Merge pull request #893 from reevoid/rui-dev

Add WeCom AIBot channel implementation and tests

README.fr.md

@@ -288,7 +288,7 @@ Discutez avec votre PicoClaw via Telegram, Discord, DingTalk, LINE ou WeCom
 | **QQ**       | Facile (AppID + AppSecret)             |
 | **DingTalk** | Moyen (identifiants de l'application)  |
 | **LINE**     | Moyen (identifiants + URL de webhook)  |
-| **WeCom**    | Moyen (CorpID + configuration webhook) |
+| **WeCom AI Bot** | Moyen (Token + clé AES)            |
 
 <details>
 <summary><b>Telegram</b> (Recommandé)</summary>
@@ -491,12 +491,13 @@ picoclaw gateway
 <details>
 <summary><b>WeCom (WeChat Work)</b></summary>
 
-PicoClaw prend en charge deux types d'intégration WeCom :
+PicoClaw prend en charge trois types d'intégration WeCom :
 
-**Option 1 : WeCom Bot (Robot Intelligent)** - Configuration plus facile, prend en charge les discussions de groupe
-**Option 2 : WeCom App (Application Personnalisée)** - Plus de fonctionnalités, messagerie proactive
+**Option 1 : WeCom Bot (Robot)** - Configuration plus facile, prend en charge les discussions de groupe
+**Option 2 : WeCom App (Application Personnalisée)** - Plus de fonctionnalités, messagerie proactive, chat privé uniquement
+**Option 3 : WeCom AI Bot (Bot Intelligent)** - Bot IA officiel, réponses en streaming, prend en charge groupe et privé
 
-Voir le [Guide de Configuration WeCom App](docs/wecom-app-configuration.md) pour des instructions détaillées.
+Voir le [Guide de Configuration WeCom AI Bot](docs/channels/wecom/wecom_aibot/README.zh.md) pour des instructions détaillées.
 
 **Configuration Rapide - WeCom Bot :**
 
@@ -563,6 +564,39 @@ picoclaw gateway
 
 > **Note** : Les callbacks webhook WeCom App sont servis par le serveur Gateway partagé (par défaut `127.0.0.1:18790`). Assurez-vous que le port `18790` est accessible ou utilisez un proxy inverse HTTPS en production.
 
+**Configuration Rapide - WeCom AI Bot :**
+
+**1. Créer un AI Bot**
+
+* Accédez à la Console d'Administration WeCom → Gestion des Applications → AI Bot
+* Configurez l'URL de callback : `http://your-server:18791/webhook/wecom-aibot`
+* Copiez le **Token** et générez l'**EncodingAESKey**
+
+**2. Configurer**
+
+```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": "Bonjour ! Comment puis-je vous aider ?"
+    }
+  }
+}
+```
+
+**3. Lancer**
+
+```bash
+picoclaw gateway
+```
+
+> **Note** : WeCom AI Bot utilise le protocole pull en streaming — pas de problème de timeout. Les tâches longues (>5,5 min) basculent automatiquement vers la livraison via `response_url`.
+
 </details>
 
 ## <img src="assets/clawdchat-icon.png" width="24" height="24" alt="ClawdChat"> Rejoignez le Réseau Social d'Agents

README.ja.md

@@ -257,7 +257,7 @@ Telegram、Discord、QQ、DingTalk、LINE、WeCom で PicoClaw と会話でき
 | **QQ** | 簡単（AppID + AppSecret） |
 | **DingTalk** | 普通（アプリ認証情報） |
 | **LINE** | 普通（認証情報 + Webhook URL） |
-| **WeCom** | 普通（CorpID + Webhook設定） |
+| **WeCom AI Bot** | 普通（Token + AES キー） |
 
 <details>
 <summary><b>Telegram</b>（推奨）</summary>
@@ -456,12 +456,13 @@ picoclaw gateway
 <details>
 <summary><b>WeCom (企業微信)</b></summary>
 
-PicoClaw は2種類の WeCom 統合をサポートしています：
+PicoClaw は3種類の WeCom 統合をサポートしています：
 
-**オプション1: WeCom Bot (智能ロボット)** - 簡単な設定、グループチャット対応
-**オプション2: WeCom App (自作アプリ)** - より多機能、アクティブメッセージング対応
+**オプション1: WeCom Bot (ロボット)** - 簡単な設定、グループチャット対応
+**オプション2: WeCom App (カスタムアプリ)** - より多機能、アクティブメッセージング対応、プライベートチャットのみ
+**オプション3: WeCom AI Bot (スマートボット)** - 公式 AI Bot、ストリーミング返信、グループ・プライベート両対応
 
-詳細な設定手順は [WeCom App Configuration Guide](docs/wecom-app-configuration.md) を参照してください。
+詳細な設定手順は [WeCom AI Bot Configuration Guide](docs/channels/wecom/wecom_aibot/README.zh.md) を参照してください。
 
 **クイックセットアップ - WeCom Bot:**
 
@@ -530,6 +531,39 @@ picoclaw gateway
 
 > **注意**: WeCom App の Webhook コールバックは共有の Gateway HTTP サーバー（デフォルト: `127.0.0.1:18790`）で提供されます。ホストからアクセスする場合は HTTPS 用のリバースプロキシを設定してください。
 
