media download (type={media_type})")
             return ""
 
-        ext_map = {ITEM_IMAGE: ".jpg", ITEM_VIDEO: ".mp4", ITEM_FILE: "", ITEM_VOICE: ".silk"}
-        ext = ext_map.get(media_type, "")
         if media_type == ITEM_FILE:
-            ext = os.path.splitext(info.get("file_name", ""))[1] or ".bin"
-
-        save_path = os.path.join(_get_tmp_dir(), f"wx_{self.msg_id}{ext}")
+            original_name = info.get("file_name", "")
+            if original_name:
+                save_path = os.path.join(_get_tmp_dir(), original_name)
+            else:
+                save_path = os.path.join(_get_tmp_dir(), f"wx_{self.msg_id}.bin")
+        else:
+            ext_map = {ITEM_IMAGE: ".jpg", ITEM_VIDEO: ".mp4", ITEM_VOICE: ".silk"}
+            ext = ext_map.get(media_type, "")
+            save_path = os.path.join(_get_tmp_dir(), f"wx_{self.msg_id}{ext}")
 
         try:
             download_media_from_cdn(cdn_base_url, encrypt_param, aes_key, save_path)

cli/VERSION

@@ -0,0 +1 @@
+2.0.4

cli/__init__.py

@@ -0,0 +1,13 @@
+"""CowAgent CLI - Manage your CowAgent from the command line."""
+
+import os as _os
+
+def _read_version():
+    version_file = _os.path.join(_os.path.dirname(_os.path.abspath(__file__)), "VERSION")
+    try:
+        with open(version_file, "r") as f:
+            return f.read().strip()
+    except FileNotFoundError:
+        return "0.0.0"
+
+__version__ = _read_version()

cli/__main__.py

@@ -0,0 +1,4 @@
+"""Allow running as: python -m cli"""
+from cli.cli import main
+
+main()

cli/cli.py

@@ -0,0 +1,73 @@
+"""CowAgent CLI entry point."""
+
+import click
+from cli import __version__
+from cli.commands.skill import skill
+from cli.commands.process import start, stop, restart, update, status, logs
+from cli.commands.context import context
+
+
+HELP_TEXT = """Usage: cow COMMAND [ARGS]...
+
+  CowAgent CLI - Manage your CowAgent instance.
+
+Commands:
+  help     Show this message.
+  version  Show the version.
+  start    Start CowAgent.
+  stop     Stop CowAgent.
+  restart  Restart CowAgent.
+  update   Update CowAgent and restart.
+  status   Show CowAgent running status.
+  logs     View CowAgent logs.
+  skill    Manage CowAgent skills.
+
+Tip: You can also send /help, /skill list, etc. in agent chat."""
+
+
+class CowCLI(click.Group):
+
+    def format_help(self, ctx, formatter):
+        formatter.write(HELP_TEXT.strip())
+        formatter.write("\n")
+
+    def parse_args(self, ctx, args):
+        if args and args[0] == 'help':
+            click.echo(HELP_TEXT.strip())
+            ctx.exit(0)
+        return super().parse_args(ctx, args)
+
+
+@click.group(cls=CowCLI, invoke_without_command=True, context_settings=dict(help_option_names=[]))
+@click.pass_context
+def main(ctx):
+    """CowAgent CLI - Manage your CowAgent instance."""
+    if ctx.invoked_subcommand is None:
+        click.echo(HELP_TEXT.strip())
+
+
+@main.command()
+def version():
+    """Show the version."""
+    click.echo(f"cow {__version__}")
+
+
+@main.command(name='help')
+@click.pass_context
+def help_cmd(ctx):
+    """Show this message."""
+    click.echo(HELP_TEXT.strip())
+
+
+main.add_command(skill)
+main.add_command(start)
+main.add_command(stop)
+main.add_command(restart)
+main.add_command(update)
+main.add_command(status)
+main.add_command(logs)
+main.add_command(context)
+
+
+if __name__ == '__main__':
+    main()

cli/commands/context.py

@@ -0,0 +1,29 @@
+"""cow context - Context management commands."""
+
+import click
+
+
+CHAT_HINT = (
+    "Context commands operate on the running agent's memory.\n"
+    "Please send the command in a chat conversation instead:\n\n"
+    "  /context        - View current context info\n"
+    "  /context clear  - Clear conversation context"
+)
+
+
+@click.group(invoke_without_command=True)
+@click.pass_context
+def context(ctx):
+    """View or manage conversation context.
+
+    Context commands need access to the running agent's memory.
+    Use them in chat conversations: /context or /context clear
+    """
+    if ctx.invoked_subcommand is None:
+        click.echo(f"\n  {CHAT_HINT}\n")
+
+
+@context.command()
+def clear():
+    """Clear conversation context (messages history)."""
+    click.echo(f"\n  {CHAT_HINT}\n")

cli/commands/process.py

@@ -0,0 +1,281 @@
+"""cow start/stop/restart/status/logs - Process management commands."""
+
+import os
+import sys
+import subprocess
+import time
+from typing import Optional
+
+import click
+
+from cli.utils import get_project_root
+
+_IS_WIN = sys.platform == "win32"
+
+
+def _get_pid_file():
+    return os.path.join(get_project_root(), ".cow.pid")
+
+
+def _get_log_file():
+    return os.path.join(get_project_root(), "nohup.out")
+
+
+def _is_pid_alive(pid: int) -> bool:
+    """Check whether a process is still running (cross-platform)."""
+    if _IS_WIN:
+        try:
+            out = subprocess.check_output(
+                ["tasklist", "/FI", f"PID eq {pid}", "/NH"],
+                stderr=subprocess.DEVNULL,
+            )
+            return str(pid) in out.decode(errors="ignore")
+        except Exception:
+            return False
+    else:
+        try:
+            os.kill(pid, 0)
+            return True
+        except (ProcessLookupError, PermissionError):
+            return False
+
+
+def _kill_pid(pid: int, force: bool = False):
+    """Terminate a process by PID (cross-platform)."""
+    if _IS_WIN:
+        flag = "/F" if force else ""
+        cmd = ["taskkill"]
+        if force:
+            cmd.append("/F")
+        cmd.extend(["/PID", str(pid)])
+        subprocess.run(cmd, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
+    else:
+        import signal
+        sig = signal.SIGKILL if force else signal.SIGTERM
+        os.kill(pid, sig)
+
+
+def _read_pid() -> Optional[int]:
+    pid_file = _get_pid_file()
+    if not os.path.exists(pid_file):
+        return None
+    try:
+        with open(pid_file, "r") as f:
+            pid = int(f.read().strip())
+        if _is_pid_alive(pid):
+            return pid
+        os.remove(pid_file)
+        return None
+    except (ValueError, OSError):
+        try:
+            os.remove(pid_file)
+        except OSError:
+            pass
+        return None
+
+
+def _write_pid(pid: int):
+    with open(_get_pid_file(), "w") as f:
+        f.write(str(pid))
+
+
+def _remove_pid():
+    pid_file = _get_pid_file()
+    if os.path.exists(pid_file):
+        os.remove(pid_file)
+
+
+@click.command()
+@click.option("--foreground", "-f", is_flag=True, help="Run in foreground (don't daemonize)")
+@click.option("--no-logs", is_flag=True, help="Don't tail logs after starting")
+def start(foreground, no_logs):
+    """Start CowAgent."""
+    pid = _read_pid()
+    if pid:
+        click.echo(f"CowAgent is already running (PID: {pid}).")
+        return
+
+    root = get_project_root()
+    app_py = os.path.join(root, "app.py")
+    if not os.path.exists(app_py):
+        click.echo("Error: app.py not found in project root.", err=True)
+        sys.exit(1)
+
+    python = sys.executable
+
+    if foreground:
+        click.echo("Starting CowAgent in foreground...")
+        if _IS_WIN:
+            sys.exit(subprocess.call([python, app_py], cwd=root))
+        else:
+            os.execv(python, [python, app_py])
+    else:
+        log_file = _get_log_file()
+        click.echo("Starting CowAgent...")
+
+        popen_kwargs = dict(cwd=root)
+        if _IS_WIN:
+            CREATE_NO_WINDOW = 0x08000000
+            popen_kwargs["creationflags"] = (
+                subprocess.CREATE_NEW_PROCESS_GROUP | CREATE_NO_WINDOW
+            )
+        else:
+            popen_kwargs["start_new_session"] = True
+
+        with open(log_file, "a") as log:
+            proc = subprocess.Popen(
+                [python, app_py],
+                stdout=log,
+                stderr=log,
+                **popen_kwargs,
+            )
+        _write_pid(proc.pid)
+        click.echo(click.style(f"✓ CowAgent started (PID: {proc.pid})", fg="green"))
+        click.echo(f"  Logs: {log_file}")
+
+        if not no_logs:
+            click.echo("  Press Ctrl+C to stop tailing logs.\n")
+            _tail_log(log_file)
+
+
+@click.command()
+def stop():
+    """Stop CowAgent."""
+    pid = _read_pid()
+    if not pid:
+        click.echo("CowAgent is not running.")
+        return
+
+    click.echo(f"Stopping CowAgent (PID: {pid})...")
+    try:
+        _kill_pid(pid)
+        for _ in range(30):
+            time.sleep(0.1)
+            if not _is_pid_alive(pid):
+                break
+        else:
+            _kill_pid(pid, force=True)
+    except (ProcessLookupError, OSError):
+        pass
+
+    _remove_pid()
+    click.echo(click.style("✓ CowAgent stopped.", fg="green"))
+
+
+@click.command()
+@click.option("--no-logs", is_flag=True, help="Don't tail logs after restarting")
+@click.pass_context
+def restart(ctx, no_logs):
+    """Restart CowAgent."""
+    ctx.invoke(stop)
+    time.sleep(1)
+    ctx.invoke(start, no_logs=no_logs)
+
+
+@click.command()
+@click.pass_context
+def update(ctx):
+    """Update CowAgent and restart."""
+    root = get_project_root()
+
+    # 1. Git pull while service is still running
+    if os.path.isdir(os.path.join(root, ".git")):
+        click.echo("Pulling latest code...")
+        ret = subprocess.call(["git", "pull"], cwd=root)
+        if ret != 0:
+            click.echo("Error: git pull failed.", err=True)
+            sys.exit(1)
+    else:
+        click.echo("Not a git repository, skipping code update.")
+
+    # 2. Stop service
+    ctx.invoke(stop)
+
+    # 3. Install dependencies
+    python = sys.executable
+    req_file = os.path.join(root, "requirements.txt")
+    if os.path.exists(req_file):
+        click.echo("Installing dependencies...")
+        subprocess.call(
+            [python, "-m", "pip", "install", "-r", "requirements.txt", "-q"],
+            cwd=root,
+        )
+    click.echo("Reinstalling cow CLI...")
+    subprocess.call(
+        [python, "-m", "pip", "install", "-e", ".", "-q"],
+        cwd=root,
+    )
+
+    # 4. Start service
+    click.echo("")
+    time.sleep(1)
+    ctx.invoke(start, no_logs=True)
+
+
+@click.command()
+def status():
+    """Show CowAgent running status."""
+    from cli import __version__
+    from cli.utils import load_config_json
+
+    pid = _read_pid()
+    if pid:
+        click.echo(click.style(f"● CowAgent is running (PID: {pid})", fg="green"))
+    else:
+        click.echo(click.style("● CowAgent is not running", fg="red"))
+
+    click.echo(f"  版本: v{__version__}")
+
+    cfg = load_config_json()
+    if cfg:
+        channel = cfg.get("channel_type", "unknown")
+        if isinstance(channel, list):
+            channel = ", ".join(channel)
+        click.echo(f"  通道: {channel}")
+        click.echo(f"  模型: {cfg.get('model', 'unknown')}")
+        mode = "Agent" if cfg.get("agent") else "Chat"
+        click.echo(f"  模式: {mode}")
+
+
+@click.command()
+@click.option("--follow", "-f", is_flag=True, help="Follow log output")
+@click.option("--lines", "-n", default=50, help="Number of lines to show")
+def logs(follow, lines):
+    """View CowAgent logs."""
+    log_file = _get_log_file()
+    if not os.path.exists(log_file):
+        click.echo("No log file found.")
+        return
+
+    if follow:
+        _tail_log(log_file, lines)
+    else:
+        _print_last_lines(log_file, lines)
+
+
+def _print_last_lines(file_path: str, n: int = 50):
+    """Print the last N lines of a file (cross-platform)."""
+    try:
+        with open(file_path, "r", encoding="utf-8", errors="replace") as f:
+            all_lines = f.readlines()
+        for line in all_lines[-n:]:
+            click.echo(line, nl=False)
+    except Exception as e:
+        click.echo(f"Error reading log file: {e}", err=True)
+
+
+def _tail_log(log_file: str, lines: int = 50):
+    """Follow log file output. Blocks until Ctrl+C (cross-platform)."""
+    _print_last_lines(log_file, lines)
+
+    try:
+        with open(log_file, "r", encoding="utf-8", errors="replace") as f:
+            f.seek(0, 2)
+            while True:
+                line = f.readline()
+                if line:
+                    click.echo(line, nl=False)
+                else:
+                    time.sleep(0.3)
+    except KeyboardInterrupt:
+        pass

