mirror of
https://github.com/sipeed/picoclaw.git
synced 2026-06-12 18:08:54 +00:00
Merge remote-tracking branch 'origin_picoclaw/main'
This commit is contained in:
@@ -0,0 +1,116 @@
|
||||
# 企业微信智能机器人 (AI Bot)
|
||||
|
||||
企业微信智能机器人(AI Bot)是企业微信官方提供的 AI 对话接入方式,支持私聊与群聊,内置流式响应协议,并支持超时后通过 `response_url` 主动推送最终回复。
|
||||
|
||||
## 与其他 WeCom 通道的对比
|
||||
|
||||
| 特性 | WeCom Bot | WeCom App | **WeCom AI Bot** |
|
||||
|------|-----------|-----------|-----------------|
|
||||
| 私聊 | ✅ | ✅ | ✅ |
|
||||
| 群聊 | ✅ | ❌ | ✅ |
|
||||
| 流式输出 | ❌ | ❌ | ✅ |
|
||||
| 超时主动推送 | ❌ | ✅ | ✅ |
|
||||
| 配置复杂度 | 低 | 高 | 中 |
|
||||
|
||||
## 配置
|
||||
|
||||
```json
|
||||
{
|
||||
"channels": {
|
||||
"wecom_aibot": {
|
||||
"enabled": true,
|
||||
"token": "YOUR_TOKEN",
|
||||
"encoding_aes_key": "YOUR_43_CHAR_ENCODING_AES_KEY",
|
||||
"webhook_path": "/webhook/wecom-aibot",
|
||||
"allow_from": [],
|
||||
"welcome_message": "你好!有什么可以帮助你的吗?",
|
||||
"max_steps": 10
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
| 字段 | 类型 | 必填 | 描述 |
|
||||
| ---------------- | ------ | ---- | -------------------------------------------------- |
|
||||
| token | string | 是 | 回调验证令牌,在 AI Bot 管理页面配置 |
|
||||
| encoding_aes_key | string | 是 | 43 字符 AES 密钥,在 AI Bot 管理页面随机生成 |
|
||||
| webhook_path | string | 否 | Webhook 路径(默认:/webhook/wecom-aibot) |
|
||||
| allow_from | array | 否 | 用户 ID 白名单,空数组表示允许所有用户 |
|
||||
| welcome_message | string | 否 | 用户进入聊天时发送的欢迎语,留空则不发送 |
|
||||
| reply_timeout | int | 否 | 回复超时时间(秒,默认:5) |
|
||||
| max_steps | int | 否 | Agent 最大执行步骤数(默认:10) |
|
||||
|
||||
## 设置流程
|
||||
|
||||
1. 登录 [企业微信管理后台](https://work.weixin.qq.com/wework_admin)
|
||||
2. 进入"应用管理" → "智能机器人",创建或选择一个 AI Bot
|
||||
3. 在 AI Bot 配置页面,填写"消息接收"信息:
|
||||
- **URL**:`http://<your-server-ip>:18791/webhook/wecom-aibot`
|
||||
- **Token**:随机生成或自定义
|
||||
- **EncodingAESKey**:点击"随机生成",得到 43 字符密钥
|
||||
4. 将 Token 和 EncodingAESKey 填入 PicoClaw 配置文件,启动服务后回到管理后台保存(企业微信会发送验证请求)
|
||||
|
||||
> [!TIP]
|
||||
> 服务器需要能被企业微信服务器访问。如在内网/本地开发,可使用 [ngrok](https://ngrok.com) 或 frp 做内网穿透。
|
||||
|
||||
## 流式响应协议
|
||||
|
||||
WeCom AI Bot 使用"流式拉取"协议,区别于普通 Webhook 的一次性回复:
|
||||
|
||||
```
|
||||
用户发消息
|
||||
│
|
||||
▼
|
||||
PicoClaw 立即返回 {finish: false}(Agent 开始处理)
|
||||
│
|
||||
▼
|
||||
企业微信每隔约 1 秒拉取一次 {msgtype: "stream", stream: {id: "..."}}
|
||||
│
|
||||
├─ Agent 未完成 → 返回 {finish: false}(继续等待)
|
||||
│
|
||||
└─ Agent 完成 → 返回 {finish: true, content: "回答内容"}
|
||||
```
|
||||
|
||||
**超时处理**(任务超过 30 秒):
|
||||
|
||||
若 Agent 处理时间超过约 30 秒(企业微信最大轮询窗口为 6 分钟),PicoClaw 会:
|
||||
|
||||
1. 立即关闭流,向用户显示「⏳ 正在处理中,请稍候,结果将稍后发送。」
|
||||
2. Agent 继续在后台运行
|
||||
3. Agent 完成后,通过消息中携带的 `response_url` 将最终回复主动推送给用户
|
||||
|
||||
> `response_url` 由企业微信颁发,有效期 1 小时,只可使用一次,无需加密,直接 POST markdown 消息体即可。
|
||||
|
||||
## 欢迎语
|
||||
|
||||
配置 `welcome_message` 后,当用户打开与 AI Bot 的聊天窗口时(`enter_chat` 事件),PicoClaw 会自动回复该欢迎语。留空则静默忽略。
|
||||
|
||||
```json
|
||||
"welcome_message": "你好!我是 PicoClaw AI 助手,有什么可以帮你?"
