Merge branch 'master' into feat-knowledge

feat(vision): prioritize main model for image recognition

.gitignore

@@ -36,6 +36,7 @@ plugins/banwords/lib/__pycache__
 !plugins/cow_cli
 client_config.json
 ref/
+**/.dev.vars
 .cursor/
 local/
 node_modules/

README.md

@@ -7,12 +7,13 @@
   [中文] | [<a href="docs/en/README.md">English</a>] | [<a href="docs/ja/README.md">日本語</a>]
 </p>
 
-**CowAgent** 是基于大模型的超级 AI 助理，能够主动思考和任务规划、操作计算机和外部资源、创造和执行 Skills、拥有长期记忆并不断成长，比 OpenClaw 更轻量和便捷。CowAgent 支持灵活切换多种模型，能处理文本、语音、图片、文件等多模态消息，可接入微信、飞书、钉钉、企微智能机器人、QQ、企微自建应用、微信公众号、网页中使用，7*24小时运行于你的个人电脑或服务器中。
+**CowAgent** 是基于大模型的超级 AI 助理，能够主动思考和任务规划、操作计算机和外部资源、创造和执行 Skills、拥有长期记忆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> &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>
 
@@ -21,12 +22,15 @@
 
 > 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，可集成到微信、飞书、钉钉、企业微信、QQ、微信公众号、网页中使用
+-  ✅  **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
 
@@ -66,6 +70,8 @@
 
 # 🏷 更新日志
 
+>**2026.04.01：** [2.0.5版本](https://github.com/zhayujie/chatgpt-on-wechat/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。
+
 >**2026.03.22：** [2.0.4版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.4)，新增个人微信通道（微信扫码即用）、新增 MiniMax-M2.7 和 GLM-5-Turbo 模型、run.sh 脚本重构、日文文档及多项修复。
 
 >**2026.03.18：** [2.0.3版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.3)，新增企微智能机器人和 QQ 通道、支持 Coding Plan、新增多个模型、Web 端文件处理、记忆系统升级。
@@ -86,11 +92,17 @@
 
 在终端执行以下命令：
 
+**Linux / macOS：**
 ```bash
 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
@@ -105,7 +117,7 @@ bash <(curl -fsSL https://cdn.link-ai.tech/code/cow/run.sh)
 
 ### 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。
 
@@ -134,6 +146,24 @@ pip3 install -r requirements-optional.txt
 
 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：
@@ -184,12 +214,13 @@ pip3 install -r requirements-optional.txt
 + 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-M2.7`、`glm-5-turbo`、`kimi-k2.5`、`qwen3.5-plus`、`claude-sonnet-4-6`、`gemini-3.1-pro-preview`，全部模型名称参考[common/const.py](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/common/const.py)文件
++ `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/chatgpt-on-wechat/blob/master/common/const.py)文件
 + `character_desc`：普通对话模式下的机器人系统提示词。在 Agent 模式下该配置不生效，由工作空间中的文件内容构成。
 + `subscribe_msg`：订阅消息，公众号和企业微信 channel 中请填写，当被订阅时会自动回复， 可使用特殊占位符。目前支持的占位符有{trigger_prefix}，在程序中它会自动替换成 bot 的触发词。
 </details>
@@ -210,7 +241,8 @@ 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。
@@ -220,15 +252,24 @@ python3 app.py         # windows 环境下该命令通常为 python app.py
 
 ### 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，项目根目录下的 `run.sh` 脚本支持一键启动和管理服务，包括 `./run.sh start`、`./run.sh stop`、`./run.sh restart`、`./run.sh logs` 等命令，执行 `./run.sh help` 可查看全部用法。
+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。
 
@@ -264,7 +305,7 @@ sudo docker logs -f chatgpt-on-wechat
 
 ## 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>
@@ -318,7 +359,7 @@ sudo docker logs -f chatgpt-on-wechat
     "minimax_api_key": ""
 }
 ```
- - `model`: 可填写 `MiniMax-M2.7、MiniMax-M2.5、MiniMax-M2.1、MiniMax-M2.1-lightning、MiniMax-M2、abab6.5-chat` 等
+ - `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：
@@ -331,7 +372,7 @@ sudo docker logs -f chatgpt-on-wechat
 }
 ```
 - `bot_type`: OpenAI 兼容方式
-- `model`: 可填 `MiniMax-M2.7、MiniMax-M2.5、MiniMax-M2.1、MiniMax-M2.1-lightning、MiniMax-M2`，参考[API文档](https://platform.minimaxi.com/document/%E5%AF%B9%E8%AF%9D?key=66701d281d57f38758d581d0#QklxsNSbaf6kM4j6wjO5eEek)
+- `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>
@@ -372,18 +413,18 @@ sudo docker logs -f chatgpt-on-wechat
 
