Update version to v1.3.19 in config.yaml

Fix Qwen model error by ensuring user message is kept after memory compression

README.md

@@ -83,6 +83,7 @@ CyberStrikeAI is an **AI-native security testing platform** built in Go. It inte
 - 📋 Batch task management: create task queues, add multiple tasks, and execute them sequentially
 - 🎭 Role-based testing: predefined security testing roles (Penetration Testing, CTF, Web App Scanning, etc.) with custom prompts and tool restrictions
 - 🎯 Skills system: 20+ predefined security testing skills (SQL injection, XSS, API security, etc.) that can be attached to roles or called on-demand by AI agents
+- 📱 **Chatbot**: DingTalk and Lark (Feishu) long-lived connections so you can talk to CyberStrikeAI from mobile (see [Robot / Chatbot guide](docs/robot_en.md) for setup and commands)
 
 ## Tool Overview
 
@@ -460,6 +461,10 @@ tools:
 enabled: true
 ```
 
+## Related documentation
+
+- [Robot / Chatbot guide (DingTalk & Lark)](docs/robot_en.md): Full setup, commands, and troubleshooting for using CyberStrikeAI from DingTalk or Lark on your phone. **Follow this doc to avoid common pitfalls.**
+
 ## Project Layout
 
 ```
@@ -470,6 +475,7 @@ CyberStrikeAI/
 ├── tools/               # YAML tool recipes (100+ examples provided)
 ├── roles/               # Role configurations (12+ predefined security testing roles)
 ├── skills/              # Skills directory (20+ predefined security testing skills)
+├── docs/                # Documentation (e.g. robot/chbot guide)
 ├── images/              # Docs screenshots & diagrams
 ├── config.yaml          # Runtime configuration
 ├── run.sh               # Convenience launcher
@@ -495,20 +501,6 @@ Compress the 5 MB nuclei report, summarize critical CVEs, and attach the artifac
 Build an attack chain for the latest engagement and export the node list with severity >= high.
 ```
 
-## Changelog
-
-### Recent Highlights
-
-- **2026-01-27** – OpenAPI documentation with interactive testing interface, supporting conversation management, message interaction, and result querying
-- **2026-01-15** – Skills system with 20+ predefined security testing skills
-- **2026-01-11** – Role-based testing with predefined security testing roles
-- **2026-01-08** – SSE transport mode support for external MCP servers
-- **2026-01-01** – Batch task management with queue-based execution
-- **2025-12-25** – Vulnerability management and conversation grouping features
-- **2025-12-20** – Knowledge base with vector search and hybrid retrieval
-
-
-
 ## 404Starlink 
 
 <img src="./images/404StarLinkLogo.png" width="30%">
@@ -526,6 +518,22 @@ CyberStrikeAI has joined [404Starlink](https://github.com/knownsec/404StarLink)
 ![Stargazers over time](https://starchart.cc/Ed1s0nZ/CyberStrikeAI.svg)
 
 
+---
+
+## ⚠️ Disclaimer
+
+**This tool is for educational and authorized testing purposes only!**
+
+CyberStrikeAI is a professional security testing platform designed to assist security researchers, penetration testers, and IT professionals in conducting security assessments and vulnerability research **with explicit authorization**.
+
+**By using this tool, you agree to:**
+- Use this tool only on systems where you have clear written authorization
+- Comply with all applicable laws, regulations, and ethical standards
+- Take full responsibility for any unauthorized use or misuse
+- Not use this tool for any illegal or malicious purposes
+
+**The developers are not responsible for any misuse!** Please ensure your usage complies with local laws and regulations, and that you have obtained explicit authorization from the target system owner.
+
 ---
 
 Need help or want to contribute? Open an issue or PR—community tooling additions are welcome!

README_CN.md

@@ -82,6 +82,7 @@ CyberStrikeAI 是一款 **AI 原生安全测试平台**，基于 Go 构建，集
 - 📋 批量任务管理：创建任务队列，批量添加任务，依次顺序执行，支持任务编辑与状态跟踪
 - 🎭 角色化测试：预设安全测试角色（渗透测试、CTF、Web 应用扫描等），支持自定义提示词和工具限制
 - 🎯 Skills 技能系统：20+ 预设安全测试技能（SQL 注入、XSS、API 安全等），可附加到角色或由 AI 按需调用
+- 📱 **机器人**：支持钉钉、飞书长连接，在手机端与 CyberStrikeAI 对话（配置与命令详见 [机器人使用说明](docs/robot.md)）
 
 ## 工具概览
 
@@ -459,6 +460,10 @@ tools:
 enabled: true
 ```
 
+## 相关文档
+
+- [机器人使用说明（钉钉 / 飞书）](docs/robot.md)：在手机端通过钉钉、飞书与 CyberStrikeAI 对话的完整配置步骤、命令与排查说明，**建议按该文档操作以避免走弯路**。
+
 ## 项目结构
 
 ```
@@ -469,6 +474,7 @@ CyberStrikeAI/
 ├── tools/               # YAML 工具目录（含 100+ 示例）
 ├── roles/               # 角色配置文件目录（含 12+ 预设安全测试角色）
 ├── skills/              # Skills 目录（含 20+ 预设安全测试技能）
+├── docs/                # 说明文档（如机器人使用说明）
 ├── images/              # 文档配图
 ├── config.yaml          # 运行配置
 ├── run.sh               # 启动脚本
@@ -494,19 +500,6 @@ CyberStrikeAI/
 构建最新一次测试的攻击链，只导出风险 >= 高的节点列表。
 ```
 
-## 更新日志
-
-### 近期亮点
-
-- **2026-01-27** – 新增 OpenAPI 文档，提供交互式测试界面，支持对话管理、消息交互和结果查询
-- **2026-01-15** – 新增 Skills 技能系统，内置 20+ 预设安全测试技能
-- **2026-01-11** – 新增角色化测试功能，支持预设安全测试角色
-- **2026-01-08** – 新增 SSE 传输模式支持，外部 MCP 联邦支持三种模式
-- **2026-01-01** – 新增批量任务管理功能，支持队列式任务执行
-- **2025-12-25** – 新增漏洞管理和对话分组功能
-- **2025-12-20** – 新增知识库功能，支持向量检索和混合搜索
-
-
 ## 404星链计划 
 <img src="./images/404StarLinkLogo.png" width="30%">
 
@@ -524,4 +517,20 @@ CyberStrikeAI 现已加入 [404星链计划](https://github.com/knownsec/404Star
 
 ---
 
+## ⚠️ 免责声明
+
+**本工具仅供教育和授权测试使用！**
+
+CyberStrikeAI 是一个专业的安全测试平台，旨在帮助安全研究人员、渗透测试人员和IT专业人员在**获得明确授权**的情况下进行安全评估和漏洞研究。
+
+**使用本工具即表示您同意：**
+- 仅在您拥有明确书面授权的系统上使用此工具
+- 遵守所有适用的法律法规和道德准则
+- 对任何未经授权的使用或滥用行为承担全部责任
+- 不会将本工具用于任何非法或恶意目的
+
+**开发者不对任何滥用行为负责！** 请确保您的使用符合当地法律法规，并获得目标系统所有者的明确授权。
+
+---
+
 欢迎提交 Issue/PR 贡献新的工具模版或优化建议！

config.yaml

@@ -10,7 +10,7 @@
 # ============================================
 
 # 前端显示的版本号（可选，不填则显示默认版本）
-version: "v1.3.8"
+version: "v1.3.19"
 
 # 服务器配置
 server:
@@ -116,6 +116,45 @@ knowledge:
     top_k: 5                        # 检索返回的Top-K结果数量
     similarity_threshold: 0.7       # 相似度阈值（0-1），低于此值的结果将被过滤
     hybrid_weight: 0.7              # 混合检索权重（0-1），向量检索的权重，1.0表示纯向量检索，0.0表示纯关键词检索
+  # ============================================
+  # 索引配置（用于解决 API 限制问题）
+  # ============================================
+  indexing:
+    # 分块配置
+    chunk_size: 512 # 每个块的最大 token 数（默认 512），长文本会被分割成多个块
+    chunk_overlap: 50 # 块之间的重叠 token 数（默认 50），保持上下文连贯性
+    max_chunks_per_item: 0 # 单个知识项的最大块数量（0 表示不限制），防止单个文件消耗过多 API 配额
+    # 速率限制配置（解决 429 错误）
+    max_rpm: 0 # 每分钟最大请求数（默认 0 表示不限制），如 OpenAI 默认 200 RPM
+    rate_limit_delay_ms: 300 # 请求间隔毫秒数（默认 300），用于避免 API 速率限制，设为 0 不限制
+    # 建议值：200 次/分钟≈300ms, 100 次/分钟≈600ms
+
+    # 重试配置
+    max_retries: 3 # 最大重试次数（默认 3），遇到速率限制或服务器错误时自动重试
+    retry_delay_ms: 1000 # 重试间隔毫秒数（默认 1000），每次重试会递增延迟
+
+# ============================================
+# 机器人配置（企业微信、钉钉、飞书）
+# ============================================
+# 用于在手机端通过企业微信/钉钉/飞书与 CyberStrikeAI 对话，无需部署在服务器上也可使用
+# 在系统设置 -> 机器人设置 中可配置
+robots:
+  wecom: # 企业微信
+    enabled: false
+    token: ""
+    encoding_aes_key: ""
+    corp_id: ""
+    secret: ""
+    agent_id: 0
+  dingtalk: # 钉钉
+    enabled: false
+    client_id: 
+    client_secret: 
+  lark: # 飞书
+    enabled: false
+    app_id: ""
+    app_secret: ""
+    verify_token: ""
 
 # ============================================
 # Skills 相关配置

docs/robot.md

@@ -0,0 +1,257 @@
+# CyberStrikeAI 机器人使用说明
+
+[English](robot_en.md)
+
+本文档说明如何通过**钉钉**、**飞书**与 **企业微信** 与 CyberStrikeAI 对话（长连接 / 回调模式），在手机端即可使用，无需在服务器上打开网页。按下面步骤操作可避免常见弯路。
+
+---
+
+## 一、在 CyberStrikeAI 里从哪里配置
+
+1. 登录 CyberStrikeAI Web 端  
+2. 左侧导航进入 **系统设置**  
+3. 在左侧设置分类中点击 **机器人设置**（位于「基本设置」与「安全设置」之间）  
+4. 按平台勾选并填写（钉钉填 Client ID / Client Secret，飞书填 App ID / App Secret）  
+5. 点击 **应用配置** 保存  
+6. **重启 CyberStrikeAI 应用**（只保存不重启，机器人不会连上）
+
+配置会写入 `config.yaml` 的 `robots` 段，也可在配置文件中直接编辑。**修改钉钉/飞书配置后必须重启，长连接才会生效。**
+
+---
+
+## 二、支持的平台（长连接 / 回调）
+
+| 平台     | 说明 |
+|----------|------|
+| 钉钉     | 使用 Stream 长连接，程序主动连接钉钉接收消息 |
+| 飞书     | 使用长连接，程序主动连接飞书接收消息 |
+| 企业微信 | 使用 HTTP 回调接收消息，被动回包 + 主动调用企业微信发送消息 API |
+
+下面第三节会按平台写清：在开放平台要做什么、要复制哪些字段、填到 CyberStrikeAI 的哪一栏。
+
+---
+
+## 三、各平台配置项与详细步骤
+
+### 3.1 钉钉
+
+**先搞清楚：两种钉钉机器人不一样**
+
+| 类型 | 从哪里创建 | 能否做「用户发消息→机器人回复」 | 本程序是否支持 |
+|------|------------|----------------------------------|----------------|
+| **自定义机器人** | 钉钉群里：群设置 → 添加机器人 → 自定义（Webhook） | ❌ 不能，只能你往群里发消息 | ❌ 不支持 |
+| **企业内部应用机器人** | [钉钉开放平台](https://open.dingtalk.com) 创建应用并开通机器人 | ✅ 能 | ✅ 支持 |
+
+如果你手里是「自定义机器人」的 Webhook 地址（`oapi.dingtalk.com/robot/send?access_token=xxx`）和加签密钥（`SEC...`），**不能直接填到本程序**，必须按下面步骤在开放平台创建「企业内部应用」并拿到 **Client ID**、**Client Secret**。
+
+---
+
+**钉钉配置完整步骤（按顺序做）**
+
+1. **打开钉钉开放平台**  
+   浏览器访问 [https://open.dingtalk.com](https://open.dingtalk.com)，用**企业管理员**账号登录。
+
+2. **进入应用开发**  
+   左侧选 **应用开发** → **企业内部开发** → 点击 **创建应用**（或选择已有应用）。填写应用名称等基本信息后创建。
+
+3. **拿到 Client ID 和 Client Secret**  
+   - 左侧点 **凭证与基础信息**（在「基础信息」下）。  
+   - 页面上有 **Client ID（原 AppKey）** 和 **Client Secret（原 AppSecret）**。  
+   - 点击复制，**不要手打**，注意：数字 **0** 和字母 **o**、数字 **1** 和字母 **l** 容易抄错（例如 `ding9gf9tiozuc504aer` 中间是数字 **504** 不是 5o4）。
+
+4. **开通机器人并选 Stream 模式**  
+   - 左侧 **应用能力** → **机器人**。  
+   - 打开「机器人配置」开关。  
+   - 填写机器人名称、简介等（必填项按提示填）。  
+   - **关键**：消息接收方式要选 **「Stream 模式」**（流式接入）。若只有「HTTP 回调」或未选 Stream，本程序收不到消息。  
+   - 保存。
+
+5. **权限与发布**  
+   - 左侧 **权限管理**：搜索「机器人」「消息」等，勾选**接收消息**、**发送消息**等机器人相关权限，并确认授权。  
+   - 左侧 **版本管理与发布**：若有未发布配置，点击 **发布新版本** / **上线**，否则修改不生效。
+
+6. **填回 CyberStrikeAI**  
+   - 回到 CyberStrikeAI → 系统设置 → 机器人设置 → 钉钉。  
+   - 勾选「启用钉钉机器人」。  
+   - **Client ID (AppKey)** 粘贴第 3 步复制的 Client ID。  
+   - **Client Secret** 粘贴第 3 步复制的 Client Secret。  
+   - 点击 **应用配置**，然后**重启 CyberStrikeAI**。
+
+---
+
+**CyberStrikeAI 钉钉栏位对照**
+
+| CyberStrikeAI 中填写项 | 在钉钉开放平台的来源 |
+|------------------------|------------------------|
+| 启用钉钉机器人 | 勾选即启用 |
+| Client ID (AppKey) | 凭证与基础信息 → **Client ID（原 AppKey）** |
+| Client Secret | 凭证与基础信息 → **Client Secret（原 AppSecret）** |
+
+---
+
+### 3.2 飞书 (Lark)
+
+| 配置项 | 说明 |
+|--------|------|
+| 启用飞书机器人 | 勾选后启动飞书长连接 |
+| App ID | 飞书开放平台应用凭证中的 App ID |
+| App Secret | 飞书开放平台应用凭证中的 App Secret |
+| Verify Token | 事件订阅用（可选） |
+
+**飞书配置简要步骤**：登录 [飞书开放平台](https://open.feishu.cn) → 创建企业自建应用 → 在「凭证与基础信息」中获取 **App ID**、**App Secret** → 在「应用能力」中开通**机器人**并启用相应权限 → 发布应用 → 将 App ID、App Secret 填到 CyberStrikeAI 机器人设置 → 保存并**重启应用**。
+
+---
+
+### 3.3 企业微信 (WeCom)
+
+> 企业微信目前采用「HTTP 回调 + 主动发送消息 API」的方式工作：  
+> - 用户发消息 → 企业微信以加密 XML **回调到你的服务器**（本程序的 `/api/robot/wecom`）；  
+> - CyberStrikeAI 解密并调用 AI → 使用企业微信的 `message/send` 接口**主动发消息给用户**。
+
+**配置概览：**
+
+- 在企业微信管理后台创建或选择一个**自建应用**。
+- 在该应用的「接收消息」处配置回调 URL、Token、EncodingAESKey。
+- 在 CyberStrikeAI 的 `config.yaml` 中填入：
+  - `robots.wecom.corp_id`：企业 ID（CorpID）
+  - `robots.wecom.agent_id`：应用的 AgentId
+  - `robots.wecom.token`：消息回调使用的 Token
+  - `robots.wecom.encoding_aes_key`：消息回调使用的 EncodingAESKey
+  - `robots.wecom.secret`：该应用的 Secret（用于调用企业微信主动发送消息接口）
+
+> **重要：IP 白名单（errcode 60020）**  
+> CyberStrikeAI 使用 `https://qyapi.weixin.qq.com/cgi-bin/message/send` 主动发送 AI 回复。  
+> 若企业微信日志或本程序日志中出现 `errcode 60020 not allow to access from your ip`：
+>
+> - 说明你的服务器出口 IP **没有加入企业微信的 IP 白名单**；  
+> - 请在企业微信管理后台中找到该自建应用的**「安全设置 / IP 白名单」**（具体入口可能因版本略有不同），将运行 CyberStrikeAI 的服务器公网 IP（如 `110.xxx.xxx.xxx`）加入白名单；  
+> - 保存后等待生效，再次发送消息测试。
+>
+> 如果 IP 未加入白名单，企业微信会拒绝主动发送消息，表现为：  
+> - 回调接口 `/api/robot/wecom` 能正常收到并处理消息；  
+> - 但手机端**始终收不到 AI 回复**，日志中有 `not allow to access from your ip` 提示。
+
+---
+
+## 四、机器人命令
+
+在钉钉/飞书中向机器人发送以下**文本命令**（仅支持文本）：
+
+| 命令 | 说明 |
+|------|------|
+| **帮助** | 显示命令帮助与说明 |
+| **列表** 或 **对话列表** | 列出所有对话的标题与对话 ID |
+| **切换 \<对话ID\>** 或 **继续 \<对话ID\>** | 指定对话 ID，后续消息在该对话中继续 |
+| **新对话** | 开启一个新对话，后续消息在新对话中 |
+| **清空** | 清空当前对话上下文（效果等同「新对话」） |
+| **当前** | 显示当前对话 ID 与标题 |
+| **停止** | 中断当前正在执行的任务 |
+| **角色** 或 **角色列表** | 列出所有可用角色（渗透测试、CTF、Web 应用扫描等） |
+| **角色 \<角色名\>** 或 **切换角色 \<角色名\>** | 切换当前使用的角色 |
+| **删除 \<对话ID\>** | 删除指定对话 |
+| **版本** | 显示当前 CyberStrikeAI 版本号 |
+
+除以上命令外，**直接输入任意文字**会作为用户消息发给 AI，与 Web 端对话逻辑一致（渗透测试/安全分析等）。
+
+---
+
+## 五、如何使用（要 @ 机器人吗？）
+
+- **单聊（推荐）**：在钉钉/飞书里**搜索并打开该机器人**，进入与机器人的**私聊**，直接输入「帮助」或任意文字即可，**不需要 @**。  
+- **群聊**：若机器人被添加到群里，在群内只有 **@机器人** 后发送的消息才会被机器人收到并回复；不 @ 的群消息不会触发机器人。
+
+总结：和机器人**单聊时直接发**；在**群里用时需要 @机器人** 再发内容。
+
+---
+
+## 六、推荐使用流程（避免漏步骤）
+
+1. **在开放平台**：按第三节完成钉钉或飞书应用创建、凭证复制、机器人开通（钉钉务必选 **Stream 模式**）、权限与发布。  
+2. **在 CyberStrikeAI**：系统设置 → 机器人设置 → 勾选对应平台，粘贴 Client ID/App ID、Client Secret/App Secret → 点击 **应用配置**。  
+3. **重启 CyberStrikeAI 进程**（否则长连接不会建立）。  
+4. **在手机钉钉/飞书**：找到该机器人（单聊直接发，群聊需 @机器人），发「帮助」或任意内容测试。
+
+若发消息没反应，先看 **第九节排查** 和 **第十节常见弯路**。
+
+---
+
+## 七、配置文件示例
+
+`config.yaml` 中机器人相关片段示例：
+
+```yaml
+robots:
+  dingtalk:
+    enabled: true
+    client_id: "your_dingtalk_app_key"
+    client_secret: "your_dingtalk_app_secret"
+  lark:
+    enabled: true
+    app_id: "your_lark_app_id"
+    app_secret: "your_lark_app_secret"
+    verify_token: ""
+```
+
+修改后需**重启应用**，长连接在应用启动时建立。
+
+---
+
+## 八、如何验证是否可用（无需钉钉/飞书客户端）
+
+在未安装钉钉或飞书时，可用**测试接口**验证机器人逻辑是否正常：
+
+1. 先登录 CyberStrikeAI Web 端（保证有登录态）。  
+2. 使用 curl 调用测试接口（需携带登录后的 Cookie）：
+
+```bash
+# 将 YOUR_COOKIE 替换为登录后获得的 Cookie（浏览器 F12 → 网络 → 任意请求 → 请求头中的 Cookie）
+curl -X POST "http://localhost:8080/api/robot/test" \
+  -H "Content-Type: application/json" \
+  -H "Cookie: YOUR_COOKIE" \
+  -d '{"platform":"dingtalk","user_id":"test_user","text":"帮助"}'
+```
+
+若返回 JSON 中含有 `"reply":"【CyberStrikeAI 机器人命令】..."`，说明命令处理正常。可再试 `"text":"列表"`、`"text":"当前"` 等。
+
+接口说明：`POST /api/robot/test`（需登录），请求体 `{"platform":"可选","user_id":"可选","text":"必填"}`，响应 `{"reply":"回复内容"}`。
+
+---
+
+## 九、钉钉发消息没反应时排查
+
+按顺序检查：
+
+0. **笔记本合盖睡眠 / 断网后**  
+   钉钉、飞书均使用长连接收消息，睡眠或断网后连接会断开。程序会**自动重连**（约 5 秒～60 秒内重试）。唤醒或恢复网络后稍等一会儿再发消息；若仍无反应，可重启 CyberStrikeAI 进程。
+
+1. **Client ID / Client Secret 是否与开放平台完全一致**  
+   从「凭证与基础信息」里**复制粘贴**，不要手打。注意数字 **0** 与字母 **o**、数字 **1** 与字母 **l**（例如 `ding9gf9tiozuc504aer` 中间是 **504** 不是 5o4）。
+
+2. **是否在保存配置后重启了应用**  
+   机器人长连接在**应用启动时**建立。在 Web 端点击「应用配置」只写入配置文件，**必须重启 CyberStrikeAI 进程**后钉钉连接才会生效。
+
+3. **看程序日志**  
+   - 启动后应看到：`钉钉 Stream 正在连接…`、`钉钉 Stream 已启动（无需公网），等待收消息`。  
+   - 若出现 `钉钉 Stream 长连接退出` 且带错误信息，多为 **Client ID / Client Secret 错误**或**开放平台未开通流式接入**。  
+   - 在钉钉里发一条消息后，若有收到，应有日志：`钉钉收到消息`；若没有，说明钉钉未把消息推到本程序（回头检查开放平台「机器人」是否开通、是否选用 **Stream 模式**）。
+
+4. **开放平台侧**  
+   应用需已**发布**；在「机器人」能力中需开启**流式接入（Stream）** 用于接收消息（仅 HTTP 回调不够）；权限管理里需有机器人接收、发送消息等权限。
+
+---
+
+## 十、常见弯路（避免踩坑）
+
+- **用错了机器人类型**：在钉钉**群里**添加的「自定义」机器人（Webhook + 加签）**不能**用来做对话，本程序只支持**开放平台「企业内部应用」**里的机器人。  
+- **只保存没重启**：在 CyberStrikeAI 里改完机器人配置后必须**重启应用**，否则长连接不会建立。  
+- **Client ID 抄错**：开放平台是 `504` 就填 `504`，不要填成 `5o4`；尽量用复制粘贴。  
+- **钉钉只开了 HTTP 回调没开 Stream**：本程序通过 **Stream 长连接**收消息，开放平台里机器人的消息接收方式必须选 **Stream 模式**。  
+- **应用没发布**：开放平台里修改了机器人或权限后，要在「版本管理与发布」里**发布新版本**，否则不生效。
+
+---
+
+## 十一、注意事项
+
+- 钉钉、飞书均**仅处理文本消息**；其他类型（如图片、语音）会提示暂不支持或忽略。  
+- 会话与 Web 端共用同一套对话数据：在机器人里创建的对话会在 Web 端「对话」列表中看到，反之亦然。  
+- 机器人执行逻辑与 **`/api/agent-loop/stream`** 一致（含进度回调、过程详情写入数据库），仅不向客户端推送 SSE，最后将完整回复一次性发回钉钉/飞书/企业微信。