|
||||
```
|
||||
|
||||
## 常见问题
|
||||
|
||||
### 回调 URL 验证失败
|
||||
|
||||
- 确认服务器防火墙已开放对应端口(默认 18791)
|
||||
- 确认 `token` 与 `encoding_aes_key` 填写正确
|
||||
- 检查 PicoClaw 日志是否收到了来自企业微信的 GET 请求
|
||||
|
||||
### 消息没有回复
|
||||
|
||||
- 检查 `allow_from` 是否意外限制了发送者
|
||||
- 查看日志中是否出现 `context canceled` 或 Agent 错误
|
||||
- 确认 Agent 配置(`model_name` 等)正确
|
||||
|
||||
### 超长任务没有收到最终推送
|
||||
|
||||
- 确认消息回调中携带了 `response_url`(仅企业微信新版 AI Bot 支持)
|
||||
- 确认服务器能主动访问外网(需向 `response_url` POST 请求)
|
||||
- 查看日志关键词 `response_url mode` 和 `Sending reply via response_url`
|
||||
|
||||
## 参考文档
|
||||
|
||||
- [企业微信 AI Bot 接入文档](https://developer.work.weixin.qq.com/document/path/100719)
|
||||
- [流式响应协议说明](https://developer.work.weixin.qq.com/document/path/100719)
|
||||
- [response_url 主动回复](https://developer.work.weixin.qq.com/document/path/101138)
|
||||
+108
-33
@@ -8,6 +8,7 @@ PicoClaw's tools configuration is located in the `tools` field of `config.json`.
|
||||
{
|
||||
"tools": {
|
||||
"web": { ... },
|
||||
"mcp": { ... },
|
||||
"exec": { ... },
|
||||
"cron": { ... },
|
||||
"skills": { ... }
|
||||
@@ -21,35 +22,35 @@ Web tools are used for web search and fetching.
|
||||
|
||||
### Brave
|
||||
|
||||
| Config | Type | Default | Description |
|
||||
|--------|------|---------|-------------|
|
||||
| `enabled` | bool | false | Enable Brave search |
|
||||
| `api_key` | string | - | Brave Search API key |
|
||||
| `max_results` | int | 5 | Maximum number of results |
|
||||
| Config | Type | Default | Description |
|
||||
| ------------- | ------ | ------- | ------------------------- |
|
||||
| `enabled` | bool | false | Enable Brave search |
|
||||
| `api_key` | string | - | Brave Search API key |
|
||||
| `max_results` | int | 5 | Maximum number of results |
|
||||
|
||||
### DuckDuckGo
|
||||
|
||||
| Config | Type | Default | Description |
|
||||
|--------|------|---------|-------------|
|
||||
| `enabled` | bool | true | Enable DuckDuckGo search |
|
||||
| `max_results` | int | 5 | Maximum number of results |
|
||||
| Config | Type | Default | Description |
|
||||
| ------------- | ---- | ------- | ------------------------- |
|
||||
| `enabled` | bool | true | Enable DuckDuckGo search |
|
||||
| `max_results` | int | 5 | Maximum number of results |
|
||||
|
||||
### Perplexity
|
||||
|
||||
| Config | Type | Default | Description |
|
||||
|--------|------|---------|-------------|
|
||||
| `enabled` | bool | false | Enable Perplexity search |
|
||||
| `api_key` | string | - | Perplexity API key |
|
||||
| `max_results` | int | 5 | Maximum number of results |
|
||||
| Config | Type | Default | Description |
|
||||
| ------------- | ------ | ------- | ------------------------- |
|
||||
| `enabled` | bool | false | Enable Perplexity search |
|
||||
| `api_key` | string | - | Perplexity API key |
|
||||
| `max_results` | int | 5 | Maximum number of results |
|
||||
|
||||
## Exec Tool
|
||||
|
||||
The exec tool is used to execute shell commands.
