feat(web): add multi-session management for web console

feat: update knowledge docs and fix claude error
fix: optimize the stability of network pre-checks
2026-06-02 09:48:22 +08:00 · 2026-04-13 18:50:31 +08:00 · 2026-04-13 11:16:26 +08:00 · 2026-04-13 10:35:38 +08:00 · 2026-04-13 10:21:44 +08:00 · 2026-04-12 11:18:44 -07:00
251 changed files with 23259 additions and 3759 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -33,7 +33,16 @@ plugins/banwords/lib/__pycache__
 !plugins/keyword
 !plugins/linkai
 !plugins/agent
+!plugins/cow_cli
 client_config.json
 ref/
+**/.dev.vars
 .cursor/
 local/
+node_modules/
+
+# cow cli
+dist/
+build/
+*.egg-info/
+.cow.pid
--- a/README.md
+++ b/README.md
@@ -1,45 +1,50 @@
-<p align="center"><img src= "https://github.com/user-attachments/assets/eca9a9ec-8534-4615-9e0f-96c5ac1d10a3" alt="Chatgpt-on-Wechat" width="550" /></p>
+<p align="center"><img src= "https://github.com/user-attachments/assets/eca9a9ec-8534-4615-9e0f-96c5ac1d10a3" alt="CowAgent" width="550" /></p>

 <p align="center">
-  <a href="https://github.com/zhayujie/chatgpt-on-wechat/releases/latest"><img src="https://img.shields.io/github/v/release/zhayujie/chatgpt-on-wechat" alt="Latest release"></a>
-  <a href="https://github.com/zhayujie/chatgpt-on-wechat/blob/master/LICENSE"><img src="https://img.shields.io/github/license/zhayujie/chatgpt-on-wechat" alt="License: MIT"></a>
-  <a href="https://github.com/zhayujie/chatgpt-on-wechat"><img src="https://img.shields.io/github/stars/zhayujie/chatgpt-on-wechat?style=flat-square" alt="Stars"></a> <br/>
-  [中文] | [<a href="docs/en/README.md">English</a>]
+  <a href="https://github.com/zhayujie/CowAgent/releases/latest"><img src="https://img.shields.io/github/v/release/zhayujie/CowAgent" alt="Latest release"></a>
+  <a href="https://github.com/zhayujie/CowAgent/blob/master/LICENSE"><img src="https://img.shields.io/github/license/zhayujie/CowAgent" alt="License: MIT"></a>
+  <a href="https://github.com/zhayujie/CowAgent"><img src="https://img.shields.io/github/stars/zhayujie/CowAgent?style=flat-square" alt="Stars"></a> <br/>
+  [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。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，可接入网页、飞书、钉钉、企微智能机器人、QQ、企微自建应用、微信公众号中使用，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、拥有长期记忆和知识库并不断成长，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;
  <a href="https://docs.cowagent.ai/">📖 文档中心</a> &nbsp;·&nbsp;
-  <a href="https://docs.cowagent.ai/guide/quick-start">🚀 快速开始</a>
+  <a href="https://docs.cowagent.ai/guide/quick-start">🚀 快速开始</a> &nbsp;·&nbsp;
+  <a href="https://skills.cowagent.ai/">🧩 技能广场</a> &nbsp;·&nbsp;
+  <a href="https://link-ai.tech/cowagent/create">☁️ 在线体验</a>
 </p>


-
 # 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
+-  ✅  **自主任务规划**：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
+-  ✅  **长期记忆：** 自动将对话记忆持久化至本地文件和数据库中，包括核心记忆和日级记忆，支持关键词及向量检索
+-  ✅  **个人知识库：** 自动整理结构化知识，通过交叉引用构建知识图谱，支持通过对话管理和可视化浏览知识库
+-  ✅  **技能系统：** Skills 安装和运行的引擎，支持从 [Skill Hub](https://skills.cowagent.ai/)、GitHub 等一键安装技能，或通过对话创造 Skills
+-  ✅  **工具系统：** 内置文件读写、终端执行、浏览器操作、定时任务等工具，Agent 自主调用以完成复杂任务
+-  ✅  **CLI系统：** 提供终端命令和对话命令，支持进程管理、技能安装、配置修改等操作
 -  ✅  **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
-  ✅  **多端部署：** 支持运行在本地计算机或服务器，可集成到网页、飞书、钉钉、微信公众号、企业微信应用中使用
-  ✅  **知识库：** 集成企业知识库能力，让Agent成为专属数字员工，基于[LinkAI](https://link-ai.tech)平台实现
+-  ✅  **多模型支持：** 支持 OpenAI, Claude, Gemini, DeepSeek, MiniMax、GLM、Qwen、Kimi、Doubao 等国内外主流模型厂商
+-  ✅  **多通道接入：** 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)

-DEMO视频(对话模式)：https://cdn.link-ai.tech/doc/cow_demo.mp4
+- 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

 ## 社区

@@ -51,11 +56,11 @@ DEMO视频(对话模式)：https://cdn.link-ai.tech/doc/cow_demo.mp4

 # 企业服务

-<a href="https://link-ai.tech" target="_blank"><img width="720" src="https://cdn.link-ai.tech/image/link-ai-intro.jpg"></a>
+<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/) 是面向企业和开发者的一站式AI智能体平台，聚合多模态大模型、知识库、Agent 插件、工作流等能力，支持一键接入主流平台并进行管理，支持SaaS、私有化部署等多种模式。
+> [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：

@@ -65,15 +70,17 @@ DEMO视频(对话模式)：https://cdn.link-ai.tech/doc/cow_demo.mp4

 # 🏷 更新日志

->**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。
+>**2026.04.01：** [2.0.5版本](https://github.com/zhayujie/CowAgent/releases/tag/2.0.5)，Cow CLI 命令系统、Skill Hub 开源、浏览器工具、企微扫码创建、多项优化和修复。

->**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。
+>**2026.03.22：** [2.0.4版本](https://github.com/zhayujie/CowAgent/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。

->**2026.02.03：** [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。
+>**2026.03.18：** [2.0.3版本](https://github.com/zhayujie/CowAgent/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。

->**2025.05.23：** [1.7.6版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.7.6) 优化web网页channel、新增 [AgentMesh](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/plugins/agent/README.md)多智能体插件、百度语音合成优化、企微应用`access_token`获取优化、支持`claude-4-sonnet`和`claude-4-opus`模型
+>**2026.02.27：** [2.0.2版本](https://github.com/zhayujie/CowAgent/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。

->**2025.04.11：** [1.7.5版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.7.5) 新增支持 [wechatferry](https://github.com/zhayujie/chatgpt-on-wechat/pull/2562) 协议、新增 deepseek 模型、新增支持腾讯云语音能力、新增支持 ModelScope 和 Gitee-AI API接口
+>**2026.02.13：** [2.0.1版本](https://github.com/zhayujie/CowAgent/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/CowAgent/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)

@@ -85,11 +92,17 @@ DEMO视频(对话模式)：https://cdn.link-ai.tech/doc/cow_demo.mp4

 在终端执行以下命令：

+**Linux / macOS：**
 ```bash
-bash <(curl -sS https://cdn.link-ai.tech/code/cow/run.sh)
+bash <(curl -fsSL https://cdn.link-ai.tech/code/cow/run.sh)
 ```

-脚本使用说明：[一键运行脚本](https://docs.cowagent.ai/guide/quick-start)
+**Windows（PowerShell）：**
+```powershell
+irm https://cdn.link-ai.tech/code/cow/run.ps1 | iex
+```
+
+脚本使用说明：[一键运行脚本](https://docs.cowagent.ai/guide/quick-start)。安装后可使用 `cow start`、`cow stop` 等 [CLI 命令](https://docs.cowagent.ai/cli/index) 管理服务。


 ## 一、准备
@@ -98,24 +111,24 @@ bash <(curl -sS 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-M2.5、glm-5、kimi-k2.5、qwen3.5-plus、claude-sonnet-4-6、gemini-3.1-pro-preview、gpt-5.4
+> 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，可灵活切换 OpenAI、Claude、Gemini、DeepSeek、Qwen、Kimi 等多种常用模型，并支持知识库、工作流、插件等Agent能力，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。

-> 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：**

 ```bash
-git clone https://github.com/zhayujie/chatgpt-on-wechat
-cd chatgpt-on-wechat/
+git clone https://github.com/zhayujie/CowAgent
+cd CowAgent/
 ```

-若遇到网络问题可使用国内仓库地址：https://gitee.com/zhayujie/chatgpt-on-wechat
+若遇到网络问题可使用国内仓库地址：https://gitee.com/zhayujie/CowAgent

 **(2) 安装核心依赖 (必选)：**

@@ -128,45 +141,69 @@ 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。

+**(4) 安装 Cow CLI (推荐)：**
+
+```bash
+pip3 install -e .
+```
+
+安装后可使用 `cow` 命令管理服务（启动、停止、更新等）和技能，详见 [命令文档](https://docs.cowagent.ai/cli/index)。
+
+**(5) 安装浏览器工具 (可选)：**
+
+如果需要 Agent 操作浏览器（如访问网页、填写表单等），需要额外安装浏览器依赖：
+
+```bash
+cow install-browser
+```
+
+该命令会自动安装 `playwright` 和 Chromium 浏览器，国内网络自动使用镜像加速。详见 [浏览器工具文档](https://docs.cowagent.ai/tools/browser)。
+
 ## 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": "web",                                      # 接入渠道类型，默认为web，支持修改为:feishu,dingtalk,wecom_bot,qq,wechatcom_app,wechatmp_service,wechatmp,terminal
-  "model": "MiniMax-M2.5",                                    # 模型名称
+  "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平台接口
-  "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
+  "web_password": "",                                         # Web 控制台访问密码，留空则不启用密码保护
+  "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": 50000,                          # Agent 模式下最大上下文 tokens，超出将自动智能压缩处理
+  "agent_max_context_turns": 20,                              # Agent 模式下最大上下文记忆轮次，一问一答为一轮，超出后智能压缩处理
+  "agent_max_steps": 20                                       # 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
 }
 ```

@@ -175,28 +212,28 @@ 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）
+ 使用 MiniMax TTS：设置 `"text_to_voice": "minimax"`，并配置 `minimax_api_key`；可通过 `"tts_voice_id"` 指定发音人（如 `English_Graceful_Lady`），`"text_to_voice_model"` 指定模型（如 `speech-2.8-hd`、`speech-2.8-turbo`）
 </details>

 <details>
 <summary>2. 其他配置</summary>

-+ `model`: 模型名称，Agent模式下推荐使用 `MiniMax-M2.5`、`glm-5`、`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`、`qwen3.6-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/CowAgent/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，使用知识库、工作流、插件等能力, 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
-+ `linkai_app_code`: LinkAI 应用或工作流的code，选填，普通对话模式中使用。
 </details>

-注：全部配置项说明可在 [`config.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/config.py) 文件中查看。
+注：全部配置项说明可在 [`config.py`](https://github.com/zhayujie/CowAgent/blob/master/config.py) 文件中查看。

 ## 三、运行

@@ -205,37 +242,48 @@ 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
+cow start              # 推荐，需先安装 Cow CLI
+python3 app.py         # 或直接运行，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)。


 ### 2.服务器部署

-在服务器中可使用 `nohup` 命令在后台运行程序：
+推荐使用 `cow` 命令管理服务：
+
+```bash
+cow start              # 后台启动
+cow stop               # 停止服务
+cow restart            # 重启服务
+cow status             # 查看运行状态
+cow logs               # 查看日志
+cow update             # 拉取最新代码并重启
+```
+
+也可以使用传统方式后台运行：

 ```bash
 nohup python3 app.py & tail -f nohup.out
 ```

-执行后程序运行于服务器后台，可通过 `ctrl+c` 关闭日志，不会影响后台程序的运行。使用 `ps -ef | grep app.py | grep -v grep` 命令可查看运行于后台的进程，如果想要重新启动程序可以先 `kill` 掉对应的进程。 日志关闭后如果想要再次打开只需输入 `tail -f nohup.out`。 
-
-此外，项目的 `scripts` 目录下有一键运行、关闭程序的脚本供使用。 运行后默认channel为web，通过可以通过修改配置文件进行切换。
+此外，项目根目录下的 `run.sh` 脚本也支持一键管理服务，包括 `./run.sh start`、`./run.sh stop`、`./run.sh restart` 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。

 ### 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/) 。

 **(1) 下载 docker-compose.yml 文件**

 ```bash
-wget https://cdn.link-ai.tech/code/cow/docker-compose.yml
+curl -O https://cdn.link-ai.tech/code/cow/docker-compose.yml
 ```

 下载完成后打开 `docker-compose.yml` 填写所需配置，例如 `CHANNEL_TYPE`、`OPEN_AI_API_KEY` 和等配置。
@@ -248,32 +296,22 @@ wget 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
 ```

-**(3) 插件使用**
-
-如果需要在docker容器中修改插件配置，可通过挂载的方式完成，将 [插件配置文件](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/plugins/config.json.template)
-重命名为 `config.json`，放置于 `docker-compose.yml` 相同目录下，并在 `docker-compose.yml` 中的 `chatgpt-on-wechat` 部分下添加 `volumes` 映射:
-
-```
-volumes:
-  - ./config.json:/app/plugins/config.json
-```
-**注**：使用docker方式部署的详细教程可以参考：[docker部署CoW项目](https://www.wangpc.cc/ai/docker-deploy-cow/)
-
+> 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

-以下对所有可支持的模型的配置和使用方法进行说明，模型接口实现在项目的 `models/` 目录下。
+推荐通过 Web 控制台在线管理模型配置，无需手动编辑文件，详见 [模型文档](https://docs.cowagent.ai/models)。以下是手动修改 `config.json` 配置模型的说明：

 <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

@@ -282,34 +320,33 @@ volumes:
    "model": "gpt-5.4",
    "open_ai_api_key": "YOUR_API_KEY",
    "open_ai_api_base": "https://api.openai.com/v1",
-    "bot_type": "chatGPT"
+    "bot_type": "openai"
 }
 ```

- - `model`: 与OpenAI接口的 [model参数](https://platform.openai.com/docs/models) 一致，支持包括 gpt-5.4、o系列、gpt-4.1等模型，Agent模式推荐使用 `gpt-5.4`
+ - `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 `chatGPT`
+ - `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

 ```json
 {
+    "model": "gpt-5.4-mini",
    "use_linkai": true,
-    "linkai_api_key": "YOUR API KEY",
-    "linkai_app_code": "YOUR APP CODE"
+    "linkai_api_key": "YOUR API KEY"
 }
 ```

-+ `use_linkai`: 是否使用LinkAI接口，默认关闭，设置为true后可对接LinkAI平台的智能体，使用知识库、工作流、数据库、MCP插件等丰富的Agent能力
-+ `linkai_api_key`: LinkAI平台的API Key，可在 [控制台](https://link-ai.tech/console/interface) 中创建
-+ `linkai_app_code`: LinkAI智能体 (应用或工作流) 的code，选填，普通对话模式可用。智能体创建可参考 [说明文档](https://docs.link-ai.tech/platform/quick-start)
-+ `model`: model字段填写空则直接使用智能体的模型，可在平台中灵活切换，[模型列表](https://link-ai.tech/console/models)中的全部模型均可使用
+ `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>

 <details>
@@ -319,26 +356,26 @@ volumes:

 ```json
 {
-    "model": "MiniMax-M2.5",
+    "model": "MiniMax-M2.7",
    "minimax_api_key": ""
 }
 ```
- - `model`: 可填写 `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
+ - `model`: 可填写 `MiniMax-M2.7、MiniMax-M2.7-highspeed、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

-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": "chatGPT",
-  "model": "MiniMax-M2.5",
+  "bot_type": "openai",
+  "model": "MiniMax-M2.7",
  "open_ai_api_base": "https://api.minimaxi.com/v1",
  "open_ai_api_key": ""
 }
 ```
- `bot_type`: OpenAI兼容方式
- `model`: 可填 `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
+- `bot_type`: OpenAI 兼容方式
+- `model`: 可填 `MiniMax-M2.7、MiniMax-M2.7-highspeed、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
 </details>

 <details>
@@ -348,54 +385,54 @@ volumes:

 ```json
 {
-  "model": "glm-5",
+  "model": "glm-5-turbo",
  "zhipu_ai_api_key": ""
 }
 ```
- - `model`: 可填 `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": "chatGPT",
-  "model": "glm-5",
+  "bot_type": "openai",
+  "model": "glm-5-turbo",
  "open_ai_api_base": "https://open.bigmodel.cn/api/paas/v4",
  "open_ai_api_key": ""
 }
 ```
- `bot_type`: OpenAI兼容方式
- `model`: 可填 `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
+- `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
 </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
 {
-    "model": "qwen3.5-plus",
+    "model": "qwen3.6-plus",
    "dashscope_api_key": "sk-qVxxxxG"
 }
 ```
- - `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
+ - `model`: 可填写 `qwen3.6-plus、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 [百炼控制台](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": "chatGPT",
-  "model": "qwen3.5-plus",
+  "bot_type": "openai",
+  "model": "qwen3.6-plus",
  "open_ai_api_base": "https://dashscope.aliyuncs.com/compatible-mode/v1",
  "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>

@@ -411,27 +448,27 @@ volumes:
 }
 ```
 - `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": "chatGPT",
+  "bot_type": "openai",
  "model": "kimi-k2.5",
  "open_ai_api_base": "https://api.moonshot.cn/v1",
  "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

@@ -449,7 +486,7 @@ volumes:
 <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

@@ -465,7 +502,7 @@ volumes:
 <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",
@@ -478,30 +515,40 @@ 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": "chatGPT"
-
+    "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

@@ -518,15 +565,15 @@ 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
 {
@@ -539,19 +586,19 @@ 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": "chatGPT",
+  "bot_type": "openai",
  "model": "ERNIE-4.0-Turbo-8K",
  "open_ai_api_base": "https://qianfan.baidubce.com/v2",
  "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>

@@ -575,16 +622,16 @@ 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": "chatGPT",
+  "bot_type": "openai",
  "model": "4.0Ultra",
  "open_ai_api_base": "https://spark-api-open.xf-yun.com/v1",
  "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
@@ -603,24 +650,58 @@ 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>

+<details>
+<summary>Coding Plan</summary>
+
+Coding Plan 是各厂商推出的编程包月套餐，所有厂商均可通过 OpenAI 兼容方式接入：
+
+```json
+{
+  "bot_type": "openai",
+  "model": "模型名称",
+  "open_ai_api_base": "厂商 Coding Plan API Base",
+  "open_ai_api_key": "YOUR_API_KEY"
+}
+```
+
+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>
+

 ## 通道说明

-以下对可接入通道的配置方式进行说明，应用通道代码在项目的 `channel/` 目录下。
+推荐通过 Web 控制台在线管理通道配置，无需手动编辑文件，详见 [通道文档](https://docs.cowagent.ai/channels/weixin)。以下为手动修改 `config.json` 配置通道的说明：

 支持同时可接入多个通道，配置时可通过逗号进行分割，例如 `"channel_type": "feishu,dingtalk"`。

 <details>
-<summary>1. Web</summary>
+<summary>1. Weixin - 微信</summary>

-项目启动后会默认运行Web控制台，配置如下：
+接入个人微信，扫码登录即可使用，支持文本、图片、语音、文件等消息收发。
+
+```json
+{
+    "channel_type": "weixin"
+}
+```
+
+启动后终端会显示二维码，使用微信扫码授权即可，也可以在 Web 控制台的「通道」页面中扫码接入。登录凭证会自动保存至 `~/.weixin_cow_credentials.json`，下次启动无需重新扫码，如需重新登录删除该文件后重启即可。
+
+详细步骤和参数说明参考 [微信接入](https://docs.cowagent.ai/channels/weixin)
+
+</details>
+
+<details>
+<summary>2. Web</summary>
+
+项目启动后会默认运行 Web 控制台，配置如下：