+**クイックセットアップ - WeCom AI Bot:**
+
+**1. AI Bot を作成**
+
+* WeCom 管理コンソール → アプリ管理 → AI Bot
+* コールバック URL を設定: `http://your-server:18791/webhook/wecom-aibot`
+* **Token** をコピーし、**EncodingAESKey** を生成
+
+**2. 設定**
+
+```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": "こんにちは！何かお手伝いできますか？"
+    }
+  }
+}
+```
+
+**3. 起動**
+
+```bash
+picoclaw gateway
+```
+
+> **注意**: WeCom AI Bot はストリーミングプルプロトコルを使用 — 返信タイムアウトの心配なし。長時間タスク（>30秒）は自動的に `response_url` によるプッシュ配信に切り替わります。
+
 </details>
 
 ## ⚙️ 設定

README.md

@@ -305,7 +305,7 @@ Talk to your picoclaw through Telegram, Discord, WhatsApp, DingTalk, LINE, or We
 | **QQ**       | Easy (AppID + AppSecret)           |
 | **DingTalk** | Medium (app credentials)           |
 | **LINE**     | Medium (credentials + webhook URL) |
-| **WeCom**    | Medium (CorpID + webhook setup)    |
+| **WeCom AI Bot** | Medium (Token + AES key)       |
 
 <details>
 <summary><b>Telegram</b> (Recommended)</summary>
@@ -557,12 +557,13 @@ picoclaw gateway
 <details>
 <summary><b>WeCom (企业微信)</b></summary>
 
-PicoClaw supports two types of WeCom integration:
+PicoClaw supports three types of WeCom integration:
 
-**Option 1: WeCom Bot (智能机器人)** - Easier setup, supports group chats
-**Option 2: WeCom App (自建应用)** - More features, proactive messaging
+**Option 1: WeCom Bot (Bot)** - Easier setup, supports group chats
+**Option 2: WeCom App (Custom App)** - More features, proactive messaging, private chat only
+**Option 3: WeCom AI Bot (AI Bot)** - Official AI Bot, streaming replies, supports group & private chat
 
-See [WeCom App Configuration Guide](docs/wecom-app-configuration.md) for detailed setup instructions.
+See [WeCom AI Bot Configuration Guide](docs/channels/wecom/wecom_aibot/README.zh.md) for detailed setup instructions.
 
 **Quick Setup - WeCom Bot:**
 
@@ -631,6 +632,39 @@ picoclaw gateway
 
 > **Note**: WeCom webhook callbacks are served on the Gateway port (default 18790). Use a reverse proxy for HTTPS.
 
+**Quick Setup - WeCom AI Bot:**
+
+**1. Create an AI Bot**
+
+* Go to WeCom Admin Console → App Management → AI Bot
+* In the AI Bot settings, configure callback URL: `http://your-server:18791/webhook/wecom-aibot`
+* Copy **Token** and click "Random Generate" for **EncodingAESKey**
+
+**2. Configure**
+
+```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": "Hello! How can I help you?"
+    }
+  }
+}
+```
+
+**3. Run**
+
+```bash
+picoclaw gateway
+```
+
+> **Note**: WeCom AI Bot uses streaming pull protocol — no reply timeout concerns. Long tasks (>30 seconds) automatically switch to `response_url` push delivery.
+
 </details>
 
 ## <img src="assets/clawdchat-icon.png" width="24" height="24" alt="ClawdChat"> Join the Agent Social Network

README.pt-br.md

@@ -282,7 +282,7 @@ Converse com seu PicoClaw via Telegram, Discord, DingTalk, LINE ou WeCom.
 | **QQ** | Fácil (AppID + AppSecret) |
 | **DingTalk** | Médio (credenciais do app) |
 | **LINE** | Médio (credenciais + webhook URL) |
-| **WeCom** | Médio (CorpID + configuração webhook) |
+| **WeCom AI Bot** | Médio (Token + chave AES) |
 
 <details>
 <summary><b>Telegram</b> (Recomendado)</summary>
@@ -485,12 +485,13 @@ picoclaw gateway
 <details>
 <summary><b>WeCom (WeChat Work)</b></summary>
 
-O PicoClaw suporta dois tipos de integração WeCom:
+O PicoClaw suporta três tipos de integração WeCom:
 
-**Opção 1: WeCom Bot (Robô Inteligente)** - Configuração mais fácil, suporta chats em grupo
-**Opção 2: WeCom App (Aplicativo Personalizado)** - Mais recursos, mensagens proativas
+**Opção 1: WeCom Bot (Robô)** - Configuração mais fácil, suporta chats em grupo
+**Opção 2: WeCom App (Aplicativo Personalizado)** - Mais recursos, mensagens proativas, somente chat privado
+**Opção 3: WeCom AI Bot (Robô Inteligente)** - Bot IA oficial, respostas em streaming, suporta grupo e privado
 
-Veja o [Guia de Configuração WeCom App](docs/wecom-app-configuration.md) para instruções detalhadas.
+Veja o [Guia de Configuração WeCom AI Bot](docs/channels/wecom/wecom_aibot/README.zh.md) para instruções detalhadas.
 