 ```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：
 ```json
 {
   "bot_type": "openai",
-  "model": "qwen3.5-plus",
+  "model": "qwen3.6-plus",
   "open_ai_api_base": "https://dashscope.aliyuncs.com/compatible-mode/v1",
   "open_ai_api_key": "sk-qVxxxxG"
 }
@@ -635,7 +676,7 @@ Coding Plan 是各厂商推出的编程包月套餐，所有厂商均可通过 O
 
 ## 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"`。
 
@@ -830,8 +871,10 @@ 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
 
+- [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。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。
+- [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。
+
 
 
 
@@ -843,7 +886,7 @@ FAQs： <https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs>
 
 # 🛠️ 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/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，向 [Skill Hub](https://skills.cowagent.ai/submit) 提交技能。
 
 # ✉ 联系
 

agent/chat/service.py

@@ -57,7 +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:
@@ -75,6 +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", "")

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}

agent/memory/conversation_store.py

@@ -188,8 +188,9 @@ 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 +199,46 @@ 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
 
@@ -312,6 +335,9 @@ 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
 

agent/memory/manager.py

@@ -285,6 +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
@@ -312,6 +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
     

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:

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:

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
@@ -206,9 +213,9 @@ def _build_tooling_section(tools: List[Any], language: str) -> List[str]:
         "",
         "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",
         "",
     ]
@@ -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",
         "",
-        "### 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
 
 
@@ -374,16 +431,18 @@ 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，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，请严格遵循",
+        "- ✅ `MEMORY.md`: 已加载 - 长期记忆索引",
         "",
         "**💬 交流规范**:",
         "",
-        "- 对话中不要暴露内部技术细节（文件名、工具名等），用自然语言表达。例如说「我已记住」而非「已更新 MEMORY.md」",
-        "- 做真正有帮助的助手，而不是表演式的客套。跳过「好的！」「当然可以！」之类的套话，直接帮忙解决问题",
+        "- 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",
         "",
@@ -476,7 +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']}")

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
@@ -231,9 +281,9 @@ _你不是一个聊天机器人，你正在成为某个人。_
 
 ## 🎯 核心原则
 
-**做真正有帮助的助手，而不是表演式的客套。** 跳过「好的！」「当然可以！」之类的套话——直接帮忙。行动胜过废话。
+**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。
 
-**有自己的观点。** 你可以不同意、有偏好、觉得有趣或无聊。一个没有个性的助手只是多了几步操作的搜索引擎。
+**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。
 
@@ -287,39 +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
 
@@ -381,4 +480,12 @@ _你刚刚启动，这是你的第一次对话。_ ✨
 """
 
 
+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 ""
 

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":
@@ -527,6 +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
@@ -584,10 +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 ""
@@ -788,7 +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",

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') and entry.upper() != 'README.MD'
-            is_skill_md = not include_root_files and entry == 'SKILL.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)

agent/skills/manager.py

@@ -102,13 +102,17 @@ class SkillManager:
             else:
                 enabled = entry.metadata.default_enabled if entry.metadata else True
 
-            merged[name] = {
+            entry_dict = {
                 "name": name,
                 "description": skill.description,
                 "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()
@@ -206,6 +210,10 @@ class SkillManager:
         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(

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',
 ]
 
 """

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}")

agent/tools/browser/__init__.py

@@ -0,0 +1,3 @@
+from agent.tools.browser.browser_tool import BrowserTool
+
+__all__ = ["BrowserTool"]

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

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")

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 

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}")

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):
         """

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:

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":

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 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, extra_headers = 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:
@@ -97,36 +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, extra_headers)
-        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, dict]:
-        """Resolve API key, base URL and extra headers. 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)")
-            from common.utils import get_cloud_headers
-            extra = get_cloud_headers(api_key)
-            extra.pop("Authorization", None)
-            extra.pop("Content-Type", None)
-            return api_key, self._ensure_v1(api_base), extra
+        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:
@@ -139,9 +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}")
@@ -165,6 +383,19 @@ 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 to under COMPRESS_THRESHOLD with max long-edge 1536px."""
@@ -220,8 +451,13 @@ class Vision(BaseTool):
         os.remove(tmp.name)
         return path
 
-    def _call_api(self, api_key: str, api_base: str, model: str,
-                  question: str, image_content: dict, extra_headers: dict = None) -> ToolResult:
+    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": [
@@ -233,34 +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",
-            **(extra_headers or {}),
+            **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", [])
@@ -270,6 +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),

bridge/agent_bridge.py

@@ -67,7 +67,7 @@ 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 = [
@@ -115,6 +115,8 @@ 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 conf().get("bot_type") == "modelscope":
+            return const.MODELSCOPE
         for prefix, btype in self._MODEL_PREFIX_MAP:
             if model_name.startswith(prefix):
                 return btype
@@ -122,14 +124,15 @@ class AgentLLMModel(LLMModel):
 
     @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):
@@ -271,10 +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}")
@@ -493,22 +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",
@@ -517,10 +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:
@@ -528,48 +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 = ""

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"""

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."""

bridge/bridge.py

@@ -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"):

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)

channel/web/chat.html

@@ -110,6 +110,11 @@
                             <i class="fas fa-brain item-icon text-xs w-5 text-center"></i>
                             <span data-i18n="menu_memory">Memory</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">Knowledge</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>
@@ -455,6 +460,11 @@
                                     <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>
                                 </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">Skill Hub</span>
+                                </a>
                             </div>
 
                             <!-- Built-in Tools Section -->
@@ -553,6 +563,106 @@
                     </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">Knowledge</h2>
+                                    <p class="text-sm text-slate-500 dark:text-slate-400 mt-1" data-i18n="knowledge_desc">Browse and explore your knowledge base</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">Documents</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">Graph</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">Loading knowledge base...</p>
+                                <p class="text-sm text-slate-400 dark:text-slate-500 mt-1" data-i18n="knowledge_loading_desc">Knowledge pages will be displayed here</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">Send documents, links or topics to the agent in chat, and it will automatically organize them into your knowledge base.</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">Start a conversation</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">Select a document to view</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                                          -->
                 <!-- ====================================================== -->
@@ -665,6 +775,7 @@
         </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>

channel/web/static/css/console.css

@@ -45,7 +45,8 @@
 .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;
@@ -146,7 +147,7 @@
     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 {
@@ -158,6 +159,20 @@
 .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;
@@ -535,3 +550,142 @@
 .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;
+}

channel/web/web_channel.py

@@ -96,9 +96,43 @@ class WebChannel(ChatChannel):
                 logger.error(f"No session_id found for request {request_id}")
                 return
 
-            # SSE mode: push done event to SSE queue
+            # SSE mode: push events to SSE queue
             if request_id in self.sse_queues:
                 content = reply.content if reply.content is not None else ""
+
+                # Intermediate status lines (e.g. /install-browser phases) must NOT use "done",
+                # or the frontend closes EventSource and drops subsequent events.
+                if getattr(reply, "sse_phase", False):
+                    self.sse_queues[request_id].put({
+                        "type": "phase",
+                        "content": content,
+                        "request_id": request_id,
+                        "timestamp": time.time(),
+                    })
+                    logger.debug(f"SSE phase for request {request_id}")
+                    return
+
+                # Files are already pushed via on_event (file_to_send) during agent execution.
+                # Skip duplicate file pushes here; just let the done event through.
+                if reply.type in (ReplyType.IMAGE_URL, ReplyType.FILE) and content.startswith("file://"):
+                    text_content = getattr(reply, 'text_content', '')
+                    if text_content:
+                        self.sse_queues[request_id].put({
+                            "type": "done",
+                            "content": text_content,
+                            "request_id": request_id,
+                            "timestamp": time.time()
+                        })
+                    logger.debug(f"SSE skipped duplicate file for request {request_id}")
+                    return
+
+                # Skip http-URL FILE/IMAGE_URL replies produced by chat_channel's media extraction:
+                # the text reply (already sent as "done") contains the URL and the frontend will
+                # render it via renderMarkdown/injectVideoPlayers, so no separate SSE event needed.
+                if reply.type in (ReplyType.FILE, ReplyType.IMAGE_URL) and content.startswith(("http://", "https://")):
+                    logger.debug(f"SSE skipped http media reply for request {request_id}")
+                    return
+
                 self.sse_queues[request_id].put({
                     "type": "done",
                     "content": content,
@@ -134,7 +168,12 @@ class WebChannel(ChatChannel):
             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:
+                    q.put({"type": "reasoning", "content": delta})
+
+            elif event_type == "message_update":
                 delta = data.get("delta", "")
                 if delta:
                     q.put({"type": "delta", "content": delta})
@@ -161,6 +200,24 @@ class WebChannel(ChatChannel):
                     "execution_time": round(exec_time, 2)
                 })
 
+            elif event_type == "message_end":
+                tool_calls = data.get("tool_calls", [])
+                if tool_calls:
+                    q.put({"type": "message_end", "has_tool_calls": True})
+
+            elif event_type == "file_to_send":
+                file_path = data.get("path", "")
+                file_name = data.get("file_name", os.path.basename(file_path))
+                file_type = data.get("file_type", "file")
+                from urllib.parse import quote
+                web_url = f"/api/file?path={quote(file_path)}"
+                is_image = file_type == "image"
+                q.put({
+                    "type": "image" if is_image else "file",
+                    "content": web_url,
+                    "file_name": file_name,
+                })
+
         return on_event
 
     def upload_file(self):
@@ -282,14 +339,18 @@ class WebChannel(ChatChannel):
         """
         SSE generator for a given request_id.
         Yields UTF-8 encoded bytes to avoid WSGI Latin-1 mangling.
+        Supports client reconnection: the queue is only removed after a
+        "done" event is consumed, so a new GET /stream with the same
+        request_id can resume reading remaining events.
         """
         if request_id not in self.sse_queues:
             yield b"data: {\"type\": \"error\", \"message\": \"invalid request_id\"}\n\n"
             return
 
         q = self.sse_queues[request_id]
-        timeout = 300  # 5 minutes max
-        deadline = time.time() + timeout
+        idle_timeout = 600  # 10 minutes without any real event
+        deadline = time.time() + idle_timeout
+        done = False
 
         try:
             while time.time() < deadline:
@@ -299,13 +360,18 @@ class WebChannel(ChatChannel):
                     yield b": keepalive\n\n"
                     continue
 
+                # Real event received, reset idle deadline
+                deadline = time.time() + idle_timeout
+
                 payload = json.dumps(item, ensure_ascii=False)
                 yield f"data: {payload}\n\n".encode("utf-8")
 
                 if item.get("type") == "done":
+                    done = True
                     break
         finally:
-            self.sse_queues.pop(request_id, None)
+            if done:
+                self.sse_queues.pop(request_id, None)
 
     def poll_response(self):
         """
@@ -377,6 +443,7 @@ class WebChannel(ChatChannel):
             '/message', 'MessageHandler',
             '/upload', 'UploadHandler',
             '/uploads/(.*)', 'UploadsHandler',
+            '/api/file', 'FileServeHandler',
             '/poll', 'PollHandler',
             '/stream', 'StreamHandler',
             '/chat', 'ChatHandler',
@@ -387,6 +454,9 @@ class WebChannel(ChatChannel):
             '/api/skills', 'SkillsHandler',
             '/api/memory', 'MemoryHandler',
             '/api/memory/content', 'MemoryContentHandler',
+            '/api/knowledge/list', 'KnowledgeListHandler',
+            '/api/knowledge/read', 'KnowledgeReadHandler',
+            '/api/knowledge/graph', 'KnowledgeGraphHandler',
             '/api/scheduler', 'SchedulerHandler',
             '/api/history', 'HistoryHandler',
             '/api/logs', 'LogsHandler',
@@ -406,8 +476,14 @@ class WebChannel(ChatChannel):
         func = web.httpserver.StaticMiddleware(app.wsgifunc())
         func = web.httpserver.LogMiddleware(func)
         server = web.httpserver.WSGIServer(("0.0.0.0", port), func)
-        # Allow concurrent requests by not blocking on in-flight handler threads
         server.daemon_threads = True
+        # Default request_queue_size(5) / timeout(10s) / numthreads(10) are
+        # too small: when SSE streams occupy many threads, the backlog fills
+        # and new connections get refused (ERR_CONNECTION_ABORTED).
+        server.request_queue_size = 128
+        server.timeout = 300
+        server.requests.min = 20
+        server.requests.max = 80
         self._http_server = server
         try:
             server.start()
@@ -463,6 +539,32 @@ class UploadsHandler:
             raise web.notfound()
 
 
+class FileServeHandler:
+    def GET(self):
+        """Serve a local file by absolute path (for agent send tool)."""
+        try:
+            params = web.input(path="")
+            file_path = params.path
+            if not file_path or not os.path.isabs(file_path):
+                raise web.notfound()
+            file_path = os.path.normpath(file_path)
+            if not os.path.isfile(file_path):
+                raise web.notfound()
+            content_type = mimetypes.guess_type(file_path)[0] or "application/octet-stream"
+            file_name = os.path.basename(file_path)
+            from urllib.parse import quote
+            web.header('Content-Type', content_type)
+            web.header('Content-Disposition', f"inline; filename*=UTF-8''{quote(file_name)}")
+            web.header('Cache-Control', 'public, max-age=3600')
+            with open(file_path, 'rb') as f:
+                return f.read()
+        except web.HTTPError:
+            raise
+        except Exception as e:
+            logger.error(f"[WebChannel] Error serving file: {e}")
+            raise web.notfound()
+
+
 class PollHandler:
     def POST(self):
         return WebChannel().poll_response()
@@ -496,7 +598,7 @@ class ConfigHandler:
     _RECOMMENDED_MODELS = [
         const.MINIMAX_M2_7, const.MINIMAX_M2_5, const.MINIMAX_M2_1, const.MINIMAX_M2_1_LIGHTNING,
         const.GLM_5_TURBO, const.GLM_5, const.GLM_4_7,
-        const.QWEN3_MAX, const.QWEN35_PLUS,
+        const.QWEN36_PLUS, const.QWEN35_PLUS, const.QWEN3_MAX,
         const.KIMI_K2_5, const.KIMI_K2,
         const.DOUBAO_SEED_2_PRO, const.DOUBAO_SEED_2_CODE,
         const.CLAUDE_4_6_SONNET, const.CLAUDE_4_6_OPUS, const.CLAUDE_4_5_SONNET,
@@ -525,7 +627,7 @@ class ConfigHandler:
             "api_key_field": "dashscope_api_key",
             "api_base_key": None,
             "api_base_default": None,
-            "models": [const.QWEN3_MAX, const.QWEN35_PLUS],
+            "models": [const.QWEN36_PLUS, const.QWEN35_PLUS, const.QWEN3_MAX],
         }),
         ("moonshot", {
             "label": "Kimi",
@@ -569,6 +671,13 @@ class ConfigHandler:
             "api_base_default": "https://api.deepseek.com/v1",
             "models": [const.DEEPSEEK_CHAT, const.DEEPSEEK_REASONER],
         }),
+        ("modelscope", {
+            "label": "ModelScope",
+            "api_key_field": "modelscope_api_key",
+            "api_base_key": None,
+            "api_base_default": None,
+            "models": [const.QWEN3_5_27B, const.QWEN3_235B_A22B_INSTRUCT_2507],
+        }),
         ("linkai", {
             "label": "LinkAI",
             "api_key_field": "linkai_api_key",
@@ -1291,6 +1400,8 @@ class MemoryContentHandler:
             service = MemoryService(workspace_root)
             result = service.get_content(params.filename)
             return json.dumps({"status": "success", **result}, ensure_ascii=False)
+        except ValueError:
+            return json.dumps({"status": "error", "message": "invalid filename"})
         except FileNotFoundError:
             return json.dumps({"status": "error", "message": "file not found"})
         except Exception as e:
@@ -1432,6 +1543,47 @@ class AssetsHandler:
             raise web.notfound()
 
 
+class KnowledgeListHandler:
+    def GET(self):
+        web.header('Content-Type', 'application/json; charset=utf-8')
+        try:
+            from agent.knowledge.service import KnowledgeService
+            svc = KnowledgeService(_get_workspace_root())
+            result = svc.list_tree()
+            return json.dumps({"status": "success", **result}, ensure_ascii=False)
+        except Exception as e:
+            logger.error(f"[WebChannel] Knowledge list error: {e}")
+            return json.dumps({"status": "error", "message": str(e)})
+
+
+class KnowledgeReadHandler:
+    def GET(self):
+        web.header('Content-Type', 'application/json; charset=utf-8')
+        try:
+            from agent.knowledge.service import KnowledgeService
+            params = web.input(path='')
+            svc = KnowledgeService(_get_workspace_root())
+            result = svc.read_file(params.path)
+            return json.dumps({"status": "success", **result}, ensure_ascii=False)
+        except (ValueError, FileNotFoundError) as e:
+            return json.dumps({"status": "error", "message": str(e)})
+        except Exception as e:
+            logger.error(f"[WebChannel] Knowledge read error: {e}")
+            return json.dumps({"status": "error", "message": str(e)})
+
+
+class KnowledgeGraphHandler:
+    def GET(self):
+        web.header('Content-Type', 'application/json; charset=utf-8')
+        try:
+            from agent.knowledge.service import KnowledgeService
+            svc = KnowledgeService(_get_workspace_root())
+            return json.dumps(svc.build_graph(), ensure_ascii=False)
+        except Exception as e:
+            logger.error(f"[WebChannel] Knowledge graph error: {e}")
+            return json.dumps({"nodes": [], "links": []})
+
+
 class VersionHandler:
     def GET(self):
         web.header('Content-Type', 'application/json; charset=utf-8')

channel/wecom_bot/wecom_bot_channel.py

@@ -330,28 +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")
@@ -378,6 +392,7 @@ class WecomBotChannel(ChatChannel):
                 else:
                     state["committed"] += state["current"]
                     state["current"] = ""
+                _push_stream(state, force=True)
 
         return on_event
 
@@ -452,11 +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},

channel/weixin/weixin_api.py

@@ -37,11 +37,19 @@ def _random_wechat_uin() -> str:
     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}"
@@ -64,6 +72,7 @@ class WeixinApi:
     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()
@@ -210,7 +219,10 @@ class WeixinApi:
     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-ClientVersion": "1"}
+        headers = {
+            "iLink-App-Id": "bot",
+            "iLink-App-ClientVersion": CLIENT_VERSION,
+        }
         try:
             resp = requests.get(url, headers=headers, timeout=timeout)
             resp.raise_for_status()
@@ -303,13 +315,18 @@ def upload_media_to_cdn(api: WeixinApi, file_path: str, to_user_id: str,
                 filesize=cipher_size,
                 aeskey=aes_key_hex,
             )
-            upload_param = resp.get("upload_param", "")
-            if not upload_param:
-                raise RuntimeError(f"[Weixin] getUploadUrl returned no upload_param: {resp}")
 
-            cdn_url = (f"{api.cdn_base_url}/upload"
-                       f"?encrypted_query_param={quote(upload_param)}"
-                       f"&filekey={quote(filekey)}")
+            # 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",

channel/weixin/weixin_channel.py

@@ -166,10 +166,18 @@ class WeixinChannel(ChatChannel):
         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)
-            qr.print_ascii(invert=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")

cli/VERSION

@@ -1 +1 @@
-2.0.4
+2.0.6

cli/cli.py

@@ -5,6 +5,8 @@ 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]...
@@ -21,6 +23,8 @@ Commands:
   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."""
 
@@ -67,6 +71,8 @@ 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__':

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)

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"

cli/commands/process.py

@@ -178,7 +178,10 @@ def update(ctx):
     """Update CowAgent and restart."""
     root = get_project_root()
 
-    # 1. Git pull while service is still running
+    # 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)
@@ -188,28 +191,61 @@ def update(ctx):
     else:
         click.echo("Not a git repository, skipping code update.")
 
-    # 2. Stop service
-    ctx.invoke(stop)
-
-    # 3. Install dependencies
     python = sys.executable
     req_file = os.path.join(root, "requirements.txt")
-    if os.path.exists(req_file):
-        click.echo("Installing dependencies...")
-        subprocess.call(
-            [python, "-m", "pip", "install", "-r", "requirements.txt", "-q"],
+
+    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,
         )
-    click.echo("Reinstalling cow CLI...")
-    subprocess.call(
-        [python, "-m", "pip", "install", "-e", ".", "-q"],
-        cwd=root,
-    )
 
-    # 4. Start service
-    click.echo("")
-    time.sleep(1)
-    ctx.invoke(start, no_logs=True)
+        # 4. Start service
+        click.echo("")
+        time.sleep(1)
+        ctx.invoke(start, no_logs=False)
 
 
 @click.command()

common/cloud_client.py

@@ -47,13 +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
@@ -88,6 +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)."""
@@ -468,6 +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
     # ------------------------------------------------------------------
@@ -487,6 +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")
@@ -629,9 +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:
@@ -648,6 +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.
 
@@ -668,8 +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**",
         "",
@@ -684,7 +770,7 @@ def start(channel, channel_mgr=None):
         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()

common/const.py

@@ -7,8 +7,8 @@ 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"
@@ -81,18 +81,19 @@ 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_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
@@ -124,6 +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"
@@ -135,11 +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
@@ -165,10 +173,10 @@ MODEL_LIST = [
               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_7, 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_TURBO, GLM_5, GLM_4, GLM_4_PLUS, GLM_4_flash, GLM_4_LONG, GLM_4_ALLTOOLS,

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",

config-template.json

@@ -29,5 +29,6 @@
   "agent": true,
   "agent_max_context_tokens": 40000,
   "agent_max_context_turns": 20,
-  "agent_max_steps": 15
+  "agent_max_steps": 15,
+  "knowledge": true
 }

config.py

@@ -180,15 +180,16 @@ 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": "",
@@ -199,6 +200,7 @@ available_setting = {
     "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
+    "knowledge": True,  # 是否开启知识库功能
 }
 
 
@@ -408,7 +410,7 @@ 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()
 
 

docker/Dockerfile.latest

@@ -4,29 +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 ${BUILD_PREFIX} \
     && cp config-template.json config.json \
     && /usr/local/bin/python -m pip install --no-cache --upgrade pip \
     && pip install --no-cache -r requirements.txt \
-    && pip install --no-cache -r requirements-optional.txt
+    && pip install --no-cache -r requirements-optional.txt \
+    && pip install --no-cache -e . \
+    && if [ "$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/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
+    && chown agent:agent /entrypoint.sh
 
 ENTRYPOINT ["/entrypoint.sh"]

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 -fsSL 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-M2.7`
-- **GLM**: `glm-5-turbo`
-- **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)

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。
 

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
+```

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>

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>

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 |

docs/docs.json

@@ -106,14 +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"
                 ]
               }
             ]
@@ -125,15 +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"
                 ]
               }
             ]
@@ -144,7 +141,19 @@
               {
                 "group": "记忆系统",
                 "pages": [
-                  "memory"
+                  "memory/index",
+                  "memory/context"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "知识",
+            "groups": [
+              {
+                "group": "知识库",
+                "pages": [
+                  "knowledge/index"
                 ]
               }
             ]
@@ -167,6 +176,20 @@
               }
             ]
           },
+          {
+            "tab": "命令",
+            "groups": [
+              {
+                "group": "命令系统",
+                "pages": [
+                  "cli/index",
+                  "cli/process",
+                  "cli/skill",
+                  "cli/general"
+                ]
+              }
+            ]
+          },
           {
             "tab": "版本",
             "groups": [
@@ -174,6 +197,7 @@
                 "group": "发布记录",
                 "pages": [
                   "releases/overview",
+                  "releases/v2.0.5",
                   "releases/v2.0.4",
                   "releases/v2.0.3",
                   "releases/v2.0.2",
@@ -254,14 +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"
                 ]
               }
             ]
@@ -273,15 +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"
                 ]
               }
             ]
@@ -292,7 +313,19 @@
               {
                 "group": "Memory System",
                 "pages": [
-                  "en/memory"
+                  "en/memory/index",
+                  "en/memory/context"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "Knowledge",
+            "groups": [
+              {
+                "group": "Knowledge Base",
+                "pages": [
+                  "en/knowledge/index"
                 ]
               }
             ]
@@ -315,6 +348,20 @@
               }
             ]
           },
+          {
+            "tab": "CLI",
+            "groups": [
+              {
+                "group": "Command System",
+                "pages": [
+                  "en/cli/index",
+                  "en/cli/process",
+                  "en/cli/skill",
+                  "en/cli/chat"
+                ]
+              }
+            ]
+          },
           {
             "tab": "Releases",
             "groups": [
@@ -322,6 +369,7 @@
                 "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",
@@ -403,14 +451,16 @@
                   "ja/tools/send",
                   "ja/tools/memory",
                   "ja/tools/env-config",
-                  "ja/tools/browser"
+                  "ja/tools/web-fetch",
+                  "ja/tools/scheduler"
                 ]
               },
               {
                 "group": "オプションツール",
                 "pages": [
                   "ja/tools/web-search",
-                  "ja/tools/scheduler"
+                  "ja/tools/vision",
+                  "ja/tools/browser"
                 ]
               }
             ]
@@ -422,15 +472,9 @@
                 "group": "スキルシステム",
                 "pages": [
                   "ja/skills/index",
-                  "ja/skills/skill-creator"
-                ]
-              },
-              {
-                "group": "内蔵スキル",
-                "pages": [
-                  "ja/skills/image-vision",
-                  "ja/skills/linkai-agent",
-                  "ja/skills/web-fetch"
+                  "ja/skills/install",
+                  "ja/skills/create",
+                  "ja/skills/hub"
                 ]
               }
             ]
@@ -441,7 +485,19 @@
               {
                 "group": "メモリシステム",
                 "pages": [
-                  "ja/memory"
+                  "ja/memory/index",
+                  "ja/memory/context"
+                ]
+              }
+            ]
+          },
+          {
+            "tab": "ナレッジ",
+            "groups": [
+              {
+                "group": "ナレッジベース",
+                "pages": [
+                  "ja/knowledge/index"
                 ]
               }
             ]
@@ -464,6 +520,20 @@
               }
             ]
           },
+          {
+            "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": [
@@ -471,6 +541,7 @@
                 "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",

docs/en/README.md

@@ -13,6 +13,7 @@
   <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> &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>
 
@@ -20,13 +21,14 @@
 
 > 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.
+- ✅ **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 WeChat, Web, Feishu, DingTalk, WeChat Official Account, and WeCom applications.
-- ✅ **Knowledge Base**: Integrates enterprise knowledge base capabilities via the [LinkAI](https://link-ai.tech) platform.
 
 ## Disclaimer
 
@@ -40,6 +42,8 @@ Try online (no deployment needed): [CowAgent](https://link-ai.tech/cowagent/crea
 
 ## Changelog
 
+> **2026.04.01:** [v2.0.5](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.5) — Cow CLI, Skill Hub open source, Browser tool, WeCom Bot QR scan, and more.
+
 > **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.
 
 > **2026.02.13:** [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.
@@ -60,13 +64,19 @@ 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 -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
 
@@ -84,7 +94,25 @@ 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
@@ -92,13 +120,25 @@ 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
@@ -125,7 +165,7 @@ Supports mainstream model providers. Recommended models for Agent mode:
 | 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` |
@@ -186,6 +226,7 @@ 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.
 
@@ -195,7 +236,7 @@ FAQs: <https://github.com/zhayujie/chatgpt-on-wechat/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/chatgpt-on-wechat/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
 

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
+```

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>

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>

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 |

docs/en/guide/manual-install.mdx

@@ -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.
@@ -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

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 -fsSL 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
+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>

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` |

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.

docs/en/intro/index.mdx

@@ -22,12 +22,21 @@ 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>
@@ -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 -fsSL 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.
 

docs/en/knowledge/index.mdx

@@ -0,0 +1,77 @@
+---
+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.
+
+## 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** — D3.js force-directed graph visualizing relationships between knowledge pages
+- **Chat integration** — Knowledge document links referenced in Agent replies are clickable for direct navigation
+
+## 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` |

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>

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` |

docs/en/models/index.mdx

@@ -6,7 +6,7 @@ description: Supported models and recommended choices for CowAgent
 CowAgent supports mainstream LLMs from domestic and international providers. Model interfaces are implemented in the project's `models/` directory.
 
 <Note>
-  For Agent mode, the following models are recommended based on quality and cost: MiniMax-M2.7, glm-5-turbo, kimi-k2.5, qwen3.5-plus, claude-sonnet-4-6, gemini-3.1-pro-preview
+  For Agent mode, the following models are recommended based on quality and cost: MiniMax-M2.7, glm-5-turbo, kimi-k2.5, qwen3.6-plus, claude-sonnet-4-6, gemini-3.1-pro-preview
 </Note>
 
 ## Configuration
@@ -25,7 +25,7 @@ You can also use the [LinkAI](https://link-ai.tech) platform interface to flexib
     glm-5-turbo, glm-5 and other series models
   </Card>
   <Card title="Qwen (Tongyi Qianwen)" href="/en/models/qwen">
-    qwen3.5-plus, qwen3-max and more
+    qwen3.6-plus, qwen3-max and more
   </Card>
   <Card title="Kimi" href="/en/models/kimi">
     kimi-k2.5, kimi-k2 and more

docs/en/models/qwen.mdx

@@ -5,14 +5,14 @@ description: Tongyi Qianwen model configuration
 