|
||||
|
||||
| Config | Type | Default | Description |
|
||||
|--------|------|---------|-------------|
|
||||
| `enable_deny_patterns` | bool | true | Enable default dangerous command blocking |
|
||||
| `custom_deny_patterns` | array | [] | Custom deny patterns (regular expressions) |
|
||||
| Config | Type | Default | Description |
|
||||
| ---------------------- | ----- | ------- | ------------------------------------------ |
|
||||
| `enable_deny_patterns` | bool | true | Enable default dangerous command blocking |
|
||||
| `custom_deny_patterns` | array | [] | Custom deny patterns (regular expressions) |
|
||||
|
||||
### Functionality
|
||||
|
||||
@@ -80,10 +81,7 @@ By default, PicoClaw blocks the following dangerous commands:
|
||||
"tools": {
|
||||
"exec": {
|
||||
"enable_deny_patterns": true,
|
||||
"custom_deny_patterns": [
|
||||
"\\brm\\s+-r\\b",
|
||||
"\\bkillall\\s+python"
|
||||
]
|
||||
"custom_deny_patterns": ["\\brm\\s+-r\\b", "\\bkillall\\s+python"]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -93,9 +91,84 @@ By default, PicoClaw blocks the following dangerous commands:
|
||||
|
||||
The cron tool is used for scheduling periodic tasks.
|
||||
|
||||
| Config | Type | Default | Description |
|
||||
|--------|------|---------|-------------|
|
||||
| `exec_timeout_minutes` | int | 5 | Execution timeout in minutes, 0 means no limit |
|
||||
| Config | Type | Default | Description |
|
||||
| ---------------------- | ---- | ------- | ---------------------------------------------- |
|
||||
| `exec_timeout_minutes` | int | 5 | Execution timeout in minutes, 0 means no limit |
|
||||
|
||||
## MCP Tool
|
||||
|
||||
The MCP tool enables integration with external Model Context Protocol servers.
|
||||
|
||||
### Global Config
|
||||
|
||||
| Config | Type | Default | Description |
|
||||
| --------- | ------ | ------- | ----------------------------------- |
|
||||
| `enabled` | bool | false | Enable MCP integration globally |
|
||||
| `servers` | object | `{}` | Map of server name to server config |
|
||||
|
||||
### Per-Server Config
|
||||
|
||||
| Config | Type | Required | Description |
|
||||
| ---------- | ------ | -------- | ------------------------------------------ |
|
||||
| `enabled` | bool | yes | Enable this MCP server |
|
||||
| `type` | string | no | Transport type: `stdio`, `sse`, `http` |
|
||||
| `command` | string | stdio | Executable command for stdio transport |
|
||||
| `args` | array | no | Command arguments for stdio transport |
|
||||
| `env` | object | no | Environment variables for stdio process |
|
||||
| `env_file` | string | no | Path to environment file for stdio process |
|
||||
| `url` | string | sse/http | Endpoint URL for `sse`/`http` transport |
|
||||
| `headers` | object | no | HTTP headers for `sse`/`http` transport |
|
||||
|
||||
### Transport Behavior
|
||||
|
||||
- If `type` is omitted, transport is auto-detected:
|
||||
- `url` is set → `sse`
|
||||
- `command` is set → `stdio`
|
||||
- `http` and `sse` both use `url` + optional `headers`.