 ```json
 {
@@ -630,12 +711,13 @@ API Key创建：在 [控制台](https://aistudio.google.com/app/apikey?hl=zh-cn)
 ```

 - `web_port`: 默认为 9899，可按需更改，需要服务器防火墙和安全组放行该端口
+- `web_password`: 访问密码，留空则不启用密码保护。部署在公网环境时建议设置
 - 如本地运行，启动后请访问 `http://localhost:9899/chat` ；如服务器运行，请访问 `http://ip:9899/chat` 
 > 注：请将上述 url 中的 ip 或者 port 替换为实际的值
 </details>

 <details>
-<summary>2. Feishu - 飞书</summary>
+<summary>3. Feishu - 飞书</summary>

 飞书支持两种事件接收模式：WebSocket 长连接（推荐）和 Webhook。

@@ -671,7 +753,7 @@ API Key创建：在 [控制台](https://aistudio.google.com/app/apikey?hl=zh-cn)
 </details>

 <details>
-<summary>3. DingTalk - 钉钉</summary>
+<summary>4. DingTalk - 钉钉</summary>

 钉钉需要在开放平台创建智能机器人应用，将以下配置填入 `config.json`：

@@ -686,7 +768,7 @@ API Key创建：在 [控制台](https://aistudio.google.com/app/apikey?hl=zh-cn)
 </details>

 <details>
-<summary>4. WeCom Bot - 企微智能机器人</summary>
+<summary>5. WeCom Bot - 企微智能机器人</summary>

 企微智能机器人使用 WebSocket 长连接模式，无需公网 IP 和域名，配置简单：

@@ -702,7 +784,7 @@ API Key创建：在 [控制台](https://aistudio.google.com/app/apikey?hl=zh-cn)
 </details>

 <details>
-<summary>5. QQ - QQ 机器人</summary>
+<summary>6. QQ - QQ 机器人</summary>

 QQ 机器人使用 WebSocket 长连接模式，无需公网 IP 和域名，支持 QQ 单聊、群聊和频道消息：

@@ -718,7 +800,7 @@ QQ 机器人使用 WebSocket 长连接模式，无需公网 IP 和域名，支
 </details>

 <details>
-<summary>6. WeCom App - 企业微信应用</summary>
+<summary>7. WeCom App - 企业微信应用</summary>

 企业微信自建应用接入需在后台创建应用并启用消息回调，配置示例：

@@ -738,7 +820,7 @@ QQ 机器人使用 WebSocket 长连接模式，无需公网 IP 和域名，支
 </details>

 <details>
-<summary>7. WeChat MP - 微信公众号</summary>
+<summary>8. WeChat MP - 微信公众号</summary>

 本项目支持订阅号和服务号两种公众号，通过服务号（`wechatmp_service`）体验更佳。

@@ -773,7 +855,7 @@ QQ 机器人使用 WebSocket 长连接模式，无需公网 IP 和域名，支
 </details>

 <details>
-<summary>8. Terminal - 终端</summary>
+<summary>9. Terminal - 终端</summary>

 修改 `config.json` 中的 `channel_type` 字段：

@@ -791,25 +873,37 @@ 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。
+- [Cow Skill Hub](https://github.com/zhayujie/cow-skill-hub)：开源的 AI Agent 技能广场，浏览、搜索、安装和发布技能，支持 CowAgent、OpenClaw、Claude Code 等多种 Agent。
+- [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。
+



 # 🔎 常见问题

-FAQs： <https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs>
+FAQs： <https://github.com/zhayujie/CowAgent/wiki/FAQs>

 或直接在线咨询 [项目小助手](https://link-ai.tech/app/Kv2fXJcH)  (知识库持续完善中，回复供参考)

 # 🛠️ 开发

-欢迎接入更多应用通道，参考 [飞书通道](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/feishu/feishu_channel.py) 新增自定义通道，实现接收和发送消息逻辑即可完成接入。 同时欢迎贡献新的Skills，参考 [Skill创造器说明](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/skills/skill-creator/SKILL.md)。
+欢迎接入更多应用通道，参考 [飞书通道](https://github.com/zhayujie/CowAgent/blob/master/channel/feishu/feishu_channel.py) 新增自定义通道，实现接收和发送消息逻辑即可完成接入。同时欢迎贡献新的 Skills，向 [Skill Hub](https://skills.cowagent.ai/submit) 提交技能。

 # ✉ 联系

-欢迎提交PR、Issues进行反馈，以及通过 🌟Star 支持并关注项目更新。项目运行遇到问题可以查看 [常见问题列表](https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs) ，以及前往 [Issues](https://github.com/zhayujie/chatgpt-on-wechat/issues) 中搜索。个人开发者可加入开源交流群参与更多讨论，企业用户可联系[产品客服](https://cdn.link-ai.tech/portal/linkai-customer-service.png)咨询。
+欢迎提交PR、Issues进行反馈，以及通过 🌟Star 支持并关注项目更新。项目运行遇到问题可以查看 [常见问题列表](https://github.com/zhayujie/CowAgent/wiki/FAQs) ，以及前往 [Issues](https://github.com/zhayujie/CowAgent/issues) 中搜索。个人开发者可加入开源交流群参与更多讨论，企业用户可联系[产品客服](https://cdn.link-ai.tech/portal/linkai-customer-service.png)咨询。

 # 🌟 贡献者

-![cow contributors](https://contrib.rocks/image?repo=zhayujie/chatgpt-on-wechat&max=1000)
+![cow contributors](https://contrib.rocks/image?repo=zhayujie/CowAgent&max=1000)
+
+# 📌 项目更名说明
+
+本项目原名 `chatgpt-on-wechat`（GitHub 原地址：https://github.com/zhayujie/chatgpt-on-wechat ），
+于 2026.04.13 正式更名为 **CowAgent**。GitHub 已自动设置重定向，原有链接仍可正常访问。
+
+如需更新本地仓库的远程地址（可选）：
+```bash
+git remote set-url origin https://github.com/zhayujie/CowAgent.git
+```
--- a/agent/chat/service.py
+++ b/agent/chat/service.py
@@ -44,6 +44,11 @@ class ChatService:
        if agent is None:
            raise RuntimeError("Failed to initialise agent for the session")

+        # Pass context metadata to model for downstream API requests
+        if hasattr(agent, 'model'):
+            agent.model.channel_type = channel_type or ""
+            agent.model.session_id = session_id or ""
+
        # State shared between the event callback and this method
        state = _StreamState()

@@ -52,7 +57,16 @@ class ChatService:
            event_type = event.get("type")
            data = event.get("data", {})

-            if event_type == "message_update":
+            if event_type == "reasoning_update":
+                delta = data.get("delta", "")
+                if delta:
+                    send_chunk_fn({
+                        "chunk_type": "reasoning",
+                        "delta": delta,
+                        "segment_id": state.segment_id,
+                    })
+
+            elif event_type == "message_update":
                # Incremental text delta
                delta = data.get("delta", "")
                if delta:
@@ -70,6 +84,23 @@ class ChatService:
                    # a new segment; collect tool results until turn_end.
                    state.pending_tool_results = []

+            elif event_type == "file_to_send":
+                url = data.get("url") or ""
+                if url:
+                    fname = data.get("file_name") or "file"
+                    ft = data.get("file_type") or "file"
+                    if ft == "image":
+                        link = f"![{fname}]({url})"
+                    else:
+                        link = f"[{fname}]({url})"
+                    send_chunk_fn({
+                        "chunk_type": "content",
+                        "delta": "\n\n" + link + "\n\n",
+                        "segment_id": state.segment_id,
+                    })
+                    # Remove url so the model won't repeat it in its reply
+                    data.pop("url", None)
+
            elif event_type == "tool_execution_start":
                # Notify the client that a tool is about to run (with its input args)
                tool_name = data.get("tool_name", "")
@@ -161,10 +192,56 @@ 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.
--- a/agent/knowledge/init.py
+++ b/agent/knowledge/init.py
--- a/agent/knowledge/service.py
+++ b/agent/knowledge/service.py
@@ -0,0 +1,218 @@
+"""
+Knowledge service for handling knowledge base operations.
+
+Provides a unified interface for listing, reading, and graphing knowledge files,
+callable from the web console, API, or CLI.
+
+Knowledge file layout (under workspace_root):
+    knowledge/index.md
+    knowledge/log.md
+    knowledge/<category>/<slug>.md
+"""
+
+import os
+import re
+from pathlib import Path
+from typing import Optional
+
+from common.log import logger
+from config import conf
+
+
+class KnowledgeService:
+    """
+    High-level service for knowledge base queries.
+    Operates directly on the filesystem.
+    """
+
+    def __init__(self, workspace_root: str):
+        self.workspace_root = workspace_root
+        self.knowledge_dir = os.path.join(workspace_root, "knowledge")
+
+    # ------------------------------------------------------------------
+    # list — directory tree with stats
+    # ------------------------------------------------------------------
+    def list_tree(self) -> dict:
+        """
+        Return the knowledge directory tree grouped by category.
+
+        Returns::
+
+            {
+                "tree": [
+                    {
+                        "dir": "concepts",
+                        "files": [
+                            {"name": "moe.md", "title": "MoE", "size": 1234},
+                            ...
+                        ]
+                    },
+                    ...
+                ],
+                "stats": {"pages": 15, "size": 32768},
+                "enabled": true
+            }
+        """
+        if not os.path.isdir(self.knowledge_dir):
+            return {"tree": [], "stats": {"pages": 0, "size": 0}, "enabled": conf().get("knowledge", True)}
+
+        tree = []
+        total_files = 0
+        total_bytes = 0
+        for name in sorted(os.listdir(self.knowledge_dir)):
+            full = os.path.join(self.knowledge_dir, name)
+            if not os.path.isdir(full) or name.startswith("."):
+                continue
+            files = []
+            for fname in sorted(os.listdir(full)):
+                if fname.endswith(".md") and not fname.startswith("."):
+                    fpath = os.path.join(full, fname)
+                    size = os.path.getsize(fpath)
+                    total_files += 1
+                    total_bytes += size
+                    title = fname.replace(".md", "")
+                    try:
+                        with open(fpath, "r", encoding="utf-8") as f:
+                            first_line = f.readline().strip()
+                        if first_line.startswith("# "):
+                            title = first_line[2:].strip()
+                    except Exception:
+                        pass
+                    files.append({"name": fname, "title": title, "size": size})
+            tree.append({"dir": name, "files": files})
+
+        return {
+            "tree": tree,
+            "stats": {"pages": total_files, "size": total_bytes},
+            "enabled": conf().get("knowledge", True),
+        }
+
+    # ------------------------------------------------------------------
+    # read — single file content
+    # ------------------------------------------------------------------
+    def read_file(self, rel_path: str) -> dict:
+        """
+        Read a single knowledge markdown file.
+
+        :param rel_path: Relative path within knowledge/, e.g. ``concepts/moe.md``
+        :return: dict with ``content`` and ``path``
+        :raises ValueError: if path is invalid or escapes knowledge dir
+        :raises FileNotFoundError: if file does not exist
+        """
+        if not rel_path or ".." in rel_path:
+            raise ValueError("invalid path")
+
+        full_path = os.path.normpath(os.path.join(self.knowledge_dir, rel_path))
+        allowed = os.path.normpath(self.knowledge_dir)
+        if not full_path.startswith(allowed + os.sep) and full_path != allowed:
+            raise ValueError("path outside knowledge dir")
+
+        if not os.path.isfile(full_path):
+            raise FileNotFoundError(f"file not found: {rel_path}")
+
+        with open(full_path, "r", encoding="utf-8") as f:
+            content = f.read()
+        return {"content": content, "path": rel_path}
+
+    # ------------------------------------------------------------------
+    # graph — nodes and links for visualization
+    # ------------------------------------------------------------------
+    def build_graph(self) -> dict:
+        """
+        Parse all knowledge pages and extract cross-reference links.
+
+        Returns::
+
+            {
+                "nodes": [
+                    {"id": "concepts/moe.md", "label": "MoE", "category": "concepts"},
+                    ...
+                ],
+                "links": [
+                    {"source": "concepts/moe.md", "target": "entities/deepseek.md"},
+                    ...
+                ]
+            }
+        """
+        knowledge_path = Path(self.knowledge_dir)
+        if not knowledge_path.is_dir():
+            return {"nodes": [], "links": []}
+
+        nodes = {}
+        links = []
+        link_re = re.compile(r'\[([^\]]*)\]\(([^)]+\.md)\)')
+
+        for md_file in knowledge_path.rglob("*.md"):
+            rel = str(md_file.relative_to(knowledge_path))
+            if rel in ("index.md", "log.md"):
+                continue
+            parts = rel.split("/")
+            category = parts[0] if len(parts) > 1 else "root"
+            title = md_file.stem.replace("-", " ").title()
+            try:
+                content = md_file.read_text(encoding="utf-8")
+                first_line = content.strip().split("\n")[0]
+                if first_line.startswith("# "):
+                    title = first_line[2:].strip()
+                for _, link_target in link_re.findall(content):
+                    resolved = (md_file.parent / link_target).resolve()
+                    try:
+                        target_rel = str(resolved.relative_to(knowledge_path))
+                    except ValueError:
+                        continue
+                    if target_rel != rel:
+                        links.append({"source": rel, "target": target_rel})
+            except Exception:
+                pass
+            nodes[rel] = {"id": rel, "label": title, "category": category}
+
+        valid_ids = set(nodes.keys())
+        links = [l for l in links if l["source"] in valid_ids and l["target"] in valid_ids]
+        seen = set()
+        deduped = []
+        for l in links:
+            key = tuple(sorted([l["source"], l["target"]]))
+            if key not in seen:
+                seen.add(key)
+                deduped.append(l)
+
+        return {"nodes": list(nodes.values()), "links": deduped}
+
+    # ------------------------------------------------------------------
+    # dispatch — single entry point for protocol messages
+    # ------------------------------------------------------------------
+    def dispatch(self, action: str, payload: Optional[dict] = None) -> dict:
+        """
+        Dispatch a knowledge management action.
+
+        :param action: ``list``, ``read``, or ``graph``
+        :param payload: action-specific payload
+        :return: protocol-compatible response dict
+        """
+        payload = payload or {}
+        try:
+            if action == "list":
+                result = self.list_tree()
+                return {"action": action, "code": 200, "message": "success", "payload": result}
+
+            elif action == "read":
+                path = payload.get("path")
+                if not path:
+                    return {"action": action, "code": 400, "message": "path is required", "payload": None}
+                result = self.read_file(path)
+                return {"action": action, "code": 200, "message": "success", "payload": result}
+
+            elif action == "graph":
+                result = self.build_graph()
+                return {"action": action, "code": 200, "message": "success", "payload": result}
+
+            else:
+                return {"action": action, "code": 400, "message": f"unknown action: {action}", "payload": None}
+
+        except ValueError as e:
+            return {"action": action, "code": 403, "message": str(e), "payload": None}
+        except FileNotFoundError as e:
+            return {"action": action, "code": 404, "message": str(e), "payload": None}
+        except Exception as e:
+            logger.error(f"[KnowledgeService] dispatch error: action={action}, error={e}")
+            return {"action": action, "code": 500, "message": str(e), "payload": None}
--- a/agent/memory/conversation_store.py
+++ b/agent/memory/conversation_store.py
@@ -28,11 +28,13 @@ from common.log import logger

 _DDL = """
 CREATE TABLE IF NOT EXISTS sessions (
-    session_id   TEXT    PRIMARY KEY,
-    channel_type TEXT    NOT NULL DEFAULT '',
-    created_at   INTEGER NOT NULL,
-    last_active  INTEGER NOT NULL,
-    msg_count    INTEGER NOT NULL DEFAULT 0
+    session_id        TEXT    PRIMARY KEY,
+    channel_type      TEXT    NOT NULL DEFAULT '',
+    title             TEXT    NOT NULL DEFAULT '',
+    context_start_seq INTEGER NOT NULL DEFAULT 0,
+    created_at        INTEGER NOT NULL,
+    last_active       INTEGER NOT NULL,
+    msg_count         INTEGER NOT NULL DEFAULT 0
 );

 CREATE TABLE IF NOT EXISTS messages (
@@ -57,6 +59,14 @@ _MIGRATION_ADD_CHANNEL_TYPE = """
 ALTER TABLE sessions ADD COLUMN channel_type TEXT NOT NULL DEFAULT '';
 """

+_MIGRATION_ADD_TITLE = """
+ALTER TABLE sessions ADD COLUMN title TEXT NOT NULL DEFAULT '';
+"""
+
+_MIGRATION_ADD_CONTEXT_START_SEQ = """
+ALTER TABLE sessions ADD COLUMN context_start_seq INTEGER NOT NULL DEFAULT 0;
+"""
+
 DEFAULT_MAX_AGE_DAYS: int = 30


@@ -188,8 +198,9 @@ def _group_into_display_turns(
            if text:
                turns.append({"role": "user", "content": text, "created_at": created_at})

-        # Collect all tool_calls and tool_results from the rest of the group
-        all_tool_calls: List[Dict[str, Any]] = []
+        # Build an ordered list of steps preserving the original sequence:
+        #   thinking → content → tool_call → content → ...
+        steps: List[Dict[str, Any]] = []
        tool_results: Dict[str, str] = {}
        final_text = ""
        final_ts: Optional[int] = None
@@ -198,24 +209,46 @@ def _group_into_display_turns(
            if role == "user":
                tool_results.update(_extract_tool_results(content))
            elif role == "assistant":
-                tcs = _extract_tool_calls(content)
-                all_tool_calls.extend(tcs)
-                t = _extract_display_text(content)
-                if t:
-                    final_text = t
+                # Walk content blocks in order to preserve interleaving
+                if isinstance(content, list):
+                    for block in content:
+                        if not isinstance(block, dict):
+                            continue
+                        btype = block.get("type")
+                        if btype == "thinking":
+                            txt = block.get("thinking", "").strip()
+                            if txt:
+                                steps.append({"type": "thinking", "content": txt})
+                        elif btype == "text":
+                            txt = block.get("text", "").strip()
+                            if txt:
+                                steps.append({"type": "content", "content": txt})
+                                final_text = txt
+                        elif btype == "tool_use":
+                            steps.append({
+                                "type": "tool",
+                                "id": block.get("id", ""),
+                                "name": block.get("name", ""),
+                                "arguments": block.get("input", {}),
+                            })
+                elif isinstance(content, str) and content.strip():
+                    steps.append({"type": "content", "content": content.strip()})
+                    final_text = content.strip()
                final_ts = created_at

-        # Attach tool results to their matching tool_call entries
-        for tc in all_tool_calls:
-            tc["result"] = tool_results.get(tc.get("id", ""), "")
+        # Attach tool results to tool steps
+        for step in steps:
+            if step["type"] == "tool":
+                step["result"] = tool_results.get(step.get("id", ""), "")

-        if final_text or all_tool_calls:
-            turns.append({
+        if steps or final_text:
+            turn = {
                "role": "assistant",
                "content": final_text,
-                "tool_calls": all_tool_calls,
+                "steps": steps,
                "created_at": final_ts or (user_row[1] if user_row else 0),
-            })
+            }
+            turns.append(turn)

    return turns

@@ -264,14 +297,21 @@ class ConversationStore:
        with self._lock:
            conn = self._connect()
            try:
+                # Respect context_start_seq: only load messages at or after the boundary
+                ctx_row = conn.execute(
+                    "SELECT context_start_seq FROM sessions WHERE session_id = ?",
+                    (session_id,),
+                ).fetchone()
+                ctx_start = ctx_row[0] if ctx_row else 0
+
                rows = conn.execute(
                    """
                    SELECT seq, role, content
                    FROM messages
-                    WHERE session_id = ?
+                    WHERE session_id = ? AND seq >= ?
                    ORDER BY seq DESC
                    """,
-                    (session_id,),
+                    (session_id, ctx_start),
                ).fetchall()
            finally:
                conn.close()
@@ -279,10 +319,7 @@ class ConversationStore:
        if not rows:
            return []

-        # Walk newest-to-oldest counting *visible* user turns (actual user text,
-        # not tool_result injections).  Record the seq of every visible user
-        # message so we can find a clean cut point later.
-        visible_turn_seqs: List[int] = []  # newest first
+        visible_turn_seqs: List[int] = []
        for seq, role, raw_content in rows:
            if role != "user":
                continue
@@ -293,17 +330,11 @@ class ConversationStore:
            if _is_visible_user_message(content):
                visible_turn_seqs.append(seq)

-        # Determine the seq of the oldest visible user message we want to keep.
-        # If the total turns fit within max_turns, keep everything.
        if len(visible_turn_seqs) <= max_turns:
-            cutoff_seq = None  # keep all
+            cutoff_seq = None
        else:
-            # The Nth visible user message (0-indexed) is the oldest we keep.
            cutoff_seq = visible_turn_seqs[max_turns - 1]

-        # Build result in chronological order, starting from cutoff.
-        # IMPORTANT: we start exactly at cutoff_seq (the visible user message),
-        # never mid-group, so tool_use / tool_result pairs are always complete.
        result = []
        for seq, role, raw_content in reversed(rows):
            if cutoff_seq is not None and seq < cutoff_seq:
@@ -312,6 +343,9 @@ class ConversationStore:
                content = json.loads(raw_content)
            except Exception:
                content = raw_content
+            # Strip thinking blocks — they are stored for UI display only
+            if role == "assistant" and isinstance(content, list):
+                content = [b for b in content if b.get("type") != "thinking"]
            result.append({"role": role, "content": content})
        return result

@@ -389,6 +423,61 @@ class ConversationStore:
                        """,
                        (session_id, session_id),
                    )
+
+                    # Auto-generate title from the first visible user message
+                    cur_title = conn.execute(
+                        "SELECT title FROM sessions WHERE session_id = ?",
+                        (session_id,),
+                    ).fetchone()
+                    if cur_title and not cur_title[0]:
+                        for msg in messages:
+                            if msg.get("role") == "user":
+                                content = msg.get("content", "")
+                                text = _extract_display_text(content)
+                                if text:
+                                    title = text[:50].split("\n")[0]
+                                    conn.execute(
+                                        "UPDATE sessions SET title = ? WHERE session_id = ?",
+                                        (title, session_id),
+                                    )
+                                    break
+            finally:
+                conn.close()
+
+    def clear_context(self, session_id: str) -> int:
+        """
+        Set the context boundary to after the current last message.
+        Messages before this boundary are still stored but excluded from LLM context.
+
+        Returns the new context_start_seq value.
+        """
+        with self._lock:
+            conn = self._connect()
+            try:
+                with conn:
+                    row = conn.execute(
+                        "SELECT COALESCE(MAX(seq), -1) FROM messages WHERE session_id = ?",
+                        (session_id,),
+                    ).fetchone()
+                    new_start = row[0] + 1
+                    conn.execute(
+                        "UPDATE sessions SET context_start_seq = ? WHERE session_id = ?",
+                        (new_start, session_id),
+                    )
+                    return new_start
+            finally:
+                conn.close()
+
+    def get_context_start_seq(self, session_id: str) -> int:
+        """Return the context_start_seq for a session (0 if not set)."""
+        with self._lock:
+            conn = self._connect()
+            try:
+                row = conn.execute(
+                    "SELECT context_start_seq FROM sessions WHERE session_id = ?",
+                    (session_id,),
+                ).fetchone()
+                return row[0] if row else 0
            finally:
                conn.close()

@@ -410,6 +499,7 @@ class ConversationStore:
    def cleanup_old_sessions(self, max_age_days: Optional[int] = None) -> int:
        """
        Delete sessions that have not been active within max_age_days.
+        Web channel sessions are excluded — they are meant to be permanent.

        Args:
            max_age_days: Override the default retention period.
@@ -433,7 +523,8 @@ class ConversationStore:
            try:
                with conn:
                    stale = conn.execute(
-                        "SELECT session_id FROM sessions WHERE last_active < ?",
+                        "SELECT session_id FROM sessions "
+                        "WHERE last_active < ? AND channel_type != 'web'",
                        (cutoff,),
                    ).fetchall()
                    for (sid,) in stale:
@@ -492,9 +583,15 @@ class ConversationStore:
        with self._lock:
            conn = self._connect()
            try:
+                ctx_row = conn.execute(
+                    "SELECT context_start_seq FROM sessions WHERE session_id = ?",
+                    (session_id,),
+                ).fetchone()
+                ctx_start = ctx_row[0] if ctx_row else 0
+
                rows = conn.execute(
                    """
-                    SELECT role, content, created_at
+                    SELECT seq, role, content, created_at
                    FROM messages
                    WHERE session_id = ?
                    ORDER BY seq ASC
@@ -504,7 +601,30 @@ class ConversationStore:
            finally:
                conn.close()

-        visible = _group_into_display_turns(rows)
+        # Strip seq for display grouping, but record max seq per visible user group
+        plain_rows = [(role, content, created_at) for _seq, role, content, created_at in rows]
+        visible = _group_into_display_turns(plain_rows)
+
+        # Build a mapping: find the seq of each visible user message to annotate context boundary.
+        # Walk through rows to find visible user message seqs in order.
+        visible_user_seqs: List[int] = []
+        for seq, role, raw_content, _ts in rows:
+            if role != "user":
+                continue
+            try:
+                content = json.loads(raw_content)
+            except Exception:
+                content = raw_content
+            if _is_visible_user_message(content):
+                visible_user_seqs.append(seq)
+
+        # Each pair of display turns (user+assistant) corresponds to a visible user seq.
+        # Mark which turns are before the context boundary.
+        user_turn_idx = 0
+        for turn in visible:
+            if turn["role"] == "user" and user_turn_idx < len(visible_user_seqs):
+                turn["_seq"] = visible_user_seqs[user_turn_idx]
+                user_turn_idx += 1

        total = len(visible)
        offset = (page - 1) * page_size
@@ -513,12 +633,98 @@ class ConversationStore:

        return {
            "messages": page_items,
+            "context_start_seq": ctx_start,
            "total": total,
            "page": page,
            "page_size": page_size,
            "has_more": offset + page_size < total,
        }

+    def list_sessions(
+        self,
+        channel_type: Optional[str] = None,
+        page: int = 1,
+        page_size: int = 50,
+    ) -> Dict[str, Any]:
+        """
+        List sessions ordered by last_active DESC, with optional channel_type filter.
+
+        Returns:
+            {
+                "sessions": [{session_id, title, created_at, last_active, msg_count}, ...],
+                "total": int,
+                "page": int,
+                "page_size": int,
+                "has_more": bool,
+            }
+        """
+        page = max(1, page)
+        with self._lock:
+            conn = self._connect()
+            try:
+                if channel_type:
+                    total = conn.execute(
+                        "SELECT COUNT(*) FROM sessions WHERE channel_type = ?",
+                        (channel_type,),
+                    ).fetchone()[0]
+                    rows = conn.execute(
+                        """
+                        SELECT session_id, title, created_at, last_active, msg_count
+                        FROM sessions
+                        WHERE channel_type = ?
+                        ORDER BY last_active DESC
+                        LIMIT ? OFFSET ?
+                        """,
+                        (channel_type, page_size, (page - 1) * page_size),
+                    ).fetchall()
+                else:
+                    total = conn.execute(
+                        "SELECT COUNT(*) FROM sessions",
+                    ).fetchone()[0]
+                    rows = conn.execute(
+                        """
+                        SELECT session_id, title, created_at, last_active, msg_count
+                        FROM sessions
+                        ORDER BY last_active DESC
+                        LIMIT ? OFFSET ?
+                        """,
+                        (page_size, (page - 1) * page_size),
+                    ).fetchall()
+            finally:
+                conn.close()
+
+        sessions = [
+            {
+                "session_id": r[0],
+                "title": r[1],
+                "created_at": r[2],
+                "last_active": r[3],
+                "msg_count": r[4],
+            }
+            for r in rows
+        ]
+        return {
+            "sessions": sessions,
+            "total": total,
+            "page": page,
+            "page_size": page_size,
+            "has_more": (page - 1) * page_size + page_size < total,
+        }
+
+    def rename_session(self, session_id: str, title: str) -> bool:
+        """Update the title of a session. Returns True if the session existed."""
+        with self._lock:
+            conn = self._connect()
+            try:
+                with conn:
+                    cur = conn.execute(
+                        "UPDATE sessions SET title = ? WHERE session_id = ?",
+                        (title, session_id),
+                    )
+                    return cur.rowcount > 0
+            finally:
+                conn.close()
+
    def get_stats(self) -> Dict[str, Any]:
        """Return basic stats keyed by channel_type, for monitoring."""
        with self._lock:
@@ -573,6 +779,20 @@ class ConversationStore:
                logger.info("[ConversationStore] Migrated: added channel_type column")
            except Exception as e:
                logger.warning(f"[ConversationStore] Migration failed: {e}")
+        if "title" not in cols:
+            try:
+                conn.execute(_MIGRATION_ADD_TITLE)
+                conn.commit()
+                logger.info("[ConversationStore] Migrated: added title column")
+            except Exception as e:
+                logger.warning(f"[ConversationStore] Migration (title) failed: {e}")
+        if "context_start_seq" not in cols:
+            try:
+                conn.execute(_MIGRATION_ADD_CONTEXT_START_SEQ)
+                conn.commit()
+                logger.info("[ConversationStore] Migrated: added context_start_seq column")
+            except Exception as e:
+                logger.warning(f"[ConversationStore] Migration (context_start_seq) failed: {e}")

    def _connect(self) -> sqlite3.Connection:
        conn = sqlite3.connect(str(self._db_path), timeout=10)
--- a/agent/memory/embedding.py
+++ b/agent/memory/embedding.py
@@ -32,18 +32,21 @@ class EmbeddingProvider(ABC):
 class OpenAIEmbeddingProvider(EmbeddingProvider):
    """OpenAI embedding provider using REST API"""
    
-    def __init__(self, model: str = "text-embedding-3-small", api_key: Optional[str] = None, api_base: Optional[str] = None):
+    def __init__(self, model: str = "text-embedding-3-small", api_key: Optional[str] = None,
+                 api_base: Optional[str] = None, extra_headers: Optional[dict] = None):
        """
        Initialize OpenAI embedding provider
-        
+
        Args:
            model: Model name (text-embedding-3-small or text-embedding-3-large)
            api_key: OpenAI API key
            api_base: Optional API base URL
+            extra_headers: Optional extra headers to include in API requests
        """
        self.model = model
        self.api_key = api_key
        self.api_base = api_base or "https://api.openai.com/v1"
+        self.extra_headers = extra_headers or {}

        # Validate API key
        if not self.api_key or self.api_key in ["", "YOUR API KEY", "YOUR_API_KEY"]:
@@ -59,7 +62,8 @@ class OpenAIEmbeddingProvider(EmbeddingProvider):
        url = f"{self.api_base}/embeddings"
        headers = {
            "Content-Type": "application/json",
-            "Authorization": f"Bearer {self.api_key}"
+            "Authorization": f"Bearer {self.api_key}",
+            **self.extra_headers,
        }
        data = {
            "input": input_data,
@@ -134,7 +138,8 @@ def create_embedding_provider(
    provider: str = "openai",
    model: Optional[str] = None,
    api_key: Optional[str] = None,
-    api_base: Optional[str] = None
+    api_base: Optional[str] = None,
+    extra_headers: Optional[dict] = None
 ) -> EmbeddingProvider:
    """
    Factory function to create embedding provider
@@ -147,10 +152,11 @@ def create_embedding_provider(
        model: Model name (default: text-embedding-3-small)
        api_key: API key (required)
        api_base: API base URL
-        
+        extra_headers: Optional extra headers to include in API requests
+
    Returns:
        EmbeddingProvider instance
-        
+
    Raises:
        ValueError: If provider is unsupported or api_key is missing
    """
@@ -158,4 +164,4 @@ def create_embedding_provider(
        raise ValueError(f"Unsupported embedding provider: {provider}. Use 'openai' or 'linkai'.")

    model = model or "text-embedding-3-small"
-    return OpenAIEmbeddingProvider(model=model, api_key=api_key, api_base=api_base)
+    return OpenAIEmbeddingProvider(model=model, api_key=api_key, api_base=api_base, extra_headers=extra_headers)
--- a/agent/memory/manager.py
+++ b/agent/memory/manager.py
@@ -76,11 +76,15 @@ class MemoryManager:
                    linkai_key = os.environ.get('LINKAI_API_KEY')
                    linkai_base = os.environ.get('LINKAI_API_BASE', 'https://api.link-ai.tech')
                    if linkai_key:
+                        from common.utils import get_cloud_headers
+                        cloud_headers = get_cloud_headers(linkai_key)
+                        cloud_headers.pop("Authorization", None)
                        self.embedding_provider = create_embedding_provider(
                            provider="linkai",
                            model=self.config.embedding_model,
                            api_key=linkai_key,
-                            api_base=f"{linkai_base}/v1"
+                            api_base=f"{linkai_base}/v1",
+                            extra_headers=cloud_headers,
                        )
                except Exception as e:
                    from common.log import logger
@@ -281,6 +285,10 @@ class MemoryManager:
        # Scan memory directory (including daily summaries)
        if memory_dir.exists():
            for file_path in memory_dir.rglob("*.md"):
+                # Skip hidden directories (e.g. .dreams/)
+                if any(part.startswith('.') for part in file_path.relative_to(workspace_dir).parts):
+                    continue
+
                # Determine scope and user_id from path
                rel_path = file_path.relative_to(workspace_dir)
                parts = rel_path.parts
@@ -308,6 +316,14 @@ class MemoryManager:
                    scope = "shared"
                
                await self._sync_file(file_path, "memory", scope, user_id)
+
+        # Scan knowledge directory (structured knowledge wiki)
+        from config import conf
+        if conf().get("knowledge", True):
+            knowledge_dir = Path(workspace_dir) / "knowledge"
+            if knowledge_dir.exists():
+                for file_path in knowledge_dir.rglob("*.md"):
+                    await self._sync_file(file_path, "knowledge", "shared", None)
        
        self._dirty = False
    
--- a/agent/memory/service.py
+++ b/agent/memory/service.py
@@ -134,6 +134,8 @@ class MemoryService:
            else:
                return {"action": action, "code": 400, "message": f"unknown action: {action}", "payload": None}

+        except ValueError as e:
+            return {"action": action, "code": 403, "message": "invalid filename", "payload": None}
        except FileNotFoundError as e:
            return {"action": action, "code": 404, "message": str(e), "payload": None}
        except Exception as e:
@@ -145,14 +147,26 @@ class MemoryService:
    # ------------------------------------------------------------------
    def _resolve_path(self, filename: str) -> str:
        """
-        Resolve a filename to its absolute path.
+        Safely resolve a filename to its absolute path within the allowed directory.

        - ``MEMORY.md`` → ``{workspace_root}/MEMORY.md``
        - ``2026-02-20.md`` → ``{workspace_root}/memory/2026-02-20.md``
+
+        Raises ValueError if the resolved path escapes the allowed directory
+        (path traversal protection).
        """
        if filename == "MEMORY.md":
-            return os.path.join(self.workspace_root, filename)
-        return os.path.join(self.memory_dir, filename)
+            base_dir = self.workspace_root
+        else:
+            base_dir = self.memory_dir
+
+        resolved = os.path.realpath(os.path.join(base_dir, filename))
+        allowed = os.path.realpath(base_dir)
+
+        if resolved != allowed and not resolved.startswith(allowed + os.sep):
+            raise ValueError(f"Invalid filename: path traversal detected")
+
+        return resolved

    @staticmethod
    def _file_info(path: str, filename: str, file_type: str) -> dict:
--- a/agent/memory/summarizer.py
+++ b/agent/memory/summarizer.py
@@ -1,9 +1,10 @@
 """
-Memory flush manager
+Memory flush manager (with Light Dream)

 Handles memory persistence when conversation context is trimmed or overflows:
 - Uses LLM to summarize discarded messages into concise key-information entries
 - Writes to daily memory files (lazy creation)
+- Light Dream: extracts long-term memories to MEMORY.md in the same LLM call
 - Deduplicates trim flushes to avoid repeated writes
 - Runs summarization asynchronously to avoid blocking normal replies
 - Provides daily summary interface for scheduler
@@ -16,16 +17,41 @@ from datetime import datetime
 from common.log import logger


-SUMMARIZE_SYSTEM_PROMPT = """你是一个记忆提取助手。你的任务是从对话记录中提取值得记住的信息，生成简洁的记忆摘要。
+SUMMARIZE_SYSTEM_PROMPT = """你是一个记忆提取助手。你的任务是从对话记录中提炼出两种记忆：

-输出要求：
-1. 以事件/关键信息为维度记录，每条一行，用 "- " 开头
-2. 记录有价值的关键信息，例如用户提出的要求及助手的解决方案，对话中涉及的事实信息，用户的偏好、决策或重要结论
-3. 每条摘要需要简明扼要，只保留关键信息
-4. 直接输出摘要内容，不要加任何前缀说明
-5. 当对话没有任何记录价值例如只是简单问候，可回复"无\""""
+## 第一部分：日常记录（[DAILY]）

-SUMMARIZE_USER_PROMPT = """请从以下对话记录中提取关键信息，生成记忆摘要：
+按「事件」维度归纳当天发生的事，不要按对话轮次逐条记录：
+- 每条一行，用 "- " 开头
+- 合并同一件事的多轮对话
+- 只记录有意义的事件，忽略闲聊和问候
+
+## 第二部分：长期记忆（[MEMORY]）
+
+提取值得**永久记住**的关键信息，这些信息在未来的对话中仍然有价值：
+- 用户的偏好、习惯、风格（如"用户偏好中文回复"、"用户喜欢简洁风格"）
+- 重要的决策或约定（如"项目决定使用 PostgreSQL"）
+- 关键人物信息（如"张总是用户的上级"）
+- 用户明确要求记住的内容
+- 重要的教训或经验总结
+
+**如果没有值得永久记住的信息，[MEMORY] 部分留空即可。**
+
+## 输出格式（严格遵守）
+
+```
+[DAILY]
+- 事件1的摘要
+- 事件2的摘要
+
+[MEMORY]
+- 值得永久记住的信息1
+- 值得永久记住的信息2
+```
+
+当对话没有任何记录价值（仅含问候或无意义内容），直接回复"无"。"""
+
+SUMMARIZE_USER_PROMPT = """请从以下对话记录中提取记忆（按 [DAILY] 和 [MEMORY] 两部分输出）：

 {conversation}"""

@@ -150,40 +176,111 @@ class MemoryFlushManager:
        reason: str,
        max_messages: int,
    ):
-        """Background worker: summarize with LLM and write to daily file."""
+        """Background worker: summarize with LLM, write daily file + MEMORY.md (Light Dream)."""
        try:
-            summary = self._summarize_messages(messages, max_messages)
-            if not summary or not summary.strip() or summary.strip() == "无":
+            raw_summary = self._summarize_messages(messages, max_messages)
+            if not raw_summary or not raw_summary.strip() or raw_summary.strip() == "无":
                logger.info(f"[MemoryFlush] No valuable content to flush (reason={reason})")
                return
-            
-            daily_file = ensure_daily_memory_file(self.workspace_dir, user_id)
-            
-            if reason == "overflow":
-                header = f"## Context Overflow Recovery ({datetime.now().strftime('%H:%M')})"
-                note = "The following conversation was trimmed due to context overflow:\n"
-            elif reason == "trim":
-                header = f"## Trimmed Context ({datetime.now().strftime('%H:%M')})"
-                note = ""
-            elif reason == "daily_summary":
-                header = f"## Daily Summary ({datetime.now().strftime('%H:%M')})"
-                note = ""
-            else:
-                header = f"## Session Notes ({datetime.now().strftime('%H:%M')})"
-                note = ""
-            
-            flush_entry = f"\n{header}\n\n{note}{summary}\n"
-            
-            with open(daily_file, "a", encoding="utf-8") as f:
-                f.write(flush_entry)
-            
+
+            daily_part, memory_part = self._parse_dual_output(raw_summary)
+
+            # --- Write daily memory ---
+            if daily_part:
+                daily_file = ensure_daily_memory_file(self.workspace_dir, user_id)
+
+                if reason == "overflow":
+                    header = f"## Context Overflow Recovery ({datetime.now().strftime('%H:%M')})"
+                    note = "The following conversation was trimmed due to context overflow:\n"
+                elif reason == "trim":
+                    header = f"## Trimmed Context ({datetime.now().strftime('%H:%M')})"
+                    note = ""
+                elif reason == "daily_summary":
+                    header = f"## Daily Summary ({datetime.now().strftime('%H:%M')})"
+                    note = ""
+                else:
+                    header = f"## Session Notes ({datetime.now().strftime('%H:%M')})"
+                    note = ""
+
+                flush_entry = f"\n{header}\n\n{note}{daily_part}\n"
+
+                with open(daily_file, "a", encoding="utf-8") as f:
+                    f.write(flush_entry)
+
+                logger.info(f"[MemoryFlush] Wrote daily memory to {daily_file.name} (reason={reason}, chars={len(daily_part)})")
+
+            # --- Light Dream: write long-term memory to MEMORY.md ---
+            if memory_part:
+                self._append_to_main_memory(memory_part, user_id)
+
            self.last_flush_timestamp = datetime.now()
-            
-            logger.info(f"[MemoryFlush] Wrote to {daily_file.name} (reason={reason}, chars={len(summary)})")
-            
+
        except Exception as e:
            logger.warning(f"[MemoryFlush] Async flush failed (reason={reason}): {e}")
-    
+
+    @staticmethod
+    def _parse_dual_output(raw: str) -> tuple:
+        """
+        Parse LLM output into (daily_part, memory_part).
+        Handles both new [DAILY]/[MEMORY] format and legacy single-section format.
+        """
+        raw = raw.strip()
+
+        if "[DAILY]" in raw or "[MEMORY]" in raw:
+            daily_part = ""
+            memory_part = ""
+
+            # Extract [DAILY] section
+            if "[DAILY]" in raw:
+                start = raw.index("[DAILY]") + len("[DAILY]")
+                end = raw.index("[MEMORY]") if "[MEMORY]" in raw else len(raw)
+                daily_part = raw[start:end].strip()
+
+            # Extract [MEMORY] section
+            if "[MEMORY]" in raw:
+                start = raw.index("[MEMORY]") + len("[MEMORY]")
+                memory_part = raw[start:].strip()
+
+            # Filter out empty markers
+            if memory_part and all(
+                not line.strip() or line.strip() == "-"
+                for line in memory_part.split("\n")
+            ):
+                memory_part = ""
+
+            return daily_part, memory_part
+
+        # Legacy format: treat entire output as daily, no memory extraction
+        return raw, ""
+
+    def _append_to_main_memory(self, memory_entries: str, user_id: Optional[str] = None):
+        """Append extracted long-term memories to MEMORY.md with date stamp."""
+        try:
+            main_file = self.get_main_memory_file(user_id)
+            today = datetime.now().strftime("%Y-%m-%d")
+
+            # Add date prefix to each entry line
+            stamped_lines = []
+            for line in memory_entries.strip().split("\n"):
+                line = line.strip()
+                if line.startswith("- "):
+                    stamped_lines.append(f"- ({today}) {line[2:]}")
+                elif line:
+                    stamped_lines.append(f"- ({today}) {line}")
+
+            if not stamped_lines:
+                return
+
+            stamped_text = "\n".join(stamped_lines)
+
+            with open(main_file, "a", encoding="utf-8") as f:
+                f.write(f"\n{stamped_text}\n")
+
+            logger.info(f"[LightDream] Appended {len(stamped_lines)} entries to MEMORY.md")
+
+        except Exception as e:
+            logger.warning(f"[LightDream] Failed to append to MEMORY.md: {e}")
+
    def create_daily_summary(
        self,
        messages: List[Dict],
@@ -220,14 +317,16 @@ class MemoryFlushManager:
        if not conversation_text.strip():
            return ""
        
-        # Try LLM summarization first
        if self.llm_model:
            try:
                summary = self._call_llm_for_summary(conversation_text)
                if summary and summary.strip() and summary.strip() != "无":
                    return summary.strip()
+                logger.info(f"[MemoryFlush] LLM returned empty or '无', using fallback")
            except Exception as e:
                logger.warning(f"[MemoryFlush] LLM summarization failed, using fallback: {e}")
+        else:
+            logger.info("[MemoryFlush] No LLM model available, using rule-based fallback")
        
        return self._extract_summary_fallback(messages, max_messages)

@@ -277,27 +376,38 @@ class MemoryFlushManager:

    @staticmethod
    def _extract_summary_fallback(messages: List[Dict], max_messages: int = 0) -> str:
-        """Rule-based fallback when LLM is unavailable."""
+        """
+        Rule-based fallback when LLM is unavailable.
+        Groups consecutive user+assistant messages into events instead of
+        listing each message individually.
+        """
        msgs = messages if max_messages == 0 else messages[-max_messages * 2:]
-        
-        items = []
+
+        events: List[str] = []
+        current_user_text = ""
        for msg in msgs:
            role = msg.get("role", "")
            text = MemoryFlushManager._extract_text_from_content(msg.get("content", ""))
            if not text or not text.strip():
                continue
            text = text.strip()
-            
+
            if role == "user":
                if len(text) <= 5:
                    continue
-                items.append(f"- 用户请求: {text[:200]}")
-            elif role == "assistant":
+                current_user_text = text[:150]
+            elif role == "assistant" and current_user_text:
                first_line = text.split("\n")[0].strip()
                if len(first_line) > 10:
-                    items.append(f"- 处理结果: {first_line[:200]}")
-        
-        return "\n".join(items[:15])
+                    events.append(f"- {current_user_text} → {first_line[:150]}")
+                else:
+                    events.append(f"- {current_user_text}")
+                current_user_text = ""
+
+        if current_user_text:
+            events.append(f"- {current_user_text}")
+
+        return "\n".join(events[:10])
    
    @staticmethod
    def _extract_text_from_content(content) -> str:
--- a/agent/prompt/builder.py
+++ b/agent/prompt/builder.py
@@ -10,6 +10,7 @@ from typing import List, Dict, Optional, Any
 from dataclasses import dataclass

 from common.log import logger
+from config import conf


@dataclass
@@ -92,10 +93,11 @@ def build_agent_system_prompt(
    顺序说明（按重要性和逻辑关系排列）:
    1. 工具系统 - 核心能力，最先介绍
    2. 技能系统 - 紧跟工具，因为技能需要用 read 工具读取
-    3. 记忆系统 - 独立的记忆能力
+    3. 记忆系统 - 记忆检索与写入引导
+    3.5 知识系统 - 结构化知识库（knowledge/index.md 注入）
    4. 工作空间 - 工作环境说明
    5. 用户身份 - 用户信息（可选）
-    6. 项目上下文 - AGENT.md, USER.md, RULE.md, BOOTSTRAP.md（定义人格、身份、规则、初始化引导）
+    6. 项目上下文 - AGENT.md, USER.md, RULE.md, MEMORY.md, BOOTSTRAP.md
    7. 运行时信息 - 元信息（时间、模型等）
    
    Args:
@@ -126,6 +128,10 @@ def build_agent_system_prompt(
    # 3. 记忆系统（独立的记忆能力）
    if memory_manager:
        sections.extend(_build_memory_section(memory_manager, tools, language))
+
+    # 3.5 知识系统（结构化知识库）
+    if conf().get("knowledge", True):
+        sections.extend(_build_knowledge_section(workspace_dir, language))
    
    # 4. 工作空间（工作环境说明）
    sections.extend(_build_workspace_section(workspace_dir, language))
@@ -165,12 +171,13 @@ def _build_tooling_section(tools: List[Any], language: str) -> List[str]:
        "terminal": "管理后台进程",
        "web_search": "网络搜索",
        "web_fetch": "获取URL内容",
-        "browser": "控制浏览器",
+        "browser": "控制浏览器（关键结果或需要协助可截图发送给用户）",
        "memory_search": "搜索记忆",
        "memory_get": "读取记忆内容",
        "env_config": "管理API密钥和技能配置",
        "scheduler": "管理定时任务和提醒",
        "send": "发送本地文件给用户（仅限本地文件，URL直接放在回复文本中）",
+        "vision": "分析图片内容（识别、描述、OCR文字提取等）",
    }

    # Preferred display order
@@ -179,7 +186,7 @@ def _build_tooling_section(tools: List[Any], language: str) -> List[str]:
        "bash", "terminal",
        "web_search", "web_fetch", "browser",
        "memory_search", "memory_get",
-        "env_config", "scheduler", "send",
+        "env_config", "scheduler", "send", "vision",
    ]

    # Build name -> summary mapping for available tools
@@ -199,16 +206,16 @@ 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),
        "",
        "工具调用风格：",
        "",
-        "- 在多步骤任务、敏感操作或用户要求时简要解释决策过程",
-        "- 持续推进直到任务完成，完成后向用户报告结果。",
-        "- 回复中涉及密钥、令牌等敏感信息必须脱敏。",
+        "- 多步骤任务、复杂决策、敏感操作时，应简要说明当前在做什么、为什么这样做，让用户了解关键进展",
+        "- 持续推进直到任务完成，完成后向用户报告结果",
+        "- 回复中涉及密钥、令牌等敏感信息必须脱敏",
        "- URL链接直接放在回复文本中即可，系统会自动处理和渲染。无需下载后使用send工具发送",
        "",
    ]
@@ -231,7 +238,7 @@ 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>。",
        "",
@@ -267,55 +274,105 @@ def _build_memory_section(memory_manager: Any, tools: Optional[List[Any]], langu
    """构建记忆系统section"""
    if not memory_manager:
        return []
-    
-    # 检查是否有memory工具
+
    has_memory_tools = False
    if tools:
        tool_names = [tool.name if hasattr(tool, 'name') else str(tool) for tool in tools]
        has_memory_tools = any(name in ['memory_search', 'memory_get'] for name in tool_names)
-    
+
    if not has_memory_tools:
        return []
-    
+
    from datetime import datetime
    today_file = datetime.now().strftime("%Y-%m-%d") + ".md"
-    
+
    lines = [
-        "## 记忆系统",
+        "## 🧠 记忆系统",
        "",
-        "### 检索记忆",
+        "### Memory Recall（mandatory）",
        "",
-        "在回答关于以前的工作、决定、日期、人物、偏好或待办事项的任何问题之前：",
+        "在回答任何关于过往工作、决策、日期、人物、偏好或待办事项的问题之前，**必须**先检索记忆。",
+        "MEMORY.md 已自动加载在项目上下文中（可能被截断），完整内容和每日记忆需要通过工具检索。",
        "",
-        "1. 不确定记忆文件位置 → 先用 `memory_search` 通过关键词和语义检索相关内容",
-        "2. 已知文件位置 → 直接用 `memory_get` 读取相应的行 (例如：MEMORY.md, memory/YYYY-MM-DD.md)",
-        "3. search 无结果 → 尝试用 `memory_get` 读取MEMORY.md及最近两天记忆文件",
+        "1. 不确定位置 → `memory_search` 关键词/语义检索",
+        "2. 已知位置 → `memory_get` 直接读取对应行",
+        "3. search 无结果 → `memory_get` 读最近两天记忆",
        "",
        "**记忆文件结构**:",
-        f"- `MEMORY.md`: 长期记忆（核心信息、偏好、决策等）",
+        "- `MEMORY.md`: 长期记忆索引（已自动加载到上下文，核心信息、偏好、决策等）",
        f"- `memory/YYYY-MM-DD.md`: 每日记忆，今天是 `memory/{today_file}`",
+        "- `knowledge/`: 结构化知识库（见下方知识系统）",
        "",
        "### 写入记忆",
        "",
-        "**主动存储**：遇到以下情况时，应主动将信息写入记忆文件（无需告知用户）：",
+        "遇到以下情况时，**主动**将信息写入记忆文件（无需告知用户）：",
        "",
-        "- 用户明确要求你记住某些信息",
+        "- 用户要求记住某些信息",
        "- 用户分享了重要的个人偏好、习惯、决策",
        "- 对话中产生了重要的结论、方案、约定",
        "- 完成了复杂任务，值得记录关键步骤和结果",
-        "- 发现了用户经常遇到的问题或解决方案",
        "",
        "**存储规则**:",
-        f"- 长期有效的核心信息 → `MEMORY.md`（文件保持精简，< 2000 tokens）",
-        f"- 当天的事件、进展、笔记 → `memory/{today_file}`",
-        "- 追加内容 → `edit` 工具，oldText 留空",
-        "- 修改内容 → `edit` 工具，oldText 填写要替换的文本",
-        "- **禁止写入敏感信息**：API密钥、令牌等敏感信息严禁写入记忆文件",
+        f"- 长期核心信息 → `MEMORY.md`",
+        f"- 当天事件/进展 → `memory/{today_file}`",
+        "- 结构化知识 → `knowledge/`（见知识系统）",
+        "- 追加 → `edit` 工具，oldText 留空",
+        "- 修改 → `edit` 工具，oldText 填写要替换的文本",
+        "- **禁止写入敏感信息**（API密钥、令牌等）",
        "",
        "**使用原则**: 自然使用记忆，就像你本来就知道；不用刻意提起，除非用户问起。",
        "",
    ]
-    
+
+    return lines
+
+
+def _build_knowledge_section(workspace_dir: str, language: str) -> List[str]:
+    """Build knowledge wiki section. Injects knowledge/index.md when present."""
+    index_path = os.path.join(workspace_dir, "knowledge", "index.md")
+    if not os.path.exists(index_path):
+        return []
+
+    try:
+        with open(index_path, 'r', encoding='utf-8') as f:
+            index_content = f.read().strip()
+    except Exception:
+        return []
+
+    lines = [
+        "## 📚 知识系统",
+        "",
+        "你拥有一个持续积累的个人知识库 `knowledge/`，这是你的长期结构化知识存储。",
+        "",
+        "### 自动写入规则（mandatory）",
+        "",
+        "以下场景**必须**在回复的同时写入知识库，**直接写入，不要询问用户是否需要**：",
+        "",
+        "1. **用户分享了文章/链接/文档** → 阅读理解后，在同一轮回复中将要点写入 `knowledge/sources/<slug>.md`",
+        "2. **深度讨论产生了结论/方案** → 整理为 `knowledge/analysis/<slug>.md`",
+        "3. **对话涉及重要实体**（人物/公司/项目）→ 创建或更新 `knowledge/entities/<name>.md`",
+        "4. **讨论了技术概念/方法论** → 整理为 `knowledge/concepts/<topic>.md`",
+        "",
+        "每次写入知识页面后，**必须同步更新** `knowledge/index.md` 添加一行索引。",
+        "详细的页面格式和操作规范，请读取技能 `knowledge-wiki` 的 SKILL.md。",
+        "",
+        "⚠️ 不要问「要不要存到知识库」——符合上述场景就直接写入，这是你的本能行为。",
+        "",
+    ]
+
+    if index_content:
+        lines.extend([
+            "### 当前知识索引",
+            "",
+            index_content,
+            "",
+        ])
+
+    lines.extend([
+        "**查询方式**：用 `read` 读取知识页面，或用 `memory_search` 检索（知识已纳入向量索引）。",
+        "",
+    ])
+
    return lines


@@ -325,7 +382,7 @@ def _build_user_identity_section(user_identity: Dict[str, str], language: str) -
        return []
    
    lines = [
-        "## 用户身份",
+        "## 👤 用户身份",
        "",
    ]
    
@@ -352,7 +409,7 @@ 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}`",
        "",
@@ -374,16 +431,20 @@ def _build_workspace_section(workspace_dir: str, language: str) -> List[str]:
        "",
        "**重要说明 - 文件已自动加载**:",
        "",
-        "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**：",
+        "以下文件在会话启动时**已经自动加载**到系统提示词中，你**无需再用 read 工具读取**：",
        "",
-        "- ✅ `AGENT.md`: 已加载 - 你的人格和灵魂设定。当用户修改你的名字、性格或交流风格时，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",
+        "- ✅ `MEMORY.md`: 已加载 - 长期记忆索引",
        "",
-        "**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」",
+        "- 记忆相关操作无需暴露文件名，用自然语言表达即可。例如说「我已记住」而非「已更新 MEMORY.md」",
+        "- 任务执行过程中的关键决策和步骤应该告知用户，让用户了解你在做什么、为什么这么做",
+        "- 做真正有帮助的助手，而不是表演式的客套，尽可能帮忙解决问题",
+        "- 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 +477,15 @@ 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("如果存在 `AGENT.md`，请体现其中定义的人格和语气。避免僵硬、模板化的回复；遵循其指导，除非有更高优先级的指令覆盖它。")
+        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("")
    
    # 添加每个文件的内容
@@ -442,7 +504,7 @@ def _build_runtime_section(runtime_info: Dict[str, Any], language: str) -> List[
        return []
    
    lines = [
-        "## 运行时信息",
+        "## ⚙️ 运行时信息",
        "",
    ]
    
@@ -473,7 +535,14 @@ def _build_runtime_section(runtime_info: Dict[str, Any], language: str) -> List[
    
    # Add other runtime info
    runtime_parts = []
-    if runtime_info.get("model"):
+    # Support dynamic model via callable, fallback to static value
+    if callable(runtime_info.get("_get_model")):
+        try:
+            runtime_parts.append(f"模型={runtime_info['_get_model']()}")
+        except Exception:
+            if runtime_info.get("model"):
+                runtime_parts.append(f"模型={runtime_info['model']}")
+    elif runtime_info.get("model"):
        runtime_parts.append(f"模型={runtime_info['model']}")
    if runtime_info.get("workspace"):
        runtime_parts.append(f"工作空间={runtime_info['workspace']}")
--- a/agent/prompt/workspace.py
+++ b/agent/prompt/workspace.py
@@ -67,6 +67,12 @@ def ensure_workspace(workspace_dir: str, create_templates: bool = True) -> Works
    # 创建websites子目录 (for web pages / sites generated by agent)
    websites_dir = os.path.join(workspace_dir, "websites")
    os.makedirs(websites_dir, exist_ok=True)
+
+    from config import conf
+    knowledge_enabled = conf().get("knowledge", True)
+    if knowledge_enabled:
+        knowledge_dir = os.path.join(workspace_dir, "knowledge")
+        os.makedirs(knowledge_dir, exist_ok=True)
    
    # 如果需要，创建模板文件
    if create_templates:
@@ -74,6 +80,15 @@ def ensure_workspace(workspace_dir: str, create_templates: bool = True) -> Works
        _create_template_if_missing(user_path, _get_user_template())
        _create_template_if_missing(rule_path, _get_rule_template())
        _create_template_if_missing(memory_path, _get_memory_template())
+        if knowledge_enabled:
+            _create_template_if_missing(
+                os.path.join(knowledge_dir, "index.md"),
+                _get_knowledge_index_template()
+            )
+            _create_template_if_missing(
+                os.path.join(knowledge_dir, "log.md"),
+                _get_knowledge_log_template()
+            )
        
        # Only create BOOTSTRAP.md for brand new workspaces;
        # agent deletes it after completing onboarding
@@ -109,6 +124,7 @@ def load_context_files(workspace_dir: str, files_to_load: Optional[List[str]] =
            DEFAULT_AGENT_FILENAME,
            DEFAULT_USER_FILENAME,
            DEFAULT_RULE_FILENAME,
+            DEFAULT_MEMORY_FILENAME,     # Long-term memory (frozen snapshot)
            DEFAULT_BOOTSTRAP_FILENAME,  # Only exists when onboarding is incomplete
        ]
    
@@ -138,6 +154,10 @@ def load_context_files(workspace_dir: str, files_to_load: Optional[List[str]] =
            # 跳过空文件或只包含模板占位符的文件
            if not content or _is_template_placeholder(content):
                continue
+
+            # Truncate MEMORY.md to protect context window (frozen snapshot)
+            if filename == DEFAULT_MEMORY_FILENAME:
+                content = _truncate_memory_content(content)
            
            context_files.append(ContextFile(
                path=filename,
@@ -163,6 +183,36 @@ def _create_template_if_missing(filepath: str, template_content: str):
            logger.error(f"[Workspace] Failed to create template {filepath}: {e}")


+_MEMORY_MAX_LINES = 200
+_MEMORY_MAX_BYTES = 25000
+
+
+def _truncate_memory_content(content: str) -> str:
+    """Truncate MEMORY.md to keep system prompt manageable.
+
+    Takes the **last** N lines (newest entries are appended at the bottom),
+    subject to 200 lines / 25 KB limits (whichever is hit first).
+    Prepends a hint when truncated so the model knows older content exists.
+    """
+    lines = content.split('\n')
+    truncated = False
+
+    if len(lines) > _MEMORY_MAX_LINES:
+        lines = lines[-_MEMORY_MAX_LINES:]
+        truncated = True
+
+    result = '\n'.join(lines)
+    if len(result.encode('utf-8')) > _MEMORY_MAX_BYTES:
+        while len(result.encode('utf-8')) > _MEMORY_MAX_BYTES and lines:
+            lines.pop(0)
+            truncated = True
+        result = '\n'.join(lines)
+
+    if truncated:
+        result = "...(older entries truncated, use `memory_search` or `memory_get` for full content)\n\n" + result
+    return result
+
+
 def _is_template_placeholder(content: str) -> bool:
    """检查内容是否为模板占位符"""
    # 常见的占位符模式
@@ -212,40 +262,42 @@ 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。** 目标是真正帮用户解决问题，在执行复杂任务时，关键的决策和过程进展要让用户知道。

-## 行为准则
+**有自己的观点和个性。** 你可以不同意、有偏好、觉得有趣或无聊。
+
+**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。
 """


@@ -285,39 +337,88 @@ def _get_rule_template() -> str:

 这个文件夹是你的家。好好对待它。

+## 工作空间目录结构
+
+```
+~/cow/
+├── AGENT.md          # 你的身份和灵魂设定
+├── USER.md           # 用户基本信息（静态）
+├── RULE.md           # 工作空间规则（本文件）
+├── MEMORY.md         # 长期记忆索引（会话启动时自动加载）
+│
+├── memory/           # 每日对话记忆
+│   └── YYYY-MM-DD.md # 当天事件、进展、笔记
+│
+├── knowledge/        # 结构化知识库（持续积累的知识）
+│   ├── index.md      # 知识目录索引（必须维护）
+│   ├── log.md        # 知识操作日志
+│   └── <子目录>/     # 按需创建，参考 index.md 已有分类
+│
+├── skills/           # 技能
+├── websites/         # 网页产物
+└── tmp/              # 系统临时文件（自动管理，勿手动存放重要文件）
+```
+
 ## 记忆系统

 你每次会话都是全新的，记忆文件让你保持连续性：

-### 📝 每日记忆：`memory/YYYY-MM-DD.md`
- 原始的对话日志
- 记录当天发生的事情
- 如果 `memory/` 目录不存在，创建它
-
 ### 🧠 长期记忆：`MEMORY.md`
- 你精选的记忆，就像人类的长期记忆
- **仅在主会话中加载**（与用户的直接聊天）
- **不要在共享上下文中加载**（群聊、与其他人的会话）
- 这是为了**安全** - 包含不应泄露给陌生人的个人上下文
- 记录重要事件、想法、决定、观点、经验教训
- 这是你精选的记忆 - 精华，而不是原始日志
- 用 `edit` 工具追加新的记忆内容
+- 你精选的记忆索引，每次会话启动时**自动加载**到上下文中
+- 记录核心事实、偏好、决策、重要人物、教训
+- 保持精简（< 200 行），是精华索引而非原始日志
+- 用 `edit` 工具追加或修改
+
+### 📝 每日记忆：`memory/YYYY-MM-DD.md`
+- 当天的事件、进展、笔记
+- 原始对话日志的沉淀

 ### 📝 写下来 - 不要"记在心里"！
- **记忆是有限的** - 如果你想记住某事，写入文件
+- **记忆是有限的** - 想记住的事就写入文件
 - "记在心里"不会在会话重启后保留，文件才会
 - 当有人说"记住这个" → 更新 `MEMORY.md` 或 `memory/YYYY-MM-DD.md`
 - 当你学到教训 → 更新 RULE.md 或相关技能
- 当你犯错 → 记录下来，这样未来的你不会重复，**文字 > 大脑** 📝
+- 当你犯错 → 记录下来，**文字 > 大脑** 📝

 ### 存储规则

 当用户分享信息时，根据类型选择存储位置：

-1. **你的身份设定 → AGENT.md**（你的名字、角色、性格、交流风格——用户修改时必须用 `edit` 更新）
-2. **用户静态身份 → USER.md**（姓名、称呼、职业、时区、联系方式、生日——用户修改时必须用 `edit` 更新）
-3. **动态记忆 → MEMORY.md**（爱好、偏好、决策、目标、项目、教训、待办事项）
+1. **你的身份设定 → AGENT.md**（名字、角色、性格、风格）
+2. **用户静态身份 → USER.md**（姓名、称呼、职业、联系方式、生日）
+3. **动态记忆 → MEMORY.md**（偏好、决策、目标、教训、待办）
 4. **当天对话 → memory/YYYY-MM-DD.md**（今天聊的内容）
+5. **结构化知识 → knowledge/**（见下方知识系统）
+
+## 知识系统
+
+知识库 `knowledge/` 是你持续积累的结构化知识。与记忆不同，知识是经过整理和编译的，有明确的主题和交叉引用。
+
+### 自动写入（不要询问，直接写入）
+
+当对话中产生了有沉淀价值的知识——无论是用户分享的资料、讨论的结论、学到的概念、还是重要的决策——你**必须**在回复的同时主动写入知识库，**无需问用户"要不要存到知识库"**。
+
+**关键原则**：学完就记是你的本能，不要征求确认。回复中可以顺带告知"已存入知识库"。
+
+### 目录组织
+
+子目录结构**不是固定的**，由你根据实际内容自主决定：
+- **首次写入时**：先读 `knowledge/index.md`，如果已有分类则延续；如果为空，根据内容选择合适的目录名
+- **默认建议**：按信息类型组织（例如sources/、concepts/、entities/、analysis/），如果用户有明确的分类偏好（例如按领域 work/、life/、tech/ 等），则按用户要求调整
+- **保持一致性**：同一用户的知识库应保持统一的组织风格
+
+### 交叉引用
+
+知识的核心价值在于**关联**。每个页面都应通过 markdown 链接引用相关页面，构建知识网络：
+- 提到已有页面的概念时，添加 `[概念名](../category/page.md)` 链接
+- 新建页面时，检查是否有已有页面应该反向链接到新页面
+- **只链接已存在的页面**——不要引用尚未创建的页面。如果某个概念值得单独建页，先创建该页面再添加链接
+
+### 索引维护
+
+每次创建或更新知识页面后，**必须同步更新** `knowledge/index.md`。
+索引格式：每行一个 `[标题](路径) — 一句话摘要`，按分类分组，不要用表格。
+详细操作规范见技能 `knowledge-wiki`。

 ## 安全

@@ -346,9 +447,9 @@ 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 +459,13 @@ _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。

@@ -373,10 +474,18 @@ _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。
 """


+def _get_knowledge_index_template() -> str:
+    """Knowledge wiki index template — empty file, agent fills it."""
+    return ""
+
+
+def _get_knowledge_log_template() -> str:
+    """Knowledge wiki operation log template — empty file, agent fills it."""
+    return ""

--- a/agent/protocol/agent.py
+++ b/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."""
--- a/agent/protocol/agent_stream.py
+++ b/agent/protocol/agent_stream.py
@@ -300,13 +300,13 @@ class AgentStreamExecutor:
                                    f"with same arguments. This may indicate a loop."
                                )
                        
-                        # Check if this is a file to send (from read tool)
+                        # Check if this is a file to send
                        if result.get("status") == "success" and isinstance(result.get("result"), dict):
                            result_data = result.get("result")
                            if result_data.get("type") == "file_to_send":
-                                # Store file metadata for later sending
                                self.files_to_send.append(result_data)
                                logger.info(f"📎 检测到待发送文件: {result_data.get('file_name', result_data.get('path'))}")
+                                self._emit_event("file_to_send", result_data)
                        
                        # Check for critical error - abort entire conversation
                        if result.get("status") == "critical_error":
@@ -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})

@@ -526,6 +527,7 @@ class AgentStreamExecutor:

        # Streaming response
        full_content = ""
+        full_reasoning = ""
        tool_calls_buffer = {}  # {index: {id, name, arguments}}
        gemini_raw_parts = None  # Preserve Gemini thoughtSignature for round-trip
        stop_reason = None  # Track why the stream stopped
@@ -583,10 +585,10 @@ class AgentStreamExecutor:
                    if finish_reason:
                        stop_reason = finish_reason

-                    # Skip reasoning_content (internal thinking from models like GLM-5)
                    reasoning_delta = delta.get("reasoning_content") or ""
-                    # if reasoning_delta:
-                    #     logger.debug(f"🧠 [thinking] {reasoning_delta[:100]}...")
+                    if reasoning_delta:
+                        full_reasoning += reasoning_delta
+                        self._emit_event("reasoning_update", {"delta": reasoning_delta})

                    # Handle text content
                    content_delta = delta.get("content") or ""
@@ -609,14 +611,14 @@ class AgentStreamExecutor:
                                    "arguments": ""
                                }

-                            if "id" in tc_delta:
+                            if tc_delta.get("id"):
                                tool_calls_buffer[index]["id"] = tc_delta["id"]

                            if "function" in tc_delta:
                                func = tc_delta["function"]
-                                if "name" in func:
+                                if func.get("name"):
                                    tool_calls_buffer[index]["name"] = func["name"]
-                                if "arguments" in func:
+                                if func.get("arguments"):
                                    tool_calls_buffer[index]["arguments"] += func["arguments"]

                    # Preserve _gemini_raw_parts for Gemini thoughtSignature round-trip
@@ -720,9 +722,9 @@ class AgentStreamExecutor:
                )
            else:
                if retry_count >= max_retries:
-                    logger.error(f"❌ LLM API error after {max_retries} retries: {e}")
+                    logger.error(f"❌ LLM API error after {max_retries} retries: {e}", exc_info=True)
                else:
-                    logger.error(f"❌ LLM call error (non-retryable): {e}")
+                    logger.error(f"❌ LLM call error (non-retryable): {e}", exc_info=True)
                raise

        # Parse tool calls
@@ -787,7 +789,12 @@ class AgentStreamExecutor:
        # Add assistant message to history (Claude format uses content blocks)
        assistant_msg = {"role": "assistant", "content": []}

-        # Add text content block if present
+        if full_reasoning:
+            assistant_msg["content"].append({
+                "type": "thinking",
+                "thinking": full_reasoning
+            })
+
        if full_content:
            assistant_msg["content"].append({
                "type": "text",
@@ -875,7 +882,7 @@ class AgentStreamExecutor:
        try:
            tool = self.tools.get(tool_name)
            if not tool:
-                raise ValueError(f"Tool '{tool_name}' not found")
+                raise ValueError(self._build_tool_not_found_message(tool_name))

            # Set tool context
            tool.model = self.model
@@ -929,6 +936,47 @@ class AgentStreamExecutor:
            })
            return error_result

+    def _build_tool_not_found_message(self, tool_name: str) -> str:
+        """Build a helpful error message when a tool is not found.
+
+        If a skill with the same name exists in skill_manager, read its
+        SKILL.md and include the content so the LLM knows how to use it.
+        """
+        available_tools = list(self.tools.keys())
+        base_msg = f"Tool '{tool_name}' not found. Available tools: {available_tools}"
+
+        skill_manager = getattr(self.agent, 'skill_manager', None)
+        if not skill_manager:
+            return base_msg
+
+        skill_entry = skill_manager.get_skill(tool_name)
+        if not skill_entry:
+            return base_msg
+
+        skill = skill_entry.skill
+        skill_md_path = skill.file_path
+        skill_content = ""
+        try:
+            with open(skill_md_path, 'r', encoding='utf-8') as f:
+                skill_content = f.read()
+        except Exception:
+            skill_content = skill.description
+
+        logger.info(
+            f"[Agent] Tool '{tool_name}' not found, but matched skill '{skill.name}'. "
+            f"Guiding LLM to use the skill instead."
+        )
+
+        return (
+            f"Tool '{tool_name}' is not a built-in tool, but a matching skill "
+            f"'{skill.name}' is available. You should use existing tools (e.g. bash with curl) "
+            f"to accomplish this task following the skill instructions below:\n\n"
+            f"--- SKILL: {skill.name} (path: {skill_md_path}) ---\n"
+            f"{skill_content}\n"
+            f"--- END SKILL ---\n\n"
+            f"Available tools: {available_tools}"
+        )
+
    def _validate_and_fix_messages(self):
        """Delegate to the shared sanitizer (see message_sanitizer.py)."""
        sanitize_claude_messages(self.messages)
--- a/agent/protocol/message_utils.py
+++ b/agent/protocol/message_utils.py
@@ -18,6 +18,107 @@ from typing import Dict, List, Set

 from common.log import logger

+_SYNTH_TOOL_ERR = (
+    "Error: Missing tool_result adjacent to tool_use (session repair). "
+    "The conversation history was inconsistent; continue from here."
+)
+
+
+def _repair_tool_use_adjacency(messages: List[Dict]) -> int:
+    """
+    Anthropic requires: after assistant content with tool_use, the next message
+    must be user content listing tool_result for every tool_use id (same user msg).
+
+    Valid histories satisfy this at every such assistant; the loop only mutates
+    when that condition fails (broken persistence, bad trims, etc.).
+    """
+
+    def _synth_block(tid: str) -> Dict:
+        return {
+            "type": "tool_result",
+            "tool_use_id": tid,
+            "content": _SYNTH_TOOL_ERR,
+            "is_error": True,
+        }
+
+    repairs = 0
+    i = 0
+    while i < len(messages):
+        msg = messages[i]
+        if msg.get("role") != "assistant":
+            i += 1
+            continue
+
+        content = msg.get("content", [])
+        if not isinstance(content, list):
+            i += 1
+            continue
+
+        required = [
+            b.get("id")
+            for b in content
+            if isinstance(b, dict) and b.get("type") == "tool_use" and b.get("id")
+        ]
+        if not required:
+            i += 1
+            continue
+
+        req_set = set(required)
+        if i + 1 >= len(messages):
+            messages.append({
+                "role": "user",
+                "content": [_synth_block(tid) for tid in required],
+            })
+            logger.warning(
+                "⚠️ Appended synthetic tool_result after trailing assistant tool_use"
+            )
+            repairs += 1
+            break
+
+        nxt = messages[i + 1]
+        if nxt.get("role") != "user":
+            messages.insert(
+                i + 1,
+                {"role": "user", "content": [_synth_block(tid) for tid in required]},
+            )
+            logger.warning(
+                "⚠️ Inserted synthetic tool_result user after tool_use "
+                f"(next role={nxt.get('role')!r})"
+            )
+            repairs += 1
+            i += 2
+            continue
+
+        nc = nxt.get("content", [])
+        if not isinstance(nc, list):
+            messages.insert(
+                i + 1,
+                {"role": "user", "content": [_synth_block(tid) for tid in required]},
+            )
+            repairs += 1
+            i += 2
+            continue
+
+        present = {
+            b.get("tool_use_id")
+            for b in nc
+            if isinstance(b, dict) and b.get("type") == "tool_result" and b.get("tool_use_id")
+        }
+        if req_set <= present:
+            i += 1
+            continue
+
+        missing = [tid for tid in required if tid not in present]
+        nxt["content"] = [_synth_block(tid) for tid in missing] + nc
+        logger.warning(
+            "⚠️ Prepended synthetic tool_result for Anthropic adjacency "
+            f"(missing_ids={missing})"
+        )
+        repairs += len(missing)
+        i += 1
+
+    return repairs
+

 # ------------------------------------------------------------------ #
 # Claude-format sanitizer (used by agent_stream)
@@ -28,33 +129,21 @@ def sanitize_claude_messages(messages: List[Dict]) -> int:
    Validate and fix a Claude-format message list **in-place**.

    Fixes handled:
-    - Trailing assistant message with tool_use but no following tool_result
+    - Anthropic adjacency: assistant tool_use must be immediately followed by
+      user message(s) containing matching tool_result blocks
    - Leading orphaned tool_result user messages
    - Mid-list tool_result blocks whose tool_use_id has no matching
      tool_use in any preceding assistant message

-    Returns the number of messages / blocks removed.
+    Returns: number of removals plus adjacency repair operations (inserts/prepends).
    """
    if not messages:
        return 0

    removed = 0

-    # 1. Remove trailing incomplete tool_use assistant messages
-    while messages:
-        last = messages[-1]
-        if last.get("role") != "assistant":
-            break
-        content = last.get("content", [])
-        if isinstance(content, list) and any(
-            isinstance(b, dict) and b.get("type") == "tool_use"
-            for b in content
-        ):
-            logger.warning("⚠️ Removing trailing incomplete tool_use assistant message")
-            messages.pop()
-            removed += 1
-        else:
-            break
+    # 1. Adjacency repair (Anthropic: tool_result must be in the next user message)
+    adj_repairs = _repair_tool_use_adjacency(messages)

    # 2. Remove leading orphaned tool_result user messages
    while messages:
@@ -136,9 +225,15 @@ def sanitize_claude_messages(messages: List[Dict]) -> int:
        if pass_removed == 0:
            break

+    # 4. Removals above can break adjacency; re-run repair only if something was removed.
+    if removed:
+        adj_repairs += _repair_tool_use_adjacency(messages)
+
    if removed:
        logger.info(f"🔧 Message validation: removed {removed} broken message(s)")
-    return removed
+    if adj_repairs:
+        logger.info(f"🔧 Message validation: adjacency repairs={adj_repairs}")
+    return removed + adj_repairs


 # ------------------------------------------------------------------ #
--- a/agent/skills/config.py
+++ b/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.
--- a/agent/skills/formatter.py
+++ b/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
--- a/agent/skills/frontmatter.py
+++ b/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:
--- a/agent/skills/loader.py
+++ b/agent/skills/loader.py
@@ -53,6 +53,12 @@ class SkillLoader:
        """
        Recursively load skills from a directory.
        
+        If a subdirectory contains its own SKILL.md, it is treated as a
+        self-contained skill (or skill-collection) and its children are
+        NOT scanned further. This prevents sub-skills inside a collection
+        (e.g. style-collection/style-anjing) from being listed as
+        independent top-level skills.
+        
        :param dir_path: Directory to scan
        :param source: Source identifier
        :param include_root_files: Whether to include root-level .md files
@@ -66,38 +72,41 @@ class SkillLoader:
        except Exception as e:
            diagnostics.append(f"Failed to list directory {dir_path}: {e}")
            return LoadSkillsResult(skills=skills, diagnostics=diagnostics)
+
+        # If this directory has its own SKILL.md, load it and stop recursing.
+        # The sub-directories are internal resources of this skill.
+        if not include_root_files and 'SKILL.md' in entries:
+            skill_md_path = os.path.join(dir_path, 'SKILL.md')
+            if os.path.isfile(skill_md_path):
+                skill_result = self._load_skill_from_file(skill_md_path, source)
+                if skill_result.skills:
+                    skills.extend(skill_result.skills)
+                diagnostics.extend(skill_result.diagnostics)
+                return LoadSkillsResult(skills=skills, diagnostics=diagnostics)
        
        for entry in entries:
-            # Skip hidden files and directories
            if entry.startswith('.'):
                continue
            
-            # Skip common non-skill directories
            if entry in ('node_modules', '__pycache__', 'venv', '.git'):
                continue
            
            full_path = os.path.join(dir_path, entry)
            
-            # Handle directories
            if os.path.isdir(full_path):
-                # Recursively scan subdirectories
                sub_result = self._load_skills_recursive(full_path, source, include_root_files=False)
                skills.extend(sub_result.skills)
                diagnostics.extend(sub_result.diagnostics)
                continue
            
-            # Handle files
            if not os.path.isfile(full_path):
                continue
            
-            # Check if this is a skill file
-            is_root_md = include_root_files and entry.endswith('.md')
-            is_skill_md = not include_root_files and entry == 'SKILL.md'
+            is_root_md = include_root_files and entry.endswith('.md') and entry.upper() != 'README.MD'
            
-            if not (is_root_md or is_skill_md):
+            if not is_root_md:
                continue
            
-            # Load the skill
            skill_result = self._load_skill_from_file(full_path, source)
            if skill_result.skills:
                skills.extend(skill_result.skills)
@@ -184,7 +193,6 @@ 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 ""
--- a/agent/skills/manager.py
+++ b/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] = {}
@@ -95,15 +95,24 @@ 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")
-            merged[name] = {
+
+            if name in saved:
+                enabled = prev.get("enabled", True)
+            else:
+                enabled = entry.metadata.default_enabled if entry.metadata else True
+
+            entry_dict = {
                "name": name,
                "description": skill.description,
-                "source": skill.source,
-                "enabled": prev.get("enabled", True),
+                "source": prev.get("source") or skill.source,
+                "enabled": enabled,
                "category": category,
            }
+            display_name = prev.get("display_name")
+            if display_name:
+                entry_dict["display_name"] = display_name
+            merged[name] = entry_dict

        self.skills_config = merged
        self._save_skills_config()
@@ -157,69 +166,118 @@ 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)]

+        from config import conf
+        if not conf().get("knowledge", True):
+            entries = [e for e in entries if e.skill.name != "knowledge-wiki"]
+
        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
    
--- a/agent/skills/types.py
+++ b/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
--- a/agent/tools/init.py
+++ b/agent/tools/init.py
@@ -87,25 +87,25 @@ FileSave = _optional_tools.get('FileSave')
 Terminal = _optional_tools.get('Terminal')


-# Delayed import for BrowserTool
+# BrowserTool (requires playwright)
 def _import_browser_tool():
+    from common.log import logger
    try:
        from agent.tools.browser.browser_tool import BrowserTool
        return BrowserTool
-    except ImportError:
-        # Return a placeholder class that will prompt the user to install dependencies when instantiated
-        class BrowserToolPlaceholder:
-            def __init__(self, *args, **kwargs):
-                raise ImportError(
-                    "The 'browser-use' package is required to use BrowserTool. "
-                    "Please install it with 'pip install browser-use>=0.1.40'."
-                )
+    except ImportError as e:
+        logger.info(
+            f"[Tools] BrowserTool not loaded - missing dependency: {e}\n"
+            f"  To enable browser tool, run:\n"
+            f"    pip install playwright\n"
+            f"    playwright install chromium"
+        )
+        return None
+    except Exception as e:
+        logger.error(f"[Tools] BrowserTool failed to load: {e}")
+        return None

-        return BrowserToolPlaceholder
-
-
-# Dynamically set BrowserTool
-# BrowserTool = _import_browser_tool()
+BrowserTool = _import_browser_tool()

 # Export all tools (including optional ones that might be None)
 __all__ = [
@@ -124,8 +124,7 @@ __all__ = [
    'WebSearch',
    'WebFetch',
    'Vision',
-    # Optional tools (may be None if dependencies not available)
-    # 'BrowserTool'
+    'BrowserTool',
 ]

 """
--- a/agent/tools/bash/bash.py
+++ b/agent/tools/bash/bash.py
@@ -18,9 +18,13 @@ from common.utils import expand_path
 class Bash(BaseTool):
    """Tool for executing bash commands"""

+    _IS_WIN = sys.platform == "win32"
+
    name: str = "bash"
    description: str = f"""Execute a bash command in the current working directory. Returns stdout and stderr. Output is truncated to last {DEFAULT_MAX_LINES} lines or {DEFAULT_MAX_BYTES // 1024}KB (whichever is hit first). If truncated, full output is saved to a temp file.
-
+{'''
+PLATFORM: Windows (cmd.exe). Do NOT use Unix-only commands like grep, head, tail, sed, awk.
+''' if _IS_WIN else ''}
 ENVIRONMENT: All API keys from env_config are auto-injected. Use $VAR_NAME directly.

 SAFETY:
@@ -103,13 +107,12 @@ SAFETY:
                logger.debug(f"[Bash] Process User: {os.environ.get('USERNAME', os.environ.get('USER', 'unknown'))}")
            
            # On Windows, convert $VAR references to %VAR% for cmd.exe
-            if sys.platform == "win32":
+            if self._IS_WIN:
                env["PYTHONIOENCODING"] = "utf-8"
                command = self._convert_env_vars_for_windows(command, dotenv_vars)
                if command and not command.strip().lower().startswith("chcp"):
                    command = f"chcp 65001 >nul 2>&1 && {command}"

-            # Execute command with inherited environment variables
            result = subprocess.run(
                command,
                shell=True,
@@ -120,7 +123,7 @@ SAFETY:
                encoding="utf-8",
                errors="replace",
                timeout=timeout,
-                env=env
+                env=env,
            )
            
            logger.debug(f"[Bash] Exit code: {result.returncode}")
--- a/agent/tools/browser/init.py
+++ b/agent/tools/browser/init.py
@@ -0,0 +1,3 @@
+from agent.tools.browser.browser_tool import BrowserTool
+
+__all__ = ["BrowserTool"]
--- a/agent/tools/browser/browser_service.py
+++ b/agent/tools/browser/browser_service.py
@@ -0,0 +1,780 @@
+"""
+Browser service - Playwright wrapper managing browser lifecycle and page operations.
+
+All Playwright calls run on a dedicated background thread so that callers from
+any worker thread can safely use the service.  An idle-timeout mechanism
+automatically shuts down the browser (and its thread) after a configurable
+period of inactivity to free resources.
+"""
+
+import os
+import sys
+import uuid
+import queue
+import threading
+from typing import Optional, Dict, Any, List, Callable
+
+from common.log import logger
+
+try:
+    from playwright.sync_api import sync_playwright, Browser, BrowserContext, Page, Playwright
+    _HAS_PLAYWRIGHT = True
+except ImportError:
+    _HAS_PLAYWRIGHT = False
+
+
+# ---------------------------------------------------------------------------
+# Snapshot DOM helpers
+# ---------------------------------------------------------------------------
+
+# Tags that typically carry useful content for an agent
+_INTERACTIVE_TAGS = {
+    "a", "button", "input", "textarea", "select", "option",
+    "label", "details", "summary",
+}
+_SEMANTIC_TAGS = {
+    "h1", "h2", "h3", "h4", "h5", "h6",
+    "p", "li", "td", "th", "caption", "figcaption", "blockquote", "pre", "code",
+    "nav", "main", "article", "section", "header", "footer", "form", "table",
+    "img", "video", "audio",
+}
+_KEEP_TAGS = _INTERACTIVE_TAGS | _SEMANTIC_TAGS
+
+_SNAPSHOT_JS = """
+() => {
+    const KEEP = new Set(%s);
+    const INTERACTIVE = new Set(%s);
+    const SKIP = new Set(["script","style","noscript","svg","path","meta","link","br","hr"]);
+    const CLICKABLE_ROLES = new Set([
+        "button","link","tab","menuitem","menuitemcheckbox","menuitemradio",
+        "option","switch","checkbox","radio","combobox","searchbox","slider",
+        "spinbutton","textbox","treeitem"
+    ]);
+    let refCounter = 0;
+    const refMap = {};
+
+    function visible(el) {
+        if (!(el instanceof HTMLElement)) return true;
+        const st = window.getComputedStyle(el);
+        if (st.display === "none" || st.visibility === "hidden") return false;
+        if (parseFloat(st.opacity) === 0) return false;
+        return true;
+    }
+
+    // Strong signals: these attributes alone are enough to mark as interactive
+    function hasStrongInteractiveSignal(el) {
+        const role = el.getAttribute("role");
+        if (role && CLICKABLE_ROLES.has(role)) return true;
+        if (el.hasAttribute("onclick") || el.hasAttribute("tabindex")) return true;
+        if (el.hasAttribute("data-click") || el.hasAttribute("data-action")) return true;
+        if (el.getAttribute("contenteditable") === "true") return true;
+        return false;
+    }
+
+    // Check if cursor:pointer is set directly (not just inherited from parent)
+    function hasOwnPointerCursor(el) {
+        try {
+            const st = window.getComputedStyle(el);
+            if (st.cursor !== "pointer") return false;
+            const parent = el.parentElement;
+            if (parent) {
+                const pst = window.getComputedStyle(parent);
+                if (pst.cursor === "pointer") return false;
+            }
+            return true;
+        } catch(e) {}
+        return false;
+    }
+
+    function hasTextOrContent(el) {
+        const t = el.textContent || "";
+        if (t.trim().length > 0) return true;
+        if (el.querySelector("img,video,audio,canvas")) return true;
+        const ariaLabel = el.getAttribute("aria-label");
+        if (ariaLabel && ariaLabel.trim()) return true;
+        const title = el.getAttribute("title");
+        if (title && title.trim()) return true;
+        return false;
+    }
+
+    function isImplicitInteractive(el) {
+        if (hasStrongInteractiveSignal(el)) return true;
+        if (hasOwnPointerCursor(el) && hasTextOrContent(el)) return true;
+        return false;
+    }
+
+    function getTextContent(el) {
+        let text = "";
+        for (const ch of el.childNodes) {
+            if (ch.nodeType === Node.TEXT_NODE) {
+                text += ch.textContent;
+            }
+        }
+        return text.trim();
+    }
+
+    function walk(node) {
+        if (node.nodeType === Node.TEXT_NODE) {
+            const t = node.textContent.trim();
+            return t ? t : null;
+        }
+        if (node.nodeType !== Node.ELEMENT_NODE) return null;
+        const tag = node.tagName.toLowerCase();
+        if (SKIP.has(tag)) return null;
+        if (!visible(node)) return null;
+
+        const children = [];
+        for (const ch of node.childNodes) {
+            const r = walk(ch);
+            if (r !== null) {
+                if (typeof r === "string") children.push(r);
+                else children.push(r);
+            }
+        }
+
+        const nativeInteractive = INTERACTIVE.has(tag);
+        const implicitInteractive = !nativeInteractive && (node instanceof HTMLElement) && isImplicitInteractive(node);
+        const keep = KEEP.has(tag) || implicitInteractive;
+
+        if (!keep) {
+            if (children.length === 0) return null;
+            if (children.length === 1) return children[0];
+            return children;
+        }
+
+        const obj = { tag };
+        if (nativeInteractive || implicitInteractive) {
+            refCounter++;
+            obj.ref = refCounter;
+            refMap[refCounter] = node;
+        }
+
+        if (implicitInteractive) {
+            const role = node.getAttribute("role");
+            if (role) obj.role = role;
+            const directText = getTextContent(node);
+            if (!directText && children.length === 0) {
+                const ariaLabel = node.getAttribute("aria-label");
+                const title = node.getAttribute("title");
+                if (ariaLabel) obj.ariaLabel = ariaLabel;
+                else if (title) obj.ariaLabel = title;
+            }
+        }
+
+        // Attributes
+        if (tag === "a" && node.href) obj.href = node.getAttribute("href");
+        if (tag === "img") {
+            obj.alt = node.alt || "";
+            obj.src = node.getAttribute("src") || "";
+        }
+        if (tag === "input" || tag === "textarea" || tag === "select") {
+            obj.type = node.type || "text";
+            obj.name = node.name || undefined;
+            obj.value = node.value || undefined;
+            obj.placeholder = node.placeholder || undefined;
+            if (node.disabled) obj.disabled = true;
+            if (tag === "input" && node.type === "checkbox") obj.checked = node.checked;
+        }
+        if (tag === "button") {
+            if (node.disabled) obj.disabled = true;
+        }
+        if (tag === "option") {
+            obj.value = node.value;
+            if (node.selected) obj.selected = true;
+        }
+        if (tag === "label" && node.htmlFor) obj.for = node.htmlFor;
+
+        // Role / aria-label for native interactive & semantic elements
+        if (!implicitInteractive) {
+            const role = node.getAttribute("role");
+            if (role) obj.role = role;
+            const ariaLabel = node.getAttribute("aria-label");
+            if (ariaLabel) obj.ariaLabel = ariaLabel;
+        }
+
+        // Children
+        if (children.length === 1 && typeof children[0] === "string") {
+            obj.text = children[0];
+        } else if (children.length > 0) {
+            obj.children = children;
+        }
+
+        return obj;
+    }
+
+    const result = walk(document.body);
+    window.__cowRefMap = refMap;
+    return { tree: result, refCount: refCounter };
+}
+""" % (
+    str(list(_KEEP_TAGS)),
+    str(list(_INTERACTIVE_TAGS)),
+)
+
+
+def _should_use_headless() -> bool:
+    """Decide headless mode: headless on Linux servers without display, headed elsewhere."""
+    if sys.platform in ("win32", "darwin"):
+        return False
+    # Linux: check for display
+    if os.environ.get("DISPLAY") or os.environ.get("WAYLAND_DISPLAY"):
+        return False
+    return True
+
+
+def _flatten_tree(node, indent=0) -> List[str]:
+    """Convert snapshot tree to compact text lines for LLM consumption."""
+    if node is None:
+        return []
+    if isinstance(node, str):
+        return [" " * indent + node]
+    if isinstance(node, list):
+        lines = []
+        for child in node:
+            lines.extend(_flatten_tree(child, indent))
+        return lines
+    if not isinstance(node, dict):
+        return []
+
+    tag = node.get("tag", "?")
+    ref = node.get("ref")
+    parts = [tag]
+    if ref:
+        parts[0] = f"[{ref}] {tag}"
+
+    # Inline attributes
+    for attr in ("type", "name", "href", "alt", "role", "ariaLabel", "placeholder", "value"):
+        val = node.get(attr)
+        if val:
+            # Truncate long values
+            s = str(val)
+            if len(s) > 80:
+                s = s[:77] + "..."
+            parts.append(f'{attr}="{s}"')
+
+    for flag in ("disabled", "checked", "selected"):
+        if node.get(flag):
+            parts.append(flag)
+
+    prefix = " " * indent
+    header = prefix + " ".join(parts)
+
+    text = node.get("text")
+    if text:
+        # Truncate long text
+        if len(text) > 120:
+            text = text[:117] + "..."
+        header += f": {text}"
+
+    lines = [header]
+    children = node.get("children", [])
+    for child in children:
+        lines.extend(_flatten_tree(child, indent + 2))
+    return lines
+
+
+class BrowserService:
+    """Manages a Playwright browser on a dedicated background thread.
+
+    All Playwright operations are dispatched to a single long-lived thread via
+    a task queue.  Callers from *any* worker thread can use the public API
+    safely.  An idle timer automatically shuts the browser down after
+    ``idle_timeout`` seconds of inactivity (default 300 = 5 min).
+    """
+
+    _IDLE_TIMEOUT_DEFAULT = 300  # seconds
+
+    def __init__(self, config: Optional[Dict[str, Any]] = None):
+        self._config = config or {}
+        self._headless: Optional[bool] = None
+        self._screenshot_dir: Optional[str] = None
+
+        # Background thread state
+        self._thread: Optional[threading.Thread] = None
+        self._task_queue: queue.Queue = queue.Queue()
+        self._lock = threading.Lock()
+        self._alive = False
+        self._ready = threading.Event()
+
+        # Playwright objects (only accessed on the background thread)
+        self._playwright = None
+        self._browser = None
+        self._context = None
+        self._page = None
+
+        # Idle auto-release
+        idle_cfg = self._config.get("idle_timeout")
+        self._idle_timeout: float = float(idle_cfg) if idle_cfg is not None else self._IDLE_TIMEOUT_DEFAULT
+        self._idle_timer: Optional[threading.Timer] = None
+
+    # ------------------------------------------------------------------
+    # Background-thread lifecycle
+    # ------------------------------------------------------------------
+
+    def _start_thread(self):
+        """Start the dedicated Playwright thread if not already running."""
+        with self._lock:
+            if self._alive and self._thread and self._thread.is_alive():
+                return
+            # Wait for old thread to fully exit before creating a new one
+            old = self._thread
+            if old and old.is_alive():
+                old.join(timeout=5)
+            # Fresh queue to avoid stale sentinels from a previous close()
+            self._task_queue = queue.Queue()
+            self._alive = True
+            self._ready = threading.Event()
+            self._thread = threading.Thread(target=self._run_loop, daemon=True, name="BrowserThread")
+            self._thread.start()
+            # Block until browser is ready (or failed)
+            self._ready.wait(timeout=30)
+
+    def _run_loop(self):
+        """Event loop running on the dedicated thread. Processes tasks until stopped."""
+        logger.info("[Browser] Background thread started")
+        try:
+            self._launch_browser()
+        except Exception as e:
+            logger.error(f"[Browser] Failed to launch browser: {e}")
+            self._alive = False
+            self._ready.set()
+            self._drain_queue(RuntimeError(f"Browser launch failed: {e}"))
+            return
+        self._ready.set()
+
+        while self._alive:
+            try:
+                task = self._task_queue.get(timeout=1.0)
+            except queue.Empty:
+                continue
+            if task is None:
+                break
+            fn, args, kwargs, result_slot = task
+            try:
+                result_slot["value"] = fn(*args, **kwargs)
+            except Exception as e:
+                result_slot["error"] = e
+            finally:
+                result_slot["event"].set()
+
+        self._shutdown_browser()
+        self._drain_queue(RuntimeError("Browser thread stopped"))
+        logger.info("[Browser] Background thread exited")
+
+    def _drain_queue(self, error: Exception):
+        """Unblock all callers waiting on the queue with an error."""
+        while True:
+            try:
+                task = self._task_queue.get_nowait()
+            except queue.Empty:
+                break
+            if task is None:
+                continue
+            _, _, _, result_slot = task
+            result_slot["error"] = error
+            result_slot["event"].set()
+
+    def _launch_browser(self):
+        """Launch Chromium on the background thread."""
+        if self._headless is None:
+            headless_cfg = self._config.get("headless")
+            self._headless = headless_cfg if headless_cfg is not None else _should_use_headless()
+
+        launch_args = ["--disable-dev-shm-usage"]
+        if self._headless:
+            launch_args.append("--no-sandbox")
+
+        extra_args = self._config.get("launch_args", [])
+        if extra_args:
+            launch_args.extend(extra_args)
+
+        viewport_w = self._config.get("viewport_width", 1280)
+        viewport_h = self._config.get("viewport_height", 720)
+
+        self._playwright = sync_playwright().start()
+        logger.info(f"[Browser] Launching Chromium (headless={self._headless})")
+        self._browser = self._playwright.chromium.launch(
+            headless=self._headless,
+            args=launch_args,
+        )
+        self._context = self._browser.new_context(
+            viewport={"width": viewport_w, "height": viewport_h},
+            user_agent=(
+                "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) "
+                "AppleWebKit/537.36 (KHTML, like Gecko) "
+                "Chrome/131.0.0.0 Safari/537.36"
+            ),
+        )
+        self._page = self._context.new_page()
+        logger.info("[Browser] Browser ready")
+
+    def _shutdown_browser(self):
+        """Shut down all Playwright resources on the background thread."""