 **Configuração Rápida - WeCom Bot:**
 
@@ -559,6 +560,39 @@ picoclaw gateway
 
 > **Nota**: O WeCom App (callbacks de webhook) é servido pelo Gateway compartilhado (padrão 127.0.0.1:18790). Em produção use um proxy reverso HTTPS para expor a porta do Gateway, ou atualize `PICOCLAW_GATEWAY_HOST` para `0.0.0.0` se necessário.
 
+**Configuração Rápida - WeCom AI Bot:**
+
+**1. Criar um AI Bot**
+
+* Acesse o Console de Administração WeCom → Gerenciamento de Aplicativos → AI Bot
+* Configure a URL de callback: `http://your-server:18791/webhook/wecom-aibot`
+* Copie o **Token** e gere o **EncodingAESKey**
+
+**2. Configurar**
+
+```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": "Olá! Como posso ajudá-lo?"
+    }
+  }
+}
+```
+
+**3. Executar**
+
+```bash
+picoclaw gateway
+```
+
+> **Nota**: O WeCom AI Bot usa protocolo de pull em streaming — sem preocupações com timeout de resposta. Tarefas longas (>5,5 min) alternam automaticamente para entrega via `response_url`.
+
 </details>
 
 ## <img src="assets/clawdchat-icon.png" width="24" height="24" alt="ClawdChat"> Junte-se a Rede Social de Agentes

README.vi.md

@@ -256,7 +256,7 @@ Trò chuyện với PicoClaw qua Telegram, Discord, DingTalk, LINE hoặc WeCom.
 | **QQ** | Dễ (AppID + AppSecret) |
 | **DingTalk** | Trung bình (app credentials) |
 | **LINE** | Trung bình (credentials + webhook URL) |
-| **WeCom** | Trung bình (CorpID + cấu hình webhook) |
+| **WeCom AI Bot** | Trung bình (Token + khóa AES) |
 
 <details>
 <summary><b>Telegram</b> (Khuyên dùng)</summary>
@@ -457,12 +457,13 @@ picoclaw gateway
 <details>
 <summary><b>WeCom (WeChat Work)</b></summary>
 
-PicoClaw hỗ trợ hai loại tích hợp WeCom:
+PicoClaw hỗ trợ ba loại tích hợp WeCom:
 
-**Tùy chọn 1: WeCom Bot (Robot Thông minh)** - Thiết lập dễ dàng hơn, hỗ trợ chat nhóm
-**Tùy chọn 2: WeCom App (Ứng dụng Tự xây dựng)** - Nhiều tính năng hơn, nhắn tin chủ động
+**Tùy chọn 1: WeCom Bot (Robot)** - Thiết lập dễ dàng hơn, hỗ trợ chat nhóm
+**Tùy chọn 2: WeCom App (Ứng dụng Tùy chỉnh)** - Nhiều tính năng hơn, nhắn tin chủ động, chỉ chat riêng tư
+**Tùy chọn 3: WeCom AI Bot (Bot Thông Minh)** - Bot AI chính thức, phản hồi streaming, hỗ trợ nhóm và riêng tư
 
-Xem [Hướng dẫn Cấu hình WeCom App](docs/wecom-app-configuration.md) để biết hướng dẫn chi tiết.
+Xem [Hướng dẫn Cấu hình WeCom AI Bot](docs/channels/wecom/wecom_aibot/README.zh.md) để biết hướng dẫn chi tiết.
 
 **Thiết lập Nhanh - WeCom Bot:**
 
@@ -531,6 +532,39 @@ picoclaw gateway
 
 > **Lưu ý**: WeCom App callback webhook được phục vụ bởi Gateway HTTP chung (mặc định 127.0.0.1:18790). Sử dụng proxy ngược để cung cấp HTTPS trong môi trường production nếu cần.
 
+**Thiết lập Nhanh - WeCom AI Bot:**
+
+**1. Tạo AI Bot**
+
+* Truy cập Bảng điều khiển Quản trị WeCom → Quản lý Ứng dụng → AI Bot
+* Cấu hình URL callback: `http://your-server:18791/webhook/wecom-aibot`
+* Sao chép **Token** và tạo **EncodingAESKey**
+
+**2. Cấu hình**
+
+```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": "Xin chào! Tôi có thể giúp gì cho bạn?"
+    }
+  }
+}
+```
+
+**3. Chạy**
+
+```bash
+picoclaw gateway
+```
+
+> **Lưu ý**: WeCom AI Bot sử dụng giao thức pull streaming — không lo timeout phản hồi. Tác vụ dài (>5,5 phút) tự động chuyển sang gửi qua `response_url`.
+
 </details>
 