|
||||
- `env` and `env_file` are only applied to `stdio` servers.
|
||||
|
||||
### Configuration Examples
|
||||
|
||||
#### 1) Stdio MCP server
|
||||
|
||||
```json
|
||||
{
|
||||
"tools": {
|
||||
"mcp": {
|
||||
"enabled": true,
|
||||
"servers": {
|
||||
"filesystem": {
|
||||
"enabled": true,
|
||||
"command": "npx",
|
||||
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
#### 2) Remote SSE/HTTP MCP server
|
||||
|
||||
```json
|
||||
{
|
||||
"tools": {
|
||||
"mcp": {
|
||||
"enabled": true,
|
||||
"servers": {
|
||||
"remote-mcp": {
|
||||
"enabled": true,
|
||||
"type": "sse",
|
||||
"url": "https://example.com/mcp",
|
||||
"headers": {
|
||||
"Authorization": "Bearer YOUR_TOKEN"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Skills Tool
|
||||
|
||||
@@ -103,13 +176,13 @@ The skills tool configures skill discovery and installation via registries like
|
||||
|
||||
### Registries
|
||||
|
||||
| Config | Type | Default | Description |
|
||||
|--------|------|---------|-------------|
|
||||
| `registries.clawhub.enabled` | bool | true | Enable ClawHub registry |
|
||||
| `registries.clawhub.base_url` | string | `https://clawhub.ai` | ClawHub base URL |
|
||||
| `registries.clawhub.search_path` | string | `/api/v1/search` | Search API path |
|
||||
| `registries.clawhub.skills_path` | string | `/api/v1/skills` | Skills API path |
|
||||
| `registries.clawhub.download_path` | string | `/api/v1/download` | Download API path |
|
||||
| Config | Type | Default | Description |
|
||||
| ---------------------------------- | ------ | -------------------- | ----------------------- |
|
||||
| `registries.clawhub.enabled` | bool | true | Enable ClawHub registry |
|
||||
| `registries.clawhub.base_url` | string | `https://clawhub.ai` | ClawHub base URL |
|
||||
| `registries.clawhub.search_path` | string | `/api/v1/search` | Search API path |
|
||||
| `registries.clawhub.skills_path` | string | `/api/v1/skills` | Skills API path |
|
||||
| `registries.clawhub.download_path` | string | `/api/v1/download` | Download API path |
|
||||
|
||||
### Configuration Example
|
||||
|
||||
@@ -136,8 +209,10 @@ The skills tool configures skill discovery and installation via registries like
|
||||
All configuration options can be overridden via environment variables with the format `PICOCLAW_TOOLS_<SECTION>_<KEY>`:
|
||||
|
||||
For example:
|
||||
|
||||
- `PICOCLAW_TOOLS_WEB_BRAVE_ENABLED=true`
|
||||
- `PICOCLAW_TOOLS_EXEC_ENABLE_DENY_PATTERNS=false`
|
||||
- `PICOCLAW_TOOLS_CRON_EXEC_TIMEOUT_MINUTES=10`
|
||||
- `PICOCLAW_TOOLS_MCP_ENABLED=true`
|
||||
|
||||
Note: Array-type environment variables are not currently supported and must be set via the config file.
|
||||
Note: Nested map-style config (for example `tools.mcp.servers.<name>.*`) is configured in `config.json` rather than environment variables.