docs/robot_en.md

@@ -0,0 +1,254 @@
+# CyberStrikeAI Robot / Chatbot Guide
+
+[中文](robot.md)
+
+This document explains how to chat with CyberStrikeAI from **DingTalk**, **Lark (Feishu)**, and **WeCom (Enterprise WeChat)** using long-lived connections or HTTP callbacks—no need to open a browser on the server. Following the steps below helps avoid common mistakes.
+
+---
+
+## 1. Where to configure in CyberStrikeAI
+
+1. Log in to the CyberStrikeAI web UI.
+2. Open **System Settings** in the left sidebar.
+3. Click **Robot settings** (between “Basic” and “Security”).
+4. Enable the platform and fill in credentials (DingTalk: Client ID / Client Secret; Lark: App ID / App Secret).
+5. Click **Apply configuration** to save.
+6. **Restart the CyberStrikeAI process** (saving alone does not establish the connection).
+
+Settings are written to the `robots` section of `config.yaml`; you can also edit the file directly. **After changing DingTalk or Lark config, you must restart for the long-lived connection to take effect.**
+
+---
+
+## 2. Supported platforms (long-lived / callback)
+
+| Platform       | Description |
+|----------------|-------------|
+| DingTalk       | Stream long-lived connection; the app connects to DingTalk to receive messages |
+| Lark (Feishu)  | Long-lived connection; the app connects to Lark to receive messages |
+| WeCom (Qiye WX)| HTTP callback to receive messages; CyberStrikeAI replies via WeCom’s message sending API |
+
+Section 3 below describes, per platform, what to do in the developer console and which fields to copy into CyberStrikeAI.
+
+---
+
+## 3. Configuration and step-by-step setup
+
+### 3.1 DingTalk
+
+**Important: two types of DingTalk bots**
+
+| Type | Where it’s created | Can do “user sends message → bot replies”? | Supported here? |
+|------|-------------------|-------------------------------------------|------------------|
+| **Custom bot (Webhook)** | In a DingTalk group: Group settings → Add robot → Custom (Webhook) | No; you can only post to the group | No |
+| **Enterprise internal app bot** | [DingTalk Open Platform](https://open.dingtalk.com): create an app and enable the bot | Yes | Yes |
+
+If you only have a **custom bot** Webhook URL (`oapi.dingtalk.com/robot/send?access_token=...`) and sign secret (`SEC...`), **do not** put them into CyberStrikeAI. You must create an **enterprise internal app** in the open platform and obtain **Client ID** and **Client Secret** as below.
+
+---
+
+**DingTalk setup (in order)**
+
+1. **Open DingTalk Open Platform**  
+   Go to [https://open.dingtalk.com](https://open.dingtalk.com) and log in with an **enterprise admin** account.
+
+2. **Create or select an app**  
+   In the left menu: **Application development** → **Enterprise internal development** → **Create application** (or choose an existing app). Fill in the app name and create.
+
+3. **Get Client ID and Client Secret**  
+   - In the left menu open **Credentials and basic info** (under “Basic information”).  
+   - Copy **Client ID (formerly AppKey)** and **Client Secret (formerly AppSecret)**.  
+   - Use copy/paste; avoid typing by hand. Watch for **0** vs **o** and **1** vs **l** (e.g. `ding9gf9tiozuc504aer` has the digits **504**, not 5o4).
+
+4. **Enable the bot and choose Stream mode**  
+   - Left menu: **Application capabilities** → **Robot**.  
+   - Turn on “Robot configuration”.  
+   - Fill in robot name, description, etc. as required.  
+   - **Critical**: set message reception to **“Stream mode”** (流式接入). If you only enable “HTTP callback” or do not select Stream, CyberStrikeAI will not receive messages.  
+   - Save.
+
+5. **Permissions and release**  
+   - Left menu: **Permission management** — search for “robot”, “message”, etc., and enable **receive message**, **send message**, and other bot-related permissions; confirm.  
+   - Left menu: **Version management and release** — if there are unpublished changes, click **Release new version** / **Publish**; otherwise changes do not take effect.
+
+6. **Fill in CyberStrikeAI**  
+   - In CyberStrikeAI: System settings → Robot settings → DingTalk.  
+   - Enable “Enable DingTalk robot”.  
+   - Paste the Client ID and Client Secret from step 3.  
+   - Click **Apply configuration**, then **restart CyberStrikeAI**.
+
+---
+
+**Field mapping (DingTalk)**
+
+| Field in CyberStrikeAI | Source in DingTalk Open Platform |
+|------------------------|----------------------------------|
+| Enable DingTalk robot | Check to enable |
+| Client ID (AppKey) | Credentials and basic info → **Client ID (formerly AppKey)** |
+| Client Secret | Credentials and basic info → **Client Secret (formerly AppSecret)** |
+
+---
+
+### 3.2 Lark (Feishu)
+
+| Field | Description |
+|-------|-------------|
+| Enable Lark robot | Check to start the Lark long-lived connection |
+| App ID | From Lark open platform app credentials |
+| App Secret | From Lark open platform app credentials |
+| Verify Token | Optional; for event subscription |
+
+**Lark setup in short**: Log in to [Lark Open Platform](https://open.feishu.cn) → Create an enterprise app → In “Credentials and basic info” get **App ID** and **App Secret** → In “Application capabilities” enable **Robot** and the right permissions → Publish the app → Enter App ID and App Secret in CyberStrikeAI robot settings → Save and **restart** the app.
+
+---
+
+### 3.3 WeCom (Enterprise WeChat)
+
+> WeCom uses a **“HTTP callback + active message send API”** model:  
+> - User sends a message → WeCom sends an **encrypted XML callback** to your server (CyberStrikeAI’s `/api/robot/wecom`).  
+> - CyberStrikeAI decrypts it, calls the AI, then uses WeCom’s `message/send` API to **actively push the reply** to the user.
+
+**Configuration overview:**
+
+- In the WeCom admin console, create or select a **custom app** (自建应用).
+- In that app’s settings, configure the message **callback URL**, **Token**, and **EncodingAESKey**.
+- In CyberStrikeAI’s `config.yaml`, fill in:
+  - `robots.wecom.corp_id`: your CorpID (企业 ID)
+  - `robots.wecom.agent_id`: the app’s AgentId
+  - `robots.wecom.token`: the Token used for message callbacks
+  - `robots.wecom.encoding_aes_key`: the EncodingAESKey used for callbacks
+  - `robots.wecom.secret`: the app’s Secret (used when calling WeCom APIs to send messages)
+
+> **Important: IP allowlist (errcode 60020)**  
+> CyberStrikeAI calls `https://qyapi.weixin.qq.com/cgi-bin/message/send` to actively send AI replies.  
+> If logs show `errcode 60020 not allow to access from your ip`:
+>
+> - Your server’s outbound IP is **not in WeCom’s IP allowlist**.  
+> - In the WeCom admin console, open the custom app’s **Security / IP allowlist** settings (name may vary slightly), and add the public IP of the machine running CyberStrikeAI (e.g. `110.xxx.xxx.xxx`).  
+> - Save and wait for it to take effect, then test again.
+>
+> If the IP is not whitelisted, WeCom will reject active message sending. You will see that `/api/robot/wecom` receives and processes callbacks, but users **never see AI replies**, and logs contain `not allow to access from your ip`.
+
+---
+
+## 4. Bot commands
+
+Send these **text commands** to the bot in DingTalk or Lark (text only):
+
+| Command | Description |
+|---------|-------------|
+| **帮助** (help) | Show command help |
+| **列表** or **对话列表** (list) | List all conversation titles and IDs |
+| **切换 \<conversationID\>** or **继续 \<conversationID\>** | Continue in the given conversation |
+| **新对话** (new) | Start a new conversation |
+| **清空** (clear) | Clear current context (same effect as new conversation) |
+| **当前** (current) | Show current conversation ID and title |
+| **停止** (stop) | Abort the currently running task |
+| **角色** or **角色列表** (roles) | List all available roles (penetration testing, CTF, Web scan, etc.) |
+| **角色 \<roleName\>** or **切换角色 \<roleName\>** | Switch to the specified role |
+| **删除 \<conversationID\>** | Delete the specified conversation |
+| **版本** (version) | Show current CyberStrikeAI version |
+
+Any other text is sent to the AI as a user message, same as in the web UI (e.g. penetration testing, security analysis).
+
+---
+
+## 5. How to use (do I need to @ the bot?)
+
+- **Direct chat (recommended)**: In DingTalk or Lark, **search for the bot and open a direct chat**. Type “帮助” or any message; **no @ needed**.  
+- **Group chat**: If the bot is in a group, only messages that **@ the bot** are received and answered; other group messages are ignored.
+
+Summary: **Direct chat** — just send; **in a group** — @ the bot first, then send.
+
+---
+
+## 6. Recommended flow (so you don’t skip steps)
+
+1. **In the open platform**: Complete app creation, copy credentials, enable the bot (DingTalk: **Stream mode**), set permissions, and publish (Section 3).  
+2. **In CyberStrikeAI**: System settings → Robot settings → Enable the platform, paste Client ID/App ID and Client Secret/App Secret → **Apply configuration**.  
+3. **Restart the CyberStrikeAI process** (otherwise the long-lived connection is not established).  
+4. **On your phone**: Open DingTalk or Lark, find the bot (direct chat or @ in a group), send “帮助” or any message to test.
+
+If the bot does not respond, see **Section 9 (troubleshooting)** and **Section 10 (common pitfalls)**.
+
+---
+
+## 7. Config file example
+
+Example `robots` section in `config.yaml`:
+
+```yaml
+robots:
+  dingtalk:
+    enabled: true
+    client_id: "your_dingtalk_app_key"
+    client_secret: "your_dingtalk_app_secret"
+  lark:
+    enabled: true
+    app_id: "your_lark_app_id"
+    app_secret: "your_lark_app_secret"
+    verify_token: ""
+```
+
+**Restart the app** after changes; the long-lived connection is created at startup.
+
+---
+
+## 8. Testing without DingTalk/Lark installed
+
+You can verify bot logic with the **test API** (no DingTalk/Lark client needed):
+
+1. Log in to the CyberStrikeAI web UI (so you have a session).
+2. Call the test endpoint with curl (include your session Cookie):
+
+```bash
+# Replace YOUR_COOKIE with the Cookie from your browser (F12 → Network → any request → Request headers → Cookie)
+curl -X POST "http://localhost:8080/api/robot/test" \
+  -H "Content-Type: application/json" \
+  -H "Cookie: YOUR_COOKIE" \
+  -d '{"platform":"dingtalk","user_id":"test_user","text":"帮助"}'
+```
+
+If the JSON response contains `"reply":"【CyberStrikeAI 机器人命令】..."`, command handling works. You can also try `"text":"列表"` or `"text":"当前"`.
+
+API: `POST /api/robot/test` (requires login). Body: `{"platform":"optional","user_id":"optional","text":"required"}`. Response: `{"reply":"..."}`.
+
+---
+
+## 9. DingTalk: no response when sending messages
+
+Check in this order:
+
+0. **After laptop sleep or network drop**  
+   DingTalk and Lark both use long-lived connections; they break when the machine sleeps or the network drops. The app **auto-reconnects** (retries within about 5–60 seconds). After wake or network recovery, wait a moment before sending; if there is still no response, restart the CyberStrikeAI process.
+
+1. **Client ID / Client Secret match the open platform exactly**  
+   Copy from “Credentials and basic info”; avoid typing. Watch **0** vs **o** and **1** vs **l** (e.g. `ding9gf9tiozuc504aer` has **504**, not 5o4).
+
+2. **Did you restart after saving?**  
+   The long-lived connection is created at **startup**. “Apply configuration” only updates the config file; you **must restart the CyberStrikeAI process** for the DingTalk connection to start.
+
+3. **Application logs**  
+   - On startup you should see: `钉钉 Stream 正在连接…`, `钉钉 Stream 已启动（无需公网），等待收消息`.  
+   - If you see `钉钉 Stream 长连接退出` with an error, it’s usually wrong **Client ID / Client Secret** or **Stream not enabled** in the open platform.  
+   - After sending a message in DingTalk, you should see `钉钉收到消息` in the logs; if not, the platform is not pushing to this app (check that the bot is enabled and **Stream mode** is selected).
+
+4. **Open platform**  
+   The app must be **published**. Under “Robot” you must enable **Stream** for receiving messages (HTTP callback only is not enough). Permission management must include robot receive/send message permissions.
+
+---
+
+## 10. Common pitfalls
+
+- **Wrong bot type**: The “Custom” bot added in a DingTalk **group** (Webhook + sign secret) **cannot** be used for two-way chat. Only the **enterprise internal app** bot from the open platform is supported.  
+- **Saved but not restarted**: After changing robot settings in CyberStrikeAI you **must restart** the app, or the long-lived connection will not be established.  
+- **Client ID typo**: If the platform shows `504`, use `504` (not `5o4`); prefer copy/paste.  
+- **DingTalk: only HTTP callback, no Stream**: This app receives messages via **Stream**. In the open platform, message reception must be **Stream mode**.  
+- **App not published**: After changing the bot or permissions in the open platform, **publish a new version** under “Version management and release”, or changes won’t apply.
+
+---
+
+## 11. Notes
+
+- DingTalk and Lark: **text messages only**; other types (e.g. image, voice) are not supported and may be ignored.  
+- Conversations are shared with the web UI: conversations created from the bot appear in the web “Conversations” list and vice versa.  
+- Bot execution uses the same logic as **`/api/agent-loop/stream`** (progress callbacks, process details stored in the DB); only the final reply is sent back to DingTalk/Lark in one message (no SSE to the client).