cli/commands/skill.py

@@ -0,0 +1,799 @@
+"""cow skill - Skill management commands."""
+
+import os
+import re
+import sys
+import json
+import hashlib
+import shutil
+import zipfile
+import tempfile
+
+from urllib.parse import urlparse
+
+import click
+import requests
+
+from cli.utils import (
+    get_project_root,
+    get_skills_dir,
+    get_builtin_skills_dir,
+    load_skills_config,
+    SKILL_HUB_API,
+)
+
+_SAFE_NAME_RE = re.compile(r"^[a-zA-Z0-9][a-zA-Z0-9_\-]{0,63}$")
+_GITHUB_URL_RE = re.compile(
+    r"^https?://github\.com/([^/]+)/([^/]+?)(?:\.git)?(?:/(?:tree|blob)/([^/]+)(?:/(.+))?)?/?$"
+)
+
+
+def _parse_github_url(url: str):
+    """Parse a full GitHub URL into (owner, repo, branch, subpath).
+
+    Returns None if the URL doesn't match.
+    Supported formats:
+      https://github.com/owner/repo
+      https://github.com/owner/repo/tree/branch
+      https://github.com/owner/repo/tree/branch/path/to/skill
+      https://github.com/owner/repo/blob/branch/path/to/skill
+    """
+    m = _GITHUB_URL_RE.match(url.strip())
+    if not m:
+        return None
+    owner, repo, branch, subpath = m.groups()
+    return owner, repo, branch or "main", subpath
+
+
+def _download_github_dir(owner, repo, branch, subpath, dest_dir):
+    """Download a subdirectory from GitHub using the Contents API.
+
+    Recursively fetches all files under the given subpath and writes them
+    to dest_dir.  Raises on any network or API error.
+    """
+    api_url = f"https://api.github.com/repos/{owner}/{repo}/contents/{subpath}?ref={branch}"
+    resp = requests.get(api_url, timeout=30, headers={"Accept": "application/vnd.github.v3+json"})
+    resp.raise_for_status()
+    items = resp.json()
+
+    if isinstance(items, dict):
+        items = [items]
+
+    for item in items:
+        rel_path = item["path"]
+        if subpath:
+            rel_path = rel_path[len(subpath.strip("/")):].lstrip("/")
+        local_path = os.path.join(dest_dir, rel_path)
+
+        if item["type"] == "file":
+            os.makedirs(os.path.dirname(local_path), exist_ok=True)
+            dl_url = item.get("download_url")
+            if not dl_url:
+                continue
+            file_resp = requests.get(dl_url, timeout=30)
+            file_resp.raise_for_status()
+            with open(local_path, "wb") as f:
+                f.write(file_resp.content)
+        elif item["type"] == "dir":
+            os.makedirs(local_path, exist_ok=True)
+            child_subpath = item["path"]
+            _download_github_dir(owner, repo, branch, child_subpath, dest_dir)
+
+
+def _register_installed_skill(name: str, source: str = "cowhub"):
+    """Register a newly installed skill into skills_config.json.
+
+    source values: builtin, cow, github, clawhub, linkai, local, url
+    """
+    skills_dir = get_skills_dir()
+    config_path = os.path.join(skills_dir, "skills_config.json")
+
+    config = {}
+    if os.path.exists(config_path):
+        try:
+            with open(config_path, "r", encoding="utf-8") as f:
+                config = json.load(f)
+        except Exception:
+            config = {}
+
+    if name in config:
+        return
+
+    skill_dir = os.path.join(skills_dir, name)
+    description = _read_skill_description(skill_dir) or ""
+
+    config[name] = {
+        "name": name,
+        "description": description,
+        "source": source,
+        "enabled": True,
+        "category": "skill",
+    }
+
+    try:
+        with open(config_path, "w", encoding="utf-8") as f:
+            json.dump(config, f, indent=4, ensure_ascii=False)
+    except Exception:
+        pass
+
+
+def _parse_skill_frontmatter(content: str) -> dict:
+    """Parse YAML frontmatter from SKILL.md content and return a dict with name/description."""
+    result = {}
+    match = re.match(r'^---\s*\n(.*?)\n---\s*\n', content, re.DOTALL)
+    if not match:
+        return result
+    for line in match.group(1).split('\n'):
+        line = line.strip()
+        for key in ('name', 'description'):
+            if line.startswith(f'{key}:'):
+                val = line[len(key) + 1:].strip()
+                result[key] = val.strip('"').strip("'")
+    return result
+
+
+def _read_skill_description(skill_dir: str) -> str:
+    """Read the description from a skill's SKILL.md frontmatter."""
+    skill_md = os.path.join(skill_dir, "SKILL.md")
+    if not os.path.exists(skill_md):
+        return ""
+    try:
+        with open(skill_md, "r", encoding="utf-8") as f:
+            content = f.read()
+        return _parse_skill_frontmatter(content).get("description", "")
+    except Exception:
+        return ""
+
+
+def _install_url(url: str):
+    """Install a skill from a direct SKILL.md URL."""
+    click.echo(f"Downloading SKILL.md from {url} ...")
+    try:
+        resp = requests.get(url, timeout=30)
+        resp.raise_for_status()
+    except Exception as e:
+        click.echo(f"Error: Failed to download SKILL.md: {e}", err=True)
+        sys.exit(1)
+
+    content = resp.text
+    fm = _parse_skill_frontmatter(content)
+    skill_name = fm.get("name")
+    if not skill_name:
+        click.echo("Error: SKILL.md missing 'name' field in frontmatter.", err=True)
+        sys.exit(1)
+
+    skill_name = skill_name.strip()
+    _validate_skill_name(skill_name)
+
+    skills_dir = get_skills_dir()
+    os.makedirs(skills_dir, exist_ok=True)
+    skill_dir = os.path.join(skills_dir, skill_name)
+
+    if os.path.isdir(skill_dir):
+        click.echo(f"Skill '{skill_name}' already exists. Overwriting SKILL.md ...")
+    os.makedirs(skill_dir, exist_ok=True)
+
+    with open(os.path.join(skill_dir, "SKILL.md"), "w", encoding="utf-8") as f:
+        f.write(content)
+
+    _register_installed_skill(skill_name, source="url")
+    _print_install_success(skill_name, "url")
+
+
+def _print_install_success(name: str, source: str):
+    """Print a unified install success message with description and source."""
+    skills_dir = get_skills_dir()
+    desc = _read_skill_description(os.path.join(skills_dir, name))
+    click.echo(click.style(f"✓ {name}", fg="green"))
+    if desc:
+        if len(desc) > 60:
+            desc = desc[:57] + "…"
+        click.echo(f"  {desc}")
+    click.echo(f"  来源: {source}")
+
+
+def _validate_skill_name(name: str):
+    """Reject names that contain path traversal or special characters."""
+    if not _SAFE_NAME_RE.match(name):
+        click.echo(
+            f"Error: Invalid skill name '{name}'. "
+            "Use only letters, digits, hyphens, and underscores.",
+            err=True,
+        )
+        sys.exit(1)
+
+
+def _validate_github_spec(spec: str):
+    """Reject specs that don't look like owner/repo."""
+    if not re.match(r"^[a-zA-Z0-9_\-]+/[a-zA-Z0-9_.\-]+$", spec):
+        click.echo(f"Error: Invalid GitHub spec '{spec}'. Expected format: owner/repo", err=True)
+        sys.exit(1)
+
+
+def _safe_extractall(zf: zipfile.ZipFile, dest: str):
+    """Extract zip while guarding against Zip Slip (path traversal)."""
+    dest = os.path.realpath(dest)
+    for member in zf.infolist():
+        target = os.path.realpath(os.path.join(dest, member.filename))
+        if not target.startswith(dest + os.sep) and target != dest:
+            raise ValueError(f"Unsafe zip entry detected: {member.filename}")
+    zf.extractall(dest)
+
+
+def _verify_checksum(content: bytes, expected: str):
+    """Verify SHA-256 checksum of downloaded content.
+
+    Returns True if checksum matches or no expected value provided.
+    Exits with error if mismatch.
+    """
+    if not expected:
+        return True
+    actual = hashlib.sha256(content).hexdigest()
+    if actual != expected.lower():
+        click.echo(
+            f"Error: Checksum mismatch!\n"
+            f"  Expected: {expected}\n"
+            f"  Actual:   {actual}\n"
+            f"The downloaded package may have been tampered with.",
+            err=True,
+        )
+        sys.exit(1)
+    return True
+
+
+@click.group()
+def skill():
+    """Manage CowAgent skills."""
+    pass
+
+
+# ------------------------------------------------------------------
+# cow skill list
+# ------------------------------------------------------------------
+@skill.command("list")
+@click.option("--remote", is_flag=True, help="Browse skills on Skill Hub")
+@click.option("--page", default=1, type=int, help="Page number for remote listing")
+def skill_list(remote, page):
+    """List installed skills or browse Skill Hub."""
+    if remote:
+        _list_remote(page=page)
+    else:
+        _list_local()
+
+
+def _list_local():
+    """List locally installed skills."""
+    config = load_skills_config()
+    skills_dir = get_skills_dir()
+    builtin_dir = get_builtin_skills_dir()
+
+    if not config:
+        # Fallback: scan directories directly
+        entries = []
+        for d in [builtin_dir, skills_dir]:
+            if not os.path.isdir(d):
+                continue
+            source = "builtin" if d == builtin_dir else "custom"
+            for name in sorted(os.listdir(d)):
+                skill_path = os.path.join(d, name)
+                if os.path.isdir(skill_path) and not name.startswith("."):
+                    has_skill_md = os.path.exists(os.path.join(skill_path, "SKILL.md"))
+                    if has_skill_md:
+                        entries.append({"name": name, "source": source, "enabled": True, "description": ""})
+        if not entries:
+            click.echo("No skills installed.")
+            return
+        _print_skill_table(entries)
+        return
+
+    entries = sorted(config.values(), key=lambda x: x.get("name", ""))
+    if not entries:
+        click.echo("No skills installed.")
+        return
+    _print_skill_table(entries)
+
+
+def _print_skill_table(entries):
+    """Print skills as a formatted table."""
+    name_w = max(len(e.get("name", "")) for e in entries)
+    name_w = max(name_w, 4) + 2
+    desc_w = 40
+
+    header = f"{'Name':<{name_w}} {'Status':<10} {'Source':<10} {'Description'}"
+    click.echo(f"\n  Installed skills ({len(entries)})\n")
+    click.echo(f"  {header}")
+    click.echo(f"  {'─' * (name_w + 10 + 10 + desc_w)}")
+
+    for e in entries:
+        name = e.get("name", "")
+        enabled = e.get("enabled", True)
+        source = e.get("source", "")
+        desc = e.get("description", "") or ""
+        if len(desc) > desc_w:
+            desc = desc[:desc_w - 3] + "..."
+
+        status_icon = click.style("✓ on ", fg="green") if enabled else click.style("✗ off", fg="red")
+        click.echo(f"  {name:<{name_w}} {status_icon}  {source:<10} {desc}")
+
+    click.echo()
+
+
+_REMOTE_PAGE_SIZE = 10
+
+
+def _list_remote(page: int = 1):
+    """List skills from remote Skill Hub with server-side pagination."""
+    try:
+        resp = requests.get(
+            f"{SKILL_HUB_API}/skills",
+            params={"page": page, "limit": _REMOTE_PAGE_SIZE},
+            timeout=10,
+        )
+        resp.raise_for_status()
+        data = resp.json()
+    except Exception as e:
+        click.echo(f"Error: Failed to fetch from Skill Hub: {e}", err=True)
+        sys.exit(1)
+
+    skills = data.get("skills", [])
+    total = data.get("total", len(skills))
+
+    if not skills and page == 1:
+        click.echo("No skills available on Skill Hub.")
+        return
+
+    total_pages = max(1, (total + _REMOTE_PAGE_SIZE - 1) // _REMOTE_PAGE_SIZE)
+    page = min(page, total_pages)
+    installed = set(load_skills_config().keys())
+
+    name_w = max((len(s.get("name", "")) for s in skills), default=4)
+    name_w = max(name_w, 4) + 2
+
+    click.echo(f"\n  Skill Hub ({total} available) — page {page}/{total_pages}\n")
+    click.echo(f"  {'Name':<{name_w}} {'Status':<12} {'Description'}")
+    click.echo(f"  {'─' * (name_w + 12 + 50)}")
+
+    for s in skills:
+        name = s.get("name", "")
+        desc = s.get("description", "") or s.get("display_name", "")
+        if len(desc) > 50:
+            desc = desc[:47] + "..."
+        status = click.style("installed", fg="green") if name in installed else "—"
+        click.echo(f"  {name:<{name_w}} {status:<12} {desc}")
+
+    click.echo()
+    nav_parts = []
+    if page > 1:
+        nav_parts.append(f"cow skill list --remote --page {page - 1}")
+    if page < total_pages:
+        nav_parts.append(f"cow skill list --remote --page {page + 1}")
+    if nav_parts:
+        click.echo(f"  Navigate: {' | '.join(nav_parts)}")
+    click.echo(f"  Install:  cow skill install <name>\n")
+
+
+# ------------------------------------------------------------------
+# cow skill search
+# ------------------------------------------------------------------
+@skill.command()
+@click.argument("query")
+def search(query):
+    """Search skills on Skill Hub."""
+    try:
+        resp = requests.get(f"{SKILL_HUB_API}/skills/search", params={"q": query}, timeout=10)
+        resp.raise_for_status()
+        data = resp.json()
+    except Exception as e:
+        click.echo(f"Error: Failed to search Skill Hub: {e}", err=True)
+        sys.exit(1)
+
+    skills = data.get("skills", [])
+    if not skills:
+        click.echo(f'No skills found for "{query}".')
+        return
+
+    installed = set(load_skills_config().keys())
+    name_w = max(len(s.get("name", "")) for s in skills)
+    name_w = max(name_w, 4) + 2
+
+    click.echo(f'\n  Search results for "{query}" ({len(skills)} found)\n')
+    click.echo(f"  {'Name':<{name_w}} {'Status':<12} {'Description'}")
+    click.echo(f"  {'─' * (name_w + 12 + 50)}")
+
+    for s in skills:
+        name = s.get("name", "")
+        desc = s.get("description", "") or s.get("display_name", "")
+        if len(desc) > 50:
+            desc = desc[:47] + "..."
+        status = click.style("installed", fg="green") if name in installed else "—"
+        click.echo(f"  {name:<{name_w}} {status:<12} {desc}")
+
+    click.echo(f"\n  Install with: cow skill install <name>\n")
+
+
+# ------------------------------------------------------------------
+# cow skill install
+# ------------------------------------------------------------------
+@skill.command()
+@click.argument("name")
+def install(name):