 ## <img src="assets/clawdchat-icon.png" width="24" height="24" alt="ClawdChat"> Tham gia Mạng xã hội Agent

README.zh.md

@@ -301,7 +301,7 @@ PicoClaw 支持多种聊天平台，使您的 Agent 能够连接到任何地方
 | **Slack**            | ⭐ 简单     | **Socket Mode** (无需公网 IP)，企业级支持 | [查看文档](docs/channels/slack/README.zh.md)                                                                    |
 | **QQ**               | ⭐⭐ 中等   | 官方机器人 API，适合国内社群              | [查看文档](docs/channels/qq/README.zh.md)                                                                       |
 | **钉钉 (DingTalk)**  | ⭐⭐ 中等   | Stream 模式无需公网，企业办公首选         | [查看文档](docs/channels/dingtalk/README.zh.md)                                                                 |
-| **企业微信 (WeCom)** | ⭐⭐⭐ 较难 | 支持群机器人(Webhook)和自建应用(API)      | [Bot 文档](docs/channels/wecom/wecom_bot/README.zh.md) / [App 文档](docs/channels/wecom/wecom_app/README.zh.md) |
+| **企业微信 (WeCom)** | ⭐⭐⭐ 较难 | 支持群机器人(Webhook)、自建应用(API)和智能机器人(AI Bot) | [Bot 文档](docs/channels/wecom/wecom_bot/README.zh.md) / [App 文档](docs/channels/wecom/wecom_app/README.zh.md) / [AI Bot 文档](docs/channels/wecom/wecom_aibot/README.zh.md) |
 | **飞书 (Feishu)**    | ⭐⭐⭐ 较难 | 企业级协作，功能丰富                      | [查看文档](docs/channels/feishu/README.zh.md)                                                                   |
 | **Line**             | ⭐⭐⭐ 较难 | 需要 HTTPS Webhook                        | [查看文档](docs/channels/line/README.zh.md)                                                                     |
 | **OneBot**           | ⭐⭐ 中等   | 兼容 NapCat/Go-CQHTTP，社区生态丰富       | [查看文档](docs/channels/onebot/README.zh.md)                                                                   |

config/config.example.json

@@ -127,7 +127,7 @@
       "reasoning_channel_id": ""
     },
     "wecom": {
-      "_comment": "WeCom Bot (智能机器人) - Easier setup, supports group chats",
+      "_comment": "WeCom Bot - Easier setup, supports group chats",
       "enabled": false,
       "token": "YOUR_TOKEN",
       "encoding_aes_key": "YOUR_43_CHAR_ENCODING_AES_KEY",
@@ -138,7 +138,7 @@
       "reasoning_channel_id": ""
     },
     "wecom_app": {
-      "_comment": "WeCom App (自建应用) - More features, proactive messaging, private chat only. See docs/wecom-app-configuration.md",
+      "_comment": "WeCom App (自建应用) - More features, proactive messaging, private chat only.",
       "enabled": false,
       "corp_id": "YOUR_CORP_ID",
       "corp_secret": "YOUR_CORP_SECRET",
@@ -149,6 +149,16 @@
       "allow_from": [],
       "reply_timeout": 5,
       "reasoning_channel_id": ""
+    },
+    "wecom_aibot": {
+      "_comment": "WeCom AI Bot (智能机器人) - Official WeCom AI Bot integration, supports proactive messaging and private chats.",
+      "enabled": false,
+      "token": "YOUR_TOKEN",
+      "encoding_aes_key": "YOUR_43_CHAR_ENCODING_AES_KEY",
+      "webhook_path": "/webhook/wecom-aibot",
+      "max_steps": 10,
+      "welcome_message": "Hello! I'm your AI assistant. How can I help you today?",
+      "reasoning_channel_id": ""
     }
   },
   "providers": {

docs/channels/wecom/wecom_aibot/README.zh.md

@@ -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)

docs/wecom-app-configuration.md

@@ -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)

pkg/channels/manager.go

@@ -255,6 +255,10 @@ func (m *Manager) initChannels() error {
 		m.initChannel("wecom", "WeCom")
 	}
 
+	if m.config.Channels.WeComAIBot.Enabled && m.config.Channels.WeComAIBot.Token != "" {
+		m.initChannel("wecom_aibot", "WeCom AI Bot")
+	}
+
 	if m.config.Channels.WeComApp.Enabled && m.config.Channels.WeComApp.CorpID != "" {
 		m.initChannel("wecom_app", "WeCom App")
 	}