go.mod

@@ -1,16 +1,21 @@
 module cyberstrike-ai
 
-go 1.23.0
+go 1.24.0
 
 toolchain go1.24.4
 
 require (
+	github.com/creack/pty v1.1.24
 	github.com/gin-gonic/gin v1.9.1
 	github.com/google/uuid v1.5.0
+	github.com/gorilla/websocket v1.5.0
+	github.com/larksuite/oapi-sdk-go/v3 v3.4.22
 	github.com/mattn/go-sqlite3 v1.14.18
 	github.com/modelcontextprotocol/go-sdk v1.2.0
+	github.com/open-dingtalk/dingtalk-stream-sdk-go v0.9.1
 	github.com/pkoukk/tiktoken-go v0.1.8
 	go.uber.org/zap v1.26.0
+	golang.org/x/time v0.14.0
 	gopkg.in/yaml.v3 v3.0.1
 )
 
@@ -24,6 +29,7 @@ require (
 	github.com/go-playground/universal-translator v0.18.1 // indirect
 	github.com/go-playground/validator/v10 v10.14.0 // indirect
 	github.com/goccy/go-json v0.10.2 // indirect
+	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/google/jsonschema-go v0.3.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/klauspost/cpuid/v2 v2.2.4 // indirect
@@ -44,3 +50,7 @@ require (
 	golang.org/x/text v0.13.0 // indirect
 	google.golang.org/protobuf v1.30.0 // indirect
 )
+
+// 修复钉钉 Stream SDK 在长连接断开（熄屏/网络中断）后 "panic: send on closed channel" 问题
+// 详见: https://github.com/open-dingtalk/dingtalk-stream-sdk-go/issues/28
+replace github.com/open-dingtalk/dingtalk-stream-sdk-go => github.com/uouuou/dingtalk-stream-sdk-go v0.0.0-20250626025113-079132acc406

go.sum

@@ -4,6 +4,8 @@ github.com/bytedance/sonic v1.9.1/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZX
 github.com/chenzhuoyu/base64x v0.0.0-20211019084208-fb5309c8db06/go.mod h1:DH46F32mSOjUmXrMHnKwZdA8wcEefY7UVqBKYGjpdQY=
 github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 h1:qSGYFH7+jGhDF8vLC+iwCD4WpbV1EBDSzWkJODFLams=
 github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311/go.mod h1:b583jCggY9gE99b6G5LEC39OIiVsWj+R97kbl5odCEk=
+github.com/creack/pty v1.1.24 h1:bJrF4RRfyJnbTJqzRLHzcGaZK1NeM5kTC9jGgovnR1s=
+github.com/creack/pty v1.1.24/go.mod h1:08sCNb52WyoAwi2QDyzUCTgcvVFhUzewun7wtTfvcwE=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -25,6 +27,8 @@ github.com/go-playground/validator/v10 v10.14.0 h1:vgvQWe3XCz3gIeFDm/HnTIbj6UGmg
 github.com/go-playground/validator/v10 v10.14.0/go.mod h1:9iXMNT7sEkjXb0I+enO7QXmzG6QCsPWY4zveKFVRSyU=
 github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
 github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
+github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
+github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
 github.com/golang-jwt/jwt/v5 v5.2.2 h1:Rl4B7itRWVtYIHFrSNd7vhTiz9UpLdi6gZhZ3wEeDy8=
 github.com/golang-jwt/jwt/v5 v5.2.2/go.mod h1:pqrtFR0X4osieyHYxtmOUWsAWrfe1Q5UVIyoH402zdk=
 github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
@@ -36,11 +40,17 @@ github.com/google/jsonschema-go v0.3.0 h1:6AH2TxVNtk3IlvkkhjrtbUc4S8AvO0Xii0DxIy
 github.com/google/jsonschema-go v0.3.0/go.mod h1:r5quNTdLOYEz95Ru18zA0ydNbBuYoo9tgaYcxEYhJVE=
 github.com/google/uuid v1.5.0 h1:1p67kYwdtXjb0gL0BPiP1Av9wiZPo5A8z2cWkTZ+eyU=
 github.com/google/uuid v1.5.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/gorilla/websocket v1.5.0 h1:PPwGk2jz7EePpoHN/+ClbZu8SPxiqlu12wZP/3sWmnc=
+github.com/gorilla/websocket v1.5.0/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
+github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
+github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
 github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
 github.com/klauspost/cpuid/v2 v2.2.4 h1:acbojRNwl3o09bUq+yDCtZFc1aiwaAAxtcn8YkZXnvk=
 github.com/klauspost/cpuid/v2 v2.2.4/go.mod h1:RVVoqg1df56z8g3pUjL/3lE5UfnlrJX8tyFgg4nqhuY=
+github.com/larksuite/oapi-sdk-go/v3 v3.4.22 h1:57daKuslQPX9X3hC2idc5bu8bl2krfsBGWGJ6b5FlD8=
+github.com/larksuite/oapi-sdk-go/v3 v3.4.22/go.mod h1:ZEplY+kwuIrj/nqw5uSCINNATcH3KdxSN7y+UxYY5fI=
 github.com/leodido/go-urn v1.2.4 h1:XlAE/cm/ms7TE/VMVoduSpNBoyc2dOxHs5MZSwAN63Q=
 github.com/leodido/go-urn v1.2.4/go.mod h1:7ZrI8mTSeBSHl/UaRyKQW1qZeMgak41ANeCNaVckg+4=
 github.com/mattn/go-isatty v0.0.19 h1:JITubQf0MOLdlGRuRq+jtsDlekdYPia9ZFsB8h/APPA=
@@ -75,8 +85,12 @@ github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS
 github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08=
 github.com/ugorji/go/codec v1.2.11 h1:BMaWp1Bb6fHwEtbplGBGJ498wD+LKlNSl25MjdZY4dU=
 github.com/ugorji/go/codec v1.2.11/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
+github.com/uouuou/dingtalk-stream-sdk-go v0.0.0-20250626025113-079132acc406 h1:b72HNsEnmTRn7vhWGOfbWHAkA5RbRCk0Pbc56V2WAuY=
+github.com/uouuou/dingtalk-stream-sdk-go v0.0.0-20250626025113-079132acc406/go.mod h1:ln3IqPYYocZbYvl9TAOrG/cxGR9xcn4pnZRLdCTEGEU=
 github.com/yosida95/uritemplate/v3 v3.0.2 h1:Ed3Oyj9yrmi9087+NczuL5BwkIc4wvTb5zIM+UJPGz4=
 github.com/yosida95/uritemplate/v3 v3.0.2/go.mod h1:ILOh0sOhIJR3+L/8afwt/kE++YT040gmv5BQTMR2HP4=
+github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
+github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 go.uber.org/goleak v1.2.0 h1:xqgm/S+aQvhWFTtR0XK3Jvg7z8kGV8P4X14IzwN3Eqk=
 go.uber.org/goleak v1.2.0/go.mod h1:XJYK+MuIchqpmGmUSAzotztawfKvYLUIgg7guXrwVUo=
 go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=
@@ -86,21 +100,47 @@ go.uber.org/zap v1.26.0/go.mod h1:dtElttAiwGvoJ/vj4IwHBS/gXsEu/pZ50mUIRWuG0so=
 golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
 golang.org/x/arch v0.3.0 h1:02VY4/ZcO/gBOH6PUaoiptASxtXU10jazRCP865E97k=
 golang.org/x/arch v0.3.0/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
+golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/crypto v0.14.0 h1:wBqGXzWJW6m1XrIKlAH0Hs1JJ7+9KBwnIO8v66Q9cHc=
 golang.org/x/crypto v0.14.0/go.mod h1:MVFd36DqK4CsrnJYDkBA3VC4m2GkXAM0PvzMCn4JQf4=
+golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
+golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
+golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20200226121028-0de0cce0169b/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
 golang.org/x/net v0.17.0 h1:pVaXccu2ozPjCXewfr1S7xza/zcXTity9cCdXQYSjIM=
 golang.org/x/net v0.17.0/go.mod h1:NxSsAGuq816PNPmqtQdLE42eU2Fs7NoRIZrHJAlaCOE=
 golang.org/x/oauth2 v0.30.0 h1:dnDm7JmhM45NNpd8FDDeLhK6FwqbOf4MLCM9zb1BOHI=
 golang.org/x/oauth2 v0.30.0/go.mod h1:B++QgG3ZKulg6sRPGD/mqlHQs5rB3Ml9erfeDY7xKlU=
+golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20220704084225-05e143d24a9e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.13.0 h1:Af8nKPmuFypiUBjVoU9V20FiaFXOcuZI21p0ycVYYGE=
 golang.org/x/sys v0.13.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
+golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.13.0 h1:ablQoSUd0tRdKxZewP80B+BaqeKJuVhuRxj/dkrun3k=
 golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
+golang.org/x/time v0.14.0 h1:MRx4UaLrDotUKUdCIqzPC48t1Y9hANFKIRpNx+Te8PI=
+golang.org/x/time v0.14.0/go.mod h1:eL/Oa2bBBK0TkX57Fyni+NgnyQQN4LitPmob2Hjnqw4=
+golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20200619180055-7c47624df98f/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
+golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.34.0 h1:qIpSLOxeCYGg9TrcJokLBG4KFA6d795g0xkBkiESGlo=
 golang.org/x/tools v0.34.0/go.mod h1:pAP9OwEaY1CAW3HOmg3hLZC5Z0CCmzjAF2UQMSqNARg=
+golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
 google.golang.org/protobuf v1.30.0 h1:kPPoIgf3TsEvrm0PFe15JQ+570QVxYzEvvHqChK+cng=
 google.golang.org/protobuf v1.30.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=

internal/agent/memory_compressor.go

@@ -345,8 +345,29 @@ func (mc *MemoryCompressor) adjustRecentStartForToolCalls(msgs []ChatMessage, re
 		adjusted--
 	}
 
+	// Ensure at least one user message is included in recent messages to avoid Qwen model error
+	// Qwen models require a user message in the message array, otherwise they return:
+	// "No user query found in messages"
+	hasUserMessage := false
+	for i := adjusted; i < len(msgs); i++ {
+		if strings.EqualFold(msgs[i].Role, "user") {
+			hasUserMessage = true
+			break
+		}
+	}
+
+	// If no user message in recent messages, adjust backwards to include one
+	if !hasUserMessage {
+		for adjusted > 0 {
+			adjusted--
+			if strings.EqualFold(msgs[adjusted].Role, "user") {
+				break
+			}
+		}
+	}
+
 	if adjusted != recentStart {
-		mc.logger.Debug("adjusted recent window to keep tool call context",
+		mc.logger.Debug("adjusted recent window to keep tool call context and user message",
 			zap.Int("original_recent_start", recentStart),
 			zap.Int("adjusted_recent_start", adjusted),
 		)

internal/app/app.go

@@ -7,6 +7,7 @@ import (
 	"net/http"
 	"os"
 	"path/filepath"
+	"sync"
 	"time"
 
 	"cyberstrike-ai/internal/agent"
@@ -14,6 +15,7 @@ import (
 	"cyberstrike-ai/internal/database"
 	"cyberstrike-ai/internal/handler"
 	"cyberstrike-ai/internal/knowledge"
+	"cyberstrike-ai/internal/robot"
 	"cyberstrike-ai/internal/logger"
 	"cyberstrike-ai/internal/mcp"
 	"cyberstrike-ai/internal/mcp/builtin"
@@ -43,6 +45,10 @@ type App struct {
 	knowledgeIndexer   *knowledge.Indexer        // 知识库索引器（用于动态初始化）
 	knowledgeHandler   *handler.KnowledgeHandler // 知识库处理器（用于动态初始化）
 	agentHandler       *handler.AgentHandler     // Agent处理器（用于更新知识库管理器）
+	robotHandler       *handler.RobotHandler     // 机器人处理器（钉钉/飞书/企业微信）
+	robotMu            sync.Mutex                 // 保护钉钉/飞书长连接的 cancel
+	dingCancel         context.CancelFunc        // 钉钉 Stream 取消函数，用于配置变更时重启
+	larkCancel         context.CancelFunc        // 飞书长连接取消函数，用于配置变更时重启
 }
 
 // New 创建新应用
@@ -192,7 +198,7 @@ func New(cfg *config.Config, log *logger.Logger) (*App, error) {
 		knowledgeRetriever = knowledge.NewRetriever(knowledgeDB, embedder, retrievalConfig, log.Logger)
 
 		// 创建索引器
-		knowledgeIndexer = knowledge.NewIndexer(knowledgeDB, embedder, log.Logger)
+		knowledgeIndexer = knowledge.NewIndexer(knowledgeDB, embedder, log.Logger, &cfg.Knowledge.Indexing)
 
 		// 注册知识检索工具到MCP服务器
 		knowledge.RegisterKnowledgeTool(mcpServer, knowledgeRetriever, knowledgeManager, log.Logger)
@@ -319,12 +325,14 @@ func New(cfg *config.Config, log *logger.Logger) (*App, error) {
 	roleHandler.SetSkillsManager(skillsManager) // 设置Skills管理器到RoleHandler
 	skillsHandler := handler.NewSkillsHandler(skillsManager, cfg, configPath, log.Logger)
 	fofaHandler := handler.NewFofaHandler(cfg, log.Logger)
+	terminalHandler := handler.NewTerminalHandler(log.Logger)
 	if db != nil {
 		skillsHandler.SetDB(db) // 设置数据库连接以便获取调用统计
 	}
 
 	// 创建OpenAPI处理器
 	conversationHandler := handler.NewConversationHandler(db, log.Logger)
+	robotHandler := handler.NewRobotHandler(cfg, db, agentHandler, log.Logger)
 	openAPIHandler := handler.NewOpenAPIHandler(db, log.Logger, resultStorage, conversationHandler, agentHandler)
 
 	// 创建 App 实例（部分字段稍后填充）
@@ -344,7 +352,10 @@ func New(cfg *config.Config, log *logger.Logger) (*App, error) {
 		knowledgeIndexer:   knowledgeIndexer,
 		knowledgeHandler:   knowledgeHandler,
 		agentHandler:       agentHandler,
+		robotHandler:       robotHandler,
 	}
+	// 飞书/钉钉长连接（无需公网），启用时在后台启动；后续前端应用配置时会通过 RestartRobotConnections 重启
+	app.startRobotConnections()
 
 	// 设置漏洞工具注册器（内置工具，必须设置）
 	vulnerabilityRegistrar := func() error {
@@ -401,6 +412,9 @@ func New(cfg *config.Config, log *logger.Logger) (*App, error) {
 		configHandler.SetRetrieverUpdater(knowledgeRetriever)
 	}
 
+	// 设置机器人连接重启器，前端应用配置后无需重启服务即可使钉钉/飞书新配置生效
+	configHandler.SetRobotRestarter(app)
+
 	// 设置路由（使用 App 实例以便动态获取 handler）
 	setupRoutes(
 		router,
@@ -408,6 +422,7 @@ func New(cfg *config.Config, log *logger.Logger) (*App, error) {
 		agentHandler,
 		monitorHandler,
 		conversationHandler,
+		robotHandler,
 		groupHandler,
 		configHandler,
 		externalMCPHandler,
@@ -417,6 +432,7 @@ func New(cfg *config.Config, log *logger.Logger) (*App, error) {
 		roleHandler,
 		skillsHandler,
 		fofaHandler,
+		terminalHandler,
 		mcpServer,
 		authManager,
 		openAPIHandler,
@@ -452,6 +468,18 @@ func (a *App) Run() error {
 