+    """Install a skill from Skill Hub, GitHub, or a SKILL.md URL.
+
+    Examples:
+
+      cow skill install pptx
+
+      cow skill install github:owner/repo
+
+      cow skill install github:owner/repo#path/to/skill
+
+      cow skill install https://github.com/owner/repo/tree/main/path/to/skill
+
+      cow skill install https://example.com/path/to/SKILL.md
+    """
+    if name.startswith(("http://", "https://")) and name.rstrip("/").endswith("SKILL.md"):
+        # GitHub SKILL.md → strip filename and install the whole directory
+        dir_url = re.sub(r'/SKILL\.md/?$', '', name)
+        gh = _parse_github_url(dir_url)
+        if gh:
+            owner, repo, branch, subpath = gh
+            spec = f"{owner}/{repo}"
+            skill_name = subpath.rstrip("/").split("/")[-1] if subpath else repo
+            _install_github(spec, subpath=subpath, skill_name=skill_name, branch=branch)
+            return
+        _install_url(name)
+        return
+
+    parsed = _parse_github_url(name)
+    if parsed:
+        owner, repo, branch, subpath = parsed
+        spec = f"{owner}/{repo}"
+        skill_name = subpath.rstrip("/").split("/")[-1] if subpath else repo
+        _install_github(spec, subpath=subpath, skill_name=skill_name, branch=branch)
+    elif name.startswith("github:"):
+        skill_name = name[7:]
+        _validate_skill_name(skill_name)
+        _install_hub(skill_name)
+    elif name.startswith("clawhub:"):
+        skill_name = name[8:]
+        _validate_skill_name(skill_name)
+        _install_hub(skill_name, provider="clawhub")
+    else:
+        _validate_skill_name(name)
+        _install_hub(name)
+
+
+def _install_hub(name, provider=None):
+    """Install a skill from Skill Hub."""
+    skills_dir = get_skills_dir()
+    os.makedirs(skills_dir, exist_ok=True)
+
+    click.echo(f"Fetching skill info for '{name}'...")
+
+    try:
+        body = {}
+        if provider:
+            body["provider"] = provider
+        resp = requests.post(
+            f"{SKILL_HUB_API}/skills/{name}/download",
+            json=body,
+            timeout=15,
+        )
+        resp.raise_for_status()
+    except requests.HTTPError as e:
+        if e.response is not None and e.response.status_code == 404:
+            click.echo(f"Error: Skill '{name}' not found on Skill Hub.", err=True)
+        else:
+            click.echo(f"Error: Failed to fetch skill: {e}", err=True)
+        sys.exit(1)
+    except Exception as e:
+        click.echo(f"Error: Failed to connect to Skill Hub: {e}", err=True)
+        sys.exit(1)
+
+    content_type = resp.headers.get("Content-Type", "")
+
+    if "application/json" in content_type:
+        data = resp.json()
+        source_type = data.get("source_type")
+
+        if source_type == "github":
+            source_url = data.get("source_url", "")
+            parsed_url = _parse_github_url(source_url)
+            if parsed_url:
+                owner, repo, branch, subpath = parsed_url
+                click.echo(f"Source: GitHub ({source_url})")
+                _install_github(f"{owner}/{repo}", subpath=subpath, skill_name=name, branch=branch)
+            else:
+                _validate_github_spec(source_url)
+                click.echo(f"Source: GitHub ({source_url})")
+                _install_github(source_url, skill_name=name)
+            return
+
+        if source_type == "registry":
+            download_url = data.get("download_url")
+            if download_url:
+                parsed = urlparse(download_url)
+                if parsed.scheme != "https":
+                    click.echo(f"Error: Refusing to download from non-HTTPS URL.", err=True)
+                    sys.exit(1)
+                provider = data.get("source_provider", "registry")
+                expected_checksum = data.get("checksum") or data.get("sha256")
+                click.echo(f"Source: {provider}")
+                click.echo("Downloading skill package...")
+                try:
+                    dl_resp = requests.get(download_url, timeout=60, allow_redirects=True)
+                    dl_resp.raise_for_status()
+                except Exception as e:
+                    click.echo(f"Error: Failed to download from {provider}: {e}", err=True)
+                    sys.exit(1)
+                _verify_checksum(dl_resp.content, expected_checksum)
+                _install_zip_bytes(dl_resp.content, name, skills_dir)
+                _register_installed_skill(name, source=provider)
+                _print_install_success(name, provider)
+            else:
+                click.echo(f"Error: Unsupported registry provider.", err=True)
+                sys.exit(1)
+            return
+
+        if "redirect" in data:
+            source_url = data.get("source_url", "")
+            parsed_url = _parse_github_url(source_url)
+            if parsed_url:
+                owner, repo, branch, subpath = parsed_url
+                click.echo(f"Source: GitHub ({source_url})")
+                _install_github(f"{owner}/{repo}", subpath=subpath, skill_name=name, branch=branch)
+            else:
+                _validate_github_spec(source_url)
+                click.echo(f"Source: GitHub ({source_url})")
+                _install_github(source_url, skill_name=name)
+            return
+
+    elif "application/zip" in content_type:
+        click.echo("Downloading skill package...")
+        expected_checksum = resp.headers.get("X-Checksum-Sha256")
+        _verify_checksum(resp.content, expected_checksum)
+        _install_zip_bytes(resp.content, name, skills_dir)
+        _register_installed_skill(name)
+        _print_install_success(name, "cowhub")
+        return
+
+    click.echo(f"Error: Unexpected response from Skill Hub.", err=True)
+    sys.exit(1)
+
+
+def _install_github(spec, subpath=None, skill_name=None, branch="main", source="github"):
+    """Install a skill from a GitHub repo.
+
+    spec format: owner/repo or owner/repo#path
+    """
+    if "#" in spec and not subpath:
+        spec, subpath = spec.split("#", 1)
+
+    _validate_github_spec(spec)
+
+    if not skill_name:
+        skill_name = subpath.rstrip("/").split("/")[-1] if subpath else spec.split("/")[-1]
+    _validate_skill_name(skill_name)
+
+    skills_dir = get_skills_dir()
+    os.makedirs(skills_dir, exist_ok=True)
+    target_dir = os.path.join(skills_dir, skill_name)
+
+    owner, repo = spec.split("/", 1)
+
+    # For subpath installs, try GitHub Contents API first (avoids downloading entire repo)
+    if subpath:
+        click.echo(f"Downloading from GitHub: {spec}/{subpath} (branch: {branch})...")
+        try:
+            with tempfile.TemporaryDirectory() as tmp_dir:
+                api_dest = os.path.join(tmp_dir, skill_name)
+                os.makedirs(api_dest)
+                _download_github_dir(owner, repo, branch, subpath.strip("/"), api_dest)
+                if os.path.exists(target_dir):
+                    shutil.rmtree(target_dir)
+                shutil.copytree(api_dest, target_dir)
+            _register_installed_skill(skill_name, source=source)
+            _print_install_success(skill_name, source)
+            return
+        except Exception:
+            click.echo("Contents API unavailable, falling back to zip download...")
+
+    # Fallback: download full repo zip
+    zip_url = f"https://github.com/{spec}/archive/refs/heads/{branch}.zip"
+    click.echo(f"Downloading from GitHub: {spec} (branch: {branch})...")
+
+    try:
+        resp = requests.get(zip_url, timeout=60, allow_redirects=True)
+        resp.raise_for_status()
+    except Exception as e:
+        click.echo(f"Error: Failed to download from GitHub: {e}", err=True)
+        sys.exit(1)
+
+    with tempfile.TemporaryDirectory() as tmp_dir:
+        zip_path = os.path.join(tmp_dir, "repo.zip")
+        with open(zip_path, "wb") as f:
+            f.write(resp.content)
+
+        extract_dir = os.path.join(tmp_dir, "extracted")
+        with zipfile.ZipFile(zip_path, "r") as zf:
+            _safe_extractall(zf, extract_dir)
+
+        top_items = [d for d in os.listdir(extract_dir) if not d.startswith(".")]
+        repo_root = extract_dir
+        if len(top_items) == 1 and os.path.isdir(os.path.join(extract_dir, top_items[0])):
+            repo_root = os.path.join(extract_dir, top_items[0])
+
+        if subpath:
+            source_dir = os.path.join(repo_root, subpath.strip("/"))
+            if not os.path.isdir(source_dir):
+                click.echo(f"Error: Path '{subpath}' not found in repository.", err=True)
+                sys.exit(1)
+        else:
+            source_dir = repo_root
+
+        if os.path.exists(target_dir):
+            shutil.rmtree(target_dir)
+        shutil.copytree(source_dir, target_dir)
+
+    _register_installed_skill(skill_name, source=source)
+    _print_install_success(skill_name, source)
+
+
+def _install_zip_bytes(content, name, skills_dir):
+    """Extract a zip archive into the skills directory."""
+    with tempfile.TemporaryDirectory() as tmp_dir:
+        zip_path = os.path.join(tmp_dir, "package.zip")
+        with open(zip_path, "wb") as f:
+            f.write(content)
+
+        extract_dir = os.path.join(tmp_dir, "extracted")
+        with zipfile.ZipFile(zip_path, "r") as zf:
+            _safe_extractall(zf, extract_dir)
+
+        top_items = [d for d in os.listdir(extract_dir) if not d.startswith(".")]
+        source = extract_dir
+        if len(top_items) == 1 and os.path.isdir(os.path.join(extract_dir, top_items[0])):
+            source = os.path.join(extract_dir, top_items[0])
+
+        target = os.path.join(skills_dir, name)
+        if os.path.exists(target):
+            shutil.rmtree(target)
+        shutil.copytree(source, target)
+
+
+
+
+# ------------------------------------------------------------------
+# cow skill uninstall
+# ------------------------------------------------------------------
+@skill.command()
+@click.argument("name")
+@click.option("--yes", "-y", is_flag=True, help="Skip confirmation")
+def uninstall(name, yes):
+    """Uninstall a skill."""
+    _validate_skill_name(name)
+    skills_dir = get_skills_dir()
+    skill_dir = os.path.join(skills_dir, name)
+
+    if not os.path.exists(skill_dir):
+        click.echo(f"Error: Skill '{name}' is not installed.", err=True)
+        sys.exit(1)
+
+    if not yes:
+        click.confirm(f"Uninstall skill '{name}'?", abort=True)
+
+    shutil.rmtree(skill_dir)
+
+    config_path = os.path.join(skills_dir, "skills_config.json")
+    if os.path.exists(config_path):
+        try:
+            with open(config_path, "r", encoding="utf-8") as f:
+                config = json.load(f)
+            config.pop(name, None)
+            with open(config_path, "w", encoding="utf-8") as f:
+                json.dump(config, f, indent=4, ensure_ascii=False)
+        except Exception:
+            pass
+
+    click.echo(click.style(f"✓ Skill '{name}' uninstalled.", fg="green"))
+
+
+# ------------------------------------------------------------------
+# cow skill enable / disable
+# ------------------------------------------------------------------
+@skill.command()
+@click.argument("name")
+def enable(name):
+    """Enable a skill."""
+    _set_enabled(name, True)
+
+
+@skill.command()
+@click.argument("name")
+def disable(name):
+    """Disable a skill."""
+    _set_enabled(name, False)
+
+
+def _set_enabled(name, enabled):
+    _validate_skill_name(name)
+    skills_dir = get_skills_dir()
+    config_path = os.path.join(skills_dir, "skills_config.json")
+
+    if not os.path.exists(config_path):
+        click.echo(f"Error: No skills config found.", err=True)
+        sys.exit(1)
+
+    try:
+        with open(config_path, "r", encoding="utf-8") as f:
+            config = json.load(f)
+    except Exception as e:
+        click.echo(f"Error: Failed to read skills config: {e}", err=True)
+        sys.exit(1)
+
+    if name not in config:
+        click.echo(f"Error: Skill '{name}' not found in config.", err=True)
+        sys.exit(1)
+
+    config[name]["enabled"] = enabled
+    with open(config_path, "w", encoding="utf-8") as f:
+        json.dump(config, f, indent=4, ensure_ascii=False)
+
+    state = "enabled" if enabled else "disabled"
+    icon = "✓" if enabled else "✗"
+    color = "green" if enabled else "yellow"
+    click.echo(click.style(f"{icon} Skill '{name}' {state}.", fg=color))
+
+
+# ------------------------------------------------------------------
+# cow skill info
+# ------------------------------------------------------------------
+@skill.command()
+@click.argument("name")
+def info(name):
+    """Show details about an installed skill."""
+    _validate_skill_name(name)
+    skills_dir = get_skills_dir()
+    builtin_dir = get_builtin_skills_dir()
+
+    skill_dir = None
+    source = None
+    config = load_skills_config()
+    for d, src in [(skills_dir, "custom"), (builtin_dir, "builtin")]:
+        candidate = os.path.join(d, name)
+        if os.path.isdir(candidate):
+            skill_dir = candidate
+            source = config.get(name, {}).get("source") or src
+            break
+
+    if not skill_dir:
+        click.echo(f"Error: Skill '{name}' not found.", err=True)
+        sys.exit(1)
+
+    skill_md = os.path.join(skill_dir, "SKILL.md")
+    if not os.path.exists(skill_md):
+        click.echo(f"Skill directory: {skill_dir}")
+        click.echo("No SKILL.md found.")
+        return
+
+    with open(skill_md, "r", encoding="utf-8") as f:
+        content = f.read()
+
+    config = load_skills_config()
+    entry = config.get(name, {})
+    enabled = entry.get("enabled", True)
+    status_str = click.style("✓ enabled", fg="green") if enabled else click.style("✗ disabled", fg="red")
+
+    click.echo(f"\n  Skill: {name}")
+    click.echo(f"  Source: {source}")
+    click.echo(f"  Status: {status_str}")
+    click.echo(f"  Path: {skill_dir}")
+    click.echo(f"\n{'─' * 60}")
+
+    # Show first ~30 lines of SKILL.md as a preview
+    lines = content.split("\n")
+    preview = "\n".join(lines[:30])
+    click.echo(preview)
+    if len(lines) > 30:
+        click.echo(f"\n  ... ({len(lines) - 30} more lines, see {skill_md})")
+    click.echo()