pkg/channels/wecom/aibot_test.go

@@ -0,0 +1,210 @@
+package wecom
+
+import (
+	"context"
+	"testing"
+
+	"github.com/sipeed/picoclaw/pkg/bus"
+	"github.com/sipeed/picoclaw/pkg/config"
+)
+
+func TestNewWeComAIBotChannel(t *testing.T) {
+	t.Run("success with valid config", func(t *testing.T) {
+		cfg := config.WeComAIBotConfig{
+			Enabled:        true,
+			Token:          "test_token",
+			EncodingAESKey: "testkey1234567890123456789012345678901234567",
+			WebhookPath:    "/webhook/test",
+		}
+
+		messageBus := bus.NewMessageBus()
+		ch, err := NewWeComAIBotChannel(cfg, messageBus)
+		if err != nil {
+			t.Fatalf("Expected no error, got %v", err)
+		}
+
+		if ch == nil {
+			t.Fatal("Expected channel to be created")
+		}
+
+		if ch.Name() != "wecom_aibot" {
+			t.Errorf("Expected name 'wecom_aibot', got '%s'", ch.Name())
+		}
+	})
+
+	t.Run("error with missing token", func(t *testing.T) {
+		cfg := config.WeComAIBotConfig{
+			Enabled:        true,
+			EncodingAESKey: "testkey1234567890123456789012345678901234567",
+		}
+
+		messageBus := bus.NewMessageBus()
+		_, err := NewWeComAIBotChannel(cfg, messageBus)
+
+		if err == nil {
+			t.Fatal("Expected error for missing token, got nil")
+		}
+	})
+
+	t.Run("error with missing encoding key", func(t *testing.T) {
+		cfg := config.WeComAIBotConfig{
+			Enabled: true,
+			Token:   "test_token",
+		}
+
+		messageBus := bus.NewMessageBus()
+		_, err := NewWeComAIBotChannel(cfg, messageBus)
+
+		if err == nil {
+			t.Fatal("Expected error for missing encoding key, got nil")
+		}
+	})
+}
+
+func TestWeComAIBotChannelStartStop(t *testing.T) {
+	cfg := config.WeComAIBotConfig{
+		Enabled:        true,
+		Token:          "test_token",
+		EncodingAESKey: "testkey1234567890123456789012345678901234567",
+	}
+
+	messageBus := bus.NewMessageBus()
+	ch, err := NewWeComAIBotChannel(cfg, messageBus)
+	if err != nil {
+		t.Fatalf("Failed to create channel: %v", err)
+	}
+
+	ctx := context.Background()
+
+	// Test Start
+	if err := ch.Start(ctx); err != nil {
+		t.Fatalf("Failed to start channel: %v", err)
+	}
+
+	if !ch.IsRunning() {
+		t.Error("Expected channel to be running")
+	}
+
+	// Test Stop
+	if err := ch.Stop(ctx); err != nil {
+		t.Fatalf("Failed to stop channel: %v", err)
+	}
+
+	if ch.IsRunning() {
+		t.Error("Expected channel to be stopped")
+	}
+}
+
+func TestWeComAIBotChannelWebhookPath(t *testing.T) {
+	t.Run("default path", func(t *testing.T) {
+		cfg := config.WeComAIBotConfig{
+			Enabled:        true,
+			Token:          "test_token",
+			EncodingAESKey: "testkey1234567890123456789012345678901234567",
+		}
+
+		messageBus := bus.NewMessageBus()
+		ch, _ := NewWeComAIBotChannel(cfg, messageBus)
+
+		expectedPath := "/webhook/wecom-aibot"
+		if ch.WebhookPath() != expectedPath {
+			t.Errorf("Expected webhook path '%s', got '%s'", expectedPath, ch.WebhookPath())
+		}
+	})
+
+	t.Run("custom path", func(t *testing.T) {
+		customPath := "/custom/webhook"
+		cfg := config.WeComAIBotConfig{
+			Enabled:        true,
+			Token:          "test_token",
+			EncodingAESKey: "testkey1234567890123456789012345678901234567",
+			WebhookPath:    customPath,
+		}
+
+		messageBus := bus.NewMessageBus()
+		ch, _ := NewWeComAIBotChannel(cfg, messageBus)
+
+		if ch.WebhookPath() != customPath {
+			t.Errorf("Expected webhook path '%s', got '%s'", customPath, ch.WebhookPath())
+		}
+	})
+}
+
+func TestGenerateStreamID(t *testing.T) {
+	cfg := config.WeComAIBotConfig{
+		Enabled:        true,
+		Token:          "test_token",
+		EncodingAESKey: "testkey1234567890123456789012345678901234567",
+	}
+
+	messageBus := bus.NewMessageBus()
+	ch, _ := NewWeComAIBotChannel(cfg, messageBus)
+
+	// Generate multiple IDs and check they are unique
+	ids := make(map[string]bool)
+	for i := 0; i < 100; i++ {
+		id := ch.generateStreamID()
+
+		if len(id) != 10 {
+			t.Errorf("Expected stream ID length 10, got %d", len(id))
+		}
+
+		if ids[id] {
+			t.Errorf("Duplicate stream ID generated: %s", id)
+		}
+		ids[id] = true
+	}
+}
+
+func TestEncryptDecrypt(t *testing.T) {
+	// Use a valid 43-character base64 key (企业微信标准格式)
+	cfg := config.WeComAIBotConfig{
+		Enabled:        true,
+		Token:          "test_token",
+		EncodingAESKey: "abcdefghijklmnopqrstuvwxyz0123456789ABCDEFG", // 43 characters
+	}
+
+	messageBus := bus.NewMessageBus()
+	ch, _ := NewWeComAIBotChannel(cfg, messageBus)
+
+	plaintext := "Hello, World!"
+	receiveid := ""
+
+	// Encrypt
+	encrypted, err := ch.encryptMessage(plaintext, receiveid)
+	if err != nil {
+		t.Fatalf("Failed to encrypt message: %v", err)
+	}
+
+	if encrypted == "" {
+		t.Fatal("Encrypted message is empty")
+	}
+
+	// Decrypt
+	decrypted, err := decryptMessageWithVerify(encrypted, cfg.EncodingAESKey, receiveid)
+	if err != nil {
+		t.Fatalf("Failed to decrypt message: %v", err)
+	}
+
+	if decrypted != plaintext {
+		t.Errorf("Expected decrypted message '%s', got '%s'", plaintext, decrypted)
+	}
+}
+
+func TestGenerateSignature(t *testing.T) {
+	token := "test_token"
+	timestamp := "1234567890"
+	nonce := "test_nonce"
+	encrypt := "encrypted_msg"
+
+	signature := computeSignature(token, timestamp, nonce, encrypt)
+
+	if signature == "" {
+		t.Error("Generated signature is empty")
+	}
+
+	// Verify signature using verifySignature function
+	if !verifySignature(token, signature, timestamp, nonce, encrypt) {
+		t.Error("Generated signature does not verify correctly")
+	}
+}