+        self._cancel_idle_timer()
+        for obj, label in [
+            (self._context, "context"),
+            (self._browser, "browser"),
+        ]:
+            try:
+                if obj:
+                    obj.close()
+            except Exception as e:
+                logger.debug(f"[Browser] {label} close error: {e}")
+        try:
+            if self._playwright:
+                self._playwright.stop()
+        except Exception as e:
+            logger.debug(f"[Browser] playwright stop error: {e}")
+        self._page = None
+        self._context = None
+        self._browser = None
+        self._playwright = None
+        logger.info("[Browser] Browser closed")
+
+    def _submit(self, fn: Callable, *args, **kwargs):
+        """Submit *fn* to the background thread and block until it completes."""
+        self._start_thread()
+
+        if not self._alive:
+            raise RuntimeError("Browser is not available")
+
+        self._reset_idle_timer()
+
+        result_slot: Dict[str, Any] = {"event": threading.Event()}
+        self._task_queue.put((fn, args, kwargs, result_slot))
+
+        # Timeout prevents permanent hang if the background thread crashes
+        completed = result_slot["event"].wait(timeout=120)
+        if not completed:
+            raise TimeoutError("Browser operation timed out (120s)")
+
+        if "error" in result_slot:
+            raise result_slot["error"]
+        return result_slot.get("value")
+
+    # ------------------------------------------------------------------
+    # Idle auto-release
+    # ------------------------------------------------------------------
+
+    def _reset_idle_timer(self):
+        self._cancel_idle_timer()
+        if self._idle_timeout > 0:
+            self._idle_timer = threading.Timer(self._idle_timeout, self._on_idle_timeout)
+            self._idle_timer.daemon = True
+            self._idle_timer.start()
+
+    def _cancel_idle_timer(self):
+        if self._idle_timer:
+            self._idle_timer.cancel()
+            self._idle_timer = None
+
+    def _on_idle_timeout(self):
+        logger.info(f"[Browser] Idle for {self._idle_timeout}s, auto-releasing browser")
+        self.close()
+
+    # ------------------------------------------------------------------
+    # Public lifecycle
+    # ------------------------------------------------------------------
+
+    def close(self):
+        """Shut down browser and background thread (safe from any thread)."""
+        self._cancel_idle_timer()
+        with self._lock:
+            if not self._alive:
+                return
+            self._alive = False
+            t = self._thread
+        if self._task_queue is not None:
+            self._task_queue.put(None)
+        if t is not None and t.is_alive():
+            t.join(timeout=10)
+        with self._lock:
+            self._thread = None
+
+    # ------------------------------------------------------------------
+    # Actions  (each method is dispatched to the background thread)
+    # ------------------------------------------------------------------
+
+    def navigate(self, url: str, timeout: int = 30000) -> Dict[str, Any]:
+        return self._submit(self._do_navigate, url, timeout)
+
+    def _do_navigate(self, url: str, timeout: int) -> Dict[str, Any]:
+        page = self._page
+        try:
+            resp = page.goto(url, wait_until="domcontentloaded", timeout=timeout)
+            status = resp.status if resp else None
+        except Exception as e:
+            return {"error": f"Navigation failed: {e}"}
+
+        try:
+            page.wait_for_load_state("networkidle", timeout=8000)
+        except Exception:
+            pass
+        page.wait_for_timeout(500)
+
+        try:
+            title = page.title()
+        except Exception:
+            title = ""
+        try:
+            current_url = page.url
+        except Exception:
+            current_url = url
+
+        return {"url": current_url, "title": title, "status": status}
+
+    def snapshot(self, selector: Optional[str] = None) -> str:
+        return self._submit(self._do_snapshot, selector)
+
+    def _do_snapshot(self, selector: Optional[str] = None) -> str:
+        page = self._page
+        try:
+            result = page.evaluate(_SNAPSHOT_JS)
+        except Exception as e:
+            return f"[Snapshot error: {e}]"
+
+        tree = result.get("tree")
+        ref_count = result.get("refCount", 0)
+        lines = _flatten_tree(tree)
+
+        try:
+            title = page.title()
+        except Exception:
+            title = ""
+        try:
+            url = page.url
+        except Exception:
+            url = ""
+
+        header = f"Page: {title}  ({url})\nInteractive elements: {ref_count}\n---"
+        body = "\n".join(lines)
+
+        max_chars = self._config.get("snapshot_max_chars", 30000)
+        if len(body) > max_chars:
+            body = body[:max_chars] + "\n... [snapshot truncated]"
+
+        return f"{header}\n{body}"
+
+    def screenshot(self, full_page: bool = False, cwd: str = "") -> str:
+        return self._submit(self._do_screenshot, full_page, cwd)
+
+    def _do_screenshot(self, full_page: bool = False, cwd: str = "") -> str:
+        page = self._page
+        save_dir = self._get_screenshot_dir(cwd)
+        filename = f"screenshot_{uuid.uuid4().hex[:8]}.png"
+        filepath = os.path.join(save_dir, filename)
+        page.screenshot(path=filepath, full_page=full_page)
+        logger.info(f"[Browser] Screenshot saved: {filepath}")
+        return filepath
+
+    def click(self, ref: Optional[int] = None, selector: Optional[str] = None,
+              timeout: int = 5000) -> Dict[str, Any]:
+        return self._submit(self._do_click, ref, selector, timeout)
+
+    def _do_click(self, ref, selector, timeout) -> Dict[str, Any]:
+        page = self._page
+        try:
+            if ref is not None:
+                result = page.evaluate(f"""
+                    () => {{
+                        const el = window.__cowRefMap && window.__cowRefMap[{ref}];
+                        if (!el) return {{ error: "ref {ref} not found. Run snapshot first." }};
+                        el.click();
+                        return {{ clicked: true, tag: el.tagName.toLowerCase() }};
+                    }}
+                """)
+                if result.get("error"):
+                    return result
+                page.wait_for_timeout(500)
+                return result
+            elif selector:
+                page.click(selector, timeout=timeout)
+                return {"clicked": True, "selector": selector}
+            else:
+                return {"error": "Provide either ref (from snapshot) or selector"}
+        except Exception as e:
+            return {"error": f"Click failed: {e}"}
+
+    def fill(self, text: str, ref: Optional[int] = None,
+             selector: Optional[str] = None, timeout: int = 5000) -> Dict[str, Any]:
+        return self._submit(self._do_fill, text, ref, selector, timeout)
+
+    def _do_fill(self, text, ref, selector, timeout) -> Dict[str, Any]:
+        page = self._page
+        try:
+            if ref is not None:
+                result = page.evaluate(f"""
+                    () => {{
+                        const el = window.__cowRefMap && window.__cowRefMap[{ref}];
+                        if (!el) return {{ error: "ref {ref} not found. Run snapshot first." }};
+                        el.focus();
+                        el.value = "";
+                        return {{ tag: el.tagName.toLowerCase(), name: el.name || "" }};
+                    }}
+                """)
+                if result.get("error"):
+                    return result
+                page.keyboard.type(text)
+                return {"filled": True, "ref": ref, "text": text}
+            elif selector:
+                page.fill(selector, text, timeout=timeout)
+                return {"filled": True, "selector": selector, "text": text}
+            else:
+                return {"error": "Provide either ref (from snapshot) or selector"}
+        except Exception as e:
+            return {"error": f"Fill failed: {e}"}
+
+    def select(self, value: str, ref: Optional[int] = None,
+               selector: Optional[str] = None, timeout: int = 5000) -> Dict[str, Any]:
+        return self._submit(self._do_select, value, ref, selector, timeout)
+
+    def _do_select(self, value, ref, selector, timeout) -> Dict[str, Any]:
+        page = self._page
+        try:
+            if ref is not None:
+                result = page.evaluate(f"""
+                    () => {{
+                        const el = window.__cowRefMap && window.__cowRefMap[{ref}];
+                        if (!el || el.tagName.toLowerCase() !== "select")
+                            return {{ error: "ref {ref} is not a <select> element" }};
+                        el.value = {repr(value)};
+                        el.dispatchEvent(new Event("change", {{ bubbles: true }}));
+                        return {{ selected: true, value: el.value }};
+                    }}
+                """)
+                return result
+            elif selector:
+                page.select_option(selector, value, timeout=timeout)
+                return {"selected": True, "selector": selector, "value": value}
+            else:
+                return {"error": "Provide either ref (from snapshot) or selector"}
+        except Exception as e:
+            return {"error": f"Select failed: {e}"}
+
+    def scroll(self, direction: str = "down", amount: int = 500) -> Dict[str, Any]:
+        return self._submit(self._do_scroll, direction, amount)
+
+    def _do_scroll(self, direction, amount) -> Dict[str, Any]:
+        page = self._page
+        delta_map = {
+            "down": (0, amount),
+            "up": (0, -amount),
+            "right": (amount, 0),
+            "left": (-amount, 0),
+        }
+        dx, dy = delta_map.get(direction, (0, amount))
+        try:
+            page.mouse.wheel(dx, dy)
+            page.wait_for_timeout(300)
+            scroll_info = page.evaluate("""
+                () => ({
+                    scrollX: window.scrollX,
+                    scrollY: window.scrollY,
+                    scrollHeight: document.documentElement.scrollHeight,
+                    clientHeight: document.documentElement.clientHeight
+                })
+            """)
+            return {"scrolled": direction, "amount": amount, **scroll_info}
+        except Exception as e:
+            return {"error": f"Scroll failed: {e}"}
+
+    def wait(self, selector: Optional[str] = None, timeout: int = 5000,
+             state: str = "visible") -> Dict[str, Any]:
+        return self._submit(self._do_wait, selector, timeout, state)
+
+    def _do_wait(self, selector, timeout, state) -> Dict[str, Any]:
+        page = self._page
+        try:
+            if selector:
+                page.wait_for_selector(selector, timeout=timeout, state=state)
+                return {"waited": True, "selector": selector, "state": state}
+            else:
+                page.wait_for_timeout(timeout)
+                return {"waited": True, "timeout_ms": timeout}
+        except Exception as e:
+            return {"error": f"Wait failed: {e}"}
+
+    def go_back(self) -> Dict[str, Any]:
+        return self._submit(self._do_go_back)
+
+    def _do_go_back(self) -> Dict[str, Any]:
+        page = self._page
+        try:
+            page.go_back(wait_until="domcontentloaded", timeout=10000)
+            try:
+                title = page.title()
+            except Exception:
+                title = ""
+            try:
+                url = page.url
+            except Exception:
+                url = ""
+            return {"url": url, "title": title}
+        except Exception as e:
+            return {"error": f"Go back failed: {e}"}
+
+    def go_forward(self) -> Dict[str, Any]:
+        return self._submit(self._do_go_forward)
+
+    def _do_go_forward(self) -> Dict[str, Any]:
+        page = self._page
+        try:
+            page.go_forward(wait_until="domcontentloaded", timeout=10000)
+            try:
+                title = page.title()
+            except Exception:
+                title = ""
+            try:
+                url = page.url
+            except Exception:
+                url = ""
+            return {"url": url, "title": title}
+        except Exception as e:
+            return {"error": f"Go forward failed: {e}"}
+
+    def get_text(self, selector: str) -> Dict[str, Any]:
+        return self._submit(self._do_get_text, selector)
+
+    def _do_get_text(self, selector) -> Dict[str, Any]:
+        page = self._page
+        try:
+            text = page.text_content(selector, timeout=5000)
+            return {"text": text or ""}
+        except Exception as e:
+            return {"error": f"Get text failed: {e}"}
+
+    def evaluate(self, script: str) -> Dict[str, Any]:
+        return self._submit(self._do_evaluate, script)
+
+    def _do_evaluate(self, script) -> Dict[str, Any]:
+        page = self._page
+        try:
+            result = page.evaluate(script)
+            return {"result": result}
+        except Exception as e:
+            return {"error": f"Evaluate failed: {e}"}
+
+    def press(self, key: str) -> Dict[str, Any]:
+        return self._submit(self._do_press, key)
+
+    def _do_press(self, key) -> Dict[str, Any]:
+        page = self._page
+        try:
+            page.keyboard.press(key)
+            page.wait_for_timeout(300)
+            return {"pressed": key}
+        except Exception as e:
+            return {"error": f"Press failed: {e}"}
+
+    # ------------------------------------------------------------------
+    # Helpers
+    # ------------------------------------------------------------------
+
+    def _get_screenshot_dir(self, cwd: str = "") -> str:
+        if self._screenshot_dir and os.path.isdir(self._screenshot_dir):
+            return self._screenshot_dir
+        base = cwd or os.getcwd()
+        d = os.path.join(base, "tmp")
+        os.makedirs(d, exist_ok=True)
+        self._screenshot_dir = d
+        return d
--- a/agent/tools/browser/browser_tool.py
+++ b/agent/tools/browser/browser_tool.py
@@ -0,0 +1,290 @@
+"""
+Browser tool - Control a Chromium browser for web navigation and interaction.
+
+Uses Playwright under the hood. Browser instance is lazily started on first
+use, reused across tool calls within the same session, and cleaned up via
+close().
+"""
+
+import json
+import os
+from typing import Dict, Any, Optional
+
+from agent.tools.base_tool import BaseTool, ToolResult
+from agent.tools.browser.browser_service import BrowserService
+from common.log import logger
+
+
+class BrowserTool(BaseTool):
+    """Single tool exposing all browser actions via an 'action' parameter."""
+
+    name: str = "browser"
+    description: str = (
+        "Control a browser to navigate web pages, interact with elements, and extract content. "
+        "Actions: navigate, snapshot, click, fill, select, scroll, screenshot, wait, back, forward, "
+        "get_text, press, evaluate.\n\n"
+        "Workflow: navigate (auto-includes snapshot with element refs) → click/fill/select by ref → snapshot to verify.\n\n"
+        "Use snapshot as the primary way to read pages. Use screenshot + send to show key results to the user. "
+        "For login/CAPTCHA/authorization etc., screenshot and ask the user for help."
+    )
+
+    params: dict = {
+        "type": "object",
+        "properties": {
+            "action": {
+                "type": "string",
+                "description": (
+                    "The browser action to perform. One of: "
+                    "navigate, snapshot, click, fill, select, scroll, "
+                    "screenshot, wait, back, forward, get_text, press, evaluate"
+                ),
+                "enum": [
+                    "navigate", "snapshot", "click", "fill", "select", "scroll",
+                    "screenshot", "wait", "back", "forward", "get_text", "press",
+                    "evaluate"
+                ]
+            },
+            "url": {
+                "type": "string",
+                "description": "URL to navigate to (for 'navigate' action)"
+            },
+            "ref": {
+                "type": "integer",
+                "description": "Element ref number from snapshot (for click/fill/select)"
+            },
+            "selector": {
+                "type": "string",
+                "description": "CSS selector as fallback when ref is unavailable (for click/fill/select/wait/get_text)"
+            },
+            "text": {
+                "type": "string",
+                "description": "Text to type (for 'fill' action)"
+            },
+            "value": {
+                "type": "string",
+                "description": "Option value (for 'select' action)"
+            },
+            "key": {
+                "type": "string",
+                "description": "Key to press, e.g. Enter, Tab, Escape (for 'press' action)"
+            },
+            "direction": {
+                "type": "string",
+                "description": "Scroll direction: up, down, left, right (for 'scroll' action, default: down)"
+            },
+            "script": {
+                "type": "string",
+                "description": "JavaScript code to execute (for 'evaluate' action)"
+            },
+            "full_page": {
+                "type": "boolean",
+                "description": "Capture full page screenshot (for 'screenshot' action, default: false)"
+            },
+            "timeout": {
+                "type": "integer",
+                "description": "Timeout in milliseconds (optional, default varies by action)"
+            }
+        },
+        "required": ["action"]
+    }
+
+    _shared_service: Optional[BrowserService] = None
+
+    def __init__(self, config: dict = None):
+        self.config = config or {}
+        self.cwd = self.config.get("cwd", os.getcwd())
+        self._service: Optional[BrowserService] = None
+
+    def _get_service(self) -> BrowserService:
+        """Get or create the browser service, sharing across copies."""
+        if self._service is not None:
+            return self._service
+
+        # Reuse shared service across tool copies within the same session
+        if BrowserTool._shared_service is not None:
+            self._service = BrowserTool._shared_service
+            return self._service
+
+        self._service = BrowserService(self.config)
+        BrowserTool._shared_service = self._service
+        return self._service
+
+    def execute(self, args: Dict[str, Any]) -> ToolResult:
+        action = args.get("action", "").strip().lower()
+        if not action:
+            return ToolResult.fail("Error: 'action' parameter is required")
+
+        handler = self._ACTION_MAP.get(action)
+        if not handler:
+            valid = ", ".join(sorted(self._ACTION_MAP.keys()))
+            return ToolResult.fail(f"Unknown action '{action}'. Valid actions: {valid}")
+
+        try:
+            return handler(self, args)
+        except Exception as e:
+            logger.error(f"[Browser] Action '{action}' error: {e}")
+            return ToolResult.fail(f"Browser error ({action}): {e}")
+
+    # ------------------------------------------------------------------
+    # Action handlers
+    # ------------------------------------------------------------------
+
+    def _do_navigate(self, args: Dict[str, Any]) -> ToolResult:
+        url = args.get("url", "").strip()
+        if not url:
+            return ToolResult.fail("Error: 'url' is required for navigate action")
+        if not url.startswith(("http://", "https://")):
+            url = "https://" + url
+        timeout = args.get("timeout", 30000)
+        service = self._get_service()
+        result = service.navigate(url, timeout=timeout)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        # Auto-snapshot after navigation so the agent gets page content in one call
+        snapshot_text = service.snapshot()
+        return ToolResult.success(
+            f"Navigated to: {result['url']}\nTitle: {result['title']}\nStatus: {result['status']}\n\n"
+            f"--- Page Snapshot ---\n{snapshot_text}"
+        )
+
+    def _do_snapshot(self, args: Dict[str, Any]) -> ToolResult:
+        selector = args.get("selector")
+        text = self._get_service().snapshot(selector=selector)
+        return ToolResult.success(text)
+
+    def _do_click(self, args: Dict[str, Any]) -> ToolResult:
+        ref = args.get("ref")
+        selector = args.get("selector")
+        timeout = args.get("timeout", 5000)
+        result = self._get_service().click(ref=ref, selector=selector, timeout=timeout)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(f"Clicked successfully. Use 'snapshot' to see updated page.")
+
+    def _do_fill(self, args: Dict[str, Any]) -> ToolResult:
+        text = args.get("text", "")
+        ref = args.get("ref")
+        selector = args.get("selector")
+        timeout = args.get("timeout", 5000)
+        if not text and text != "":
+            return ToolResult.fail("Error: 'text' is required for fill action")
+        result = self._get_service().fill(text, ref=ref, selector=selector, timeout=timeout)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(f"Filled text into element. Use 'snapshot' to verify.")
+
+    def _do_select(self, args: Dict[str, Any]) -> ToolResult:
+        value = args.get("value", "")
+        ref = args.get("ref")
+        selector = args.get("selector")
+        timeout = args.get("timeout", 5000)
+        if not value:
+            return ToolResult.fail("Error: 'value' is required for select action")
+        result = self._get_service().select(value, ref=ref, selector=selector, timeout=timeout)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(f"Selected option '{value}'.")
+
+    def _do_scroll(self, args: Dict[str, Any]) -> ToolResult:
+        direction = args.get("direction", "down")
+        amount = args.get("timeout", 500)  # reuse timeout field or default
+        if "amount" in args:
+            amount = args["amount"]
+        result = self._get_service().scroll(direction=direction, amount=amount)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        pos = f"scrollY={result.get('scrollY', '?')}/{result.get('scrollHeight', '?')}"
+        return ToolResult.success(f"Scrolled {direction}. Position: {pos}")
+
+    def _do_screenshot(self, args: Dict[str, Any]) -> ToolResult:
+        full_page = args.get("full_page", False)
+        filepath = self._get_service().screenshot(full_page=full_page, cwd=self.cwd)
+        return ToolResult.success(f"Screenshot saved to: {filepath}")
+
+    def _do_wait(self, args: Dict[str, Any]) -> ToolResult:
+        selector = args.get("selector")
+        timeout = args.get("timeout", 5000)
+        result = self._get_service().wait(selector=selector, timeout=timeout)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(f"Wait completed.")
+
+    def _do_back(self, args: Dict[str, Any]) -> ToolResult:
+        result = self._get_service().go_back()
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(f"Navigated back to: {result['url']}")
+
+    def _do_forward(self, args: Dict[str, Any]) -> ToolResult:
+        result = self._get_service().go_forward()
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(f"Navigated forward to: {result['url']}")
+
+    def _do_get_text(self, args: Dict[str, Any]) -> ToolResult:
+        selector = args.get("selector", "").strip()
+        if not selector:
+            return ToolResult.fail("Error: 'selector' is required for get_text action")
+        result = self._get_service().get_text(selector)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(result["text"])
+
+    def _do_press(self, args: Dict[str, Any]) -> ToolResult:
+        key = args.get("key", "").strip()
+        if not key:
+            return ToolResult.fail("Error: 'key' is required for press action")
+        result = self._get_service().press(key)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        return ToolResult.success(f"Pressed key: {key}")
+
+    def _do_evaluate(self, args: Dict[str, Any]) -> ToolResult:
+        script = args.get("script", "").strip()
+        if not script:
+            return ToolResult.fail("Error: 'script' is required for evaluate action")
+        result = self._get_service().evaluate(script)
+        if "error" in result:
+            return ToolResult.fail(result["error"])
+        val = result.get("result")
+        if isinstance(val, (dict, list)):
+            return ToolResult.success(json.dumps(val, ensure_ascii=False, indent=2))
+        return ToolResult.success(str(val) if val is not None else "(no return value)")
+
+    # Action dispatch table
+    _ACTION_MAP = {
+        "navigate": _do_navigate,
+        "snapshot": _do_snapshot,
+        "click": _do_click,
+        "fill": _do_fill,
+        "select": _do_select,
+        "scroll": _do_scroll,
+        "screenshot": _do_screenshot,
+        "wait": _do_wait,
+        "back": _do_back,
+        "forward": _do_forward,
+        "get_text": _do_get_text,
+        "press": _do_press,
+        "evaluate": _do_evaluate,
+    }
+
+    # ------------------------------------------------------------------
+    # Lifecycle
+    # ------------------------------------------------------------------
+
+    def copy(self):
+        """Share browser instance across tool copies (avoids re-launching)."""
+        new_tool = BrowserTool(self.config)
+        new_tool.model = self.model
+        new_tool.context = getattr(self, "context", None)
+        new_tool.cwd = self.cwd
+        new_tool._service = self._service
+        return new_tool
+
+    def close(self):
+        """Release browser resources."""
+        if self._service:
+            self._service.close()
+            self._service = None
+        BrowserTool._shared_service = None
+        logger.info("[Browser] BrowserTool closed")
--- a/agent/tools/browser_tool.py
+++ b/agent/tools/browser_tool.py
@@ -1,18 +0,0 @@
-def copy(self):
-    """
-    Special copy method for browser tool to avoid recreating browser instance.
-    
-    :return: A new instance with shared browser reference but unique model
-    """
-    new_tool = self.__class__()
-    
-    # Copy essential attributes
-    new_tool.model = self.model
-    new_tool.context = getattr(self, 'context', None)
-    new_tool.config = getattr(self, 'config', None)
-    
-    # Share the browser instance instead of creating a new one
-    if hasattr(self, 'browser'):
-        new_tool.browser = self.browser
-    
-    return new_tool 
--- a/agent/tools/memory/memory_get.py
+++ b/agent/tools/memory/memory_get.py
@@ -44,6 +44,19 @@ class MemoryGetTool(BaseTool):
        """
        super().__init__()
        self.memory_manager = memory_manager
+
+        from config import conf
+        if conf().get("knowledge", True):
+            self.description = (
+                "Read specific content from memory or knowledge files. "
+                "Use this to get full context from a memory file, knowledge page, or specific line range."
+            )
+            self.params = {**self.params}
+            self.params["properties"] = {**self.params["properties"]}
+            self.params["properties"]["path"] = {
+                "type": "string",
+                "description": "Relative path to the memory or knowledge file (e.g. 'MEMORY.md', 'memory/2026-01-01.md', 'knowledge/concepts/moe.md')"
+            }
    
    def execute(self, args: dict):
        """
@@ -68,11 +81,15 @@ class MemoryGetTool(BaseTool):
            workspace_dir = self.memory_manager.config.get_workspace()
            
            # Auto-prepend memory/ if not present and not absolute path
-            # Exception: MEMORY.md is in the root directory
-            if not path.startswith('memory/') and not path.startswith('/') and path != 'MEMORY.md':
+            # Exceptions: MEMORY.md in root, knowledge/ files at workspace root
+            if not path.startswith('memory/') and not path.startswith('knowledge/') and not path.startswith('/') and path != 'MEMORY.md':
                path = f'memory/{path}'
            
-            file_path = workspace_dir / path
+            file_path = (workspace_dir / path).resolve()
+            workspace_resolved = workspace_dir.resolve()
+            
+            if not str(file_path).startswith(str(workspace_resolved) + '/') and file_path != workspace_resolved:
+                return ToolResult.fail(f"Error: Access denied: path outside workspace")
            
            if not file_path.exists():
                return ToolResult.fail(f"Error: File not found: {path}")
--- a/agent/tools/memory/memory_search.py
+++ b/agent/tools/memory/memory_search.py
@@ -48,6 +48,13 @@ class MemorySearchTool(BaseTool):
        super().__init__()
        self.memory_manager = memory_manager
        self.user_id = user_id
+
+        from config import conf
+        if conf().get("knowledge", True):
+            self.description = (
+                "Search agent's long-term memory and knowledge base using semantic and keyword search. "
+                "Use this to recall past conversations, preferences, and knowledge pages."
+            )
    
    def execute(self, args: dict):
        """
--- a/agent/tools/read/read.py
+++ b/agent/tools/read/read.py
@@ -48,7 +48,8 @@ class Read(BaseTool):
        self.binary_extensions = {'.exe', '.dll', '.so', '.dylib', '.bin', '.dat', '.db', '.sqlite'}
        self.archive_extensions = {'.zip', '.tar', '.gz', '.rar', '.7z', '.bz2', '.xz'}
        self.pdf_extensions = {'.pdf'}
-        
+        self.office_extensions = {'.doc', '.docx', '.xls', '.xlsx', '.ppt', '.pptx'}
+
        # Readable text formats (will be read with truncation)
        self.text_extensions = {
            '.txt', '.md', '.markdown', '.rst', '.log', '.csv', '.tsv', '.json', '.xml', '.yaml', '.yml',
@@ -57,7 +58,6 @@ class Read(BaseTool):
            '.sh', '.bash', '.zsh', '.fish', '.ps1', '.bat', '.cmd',
            '.sql', '.r', '.m', '.swift', '.kt', '.scala', '.clj', '.erl', '.ex',
            '.dockerfile', '.makefile', '.cmake', '.gradle', '.properties', '.ini', '.conf', '.cfg',
-            '.doc', '.docx', '.xls', '.xlsx', '.ppt', '.pptx'  # Office documents
        }
    
    def execute(self, args: Dict[str, Any]) -> ToolResult:
@@ -120,7 +120,11 @@ class Read(BaseTool):
        # Check if PDF
        if file_ext in self.pdf_extensions:
            return self._read_pdf(absolute_path, path, offset, limit)
-        
+
+        # Check if Office document (.docx, .xlsx, .pptx, etc.)
+        if file_ext in self.office_extensions:
+            return self._read_office(absolute_path, path, file_ext, offset, limit)
+
        # Read text file (with truncation for large files)
        return self._read_text(absolute_path, path, offset, limit)
    
@@ -337,6 +341,116 @@ class Read(BaseTool):
        except Exception as e:
            return ToolResult.fail(f"Error reading file: {str(e)}")
    
+    def _read_office(self, absolute_path: str, display_path: str, file_ext: str,
+                     offset: int = None, limit: int = None) -> ToolResult:
+        """Read Office documents (.docx, .xlsx, .pptx) using python-docx / openpyxl / python-pptx."""
+        try:
+            text = self._extract_office_text(absolute_path, file_ext)
+        except ImportError as e:
+            return ToolResult.fail(str(e))
+        except Exception as e:
+            return ToolResult.fail(f"Error reading Office document: {e}")
+
+        if not text or not text.strip():
+            return ToolResult.success({
+                "content": f"[Office file {Path(absolute_path).name}: no text content could be extracted]",
+            })
+
+        all_lines = text.split('\n')
+        total_lines = len(all_lines)
+
+        start_line = 0
+        if offset is not None:
+            if offset < 0:
+                start_line = max(0, total_lines + offset)
+            else:
+                start_line = max(0, offset - 1)
+                if start_line >= total_lines:
+                    return ToolResult.fail(
+                        f"Error: Offset {offset} is beyond end of content ({total_lines} lines total)"
+                    )
+
+        selected_content = text
+        user_limited_lines = None
+        if limit is not None:
+            end_line = min(start_line + limit, total_lines)
+            selected_content = '\n'.join(all_lines[start_line:end_line])
+            user_limited_lines = end_line - start_line
+        elif offset is not None:
+            selected_content = '\n'.join(all_lines[start_line:])
+
+        truncation = truncate_head(selected_content)
+        start_line_display = start_line + 1
+        output_text = ""
+
+        if truncation.truncated:
+            end_line_display = start_line_display + truncation.output_lines - 1
+            next_offset = end_line_display + 1
+            output_text = truncation.content
+            output_text += f"\n\n[Showing lines {start_line_display}-{end_line_display} of {total_lines}. Use offset={next_offset} to continue.]"
+        elif user_limited_lines is not None and start_line + user_limited_lines < total_lines:
+            remaining = total_lines - (start_line + user_limited_lines)
+            next_offset = start_line + user_limited_lines + 1
+            output_text = truncation.content
+            output_text += f"\n\n[{remaining} more lines in file. Use offset={next_offset} to continue.]"
+        else:
+            output_text = truncation.content
+
+        return ToolResult.success({
+            "content": output_text,
+            "total_lines": total_lines,
+            "start_line": start_line_display,
+            "output_lines": truncation.output_lines,
+        })
+
+    @staticmethod
+    def _extract_office_text(absolute_path: str, file_ext: str) -> str:
+        """Extract plain text from an Office document."""
+        if file_ext in ('.docx', '.doc'):
+            try:
+                from docx import Document
+            except ImportError:
+                raise ImportError("Error: python-docx library not installed. Install with: pip install python-docx")
+            doc = Document(absolute_path)
+            paragraphs = [p.text for p in doc.paragraphs]
+            for table in doc.tables:
+                for row in table.rows:
+                    paragraphs.append('\t'.join(cell.text for cell in row.cells))
+            return '\n'.join(paragraphs)
+
+        if file_ext in ('.xlsx', '.xls'):
+            try:
+                from openpyxl import load_workbook
+            except ImportError:
+                raise ImportError("Error: openpyxl library not installed. Install with: pip install openpyxl")
+            wb = load_workbook(absolute_path, read_only=True, data_only=True)
+            parts = []
+            for ws in wb.worksheets:
+                parts.append(f"--- Sheet: {ws.title} ---")
+                for row in ws.iter_rows(values_only=True):
+                    parts.append('\t'.join(str(c) if c is not None else '' for c in row))
+            wb.close()
+            return '\n'.join(parts)
+
+        if file_ext in ('.pptx', '.ppt'):
+            try:
+                from pptx import Presentation
+            except ImportError:
+                raise ImportError("Error: python-pptx library not installed. Install with: pip install python-pptx")
+            prs = Presentation(absolute_path)
+            parts = []
+            for i, slide in enumerate(prs.slides, 1):
+                parts.append(f"--- Slide {i} ---")
+                for shape in slide.shapes:
+                    if shape.has_text_frame:
+                        for para in shape.text_frame.paragraphs:
+                            text = para.text.strip()
+                            if text:
+                                parts.append(text)
+            return '\n'.join(parts)
+
+        return ""
+
    def _read_pdf(self, absolute_path: str, display_path: str, offset: int = None, limit: int = None) -> ToolResult:
        """
        Read PDF file content
--- a/agent/tools/send/send.py
+++ b/agent/tools/send/send.py
@@ -98,7 +98,18 @@ class Send(BaseTool):
            "size_formatted": self._format_size(file_size),
            "message": message or f"正在发送 {file_name}"
        }
-        
+
+        try:
+            from common.cloud_client import get_website_base_url, copy_send_file
+
+            # Do nothing when in local env
+            if get_website_base_url():
+                url = copy_send_file(absolute_path, self.cwd)
+                if url:
+                    result["url"] = url
+        except Exception:
+            pass
+
        return ToolResult.success(result)
    
    def _resolve_path(self, path: str) -> str:
--- a/agent/tools/tool_manager.py
+++ b/agent/tools/tool_manager.py
@@ -84,11 +84,11 @@ class ToolManager:
                                except ImportError as e:
                                    # Handle missing dependencies with helpful messages
                                    error_msg = str(e)
-                                    if "browser-use" in error_msg or "browser_use" in error_msg:
+                                    if "playwright" in error_msg:
                                        logger.warning(
                                            f"[ToolManager] Browser tool not loaded - missing dependencies.\n"
                                            f"  To enable browser tool, run:\n"
-                                            f"    pip install browser-use markdownify playwright\n"
+                                            f"    pip install playwright\n"
                                            f"    playwright install chromium"
                                        )
                                    elif "markdownify" in error_msg:
@@ -154,11 +154,11 @@ class ToolManager:
                            except ImportError as e:
                                # Handle missing dependencies with helpful messages
                                error_msg = str(e)
-                                if "browser-use" in error_msg or "browser_use" in error_msg:
+                                if "playwright" in error_msg:
                                    logger.warning(
                                        f"[ToolManager] Browser tool not loaded - missing dependencies.\n"
                                        f"  To enable browser tool, run:\n"
-                                        f"    pip install browser-use markdownify playwright\n"
+                                        f"    pip install playwright\n"
                                        f"    playwright install chromium"
                                    )
                                elif "markdownify" in error_msg:
@@ -197,7 +197,7 @@ class ToolManager:
                        logger.warning(
                            f"[ToolManager] Browser tool is configured but not loaded.\n"
                            f"  To enable browser tool, run:\n"
-                            f"    pip install browser-use markdownify playwright\n"
+                            f"    pip install playwright\n"
                            f"    playwright install chromium"
                        )
                    elif tool_name == "google_search":
--- a/agent/tools/vision/vision.py
+++ b/agent/tools/vision/vision.py
@@ -1,22 +1,30 @@
 """
-Vision tool - Analyze images using OpenAI-compatible Vision API.
+Vision tool - Analyze images using Vision API.
 Supports local files (auto base64-encoded) and HTTP URLs.
-Providers: OpenAI (preferred) > LinkAI (fallback).
+
+Provider priority (default):
+  1. Main model via bot.call_vision — zero extra cost
+  2. Other models whose API key is configured — auto-discovered
+  3. OpenAI / LinkAI raw HTTP — reliable fallback
+  When use_linkai=true, LinkAI is promoted to #1.
+  When tool.vision.model is set, that model is used exclusively first.
 """

 import base64
 import os
 import subprocess
 import tempfile
-from typing import Any, Dict, Optional, Tuple
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional

 import requests

 from agent.tools.base_tool import BaseTool, ToolResult
+from common import const
 from common.log import logger
 from config import conf

-DEFAULT_MODEL = "gpt-4.1-mini"
+DEFAULT_MODEL = const.GPT_41_MINI
 DEFAULT_TIMEOUT = 60
 MAX_TOKENS = 1000
 COMPRESS_THRESHOLD = 1_048_576  # 1 MB
@@ -29,15 +37,46 @@ SUPPORTED_EXTENSIONS = {
    "webp": "image/webp",
 }

+_MAIN_MODEL_PROVIDER_NAME = "MainModel"
+
+# (config_key_for_api_key, bot_type, default_vision_model, provider_display_name)
+# Auto-discovered as fallback vision providers when their API key is configured.
+# OpenAI and LinkAI are handled separately (raw HTTP providers), so not listed here.
+_DISCOVERABLE_MODELS = [
+    ("moonshot_api_key", const.MOONSHOT, const.KIMI_K2_5, "Moonshot"),
+    ("ark_api_key", const.DOUBAO, const.DOUBAO_SEED_2_PRO, "Doubao"),
+    ("dashscope_api_key", const.QWEN_DASHSCOPE, const.QWEN36_PLUS, "DashScope"),
+    ("claude_api_key", const.CLAUDEAPI, const.CLAUDE_4_6_SONNET, "Claude"),
+    ("gemini_api_key", const.GEMINI, const.GEMINI_31_FLASH_LITE_PRE, "Gemini"),
+    ("zhipu_ai_api_key", const.ZHIPU_AI, const.GLM_4_7, "ZhipuAI"),
+    ("minimax_api_key", const.MiniMax, const.MINIMAX_M2_7, "MiniMax"),
+]
+
+
+@dataclass
+class VisionProvider:
+    """A single Vision API provider configuration."""
+    name: str
+    api_key: str
+    api_base: str
+    extra_headers: dict = field(default_factory=dict)
+    model_override: Optional[str] = None
+    use_bot: bool = False  # When True, call via bot.call_vision instead of raw HTTP
+    fallback_bot: Any = None  # Bot instance for non-main-model providers
+
+
+class VisionAPIError(Exception):
+    """Raised when a Vision API call fails and should trigger fallback."""
+    pass
+

 class Vision(BaseTool):
-    """Analyze images using OpenAI-compatible Vision API"""
+    """Analyze images using Vision API"""

    name: str = "vision"
    description: str = (
-        "Analyze an image (local file or URL) using Vision API. "
+        "Analyze a local image or image URL (jpg/jpeg/png) using Vision API. "
        "Can describe content, extract text, identify objects, colors, etc. "
-        "Requires OPENAI_API_KEY or LINKAI_API_KEY."
    )

    params: dict = {
@@ -51,13 +90,6 @@ class Vision(BaseTool):
                "type": "string",
                "description": "Question to ask about the image",
            },
-            "model": {
-                "type": "string",
-                "description": (
-                    f"Vision model to use (default: {DEFAULT_MODEL}). "
-                    "Options: gpt-4.1-mini, gpt-4.1, gpt-4o-mini, gpt-4o"
-                ),
-            },
        },
        "required": ["image", "question"],
    }
@@ -67,29 +99,26 @@ class Vision(BaseTool):

    @staticmethod
    def is_available() -> bool:
-        return bool(
-            conf().get("open_ai_api_key") or os.environ.get("OPENAI_API_KEY")
-            or conf().get("linkai_api_key") or os.environ.get("LINKAI_API_KEY")
-        )
+        return True

    def execute(self, args: Dict[str, Any]) -> ToolResult:
        image = args.get("image", "").strip()
        question = args.get("question", "").strip()
-        model = args.get("model", DEFAULT_MODEL).strip() or DEFAULT_MODEL

        if not image:
            return ToolResult.fail("Error: 'image' parameter is required")
        if not question:
            return ToolResult.fail("Error: 'question' parameter is required")

-        api_key, api_base = self._resolve_provider()
-        if not api_key:
+        providers = self._resolve_providers()
+        if not providers:
            return ToolResult.fail(
-                "Error: No API key configured for Vision.\n"
-                "Please configure one of the following using env_config tool:\n"
-                "  1. OPENAI_API_KEY (preferred): env_config(action=\"set\", key=\"OPENAI_API_KEY\", value=\"your-key\")\n"
-                "  2. LINKAI_API_KEY (fallback): env_config(action=\"set\", key=\"LINKAI_API_KEY\", value=\"your-key\")\n\n"
-                "Get your key at: https://platform.openai.com/api-keys or https://link-ai.tech"
+                "Error: No model available for Vision.\n"
+                "The main model does not support vision and no other API keys are configured.\n"
+                "Options:\n"
+                "  1. Switch to a multimodal model (e.g. qwen3.6-plus, claude-sonnet-4-6, gemini-2.0-flash)\n"
+                "  2. Configure OPENAI_API_KEY: env_config(action=\"set\", key=\"OPENAI_API_KEY\", value=\"your-key\")\n"
+                "  3. Configure LINKAI_API_KEY: env_config(action=\"set\", key=\"LINKAI_API_KEY\", value=\"your-key\")"
            )

        try:
@@ -97,32 +126,221 @@ class Vision(BaseTool):
        except Exception as e:
            return ToolResult.fail(f"Error: {e}")

+        return self._call_with_fallback(providers, DEFAULT_MODEL, question, image_content)
+
+    def _call_with_fallback(self, providers: List[VisionProvider], model: str,
+                            question: str, image_content: dict) -> ToolResult:
+        """Try each provider in order; fall back to the next one on failure."""
+        errors: List[str] = []
+        for i, provider in enumerate(providers):
+            use_model = provider.model_override or model
+            try:
+                logger.info(f"[Vision] Trying provider '{provider.name}' "
+                            f"with model '{use_model}' ({i + 1}/{len(providers)})")
+                if provider.use_bot:
+                    result = self._call_via_bot(use_model, question, image_content, provider)
+                else:
+                    result = self._call_api(provider, use_model, question, image_content)
+                logger.info(f"[Vision] ✅ Success via {provider.name} (model={use_model})")
+                return result
+            except VisionAPIError as e:
+                errors.append(f"[{provider.name}/{use_model}] {e}")
+                logger.warning(f"[Vision] Provider '{provider.name}' failed: {e}")
+            except requests.Timeout:
+                errors.append(f"[{provider.name}/{use_model}] Request timed out after {DEFAULT_TIMEOUT}s")
+                logger.warning(f"[Vision] Provider '{provider.name}' timed out")
+            except requests.ConnectionError:
+                errors.append(f"[{provider.name}/{use_model}] Connection failed")
+                logger.warning(f"[Vision] Provider '{provider.name}' connection failed")
+            except Exception as e:
+                errors.append(f"[{provider.name}/{use_model}] {e}")
+                logger.error(f"[Vision] Provider '{provider.name}' unexpected error: {e}", exc_info=True)
+
+        return ToolResult.fail(
+            "Error: All Vision API providers failed.\n" + "\n".join(f"  - {err}" for err in errors)
+        )
+
+    def _resolve_providers(self) -> List[VisionProvider]:
+        """
+        Build an ordered list of available providers.
+
+        Priority:
+          - use_linkai=true  → [LinkAI, MainModel, OtherModels…, OpenAI]
+          - default          → [MainModel, OtherModels…, OpenAI, LinkAI]
+
+        "OtherModels" are auto-discovered from configured API keys.
+        The main model's bot_type is excluded from OtherModels to avoid
+        duplicating the MainModel provider.
+        """
+        use_linkai = conf().get("use_linkai", False) and conf().get("linkai_api_key")
+        providers: List[VisionProvider] = []
+
+        if use_linkai:
+            self._append_provider(providers, self._build_linkai_provider)
+            self._append_provider(providers, self._build_main_model_provider)
+            self._append_other_model_providers(providers)
+            self._append_provider(providers, self._build_openai_provider)
+        else:
+            self._append_provider(providers, self._build_main_model_provider)
+            self._append_other_model_providers(providers)
+            self._append_provider(providers, self._build_openai_provider)
+            self._append_provider(providers, self._build_linkai_provider)
+
+        return providers
+
+    @staticmethod
+    def _append_provider(providers: List[VisionProvider], builder) -> None:
+        p = builder()
+        if p:
+            providers.append(p)
+
+    def _append_other_model_providers(self, providers: List[VisionProvider]) -> None:
+        """
+        Auto-discover other models whose API key is configured.
+        Skip the main model's own bot_type (already covered by MainModel provider).
+        Skip bot_types that already have a provider in the list (e.g. OpenAI).
+        """
+        # Determine main model's bot_type so we can skip it
+        main_bot_type = None
+        if self.model and hasattr(self.model, '_resolve_bot_type'):
+            main_bot_type = self.model._resolve_bot_type(conf().get("model", ""))
+
+        existing_names = {p.name for p in providers}
+
+        for config_key, bot_type, default_model, display_name in _DISCOVERABLE_MODELS:
+            if display_name in existing_names:
+                continue
+            if bot_type == main_bot_type:
+                continue
+            api_key = conf().get(config_key, "")
+            if not api_key or not api_key.strip():
+                continue
+
+            # Create a bot instance and check if it supports call_vision
+            try:
+                from models.bot_factory import create_bot
+                bot = create_bot(bot_type)
+                if not hasattr(bot, 'call_vision'):
+                    continue
+            except Exception:
+                continue
+
+            providers.append(VisionProvider(
+                name=display_name,
+                api_key="",
+                api_base="",
+                model_override=default_model,
+                use_bot=True,
+                fallback_bot=bot,
+            ))
+
+    def _resolve_vision_model(self) -> Optional[str]:
+        """
+        Determine which model to use for vision.
+
+        1. User explicit config: tool.vision.model in config.json
+        2. Fallback to the main configured model name
+        """
+        tool_conf = conf().get("tool", {})
+        user_vision_model = tool_conf.get("vision", {}).get("model") if isinstance(tool_conf, dict) else None
+        if user_vision_model:
+            return user_vision_model
+        model_name = conf().get("model", "")
+        return model_name or None
+
+    def _build_main_model_provider(self) -> Optional[VisionProvider]:
+        """
+        Use the vendor's own model for vision via bot.call_vision.
+        Only available when the bot class has call_vision.
+        """
+        if not (self.model and hasattr(self.model, 'bot')):
+            return None
        try:
-            return self._call_api(api_key, api_base, model, question, image_content)
-        except requests.Timeout:
-            return ToolResult.fail(f"Error: Vision API request timed out after {DEFAULT_TIMEOUT}s")
-        except requests.ConnectionError:
-            return ToolResult.fail("Error: Failed to connect to Vision API")
-        except Exception as e:
-            logger.error(f"[Vision] Unexpected error: {e}", exc_info=True)
-            return ToolResult.fail(f"Error: Vision API call failed - {e}")
+            bot = self.model.bot
+            if not hasattr(bot, 'call_vision'):
+                return None
+        except Exception:
+            return None

-    def _resolve_provider(self) -> Tuple[Optional[str], str]:
-        """Resolve API key and base URL. Priority: conf() > env vars."""
+        vision_model = self._resolve_vision_model()
+
+        return VisionProvider(
+            name=_MAIN_MODEL_PROVIDER_NAME,
+            api_key="",
+            api_base="",
+            model_override=vision_model,
+            use_bot=True,
+        )
+
+    def _build_openai_provider(self) -> Optional[VisionProvider]:
        api_key = conf().get("open_ai_api_key") or os.environ.get("OPENAI_API_KEY")
-        if api_key:
-            api_base = (conf().get("open_ai_api_base") or os.environ.get("OPENAI_API_BASE", "")).rstrip("/") \
-                or "https://api.openai.com/v1"
-            return api_key, self._ensure_v1(api_base)
+        if not api_key:
+            return None
+        api_base = (conf().get("open_ai_api_base") or os.environ.get("OPENAI_API_BASE", "")).rstrip("/") \
+            or "https://api.openai.com/v1"
+        return VisionProvider(name="OpenAI", api_key=api_key, api_base=self._ensure_v1(api_base))

+    def _build_linkai_provider(self) -> Optional[VisionProvider]:
        api_key = conf().get("linkai_api_key") or os.environ.get("LINKAI_API_KEY")
-        if api_key:
-            api_base = (conf().get("linkai_api_base") or os.environ.get("LINKAI_API_BASE", "")).rstrip("/") \
-                or "https://api.link-ai.tech"
-            logger.debug("[Vision] Using LinkAI API (OPENAI_API_KEY not set)")
-            return api_key, self._ensure_v1(api_base)
+        if not api_key:
+            return None
+        api_base = (conf().get("linkai_api_base") or os.environ.get("LINKAI_API_BASE", "")).rstrip("/") \
+            or "https://api.link-ai.tech"
+        from common.utils import get_cloud_headers
+        extra = get_cloud_headers(api_key)
+        extra.pop("Authorization", None)
+        extra.pop("Content-Type", None)
+        return VisionProvider(name="LinkAI", api_key=api_key, api_base=self._ensure_v1(api_base),
+                              extra_headers=extra)

-        return None, ""
+    def _call_via_bot(self, model: str, question: str, image_content: dict,
+                      provider: Optional[VisionProvider] = None) -> ToolResult:
+        """
+        Call a model's call_vision with vendor-native API format.
+        Uses the provider's _fallback_bot if set, otherwise the main model bot.
+        Raises VisionAPIError on failure so fallback can proceed.
+        """
+        try:
+            bot = (provider and provider.fallback_bot) or self.model.bot
+        except Exception as e:
+            raise VisionAPIError(f"Cannot access bot: {e}")
+
+        # Extract the raw image URL from the OpenAI-format image_content block
+        image_url = image_content.get("image_url", {}).get("url", "")
+        if not image_url:
+            raise VisionAPIError("No image URL in content block")
+
+        try:
+            response = bot.call_vision(
+                image_url=image_url,
+                question=question,
+                model=model,
+                max_tokens=MAX_TOKENS,
+            )
+        except Exception as e:
+            raise VisionAPIError(f"call_vision failed: {e}")
+
+        if response is NotImplemented:
+            raise VisionAPIError("Bot does not support vision")
+
+        if isinstance(response, dict) and response.get("error"):
+            raise VisionAPIError(f"API error - {response.get('message', 'Unknown')}")
+
+        content = response.get("content", "") if isinstance(response, dict) else ""
+        if not content:
+            raise VisionAPIError("Empty response from main model")
+
+        usage_info = response.get("usage", {}) if isinstance(response, dict) else {}
+
+        # Use the actual model name from the bot response if available
+        actual_model = response.get("model", model) if isinstance(response, dict) else model
+        provider_name = provider.name if provider else _MAIN_MODEL_PROVIDER_NAME
+        return ToolResult.success({
+            "model": actual_model,
+            "provider": provider_name,
+            "content": content,
+            "usage": usage_info,
+        })

    @staticmethod
    def _ensure_v1(api_base: str) -> str:
@@ -135,9 +353,13 @@ class Vision(BaseTool):
        return api_base.rstrip("/") + "/v1"

    def _build_image_content(self, image: str) -> dict:
-        """Build the image_url content block for the API request."""
+        """
+        Build the image_url content block.
+        Both remote URLs and local files are converted to base64 data URLs
+        so every bot backend can consume them without extra downloads.
+        """
        if image.startswith(("http://", "https://")):
-            return {"type": "image_url", "image_url": {"url": image}}
+            return self._download_to_data_url(image)

        if not os.path.isfile(image):
            raise FileNotFoundError(f"Image file not found: {image}")
@@ -161,9 +383,22 @@ class Vision(BaseTool):
        data_url = f"data:{mime_type};base64,{b64}"
        return {"type": "image_url", "image_url": {"url": data_url}}

+    @staticmethod
+    def _download_to_data_url(url: str) -> dict:
+        """Download a remote image and return it as a base64 data URL."""
+        resp = requests.get(url, timeout=30)
+        if resp.status_code != 200:
+            raise VisionAPIError(f"Failed to download image: HTTP {resp.status_code}")
+        content_type = resp.headers.get("Content-Type", "image/jpeg").split(";")[0].strip()
+        if not content_type.startswith("image/"):
+            content_type = "image/jpeg"
+        b64 = base64.b64encode(resp.content).decode("ascii")
+        data_url = f"data:{content_type};base64,{b64}"
+        return {"type": "image_url", "image_url": {"url": data_url}}
+
    @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
@@ -171,33 +406,58 @@ 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

-    def _call_api(self, api_key: str, api_base: str, model: str,
+    def _call_api(self, provider: VisionProvider, model: str,
                  question: str, image_content: dict) -> ToolResult:
+        """
+        Call a single provider's Vision API.
+        Raises VisionAPIError on recoverable failures so the caller can try
+        the next provider.
+        """
        payload = {
            "model": model,
            "messages": [
@@ -209,33 +469,29 @@ class Vision(BaseTool):
                    ],
                }
            ],
-            "max_tokens": MAX_TOKENS,
        }

        headers = {
-            "Authorization": f"Bearer {api_key}",
+            "Authorization": f"Bearer {provider.api_key}",
            "Content-Type": "application/json",
+            **provider.extra_headers,
        }

        resp = requests.post(
-            f"{api_base}/chat/completions",
+            f"{provider.api_base}/chat/completions",
            headers=headers,
            json=payload,
            timeout=DEFAULT_TIMEOUT,
        )

-        if resp.status_code == 401:
-            return ToolResult.fail("Error: Invalid API key. Please check your configuration.")
-        if resp.status_code == 429:
-            return ToolResult.fail("Error: API rate limit reached. Please try again later.")
        if resp.status_code != 200:
-            return ToolResult.fail(f"Error: Vision API returned HTTP {resp.status_code}: {resp.text[:200]}")
+            raise VisionAPIError(f"HTTP {resp.status_code}: {resp.text[:200]}")

        data = resp.json()

        if "error" in data:
            msg = data["error"].get("message", "Unknown API error")
-            return ToolResult.fail(f"Error: Vision API error - {msg}")
+            raise VisionAPIError(f"API error - {msg}")

        content = ""
        choices = data.get("choices", [])
@@ -245,6 +501,7 @@ class Vision(BaseTool):
        usage = data.get("usage", {})
        result = {
            "model": model,
+            "provider": provider.name,
            "content": content,
            "usage": {
                "prompt_tokens": usage.get("prompt_tokens", 0),
--- a/agent/tools/web_fetch/web_fetch.py
+++ b/agent/tools/web_fetch/web_fetch.py
@@ -78,7 +78,7 @@ class WebFetch(BaseTool):

    name: str = "web_fetch"
    description: str = (
-        "Fetch content from a URL. For web pages, extracts readable text. "
+        "Fetch content from a http/https URL. For web pages, extracts readable text. "
        "For document files (PDF, Word, TXT, Markdown, Excel, PPT), downloads and parses the file content. "
        "Supported file types: .pdf, .docx, .txt, .md, .csv, .xls, .xlsx, .ppt, .pptx"
    )
--- a/agent/tools/web_search/web_search.py
+++ b/agent/tools/web_search/web_search.py
@@ -225,10 +225,8 @@ class WebSearch(BaseTool):
        api_base = conf().get("linkai_api_base", "https://api.link-ai.tech")
        url = f"{api_base.rstrip('/')}/v1/plugin/execute"

-        headers = {
-            "Content-Type": "application/json",
-            "Authorization": f"Bearer {api_key}"
-        }
+        from common.utils import get_cloud_headers
+        headers = get_cloud_headers(api_key)

        payload = {
            "code": "web-search",
--- a/app.py
+++ b/app.py
@@ -78,7 +78,13 @@ class ChannelManager:
            if first_start:
                PluginManager().load_plugins()

-                if conf().get("use_linkai"):
+                # Cloud client is optional. It is only started when
+                # use_linkai=True AND cloud_deployment_id is set.
+                # By default neither is configured, so the app runs
+                # entirely locally without any remote connection.
+                if conf().get("use_linkai") and (
+                    os.environ.get("CLOUD_DEPLOYMENT_ID") or conf().get("cloud_deployment_id")
+                ):
                    try:
                        from common import cloud_client
                        threading.Thread(
@@ -229,6 +235,8 @@ def _clear_singleton_cache(channel_name: str):
        const.DINGTALK: "channel.dingtalk.dingtalk_channel.DingTalkChanel",
        const.WECOM_BOT: "channel.wecom_bot.wecom_bot_channel.WecomBotChannel",
        const.QQ: "channel.qq.qq_channel.QQChannel",
+        const.WEIXIN: "channel.weixin.weixin_channel.WeixinChannel",
+        "wx": "channel.weixin.weixin_channel.WeixinChannel",
    }
    module_path = cls_map.get(channel_name)
    if not module_path:
--- a/bridge/agent_bridge.py
+++ b/bridge/agent_bridge.py
@@ -67,14 +67,14 @@ class AgentLLMModel(LLMModel):

    _MODEL_BOT_TYPE_MAP = {
        "wenxin": const.BAIDU, "wenxin-4": const.BAIDU,
-        "xunfei": const.XUNFEI, const.QWEN: const.QWEN,
+        "xunfei": const.XUNFEI, const.QWEN: const.QWEN_DASHSCOPE,
        const.MODELSCOPE: const.MODELSCOPE,
    }
    _MODEL_PREFIX_MAP = [
        ("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"):
@@ -106,7 +106,7 @@ class AgentLLMModel(LLMModel):
            return configured_bot_type
       
        if not model_name or not isinstance(model_name, str):
-            return const.CHATGPT
+            return const.OPENAI
        if model_name in self._MODEL_BOT_TYPE_MAP:
            return self._MODEL_BOT_TYPE_MAP[model_name]
        if model_name.lower().startswith("minimax") or model_name in ["abab6.5-chat"]:
@@ -115,23 +115,24 @@ 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.CHATGPT
+        if conf().get("bot_type") == "modelscope":
+            return const.MODELSCOPE
        for prefix, btype in self._MODEL_PREFIX_MAP:
            if model_name.startswith(prefix):
                return btype
-        return const.CHATGPT
+        return const.OPENAI

    @property
    def bot(self):
-        """Lazy load the bot, re-create when model changes"""
+        """Lazy load the bot, re-create when model or bot_type changes"""
        from models.bot_factory import create_bot
        cur_model = self.model
-        if self._bot is None or self._bot_model != cur_model:
-            bot_type = self._resolve_bot_type(cur_model)
-            self._bot = create_bot(bot_type)
+        cur_bot_type = self._resolve_bot_type(cur_model)
+        if self._bot is None or self._bot_model != cur_model or getattr(self, '_bot_type', None) != cur_bot_type:
+            self._bot = create_bot(cur_bot_type)
            self._bot = add_openai_compatible_support(self._bot)
            self._bot_model = cur_model
+            self._bot_type = cur_bot_type
        return self._bot

    def call(self, request: LLMRequest):
@@ -152,12 +153,20 @@ class AgentLLMModel(LLMModel):
                # Only pass max_tokens if it's explicitly set
                if request.max_tokens is not None:
                    kwargs['max_tokens'] = request.max_tokens
-                
+
                # Extract system prompt if present
                system_prompt = getattr(request, 'system', None)
                if system_prompt:
                    kwargs['system'] = system_prompt
-                
+
+                # Pass context metadata to bot
+                channel_type = getattr(self, 'channel_type', None)
+                if channel_type:
+                    kwargs['channel_type'] = channel_type
+                session_id = getattr(self, 'session_id', None)
+                if session_id:
+                    kwargs['session_id'] = session_id
+
                response = self.bot.call_with_tools(**kwargs)
                return self._format_response(response)
            else:
@@ -195,10 +204,13 @@ class AgentLLMModel(LLMModel):
                if system_prompt:
                    kwargs['system'] = system_prompt

-                # Pass channel_type for linkai tracking
+                # Pass context metadata to bot
                channel_type = getattr(self, 'channel_type', None)
                if channel_type:
                    kwargs['channel_type'] = channel_type
+                session_id = getattr(self, 'session_id', None)
+                if session_id:
+                    kwargs['session_id'] = session_id

                stream = self.bot.call_with_tools(**kwargs)
                
@@ -262,10 +274,13 @@ class AgentBridge:
            tool_manager.load_tools()
            
            tools = []
+            workspace_dir = kwargs.get("workspace_dir")
            for tool_name in tool_manager.tool_classes.keys():
                try:
                    tool = tool_manager.create_tool(tool_name)
                    if tool:
+                        if workspace_dir and hasattr(tool, 'cwd'):
+                            tool.cwd = workspace_dir
                        tools.append(tool)
                except Exception as e:
                    logger.warning(f"[AgentBridge] Failed to load tool {tool_name}: {e}")
@@ -278,12 +293,13 @@ class AgentBridge:
            tools=tools,
            max_steps=kwargs.get("max_steps", 15),
            output_mode=kwargs.get("output_mode", "logger"),
-            workspace_dir=kwargs.get("workspace_dir"),  # Pass workspace for skills loading
-            enable_skills=kwargs.get("enable_skills", True),  # Enable skills by default
-            memory_manager=kwargs.get("memory_manager"),  # Pass memory manager
+            workspace_dir=kwargs.get("workspace_dir"),
+            skill_manager=kwargs.get("skill_manager"),
+            enable_skills=kwargs.get("enable_skills", True),
+            memory_manager=kwargs.get("memory_manager"),
            max_context_tokens=kwargs.get("max_context_tokens"),
            context_reserve_tokens=kwargs.get("context_reserve_tokens"),
-            runtime_info=kwargs.get("runtime_info")  # Pass runtime_info for dynamic time updates
+            runtime_info=kwargs.get("runtime_info"),
        )

        # Log skill loading details
@@ -374,9 +390,10 @@ class AgentBridge:
                                logger.warning(f"[AgentBridge] Failed to attach context to scheduler: {e}")
                            break
            
-            # Pass channel_type to model so linkai requests carry it
+            # Pass context metadata to model for downstream API requests
            if context and hasattr(agent, 'model'):
                agent.model.channel_type = context.get("channel_type", "")
+                agent.model.session_id = session_id or ""

            # Store session_id on agent so executor can clear DB on fatal errors
            agent._current_session_id = session_id
@@ -482,22 +499,26 @@ class AgentBridge:
                reply.text_content = text_response
            return reply
        
-        # For other unknown file types, return text with file info
-        message = text_response or file_info.get("message", "文件已准备")
-        message += f"\n\n[文件: {file_info.get('file_name', file_path)}]"
-        return Reply(ReplyType.TEXT, message)
+        # For all other file types (tar.gz, zip, etc.), also use FILE type
+        file_url = f"file://{file_path}"
+        logger.info(f"[AgentBridge] Sending generic file: {file_url}")
+        reply = Reply(ReplyType.FILE, file_url)
+        reply.file_name = file_info.get("file_name", os.path.basename(file_path))
+        if text_response:
+            reply.text_content = text_response
+        return reply
    
    def _migrate_config_to_env(self, workspace_root: str):
        """
-        Migrate API keys from config.json to .env file if not already set
-        
+        Sync API keys from config.json to .env file.
+        Adds new keys and updates changed values on each startup.
+
        Args:
            workspace_root: Workspace directory path (not used, kept for compatibility)
        """
        from config import conf
        import os
        
-        # Mapping from config.json keys to environment variable names
        key_mapping = {
            "open_ai_api_key": "OPENAI_API_KEY",
            "open_ai_api_base": "OPENAI_API_BASE",
@@ -506,10 +527,9 @@ class AgentBridge:
            "linkai_api_key": "LINKAI_API_KEY",
        }
        
-        # Use fixed secure location for .env file
        env_file = expand_path("~/.cow/.env")
        
-        # Read existing env vars from .env file
+        # Read existing env vars (key -> value)
        existing_env_vars = {}
        if os.path.exists(env_file):
            try:
@@ -517,48 +537,46 @@ class AgentBridge:
                    for line in f:
                        line = line.strip()
                        if line and not line.startswith('#') and '=' in line:
-                            key, _ = line.split('=', 1)
-                            existing_env_vars[key.strip()] = True
+                            key, val = line.split('=', 1)
+                            existing_env_vars[key.strip()] = val.strip()
            except Exception as e:
                logger.warning(f"[AgentBridge] Failed to read .env file: {e}")
        
-        # Check which keys need to be migrated
-        keys_to_migrate = {}
+        # Sync config.json values into .env (add/update/remove)
+        updated = False
        for config_key, env_key in key_mapping.items():
-            # Skip if already in .env file
-            if env_key in existing_env_vars:
-                continue
-            
-            # Get value from config.json
-            value = conf().get(config_key, "")
-            if value and value.strip():  # Only migrate non-empty values
-                keys_to_migrate[env_key] = value.strip()
-        
-        # Log summary if there are keys to skip
-        if existing_env_vars:
-            logger.debug(f"[AgentBridge] {len(existing_env_vars)} env vars already in .env")
-        
-        # Write new keys to .env file
-        if keys_to_migrate:
+            raw = conf().get(config_key, "")
+            value = raw.strip() if raw else ""
+            old_value = existing_env_vars.get(env_key)
+
+            if value:
+                if old_value == value:
+                    continue
+                existing_env_vars[env_key] = value
+                os.environ[env_key] = value
+                updated = True
+            else:
+                if old_value is None:
+                    continue
+                existing_env_vars.pop(env_key, None)
+                os.environ.pop(env_key, None)
+                updated = True
+            updated = True
+
+        if updated:
            try:
-                # Ensure ~/.cow directory and .env file exist
                env_dir = os.path.dirname(env_file)
-                if not os.path.exists(env_dir):
-                    os.makedirs(env_dir, exist_ok=True)
-                if not os.path.exists(env_file):
-                    open(env_file, 'a').close()
-                
-                # Append new keys
-                with open(env_file, 'a', encoding='utf-8') as f:
-                    f.write('\n# Auto-migrated from config.json\n')
-                    for key, value in keys_to_migrate.items():
+                os.makedirs(env_dir, exist_ok=True)
+
+                with open(env_file, 'w', encoding='utf-8') as f:
+                    f.write('# Environment variables for agent\n')
+                    f.write('# Auto-managed - synced from config.json on startup\n\n')
+                    for key, value in sorted(existing_env_vars.items()):
                        f.write(f'{key}={value}\n')
-                        # Also set in current process
-                        os.environ[key] = value
-                
-                logger.info(f"[AgentBridge] Migrated {len(keys_to_migrate)} API keys from config.json to .env: {list(keys_to_migrate.keys())}")
+
+                logger.info(f"[AgentBridge] Synced API keys from config.json to .env")
            except Exception as e:
-                logger.warning(f"[AgentBridge] Failed to migrate API keys: {e}")
+                logger.warning(f"[AgentBridge] Failed to sync API keys: {e}")
    
    def _persist_messages(
        self, session_id: str, new_messages: list, channel_type: str = ""
--- a/bridge/agent_event_handler.py
+++ b/bridge/agent_event_handler.py
@@ -26,8 +26,7 @@ class AgentEventHandler:
        if context:
            self.channel = context.kwargs.get("channel") if hasattr(context, "kwargs") else None
        
-        # Track current thinking for channel output
-        self.current_thinking = ""
+        self.current_content = ""
        self.turn_number = 0
    
    def handle_event(self, event):
@@ -47,6 +46,8 @@ class AgentEventHandler:
            self._handle_message_update(data)
        elif event_type == "message_end":
            self._handle_message_end(data)
+        elif event_type == "reasoning_update":
+            pass
        elif event_type == "tool_execution_start":
            self._handle_tool_execution_start(data)
        elif event_type == "tool_execution_end":
@@ -59,30 +60,26 @@ class AgentEventHandler:
    def _handle_turn_start(self, data):
        """Handle turn start event"""
        self.turn_number = data.get("turn", 0)
-        self.has_tool_calls_in_turn = False
-        self.current_thinking = ""
+        self.current_content = ""
    
    def _handle_message_update(self, data):
-        """Handle message update event (streaming text)"""
+        """Handle message update event (streaming content text)"""
        delta = data.get("delta", "")
-        self.current_thinking += delta
+        self.current_content += delta
    
    def _handle_message_end(self, data):
        """Handle message end event"""
        tool_calls = data.get("tool_calls", [])
        
-        # Only send thinking process if followed by tool calls
        if tool_calls:
-            if self.current_thinking.strip():
-                logger.info(f"💭 {self.current_thinking.strip()[:200]}{'...' if len(self.current_thinking) > 200 else ''}")
-                # Send thinking process to channel
-                self._send_to_channel(f"{self.current_thinking.strip()}")
+            if self.current_content.strip():
+                logger.info(f"💭 {self.current_content.strip()[:200]}{'...' if len(self.current_content) > 200 else ''}")
+                self._send_to_channel(self.current_content.strip())
        else:
-            # No tool calls = final response (logged at agent_stream level)
-            if self.current_thinking.strip():
-                logger.debug(f"💬 {self.current_thinking.strip()[:200]}{'...' if len(self.current_thinking) > 200 else ''}")
+            if self.current_content.strip():
+                logger.debug(f"💬 {self.current_content.strip()[:200]}{'...' if len(self.current_content) > 200 else ''}")
        
-        self.current_thinking = ""
+        self.current_content = ""
    
    def _handle_tool_execution_start(self, data):
        """Handle tool execution start event - logged by agent_stream.py"""
--- a/bridge/agent_initializer.py
+++ b/bridge/agent_initializer.py
@@ -366,7 +366,7 @@ class AgentInitializer:

                if tool:
                    # Apply workspace config to file operation tools
-                    if tool_name in ['read', 'write', 'edit', 'bash', 'grep', 'find', 'ls', 'web_fetch']:
+                    if tool_name in ['read', 'write', 'edit', 'bash', 'grep', 'find', 'ls', 'web_fetch', 'send', 'browser']:
                        tool.config = file_config
                        tool.cwd = file_config.get("cwd", getattr(tool, 'cwd', None))
                        if 'memory_manager' in file_config:
@@ -465,8 +465,12 @@ class AgentInitializer:
                'timezone': timezone_name
            }
        
+        def get_model():
+            """Get current model name dynamically from config"""
+            return conf().get("model", "unknown")
+
        return {
-            "model": conf().get("model", "unknown"),
+            "_get_model": get_model,
            "workspace": workspace_root,
            "channel": ", ".join(conf().get("channel_type")) if isinstance(conf().get("channel_type"), list) else conf().get("channel_type", "unknown"),
            "_get_current_time": get_current_time  # Dynamic time function
@@ -486,7 +490,7 @@ class AgentInitializer:
        
        env_file = expand_path("~/.cow/.env")
        
-        # Read existing env vars
+        # Read existing env vars (key -> value)
        existing_env_vars = {}
        if os.path.exists(env_file):
            try:
@@ -494,38 +498,46 @@ class AgentInitializer:
                    for line in f:
                        line = line.strip()
                        if line and not line.startswith('#') and '=' in line:
-                            key, _ = line.split('=', 1)
-                            existing_env_vars[key.strip()] = True
+                            key, val = line.split('=', 1)
+                            existing_env_vars[key.strip()] = val.strip()
            except Exception as e:
                logger.warning(f"[AgentInitializer] Failed to read .env file: {e}")
        
-        # Check which keys need migration
-        keys_to_migrate = {}
+        # Sync config.json values into .env (add/update/remove)
+        updated = False
        for config_key, env_key in key_mapping.items():
-            if env_key in existing_env_vars:
-                continue
-            value = conf().get(config_key, "")
-            if value and value.strip():
-                keys_to_migrate[env_key] = value.strip()
-        
-        # Write new keys
-        if keys_to_migrate:
+            raw = conf().get(config_key, "")
+            value = raw.strip() if raw else ""
+            old_value = existing_env_vars.get(env_key)
+
+            if value:
+                if old_value == value:
+                    continue
+                existing_env_vars[env_key] = value
+                os.environ[env_key] = value
+                updated = True
+            else:
+                if old_value is None:
+                    continue
+                existing_env_vars.pop(env_key, None)
+                os.environ.pop(env_key, None)
+                updated = True
+
+        if updated:
            try:
                env_dir = os.path.dirname(env_file)
-                if not os.path.exists(env_dir):
-                    os.makedirs(env_dir, exist_ok=True)
-                if not os.path.exists(env_file):
-                    open(env_file, 'a').close()
-                
-                with open(env_file, 'a', encoding='utf-8') as f:
-                    f.write('\n# Auto-migrated from config.json\n')
-                    for key, value in keys_to_migrate.items():
+                os.makedirs(env_dir, exist_ok=True)
+
+                # Rewrite the entire .env file to ensure consistency
+                with open(env_file, 'w', encoding='utf-8') as f:
+                    f.write('# Environment variables for agent\n')
+                    f.write('# Auto-managed - synced from config.json on startup\n\n')
+                    for key, value in sorted(existing_env_vars.items()):
                        f.write(f'{key}={value}\n')
-                        os.environ[key] = value
-                
-                logger.info(f"[AgentInitializer] Migrated {len(keys_to_migrate)} API keys to .env: {list(keys_to_migrate.keys())}")
+
+                logger.info(f"[AgentInitializer] Synced API keys from config.json to .env")
            except Exception as e:
-                logger.warning(f"[AgentInitializer] Failed to migrate API keys: {e}")
+                logger.warning(f"[AgentInitializer] Failed to sync API keys: {e}")

    def _start_daily_flush_timer(self):
        """Start a background thread that flushes all agents' memory daily at 23:55."""
--- a/bridge/bridge.py
+++ b/bridge/bridge.py
@@ -13,7 +13,7 @@ from voice.factory import create_voice
 class Bridge(object):
    def __init__(self):
        self.btype = {
-            "chat": const.CHATGPT,
+            "chat": const.OPENAI,
            "voice_to_text": conf().get("voice_to_text", "openai"),
            "text_to_voice": conf().get("text_to_voice", "google"),
            "translate": conf().get("translate", "baidu"),
@@ -39,11 +39,8 @@ class Bridge(object):
                self.btype["chat"] = const.BAIDU
            if model_type in ["xunfei"]:
                self.btype["chat"] = const.XUNFEI
-            if model_type in [const.QWEN]:
-                self.btype["chat"] = const.QWEN
-            if model_type in [const.QWEN_TURBO, const.QWEN_PLUS, const.QWEN_MAX]:
+            if model_type in [const.QWEN, const.QWEN_TURBO, const.QWEN_PLUS, const.QWEN_MAX]:
                self.btype["chat"] = const.QWEN_DASHSCOPE
-            # Support Qwen3 and other DashScope models
            if model_type and (model_type.startswith("qwen") or model_type.startswith("qwq") or model_type.startswith("qvq")):
                self.btype["chat"] = const.QWEN_DASHSCOPE
            if model_type and model_type.startswith("gemini"):
@@ -61,6 +58,9 @@ 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
            
--- a/channel/channel_factory.py
+++ b/channel/channel_factory.py
@@ -39,6 +39,10 @@ def create_channel(channel_type) -> Channel:
    elif channel_type == const.QQ:
        from channel.qq.qq_channel import QQChannel
        ch = QQChannel()
+    elif channel_type in (const.WEIXIN, "wx"):
+        from channel.weixin.weixin_channel import WeixinChannel
+        ch = WeixinChannel()
+        channel_type = const.WEIXIN
    else:
        raise RuntimeError
    ch.channel_type = channel_type
--- a/channel/chat_channel.py
+++ b/channel/chat_channel.py
@@ -347,38 +347,30 @@ class ChatChannel(Channel):
        if media_items:
            logger.info(f"[chat_channel] Extracted {len(media_items)} media item(s) from reply")
            
-            # 先发送文本（保持原文本不变）
+            # Send text first (the frontend will embed video players via renderMarkdown).
            logger.info(f"[chat_channel] Sending text content before media: {reply.content[:100]}...")
            self._send(reply, context)
            logger.info(f"[chat_channel] Text sent, now sending {len(media_items)} media item(s)")
            
-            # 然后逐个发送媒体文件
            for i, (url, media_type) in enumerate(media_items):
                try:
-                    # 判断是本地文件还是URL
+                    # Determine whether it is a remote URL or a local file.
                    if url.startswith(('http://', 'https://')):
-                        # 网络资源
                        if media_type == 'video':
-                            # 视频使用 FILE 类型发送
                            media_reply = Reply(ReplyType.FILE, url)
                            media_reply.file_name = os.path.basename(url)
                        else:
-                            # 图片使用 IMAGE_URL 类型
                            media_reply = Reply(ReplyType.IMAGE_URL, url)
                    elif os.path.exists(url):
-                        # 本地文件
                        if media_type == 'video':
-                            # 视频使用 FILE 类型，转换为 file:// URL
                            media_reply = Reply(ReplyType.FILE, f"file://{url}")
                            media_reply.file_name = os.path.basename(url)
                        else:
-                            # 图片使用 IMAGE_URL 类型，转换为 file:// URL
                            media_reply = Reply(ReplyType.IMAGE_URL, f"file://{url}")
                    else:
                        logger.warning(f"[chat_channel] Media file not found or invalid URL: {url}")
                        continue
                    
-                    # 发送媒体文件（添加小延迟避免频率限制）
                    if i > 0:
                        time.sleep(0.5)
                    self._send(media_reply, context)
--- a/channel/feishu/feishu_channel.py
+++ b/channel/feishu/feishu_channel.py
@@ -454,7 +454,7 @@ class FeiShuChanel(ChatChannel):
        can_reply = is_group and msg and hasattr(msg, 'msg_id') and msg.msg_id

        # Build content JSON
-        content_json = json.dumps(reply_content) if content_key is None else json.dumps({content_key: reply_content})
+        content_json = json.dumps(reply_content, ensure_ascii=False) if content_key is None else json.dumps({content_key: reply_content}, ensure_ascii=False)
        logger.debug(f"[FeiShu] Sending message: msg_type={msg_type}, content={content_json[:200]}")

        if can_reply:
--- a/channel/qq/qq_channel.py
+++ b/channel/qq/qq_channel.py
@@ -23,6 +23,7 @@ from channel.qq.qq_message import QQMessage
 from common.expired_dict import ExpiredDict
 from common.log import logger
 from common.singleton import singleton
+from common.ws_client_compat import websocket_app_run_forever
 from config import conf

 # Rich media file_type constants
@@ -210,7 +211,7 @@ class QQChannel(ChatChannel):

        def run_forever():
            try:
-                self._ws.run_forever(ping_interval=0, reconnect=0)
+                websocket_app_run_forever(self._ws, ping_interval=0, reconnect=0)
            except (SystemExit, KeyboardInterrupt):
                logger.info("[QQ] WebSocket thread interrupted")
            except Exception as e:
@@ -299,7 +300,7 @@ class QQChannel(ChatChannel):
                self._send_identify()

        elif op == OP_HEARTBEAT_ACK:
-            logger.debug("[QQ] Heartbeat ACK received")
+            pass

        elif op == OP_HEARTBEAT:
            self._ws_send({"op": OP_HEARTBEAT, "d": self._last_seq})
--- a/channel/web/chat.html
+++ b/channel/web/chat.html
@@ -50,16 +50,53 @@
    (function() {
        var theme = localStorage.getItem('cow_theme') || 'dark';
        if (theme === 'dark') document.documentElement.classList.add('dark');
+        var lang = localStorage.getItem('cow_lang') || 'zh';
+        document.documentElement.setAttribute('lang', lang);
    })();
    </script>
 </head>
 <body class="h-screen overflow-hidden bg-gray-50 dark:bg-[#111111] text-slate-800 dark:text-slate-200 font-sans">
+
+    <!-- Login Overlay -->
+    <div id="login-overlay" class="fixed inset-0 z-[200] bg-gray-50 dark:bg-[#111111] flex items-center justify-center hidden">
+        <div class="w-full max-w-sm mx-4">
+            <div class="flex flex-col items-center mb-8">
+                <img src="assets/logo.jpg" alt="CowAgent" class="w-16 h-16 rounded-2xl mb-4 shadow-lg">
+                <h1 class="text-xl font-bold text-slate-800 dark:text-slate-100">CowAgent</h1>
+                <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" id="login-subtitle">请输入密码以访问控制台</p>
+            </div>
+            <form id="login-form" class="space-y-4" onsubmit="return false;">
+                <div class="relative">
+                    <input id="login-password" type="password" autocomplete="current-password"
+                           placeholder="Password"
+                           class="w-full px-4 py-3 rounded-xl border border-slate-200 dark:border-white/10
+                                  bg-white dark:bg-[#1A1A1A] text-slate-800 dark:text-slate-200
+                                  placeholder-slate-400 dark:placeholder-slate-500
+                                  focus:outline-none focus:ring-2 focus:ring-primary-400/50 focus:border-primary-400
+                                  transition-all duration-150 text-sm">
+                    <button type="button" id="login-toggle-pwd"
+                            class="absolute right-3 top-1/2 -translate-y-1/2 text-slate-400 hover:text-slate-600
+                                   dark:hover:text-slate-300 cursor-pointer transition-colors"
+                            onclick="toggleLoginPassword()">
+                        <i class="fas fa-eye text-sm"></i>
+                    </button>
+                </div>
+                <p id="login-error" class="text-sm text-red-500 hidden"></p>
+                <button id="login-btn" type="submit"
+                        class="w-full py-3 rounded-xl bg-primary-500 hover:bg-primary-600 text-white font-medium
+                               text-sm cursor-pointer transition-colors duration-150 disabled:opacity-50 disabled:cursor-not-allowed">
+                    登录
+                </button>
+            </form>
+        </div>
+    </div>
+
    <div id="app" class="flex h-screen">

        <!-- ================================================================ -->
        <!-- SIDEBAR                                                          -->
        <!-- ================================================================ -->
-        <aside id="sidebar" class="fixed inset-y-0 left-0 z-50 w-64 bg-[#0A0A0A] text-neutral-400 flex flex-col
+        <aside id="sidebar" class="fixed inset-y-0 left-0 z-50 w-52 bg-[#0A0A0A] text-neutral-400 flex flex-col
                                    transform -translate-x-full lg:relative lg:translate-x-0
                                    transition-transform duration-300 ease-in-out">
            <!-- Logo -->
@@ -67,7 +104,7 @@
                <img src="assets/logo.jpg" alt="CowAgent" class="w-8 h-8 rounded-lg flex-shrink-0">
                <div class="flex flex-col min-w-0">
                    <span class="text-white font-semibold text-sm truncate">CowAgent</span>
-                    <span class="text-neutral-500 text-xs" data-i18n="console">Console</span>
+                    <span class="text-neutral-500 text-xs" data-i18n="console">控制台</span>
                </div>
            </div>

@@ -77,13 +114,13 @@
                <div class="menu-group open" data-group="chat">
                    <button class="w-full flex items-center gap-2 px-3 py-2 text-xs font-semibold uppercase tracking-wider text-neutral-500 hover:text-neutral-300 cursor-pointer transition-colors duration-150">
                        <i class="fas fa-chevron-right text-[10px] chevron"></i>
-                        <span data-i18n="nav_chat">Chat</span>
+                        <span data-i18n="nav_chat">对话</span>
                    </button>
                    <div class="menu-group-items pl-2">
                        <a class="sidebar-item active flex items-center gap-3 px-3 py-2 rounded-lg cursor-pointer transition-all duration-150 hover:bg-white/5 hover:text-neutral-200 text-[14px]"
                           data-view="chat">
                            <i class="fas fa-message item-icon text-xs w-5 text-center"></i>
-                            <span data-i18n="menu_chat">Chat</span>
+                            <span data-i18n="menu_chat">对话</span>
                        </a>
                    </div>
                </div>
@@ -92,33 +129,38 @@
                <div class="menu-group open" data-group="manage">
                    <button class="w-full flex items-center gap-2 px-3 py-2 text-xs font-semibold uppercase tracking-wider text-neutral-500 hover:text-neutral-300 cursor-pointer transition-colors duration-150">
                        <i class="fas fa-chevron-right text-[10px] chevron"></i>
-                        <span data-i18n="nav_manage">Management</span>
+                        <span data-i18n="nav_manage">管理</span>
                    </button>
                    <div class="menu-group-items pl-2">
                        <a class="sidebar-item flex items-center gap-3 px-3 py-2 rounded-lg cursor-pointer transition-all duration-150 hover:bg-white/5 hover:text-neutral-200 text-[14px]"
                           data-view="config">
                            <i class="fas fa-sliders item-icon text-xs w-5 text-center"></i>
-                            <span data-i18n="menu_config">Config</span>
+                            <span data-i18n="menu_config">配置</span>
                        </a>
                        <a class="sidebar-item flex items-center gap-3 px-3 py-2 rounded-lg cursor-pointer transition-all duration-150 hover:bg-white/5 hover:text-neutral-200 text-[14px]"
                           data-view="skills">
                            <i class="fas fa-bolt item-icon text-xs w-5 text-center"></i>
-                            <span data-i18n="menu_skills">Skills</span>
+                            <span data-i18n="menu_skills">技能</span>
                        </a>
                        <a class="sidebar-item flex items-center gap-3 px-3 py-2 rounded-lg cursor-pointer transition-all duration-150 hover:bg-white/5 hover:text-neutral-200 text-[14px]"
                           data-view="memory">
                            <i class="fas fa-brain item-icon text-xs w-5 text-center"></i>
-                            <span data-i18n="menu_memory">Memory</span>
+                            <span data-i18n="menu_memory">记忆</span>
+                        </a>
+                        <a class="sidebar-item flex items-center gap-3 px-3 py-2 rounded-lg cursor-pointer transition-all duration-150 hover:bg-white/5 hover:text-neutral-200 text-[14px]"
+                           data-view="knowledge">
+                            <i class="fas fa-book item-icon text-xs w-5 text-center"></i>
+                            <span data-i18n="menu_knowledge">知识</span>
                        </a>
                        <a class="sidebar-item flex items-center gap-3 px-3 py-2 rounded-lg cursor-pointer transition-all duration-150 hover:bg-white/5 hover:text-neutral-200 text-[14px]"
                           data-view="channels">
                            <i class="fas fa-tower-broadcast item-icon text-xs w-5 text-center"></i>
-                            <span data-i18n="menu_channels">Channels</span>
+                            <span data-i18n="menu_channels">通道</span>
                        </a>
                        <a class="sidebar-item flex items-center gap-3 px-3 py-2 rounded-lg cursor-pointer transition-all duration-150 hover:bg-white/5 hover:text-neutral-200 text-[14px]"
                           data-view="tasks">
                            <i class="fas fa-clock item-icon text-xs w-5 text-center"></i>
-                            <span data-i18n="menu_tasks">Tasks</span>
+                            <span data-i18n="menu_tasks">定时</span>
                        </a>
                    </div>
                </div>
@@ -127,13 +169,13 @@
                <div class="menu-group open" data-group="monitor">
                    <button class="w-full flex items-center gap-2 px-3 py-2 text-xs font-semibold uppercase tracking-wider text-neutral-500 hover:text-neutral-300 cursor-pointer transition-colors duration-150">
                        <i class="fas fa-chevron-right text-[10px] chevron"></i>
-                        <span data-i18n="nav_monitor">Monitor</span>
+                        <span data-i18n="nav_monitor">监控</span>
                    </button>
                    <div class="menu-group-items pl-2">
                        <a class="sidebar-item flex items-center gap-3 px-3 py-2 rounded-lg cursor-pointer transition-all duration-150 hover:bg-white/5 hover:text-neutral-200 text-[14px]"
                           data-view="logs">
                            <i class="fas fa-terminal item-icon text-xs w-5 text-center"></i>
-                            <span data-i18n="menu_logs">Logs</span>
+                            <span data-i18n="menu_logs">日志</span>
                        </a>
                    </div>
                </div>
@@ -154,6 +196,23 @@
        <!-- Mobile Overlay -->
        <div id="sidebar-overlay" class="fixed inset-0 bg-black/50 z-40 hidden lg:hidden cursor-pointer" onclick="toggleSidebar()"></div>

+        <!-- ================================================================ -->
+        <!-- SESSION PANEL (collapsible)                                      -->
+        <!-- ================================================================ -->
+        <aside id="session-panel" class="session-panel hidden">
+            <div class="session-panel-header">
+                <span class="session-panel-title" data-i18n="session_history">历史会话</span>
+                <button class="session-panel-close" onclick="toggleSessionPanel()" title="Close">
+                    <i class="fas fa-times"></i>
+                </button>
+            </div>
+            <button class="session-panel-new" onclick="newChat()">
+                <i class="fas fa-plus"></i>
+                <span data-i18n="new_chat">新对话</span>
+            </button>
+            <div id="session-list" class="session-list"></div>
+        </aside>
+
        <!-- ================================================================ -->
        <!-- MAIN CONTENT                                                     -->
        <!-- ================================================================ -->
@@ -166,11 +225,17 @@
                    <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">
-                    <span id="breadcrumb-group" class="text-slate-400 dark:text-slate-500 truncate" data-i18n="nav_chat">Chat</span>
+                <!-- Session panel toggle -->
+                <button id="session-toggle-btn" class="p-2 rounded-lg hover:bg-slate-100 dark:hover:bg-white/10 cursor-pointer transition-colors duration-150"
+                        onclick="toggleSessionPanel()">
+                    <i class="fas fa-clock-rotate-left text-slate-500 dark:text-slate-400"></i>
+                </button>
+
+                <!-- 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">对话</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>
+                    <span id="breadcrumb-page" class="font-medium text-slate-700 dark:text-slate-200 truncate" data-i18n="menu_chat">对话</span>
                </div>

                <div class="flex-1"></div>
@@ -224,22 +289,22 @@
                    <!-- Messages -->
                    <div id="chat-messages" class="flex-1 overflow-y-auto">
                        <!-- Welcome Screen -->
-                        <div id="welcome-screen" class="flex flex-col items-center justify-center h-full px-6 py-12">