cli/utils.py

@@ -0,0 +1,62 @@
+"""Shared utilities for cow CLI."""
+
+import os
+import sys
+import json
+
+
+def get_project_root() -> str:
+    """Get the CowAgent project root directory."""
+    # cli/ is directly under the project root
+    return os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+
+def get_workspace_dir() -> str:
+    """Get the agent workspace directory from config, defaulting to ~/cow."""
+    config = load_config_json()
+    workspace = config.get("agent_workspace", "~/cow")
+    return os.path.expanduser(workspace)
+
+
+def get_skills_dir() -> str:
+    """Get the custom skills directory."""
+    return os.path.join(get_workspace_dir(), "skills")
+
+
+def get_builtin_skills_dir() -> str:
+    """Get the builtin skills directory."""
+    return os.path.join(get_project_root(), "skills")
+
+
+def load_config_json() -> dict:
+    """Load config.json from project root."""
+    config_path = os.path.join(get_project_root(), "config.json")
+    if not os.path.exists(config_path):
+        return {}
+    try:
+        with open(config_path, "r", encoding="utf-8") as f:
+            return json.load(f)
+    except Exception:
+        return {}
+
+
+def load_skills_config() -> dict:
+    """Load skills_config.json from the custom skills directory."""
+    path = os.path.join(get_skills_dir(), "skills_config.json")
+    if not os.path.exists(path):
+        return {}
+    try:
+        with open(path, "r", encoding="utf-8") as f:
+            return json.load(f)
+    except Exception:
+        return {}
+
+
+def ensure_sys_path():
+    """Add project root to sys.path so we can import agent modules."""
+    root = get_project_root()
+    if root not in sys.path:
+        sys.path.insert(0, root)
+
+
+SKILL_HUB_API = "https://skills.cowagent.ai/api"

common/cloud_client.py

@@ -222,7 +222,14 @@ class CloudClient(LinkAIClient):
             return
 
         existing_ch = self.channel_mgr.get_channel(channel_type)
-        if existing_ch and not cred_changed:
+        skip_restart = existing_ch and not cred_changed
+        if skip_restart and channel_type in ("weixin", "wx"):
+            login_status = getattr(existing_ch, "login_status", "")
+            if login_status != "logged_in":
+                skip_restart = False
+                logger.info(f"[CloudClient] Channel '{channel_type}' not logged in "
+                            f"(status={login_status}), forcing restart")
+        if skip_restart:
             logger.info(f"[CloudClient] Channel '{channel_type}' already running with same config, "
                         "skip restart, reporting status only")
             threading.Thread(
@@ -255,7 +262,14 @@ class CloudClient(LinkAIClient):
             ).start()
         else:
             existing_ch = self.channel_mgr.get_channel(channel_type)
-            if existing_ch and not cred_changed:
+            needs_restart = cred_changed or not existing_ch
+            if not needs_restart and channel_type in ("weixin", "wx"):
+                login_status = getattr(existing_ch, "login_status", "")
+                if login_status != "logged_in":
+                    needs_restart = True
+                    logger.info(f"[CloudClient] Channel '{channel_type}' not logged in "
+                                f"(status={login_status}), forcing restart")
+            if existing_ch and not needs_restart:
                 logger.info(f"[CloudClient] Channel '{channel_type}' already running with same config, "
                             "skip restart, reporting status only")
                 threading.Thread(

docker/Dockerfile.latest

@@ -17,8 +17,7 @@ RUN apt-get update \
     && cp config-template.json config.json \
     && /usr/local/bin/python -m pip install --no-cache --upgrade pip \
     && pip install --no-cache -r requirements.txt \
-    && pip install --no-cache -r requirements-optional.txt \
-    && pip install azure-cognitiveservices-speech
+    && pip install --no-cache -r requirements-optional.txt
 
 WORKDIR ${BUILD_PREFIX}
 
@@ -30,6 +29,4 @@ RUN chmod +x /entrypoint.sh \
     && useradd -r -g agent -s /bin/bash -d /home/agent agent \
     && chown -R agent:agent /home/agent ${BUILD_PREFIX} /usr/local/lib
 
-USER agent
-
 ENTRYPOINT ["/entrypoint.sh"]

docker/entrypoint.sh

@@ -43,9 +43,15 @@ fi
 # fi
 
 
-# go to prefix dir
+# fix ownership of mounted volumes then drop to non-root user
+if [ "$(id -u)" = "0" ]; then
+    mkdir -p /home/agent/cow
+    chown agent:agent /home/agent/cow
+    exec su agent -s /bin/bash -c "cd $CHATGPT_ON_WECHAT_PREFIX && $CHATGPT_ON_WECHAT_EXEC"
+fi
+
+# fallback: already running as agent
 cd $CHATGPT_ON_WECHAT_PREFIX
-# excute
 $CHATGPT_ON_WECHAT_EXEC
 
 

docs/channels/weixin.mdx

@@ -1,9 +1,9 @@
 ---
 title: 微信
-description: 将 CowAgent 接入个人微信
+description: 将 CowAgent 接入个人微信（基于官方接口）
 ---
 
-> 接入个人微信，扫码登录即可使用，支持文本、图片、语音、文件、视频等消息的收发。
+> 接入个人微信，扫码登录即可使用，支持文本、图片、语音、文件、视频等消息的私聊收发。通过微信官方API进行接入，无安全风险，接入后会在会话中新增一个机器人助手，不影响当前账号的使用。
 
 ## 一、配置和运行
 

docs/en/models/deepseek.mdx

@@ -3,7 +3,22 @@ title: DeepSeek
 description: DeepSeek model configuration
 ---
 
-Use OpenAI-compatible configuration:
+Option 1: Native integration (recommended):
+
+```json
+{
+  "model": "deepseek-chat",
+  "deepseek_api_key": "YOUR_API_KEY"
+}
+```
+
+| Parameter | Description |
+| --- | --- |
+| `model` | `deepseek-chat` (DeepSeek-V3.2, non-thinking mode), `deepseek-reasoner` (DeepSeek-R1, thinking mode) |
+| `deepseek_api_key` | Create at [DeepSeek Platform](https://platform.deepseek.com/api_keys) |
+| `deepseek_api_base` | Optional, defaults to `https://api.deepseek.com/v1`. Can be changed to a third-party proxy |
+
+Option 2: OpenAI-compatible configuration:
 
 ```json
 {
@@ -14,9 +29,4 @@ Use OpenAI-compatible configuration:
 }
 ```
 