 // Shutdown 关闭应用
 func (a *App) Shutdown() {
+	// 停止钉钉/飞书长连接
+	a.robotMu.Lock()
+	if a.dingCancel != nil {
+		a.dingCancel()
+		a.dingCancel = nil
+	}
+	if a.larkCancel != nil {
+		a.larkCancel()
+		a.larkCancel = nil
+	}
+	a.robotMu.Unlock()
+
 	// 停止所有外部MCP客户端
 	if a.externalMCPMgr != nil {
 		a.externalMCPMgr.StopAll()
@@ -465,6 +493,40 @@ func (a *App) Shutdown() {
 	}
 }
 
+// startRobotConnections 根据当前配置启动钉钉/飞书长连接（不先关闭已有连接，仅用于首次启动）
+func (a *App) startRobotConnections() {
+	a.robotMu.Lock()
+	defer a.robotMu.Unlock()
+	cfg := a.config
+	if cfg.Robots.Lark.Enabled && cfg.Robots.Lark.AppID != "" && cfg.Robots.Lark.AppSecret != "" {
+		ctx, cancel := context.WithCancel(context.Background())
+		a.larkCancel = cancel
+		go robot.StartLark(ctx, cfg.Robots.Lark, a.robotHandler, a.logger.Logger)
+	}
+	if cfg.Robots.Dingtalk.Enabled && cfg.Robots.Dingtalk.ClientID != "" && cfg.Robots.Dingtalk.ClientSecret != "" {
+		ctx, cancel := context.WithCancel(context.Background())
+		a.dingCancel = cancel
+		go robot.StartDing(ctx, cfg.Robots.Dingtalk, a.robotHandler, a.logger.Logger)
+	}
+}
+
+// RestartRobotConnections 重启钉钉/飞书长连接，使前端应用配置后立即生效（实现 handler.RobotRestarter）
+func (a *App) RestartRobotConnections() {
+	a.robotMu.Lock()
+	if a.dingCancel != nil {
+		a.dingCancel()
+		a.dingCancel = nil
+	}
+	if a.larkCancel != nil {
+		a.larkCancel()
+		a.larkCancel = nil
+	}
+	a.robotMu.Unlock()
+	// 给旧 goroutine 一点时间退出
+	time.Sleep(200 * time.Millisecond)
+	a.startRobotConnections()
+}
+
 // setupRoutes 设置路由
 func setupRoutes(
 	router *gin.Engine,
@@ -472,6 +534,7 @@ func setupRoutes(
 	agentHandler *handler.AgentHandler,
 	monitorHandler *handler.MonitorHandler,
 	conversationHandler *handler.ConversationHandler,
+	robotHandler *handler.RobotHandler,
 	groupHandler *handler.GroupHandler,
 	configHandler *handler.ConfigHandler,
 	externalMCPHandler *handler.ExternalMCPHandler,
@@ -481,6 +544,7 @@ func setupRoutes(
 	roleHandler *handler.RoleHandler,
 	skillsHandler *handler.SkillsHandler,
 	fofaHandler *handler.FofaHandler,
+	terminalHandler *handler.TerminalHandler,
 	mcpServer *mcp.Server,
 	authManager *security.AuthManager,
 	openAPIHandler *handler.OpenAPIHandler,
@@ -497,9 +561,18 @@ func setupRoutes(
 		authRoutes.GET("/validate", security.AuthMiddleware(authManager), authHandler.Validate)
 	}
 
+	// 机器人回调（无需登录，供企业微信/钉钉/飞书服务器调用）
+	api.GET("/robot/wecom", robotHandler.HandleWecomGET)
+	api.POST("/robot/wecom", robotHandler.HandleWecomPOST)
+	api.POST("/robot/dingtalk", robotHandler.HandleDingtalkPOST)
+	api.POST("/robot/lark", robotHandler.HandleLarkPOST)
+
 	protected := api.Group("")
 	protected.Use(security.AuthMiddleware(authManager))
 	{
+		// 机器人测试（需登录）：POST /api/robot/test，body: {"platform":"dingtalk","user_id":"test","text":"帮助"}，用于验证机器人逻辑
+		protected.POST("/robot/test", robotHandler.HandleRobotTest)
+
 		// Agent Loop
 		protected.POST("/agent-loop", agentHandler.AgentLoop)
 		// Agent Loop 流式输出
@@ -558,6 +631,11 @@ func setupRoutes(
 		protected.PUT("/config", configHandler.UpdateConfig)
 		protected.POST("/config/apply", configHandler.ApplyConfig)
 
+		// 系统设置 - 终端（执行命令，提高运维效率）
+		protected.POST("/terminal/run", terminalHandler.RunCommand)
+		protected.POST("/terminal/run/stream", terminalHandler.RunCommandStream)
+		protected.GET("/terminal/ws", terminalHandler.RunCommandWS)
+
 		// 外部MCP管理
 		protected.GET("/external-mcp", externalMCPHandler.GetExternalMCPs)
 		protected.GET("/external-mcp/stats", externalMCPHandler.GetExternalMCPStats)
@@ -1024,7 +1102,7 @@ func initializeKnowledge(
 	knowledgeRetriever := knowledge.NewRetriever(knowledgeDB, embedder, retrievalConfig, logger)
 
 	// 创建索引器
-	knowledgeIndexer := knowledge.NewIndexer(knowledgeDB, embedder, logger)
+	knowledgeIndexer := knowledge.NewIndexer(knowledgeDB, embedder, logger, &cfg.Knowledge.Indexing)
 
 	// 注册知识检索工具到MCP服务器
 	knowledge.RegisterKnowledgeTool(mcpServer, knowledgeRetriever, knowledgeManager, logger)

internal/config/config.go

@@ -25,11 +25,44 @@ type Config struct {
 	Auth        AuthConfig            `yaml:"auth"`
 	ExternalMCP ExternalMCPConfig     `yaml:"external_mcp,omitempty"`
 	Knowledge   KnowledgeConfig       `yaml:"knowledge,omitempty"`
+	Robots      RobotsConfig          `yaml:"robots,omitempty" json:"robots,omitempty"`         // 企业微信/钉钉/飞书等机器人配置
 	RolesDir    string                `yaml:"roles_dir,omitempty" json:"roles_dir,omitempty"`   // 角色配置文件目录（新方式）
 	Roles       map[string]RoleConfig `yaml:"roles,omitempty" json:"roles,omitempty"`           // 向后兼容：支持在主配置文件中定义角色
 	SkillsDir   string                `yaml:"skills_dir,omitempty" json:"skills_dir,omitempty"` // Skills配置文件目录
 }
 
+// RobotsConfig 机器人配置（企业微信、钉钉、飞书等）
+type RobotsConfig struct {
+	Wecom   RobotWecomConfig   `yaml:"wecom,omitempty" json:"wecom,omitempty"`     // 企业微信
+	Dingtalk RobotDingtalkConfig `yaml:"dingtalk,omitempty" json:"dingtalk,omitempty"` // 钉钉
+	Lark    RobotLarkConfig    `yaml:"lark,omitempty" json:"lark,omitempty"`     // 飞书
+}
+
+// RobotWecomConfig 企业微信机器人配置
+type RobotWecomConfig struct {
+	Enabled       bool   `yaml:"enabled" json:"enabled"`
+	Token         string `yaml:"token" json:"token"`                     // 回调 URL 校验 Token
+	EncodingAESKey string `yaml:"encoding_aes_key" json:"encoding_aes_key"` // EncodingAESKey
+	CorpID        string `yaml:"corp_id" json:"corp_id"`               // 企业 ID
+	Secret        string `yaml:"secret" json:"secret"`                  // 应用 Secret
+	AgentID       int64  `yaml:"agent_id" json:"agent_id"`              // 应用 AgentId
+}
+
+// RobotDingtalkConfig 钉钉机器人配置
+type RobotDingtalkConfig struct {
+	Enabled      bool   `yaml:"enabled" json:"enabled"`
+	ClientID     string `yaml:"client_id" json:"client_id"`         // 应用 Key (AppKey)
+	ClientSecret string `yaml:"client_secret" json:"client_secret"` // 应用 Secret
+}
+
+// RobotLarkConfig 飞书机器人配置
+type RobotLarkConfig struct {
+	Enabled   bool   `yaml:"enabled" json:"enabled"`
+	AppID     string `yaml:"app_id" json:"app_id"`         // 应用 App ID
+	AppSecret string `yaml:"app_secret" json:"app_secret"` // 应用 App Secret
+	VerifyToken string `yaml:"verify_token" json:"verify_token"` // 事件订阅 Verification Token（可选）
+}
+
 type ServerConfig struct {
 	Host string `yaml:"host"`
 	Port int    `yaml:"port"`
@@ -549,9 +582,18 @@ func Default() *Config {
 			},
 			Retrieval: RetrievalConfig{
 				TopK:                5,
-				SimilarityThreshold: 0.7,
+				SimilarityThreshold: 0.65, // 降低阈值到 0.65，减少漏检
 				HybridWeight:        0.7,
 			},
+			Indexing: IndexingConfig{
+				ChunkSize:        768,   // 增加到 768，更好的上下文保持
+				ChunkOverlap:     50,
+				MaxChunksPerItem: 20,    // 限制单个知识项最多 20 个块，避免消耗过多配额
+				MaxRPM:           100,   // 默认 100 RPM，避免 429 错误
+				RateLimitDelayMs: 600,   // 600ms 间隔，对应 100 RPM
+				MaxRetries:       3,
+				RetryDelayMs:     1000,
+			},
 		},
 	}
 }
@@ -562,6 +604,26 @@ type KnowledgeConfig struct {
 	BasePath  string          `yaml:"base_path" json:"base_path"` // 知识库路径
 	Embedding EmbeddingConfig `yaml:"embedding" json:"embedding"`
 	Retrieval RetrievalConfig `yaml:"retrieval" json:"retrieval"`
+	Indexing  IndexingConfig  `yaml:"indexing,omitempty" json:"indexing,omitempty"` // 索引构建配置
+}
+
+// IndexingConfig 索引构建配置（用于控制知识库索引构建时的行为）
+type IndexingConfig struct {
+	// 分块配置
+	ChunkSize       int `yaml:"chunk_size,omitempty" json:"chunk_size,omitempty"`           // 每个块的最大 token 数（估算），默认 512
+	ChunkOverlap    int `yaml:"chunk_overlap,omitempty" json:"chunk_overlap,omitempty"`     // 块之间的重叠 token 数，默认 50
+	MaxChunksPerItem int `yaml:"max_chunks_per_item,omitempty" json:"max_chunks_per_item,omitempty"` // 单个知识项的最大块数量，0 表示不限制
+
+	// 速率限制配置（用于避免 API 速率限制）
+	RateLimitDelayMs int `yaml:"rate_limit_delay_ms,omitempty" json:"rate_limit_delay_ms,omitempty"` // 请求间隔时间（毫秒），0 表示不使用固定延迟
+	MaxRPM          int `yaml:"max_rpm,omitempty" json:"max_rpm,omitempty"`                         // 每分钟最大请求数，0 表示不限制
+
+	// 重试配置（用于处理临时错误）
+	MaxRetries     int `yaml:"max_retries,omitempty" json:"max_retries,omitempty"`       // 最大重试次数，默认 3
+	RetryDelayMs   int `yaml:"retry_delay_ms,omitempty" json:"retry_delay_ms,omitempty"` // 重试间隔（毫秒），默认 1000
+
+	// 批处理配置（用于批量嵌入，当前未使用，保留扩展）
+	BatchSize      int `yaml:"batch_size,omitempty" json:"batch_size,omitempty"`         // 批量处理大小，0 表示逐个处理
 }
 
 // EmbeddingConfig 嵌入配置

internal/handler/agent.go

@@ -2,10 +2,14 @@ package handler
 
 import (
 	"context"
+	"crypto/rand"
+	"encoding/base64"
 	"encoding/json"
 	"errors"
 	"fmt"
 	"net/http"
+	"os"
+	"path/filepath"
 	"strconv"
 	"strings"
 	"time"
@@ -108,11 +112,132 @@ func (h *AgentHandler) SetSkillsManager(manager *skills.Manager) {
 	h.skillsManager = manager
 }
 
+// ChatAttachment 聊天附件（用户上传的文件）
+type ChatAttachment struct {
+	FileName string `json:"fileName"` // 文件名
+	Content  string `json:"content"`  // 文本内容或 base64（由 MimeType 决定是否解码）
+	MimeType string `json:"mimeType,omitempty"`
+}
+
 // ChatRequest 聊天请求
 type ChatRequest struct {
-	Message        string `json:"message" binding:"required"`
+	Message        string            `json:"message" binding:"required"`
-	ConversationID string `json:"conversationId,omitempty"`
+	ConversationID string            `json:"conversationId,omitempty"`
-	Role           string `json:"role,omitempty"` // 角色名称
+	Role           string            `json:"role,omitempty"` // 角色名称
+	Attachments    []ChatAttachment  `json:"attachments,omitempty"`
+}
+
+const (
+	maxAttachments     = 10
+	chatUploadsDirName = "chat_uploads" // 对话附件保存的根目录（相对当前工作目录）
+)
+
+// saveAttachmentsToDateAndConversationDir 将附件保存到 chat_uploads/YYYY-MM-DD/{conversationID}/，返回每个文件的保存路径（与 attachments 顺序一致）
+// conversationID 为空时使用 "_new" 作为目录名（新对话尚未有 ID）
+func saveAttachmentsToDateAndConversationDir(attachments []ChatAttachment, conversationID string, logger *zap.Logger) (savedPaths []string, err error) {
+	if len(attachments) == 0 {
+		return nil, nil
+	}
+	cwd, err := os.Getwd()
+	if err != nil {
+		return nil, fmt.Errorf("获取当前工作目录失败: %w", err)
+	}
+	dateDir := filepath.Join(cwd, chatUploadsDirName, time.Now().Format("2006-01-02"))
+	convDirName := strings.TrimSpace(conversationID)
+	if convDirName == "" {
+		convDirName = "_new"
+	} else {
+		convDirName = strings.ReplaceAll(convDirName, string(filepath.Separator), "_")
+	}
+	targetDir := filepath.Join(dateDir, convDirName)
+	if err = os.MkdirAll(targetDir, 0755); err != nil {
+		return nil, fmt.Errorf("创建上传目录失败: %w", err)
+	}
+	savedPaths = make([]string, 0, len(attachments))
+	for i, a := range attachments {
+		raw, decErr := attachmentContentToBytes(a)
+		if decErr != nil {
+			return nil, fmt.Errorf("附件 %s 解码失败: %w", a.FileName, decErr)
+		}
+		baseName := filepath.Base(a.FileName)
+		if baseName == "" || baseName == "." {
+			baseName = "file"
+		}
+		baseName = strings.ReplaceAll(baseName, string(filepath.Separator), "_")
+		ext := filepath.Ext(baseName)
+		nameNoExt := strings.TrimSuffix(baseName, ext)
+		suffix := fmt.Sprintf("_%s_%s", time.Now().Format("150405"), shortRand(6))
+		var unique string
+		if ext != "" {
+			unique = nameNoExt + suffix + ext
+		} else {
+			unique = baseName + suffix
+		}
+		fullPath := filepath.Join(targetDir, unique)
+		if err = os.WriteFile(fullPath, raw, 0644); err != nil {
+			return nil, fmt.Errorf("写入文件 %s 失败: %w", a.FileName, err)
+		}
+		absPath, _ := filepath.Abs(fullPath)
+		savedPaths = append(savedPaths, absPath)
+		if logger != nil {
+			logger.Debug("对话附件已保存", zap.Int("index", i+1), zap.String("fileName", a.FileName), zap.String("path", absPath))
+		}
+	}
+	return savedPaths, nil
+}
+
+func shortRand(n int) string {
+	const letters = "0123456789abcdef"
+	b := make([]byte, n)
+	_, _ = rand.Read(b)
+	for i := range b {
+		b[i] = letters[int(b[i])%len(letters)]
+	}
+	return string(b)
+}
+
+func attachmentContentToBytes(a ChatAttachment) ([]byte, error) {
+	content := a.Content
+	if decoded, err := base64.StdEncoding.DecodeString(content); err == nil && len(decoded) > 0 {
+		return decoded, nil
+	}
+	return []byte(content), nil
+}
+
+// userMessageContentForStorage 返回要存入数据库的用户消息内容：有附件时在正文后追加附件名（及路径），刷新后仍能显示，继续对话时大模型也能从历史中拿到路径
+func userMessageContentForStorage(message string, attachments []ChatAttachment, savedPaths []string) string {
+	if len(attachments) == 0 {
+		return message
+	}
+	var b strings.Builder
+	b.WriteString(message)
+	for i, a := range attachments {
+		b.WriteString("\n📎 ")
+		b.WriteString(a.FileName)
+		if i < len(savedPaths) && savedPaths[i] != "" {
+			b.WriteString(": ")
+			b.WriteString(savedPaths[i])
+		}
+	}
+	return b.String()
+}
+
+// appendAttachmentsToMessage 仅将附件的保存路径追加到用户消息末尾，不再内联附件内容，避免上下文过长
+func appendAttachmentsToMessage(msg string, attachments []ChatAttachment, savedPaths []string) string {
+	if len(attachments) == 0 {
+		return msg
+	}
+	var b strings.Builder
+	b.WriteString(msg)
+	b.WriteString("\n\n[用户上传的文件已保存到以下路径（请按需读取文件内容，而不是依赖内联内容）]\n")
+	for i, a := range attachments {
+		if i < len(savedPaths) && savedPaths[i] != "" {
+			b.WriteString(fmt.Sprintf("- %s: %s\n", a.FileName, savedPaths[i]))
+		} else {
+			b.WriteString(fmt.Sprintf("- %s: （路径未知，可能保存失败）\n", a.FileName))
+		}
+	}
+	return b.String()
 }
 
 // ChatResponse 聊天响应
@@ -181,6 +306,12 @@ func (h *AgentHandler) AgentLoop(c *gin.Context) {
 		h.logger.Info("从ReAct数据恢复历史上下文", zap.Int("count", len(agentHistoryMessages)))
 	}
 