pkg/channels/wecom/common.go

@@ -1,12 +1,15 @@
 package wecom
 
 import (
+	"bytes"
 	"crypto/aes"
 	"crypto/cipher"
+	"crypto/rand"
 	"crypto/sha1"
 	"encoding/base64"
 	"encoding/binary"
 	"fmt"
+	"math/big"
 	"sort"
 	"strings"
 )
@@ -14,25 +17,23 @@ import (
 // blockSize is the PKCS7 block size used by WeCom (32)
 const blockSize = 32
 
+// computeSignature computes the WeCom message signature from the given parameters.
+// It sorts [token, timestamp, nonce, encrypt], concatenates them and returns the SHA1 hex digest.
+func computeSignature(token, timestamp, nonce, encrypt string) string {
+	params := []string{token, timestamp, nonce, encrypt}
+	sort.Strings(params)
+	str := strings.Join(params, "")
+	hash := sha1.Sum([]byte(str))
+	return fmt.Sprintf("%x", hash)
+}
+
 // verifySignature verifies the message signature for WeCom
 // This is a common function used by both WeCom Bot and WeCom App
 func verifySignature(token, msgSignature, timestamp, nonce, msgEncrypt string) bool {
 	if token == "" {
 		return true // Skip verification if token is not set
 	}
-
-	// Sort parameters
-	params := []string{token, timestamp, nonce, msgEncrypt}
-	sort.Strings(params)
-
-	// Concatenate
-	str := strings.Join(params, "")
-
-	// SHA1 hash
-	hash := sha1.Sum([]byte(str))
-	expectedSignature := fmt.Sprintf("%x", hash)
-
-	return expectedSignature == msgSignature
+	return computeSignature(token, timestamp, nonce, msgEncrypt) == msgSignature
 }
 
 // decryptMessage decrypts the encrypted message using AES
@@ -53,64 +54,128 @@ func decryptMessageWithVerify(encryptedMsg, encodingAESKey, receiveid string) (s
 		return string(decoded), nil
 	}
 
-	// Decode AES key (base64)
-	aesKey, err := base64.StdEncoding.DecodeString(encodingAESKey + "=")
+	aesKey, err := decodeWeComAESKey(encodingAESKey)
 	if err != nil {
-		return "", fmt.Errorf("failed to decode AES key: %w", err)
+		return "", err
 	}
 
-	// Decode encrypted message
 	cipherText, err := base64.StdEncoding.DecodeString(encryptedMsg)
 	if err != nil {
 		return "", fmt.Errorf("failed to decode message: %w", err)
 	}
 
-	// AES decrypt
+	plainText, err := decryptAESCBC(aesKey, cipherText)
+	if err != nil {
+		return "", err
+	}
+
+	return unpackWeComFrame(plainText, receiveid)
+}
+
+// decodeWeComAESKey base64-decodes the 43-character EncodingAESKey (trailing "=" is
+// appended automatically) and validates that the result is exactly 32 bytes.
+// It is the single place that handles this repeated pattern in both encrypt and decrypt paths.
+func decodeWeComAESKey(encodingAESKey string) ([]byte, error) {
+	aesKey, err := base64.StdEncoding.DecodeString(encodingAESKey + "=")
+	if err != nil {
+		return nil, fmt.Errorf("failed to decode AES key: %w", err)
+	}
+	if len(aesKey) != 32 {
+		return nil, fmt.Errorf("invalid AES key length: %d", len(aesKey))
+	}
+	return aesKey, nil
+}
+
+// encryptAESCBC encrypts plaintext using AES-CBC with the given key, mirroring
+// decryptAESCBC. IV = aesKey[:aes.BlockSize]. The caller must PKCS7-pad the
+// plaintext to a multiple of aes.BlockSize before calling.
+func encryptAESCBC(aesKey, plaintext []byte) ([]byte, error) {
 	block, err := aes.NewCipher(aesKey)
 	if err != nil {
-		return "", fmt.Errorf("failed to create cipher: %w", err)
+		return nil, fmt.Errorf("failed to create cipher: %w", err)
 	}
-
-	if len(cipherText) < aes.BlockSize {
-		return "", fmt.Errorf("ciphertext too short")
-	}
-
-	// IV is the first 16 bytes of AESKey
 	iv := aesKey[:aes.BlockSize]
-	mode := cipher.NewCBCDecrypter(block, iv)
-	plainText := make([]byte, len(cipherText))
-	mode.CryptBlocks(plainText, cipherText)
+	ciphertext := make([]byte, len(plaintext))
+	cipher.NewCBCEncrypter(block, iv).CryptBlocks(ciphertext, plaintext)
+	return ciphertext, nil
+}
 