-| Parameter | Description |
-| --- | --- |
-| `model` | `deepseek-chat` (DeepSeek-V3), `deepseek-reasoner` (DeepSeek-R1) |
-| `bot_type` | Must be `openai` (OpenAI-compatible mode) |
-| `open_ai_api_key` | Create at [DeepSeek Platform](https://platform.deepseek.com/api_keys) |
-| `open_ai_api_base` | DeepSeek platform BASE URL |
+

docs/guide/manual-install.mdx

@@ -30,6 +30,8 @@ pip3 install -r requirements.txt
 pip3 install -r requirements-optional.txt
 ```
 
+> 国内网络可使用镜像源加速：`pip3 install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple`
+
 ### 3. 配置
 
 复制配置文件模板并编辑：

docs/guide/upgrade.mdx

@@ -5,7 +5,7 @@ description: CowAgent 的升级方式说明
 
 ## 脚本升级（推荐）
 
-如果使用 `run.sh` 管理服务，执行以下命令即可一键升级：
+如果使用 `run.sh` 管理服务，在项目根目录执行以下命令即可一键升级：
 
 ```bash
 ./run.sh update

docs/ja/models/deepseek.mdx

@@ -3,7 +3,22 @@ title: DeepSeek
 description: DeepSeekモデルの設定
 ---
 
-OpenAI互換の設定を使用します:
+方法1：公式接続（推奨）：
+
+```json
+{
+  "model": "deepseek-chat",
+  "deepseek_api_key": "YOUR_API_KEY"
+}
+```
+
+| パラメータ | 説明 |
+| --- | --- |
+| `model` | `deepseek-chat`（DeepSeek-V3.2、非思考モード）、`deepseek-reasoner`（DeepSeek-R1、思考モード） |
+| `deepseek_api_key` | [DeepSeek Platform](https://platform.deepseek.com/api_keys)で作成 |
+| `deepseek_api_base` | オプション、デフォルトは `https://api.deepseek.com/v1`。サードパーティプロキシに変更可能 |
+
+方法2：OpenAI互換方式：
 
 ```json
 {
@@ -13,10 +28,3 @@ OpenAI互換の設定を使用します:
   "open_ai_api_base": "https://api.deepseek.com/v1"
 }
 ```
-
-| パラメータ | 説明 |
-| --- | --- |
-| `model` | `deepseek-chat` (DeepSeek-V3)、`deepseek-reasoner` (DeepSeek-R1) |
-| `bot_type` | `openai`を指定（OpenAI互換モード） |
-| `open_ai_api_key` | [DeepSeek Platform](https://platform.deepseek.com/api_keys)で作成 |
-| `open_ai_api_base` | DeepSeekプラットフォームのBASE URL |

docs/models/deepseek.mdx

@@ -3,20 +3,29 @@ title: DeepSeek
 description: DeepSeek 模型配置
 ---
 
-通过 OpenAI 兼容方式接入：
+方式一：官方接入（推荐）：
 
 ```json
 {
   "model": "deepseek-chat",
-  "open_ai_api_key": "YOUR_API_KEY",
-  "open_ai_api_base": "https://api.deepseek.com/v1",
-  "bot_type": "openai"
+  "deepseek_api_key": "YOUR_API_KEY"
 }
 ```
 
 | 参数 | 说明 |
 | --- | --- |
-| `model` | `deepseek-chat`（DeepSeek-V3）、`deepseek-reasoner`（DeepSeek-R1） |
-| `bot_type` | 固定为 `openai`（OpenAI 兼容方式） |
-| `open_ai_api_key` | 在 [DeepSeek 平台](https://platform.deepseek.com/api_keys) 创建 |
-| `open_ai_api_base` | DeepSeek 平台 BASE URL |
+| `model` | `deepseek-chat`（DeepSeek-V3.2，非思考模式）、`deepseek-reasoner`（DeepSeek-R1，思考模式） |
+| `deepseek_api_key` | 在 [DeepSeek 平台](https://platform.deepseek.com/api_keys) 创建 |
+| `deepseek_api_base` | 可选，默认为 `https://api.deepseek.com/v1`，可修改为第三方代理地址 |
+
+方式二：OpenAI 兼容方式接入：
+
+```json
+{
+  "model": "deepseek-chat",
+  "bot_type": "openai",
+  "open_ai_api_key": "YOUR_API_KEY",
+  "open_ai_api_base": "https://api.deepseek.com/v1"
+}
+```
+

models/bot_factory.py

@@ -17,7 +17,11 @@ def create_bot(bot_type):
         from models.baidu.baidu_wenxin import BaiduWenxinBot
         return BaiduWenxinBot()
 
-    elif bot_type in (const.OPENAI, const.CHATGPT, const.DEEPSEEK):  # OpenAI-compatible API
+    elif bot_type == const.DEEPSEEK:
+        from models.deepseek.deepseek_bot import DeepSeekBot
+        return DeepSeekBot()
+
+    elif bot_type in (const.OPENAI, const.CHATGPT):  # OpenAI-compatible API
         from models.chatgpt.chat_gpt_bot import ChatGPTBot
         return ChatGPTBot()
 

models/deepseek/deepseek_bot.py

@@ -0,0 +1,160 @@
+# encoding:utf-8
+
+"""
+DeepSeek Bot — fully OpenAI-compatible, uses its own API key / base config.
+"""
+
+import time
+
+import requests
+from models.bot import Bot
+from models.openai_compatible_bot import OpenAICompatibleBot
+from models.session_manager import SessionManager
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common import const
+from common.log import logger
+from config import conf, load_config
+from .deepseek_session import DeepSeekSession
+
+DEFAULT_API_BASE = "https://api.deepseek.com/v1"
+
+
+class DeepSeekBot(Bot, OpenAICompatibleBot):
+    def __init__(self):
+        super().__init__()
+        self.sessions = SessionManager(
+            DeepSeekSession,
+            model=conf().get("model") or const.DEEPSEEK_CHAT,
+        )
+        conf_model = conf().get("model") or const.DEEPSEEK_CHAT
+        self.args = {
+            "model": conf_model,
+            "temperature": conf().get("temperature", 0.7),
+            "top_p": conf().get("top_p", 1.0),
+            "frequency_penalty": conf().get("frequency_penalty", 0.0),
+            "presence_penalty": conf().get("presence_penalty", 0.0),
+        }
+
+    # ---------- config helpers ----------
+
+    @property
+    def api_key(self):
+        return conf().get("deepseek_api_key") or conf().get("open_ai_api_key")
+
+    @property
+    def api_base(self):
+        url = (
+            conf().get("deepseek_api_base")
+            or conf().get("open_ai_api_base")
+            or DEFAULT_API_BASE
+        )
+        return url.rstrip("/")
+
+    def get_api_config(self):
+        """OpenAICompatibleBot interface — used by call_with_tools()."""
+        return {
+            "api_key": self.api_key,
+            "api_base": self.api_base,
+            "model": conf().get("model", const.DEEPSEEK_CHAT),
+            "default_temperature": conf().get("temperature", 0.7),
+            "default_top_p": conf().get("top_p", 1.0),
+            "default_frequency_penalty": conf().get("frequency_penalty", 0.0),
+            "default_presence_penalty": conf().get("presence_penalty", 0.0),
+        }
+
+    # ---------- simple chat (non-agent mode) ----------
+
+    def reply(self, query, context=None):
+        if context.type == ContextType.TEXT:
+            logger.info("[DEEPSEEK] query={}".format(query))
+
+            session_id = context["session_id"]
+            reply = None
+            clear_memory_commands = conf().get("clear_memory_commands", ["#清除记忆"])
+            if query in clear_memory_commands:
+                self.sessions.clear_session(session_id)
+                reply = Reply(ReplyType.INFO, "记忆已清除")
+            elif query == "#清除所有":
+                self.sessions.clear_all_session()
+                reply = Reply(ReplyType.INFO, "所有人记忆已清除")
+            elif query == "#更新配置":
+                load_config()
+                reply = Reply(ReplyType.INFO, "配置已更新")
+            if reply:
+                return reply
+
+            session = self.sessions.session_query(query, session_id)
+            logger.debug("[DEEPSEEK] session query={}".format(session.messages))
+
+            new_args = self.args.copy()
+            reply_content = self.reply_text(session, args=new_args)
+            logger.debug(
+                "[DEEPSEEK] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(
+                    session.messages, session_id,
+                    reply_content["content"], reply_content["completion_tokens"],
+                )
+            )
+            if reply_content["completion_tokens"] == 0 and len(reply_content["content"]) > 0:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+            elif reply_content["completion_tokens"] > 0:
+                self.sessions.session_reply(
+                    reply_content["content"], session_id, reply_content["total_tokens"],
+                )
+                reply = Reply(ReplyType.TEXT, reply_content["content"])
+            else:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+                logger.debug("[DEEPSEEK] reply {} used 0 tokens.".format(reply_content))
+            return reply
+        else:
+            reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
+            return reply
+
+    def reply_text(self, session, args=None, retry_count: int = 0) -> dict:
+        try:
+            headers = {
+                "Content-Type": "application/json",
+                "Authorization": "Bearer " + self.api_key,
+            }
+            body = args.copy()
+            body["messages"] = session.messages
+
+            res = requests.post(
+                f"{self.api_base}/chat/completions",
+                headers=headers,
+                json=body,
+                timeout=180,
+            )
+            if res.status_code == 200:
+                response = res.json()
+                return {
+                    "total_tokens": response["usage"]["total_tokens"],
+                    "completion_tokens": response["usage"]["completion_tokens"],
+                    "content": response["choices"][0]["message"]["content"],
+                }
+            else:
+                response = res.json()
+                error = response.get("error", {})
+                logger.error(
+                    f"[DEEPSEEK] chat failed, status_code={res.status_code}, "
+                    f"msg={error.get('message')}, type={error.get('type')}"
+                )
+                result = {"completion_tokens": 0, "content": "提问太快啦，请休息一下再问我吧"}
+                need_retry = False
+                if res.status_code >= 500:
+                    need_retry = retry_count < 2
+                elif res.status_code == 401:
+                    result["content"] = "授权失败，请检查API Key是否正确"
+                elif res.status_code == 429:
+                    result["content"] = "请求过于频繁，请稍后再试"
+                    need_retry = retry_count < 2
+
+                if need_retry:
+                    time.sleep(3)
+                    return self.reply_text(session, args, retry_count + 1)
+                return result
+        except Exception as e:
+            logger.exception(e)
+            if retry_count < 2:
+                return self.reply_text(session, args, retry_count + 1)
+            return {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}

models/deepseek/deepseek_session.py

@@ -0,0 +1,57 @@
+from models.session_manager import Session
+from common.log import logger
+
+
+class DeepSeekSession(Session):
+    def __init__(self, session_id, system_prompt=None, model="deepseek-chat"):
+        super().__init__(session_id, system_prompt)
+        self.model = model
+        self.reset()
+
+    def discard_exceeding(self, max_tokens, cur_tokens=None):
+        precise = True
+        try:
+            cur_tokens = self.calc_tokens()
+        except Exception as e:
+            precise = False
+            if cur_tokens is None:
+                raise e
+            logger.debug("Exception when counting tokens precisely for query: {}".format(e))
+        while cur_tokens > max_tokens:
+            if len(self.messages) > 2:
+                self.messages.pop(1)
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "assistant":
+                self.messages.pop(1)
+                if precise:
+                    cur_tokens = self.calc_tokens()
+                else:
+                    cur_tokens = cur_tokens - max_tokens
+                break
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "user":
+                logger.warn("user message exceed max_tokens. total_tokens={}".format(cur_tokens))
+                break
+            else:
+                logger.debug("max_tokens={}, total_tokens={}, len(messages)={}".format(
+                    max_tokens, cur_tokens, len(self.messages)))
+                break
+            if precise:
+                cur_tokens = self.calc_tokens()
+            else:
+                cur_tokens = cur_tokens - max_tokens
+        return cur_tokens
+
+    def calc_tokens(self):
+        return num_tokens_from_messages(self.messages, self.model)
+
+
+def num_tokens_from_messages(messages, model):
+    tokens = 0
+    for msg in messages:
+        content = msg.get("content", "")
+        if isinstance(content, str):
+            tokens += len(content)
+        elif isinstance(content, list):
+            for block in content:
+                if isinstance(block, dict):
+                    tokens += len(block.get("text", ""))
+    return tokens

models/gemini/google_gemini_bot.py

@@ -34,6 +34,13 @@ class GoogleGeminiBot(Bot):
     def api_key(self):
         return conf().get("gemini_api_key")
 