 ```json
 {
-  "model": "qwen3.5-plus",
+  "model": "qwen3.6-plus",
   "dashscope_api_key": "YOUR_API_KEY"
 }
 ```
 
 | Parameter | Description |
 | --- | --- |
-| `model` | Options include `qwen3.5-plus`, `qwen3-max`, `qwen-max`, `qwen-plus`, `qwen-turbo`, `qwq-plus`, etc. |
+| `model` | Options include `qwen3.6-plus`, `qwen3.5-plus`, `qwen3-max`, `qwen-max`, `qwen-plus`, `qwen-turbo`, `qwq-plus`, etc. |
 | `dashscope_api_key` | Create at [Bailian Console](https://bailian.console.aliyun.com/?tab=model#/api-key). See [official docs](https://bailian.console.aliyun.com/?tab=api#/api) |
 
 OpenAI-compatible configuration is also supported:
@@ -20,7 +20,7 @@ OpenAI-compatible configuration is also supported:
 ```json
 {
   "bot_type": "openai",
-  "model": "qwen3.5-plus",
+  "model": "qwen3.6-plus",
   "open_ai_api_base": "https://dashscope.aliyuncs.com/compatible-mode/v1",
   "open_ai_api_key": "YOUR_API_KEY"
 }

docs/en/releases/overview.mdx

@@ -5,6 +5,7 @@ description: CowAgent version history
 
 | Version | Date | Description |
 | --- | --- | --- |
+| [2.0.5](/en/releases/v2.0.5) | 2026.04.01 | Cow CLI, Skill Hub open source, Browser tool, WeCom Bot QR scan, and more |
 | [2.0.4](/en/releases/v2.0.4) | 2026.03.22 | Personal WeChat channel, new model support, Japanese docs, script refactoring and bug fixes |
 | [2.0.2](/en/releases/v2.0.2) | 2026.02.27 | Web Console upgrade, multi-channel concurrency, session persistence |
 | [2.0.1](/en/releases/v2.0.1) | 2026.02.27 | Built-in Web Search tool, smart context management, multiple fixes |

docs/en/releases/v2.0.5.mdx

@@ -0,0 +1,77 @@
+---
+title: v2.0.5
+description: CowAgent 2.0.5 - Cow CLI, Skill Hub open source, Browser tool, WeCom Bot QR scan, and more
+---
+
+## 🖥️ Cow CLI
+
+New CLI command system for managing CowAgent from terminal and chat:
+
+- **Terminal commands**: Run `cow <command>` for `start`, `stop`, `restart`, `update`, `status`, `logs`, etc.
+- **Chat commands**: Type `/<command>` in conversation for `/help`, `/status`, `/config`, `/skill`, `/context`, `/logs`, `/version`, etc.
+- **Web console**: Type `/` in the input box to open a slash command menu, with arrow-key input history
+- **Windows support**: New PowerShell script `scripts/run.ps1` with `cow` command support
+
+Docs: [Command Overview](https://docs.cowagent.ai/en/cli)
+
+<img src="https://cdn.link-ai.tech/doc/20260401114549.png" width="750" />
+
+## 🧩 Cow Skill Hub Open Source
+
+[Cow Skill Hub](https://skills.cowagent.ai) is now open source and live — browse, search, install, and publish AI Agent skills:
+
+- **One-command install**: `/skill install <name>` in chat or `cow skill install <name>` in terminal
+- **Multi-source**: Install from Skill Hub, GitHub, ClawHub, LinkAI, and more
+- **Search**: `/skill search` and `/skill list --remote` to browse the hub
+- **Publish**: Submit your own skills at [skills.cowagent.ai/submit](https://skills.cowagent.ai/submit)
+- **Mirror**: Mirror acceleration for faster downloads in China
+
+Open source repo: [cow-skill-hub](https://github.com/zhayujie/cow-skill-hub)
+
+Docs: [Skill Hub](https://docs.cowagent.ai/en/skills/hub), [Install Skills](https://docs.cowagent.ai/en/skills/install)
+
+<img src="https://cdn.link-ai.tech/doc/20260401110103.png" width="750" />
+
+## 🌐 Browser Tool
+
+New Browser tool — Agent can control a Chromium browser to visit and interact with web pages:
+
+- **Navigation & interaction**: `navigate`, `click`, `fill`, `select`, `scroll`, `press`, etc.
+- **Page snapshot**: Compact DOM snapshot for efficient page understanding, auto-snapshot after navigation
+- **Screenshot**: Save page screenshots to workspace
+- **JavaScript execution**: Run custom scripts on pages
+- **CLI install**: `cow install-browser` for one-command setup
+- **Docker support**: Browser install built into Docker image
+
+Docs: [Browser Tool](https://docs.cowagent.ai/en/tools/browser)
+
+<img src="https://cdn.link-ai.tech/doc/20260401115728.png" width="750" />
+
+## 🤖 WeCom Bot QR Code Setup
+
+WeCom Bot channel now supports QR code scan for one-click bot creation:
+
+- **QR scan in Web console**: Select "Scan QR" mode, scan with WeCom to auto-create and connect a bot — no manual configuration needed
+- **Manual mode**: Still supports manual Bot ID and Secret input
+- **Stream push optimization**: Throttled push to avoid WebSocket congestion
+
+Docs: [WeCom Bot](https://docs.cowagent.ai/en/channels/wecom-bot)
+
+PR: [#2735](https://github.com/zhayujie/chatgpt-on-wechat/pull/2735). Thanks [@WecomTeam](https://github.com/WecomTeam)
+
+## 🐛 Other Improvements & Fixes
+
+- **DeepSeek module**: Independent DeepSeek Bot with dedicated `deepseek_api_key` config ([#2719](https://github.com/zhayujie/chatgpt-on-wechat/pull/2719)). Thanks [@6vision](https://github.com/6vision)
+- **Web console**: Slash command menu, input history, new model options, mobile optimization ([#2731](https://github.com/zhayujie/chatgpt-on-wechat/pull/2731)). Thanks [@zkjqd](https://github.com/zkjqd)
+- **Context loss**: Fix context loss after trimming ([393f0c0](https://github.com/zhayujie/chatgpt-on-wechat/commit/393f0c0))
+- **System prompt**: Fix system prompt not rebuilding on every turn ([13f5fde](https://github.com/zhayujie/chatgpt-on-wechat/commit/13f5fde))
+- **Gemini**: Fix missing model attribute in GoogleGeminiBot ([#2716](https://github.com/zhayujie/chatgpt-on-wechat/pull/2716)). Thanks [@cowagent](https://github.com/cowagent)
+- **WeChat channel**: Fix file send failures and filename loss ([6d9b7ba](https://github.com/zhayujie/chatgpt-on-wechat/commit/6d9b7ba), [45faa9c](https://github.com/zhayujie/chatgpt-on-wechat/commit/45faa9c))
+- **Docker**: Fix volume permissions, reduce image size ([3eb8348](https://github.com/zhayujie/chatgpt-on-wechat/commit/3eb8348), [4470d4c](https://github.com/zhayujie/chatgpt-on-wechat/commit/4470d4c))
+- **Security**: Fix Memory Content path traversal risk. Thanks [@August829](https://github.com/August829)
+
+## 📦 Upgrade
+
+Run `cow update` or `./run.sh update` to upgrade, or pull the latest code and restart. See [Upgrade Guide](https://docs.cowagent.ai/en/guide/upgrade).
+
+**Release Date**: 2026.04.01 | [Full Changelog](https://github.com/zhayujie/chatgpt-on-wechat/compare/2.0.4...master)

docs/en/skills/create.mdx

@@ -0,0 +1,58 @@
+---
+title: Create Skills
+description: Create custom skills through conversation
+---
+
+CowAgent includes a built-in Skill Creator that lets you quickly create, install, or update skills through natural language conversation.
+
+## Usage
+
+Simply describe the skill you want in a conversation, and the Agent will handle the creation:
+
+- Codify workflows as skills: "Create a skill from this deployment process"
+- Integrate third-party APIs: "Create a skill based on this API documentation"
+- Install remote skills: "Install xxx skill for me"
+
+## Creation Flow
+
+1. Tell the Agent what skill you want to create
+2. Agent automatically generates `SKILL.md` description and execution scripts
+3. Skill is saved to the workspace `~/cow/skills/` directory
+4. Agent will automatically recognize and use the skill in future conversations
+
+<Frame>
+  <img src="https://cdn.link-ai.tech/doc/20260202202247.png" width="800" />
+</Frame>
+
+## SKILL.md Format
+
+Created skills follow the standard SKILL.md format:
+
+```markdown
+---
+name: my-skill
+description: Brief description of the skill
+metadata:
+  emoji: 🔧
+  requires:
+    bins: ["curl"]
+    env: ["MY_API_KEY"]
+  primaryEnv: "MY_API_KEY"
+---
+
+# My Skill
+
+Detailed instructions...
+```
+
+| Field | Description |
+| --- | --- |
+| `name` | Skill name, must match directory name |
+| `description` | Skill description, Agent decides whether to invoke based on this |
+| `metadata.requires.bins` | Required system commands |
+| `metadata.requires.env` | Required environment variables |
+| `metadata.always` | Always load (default false) |
+
+<Tip>
+  See the [Skill Creator documentation](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/skills/skill-creator/SKILL.md) for details.
+</Tip>

docs/en/skills/image-vision.mdx

@@ -1,31 +0,0 @@
----
-title: Image Vision
-description: Recognize images using OpenAI vision models
----
-
-Analyze image content using OpenAI's GPT-4 Vision API, understanding objects, text, colors, and other elements in images.
-
-## Dependencies
-
-| Dependency | Description |
-| --- | --- |
-| `OPENAI_API_KEY` | OpenAI API key |
-| `curl`, `base64` | System commands (usually pre-installed) |
-
-Configuration:
-
-- Configure `OPENAI_API_KEY` via the `env_config` tool
-- Or set `open_ai_api_key` in `config.json`
-
-## Supported Models
-
-- `gpt-4.1-mini` (recommended, cost-effective)
-- `gpt-4.1`
-
-## Usage
-
-Once configured, send an image to the Agent to automatically trigger image recognition.
-
-<Frame>
-  <img src="https://cdn.link-ai.tech/doc/20260202213219.png" width="800" />
-</Frame>

docs/en/skills/index.mdx

@@ -7,20 +7,17 @@ Skills provide infinite extensibility for the Agent. Each Skill consists of a de
 
 The difference between Skills and Tools: Tools are atomic operations implemented in code (e.g., file read/write, command execution), while Skills are high-level workflows based on description files that can combine multiple Tools to complete complex tasks.
 
-## Built-in Skills
+## Getting Skills
 
-Located in the project `skills/` directory, automatically enabled based on dependency conditions:
+CowAgent offers multiple ways to acquire skills:
 
-| Skill | Description | Dependencies |
-| --- | --- | --- |
-| [`skill-creator`](/en/skills/skill-creator) | Create custom skills through conversation | None |
-| [`openai-image-vision`](/en/skills/image-vision) | Recognize images using OpenAI vision models | `OPENAI_API_KEY` |
-| [`linkai-agent`](/en/skills/linkai-agent) | Integrate LinkAI platform agents | `LINKAI_API_KEY` |
-| [`web-fetch`](/en/skills/web-fetch) | Fetch web page text content | `curl` (enabled by default) |
+- **Cow Skill Hub** — Browse and install community skills via `/skill list --remote`
+- **GitHub** — Install directly from GitHub repositories, with batch install support
+- **ClawHub** — Install ClawHub skills via `/skill install clawhub:name`
+- **URL** — Install from zip archives or SKILL.md links
+- **Conversational creation** — Let the Agent create skills through natural language conversation
 
-## Custom Skills
-
-Created by users through conversation, stored in workspace (`~/cow/skills/`), can implement any complex business process and third-party system integration.
+See [Install Skills](/en/skills/install) and [Skill Management Commands](/en/cli/skill) for details. You can also [create skills](/en/skills/create) through conversation.
 