+	// 校验附件数量（非流式）
+	if len(req.Attachments) > maxAttachments {
+		c.JSON(http.StatusBadRequest, gin.H{"error": fmt.Sprintf("附件最多 %d 个", maxAttachments)})
+		return
+	}
+
 	// 应用角色用户提示词和工具配置
 	finalMessage := req.Message
 	var roleTools []string // 角色配置的工具列表
@@ -206,9 +337,20 @@ func (h *AgentHandler) AgentLoop(c *gin.Context) {
 			}
 		}
 	}
+	var savedPaths []string
+	if len(req.Attachments) > 0 {
+		savedPaths, err = saveAttachmentsToDateAndConversationDir(req.Attachments, conversationID, h.logger)
+		if err != nil {
+			h.logger.Error("保存对话附件失败", zap.Error(err))
+			c.JSON(http.StatusInternalServerError, gin.H{"error": "保存上传文件失败: " + err.Error()})
+			return
+		}
+	}
+	finalMessage = appendAttachmentsToMessage(finalMessage, req.Attachments, savedPaths)
 
-	// 保存用户消息（保存原始消息，不包含角色提示词）
+	// 保存用户消息：有附件时一并保存附件名与路径，刷新后显示、继续对话时大模型也能从历史中拿到路径
-	_, err = h.db.AddMessage(conversationID, "user", req.Message, nil)
+	userContent := userMessageContentForStorage(req.Message, req.Attachments, savedPaths)
+	_, err = h.db.AddMessage(conversationID, "user", userContent, nil)
 	if err != nil {
 		h.logger.Error("保存用户消息失败", zap.Error(err))
 		c.JSON(http.StatusInternalServerError, gin.H{"error": "保存用户消息失败: " + err.Error()})
@@ -259,6 +401,96 @@ func (h *AgentHandler) AgentLoop(c *gin.Context) {
 	})
 }
 
+// ProcessMessageForRobot 供机器人（企业微信/钉钉/飞书）调用：与 /api/agent-loop/stream 相同执行路径（含 progressCallback、过程详情），仅不发送 SSE，最后返回完整回复
+func (h *AgentHandler) ProcessMessageForRobot(ctx context.Context, conversationID, message, role string) (response string, convID string, err error) {
+	if conversationID == "" {
+		title := safeTruncateString(message, 50)
+		conv, createErr := h.db.CreateConversation(title)
+		if createErr != nil {
+			return "", "", fmt.Errorf("创建对话失败: %w", createErr)
+		}
+		conversationID = conv.ID
+	} else {
+		if _, getErr := h.db.GetConversation(conversationID); getErr != nil {
+			return "", "", fmt.Errorf("对话不存在")
+		}
+	}
+
+	agentHistoryMessages, err := h.loadHistoryFromReActData(conversationID)
+	if err != nil {
+		historyMessages, getErr := h.db.GetMessages(conversationID)
+		if getErr != nil {
+			agentHistoryMessages = []agent.ChatMessage{}
+		} else {
+			agentHistoryMessages = make([]agent.ChatMessage, 0, len(historyMessages))
+			for _, msg := range historyMessages {
+				agentHistoryMessages = append(agentHistoryMessages, agent.ChatMessage{Role: msg.Role, Content: msg.Content})
+			}
+		}
+	}
+
+	finalMessage := message
+	var roleTools, roleSkills []string
+	if role != "" && role != "默认" && h.config.Roles != nil {
+		if r, exists := h.config.Roles[role]; exists && r.Enabled {
+			if r.UserPrompt != "" {
+				finalMessage = r.UserPrompt + "\n\n" + message
+			}
+			roleTools = r.Tools
+			roleSkills = r.Skills
+		}
+	}
+
+	if _, err = h.db.AddMessage(conversationID, "user", message, nil); err != nil {
+		return "", "", fmt.Errorf("保存用户消息失败: %w", err)
+	}
+
+	// 与 agent-loop/stream 一致：先创建助手消息占位，用 progressCallback 写过程详情（不发送 SSE）
+	assistantMsg, err := h.db.AddMessage(conversationID, "assistant", "处理中...", nil)
+	if err != nil {
+		h.logger.Warn("机器人：创建助手消息占位失败", zap.Error(err))
+	}
+	var assistantMessageID string
+	if assistantMsg != nil {
+		assistantMessageID = assistantMsg.ID
+	}
+	progressCallback := h.createProgressCallback(conversationID, assistantMessageID, nil)
+
+	result, err := h.agent.AgentLoopWithProgress(ctx, finalMessage, agentHistoryMessages, conversationID, progressCallback, roleTools, roleSkills)
+	if err != nil {
+		errMsg := "执行失败: " + err.Error()
+		if assistantMessageID != "" {
+			_, _ = h.db.Exec("UPDATE messages SET content = ? WHERE id = ?", errMsg, assistantMessageID)
+			_ = h.db.AddProcessDetail(assistantMessageID, conversationID, "error", errMsg, nil)
+		}
+		return "", conversationID, err
+	}
+
+	// 更新助手消息内容与 MCP 执行 ID（与 stream 一致）
+	if assistantMessageID != "" {
+		mcpIDsJSON := ""
+		if len(result.MCPExecutionIDs) > 0 {
+			jsonData, _ := json.Marshal(result.MCPExecutionIDs)
+			mcpIDsJSON = string(jsonData)
+		}
+		_, err = h.db.Exec(
+			"UPDATE messages SET content = ?, mcp_execution_ids = ? WHERE id = ?",
+			result.Response, mcpIDsJSON, assistantMessageID,
+		)
+		if err != nil {
+			h.logger.Warn("机器人：更新助手消息失败", zap.Error(err))
+		}
+	} else {
+		if _, err = h.db.AddMessage(conversationID, "assistant", result.Response, result.MCPExecutionIDs); err != nil {
+			h.logger.Warn("机器人：保存助手消息失败", zap.Error(err))
+		}
+	}
+	if result.LastReActInput != "" || result.LastReActOutput != "" {
+		_ = h.db.SaveReActData(conversationID, result.LastReActInput, result.LastReActOutput)
+	}
+	return result.Response, conversationID, nil
+}
+
 // StreamEvent 流式事件
 type StreamEvent struct {
 	Type    string      `json:"type"`    // conversation, progress, tool_call, tool_result, response, error, cancelled, done
@@ -528,6 +760,12 @@ func (h *AgentHandler) AgentLoopStream(c *gin.Context) {
 		h.logger.Info("从ReAct数据恢复历史上下文", zap.Int("count", len(agentHistoryMessages)))
 	}
 
+	// 校验附件数量
+	if len(req.Attachments) > maxAttachments {
+		sendEvent("error", fmt.Sprintf("附件最多 %d 个", maxAttachments), nil)
+		return
+	}
+
 	// 应用角色用户提示词和工具配置
 	finalMessage := req.Message
 	var roleTools []string // 角色配置的工具列表
@@ -555,10 +793,22 @@ func (h *AgentHandler) AgentLoopStream(c *gin.Context) {
 			}
 		}
 	}
+	var savedPaths []string
+	if len(req.Attachments) > 0 {
+		savedPaths, err = saveAttachmentsToDateAndConversationDir(req.Attachments, conversationID, h.logger)
+		if err != nil {
+			h.logger.Error("保存对话附件失败", zap.Error(err))
+			sendEvent("error", "保存上传文件失败: "+err.Error(), nil)
+			return
+		}
+	}
+	// 仅将附件保存路径追加到 finalMessage，避免将文件内容内联到大模型上下文中
+	finalMessage = appendAttachmentsToMessage(finalMessage, req.Attachments, savedPaths)
 	// 如果roleTools为空，表示使用所有工具（默认角色或未配置工具的角色）
 
-	// 保存用户消息（保存原始消息，不包含角色提示词）
+	// 保存用户消息：有附件时一并保存附件名与路径，刷新后显示、继续对话时大模型也能从历史中拿到路径
-	_, err = h.db.AddMessage(conversationID, "user", req.Message, nil)
+	userContent := userMessageContentForStorage(req.Message, req.Attachments, savedPaths)
+	_, err = h.db.AddMessage(conversationID, "user", userContent, nil)
 	if err != nil {
 		h.logger.Error("保存用户消息失败", zap.Error(err))
 	}
@@ -1194,7 +1444,8 @@ func (h *AgentHandler) executeBatchQueue(queueID string) {
 		// 执行任务（使用包含角色提示词的finalMessage和角色工具列表）
 		h.logger.Info("执行批量任务", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("message", task.Message), zap.String("role", queue.Role), zap.String("conversationId", conversationID))
 
-		ctx, cancel := context.WithTimeout(context.Background(), 30*time.Minute)
+		// 单个子任务超时时间：从30分钟调整为6小时，适配长时间渗透/扫描任务
+		ctx, cancel := context.WithTimeout(context.Background(), 6*time.Hour)
 		// 存储取消函数，以便在取消队列时能够取消当前任务
 		h.batchTaskManager.SetTaskCancel(queueID, cancel)
 		// 使用队列配置的角色工具列表（如果为空，表示使用所有工具）

internal/handler/config.go

@@ -44,6 +44,11 @@ type AppUpdater interface {
 	UpdateKnowledgeComponents(handler *KnowledgeHandler, manager interface{}, retriever interface{}, indexer interface{})
 }
 
+// RobotRestarter 机器人连接重启器（用于配置应用后重启钉钉/飞书长连接）
+type RobotRestarter interface {
+	RestartRobotConnections()
+}
+
 // ConfigHandler 配置处理器
 type ConfigHandler struct {
 	configPath                 string
@@ -59,6 +64,7 @@ type ConfigHandler struct {
 	retrieverUpdater           RetrieverUpdater           // 检索器更新器（可选）
 	knowledgeInitializer       KnowledgeInitializer       // 知识库初始化器（可选）
 	appUpdater                 AppUpdater                 // App更新器（可选）
+	robotRestarter             RobotRestarter             // 机器人连接重启器（可选），ApplyConfig 时重启钉钉/飞书
 	logger                     *zap.Logger
 	mu                         sync.RWMutex
 	lastEmbeddingConfig        *config.EmbeddingConfig // 上一次的嵌入模型配置（用于检测变更）
@@ -142,6 +148,13 @@ func (h *ConfigHandler) SetAppUpdater(updater AppUpdater) {
 	h.appUpdater = updater
 }
 
+// SetRobotRestarter 设置机器人连接重启器（ApplyConfig 时用于重启钉钉/飞书长连接）
+func (h *ConfigHandler) SetRobotRestarter(restarter RobotRestarter) {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+	h.robotRestarter = restarter
+}
+
 // GetConfigResponse 获取配置响应
 type GetConfigResponse struct {
 	OpenAI    config.OpenAIConfig    `json:"openai"`
@@ -150,6 +163,7 @@ type GetConfigResponse struct {
 	Tools     []ToolConfigInfo       `json:"tools"`
 	Agent     config.AgentConfig     `json:"agent"`
 	Knowledge config.KnowledgeConfig `json:"knowledge"`
+	Robots    config.RobotsConfig     `json:"robots,omitempty"`
 }
 
 // ToolConfigInfo 工具配置信息
@@ -222,6 +236,7 @@ func (h *ConfigHandler) GetConfig(c *gin.Context) {
 		Tools:     tools,
 		Agent:     h.config.Agent,
 		Knowledge: h.config.Knowledge,
+		Robots:    h.config.Robots,
 	})
 }
 
@@ -479,6 +494,7 @@ type UpdateConfigRequest struct {
 	Tools     []ToolEnableStatus      `json:"tools,omitempty"`
 	Agent     *config.AgentConfig     `json:"agent,omitempty"`
 	Knowledge *config.KnowledgeConfig `json:"knowledge,omitempty"`
+	Robots    *config.RobotsConfig    `json:"robots,omitempty"`
 }
 
 // ToolEnableStatus 工具启用状态
@@ -555,6 +571,16 @@ func (h *ConfigHandler) UpdateConfig(c *gin.Context) {
 		)
 	}
 
+	// 更新机器人配置
+	if req.Robots != nil {
+		h.config.Robots = *req.Robots
+		h.logger.Info("更新机器人配置",
+			zap.Bool("wecom_enabled", h.config.Robots.Wecom.Enabled),
+			zap.Bool("dingtalk_enabled", h.config.Robots.Dingtalk.Enabled),
+			zap.Bool("lark_enabled", h.config.Robots.Lark.Enabled),
+		)
+	}
+
 	// 更新工具启用状态
 	if req.Tools != nil {
 		// 分离内部工具和外部工具
@@ -824,6 +850,12 @@ func (h *ConfigHandler) ApplyConfig(c *gin.Context) {
 		}
 	}
 
+	// 重启钉钉/飞书长连接，使前端修改的机器人配置立即生效（无需重启服务）
+	if h.robotRestarter != nil {
+		h.robotRestarter.RestartRobotConnections()
+		h.logger.Info("已触发机器人连接重启（钉钉/飞书）")
+	}
+
 	h.logger.Info("配置已应用",
 		zap.Int("tools_count", len(h.config.Security.Tools)),
 	)
@@ -856,6 +888,7 @@ func (h *ConfigHandler) saveConfig() error {
 	updateOpenAIConfig(root, h.config.OpenAI)
 	updateFOFAConfig(root, h.config.FOFA)
 	updateKnowledgeConfig(root, h.config.Knowledge)
+	updateRobotsConfig(root, h.config.Robots)
 	// 更新外部MCP配置（使用external_mcp.go中的函数，同一包中可直接调用）
 	// 读取原始配置以保持向后兼容
 	originalConfigs := make(map[string]map[string]bool)
@@ -1029,6 +1062,40 @@ func updateKnowledgeConfig(doc *yaml.Node, cfg config.KnowledgeConfig) {
 	setIntInMap(retrievalNode, "top_k", cfg.Retrieval.TopK)
 	setFloatInMap(retrievalNode, "similarity_threshold", cfg.Retrieval.SimilarityThreshold)
 	setFloatInMap(retrievalNode, "hybrid_weight", cfg.Retrieval.HybridWeight)
+
+	// 更新索引配置
+	indexingNode := ensureMap(knowledgeNode, "indexing")
+	setIntInMap(indexingNode, "chunk_size", cfg.Indexing.ChunkSize)
+	setIntInMap(indexingNode, "chunk_overlap", cfg.Indexing.ChunkOverlap)
+	setIntInMap(indexingNode, "max_chunks_per_item", cfg.Indexing.MaxChunksPerItem)
+	setIntInMap(indexingNode, "max_rpm", cfg.Indexing.MaxRPM)
+	setIntInMap(indexingNode, "rate_limit_delay_ms", cfg.Indexing.RateLimitDelayMs)
+	setIntInMap(indexingNode, "max_retries", cfg.Indexing.MaxRetries)
+	setIntInMap(indexingNode, "retry_delay_ms", cfg.Indexing.RetryDelayMs)
+}
+
+func updateRobotsConfig(doc *yaml.Node, cfg config.RobotsConfig) {
+	root := doc.Content[0]
+	robotsNode := ensureMap(root, "robots")
+
+	wecomNode := ensureMap(robotsNode, "wecom")
+	setBoolInMap(wecomNode, "enabled", cfg.Wecom.Enabled)
+	setStringInMap(wecomNode, "token", cfg.Wecom.Token)
+	setStringInMap(wecomNode, "encoding_aes_key", cfg.Wecom.EncodingAESKey)
+	setStringInMap(wecomNode, "corp_id", cfg.Wecom.CorpID)
+	setStringInMap(wecomNode, "secret", cfg.Wecom.Secret)
+	setIntInMap(wecomNode, "agent_id", int(cfg.Wecom.AgentID))
+
+	dingtalkNode := ensureMap(robotsNode, "dingtalk")
+	setBoolInMap(dingtalkNode, "enabled", cfg.Dingtalk.Enabled)
+	setStringInMap(dingtalkNode, "client_id", cfg.Dingtalk.ClientID)
+	setStringInMap(dingtalkNode, "client_secret", cfg.Dingtalk.ClientSecret)
+
+	larkNode := ensureMap(robotsNode, "lark")
+	setBoolInMap(larkNode, "enabled", cfg.Lark.Enabled)
+	setStringInMap(larkNode, "app_id", cfg.Lark.AppID)
+	setStringInMap(larkNode, "app_secret", cfg.Lark.AppSecret)
+	setStringInMap(larkNode, "verify_token", cfg.Lark.VerifyToken)
 }
 
 func ensureMap(parent *yaml.Node, path ...string) *yaml.Node {

internal/handler/knowledge.go

@@ -75,7 +75,7 @@ func (h *KnowledgeHandler) GetItems(c *gin.Context) {
 			groupedByCategory[cat] = append(groupedByCategory[cat], item)
 		}
 
-		// 转换为CategoryWithItems格式
+		// 转换为 CategoryWithItems 格式
 		categoriesWithItems := make([]*knowledge.CategoryWithItems, 0, len(groupedByCategory))
 		for cat, catItems := range groupedByCategory {
 			categoriesWithItems = append(categoriesWithItems, &knowledge.CategoryWithItems{
@@ -107,7 +107,7 @@ func (h *KnowledgeHandler) GetItems(c *gin.Context) {
 	categoryPageMode := c.Query("categoryPage") != "false" // 默认使用分类分页
 
 	// 分页参数
-	limit := 50 // 默认每页50条（分类分页时为分类数，项分页时为项数）
+	limit := 50 // 默认每页 50 条（分类分页时为分类数，项分页时为项数）
 	offset := 0
 	if limitStr := c.Query("limit"); limitStr != "" {
 		if parsed, err := parseInt(limitStr); err == nil && parsed > 0 && parsed <= 500 {
@@ -120,7 +120,7 @@ func (h *KnowledgeHandler) GetItems(c *gin.Context) {
 		}
 	}
 