+                        <div id="welcome-screen" class="flex flex-col items-center justify-center h-full px-6 pb-16" style="padding-top: 6vh">
                            <img src="assets/logo.jpg" alt="CowAgent" class="w-16 h-16 rounded-2xl mb-6 shadow-lg shadow-primary-500/20">
                            <h1 id="welcome-title" class="text-2xl font-bold text-slate-800 dark:text-slate-100 mb-3">CowAgent</h1>
                            <p id="welcome-subtitle" class="text-slate-500 dark:text-slate-400 text-center max-w-lg mb-10 leading-relaxed"
-                               data-i18n-html="welcome_subtitle">I can help you answer questions, manage your computer, create and execute skills,<br>and keep growing through long-term memory.</p>
+                               data-i18n-html="welcome_subtitle">我可以帮你解答问题、管理计算机、创造和执行技能，并通过<br>长期记忆和知识库不断成长</p>

-                            <div class="grid grid-cols-1 sm:grid-cols-3 gap-4 w-full max-w-2xl">
+                            <div class="grid grid-cols-2 sm:grid-cols-3 gap-3 w-full max-w-2xl">
                                <div class="example-card group bg-white dark:bg-[#1A1A1A] border border-slate-200 dark:border-white/10 rounded-xl p-4
                                            cursor-pointer hover:border-primary-300 dark:hover:border-primary-600 hover:shadow-md transition-all duration-200">
                                    <div class="flex items-center gap-2 mb-2">
                                        <div class="w-7 h-7 rounded-lg bg-blue-50 dark:bg-blue-900/30 flex items-center justify-center">
                                            <i class="fas fa-folder-open text-blue-500 text-xs"></i>
                                        </div>
-                                        <span class="font-medium text-sm text-slate-700 dark:text-slate-200" data-i18n="example_sys_title">System</span>
+                                        <span class="font-medium text-sm text-slate-700 dark:text-slate-200" data-i18n="example_sys_title">系统管理</span>
                                    </div>
-                                    <p class="text-sm text-slate-500 dark:text-slate-400 leading-relaxed" data-i18n="example_sys_text">Show me the files in the workspace</p>
+                                    <p class="text-sm text-slate-500 dark:text-slate-400 leading-relaxed" data-i18n="example_sys_text">查看工作空间里有哪些文件</p>
                                </div>
                                <div class="example-card group bg-white dark:bg-[#1A1A1A] border border-slate-200 dark:border-white/10 rounded-xl p-4
                                            cursor-pointer hover:border-primary-300 dark:hover:border-primary-600 hover:shadow-md transition-all duration-200">
@@ -247,9 +312,9 @@
                                        <div class="w-7 h-7 rounded-lg bg-amber-50 dark:bg-amber-900/30 flex items-center justify-center">
                                            <i class="fas fa-clock text-amber-500 text-xs"></i>
                                        </div>
-                                        <span class="font-medium text-sm text-slate-700 dark:text-slate-200" data-i18n="example_task_title">Smart Task</span>
+                                        <span class="font-medium text-sm text-slate-700 dark:text-slate-200" data-i18n="example_task_title">定时任务</span>
                                    </div>
-                                    <p class="text-sm text-slate-500 dark:text-slate-400 leading-relaxed" data-i18n="example_task_text">Remind me to check the server in 5 minutes</p>
+                                    <p class="text-sm text-slate-500 dark:text-slate-400 leading-relaxed" data-i18n="example_task_text">1分钟后提醒我检查服务器</p>
                                </div>
                                <div class="example-card group bg-white dark:bg-[#1A1A1A] border border-slate-200 dark:border-white/10 rounded-xl p-4
                                            cursor-pointer hover:border-primary-300 dark:hover:border-primary-600 hover:shadow-md transition-all duration-200">
@@ -257,9 +322,40 @@
                                        <div class="w-7 h-7 rounded-lg bg-emerald-50 dark:bg-emerald-900/30 flex items-center justify-center">
                                            <i class="fas fa-code text-emerald-500 text-xs"></i>
                                        </div>
-                                        <span class="font-medium text-sm text-slate-700 dark:text-slate-200" data-i18n="example_code_title">Coding</span>
+                                        <span class="font-medium text-sm text-slate-700 dark:text-slate-200" data-i18n="example_code_title">编程助手</span>
                                    </div>
-                                    <p class="text-sm text-slate-500 dark:text-slate-400 leading-relaxed" data-i18n="example_code_text">Write a Python web scraper script</p>
+                                    <p class="text-sm text-slate-500 dark:text-slate-400 leading-relaxed" data-i18n="example_code_text">搜索AI资讯并生成可视化网页报告</p>
+                                </div>
+                                <div class="example-card group bg-white dark:bg-[#1A1A1A] border border-slate-200 dark:border-white/10 rounded-xl p-4
+                                            cursor-pointer hover:border-primary-300 dark:hover:border-primary-600 hover:shadow-md transition-all duration-200">
+                                    <div class="flex items-center gap-2 mb-2">
+                                        <div class="w-7 h-7 rounded-lg bg-violet-50 dark:bg-violet-900/30 flex items-center justify-center">
+                                            <i class="fas fa-book text-violet-500 text-xs"></i>
+                                        </div>
+                                        <span class="font-medium text-sm text-slate-700 dark:text-slate-200" data-i18n="example_knowledge_title">知识库</span>
+                                    </div>
+                                    <p class="text-sm text-slate-500 dark:text-slate-400 leading-relaxed" data-i18n="example_knowledge_text">查看知识库当前文档情况</p>
+                                </div>
+                                <div class="example-card group bg-white dark:bg-[#1A1A1A] border border-slate-200 dark:border-white/10 rounded-xl p-4
+                                            cursor-pointer hover:border-primary-300 dark:hover:border-primary-600 hover:shadow-md transition-all duration-200">
+                                    <div class="flex items-center gap-2 mb-2">
+                                        <div class="w-7 h-7 rounded-lg bg-rose-50 dark:bg-rose-900/30 flex items-center justify-center">
+                                            <i class="fas fa-puzzle-piece text-rose-500 text-xs"></i>
+                                        </div>
+                                        <span class="font-medium text-sm text-slate-700 dark:text-slate-200" data-i18n="example_skill_title">技能系统</span>
+                                    </div>
+                                    <p class="text-sm text-slate-500 dark:text-slate-400 leading-relaxed" data-i18n="example_skill_text">查看所有支持的工具和技能</p>
+                                </div>
+                                <div class="example-card group bg-white dark:bg-[#1A1A1A] border border-slate-200 dark:border-white/10 rounded-xl p-4
+                                            cursor-pointer hover:border-primary-300 dark:hover:border-primary-600 hover:shadow-md transition-all duration-200"
+                                     data-send="/help">
+                                    <div class="flex items-center gap-2 mb-2">
+                                        <div class="w-7 h-7 rounded-lg bg-slate-100 dark:bg-slate-800 flex items-center justify-center">
+                                            <i class="fas fa-terminal text-slate-500 text-xs"></i>
+                                        </div>
+                                        <span class="font-medium text-sm text-slate-700 dark:text-slate-200" data-i18n="example_web_title">指令中心</span>
+                                    </div>
+                                    <p class="text-sm text-slate-500 dark:text-slate-400 leading-relaxed" data-i18n="example_web_text">查看全部命令</p>
                                </div>
                            </div>
                        </div>
@@ -267,30 +363,51 @@

                    <!-- Chat Input -->
                    <div class="flex-shrink-0 border-t border-slate-200 dark:border-white/10 bg-white dark:bg-[#1A1A1A] px-4 py-3">
-                        <div class="max-w-3xl mx-auto flex items-center gap-2">
-                            <button id="new-chat-btn" class="flex-shrink-0 w-10 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
-                                                             cursor-pointer transition-colors duration-150" title="New Chat"
-                                    onclick="newChat()">
-                                <i class="fas fa-plus text-base"></i>
-                            </button>
-                            <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
-                                             placeholder:text-slate-400 dark:placeholder:text-slate-500
-                                             focus:outline-none focus:ring-0 focus:border-primary-600
-                                             text-sm leading-relaxed"
-                                      rows="1"
-                                      data-i18n-placeholder="input_placeholder"
-                                      placeholder="Type a message..."></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
-                                           disabled:bg-slate-300 dark:disabled:bg-slate-600
-                                           disabled:cursor-not-allowed cursor-pointer transition-colors duration-150"
-                                    disabled onclick="sendMessage()">
-                                <i class="fas fa-paper-plane text-sm"></i>
-                            </button>
+                        <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 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
+                                                                     cursor-pointer transition-colors duration-150"
+                                            onclick="newChat()">
+                                        <i class="fas fa-plus text-base"></i>
+                                    </button>
+                                    <button id="clear-context-btn" class="w-9 h-10 flex items-center justify-center rounded-lg
+                                                                          text-slate-400 hover:text-amber-500 hover:bg-amber-50 dark:hover:bg-amber-900/20
+                                                                          cursor-pointer transition-colors duration-150"
+                                            onclick="clearContext()">
+                                        <i class="fas fa-trash-can text-base"></i>
+                                    </button>
+                                    <button id="attach-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
+                                                                   cursor-pointer transition-colors duration-150"
+                                            onclick="document.getElementById('file-input').click()">
+                                        <i class="fas fa-paperclip text-base"></i>
+                                    </button>
+                                </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
+                                                 placeholder:text-slate-400 dark:placeholder:text-slate-500
+                                                 focus:outline-none focus:ring-0 focus:border-primary-600
+                                                 text-sm leading-relaxed"
+                                          rows="1"
+                                          data-i18n-placeholder="input_placeholder"
+                                          placeholder="输入消息，或输入 / 使用指令"></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
+                                               disabled:bg-slate-300 dark:disabled:bg-slate-600
+                                               disabled:cursor-not-allowed cursor-pointer transition-colors duration-150"
+                                        disabled onclick="sendMessage()">
+                                    <i class="fas fa-paper-plane text-sm"></i>
+                                </button>
+                            </div>
                        </div>
                    </div>
                </div>
@@ -303,8 +420,8 @@
                        <div class="max-w-4xl mx-auto">
                            <div class="flex items-center justify-between mb-6">
                                <div>
-                                    <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="config_title">Configuration</h2>
-                                    <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="config_desc">Manage model and agent settings</p>
+                                    <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="config_title">配置管理</h2>
+                                    <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="config_desc">管理模型和 Agent 配置</p>
                                </div>
                            </div>
                            <div class="grid gap-6">
@@ -315,12 +432,12 @@
                                        <div class="w-9 h-9 rounded-lg bg-primary-50 dark:bg-primary-900/30 flex items-center justify-center">
                                            <i class="fas fa-microchip text-primary-500 text-sm"></i>
                                        </div>
-                                        <h3 class="font-semibold text-slate-800 dark:text-slate-100" data-i18n="config_model">Model Configuration</h3>
+                                        <h3 class="font-semibold text-slate-800 dark:text-slate-100" data-i18n="config_model">模型配置</h3>
                                    </div>
                                    <div class="space-y-5">
                                        <!-- Provider -->
                                        <div>
-                                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5" data-i18n="config_provider">Provider</label>
+                                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5" data-i18n="config_provider">模型厂商</label>
                                            <div id="cfg-provider" class="cfg-dropdown" tabindex="0">
                                                <div class="cfg-dropdown-selected">
                                                    <span class="cfg-dropdown-text">--</span>
@@ -331,7 +448,7 @@
                                        </div>
                                        <!-- Model -->
                                        <div>
-                                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5" data-i18n="config_model_name">Model</label>
+                                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5" data-i18n="config_model_name">模型</label>
                                            <div id="cfg-model-select" class="cfg-dropdown" tabindex="0">
                                                <div class="cfg-dropdown-selected">
                                                    <span class="cfg-dropdown-text">--</span>
@@ -344,7 +461,7 @@
                                                       class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600
                                                              bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100
                                                              focus:outline-none focus:border-primary-500 font-mono transition-colors"
-                                                       data-i18n-placeholder="config_custom_model_hint" placeholder="Enter custom model name">
+                                                       data-i18n-placeholder="config_custom_model_hint" placeholder="输入自定义模型名称">
                                            </div>
                                        </div>
                                        <!-- API Key -->
@@ -379,7 +496,7 @@
                                            <button id="cfg-model-save"
                                                    class="px-4 py-2 rounded-lg bg-primary-500 hover:bg-primary-600 text-white text-sm font-medium
                                                           cursor-pointer transition-colors duration-150 disabled:opacity-50 disabled:cursor-not-allowed"
-                                                    onclick="saveModelConfig()" data-i18n="config_save">Save</button>
+                                                    onclick="saveModelConfig()" data-i18n="config_save">保存</button>
                                        </div>
                                    </div>
                                </div>
@@ -390,25 +507,34 @@
                                        <div class="w-9 h-9 rounded-lg bg-emerald-50 dark:bg-emerald-900/30 flex items-center justify-center">
                                            <i class="fas fa-robot text-emerald-500 text-sm"></i>
                                        </div>
-                                        <h3 class="font-semibold text-slate-800 dark:text-slate-100" data-i18n="config_agent">Agent Configuration</h3>
+                                        <h3 class="font-semibold text-slate-800 dark:text-slate-100" data-i18n="config_agent">Agent 配置</h3>
                                    </div>
                                    <div class="space-y-4">
                                        <div>
-                                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5" data-i18n="config_max_tokens">Max Context Tokens</label>
+                                            <label class="flex items-center gap-1.5 text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5">
+                                                <span data-i18n="config_max_tokens">最大上下文 Token</span>
+                                                <span class="cfg-tip" data-tip-key="config_max_tokens_hint"><i class="fas fa-circle-question"></i></span>
+                                            </label>
                                            <input id="cfg-max-tokens" type="number" min="1000" max="200000" step="1000"
                                                   class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600
                                                          bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100
                                                          focus:outline-none focus:border-primary-500 font-mono transition-colors">
                                        </div>
                                        <div>
-                                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5" data-i18n="config_max_turns">Max Context Turns</label>
+                                            <label class="flex items-center gap-1.5 text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5">
+                                                <span data-i18n="config_max_turns">最大记忆轮次</span>
+                                                <span class="cfg-tip" data-tip-key="config_max_turns_hint"><i class="fas fa-circle-question"></i></span>
+                                            </label>
                                            <input id="cfg-max-turns" type="number" min="1" max="100" step="1"
                                                   class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600
                                                          bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100
                                                          focus:outline-none focus:border-primary-500 font-mono transition-colors">
                                        </div>
                                        <div>
-                                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5" data-i18n="config_max_steps">Max Steps</label>
+                                            <label class="flex items-center gap-1.5 text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5">
+                                                <span data-i18n="config_max_steps">最大执行步数</span>
+                                                <span class="cfg-tip" data-tip-key="config_max_steps_hint"><i class="fas fa-circle-question"></i></span>
+                                            </label>
                                            <input id="cfg-max-steps" type="number" min="1" max="50" step="1"
                                                   class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600
                                                          bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100
@@ -419,7 +545,36 @@
                                            <button id="cfg-agent-save"
                                                    class="px-4 py-2 rounded-lg bg-primary-500 hover:bg-primary-600 text-white text-sm font-medium
                                                           cursor-pointer transition-colors duration-150 disabled:opacity-50 disabled:cursor-not-allowed"
-                                                    onclick="saveAgentConfig()" data-i18n="config_save">Save</button>
+                                                    onclick="saveAgentConfig()" data-i18n="config_save">保存</button>
+                                        </div>
+                                    </div>
+                                </div>
+
+                                <!-- Security Config Card -->
+                                <div class="bg-white dark:bg-[#1A1A1A] rounded-xl border border-slate-200 dark:border-white/10 p-6">
+                                    <div class="flex items-center gap-3 mb-5">
+                                        <div class="w-9 h-9 rounded-lg bg-amber-50 dark:bg-amber-900/30 flex items-center justify-center">
+                                            <i class="fas fa-lock text-amber-500 text-sm"></i>
+                                        </div>
+                                        <h3 class="font-semibold text-slate-800 dark:text-slate-100" data-i18n="config_security">安全设置</h3>
+                                    </div>
+                                    <div class="space-y-4">
+                                        <div>
+                                            <label class="block text-sm font-medium text-slate-600 dark:text-slate-400 mb-1.5" data-i18n="config_password">访问密码</label>
+                                            <input id="cfg-password" type="password" autocomplete="new-password"
+                                                   class="w-full px-3 py-2 rounded-lg border border-slate-200 dark:border-slate-600
+                                                          bg-slate-50 dark:bg-white/5 text-sm text-slate-800 dark:text-slate-100
+                                                          focus:outline-none focus:border-primary-500 font-mono transition-colors
+                                                          cfg-key-masked"
+                                                   data-masked="1">
+                                            <p class="text-xs text-slate-400 dark:text-slate-500 mt-1.5" data-i18n="config_password_hint">留空则不启用密码保护</p>
+                                        </div>
+                                        <div class="flex items-center justify-end gap-3 pt-1">
+                                            <span id="cfg-password-status" class="text-xs text-primary-500 opacity-0 transition-opacity duration-300"></span>
+                                            <button id="cfg-password-save"
+                                                    class="px-4 py-2 rounded-lg bg-primary-500 hover:bg-primary-600 text-white text-sm font-medium
+                                                           cursor-pointer transition-colors duration-150 disabled:opacity-50 disabled:cursor-not-allowed"
+                                                    onclick="savePasswordConfig()" data-i18n="config_save">保存</button>
                                        </div>
                                    </div>
                                </div>
@@ -437,20 +592,25 @@
                        <div class="max-w-4xl mx-auto">
                            <div class="flex items-center justify-between mb-6">
                                <div>
-                                    <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="skills_title">Skills</h2>
-                                    <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="skills_desc">View, enable, or disable agent skills</p>
+                                    <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="skills_title">技能管理</h2>
+                                    <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="skills_desc">查看、启用或禁用 Agent 技能</p>
                                </div>
+                                <a href="https://skills.cowagent.ai/" target="_blank"
+                                   class="inline-flex items-center gap-1.5 px-3 py-1.5 rounded-lg text-xs font-medium text-primary-500 bg-primary-50 dark:bg-primary-900/20 hover:bg-primary-100 dark:hover:bg-primary-900/30 transition-colors">
+                                    <i class="fas fa-puzzle-piece text-[10px]"></i>
+                                    <span data-i18n="skills_hub_btn">探索技能广场</span>
+                                </a>
                            </div>

                            <!-- Built-in Tools Section -->
                            <div class="mb-8">
                                <div class="flex items-center gap-2 mb-3">
-                                    <span class="text-xs font-semibold uppercase tracking-wider text-slate-400 dark:text-slate-500" data-i18n="tools_section_title">Built-in Tools</span>
+                                    <span class="text-xs font-semibold uppercase tracking-wider text-slate-400 dark:text-slate-500" data-i18n="tools_section_title">内置工具</span>
                                    <span id="tools-count-badge" class="hidden px-2 py-0.5 rounded-full text-xs bg-slate-100 dark:bg-white/10 text-slate-500 dark:text-slate-400"></span>
                                </div>
                                <div id="tools-empty" class="flex items-center gap-2 py-4 text-slate-400 dark:text-slate-500 text-sm">
                                    <i class="fas fa-spinner fa-spin text-xs"></i>
-                                    <span data-i18n="tools_loading">Loading tools...</span>
+                                    <span data-i18n="tools_loading">加载工具中...</span>
                                </div>
                                <div id="tools-list" class="grid gap-3 sm:grid-cols-2 hidden"></div>
                            </div>
@@ -458,15 +618,15 @@
                            <!-- Skills Section -->
                            <div>
                                <div class="flex items-center gap-2 mb-3">
-                                    <span class="text-xs font-semibold uppercase tracking-wider text-slate-400 dark:text-slate-500" data-i18n="skills_section_title">Skills</span>
+                                    <span class="text-xs font-semibold uppercase tracking-wider text-slate-400 dark:text-slate-500" data-i18n="skills_section_title">技能</span>
                                    <span id="skills-count-badge" class="hidden px-2 py-0.5 rounded-full text-xs bg-slate-100 dark:bg-white/10 text-slate-500 dark:text-slate-400"></span>
                                </div>
                                <div id="skills-empty" class="flex flex-col items-center justify-center py-12">
                                    <div class="w-14 h-14 rounded-2xl bg-amber-50 dark:bg-amber-900/20 flex items-center justify-center mb-3">
                                        <i class="fas fa-bolt text-amber-400 text-lg"></i>
                                    </div>
-                                    <p class="text-slate-500 dark:text-slate-400 font-medium" data-i18n="skills_loading">Loading skills...</p>
-                                    <p class="text-sm text-slate-400 dark:text-slate-500 mt-1" data-i18n="skills_loading_desc">Skills will be displayed here after loading</p>
+                                    <p class="text-slate-500 dark:text-slate-400 font-medium" data-i18n="skills_loading">加载技能中...</p>
+                                    <p class="text-sm text-slate-400 dark:text-slate-500 mt-1" data-i18n="skills_loading_desc">技能加载后将显示在此处</p>
                                </div>
                                <div id="skills-list" class="grid gap-4 sm:grid-cols-2"></div>
                            </div>
@@ -485,26 +645,26 @@
                            <div id="memory-panel-list">
                                <div class="flex items-center justify-between mb-6">
                                    <div>
-                                        <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="memory_title">Memory</h2>
-                                        <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="memory_desc">View agent memory files and contents</p>
+                                        <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="memory_title">记忆管理</h2>
+                                        <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="memory_desc">查看 Agent 记忆文件和内容</p>
                                    </div>
                                </div>
                                <div id="memory-empty" class="flex flex-col items-center justify-center py-20">
                                    <div class="w-16 h-16 rounded-2xl bg-purple-50 dark:bg-purple-900/20 flex items-center justify-center mb-4">
                                        <i class="fas fa-brain text-purple-400 text-xl"></i>
                                    </div>
-                                    <p class="text-slate-500 dark:text-slate-400 font-medium" data-i18n="memory_loading">Loading memory files...</p>
-                                    <p class="text-sm text-slate-400 dark:text-slate-500 mt-1" data-i18n="memory_loading_desc">Memory files will be displayed here</p>
+                                    <p class="text-slate-500 dark:text-slate-400 font-medium" data-i18n="memory_loading">加载记忆文件中...</p>
+                                    <p class="text-sm text-slate-400 dark:text-slate-500 mt-1" data-i18n="memory_loading_desc">记忆文件将显示在此处</p>
                                </div>
                                <div id="memory-list" class="hidden">
                                    <div class="bg-white dark:bg-[#1A1A1A] rounded-xl border border-slate-200 dark:border-white/10 overflow-hidden">
                                        <table class="w-full">
                                            <thead>
                                                <tr class="border-b border-slate-200 dark:border-white/10">
-                                                    <th class="text-left px-4 py-3 text-xs font-semibold uppercase tracking-wider text-slate-500 dark:text-slate-400" data-i18n="memory_col_name">Filename</th>
-                                                    <th class="text-left px-4 py-3 text-xs font-semibold uppercase tracking-wider text-slate-500 dark:text-slate-400" data-i18n="memory_col_type">Type</th>
-                                                    <th class="text-left px-4 py-3 text-xs font-semibold uppercase tracking-wider text-slate-500 dark:text-slate-400" data-i18n="memory_col_size">Size</th>
-                                                    <th class="text-left px-4 py-3 text-xs font-semibold uppercase tracking-wider text-slate-500 dark:text-slate-400" data-i18n="memory_col_updated">Updated</th>
+                                                    <th class="text-left px-4 py-3 text-xs font-semibold uppercase tracking-wider text-slate-500 dark:text-slate-400" data-i18n="memory_col_name">文件名</th>
+                                                    <th class="text-left px-4 py-3 text-xs font-semibold uppercase tracking-wider text-slate-500 dark:text-slate-400" data-i18n="memory_col_type">类型</th>
+                                                    <th class="text-left px-4 py-3 text-xs font-semibold uppercase tracking-wider text-slate-500 dark:text-slate-400" data-i18n="memory_col_size">大小</th>
+                                                    <th class="text-left px-4 py-3 text-xs font-semibold uppercase tracking-wider text-slate-500 dark:text-slate-400" data-i18n="memory_col_updated">更新时间</th>
                                                </tr>
                                            </thead>
                                            <tbody id="memory-table-body"></tbody>
@@ -522,7 +682,7 @@
                                                   text-slate-500 dark:text-slate-400 hover:bg-slate-100 dark:hover:bg-white/10
                                                   border border-slate-200 dark:border-white/10 transition-colors cursor-pointer">
                                        <i class="fas fa-arrow-left text-xs"></i>
-                                        <span data-i18n="memory_back">Back</span>
+                                        <span data-i18n="memory_back">返回列表</span>
                                    </button>
                                    <h2 id="memory-viewer-title"
                                        class="text-base font-semibold text-slate-800 dark:text-slate-100 font-mono truncate"></h2>
@@ -538,6 +698,106 @@
                    </div>
                </div>

+                <!-- ====================================================== -->
+                <!-- VIEW: Knowledge                                         -->
+                <!-- ====================================================== -->
+                <div id="view-knowledge" class="view">
+                    <div class="flex-1 overflow-y-auto p-4 md:p-8 lg:p-10">
+                        <div class="w-full max-w-[1600px] mx-auto">
+
+                            <!-- Header -->
+                            <div class="flex flex-col sm:flex-row sm:items-center justify-between gap-3 mb-4 md:mb-6">
+                                <div>
+                                    <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="knowledge_title">知识库</h2>
+                                    <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="knowledge_desc">浏览和探索你的知识库</p>
+                                </div>
+                                <div class="flex items-center gap-2">
+                                    <span id="knowledge-stats" class="text-xs text-slate-400 dark:text-slate-500 hidden sm:inline"></span>
+                                    <div class="flex items-center bg-slate-100 dark:bg-white/10 rounded-lg p-0.5">
+                                        <button id="knowledge-tab-docs" onclick="switchKnowledgeTab('docs')"
+                                                class="knowledge-tab px-3 py-1.5 rounded-md text-xs font-medium cursor-pointer transition-colors duration-150 active">
+                                            <i class="fas fa-folder-tree mr-1.5"></i><span data-i18n="knowledge_tab_docs">文档</span>
+                                        </button>
+                                        <button id="knowledge-tab-graph" onclick="switchKnowledgeTab('graph')"
+                                                class="knowledge-tab px-3 py-1.5 rounded-md text-xs font-medium cursor-pointer transition-colors duration-150">
+                                            <i class="fas fa-diagram-project mr-1.5"></i><span data-i18n="knowledge_tab_graph">图谱</span>
+                                        </button>
+                                    </div>
+                                </div>
+                            </div>
+
+                            <!-- Empty state -->
+                            <div id="knowledge-empty" class="flex flex-col items-center justify-center py-20">
+                                <div class="w-16 h-16 rounded-2xl bg-emerald-50 dark:bg-emerald-900/20 flex items-center justify-center mb-4">
+                                    <i class="fas fa-book text-emerald-400 text-xl"></i>
+                                </div>
+                                <p class="text-slate-500 dark:text-slate-400 font-medium" data-i18n="knowledge_loading">加载知识库中...</p>
+                                <p class="text-sm text-slate-400 dark:text-slate-500 mt-1" data-i18n="knowledge_loading_desc">知识页面将显示在这里</p>
+                                <div id="knowledge-empty-guide" class="hidden mt-6 max-w-sm text-center">
+                                    <p class="text-sm text-slate-500 dark:text-slate-400 mb-4" data-i18n="knowledge_empty_guide">在对话中发送文档、链接或主题给 Agent，它会自动整理到你的知识库中。</p>
+                                    <button onclick="navigateTo('chat')"
+                                            class="inline-flex items-center gap-2 px-4 py-2 rounded-lg bg-primary-500 hover:bg-primary-600
+                                                   text-white text-sm font-medium cursor-pointer transition-colors duration-150">
+                                        <i class="fas fa-message text-xs"></i>
+                                        <span data-i18n="knowledge_go_chat">开始对话</span>
+                                    </button>
+                                </div>
+                            </div>
+
+                            <!-- Documents panel -->
+                            <div id="knowledge-panel-docs" class="hidden">
+                                <div class="flex flex-col md:flex-row gap-4 md:gap-6" style="min-height: calc(100vh - 220px)">
+                                    <!-- File tree -->
+                                    <div id="knowledge-sidebar" class="w-full md:w-72 lg:w-80 flex-shrink-0">
+                                        <div class="bg-white dark:bg-[#1A1A1A] rounded-xl border border-slate-200 dark:border-white/10 overflow-hidden">
+                                            <div class="px-4 py-3 border-b border-slate-200 dark:border-white/10">
+                                                <div class="relative">
+                                                    <i class="fas fa-search absolute left-3 top-1/2 -translate-y-1/2 text-slate-400 text-xs"></i>
+                                                    <input id="knowledge-search" type="text" placeholder="Search..."
+                                                           class="w-full pl-8 pr-3 py-1.5 text-xs bg-slate-50 dark:bg-white/5 border border-slate-200 dark:border-white/10 rounded-lg text-slate-700 dark:text-slate-200 placeholder-slate-400 dark:placeholder-slate-500 focus:outline-none focus:ring-1 focus:ring-primary-400/50"
+                                                           oninput="filterKnowledgeTree(this.value)">
+                                                </div>
+                                            </div>
+                                            <div id="knowledge-tree" class="p-2 overflow-y-auto max-h-[50vh] md:max-h-[calc(100vh-300px)]"></div>
+                                        </div>
+                                    </div>
+                                    <!-- Content viewer -->
+                                    <div class="flex-1 min-w-0">
+                                        <div id="knowledge-content-placeholder"
+                                             class="flex flex-col items-center justify-center py-20 text-slate-400 dark:text-slate-500">
+                                            <i class="fas fa-file-lines text-3xl mb-3 opacity-40"></i>
+                                            <p class="text-sm" data-i18n="knowledge_select_hint">选择一个文档查看</p>
+                                        </div>
+                                        <div id="knowledge-content-viewer" class="hidden">
+                                            <div class="bg-white dark:bg-[#1A1A1A] rounded-xl border border-slate-200 dark:border-white/10 overflow-hidden">
+                                                <div class="flex items-center gap-3 px-4 md:px-5 py-3 border-b border-slate-200 dark:border-white/10">
+                                                    <button onclick="knowledgeMobileBack()" class="md:hidden p-1 -ml-1 text-slate-400 hover:text-slate-600 dark:hover:text-slate-300 cursor-pointer">
+                                                        <i class="fas fa-arrow-left text-xs"></i>
+                                                    </button>
+                                                    <i class="fas fa-file-lines text-slate-400 text-sm hidden md:inline"></i>
+                                                    <span id="knowledge-viewer-title" class="text-sm font-medium text-slate-700 dark:text-slate-200 truncate"></span>
+                                                    <span id="knowledge-viewer-path" class="text-xs text-slate-400 dark:text-slate-500 ml-auto font-mono truncate hidden md:inline"></span>
+                                                </div>
+                                                <div id="knowledge-viewer-body"
+                                                     class="p-4 md:p-5 overflow-y-auto text-sm msg-content text-slate-700 dark:text-slate-200"
+                                                     style="max-height: calc(100vh - 280px)"></div>
+                                            </div>
+                                        </div>
+                                    </div>
+                                </div>
+                            </div>
+
+                            <!-- Graph panel -->
+                            <div id="knowledge-panel-graph" class="hidden">
+                                <div class="bg-white dark:bg-[#1A1A1A] rounded-xl border border-slate-200 dark:border-white/10 overflow-hidden">
+                                    <div id="knowledge-graph-container" class="w-full h-[60vh] md:h-[calc(100vh-220px)]"></div>
+                                </div>
+                            </div>
+
+                        </div>
+                    </div>
+                </div>
+
                <!-- ====================================================== -->
                <!-- VIEW: Channels                                          -->
                <!-- ====================================================== -->
@@ -546,14 +806,14 @@
                        <div class="max-w-4xl mx-auto">
                            <div class="flex items-center justify-between mb-6">
                                <div>
-                                    <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="channels_title">Channels</h2>
-                                    <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="channels_desc">View and manage messaging channels</p>
+                                    <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="channels_title">通道管理</h2>
+                                    <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="channels_desc">管理已接入的消息通道</p>
                                </div>
                                <button id="add-channel-btn" onclick="openAddChannelPanel()"
                                        class="flex items-center gap-2 px-4 py-2 rounded-lg bg-primary-500 hover:bg-primary-600
                                               text-white text-sm font-medium cursor-pointer transition-colors duration-150">
                                    <i class="fas fa-plus text-xs"></i>
-                                    <span data-i18n="channels_add">Connect</span>
+                                    <span data-i18n="channels_add">接入通道</span>
                                </button>
                            </div>
                            <div id="channels-content" class="grid gap-4"></div>
@@ -570,8 +830,8 @@
                        <div class="max-w-4xl mx-auto">
                            <div class="flex items-center justify-between mb-6">
                                <div>
-                                    <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="tasks_title">Scheduled Tasks</h2>
-                                    <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="tasks_desc">View and manage scheduled tasks</p>
+                                    <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="tasks_title">定时任务</h2>
+                                    <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="tasks_desc">查看和管理定时任务</p>
                                </div>
                            </div>
                            <div id="tasks-empty" class="flex flex-col items-center justify-center py-20">
@@ -593,8 +853,8 @@
                        <div class="max-w-5xl mx-auto">
                            <div class="flex items-center justify-between mb-6">
                                <div>
-                                    <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="logs_title">Logs</h2>
-                                    <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="logs_desc">Real-time log output (run.log)</p>
+                                    <h2 class="text-xl font-bold text-slate-800 dark:text-slate-100" data-i18n="logs_title">日志</h2>
+                                    <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="logs_desc">实时日志输出 (run.log)</p>
                                </div>
                            </div>
                            <!-- Log Terminal -->
@@ -609,11 +869,11 @@
                                    <div class="flex-1"></div>
                                    <div class="flex items-center gap-1.5">
                                        <span class="w-2 h-2 rounded-full bg-emerald-500 animate-pulse"></span>
-                                        <span class="text-xs text-slate-500" data-i18n="logs_live">Live</span>
+                                        <span class="text-xs text-slate-500" data-i18n="logs_live">实时</span>
                                    </div>
                                </div>
                                <div id="log-output" class="p-4 overflow-y-auto font-mono text-xs leading-relaxed text-slate-300 whitespace-pre-wrap break-all" style="height: calc(100vh - 272px)">
-                                    <p class="text-slate-500" data-i18n="logs_coming_msg">Log streaming will be available here. Connects to run.log for real-time output similar to tail -f.</p>
+                                    <p class="text-slate-500" data-i18n="logs_coming_msg">日志流即将在此提供。将连接 run.log 实现类似 tail -f 的实时输出。</p>
                                </div>
                            </div>
                        </div>
@@ -650,6 +910,7 @@
        </div>
    </div>

+    <script src="https://cdn.jsdelivr.net/npm/d3@7/dist/d3.min.js"></script>
    <script src="assets/js/console.js"></script>
 </body>
 </html>
--- a/channel/web/static/css/console.css
+++ b/channel/web/static/css/console.css
@@ -17,6 +17,45 @@
 .dark ::-webkit-scrollbar-thumb { background: #475569; }
 .dark ::-webkit-scrollbar-thumb:hover { background: #64748b; }

+/* Generic Tooltip (via data-tooltip attribute) */
+[data-tooltip] {
+    position: relative;
+}
+[data-tooltip]::after {
+    content: attr(data-tooltip);
+    position: absolute;
+    left: 50%;
+    bottom: calc(100% + 8px);
+    transform: translateX(-50%);
+    padding: 5px 10px;
+    border-radius: 6px;
+    font-size: 12px;
+    font-weight: 400;
+    line-height: 1.4;
+    white-space: nowrap;
+    background: #1e293b;
+    color: #e2e8f0;
+    box-shadow: 0 4px 12px rgba(0, 0, 0, 0.15);
+    opacity: 0;
+    pointer-events: none;
+    transition: opacity 0.15s ease;
+    z-index: 100;
+}
+[data-tooltip-pos="bottom"]::after {
+    bottom: auto;
+    top: calc(100% + 8px);
+}
+.dark [data-tooltip]::after {
+    background: #334155;
+    color: #f1f5f9;
+}
+[data-tooltip]:hover::after {
+    opacity: 1;
+}
+[data-tooltip=""]:hover::after {
+    display: none;
+}
+
 /* Sidebar */
 .sidebar-item.active {
    background: rgba(255, 255, 255, 0.08);
@@ -24,9 +63,300 @@
 }
 .sidebar-item.active .item-icon { color: #4ABE6E; }

+/* Session Panel */
+.session-panel {
+    width: 220px;
+    flex-shrink: 0;
+    display: flex;
+    flex-direction: column;
+    background: #fafafa;
+    border-right: 1px solid #e5e7eb;
+    height: 100vh;
+    overflow: hidden;
+    transition: width 0.2s ease;
+}
+.dark .session-panel {
+    background: #111111;
+    border-right-color: rgba(255, 255, 255, 0.08);
+}
+.session-panel.hidden { display: none; }
+.session-panel-header {
+    display: flex;
+    align-items: center;
+    justify-content: space-between;
+    padding: 12px 16px;
+    border-bottom: 1px solid #e5e7eb;
+    flex-shrink: 0;
+}
+.dark .session-panel-header { border-bottom-color: rgba(255, 255, 255, 0.08); }
+.session-panel-title {
+    font-size: 14px;
+    font-weight: 600;
+    color: #374151;
+}
+.dark .session-panel-title { color: #d1d5db; }
+.session-panel-close {
+    width: 28px;
+    height: 28px;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    border-radius: 6px;
+    border: none;
+    background: none;
+    color: #9ca3af;
+    cursor: pointer;
+    transition: background 0.15s, color 0.15s;
+    font-size: 12px;
+}
+.session-panel-close:hover {
+    background: #f3f4f6;
+    color: #374151;
+}
+.dark .session-panel-close:hover {
+    background: rgba(255, 255, 255, 0.08);
+    color: #e5e5e5;
+}
+.session-panel-new {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+    margin: 10px 12px;
+    padding: 8px 14px;
+    border-radius: 8px;
+    border: 1px dashed #d1d5db;
+    background: none;
+    color: #6b7280;
+    font-size: 13px;
+    cursor: pointer;
+    transition: border-color 0.15s, color 0.15s, background 0.15s;
+    flex-shrink: 0;
+}
+.session-panel-new:hover {
+    border-color: #9ca3af;
+    color: #374151;
+    background: #f9fafb;
+}
+.dark .session-panel-new {
+    border-color: rgba(255, 255, 255, 0.12);
+    color: #9ca3af;
+}
+.dark .session-panel-new:hover {
+    border-color: rgba(255, 255, 255, 0.25);
+    color: #e5e5e5;
+    background: rgba(255, 255, 255, 0.04);
+}
+
+/* Session List */
+.session-list {
+    flex: 1;
+    overflow-y: auto;
+    padding: 4px 8px;
+    scrollbar-width: none;
+}
+.session-list:hover { scrollbar-width: thin; }
+.session-list::-webkit-scrollbar { width: 4px; background: transparent; }
+.session-list::-webkit-scrollbar-thumb { background: transparent; border-radius: 2px; }
+.session-list:hover::-webkit-scrollbar-thumb { background: rgba(0,0,0,0.2); }
+.dark .session-list:hover::-webkit-scrollbar-thumb { background: rgba(255,255,255,0.15); }
+.session-group-label {
+    padding: 10px 8px 4px;
+    font-size: 11px;
+    font-weight: 600;
+    text-transform: uppercase;
+    letter-spacing: 0.05em;
+    color: #9ca3af;
+}
+.dark .session-group-label { color: #525252; }
+.session-empty {
+    padding: 20px 12px;
+    text-align: center;
+    font-size: 13px;
+    color: #9ca3af;
+}
+.session-item {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+    padding: 8px 10px;
+    margin: 1px 0;
+    border-radius: 8px;
+    cursor: pointer;
+    transition: background 0.15s, color 0.15s;
+    color: #6b7280;
+    font-size: 13px;
+    position: relative;
+}
+.dark .session-item { color: #a3a3a3; }
+.session-item:hover {
+    background: #f3f4f6;
+    color: #111827;
+}
+.dark .session-item:hover {
+    background: rgba(255, 255, 255, 0.05);
+    color: #e5e5e5;
+}
+.session-item.active {
+    background: #e5e7eb;
+    color: #111827;
+}
+.dark .session-item.active {
+    background: rgba(255, 255, 255, 0.1);
+    color: #ffffff;
+}
+.session-icon {
+    flex-shrink: 0;
+    font-size: 11px;
+    color: #9ca3af;
+    width: 16px;
+    text-align: center;
+}
+.dark .session-icon { color: #525252; }
+.session-item.active .session-icon { color: #4ABE6E; }
+.session-title {
+    flex: 1;
+    min-width: 0;
+    overflow: hidden;
+    text-overflow: ellipsis;
+    white-space: nowrap;
+}
+.session-delete {
+    flex-shrink: 0;
+    width: 22px;
+    height: 22px;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    border-radius: 5px;
+    font-size: 10px;
+    color: #9ca3af;
+    opacity: 0;
+    transition: opacity 0.15s, color 0.15s, background 0.15s;
+    cursor: pointer;
+    background: none;
+    border: none;
+    padding: 0;
+}
+.session-item:hover .session-delete { opacity: 1; }
+.session-delete:hover {
+    color: #ef4444;
+    background: rgba(239, 68, 68, 0.1);
+}
+.dark .session-delete:hover { background: rgba(239, 68, 68, 0.15); }
+
+/* Context Divider */
+.context-divider {
+    display: flex;
+    align-items: center;
+    gap: 12px;
+    padding: 12px 24px;
+    color: #9ca3af;
+}
+.context-divider::before, .context-divider::after {
+    content: '';
+    flex: 1;
+    height: 1px;
+    background: linear-gradient(to right, transparent, #d1d5db, transparent);
+}
+.dark .context-divider::before, .dark .context-divider::after {
+    background: linear-gradient(to right, transparent, rgba(255,255,255,0.12), transparent);
+}
+.context-divider span {
+    font-size: 12px;
+    white-space: nowrap;
+    color: #9ca3af;
+}
+
+/* Confirm Modal */
+.confirm-overlay {
+    position: fixed;
+    inset: 0;
+    z-index: 9999;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    background: rgba(0, 0, 0, 0.4);
+    opacity: 0;
+    transition: opacity 0.2s ease;
+}
+.confirm-overlay.visible { opacity: 1; }
+.confirm-modal {
+    background: #fff;
+    border-radius: 14px;
+    width: 380px;
+    max-width: 90vw;
+    padding: 28px 24px 20px;
+    box-shadow: 0 20px 60px rgba(0, 0, 0, 0.18);
+    transform: scale(0.92);
+    transition: transform 0.2s ease;
+}
+.confirm-overlay.visible .confirm-modal { transform: scale(1); }
+.dark .confirm-modal {
+    background: #1e1e1e;
+    box-shadow: 0 20px 60px rgba(0, 0, 0, 0.5);
+}
+.confirm-title {
+    font-size: 16px;
+    font-weight: 600;
+    color: #1f2937;
+    margin-bottom: 8px;
+}
+.dark .confirm-title { color: #e5e7eb; }
+.confirm-message {
+    font-size: 14px;
+    color: #6b7280;
+    line-height: 1.5;
+    margin-bottom: 24px;
+}
+.dark .confirm-message { color: #9ca3af; }
+.confirm-actions {
+    display: flex;
+    justify-content: flex-end;
+    gap: 10px;
+}
+.confirm-btn {
+    padding: 8px 20px;
+    border-radius: 8px;
+    font-size: 14px;
+    font-weight: 500;
+    cursor: pointer;
+    border: none;
+    transition: all 0.15s ease;
+}
+.confirm-btn-cancel {
+    background: #f3f4f6;
+    color: #374151;
+}
+.confirm-btn-cancel:hover { background: #e5e7eb; }
+.dark .confirm-btn-cancel {
+    background: rgba(255, 255, 255, 0.08);
+    color: #d1d5db;
+}
+.dark .confirm-btn-cancel:hover { background: rgba(255, 255, 255, 0.14); }
+.confirm-btn-ok {
+    background: #ef4444;
+    color: #fff;
+}
+.confirm-btn-ok:hover { background: #dc2626; }
+
+/* Mobile: session panel as overlay */
+@media (max-width: 768px) {
+    .session-panel {
+        position: fixed;
+        top: 0;
+        left: 0;
+        z-index: 45;
+        width: 220px;
+        box-shadow: 4px 0 24px rgba(0, 0, 0, 0.15);
+    }
+    .dark .session-panel {
+        box-shadow: 4px 0 24px rgba(0, 0, 0, 0.4);
+    }
+}
+
 /* Menu Groups */
 .menu-group-items { max-height: 0; overflow: hidden; transition: max-height 0.25s ease-out; }
-.menu-group.open .menu-group-items { max-height: 500px; transition: max-height 0.35s ease-in; }
+.menu-group.open .menu-group-items { max-height: 2000px; transition: max-height 0.35s ease-in; }
 .menu-group .chevron { transition: transform 0.25s ease; }
 .menu-group.open .chevron { transform: rotate(90deg); }

@@ -45,7 +375,8 @@
 .msg-content h1 { font-size: 1.4em; }
 .msg-content h2 { font-size: 1.25em; }
 .msg-content h3 { font-size: 1.1em; }
-.msg-content ul, .msg-content ol { margin: 0.5em 0; padding-left: 1.8em; }
+.msg-content ul { margin: 0.5em 0; padding-left: 1.8em; list-style: disc; }
+.msg-content ol { margin: 0.5em 0; padding-left: 1.8em; list-style: decimal; }
 .msg-content li { margin: 0.25em 0; }
 .msg-content pre {
    border-radius: 8px; overflow-x: auto; margin: 0.8em 0;
@@ -79,6 +410,11 @@
 .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); }

@@ -141,7 +477,7 @@
    font-size: 0.75rem;
    line-height: 1.5;
    color: #94a3b8;
-    max-height: 200px;
+    max-height: 300px;
    overflow-y: auto;
 }
 .dark .agent-thinking-step .thinking-full {
@@ -153,6 +489,20 @@
 .agent-thinking-step .thinking-full p:first-child { margin-top: 0; }
 .agent-thinking-step .thinking-full p:last-child { margin-bottom: 0; }

+/* Content step - real text output frozen before tool calls */
+.agent-content-step {
+    font-size: 0.875rem;
+    line-height: 1.6;
+    color: inherit;
+    margin-bottom: 0.5rem;
+    padding-bottom: 0.5rem;
+    border-bottom: 1px dashed rgba(0, 0, 0, 0.06);
+}
+.dark .agent-content-step { border-bottom-color: rgba(255, 255, 255, 0.06); }
+.agent-content-step .agent-content-body p { margin: 0.25em 0; }
+.agent-content-step .agent-content-body p:first-child { margin-top: 0; }
+.agent-content-step .agent-content-body p:last-child { margin-bottom: 0; }
+
 /* Tool step - collapsible */
 .agent-tool-step .tool-header {
    display: flex;
@@ -344,6 +694,100 @@
    transition: border-color 0.2s ease;
 }

+/* Attachment Preview Bar */
+.attachment-preview {
+    display: flex;
+    flex-wrap: wrap;
+    gap: 8px;
+    padding: 8px 0;
+}
+.attachment-preview.hidden { display: none; }
+
+.att-thumb {
+    position: relative;
+    width: 64px; height: 64px;
+    border-radius: 8px;
+    overflow: hidden;
+    border: 1px solid #e2e8f0;
+    flex-shrink: 0;
+}
+.dark .att-thumb { border-color: rgba(255,255,255,0.1); }
+.att-thumb img {
+    width: 100%; height: 100%;
+    object-fit: cover;
+}
+
+.att-chip {
+    position: relative;
+    display: flex;
+    align-items: center;
+    gap: 6px;
+    padding: 6px 28px 6px 10px;
+    border-radius: 8px;
+    background: #f1f5f9;
+    border: 1px solid #e2e8f0;
+    font-size: 12px;
+    color: #475569;
+    max-width: 180px;
+}
+.dark .att-chip { background: rgba(255,255,255,0.05); border-color: rgba(255,255,255,0.1); color: #94a3b8; }
+.att-uploading { opacity: 0.6; pointer-events: none; }
+.att-name {
+    overflow: hidden;
+    text-overflow: ellipsis;
+    white-space: nowrap;
+}
+
+.att-remove {
+    position: absolute;
+    top: -4px; right: -4px;
+    width: 18px; height: 18px;
+    border-radius: 50%;
+    background: #ef4444;
+    color: #fff;
+    border: none;
+    font-size: 12px;
+    line-height: 18px;
+    text-align: center;
+    cursor: pointer;
+    padding: 0;
+    opacity: 0;
+    transition: opacity 0.15s;
+}
+.att-thumb:hover .att-remove,
+.att-chip:hover .att-remove { opacity: 1; }
+
+/* Drag-over highlight */
+.drag-over {
+    background: rgba(74, 190, 110, 0.08) !important;
+    border-color: #4ABE6E !important;
+}
+
+/* User message attachments */
+.user-msg-attachments {
+    display: flex;
+    flex-wrap: wrap;
+    gap: 6px;
+    margin-bottom: 6px;
+}
+.user-msg-image {
+    max-width: 200px;
+    max-height: 160px;
+    border-radius: 8px;
+    object-fit: cover;
+    cursor: pointer;
+}
+.user-msg-image:hover { opacity: 0.9; }
+.user-msg-file {
+    display: flex;
+    align-items: center;
+    gap: 6px;
+    padding: 4px 10px;
+    border-radius: 6px;
+    background: rgba(255,255,255,0.15);
+    font-size: 12px;
+}
+
 /* Placeholder Cards */
 .placeholder-card {
    transition: transform 0.2s ease, box-shadow 0.2s ease;
@@ -352,3 +796,279 @@
    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;
+}
+
+/* ============================================================
+   Knowledge View
+   ============================================================ */
+
+/* Tab toggle */
+.knowledge-tab {
+    color: #64748b;
+}
+.knowledge-tab.active {
+    background: #fff;
+    color: #334155;
+    box-shadow: 0 1px 3px rgba(0,0,0,0.08);
+}
+.dark .knowledge-tab.active {
+    background: rgba(255,255,255,0.1);
+    color: #e2e8f0;
+}
+
+/* File tree */
+.knowledge-tree-group {
+    margin-bottom: 2px;
+}
+.knowledge-tree-group-btn {
+    display: flex;
+    align-items: center;
+    gap: 6px;
+    width: 100%;
+    padding: 6px 8px;
+    border-radius: 6px;
+    font-size: 12px;
+    font-weight: 600;
+    color: #64748b;
+    cursor: pointer;
+    border: none;
+    background: none;
+    transition: background 0.15s, color 0.15s;
+    text-transform: capitalize;
+}
+.knowledge-tree-group-btn:hover {
+    background: rgba(0,0,0,0.04);
+    color: #334155;
+}
+.dark .knowledge-tree-group-btn:hover {
+    background: rgba(255,255,255,0.06);
+    color: #e2e8f0;
+}
+.knowledge-tree-group-btn i.chevron {
+    font-size: 8px;
+    transition: transform 0.15s;
+}
+.knowledge-tree-group.open .chevron {
+    transform: rotate(90deg);
+}
+.knowledge-tree-group-items {
+    display: none;
+}
+.knowledge-tree-group.open .knowledge-tree-group-items {
+    display: block;
+}
+
+.knowledge-tree-file {
+    display: flex;
+    align-items: center;
+    gap: 6px;
+    padding: 5px 8px 5px 24px;
+    border-radius: 6px;
+    font-size: 12px;
+    color: #64748b;
+    cursor: pointer;
+    border: none;
+    background: none;
+    width: 100%;
+    text-align: left;
+    transition: background 0.15s, color 0.15s;
+    white-space: nowrap;
+    overflow: hidden;
+    text-overflow: ellipsis;
+}
+.knowledge-tree-file:hover {
+    background: rgba(0,0,0,0.04);
+    color: #334155;
+}
+.knowledge-tree-file.active {
+    background: #EDFDF3;
+    color: #228547;
+}
+.dark .knowledge-tree-file:hover {
+    background: rgba(255,255,255,0.06);
+    color: #e2e8f0;
+}
+.dark .knowledge-tree-file.active {
+    background: rgba(74, 190, 110, 0.1);
+    color: #4ABE6E;
+}
+
+/* Graph legend */
+.knowledge-graph-legend {
+    position: absolute;
+    top: 12px;
+    right: 12px;
+    display: flex;
+    flex-wrap: wrap;
+    gap: 8px;
+    font-size: 11px;
+    color: #64748b;
+    z-index: 10;
+}
+.knowledge-graph-legend-item {
+    display: flex;
+    align-items: center;
+    gap: 4px;
+}
+.knowledge-graph-legend-dot {
+    width: 8px;
+    height: 8px;
+    border-radius: 50%;
+}
+
+/* Graph tooltip */
+.knowledge-graph-tooltip {
+    position: absolute;
+    padding: 6px 10px;
+    background: #fff;
+    border: 1px solid #e2e8f0;
+    border-radius: 8px;
+    font-size: 12px;
+    color: #334155;
+    box-shadow: 0 4px 12px rgba(0,0,0,0.08);
+    pointer-events: none;
+    opacity: 0;
+    transition: opacity 0.15s;
+    z-index: 20;
+}
+.dark .knowledge-graph-tooltip {
+    background: #1A1A1A;
+    border-color: rgba(255,255,255,0.1);
+    color: #e2e8f0;
+}
+
+/* Config field tooltip */
+.cfg-tip {
+    position: relative;
+    display: inline-flex;
+    align-items: center;
+    color: #94a3b8;
+    cursor: help;
+    font-size: 12px;
+}
+.cfg-tip:hover { color: #64748b; }
+.dark .cfg-tip:hover { color: #cbd5e1; }
+.cfg-tip::after {
+    content: attr(data-tooltip);
+    position: absolute;
+    left: 50%;
+    bottom: calc(100% + 6px);
+    transform: translateX(-50%);
+    padding: 6px 10px;
+    border-radius: 8px;
+    font-size: 12px;
+    font-weight: 400;
+    line-height: 1.4;
+    white-space: nowrap;
+    background: #1e293b;
+    color: #e2e8f0;
+    box-shadow: 0 4px 12px rgba(0,0,0,0.15);
+    opacity: 0;
+    pointer-events: none;
+    transition: opacity 0.15s;
+    z-index: 50;
+}
+.dark .cfg-tip::after {
+    background: #334155;
+    color: #f1f5f9;
+}
+.cfg-tip:hover::after {
+    opacity: 1;
+}
+
+/* Example cards: equal height via flex stretch + fixed 2-line description area */
+.example-card {
+    display: flex;
+    flex-direction: column;
+}
+.example-card > p {
+    flex: 1;
+    display: -webkit-box;
+    -webkit-line-clamp: 2;
+    -webkit-box-orient: vertical;
+    overflow: hidden;
+    min-height: 2.5em;  /* ~2 lines at text-sm leading-relaxed */
+}
--- a/channel/web/static/js/console.js
+++ b/channel/web/static/js/console.js
--- a/channel/web/web_channel.py
+++ b/channel/web/web_channel.py
--- a/channel/wecom_bot/wecom_bot_channel.py
+++ b/channel/wecom_bot/wecom_bot_channel.py
@@ -26,6 +26,7 @@ from channel.wecom_bot.wecom_bot_message import WecomBotMessage
 from common.expired_dict import ExpiredDict
 from common.log import logger
 from common.singleton import singleton
+from common.ws_client_compat import websocket_app_run_forever
 from config import conf

 WECOM_WS_URL = "wss://openws.work.weixin.qq.com"
@@ -119,7 +120,7 @@ class WecomBotChannel(ChatChannel):

        def run_forever():
            try:
-                self._ws.run_forever(ping_interval=0, reconnect=0)
+                websocket_app_run_forever(self._ws, ping_interval=0, reconnect=0)
            except (SystemExit, KeyboardInterrupt):
                logger.info("[WecomBot] WebSocket thread interrupted")
            except Exception as e:
@@ -329,28 +330,42 @@ class WecomBotChannel(ChatChannel):

        All intermediate segments (thinking before tool calls) and the final answer
        are accumulated into a single stream message, separated by '---'.
+        Throttles push to at most once per 100ms to avoid WebSocket congestion.
        """
        stream_id = uuid.uuid4().hex[:16]
        self._stream_states[req_id] = {
            "stream_id": stream_id,
-            "committed": "",  # finalized content from previous segments
-            "current": "",    # current segment being streamed
+            "committed": "",
+            "current": "",
+            "last_push_time": 0,
+            "last_push_len": 0,
        }

-        def _push_stream(state: dict):
-            """Push current stream content to wecom."""
-            self._ws_send({
-                "cmd": "aibot_respond_msg",
-                "headers": {"req_id": req_id},
-                "body": {
-                    "msgtype": "stream",
-                    "stream": {
-                        "id": state["stream_id"],
-                        "finish": False,
-                        "content": state["committed"] + state["current"],
+        def _push_stream(state: dict, force: bool = False):
+            """Push current stream content to wecom (throttled unless forced)."""
+            now = time.time()
+            if not force and now - state["last_push_time"] < 0.1:
+                return
+            content = state["committed"] + state["current"]
+            if len(content) == state["last_push_len"]:
+                return
+            state["last_push_time"] = now
+            state["last_push_len"] = len(content)
+            try:
+                self._ws_send({
+                    "cmd": "aibot_respond_msg",
+                    "headers": {"req_id": req_id},
+                    "body": {
+                        "msgtype": "stream",
+                        "stream": {
+                            "id": state["stream_id"],
+                            "finish": False,
+                            "content": content,
+                        },
                    },
-                },
-            })
+                })
+            except Exception as e:
+                logger.warning(f"[WecomBot] Stream push failed: {e}")

        def on_event(event: dict):
            event_type = event.get("type")
@@ -377,6 +392,7 @@ class WecomBotChannel(ChatChannel):
                else:
                    state["committed"] += state["current"]
                    state["current"] = ""
+                _push_stream(state, force=True)

        return on_event

@@ -451,11 +467,16 @@ class WecomBotChannel(ChatChannel):
        if req_id:
            state = self._stream_states.pop(req_id, None)
            if state:
-                final_content = state["committed"]
+                final_content = state["committed"] if state["committed"] else content
                stream_id = state["stream_id"]
            else:
                final_content = content
                stream_id = uuid.uuid4().hex[:16]
+
+            # Brief pause so the server finishes processing the last intermediate chunk
+            # before receiving the finish packet
+            time.sleep(0.15)
+
            self._ws_send({
                "cmd": "aibot_respond_msg",
                "headers": {"req_id": req_id},
--- a/channel/weixin/init.py
+++ b/channel/weixin/init.py
--- a/channel/weixin/weixin_api.py
+++ b/channel/weixin/weixin_api.py
@@ -0,0 +1,412 @@
+"""
+Weixin HTTP JSON API client.
+
+Implements the ilink bot protocol:
+  - getUpdates (long-poll)
+  - sendMessage
+  - getUploadUrl
+  - getConfig
+  - sendTyping
+  - QR login (get_bot_qrcode / get_qrcode_status)
+
+CDN media upload with AES-128-ECB encryption.
+"""
+
+import base64
+import hashlib
+import os
+import random
+import struct
+import time
+import uuid
+
+import requests
+
+from common.log import logger
+
+DEFAULT_BASE_URL = "https://ilinkai.weixin.qq.com"
+CDN_BASE_URL = "https://novac2c.cdn.weixin.qq.com/c2c"
+DEFAULT_LONG_POLL_TIMEOUT = 35
+DEFAULT_API_TIMEOUT = 15
+QR_POLL_TIMEOUT = 35
+BOT_TYPE = "3"
+
+
+def _random_wechat_uin() -> str:
+    val = random.randint(0, 0xFFFFFFFF)
+    return base64.b64encode(str(val).encode("utf-8")).decode("utf-8")
+
+
+CHANNEL_VERSION = "2.0.0"
+# iLink-App-ClientVersion: uint32 encoded as major<<16 | minor<<8 | patch
+# 2.0.0 → 0x00020000 = 131072
+CLIENT_VERSION = "131072"
+
+
+def _build_headers(token: str = "") -> dict:
+    headers = {
+        "Content-Type": "application/json",
+        "AuthorizationType": "ilink_bot_token",
+        "X-WECHAT-UIN": _random_wechat_uin(),
+        "iLink-App-Id": "bot",
+        "iLink-App-ClientVersion": CLIENT_VERSION,
+    }
+    if token:
+        headers["Authorization"] = f"Bearer {token}"
+    return headers
+
+
+def _ensure_trailing_slash(url: str) -> str:
+    return url if url.endswith("/") else url + "/"
+
+
+class WeixinApi:
+    """Stateless HTTP client for the Weixin ilink bot API."""
+
+    def __init__(self, base_url: str = DEFAULT_BASE_URL, token: str = "",
+                 cdn_base_url: str = CDN_BASE_URL):
+        self.base_url = base_url
+        self.token = token
+        self.cdn_base_url = cdn_base_url
+
+    def _post(self, endpoint: str, body: dict, timeout: int = DEFAULT_API_TIMEOUT) -> dict:
+        url = _ensure_trailing_slash(self.base_url) + endpoint
+        headers = _build_headers(self.token)
+        body.setdefault("base_info", {}).setdefault("channel_version", CHANNEL_VERSION)
+        try:
+            resp = requests.post(url, json=body, headers=headers, timeout=timeout)
+            resp.raise_for_status()
+            return resp.json()
+        except requests.exceptions.Timeout:
+            logger.debug(f"[Weixin] API timeout: {endpoint}")
+            return {"ret": 0, "msgs": []}
+        except Exception as e:
+            logger.error(f"[Weixin] API error {endpoint}: {e}")
+            raise
+
+    # ── getUpdates (long-poll) ─────────────────────────────────────────
+
+    def get_updates(self, get_updates_buf: str = "", timeout: int = DEFAULT_LONG_POLL_TIMEOUT) -> dict:
+        return self._post("ilink/bot/getupdates", {
+            "get_updates_buf": get_updates_buf,
+        }, timeout=timeout + 5)
+
+    # ── sendMessage ────────────────────────────────────────────────────
+
+    def send_text(self, to: str, text: str, context_token: str) -> dict:
+        return self._post("ilink/bot/sendmessage", {
+            "msg": {
+                "from_user_id": "",
+                "to_user_id": to,
+                "client_id": uuid.uuid4().hex[:16],
+                "message_type": 2,  # BOT
+                "message_state": 2,  # FINISH
+                "item_list": [{"type": 1, "text_item": {"text": text}}],
+                "context_token": context_token,
+            }
+        })
+
+    def send_image_item(self, to: str, context_token: str,
+                        encrypt_query_param: str, aes_key_b64: str,
+                        ciphertext_size: int, text: str = "") -> dict:
+        items = []
+        if text:
+            items.append({"type": 1, "text_item": {"text": text}})
+        items.append({
+            "type": 2,
+            "image_item": {
+                "media": {
+                    "encrypt_query_param": encrypt_query_param,
+                    "aes_key": aes_key_b64,
+                    "encrypt_type": 1,
+                },
+                "mid_size": ciphertext_size,
+            }
+        })
+        return self._send_items(to, context_token, items)
+
+    def send_file_item(self, to: str, context_token: str,
+                       encrypt_query_param: str, aes_key_b64: str,
+                       file_name: str, file_size: int, text: str = "") -> dict:
+        items = []
+        if text:
+            items.append({"type": 1, "text_item": {"text": text}})
+        items.append({
+            "type": 4,
+            "file_item": {
+                "media": {
+                    "encrypt_query_param": encrypt_query_param,
+                    "aes_key": aes_key_b64,
+                    "encrypt_type": 1,
+                },
+                "file_name": file_name,
+                "len": str(file_size),
+            }
+        })
+        return self._send_items(to, context_token, items)
+
+    def send_video_item(self, to: str, context_token: str,
+                        encrypt_query_param: str, aes_key_b64: str,
+                        ciphertext_size: int, text: str = "") -> dict:
+        items = []
+        if text:
+            items.append({"type": 1, "text_item": {"text": text}})
+        items.append({
+            "type": 5,
+            "video_item": {
+                "media": {
+                    "encrypt_query_param": encrypt_query_param,
+                    "aes_key": aes_key_b64,
+                    "encrypt_type": 1,
+                },
+                "video_size": ciphertext_size,
+            }
+        })
+        return self._send_items(to, context_token, items)
+
+    def _send_items(self, to: str, context_token: str, items: list) -> dict:
+        return self._post("ilink/bot/sendmessage", {
+            "msg": {
+                "from_user_id": "",
+                "to_user_id": to,
+                "client_id": uuid.uuid4().hex[:16],
+                "message_type": 2,
+                "message_state": 2,
+                "item_list": items,
+                "context_token": context_token,
+            }
+        })
+
+    # ── getUploadUrl ───────────────────────────────────────────────────
+
+    def get_upload_url(self, filekey: str, media_type: int, to_user_id: str,
+                       rawsize: int, rawfilemd5: str, filesize: int,
+                       aeskey: str) -> dict:
+        return self._post("ilink/bot/getuploadurl", {
+            "filekey": filekey,
+            "media_type": media_type,
+            "to_user_id": to_user_id,
+            "rawsize": rawsize,
+            "rawfilemd5": rawfilemd5,
+            "filesize": filesize,
+            "aeskey": aeskey,
+            "no_need_thumb": True,
+        })
+
+    # ── getConfig / sendTyping ─────────────────────────────────────────
+
+    def get_config(self, user_id: str, context_token: str = "") -> dict:
+        return self._post("ilink/bot/getconfig", {
+            "ilink_user_id": user_id,
+            "context_token": context_token,
+        }, timeout=10)
+
+    def send_typing(self, user_id: str, typing_ticket: str, status: int = 1) -> dict:
+        return self._post("ilink/bot/sendtyping", {
+            "ilink_user_id": user_id,
+            "typing_ticket": typing_ticket,
+            "status": status,
+        }, timeout=10)
+
+    # ── QR Login ───────────────────────────────────────────────────────
+
+    def fetch_qr_code(self) -> dict:
+        url = _ensure_trailing_slash(self.base_url) + f"ilink/bot/get_bot_qrcode?bot_type={BOT_TYPE}"
+        resp = requests.get(url, timeout=15)
+        resp.raise_for_status()
+        return resp.json()
+
+    def poll_qr_status(self, qrcode: str, timeout: int = QR_POLL_TIMEOUT) -> dict:
+        url = (_ensure_trailing_slash(self.base_url) +
+               f"ilink/bot/get_qrcode_status?qrcode={requests.utils.quote(qrcode)}")
+        headers = {
+            "iLink-App-Id": "bot",
+            "iLink-App-ClientVersion": CLIENT_VERSION,
+        }
+        try:
+            resp = requests.get(url, headers=headers, timeout=timeout)
+            resp.raise_for_status()
+            return resp.json()
+        except requests.exceptions.Timeout:
+            return {"status": "wait"}
+
+
+# ── AES-128-ECB helpers ─────────────────────────────────────────────
+
+def _aes_ecb_encrypt(data: bytes, key: bytes) -> bytes:
+    from Crypto.Cipher import AES
+    pad_len = 16 - (len(data) % 16)
+    padded = data + bytes([pad_len] * pad_len)
+    cipher = AES.new(key, AES.MODE_ECB)
+    return cipher.encrypt(padded)
+
+
+def _aes_ecb_decrypt(data: bytes, key: bytes) -> bytes:
+    from Crypto.Cipher import AES
+    cipher = AES.new(key, AES.MODE_ECB)
+    decrypted = cipher.decrypt(data)
+    pad_len = decrypted[-1]
+    if pad_len > 16:
+        return decrypted
+    return decrypted[:-pad_len]
+
+
+def _file_md5(file_path: str) -> str:
+    h = hashlib.md5()
+    with open(file_path, "rb") as f:
+        for chunk in iter(lambda: f.read(8192), b""):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+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 (matching official plugin protocol).
+
+    Args:
+        api: WeixinApi instance
+        file_path: local file path
+        to_user_id: target user id
+        media_type: 1=IMAGE, 2=VIDEO, 3=FILE
+
+    Returns:
+        dict with keys: encrypt_query_param, aes_key_b64, ciphertext_size, raw_size
+    """
+    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)
+
+    from urllib.parse import quote
+
+    download_param = None
+    last_error = None
+    for attempt in range(1, UPLOAD_MAX_RETRIES + 1):
+        try:
+            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,
+            )
+
+            # API may return either upload_full_url (new) or upload_param (legacy)
+            upload_full_url = resp.get("upload_full_url", "")
+            upload_param = resp.get("upload_param", "")
+            if upload_full_url:
+                cdn_url = upload_full_url
+            elif upload_param:
+                cdn_url = (f"{api.cdn_base_url}/upload"
+                           f"?encrypted_query_param={quote(upload_param)}"
+                           f"&filekey={quote(filekey)}")
+            else:
+                raise RuntimeError(f"[Weixin] getUploadUrl returned neither upload_full_url nor upload_param: {resp}")
+
+            cdn_resp = requests.post(cdn_url, data=encrypted, headers={
+                "Content-Type": "application/octet-stream",
+                "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:
+            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": download_param,
+        "aes_key_b64": aes_key_b64,
+        "ciphertext_size": cipher_size,
+        "raw_size": raw_size,
+    }
+
+
+def download_media_from_cdn(cdn_base_url: str, encrypt_query_param: str,
+                            aes_key: str, save_path: str) -> str:
+    """
+    Download and decrypt a media file from Weixin CDN.
+
+    Args:
+        cdn_base_url: CDN base URL
+        encrypt_query_param: encrypted query parameter from message
+        aes_key: hex or base64 encoded AES key
+        save_path: path to save decrypted file
+
+    Returns:
+        save_path on success
+    """
+    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:
+    # 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):
+        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)
+
+    os.makedirs(os.path.dirname(save_path), exist_ok=True)
+    with open(save_path, "wb") as f:
+        f.write(decrypted)
+    return save_path
--- a/channel/weixin/weixin_channel.py
+++ b/channel/weixin/weixin_channel.py
@@ -0,0 +1,637 @@
+"""
+Weixin channel implementation.
+
+Uses HTTP long-poll (getUpdates) to receive messages and sendMessage to reply.
+Login via QR code scan through the ilink bot API.
+"""
+
+import json
+import os
+import threading
+import time
+import uuid
+
+import requests
+
+from bridge.context import Context, ContextType
+from bridge.reply import Reply, ReplyType
+from channel.chat_channel import ChatChannel, check_prefix
+from channel.weixin.weixin_api import (
+    WeixinApi, upload_media_to_cdn,
+    DEFAULT_BASE_URL, CDN_BASE_URL,
+)
+from channel.weixin.weixin_message import WeixinMessage
+from common.expired_dict import ExpiredDict
+from common.log import logger
+from common.singleton import singleton
+from config import conf
+
+MAX_CONSECUTIVE_FAILURES = 3
+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:
+    """Load saved credentials from JSON file."""
+    try:
+        if os.path.exists(cred_path):
+            with open(cred_path, "r") as f:
+                return json.load(f)
+    except Exception as e:
+        logger.warning(f"[Weixin] Failed to load credentials: {e}")
+    return {}
+
+
+def _save_credentials(cred_path: str, data: dict):
+    """Save credentials to JSON file."""
+    os.makedirs(os.path.dirname(cred_path), exist_ok=True)
+    with open(cred_path, "w") as f:
+        json.dump(data, f, indent=2)
+    try:
+        os.chmod(cred_path, 0o600)
+    except Exception:
+        pass
+
+
+@singleton
+class WeixinChannel(ChatChannel):
+
+    LOGIN_STATUS_IDLE = "idle"
+    LOGIN_STATUS_WAITING = "waiting_scan"
+    LOGIN_STATUS_SCANNED = "scanned"
+    LOGIN_STATUS_OK = "logged_in"
+
+    def __init__(self):
+        super().__init__()
+        self.api = None
+        self._stop_event = threading.Event()
+        self._poll_thread = None
+        self._context_tokens = {}  # user_id -> context_token
+        self._received_msgs = ExpiredDict(60 * 60 * 7.1)
+        self._get_updates_buf = ""
+        self._credentials_path = ""
+        self.login_status = self.LOGIN_STATUS_IDLE
+        self._current_qr_url = ""
+
+        conf()["single_chat_prefix"] = [""]
+
+    # ── 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", "")
+
+        self._credentials_path = os.path.expanduser(
+            conf().get("weixin_credentials_path", "~/.weixin_cow_credentials.json")
+        )
+
+        if not token:
+            creds = _load_credentials(self._credentials_path)
+            token = creds.get("token", "")
+            if creds.get("base_url"):
+                base_url = creds["base_url"]
+
+        if not token:
+            token, base_url = self._login_with_retry(base_url)
+            if not token:
+                return
+
+        self.api = WeixinApi(base_url=base_url, token=token, cdn_base_url=cdn_base_url)
+        self.login_status = self.LOGIN_STATUS_OK
+
+        logger.info(f"[Weixin] 微信通道已启动，凭证保存在 {self._credentials_path}，"
+                     f"如需重新扫码登录请删除该文件后重启")
+        self.report_startup_success()
+
+        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()
+
+    def _relogin(self) -> bool:
+        """Re-login after session expiry. Returns True on success."""
+        base_url = self.api.base_url if self.api else DEFAULT_BASE_URL
+        if os.path.exists(self._credentials_path):
+            try:
+                os.remove(self._credentials_path)
+            except Exception:
+                pass
+        self.login_status = self.LOGIN_STATUS_WAITING
+        result = self._qr_login(base_url)
+        if not result:
+            self.login_status = self.LOGIN_STATUS_IDLE
+            return False
+        self.api = WeixinApi(
+            base_url=result.get("base_url", base_url),
+            token=result["token"],
+            cdn_base_url=self.api.cdn_base_url if self.api else CDN_BASE_URL,
+        )
+        self.login_status = self.LOGIN_STATUS_OK
+        self._context_tokens.clear()
+        return True
+
+    # ── QR Login ───────────────────────────────────────────────────────
+
+    @staticmethod
+    def _print_qr(qrcode_url: str):
+        """Print QR code to terminal for scanning."""
+        print("\n" + "=" * 60)
+        print("  请使用微信扫描二维码登录 (二维码约2分钟后过期)")
+        print("=" * 60)
+        try:
+            import qrcode as qr_lib
+            import io
+            qr = qr_lib.QRCode(error_correction=qr_lib.constants.ERROR_CORRECT_L, box_size=1, border=1)
+            qr.add_data(qrcode_url)
+            qr.make(fit=True)
+            buf = io.StringIO()
+            qr.print_ascii(out=buf, invert=True)
+            try:
+                print(buf.getvalue())
+            except UnicodeEncodeError:
+                # Windows GBK terminals cannot render Unicode block characters
+                print(f"\n  (终端不支持显示二维码，请使用链接扫码)")
+                print(f"  二维码链接: {qrcode_url}\n")
+        except ImportError:
+            print(f"\n  二维码链接: {qrcode_url}")
+            print("  (安装 'qrcode' 包可在终端显示二维码)\n")
+
+    def _notify_cloud_qrcode(self, qrcode_url: str):
+        """Send QR code URL to cloud console when running in cloud mode."""
+        if not self.cloud_mode:
+            return
+        try:
+            from common import cloud_client
+            client = getattr(cloud_client, "chat_client", None)
+            if client and getattr(client, "client_id", None):
+                client.send_channel_qrcode("weixin", qrcode_url)
+        except Exception as e:
+            logger.warning(f"[Weixin] Failed to notify cloud QR code: {e}")
+
+    def _notify_cloud_connected(self):
+        """Send connected status to cloud console when login succeeds."""
+        if not self.cloud_mode:
+            return
+        try:
+            from common import cloud_client
+            client = getattr(cloud_client, "chat_client", None)
+            if client and getattr(client, "client_id", None):
+                client.send_channel_status("weixin", "connected")
+        except Exception as e:
+            logger.warning(f"[Weixin] Failed to notify cloud connected: {e}")
+
+    def _qr_login(self, base_url: str) -> dict:
+        """Perform interactive QR code login. Returns dict with token/base_url or empty dict."""
+        api = WeixinApi(base_url=base_url)
+        try:
+            qr_resp = api.fetch_qr_code()
+        except Exception as e:
+            logger.error(f"[Weixin] Failed to fetch QR code: {e}")
+            return {}
+
+        qrcode = qr_resp.get("qrcode", "")
+        qrcode_url = qr_resp.get("qrcode_img_content", "")
+
+        if not qrcode:
+            logger.error("[Weixin] No QR code returned from server")
+            return {}
+
+        self._current_qr_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:
+                logger.error(f"[Weixin] QR status poll error: {e}")
+                return {}
+
+            status = status_resp.get("status", "wait")
+
+            if status == "wait":
+                pass
+            elif status == "scaned":
+                self.login_status = self.LOGIN_STATUS_SCANNED
+                if not scanned_printed:
+                    print("  已扫码，请在手机上确认...")
+                    scanned_printed = True
+            elif status == "expired":
+                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] 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:
+                    logger.error(f"[Weixin] QR refresh failed: {e}")
+                    return {}
+            elif status == "confirmed":
+                bot_token = status_resp.get("bot_token", "")
+                bot_id = status_resp.get("ilink_bot_id", "")
+                result_base_url = status_resp.get("baseurl", base_url)
+                user_id = status_resp.get("ilink_user_id", "")
+
+                if not bot_token or not bot_id:
+                    logger.error("[Weixin] Login confirmed but missing token/bot_id")
+                    return {}
+
+                self._current_qr_url = ""
+                print(f"\n  ✅ 微信登录成功！bot_id={bot_id}")
+                logger.info(f"[Weixin] Login confirmed: bot_id={bot_id}")
+                self._notify_cloud_connected()
+
+                creds = {
+                    "token": bot_token,
+                    "base_url": result_base_url,
+                    "bot_id": bot_id,
+                    "user_id": user_id,
+                }
+                _save_credentials(self._credentials_path, creds)
+                logger.info(f"[Weixin] Credentials saved to {self._credentials_path}")
+
+                return {"token": bot_token, "base_url": result_base_url}
+
+            self._stop_event.wait(1)
+
+        self._current_qr_url = ""
+        if self._stop_event.is_set():
+            logger.info("[Weixin] QR login cancelled by stop event")
+        return {}
+
+    # ── Long-poll loop ─────────────────────────────────────────────────
+
+    def _poll_loop(self):
+        """Main long-poll loop: getUpdates -> parse -> produce."""
+        logger.info("[Weixin] Starting long-poll loop")
+        consecutive_failures = 0
+
+        while not self._stop_event.is_set():
+            try:
+                resp = self.api.get_updates(self._get_updates_buf)
+
+                ret = resp.get("ret", 0)
+                errcode = resp.get("errcode", 0)
+
+                is_error = (ret != 0) or (errcode != 0)
+                if is_error:
+                    if errcode == SESSION_EXPIRED_ERRCODE or ret == SESSION_EXPIRED_ERRCODE:
+                        logger.error("[Weixin] Session expired (errcode -14), starting re-login...")
+                        if self._relogin():
+                            logger.info("[Weixin] Re-login successful, resuming long-poll")
+                            self._get_updates_buf = ""
+                            consecutive_failures = 0
+                            continue
+                        else:
+                            logger.error("[Weixin] Re-login failed, will retry in 5 minutes")
+                            self._stop_event.wait(300)
+                            continue
+
+                    consecutive_failures += 1
+                    errmsg = resp.get("errmsg", "")
+                    logger.error(f"[Weixin] getUpdates error: ret={ret} errcode={errcode} "
+                                 f"errmsg={errmsg} ({consecutive_failures}/{MAX_CONSECUTIVE_FAILURES})")
+                    if consecutive_failures >= MAX_CONSECUTIVE_FAILURES:
+                        consecutive_failures = 0
+                        self._stop_event.wait(BACKOFF_DELAY)
+                    else:
+                        self._stop_event.wait(RETRY_DELAY)
+                    continue
+
+                consecutive_failures = 0
+
+                # Update sync cursor
+                new_buf = resp.get("get_updates_buf", "")
+                if new_buf:
+                    self._get_updates_buf = new_buf
+
+                # Process messages
+                msgs = resp.get("msgs", [])
+                for raw_msg in msgs:
+                    try:
+                        self._process_message(raw_msg)
+                    except Exception as e:
+                        logger.error(f"[Weixin] Failed to process message: {e}", exc_info=True)
+
+            except Exception as e:
+                if self._stop_event.is_set():
+                    break
+                consecutive_failures += 1
+                logger.error(f"[Weixin] getUpdates exception: {e} "
+                             f"({consecutive_failures}/{MAX_CONSECUTIVE_FAILURES})")
+                if consecutive_failures >= MAX_CONSECUTIVE_FAILURES:
+                    consecutive_failures = 0
+                    self._stop_event.wait(BACKOFF_DELAY)
+                else:
+                    self._stop_event.wait(RETRY_DELAY)
+
+        logger.info("[Weixin] Long-poll loop ended")
+
+    def _process_message(self, raw_msg: dict):
+        """Parse a single inbound message and produce to the handling queue."""
+        msg_type = raw_msg.get("message_type", 0)
+        if msg_type != 1:  # Only process USER messages (type=1)
+            return
+
+        msg_id = str(raw_msg.get("message_id", raw_msg.get("seq", "")))
+        if self._received_msgs.get(msg_id):
+            return
+        self._received_msgs[msg_id] = True
+
+        from_user = raw_msg.get("from_user_id", "")
+        context_token = raw_msg.get("context_token", "")
+
+        if context_token and from_user:
+            self._context_tokens[from_user] = context_token
+
+        cdn_base_url = self.api.cdn_base_url if self.api else CDN_BASE_URL
+        try:
+            wx_msg = WeixinMessage(raw_msg, cdn_base_url=cdn_base_url)
+        except Exception as e:
+            logger.error(f"[Weixin] Failed to parse WeixinMessage: {e}", exc_info=True)
+            return
+
+        logger.info(f"[Weixin] Received: from={from_user} ctype={wx_msg.ctype} "
+                     f"content={str(wx_msg.content)[:50]}")
+
+        # File cache logic
+        from channel.file_cache import get_file_cache
+        file_cache = get_file_cache()
+        session_id = from_user
+
+        if wx_msg.ctype == ContextType.IMAGE:
+            if hasattr(wx_msg, "image_path") and wx_msg.image_path:
+                file_cache.add(session_id, wx_msg.image_path, file_type="image")
+                logger.info(f"[Weixin] Image cached for session {session_id}")
+            return
+
+        if wx_msg.ctype == ContextType.FILE:
+            wx_msg.prepare()
+            file_cache.add(session_id, wx_msg.content, file_type="file")
+            logger.info(f"[Weixin] File cached for session {session_id}: {wx_msg.content}")
+            return
+
+        if wx_msg.ctype == ContextType.TEXT:
+            cached_files = file_cache.get(session_id)
+            if cached_files:
+                refs = []
+                for fi in cached_files:
+                    ftype, fpath = fi["type"], fi["path"]
+                    if ftype == "image":
+                        refs.append(f"[图片: {fpath}]")
+                    elif ftype == "video":
+                        refs.append(f"[视频: {fpath}]")
+                    else:
+                        refs.append(f"[文件: {fpath}]")
+                wx_msg.content = wx_msg.content + "\n" + "\n".join(refs)
+                file_cache.clear(session_id)
+
+        context = self._compose_context(
+            wx_msg.ctype,
+            wx_msg.content,
+            isgroup=False,
+            msg=wx_msg,
+            no_need_at=True,
+        )
+        if context:
+            self.produce(context)
+
+    # ── _compose_context ───────────────────────────────────────────────
+
+    def _compose_context(self, ctype: ContextType, content, **kwargs):
+        context = Context(ctype, content)
+        context.kwargs = kwargs
+        if "channel_type" not in context:
+            context["channel_type"] = self.channel_type
+        if "origin_ctype" not in context:
+            context["origin_ctype"] = ctype
+
+        cmsg = context["msg"]
+        context["session_id"] = cmsg.from_user_id
+        context["receiver"] = cmsg.other_user_id
+
+        if ctype == ContextType.TEXT:
+            img_match_prefix = check_prefix(content, conf().get("image_create_prefix"))
+            if img_match_prefix:
+                content = content.replace(img_match_prefix, "", 1)
+                context.type = ContextType.IMAGE_CREATE
+            else:
+                context.type = ContextType.TEXT
+            context.content = content.strip()
+
+        return context
+
+    # ── Send reply ─────────────────────────────────────────────────────
+
+    def send(self, reply: Reply, context: Context):
+        receiver = context.get("receiver", "")
+        msg = context.get("msg")
+        context_token = self._get_context_token(receiver, msg)
+
+        if not context_token:
+            logger.error(f"[Weixin] No context_token for receiver={receiver}, cannot send")
+            return
+
+        if reply.type == ReplyType.TEXT:
+            self._send_text(reply.content, receiver, context_token)
+        elif reply.type in (ReplyType.IMAGE_URL, ReplyType.IMAGE):
+            self._send_image(reply.content, receiver, context_token)
+        elif reply.type == ReplyType.FILE:
+            self._send_file(reply.content, receiver, context_token)
+        elif reply.type in (ReplyType.VIDEO, ReplyType.VIDEO_URL):
+            self._send_video(reply.content, receiver, context_token)
+        else:
+            logger.warning(f"[Weixin] Unsupported reply type: {reply.type}, fallback to text")
+            self._send_text(str(reply.content), receiver, context_token)
+
+    def _get_context_token(self, receiver: str, msg=None) -> str:
+        """Get the context_token for a receiver, required for all sends."""
+        if msg and hasattr(msg, "context_token") and msg.context_token:
+            return msg.context_token
+        return self._context_tokens.get(receiver, "")
+
+    def _send_text(self, text: str, receiver: str, context_token: str):
+        if len(text) <= TEXT_CHUNK_LIMIT:
+            try:
+                self.api.send_text(receiver, text, context_token)
+                logger.debug(f"[Weixin] Text sent to {receiver}, len={len(text)}")
+            except Exception as e:
+                logger.error(f"[Weixin] Failed to send text: {e}")
+            return
+
+        chunks = self._split_text(text, TEXT_CHUNK_LIMIT)
+        for i, chunk in enumerate(chunks):
+            try:
+                self.api.send_text(receiver, chunk, context_token)
+                logger.debug(f"[Weixin] Text chunk {i+1}/{len(chunks)} sent to {receiver}, len={len(chunk)}")
+            except Exception as e:
+                logger.error(f"[Weixin] Failed to send text chunk {i+1}/{len(chunks)}: {e}")
+                break
+            if i < len(chunks) - 1:
+                time.sleep(0.5)
+
+    @staticmethod
+    def _split_text(text: str, limit: int) -> list:
+        """Split text into chunks, preferring to break at paragraph or line boundaries."""
+        if len(text) <= limit:
+            return [text]
+        chunks = []
+        while text:
+            if len(text) <= limit:
+                chunks.append(text)
+                break
+            cut = text.rfind("\n\n", 0, limit)
+            if cut <= 0:
+                cut = text.rfind("\n", 0, limit)
+            if cut <= 0:
+                cut = limit
+            chunks.append(text[:cut])
+            text = text[cut:].lstrip("\n")
+        return chunks
+
+    def _send_image(self, img_path_or_url: str, receiver: str, context_token: str):
+        local_path = self._resolve_media_path(img_path_or_url)
+        if not local_path:
+            self._send_text("[Image send failed: file not found]", receiver, context_token)