-	// Remove PKCS7 padding
-	plainText, err = pkcs7Unpad(plainText)
-	if err != nil {
-		return "", fmt.Errorf("failed to unpad: %w", err)
+// packWeComFrame builds the WeCom wire format:
+//
+//	random(16 ASCII digits) + msg_len(4, big-endian) + msg + receiveid
+func packWeComFrame(msg, receiveid string) ([]byte, error) {
+	randomBytes := make([]byte, 16)
+	for i := range 16 {
+		n, err := rand.Int(rand.Reader, big.NewInt(10))
+		if err != nil {
+			return nil, fmt.Errorf("failed to generate random: %w", err)
+		}
+		randomBytes[i] = byte('0' + n.Int64())
 	}
+	msgBytes := []byte(msg)
+	msgLenBytes := make([]byte, 4)
+	binary.BigEndian.PutUint32(msgLenBytes, uint32(len(msgBytes)))
+	var buf bytes.Buffer
+	buf.Write(randomBytes)
+	buf.Write(msgLenBytes)
+	buf.Write(msgBytes)
+	buf.WriteString(receiveid)
+	return buf.Bytes(), nil
+}
 
-	// Parse message structure
-	// Format: random(16) + msg_len(4) + msg + receiveid
-	if len(plainText) < 20 {
-		return "", fmt.Errorf("decrypted message too short")
+// unpackWeComFrame parses the WeCom wire format produced by packWeComFrame.
+// If receiveid is non-empty it verifies the frame's trailing receiveid field.
+func unpackWeComFrame(data []byte, receiveid string) (string, error) {
+	if len(data) < 20 {
+		return "", fmt.Errorf("decrypted frame too short: %d bytes", len(data))
 	}
-
-	msgLen := binary.BigEndian.Uint32(plainText[16:20])
-	if int(msgLen) > len(plainText)-20 {
-		return "", fmt.Errorf("invalid message length")
+	msgLen := binary.BigEndian.Uint32(data[16:20])
+	if int(msgLen) > len(data)-20 {
+		return "", fmt.Errorf("invalid message length: %d", msgLen)
 	}
-
-	msg := plainText[20 : 20+msgLen]
-
-	// Verify receiveid if provided
-	if receiveid != "" && len(plainText) > 20+int(msgLen) {
-		actualReceiveID := string(plainText[20+msgLen:])
+	msg := data[20 : 20+msgLen]
+	if receiveid != "" && len(data) > 20+int(msgLen) {
+		actualReceiveID := string(data[20+msgLen:])
 		if actualReceiveID != receiveid {
 			return "", fmt.Errorf("receiveid mismatch: expected %s, got %s", receiveid, actualReceiveID)
 		}
 	}
-
 	return string(msg), nil
 }
 
+// decryptAESCBC decrypts ciphertext using AES-CBC with the given key.
+// IV = aesKey[:aes.BlockSize]. PKCS7 padding is stripped from the returned plaintext.
+func decryptAESCBC(aesKey, ciphertext []byte) ([]byte, error) {
+	if len(ciphertext) == 0 {
+		return nil, fmt.Errorf("ciphertext is empty")
+	}
+	if len(ciphertext)%aes.BlockSize != 0 {
+		return nil, fmt.Errorf("ciphertext length %d is not a multiple of block size", len(ciphertext))
+	}
+	block, err := aes.NewCipher(aesKey)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create cipher: %w", err)
+	}
+	iv := aesKey[:aes.BlockSize]
+	plaintext := make([]byte, len(ciphertext))
+	cipher.NewCBCDecrypter(block, iv).CryptBlocks(plaintext, ciphertext)
+	plaintext, err = pkcs7Unpad(plaintext)
+	if err != nil {
+		return nil, fmt.Errorf("failed to unpad: %w", err)
+	}
+	return plaintext, nil
+}
+
+// pkcs7Pad adds PKCS7 padding
+func pkcs7Pad(data []byte, blockSize int) []byte {
+	padding := blockSize - (len(data) % blockSize)
+	if padding == 0 {
+		padding = blockSize
+	}
+	padText := bytes.Repeat([]byte{byte(padding)}, padding)
+	return append(data, padText...)
+}
+
 // pkcs7Unpad removes PKCS7 padding with validation
 func pkcs7Unpad(data []byte) ([]byte, error) {
 	if len(data) == 0 {

pkg/channels/wecom/init.go

@@ -13,4 +13,7 @@ func init() {
 	channels.RegisterFactory("wecom_app", func(cfg *config.Config, b *bus.MessageBus) (channels.Channel, error) {
 		return NewWeComAppChannel(cfg.Channels.WeComApp, b)
 	})
+	channels.RegisterFactory("wecom_aibot", func(cfg *config.Config, b *bus.MessageBus) (channels.Channel, error) {
+		return NewWeComAIBotChannel(cfg.Channels.WeComAIBot, b)
+	})
 }