+    @property
+    def model(self):
+        model_name = conf().get("model") or "gemini-3.1-pro-preview"
+        if model_name == "gemini":
+            model_name = "gemini-3.1-pro-preview"
+        return model_name
+
     @property
     def api_base(self):
         base = conf().get("gemini_api_base", "").strip()

plugins/cow_cli/__init__.py

@@ -0,0 +1 @@
+from .cow_cli import CowCliPlugin

pyproject.toml

@@ -0,0 +1,19 @@
+[build-system]
+requires = ["setuptools>=45.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "cowagent"
+version = "0.0.1"
+description = "CowAgent - AI Agent on WeChat and more"
+requires-python = ">=3.9"
+dependencies = [
+    "click>=8.0",
+    "requests>=2.28.2",
+]
+
+[project.scripts]
+cow = "cli.cli:main"
+
+[tool.setuptools.packages.find]
+include = ["cli*"]

requirements-optional.txt

@@ -2,14 +2,8 @@ tiktoken>=0.3.2 # openai calculate token
 
 #voice
 pydub>=0.25.1 # need ffmpeg
-SpeechRecognition # google speech to text
 gTTS>=2.3.1 # google text to speech
-pyttsx3>=2.90 # pytsx text to speech
-baidu_aip>=4.16.10 # baidu voice
-azure-cognitiveservices-speech # azure voice
 edge-tts # edge-tts
-numpy<=1.24.2
-langid # language detect
 elevenlabs==1.0.3 # elevenlabs TTS
 
 #install plugin
@@ -18,18 +12,9 @@ dulwich
 # xunfei spark
 websocket-client==1.2.0
 
-# claude API
-anthropic==0.25.0
-
-# tongyi qwen
-broadscope_bailian
-
 # google
 google-generativeai
 
-# tencentcloud sdk
-tencentcloud-sdk-python>=3.0.0
-
 # file parsing (web_fetch document support)
 pypdf
 python-docx

run.sh

@@ -171,8 +171,11 @@ clone_project() {
         mv chatgpt-on-wechat-master chatgpt-on-wechat
         rm chatgpt-on-wechat.zip
     else
-        git clone https://github.com/zhayujie/chatgpt-on-wechat.git || \
-        git clone https://gitee.com/zhayujie/chatgpt-on-wechat.git
+        GIT_HTTP_CONNECT_TIMEOUT=10 GIT_HTTP_LOW_SPEED_LIMIT=1024 GIT_HTTP_LOW_SPEED_TIME=15 \
+        git clone --depth 10 --progress https://github.com/zhayujie/chatgpt-on-wechat.git || {
+            echo -e "${YELLOW}⚠️  GitHub is slow, switching to Gitee mirror...${NC}"
+            git clone --depth 10 --progress https://gitee.com/zhayujie/chatgpt-on-wechat.git
+        }
         if [[ $? -ne 0 ]]; then
             echo -e "${RED}❌ Project clone failed. Please check network connection.${NC}"
             exit 1
@@ -195,7 +198,10 @@ clone_project() {
 # Install dependencies
 install_dependencies() {
     echo -e "${GREEN}📦 Installing dependencies...${NC}"
-    local PIP_MIRROR="-i https://pypi.tuna.tsinghua.edu.cn/simple"
+    local PIP_MIRROR=""
+    if curl -s --connect-timeout 5 https://pypi.tuna.tsinghua.edu.cn/simple/ > /dev/null 2>&1; then
+        PIP_MIRROR="-i https://pypi.tuna.tsinghua.edu.cn/simple"
+    fi
 
     PIP_EXTRA_ARGS=""
     if $PYTHON_CMD -c "import sys; exit(0 if sys.version_info >= (3, 11) else 1)" 2>/dev/null; then
@@ -242,6 +248,17 @@ install_dependencies() {
     fi
 
     rm -f /tmp/pip_install.log
+
+    # Register `cow` CLI command via editable install
+    echo -e "${YELLOW}Registering cow CLI...${NC}"
+    set +e
+    $PYTHON_CMD -m pip install -e . $PIP_EXTRA_ARGS $PIP_MIRROR > /dev/null 2>&1
+    if command -v cow &> /dev/null; then
+        echo -e "${GREEN}✅ cow CLI registered.${NC}"
+    else
+        echo -e "${YELLOW}⚠️  cow CLI not in PATH, you can still use: $PYTHON_CMD -m cli.cli${NC}"
+    fi
+    set -e
 }
 
 # Select model
@@ -527,23 +544,31 @@ start_project() {
     echo -e "${GREEN}${EMOJI_ROCKET} Starting CowAgent...${NC}"
     sleep 1
 
-    if [ ! -f "${BASE_DIR}/nohup.out" ]; then
-        touch "${BASE_DIR}/nohup.out"
+    local USE_COW=false
+    if command -v cow &> /dev/null; then
+        USE_COW=true
     fi
 
-    OS_TYPE=$(uname)
-
-    if [[ "$OS_TYPE" == "Linux" ]]; then
-        # Linux: use setsid to detach from terminal
-        nohup setsid $PYTHON_CMD "${BASE_DIR}/app.py" > "${BASE_DIR}/nohup.out" 2>&1 &
-        echo -e "${GREEN}${EMOJI_COW} CowAgent started on Linux (using $PYTHON_CMD)${NC}"
-    elif [[ "$OS_TYPE" == "Darwin" ]]; then
-        # macOS: use nohup to prevent SIGHUP
-        nohup $PYTHON_CMD "${BASE_DIR}/app.py" > "${BASE_DIR}/nohup.out" 2>&1 &
-        echo -e "${GREEN}${EMOJI_COW} CowAgent started on macOS (using $PYTHON_CMD)${NC}"
+    if $USE_COW; then
+        cd "${BASE_DIR}"
+        cow start --no-logs
     else
-        echo -e "${RED}❌ Unsupported OS: ${OS_TYPE}${NC}"
-        exit 1
+        if [ ! -f "${BASE_DIR}/nohup.out" ]; then
+            touch "${BASE_DIR}/nohup.out"
+        fi
+
+        OS_TYPE=$(uname)
+
+        if [[ "$OS_TYPE" == "Linux" ]]; then
+            nohup setsid $PYTHON_CMD "${BASE_DIR}/app.py" > "${BASE_DIR}/nohup.out" 2>&1 &
+            echo -e "${GREEN}${EMOJI_COW} CowAgent started on Linux (using $PYTHON_CMD)${NC}"
+        elif [[ "$OS_TYPE" == "Darwin" ]]; then
+            nohup $PYTHON_CMD "${BASE_DIR}/app.py" > "${BASE_DIR}/nohup.out" 2>&1 &
+            echo -e "${GREEN}${EMOJI_COW} CowAgent started on macOS (using $PYTHON_CMD)${NC}"
+        else
+            echo -e "${RED}❌ Unsupported OS: ${OS_TYPE}${NC}"
+            exit 1
+        fi
     fi
 
     sleep 2
@@ -554,14 +579,21 @@ start_project() {
     echo -e "${CYAN}$ACCESS_INFO${NC}"
     echo ""
     echo -e "${CYAN}${BOLD}Management Commands:${NC}"
-    echo -e "  ${GREEN}./run.sh stop${NC}       Stop the service"
-    echo -e "  ${GREEN}./run.sh restart${NC}    Restart the service"
-    echo -e "  ${GREEN}./run.sh status${NC}     Check status"
-    echo -e "  ${GREEN}./run.sh logs${NC}       View logs"
+    if $USE_COW; then
+        echo -e "  ${GREEN}cow stop${NC}       Stop the service"
+        echo -e "  ${GREEN}cow restart${NC}    Restart the service"
+        echo -e "  ${GREEN}cow status${NC}     Check status"
+        echo -e "  ${GREEN}cow logs${NC}       View logs"
+    else
+        echo -e "  ${GREEN}./run.sh stop${NC}       Stop the service"
+        echo -e "  ${GREEN}./run.sh restart${NC}    Restart the service"
+        echo -e "  ${GREEN}./run.sh status${NC}     Check status"
+        echo -e "  ${GREEN}./run.sh logs${NC}       View logs"
+    fi
     echo -e "  ${GREEN}./run.sh update${NC}     Update and restart"
     echo -e "${CYAN}${BOLD}=========================================${NC}"
     echo ""
-    
+
     echo -e "${YELLOW}Showing recent logs (Ctrl+C to exit, agent keeps running):${NC}"
     sleep 2
     tail -n 30 -f "${BASE_DIR}/nohup.out"
@@ -603,7 +635,7 @@ ensure_python_cmd() {
 # Get service PID (empty string if not running)
 get_pid() {
     ensure_python_cmd > /dev/null 2>&1
-    ps ax | grep -i app.py | grep "${BASE_DIR}" | grep "$PYTHON_CMD" | grep -v grep | awk '{print $1}' | grep -E '^[0-9]+$'
+    ps ax | grep -i app.py | grep "${BASE_DIR}" | grep "$PYTHON_CMD" | grep -v grep | awk '{print $1}' | grep -E '^[0-9]+$' | head -1
 }
 
 # Check if service is running
@@ -611,94 +643,122 @@ is_running() {
     [ -n "$(get_pid)" ]
 }
 
+# Check if cow CLI is available
+has_cow() {
+    command -v cow &> /dev/null
+}
+
 # Start service
 cmd_start() {
-    # Check if config.json exists
     if [ ! -f "${BASE_DIR}/config.json" ]; then
         echo -e "${RED}${EMOJI_CROSS} config.json not found${NC}"
         echo -e "${YELLOW}Please run './run.sh' to configure first${NC}"
         exit 1
     fi
-    
-    if is_running; then
-        echo -e "${YELLOW}${EMOJI_WARN} CowAgent is already running (PID: $(get_pid))${NC}"
-        echo -e "${YELLOW}Use './run.sh restart' to restart${NC}"
-        return
+
+    if has_cow; then
+        cd "${BASE_DIR}"
+        cow start
+    else
+        if is_running; then
+            echo -e "${YELLOW}${EMOJI_WARN} CowAgent is already running (PID: $(get_pid))${NC}"
+            echo -e "${YELLOW}Use './run.sh restart' to restart${NC}"
+            return
+        fi
+        check_python_version
+        start_project
     fi
-    
-    check_python_version
-    start_project
 }
 
 # Stop service
 cmd_stop() {
-    echo -e "${GREEN}${EMOJI_STOP} Stopping CowAgent...${NC}"
+    if has_cow; then
+        cd "${BASE_DIR}"
+        cow stop
+    else
+        echo -e "${GREEN}${EMOJI_STOP} Stopping CowAgent...${NC}"
 
-    if ! is_running; then
-        echo -e "${YELLOW}${EMOJI_WARN} CowAgent is not running${NC}"
-        return
+        if ! is_running; then
+            echo -e "${YELLOW}${EMOJI_WARN} CowAgent is not running${NC}"
+            return
+        fi
+
+        pid=$(get_pid)
+        if [ -z "$pid" ] || ! echo "$pid" | grep -qE '^[0-9]+$'; then
+            echo -e "${RED}❌ Failed to get valid PID (got: ${pid})${NC}"
+            return 1
+        fi
+
+        echo -e "${GREEN}Found running process (PID: ${pid})${NC}"
+
+        kill ${pid}
+        sleep 3
+
+        if ps -p ${pid} > /dev/null 2>&1; then
+            echo -e "${YELLOW}⚠️  Process not stopped, forcing termination...${NC}"
+            kill -9 ${pid}
+        fi
+
+        echo -e "${GREEN}${EMOJI_CHECK} CowAgent stopped${NC}"
     fi
-
-    pid=$(get_pid)
-    if [ -z "$pid" ] || ! echo "$pid" | grep -qE '^[0-9]+$'; then
-        echo -e "${RED}❌ Failed to get valid PID (got: ${pid})${NC}"
-        return 1
-    fi
-
-    echo -e "${GREEN}Found running process (PID: ${pid})${NC}"
-
-    kill ${pid}
-    sleep 3
-
-    if ps -p ${pid} > /dev/null 2>&1; then
-        echo -e "${YELLOW}⚠️  Process not stopped, forcing termination...${NC}"
-        kill -9 ${pid}
-    fi
-
-    echo -e "${GREEN}${EMOJI_CHECK} CowAgent stopped${NC}"
 }
 