 ## Skill Loading Priority
 

docs/en/skills/install.mdx

@@ -0,0 +1,53 @@
+---
+title: Install Skills
+description: Install skills from multiple sources with a single command
+---
+
+CowAgent supports installing skills from **Cow Skill Hub, GitHub, ClawHub**, and any URL with a unified `install` command. Use `/skill install` in chat or `cow skill install` in the terminal.
+
+## From Skill Hub
+
+Browse the Skill Hub and install:
+
+```text
+/skill list --remote
+/skill install pptx
+```
+
+## From GitHub
+
+Supports batch install from repositories and single skill from subdirectories:
+
+```text
+/skill install larksuite/cli
+/skill install https://github.com/larksuite/cli/tree/main/skills/lark-im
+```
+
+## From ClawHub
+
+```text
+/skill install clawhub:baidu-search
+```
+
+## From URL
+
+Supports zip archives and SKILL.md file links:
+
+```text
+/skill install https://cdn.link-ai.tech/skills/pptx.zip
+/skill install https://example.com/path/to/SKILL.md
+```
+
+## Manage Skills
+
+```text
+/skill list                  # View installed skills
+/skill info pptx             # View skill details
+/skill enable pptx           # Enable a skill
+/skill disable pptx          # Disable a skill
+/skill uninstall pptx        # Uninstall a skill
+```
+
+<Tip>
+  All commands above work in the terminal by replacing `/skill` with `cow skill`. See [Skill Management Commands](/en/cli/skill) for full documentation.
+</Tip>

docs/en/skills/linkai-agent.mdx

@@ -1,47 +0,0 @@
----
-title: LinkAI Agent
-description: Integrate LinkAI platform multi-agent skill
----
-
-Use agents from the [LinkAI](https://link-ai.tech/) platform as Skills for multi-agent decision-making. The Agent intelligently selects based on agent names and descriptions, calling the corresponding application or workflow via `app_code`.
-
-## Dependencies
-
-| Dependency | Description |
-| --- | --- |
-| `LINKAI_API_KEY` | LinkAI platform API key, created in [Console](https://link-ai.tech/console/interface) |
-| `curl` | System command (usually pre-installed) |
-
-Configuration:
-
-- Configure `LINKAI_API_KEY` via the `env_config` tool
-- Or set `linkai_api_key` in `config.json`
-
-## Configure Agents
-
-Add available agents in `skills/linkai-agent/config.json`:
-
-```json
-{
-  "apps": [
-    {
-      "app_code": "G7z6vKwp",
-      "app_name": "LinkAI Customer Support",
-      "app_description": "Select this assistant only when the user needs help with LinkAI platform questions"
-    },
-    {
-      "app_code": "SFY5x7JR",
-      "app_name": "Content Creator",
-      "app_description": "Use this assistant only when the user needs to create images or videos"
-    }
-  ]
-}
-```
-
-## Usage
-
-Once configured, the Agent will automatically select the appropriate LinkAI agent based on the user's question.
-
-<Frame>
-  <img src="https://cdn.link-ai.tech/doc/20260202234350.png" width="750" />
-</Frame>

docs/en/skills/skill-creator.mdx

@@ -1,31 +0,0 @@
----
-title: Skill Creator
-description: Create custom skills through conversation
----
-
-Quickly create, install, or update skills through natural language conversation.
-
-## Dependencies
-
-No extra dependencies, always available.
-
-## Usage
-
-- Codify workflows as skills: "Create a skill from this deployment process"
-- Integrate third-party APIs: "Create a skill based on this API documentation"
-- Install remote skills: "Install xxx skill for me"
-
-## Creation Flow
-
-1. Tell the Agent what skill you want to create
-2. Agent automatically generates `SKILL.md` description and execution scripts
-3. Skill is saved to the workspace `~/cow/skills/` directory
-4. Agent will automatically recognize and use the skill in future conversations
-
-<Frame>
-  <img src="https://cdn.link-ai.tech/doc/20260202202247.png" width="800" />
-</Frame>
-
-<Tip>
-  See the [Skill Creator documentation](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/skills/skill-creator/SKILL.md) for details.
-</Tip>

docs/en/skills/web-fetch.mdx

@@ -1,31 +0,0 @@
----
-title: Web Fetch
-description: Fetch web page text content
----
-
-Use curl to fetch web pages and extract readable text content. A lightweight web access method without browser automation.
-
-## Dependencies
-
-| Dependency | Description |
-| --- | --- |
-| `curl` | System command (usually pre-installed) |
-
-This skill has `always: true` set, enabled by default as long as the system has the `curl` command.
-
-## Usage
-
-Automatically invoked when the Agent needs to fetch content from a URL, no extra configuration needed.
-
-## Comparison with browser Tool
-
-| Feature | web-fetch (skill) | browser (tool) |
-| --- | --- | --- |
-| Dependencies | curl only | browser-use + playwright |
-| JS rendering | Not supported | Supported |
-| Page interaction | Not supported | Supports click, type, etc. |
-| Best for | Static page text | Dynamic web pages |
-
-<Tip>
-  For most web content retrieval scenarios, web-fetch is sufficient. Only use the browser tool when you need JS rendering or page interaction.
-</Tip>

docs/en/tools/memory.mdx

@@ -1,9 +1,11 @@
 ---
-title: memory - Memory
-description: Search and read long-term memory
+title: memory - Memory & Knowledge
+description: Search and read long-term memory and knowledge base files
 ---
 
-The memory tool contains two sub-tools: `memory_search` (search memory) and `memory_get` (read memory files).
+The memory tool contains two sub-tools: `memory_search` (search memory) and `memory_get` (read memory or knowledge files).
+
+When the [knowledge base](/en/knowledge) feature is enabled, both tools also support accessing files under the `knowledge/` directory.
 
 ## Dependencies
 
@@ -11,7 +13,7 @@ No extra dependencies, available by default. Managed by the Agent Core memory sy
 
 ## memory_search
 
-Search historical memory with hybrid keyword and vector retrieval.
+Search historical memory and knowledge base content with hybrid keyword and vector retrieval.
 
 | Parameter | Type | Required | Description |
 | --- | --- | --- | --- |
@@ -19,11 +21,11 @@ Search historical memory with hybrid keyword and vector retrieval.
 
 ## memory_get
 
-Read the content of a specific memory file.
+Read the content of a specific memory or knowledge file.
 
 | Parameter | Type | Required | Description |
 | --- | --- | --- | --- |
-| `path` | string | Yes | Relative path to memory file (e.g. `MEMORY.md`, `memory/2026-01-01.md`) |
+| `path` | string | Yes | Relative path to the file (e.g. `MEMORY.md`, `memory/2026-01-01.md`, `knowledge/concepts/rag.md`) |
 | `start_line` | integer | No | Start line number |
 | `end_line` | integer | No | End line number |
 
@@ -34,3 +36,8 @@ The Agent automatically invokes memory tools in these scenarios:
 - When the user shares important information → stores to memory
 - When historical context is needed → searches relevant memory
 - When conversation reaches a certain length → extracts summary for storage
+- When discussing domain knowledge → retrieves relevant pages from the knowledge base
+
+<Note>
+  When `knowledge` is set to `false` in config, the tool descriptions and search scope automatically adjust to include only memory files.
+</Note>

docs/en/tools/vision.mdx

@@ -0,0 +1,72 @@
+---
+title: vision - Image Analysis
+description: Analyze image content (recognition, description, OCR, etc.)
+---
+
+Analyze local images or image URLs using Vision API. Supports content description, text extraction (OCR), object recognition, and more.
+
+## Model Selection
+
+The vision tool uses a multi-level auto-selection strategy with automatic fallback — no manual configuration required:
+
+1. **Main model** — uses the currently configured main model for image recognition (zero extra cost)
+2. **Other configured models** — auto-discovers other models with configured API keys as alternatives
+3. **OpenAI** — uses `open_ai_api_key` to call gpt-4.1-mini
+4. **LinkAI** — uses `linkai_api_key` to call LinkAI vision service
+
+When `use_linkai=true`, LinkAI is promoted to the highest priority.
+
+If the current provider fails, the tool automatically tries the next one until it succeeds or all fail.
+
+### Supported Models
+
+| Vendor | Vision Model | Notes |
+| --- | --- | --- |
+| OpenAI / Compatible | Main model | All OpenAI-compatible multimodal models |
+| Qwen (DashScope) | Main model | Via MultiModalConversation API |
+| Claude | Main model | Anthropic native image format |
+| Gemini | Main model | inlineData format |
+| Doubao | Main model | doubao-seed-2-0 series natively supported |
+| Kimi (Moonshot) | Main model | kimi-k2.5 natively supported |
+| ZhipuAI | glm-5v-turbo | Always uses dedicated vision model |
+| MiniMax | MiniMax-Text-01 | Always uses dedicated vision model |
+
+<Note>
+  ZhipuAI and MiniMax text models do not support image understanding, so their dedicated vision models are always used automatically.
+</Note>
+
+## Parameters
+
+| Parameter | Type | Required | Description |
+| --- | --- | --- | --- |
+| `image` | string | Yes | Local file path or HTTP(S) image URL |
+| `question` | string | Yes | Question to ask about the image |
+
+Supported image formats: jpg, jpeg, png, gif, webp
+
+## Custom Configuration
+
+To specify a particular model for the vision tool, add to `config.json`:
+
+```json
+{
+    "tool": {
+        "vision": {
+            "model": "gpt-4o"
+        }
+    }
+}
+```
+
+In most cases no configuration is needed. The tool works automatically as long as the main model supports multimodal input or any vision-capable API key is configured.
+
+## Use Cases
+
+- Describe image content
+- Extract text from images (OCR)
+- Identify objects, colors, scenes
+- Analyze screenshots and scanned documents
+
+<Note>
+  Images larger than 1MB are automatically compressed (max edge 1536px). All images (including remote URLs) are converted to base64 for transmission to ensure compatibility with all model backends.
+</Note>

docs/guide/manual-install.mdx

@@ -32,7 +32,39 @@ pip3 install -r requirements-optional.txt
 
 > 国内网络可使用镜像源加速：`pip3 install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple`
 
-### 3. 配置
+### 3. 安装 Cow CLI
+
+安装命令行工具，用于管理服务和技能：
+
+```bash
+pip3 install -e .
+```
+
+安装后即可使用 `cow` 命令：
+
+```bash
+cow help
+```
+
+<Note>
+  此步骤为推荐操作。安装后可以使用 `cow start`、`cow stop`、`cow update` 等命令管理服务，也可以使用 `cow skill` 管理技能。如果不安装 CLI，可以使用 `./run.sh` 或 `python3 app.py` 运行。
+</Note>
+
+### 3.1 安装浏览器工具（可选）
+
+如需使用浏览器工具（控制浏览器访问网页、填写表单等），运行：
+
+```bash
+cow install-browser
+```
+
+该命令会自动安装 Playwright 和 Chromium 浏览器。详细说明参考 [浏览器工具文档](/tools/browser)。
+
+<Note>
+  浏览器工具依赖较重（~300MB），如不需要可跳过，不影响其他功能正常使用。
+</Note>
+
+### 4. 配置
 
 复制配置文件模板并编辑：
 
@@ -42,9 +74,15 @@ cp config-template.json config.json
 
 在 `config.json` 中填写模型 API Key 和通道类型等配置，详细说明参考各 [模型文档](/models/minimax)。
 
-### 4. 运行
+### 5. 运行
 
-**本地运行：**
+**使用 Cow CLI 运行（推荐）：**
+
+```bash
+cow start
+```
+
+**或者本地前台运行：**
 
 ```bash
 python3 app.py
@@ -52,7 +90,7 @@ python3 app.py
 
 运行后默认启动 Web 控制台，访问 `http://localhost:9899` 开始对话和管理Agent。
 
-**服务器后台运行：**
+**服务器后台运行（不使用 CLI 时）：**
 
 ```bash
 nohup python3 app.py & tail -f nohup.out
@@ -96,28 +134,44 @@ sudo docker logs -f chatgpt-on-wechat
 
 ## 核心配置项
 
-```json
-{
-  "channel_type": "web",
-  "model": "MiniMax-M2.5",
-  "agent": true,
-  "agent_workspace": "~/cow",
-  "agent_max_context_tokens": 40000,
-  "agent_max_context_turns": 30,
-  "agent_max_steps": 15
-}
-```
+<Tabs>
+  <Tab title="源码部署（config.json）">
+    ```json
+    {
+      "channel_type": "web",
+      "model": "MiniMax-M2.7",
+      "agent": true,
+      "agent_workspace": "~/cow",
+      "agent_max_context_tokens": 40000,
+      "agent_max_context_turns": 30,
+      "agent_max_steps": 15
+    }
+    ```
+  </Tab>
+  <Tab title="Docker 部署（docker-compose.yml）">
+    ```yaml
+    environment:
+      CHANNEL_TYPE: 'web'
+      MODEL: 'MiniMax-M2.7'
+      MINIMAX_API_KEY: 'your-api-key'
+      AGENT: 'True'
+      AGENT_MAX_CONTEXT_TOKENS: 40000
+      AGENT_MAX_CONTEXT_TURNS: 30
+      AGENT_MAX_STEPS: 15
+    ```
+  </Tab>
+</Tabs>
 
-| 参数 | 说明 | 默认值 |
-| --- | --- | --- |
-| `channel_type` | 接入渠道类型 | `web` |
-| `model` | 模型名称 | `MiniMax-M2.5` |
-| `agent` | 是否启用 Agent 模式 | `true` |
-| `agent_workspace` | Agent 工作空间路径 | `~/cow` |
-| `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` |
+| 参数 | 环境变量 | 说明 | 默认值 |
+| --- | --- | --- | --- |
+| `channel_type` | `CHANNEL_TYPE` | 接入渠道类型 | `web` |
+| `model` | `MODEL` | 模型名称 | `MiniMax-M2.5` |
+| `agent` | `AGENT` | 是否启用 Agent 模式 | `true` |
+| `agent_workspace` | - | Agent 工作空间路径 | `~/cow` |
+| `agent_max_context_tokens` | `AGENT_MAX_CONTEXT_TOKENS` | 最大上下文 tokens | `40000` |
+| `agent_max_context_turns` | `AGENT_MAX_CONTEXT_TURNS` | 最大上下文记忆轮次 | `30` |
+| `agent_max_steps` | `AGENT_MAX_STEPS` | 单次任务最大决策步数 | `15` |
 
 <Tip>
-  全部配置项可在项目 [`config.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/config.py) 文件中查看。
+  全部配置项可在项目 [`config.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/config.py) 文件中查看。Docker 部署时，配置项名称需转为大写环境变量格式。
 </Tip>

docs/guide/quick-start.mdx

@@ -9,16 +9,25 @@ description: 使用脚本一键安装和管理 CowAgent
 
 ## 安装命令
 
-```bash
-bash <(curl -fsSL 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>
 
 脚本自动执行以下流程：
 
 1. 检查 Python 环境（需要 Python 3.7+）
 2. 安装必要工具（git、curl 等）
 3. 克隆项目代码到 `~/chatgpt-on-wechat`
-4. 安装 Python 依赖
+4. 安装 Python 依赖和 Cow CLI
 5. 引导配置 AI 模型和通信渠道
 6. 启动服务
 
@@ -26,14 +35,20 @@ bash <(curl -fsSL https://cdn.link-ai.tech/code/cow/run.sh)
 
 ## 管理命令
 
-安装完成后，可使用以下命令管理服务：
+安装完成后，使用 `cow` CLI 管理服务：
 
 | 命令 | 说明 |
 | --- | --- |
-| `./run.sh start` | 启动服务 |
-| `./run.sh stop` | 停止服务 |
-| `./run.sh restart` | 重启服务 |
-| `./run.sh status` | 查看运行状态 |
-| `./run.sh logs` | 查看实时日志 |
-| `./run.sh config` | 重新配置 |
-| `./run.sh update` | 更新项目代码 |
+| `cow start` | 启动服务 |
+| `cow stop` | 停止服务 |
+| `cow restart` | 重启服务 |
+| `cow status` | 查看运行状态 |
+| `cow logs` | 查看实时日志 |
+| `cow update` | 更新代码并重启 |
+| `cow install-browser` | 安装浏览器工具依赖 |
+
+更多命令和用法参考 [命令文档](/cli/index)。
+
+<Note>
+  如果 `cow` 命令不可用，也可以使用 `./run.sh <命令>`（Linux/macOS）或 `.\scripts\run.ps1 <命令>`（Windows）作为替代，功能等效。
+</Note>

docs/guide/upgrade.mdx

@@ -3,20 +3,25 @@ title: 更新升级
 description: CowAgent 的升级方式说明
 ---
 
-## 脚本升级（推荐）
+## 命令升级（推荐）
 
-如果使用 `run.sh` 管理服务，在项目根目录执行以下命令即可一键升级：
+使用 `cow update` 一键完成代码更新和服务重启：
 
 ```bash
-./run.sh update
+cow update
 ```
 
 该命令会自动完成以下流程：
 
-1. 停止当前运行的服务
-2. 拉取最新代码
-3. 重新检查依赖
-4. 启动服务
+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
+
+<Note>
+  如果未安装 Cow CLI，也可以使用 `./run.sh update` 完成相同操作。
+</Note>
 