|
||||
|
||||
@@ -1,115 +0,0 @@
|
||||
# 企业微信自建应用 (WeCom App) 配置指南
|
||||
|
||||
本文档介绍如何在 PicoClaw 中配置企业微信自建应用 (wecom-app) 通道。
|
||||
|
||||
## 功能特性
|
||||
|
||||
| 功能 | 支持状态 |
|
||||
|------|---------|
|
||||
| 被动接收消息 | ✅ |
|
||||
| 主动发送消息 | ✅ |
|
||||
| 私聊 | ✅ |
|
||||
| 群聊 | ❌ |
|
||||
|
||||
## 配置步骤
|
||||
|
||||
### 1. 企业微信后台配置
|
||||
|
||||
1. 登录 [企业微信管理后台](https://work.weixin.qq.com/wework_admin)
|
||||
2. 进入"应用管理" → 选择自建应用
|
||||
3. 记录以下信息:
|
||||
- **AgentId**: 应用详情页显示
|
||||
- **Secret**: 点击"查看"获取
|
||||
4. 进入"我的企业"页面,记录 **企业ID** (CorpID)
|
||||
|
||||
### 2. 接收消息配置
|
||||
|
||||
1. 在应用详情页,点击"接收消息"的"设置API接收"
|
||||
2. 填写以下信息:
|
||||
- **URL**: `http://your-server:18790/webhook/wecom-app`
|
||||
- **Token**: 随机生成或自定义(用于签名验证)
|
||||
- **EncodingAESKey**: 点击"随机生成"生成43字符的密钥
|
||||
3. 点击"保存"时,企业微信会发送验证请求
|
||||
|
||||
### 3. PicoClaw 配置
|
||||
|
||||
在 `config.json` 中添加以下配置:
|
||||
|
||||
```json
|
||||
{
|
||||
"channels": {
|
||||
"wecom_app": {
|
||||
"enabled": true,
|
||||
"corp_id": "wwxxxxxxxxxxxxxxxx", // 企业ID
|
||||
"corp_secret": "xxxxxxxxxxxxxxxxxxxxxxxx", // 应用Secret
|
||||
"agent_id": 1000002, // 应用AgentId
|
||||
"token": "your_token", // 接收消息配置的Token
|
||||
"encoding_aes_key": "your_encoding_aes_key", // 接收消息配置的EncodingAESKey
|
||||
"webhook_path": "/webhook/wecom-app",
|
||||
"allow_from": [],
|
||||
"reply_timeout": 5
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## 常见问题
|
||||
|
||||
### 1. 回调URL验证失败
|
||||
|
||||
**症状**: 企业微信保存API接收消息时提示验证失败
|
||||
|
||||
**检查项**:
|
||||
- 确认服务器防火墙已开放 Gateway 端口(默认 18790)
|
||||
- 确认 `corp_id`、`token`、`encoding_aes_key` 配置正确
|
||||
- 查看 PicoClaw 日志是否有请求到达
|
||||
|
||||
### 2. 中文消息解密失败
|
||||
|
||||
**症状**: 发送中文消息时出现 `invalid padding size` 错误
|
||||
|
||||
**原因**: 企业微信使用非标准的 PKCS7 填充(32字节块大小)
|
||||
|
||||
**解决**: 确保使用最新版本的 PicoClaw,已修复此问题。
|
||||
|
||||
### 3. 端口冲突
|
||||
|
||||
**症状**: 启动时提示端口已被占用
|
||||
|
||||
**解决**: 修改 `gateway.port` 为其他端口(所有 Webhook 渠道共享同一个 Gateway HTTP 服务器)
|
||||
|
||||
## 技术细节
|
||||
|
||||
### 加密算法
|
||||
|
||||
- **算法**: AES-256-CBC
|
||||
- **密钥**: EncodingAESKey Base64解码后的32字节
|
||||
- **IV**: AESKey的前16字节
|
||||
- **填充**: PKCS7(块大小为32字节,非标准16字节)
|
||||
- **消息格式**: XML
|
||||
|
||||
### 消息结构
|
||||
|
||||
解密后的消息格式:
|
||||
```
|
||||
random(16B) + msg_len(4B) + msg + receiveid
|
||||
```
|
||||
|
||||
其中 `receiveid` 对于自建应用是 `corp_id`。
|
||||
|
||||
## 调试
|
||||
|
||||
启用调试模式查看详细日志:
|
||||
|
||||
```bash
|
||||
picoclaw gateway --debug
|
||||
```
|
||||
|
||||
关键日志标识:
|
||||
- `wecom_app`: WeCom App 通道相关日志
|
||||
- `wecom_common`: 加密解密相关日志
|
||||
|
||||
## 参考文档
|
||||
|
||||
- [企业微信官方文档 - 接收消息](https://developer.work.weixin.qq.com/document/path/96211)
|
||||
- [企业微信官方加解密库](https://github.com/sbzhu/weworkapi_golang)
|
||||
Reference in New Issue
Block a user