 # Restart service
 cmd_restart() {
-    cmd_stop
-    sleep 1
-    cmd_start
+    if has_cow; then
+        cd "${BASE_DIR}"
+        cow restart
+    else
+        cmd_stop
+        sleep 1
+        cmd_start
+    fi
 }
 
 # Check status
 cmd_status() {
-    echo -e "${CYAN}${BOLD}=========================================${NC}"
-    echo -e "${CYAN}${BOLD}   ${EMOJI_COW} CowAgent Status${NC}"
-    echo -e "${CYAN}${BOLD}=========================================${NC}"
-    
-    if is_running; then
-        pid=$(get_pid)
-        echo -e "${GREEN}Status:${NC} ✅ Running"
-        echo -e "${GREEN}PID:${NC}    ${pid}"
-        if [ -f "${BASE_DIR}/nohup.out" ]; then
-            echo -e "${GREEN}Logs:${NC}   ${BASE_DIR}/nohup.out"
-        fi
+    if has_cow; then
+        cd "${BASE_DIR}"
+        cow status
     else
-        echo -e "${YELLOW}Status:${NC} ⭐ Stopped"
+        echo -e "${CYAN}${BOLD}=========================================${NC}"
+        echo -e "${CYAN}${BOLD}   ${EMOJI_COW} CowAgent Status${NC}"
+        echo -e "${CYAN}${BOLD}=========================================${NC}"
+
+        if is_running; then
+            pid=$(get_pid)
+            echo -e "${GREEN}Status:${NC} ✅ Running"
+            echo -e "${GREEN}PID:${NC}    ${pid}"
+            if [ -f "${BASE_DIR}/nohup.out" ]; then
+                echo -e "${GREEN}Logs:${NC}   ${BASE_DIR}/nohup.out"
+            fi
+        else
+            echo -e "${YELLOW}Status:${NC} ⭐ Stopped"
+        fi
+
+        if [ -f "${BASE_DIR}/config.json" ]; then
+            model=$(grep -o '"model"[[:space:]]*:[[:space:]]*"[^"]*"' "${BASE_DIR}/config.json" | cut -d'"' -f4)
+            channel=$(grep -o '"channel_type"[[:space:]]*:[[:space:]]*"[^"]*"' "${BASE_DIR}/config.json" | cut -d'"' -f4)
+            echo -e "${GREEN}Model:${NC}  ${model}"
+            echo -e "${GREEN}Channel:${NC} ${channel}"
+        fi
+
+        echo -e "${CYAN}${BOLD}=========================================${NC}"
     fi
-    
-    if [ -f "${BASE_DIR}/config.json" ]; then
-        model=$(grep -o '"model"[[:space:]]*:[[:space:]]*"[^"]*"' "${BASE_DIR}/config.json" | cut -d'"' -f4)
-        channel=$(grep -o '"channel_type"[[:space:]]*:[[:space:]]*"[^"]*"' "${BASE_DIR}/config.json" | cut -d'"' -f4)
-        echo -e "${GREEN}Model:${NC}  ${model}"
-        echo -e "${GREEN}Channel:${NC} ${channel}"
-    fi
-    
-    echo -e "${CYAN}${BOLD}=========================================${NC}"
 }
 
 # View logs
 cmd_logs() {
-    if [ -f "${BASE_DIR}/nohup.out" ]; then
-        echo -e "${YELLOW}Viewing logs (Ctrl+C to exit):${NC}"
-        tail -f "${BASE_DIR}/nohup.out"
+    if has_cow; then
+        cd "${BASE_DIR}"
+        cow logs -f
     else
-        echo -e "${RED}❌ Log file not found: ${BASE_DIR}/nohup.out${NC}"
+        if [ -f "${BASE_DIR}/nohup.out" ]; then
+            echo -e "${YELLOW}Viewing logs (Ctrl+C to exit):${NC}"
+            tail -f "${BASE_DIR}/nohup.out"
+        else
+            echo -e "${RED}❌ Log file not found: ${BASE_DIR}/nohup.out${NC}"
+        fi
     fi
 }
 