+            return
+        try:
+            result = upload_media_to_cdn(self.api, local_path, receiver, media_type=1)
+            self.api.send_image_item(
+                to=receiver,
+                context_token=context_token,
+                encrypt_query_param=result["encrypt_query_param"],
+                aes_key_b64=result["aes_key_b64"],
+                ciphertext_size=result["ciphertext_size"],
+            )
+            logger.info(f"[Weixin] Image sent to {receiver}")
+        except Exception as e:
+            logger.error(f"[Weixin] Image send failed: {e}")
+            self._send_text("[Image send failed]", receiver, context_token)
+
+    def _send_file(self, file_path_or_url: str, receiver: str, context_token: str):
+        local_path = self._resolve_media_path(file_path_or_url)
+        if not local_path:
+            self._send_text("[File send failed: file not found]", receiver, context_token)
+            return
+        try:
+            result = upload_media_to_cdn(self.api, local_path, receiver, media_type=3)
+            self.api.send_file_item(
+                to=receiver,
+                context_token=context_token,
+                encrypt_query_param=result["encrypt_query_param"],
+                aes_key_b64=result["aes_key_b64"],
+                file_name=os.path.basename(local_path),
+                file_size=result["raw_size"],
+            )
+            logger.info(f"[Weixin] File sent to {receiver}")
+        except Exception as e:
+            logger.error(f"[Weixin] File send failed: {e}")
+            self._send_text("[File send failed]", receiver, context_token)
+
+    def _send_video(self, video_path_or_url: str, receiver: str, context_token: str):
+        local_path = self._resolve_media_path(video_path_or_url)
+        if not local_path:
+            self._send_text("[Video send failed: file not found]", receiver, context_token)
+            return
+        try:
+            result = upload_media_to_cdn(self.api, local_path, receiver, media_type=2)
+            self.api.send_video_item(
+                to=receiver,
+                context_token=context_token,
+                encrypt_query_param=result["encrypt_query_param"],
+                aes_key_b64=result["aes_key_b64"],
+                ciphertext_size=result["ciphertext_size"],
+            )
+            logger.info(f"[Weixin] Video sent to {receiver}")
+        except Exception as e:
+            logger.error(f"[Weixin] Video send failed: {e}")
+            self._send_text("[Video send failed]", receiver, context_token)
+
+    @staticmethod
+    def _resolve_media_path(path_or_url: str) -> str:
+        """Resolve a file path or URL to a local file path. Downloads if needed."""
+        if not path_or_url:
+            return ""
+
+        local_path = path_or_url
+        if local_path.startswith("file://"):
+            local_path = local_path[7:]
+
+        if local_path.startswith(("http://", "https://")):
+            try:
+                resp = requests.get(local_path, timeout=60)
+                resp.raise_for_status()
+                ct = resp.headers.get("Content-Type", "")
+                ext = ".bin"
+                if "jpeg" in ct or "jpg" in ct:
+                    ext = ".jpg"
+                elif "png" in ct:
+                    ext = ".png"
+                elif "gif" in ct:
+                    ext = ".gif"
+                elif "webp" in ct:
+                    ext = ".webp"
+                elif "mp4" in ct:
+                    ext = ".mp4"
+                elif "pdf" in ct:
+                    ext = ".pdf"
+
+                tmp_path = f"/tmp/wx_media_{uuid.uuid4().hex[:8]}{ext}"
+                with open(tmp_path, "wb") as f:
+                    f.write(resp.content)
+                return tmp_path
+            except Exception as e:
+                logger.error(f"[Weixin] Failed to download media: {e}")
+                return ""
+
+        if os.path.exists(local_path):
+            return local_path
+
+        logger.warning(f"[Weixin] Media file not found: {local_path}")
+        return ""
--- a/channel/weixin/weixin_message.py
+++ b/channel/weixin/weixin_message.py
@@ -0,0 +1,204 @@
+"""
+Weixin ChatMessage implementation.
+
+Parses WeixinMessage from the getUpdates API into the unified ChatMessage format.
+"""
+
+import os
+import uuid
+
+from bridge.context import ContextType
+from channel.chat_message import ChatMessage
+from channel.weixin.weixin_api import download_media_from_cdn, CDN_BASE_URL
+from common.log import logger
+from common.utils import expand_path
+from config import conf
+
+
+# MessageItemType constants from the Weixin protocol
+ITEM_TEXT = 1
+ITEM_IMAGE = 2
+ITEM_VOICE = 3
+ITEM_FILE = 4
+ITEM_VIDEO = 5
+
+
+def _get_tmp_dir() -> str:
+    ws_root = expand_path(conf().get("agent_workspace", "~/cow"))
+    tmp_dir = os.path.join(ws_root, "tmp")
+    os.makedirs(tmp_dir, exist_ok=True)
+    return tmp_dir
+
+
+class WeixinMessage(ChatMessage):
+    """Message wrapper for Weixin channel."""
+
+    def __init__(self, msg: dict, cdn_base_url: str = CDN_BASE_URL):
+        super().__init__(msg)
+
+        self.msg_id = str(msg.get("message_id", msg.get("seq", uuid.uuid4().hex[:8])))
+        self.create_time = msg.get("create_time_ms", 0)
+        self.context_token = msg.get("context_token", "")
+        self.is_group = False  # Weixin plugin only supports direct chat
+        self.is_at = False
+
+        from_user_id = msg.get("from_user_id", "")
+        to_user_id = msg.get("to_user_id", "")
+
+        self.from_user_id = from_user_id
+        self.from_user_nickname = from_user_id
+        self.to_user_id = to_user_id
+        self.to_user_nickname = to_user_id
+        self.other_user_id = from_user_id
+        self.other_user_nickname = from_user_id
+        self.actual_user_id = from_user_id
+        self.actual_user_nickname = from_user_id
+
+        item_list = msg.get("item_list", [])
+
+        # Parse items: find text and media
+        text_body = ""
+        media_item = None
+        media_type = None
+        ref_text = ""
+
+        for item in item_list:
+            itype = item.get("type", 0)
+
+            if itype == ITEM_TEXT:
+                text_item = item.get("text_item", {})
+                text_body = text_item.get("text", "")
+
+                ref = item.get("ref_msg")
+                if ref:
+                    ref_title = ref.get("title", "")
+                    ref_mi = ref.get("message_item", {})
+                    ref_body = ""
+                    if ref_mi.get("type") == ITEM_TEXT:
+                        ref_body = ref_mi.get("text_item", {}).get("text", "")
+                    if ref_title or ref_body:
+                        parts = [p for p in [ref_title, ref_body] if p]
+                        ref_text = f"[引用: {' | '.join(parts)}]\n"
+                    # If ref is a media item, treat it as the media to download
+                    if ref_mi.get("type") in (ITEM_IMAGE, ITEM_VIDEO, ITEM_FILE):
+                        media_item = ref_mi
+                        media_type = ref_mi.get("type")
+
+            elif itype == ITEM_VOICE:
+                voice_item = item.get("voice_item", {})
+                voice_text = voice_item.get("text", "")
+                if voice_text:
+                    text_body = voice_text
+                else:
+                    # Voice without transcription - download the audio
+                    media_item = item
+                    media_type = ITEM_VOICE
+
+            elif itype in (ITEM_IMAGE, ITEM_VIDEO, ITEM_FILE):
+                if not media_item:
+                    media_item = item
+                    media_type = itype
+
+        # Determine ctype and content
+        if media_item and not text_body:
+            self._setup_media(media_item, media_type, cdn_base_url)
+        elif media_item and text_body:
+            # Text + media: download media, attach as file ref in text
+            self.ctype = ContextType.TEXT
+            media_path = self._download_media(media_item, media_type, cdn_base_url)
+            if media_path:
+                if media_type == ITEM_IMAGE:
+                    text_body += f"\n[图片: {media_path}]"
+                elif media_type == ITEM_VIDEO:
+                    text_body += f"\n[视频: {media_path}]"
+                else:
+                    text_body += f"\n[文件: {media_path}]"
+            self.content = ref_text + text_body
+        else:
+            self.ctype = ContextType.TEXT
+            self.content = ref_text + text_body
+
+    def _setup_media(self, item: dict, media_type: int, cdn_base_url: str):
+        """Set up message as a media type, with lazy download via _prepare_fn."""
+        if media_type == ITEM_IMAGE:
+            self.ctype = ContextType.IMAGE
+            image_path = self._download_media(item, ITEM_IMAGE, cdn_base_url)
+            if image_path:
+                self.content = image_path
+                self.image_path = image_path
+            else:
+                self.ctype = ContextType.TEXT
+                self.content = "[Image download failed]"
+
+        elif media_type == ITEM_VIDEO:
+            self.ctype = ContextType.FILE
+            save_path = os.path.join(_get_tmp_dir(), f"wx_{self.msg_id}.mp4")
+            self.content = save_path
+
+            def _download():
+                path = self._download_media(item, ITEM_VIDEO, cdn_base_url)
+                if path:
+                    self.content = path
+            self._prepare_fn = _download
+
+        elif media_type == ITEM_FILE:
+            self.ctype = ContextType.FILE
+            file_name = item.get("file_item", {}).get("file_name", f"wx_{self.msg_id}")
+            save_path = os.path.join(_get_tmp_dir(), file_name)
+            self.content = save_path
+
+            def _download():
+                path = self._download_media(item, ITEM_FILE, cdn_base_url)
+                if path:
+                    self.content = path
+            self._prepare_fn = _download
+
+        elif media_type == ITEM_VOICE:
+            self.ctype = ContextType.VOICE
+            save_path = os.path.join(_get_tmp_dir(), f"wx_{self.msg_id}.silk")
+            self.content = save_path
+
+            def _download():
+                path = self._download_media(item, ITEM_VOICE, cdn_base_url)
+                if path:
+                    self.content = path
+            self._prepare_fn = _download
+
+    def _download_media(self, item: dict, media_type: int, cdn_base_url: str) -> str:
+        """Download media from CDN, returns local file path or empty string."""
+        type_key_map = {
+            ITEM_IMAGE: "image_item",
+            ITEM_VIDEO: "video_item",
+            ITEM_FILE: "file_item",
+            ITEM_VOICE: "voice_item",
+        }
+        key = type_key_map.get(media_type, "")
+        info = item.get(key, {})
+        media = info.get("media", {})
+
+        encrypt_param = media.get("encrypt_query_param", "")
+        # aes_key can be in image_item.aeskey (hex) or media.aes_key (b64)
+        aes_key = info.get("aeskey", "") or media.get("aes_key", "")
+
+        if not encrypt_param or not aes_key:
+            logger.warning(f"[Weixin] Missing CDN params for media download (type={media_type})")
+            return ""
+
+        if media_type == ITEM_FILE:
+            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)
+            logger.info(f"[Weixin] Media downloaded: {save_path}")
+            return save_path
+        except Exception as e:
+            logger.error(f"[Weixin] Media download failed: {e}")
+            return ""
--- a/cli/VERSION
+++ b/cli/VERSION
@@ -0,0 +1 @@
+2.0.5
--- a/cli/init.py
+++ b/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()
--- a/cli/main.py
+++ b/cli/main.py
@@ -0,0 +1,4 @@
+"""Allow running as: python -m cli"""
+from cli.cli import main
+
+main()
--- a/cli/cli.py
+++ b/cli/cli.py
@@ -0,0 +1,79 @@
+"""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
+from cli.commands.install import install_browser
+from cli.commands.knowledge import knowledge
+
+
+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.
+  knowledge  Manage knowledge base.
+  install-browser  Install browser tool (Playwright + Chromium).
+
+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)
+main.add_command(knowledge)
+main.add_command(install_browser)
+
+
+if __name__ == '__main__':
+    main()
--- a/cli/commands/init.py
+++ b/cli/commands/init.py
--- a/cli/commands/context.py
+++ b/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")
--- a/cli/commands/install.py
+++ b/cli/commands/install.py
@@ -0,0 +1,259 @@
+"""cow install-browser - Install Playwright + Chromium for the browser tool."""
+
+import os
+import sys
+import subprocess
+from typing import Callable, Optional
+
+import click
+
+PLAYWRIGHT_VERSION = "1.52.0"
+PLAYWRIGHT_LEGACY_VERSION = "1.28.0"
+GLIBC_THRESHOLD = (2, 28)
+CHINA_MIRROR = "https://registry.npmmirror.com/-/binary/playwright"
+
+# stream(msg, fg=None) — fg is "yellow" | "green" | "red" | None
+StreamFn = Callable[[str, Optional[str]], None]
+# on_phase(msg) — coarse-grained progress for chat channels (Chinese)
+PhaseFn = Callable[[str], None]
+
+
+def _phase(cb: Optional[PhaseFn], msg: str) -> None:
+    if cb:
+        cb(msg)
+
+
+def _has_display() -> bool:
+    """Check if a graphical display is available (Linux only)."""
+    return bool(os.environ.get("DISPLAY") or os.environ.get("WAYLAND_DISPLAY"))
+
+
+def _is_headless_linux() -> bool:
+    return sys.platform == "linux" and not _has_display()
+
+
+def _get_installed_version() -> str:
+    try:
+        out = subprocess.check_output(
+            [sys.executable, "-c", "import playwright; print(playwright.__version__)"],
+            stderr=subprocess.DEVNULL,
+        )
+        return out.decode().strip()
+    except Exception:
+        return ""
+
+
+def _version_tuple(v: str):
+    try:
+        return tuple(int(x) for x in v.split(".")[:3])
+    except (ValueError, AttributeError):
+        return (0, 0, 0)
+
+
+def _get_glibc_version():
+    if sys.platform != "linux":
+        return None
+    try:
+        import ctypes
+        libc = ctypes.CDLL("libc.so.6")
+        gnu_get_libc_version = libc.gnu_get_libc_version
+        gnu_get_libc_version.restype = ctypes.c_char_p
+        ver = gnu_get_libc_version().decode()
+        parts = ver.split(".")
+        return (int(parts[0]), int(parts[1]))
+    except Exception:
+        return None
+
+
+def _is_china_network() -> bool:
+    try:
+        out = subprocess.check_output(
+            [sys.executable, "-m", "pip", "config", "get", "global.index-url"],
+            stderr=subprocess.DEVNULL,
+        )
+        url = out.decode().strip().lower()
+        return any(kw in url for kw in ("tsinghua", "aliyun", "npmmirror", "douban", "ustc", "huawei", "tencentyun"))
+    except Exception:
+        return False
+
+
+def _pip_install(package_spec: str, stream: StreamFn) -> int:
+    """Install a package, retrying with --user on permission failure."""
+    python = sys.executable
+    ret = subprocess.call([python, "-m", "pip", "install", package_spec])
+    if ret != 0:
+        stream("  Retrying with --user flag...", "yellow")
+        ret = subprocess.call([python, "-m", "pip", "install", "--user", package_spec])
+    return ret
+
+
+def _default_stream(msg: str, fg: Optional[str] = None) -> None:
+    """CLI: colored click output."""
+    if fg == "yellow":
+        click.echo(click.style(msg, fg="yellow"))
+    elif fg == "green":
+        click.echo(click.style(msg, fg="green"))
+    elif fg == "red":
+        click.echo(click.style(msg, fg="red"))
+    else:
+        click.echo(msg)
+
+
+def run_install_browser(
+    stream: Optional[StreamFn] = None,
+    on_phase: Optional[PhaseFn] = None,
+) -> int:
+    """
+    Install Playwright Python package, optional Linux deps, and Chromium.
+
+    Reused by ``cow install-browser`` CLI and chat ``/install-browser``.
+
+    Args:
+        stream: Optional callback ``(message, fg)`` for each line. ``fg`` is
+            ``yellow`` / ``green`` / ``red`` or None. Defaults to colored click output.
+        on_phase: Optional callback for coarse progress (e.g. push to chat);
+            messages are short Chinese status lines.
+
+    Returns:
+        0 on success, 1 on fatal failure (pip or chromium install failed).
+    """
+    stream = stream or _default_stream
+    python = sys.executable
+    legacy_mode = False
+
+    _phase(on_phase, "🔧 开始安装浏览器工具依赖（约几分钟，请耐心等待）…")
+
+    glibc = _get_glibc_version()
+    if glibc and glibc < GLIBC_THRESHOLD:
+        legacy_mode = True
+        glibc_str = f"{glibc[0]}.{glibc[1]}"
+        stream(
+            f"glibc {glibc_str} detected (< 2.28). "
+            f"Will install playwright {PLAYWRIGHT_LEGACY_VERSION} for compatibility.",
+            "yellow",
+        )
+        stream("  Note: upgrade your OS for full browser tool support.", "yellow")
+        stream("")
+        _phase(
+            on_phase,
+            f"ℹ️ 检测到 glibc {glibc_str}（较旧），将安装兼容版 Playwright {PLAYWRIGHT_LEGACY_VERSION}。",
+        )
+
+    target_version = PLAYWRIGHT_LEGACY_VERSION if legacy_mode else PLAYWRIGHT_VERSION
+
+    _phase(on_phase, "📦 [1/3] 正在安装 Playwright Python 包…")
+    stream("[1/3] Installing playwright Python package...", "yellow")
+    ret = _pip_install(f"playwright=={target_version}", stream)
+    if ret != 0:
+        stream("Failed to install playwright package.", "red")
+        _phase(on_phase, "❌ [1/3] Playwright Python 包安装失败。")
+        return 1
+
+    installed = _get_installed_version()
+    if installed:
+        stream(f"  playwright {installed} installed.", "green")
+    stream("")
+    _phase(on_phase, f"✅ [1/3] Playwright 包已安装（{installed or target_version}）。")
+
+    if sys.platform == "linux":
+        _phase(on_phase, "🔧 [2/3] 正在安装 Linux 系统依赖与轻量中文字体（文泉驿正黑，部分步骤可能需要 sudo）…")
+        stream("[2/3] Installing system dependencies (Linux)...", "yellow")
+        ret = subprocess.call([python, "-m", "playwright", "install-deps", "chromium"])
+        if ret != 0:
+            stream(
+                "  Could not auto-install system deps (may need sudo).\n"
+                f"  Run manually: sudo {python} -m playwright install-deps chromium",
+                "yellow",
+            )
+        # Prefer fonts-wqy-zenhei only (~few MB). fonts-noto-cjk is much larger (~150MB+).
+        stream("  Installing CJK font (fonts-wqy-zenhei, lightweight)...")
+        font_ret = subprocess.call(
+            ["sudo", "apt-get", "install", "-y", "--no-install-recommends", "fonts-wqy-zenhei"],
+            stderr=subprocess.DEVNULL,
+        )
+        if font_ret != 0:
+            stream(
+                "  Could not auto-install CJK font.\n"
+                "  Run manually: sudo apt-get install -y fonts-wqy-zenhei\n"
+                "  (Optional, larger full coverage: sudo apt-get install -y fonts-noto-cjk)",
+                "yellow",
+            )
+        else:
+            subprocess.call(["fc-cache", "-fv"], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
+            stream("  CJK font (wqy-zenhei) installed.", "green")
+        _phase(
+            on_phase,
+            "✅ [2/3] Linux 依赖与字体步骤已执行（若有权限问题请查看服务器日志或手动执行提示命令）。",
+        )
+    else:
+        stream(f"[2/3] Skipping system deps (not needed on {sys.platform}).", "yellow")
+        _phase(on_phase, f"ℹ️ [2/3] 当前系统（{sys.platform}）跳过 Linux 专用依赖。")
+    stream("")
+
+    _phase(on_phase, "🌐 [3/3] 正在下载并安装 Chromium（体积较大，请耐心等待）…")
+    stream("[3/3] Installing Chromium browser...", "yellow")
+    cmd = [python, "-m", "playwright", "install", "chromium"]
+
+    if _is_headless_linux() and not legacy_mode:
+        ver = _version_tuple(installed or "")
+        if ver >= (1, 57, 0):
+            cmd.append("--only-shell")
+            stream("  (headless shell for Linux server)", None)
+        else:
+            stream("  (full Chromium)", None)
+    elif sys.platform == "linux" and _has_display():
+        stream("  (full browser for Linux desktop)", None)
+
+    env = os.environ.copy()
+    use_mirror = _is_china_network()
+    if use_mirror:
+        env["PLAYWRIGHT_DOWNLOAD_HOST"] = CHINA_MIRROR
+        stream(f"  (using China mirror: {CHINA_MIRROR})", None)
+        _phase(on_phase, "📡 检测到国内 pip 源配置，Chromium 将优先走国内镜像下载。")
+
+    ret = subprocess.call(cmd, env=env)
+
+    if ret != 0 and use_mirror:
+        stream("  Mirror download failed, retrying with official CDN...", "yellow")
+        _phase(on_phase, "⚠️ 镜像下载失败，正在改用官方源重试…")
+        env_no_mirror = os.environ.copy()
+        env_no_mirror.pop("PLAYWRIGHT_DOWNLOAD_HOST", None)
+        ret = subprocess.call(cmd, env=env_no_mirror)
+
+    if ret != 0:
+        stream("Failed to install Chromium.", "red")
+        _phase(on_phase, "❌ [3/3] Chromium 安装失败。")
+        return 1
+
+    stream("")
+    _phase(on_phase, "✅ [3/3] Chromium 已安装。")
+
+    stream("Verifying browser installation...", None)
+    _phase(on_phase, "🔍 正在验证 Playwright 能否正常加载…")
+    ret = subprocess.call(
+        [python, "-c", "from playwright.sync_api import sync_playwright; print('OK')"],
+        stderr=subprocess.DEVNULL,
+    )
+    if ret != 0:
+        stream(
+            "  Warning: playwright import failed. Browser tool may not work on this system.\n"
+            "  Consider upgrading your OS or using Docker.",
+            "yellow",
+        )
+        _phase(on_phase, "⚠️ 验证未完全通过：本机可能仍无法使用浏览器工具，请查看日志或升级系统。")
+    else:
+        stream("  Verification passed.", "green")
+        _phase(on_phase, "✅ 验证通过。")
+
+    stream("")
+    stream("Browser tool ready! Restart CowAgent to enable it.", "green")
+    _phase(on_phase, "🎉 全部步骤结束。请重启 CowAgent 后使用 browser 工具。")
+    return 0
+
+
+@click.command("install-browser")
+def install_browser():
+    """Install browser tool dependencies (Playwright + Chromium)."""
+    code = run_install_browser()
+    if code != 0:
+        raise SystemExit(code)
--- a/cli/commands/knowledge.py
+++ b/cli/commands/knowledge.py
@@ -0,0 +1,121 @@
+"""cow knowledge - Knowledge base management commands."""
+
+import os
+
+import click
+
+from cli.utils import get_project_root
+
+
+def _get_knowledge_dir():
+    """Resolve the knowledge directory path from config or default."""
+    try:
+        import sys
+        sys.path.insert(0, get_project_root())
+        from config import conf
+        from common.utils import expand_path
+        workspace = expand_path(conf().get("agent_workspace", "~/cow"))
+    except Exception:
+        workspace = os.path.expanduser("~/cow")
+    return os.path.join(workspace, "knowledge")
+
+
+def _get_knowledge_enabled():
+    try:
+        import sys
+        sys.path.insert(0, get_project_root())
+        from config import conf
+        return conf().get("knowledge", True)
+    except Exception:
+        return True
+
+
+@click.group(invoke_without_command=True)
+@click.pass_context
+def knowledge(ctx):
+    """Manage CowAgent knowledge base."""
+    if ctx.invoked_subcommand is None:
+        click.echo(_stats())
+
+
+@knowledge.command("list")
+def knowledge_list():
+    """Display knowledge base file tree."""
+    click.echo(_tree())
+
+
+def _stats() -> str:
+    knowledge_dir = _get_knowledge_dir()
+    if not os.path.isdir(knowledge_dir):
+        return "Knowledge base directory not found."
+
+    enabled = _get_knowledge_enabled()
+    total_files = 0
+    total_bytes = 0
+    cat_count = {}
+
+    for root, dirs, files in os.walk(knowledge_dir):
+        dirs[:] = [d for d in dirs if not d.startswith(".")]
+        rel_root = os.path.relpath(root, knowledge_dir)
+        category = rel_root.split(os.sep)[0] if rel_root != "." else "root"
+        for f in files:
+            if f.endswith(".md") and f not in ("index.md", "log.md"):
+                total_files += 1
+                total_bytes += os.path.getsize(os.path.join(root, f))
+                cat_count[category] = cat_count.get(category, 0) + 1
+
+    status_icon = click.style("enabled", fg="green") if enabled else click.style("disabled", fg="red")
+    lines = [
+        f"\n  Knowledge Base  [{status_icon}]",
+        "",
+        f"  Pages:  {total_files}",
+        f"  Size:   {total_bytes / 1024:.1f} KB",
+        "",
+    ]
+    if cat_count:
+        lines.append("  Categories:")
+        for cat in sorted(cat_count.keys()):
+            lines.append(f"    {cat}/  ({cat_count[cat]} pages)")
+        lines.append("")
+
+    lines.append(f"  Path: {knowledge_dir}")
+    lines.append("")
+    return "\n".join(lines)
+
+
+def _tree() -> str:
+    knowledge_dir = _get_knowledge_dir()
+    if not os.path.isdir(knowledge_dir):
+        return "Knowledge base directory not found."
+
+    tree_lines = ["  knowledge/"]
+
+    subdirs = sorted([
+        d for d in os.listdir(knowledge_dir)
+        if os.path.isdir(os.path.join(knowledge_dir, d)) and not d.startswith(".")
+    ])
+
+    for i, subdir in enumerate(subdirs):
+        is_last_dir = (i == len(subdirs) - 1)
+        branch = "└── " if is_last_dir else "├── "
+        subdir_path = os.path.join(knowledge_dir, subdir)
+        md_files = sorted([
+            f for f in os.listdir(subdir_path)
+            if f.endswith(".md") and not f.startswith(".")
+        ])
+        tree_lines.append(f"  {branch}{subdir}/ ({len(md_files)})")
+
+        child_prefix = "      " if is_last_dir else "  │   "
+        max_show = 15
+        for j, fname in enumerate(md_files[:max_show]):
+            is_last_file = (j == len(md_files[:max_show]) - 1) and len(md_files) <= max_show
+            fb = "└── " if is_last_file else "├── "
+            name = fname.replace(".md", "")
+            tree_lines.append(f"{child_prefix}{fb}{name}")
+        if len(md_files) > max_show:
+            tree_lines.append(f"{child_prefix}└── ... +{len(md_files) - max_show} more")
+
+    if not subdirs:
+        tree_lines.append("  (empty)")
+
+    return "\n" + "\n".join(tree_lines) + "\n"
--- a/cli/commands/process.py
+++ b/cli/commands/process.py
@@ -0,0 +1,317 @@
+"""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. Stop service first so git pull won't conflict with running code
+    ctx.invoke(stop)
+
+    # 2. Git pull
+    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.")
+
+    python = sys.executable
+    req_file = os.path.join(root, "requirements.txt")
+
+    if _IS_WIN:
+        # On Windows, `cow.exe` (this process) locks the exe file, so
+        # `pip install -e .` fails with WinError 5.  Write a small .bat
+        # helper that waits for cow.exe to exit, then installs & starts.
+        bat = os.path.join(root, "_cow_update.bat")
+        lines = [
+            "@echo off",
+            "chcp 65001 >nul",
+            "echo Waiting for cow.exe to exit...",
+            "timeout /t 3 /nobreak >nul",
+        ]
+        if os.path.exists(req_file):
+            lines.append(f'echo Installing dependencies...')
+            lines.append(f'"{python}" -m pip install -r requirements.txt -q')
+        lines += [
+            "echo Reinstalling cow CLI...",
+            f'"{python}" -m pip install -e . -q',
+            "echo Starting CowAgent...",
+            f'"{python}" -m cli.cli start --no-logs',
+            "echo.",
+            "echo Update complete. You can close this window.",
+            "pause >nul",
+            "del \"%~f0\"",
+        ]
+        with open(bat, "w", encoding="utf-8") as f:
+            f.write("\n".join(lines) + "\n")
+
+        subprocess.Popen(
+            ["cmd.exe", "/c", "start", "CowAgent Update", "/wait", bat],
+            cwd=root,
+        )
+        click.echo(click.style(
+            "✓ Update script launched. Please follow the new window for progress.",
+            fg="green"))
+    else:
+        # 3. Install dependencies
+        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=False)
+
+
+@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
--- a/cli/commands/skill.py
+++ b/cli/commands/skill.py
--- a/cli/utils.py
+++ b/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"
--- a/common/cloud_client.py
+++ b/common/cloud_client.py
@@ -3,6 +3,18 @@ Cloud management client for connecting to the LinkAI control console.

 Handles remote configuration sync, message push, and skill management
 via the LinkAI socket protocol.
+
+NOTE: By default, no cloud-related config is enabled. The application runs
+entirely locally without connecting to any remote service. The cloud client
+is only activated when BOTH of the following conditions are met:
+
+  1. ``use_linkai`` is set to True in config (checked in app.py before
+     importing this module).
+  2. ``cloud_deployment_id`` (or env CLOUD_DEPLOYMENT_ID) is non-empty
+     (checked in app.py and again in the ``start()`` function below).
+
+If either condition is missing, this module is never loaded and the
+program continues as a purely local application.
 """

 from bridge.context import Context, ContextType
@@ -35,13 +47,14 @@ CREDENTIAL_MAP = {


 class CloudClient(LinkAIClient):
-    def __init__(self, api_key: str, channel, host: str = ""):
-        super().__init__(api_key, host)
+    def __init__(self, api_key: str, channel, host: str = "", port=None):
+        super().__init__(api_key, host, port=port)
        self.channel = channel
        self.client_type = channel.channel_type
        self.channel_mgr = None
        self._skill_service = None
        self._memory_service = None
+        self._knowledge_service = None
        self._chat_service = None

    @property
@@ -76,6 +89,21 @@ class CloudClient(LinkAIClient):
                logger.error(f"[CloudClient] Failed to init MemoryService: {e}")
        return self._memory_service

+    @property
+    def knowledge_service(self):
+        """Lazy-init KnowledgeService."""
+        if self._knowledge_service is None:
+            try:
+                from agent.knowledge.service import KnowledgeService
+                from config import conf
+                from common.utils import expand_path
+                workspace_root = expand_path(conf().get("agent_workspace", "~/cow"))
+                self._knowledge_service = KnowledgeService(workspace_root)
+                logger.debug("[CloudClient] KnowledgeService initialised")
+            except Exception as e:
+                logger.error(f"[CloudClient] Failed to init KnowledgeService: {e}")
+        return self._knowledge_service
+
    @property
    def chat_service(self):
        """Lazy-init ChatService (requires AgentBridge via Bridge singleton)."""
@@ -201,27 +229,43 @@ class CloudClient(LinkAIClient):

    def _handle_channel_create(self, channel_type: str, data: dict):
        local_config = conf()
-        self._set_channel_credentials(local_config, channel_type,
-                                      data.get("appId"), data.get("appSecret"))
+        cred_changed = self._set_channel_credentials(
+            local_config, channel_type, data.get("appId"), data.get("appSecret"))
        self._add_channel_type(local_config, channel_type)
        self._save_config_to_file(local_config)

-        if self.channel_mgr:
+        if not self.channel_mgr:
+            return
+
+        existing_ch = self.channel_mgr.get_channel(channel_type)
+        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(
-                target=self._do_add_channel, args=(channel_type,), daemon=True
+                target=self._report_channel_startup, args=(channel_type,), daemon=True
            ).start()
+            return
+
+        threading.Thread(
+            target=self._do_add_channel, args=(channel_type,), daemon=True
+        ).start()

    def _handle_channel_update(self, channel_type: str, data: dict):
        local_config = conf()
        enabled = data.get("enabled", "Y")

-        self._set_channel_credentials(local_config, channel_type,
-                                      data.get("appId"), data.get("appSecret"))
+        cred_changed = self._set_channel_credentials(
+            local_config, channel_type, data.get("appId"), data.get("appSecret"))
        if enabled == "N":
            self._remove_channel_type(local_config, channel_type)
        else:
-            # Ensure channel_type is persisted even if this channel was not
-            # previously listed (e.g. update used as implicit create).
            self._add_channel_type(local_config, channel_type)
        self._save_config_to_file(local_config)

@@ -233,9 +277,24 @@ class CloudClient(LinkAIClient):
                target=self._do_remove_channel, args=(channel_type,), daemon=True
            ).start()
        else:
-            threading.Thread(
-                target=self._do_restart_channel, args=(self.channel_mgr, channel_type), daemon=True
-            ).start()
+            existing_ch = self.channel_mgr.get_channel(channel_type)
+            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(
+                    target=self._report_channel_startup, args=(channel_type,), daemon=True
+                ).start()
+            else:
+                threading.Thread(
+                    target=self._do_restart_channel, args=(self.channel_mgr, channel_type), daemon=True
+                ).start()

    def _handle_channel_delete(self, channel_type: str, data: dict):
        local_config = conf()
@@ -243,11 +302,27 @@ class CloudClient(LinkAIClient):
        self._remove_channel_type(local_config, channel_type)
        self._save_config_to_file(local_config)

+        if channel_type in ("weixin", "wx"):
+            self._remove_weixin_credentials()
+
        if self.channel_mgr:
            threading.Thread(
                target=self._do_remove_channel, args=(channel_type,), daemon=True
            ).start()

+    @staticmethod
+    def _remove_weixin_credentials():
+        """Remove the weixin token credentials file so next connect triggers QR login."""
+        cred_path = os.path.expanduser(
+            conf().get("weixin_credentials_path", "~/.weixin_cow_credentials.json")
+        )
+        try:
+            if os.path.exists(cred_path):
+                os.remove(cred_path)
+                logger.info(f"[CloudClient] Removed weixin credentials: {cred_path}")
+        except Exception as e:
+            logger.warning(f"[CloudClient] Failed to remove weixin credentials: {e}")
+
    # ------------------------------------------------------------------
    # channel credentials helpers
    # ------------------------------------------------------------------
@@ -322,7 +397,7 @@ class CloudClient(LinkAIClient):
            self.channel_mgr.add_channel(channel_type)
            logger.info(f"[CloudClient] Channel '{channel_type}' added successfully")
        except Exception as e:
-            logger.error(f"[CloudClient] Failed to add channel '{channel_type}': {e}")
+            logger.error(f"[CloudClient] Failed to add channel '{channel_type}': {e}", exc_info=True)
            self.send_channel_status(channel_type, "error", str(e))
            return
        self._report_channel_startup(channel_type)
@@ -334,12 +409,31 @@ class CloudClient(LinkAIClient):
        except Exception as e:
            logger.error(f"[CloudClient] Failed to remove channel '{channel_type}': {e}")

+    def send_channel_qrcode(self, channel_type: str, qrcode_url: str):
+        """Report QR code URL for a channel that requires scan-to-login."""
+        if self.client_id:
+            from linkai.api.client.client import ClientMsgType
+            msg = self._build_package(ClientMsgType.CHANNEL_STATUS)
+            msg["data"]["channelType"] = channel_type
+            msg["data"]["status"] = "qrcode"
+            msg["data"]["qrcodeUrl"] = qrcode_url
+            self._send_package(msg)
+            logger.info(f"[CloudClient] Sent QR code status for '{channel_type}'")
+
    def _report_channel_startup(self, channel_type: str):
        """Wait for channel startup result and report to cloud."""
        ch = self.channel_mgr.get_channel(channel_type)
        if not ch:
            self.send_channel_status(channel_type, "error", "channel instance not found")
            return
+
+        if channel_type in ("weixin", "wx") and hasattr(ch, "login_status"):
+            login_status = getattr(ch, "login_status", "")
+            if login_status in ("waiting_scan", "scanned", "idle"):
+                logger.info(f"[CloudClient] Channel '{channel_type}' is waiting for QR login, "
+                            "skip reporting connected")
+                return
+
        success, error = ch.wait_startup(timeout=3)
        if success:
            logger.info(f"[CloudClient] Channel '{channel_type}' connected, reporting status")
@@ -390,6 +484,27 @@ class CloudClient(LinkAIClient):

        return svc.dispatch(action, payload)

+    # ------------------------------------------------------------------
+    # knowledge callback
+    # ------------------------------------------------------------------
+    def on_knowledge(self, data: dict) -> dict:
+        """
+        Handle KNOWLEDGE messages from the cloud console.
+        Delegates to KnowledgeService.dispatch for the actual operations.
+
+        :param data: message data with 'action', 'clientId', 'payload'
+        :return: response dict
+        """
+        action = data.get("action", "")
+        payload = data.get("payload")
+        logger.info(f"[CloudClient] on_knowledge: action={action}")
+
+        svc = self.knowledge_service
+        if svc is None:
+            return {"action": action, "code": 500, "message": "KnowledgeService not available", "payload": None}
+
+        return svc.dispatch(action, payload)
+
    # ------------------------------------------------------------------
    # chat callback
    # ------------------------------------------------------------------
@@ -409,6 +524,19 @@ class CloudClient(LinkAIClient):
            session_id = f"session_{session_id}"
        logger.info(f"[CloudClient] on_chat: session={session_id}, channel={channel_type}, query={query[:80]}")

+        # Intercept cow/slash commands before the agent runs
+        try:
+            from plugins import PluginManager
+            mgr = PluginManager()
+            instance = mgr.instances.get("COW_CLI")
+            if instance and hasattr(instance, "execute"):
+                result = instance.execute(query, session_id=session_id)
+                if result is not None:
+                    send_chunk_fn({"chunk_type": "content", "delta": result, "segment_id": 0})
+                    return
+        except Exception as e:
+            logger.warning(f"[CloudClient] cow_cli intercept failed: {e}")
+
        svc = self.chat_service
        if svc is None:
            raise RuntimeError("ChatService not available")
@@ -551,9 +679,9 @@ def get_deployment_id() -> str:


 def get_website_base_url() -> str:
-    """Return the public URL prefix that maps to the workspace websites/ dir.
+    """Return the URL prefix that maps to the workspace websites/ dir.

-    Returns empty string when cloud deployment is not configured.
+    Do nothing when in local env.
    """
    deployment_id = get_deployment_id()
    if not deployment_id:
@@ -570,6 +698,42 @@ def get_website_base_url() -> str:
    return f"https://app.{domain}/{deployment_id}"


+# Subdir under websites/ used by the send tool
+COW_SEND_WEB_SUBDIR = "cow-send"
+
+
+def copy_send_file(src_path: str, workspace_root: str) -> str:
+    """Copy *src_path* into ``websites/cow-send/`` and return its URL.
+
+    Returns empty string in local env.
+    """
+    import shutil
+    import uuid
+
+    from common.utils import expand_path
+
+    base = get_website_base_url()
+    if not base or not src_path or not os.path.isfile(src_path):
+        return ""
+    ws = os.path.abspath(expand_path(workspace_root))
+    send_dir = os.path.join(ws, "websites", COW_SEND_WEB_SUBDIR)
+    try:
+        os.makedirs(send_dir, exist_ok=True)
+    except OSError:
+        return ""
+    ext = os.path.splitext(src_path)[1].lower()
+    if len(ext) > 12 or not ext.replace(".", "").isalnum():
+        ext = ""
+    dest_name = f"{uuid.uuid4().hex}{ext}"
+    dest_path = os.path.join(send_dir, dest_name)
+    try:
+        shutil.copy2(src_path, dest_path)
+    except OSError as e:
+        logger.warning(f"[cloud] copy_send_file: copy failed: {e}")
+        return ""
+    return f"{base}/{COW_SEND_WEB_SUBDIR}/{dest_name}"
+
+
 def build_website_prompt(workspace_dir: str) -> list:
    """Build system prompt lines for cloud website/file sharing rules.

@@ -590,8 +754,8 @@ def build_website_prompt(workspace_dir: str) -> list:
        f"   - 例如: `websites/my-app/index.html` → `{base_url}/my-app/index.html`",
        "",
        "2. **生成文件分享** (PPT、PDF、图片、音视频等): 当你为用户生成了需要下载或查看的文件时，**可以**将文件保存到 `websites/` 目录中",
-        f"   - 例如: 生成的PPT保存到 `websites/files/report.pptx` → 下载链接为 `{base_url}/files/report.pptx`",
-        "   - 你仍然可以同时使用 `send` 工具发送文件（在飞书、钉钉等IM渠道中有效），但**必须同时在回复文本中提供下载链接**作为兜底，因为部分渠道（如网页端）无法通过 send 接收本地文件",
+        f"  - 例如: 生成的PPT保存到 `websites/files/report.pptx` → 下载链接为 `{base_url}/files/report.pptx`",
+        "   - 你仍然可以同时使用 `send` 工具发送文件（在微信、飞书、钉钉、web等渠道中有效），但**必须同时在回复文本中提供下载链接**作为兜底，因为部分渠道无法通过 send 接收本地文件",
        "",
        "3. **必须发送链接**: 无论是网页还是文件，生成后**必须将完整的访问/下载链接直接写在回复文本中发送给用户**",
        "",
@@ -602,8 +766,11 @@ def build_website_prompt(workspace_dir: str) -> list:
    ]

 def start(channel, channel_mgr=None):
+    if not get_deployment_id():
+        return
+
    global chat_client
-    chat_client = CloudClient(api_key=conf().get("linkai_api_key"), host=conf().get("cloud_host", ""), channel=channel)
+    chat_client = CloudClient(api_key=conf().get("linkai_api_key"), host=conf().get("cloud_host", ""), port=conf().get("cloud_port"), channel=channel)
    chat_client.channel_mgr = channel_mgr
    chat_client.config = _build_config()
    chat_client.start()
--- a/common/const.py
+++ b/common/const.py
@@ -1,13 +1,14 @@
 # 厂商类型
 OPEN_AI = "openAI"
-CHATGPT = "chatGPT"
+OPENAI = "openai"
+CHATGPT = "chatGPT"  # legacy alias for OPENAI, kept for backward compatibility
 BAIDU = "baidu"
 XUNFEI = "xunfei"
 CHATGPTONAZURE = "chatGPTOnAzure"
 LINKAI = "linkai"
 CLAUDEAPI= "claudeAPI"
-QWEN = "qwen"  # 旧版千问接入
-QWEN_DASHSCOPE = "dashscope"  # 新版千问接入(百炼)
+QWEN = "qwen"  # 千问 (兼容旧配置，实际走 DashscopeBot)
+QWEN_DASHSCOPE = "dashscope"  # 千问 DashScope 接入
 GEMINI = "gemini" 
 ZHIPU_AI = "zhipu"  
 MOONSHOT = "moonshot"
@@ -68,6 +69,8 @@ GPT_5 = "gpt-5"
 GPT_5_MINI = "gpt-5-mini"
 GPT_5_NANO = "gpt-5-nano"
 GPT_54 = "gpt-5.4"  # GPT-5.4 - Agent recommended model
+GPT_54_MINI = "gpt-5.4-mini"
+GPT_54_NANO = "gpt-5.4-nano"
 O1 = "o1-preview"
 O1_MINI = "o1-mini"
 WHISPER_1 = "whisper-1"
@@ -78,25 +81,28 @@ TTS_1_HD = "tts-1-hd"
 DEEPSEEK_CHAT = "deepseek-chat"  # DeepSeek-V3对话模型
 DEEPSEEK_REASONER = "deepseek-reasoner"  # DeepSeek-R1模型

-# Qwen (通义千问 - 阿里云)
-QWEN = "qwen"
+# Qwen (通义千问 - 阿里云 DashScope)
 QWEN_TURBO = "qwen-turbo"
 QWEN_PLUS = "qwen-plus"
 QWEN_MAX = "qwen-max"
 QWEN_LONG = "qwen-long"
 QWEN3_MAX = "qwen3-max"  # Qwen3 Max - Agent推荐模型
 QWEN35_PLUS = "qwen3.5-plus"  # Qwen3.5 Plus - Omni model (MultiModalConversation)
+QWEN36_PLUS = "qwen3.6-plus"  # Qwen3.6 Plus - Omni model (MultiModalConversation)
 QWQ_PLUS = "qwq-plus"

 # MiniMax
-MINIMAX_M2_5 = "MiniMax-M2.5"  # MiniMax M2.5 - Latest
-MINIMAX_M2_1 = "MiniMax-M2.1"  # MiniMax M2.1 - Agent推荐模型
+MINIMAX_M2_7 = "MiniMax-M2.7"  # MiniMax M2.7 - Latest
+MINIMAX_M2_7_HIGHSPEED = "MiniMax-M2.7-highspeed"  # MiniMax M2.7 highspeed
+MINIMAX_M2_5 = "MiniMax-M2.5"  # MiniMax M2.5
+MINIMAX_M2_1 = "MiniMax-M2.1"  # MiniMax M2.1
 MINIMAX_M2_1_LIGHTNING = "MiniMax-M2.1-lightning"  # MiniMax M2.1 极速版
 MINIMAX_M2 = "MiniMax-M2"  # MiniMax M2
 MINIMAX_ABAB6_5 = "abab6.5-chat"  # MiniMax abab6.5

 # GLM (智谱AI)
-GLM_5 = "glm-5"  # 智谱 GLM-5 - Latest
+GLM_5_TURBO = "glm-5-turbo"  # 智谱 GLM-5-Turbo - Latest
+GLM_5 = "glm-5"  # 智谱 GLM-5
 GLM_4 = "glm-4"
 GLM_4_PLUS = "glm-4-plus"
 GLM_4_flash = "glm-4-flash"
@@ -119,6 +125,10 @@ DOUBAO_SEED_2_PRO = "doubao-seed-2-0-pro-260215"
 DOUBAO_SEED_2_LITE = "doubao-seed-2-0-lite-260215"
 DOUBAO_SEED_2_MINI = "doubao-seed-2-0-mini-260215"

+# ModelScope(魔搭社区)
+QWEN3_235B_A22B_INSTRUCT_2507 = "Qwen/Qwen3-235B-A22B-Instruct-2507"
+QWEN3_5_27B = "Qwen/Qwen3.5-27B"
+
 # 其他模型
 WEN_XIN = "wenxin"
 WEN_XIN_4 = "wenxin-4"
@@ -130,11 +140,14 @@ MODELSCOPE = "modelscope"

 GITEE_AI_MODEL_LIST = ["Yi-34B-Chat", "InternVL2-8B", "deepseek-coder-33B-instruct", "InternVL2.5-26B", "Qwen2-VL-72B", "Qwen2.5-32B-Instruct", "glm-4-9b-chat", "codegeex4-all-9b", "Qwen2.5-Coder-32B-Instruct", "Qwen2.5-72B-Instruct", "Qwen2.5-7B-Instruct", "Qwen2-72B-Instruct", "Qwen2-7B-Instruct", "code-raccoon-v1", "Qwen2.5-14B-Instruct"]

-MODELSCOPE_MODEL_LIST = ["LLM-Research/c4ai-command-r-plus-08-2024","mistralai/Mistral-Small-Instruct-2409","mistralai/Ministral-8B-Instruct-2410","mistralai/Mistral-Large-Instruct-2407",
-                          "Qwen/Qwen2.5-Coder-32B-Instruct","Qwen/Qwen2.5-Coder-14B-Instruct","Qwen/Qwen2.5-Coder-7B-Instruct","Qwen/Qwen2.5-72B-Instruct","Qwen/Qwen2.5-32B-Instruct","Qwen/Qwen2.5-14B-Instruct","Qwen/Qwen2.5-7B-Instruct","Qwen/QwQ-32B-Preview",
-                          "LLM-Research/Llama-3.3-70B-Instruct","opencompass/CompassJudger-1-32B-Instruct","Qwen/QVQ-72B-Preview","LLM-Research/Meta-Llama-3.1-405B-Instruct","LLM-Research/Meta-Llama-3.1-8B-Instruct","Qwen/Qwen2-VL-7B-Instruct","LLM-Research/Meta-Llama-3.1-70B-Instruct",
-                          "Qwen/Qwen2.5-14B-Instruct-1M","Qwen/Qwen2.5-7B-Instruct-1M","Qwen/Qwen2.5-VL-3B-Instruct","Qwen/Qwen2.5-VL-7B-Instruct","Qwen/Qwen2.5-VL-72B-Instruct","deepseek-ai/DeepSeek-R1-Distill-Llama-70B","deepseek-ai/DeepSeek-R1-Distill-Llama-8B","deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
-                          "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","deepseek-ai/DeepSeek-R1","deepseek-ai/DeepSeek-V3","Qwen/QwQ-32B"]
+MODELSCOPE_MODEL_LIST = ["deepseek-ai/DeepSeek-R1-0528", "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "deepseek-ai/DeepSeek-R1-Distill-Llama-8B", "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
+                         "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "deepseek-ai/DeepSeek-V3.2", "LLM-Research/c4ai-command-r-plus-08-2024", "LLM-Research/Llama-4-Maverick-17B-128E-Instruct", "meituan-longcat/LongCat-Flash-Lite", "MiniMax/MiniMax-M1-80k", "MiniMax/MiniMax-M2.5", "mistralai/Ministral-8B-Instruct-2410",
+                         "mistralai/Mistral-Large-Instruct-2407", "mistralai/Mistral-Small-Instruct-2409", "moonshotai/Kimi-K2.5", "MusePublic/Qwen-Image-Edit", "opencompass/CompassJudger-1-32B-Instruct", "OpenGVLab/InternVL3_5-241B-A28B",
+                         "Qwen/QVQ-72B-Preview", "Qwen/Qwen-Image-Edit", "Qwen/Qwen3-0.6B", "Qwen/Qwen3-1.7B", "Qwen/Qwen3-14B", "Qwen/Qwen3-235B-A22B", "Qwen/Qwen3-235B-A22B-Instruct-2507", "Qwen/Qwen3-235B-A22B-Thinking-2507", "Qwen/Qwen3-30B-A3B", "Qwen/Qwen3-30B-A3B-Thinking-2507",
+                         "Qwen/Qwen3-32B", "Qwen/Qwen3-4B", "Qwen/Qwen3-8B", "Qwen/Qwen3-Coder-30B-A3B-Instruct", "Qwen/Qwen3-Coder-480B-A35B-Instruct", "Qwen/Qwen3-Next-80B-A3B-Instruct", "Qwen/Qwen3-Next-80B-A3B-Thinking", "Qwen/Qwen3-VL-235B-A22B-Instruct", "Qwen/Qwen3-VL-8B-Instruct",
+                         "Qwen/Qwen3-VL-8B-Thinking", "Qwen/Qwen3.5-122B-A10B", "Qwen/Qwen3.5-27B", "Qwen/Qwen3.5-35B-A3B", "Qwen/Qwen3.5-397B-A17B", "Qwen/QwQ-32B", "Qwen/QwQ-32B-Preview", "Shanghai_AI_Laboratory/Intern-S1", "Shanghai_AI_Laboratory/Intern-S1-mini",
+                         "stepfun-ai/Step-3.5-Flash", "XiaomiMiMo/MiMo-V2-Flash", "ZhipuAI/GLM-4.7-Flash", "ZhipuAI/GLM-5"]
+

 MODEL_LIST = [
              # Claude
@@ -153,20 +166,20 @@ MODEL_LIST = [
              GPT_4o, GPT_4O_0806, GPT_4o_MINI,
              GPT_41, GPT_41_MINI, GPT_41_NANO,
              GPT_5, GPT_5_MINI, GPT_5_NANO,
-              GPT_54,
+              GPT_54, GPT_54_MINI, GPT_54_NANO,
              O1, O1_MINI,
              
              # DeepSeek
              DEEPSEEK_CHAT, DEEPSEEK_REASONER,
              
              # Qwen
-              QWEN, QWEN_TURBO, QWEN_PLUS, QWEN_MAX, QWEN_LONG, QWEN3_MAX, QWEN35_PLUS,
+              QWEN36_PLUS, QWEN35_PLUS, QWEN3_MAX, QWEN_MAX, QWEN_PLUS, QWEN_TURBO, QWEN_LONG,
              
              # MiniMax
-              MiniMax, MINIMAX_M2_5, MINIMAX_M2_1, MINIMAX_M2_1_LIGHTNING, MINIMAX_M2, MINIMAX_ABAB6_5,
+              MiniMax, MINIMAX_M2_7, MINIMAX_M2_7_HIGHSPEED, MINIMAX_M2_5, MINIMAX_M2_1, MINIMAX_M2_1_LIGHTNING, MINIMAX_M2, MINIMAX_ABAB6_5,

              # GLM
-              ZHIPU_AI, GLM_5, GLM_4, GLM_4_PLUS, GLM_4_flash, GLM_4_LONG, GLM_4_ALLTOOLS,
+              ZHIPU_AI, GLM_5_TURBO, GLM_5, GLM_4, GLM_4_PLUS, GLM_4_flash, GLM_4_LONG, GLM_4_ALLTOOLS,
              GLM_4_0520, GLM_4_AIR, GLM_4_AIRX, GLM_4_7,

              # Kimi
@@ -188,3 +201,4 @@ FEISHU = "feishu"
 DINGTALK = "dingtalk"
 WECOM_BOT = "wecom_bot"
 QQ = "qq"
+WEIXIN = "weixin"
--- a/common/log.py
+++ b/common/log.py
@@ -1,5 +1,6 @@
 import logging
 import sys
+import io


 def _reset_logger(log):
@@ -9,7 +10,10 @@ def _reset_logger(log):
        del handler
    log.handlers.clear()
    log.propagate = False
-    console_handle = logging.StreamHandler(sys.stdout)
+    stdout = sys.stdout
+    if hasattr(stdout, "buffer"):
+        stdout = io.TextIOWrapper(stdout.buffer, encoding="utf-8", errors="replace", line_buffering=True)
+    console_handle = logging.StreamHandler(stdout)
    console_handle.setFormatter(
        logging.Formatter(
            "[%(levelname)s][%(asctime)s][%(filename)s:%(lineno)d] - %(message)s",
--- a/common/utils.py
+++ b/common/utils.py
@@ -115,3 +115,22 @@ def expand_path(path: str) -> str:
                expanded = os.path.join(home, path[2:])
    
    return expanded
+
+
+def get_cloud_headers(api_key: str) -> dict:
+    """
+    Build standard headers for LinkAI API requests,
+    including client_id when available.
+    """
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {api_key}",
+    }
+    try:
+        from linkai import LinkAIClient
+        client_id = LinkAIClient.fetch_client_id()
+        if client_id:
+            headers["X-Client-Id"] = client_id
+    except Exception:
+        pass
+    return headers
--- a/common/ws_client_compat.py
+++ b/common/ws_client_compat.py
@@ -0,0 +1,17 @@
+import inspect
+from typing import Any
+
+
+def websocket_app_run_forever(ws: Any, **kwargs: Any) -> None:
+    """
+    Call WebSocketApp.run_forever; strip reconnect= if the installed
+    websocket-client is too old (reconnect was added in a later 1.x release).
+    """
+    if "reconnect" in kwargs:
+        try:
+            params = inspect.signature(ws.run_forever).parameters
+        except (TypeError, ValueError):
+            params = {}
+        if "reconnect" not in params:
+            kwargs = {k: v for k, v in kwargs.items() if k != "reconnect"}
+    ws.run_forever(**kwargs)
--- a/config-template.json
+++ b/config-template.json
@@ -1,6 +1,6 @@
 {
-  "channel_type": "web",
-  "model": "MiniMax-M2.5",
+  "channel_type": "weixin",
+  "model": "MiniMax-M2.7",
  "minimax_api_key": "",
  "zhipu_ai_api_key": "",
  "ark_api_key": "",
@@ -26,8 +26,10 @@
  "dingtalk_client_secret":"",
  "wecom_bot_id": "",
  "wecom_bot_secret": "",
+  "web_password": "",
  "agent": true,
-  "agent_max_context_tokens": 40000,
+  "agent_max_context_tokens": 50000,
  "agent_max_context_turns": 20,
-  "agent_max_steps": 15
+  "agent_max_steps": 20,
+  "knowledge": true
 }
--- a/config.py
+++ b/config.py
@@ -20,7 +20,7 @@ available_setting = {
    "proxy": "",  # openai使用的代理
    # chatgpt模型， 当use_azure_chatgpt为true时，其名称为Azure上model deployment名称
    "model": "gpt-3.5-turbo",  # 可选择: gpt-4o, pt-4o-mini, gpt-4-turbo, claude-3-sonnet, wenxin, moonshot, qwen-turbo, xunfei, glm-4, minimax, gemini等模型，全部可选模型详见common/const.py文件
-    "bot_type": "",  # 可选配置，使用兼容openai格式的三方服务时候，需填"chatGPT"。bot具体名称详见common/const.py文件列出的bot_type，如不填根据model名称判断，
+    "bot_type": "",  # 可选配置，使用兼容openai格式的三方服务时候，需填"openai"（历史值"chatGPT"仍兼容）。bot具体名称详见common/const.py文件，如不填根据model名称判断
    "use_azure_chatgpt": False,  # 是否使用azure的chatgpt
    "azure_deployment_id": "",  # azure 模型部署名称
    "azure_api_version": "",  # azure api版本
@@ -153,10 +153,15 @@ available_setting = {
    # 企微智能机器人配置(长连接模式)
    "wecom_bot_id": "",  # 企微智能机器人BotID
    "wecom_bot_secret": "",  # 企微智能机器人长连接Secret
+    # 微信配置
+    "weixin_token": "",  # 微信登录后获取的bot_token，留空则启动时自动扫码登录
+    "weixin_base_url": "https://ilinkai.weixin.qq.com",  # Weixin ilink API base URL
+    "weixin_cdn_base_url": "https://novac2c.cdn.weixin.qq.com/c2c",  # CDN base URL
+    "weixin_credentials_path": "~/.weixin_cow_credentials.json",  # credentials file path
    # chatgpt指令自定义触发词
    "clear_memory_commands": ["#清除记忆"],  # 重置会话指令，必须以#开头
    # channel配置
-    "channel_type": "",  # 通道类型，支持多渠道同时运行。单个: "feishu"，多个: "feishu, dingtalk" 或 ["feishu", "dingtalk"]。可选值: web,feishu,dingtalk,wecom_bot,wechatmp,wechatmp_service,wechatcom_app
+    "channel_type": "",  # 通道类型，支持多渠道同时运行。单个: "feishu"，多个: "feishu, dingtalk" 或 ["feishu", "dingtalk"]。可选值: web,feishu,dingtalk,wecom_bot,weixin,wechatmp,wechatmp_service,wechatcom_app
    "web_console": True,  # 是否自动启动Web控制台（默认启动）。设为False可禁用
    "subscribe_msg": "",  # 订阅消息, 支持: wechatmp, wechatmp_service, wechatcom_app
    "debug": False,  # 是否开启debug模式，开启后会打印更多日志
@@ -175,25 +180,29 @@ available_setting = {
    # 豆包(火山方舟) 平台配置
    "ark_api_key": "",
    "ark_base_url": "https://ark.cn-beijing.volces.com/api/v3",
-    #魔搭社区 平台配置
+    # 魔搭社区 平台配置
    "modelscope_api_key": "",
    "modelscope_base_url": "https://api-inference.modelscope.cn/v1/chat/completions",
    # LinkAI平台配置
    "use_linkai": False,
    "linkai_api_key": "",
    "linkai_app_code": "",
-    "linkai_api_base": "https://api.link-ai.tech",  # linkAI服务地址
+    "linkai_api_base": "https://api.link-ai.tech",
    "cloud_host": "client.link-ai.tech",
+    "cloud_port": None,
    "cloud_deployment_id": "",
    "minimax_api_key": "",
    "Minimax_group_id": "",
    "Minimax_base_url": "",
    "web_port": 9899,
+    "web_password": "",  # Web console password; empty means no authentication required
+    "web_session_expire_days": 30,  # Auth session expiry in days
    "agent": True,  # 是否开启Agent模式
    "agent_workspace": "~/cow",  # agent工作空间路径，用于存储skills、memory等
    "agent_max_context_tokens": 50000,  # Agent模式下最大上下文tokens
-    "agent_max_context_turns": 30,  # Agent模式下最大上下文记忆轮次
-    "agent_max_steps": 15,  # Agent模式下单次运行最大决策步数
+    "agent_max_context_turns": 20,  # Agent模式下最大上下文记忆轮次
+    "agent_max_steps": 20,  # Agent模式下单次运行最大决策步数
+    "knowledge": True,  # 是否开启知识库功能
 }


@@ -382,7 +391,8 @@ def load_config():
        "wechatcomapp_agent_id": "WECHATCOMAPP_AGENT_ID",
        "wechatcomapp_secret": "WECHATCOMAPP_SECRET",
        "qq_app_id": "QQ_APP_ID",
-        "qq_app_secret": "QQ_APP_SECRET"
+        "qq_app_secret": "QQ_APP_SECRET",
+        "weixin_token": "WEIXIN_TOKEN",
    }
    injected = 0
    for conf_key, env_key in _CONFIG_TO_ENV.items():
@@ -402,7 +412,7 @@ def get_root():


 def read_file(path):
-    with open(path, mode="r", encoding="utf-8") as f:
+    with open(path, mode="r", encoding="utf-8-sig") as f:
        return f.read()


--- a/docker/Dockerfile.latest
+++ b/docker/Dockerfile.latest
@@ -4,32 +4,54 @@ LABEL maintainer="foo@bar.com"
 ARG TZ='Asia/Shanghai'

 ARG CHATGPT_ON_WECHAT_VER
+# Set to "false" to skip Playwright/Chromium and produce a smaller image
+ARG INSTALL_BROWSER=true
+# Set to "true" to use China mirrors for apt / pip / playwright (faster in CN)
+ARG USE_CN_MIRROR=false

-RUN echo /etc/apt/sources.list
-# RUN sed -i 's/deb.debian.org/mirrors.tuna.tsinghua.edu.cn/g' /etc/apt/sources.list
+ENV PLAYWRIGHT_BROWSERS_PATH=/app/ms-playwright
 ENV BUILD_PREFIX=/app

+# Optionally switch apt and pip to China mirrors
+RUN if [ "$USE_CN_MIRROR" = "true" ]; then \
+        sed -i 's/deb.debian.org/mirrors.tuna.tsinghua.edu.cn/g' /etc/apt/sources.list; \
+        pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple/; \
+    fi
+
 ADD . ${BUILD_PREFIX}

+# All heavy installs + user creation in ONE layer to avoid chown duplication
 RUN apt-get update \
-    &&apt-get install -y --no-install-recommends bash ffmpeg espeak libavcodec-extra\
+    && apt-get install -y --no-install-recommends bash ffmpeg espeak libavcodec-extra \
    && cd ${BUILD_PREFIX} \
    && cp config-template.json config.json \
    && /usr/local/bin/python -m pip install --no-cache --upgrade pip \
    && pip install --no-cache -r requirements.txt \
    && pip install --no-cache -r requirements-optional.txt \
-    && pip install azure-cognitiveservices-speech
+    && pip install --no-cache -e . \
+    && if [ "$INSTALL_BROWSER" = "true" ]; then \
+        apt-get install -y --no-install-recommends fonts-wqy-zenhei \
+        && pip install --no-cache "playwright==1.52.0" \
+        && python -m playwright install-deps chromium \
+        && mkdir -p /app/ms-playwright \
+        && if [ "$USE_CN_MIRROR" = "true" ]; then \
+            PLAYWRIGHT_DOWNLOAD_HOST=https://registry.npmmirror.com/-/binary/playwright \
+            python -m playwright install chromium; \
+        else \
+            python -m playwright install chromium; \
+        fi; \
+    fi \
+    && rm -rf /var/lib/apt/lists/* \
+    && mkdir -p /home/agent/cow \
+    && groupadd -r agent \
+    && useradd -r -g agent -s /bin/bash -d /home/agent agent \
+    && chown -R agent:agent /home/agent ${BUILD_PREFIX} /usr/local/lib

 WORKDIR ${BUILD_PREFIX}

 ADD docker/entrypoint.sh /entrypoint.sh

 RUN chmod +x /entrypoint.sh \
-    && mkdir -p /home/noroot \
-    && groupadd -r noroot \
-    && useradd -r -g noroot -s /bin/bash -d /home/noroot noroot \
-    && chown -R noroot:noroot /home/noroot ${BUILD_PREFIX} /usr/local/lib
-
-USER noroot
+    && chown agent:agent /entrypoint.sh

 ENTRYPOINT ["/entrypoint.sh"]
--- a/docker/docker-compose.yml
+++ b/docker/docker-compose.yml
@@ -5,22 +5,40 @@ services:
    container_name: chatgpt-on-wechat
    security_opt:
      - seccomp:unconfined
+    ports:
+      - "9899:9899"
    environment:
-      CHANNEL_TYPE: 'web'
-      OPEN_AI_API_KEY: 'YOUR API KEY'
-      MODEL: ''
-      PROXY: ''
-      SINGLE_CHAT_PREFIX: '["bot", "@bot"]'
-      SINGLE_CHAT_REPLY_PREFIX: '"[bot] "'
-      GROUP_CHAT_PREFIX: '["@bot"]'
-      GROUP_NAME_WHITE_LIST: '["ChatGPT测试群", "ChatGPT测试群2"]'
-      IMAGE_CREATE_PREFIX: '["画", "看", "找"]'
-      CONVERSATION_MAX_TOKENS: 1000
-      SPEECH_RECOGNITION: 'False'
-      CHARACTER_DESC: '你是基于大语言模型的AI智能助手，旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。'
-      EXPIRES_IN_SECONDS: 3600
-      USE_GLOBAL_PLUGIN_CONFIG: 'True'
+      CHANNEL_TYPE: 'weixin'
+      MODEL: 'MiniMax-M2.7'
+      MINIMAX_API_KEY: ''
+      ZHIPU_AI_API_KEY: ''
+      ARK_API_KEY: ''
+      MOONSHOT_API_KEY: ''
+      DASHSCOPE_API_KEY: ''
+      CLAUDE_API_KEY: ''
+      CLAUDE_API_BASE: 'https://api.anthropic.com/v1'
+      OPEN_AI_API_KEY: ''
+      OPEN_AI_API_BASE: 'https://api.openai.com/v1'
+      GEMINI_API_KEY: ''
+      GEMINI_API_BASE: 'https://generativelanguage.googleapis.com'
+      VOICE_TO_TEXT: 'openai'
+      TEXT_TO_VOICE: 'openai'
+      VOICE_REPLY_VOICE: 'False'
+      SPEECH_RECOGNITION: 'True'
+      GROUP_SPEECH_RECOGNITION: 'False'
      USE_LINKAI: 'False'
-      AGENT: 'True'
      LINKAI_API_KEY: ''
      LINKAI_APP_CODE: ''
+      FEISHU_APP_ID: ''
+      FEISHU_APP_SECRET: ''
+      DINGTALK_CLIENT_ID: ''
+      DINGTALK_CLIENT_SECRET: ''
+      WECOM_BOT_ID: ''
+      WECOM_BOT_SECRET: ''
+      WEB_PASSWORD: ''
+      AGENT: 'True'
+      AGENT_MAX_CONTEXT_TOKENS: 50000
+      AGENT_MAX_CONTEXT_TURNS: 20
+      AGENT_MAX_STEPS: 20
+    volumes:
+      - ./cow:/home/agent/cow
--- a/docker/entrypoint.sh
+++ b/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


--- a/docs/agent.md
+++ b/docs/agent.md
@@ -1,185 +0,0 @@
-# CowAgent介绍
-
-## 概述
-
-Cow项目从简单的聊天机器人全面升级为超级智能助理 **CowAgent**，能够主动规思考和规划任务、拥有长期记忆、操作计算机和外部资源、创造和执行Skill，真正理解你并和你一起成长。CowAgent能够长期运行在个人电脑或服务器中，通过飞书、钉钉、企业微信、网页等多种方式进行交互。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，支持多轮推理和上下文理解
- **工具系统**：内置实现10+种工具，包括文件读写、bash终端、浏览器、定时任务、记忆管理等，通过Agent管理你的计算机或服务器
- **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
- **Skills系统**：新增Skill运行引擎，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
- **多渠道和多模型支持**：支持在Web、飞书、钉钉、企微等多渠道与Agent交互，支持Claude、Gemini、OpenAI、GLM、MiniMax、Qwen、Kimi、Doubao 等多种国内外主流模型
- **安全和成本**：通过秘钥管理工具、提示词控制、系统权限等手段控制Agent的访问安全；通过最大记忆轮次、最大上下文token、工具执行步数对token成本进行限制
-
-
-## 核心功能
-
-### 1. 长期记忆
-
-> 记忆系统让 Agent 能够长期记住重要信息。Agent 会在用户分享偏好、决策、事实等重要信息时主动存储，也会在对话达到一定长度时自动提取摘要。记忆分为核心记忆、天级记忆，支持语义搜索和向量检索的混合检索模式。
-
-
-第一次启动Agent会主动向用户获取询问关键信息，并记录至工作空间 (默认为 ~/cow) 中的智能体设定、用户身份、记忆文件中。
-
-在后续的长期对话中，Agent会在需要的时候智能记录或检索记忆，并对自身设定、用户偏好、记忆文件等进行不断更新，总结和记录经验和教训，真正实现自主思考和不断成长。
-
-<img width="800" src="https://cdn.link-ai.tech/doc/20260203000455.png" />
-
-
-
-### 2. 任务规划和工具调用
-
-工具是Agent访问操作系统资源的核心，Agent会根据任务需求智能选择和调用工具，完成文件读写、命令执行、定时任务等各类操作。内置工具的视线在项目的 `tools` 目录下。
-
-**主要工具：** 文件读写编辑、Bash终端、浏览器、文件发送、定时调度、记忆搜索、环境配置等。
-
-#### 1.1 终端和文件访问能力
-
-针对操作系统的终端和文件的访问能力，是最基础和核心的工具，其他很多工具或技能都是基于基础工具进行扩展。用户可通过手机端与Agent交互，操作个人电脑或服务器上的资源：
-
-<img width="800" src="https://cdn.link-ai.tech/doc/20260202181130.png" />
-
-#### 1.2 编程能力
-
-基于编程能力和系统访问能力，Agent可以实现从信息搜索、图片等素材生成、编码、测试、部署、Nginx配置修改、发布的 Vibecoding 全流程，通过手机端简单的一句命令完成应用的快速demo：
-
-
-<img width="800" src="https://cdn.link-ai.tech/doc/20260203121008.png" />
-
-
-
-#### 1.3 定时任务
-
-基于 scheduler 工具实现动态定时任务，支持 **一次性任务、固定时间间隔、Cron表达式** 三种形式，任务触发可选择**固定消息发送** 或 **Agent动态任务** 执行两种模式，有很高灵活性：
-
-
-<img width="800" src="https://cdn.link-ai.tech/doc/20260202195402.png" />
-
-同时你也可以通过自然语言快速查看和管理已有的定时任务。
-
-
-#### 1.4 环境变量管理
-
-技能所需要的秘钥存储在环境变量文件中，由 `env_config` 工具进行管理，你可以通过对话的方式更新秘钥，工具内置了安全保护和脱敏策略，会严格保护秘钥安全：
-
-<img width="800" src="https://cdn.link-ai.tech/doc/20260202234939.png" />
-
-### 3. 技能系统
-
-> 技能系统为Agent提供无限的扩展性，每个Skill由说明文件、运行脚本 (可选)、资源 (可选) 组成，描述如何完成特定类型的任务。通过Skill可以让Agent遵循说明完成复杂流程，调用各类工具或对接第三方系统等。
-
- **内置技能：** 在项目的`skills`目录下，包含技能创造器、网络搜索、图像识别（openai-image-vision）、LinkAI智能体、网页抓取等。内置Skill根据依赖条件 (API Key、系统命令等) 自动判断是否启用。通过技能创造器可以快速创建自定义技能。
-
- **自定义技能：** 由用户通过对话创建，存放在工作空间中 (`~/cow/skills/`)，基于自定义技能可以实现任何复杂的业务流程和第三方系统对接。
-
-
-#### 3.1 创建技能
-
-通过 `skill-creator` 技能可以通过对话的方式快速创建技能。你可以在与Agent的写作中让他对将某个工作流程固化为技能，或者把任意接口文档和示例发送给Agent，让他直接完成对接：
-
-<img width="800" src="https://cdn.link-ai.tech/doc/20260202202247.png" />
-
-
-#### 3.2 搜索和图像识别
-
- **搜索技能：** 系统内置实现了 `bocha-search`(博查搜索)的Skill，依赖环境变量 `BOCHA_SEARCH_API_KEY`，可在[控制台](https://open.bochaai.com/)进行创建，并发送给Agent完成配置
- **图像识别技能：** 实现了 `openai-image-vision` 插件，可使用 gpt-4.1-mini、gpt-4.1 等图像识别模型。依赖秘钥 `OPENAI_API_KEY`，可通过config.json或env_config工具进行维护。
-
-<img width="800" src="https://cdn.link-ai.tech/doc/20260202213219.png" />
-
-
-#### 3.3 三方知识库和插件
-
-`linkai-agent` 技能可以将 [LinkAI](https://link-ai.tech/) 上的所有智能体作为skill交给Agent使用，并实现多智能体决策的效果。
-
-使用方式：需通过对话的方式配置 `LINKAI_API_KEY`，或在config.json中添加 `linkai_api_key`。 并在 `skills/linkai-agent/config.json`中添加智能体说明，示例如下：
-
-```json
-{
-  "apps": [
-    {
-      "app_code": "G7z6vKwp",
-      "app_name": "LinkAI客服助手",
-      "app_description": "当用户需要了解LinkAI平台相关问题时才选择该助手，基于LinkAI知识库进行回答"
-    },
-    {
-      "app_code": "SFY5x7JR",
-      "app_name": "内容创作助手",
-      "app_description": "当用户需要创作图片或视频时才使用该助手，支持Nano Banana、Seedream、即梦、Veo、可灵等多种模型"
-    }
-  ]
-}
-```
-
-Agent可根据智能体的名称和描述进行决策，并通过 app_code 调用接口访问对应的应用/工作流，通过该技能，可以灵活访问LinkAI平台上的智能体、知识库、插件等能力，实现效果如下：
-
-<img width="750" src="https://cdn.link-ai.tech/doc/20260202234350.png" />
-
-注：需通过 `env_config` 配置 `LINKAI_API_KEY`，或在config.json中添加 `linkai_api_key` 配置。
-
-
-## 使用方式
-
-> 详细使用方式参考项目README.md文档进行
-
-### 1.项目运行
-
-在命令行中执行：
-
-```bash
-bash <(curl -sS https://cdn.link-ai.tech/code/cow/run.sh)
-```
-
-详细说明及后续程序管理参考：[项目启动脚本](https://github.com/zhayujie/chatgpt-on-wechat/wiki/CowAgentQuickStart)
-
-
-### 2.模型选择
-
-Agent模式推荐使用以下模型，可根据效果及成本综合选择：
-
- **MiniMax**: `MiniMax-M2.5`
- **GLM**: `glm-5`
- **Kimi**: `kimi-k2.5`
- **Doubao**: `doubao-seed-2-0-code-preview-260215`
- **Qwen**: `qwen3.5-plus`
- **Claude**: `claude-sonnet-4-6`
- **Gemini**: `gemini-3.1-flash-lite-preview`
- **OpenAI**: `gpt-5.4`
-
-详细模型配置方式参考 [README.md 模型说明](../README.md#模型说明)
-
-### 3.Agent核心配置
-
-Agent模式的核心配置项如下，在 `config.json` 中配置：
-
-```bash
-{
-  "agent": true,                           # 是否启用Agent模式
-  "agent_workspace": "~/cow",              # Agent工作空间路径
-  "agent_max_context_tokens": 40000,       # 最大上下文tokens
-  "agent_max_context_turns": 30,           # 最大上下文记忆轮次
-  "agent_max_steps": 15                    # 单次任务最大决策步数
-}
-```
-
-**配置说明：**
-
- `agent`: 设为 `true` 启用Agent模式，获得多轮工具决策、长期记忆、Skills等能力
- `agent_workspace`: 工作空间路径，用于存储 memory、skills、其他系统设定提示词
- `agent_max_context_tokens`: 上下文token上限，超出将自动丢弃最早的对话
- `agent_max_context_turns`: 上下文记忆轮次，每轮包括一次提问和回复
- `agent_max_steps`: 单次任务最大工具调用步数，防止无限循环
-
-
-### 4.渠道接入
-
-Agent支持在多种渠道中使用，只需修改 `config.json` 中的 `channel_type` 配置即可切换。
-
- **Web网页**：默认使用该渠道，运行后监听本地端口，通过浏览器访问
- **飞书接入**：[飞书接入文档](https://docs.link-ai.tech/cow/multi-platform/feishu)
- **钉钉接入**：[钉钉接入文档](https://docs.link-ai.tech/cow/multi-platform/dingtalk)
- **企业微信应用接入**：[企微应用文档](https://docs.link-ai.tech/cow/multi-platform/wechat-com)
- **企微智能机器人**：[企微智能机器人文档](https://docs.link-ai.tech/cow/multi-platform/wecom-bot)
- **QQ机器人**：[QQ机器人文档](https://docs.link-ai.tech/cow/multi-platform/qq)
-
-更多渠道配置参考：[通道说明](../README.md#通道说明)
--- a/docs/channels/web.mdx
+++ b/docs/channels/web.mdx
@@ -30,6 +30,25 @@ Web 控制台是 CowAgent 的默认通道，启动后会自动运行，通过浏
  请确保服务器防火墙和安全组已放行对应端口。
 </Note>

+## 密码保护
+
+Web 控制台默认无需密码即可访问。如果部署在公网环境，建议配置访问密码：
+
+```json
+{
+  "web_password": "your_password"
+}
+```
+
+| 参数 | 说明 | 默认值 |
+| --- | --- | --- |
+| `web_password` | 访问密码，留空表示不启用密码保护 | `""` |
+| `web_session_expire_days` | 登录会话有效天数 | `30` |
+
+配置密码后，访问控制台时需先输入密码完成登录。登录状态默认保持 30 天，期间重启服务也无需重新登录。修改密码后，所有已登录的会话将自动失效。
+
+密码也支持在控制台的「配置」页面中在线修改。
+
 ## 功能介绍

 ### 对话界面
@@ -38,6 +57,16 @@ Web 控制台是 CowAgent 的默认通道，启动后会自动运行，通过浏

 <img width="850" src="https://cdn.link-ai.tech/doc/20260227180120.png" />

+#### 多会话管理
+
+对话界面支持多会话（Session）管理，所有会话记录持久化存储在数据库中：
+
+- **会话列表**：点击左侧历史会话图标可展开/收起会话列表面板，支持滚动加载全部历史会话
+- **AI 生成标题**：新会话在首轮对话完成后，自动调用模型生成简短的会话摘要标题
+- **新建会话**：点击会话列表顶部的「新对话」按钮或输入区的 `+` 按钮创建新会话
+- **删除会话**：点击会话项的删除按钮，确认后永久删除该会话及其所有消息
+- **清除上下文**：点击输入区的清除按钮，在当前会话中插入一条分隔线，分隔线以上的消息仍然展示但不再作为模型的上下文输入
+
 ### 模型管理

 支持在线管理模型配置，无需手动编辑配置文件：
--- a/docs/channels/wecom-bot.mdx
+++ b/docs/channels/wecom-bot.mdx
@@ -9,7 +9,23 @@ description: 将 CowAgent 接入企业微信智能机器人（长连接模式）
  智能机器人与企业微信自建应用是两种不同的接入方式。智能机器人使用 WebSocket 长连接，无需服务器公网 IP 和域名，配置更简单。
 </Note>

-## 一、创建智能机器人
+## 一、接入方式
+
+### 方式一：扫码一键接入（推荐）
+
+无需提前创建机器人，启动 Cow 项目后打开 Web 控制台（本地链接：http://127.0.0.1:9899/），选择 **通道** 菜单，点击**接入通道**，选择**企微智能机器人**，切换到「扫码接入」模式，使用**企业微信**扫码即可自动完成机器人创建和接入。
+
+<img src="https://cdn.link-ai.tech/doc/20260401121213.png" width="800"/>
+
+<Note>
+  扫码成功后，可在企业微信工作台 - **智能机器人**页面对机器人进行进一步配置，包括修改名称、头像、可见范围等。
+</Note>
+
+### 方式二：手动创建接入
+
+需要先在企业微信中创建智能机器人并获取 Bot ID 和 Secret，再通过 Web 控制台或配置文件接入。
+
+**步骤一：创建智能机器人**

 1. 打开企业微信客户端，进入工作台，点击**智能机器人**：

@@ -25,34 +41,35 @@ description: 将 CowAgent 接入企业微信智能机器人（长连接模式）

 4. 设置机器人名称、头像、可见范围，并选择**长连接模式**，记录下 **Bot ID** 和 **Secret** 信息后点击保存。

-## 二、配置和运行
+**步骤二：接入 CowAgent**

-### 方式一：Web 控制台接入
+<Tabs>
+  <Tab title="Web 控制台">
+    打开 Web 控制台，选择**通道**菜单，点击**接入通道**，选择**企微智能机器人**，切换到「手动填写」模式，输入 Bot ID 和 Secret，点击接入即可。

-启动Cow项目后打开 Web 控制台 (本地链接为: http://127.0.0.1:9899/ )，选择 **通道** 菜单，点击 **接入通道**，选择 **企微智能机器人**，填写上一步保存的 Bot ID 和 Secret，点击接入即可。
+    <img src="https://cdn.link-ai.tech/doc/20260316181711.png" width="800"/>
+  </Tab>
+  <Tab title="配置文件">
+    在 `config.json` 中添加以下配置后启动程序：

-<img src="https://cdn.link-ai.tech/doc/20260316181711.png" width="800"/>
+    ```json
+    {
+      "channel_type": "wecom_bot",
+      "wecom_bot_id": "YOUR_BOT_ID",
+      "wecom_bot_secret": "YOUR_SECRET"
+    }
+    ```

-### 方式二：配置文件接入
+    | 参数 | 说明 |
+    | --- | --- |
+    | `wecom_bot_id` | 智能机器人的 BotID |
+    | `wecom_bot_secret` | 智能机器人的 Secret |
+  </Tab>
+</Tabs>

-在 `config.json` 中添加以下配置：
+日志显示 `[WecomBot] Subscribe success` 即表示连接成功。

-```json
-{
-  "channel_type": "wecom_bot",
-  "wecom_bot_id": "YOUR_BOT_ID",
-  "wecom_bot_secret": "YOUR_SECRET"
-}
-```
-
-| 参数 | 说明 |
-| --- | --- |
-| `wecom_bot_id` | 智能机器人的 BotID |
-| `wecom_bot_secret` | 智能机器人的 Secret |
-
-配置完成后启动程序，日志显示 `[WecomBot] Subscribe success` 即表示连接成功。
-
-## 三、功能说明
+## 二、功能说明

 | 功能 | 支持情况 |
 | --- | --- |
@@ -64,7 +81,7 @@ description: 将 CowAgent 接入企业微信智能机器人（长连接模式）
 | 流式回复 | ✅ |
 | 定时任务主动推送 | ✅ |

-## 四、使用
+## 三、使用

 在企业微信中搜索创建的机器人名称，即可开始单聊对话。

--- a/docs/channels/weixin.mdx
+++ b/docs/channels/weixin.mdx
@@ -0,0 +1,74 @@
+---
+title: 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
+
+### 方式一：Web 控制台接入
+
+启动 Cow 项目后打开 Web 控制台 (本地链接为: http://127.0.0.1:9899/ )，选择 **通道** 菜单，点击 **接入通道**，选择 **微信**，点击接入后按照提示扫码登录。
+
+<img src="https://cdn.link-ai.tech/doc/20260322195114.png" width="800" />
+
+### 方式二：配置文件接入
+
+在 `config.json` 中设置 `channel_type` 为 `weixin`：
+
+```json
+{
+  "channel_type": "weixin"
+}
+```
+
+启动程序后，终端会显示二维码，使用微信扫码授权即可完成登录。
+
+<img src="https://cdn.link-ai.tech/doc/20260322195509.png" width="800" />
+
+
+<Note>
+  1. 兼容历史配置：`channel_type` 设为 `wx` 同样可以启用微信通道。
+  2. 注意微信客户端需要更新至 8.0.69 版本或以上
+</Note>
+
+## 二、使用说明
+
+微信扫码并进行授权确认后，即可完成接入并开始对话。接入微信后会在对话中创建出一个机器人助理，不会对已有账号的正常使用有任何影响。
+
+> 你可以通过搜索"微信ClawBot"随时找到这个机器人，还可以修改这个机器人的头像、备注等信息，将机器人置顶在消息列表等。
+
+<img src="https://cdn.link-ai.tech/doc/83ae8251d896219fde4803f4205205be.jpg" width="250" />
+
+
+
+## 三、登录说明
+
+### 扫码登录
+
+首次启动时，终端会显示一个二维码（有效期约 2 分钟）。使用微信扫描二维码并在手机上确认后即可完成登录。
+
+- 二维码过期后会自动刷新并重新显示
+- `requirements.txt` 中已默认包含 `qrcode` 依赖，安装后可在终端直接渲染二维码图案
+
+### 凭证保存
+
+登录成功后，凭证会自动保存至 `~/.weixin_cow_credentials.json`，下次启动时无需重新扫码。
+
+如需重新登录，删除该凭证文件后重启程序即可。
+
+### Session 过期
+
+当微信 session 过期时（errcode -14），程序会自动清除旧凭证并重新发起扫码登录，无需手动干预。
+
+## 四、功能说明
+
+| 功能 | 支持情况 |
+| --- | --- |
+| 单聊 | ✅ |
+| 文本消息 | ✅ 收发 |
+| 图片消息 | ✅ 收发 |
+| 文件消息 | ✅ 收发 |
+| 视频消息 | ✅ 收发 |
+| 语音消息 | ✅ 接收 (自带语音识别) |
--- a/docs/cli/general.mdx
+++ b/docs/cli/general.mdx
@@ -0,0 +1,154 @@
+---
+title: 常用命令
+description: 查看状态、管理配置和上下文等常用命令
+---
+
+以下命令支持在对话中使用 `/` 前缀，也支持在终端中使用 `cow` 前缀（部分命令仅对话可用）。
+
+<Tip>
+  在 Web 控制台中输入 `/` 会自动弹出命令提示，支持键盘上下选择和 Tab 补全。
+</Tip>
+
+## help
+
+显示所有可用命令的帮助信息。
+
+```text
+/help
+```
+
+## status
+
+查看当前会话和服务的运行状态，包括进程信息、模型配置、会话消息数量和已加载技能数量。
+
+```text
+/status
+```
+
+输出示例：
+
+```
+🐮 CowAgent Status
+
+Process: PID 12345 | Running 2h 15m
+Version: 2.0.4
+Channel: web
+Model:   MiniMax-M2.5
+Mode:    agent
+
+Session: 12 messages | 8 skills loaded
+```
+
+## config
+
+查看或修改运行时配置。修改后立即生效，无需重启服务。
+
+**查看所有可配置项：**
+
+```text
+/config
+```
+
+**查看单个配置项：**
+
+```text
+/config model
+```
+
+**修改配置项：**
+
+```text
+/config model deepseek-chat
+```
+
+**支持修改的配置项：**
+
+| 配置项 | 说明 | 示例值 |
+| --- | --- | --- |
+| `model` | AI 模型名称 | `deepseek-chat` |
+| `agent_max_context_tokens` | 最大上下文 tokens | `40000` |
+| `agent_max_context_turns` | 最大上下文记忆轮次 | `30` |
+| `agent_max_steps` | 单次任务最大决策步数 | `15` |
+
+<Note>
+  修改 `model` 时，系统会自动匹配对应的模型调用方式。配置会写入 `config.json` 并持久保存。
+</Note>
+
+## context
+
+查看当前会话的上下文信息，包括消息数量、内容长度等统计。
+
+```text
+/context
+```
+
+**清空当前会话上下文：**
+
+```text
+/context clear
+```
+
+<Tip>
+  清空上下文后，Agent 会"忘记"之前的对话内容，适用于切换话题或释放上下文空间。
+</Tip>
+
+## logs
+
+查看最近的服务日志，默认显示最近 20 行，最多 50 行。
+
+```text
+/logs
+```
+
+**指定行数：**
+
+```text
+/logs 50
+```
+
+## knowledge
+
+查看和管理个人知识库。默认显示知识库统计信息。
+
+```text
+/knowledge
+```
+
+输出示例：
+
+```
+📚 知识库
+
+- 状态：已开启
+- 页面数：12
+- 总大小：45.2 KB
+- 分类明细：
+  - concepts/: 5 篇
+  - entities/: 4 篇
+  - sources/: 3 篇
+```
+
+**查看目录结构：**
+
+```text
+/knowledge list
+```
+
+**开启 / 关闭知识库：**
+
+```text
+/knowledge on
+/knowledge off
+```
+
+<Note>
+  终端 CLI 中 `cow knowledge` 和 `cow knowledge list` 可用，但 `on|off` 仅支持在对话中使用（需实时生效）。
+</Note>
+
+## version
+
+显示当前 CowAgent 版本号。
+
+```text
+/version
+```
--- a/docs/cli/index.mdx
+++ b/docs/cli/index.mdx
@@ -0,0 +1,93 @@
+---
+title: 命令总览
+description: CowAgent 命令系统 — 终端 CLI 和对话命令
+---
+
+CowAgent 提供两种命令交互方式：
+
+- **终端CLI** — 在系统终端中执行 `cow <命令>`，用于服务管理、技能管理等运维操作
+- **对话命令** — 在对话中输入 `/<命令>` 或 `cow <命令>`，用于查看状态、管理技能、调整配置等
+
+## 终端命令
+
+通过一键安装脚本部署后，`cow` 命令会自动可用。手动安装的用户需要在项目根目录下额外执行：
+
+```bash
+pip install -e .
+```
+
+安装后即可在任意位置使用 `cow` 命令：
+
+```bash
+cow help
+```
+
+输出示例：
+
+```
+CowAgent CLI
+
+Usage: cow <command>
+
+Service:
+  start     Start the CowAgent service
+  stop      Stop the CowAgent service
+  restart   Restart the CowAgent service
+  update    Update code and restart service
+  status    Show service status
+  logs      View service logs
+
+Skills:
+  skill     Manage skills (list / search / install / uninstall ...)
+
+Knowledge:
+  knowledge View knowledge base stats and structure
+
+Others:
+  help      Show this help message
+  version   Show version
+```
+
+## 对话命令
+
+在 Web 控制台或任意接入渠道的对话中，支持输入以 `/` 开头的命令：
+
+| 命令 | 说明 |
+| --- | --- |
+| `/help` | 显示命令帮助 |
+| `/status` | 查看服务状态和配置 |
+| `/config` | 查看或修改运行时配置 |
+| `/skill` | 管理技能（安装、卸载、启用、禁用等） |
+| `/knowledge` | 查看知识库统计信息 |
+| `/knowledge list` | 查看知识库目录结构 |
+| `/knowledge on\|off` | 开启或关闭知识库 |
+| `/context` | 查看当前会话上下文信息 |
+| `/context clear` | 清空当前会话上下文 |
+| `/logs` | 查看最近日志 |
+| `/version` | 显示版本号 |
+
+<Tip>
+  对话命令中 `/start`、`/stop`、`/restart` 等服务管理命令会提示到终端中执行，因为它们涉及进程操作。
+</Tip>
+
+## 命令对照表
+
+以下是各命令在终端和对话中的可用性：
+
+| 命令 | 终端 (`cow`) | 对话 (`/`) |
+| --- | :---: | :---: |
+| help | ✓ | ✓ |
+| version | ✓ | ✓ |
+| status | ✓ | ✓ |
+| logs | ✓ | ✓ |
+| config | ✗ | ✓ |
+| context | — | ✓ |
+| knowledge (子命令) | ✓ | ✓ |
+| skill (子命令) | ✓ | ✓ |
+| start / stop / restart | ✓ | ✗ |
+| update | ✓ | ✗ |
+| install-browser | ✓ | ✗ |
+
+<Note>
+  `context` 在终端中仅提示到对话中使用。`config` 仅支持在对话中修改。
+</Note>
--- a/docs/cli/process.mdx
+++ b/docs/cli/process.mdx
@@ -0,0 +1,134 @@
+---
+title: 进程管理
+description: 使用 cow 命令管理 CowAgent 进程的启动、停止、重启、更新等操作
+---
+
+进程管理命令用于控制 CowAgent 后台进程的生命周期。这些命令仅在终端中可用。
+
+## start
+
+启动 CowAgent 服务。默认以后台进程方式运行，并自动跟踪日志输出。
+
+```bash
+cow start
+```
+
+**选项：**
+
+| 选项 | 说明 |
+| --- | --- |
+| `-f`, `--foreground` | 前台运行，不以后台守护进程方式启动 |
+| `--no-logs` | 启动后不自动跟踪日志 |
+
+## stop
+
+停止正在运行的 CowAgent 服务。
+
+```bash
+cow stop
+```
+
+## restart
+
+重启 CowAgent 服务（先停止再启动）。
+
+```bash
+cow restart
+```
+
+**选项：**
+
+| 选项 | 说明 |
+| --- | --- |
+| `--no-logs` | 重启后不自动跟踪日志 |
+
+## update
+
+更新代码并重启服务。自动执行以下流程：
+
+1. 拉取最新代码（`git pull`）
+2. 停止当前服务
+3. 更新 Python 依赖
+4. 重新安装 CLI
+5. 启动服务
+
+```bash
+cow update
+```
+
+<Warning>
+  如果 `git pull` 失败（如存在本地未提交的修改），更新会中止，服务不受影响。
+</Warning>
+
+## status
+
+查看 CowAgent 服务运行状态，包括进程信息、版本号、当前配置的模型和通道。
+
+```bash
+cow status
+```
+
+输出示例：
+
+```
+🐮 CowAgent Status
+  Status:   ● Running (PID: 12345)
+  Version:  2.0.4
+  Channel:  web
+  Model:    MiniMax-M2.5
+  Mode:     agent
+```
+
+## logs
+
+查看服务日志。
+
+```bash
+cow logs
+```
+
+**选项：**
+
+| 选项 | 说明 | 默认值 |
+| --- | --- | --- |
+| `-f`, `--follow` | 持续跟踪日志输出 | 否 |
+| `-n`, `--lines` | 显示最近 N 行 | 50 |
+
+示例：
+
+```bash
+# 查看最近 100 行日志
+cow logs -n 100
+
+# 持续跟踪日志
+cow logs -f
+```
+
+## install-browser
+
+安装 Playwright 和 Chromium 浏览器，用于启用 [浏览器工具](/tools/browser)。
+
+```bash
+cow install-browser
+```
+
+<Tip>
+  仅在需要使用浏览器工具（如网页浏览、截图等）时才需要安装。
+</Tip>
+
+## run.sh 兼容
+
+如果未安装 Cow CLI，也可以使用 `run.sh` 脚本管理服务：
+
+| cow 命令 | run.sh 等效命令 |
+| --- | --- |
+| `cow start` | `./run.sh start` |
+| `cow stop` | `./run.sh stop` |
+| `cow restart` | `./run.sh restart` |
+| `cow update` | `./run.sh update` |
+| `cow status` | `./run.sh status` |
+| `cow logs` | `./run.sh logs` |
+
+<Note>
+  推荐使用 `cow` 命令，它提供更简洁的语法和更丰富的功能。通过一键安装脚本部署时 `cow` 命令会自动安装。
+</Note>
--- a/docs/cli/skill.mdx
+++ b/docs/cli/skill.mdx
@@ -0,0 +1,218 @@
+---
+title: 技能管理
+description: 通过命令安装、卸载、启用、禁用和管理技能
+---
+
+技能管理命令用于安装、查询和管理 CowAgent 的技能。在对话中使用 `/skill <子命令>`，在终端中使用 `cow skill <子命令>`。
+
+## list
+
+列出已安装的技能及其状态。
+
+<CodeGroup>
+```text 对话
+/skill list
+```
+
+```bash 终端
+cow skill list
+```
+</CodeGroup>
+
+输出示例：
+
+```
+📦 已安装的技能 (3/4)
+
+✅ pptx
+   Use this skill any time a .pptx file is involved…
+   来源: cowhub
+
+✅ skill-creator
+   Create, install, or update skills…
+   来源: builtin
+
+⏸️ image-vision (已禁用)
+   图片理解和视觉分析
+   来源: builtin
+```
+
+**浏览技能广场**（查看 Hub 上所有可安装的技能）：
+
+<CodeGroup>
+```text 对话
+/skill list --remote
+```
+
+```bash 终端
+cow skill list --remote
+```
+</CodeGroup>
+
+**选项：**
+
+| 选项 | 说明 | 默认值 |
+| --- | --- | --- |
+| `--remote`, `-r` | 浏览 Skill Hub 远程技能列表 | 否 |
+| `--page` | 远程列表分页页码 | 1 |
+
+## search
+
+在技能广场中搜索技能。
+
+<CodeGroup>
+```text 对话
+/skill search pptx
+```
+
+```bash 终端
+cow skill search pptx
+```
+</CodeGroup>
+
+## install
+
+安装技能。通过统一的 `install` 命令，可一键安装来自 **Cow 技能广场、GitHub、ClawHub** 以及任意 URL（zip 压缩包、SKILL.md 链接）上的技能，无需手动下载和配置。
+
+**从 Cow 技能广场安装（推荐）：**
+
+<CodeGroup>
+```text 对话
+/skill install pptx
+```
+
+```bash 终端
+cow skill install pptx
+```
+</CodeGroup>
+
+**从 GitHub 安装：**
+
+<CodeGroup>
+```text 对话
+# 安装仓库中的所有技能（自动扫描包含 SKILL.md 的子目录）
+/skill install larksuite/cli
+
+# 指定子目录，只安装单个技能
+/skill install https://github.com/larksuite/cli/tree/main/skills/lark-im
+
+# 使用 # 指定子目录
+/skill install larksuite/cli#skills/lark-minutes
+```
+
+```bash 终端
+# 安装仓库中的所有技能（自动扫描包含 SKILL.md 的子目录）
+cow skill install larksuite/cli
+
+# 指定子目录，只安装单个技能
+cow skill install https://github.com/larksuite/cli/tree/main/skills/lark-im
+
+# 使用 # 指定子目录
+cow skill install larksuite/cli#skills/lark-minutes
+```
+</CodeGroup>
+
+支持完整的 GitHub URL 和 `owner/repo` 简写。对于 mono-repo（一个仓库中包含多个技能），不指定子目录时会自动发现并批量安装所有技能；指定子目录时只安装该目录下的技能。
+
+**从 ClawHub 安装：**
+
+<CodeGroup>
+```text 对话
+/skill install clawhub:baidu-search
+```
+
+```bash 终端
+cow skill install clawhub:baidu-search
+```
+</CodeGroup>
+
+**从 URL 安装：**
+
+<CodeGroup>
+```text 对话
+# 从 zip 压缩包安装（支持单个或批量）
+/skill install https://cdn.link-ai.tech/skills/pptx.zip
+
+# 从 SKILL.md 链接安装
+/skill install https://example.com/path/to/SKILL.md
+```
+
+```bash 终端
+# 从 zip 压缩包安装（支持单个或批量）
+cow skill install https://cdn.link-ai.tech/skills/pptx.zip
+
+# 从 SKILL.md 链接安装
+cow skill install https://example.com/path/to/SKILL.md
+```
+</CodeGroup>
+
+支持从 zip / tar.gz 压缩包 URL 安装，解压后自动扫描包含 `SKILL.md` 的目录，支持单个或批量安装。也支持直接从 `SKILL.md` 文件链接安装，会自动解析技能名称和描述。
+
+安装成功后会显示技能名称、描述和来源，例如：
+
+```
+✅ baidu-search
+   百度搜索：使用百度搜索引擎检索信息…
+   来源: clawhub
+```
+
+## uninstall
+
+卸载已安装的技能。
+
+<CodeGroup>
+```text 对话
+/skill uninstall pptx
+```
+
+```bash 终端
+cow skill uninstall pptx
+```
+</CodeGroup>
+
+<Warning>
+  卸载操作会删除技能目录下的所有文件，此操作不可恢复。
+</Warning>
+
+## enable / disable
+
+启用或禁用技能，禁用后技能不会被 Agent 调用。
+
+<CodeGroup>
+```text 对话
+/skill enable pptx
+/skill disable pptx
+```
+
+```bash 终端
+cow skill enable pptx
+cow skill disable pptx
+```
+</CodeGroup>
+
+## info
+
+查看已安装技能的详细信息，包括 `SKILL.md` 内容预览。
+
+<CodeGroup>
+```text 对话
+/skill info pptx
+```
+
+```bash 终端
+cow skill info pptx
+```
+</CodeGroup>
+
+## 技能来源
+
+安装的技能会记录来源信息，可通过 `/skill list` 查看：
+
+| 来源标识 | 说明 |
+| --- | --- |
+| `builtin` | 项目内置技能 |
+| `cowhub` | 从 CowAgent Skill Hub 安装 |
+| `github` | 从 GitHub URL 直接安装 |
+| `clawhub` | 从 ClawHub 安装 |
+| `url` | 从 SKILL.md URL 安装 |
+| `local` | 本地创建的技能 |
--- a/docs/docs.json
+++ b/docs/docs.json
@@ -24,13 +24,13 @@
      },
      {
        "label": "GitHub",
-        "href": "https://github.com/zhayujie/chatgpt-on-wechat"
+        "href": "https://github.com/zhayujie/CowAgent"
      }
    ]
  },
  "footer": {
    "socials": {
-      "github": "https://github.com/zhayujie/chatgpt-on-wechat"
+      "github": "https://github.com/zhayujie/CowAgent"
    }
  },
  "navigation": {
@@ -59,7 +59,8 @@
                "group": "安装部署",
                "pages": [
                  "guide/quick-start",
-                  "guide/manual-install"
+                  "guide/manual-install",
+                  "guide/upgrade"
                ]
              }
            ]
@@ -80,7 +81,8 @@
                  "models/gemini",
                  "models/openai",
                  "models/deepseek",
-                  "models/linkai"
+                  "models/linkai",
+                  "models/coding-plan"
                ]
              }
            ]
@@ -104,14 +106,17 @@
                  "tools/bash",
                  "tools/send",
                  "tools/memory",
-                  "tools/env-config"
+                  "tools/env-config",
+                  "tools/web-fetch",
+                  "tools/scheduler"
                ]
              },
              {
                "group": "可选工具",
                "pages": [
                  "tools/web-search",
-                  "tools/scheduler"
+                  "tools/vision",
+                  "tools/browser"
                ]
              }
            ]
@@ -123,15 +128,9 @@
                "group": "技能系统",
                "pages": [
                  "skills/index",
-                  "skills/skill-creator"
-                ]
-              },
-              {
-                "group": "内置技能",
-                "pages": [
-                  "skills/image-vision",
-                  "skills/linkai-agent",
-                  "skills/web-fetch"
+                  "skills/install",
+                  "skills/create",
+                  "skills/hub"
                ]
              }
            ]
@@ -142,7 +141,19 @@
              {
                "group": "记忆系统",
                "pages": [
-                  "memory"
+                  "memory/index",
+                  "memory/context"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "知识",
+            "groups": [
+              {
+                "group": "知识库",
+                "pages": [
+                  "knowledge/index"
                ]
              }
            ]
@@ -153,6 +164,7 @@
              {
                "group": "接入渠道",
                "pages": [
+                  "channels/weixin",
                  "channels/web",
                  "channels/feishu",
                  "channels/dingtalk",
@@ -164,6 +176,20 @@
              }
            ]
          },
+          {
+            "tab": "命令",
+            "groups": [
+              {
+                "group": "命令系统",
+                "pages": [
+                  "cli/index",
+                  "cli/process",
+                  "cli/skill",
+                  "cli/general"
+                ]
+              }
+            ]
+          },
          {
            "tab": "版本",
            "groups": [
@@ -171,6 +197,9 @@
                "group": "发布记录",
                "pages": [
                  "releases/overview",
+                  "releases/v2.0.5",
+                  "releases/v2.0.4",
+                  "releases/v2.0.3",
                  "releases/v2.0.2",
                  "releases/v2.0.1",
                  "releases/v2.0.0"
@@ -224,7 +253,8 @@
                  "en/models/gemini",
                  "en/models/openai",
                  "en/models/deepseek",
-                  "en/models/linkai"
+                  "en/models/linkai",
+                  "en/models/coding-plan"
                ]
              }
            ]
@@ -248,14 +278,17 @@
                  "en/tools/bash",
                  "en/tools/send",
                  "en/tools/memory",
-                  "en/tools/env-config"
+                  "en/tools/env-config",
+                  "en/tools/web-fetch",
+                  "en/tools/scheduler"
                ]
              },
              {
                "group": "Optional Tools",
                "pages": [
                  "en/tools/web-search",
-                  "en/tools/scheduler"
+                  "en/tools/vision",
+                  "en/tools/browser"
                ]
              }
            ]
@@ -267,15 +300,9 @@
                "group": "Skills System",
                "pages": [
                  "en/skills/index",
-                  "en/skills/skill-creator"
-                ]
-              },
-              {
-                "group": "Built-in Skills",
-                "pages": [
-                  "en/skills/image-vision",
-                  "en/skills/linkai-agent",
-                  "en/skills/web-fetch"
+                  "en/skills/install",
+                  "en/skills/skill-creator",
+                  "en/skills/hub"
                ]
              }
            ]
@@ -286,7 +313,19 @@
              {
                "group": "Memory System",
                "pages": [
-                  "en/memory"
+                  "en/memory/index",
+                  "en/memory/context"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "Knowledge",
+            "groups": [
+              {
+                "group": "Knowledge Base",
+                "pages": [
+                  "en/knowledge/index"
                ]
              }
            ]
@@ -297,6 +336,7 @@
              {
                "group": "Platforms",
                "pages": [
+                  "en/channels/weixin",
                  "en/channels/web",
                  "en/channels/feishu",
                  "en/channels/dingtalk",
@@ -308,6 +348,20 @@
              }
            ]
          },
+          {
+            "tab": "CLI",
+            "groups": [
+              {
+                "group": "Command System",
+                "pages": [
+                  "en/cli/index",
+                  "en/cli/process",
+                  "en/cli/skill",
+                  "en/cli/chat"
+                ]
+              }
+            ]
+          },
          {
            "tab": "Releases",
            "groups": [
@@ -315,6 +369,8 @@
                "group": "Release Notes",
                "pages": [
                  "en/releases/overview",
+                  "en/releases/v2.0.5",
+                  "en/releases/v2.0.4",
                  "en/releases/v2.0.2",
                  "en/releases/v2.0.1",
                  "en/releases/v2.0.0"
@@ -323,6 +379,179 @@
            ]
          }
        ]
+      },
+      {
+        "language": "ja",
+        "tabs": [
+          {
+            "tab": "紹介",
+            "groups": [
+              {
+                "group": "概要",
+                "pages": [
+                  "ja/intro/index",
+                  "ja/intro/architecture",
+                  "ja/intro/features"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "クイックスタート",
+            "groups": [
+              {
+                "group": "インストール",
+                "pages": [
+                  "ja/guide/quick-start",
+                  "ja/guide/manual-install",
+                  "ja/guide/upgrade"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "モデル",
+            "groups": [
+              {
+                "group": "モデル設定",
+                "pages": [
+                  "ja/models/index",
+                  "ja/models/minimax",
+                  "ja/models/glm",
+                  "ja/models/qwen",
+                  "ja/models/kimi",
+                  "ja/models/doubao",
+                  "ja/models/claude",
+                  "ja/models/gemini",
+                  "ja/models/openai",
+                  "ja/models/deepseek",
+                  "ja/models/linkai",
+                  "ja/models/coding-plan"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "ツール",
+            "groups": [
+              {
+                "group": "ツールシステム",
+                "pages": [
+                  "ja/tools/index"
+                ]
+              },
+              {
+                "group": "内蔵ツール",
+                "pages": [
+                  "ja/tools/read",
+                  "ja/tools/write",
+                  "ja/tools/edit",
+                  "ja/tools/ls",
+                  "ja/tools/bash",
+                  "ja/tools/send",
+                  "ja/tools/memory",
+                  "ja/tools/env-config",
+                  "ja/tools/web-fetch",
+                  "ja/tools/scheduler"
+                ]
+              },
+              {
+                "group": "オプションツール",
+                "pages": [
+                  "ja/tools/web-search",
+                  "ja/tools/vision",
+                  "ja/tools/browser"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "スキル",
+            "groups": [
+              {
+                "group": "スキルシステム",
+                "pages": [
+                  "ja/skills/index",
+                  "ja/skills/install",
+                  "ja/skills/create",
+                  "ja/skills/hub"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "メモリ",
+            "groups": [
+              {
+                "group": "メモリシステム",
+                "pages": [
+                  "ja/memory/index",
+                  "ja/memory/context"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "ナレッジ",
+            "groups": [
+              {
+                "group": "ナレッジベース",
+                "pages": [
+                  "ja/knowledge/index"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "チャネル",
+            "groups": [
+              {
+                "group": "プラットフォーム",
+                "pages": [
+                  "ja/channels/weixin",
+                  "ja/channels/web",
+                  "ja/channels/feishu",
+                  "ja/channels/dingtalk",
+                  "ja/channels/wecom-bot",
+                  "ja/channels/qq",
+                  "ja/channels/wecom",
+                  "ja/channels/wechatmp"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "CLI",
+            "groups": [
+              {
+                "group": "コマンドシステム",
+                "pages": [
+                  "ja/cli/index",
+                  "ja/cli/process",
+                  "ja/cli/skill",
+                  "ja/cli/general"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "リリース",
+            "groups": [
+              {
+                "group": "リリースノート",
+                "pages": [
+                  "ja/releases/overview",
+                  "ja/releases/v2.0.5",
+                  "ja/releases/v2.0.4",
+                  "ja/releases/v2.0.3",
+                  "ja/releases/v2.0.2",
+                  "ja/releases/v2.0.1",
+                  "ja/releases/v2.0.0"
+                ]
+              }
+            ]
+          }
+        ]
      }
    ]
  }
--- a/docs/en/README.md
+++ b/docs/en/README.md
@@ -1,31 +1,35 @@
 <p align="center"><img src="https://github.com/user-attachments/assets/eca9a9ec-8534-4615-9e0f-96c5ac1d10a3" alt="CowAgent" width="550" /></p>

 <p align="center">
-  <a href="https://github.com/zhayujie/chatgpt-on-wechat/releases/latest"><img src="https://img.shields.io/github/v/release/zhayujie/chatgpt-on-wechat" alt="Latest release"></a>
-  <a href="https://github.com/zhayujie/chatgpt-on-wechat/blob/master/LICENSE"><img src="https://img.shields.io/github/license/zhayujie/chatgpt-on-wechat" alt="License: MIT"></a>
-  <a href="https://github.com/zhayujie/chatgpt-on-wechat"><img src="https://img.shields.io/github/stars/zhayujie/chatgpt-on-wechat?style=flat-square" alt="Stars"></a> <br/>
-  [<a href="https://github.com/zhayujie/chatgpt-on-wechat/blob/master/README.md">中文</a>] | [English]
+  <a href="https://github.com/zhayujie/CowAgent/releases/latest"><img src="https://img.shields.io/github/v/release/zhayujie/CowAgent" alt="Latest release"></a>
+  <a href="https://github.com/zhayujie/CowAgent/blob/master/LICENSE"><img src="https://img.shields.io/github/license/zhayujie/CowAgent" alt="License: MIT"></a>
+  <a href="https://github.com/zhayujie/CowAgent"><img src="https://img.shields.io/github/stars/zhayujie/CowAgent?style=flat-square" alt="Stars"></a> <br/>
+  [<a href="https://github.com/zhayujie/CowAgent/blob/master/README.md">中文</a>] | [English] | [<a href="https://github.com/zhayujie/CowAgent/blob/master/docs/ja/README.md">日本語</a>]
 </p>

-**CowAgent** is an AI super assistant powered by LLMs, capable of autonomous task planning, operating computers and external resources, creating and executing Skills, and continuously growing with long-term memory. It supports flexible model switching, handles text, voice, images, and files, and can be integrated into Web, Feishu, DingTalk, WeCom Bot, WeCom App, and WeChat Official Account — running 7×24 hours on your personal computer or server.
+**CowAgent** is an AI super assistant powered by LLMs, capable of autonomous task planning, operating computers and external resources, creating and executing Skills, and continuously growing with long-term memory and a personal knowledge base. It supports flexible model switching, handles text, voice, images, and files, and can be integrated into WeChat, Web, Feishu, DingTalk, WeCom Bot, WeCom App, and WeChat Official Account — running 7×24 hours on your personal computer or server.

 <p align="center">
  <a href="https://cowagent.ai/">🌐 Website</a> &nbsp;·&nbsp;
  <a href="https://docs.cowagent.ai/en/intro/index">📖 Docs</a> &nbsp;·&nbsp;
-  <a href="https://docs.cowagent.ai/en/guide/quick-start">🚀 Quick Start</a>
+  <a href="https://docs.cowagent.ai/en/guide/quick-start">🚀 Quick Start</a> &nbsp;·&nbsp;
+  <a href="https://skills.cowagent.ai/">🧩 Skill Hub</a> &nbsp;·&nbsp;
+  <a href="https://link-ai.tech/cowagent/create">☁️ Try Online</a>
 </p>

 ## Introduction

 > CowAgent is both an out-of-the-box AI super assistant and a highly extensible Agent framework. You can extend it with new model interfaces, channels, built-in tools, and the Skills system to flexibly implement various customization needs.

- ✅ **Autonomous Task Planning**: Understands complex tasks and autonomously plans execution, continuously thinking and invoking tools until goals are achieved. Supports accessing files, terminal, browser, schedulers, and other system resources via tools.
+- ✅ **Autonomous Task Planning**: Understands complex tasks and autonomously plans execution, continuously thinking and invoking tools until goals are achieved.
 - ✅ **Long-term Memory**: Automatically persists conversation memory to local files and databases, including core memory and daily memory, with keyword and vector retrieval support.
- ✅ **Skills System**: Implements a Skills creation and execution engine with multiple built-in skills, and supports custom Skills development through natural language conversation.
+- ✅ **Personal Knowledge Base**: Automatically organizes structured knowledge with cross-references to build a knowledge graph, with web-based visualization and conversational management.
+- ✅ **Skills System**: Implements a Skills creation and execution engine, supports installing skills from [Skill Hub](https://skills.cowagent.ai), GitHub, etc., or creating custom Skills through conversation.
+- ✅ **Tool System**: Built-in tools for file I/O, terminal execution, browser automation, scheduled tasks, messaging, and more — autonomously invoked by the Agent.
+- ✅ **CLI System**: Provides terminal commands and in-chat commands for process management, skill installation, configuration, and more.
 - ✅ **Multimodal Messages**: Supports parsing, processing, generating, and sending text, images, voice, files, and other message types.
 - ✅ **Multiple Model Support**: Supports OpenAI, Claude, Gemini, DeepSeek, MiniMax, GLM, Qwen, Kimi, Doubao, and other mainstream model providers.
- ✅ **Multi-platform Deployment**: Runs on local computers or servers, integrable into Web, Feishu, DingTalk, WeChat Official Account, and WeCom applications.
- ✅ **Knowledge Base**: Integrates enterprise knowledge base capabilities via the [LinkAI](https://link-ai.tech) platform.
+- ✅ **Multi-platform Deployment**: Runs on local computers or servers, integrable into WeChat, Web, Feishu, DingTalk, WeChat Official Account, and WeCom applications.

 ## Disclaimer

@@ -33,19 +37,25 @@
 2. Agent mode consumes more tokens than normal chat mode. Choose models based on effectiveness and cost. Agent has access to the host OS — please deploy in trusted environments.
 3. CowAgent focuses on open-source development and does not participate in, authorize, or issue any cryptocurrency.

+## Demo
+
+Try online (no deployment needed): [CowAgent](https://link-ai.tech/cowagent/create)
+
 ## Changelog

-> **2026.02.27:** [v2.0.2](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.2) — Web console overhaul (streaming chat, model/skill/memory/channel/scheduler/log management), multi-channel concurrent running, session persistence, new models including Gemini 3.1 Pro / Claude 4.6 Sonnet / Qwen3.5 Plus.
+> **2026.04.01:** [v2.0.5](https://github.com/zhayujie/CowAgent/releases/tag/2.0.5) — Cow CLI, Skill Hub open source, Browser tool, WeCom Bot QR scan, and more.

-> **2026.02.13:** [v2.0.1](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.1) — Built-in Web Search tool, smart context trimming, runtime info dynamic update, Windows compatibility, fixes for scheduler memory loss, Feishu connection issues, and more.
+> **2026.02.27:** [v2.0.2](https://github.com/zhayujie/CowAgent/releases/tag/2.0.2) — Web console overhaul (streaming chat, model/skill/memory/channel/scheduler/log management), multi-channel concurrent running, session persistence, new models including Gemini 3.1 Pro / Claude 4.6 Sonnet / Qwen3.5 Plus.

-> **2026.02.03:** [v2.0.0](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.0) — Full upgrade to AI super assistant with multi-step task planning, long-term memory, built-in tools, Skills framework, new models, and optimized channels.
+> **2026.02.13:** [v2.0.1](https://github.com/zhayujie/CowAgent/releases/tag/2.0.1) — Built-in Web Search tool, smart context trimming, runtime info dynamic update, Windows compatibility, fixes for scheduler memory loss, Feishu connection issues, and more.

-> **2025.05.23:** [v1.7.6](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.7.6) — Web channel optimization, AgentMesh multi-agent plugin, Baidu TTS, claude-4-sonnet/opus support.
+> **2026.02.03:** [v2.0.0](https://github.com/zhayujie/CowAgent/releases/tag/2.0.0) — Full upgrade to AI super assistant with multi-step task planning, long-term memory, built-in tools, Skills framework, new models, and optimized channels.

-> **2025.04.11:** [v1.7.5](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.7.5) — wechatferry protocol, DeepSeek model, Tencent Cloud voice, ModelScope and Gitee-AI support.
+> **2025.05.23:** [v1.7.6](https://github.com/zhayujie/CowAgent/releases/tag/1.7.6) — Web channel optimization, AgentMesh multi-agent plugin, Baidu TTS, claude-4-sonnet/opus support.

-> **2024.12.13:** [v1.7.4](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.7.4) — Gemini 2.0 model, Web channel, memory leak fix.
+> **2025.04.11:** [v1.7.5](https://github.com/zhayujie/CowAgent/releases/tag/1.7.5) — wechatferry protocol, DeepSeek model, Tencent Cloud voice, ModelScope and Gitee-AI support.
+
+> **2024.12.13:** [v1.7.4](https://github.com/zhayujie/CowAgent/releases/tag/1.7.4) — Gemini 2.0 model, Web channel, memory leak fix.

 Full changelog: [Release Notes](https://docs.cowagent.ai/en/releases/overview)

@@ -55,21 +65,27 @@ Full changelog: [Release Notes](https://docs.cowagent.ai/en/releases/overview)

 The project provides a one-click script for installation, configuration, startup, and management:

+**Linux / macOS:**
 ```bash
-bash <(curl -sS https://cdn.link-ai.tech/code/cow/run.sh)
+bash <(curl -fsSL https://cdn.link-ai.tech/code/cow/run.sh)
+```
+
+**Windows (PowerShell):**
+```powershell
+irm https://cdn.link-ai.tech/code/cow/run.ps1 | iex
 ```

 After running, the Web service starts by default. Access `http://localhost:9899/chat` to chat.

-Script usage: [One-click Install](https://docs.cowagent.ai/en/guide/quick-start)
+Script usage: [One-click Install](https://docs.cowagent.ai/en/guide/quick-start). After installation, you can also use `cow start`, `cow stop`, and other [CLI commands](https://docs.cowagent.ai/en/cli/index) to manage the service.

 ### Manual Installation

 **1. Clone the project**