-	// 如果指定了category参数，且使用分类分页模式，则只返回该分类
+	// 如果指定了 category 参数，且使用分类分页模式，则只返回该分类
 	if category != "" && categoryPageMode {
 		// 单分类模式：返回该分类的所有知识项（不分页）
 		items, total, err := h.manager.GetItemsSummary(category, 0, 0)
@@ -150,9 +150,9 @@ func (h *KnowledgeHandler) GetItems(c *gin.Context) {
 
 	if categoryPageMode {
 		// 按分类分页模式（默认）
-		// limit表示每页分类数，推荐5-10个分类
+		// limit 表示每页分类数，推荐 5-10 个分类
 		if limit <= 0 || limit > 100 {
-			limit = 10 // 默认每页10个分类
+			limit = 10 // 默认每页 10 个分类
 		}
 
 		categoriesWithItems, totalCategories, err := h.manager.GetCategoriesWithItems(limit, offset)
@@ -172,7 +172,7 @@ func (h *KnowledgeHandler) GetItems(c *gin.Context) {
 	}
 
 	// 按项分页模式（向后兼容）
-	// 是否包含完整内容（默认false，只返回摘要）
+	// 是否包含完整内容（默认 false，只返回摘要）
 	includeContent := c.Query("includeContent") == "true"
 
 	if includeContent {
@@ -358,7 +358,7 @@ func (h *KnowledgeHandler) ScanKnowledgeBase(c *gin.Context) {
 					)
 				}
 
-				// 如果连续失败2次，立即停止增量索引
+				// 如果连续失败 2 次，立即停止增量索引
 				if consecutiveFailures >= 2 {
 					h.logger.Error("连续索引失败次数过多，立即停止增量索引",
 						zap.Int("consecutiveFailures", consecutiveFailures),
@@ -397,7 +397,7 @@ func (h *KnowledgeHandler) ScanKnowledgeBase(c *gin.Context) {
 func (h *KnowledgeHandler) GetRetrievalLogs(c *gin.Context) {
 	conversationID := c.Query("conversationId")
 	messageID := c.Query("messageId")
-	limit := 50 // 默认50条
+	limit := 50 // 默认 50 条
 
 	if limitStr := c.Query("limit"); limitStr != "" {
 		if parsed, err := parseInt(limitStr); err == nil && parsed > 0 {
@@ -441,18 +441,40 @@ func (h *KnowledgeHandler) GetIndexStatus(c *gin.Context) {
 	if h.indexer != nil {
 		lastError, lastErrorTime := h.indexer.GetLastError()
 		if lastError != "" {
-			// 如果错误是最近发生的（5分钟内），则返回错误信息
+			// 如果错误是最近发生的（5 分钟内），则返回错误信息
 			if time.Since(lastErrorTime) < 5*time.Minute {
 				status["last_error"] = lastError
 				status["last_error_time"] = lastErrorTime.Format(time.RFC3339)
 			}
 		}
+
+		// 获取重建索引状态
+		isRebuilding, totalItems, current, failed, lastItemID, lastChunks, startTime := h.indexer.GetRebuildStatus()
+		if isRebuilding {
+			status["is_rebuilding"] = true
+			status["rebuild_total"] = totalItems
+			status["rebuild_current"] = current
+			status["rebuild_failed"] = failed
+			status["rebuild_start_time"] = startTime.Format(time.RFC3339)
+			if lastItemID != "" {
+				status["rebuild_last_item_id"] = lastItemID
+			}
+			if lastChunks > 0 {
+				status["rebuild_last_chunks"] = lastChunks
+			}
+			// 重建中时，is_complete 为 false
+			status["is_complete"] = false
+			// 计算重建进度百分比
+			if totalItems > 0 {
+				status["progress_percent"] = float64(current) / float64(totalItems) * 100
+			}
+		}
 	}
 
 	c.JSON(http.StatusOK, status)
 }
 
-// Search 搜索知识库（用于API调用，Agent内部使用Retriever）
+// Search 搜索知识库（用于 API 调用，Agent 内部使用 Retriever）
 func (h *KnowledgeHandler) Search(c *gin.Context) {
 	var req knowledge.SearchRequest
 	if err := c.ShouldBindJSON(&req); err != nil {