 ## 手动升级
 
@@ -25,15 +30,19 @@ description: CowAgent 的升级方式说明
 ```bash
 git pull
 pip3 install -r requirements.txt
+pip3 install -e .
 ```
 
 更新完成后重启服务：
 
 ```bash
-# 如果使用 run.sh 管理
+# 使用 Cow CLI (推荐)
+cow restart
+
+# 或使用 run.sh
 ./run.sh restart
 
-# 如果使用 nohup 直接运行
+# 或使用 nohup 直接运行
 kill $(ps -ef | grep app.py | grep -v grep | awk '{print $2}')
 nohup python3 app.py & tail -f nohup.out
 ```

docs/intro/architecture.mdx

@@ -11,25 +11,27 @@ CowAgent 的整体架构由以下核心模块组成：
 
 <img src="https://cdn.link-ai.tech/doc/68ef7b212c6f791e0e74314b912149f9-sz_5847990.png" alt="CowAgent Architecture" />
 
-### 核心模块说明
-
 | 模块 | 说明 |
 | --- | --- |
-| **Channels** | 消息通道层，负责接收和发送消息，支持 Web、飞书、钉钉、企微、公众号等 |
-| **Agent Core** | 智能体核心引擎，包括任务规划、记忆系统和技能引擎 |
-| **Tools** | 工具层，Agent 通过工具访问操作系统资源，内置 10+ 种工具 |
-| **Models** | 模型层，支持国内外主流大语言模型的统一接入 |
+| **Plan** | 理解用户意图，将复杂任务分解为多步骤计划，循环调用工具直到完成目标 |
+| **Memory** | 自动将重要信息持久化为核心记忆和日级记忆，支持关键词和向量混合检索，跨会话保持上下文连续性 |
+| **Knowledge** | 以主题维度组织结构化知识，Agent 自主整理有价值信息为 Markdown 页面，维护索引和交叉引用，构建持续增长的知识网络 |
+| **Tools** | Agent 访问操作系统资源的核心能力，内置文件读写、终端执行、浏览器操作、定时调度、记忆检索、联网搜索等 10+ 种工具 |
+| **Skills** | 加载和管理 Skills，支持从 Skill Hub、GitHub 等一键安装，或通过对话创建自定义技能 |
+| **Models** | 模型层，统一接入 OpenAI、Claude、Gemini、DeepSeek、MiniMax、GLM、Qwen 等国内外主流大语言模型 |
+| **Channels** | 消息通道层，负责接收和发送消息，支持 Web 控制台、微信、飞书、钉钉、企微、公众号等，统一消息协议 |
+| **CLI** | 命令行系统，提供终端命令（`cow`）和对话命令（`/`），支持进程管理、技能安装、配置修改、知识库管理等操作 |
 
 ## Agent 模式
 
 启用 Agent 模式后，CowAgent 会以自主智能体的方式运行，核心工作流如下：
 
-1. **接收消息** - 通过通道接收用户输入
-2. **理解意图** - 分析任务需求和上下文
-3. **规划任务** - 将复杂任务分解为多个步骤
-4. **调用工具** - 选择合适的工具执行每个步骤
-5. **记忆更新** - 将重要信息存入长期记忆
-6. **返回结果** - 将执行结果发送回用户
+1. **接收消息** — 通过通道接收用户输入
+2. **理解意图** — 分析任务需求和上下文
+3. **规划任务** — 将复杂任务分解为多个步骤
+4. **调用工具** — 选择合适的工具执行每个步骤
+5. **记忆与知识更新** — 将重要信息存入长期记忆，将结构化知识整理至知识库
+6. **返回结果** — 将执行结果发送回用户
 
 ## 工作空间
 
@@ -37,11 +39,14 @@ Agent 的工作空间默认位于 `~/cow` 目录，用于存储系统提示词
 
 ```
 ~/cow/
-├── system.md          # Agent system prompt
-├── user.md            # User profile
+├── 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 @@ Agent 的工作空间默认位于 `~/cow` 目录，用于存储系统提示词
 | `agent_max_context_tokens` | 最大上下文 token 数 | `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` |
+| `knowledge` | 是否启用个人知识库 | `true` |

docs/intro/features.mdx

@@ -1,6 +1,6 @@
 ---
 title: 功能介绍
-description: CowAgent 长期记忆、任务规划、技能系统详细说明
+description: CowAgent 长期记忆、个人知识库、任务规划、技能系统、CLI 命令、浏览器工具详细说明
 ---
 
 ## 1. 长期记忆
@@ -15,13 +15,26 @@ description: CowAgent 长期记忆、任务规划、技能系统详细说明
   <img src="https://cdn.link-ai.tech/doc/20260203000455.png" width="800" />
 </Frame>
 
-## 2. 任务规划和工具调用
+## 2. 个人知识库
+
+> 知识库系统让 Agent 能够持续积累和组织结构化知识。与按时间线记录的记忆不同，知识库以主题为维度，将文章、对话洞察、学习材料等整理为互相关联的 Markdown 页面，形成持续增长的知识网络。
+
+Agent 会在对话中自动将有价值的信息整理为知识页面，维护交叉引用和索引，通过 Web 控制台可浏览文档和查看知识图谱。知识库存储在工作空间的 `~/cow/knowledge/` 目录下。
+
+- **自动整理**：Agent 在对话中自主提取和整理结构化知识，维护索引和交叉引用
+- **知识图谱**：基于页面间的交叉引用自动构建知识图谱，Web 控制台提供可视化关系图浏览
+- **对话联动**：Agent 回复中引用的知识文档链接可在 Web 控制台中直接点击跳转查看
+- **CLI 管理**：通过 `/knowledge` 命令查看统计、浏览目录，通过 `/knowledge on|off` 开关功能
+
+详细说明请参考 [个人知识库](/knowledge)。
+
+## 3. 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。内置工具的实现在项目的 `agent/tools/` 目录下。
 
-**主要工具：** 文件读写编辑、Bash 终端、文件发送、定时调度、记忆搜索、联网搜索、环境配置等。
+**主要工具：** 文件读写编辑、Bash 终端、浏览器操作、文件发送、定时调度、记忆搜索、联网搜索、环境配置等。
 
-### 2.1 终端和文件访问
+### 3.1 终端和文件访问
 
 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此进行扩展。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：
 
@@ -29,7 +42,7 @@ description: CowAgent 长期记忆、任务规划、技能系统详细说明
   <img src="https://cdn.link-ai.tech/doc/20260202181130.png" width="800" />
 </Frame>
 
-### 2.2 编程能力
+### 3.2 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：
 
@@ -37,7 +50,7 @@ description: CowAgent 长期记忆、任务规划、技能系统详细说明
   <img src="https://cdn.link-ai.tech/doc/20260203121008.png" width="800" />
 </Frame>
 
-### 2.3 定时任务
+### 3.3 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：
 
@@ -45,7 +58,15 @@ description: CowAgent 长期记忆、任务规划、技能系统详细说明
   <img src="https://cdn.link-ai.tech/doc/20260202195402.png" width="800" />
 </Frame>
 
-### 2.4 环境变量管理
+### 3.4 浏览器操作
+
+内置 `browser` 工具，Agent 可控制浏览器访问网页、填写表单、点击元素、截图，支持动态 JS 渲染页面。运行 `cow install-browser` 一键安装，自动适配服务器（无头模式）和桌面环境：
+
+<Frame>
+  <img src="https://cdn.link-ai.tech/doc/20260401115728.png" width="750" />
+</Frame>
+
+### 3.5 环境变量管理
 
 技能所需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，工具内置安全保护和脱敏策略：
 
@@ -53,14 +74,17 @@ description: CowAgent 长期记忆、任务规划、技能系统详细说明
   <img src="https://cdn.link-ai.tech/doc/20260202234939.png" width="800" />
 </Frame>
 
-## 3. 技能系统
+## 4. 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。
 
+- **[Skill Hub](https://skills.cowagent.ai/)：** 开放的技能广场，汇集官方推荐、社区贡献和第三方技能，支持一键安装。
 - **内置技能：** 在项目的 `skills/` 目录下，包含技能创造器、图像识别、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。
 - **自定义技能：** 由用户通过对话创建，存放在工作空间中（`~/cow/skills/`），可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
+安装技能：`/skill install <名称>` 或 `cow skill install <名称>`，支持从 Skill Hub、GitHub、ClawHub、URL 等来源安装。
+
+### 4.1 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。你可以让 Agent 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：
 
@@ -68,7 +92,7 @@ description: CowAgent 长期记忆、任务规划、技能系统详细说明
   <img src="https://cdn.link-ai.tech/doc/20260202202247.png" width="800" />
 </Frame>
 
-### 3.2 搜索和图像识别
+### 4.2 搜索和图像识别
 
 - **联网搜索：** 内置 `web_search` 工具，支持多种搜索引擎，配置 `BOCHA_API_KEY` 或 `LINKAI_API_KEY` 后启用。
 - **图像识别：** 内置 `openai-image-vision` 技能，可使用 `gpt-4.1-mini`、`gpt-4.1` 等模型，依赖 `OPENAI_API_KEY`。
@@ -77,29 +101,36 @@ description: CowAgent 长期记忆、任务规划、技能系统详细说明
   <img src="https://cdn.link-ai.tech/doc/20260202213219.png" width="800" />
 </Frame>
 
-### 3.3 三方知识库和插件
+### 4.3 技能广场
 
-`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，实现多智能体决策效果。
+访问 [skills.cowagent.ai](https://skills.cowagent.ai/) 浏览所有可用技能，或在对话中执行：
 
-配置方式：通过 `env_config` 配置 `LINKAI_API_KEY`，并在 `skills/linkai-agent/config.json` 中添加智能体说明：
-
-```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"
-    },
-    {
-      "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"
-    }
-  ]
-}
+```text
+/skill list --remote          # 浏览技能广场
+/skill search <关键词>         # 搜索技能
+/skill install <名称>          # 一键安装
 ```
 
-<Frame>
-  <img src="https://cdn.link-ai.tech/doc/20260202234350.png" width="750" />
-</Frame>
+同时还支持安装Github、ClawHub、LinkAI等第三方平台上的所有技能，详情查看 [技能安装](/skills/install)
+
+<img src="https://cdn.link-ai.tech/doc/20260401110103.png" width="750" />
+
+
+## 5. CLI 命令系统
+
+CowAgent 提供两种命令交互方式，覆盖服务管理、技能安装、配置调整等日常运维操作：
+
+- **终端 CLI：** 在系统终端执行 `cow <命令>`，支持 `start`、`stop`、`restart`、`update`、`status`、`logs`、`skill` 等
+- **对话命令：** 在对话中输入 `/<命令>`，Web 控制台输入 `/` 可弹出指令菜单快速选择
+
+```bash
+cow start              # 启动服务
+cow stop               # 停止服务
+cow update             # 更新并重启
+cow skill install pptx # 安装技能
+cow install-browser    # 安装浏览器工具
+```
+
+详细命令参考 [命令总览](https://docs.cowagent.ai/cli)。
+
+<img src="https://cdn.link-ai.tech/doc/20260401114549.png" width="750" />

docs/intro/index.mdx

@@ -5,7 +5,7 @@ description: CowAgent - 基于大模型的超级AI助理
 
 <img src="https://cdn.link-ai.tech/doc/78c5dd674e2c828642ecc0406669fed7.png" alt="CowAgent" width="450px"/>
 
-**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** 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。
 
 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、企业微信应用、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。
 
@@ -22,21 +22,27 @@ CowAgent 支持灵活切换多种模型，能处理文本、语音、图片、
 
 <CardGroup cols={2}>
   <Card title="复杂任务规划" icon="brain" href="/intro/architecture">
-    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。
+    能够理解复杂任务并自主规划执行，持续思考和调用各类工具和技能直到完成目标。
   </Card>
   <Card title="长期记忆" icon="database" href="/memory">
     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。
   </Card>
+  <Card title="个人知识库" icon="book" href="/knowledge">
+    自动整理结构化知识，支持知识图谱可视化，通过交叉引用构建持续增长的知识网络。
+  </Card>
   <Card title="技能系统" icon="puzzle-piece" href="/skills/index">
     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。
   </Card>
-  <Card title="多模态消息" icon="image" href="/channels/web">
-    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。
+  <Card title="工具系统" icon="wrench" href="/tools/index">
+    内置文件读写、终端执行、浏览器操作、定时任务、消息发送等工具，Agent 可自主调用工具完成复杂任务。
   </Card>
-  <Card title="多模型接入" icon="microchip" href="/models/index">
+  <Card title="命令系统" icon="terminal" href="/cli/index">
+    提供终端 CLI 和对话中的命令，支持进程管理、技能安装、配置修改、上下文查看等常用操作。
+  </Card>
+  <Card title="多模型支持" icon="microchip" href="/models/index">
     支持 OpenAI, Claude, Gemini, DeepSeek, MiniMax, GLM, Qwen, Kimi, Doubao 等国内外主流模型厂商。
   </Card>
-  <Card title="多端部署" icon="server" href="/channels/weixin">
+  <Card title="多通道接入" icon="server" href="/channels/weixin">
     支持运行在本地计算机或服务器，可集成到微信、网页、飞书、钉钉、微信公众号、企业微信应用中使用。
   </Card>
 </CardGroup>
@@ -45,9 +51,18 @@ CowAgent 支持灵活切换多种模型，能处理文本、语音、图片、
 
 在终端执行以下命令，即可一键安装、配置、启动 CowAgent：
 
-```bash
-bash <(curl -fsSL 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>
 
 运行后默认会启动 Web 控制台，通过访问 `http://localhost:9899` 可以在网页端进行对话、配置、应用通道接入等操作。
 

docs/ja/README.md

@@ -13,6 +13,7 @@
   <a href="https://cowagent.ai/">🌐 ウェブサイト</a> &nbsp;·&nbsp;
   <a href="https://docs.cowagent.ai/en/intro/index">📖 ドキュメント</a> &nbsp;·&nbsp;
   <a href="https://docs.cowagent.ai/en/guide/quick-start">🚀 クイックスタート</a> &nbsp;·&nbsp;
+  <a href="https://skills.cowagent.ai/">🧩 Skill Hub</a> &nbsp;·&nbsp;
   <a href="https://link-ai.tech/cowagent/create">☁️ オンラインで試す</a>
 </p>
 
@@ -20,13 +21,14 @@
 
 > CowAgentは、すぐに使えるAIスーパーアシスタントであると同時に、高い拡張性を持つAgentフレームワークでもあります。新しいモデルインターフェース、チャネル、組み込みツール、Skillシステムを拡張することで、さまざまなカスタマイズニーズに柔軟に対応できます。
 
-- ✅ **自律的タスク計画**: 複雑なタスクを理解し、自律的に実行計画を立て、目標達成までツールを呼び出しながら継続的に思考します。ツールを通じてファイル、ターミナル、ブラウザ、スケジューラなどのシステムリソースにアクセスできます。
+- ✅ **自律的タスク計画**: 複雑なタスクを理解し、自律的に実行計画を立て、目標達成までツールを呼び出しながら継続的に思考します。
 - ✅ **長期記憶**: 会話の記憶をローカルファイルやデータベースに自動的に永続化します。コアメモリとデイリーメモリを含み、キーワード検索やベクトル検索に対応しています。
-- ✅ **Skillシステム**: Skillの作成・実行エンジンを実装しており、複数の組み込みSkillを備え、自然言語での会話を通じたカスタムSkillの開発もサポートしています。
+- ✅ **Skillシステム**: Skillの作成・実行エンジンを実装。[Skill Hub](https://skills.cowagent.ai)、GitHubなどからSkillをインストールでき、会話を通じたカスタムSkill作成もサポートしています。
+- ✅ **ツールシステム**: ファイル読み書き、ターミナル実行、ブラウザ操作、スケジュールタスク、メッセージ送信などの組み込みツールを提供。Agentが自律的に呼び出して複雑なタスクを完了します。
+- ✅ **CLIシステム**: ターミナルコマンドとチャットコマンドを提供し、プロセス管理、Skillインストール、設定変更などの操作をサポートします。
 - ✅ **マルチモーダルメッセージ**: テキスト、画像、音声、ファイルなど、さまざまなメッセージタイプの解析・処理・生成・送信に対応しています。
 - ✅ **複数モデル対応**: OpenAI、Claude、Gemini、DeepSeek、MiniMax、GLM、Qwen、Kimi、Doubaoなど、主要なモデルプロバイダーに対応しています。
 - ✅ **マルチプラットフォームデプロイ**: ローカルPCやサーバー上で実行でき、WeChat、Web、Feishu、DingTalk、WeChat公式アカウント、WeComアプリケーションに統合可能です。
-- ✅ **ナレッジベース**: [LinkAI](https://link-ai.tech) プラットフォームを通じて、企業向けナレッジベース機能を統合できます。
 