 ```bash
-git clone https://github.com/zhayujie/chatgpt-on-wechat
-cd chatgpt-on-wechat/
+git clone https://github.com/zhayujie/CowAgent
+cd CowAgent/
 ```

 **2. Install dependencies**
@@ -79,7 +95,25 @@ pip3 install -r requirements.txt
 pip3 install -r requirements-optional.txt   # optional but recommended
 ```

-**3. Configure**
+**3. Install Cow CLI (recommended)**
+
+```bash
+pip3 install -e .
+```
+
+After installation, use `cow` commands to manage the service (start, stop, update, etc.) and skills. See [Command Docs](https://docs.cowagent.ai/en/cli/index).
+
+**4. Install browser (optional)**
+
+If you need the Agent to operate a browser (visit web pages, fill forms, etc.):
+
+```bash
+cow install-browser
+```
+
+This auto-installs `playwright` and Chromium. See [Browser Tool Docs](https://docs.cowagent.ai/en/tools/browser).
+
+**5. Configure**

 ```bash
 cp config-template.json config.json
@@ -87,13 +121,25 @@ cp config-template.json config.json

 Fill in your model API key and channel type in `config.json`. See the [configuration docs](https://docs.cowagent.ai/en/guide/manual-install) for details.

-**4. Run**
+**6. Run**