internal/handler/robot.go

@@ -0,0 +1,897 @@
+package handler
+
+import (
+	"bytes"
+	"context"
+	"crypto/aes"
+	"crypto/cipher"
+	"crypto/rand"
+	"crypto/sha1"
+	"encoding/base64"
+	"encoding/binary"
+	"encoding/json"
+	"encoding/xml"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"sort"
+	"strings"
+	"sync"
+	"time"
+
+	"cyberstrike-ai/internal/config"
+	"cyberstrike-ai/internal/database"
+
+	"github.com/gin-gonic/gin"
+	"go.uber.org/zap"
+)
+
+const (
+	robotCmdHelp        = "帮助"
+	robotCmdList        = "列表"
+	robotCmdListAlt     = "对话列表"
+	robotCmdSwitch      = "切换"
+	robotCmdContinue    = "继续"
+	robotCmdNew         = "新对话"
+	robotCmdClear       = "清空"
+	robotCmdCurrent     = "当前"
+	robotCmdStop        = "停止"
+	robotCmdRoles       = "角色"
+	robotCmdRolesList   = "角色列表"
+	robotCmdSwitchRole  = "切换角色"
+	robotCmdDelete      = "删除"
+	robotCmdVersion     = "版本"
+)
+
+// RobotHandler 企业微信/钉钉/飞书等机器人回调处理
+type RobotHandler struct {
+	config         *config.Config
+	db             *database.DB
+	agentHandler   *AgentHandler
+	logger         *zap.Logger
+	mu             sync.RWMutex
+	sessions       map[string]string             // key: "platform_userID", value: conversationID
+	sessionRoles   map[string]string             // key: "platform_userID", value: roleName（默认"默认"）
+	cancelMu       sync.Mutex                    // 保护 runningCancels
+	runningCancels map[string]context.CancelFunc // key: "platform_userID", 用于停止命令中断任务
+}
+
+// NewRobotHandler 创建机器人处理器
+func NewRobotHandler(cfg *config.Config, db *database.DB, agentHandler *AgentHandler, logger *zap.Logger) *RobotHandler {
+	return &RobotHandler{
+		config:         cfg,
+		db:             db,
+		agentHandler:   agentHandler,
+		logger:         logger,
+		sessions:       make(map[string]string),
+		sessionRoles:   make(map[string]string),
+		runningCancels: make(map[string]context.CancelFunc),
+	}
+}
+
+// sessionKey 生成会话 key
+func (h *RobotHandler) sessionKey(platform, userID string) string {
+	return platform + "_" + userID
+}
+
+// getOrCreateConversation 获取或创建当前会话，title 用于新对话的标题（取用户首条消息前50字）
+func (h *RobotHandler) getOrCreateConversation(platform, userID, title string) (convID string, isNew bool) {
+	h.mu.RLock()
+	convID = h.sessions[h.sessionKey(platform, userID)]
+	h.mu.RUnlock()
+	if convID != "" {
+		return convID, false
+	}
+	t := strings.TrimSpace(title)
+	if t == "" {
+		t = "新对话 " + time.Now().Format("01-02 15:04")
+	} else {
+		t = safeTruncateString(t, 50)
+	}
+	conv, err := h.db.CreateConversation(t)
+	if err != nil {
+		h.logger.Warn("创建机器人会话失败", zap.Error(err))
+		return "", false
+	}
+	convID = conv.ID
+	h.mu.Lock()
+	h.sessions[h.sessionKey(platform, userID)] = convID
+	h.mu.Unlock()
+	return convID, true
+}
+
+// setConversation 切换当前会话
+func (h *RobotHandler) setConversation(platform, userID, convID string) {
+	h.mu.Lock()
+	h.sessions[h.sessionKey(platform, userID)] = convID
+	h.mu.Unlock()
+}
+
+// getRole 获取当前用户使用的角色，未设置时返回"默认"
+func (h *RobotHandler) getRole(platform, userID string) string {
+	h.mu.RLock()
+	role := h.sessionRoles[h.sessionKey(platform, userID)]
+	h.mu.RUnlock()
+	if role == "" {
+		return "默认"
+	}
+	return role
+}
+
+// setRole 设置当前用户使用的角色
+func (h *RobotHandler) setRole(platform, userID, roleName string) {
+	h.mu.Lock()
+	h.sessionRoles[h.sessionKey(platform, userID)] = roleName
+	h.mu.Unlock()
+}
+
+// clearConversation 清空当前会话（切换到新对话）
+func (h *RobotHandler) clearConversation(platform, userID string) (newConvID string) {
+	title := "新对话 " + time.Now().Format("01-02 15:04")
+	conv, err := h.db.CreateConversation(title)
+	if err != nil {
+		h.logger.Warn("创建新对话失败", zap.Error(err))
+		return ""
+	}
+	h.setConversation(platform, userID, conv.ID)
+	return conv.ID
+}
+
+// HandleMessage 处理用户输入，返回回复文本（供各平台 webhook 调用）
+func (h *RobotHandler) HandleMessage(platform, userID, text string) (reply string) {
+	text = strings.TrimSpace(text)
+	if text == "" {
+		return "请输入内容或发送「帮助」/ help 查看命令。"
+	}
+
+	// 先尝试作为命令处理（支持中英文）
+	if cmdReply, ok := h.handleRobotCommand(platform, userID, text); ok {
+		return cmdReply
+	}
+
+	// 普通消息：走 Agent
+	convID, _ := h.getOrCreateConversation(platform, userID, text)
+	if convID == "" {
+		return "无法创建或获取对话，请稍后再试。"
+	}
+	// 若对话标题为「新对话 xx:xx」格式（由「新对话」命令创建），将标题更新为首条消息内容，与 Web 端体验一致
+	if conv, err := h.db.GetConversation(convID); err == nil && strings.HasPrefix(conv.Title, "新对话 ") {
+		newTitle := safeTruncateString(text, 50)
+		if newTitle != "" {
+			_ = h.db.UpdateConversationTitle(convID, newTitle)
+		}
+	}
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Minute)
+	sk := h.sessionKey(platform, userID)
+	h.cancelMu.Lock()
+	h.runningCancels[sk] = cancel
+	h.cancelMu.Unlock()
+	defer func() {
+		cancel()
+		h.cancelMu.Lock()
+		delete(h.runningCancels, sk)
+		h.cancelMu.Unlock()
+	}()
+	role := h.getRole(platform, userID)
+	resp, newConvID, err := h.agentHandler.ProcessMessageForRobot(ctx, convID, text, role)
+	if err != nil {
+		h.logger.Warn("机器人 Agent 执行失败", zap.String("platform", platform), zap.String("userID", userID), zap.Error(err))
+		if errors.Is(err, context.Canceled) {
+			return "任务已取消。"
+		}
+		return "处理失败: " + err.Error()
+	}
+	if newConvID != convID {
+		h.setConversation(platform, userID, newConvID)
+	}
+	return resp
+}
+
+func (h *RobotHandler) cmdHelp() string {
+	return "**【CyberStrikeAI 机器人命令】**\n\n" +
+		"- `帮助` `help` — 显示本帮助 | Show this help\n" +
+		"- `列表` `list` — 列出所有对话标题与 ID | List conversations\n" +
+		"- `切换 <ID>` `switch <ID>` — 指定对话继续 | Switch to conversation\n" +
+		"- `新对话` `new` — 开启新对话 | Start new conversation\n" +
+		"- `清空` `clear` — 清空当前上下文 | Clear context\n" +
+		"- `当前` `current` — 显示当前对话 ID 与标题 | Show current conversation\n" +
+		"- `停止` `stop` — 中断当前任务 | Stop running task\n" +
+		"- `角色` `roles` — 列出所有可用角色 | List roles\n" +
+		"- `角色 <名>` `role <name>` — 切换当前角色 | Switch role\n" +
+		"- `删除 <ID>` `delete <ID>` — 删除指定对话 | Delete conversation\n" +
+		"- `版本` `version` — 显示当前版本号 | Show version\n\n" +
+		"---\n" +
+		"除以上命令外，直接输入内容将发送给 AI 进行渗透测试/安全分析。\n" +
+		"Otherwise, send any text for AI penetration testing / security analysis."
+}
+
+func (h *RobotHandler) cmdList() string {
+	convs, err := h.db.ListConversations(50, 0, "")
+	if err != nil {
+		return "获取对话列表失败: " + err.Error()
+	}
+	if len(convs) == 0 {
+		return "暂无对话。发送任意内容将自动创建新对话。"
+	}
+	var b strings.Builder
+	b.WriteString("【对话列表】\n")
+	for i, c := range convs {
+		if i >= 20 {
+			b.WriteString("… 仅显示前 20 条\n")
+			break
+		}
+		b.WriteString(fmt.Sprintf("· %s\n  ID: %s\n", c.Title, c.ID))
+	}
+	return strings.TrimSuffix(b.String(), "\n")
+}
+
+func (h *RobotHandler) cmdSwitch(platform, userID, convID string) string {
+	if convID == "" {
+		return "请指定对话 ID，例如：切换 xxx-xxx-xxx"
+	}
+	conv, err := h.db.GetConversation(convID)
+	if err != nil {
+		return "对话不存在或 ID 错误。"
+	}
+	h.setConversation(platform, userID, conv.ID)
+	return fmt.Sprintf("已切换到对话：「%s」\nID: %s", conv.Title, conv.ID)
+}
+
+func (h *RobotHandler) cmdNew(platform, userID string) string {
+	newID := h.clearConversation(platform, userID)
+	if newID == "" {
+		return "创建新对话失败，请重试。"
+	}
+	return "已开启新对话，可直接发送内容。"
+}
+
+func (h *RobotHandler) cmdClear(platform, userID string) string {
+	return h.cmdNew(platform, userID)
+}
+
+func (h *RobotHandler) cmdStop(platform, userID string) string {
+	sk := h.sessionKey(platform, userID)
+	h.cancelMu.Lock()
+	cancel, ok := h.runningCancels[sk]
+	if ok {
+		delete(h.runningCancels, sk)
+		cancel()
+	}
+	h.cancelMu.Unlock()
+	if !ok {
+		return "当前没有正在执行的任务。"
+	}
+	return "已停止当前任务。"
+}
+
+func (h *RobotHandler) cmdCurrent(platform, userID string) string {
+	h.mu.RLock()
+	convID := h.sessions[h.sessionKey(platform, userID)]
+	h.mu.RUnlock()
+	if convID == "" {
+		return "当前没有进行中的对话。发送任意内容将创建新对话。"
+	}
+	conv, err := h.db.GetConversation(convID)
+	if err != nil {
+		return "当前对话 ID: " + convID + "（获取标题失败）"
+	}
+	role := h.getRole(platform, userID)
+	return fmt.Sprintf("当前对话：「%s」\nID: %s\n当前角色: %s", conv.Title, conv.ID, role)
+}
+
+func (h *RobotHandler) cmdRoles() string {
+	if h.config.Roles == nil || len(h.config.Roles) == 0 {
+		return "暂无可用角色。"
+	}
+	names := make([]string, 0, len(h.config.Roles))
+	for name, role := range h.config.Roles {
+		if role.Enabled {
+			names = append(names, name)
+		}
+	}
+	if len(names) == 0 {
+		return "暂无可用角色。"
+	}
+	sort.Slice(names, func(i, j int) bool {
+		if names[i] == "默认" {
+			return true
+		}
+		if names[j] == "默认" {
+			return false
+		}
+		return names[i] < names[j]
+	})
+	var b strings.Builder
+	b.WriteString("【角色列表】\n")
+	for _, name := range names {
+		role := h.config.Roles[name]
+		desc := role.Description
+		if desc == "" {
+			desc = "无描述"
+		}
+		b.WriteString(fmt.Sprintf("· %s — %s\n", name, desc))
+	}
+	return strings.TrimSuffix(b.String(), "\n")
+}
+
+func (h *RobotHandler) cmdSwitchRole(platform, userID, roleName string) string {
+	if roleName == "" {
+		return "请指定角色名称，例如：角色 渗透测试"
+	}
+	if h.config.Roles == nil {
+		return "暂无可用角色。"
+	}
+	role, exists := h.config.Roles[roleName]
+	if !exists {
+		return fmt.Sprintf("角色「%s」不存在。发送「角色」查看可用角色。", roleName)
+	}
+	if !role.Enabled {
+		return fmt.Sprintf("角色「%s」已禁用。", roleName)
+	}
+	h.setRole(platform, userID, roleName)
+	return fmt.Sprintf("已切换到角色：「%s」\n%s", roleName, role.Description)
+}
+
+func (h *RobotHandler) cmdDelete(platform, userID, convID string) string {
+	if convID == "" {
+		return "请指定对话 ID，例如：删除 xxx-xxx-xxx"
+	}
+	sk := h.sessionKey(platform, userID)
+	h.mu.RLock()
+	currentConvID := h.sessions[sk]
+	h.mu.RUnlock()
+	if convID == currentConvID {
+		// 删除当前对话时，先清空会话绑定
+		h.mu.Lock()
+		delete(h.sessions, sk)
+		h.mu.Unlock()
+	}
+	if err := h.db.DeleteConversation(convID); err != nil {
+		return "删除失败: " + err.Error()
+	}
+	return fmt.Sprintf("已删除对话 ID: %s", convID)
+}
+
+func (h *RobotHandler) cmdVersion() string {
+	v := h.config.Version
+	if v == "" {
+		v = "未知"
+	}
+	return "CyberStrikeAI " + v
+}
+
+// handleRobotCommand 处理机器人内置命令；若匹配到命令返回 (回复内容, true)，否则返回 ("", false)
+func (h *RobotHandler) handleRobotCommand(platform, userID, text string) (string, bool) {
+	switch {
+	case text == robotCmdHelp || text == "help" || text == "？" || text == "?":
+		return h.cmdHelp(), true
+	case text == robotCmdList || text == robotCmdListAlt || text == "list":
+		return h.cmdList(), true
+	case strings.HasPrefix(text, robotCmdSwitch+" ") || strings.HasPrefix(text, robotCmdContinue+" ") || strings.HasPrefix(text, "switch ") || strings.HasPrefix(text, "continue "):
+		var id string
+		switch {
+		case strings.HasPrefix(text, robotCmdSwitch+" "):
+			id = strings.TrimSpace(text[len(robotCmdSwitch)+1:])
+		case strings.HasPrefix(text, robotCmdContinue+" "):
+			id = strings.TrimSpace(text[len(robotCmdContinue)+1:])
+		case strings.HasPrefix(text, "switch "):
+			id = strings.TrimSpace(text[7:])
+		default:
+			id = strings.TrimSpace(text[9:])
+		}
+		return h.cmdSwitch(platform, userID, id), true
+	case text == robotCmdNew || text == "new":
+		return h.cmdNew(platform, userID), true
+	case text == robotCmdClear || text == "clear":
+		return h.cmdClear(platform, userID), true
+	case text == robotCmdCurrent || text == "current":
+		return h.cmdCurrent(platform, userID), true
+	case text == robotCmdStop || text == "stop":
+		return h.cmdStop(platform, userID), true
+	case text == robotCmdRoles || text == robotCmdRolesList || text == "roles":
+		return h.cmdRoles(), true
+	case strings.HasPrefix(text, robotCmdRoles+" ") || strings.HasPrefix(text, robotCmdSwitchRole+" ") || strings.HasPrefix(text, "role "):
+		var roleName string
+		switch {
+		case strings.HasPrefix(text, robotCmdRoles+" "):
+			roleName = strings.TrimSpace(text[len(robotCmdRoles)+1:])
+		case strings.HasPrefix(text, robotCmdSwitchRole+" "):
+			roleName = strings.TrimSpace(text[len(robotCmdSwitchRole)+1:])
+		default:
+			roleName = strings.TrimSpace(text[5:])
+		}
+		return h.cmdSwitchRole(platform, userID, roleName), true
+	case strings.HasPrefix(text, robotCmdDelete+" ") || strings.HasPrefix(text, "delete "):
+		var convID string
+		if strings.HasPrefix(text, robotCmdDelete+" ") {
+			convID = strings.TrimSpace(text[len(robotCmdDelete)+1:])
+		} else {
+			convID = strings.TrimSpace(text[7:])
+		}
+		return h.cmdDelete(platform, userID, convID), true
+	case text == robotCmdVersion || text == "version":
+		return h.cmdVersion(), true
+	default:
+		return "", false
+	}
+}
+
+// —————— 企业微信 ——————
+
+// wecomXML 企业微信回调 XML（明文模式下的简化结构；加密模式需先解密再解析）
+type wecomXML struct {
+	ToUserName   string `xml:"ToUserName"`
+	FromUserName string `xml:"FromUserName"`
+	CreateTime   int64  `xml:"CreateTime"`
+	MsgType      string `xml:"MsgType"`
+	Content      string `xml:"Content"`
+	MsgID        string `xml:"MsgId"`
+	AgentID      int64  `xml:"AgentID"`
+	Encrypt      string `xml:"Encrypt"` // 加密模式下消息在此
+}
+
+// wecomReplyXML 被动回复 XML（仅用于兼容，当前使用手动构造 XML）
+type wecomReplyXML struct {
+	XMLName      xml.Name `xml:"xml"`
+	ToUserName   string   `xml:"ToUserName"`
+	FromUserName string   `xml:"FromUserName"`
+	CreateTime   int64    `xml:"CreateTime"`
+	MsgType      string   `xml:"MsgType"`
+	Content      string   `xml:"Content"`
+}
+
+// HandleWecomGET 企业微信 URL 校验（GET）
+func (h *RobotHandler) HandleWecomGET(c *gin.Context) {
+	if !h.config.Robots.Wecom.Enabled {
+		c.String(http.StatusNotFound, "")
+		return
+	}
+	// Gin 的 Query() 会自动 URL 解码，拿到的就是正确的 base64 字符串
+	echostr := c.Query("echostr")
+	msgSignature := c.Query("msg_signature")
+	timestamp := c.Query("timestamp")
+	nonce := c.Query("nonce")
+
+	// 验证签名：将 token、timestamp、nonce、echostr 四个参数排序后拼接计算 SHA1
+	signature := h.signWecomRequest(h.config.Robots.Wecom.Token, timestamp, nonce, echostr)
+	if signature != msgSignature {
+		h.logger.Warn("企业微信 URL 验证签名失败", zap.String("expected", msgSignature), zap.String("got", signature))
+		c.String(http.StatusBadRequest, "invalid signature")
+		return
+	}
+
+	if echostr == "" {
+		c.String(http.StatusBadRequest, "missing echostr")
+		return
+	}
+
+	// 如果配置了 EncodingAESKey，说明是加密模式，需要解密 echostr
+	if h.config.Robots.Wecom.EncodingAESKey != "" {
+		decrypted, err := wecomDecrypt(h.config.Robots.Wecom.EncodingAESKey, echostr)
+		if err != nil {
+			h.logger.Warn("企业微信 echostr 解密失败", zap.Error(err))
+			c.String(http.StatusBadRequest, "decrypt failed")
+			return
+		}
+		c.String(http.StatusOK, string(decrypted))
+		return
+	}
+
+	// 明文模式直接返回 echostr
+	c.String(http.StatusOK, echostr)
+}
+
+// signWecomRequest 生成企业微信请求签名
+// 企业微信签名算法：将 token、timestamp、nonce、echostr 四个值排序后拼接成字符串，再计算 SHA1
+func (h *RobotHandler) signWecomRequest(token, timestamp, nonce, echostr string) string {
+	strs := []string{token, timestamp, nonce, echostr}
+	sort.Strings(strs)
+	s := strings.Join(strs, "")
+	hash := sha1.Sum([]byte(s))
+	return fmt.Sprintf("%x", hash)
+}
+
+// wecomDecrypt 企业微信消息解密（AES-256-CBC，PKCS7，明文格式：16字节随机+4字节长度+消息+corpID）
+func wecomDecrypt(encodingAESKey, encryptedB64 string) ([]byte, error) {
+	key, err := base64.StdEncoding.DecodeString(encodingAESKey + "=")
+	if err != nil {
+		return nil, err
+	}
+	if len(key) != 32 {
+		return nil, fmt.Errorf("encoding_aes_key 解码后应为 32 字节")
+	}
+	ciphertext, err := base64.StdEncoding.DecodeString(encryptedB64)
+	if err != nil {
+		return nil, err
+	}
+	block, err := aes.NewCipher(key)
+	if err != nil {
+		return nil, err
+	}
+	iv := key[:16]
+	mode := cipher.NewCBCDecrypter(block, iv)
+	if len(ciphertext)%aes.BlockSize != 0 {
+		return nil, fmt.Errorf("密文长度不是块大小的倍数")
+	}
+	plain := make([]byte, len(ciphertext))
+	mode.CryptBlocks(plain, ciphertext)
+	// 去除 PKCS7 填充
+	n := int(plain[len(plain)-1])
+	if n < 1 || n > 32 {
+		return nil, fmt.Errorf("无效的 PKCS7 填充")
+	}
+	plain = plain[:len(plain)-n]
+	// 企业微信格式：16 字节随机 + 4 字节长度(大端) + 消息 + corpID
+	if len(plain) < 20 {
+		return nil, fmt.Errorf("明文过短")
+	}
+	msgLen := binary.BigEndian.Uint32(plain[16:20])
+	if int(20+msgLen) > len(plain) {
+		return nil, fmt.Errorf("消息长度越界")
+	}
+	return plain[20 : 20+msgLen], nil
+}
+
+// wecomEncrypt 企业微信消息加密（AES-256-CBC，PKCS7，明文格式：16字节随机+4字节长度+消息+corpID）
+func wecomEncrypt(encodingAESKey, message, corpID string) (string, error) {
+	key, err := base64.StdEncoding.DecodeString(encodingAESKey + "=")
+	if err != nil {
+		return "", err
+	}
+	if len(key) != 32 {
+		return "", fmt.Errorf("encoding_aes_key 解码后应为 32 字节")
+	}
+	// 构造明文：16 字节随机 + 4 字节长度 (大端) + 消息 + corpID
+	random := make([]byte, 16)
+	if _, err := rand.Read(random); err != nil {
+		// 降级方案：使用时间戳生成随机数
+		for i := range random {
+			random[i] = byte(time.Now().UnixNano() % 256)
+		}
+	}
+	msgLen := len(message)
+	msgBytes := []byte(message)
+	corpBytes := []byte(corpID)
+	plain := make([]byte, 16+4+msgLen+len(corpBytes))
+	copy(plain[:16], random)
+	binary.BigEndian.PutUint32(plain[16:20], uint32(msgLen))
+	copy(plain[20:20+msgLen], msgBytes)
+	copy(plain[20+msgLen:], corpBytes)
+	// PKCS7 填充
+	padding := aes.BlockSize - len(plain)%aes.BlockSize
+	pad := bytes.Repeat([]byte{byte(padding)}, padding)
+	plain = append(plain, pad...)
+	// AES-256-CBC 加密
+	block, err := aes.NewCipher(key)
+	if err != nil {
+		return "", err
+	}
+	iv := key[:16]
+	ciphertext := make([]byte, len(plain))
+	mode := cipher.NewCBCEncrypter(block, iv)
+	mode.CryptBlocks(ciphertext, plain)
+	return base64.StdEncoding.EncodeToString(ciphertext), nil
+}
+
+// HandleWecomPOST 企业微信消息回调（POST），支持明文与加密模式
+func (h *RobotHandler) HandleWecomPOST(c *gin.Context) {
+	if !h.config.Robots.Wecom.Enabled {
+		h.logger.Debug("企业微信机器人未启用，跳过请求")
+		c.String(http.StatusOK, "")
+		return
+	}
+	// 从 URL 获取签名参数（加密模式回复时需要用到）
+	timestamp := c.Query("timestamp")
+	nonce := c.Query("nonce")
+	msgSignature := c.Query("msg_signature")
+
+	// 先读取请求体，后续解析/签名验证都会用到
+	bodyRaw, err := io.ReadAll(c.Request.Body)
+	if err != nil {
+		h.logger.Warn("企业微信 POST 读取请求体失败", zap.Error(err))
+		c.String(http.StatusOK, "")
+		return
+	}
+	h.logger.Debug("企业微信 POST 收到请求", zap.String("body", string(bodyRaw)))
+
+	// 验证请求签名防止伪造。企业微信签名算法同 URL 验证，使用 token、timestamp、nonce、 Encrypt 四个字段
+	if msgSignature != "" {
+		var tmp wecomXML
+		if err := xml.Unmarshal(bodyRaw, &tmp); err == nil {
+			expected := h.signWecomRequest(h.config.Robots.Wecom.Token, timestamp, nonce, tmp.Encrypt)
+			if expected != msgSignature {
+				h.logger.Warn("企业微信 POST 签名验证失败", zap.String("expected", expected), zap.String("got", msgSignature))
+				c.String(http.StatusOK, "")
+				return
+			}
+		}
+	}
+
+	var body wecomXML
+	if err := xml.Unmarshal(bodyRaw, &body); err != nil {
+		h.logger.Warn("企业微信 POST 解析 XML 失败", zap.Error(err))
+		c.String(http.StatusOK, "")
+		return
+	}
+	h.logger.Debug("企业微信 XML 解析成功", zap.String("ToUserName", body.ToUserName), zap.String("FromUserName", body.FromUserName), zap.String("MsgType", body.MsgType), zap.String("Content", body.Content), zap.String("Encrypt", body.Encrypt))
+
+	// 保存企业 ID（用于明文模式回复）
+	enterpriseID := body.ToUserName
+
+	// 加密模式：先解密再解析内层 XML
+	if body.Encrypt != "" && h.config.Robots.Wecom.EncodingAESKey != "" {
+		h.logger.Debug("企业微信进入加密模式解密流程")
+		decrypted, err := wecomDecrypt(h.config.Robots.Wecom.EncodingAESKey, body.Encrypt)
+		if err != nil {
+			h.logger.Warn("企业微信消息解密失败", zap.Error(err))
+			c.String(http.StatusOK, "")
+			return
+		}
+		h.logger.Debug("企业微信解密成功", zap.String("decrypted", string(decrypted)))
+		if err := xml.Unmarshal(decrypted, &body); err != nil {
+			h.logger.Warn("企业微信解密后 XML 解析失败", zap.Error(err))
+			c.String(http.StatusOK, "")
+			return
+		}
+		h.logger.Debug("企业微信内层 XML 解析成功", zap.String("FromUserName", body.FromUserName), zap.String("Content", body.Content))
+	}
+
+	userID := body.FromUserName
+	text := strings.TrimSpace(body.Content)
+
+	// 限制回复内容长度（企业微信限制 2048 字节）
+	maxReplyLen := 2000
+	limitReply := func(s string) string {
+		if len(s) > maxReplyLen {
+			return s[:maxReplyLen] + "\n\n（内容过长，已截断）"
+		}
+		return s
+	}
+
+	if body.MsgType != "text" {
+		h.logger.Debug("企业微信收到非文本消息", zap.String("MsgType", body.MsgType))
+		h.sendWecomReply(c, userID, enterpriseID, limitReply("暂仅支持文本消息，请发送文字。"), timestamp, nonce)
+		return
+	}
+
+	// 文本消息：先判断是否为内置命令（如 帮助/列表/新对话 等），这类命令处理很快，可以直接走被动回复，避免依赖主动发送 API。
+	if cmdReply, ok := h.handleRobotCommand("wecom", userID, text); ok {
+		h.logger.Debug("企业微信收到命令消息，走被动回复", zap.String("userID", userID), zap.String("text", text))
+		h.sendWecomReply(c, userID, enterpriseID, limitReply(cmdReply), timestamp, nonce)
+		return
+	}
+
+	h.logger.Debug("企业微信开始处理消息（异步 AI）", zap.String("userID", userID), zap.String("text", text))
+
+	// 企业微信被动回复有 5 秒超时限制，而 AI 调用通常超过该时长。
+	// 这里采用推荐做法：立即返回 success（或空串），然后通过主动发送接口推送完整回复。
+	c.String(http.StatusOK, "success")
+
+	// 异步处理消息并通过企业微信主动消息接口发送结果
+	go func() {
+		reply := h.HandleMessage("wecom", userID, text)
+		reply = limitReply(reply)
+		h.logger.Debug("企业微信消息处理完成", zap.String("userID", userID), zap.String("reply", reply))
+		// 调用企业微信 API 主动发送消息
+		h.sendWecomMessageViaAPI(userID, enterpriseID, reply)
+	}()
+}
+
+// sendWecomReply 发送企业微信回复（加密模式自动加密）
+// 参数：toUser=用户 ID, fromUser=企业 ID（明文模式）/CorpID（加密模式）, content=回复内容，timestamp/nonce=请求参数
+func (h *RobotHandler) sendWecomReply(c *gin.Context, toUser, fromUser, content, timestamp, nonce string) {
+	// 加密模式：判断 EncodingAESKey 是否配置
+	if h.config.Robots.Wecom.EncodingAESKey != "" {
+		// 加密模式使用 CorpID 进行加密
+		corpID := h.config.Robots.Wecom.CorpID
+		if corpID == "" {
+			h.logger.Warn("企业微信加密模式缺少 CorpID 配置")
+			c.String(http.StatusOK, "")
+			return
+		}
+
+		// 构造完整的明文 XML 回复（格式严格按企业微信文档要求）
+		plainResp := fmt.Sprintf(`<xml>
+<ToUserName><![CDATA[%s]]></ToUserName>
+<FromUserName><![CDATA[%s]]></FromUserName>
+<CreateTime>%d</CreateTime>
+<MsgType><![CDATA[text]]></MsgType>
+<Content><![CDATA[%s]]></Content>
+</xml>`, toUser, fromUser, time.Now().Unix(), content)
+
+		encrypted, err := wecomEncrypt(h.config.Robots.Wecom.EncodingAESKey, plainResp, corpID)
+		if err != nil {
+			h.logger.Warn("企业微信回复加密失败", zap.Error(err))
+			c.String(http.StatusOK, "")
+			return
+		}
+		// 使用请求中的 timestamp/nonce 生成签名（企业微信要求回复时使用与请求相同的 timestamp 和 nonce）
+		msgSignature := h.signWecomRequest(h.config.Robots.Wecom.Token, timestamp, nonce, encrypted)
+
+		h.logger.Debug("企业微信发送加密回复",
+			zap.String("Encrypt", encrypted[:50]+"..."),
+			zap.String("MsgSignature", msgSignature),
+			zap.String("TimeStamp", timestamp),
+			zap.String("Nonce", nonce))
+
+		// 加密模式仅返回 4 个核心字段（企业微信官方要求）
+		xmlResp := fmt.Sprintf(`<xml><Encrypt><![CDATA[%s]]></Encrypt><MsgSignature><![CDATA[%s]]></MsgSignature><TimeStamp><![CDATA[%s]]></TimeStamp><Nonce><![CDATA[%s]]></Nonce></xml>`, encrypted, msgSignature, timestamp, nonce)
+		// also log the final response body so we can cross-check with the
+		// network traffic or developer console
+		h.logger.Debug("企业微信加密回复包", zap.String("xml", xmlResp))
+		// for additional confidence, decrypt the payload ourselves and log it
+		if dec, err2 := wecomDecrypt(h.config.Robots.Wecom.EncodingAESKey, encrypted); err2 == nil {
+			h.logger.Debug("企业微信加密回复解密检查", zap.String("plain", string(dec)))
+		} else {
+			h.logger.Warn("企业微信加密回复解密检查失败", zap.Error(err2))
+		}
+
+		// 使用 c.Writer.Write 直接写入响应，避免 c.String 的转义问题
+		c.Writer.WriteHeader(http.StatusOK)
+		// use text/xml as that's what WeCom examples show
+		c.Writer.Header().Set("Content-Type", "text/xml; charset=utf-8")
+		_, _ = c.Writer.Write([]byte(xmlResp))
+		h.logger.Debug("企业微信加密回复已发送")
+		return
+	}
+
+	// 明文模式
+	h.logger.Debug("企业微信发送明文回复", zap.String("ToUserName", toUser), zap.String("FromUserName", fromUser), zap.String("Content", content[:50]+"..."))
+
+	// 手动构造 XML 响应（使用 CDATA 包裹所有字段，并包含 AgentID）
+	xmlResp := fmt.Sprintf(`<xml>
+<ToUserName><![CDATA[%s]]></ToUserName>
+<FromUserName><![CDATA[%s]]></FromUserName>
+<CreateTime>%d</CreateTime>
+<MsgType><![CDATA[text]]></MsgType>
+<Content><![CDATA[%s]]></Content>
+</xml>`, toUser, fromUser, time.Now().Unix(), content)
+
+	// log the exact plaintext response for debugging
+	h.logger.Debug("企业微信明文回复包", zap.String("xml", xmlResp))
+
+	// use text/xml as recommended by WeCom docs
+	c.Header("Content-Type", "text/xml; charset=utf-8")
+	c.String(http.StatusOK, xmlResp)
+	h.logger.Debug("企业微信明文回复已发送")
+}
+
+// —————— 测试接口（需登录，用于验证机器人逻辑，无需钉钉/飞书客户端） ——————
+
+// RobotTestRequest 模拟机器人消息请求
+type RobotTestRequest struct {
+	Platform string `json:"platform"` // 如 "dingtalk"、"lark"、"wecom"
+	UserID   string `json:"user_id"`
+	Text     string `json:"text"`
+}
+
+// HandleRobotTest 供本地验证：POST JSON { "platform", "user_id", "text" }，返回 { "reply": "..." }
+func (h *RobotHandler) HandleRobotTest(c *gin.Context) {
+	var req RobotTestRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "请求体需为 JSON，包含 platform、user_id、text"})
+		return
+	}
+	platform := strings.TrimSpace(req.Platform)
+	if platform == "" {
+		platform = "test"
+	}
+	userID := strings.TrimSpace(req.UserID)
+	if userID == "" {
+		userID = "test_user"
+	}
+	reply := h.HandleMessage(platform, userID, req.Text)
+	c.JSON(http.StatusOK, gin.H{"reply": reply})
+}
+
+// sendWecomMessageViaAPI 通过企业微信 API 主动发送消息（用于异步处理后的结果发送）
+func (h *RobotHandler) sendWecomMessageViaAPI(toUser, toParty, content string) {
+	if !h.config.Robots.Wecom.Enabled {
+		return
+	}
+
+	secret := h.config.Robots.Wecom.Secret
+	corpID := h.config.Robots.Wecom.CorpID
+	agentID := h.config.Robots.Wecom.AgentID
+
+	if secret == "" || corpID == "" {
+		h.logger.Warn("企业微信主动 API 缺少 secret 或 corpID 配置")
+		return
+	}
+
+	// 第 1 步：获取 access_token
+	tokenURL := fmt.Sprintf("https://qyapi.weixin.qq.com/cgi-bin/gettoken?corpid=%s&corpsecret=%s", corpID, secret)
+	resp, err := http.Get(tokenURL)
+	if err != nil {
+		h.logger.Warn("企业微信获取 token 失败", zap.Error(err))
+		return
+	}
+	defer resp.Body.Close()
+
+	var tokenResp struct {
+		AccessToken string `json:"access_token"`
+		ErrCode     int    `json:"errcode"`
+		ErrMsg      string `json:"errmsg"`
+	}
+	if err := json.NewDecoder(resp.Body).Decode(&tokenResp); err != nil {
+		h.logger.Warn("企业微信 token 响应解析失败", zap.Error(err))
+		return
+	}
+	if tokenResp.ErrCode != 0 {
+		h.logger.Warn("企业微信 token 获取错误", zap.String("errmsg", tokenResp.ErrMsg), zap.Int("errcode", tokenResp.ErrCode))
+		return
+	}
+
+	// 第 2 步：构造发送消息请求
+	msgReq := map[string]interface{}{
+		"touser":  toUser,
+		"msgtype": "text",
+		"agentid": agentID,
+		"text": map[string]interface{}{
+			"content": content,
+		},
+	}
+
+	msgBody, err := json.Marshal(msgReq)
+	if err != nil {
+		h.logger.Warn("企业微信消息序列化失败", zap.Error(err))
+		return
+	}
+
+	// 第 3 步：发送消息
+	sendURL := fmt.Sprintf("https://qyapi.weixin.qq.com/cgi-bin/message/send?access_token=%s", tokenResp.AccessToken)
+	msgResp, err := http.Post(sendURL, "application/json", bytes.NewReader(msgBody))
+	if err != nil {
+		h.logger.Warn("企业微信主动发送消息失败", zap.Error(err))
+		return
+	}
+	defer msgResp.Body.Close()
+
+	var sendResp struct {
+		ErrCode     int    `json:"errcode"`
+		ErrMsg      string `json:"errmsg"`
+		InvalidUser string `json:"invaliduser"`
+		MsgID       string `json:"msgid"`
+	}
+	if err := json.NewDecoder(msgResp.Body).Decode(&sendResp); err != nil {
+		h.logger.Warn("企业微信发送响应解析失败", zap.Error(err))
+		return
+	}
+
+	if sendResp.ErrCode == 0 {
+		h.logger.Debug("企业微信主动发送消息成功", zap.String("msgid", sendResp.MsgID))
+	} else {
+		h.logger.Warn("企业微信主动发送消息失败", zap.String("errmsg", sendResp.ErrMsg), zap.Int("errcode", sendResp.ErrCode), zap.String("invaliduser", sendResp.InvalidUser))
+	}
+}
+
+// —————— 钉钉 ——————
+
+// HandleDingtalkPOST 钉钉事件回调（流式接入等）；当前为占位，返回 200
+func (h *RobotHandler) HandleDingtalkPOST(c *gin.Context) {
+	if !h.config.Robots.Dingtalk.Enabled {
+		c.JSON(http.StatusOK, gin.H{})
+		return
+	}
+	// 钉钉流式/事件回调格式需按官方文档解析并异步回复，此处仅返回 200
+	c.JSON(http.StatusOK, gin.H{"message": "ok"})
+}
+
+// —————— 飞书 ——————
+
+// HandleLarkPOST 飞书事件回调；当前为占位，返回 200；验证时需返回 challenge
+func (h *RobotHandler) HandleLarkPOST(c *gin.Context) {
+	if !h.config.Robots.Lark.Enabled {
+		c.JSON(http.StatusOK, gin.H{})
+		return
+	}
+	var body struct {
+		Challenge string `json:"challenge"`
+	}
+	if err := c.ShouldBindJSON(&body); err == nil && body.Challenge != "" {
+		c.JSON(http.StatusOK, gin.H{"challenge": body.Challenge})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{})
+}