scripts/run.ps1

@@ -0,0 +1,447 @@
+#Requires -Version 5.1
+<#
+.SYNOPSIS
+    CowAgent installer & management script for Windows.
+.DESCRIPTION
+    One-liner install:
+      irm https://raw.githubusercontent.com/zhayujie/chatgpt-on-wechat/master/scripts/run.ps1 | iex
+    Or from a local clone:
+      .\scripts\run.ps1              # install / configure
+      .\scripts\run.ps1 start        # start service  (delegates to cow CLI)
+      .\scripts\run.ps1 stop|restart|status|logs|config|update|help
+#>
+
+param(
+    [Parameter(Position = 0)]
+    [string]$Command = ""
+)
+
+$ErrorActionPreference = "Stop"
+
+# ── colours ──────────────────────────────────────────────────────
+function Write-Cow   { param([string]$M) Write-Host $M -ForegroundColor Green  }
+function Write-Warn  { param([string]$M) Write-Host $M -ForegroundColor Yellow }
+function Write-Err   { param([string]$M) Write-Host $M -ForegroundColor Red    }
+function Write-Info  { param([string]$M) Write-Host $M -ForegroundColor Cyan   }
+
+# ── detect project directory ─────────────────────────────────────
+$ScriptDir = if ($PSScriptRoot) { $PSScriptRoot } else { $PWD.Path }
+$BaseDir   = Split-Path $ScriptDir -Parent
+
+$IsProjectDir = (Test-Path "$BaseDir\app.py") -and (Test-Path "$BaseDir\config-template.json")
+if (-not $IsProjectDir) {
+    $BaseDir = $PWD.Path
+    $IsProjectDir = (Test-Path "$BaseDir\app.py") -and (Test-Path "$BaseDir\config-template.json")
+}
+
+# ── Python detection ─────────────────────────────────────────────
+function Find-Python {
+    foreach ($cmd in @("python3", "python")) {
+        $bin = Get-Command $cmd -ErrorAction SilentlyContinue
+        if (-not $bin) { continue }
+        try {
+            $ver = & $bin.Source -c "import sys; v=sys.version_info; print(f'{v.major}.{v.minor}')" 2>$null
+            $parts = $ver -split '\.'
+            $major = [int]$parts[0]; $minor = [int]$parts[1]
+            if ($major -eq 3 -and $minor -ge 9 -and $minor -le 13) {
+                return $bin.Source
+            }
+        } catch {}
+    }
+    return $null
+}
+
+$PythonCmd = Find-Python
+function Assert-Python {
+    if (-not $PythonCmd) {
+        Write-Err "Python 3.9-3.13 not found. Please install from https://www.python.org/downloads/"
+        exit 1
+    }
+    Write-Cow "Found Python: $PythonCmd"
+}
+
+# ── clone project ────────────────────────────────────────────────
+function Install-Project {
+    if (Test-Path "chatgpt-on-wechat") {
+        Write-Warn "Directory 'chatgpt-on-wechat' already exists."
+        $choice = Read-Host "Overwrite(o), backup(b), or quit(q)? [default: b]"
+        if (-not $choice) { $choice = "b" }
+        switch ($choice.ToLower()) {
+            "o" { Remove-Item -Recurse -Force "chatgpt-on-wechat" }
+            "b" {
+                $backup = "chatgpt-on-wechat_backup_$(Get-Date -Format 'yyyyMMddHHmmss')"
+                Rename-Item "chatgpt-on-wechat" $backup
+                Write-Cow "Backed up to '$backup'"
+            }
+            "q" { Write-Err "Installation cancelled."; exit 1 }
+            default { Write-Err "Invalid choice."; exit 1 }
+        }
+    }
+
+    $gitBin = Get-Command git -ErrorAction SilentlyContinue
+    if (-not $gitBin) {
+        Write-Err "Git not found. Please install from https://git-scm.com/download/win"
+        exit 1
+    }
+
+    Write-Cow "Cloning CowAgent project..."
+    git clone https://github.com/zhayujie/chatgpt-on-wechat.git 2>$null
+    if ($LASTEXITCODE -ne 0) {
+        Write-Warn "GitHub failed, trying Gitee..."
+        git clone https://gitee.com/zhayujie/chatgpt-on-wechat.git
+        if ($LASTEXITCODE -ne 0) {
+            Write-Err "Clone failed. Check your network."
+            exit 1
+        }
+    }
+
+    Set-Location "chatgpt-on-wechat"
+    $script:BaseDir = $PWD.Path
+    $script:IsProjectDir = $true
+    Write-Cow "Project cloned: $BaseDir"
+}
+
+# ── install dependencies ─────────────────────────────────────────
+function Install-Dependencies {
+    Write-Cow "Installing dependencies..."
+
+    & $PythonCmd -m pip install --upgrade pip setuptools wheel 2>$null | Out-Null
+
+    & $PythonCmd -m pip install -r "$BaseDir\requirements.txt" 2>&1 | ForEach-Object { Write-Host $_ }
+    if ($LASTEXITCODE -ne 0) {
+        Write-Warn "Some dependencies may have issues, but continuing..."
+    }
+
+    Write-Cow "Registering cow CLI..."
+    & $PythonCmd -m pip install -e $BaseDir 2>$null | Out-Null
+    $cowBin = Get-Command cow -ErrorAction SilentlyContinue
+    if ($cowBin) {
+        Write-Cow "cow CLI registered."
+    } else {
+        Write-Warn "cow CLI not in PATH. You can use: $PythonCmd -m cli.cli"
+    }
+}
+
+# ── model selection ──────────────────────────────────────────────
+$ModelChoices = @{
+    "1" = @{ Provider = "MiniMax";                  Default = "MiniMax-M2.7";                           Key = "MINIMAX_KEY" }
+    "2" = @{ Provider = "Zhipu AI";                 Default = "glm-5-turbo";                            Key = "ZHIPU_KEY" }
+    "3" = @{ Provider = "Kimi (Moonshot)";          Default = "kimi-k2.5";                              Key = "MOONSHOT_KEY" }
+    "4" = @{ Provider = "Doubao (Volcengine Ark)";  Default = "doubao-seed-2-0-code-preview-260215";    Key = "ARK_KEY" }
+    "5" = @{ Provider = "Qwen (DashScope)";         Default = "qwen3.5-plus";                           Key = "DASHSCOPE_KEY" }
+    "6" = @{ Provider = "Claude";                   Default = "claude-sonnet-4-6";                      Key = "CLAUDE_KEY";  Base = "https://api.anthropic.com/v1" }
+    "7" = @{ Provider = "Gemini";                   Default = "gemini-3.1-pro-preview";                 Key = "GEMINI_KEY";  Base = "https://generativelanguage.googleapis.com" }
+    "8" = @{ Provider = "OpenAI GPT";               Default = "gpt-5.4";                                Key = "OPENAI_KEY";  Base = "https://api.openai.com/v1" }
+    "9" = @{ Provider = "LinkAI";                   Default = "MiniMax-M2.7";                           Key = "LINKAI_KEY" }
+}
+
+function Select-Model {
+    Write-Info "========================================="
+    Write-Info "   Select AI Model"
+    Write-Info "========================================="
+    Write-Host "1) MiniMax (MiniMax-M2.7, MiniMax-M2.5, etc.)"
+    Write-Host "2) Zhipu AI (glm-5-turbo, glm-5, etc.)"
+    Write-Host "3) Kimi (kimi-k2.5, kimi-k2, etc.)"
+    Write-Host "4) Doubao (doubao-seed-2-0-code-preview-260215, etc.)"
+    Write-Host "5) Qwen (qwen3.5-plus, qwen3-max, qwq-plus, etc.)"
+    Write-Host "6) Claude (claude-sonnet-4-6, claude-opus-4-6, etc.)"
+    Write-Host "7) Gemini (gemini-3.1-flash-lite-preview, gemini-3.1-pro-preview, etc.)"
+    Write-Host "8) OpenAI GPT (gpt-5.4, gpt-5.2, gpt-4.1, etc.)"
+    Write-Host "9) LinkAI (access multiple models via one API)"
+    Write-Host ""
+
+    do {
+        $choice = Read-Host "Enter your choice [default: 1 - MiniMax]"
+        if (-not $choice) { $choice = "1" }
+    } while ($choice -notmatch '^[1-9]$')
+
+    $m = $ModelChoices[$choice]
+    Write-Cow "Configuring $($m.Provider)..."
+
+    $script:ApiKey    = Read-Host "Enter $($m.Provider) API Key"
+    $model            = Read-Host "Enter model name [default: $($m.Default)]"
+    if (-not $model) { $model = $m.Default }
+    $script:ModelName = $model
+    $script:KeyName   = $m.Key
+    $script:UseLinkai = ($choice -eq "9")
+
+    if ($m.Base) {
+        $base = Read-Host "Enter API Base URL [default: $($m.Base)]"
+        if (-not $base) { $base = $m.Base }
+        $script:ApiBase = $base
+    } else {
+        $script:ApiBase = ""
+    }
+    $script:ModelChoice = $choice
+}
+
+# ── channel selection ────────────────────────────────────────────
+function Select-Channel {
+    Write-Host ""
+    Write-Info "========================================="
+    Write-Info "   Select Communication Channel"
+    Write-Info "========================================="
+    Write-Host "1) Weixin"
+    Write-Host "2) Feishu"
+    Write-Host "3) DingTalk"
+    Write-Host "4) WeCom Bot"
+    Write-Host "5) QQ"
+    Write-Host "6) WeCom App"
+    Write-Host "7) Web"
+    Write-Host ""
+
+    do {
+        $choice = Read-Host "Enter your choice [default: 1 - Weixin]"
+        if (-not $choice) { $choice = "1" }
+    } while ($choice -notmatch '^[1-7]$')
+
+    $script:ChannelExtra = @{}
+
+    switch ($choice) {
+        "1" { $script:ChannelType = "weixin" }
+        "2" {
+            $script:ChannelType = "feishu"
+            $script:ChannelExtra["feishu_app_id"]     = Read-Host "Enter Feishu App ID"
+            $script:ChannelExtra["feishu_app_secret"]  = Read-Host "Enter Feishu App Secret"
+        }
+        "3" {
+            $script:ChannelType = "dingtalk"
+            $script:ChannelExtra["dingtalk_client_id"]     = Read-Host "Enter DingTalk Client ID"
+            $script:ChannelExtra["dingtalk_client_secret"]  = Read-Host "Enter DingTalk Client Secret"
+        }
+        "4" {
+            $script:ChannelType = "wecom_bot"
+            $script:ChannelExtra["wecom_bot_id"]     = Read-Host "Enter WeCom Bot ID"
+            $script:ChannelExtra["wecom_bot_secret"]  = Read-Host "Enter WeCom Bot Secret"
+        }
+        "5" {
+            $script:ChannelType = "qq"
+            $script:ChannelExtra["qq_app_id"]     = Read-Host "Enter QQ App ID"
+            $script:ChannelExtra["qq_app_secret"]  = Read-Host "Enter QQ App Secret"
+        }
+        "6" {
+            $script:ChannelType = "wechatcom_app"
+            $script:ChannelExtra["wechatcom_corp_id"]       = Read-Host "Enter WeChat Corp ID"
+            $script:ChannelExtra["wechatcomapp_token"]      = Read-Host "Enter WeChat Com App Token"
+            $script:ChannelExtra["wechatcomapp_secret"]     = Read-Host "Enter WeChat Com App Secret"
+            $script:ChannelExtra["wechatcomapp_agent_id"]   = Read-Host "Enter WeChat Com App Agent ID"
+            $script:ChannelExtra["wechatcomapp_aes_key"]    = Read-Host "Enter WeChat Com App AES Key"
+            $port = Read-Host "Enter port [default: 9898]"
+            if (-not $port) { $port = "9898" }
+            $script:ChannelExtra["wechatcomapp_port"] = [int]$port
+        }
+        "7" {
+            $script:ChannelType = "web"
+            $port = Read-Host "Enter web port [default: 9899]"
+            if (-not $port) { $port = "9899" }
+            $script:ChannelExtra["web_port"] = [int]$port
+        }
+    }
+}
+
+# ── generate config.json ─────────────────────────────────────────
+function New-ConfigFile {
+    Write-Cow "Generating config.json..."
+
+    $config = [ordered]@{
+        channel_type              = $ChannelType
+        model                     = $ModelName
+        open_ai_api_key           = ""
+        open_ai_api_base          = "https://api.openai.com/v1"
+        claude_api_key            = ""
+        claude_api_base           = "https://api.anthropic.com/v1"
+        gemini_api_key            = ""
+        gemini_api_base           = "https://generativelanguage.googleapis.com"
+        zhipu_ai_api_key          = ""
+        moonshot_api_key          = ""
+        ark_api_key               = ""
+        dashscope_api_key         = ""
+        minimax_api_key           = ""
+        voice_to_text             = "openai"
+        text_to_voice             = "openai"
+        voice_reply_voice         = $false
+        speech_recognition        = $true
+        group_speech_recognition  = $false
+        use_linkai                = $UseLinkai
+        linkai_api_key            = ""
+        linkai_app_code           = ""
+        agent                     = $true
+        agent_max_context_tokens  = 40000
+        agent_max_context_turns   = 30
+        agent_max_steps           = 15
+    }
+
+    # Set the correct API key field
+    $keyMap = @{
+        OPENAI_KEY   = "open_ai_api_key"
+        CLAUDE_KEY   = "claude_api_key"
+        GEMINI_KEY   = "gemini_api_key"
+        ZHIPU_KEY    = "zhipu_ai_api_key"
+        MOONSHOT_KEY = "moonshot_api_key"
+        ARK_KEY      = "ark_api_key"
+        DASHSCOPE_KEY = "dashscope_api_key"
+        MINIMAX_KEY  = "minimax_api_key"
+        LINKAI_KEY   = "linkai_api_key"
+    }
+    if ($keyMap.ContainsKey($KeyName)) {
+        $config[$keyMap[$KeyName]] = $ApiKey
+    }
+
+    # Set API base if provided
+    $baseMap = @{
+        "6" = "claude_api_base"
+        "7" = "gemini_api_base"
+        "8" = "open_ai_api_base"
+    }
+    if ($ApiBase -and $baseMap.ContainsKey($ModelChoice)) {
+        $config[$baseMap[$ModelChoice]] = $ApiBase
+    }
+
+    # Merge channel-specific fields
+    foreach ($k in $ChannelExtra.Keys) {
+        $config[$k] = $ChannelExtra[$k]
+    }
+
+    $config | ConvertTo-Json -Depth 5 | Set-Content -Path "$BaseDir\config.json" -Encoding UTF8
+    Write-Cow "Configuration file created."
+}
+
+# ── start via cow CLI ─────────────────────────────────────────────
+function Start-CowAgent {
+    Write-Cow "Starting CowAgent..."
+    $cowBin = Get-Command cow -ErrorAction SilentlyContinue
+    if ($cowBin) {
+        & cow start
+    } else {
+        Write-Warn "cow CLI not found, starting directly..."
+        & $PythonCmd "$BaseDir\app.py"
+    }
+}
+
+# ── delegate management commands to cow CLI ──────────────────────
+function Invoke-CowCommand {
+    param([string]$Cmd)
+    $cowBin = Get-Command cow -ErrorAction SilentlyContinue
+    if ($cowBin) {
+        & cow $Cmd
+    } else {
+        Write-Err "cow CLI not found. Run this script without arguments first to install."
+        exit 1
+    }
+}
+
+# ── usage ─────────────────────────────────────────────────────────
+function Show-Usage {
+    Write-Info "========================================="
+    Write-Info "   CowAgent Management Script (Windows)"
+    Write-Info "========================================="
+    Write-Host ""
+    Write-Host "Usage:"
+    Write-Host "  .\run.ps1               # Install / Configure"
+    Write-Host "  .\run.ps1 <command>     # Management command"
+    Write-Host ""
+    Write-Host "Commands:"
+    Write-Host "  start      Start the service"
+    Write-Host "  stop       Stop the service"
+    Write-Host "  restart    Restart the service"
+    Write-Host "  status     Check service status"
+    Write-Host "  logs       View logs"
+    Write-Host "  config     Reconfigure project"
+    Write-Host "  update     Update and restart"
+    Write-Host "  help       Show this message"
+    Write-Host ""
+}
+
+# ── install mode ──────────────────────────────────────────────────
+function Install-Mode {
+    Clear-Host
+    Write-Info "========================================="
+    Write-Info "   CowAgent Installation (Windows)"
+    Write-Info "========================================="
+    Write-Host ""
+
+    if ($IsProjectDir) {
+        Write-Cow "Detected existing project directory."
+        if (Test-Path "$BaseDir\config.json") {
+            Write-Cow "Project already configured."
+            Write-Host ""
+            Show-Usage
+            return
+        }
+        Write-Warn "No config.json found. Let's configure your project!"
+        Write-Host ""
+        Assert-Python
+    } else {
+        Assert-Python
+        Install-Project
+    }
+
+    Install-Dependencies
+    Select-Model
+    Select-Channel
+    New-ConfigFile
+
+    Write-Host ""
+    $startNow = Read-Host "Start CowAgent now? [Y/n]"
+    if ($startNow -ne "n" -and $startNow -ne "N") {
+        Start-CowAgent
+    } else {
+        Write-Cow "Installation complete!"
+        Write-Host ""
+        Write-Host "To start manually:"
+        Write-Host "  cd $BaseDir"
+        Write-Host "  cow start"
+    }
+}
+
+# ── update ────────────────────────────────────────────────────────
+function Update-Project {
+    Write-Cow "Updating CowAgent..."
+    Set-Location $BaseDir
+
+    # Stop if running
+    $cowBin = Get-Command cow -ErrorAction SilentlyContinue
+    if ($cowBin) { & cow stop 2>$null }
+
+    if (Test-Path "$BaseDir\.git") {
+        Write-Cow "Pulling latest code..."
+        git pull 2>$null
+        if ($LASTEXITCODE -ne 0) {
+            Write-Warn "GitHub failed, trying Gitee..."
+            git remote set-url origin https://gitee.com/zhayujie/chatgpt-on-wechat.git
+            git pull
+        }
+    } else {
+        Write-Warn "Not a git repository, skipping code update."
+    }
+
+    Assert-Python
+    Install-Dependencies
+    Start-CowAgent
+}
+
+# ── main ──────────────────────────────────────────────────────────
+switch ($Command.ToLower()) {
+    ""        { Install-Mode }
+    "start"   { Invoke-CowCommand "start" }
+    "stop"    { Invoke-CowCommand "stop" }
+    "restart" { Invoke-CowCommand "restart" }
+    "status"  { Invoke-CowCommand "status" }
+    "logs"    { Invoke-CowCommand "logs" }
+    "config"  {
+        Assert-Python
+        Install-Dependencies
+        Select-Model
+        Select-Channel
+        New-ConfigFile
+        $r = Read-Host "Restart service now? [Y/n]"
+        if ($r -ne "n" -and $r -ne "N") { Invoke-CowCommand "restart" }
+    }
+    "update"  { Update-Project }
+    "help"    { Show-Usage }
+    default   {
+        Write-Err "Unknown command: $Command"
+        Show-Usage
+        exit 1
+    }
+}

skills/linkai-agent/SKILL.md

@@ -4,6 +4,7 @@ description: Call LinkAI applications and workflows. Use bash with curl to invok
 homepage: https://link-ai.tech
 metadata:
   emoji: 🤖
+  default_enabled: false
   requires:
     bins: ["curl"]
     env: ["LINKAI_API_KEY"]