 ```bash
-python3 app.py
+cow start              # recommended, requires Cow CLI
+python3 app.py         # or run directly
 ```

-For server background run:
+For server deployment, use `cow` commands to manage the service:
+
+```bash
+cow start              # start in background
+cow stop               # stop service
+cow restart            # restart service
+cow status             # check running status
+cow logs               # view logs
+cow update             # pull latest code and restart
+```
+
+Or use the traditional way:

 ```bash
 nohup python3 app.py & tail -f nohup.out
@@ -102,7 +148,7 @@ nohup python3 app.py & tail -f nohup.out
 ### Docker Deployment

 ```bash
-wget https://cdn.link-ai.tech/code/cow/docker-compose.yml
+curl -O https://cdn.link-ai.tech/code/cow/docker-compose.yml
 # Edit docker-compose.yml with your config
 sudo docker compose up -d
 sudo docker logs -f chatgpt-on-wechat
@@ -116,11 +162,11 @@ Supports mainstream model providers. Recommended models for Agent mode:

 | Provider | Recommended Model |
 | --- | --- |
-| MiniMax | `MiniMax-M2.5` |
-| GLM | `glm-5` |
+| MiniMax | `MiniMax-M2.7` |
+| GLM | `glm-5-turbo` |
 | Kimi | `kimi-k2.5` |
 | Doubao | `doubao-seed-2-0-code-preview-260215` |
-| Qwen | `qwen3.5-plus` |
+| Qwen | `qwen3.6-plus` |
 | Claude | `claude-sonnet-4-6` |
 | Gemini | `gemini-3.1-pro-preview` |
 | OpenAI | `gpt-5.4` |
@@ -128,6 +174,28 @@ Supports mainstream model providers. Recommended models for Agent mode:

 For detailed configuration of each model, see the [Models documentation](https://docs.cowagent.ai/en/models/index).

+### Coding Plan
+
+Coding Plan is a monthly subscription package offered by various providers, ideal for high-frequency Agent usage. All providers can be accessed via OpenAI-compatible mode:
+
+```json
+{
+  "bot_type": "openai",
+  "model": "MODEL_NAME",
+  "open_ai_api_base": "PROVIDER_CODING_PLAN_API_BASE",
+  "open_ai_api_key": "YOUR_API_KEY"
+}
+```
+
+- `bot_type`: Must be `openai`
+- `model`: Model name supported by the provider
+- `open_ai_api_base`: Provider's Coding Plan API Base (different from standard pay-as-you-go)
+- `open_ai_api_key`: Provider's Coding Plan API Key
+
+> Note: Coding Plan API Base and API Key are usually separate from standard pay-as-you-go ones. Please obtain them from each provider's platform.
+
+Supported providers include Alibaba Cloud, MiniMax, Zhipu GLM, Kimi, Volcengine, and more. For detailed configuration of each provider, see the [Coding Plan documentation](https://docs.cowagent.ai/en/models/coding-plan).
+
 <br/>

 ## Channels
@@ -136,6 +204,7 @@ Supports multiple platforms. Set `channel_type` in `config.json` to switch:

 | Channel | `channel_type` | Docs |
 | --- | --- | --- |
+| WeChat | `weixin` | [WeChat Setup](https://docs.cowagent.ai/en/channels/weixin) |
 | Web (default) | `web` | [Web Channel](https://docs.cowagent.ai/en/channels/web) |
 | Feishu | `feishu` | [Feishu Setup](https://docs.cowagent.ai/en/channels/feishu) |
 | DingTalk | `dingtalk` | [DingTalk Setup](https://docs.cowagent.ai/en/channels/dingtalk) |
@@ -158,21 +227,22 @@ Multiple channels can be enabled simultaneously, separated by commas: `"channel_

 ## 🔗 Related Projects

+- [Cow Skill Hub](https://github.com/zhayujie/cow-skill-hub): Open skill marketplace for AI Agents — browse, search, install, and publish skills for CowAgent, OpenClaw, Claude Code, and more.
 - [bot-on-anything](https://github.com/zhayujie/bot-on-anything): Lightweight and highly extensible LLM application framework supporting Slack, Telegram, Discord, Gmail, and more.
 - [AgentMesh](https://github.com/MinimalFuture/AgentMesh): Open-source Multi-Agent framework for complex problem solving through agent team collaboration.

 ## 🔎 FAQ

-FAQs: <https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs>
+FAQs: <https://github.com/zhayujie/CowAgent/wiki/FAQs>

 ## 🛠️ Contributing

-Welcome to add new channels, referring to the [Feishu channel](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/feishu/feishu_channel.py) as an example. Also welcome to contribute new Skills, referring to the [Skill Creator docs](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/skills/skill-creator/SKILL.md).
+Welcome to add new channels, referring to the [Feishu channel](https://github.com/zhayujie/CowAgent/blob/master/channel/feishu/feishu_channel.py) as an example. Also welcome to contribute new Skills, see the [Skill Creation docs](https://docs.cowagent.ai/en/skills/create), or submit to [Skill Hub](https://skills.cowagent.ai/submit).

 ## ✉ Contact

-Welcome to submit PRs and Issues, and support the project with a 🌟 Star. For questions, check the [FAQ list](https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs) or search [Issues](https://github.com/zhayujie/chatgpt-on-wechat/issues).
+Welcome to submit PRs and Issues, and support the project with a 🌟 Star. For questions, check the [FAQ list](https://github.com/zhayujie/CowAgent/wiki/FAQs) or search [Issues](https://github.com/zhayujie/CowAgent/issues).

 ## 🌟 Contributors

-![cow contributors](https://contrib.rocks/image?repo=zhayujie/chatgpt-on-wechat&max=1000)
+![cow contributors](https://contrib.rocks/image?repo=zhayujie/CowAgent&max=1000)
--- a/docs/en/channels/web.mdx
+++ b/docs/en/channels/web.mdx
@@ -38,6 +38,16 @@ Supports streaming output with real-time display of the Agent's reasoning proces

 <img width="850" src="https://cdn.link-ai.tech/doc/20260227180120.png" />

+#### Multi-Session Management
+
+The chat interface supports multi-session management. All session records are persistently stored in a SQLite database:
+
+- **Session List**: Click the history icon on the left to expand/collapse the session list panel, with scroll-to-load support for all historical sessions
+- **AI-Generated Titles**: After the first exchange in a new session, the model is automatically called to generate a short summary title
+- **New Session**: Click the "New Chat" button at the top of the session list or the `+` button in the input area to create a new session
+- **Delete Session**: Click the delete button on a session item and confirm to permanently delete the session and all its messages
+- **Clear Context**: Click the clear button in the input area to insert a divider in the current session. Messages above the divider are still displayed but no longer included as context for the model
+
 ### Model Management

 Manage model configurations online without manually editing config files:
--- a/docs/en/channels/weixin.mdx
+++ b/docs/en/channels/weixin.mdx
@@ -0,0 +1,72 @@
+---
+title: WeChat
+description: Connect CowAgent to personal WeChat
+---
+
+> Connect CowAgent to your personal WeChat. Simply scan a QR code to log in — no public IP required. Supports text, image, voice, file, and video messages.
+
+## 1. Configuration
+
+### Option A: Web Console
+
+Start the program and open the Web console (local access: http://127.0.0.1:9899). Go to the **Channels** tab, click **Connect Channel**, select **WeChat**, and follow the prompts to scan the QR code.
+
+### Option B: Config File
+
+Set `channel_type` to `weixin` in your `config.json`:
+
+```json
+{
+  "channel_type": "weixin"
+}
+```
+
+After starting the program, a QR code will be displayed in the terminal. Scan it with WeChat and confirm on your phone to complete login.
+
+<Note>
+  For backward compatibility, setting `channel_type` to `wx` also activates the WeChat channel.
+</Note>
+
+## 2. Parameters
+
+| Parameter | Description | Default |
+| --- | --- | --- |
+| `channel_type` | Set to `weixin` or `wx` | — |
+
+Login credentials are automatically saved to `~/.weixin_cow_credentials.json`. To force a re-login, delete this file and restart.
+
+## 3. Login
+
+### QR Code Login
+
+On first startup, a QR code is displayed in the terminal (valid for approximately 2 minutes). Scan it with WeChat and confirm on your phone.
+
+- The QR code automatically refreshes when it expires
+- The `qrcode` dependency is already included in `requirements.txt`, enabling QR code rendering directly in the terminal
+
+### Credential Persistence
+
+After successful login, credentials are saved to `~/.weixin_cow_credentials.json`. Subsequent startups will reuse the saved credentials without requiring a new scan.
+
+To force a re-login, delete the credentials file and restart the program.
+
+### Session Expiry
+
+When the WeChat session expires (errcode -14), the program automatically clears old credentials and initiates a new QR login — no manual intervention required.
+
+## 4. Supported Features
+
+| Feature | Status |
+| --- | --- |
+| Direct Messages | ✅ |
+| Text Messages | ✅ Send & Receive |
+| Image Messages | ✅ Send & Receive |
+| File Messages | ✅ Send & Receive |
+| Video Messages | ✅ Send & Receive |
+| Voice Messages | ✅ Receive |
+
+## 5. Notes
+
+1. Ensure network access to `ilinkai.weixin.qq.com`.
+2. Media files (images, files, videos) are transferred via CDN with AES-128-ECB encryption, handled automatically by the program.
+3. A stable network connection is recommended to avoid frequent disconnections that would require re-scanning.
--- a/docs/en/cli/general.mdx
+++ b/docs/en/cli/general.mdx
@@ -0,0 +1,126 @@
+---
+title: General Commands
+description: View status, manage config, and control context with commonly used commands
+---
+
+The following commands can be used in chat with the `/` prefix or in the terminal with the `cow` prefix (some are chat-only).
+
+<Tip>
+  In the Web console, typing `/` brings up an autocomplete menu with keyboard navigation and Tab completion.
+</Tip>
+
+## help
+
+Show help information for all available commands.
+
+```text
+/help
+```
+
+## status
+
+View current session and service status, including process info, model configuration, message count, and loaded skills.
+
+```text
+/status
+```
+
+## config
+
+View or modify runtime configuration. Changes take effect immediately without restarting.
+
+**View all configurable items:**
+
+```text
+/config
+```
+
+**View a single item:**
+
+```text
+/config model
+```
+
+**Modify a config item:**
+
+```text
+/config model deepseek-chat
+```
+
+**Configurable items:**
+
+| Item | Description | Example |
+| --- | --- | --- |
+| `model` | AI model name | `deepseek-chat` |
+| `agent_max_context_tokens` | Max context tokens | `40000` |
+| `agent_max_context_turns` | Max context memory turns | `30` |
+| `agent_max_steps` | Max decision steps per task | `15` |
+
+<Note>
+  When changing `model`, the system automatically matches the corresponding model API. Configuration is persisted to `config.json`.
+</Note>
+
+## context
+
+View current session context statistics, including message count and content length.
+
+```text
+/context
+```
+
+**Clear current session context:**
+
+```text
+/context clear
+```
+
+<Tip>
+  Clearing context makes the Agent "forget" previous conversation, useful for switching topics or freeing context space.
+</Tip>
+
+## logs
+
+View recent service logs. Shows the last 20 lines by default, up to 50.
+
+```text
+/logs
+```
+
+**Specify line count:**
+
+```text
+/logs 50
+```
+
+## knowledge
+
+View and manage the personal knowledge base. Shows statistics by default.
+
+```text
+/knowledge
+```
+
+**View directory structure:**
+
+```text
+/knowledge list
+```
+
+**Enable / disable knowledge base:**
+
+```text
+/knowledge on
+/knowledge off
+```
+
+<Note>
+  In the terminal CLI, `cow knowledge` and `cow knowledge list` are available, but `on|off` is only supported in chat (requires runtime effect).
+</Note>
+
+## version
+
+Show the current CowAgent version.
+
+```text
+/version
+```
--- a/docs/en/cli/index.mdx
+++ b/docs/en/cli/index.mdx
@@ -0,0 +1,91 @@
+---
+title: Commands Overview
+description: CowAgent command system — Terminal CLI and chat commands
+---
+
+CowAgent provides two ways to interact via commands:
+
+- **Terminal CLI** — Run `cow <command>` in your system terminal for service management, skill management, and other operations
+- **Chat Commands** — Type `/<command>` or `cow <command>` in any conversation to check status, manage skills, adjust configuration, etc.
+
+## Cow CLI
+
+After deploying with the one-click install script, the `cow` command is automatically available. For manual installations, run:
+
+```bash
+pip install -e .
+```
+
+Then use the `cow` command from anywhere:
+
+```bash
+cow help
+```
+
+Example output:
+
+```
+🐮 CowAgent CLI
+
+Usage: cow <command>
+
+Service:
+  start     Start the CowAgent service
+  stop      Stop the CowAgent service
+  restart   Restart the CowAgent service
+  update    Update code and restart service
+  status    Show service status
+  logs      View service logs
+
+Skills:
+  skill     Manage skills (list / search / install / uninstall ...)
+
+Knowledge:
+  knowledge View knowledge base stats and structure
+
+Others:
+  help      Show this help message
+  version   Show version
+```
+
+## Chat Commands
+
+In the Web console or any connected channel, type `/` to see command suggestions. Supported commands:
+
+| Command | Description |
+| --- | --- |
+| `/help` | Show command help |
+| `/status` | View service status and configuration |
+| `/config` | View or modify runtime configuration |
+| `/skill` | Manage skills (install, uninstall, enable, disable, etc.) |
+| `/knowledge` | View knowledge base statistics |
+| `/knowledge list` | View knowledge base directory structure |
+| `/knowledge on\|off` | Enable or disable knowledge base |
+| `/context` | View current session context info |
+| `/context clear` | Clear current session context |
+| `/logs` | View recent logs |
+| `/version` | Show version number |
+
+<Tip>
+  Service management commands like `/start`, `/stop`, `/restart` will prompt you to use them in the terminal instead, as they involve process operations.
+</Tip>
+
+## Command Availability
+
+| Command | Terminal (`cow`) | Chat (`/`) |
+| --- | :---: | :---: |
+| help | ✓ | ✓ |
+| version | ✓ | ✓ |
+| status | ✓ | ✓ |
+| logs | ✓ | ✓ |
+| config | ✗ | ✓ |
+| context | — | ✓ |
+| knowledge (subcommands) | ✓ | ✓ |
+| skill (subcommands) | ✓ | ✓ |
+| start / stop / restart | ✓ | ✗ |
+| update | ✓ | ✗ |
+| install-browser | ✓ | ✗ |
+
+<Note>
+  `context` only shows a hint in the terminal to use it in chat. `config` is only available in chat.
+</Note>
--- a/docs/en/cli/process.mdx
+++ b/docs/en/cli/process.mdx
@@ -0,0 +1,123 @@
+---
+title: Process Management
+description: Manage CowAgent process lifecycle with cow commands
+---
+
+Process management commands control the CowAgent background process. These commands are only available in the terminal.
+
+## start
+
+Start the CowAgent service. Runs as a background daemon by default and automatically tails logs.
+
+```bash
+cow start
+```
+
+**Options:**
+
+| Option | Description |
+| --- | --- |
+| `-f`, `--foreground` | Run in foreground, not as a background daemon |
+| `--no-logs` | Don't tail logs after starting |
+
+## stop
+
+Stop the running CowAgent service.
+
+```bash
+cow stop
+```
+
+## restart
+
+Restart the CowAgent service (stop then start).
+
+```bash
+cow restart
+```
+
+**Options:**
+
+| Option | Description |
+| --- | --- |
+| `--no-logs` | Don't tail logs after restart |
+
+## update
+
+Update code and restart the service. Automatically performs:
+
+1. Pull latest code (`git pull`)
+2. Stop current service
+3. Update Python dependencies
+4. Reinstall CLI
+5. Start service
+
+```bash
+cow update
+```
+
+<Warning>
+  If `git pull` fails (e.g., uncommitted local changes), the update aborts and the service remains unaffected.
+</Warning>
+
+## status
+
+Check CowAgent service status, including process info, version, and current model/channel configuration.
+
+```bash
+cow status
+```
+
+## logs
+
+View service logs.
+
+```bash
+cow logs
+```
+
+**Options:**
+
+| Option | Description | Default |
+| --- | --- | --- |
+| `-f`, `--follow` | Continuously tail log output | No |
+| `-n`, `--lines` | Show last N lines | 50 |
+
+Examples:
+
+```bash
+# View last 100 lines
+cow logs -n 100
+
+# Continuously tail logs
+cow logs -f
+```
+
+## install-browser
+
+Install Playwright and Chromium browser for the [browser tool](/en/tools/browser).
+
+```bash
+cow install-browser
+```
+
+<Tip>
+  Only needed when using browser tools (web browsing, screenshots, etc.).
+</Tip>
+
+## run.sh Compatibility
+
+If Cow CLI is not installed, you can use `run.sh` to manage the service:
+
+| cow command | run.sh equivalent |
+| --- | --- |
+| `cow start` | `./run.sh start` |
+| `cow stop` | `./run.sh stop` |
+| `cow restart` | `./run.sh restart` |
+| `cow update` | `./run.sh update` |
+| `cow status` | `./run.sh status` |
+| `cow logs` | `./run.sh logs` |
+
+<Note>
+  The `cow` command is recommended — it provides cleaner syntax and richer features. It is automatically installed via the one-click install script.
+</Note>
--- a/docs/en/cli/skill.mdx
+++ b/docs/en/cli/skill.mdx
@@ -0,0 +1,192 @@
+---
+title: Skill Management
+description: Install, uninstall, enable, disable, and manage skills via commands
+---
+
+Skill management commands are used to install, query, and manage CowAgent skills. Use `/skill <subcommand>` in chat or `cow skill <subcommand>` in the terminal.
+
+## list
+
+List installed skills and their status.
+
+<CodeGroup>
+```text Chat
+/skill list
+```
+
+```bash Terminal
+cow skill list
+```
+</CodeGroup>
+
+**Browse the Skill Hub** (view all available skills):
+
+<CodeGroup>
+```text Chat
+/skill list --remote
+```
+
+```bash Terminal
+cow skill list --remote
+```
+</CodeGroup>
+
+**Options:**
+
+| Option | Description | Default |
+| --- | --- | --- |
+| `--remote`, `-r` | Browse Skill Hub remote skill list | No |
+| `--page` | Page number for remote listing | 1 |
+
+## search
+
+Search for skills on the Skill Hub.
+
+<CodeGroup>
+```text Chat
+/skill search pptx
+```
+
+```bash Terminal
+cow skill search pptx
+```
+</CodeGroup>
+
+## install
+
+Install skills with a single `install` command from Cow Skill Hub, GitHub, ClawHub, or any URL (zip archives, SKILL.md links) — no manual download or configuration required.
+
+**From Skill Hub (recommended):**
+
+<CodeGroup>
+```text Chat
+/skill install pptx
+```
+
+```bash Terminal
+cow skill install pptx
+```
+</CodeGroup>
+
+**From GitHub:**
+
+<CodeGroup>
+```text Chat
+# Install all skills in a repo (auto-discovers subdirectories with SKILL.md)
+/skill install larksuite/cli
+
+# Specify a subdirectory to install a single skill
+/skill install https://github.com/larksuite/cli/tree/main/skills/lark-im
+
+# Use # to specify a subdirectory
+/skill install larksuite/cli#skills/lark-minutes
+```
+
+```bash Terminal
+# Install all skills in a repo (auto-discovers subdirectories with SKILL.md)
+cow skill install larksuite/cli
+
+# Specify a subdirectory to install a single skill
+cow skill install https://github.com/larksuite/cli/tree/main/skills/lark-im
+
+# Use # to specify a subdirectory
+cow skill install larksuite/cli#skills/lark-minutes
+```
+</CodeGroup>
+
+Supports full GitHub URLs and `owner/repo` shorthand. For mono-repos (multiple skills in one repository), omitting the subdirectory auto-discovers and batch-installs all skills; specifying a subdirectory installs only that skill.
+
+**From ClawHub:**
+
+<CodeGroup>
+```text Chat
+/skill install clawhub:baidu-search
+```
+
+```bash Terminal
+cow skill install clawhub:baidu-search
+```
+</CodeGroup>
+
+**From URL:**
+
+<CodeGroup>
+```text Chat
+# Install from a zip archive (single or batch)
+/skill install https://cdn.link-ai.tech/skills/pptx.zip
+
+# Install from a SKILL.md link
+/skill install https://example.com/path/to/SKILL.md
+```
+
+```bash Terminal
+# Install from a zip archive (single or batch)
+cow skill install https://cdn.link-ai.tech/skills/pptx.zip
+
+# Install from a SKILL.md link
+cow skill install https://example.com/path/to/SKILL.md
+```
+</CodeGroup>
+
+Supports installing from zip / tar.gz archive URLs — automatically extracts and discovers directories containing `SKILL.md`, with support for single or batch install. Also supports installing directly from a `SKILL.md` file URL, automatically parsing the skill name and description.
+
+## uninstall
+
+Uninstall an installed skill.
+
+<CodeGroup>
+```text Chat
+/skill uninstall pptx
+```
+
+```bash Terminal
+cow skill uninstall pptx
+```
+</CodeGroup>
+
+<Warning>
+  Uninstalling deletes all files in the skill directory. This action cannot be undone.
+</Warning>
+
+## enable / disable
+
+Enable or disable a skill. Disabled skills will not be invoked by the Agent.
+
+<CodeGroup>
+```text Chat
+/skill enable pptx
+/skill disable pptx
+```
+
+```bash Terminal
+cow skill enable pptx
+cow skill disable pptx
+```
+</CodeGroup>
+
+## info
+
+View details of an installed skill, including a preview of its `SKILL.md`.
+
+<CodeGroup>
+```text Chat
+/skill info pptx
+```
+
+```bash Terminal
+cow skill info pptx
+```
+</CodeGroup>
+
+## Skill Sources
+
+Installed skills track their origin, viewable via `/skill list`:
+
+| Source | Description |
+| --- | --- |
+| `builtin` | Built-in project skills |
+| `cowhub` | Installed from CowAgent Skill Hub |
+| `github` | Installed directly from a GitHub URL |
+| `clawhub` | Installed from ClawHub |
+| `url` | Installed from a SKILL.md URL |
+| `local` | Locally created skills |
--- a/docs/en/guide/manual-install.mdx
+++ b/docs/en/guide/manual-install.mdx
@@ -8,12 +8,12 @@ description: Deploy CowAgent manually (source code / Docker)
 ### 1. Clone the project