 ## 免責事項
 
@@ -40,6 +42,8 @@
 
 ## 更新履歴
 
+> **2026.04.01:** [v2.0.5](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.5) — Cow CLI、Skill Hubオープンソース化、ブラウザツール、WeCom Botスキャン作成など。
+
 > **2026.02.27:** [v2.0.2](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.2) — Webコンソールの全面刷新（ストリーミングチャット、モデル/Skill/メモリ/チャネル/スケジューラ/ログ管理）、マルチチャネル同時実行、セッション永続化、Gemini 3.1 Pro / Claude 4.6 Sonnet / Qwen3.5 Plusなど新モデル追加。
 
 > **2026.02.13:** [v2.0.1](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/2.0.1) — 組み込みWeb検索ツール、スマートコンテキストトリミング、ランタイム情報の動的更新、Windows互換性、スケジューラのメモリ喪失やFeishu接続問題などの修正。
@@ -60,13 +64,19 @@
 
 本プロジェクトは、インストール・設定・起動・管理をワンクリックで行えるスクリプトを提供しています：
 
+**Linux / macOS:**
 ```bash
 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
+```
+
 実行後、デフォルトでWebサービスが起動します。`http://localhost:9899/chat` にアクセスしてチャットを開始できます。
 
-スクリプトの使い方: [ワンクリックインストール](https://docs.cowagent.ai/en/guide/quick-start)
+スクリプトの使い方: [ワンクリックインストール](https://docs.cowagent.ai/ja/guide/quick-start)。インストール後は `cow start`、`cow stop` などの [CLI コマンド](https://docs.cowagent.ai/ja/cli/index)でサービスを管理できます。
 
 ### 手動インストール
 
@@ -84,7 +94,25 @@ pip3 install -r requirements.txt
 pip3 install -r requirements-optional.txt   # 任意ですが推奨
 ```
 
-**3. 設定**
+**3. Cow CLI のインストール（推奨）**
+
+```bash
+pip3 install -e .
+```
+
+インストール後、`cow` コマンドでサービス管理（起動、停止、更新など）やSkill管理ができます。[コマンドドキュメント](https://docs.cowagent.ai/ja/cli/index)を参照してください。
+
+**4. ブラウザのインストール（任意）**
+
+Agentにブラウザ操作（Webページへのアクセス、フォーム入力など）が必要な場合：
+
+```bash
+cow install-browser
+```
+
+`playwright` と Chromium を自動インストールします。[ブラウザツールドキュメント](https://docs.cowagent.ai/ja/tools/browser)を参照してください。
+
+**5. 設定**
 
 ```bash
 cp config-template.json config.json
@@ -92,13 +120,25 @@ cp config-template.json config.json
 
 `config.json` にモデルのAPIキーとチャネルタイプを記入してください。詳細は[設定ドキュメント](https://docs.cowagent.ai/en/guide/manual-install)を参照してください。
 
-**4. 実行**
+**6. 実行**
 
 ```bash
-python3 app.py
+cow start              # 推奨、Cow CLI が必要
+python3 app.py         # または直接実行
 ```
 
-サーバーでバックグラウンド実行する場合：
+サーバーデプロイでは、`cow` コマンドでサービスを管理できます：
+
+```bash
+cow start              # バックグラウンドで起動
+cow stop               # サービス停止
+cow restart            # サービス再起動
+cow status             # 実行状態を確認
+cow logs               # ログを表示
+cow update             # 最新コードを取得して再起動
+```
+
+または従来の方法で実行：
 
 ```bash
 nohup python3 app.py & tail -f nohup.out
@@ -125,7 +165,7 @@ sudo docker logs -f chatgpt-on-wechat
 | 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` |
@@ -186,6 +226,7 @@ Coding Planは各プロバイダーが提供する月額サブスクリプショ
 
 ## 🔗 関連プロジェクト
 
+- [Cow Skill Hub](https://github.com/zhayujie/cow-skill-hub): AIエージェント向けのオープンSkillマーケットプレイス。CowAgent、OpenClaw、Claude Codeなどで利用可能なSkillの閲覧・検索・インストール・公開が可能。
 - [bot-on-anything](https://github.com/zhayujie/bot-on-anything): 軽量で高い拡張性を持つLLMアプリケーションフレームワーク。Slack、Telegram、Discord、Gmailなどに対応。
 - [AgentMesh](https://github.com/MinimalFuture/AgentMesh): エージェントチームの協調による複雑な問題解決のためのオープンソースのマルチエージェントフレームワーク。
 
@@ -195,7 +236,7 @@ FAQ: <https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs>
 
 ## 🛠️ コントリビューション
 
-新しいチャネルの追加を歓迎します。[Feishuチャネル](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/feishu/feishu_channel.py)を参考にしてください。また、新しいSkillのコントリビューションも歓迎します。[Skill Creatorドキュメント](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/skills/skill-creator/SKILL.md)を参照してください。
+新しいチャネルの追加を歓迎します。[Feishuチャネル](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/feishu/feishu_channel.py)を参考にしてください。また、新しいSkillのコントリビューションも歓迎します。[Skill作成ドキュメント](https://docs.cowagent.ai/ja/skills/create)を参照するか、[Skill Hub](https://skills.cowagent.ai/submit)に提出してください。
 
 ## ✉ お問い合わせ
 

docs/ja/cli/general.mdx

@@ -0,0 +1,126 @@
+---
+title: 汎用コマンド
+description: ステータスの確認、設定管理、コンテキスト制御などのよく使うコマンド
+---
+
+以下のコマンドはチャットで `/` プレフィックス、ターミナルで `cow` プレフィックスで使用できます（一部はチャット専用）。
+
+<Tip>
+  Web コンソールでは `/` を入力すると自動補完メニューが表示され、キーボードのナビゲーションと Tab 補完に対応しています。
+</Tip>
+
+## help
+
+使用可能なすべてのコマンドのヘルプ情報を表示します。
+
+```text
+/help
+```
+
+## status
+
+現在のセッションとサービスの実行状態を表示します。プロセス情報、モデル設定、メッセージ数、読み込み済みスキル数を含みます。
+
+```text
+/status
+```
+
+## config
+
+実行時設定の表示または変更を行います。変更は即座に反映され、再起動は不要です。
+
+**すべての設定項目を表示：**
+
+```text
+/config
+```
+
+**単一の設定項目を表示：**
+
+```text
+/config model
+```
+
+**設定項目を変更：**
+
+```text
+/config model deepseek-chat
+```
+
+**変更可能な設定項目：**
+
+| 項目 | 説明 | 例 |
+| --- | --- | --- |
+| `model` | AI モデル名 | `deepseek-chat` |
+| `agent_max_context_tokens` | 最大コンテキストトークン数 | `40000` |
+| `agent_max_context_turns` | 最大コンテキスト記憶ターン数 | `30` |
+| `agent_max_steps` | タスクごとの最大判断ステップ数 | `15` |
+
+<Note>
+  `model` を変更すると、システムが対応するモデル API を自動的にマッチングします。設定は `config.json` に永続的に保存されます。
+</Note>
+
+## context
+
+現在のセッションのコンテキスト統計情報を表示します。メッセージ数やコンテンツの長さを含みます。
+
+```text
+/context
+```
+
+**現在のセッションのコンテキストをクリア：**
+
+```text
+/context clear
+```
+
+<Tip>
+  コンテキストをクリアすると、Agent は以前の会話内容を「忘れます」。話題の切り替えやコンテキストスペースの解放に便利です。
+</Tip>
+
+## logs
+
+最近のサービスログを表示します。デフォルトでは最近の 20 行を表示し、最大 50 行です。
+
+```text
+/logs
+```
+
+**行数を指定：**
+
+```text
+/logs 50
+```
+
+## knowledge
+
+パーソナルナレッジベースの表示と管理を行います。デフォルトでは統計情報を表示します。
+
+```text
+/knowledge
+```
+
+**ディレクトリ構造を表示：**
+
+```text
+/knowledge list
+```
+
+**ナレッジベースの有効化・無効化：**
+
+```text
+/knowledge on
+/knowledge off
+```
+
+<Note>
+  ターミナル CLI では `cow knowledge` と `cow knowledge list` が利用可能ですが、`on|off` はチャットでのみサポートされます（実行時に即座に反映するため）。
+</Note>
+
+## version
+
+現在の CowAgent のバージョンを表示します。
+
+```text
+/version
+```

docs/ja/cli/index.mdx

@@ -0,0 +1,91 @@
+---
+title: コマンド概要
+description: CowAgent コマンドシステム — ターミナル CLI とチャットコマンド
+---
+
+CowAgent は2つのコマンド操作方法を提供しています：
+
+- **ターミナル CLI** — システムターミナルで `cow <コマンド>` を実行し、サービス管理やスキル管理を行います
+- **チャットコマンド** — 会話で `/<コマンド>` または `cow <コマンド>` を入力し、ステータス確認、スキル管理、設定変更を行います
+
+## Cow CLI
+
+ワンクリックインストールスクリプトでデプロイすると、`cow` コマンドが自動的に利用可能になります。手動インストールの場合は以下を実行してください：
+
+```bash
+pip install -e .
+```
+
+インストール後、任意の場所で `cow` コマンドを使用できます：
+
+```bash
+cow help
+```
+
+出力例：
+
+```
+🐮 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
+```
+
+## チャットコマンド
+
+Web コンソールや接続されたチャネルの会話で `/` を入力すると、コマンドの候補が表示されます。使用可能なコマンド：
+
+| コマンド | 説明 |
+| --- | --- |
+| `/help` | コマンドヘルプを表示 |
+| `/status` | サービスの状態と設定を表示 |
+| `/config` | 実行時設定の表示・変更 |
+| `/skill` | スキル管理（インストール、アンインストール、有効化、無効化など） |
+| `/knowledge` | ナレッジベースの統計情報を表示 |
+| `/knowledge list` | ナレッジベースのディレクトリ構造を表示 |
+| `/knowledge on\|off` | ナレッジベースの有効化・無効化 |
+| `/context` | 現在のセッションのコンテキスト情報を表示 |
+| `/context clear` | 現在のセッションのコンテキストをクリア |
+| `/logs` | 最近のログを表示 |
+| `/version` | バージョン番号を表示 |
+
+<Tip>
+  `/start`、`/stop`、`/restart` などのサービス管理コマンドは、プロセス操作を伴うため、ターミナルでの使用を案内します。
+</Tip>
+
+## コマンド対応表
+
+| コマンド | ターミナル (`cow`) | チャット (`/`) |
+| --- | :---: | :---: |
+| help | ✓ | ✓ |
+| version | ✓ | ✓ |
+| status | ✓ | ✓ |
+| logs | ✓ | ✓ |
+| config | ✗ | ✓ |
+| context | — | ✓ |
+| knowledge（サブコマンド） | ✓ | ✓ |
+| skill（サブコマンド） | ✓ | ✓ |
+| start / stop / restart | ✓ | ✗ |
+| update | ✓ | ✗ |
+| install-browser | ✓ | ✗ |
+
+<Note>
+  `context` はターミナルではチャットでの使用を案内するのみです。`config` はチャットでのみ利用可能です。
+</Note>

docs/ja/cli/process.mdx

@@ -0,0 +1,123 @@
+---
+title: プロセス管理
+description: cow コマンドで CowAgent プロセスのライフサイクルを管理
+---
+
+プロセス管理コマンドは CowAgent バックグラウンドプロセスのライフサイクルを制御します。これらのコマンドはターミナルでのみ使用可能です。
+
+## start
+
+CowAgent サービスを起動します。デフォルトではバックグラウンドデーモンとして実行され、自動的にログを表示します。
+
+```bash
+cow start
+```
+
+**オプション：**
+
+| オプション | 説明 |
+| --- | --- |
+| `-f`, `--foreground` | フォアグラウンドで実行（デーモンとして起動しない） |
+| `--no-logs` | 起動後にログを自動表示しない |
+
+## stop
+
+実行中の CowAgent サービスを停止します。
+
+```bash
+cow stop
+```
+
+## restart
+
+CowAgent サービスを再起動します（停止してから起動）。
+
+```bash
+cow restart
+```
+
+**オプション：**
+
+| オプション | 説明 |
+| --- | --- |
+| `--no-logs` | 再起動後にログを自動表示しない |
+
+## update
+
+コードを更新してサービスを再起動します。自動的に以下を実行します：
+
+1. 最新コードをプル（`git pull`）
+2. 現在のサービスを停止
+3. Python 依存パッケージを更新
+4. CLI を再インストール
+5. サービスを起動
+
+```bash
+cow update
+```
+
+<Warning>
+  `git pull` が失敗した場合（ローカルの未コミットの変更がある場合など）、更新は中止され、サービスには影響しません。
+</Warning>
+
+## status
+
+CowAgent サービスの実行状態を確認します。プロセス情報、バージョン、現在のモデルとチャネルの設定を含みます。
+
+```bash
+cow status
+```
+
+## logs
+
+サービスログを表示します。
+
+```bash
+cow logs
+```
+
+**オプション：**
+
+| オプション | 説明 | デフォルト値 |
+| --- | --- | --- |
+| `-f`, `--follow` | ログ出力を継続的に追跡 | いいえ |
+| `-n`, `--lines` | 最近の N 行を表示 | 50 |
+
+例：
+
+```bash
+# 最近の100行を表示
+cow logs -n 100
+
+# ログを継続的に追跡
+cow logs -f
+```
+
+## install-browser
+
+[ブラウザツール](/ja/tools/browser)のために Playwright と Chromium ブラウザをインストールします。
+
+```bash
+cow install-browser
+```
+
+<Tip>
+  ブラウザツール（Web ブラウジング、スクリーンショットなど）を使用する場合にのみ必要です。
+</Tip>
+
+## run.sh との互換性
+
+Cow CLI がインストールされていない場合は、`run.sh` でサービスを管理できます：
+
+| cow コマンド | run.sh 相当 |
+| --- | --- |
+| `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>
+  `cow` コマンドの使用を推奨します。よりシンプルな構文と豊富な機能を提供します。ワンクリックインストールスクリプトで自動的にインストールされます。
+</Note>