pkg/config/config.go

@@ -192,19 +192,20 @@ func (d *AgentDefaults) GetModelName() string {
 }
 
 type ChannelsConfig struct {
-	WhatsApp WhatsAppConfig `json:"whatsapp"`
-	Telegram TelegramConfig `json:"telegram"`
-	Feishu   FeishuConfig   `json:"feishu"`
-	Discord  DiscordConfig  `json:"discord"`
-	MaixCam  MaixCamConfig  `json:"maixcam"`
-	QQ       QQConfig       `json:"qq"`
-	DingTalk DingTalkConfig `json:"dingtalk"`
-	Slack    SlackConfig    `json:"slack"`
-	LINE     LINEConfig     `json:"line"`
-	OneBot   OneBotConfig   `json:"onebot"`
-	WeCom    WeComConfig    `json:"wecom"`
-	WeComApp WeComAppConfig `json:"wecom_app"`
-	Pico     PicoConfig     `json:"pico"`
+	WhatsApp   WhatsAppConfig   `json:"whatsapp"`
+	Telegram   TelegramConfig   `json:"telegram"`
+	Feishu     FeishuConfig     `json:"feishu"`
+	Discord    DiscordConfig    `json:"discord"`
+	MaixCam    MaixCamConfig    `json:"maixcam"`
+	QQ         QQConfig         `json:"qq"`
+	DingTalk   DingTalkConfig   `json:"dingtalk"`
+	Slack      SlackConfig      `json:"slack"`
+	LINE       LINEConfig       `json:"line"`
+	OneBot     OneBotConfig     `json:"onebot"`
+	WeCom      WeComConfig      `json:"wecom"`
+	WeComApp   WeComAppConfig   `json:"wecom_app"`
+	WeComAIBot WeComAIBotConfig `json:"wecom_aibot"`
+	Pico       PicoConfig       `json:"pico"`
 }
 
 // GroupTriggerConfig controls when the bot responds in group chats.
@@ -360,6 +361,18 @@ type WeComAppConfig struct {
 	ReasoningChannelID string              `json:"reasoning_channel_id"    env:"PICOCLAW_CHANNELS_WECOM_APP_REASONING_CHANNEL_ID"`
 }
 
+type WeComAIBotConfig struct {
+	Enabled            bool                `json:"enabled"              env:"PICOCLAW_CHANNELS_WECOM_AIBOT_ENABLED"`
+	Token              string              `json:"token"                env:"PICOCLAW_CHANNELS_WECOM_AIBOT_TOKEN"`
+	EncodingAESKey     string              `json:"encoding_aes_key"     env:"PICOCLAW_CHANNELS_WECOM_AIBOT_ENCODING_AES_KEY"`
+	WebhookPath        string              `json:"webhook_path"         env:"PICOCLAW_CHANNELS_WECOM_AIBOT_WEBHOOK_PATH"`
+	AllowFrom          FlexibleStringSlice `json:"allow_from"           env:"PICOCLAW_CHANNELS_WECOM_AIBOT_ALLOW_FROM"`
+	ReplyTimeout       int                 `json:"reply_timeout"        env:"PICOCLAW_CHANNELS_WECOM_AIBOT_REPLY_TIMEOUT"`
+	MaxSteps           int                 `json:"max_steps"            env:"PICOCLAW_CHANNELS_WECOM_AIBOT_MAX_STEPS"`       // Maximum streaming steps
+	WelcomeMessage     string              `json:"welcome_message"      env:"PICOCLAW_CHANNELS_WECOM_AIBOT_WELCOME_MESSAGE"` // Sent on enter_chat event; empty = no welcome
+	ReasoningChannelID string              `json:"reasoning_channel_id" env:"PICOCLAW_CHANNELS_WECOM_AIBOT_REASONING_CHANNEL_ID"`
+}
+
 type PicoConfig struct {
 	Enabled         bool                `json:"enabled"                     env:"PICOCLAW_CHANNELS_PICO_ENABLED"`
 	Token           string              `json:"token"                       env:"PICOCLAW_CHANNELS_PICO_TOKEN"`
@@ -637,7 +650,8 @@ func (c *Config) migrateChannelConfigs() {
 	}
 
 	// OneBot: group_trigger_prefix -> group_trigger.prefixes
-	if len(c.Channels.OneBot.GroupTriggerPrefix) > 0 && len(c.Channels.OneBot.GroupTrigger.Prefixes) == 0 {
+	if len(c.Channels.OneBot.GroupTriggerPrefix) > 0 &&
+		len(c.Channels.OneBot.GroupTrigger.Prefixes) == 0 {
 		c.Channels.OneBot.GroupTrigger.Prefixes = c.Channels.OneBot.GroupTriggerPrefix
 	}
 }

pkg/config/defaults.go

@@ -137,6 +137,16 @@ func DefaultConfig() *Config {
 				AllowFrom:      FlexibleStringSlice{},
 				ReplyTimeout:   5,
 			},
+			WeComAIBot: WeComAIBotConfig{
+				Enabled:        false,
+				Token:          "",
+				EncodingAESKey: "",
+				WebhookPath:    "/webhook/wecom-aibot",
+				AllowFrom:      FlexibleStringSlice{},
+				ReplyTimeout:   5,
+				MaxSteps:       10,
+				WelcomeMessage: "Hello! I'm your AI assistant. How can I help you today?",
+			},
 			Pico: PicoConfig{
 				Enabled:        false,
 				Token:          "",