 ```bash
-git clone https://github.com/zhayujie/chatgpt-on-wechat
-cd chatgpt-on-wechat/
+git clone https://github.com/zhayujie/CowAgent
+cd CowAgent/
 ```

 <Tip>
-  For network issues, use the mirror: https://gitee.com/zhayujie/chatgpt-on-wechat
+  For network issues, use the mirror: https://gitee.com/zhayujie/CowAgent
 </Tip>

 ### 2. Install dependencies
@@ -30,7 +30,25 @@ Optional dependencies (recommended):
 pip3 install -r requirements-optional.txt
 ```

-### 3. Configure
+### 3. Install Cow CLI
+
+Install the command-line tool for managing services and skills:
+
+```bash
+pip3 install -e .
+```
+
+Then use the `cow` command:
+
+```bash
+cow help
+```
+
+<Note>
+  This step is recommended. After installation you can use `cow start`, `cow stop`, `cow update` to manage the service, and `cow skill` to manage skills. Without the CLI, you can use `./run.sh` or `python3 app.py` to run.
+</Note>
+
+### 4. Configure

 Copy the config template and edit:

@@ -40,22 +58,32 @@ cp config-template.json config.json

 Fill in model API keys, channel type, and other settings in `config.json`. See the [model docs](/en/models/index) for details.

-### 4. Run
+### 5. Run

-**Local run:**
+**Using Cow CLI (recommended):**
+
+```bash
+cow start
+```
+
+**Or run locally in foreground:**

 ```bash
 python3 app.py
 ```

-By default, the Web service starts. Access `http://localhost:9899/chat` to chat.
+By default, the Web console starts. Access `http://localhost:9899` to chat.

-**Background run on server:**
+**Background run on server (without CLI):**

 ```bash
 nohup python3 app.py & tail -f nohup.out
 ```

+<Tip>
+  If deploying on a server, open port `9899` in your firewall or security group to access the Web console. It's recommended to restrict access to specific IPs for security.
+</Tip>
+
 ## Docker Deployment

 Docker deployment does not require cloning source code or installing dependencies. For Agent mode, source deployment is recommended for broader system access.
@@ -67,7 +95,7 @@ Docker deployment does not require cloning source code or installing dependencie
 **1. Download config**

 ```bash
-wget https://cdn.link-ai.tech/code/cow/docker-compose.yml
+curl -O https://cdn.link-ai.tech/code/cow/docker-compose.yml
 ```

 Edit `docker-compose.yml` with your configuration.
@@ -84,6 +112,10 @@ sudo docker compose up -d
 sudo docker logs -f chatgpt-on-wechat
 ```

+<Tip>
+  If deploying on a server, open port `9899` in your firewall or security group to access the Web console. It's recommended to restrict access to specific IPs for security.
+</Tip>
+
 ## Core Configuration

 ```json
@@ -109,5 +141,5 @@ sudo docker logs -f chatgpt-on-wechat
 | `agent_max_steps` | Max decision steps per task | `15` |

 <Tip>
-  Full configuration options are in the project [`config.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/config.py).
+  Full configuration options are in the project [`config.py`](https://github.com/zhayujie/CowAgent/blob/master/config.py).
 </Tip>
--- a/docs/en/guide/quick-start.mdx
+++ b/docs/en/guide/quick-start.mdx
@@ -9,31 +9,46 @@ Supports Linux, macOS, and Windows. Requires Python 3.7-3.12 (3.9 recommended).

 ## Install Command

-```bash
-bash <(curl -sS https://cdn.link-ai.tech/code/cow/run.sh)
-```
+<Tabs>
+  <Tab title="Linux / macOS">
+    ```bash
+    bash <(curl -fsSL https://cdn.link-ai.tech/code/cow/run.sh)
+    ```
+  </Tab>
+  <Tab title="Windows (PowerShell)">
+    ```powershell
+    irm https://cdn.link-ai.tech/code/cow/run.ps1 | iex
+    ```
+  </Tab>
+</Tabs>

 The script automatically performs these steps:

 1. Check Python environment (requires Python 3.7+)
 2. Install required tools (git, curl, etc.)
-3. Clone project to `~/chatgpt-on-wechat`
-4. Install Python dependencies
+3. Clone project to `~/CowAgent`
+4. Install Python dependencies and Cow CLI
 5. Guided configuration for AI model and channel
 6. Start service

-By default, the Web service starts after installation. Access `http://localhost:9899/chat` to begin chatting.
+By default, the Web console starts after installation. Access `http://localhost:9899` to begin chatting.

 ## Management Commands

-After installation, use these commands to manage the service:
+After installation, use the `cow` command to manage the service:

 | Command | Description |
 | --- | --- |
-| `./run.sh start` | Start service |
-| `./run.sh stop` | Stop service |
-| `./run.sh restart` | Restart service |
-| `./run.sh status` | Check run status |
-| `./run.sh logs` | View real-time logs |
-| `./run.sh config` | Reconfigure |
-| `./run.sh update` | Update project code |
+| `cow start` | Start service |
+| `cow stop` | Stop service |
+| `cow restart` | Restart service |
+| `cow status` | Check run status |
+| `cow logs` | View real-time logs |
+| `cow update` | Update code and restart |
+| `cow install-browser` | Install browser tool dependencies |
+
+See the [Commands documentation](/en/cli/index) for more details.
+
+<Note>
+  If the `cow` command is not available, you can use `./run.sh <command>` (Linux/macOS) or `.\scripts\run.ps1 <command>` (Windows) as a fallback. Both are functionally equivalent.
+</Note>
--- a/docs/en/intro/architecture.mdx
+++ b/docs/en/intro/architecture.mdx
@@ -11,14 +11,16 @@ CowAgent's architecture consists of the following core modules:

 <img src="https://cdn.link-ai.tech/doc/68ef7b212c6f791e0e74314b912149f9-sz_5847990.png" alt="CowAgent Architecture" />

-### Core Modules
-
 | Module | Description |
 | --- | --- |
-| **Channels** | Message channel layer for receiving and sending messages. Supports Web, Feishu, DingTalk, WeCom, WeChat Official Account, and more |
-| **Agent Core** | Agent engine including task planning, memory system, and skills engine |
-| **Tools** | Tool layer for Agent to access OS resources. 10+ built-in tools |
-| **Models** | Model layer with unified access to mainstream LLMs |
+| **Plan** | Understands user intent, decomposes complex tasks into multi-step plans, and iteratively invokes tools until the goal is achieved |
+| **Memory** | Automatically persists important information as core memory and daily memory, with hybrid keyword and vector retrieval for cross-session context continuity |
+| **Knowledge** | Organizes structured knowledge by topic. The Agent autonomously distills valuable information into Markdown pages, maintaining indexes and cross-references to build a growing knowledge network |
+| **Tools** | Core capability for Agent to access OS resources. 10+ built-in tools including file read/write, terminal, browser, scheduler, memory search, web search, and more |
+| **Skills** | Loads and manages Skills. Supports one-click installation from Skill Hub, GitHub, and more, or custom skill creation through conversation |
+| **Models** | Model layer with unified access to OpenAI, Claude, Gemini, DeepSeek, MiniMax, GLM, Qwen, and other mainstream LLMs |
+| **Channels** | Message channel layer for receiving and sending messages. Supports Web console, WeChat, Feishu, DingTalk, WeCom, WeChat Official Account, and more with a unified protocol |
+| **CLI** | Command-line system providing terminal commands (`cow`) and chat commands (`/`) for process management, skill installation, configuration, knowledge base management, and more |

 ## Agent Mode Workflow

@@ -28,7 +30,7 @@ When Agent mode is enabled, CowAgent runs as an autonomous agent with the follow
 2. **Understand Intent** — Analyze task requirements and context
 3. **Plan Task** — Break complex tasks into multiple steps
 4. **Invoke Tools** — Select and execute appropriate tools for each step
-5. **Update Memory** — Store important information in long-term memory
+5. **Update Memory & Knowledge** — Store important information in long-term memory and organize structured knowledge into the knowledge base
 6. **Return Result** — Send execution results back to the user

 ## Workspace Directory Structure
@@ -39,9 +41,12 @@ The Agent workspace is located at `~/cow` by default and stores system prompts,
 ~/cow/
 ├── system.md          # Agent system prompt
 ├── user.md            # User profile
+├── MEMORY.md          # Core memory
 ├── memory/            # Long-term memory storage
-│   ├── core.md        # Core memory
-│   └── daily/         # Daily memory
+│   └── YYYY-MM-DD.md  # Daily memory
+├── knowledge/         # Personal knowledge base
+│   ├── index.md       # Knowledge index
+│   └── <category>/    # Topic-based pages
 └── skills/            # Custom skills
    ├── skill-1/
    └── skill-2/
@@ -75,3 +80,4 @@ Configure Agent mode parameters in `config.json`:
 | `agent_max_context_tokens` | Max context tokens | `40000` |
 | `agent_max_context_turns` | Max context turns | `30` |
 | `agent_max_steps` | Max decision steps per task | `15` |
+| `knowledge` | Enable personal knowledge base | `true` |
--- a/docs/en/intro/features.mdx
+++ b/docs/en/intro/features.mdx
@@ -1,6 +1,6 @@
 ---
 title: Features
-description: CowAgent long-term memory, task planning, and skills system in detail
+description: CowAgent long-term memory, task planning, skills system, CLI commands, and browser tool in detail
 ---

 ## 1. Long-term Memory
@@ -15,13 +15,26 @@ In subsequent long-term conversations, the Agent intelligently stores or retriev
  <img src="https://cdn.link-ai.tech/doc/20260203000455.png" width="800" />
 </Frame>

-## 2. Task Planning and Tool Use
+## 2. Personal Knowledge Base
+
+> The knowledge base system enables the Agent to continuously accumulate and organize structured knowledge. Unlike memory which records along a timeline, the knowledge base is organized by topics, transforming articles, conversation insights, and learning materials into interconnected Markdown pages that form a continuously growing knowledge network.
+
+The Agent automatically organizes valuable information from conversations into knowledge pages, maintaining cross-references and indexes. The Web console provides document browsing and knowledge graph visualization. Knowledge is stored in `~/cow/knowledge/` within the workspace.
+
+- **Auto-organization**: The Agent autonomously extracts and organizes structured knowledge during conversations, maintaining indexes and cross-references
+- **Knowledge graph**: Automatically builds a knowledge graph from cross-references between pages, with interactive graph visualization in the Web console
+- **Chat integration**: Knowledge document links referenced in Agent replies can be clicked directly in the Web console for viewing
+- **CLI management**: Use `/knowledge` commands to view stats, browse directory, and toggle the feature with `/knowledge on|off`
+
+See [Personal Knowledge Base](/en/knowledge) for details.
+
+## 3. Task Planning and Tool Use

 Tools are the core of how the Agent accesses operating system resources. The Agent intelligently selects and invokes tools based on task requirements, performing file read/write, command execution, scheduled tasks, and more. Built-in tools are implemented in the project's `agent/tools/` directory.

-**Key tools:** file read/write/edit, Bash terminal, file send, scheduler, memory search, web search, environment config, and more.
+**Key tools:** file read/write/edit, Bash terminal, browser, file send, scheduler, memory search, web search, environment config, and more.

-### 2.1 Terminal and File Access
+### 3.1 Terminal and File Access

 Access to the OS terminal and file system is the most fundamental and core capability. Many other tools and skills build on top of this. Users can interact with the Agent from a mobile device to operate resources on their personal computer or server:

@@ -29,7 +42,7 @@ Access to the OS terminal and file system is the most fundamental and core capab
  <img src="https://cdn.link-ai.tech/doc/20260202181130.png" width="800" />
 </Frame>

-### 2.2 Programming Capability
+### 3.2 Programming Capability

 Combining programming and system access, the Agent can execute the complete **Vibecoding workflow** — from information search, asset generation, coding, testing, deployment, Nginx configuration, to publishing — all triggered by a single command from your phone:

@@ -37,7 +50,7 @@ Combining programming and system access, the Agent can execute the complete **Vi
  <img src="https://cdn.link-ai.tech/doc/20260203121008.png" width="800" />
 </Frame>

-### 2.3 Scheduled Tasks
+### 3.3 Scheduled Tasks

 The `scheduler` tool enables dynamic scheduled tasks, supporting **one-time tasks, fixed intervals, and Cron expressions**. Tasks can be triggered as either a **fixed message send** or an **Agent dynamic task** execution:

@@ -45,7 +58,15 @@ The `scheduler` tool enables dynamic scheduled tasks, supporting **one-time task
  <img src="https://cdn.link-ai.tech/doc/20260202195402.png" width="800" />
 </Frame>

-### 2.4 Environment Variable Management
+### 3.4 Browser
+
+The built-in `browser` tool allows the Agent to control a Chromium browser to visit web pages, fill forms, click elements, and take screenshots, with support for dynamic JS-rendered pages. Run `cow install-browser` to install with one command, automatically adapting to server (headless) and desktop environments:
+
+<Frame>
+  <img src="https://cdn.link-ai.tech/doc/20260401110103.png" width="800" />
+</Frame>
+
+### 3.5 Environment Variable Management

 Secrets required by skills are stored in an environment variable file, managed by the `env_config` tool. You can update secrets through conversation, with built-in security protection and desensitization:

@@ -53,14 +74,17 @@ Secrets required by skills are stored in an environment variable file, managed b
  <img src="https://cdn.link-ai.tech/doc/20260202234939.png" width="800" />
 </Frame>

-## 3. Skills System
+## 4. Skills System

 The Skills system provides infinite extensibility for the Agent. Each Skill consists of a description file, execution scripts (optional), and resources (optional), describing how to complete specific types of tasks. Skills allow the Agent to follow instructions for complex workflows, invoke tools, or integrate third-party systems.

+- **[Skill Hub](https://skills.cowagent.ai/):** An open skill marketplace featuring official, community, and third-party skills. Install with one command.
 - **Built-in skills:** Located in the project's `skills/` directory, including skill creator, image recognition, LinkAI agent, web fetch, and more. Built-in skills are automatically enabled based on dependency conditions (API keys, system commands, etc.).
 - **Custom skills:** Created by users through conversation, stored in the workspace (`~/cow/skills/`), capable of implementing any complex business process or third-party integration.

-### 3.1 Creating Skills
+Install skills: `/skill install <name>` or `cow skill install <name>`, supporting Skill Hub, GitHub, ClawHub, URL, and more.
+
+### 4.1 Creating Skills

 The `skill-creator` skill enables rapid skill creation through conversation. You can ask the Agent to codify a workflow as a skill, or send any API documentation and examples for the Agent to complete the integration directly:

@@ -68,7 +92,7 @@ The `skill-creator` skill enables rapid skill creation through conversation. You
  <img src="https://cdn.link-ai.tech/doc/20260202202247.png" width="800" />
 </Frame>

-### 3.2 Web Search and Image Recognition
+### 4.2 Web Search and Image Recognition

 - **Web search:** Built-in `web_search` tool, supports multiple search engines. Configure `BOCHA_API_KEY` or `LINKAI_API_KEY` to enable.
 - **Image recognition:** Built-in `openai-image-vision` skill, supports `gpt-4.1-mini`, `gpt-4.1`, and other models. Requires `OPENAI_API_KEY`.
@@ -77,29 +101,33 @@ The `skill-creator` skill enables rapid skill creation through conversation. You
  <img src="https://cdn.link-ai.tech/doc/20260202213219.png" width="800" />
 </Frame>

-### 3.3 Third-party Knowledge Bases and Plugins
+### 4.3 Skill Hub

-The `linkai-agent` skill makes all agents on [LinkAI](https://link-ai.tech/) available as Skills for the Agent, enabling multi-agent decision making.
+Visit [skills.cowagent.ai](https://skills.cowagent.ai/) to browse all available skills, or use commands in conversation:

-Configuration: set `LINKAI_API_KEY` via `env_config`, then add agent descriptions in `skills/linkai-agent/config.json`:
-
-```json
-{
-  "apps": [
-    {
-      "app_code": "G7z6vKwp",
-      "app_name": "LinkAI Customer Support",
-      "app_description": "Select only when the user needs help with LinkAI platform questions"
-    },
-    {
-      "app_code": "SFY5x7JR",
-      "app_name": "Content Creator",
-      "app_description": "Use only when the user needs to create images or videos"
-    }
-  ]
-}
+```text
+/skill list --remote          # Browse Skill Hub
+/skill search <keyword>       # Search skills
+/skill install <name>          # Install with one command
 ```

-<Frame>
-  <img src="https://cdn.link-ai.tech/doc/20260202234350.png" width="750" />
-</Frame>
+Also supports installing skills from GitHub, ClawHub, LinkAI, and other third-party platforms. See [Install Skills](/en/skills/install) for details.
+
+<img src="https://cdn.link-ai.tech/doc/20260401110103.png" width="750" />
+
+## 5. CLI Command System
+
+CowAgent provides two command interaction methods, covering service management, skill installation, configuration, and more:
+
+- **Terminal CLI:** Run `cow <command>` in the system terminal, supporting `start`, `stop`, `restart`, `update`, `status`, `logs`, `skill`, etc.
+- **Chat commands:** Type `/<command>` in conversation. The Web console shows a command menu when you type `/`.
+
+```bash
+cow start              # Start service
+cow stop               # Stop service
+cow update             # Update and restart
+cow skill install pptx # Install a skill
+cow install-browser    # Install browser tool
+```
+
+See [Command Overview](https://docs.cowagent.ai/en/cli) for details.
--- a/docs/en/intro/index.mdx
+++ b/docs/en/intro/index.mdx
@@ -7,10 +7,10 @@ description: CowAgent - AI Super Assistant powered by LLMs

 **CowAgent** is an AI super assistant powered by LLMs with autonomous task planning, long-term memory, skills system, multimodal messages, multiple model support, and multi-platform deployment.

-CowAgent can proactively think and plan tasks, operate computers and external resources, create and execute Skills, and continuously grow with long-term memory. It supports flexible switching between multiple models, handles text, voice, images, files and other multimodal messages, and can be integrated into web, Feishu, DingTalk, WeCom, and WeChat Official Account. It runs 7x24 hours on your personal computer or server.
+CowAgent can proactively think and plan tasks, operate computers and external resources, create and execute Skills, and continuously grow with long-term memory. It supports flexible switching between multiple models, handles text, voice, images, files and other multimodal messages, and can be integrated into WeChat, web, Feishu, DingTalk, WeCom, and WeChat Official Account. It runs 7x24 hours on your personal computer or server.

-<Card title="GitHub" icon="github" href="https://github.com/zhayujie/chatgpt-on-wechat">
-  github.com/zhayujie/chatgpt-on-wechat
+<Card title="GitHub" icon="github" href="https://github.com/zhayujie/CowAgent">
+  github.com/zhayujie/CowAgent
 </Card>

 ## Core Capabilities
@@ -22,17 +22,26 @@ CowAgent can proactively think and plan tasks, operate computers and external re
  <Card title="Long-term Memory" icon="database" href="/en/memory">
    Automatically persists conversation memory to local files and databases, including core memory and daily memory, with keyword and vector retrieval support.
  </Card>
+  <Card title="Knowledge Base" icon="book" href="/en/knowledge">
+    Automatically organizes structured knowledge with knowledge graph visualization, building a continuously growing knowledge network through cross-references.
+  </Card>
  <Card title="Skills System" icon="puzzle-piece" href="/en/skills/index">
    Implements a Skills creation and execution engine with built-in skills, and supports custom Skills development through natural language conversation.
  </Card>
  <Card title="Multimodal Messages" icon="image" href="/en/channels/web">
    Supports parsing, processing, generating, and sending text, images, voice, files, and other message types.
  </Card>
+  <Card title="Tool System" icon="wrench" href="/en/tools/index">
+    Built-in tools for file I/O, terminal execution, browser automation, scheduled tasks, messaging, and more. The Agent autonomously invokes tools to accomplish complex tasks.
+  </Card>
+  <Card title="Command System" icon="terminal" href="/en/cli/index">
+    Provides terminal CLI and in-chat commands for process management, skill installation, configuration, context inspection, and other common operations.
+  </Card>
  <Card title="Multiple Model Support" icon="microchip" href="/en/models/index">
    Supports mainstream model providers including OpenAI, Claude, Gemini, DeepSeek, MiniMax, GLM, Qwen, Kimi, Doubao, and more.
  </Card>
-  <Card title="Multi-platform Deployment" icon="server" href="/en/channels/web">
-    Runs on local computers or servers, integrable into web, Feishu, DingTalk, WeChat Official Account, and WeCom applications.
+  <Card title="Multi-platform Deployment" icon="server" href="/en/channels/weixin">
+    Runs on local computers or servers, integrable into WeChat, web, Feishu, DingTalk, WeChat Official Account, and WeCom applications.
  </Card>
 </CardGroup>

@@ -40,9 +49,18 @@ CowAgent can proactively think and plan tasks, operate computers and external re

 Run the following command in your terminal for one-click install, configuration, and startup:

-```bash
-bash <(curl -sS https://cdn.link-ai.tech/code/cow/run.sh)
-```
+<Tabs>
+  <Tab title="Linux / macOS">
+    ```bash
+    bash <(curl -fsSL https://cdn.link-ai.tech/code/cow/run.sh)
+    ```
+  </Tab>
+  <Tab title="Windows (PowerShell)">
+    ```powershell
+    irm https://cdn.link-ai.tech/code/cow/run.ps1 | iex
+    ```
+  </Tab>
+</Tabs>

 By default, the Web service starts after running. Access `http://localhost:9899/chat` to chat in the web interface.

@@ -57,7 +75,7 @@ By default, the Web service starts after running. Access `http://localhost:9899/

 ## Disclaimer

-1. This project follows the [MIT License](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/LICENSE) and is intended for technical research and learning. Users must comply with local laws, regulations, policies, and corporate bylaws. Any illegal or rights-infringing use is prohibited.
+1. This project follows the [MIT License](https://github.com/zhayujie/CowAgent/blob/master/LICENSE) and is intended for technical research and learning. Users must comply with local laws, regulations, policies, and corporate bylaws. Any illegal or rights-infringing use is prohibited.
 2. Agent mode consumes more tokens than normal chat mode. Choose models based on effectiveness and cost. Agent has access to the host operating system — deploy with caution.
 3. CowAgent focuses on open-source development and does not participate in, authorize, or issue any cryptocurrency.

--- a/docs/en/knowledge/index.mdx
+++ b/docs/en/knowledge/index.mdx
@@ -0,0 +1,89 @@
+---
+title: Personal Knowledge Base
+description: CowAgent personal knowledge base — structured knowledge accumulation, automatic organization, and knowledge graph
+---
+
+The personal knowledge base is the Agent's long-term structured knowledge store, saved in the `knowledge/` directory within the workspace. Unlike memory, which is organized by timeline, the knowledge base organizes content by topic — articles, conversation insights, and learning materials are structured into interlinked Markdown pages, forming a continuously growing knowledge network.
+
+## Core Concepts
+
+### Knowledge vs Memory
+
+| Dimension | Knowledge Base (knowledge/) | Long-term Memory (memory/) |
+| --- | --- | --- |
+| Organization | By topic, interlinked | By timeline, dated files |
+| Writing | Agent actively structures content | Auto-summarized on context trimming |
+| Content | Refined, structured knowledge | Raw conversation summaries |
+| Use cases | Study notes, tech docs, project knowledge | Conversation history, event records |
+
+### Directory Structure
+
+```
+~/cow/knowledge/
+├── index.md          # Knowledge index, entry point for all pages
+├── log.md            # Change log, records each write
+├── concepts/         # Conceptual knowledge
+│   └── machine-learning.md
+├── entities/         # Entity knowledge (people, orgs, tools)
+│   └── openai.md
+└── sources/          # Source knowledge (articles, papers)
+    └── llm-wiki.md
+```
+
+The directory structure is flexible — the Agent automatically creates appropriate category directories based on actual content. Users can also customize the organization.
+
+## Automatic Organization
+
+Knowledge writing is an autonomous Agent behavior, triggered in these scenarios:
+
+- **User shares an article or document** — The Agent automatically extracts key information and creates a structured knowledge page
+- **Conversation produces valuable conclusions** — The Agent organizes insights into knowledge pages and links them to existing knowledge
+- **User explicitly requests organization** — Users can guide the Agent to organize and update knowledge through conversation
+
+Each knowledge page includes cross-reference links to related pages, gradually building a knowledge graph.
+
+<Frame>
+  <img src="https://gist.github.com/user-attachments/assets/3ce92f78-1863-4820-8fa8-660c0f2b7f09" alt="Conversational knowledge ingest" />
+</Frame>
+
+## Knowledge Retrieval
+
+The Agent can retrieve knowledge during conversation through:
+
+- **Index lookup** — Quickly locate relevant pages via `knowledge/index.md`
+- **Semantic search** — Search knowledge content via the `memory_search` tool
+- **Direct read** — Read specific knowledge files via the `memory_get` tool
+
+## Web Console
+
+The web console provides a dedicated "Knowledge" module with:
+
+- **Document browsing** — Tree-style directory structure, searchable and collapsible, click to view content
+- **Knowledge graph** — Interactive graph visualizing relationships between knowledge pages
+- **Chat integration** — Knowledge document links referenced in Agent replies are clickable for direct navigation
+
+<Frame>
+  <img src="https://gist.github.com/user-attachments/assets/b7b9d6be-0ac1-4c65-803b-2c6b36bd59a7" alt="Knowledge document browsing" />
+</Frame>
+
+<Frame>
+  <img src="https://gist.github.com/user-attachments/assets/44ae68ca-96cc-40b9-ab33-cdbec34c2379" alt="Knowledge graph visualization" />
+</Frame>
+
+## CLI Commands
+
+Manage the knowledge base with the `/knowledge` command:
+
+| Command | Description |
+| --- | --- |
+| `/knowledge` | Show knowledge base statistics |
+| `/knowledge list` | Display file directory as a tree |
+| `/knowledge on` | Enable the knowledge base feature |
+| `/knowledge off` | Disable the knowledge base feature |
+
+## Configuration
+
+| Parameter | Description | Default |
+| --- | --- | --- |
+| `knowledge` | Whether to enable the personal knowledge base | `true` |
+| `agent_workspace` | Workspace path; knowledge is stored under the `knowledge/` subdirectory | `~/cow` |
--- a/docs/en/memory/context.mdx
+++ b/docs/en/memory/context.mdx
@@ -0,0 +1,80 @@
+---
+title: Short-term Memory
+description: Conversation context — message management, compression strategies, and context operations
+---
+
+Conversation context is the Agent's short-term memory, containing all messages in the current session (user input, Agent replies, tool calls and results). Proper context management is critical for the Agent's reasoning quality and cost control.
+
+## Context Structure
+
+Each conversation turn consists of:
+
+```
+User message → Agent thinking → Tool call → Tool result → ... → Agent final reply
+```
+
+A single turn may include multiple tool calls (controlled by `agent_max_steps`). All tool calls and results are retained in context until compressed or trimmed.
+
+## Key Configuration
+
+| Parameter | Description | Default |
+| --- | --- | --- |
+| `agent_max_context_tokens` | Maximum context token budget | `50000` |
+| `agent_max_context_turns` | Maximum conversation turns in context | `20` |
+| `agent_max_steps` | Maximum decision steps per turn (tool call count) | `15` |
+
+Configurable via `config.json` or the `/config` chat command.
+
+## Compression Strategy
+
+When context exceeds limits, the system automatically compresses to free space. The process has multiple stages:
+
+### 1. Tool Result Truncation
+
+Before each decision loop, the system checks tool call results in historical turns. Results exceeding **20,000 characters** are truncated, keeping only the beginning and end with a truncation notice. Current turn results are not affected.
+
+### 2. Turn Trimming
+
+When conversation turns exceed `agent_max_context_turns`:
+
+- The **oldest half** of complete turns is trimmed (preserving tool call chain integrity)
+- Trimmed messages are summarized by LLM and **written to the daily memory file**
+- Remaining turns stay intact
+
+### 3. Token Budget Trimming
+
+After turn trimming, if tokens still exceed the budget:
+
+- **Fewer than 5 turns**: All turns undergo **text compression** — each turn keeps only the first user text and last Agent reply, removing intermediate tool call chains
+- **5 or more turns**: The **first half** of turns is trimmed again, with discarded content also written to memory
+
+### 4. Overflow Emergency Handling
+
+When the model API returns a context overflow error:
+
+1. All current messages are summarized and written to memory
+2. Aggressive trimming is applied (tool results limited to 10K chars, user text to 10K, max 5 turns)
+3. If still overflowing, the entire conversation context is cleared
+
+## Session Persistence
+
+Conversation messages are persisted to a local database, automatically restored after service restart. Restore strategy:
+
+- Restores the most recent **`max(3, max_context_turns / 6)`** turns
+- Only retains each turn's **user text and Agent final reply**, not intermediate tool call chains
+- Sessions older than **30 days** are automatically cleaned up
+
+## Commands
+
+Use these commands in chat to manage context:
+
+| Command | Description |
+| --- | --- |
+| `/context` | View current context statistics (message count, role distribution, total characters) |
+| `/context clear` | Clear current session context |
+| `/config agent_max_context_tokens 80000` | Adjust context token budget |
+| `/config agent_max_context_turns 30` | Adjust context turn limit |
+
+<Tip>
+  After clearing context, the Agent "forgets" previous conversation content. Content that was already written to long-term memory can still be retrieved via memory search.
+</Tip>
--- a/docs/en/memory/index.mdx
+++ b/docs/en/memory/index.mdx
@@ -1,30 +1,39 @@
 ---
-title: Memory
-description: CowAgent long-term memory system
+title: Long-term Memory
+description: CowAgent long-term memory system — file persistence, automatic writing, and hybrid retrieval
 ---

-The memory system enables the Agent to remember important information over time, continuously accumulating experience, understanding user preferences, and truly achieving autonomous thinking and continuous growth.
+Long-term memory is stored in workspace files, persisting across sessions. The Agent loads historical memory on demand via retrieval tools during conversation, and automatically writes conversation summaries to long-term memory when context is trimmed.

 ## Memory Types

 ### Core Memory (MEMORY.md)

-Stored in `~/cow/MEMORY.md`, containing long-term user preferences, important decisions, key facts, and other information that doesn't fade over time. Automatically injected into the system prompt on every conversation turn as background knowledge.
+Stored in `~/cow/MEMORY.md`, containing long-term user preferences, important decisions, key facts, and other information that doesn't fade over time. The Agent reads and writes this file via tools to maintain long-term knowledge.

 ### Daily Memory (memory/YYYY-MM-DD.md)

-Stored in `~/cow/memory/` directory, named by date (e.g. `2026-03-08.md`), recording daily conversation summaries and key events. Files are only created on first write to avoid generating empty files.
+Stored in `~/cow/memory/` directory, named by date (e.g., `2026-03-08.md`), recording daily conversation summaries and key events. Files are only created on first write to avoid generating empty files.

-## Memory Writing
+## Automatic Writing

-The Agent automatically persists conversation content to daily memory through the following mechanisms:
+The Agent automatically persists conversation content to long-term memory through the following mechanisms:

- **On context trimming** — When conversation turns or tokens exceed the configured limit, the oldest half of the context is trimmed in batch, and the discarded content is summarized by LLM into key information and written to the daily memory file
+- **On context trimming** — When conversation turns or tokens exceed the configured limit, the oldest half of the context is trimmed, and the discarded content is summarized by LLM into key information and written to the daily memory file
 - **Daily scheduled summary** — A full summary is automatically triggered at 23:55 every day, ensuring memory is preserved even on low-activity days (skipped if content hasn't changed)
 - **On API context overflow** — When the model API returns a context overflow error, the current conversation summary is saved as an emergency measure

 All memory writes run asynchronously in a background thread (LLM summarization + file writing), never blocking normal conversation replies.

+## Memory Retrieval
+
+The memory system supports hybrid retrieval modes:
+
+- **Keyword retrieval** — FTS5 full-text index matching with BM25 ranking
+- **Vector retrieval** — Embedding-based semantic similarity search, finds relevant memory even with different wording
+
+The Agent automatically triggers memory retrieval during conversation as needed, incorporating relevant historical information into context. Results are ranked by a combined score (default: 0.7 vector weight + 0.3 keyword weight). Daily memory scores decay over time (30-day half-life), while core memory does not decay.
+
 ## First Launch

 On first launch, the Agent will proactively ask the user for key information and save it to the workspace (default `~/cow`):
@@ -40,27 +49,10 @@ On first launch, the Agent will proactively ask the user for key information and
  <img src="https://cdn.link-ai.tech/doc/20260203000455.png" width="800" />
 </Frame>

-## Memory Retrieval
-
-The memory system supports hybrid retrieval modes:
-
- **Keyword retrieval** — Match historical memory based on keywords
- **Vector retrieval** — Semantic similarity search, finds relevant memory even with different wording
-
-The Agent automatically triggers memory retrieval during conversation as needed, incorporating relevant historical information into context. Core memory (`MEMORY.md`) is always injected into the system prompt, while daily memory is loaded on demand via retrieval.
-
 ## Configuration

-```json
-{
-  "agent_workspace": "~/cow",
-  "agent_max_context_tokens": 40000,
-  "agent_max_context_turns": 20
-}
-```
-
 | Parameter | Description | Default |
 | --- | --- | --- |
 | `agent_workspace` | Workspace path, memory files stored under this directory | `~/cow` |
-| `agent_max_context_tokens` | Max context tokens; when exceeded, half is trimmed and summarized into memory | `40000` |
-| `agent_max_context_turns` | Max context turns; when exceeded, half is trimmed and summarized into memory | `20` |
+| `agent_max_context_tokens` | Max context tokens; when exceeded, content is trimmed and summarized into memory | `50000` |
+| `agent_max_context_turns` | Max context turns; when exceeded, content is trimmed and summarized into memory | `20` |
--- a/docs/en/models/coding-plan.mdx
+++ b/docs/en/models/coding-plan.mdx
@@ -0,0 +1,139 @@
+---
+title: Coding Plan
+description: Coding Plan model configuration
+---
+
+> Coding Plan is a monthly subscription package offered by various providers, ideal for high-frequency Agent usage. CowAgent supports all Coding Plan providers via OpenAI-compatible mode.
+
+<Note>
+  Coding Plan API Base and API Key are usually separate from the standard pay-as-you-go ones. Please obtain them from each provider's platform.
+</Note>
+
+## General Configuration
+
+All providers can be accessed via the OpenAI-compatible protocol, and can be quickly configured through the web console. Set the model provider to **OpenAI**, select a custom model and enter the model code, then fill in the corresponding provider's API Base and API Key:
+
+<img src="https://cdn.link-ai.tech/doc/20260318113134.png" width="800"/>
+
+You can also configure directly in `config.json`:
+
+```json
+{
+  "bot_type": "openai",
+  "model": "MODEL_NAME",
+  "open_ai_api_base": "PROVIDER_CODING_PLAN_API_BASE",
+  "open_ai_api_key": "YOUR_API_KEY"
+}
+```
+
+| Parameter | Description |
+| --- | --- |
+| `bot_type` | Must be `openai` (OpenAI-compatible mode) |
+| `model` | Model name supported by the provider |
+| `open_ai_api_base` | Provider's Coding Plan API Base URL |
+| `open_ai_api_key` | Provider's Coding Plan API Key |
+
+---
+
+## Alibaba Cloud
+
+```json
+{
+  "bot_type": "openai",
+  "model": "qwen3.5-plus",
+  "open_ai_api_base": "https://coding.dashscope.aliyuncs.com/v1",
+  "open_ai_api_key": "YOUR_API_KEY"
+}
+```
+
+| Parameter | Description |
+| --- | --- |
+| `model` | `qwen3.5-plus`, `qwen3-max-2026-01-23`, `qwen3-coder-next`, `qwen3-coder-plus`, `glm-5`, `glm-4.7`, `kimi-k2.5`, `MiniMax-M2.5` |
+| `open_ai_api_base` | `https://coding.dashscope.aliyuncs.com/v1` |
+| `open_ai_api_key` | Coding Plan specific key (not shared with pay-as-you-go) |
+
+Reference: [Quick Start](https://help.aliyun.com/zh/model-studio/coding-plan-quickstart?spm=a2c4g.11186623.help-menu-2400256.d_0_2_1.70115203zi5Igc), [Model List](https://help.aliyun.com/zh/model-studio/coding-plan)
+
+---
+
+## MiniMax
+
+```json
+{
+  "bot_type": "openai",
+  "model": "MiniMax-M2.5",
+  "open_ai_api_base": "https://api.minimaxi.com/v1",
+  "open_ai_api_key": "YOUR_API_KEY"
+}
+```
+
+| Parameter | Description |
+| --- | --- |
+| `model` | `MiniMax-M2.5`, `MiniMax-M2.5-highspeed`, `MiniMax-M2.1`, `MiniMax-M2` |
+| `open_ai_api_base` | China: `https://api.minimaxi.com/v1`; Global: `https://api.minimax.io/v1` |
+| `open_ai_api_key` | Coding Plan specific key (not shared with pay-as-you-go) |
+
+Reference: [China Key](https://platform.minimaxi.com/docs/coding-plan/quickstart), [Model List](https://platform.minimaxi.com/docs/guides/pricing-coding-plan), [Global Key](https://platform.minimax.io/docs/coding-plan/quickstart)
+
+---
+
+## Zhipu GLM
+
+```json
+{
+  "bot_type": "openai",
+  "model": "glm-4.7",
+  "open_ai_api_base": "https://open.bigmodel.cn/api/coding/paas/v4",
+  "open_ai_api_key": "YOUR_API_KEY"
+}
+```
+
+| Parameter | Description |
+| --- | --- |
+| `model` | `glm-5`, `glm-4.7`, `glm-4.6`, `glm-4.5`, `glm-4.5-air` |
+| `open_ai_api_base` | China: `https://open.bigmodel.cn/api/coding/paas/v4`; Global: `https://api.z.ai/api/coding/paas/v4` |
+| `open_ai_api_key` | Shared with standard API |
+
+Reference: [China Quick Start](https://docs.bigmodel.cn/cn/coding-plan/quick-start), [Global Quick Start](https://docs.z.ai/devpack/quick-start)
+
+---
+
+## Kimi
+
+```json
+{
+  "bot_type": "openai",
+  "model": "kimi-for-coding",
+  "open_ai_api_base": "https://api.kimi.com/coding/v1",
+  "open_ai_api_key": "YOUR_API_KEY"
+}
+```
+
+| Parameter | Description |
+| --- | --- |
+| `model` | `kimi-for-coding` |
+| `open_ai_api_base` | `https://api.kimi.com/coding/v1` |
+| `open_ai_api_key` | Coding Plan specific key (not shared with pay-as-you-go) |
+
+Reference: [Key & Docs](https://www.kimi.com/code/docs/)
+
+---
+
+## Volcengine
+
+```json
+{
+  "bot_type": "openai",
+  "model": "Doubao-Seed-2.0-Code",
+  "open_ai_api_base": "https://ark.cn-beijing.volces.com/api/coding/v3",
+  "open_ai_api_key": "YOUR_API_KEY"
+}
+```
+
+| Parameter | Description |
+| --- | --- |
+| `model` | `Doubao-Seed-2.0-Code`, `Doubao-Seed-2.0-pro`, `Doubao-Seed-2.0-lite`, `Doubao-Seed-Code`, `MiniMax-M2.5`, `Kimi-K2.5`, `GLM-4.7`, `DeepSeek-V3.2` |
+| `open_ai_api_base` | `https://ark.cn-beijing.volces.com/api/coding/v3` |
+| `open_ai_api_key` | Shared with standard API |
+
+Reference: [Quick Start](https://www.volcengine.com/docs/82379/1928261?lang=zh)
--- a/docs/en/models/deepseek.mdx
+++ b/docs/en/models/deepseek.mdx
@@ -3,20 +3,30 @@ title: DeepSeek
 description: DeepSeek model configuration
 ---

-Use OpenAI-compatible configuration:
+Option 1: Native integration (recommended):

 ```json
 {
  "model": "deepseek-chat",
-  "bot_type": "chatGPT",
-  "open_ai_api_key": "YOUR_API_KEY",
-  "open_ai_api_base": "https://api.deepseek.com/v1"
+  "deepseek_api_key": "YOUR_API_KEY"
 }
 ```

 | Parameter | Description |
 | --- | --- |
-| `model` | `deepseek-chat` (DeepSeek-V3), `deepseek-reasoner` (DeepSeek-R1) |
-| `bot_type` | Must be `chatGPT` (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 |
+| `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
+{
+  "model": "deepseek-chat",
+  "bot_type": "openai",
+  "open_ai_api_key": "YOUR_API_KEY",
+  "open_ai_api_base": "https://api.deepseek.com/v1"
+}
+```
+
+
--- a/Show More
+++ b/Show More