docs/ja/cli/skill.mdx

@@ -0,0 +1,192 @@
+---
+title: スキル管理
+description: コマンドでスキルのインストール、アンインストール、有効化、無効化、管理を行う
+---
+
+スキル管理コマンドは CowAgent のスキルのインストール、検索、管理に使用します。チャットでは `/skill <サブコマンド>`、ターミナルでは `cow skill <サブコマンド>` を使用します。
+
+## list
+
+インストール済みスキルとその状態を一覧表示します。
+
+<CodeGroup>
+```text チャット
+/skill list
+```
+
+```bash ターミナル
+cow skill list
+```
+</CodeGroup>
+
+**スキル広場を閲覧**（利用可能なすべてのスキルを表示）：
+
+<CodeGroup>
+```text チャット
+/skill list --remote
+```
+
+```bash ターミナル
+cow skill list --remote
+```
+</CodeGroup>
+
+**オプション：**
+
+| オプション | 説明 | デフォルト値 |
+| --- | --- | --- |
+| `--remote`, `-r` | Skill Hub のリモートスキルリストを閲覧 | いいえ |
+| `--page` | リモートリストのページ番号 | 1 |
+
+## search
+
+スキル広場でスキルを検索します。
+
+<CodeGroup>
+```text チャット
+/skill search pptx
+```
+
+```bash ターミナル
+cow skill search pptx
+```
+</CodeGroup>
+
+## install
+
+統一された `install` コマンドで、Cow スキル広場、GitHub、ClawHub、任意の URL（zip アーカイブ、SKILL.md リンク）からスキルをワンクリックでインストールできます。手動ダウンロードや設定は不要です。
+
+**スキル広場からインストール（推奨）：**
+
+<CodeGroup>
+```text チャット
+/skill install pptx
+```
+
+```bash ターミナル
+cow skill install pptx
+```
+</CodeGroup>
+
+**GitHub からインストール：**
+
+<CodeGroup>
+```text チャット
+# リポジトリ内のすべてのスキルをインストール（SKILL.md を含むサブディレクトリを自動検出）
+/skill install larksuite/cli
+
+# サブディレクトリを指定して単一スキルをインストール
+/skill install https://github.com/larksuite/cli/tree/main/skills/lark-im
+
+# # でサブディレクトリを指定
+/skill install larksuite/cli#skills/lark-minutes
+```
+
+```bash ターミナル
+# リポジトリ内のすべてのスキルをインストール（SKILL.md を含むサブディレクトリを自動検出）
+cow skill install larksuite/cli
+
+# サブディレクトリを指定して単一スキルをインストール
+cow skill install https://github.com/larksuite/cli/tree/main/skills/lark-im
+
+# # でサブディレクトリを指定
+cow skill install larksuite/cli#skills/lark-minutes
+```
+</CodeGroup>
+
+完全な GitHub URL と `owner/repo` 省略形に対応しています。モノリポ（1つのリポジトリに複数のスキル）の場合、サブディレクトリを省略するとすべてのスキルを自動検出して一括インストールします。サブディレクトリを指定した場合は、そのスキルのみをインストールします。
+
+**ClawHub からインストール：**
+
+<CodeGroup>
+```text チャット
+/skill install clawhub:baidu-search
+```
+
+```bash ターミナル
+cow skill install clawhub:baidu-search
+```
+</CodeGroup>
+
+**URL からインストール：**
+
+<CodeGroup>
+```text チャット
+# zip アーカイブからインストール（単一またはバッチ）
+/skill install https://cdn.link-ai.tech/skills/pptx.zip
+
+# SKILL.md リンクからインストール
+/skill install https://example.com/path/to/SKILL.md
+```
+
+```bash ターミナル
+# zip アーカイブからインストール（単一またはバッチ）
+cow skill install https://cdn.link-ai.tech/skills/pptx.zip
+
+# SKILL.md リンクからインストール
+cow skill install https://example.com/path/to/SKILL.md
+```
+</CodeGroup>
+
+zip / tar.gz アーカイブ URL からのインストールに対応しており、自動的に解凍して `SKILL.md` を含むディレクトリを検出し、単一またはバッチインストールをサポートします。`SKILL.md` ファイルの URL から直接インストールすることもでき、スキル名と説明を自動的に解析します。
+
+## uninstall
+
+インストール済みスキルをアンインストールします。
+
+<CodeGroup>
+```text チャット
+/skill uninstall pptx
+```
+
+```bash ターミナル
+cow skill uninstall pptx
+```
+</CodeGroup>
+
+<Warning>
+  アンインストールするとスキルディレクトリ内のすべてのファイルが削除されます。この操作は元に戻せません。
+</Warning>
+
+## enable / disable
+
+スキルの有効化・無効化を行います。無効化されたスキルは Agent から呼び出されません。
+
+<CodeGroup>
+```text チャット
+/skill enable pptx
+/skill disable pptx
+```
+
+```bash ターミナル
+cow skill enable pptx
+cow skill disable pptx
+```
+</CodeGroup>
+
+## info
+
+インストール済みスキルの詳細情報を表示します。`SKILL.md` のプレビューを含みます。
+
+<CodeGroup>
+```text チャット
+/skill info pptx
+```
+
+```bash ターミナル
+cow skill info pptx
+```
+</CodeGroup>
+
+## スキルのソース
+
+インストールされたスキルはソース情報を記録しており、`/skill list` で確認できます：
+
+| ソース | 説明 |
+| --- | --- |
+| `builtin` | プロジェクト内蔵スキル |
+| `cowhub` | CowAgent Skill Hub からインストール |
+| `github` | GitHub URL から直接インストール |
+| `clawhub` | ClawHub からインストール |
+| `url` | SKILL.md URL からインストール |
+| `local` | ローカルで作成されたスキル |

docs/ja/guide/manual-install.mdx

@@ -30,7 +30,25 @@ pip3 install -r requirements.txt
 pip3 install -r requirements-optional.txt
 ```
 
-### 3. 設定
+### 3. Cow CLI をインストール
+
+サービスとスキルを管理するためのコマンドラインツールをインストールします：
+
+```bash
+pip3 install -e .
+```
+
+インストール後、`cow` コマンドが使用可能になります：
+
+```bash
+cow help
+```
+
+<Note>
+  このステップは推奨です。インストール後、`cow start`、`cow stop`、`cow update` でサービスを管理でき、`cow skill` でスキルを管理できます。CLI をインストールしない場合は、`./run.sh` または `python3 app.py` で実行できます。
+</Note>
+
+### 4. 設定
 
 設定テンプレートをコピーして編集します：
 
@@ -40,22 +58,32 @@ cp config-template.json config.json
 
 `config.json` にモデルの API キー、チャネルタイプ、その他の設定を入力します。詳細は[モデルのドキュメント](/ja/models/index)を参照してください。
 
-### 4. 実行
+### 5. 実行
 
-**ローカルで実行：**
+**Cow CLI を使用して実行（推奨）：**
+
+```bash
+cow start
+```
+
+**またはローカルでフォアグラウンド実行：**
 
 ```bash
 python3 app.py
 ```
 
-デフォルトではWebサービスが起動します。`http://localhost:9899/chat` にアクセスしてチャットできます。
+デフォルトでは Web コンソールが起動します。`http://localhost:9899` にアクセスしてチャットできます。
 
-**サーバーでバックグラウンド実行：**
+**サーバーでバックグラウンド実行（CLI 未使用時）：**
 
 ```bash
 nohup python3 app.py & tail -f nohup.out
 ```
 
+<Tip>
+  サーバーにデプロイする場合は、ファイアウォールまたはセキュリティグループでポート `9899` を開放して Web コンソールにアクセスできるようにしてください。セキュリティのため、特定の IP のみにアクセスを制限することを推奨します。
+</Tip>
+
 ## Docker によるデプロイ
 
 Docker デプロイでは、ソースコードのクローンや依存パッケージのインストールは不要です。Agent モードを使用する場合は、より広範なシステムアクセスが可能なソースコードによるデプロイを推奨します。
@@ -84,6 +112,10 @@ sudo docker compose up -d
 sudo docker logs -f chatgpt-on-wechat
 ```
 
+<Tip>
+  サーバーにデプロイする場合は、ファイアウォールまたはセキュリティグループでポート `9899` を開放して Web コンソールにアクセスできるようにしてください。セキュリティのため、特定の IP のみにアクセスを制限することを推奨します。
+</Tip>
+
 ## 主要な設定項目
 
 ```json

docs/ja/guide/quick-start.mdx

@@ -9,31 +9,46 @@ Linux、macOS、Windowsに対応しています。Python 3.7〜3.12が必要で
 
 ## インストールコマンド
 
-```bash
-bash <(curl -fsSL 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>
 
 スクリプトは以下の手順を自動的に実行します：
 
 1. Python環境の確認（Python 3.7以上が必要）
 2. 必要なツールのインストール（git、curlなど）
 3. プロジェクトを `~/chatgpt-on-wechat` にクローン
-4. Pythonの依存パッケージをインストール
+4. Pythonの依存パッケージと Cow CLI をインストール
 5. AIモデルとチャネルの対話式設定
 6. サービスの起動
 
-デフォルトでは、インストール後にWebサービスが起動します。`http://localhost:9899/chat` にアクセスしてチャットを開始できます。
+デフォルトでは、インストール後に Web コンソールが起動します。`http://localhost:9899` にアクセスしてチャットを開始できます。
 
 ## 管理コマンド
 
-インストール後、以下のコマンドでサービスを管理できます：
+インストール後、`cow` コマンドでサービスを管理できます：
 
 | コマンド | 説明 |
 | --- | --- |
-| `./run.sh start` | サービスを起動 |
-| `./run.sh stop` | サービスを停止 |
-| `./run.sh restart` | サービスを再起動 |
-| `./run.sh status` | 実行状態を確認 |
-| `./run.sh logs` | リアルタイムログを表示 |
-| `./run.sh config` | 再設定 |
-| `./run.sh update` | プロジェクトコードを更新 |
+| `cow start` | サービスを起動 |
+| `cow stop` | サービスを停止 |
+| `cow restart` | サービスを再起動 |
+| `cow status` | 実行状態を確認 |
+| `cow logs` | リアルタイムログを表示 |
+| `cow update` | コードを更新して再起動 |
+| `cow install-browser` | ブラウザツールの依存をインストール |
+
+詳細は[コマンドドキュメント](/ja/cli/index)を参照してください。
+
+<Note>
+  `cow` コマンドが利用できない場合は、`./run.sh <コマンド>`（Linux/macOS）または `.\scripts\run.ps1 <コマンド>`（Windows）で代替できます。機能は同等です。
+</Note>

docs/ja/guide/upgrade.mdx

@@ -3,20 +3,25 @@ title: アップデート
 description: CowAgent のアップグレード方法
 ---
 
-## スクリプトによるアップグレード（推奨）
+## コマンドによるアップグレード（推奨）
 
-`run.sh` でサービスを管理している場合、以下のコマンドでワンクリックアップグレードできます：
+`cow update` でコードの更新とサービスの再起動をワンクリックで実行できます：
 
 ```bash
-./run.sh update
+cow update
 ```
 
 このコマンドは以下のフローを自動的に実行します：
 
-1. 現在実行中のサービスを停止
-2. 最新コードをプル
-3. 依存関係を再チェック
-4. サービスを起動
+1. 最新コードをプル（`git pull`）
+2. 現在のサービスを停止
+3. Python 依存パッケージを更新
+4. CLI を再インストール
+5. サービスを起動
+
+<Note>
+  Cow CLI がインストールされていない場合は、`./run.sh update` でも同様の操作が可能です。
+</Note>
 
 ## 手動アップグレード
 
@@ -25,15 +30,19 @@ description: CowAgent のアップグレード方法
 ```bash
 git pull
 pip3 install -r requirements.txt
+pip3 install -e .
 ```
 
 更新完了後、サービスを再起動します：
 
 ```bash
-# run.sh で管理している場合
+# Cow CLI を使用
+cow restart
+
+# または run.sh を使用
 ./run.sh restart
 
-# nohup で直接実行している場合
+# または nohup で直接実行
 kill $(ps -ef | grep app.py | grep -v grep | awk '{print $2}')
 nohup python3 app.py & tail -f nohup.out
 ```

docs/ja/intro/architecture.mdx

@@ -11,14 +11,16 @@ CowAgent のアーキテクチャは以下のコアモジュールで構成さ
 
 <img src="https://cdn.link-ai.tech/doc/68ef7b212c6f791e0e74314b912149f9-sz_5847990.png" alt="CowAgent Architecture" />
 
-### コアモジュール
-
 | モジュール | 説明 |
 | --- | --- |
-| **Channels** | メッセージの受信と送信を行うメッセージチャネル層。Web、Feishu（飛書）、DingTalk（釘釘）、WeCom（企業微信）、WeChat公式アカウントなどをサポート |
-| **Agent Core** | タスク計画、記憶システム、Skill エンジンを含む Agent エンジン |
-| **Tools** | Agent が OS リソースにアクセスするためのツール層。10 以上の組み込みツール |
-| **Models** | 主要な LLM への統一アクセスを提供するモデル層 |
+| **Plan** | ユーザーの意図を理解し、複雑なタスクをマルチステップの計画に分解、目標達成までツールを反復的に呼び出す |
+| **Memory** | 重要な情報をコアメモリとデイリーメモリとして自動永続化し、キーワードとベクトルのハイブリッド検索でセッション間の連続性を実現 |
+| **Knowledge** | トピック別に構造化された知識を整理。Agent が価値ある情報を Markdown ページとして自律的に整理し、インデックスと相互参照で成長するナレッジネットワークを構築 |
+| **Tools** | Agent が OS リソースにアクセスするための中核能力。ファイル読み書き、ターミナル、ブラウザ、スケジューラ、記憶検索、Web 検索など 10 以上の組み込みツール |
+| **Skills** | Skill の読み込み・管理。Skill Hub や GitHub からのワンクリックインストール、または会話を通じたカスタム Skill の作成をサポート |
+| **Models** | モデル層。OpenAI、Claude、Gemini、DeepSeek、MiniMax、GLM、Qwen など主要 LLM への統一アクセスを提供 |
+| **Channels** | メッセージチャネル層。Web コンソール、WeChat、Feishu、DingTalk、WeCom、公式アカウントなど複数チャネルを統一プロトコルでサポート |
+| **CLI** | コマンドラインシステム。ターミナルコマンド（`cow`）とチャットコマンド（`/`）で、プロセス管理、Skill インストール、設定変更、ナレッジベース管理などをサポート |
 
 ## Agent モードのワークフロー
 
@@ -28,7 +30,7 @@ Agent モードが有効な場合、CowAgent は以下のワークフローで
 2. **意図の理解** — タスク要件とコンテキストを分析
 3. **タスク計画** — 複雑なタスクを複数のステップに分解
 4. **ツール呼び出し** — 各ステップに適切なツールを選択・実行
-5. **記憶の更新** — 重要な情報を長期記憶に保存
+5. **記憶・ナレッジの更新** — 重要な情報を長期記憶に保存し、構造化された知識をナレッジベースに整理
 6. **結果の返却** — 実行結果をユーザーに送信
 
 ## ワークスペースのディレクトリ構成
@@ -39,9 +41,12 @@ Agent のワークスペースはデフォルトで `~/cow` にあり、シス
 ~/cow/
 ├── system.md          # Agent システムプロンプト
 ├── user.md            # ユーザープロフィール
+├── MEMORY.md          # コアメモリ
 ├── memory/            # 長期記憶ストレージ
-│   ├── core.md        # コアメモリ
-│   └── daily/         # デイリーメモリ
+│   └── YYYY-MM-DD.md  # デイリーメモリ
+├── knowledge/         # パーソナルナレッジベース
+│   ├── index.md       # ナレッジインデックス
+│   └── <category>/    # トピック別ページ
 └── skills/            # カスタム Skill
     ├── skill-1/
     └── skill-2/
@@ -75,3 +80,4 @@ Agent のワークスペースはデフォルトで `~/cow` にあり、シス
 | `agent_max_context_tokens` | 最大コンテキストトークン数 | `40000` |
 | `agent_max_context_turns` | 最大コンテキストターン数 | `30` |
 | `agent_max_steps` | タスクあたりの最大判断ステップ数 | `15` |
+| `knowledge` | パーソナルナレッジベースの有効化 | `true` |

docs/ja/intro/features.mdx

@@ -1,6 +1,6 @@
 ---
 title: 機能詳細
-description: CowAgent の長期記憶、タスク計画、Skill システムの詳細
+description: CowAgent の長期記憶、タスク計画、Skill システム、CLI コマンド、ブラウザツールの詳細
 ---
 
 ## 1. 長期記憶
@@ -15,13 +15,26 @@ description: CowAgent の長期記憶、タスク計画、Skill システムの
   <img src="https://cdn.link-ai.tech/doc/20260203000455.png" width="800" />
 </Frame>
 
-## 2. タスク計画とツール活用
+## 2. パーソナルナレッジベース
+
+> ナレッジベースシステムにより、Agent は構造化された知識を継続的に蓄積・整理できます。時系列で記録されるメモリとは異なり、ナレッジベースはトピック別に整理され、記事、会話からの洞察、学習資料などを相互にリンクされた Markdown ページとして整理し、継続的に成長するナレッジネットワークを形成します。
+
+Agent は会話中に価値ある情報を自動的にナレッジページとして整理し、相互参照とインデックスを維持します。Web コンソールではドキュメントの閲覧とナレッジグラフの可視化が可能です。ナレッジはワークスペースの `~/cow/knowledge/` ディレクトリに保存されます。
+
+- **自動整理**：Agent が会話中に構造化された知識を自律的に抽出・整理し、インデックスと相互参照を維持
+- **ナレッジグラフ**：ページ間の相互参照から自動的にナレッジグラフを構築し、Web コンソールでインタラクティブな関係図として可視化
+- **チャット連携**：Agent の回答で参照されるナレッジドキュメントのリンクを Web コンソールで直接クリックして閲覧可能
+- **CLI 管理**：`/knowledge` コマンドで統計表示、ディレクトリ閲覧、`/knowledge on|off` で機能の切り替えが可能
+
+詳細は [パーソナルナレッジベース](/ja/knowledge) を参照してください。
+
+## 3. タスク計画とツール活用
 
 ツールは Agent がオペレーティングシステムのリソースにアクセスするための中核です。Agent はタスク要件に基づいてインテリジェントにツールを選択・呼び出し、ファイルの読み書き、コマンド実行、スケジュールタスクなどを実行します。組み込みツールはプロジェクトの `agent/tools/` ディレクトリに実装されています。
 
-**主なツール：** ファイルの読み書き・編集、Bash ターミナル、ファイル送信、スケジューラ、記憶検索、Web 検索、環境設定など。
+**主なツール：** ファイルの読み書き・編集、Bash ターミナル、ブラウザ操作、ファイル送信、スケジューラ、記憶検索、Web 検索、環境設定など。
 
-### 2.1 ターミナルとファイルアクセス
+### 3.1 ターミナルとファイルアクセス
 
 OS のターミナルとファイルシステムへのアクセスは、最も基本的かつ中核的な機能です。多くの他のツールや Skill はこの機能の上に構築されています。ユーザーはモバイルデバイスから Agent とやり取りし、パソコンやサーバーのリソースを操作できます：
 
@@ -29,7 +42,7 @@ OS のターミナルとファイルシステムへのアクセスは、最も
   <img src="https://cdn.link-ai.tech/doc/20260202181130.png" width="800" />
 </Frame>
 
-### 2.2 プログラミング能力
+### 3.2 プログラミング能力
 
 プログラミングとシステムアクセスを組み合わせることで、Agent は完全な **Vibecoding ワークフロー** を実行できます。情報検索、アセット生成、コーディング、テスト、デプロイ、Nginx 設定、公開まで、すべてスマートフォンからの一つのコマンドで実行可能です：
 
@@ -37,7 +50,7 @@ OS のターミナルとファイルシステムへのアクセスは、最も
   <img src="https://cdn.link-ai.tech/doc/20260203121008.png" width="800" />
 </Frame>
 
-### 2.3 スケジュールタスク
+### 3.3 スケジュールタスク
 
 `scheduler` ツールにより動的なスケジュールタスクが可能で、**ワンタイムタスク、固定間隔、Cron 式**をサポートしています。タスクは**固定メッセージ送信**または **Agent 動的タスク**実行としてトリガーできます：
 
@@ -45,7 +58,15 @@ OS のターミナルとファイルシステムへのアクセスは、最も
   <img src="https://cdn.link-ai.tech/doc/20260202195402.png" width="800" />
 </Frame>
 
-### 2.4 環境変数管理
+### 3.4 ブラウザ操作
+
+組み込みの `browser` ツールにより、Agent は Chromium ブラウザを制御して Web ページへのアクセス、フォームの入力、要素のクリック、スクリーンショットの撮影が可能です。動的 JS レンダリングページにも対応しています。`cow install-browser` でワンコマンドインストール、サーバー（ヘッドレス）とデスクトップ環境に自動対応します：
+
+<Frame>
+  <img src="https://cdn.link-ai.tech/doc/20260401110103.png" width="800" />
+</Frame>
+
+### 3.5 環境変数管理
 
 Skill が必要とするシークレットキーは環境変数ファイルに保存され、`env_config` ツールによって管理されます。会話を通じてシークレットを更新でき、セキュリティ保護とマスキング機能が組み込まれています：
 
@@ -53,14 +74,17 @@ Skill が必要とするシークレットキーは環境変数ファイルに
   <img src="https://cdn.link-ai.tech/doc/20260202234939.png" width="800" />
 </Frame>
 
-## 3. Skill システム
+## 4. Skill システム
 
 Skill システムは Agent に無限の拡張性を提供します。各 Skill は説明ファイル、実行スクリプト（任意）、リソース（任意）で構成され、特定のタイプのタスクを完了する方法を記述します。Skill により Agent は複雑なワークフローの指示に従い、ツールを呼び出し、サードパーティシステムと連携できます。
 
+- **[Skill Hub](https://skills.cowagent.ai/)：** オープンな Skill マーケットプレイス。公式推奨、コミュニティ、サードパーティの Skill を収録。ワンコマンドでインストール可能。
 - **組み込み Skill：** プロジェクトの `skills/` ディレクトリにあり、Skill クリエイター、画像認識、LinkAI Agent、Web フェッチなどが含まれます。組み込み Skill は依存条件（API キー、システムコマンドなど）に基づいて自動的に有効化されます。
 - **カスタム Skill：** ユーザーが会話を通じて作成し、ワークスペース（`~/cow/skills/`）に保存されます。あらゆる複雑なビジネスプロセスやサードパーティ連携を実装できます。
 
-### 3.1 Skill の作成
+Skill のインストール：`/skill install <名前>` または `cow skill install <名前>`。Skill Hub、GitHub、ClawHub、URL などからインストール可能。
+
+### 4.1 Skill の作成
 
 `skill-creator` Skill により、会話を通じて Skill を素早く作成できます。ワークフローを Skill としてコード化するよう Agent に依頼したり、API ドキュメントやサンプルを送信して Agent に直接連携を完成させることができます：
 
@@ -68,7 +92,7 @@ Skill システムは Agent に無限の拡張性を提供します。各 Skill
   <img src="https://cdn.link-ai.tech/doc/20260202202247.png" width="800" />
 </Frame>
 
-### 3.2 Web 検索と画像認識
+### 4.2 Web 検索と画像認識
 
 - **Web 検索：** 組み込みの `web_search` ツールで、複数の検索エンジンをサポートします。`BOCHA_API_KEY` または `LINKAI_API_KEY` を設定して有効化してください。
 - **画像認識：** 組み込みの `openai-image-vision` Skill で、`gpt-4.1-mini`、`gpt-4.1` などのモデルをサポートします。`OPENAI_API_KEY` が必要です。
@@ -77,29 +101,33 @@ Skill システムは Agent に無限の拡張性を提供します。各 Skill
   <img src="https://cdn.link-ai.tech/doc/20260202213219.png" width="800" />
 </Frame>
 
-### 3.3 サードパーティナレッジベースとプラグイン
+### 4.3 Skill Hub
 
-`linkai-agent` Skill により、[LinkAI](https://link-ai.tech/) 上のすべての Agent を Skill として利用でき、マルチ Agent による意思決定が可能になります。
+[skills.cowagent.ai](https://skills.cowagent.ai/) で利用可能なすべての Skill を閲覧するか、会話内でコマンドを実行できます：
 
-設定方法：`env_config` で `LINKAI_API_KEY` を設定し、`skills/linkai-agent/config.json` に Agent の説明を追加します：
-
-```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          # Skill Hub を閲覧
+/skill search <キーワード>     # Skill を検索
+/skill install <名前>          # ワンコマンドでインストール
 ```
 
-<Frame>
-  <img src="https://cdn.link-ai.tech/doc/20260202234350.png" width="750" />
-</Frame>
+GitHub、ClawHub、LinkAI などサードパーティプラットフォームの Skill もインストール可能です。詳細は [Skill のインストール](/ja/skills/install) を参照してください。
+
+<img src="https://cdn.link-ai.tech/doc/20260401110103.png" width="750" />
+
+## 5. CLI コマンドシステム
+
+CowAgent はサービス管理、Skill インストール、設定変更などをカバーする2つのコマンドインターフェースを提供します：
+
+- **ターミナル CLI：** システムターミナルで `cow <コマンド>` を実行。`start`、`stop`、`restart`、`update`、`status`、`logs`、`skill` などをサポート。
+- **チャットコマンド：** 会話内で `/<コマンド>` を入力。Web コンソールでは `/` を入力するとコマンドメニューが表示されます。
+
+```bash
+cow start              # サービスを開始
+cow stop               # サービスを停止
+cow update             # 更新して再起動
+cow skill install pptx # Skill をインストール
+cow install-browser    # ブラウザツールをインストール
+```
+
+詳細は [コマンド一覧](https://docs.cowagent.ai/ja/cli) を参照してください。

docs/ja/intro/index.mdx

@@ -22,12 +22,21 @@ CowAgent は自ら思考しタスクを計画し、コンピュータや外部
   <Card title="長期記憶" icon="database" href="/ja/memory">
     会話の記憶をローカルファイルやデータベースに自動的に永続化します。コアメモリとデイリーメモリを含み、キーワード検索とベクトル検索に対応しています。
   </Card>
+  <Card title="ナレッジベース" icon="book" href="/ja/knowledge">
+    構造化された知識を自動整理し、ナレッジグラフの可視化をサポート。相互参照により継続的に成長するナレッジネットワークを構築します。
+  </Card>
   <Card title="Skill システム" icon="puzzle-piece" href="/ja/skills/index">
     Skill の作成・実行エンジンを実装し、組み込み Skill を搭載。自然言語の会話を通じてカスタム Skill の開発もサポートしています。
   </Card>
   <Card title="マルチモーダルメッセージ" icon="image" href="/ja/channels/web">
     テキスト、画像、音声、ファイルなどのメッセージタイプの解析、処理、生成、送信をサポートします。
   </Card>
+  <Card title="ツールシステム" icon="wrench" href="/ja/tools/index">
+    ファイル読み書き、ターミナル実行、ブラウザ操作、スケジュールタスク、メッセージ送信などの組み込みツールを提供。Agent が自律的にツールを呼び出して複雑なタスクを完了します。
+  </Card>
+  <Card title="コマンドシステム" icon="terminal" href="/ja/cli/index">
+    ターミナル CLI とチャット内コマンドを提供し、プロセス管理、Skill インストール、設定変更、コンテキスト確認などの一般的な操作をサポートします。
+  </Card>
   <Card title="複数モデル対応" icon="microchip" href="/ja/models/index">
     OpenAI、Claude、Gemini、DeepSeek、MiniMax、GLM、Qwen、Kimi、Doubao など、主要なモデルプロバイダーをサポートしています。
   </Card>
@@ -40,9 +49,18 @@ CowAgent は自ら思考しタスクを計画し、コンピュータや外部
 
 ターミナルで以下のコマンドを実行すると、ワンクリックでインストール、設定、起動ができます：
 
-```bash
-bash <(curl -fsSL 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>
 
 デフォルトでは実行後に Web サービスが起動します。`http://localhost:9899/chat` にアクセスして Web インターフェースでチャットできます。
 

docs/ja/knowledge/index.mdx

@@ -0,0 +1,77 @@
+---
+title: パーソナルナレッジベース
+description: CowAgent のパーソナルナレッジベース — 構造化された知識の蓄積、自動整理、ナレッジグラフ
+---
+
+パーソナルナレッジベースは、Agent の長期的な構造化知識ストレージで、ワークスペースの `knowledge/` ディレクトリに保存されます。タイムラインで整理されるメモリとは異なり、ナレッジベースはトピック別にコンテンツを整理します。記事、会話のインサイト、学習資料が相互リンクされた Markdown ページとして構造化され、継続的に成長するナレッジネットワークを形成します。
+
+## コアコンセプト
+
+### ナレッジ vs メモリ
+
+| 次元 | ナレッジベース（knowledge/） | 長期記憶（memory/） |
+| --- | --- | --- |
+| 整理方法 | トピック別、相互リンク | タイムライン順、日付ファイル |
+| 書き込み | Agent が能動的に構造化 | コンテキストトリミング時に自動要約 |
+| コンテンツ | 精製された構造化知識 | 生の会話要約 |
+| 用途 | 学習ノート、技術ドキュメント、プロジェクト知識 | 会話履歴、イベント記録 |
+
+### ディレクトリ構造
+
+```
+~/cow/knowledge/
+├── index.md          # ナレッジインデックス、全ページのエントリポイント
+├── log.md            # 変更ログ、各書き込みの記録
+├── concepts/         # 概念的な知識
+│   └── machine-learning.md
+├── entities/         # エンティティ知識（人物、組織、ツール）
+│   └── openai.md
+└── sources/          # ソース知識（記事、論文）
+    └── llm-wiki.md
+```
+
+ディレクトリ構造は柔軟です — Agent は実際のコンテンツに基づいて適切なカテゴリディレクトリを自動作成します。ユーザーが整理方法をカスタマイズすることも可能です。
+
+## 自動整理
+
+ナレッジの書き込みは Agent の自律的な動作で、以下のシナリオでトリガーされます：
+
+- **ユーザーが記事やドキュメントを共有** — Agent が自動的にキー情報を抽出し、構造化されたナレッジページを作成
+- **会話から価値ある結論が生まれた場合** — Agent がインサイトをナレッジページに整理し、既存の知識とリンク
+- **ユーザーが明示的に整理を要求** — ユーザーは会話を通じて Agent にナレッジの整理・更新を指示可能
+
+各ナレッジページには関連ページへの相互参照リンクが含まれ、ナレッジグラフを段階的に構築します。
+
+## ナレッジ検索
+
+Agent は会話中に以下の方法でナレッジを検索できます：
+
+- **インデックス参照** — `knowledge/index.md` で関連ページを素早く特定
+- **セマンティック検索** — `memory_search` ツールでナレッジコンテンツをセマンティック検索
+- **直接読み取り** — `memory_get` ツールで特定のナレッジファイルを読み取り
+
+## Web コンソール
+
+Web コンソールには専用の「ナレッジ」モジュールがあり、以下をサポートします：
+
+- **ドキュメント閲覧** — ツリー形式のディレクトリ構造、検索・折りたたみ可能、クリックでコンテンツ表示
+- **ナレッジグラフ** — D3.js フォースダイレクテッドグラフによるナレッジ間の関係を可視化
+- **チャット連携** — Agent の返信で参照されたナレッジドキュメントリンクはクリックで直接ナビゲーション
+
+## CLI コマンド
+
+`/knowledge` コマンドでナレッジベースを管理：
+
+| コマンド | 説明 |
+| --- | --- |
+| `/knowledge` | ナレッジベースの統計情報を表示 |
+| `/knowledge list` | ファイルディレクトリをツリー形式で表示 |
+| `/knowledge on` | ナレッジベース機能を有効化 |
+| `/knowledge off` | ナレッジベース機能を無効化 |
+
+## 設定
+
+| パラメータ | 説明 | デフォルト |
+| --- | --- | --- |
+| `knowledge` | パーソナルナレッジベースの有効/無効 | `true` |
+| `agent_workspace` | ワークスペースパス、ナレッジは `knowledge/` サブディレクトリに保存されます | `~/cow` |