internal/handler/terminal.go

@@ -0,0 +1,257 @@
+package handler
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"net/http"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"runtime"
+	"strings"
+	"time"
+
+	"github.com/gin-gonic/gin"
+	"go.uber.org/zap"
+)
+
+const (
+	terminalMaxCommandLen = 4096
+	terminalMaxOutputLen  = 256 * 1024 // 256KB
+	terminalTimeout       = 120 * time.Second
+)
+
+// TerminalHandler 处理系统设置中的终端命令执行
+type TerminalHandler struct {
+	logger *zap.Logger
+}
+
+// maskTerminalCommand 对可能包含敏感信息的终端命令做脱敏，避免在日志中直接记录密码等内容
+func maskTerminalCommand(cmd string) string {
+	trimmed := strings.TrimSpace(cmd)
+	lower := strings.ToLower(trimmed)
+	if strings.Contains(lower, "sudo") || strings.Contains(lower, "password") {
+		return "[masked sensitive terminal command]"
+	}
+	if len(trimmed) > 256 {
+		return trimmed[:256] + "..."
+	}
+	return trimmed
+}
+
+// NewTerminalHandler 创建终端处理器
+func NewTerminalHandler(logger *zap.Logger) *TerminalHandler {
+	return &TerminalHandler{logger: logger}
+}
+
+// RunCommandRequest 执行命令请求
+type RunCommandRequest struct {
+	Command string `json:"command"`
+	Shell   string `json:"shell,omitempty"`
+	Cwd     string `json:"cwd,omitempty"`
+}
+
+// RunCommandResponse 执行命令响应
+type RunCommandResponse struct {
+	Stdout   string `json:"stdout"`
+	Stderr   string `json:"stderr"`
+	ExitCode int    `json:"exit_code"`
+	Error    string `json:"error,omitempty"`
+}
+
+// RunCommand 执行终端命令（需登录）
+func (h *TerminalHandler) RunCommand(c *gin.Context) {
+	var req RunCommandRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "请求体无效，需要 command 字段"})
+		return
+	}
+
+	cmdStr := strings.TrimSpace(req.Command)
+	if cmdStr == "" {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "command 不能为空"})
+		return
+	}
+	if len(cmdStr) > terminalMaxCommandLen {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "命令过长"})
+		return
+	}
+
+	shell := req.Shell
+	if shell == "" {
+		if runtime.GOOS == "windows" {
+			shell = "cmd"
+		} else {
+			shell = "sh"
+		}
+	}
+
+	ctx, cancel := context.WithTimeout(c.Request.Context(), terminalTimeout)
+	defer cancel()
+
+	var cmd *exec.Cmd
+	if runtime.GOOS == "windows" {
+		cmd = exec.CommandContext(ctx, "cmd", "/c", cmdStr)
+	} else {
+		cmd = exec.CommandContext(ctx, shell, "-c", cmdStr)
+		// 无 TTY 时设置 COLUMNS/TERM，使 ping 等工具的 usage 排版与真实终端一致
+		cmd.Env = append(os.Environ(), "COLUMNS=256", "LINES=40", "TERM=xterm-256color")
+	}
+
+	if req.Cwd != "" {
+		absCwd, err := filepath.Abs(req.Cwd)
+		if err != nil {
+			c.JSON(http.StatusBadRequest, gin.H{"error": "工作目录无效"})
+			return
+		}
+		cur, _ := os.Getwd()
+		curAbs, _ := filepath.Abs(cur)
+		rel, err := filepath.Rel(curAbs, absCwd)
+		if err != nil || strings.HasPrefix(rel, "..") || rel == ".." {
+			c.JSON(http.StatusBadRequest, gin.H{"error": "工作目录必须在当前进程目录下"})
+			return
+		}
+		cmd.Dir = absCwd
+	}
+
+	var stdout, stderr bytes.Buffer
+	cmd.Stdout = &stdout
+	cmd.Stderr = &stderr
+
+	err := cmd.Run()
+	stdoutBytes := stdout.Bytes()
+	stderrBytes := stderr.Bytes()
+
+	// 限制输出长度，防止内存占用过大（复制后截断，避免修改原 buffer）
+	truncSuffix := []byte("\n...(输出已截断)\n")
+	if len(stdoutBytes) > terminalMaxOutputLen {
+		tmp := make([]byte, terminalMaxOutputLen+len(truncSuffix))
+		n := copy(tmp, stdoutBytes[:terminalMaxOutputLen])
+		copy(tmp[n:], truncSuffix)
+		stdoutBytes = tmp
+	}
+	if len(stderrBytes) > terminalMaxOutputLen {
+		tmp := make([]byte, terminalMaxOutputLen+len(truncSuffix))
+		n := copy(tmp, stderrBytes[:terminalMaxOutputLen])
+		copy(tmp[n:], truncSuffix)
+		stderrBytes = tmp
+	}
+
+	exitCode := 0
+	if err != nil {
+		if exitErr, ok := err.(*exec.ExitError); ok {
+			exitCode = exitErr.ExitCode()
+		} else {
+			exitCode = -1
+		}
+		if ctx.Err() == context.DeadlineExceeded {
+			so := strings.ReplaceAll(string(stdoutBytes), "\r\n", "\n")
+			so = strings.ReplaceAll(so, "\r", "\n")
+			se := strings.ReplaceAll(string(stderrBytes), "\r\n", "\n")
+			se = strings.ReplaceAll(se, "\r", "\n")
+			resp := RunCommandResponse{
+				Stdout:   so,
+				Stderr:   se,
+				ExitCode: -1,
+				Error:    "命令执行超时（" + terminalTimeout.String() + "）",
+			}
+			c.JSON(http.StatusOK, resp)
+			return
+		}
+		h.logger.Debug("终端命令执行异常", zap.String("command", maskTerminalCommand(cmdStr)), zap.Error(err))
+	}
+
+	// 统一为 \n，避免前端因 \r 出现错位/对角线排版
+	stdoutStr := strings.ReplaceAll(string(stdoutBytes), "\r\n", "\n")
+	stdoutStr = strings.ReplaceAll(stdoutStr, "\r", "\n")
+	stderrStr := strings.ReplaceAll(string(stderrBytes), "\r\n", "\n")
+	stderrStr = strings.ReplaceAll(stderrStr, "\r", "\n")
+
+	resp := RunCommandResponse{
+		Stdout:   stdoutStr,
+		Stderr:   stderrStr,
+		ExitCode: exitCode,
+	}
+	if err != nil && exitCode != 0 {
+		resp.Error = err.Error()
+	}
+	c.JSON(http.StatusOK, resp)
+}
+
+// streamEvent SSE 事件
+type streamEvent struct {
+	T string `json:"t"` // "out" | "err" | "exit"
+	D string `json:"d,omitempty"`
+	C int    `json:"c"` // exit code（不用 omitempty，否则 0 不序列化导致前端显示 [exit undefined]）
+}
+
+// RunCommandStream 流式执行命令，输出实时推送到前端（SSE）
+func (h *TerminalHandler) RunCommandStream(c *gin.Context) {
+	var req RunCommandRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "请求体无效，需要 command 字段"})
+		return
+	}
+	cmdStr := strings.TrimSpace(req.Command)
+	if cmdStr == "" {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "command 不能为空"})
+		return
+	}
+	if len(cmdStr) > terminalMaxCommandLen {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "命令过长"})
+		return
+	}
+	shell := req.Shell
+	if shell == "" {
+		if runtime.GOOS == "windows" {
+			shell = "cmd"
+		} else {
+			shell = "sh"
+		}
+	}
+	ctx, cancel := context.WithTimeout(c.Request.Context(), terminalTimeout)
+	defer cancel()
+
+	var cmd *exec.Cmd
+	if runtime.GOOS == "windows" {
+		cmd = exec.CommandContext(ctx, "cmd", "/c", cmdStr)
+	} else {
+		cmd = exec.CommandContext(ctx, shell, "-c", cmdStr)
+		cmd.Env = append(os.Environ(), "COLUMNS=256", "LINES=40", "TERM=xterm-256color")
+	}
+	if req.Cwd != "" {
+		absCwd, err := filepath.Abs(req.Cwd)
+		if err != nil {
+			c.JSON(http.StatusBadRequest, gin.H{"error": "工作目录无效"})
+			return
+		}
+		cur, _ := os.Getwd()
+		curAbs, _ := filepath.Abs(cur)
+		rel, err := filepath.Rel(curAbs, absCwd)
+		if err != nil || strings.HasPrefix(rel, "..") || rel == ".." {
+			c.JSON(http.StatusBadRequest, gin.H{"error": "工作目录必须在当前进程目录下"})
+			return
+		}
+		cmd.Dir = absCwd
+	}
+
+	c.Header("Content-Type", "text/event-stream")
+	c.Header("Cache-Control", "no-cache")
+	c.Header("Connection", "keep-alive")
+	c.Header("X-Accel-Buffering", "no")
+	c.Writer.WriteHeader(http.StatusOK)
+	flusher, ok := c.Writer.(http.Flusher)
+	if !ok {
+		cancel()
+		return
+	}
+
+	sendEvent := func(ev streamEvent) {
+		body, _ := json.Marshal(ev)
+		c.SSEvent("", string(body))
+		flusher.Flush()
+	}
+
+	runCommandStreamImpl(cmd, sendEvent, ctx)
+}

internal/handler/terminal_stream_unix.go

@@ -0,0 +1,46 @@
+//go:build !windows
+
+package handler
+
+import (
+	"bufio"
+	"context"
+	"os/exec"
+	"strings"
+
+	"github.com/creack/pty"
+)
+
+const ptyCols = 256
+const ptyRows = 40
+
+// runCommandStreamImpl 在 Unix 下用 PTY 执行，使 ping 等命令按终端宽度排版（isatty 为真）
+func runCommandStreamImpl(cmd *exec.Cmd, sendEvent func(streamEvent), ctx context.Context) {
+	ptmx, err := pty.StartWithSize(cmd, &pty.Winsize{Cols: ptyCols, Rows: ptyRows})
+	if err != nil {
+		sendEvent(streamEvent{T: "exit", C: -1})
+		return
+	}
+	defer ptmx.Close()
+
+	normalize := func(s string) string {
+		s = strings.ReplaceAll(s, "\r\n", "\n")
+		return strings.ReplaceAll(s, "\r", "\n")
+	}
+	sc := bufio.NewScanner(ptmx)
+	for sc.Scan() {
+		sendEvent(streamEvent{T: "out", D: normalize(sc.Text())})
+	}
+	exitCode := 0
+	if err := cmd.Wait(); err != nil {
+		if exitErr, ok := err.(*exec.ExitError); ok {
+			exitCode = exitErr.ExitCode()
+		} else {
+			exitCode = -1
+		}
+	}
+	if ctx.Err() == context.DeadlineExceeded {
+		exitCode = -1
+	}
+	sendEvent(streamEvent{T: "exit", C: exitCode})
+}

internal/handler/terminal_stream_windows.go

@@ -0,0 +1,65 @@
+//go:build windows
+
+package handler
+
+import (
+	"bufio"
+	"context"
+	"os/exec"
+	"strings"
+	"sync"
+)
+
+// runCommandStreamImpl 在 Windows 下用 stdout/stderr 管道执行
+func runCommandStreamImpl(cmd *exec.Cmd, sendEvent func(streamEvent), ctx context.Context) {
+	stdoutPipe, err := cmd.StdoutPipe()
+	if err != nil {
+		sendEvent(streamEvent{T: "exit", C: -1})
+		return
+	}
+	stderrPipe, err := cmd.StderrPipe()
+	if err != nil {
+		sendEvent(streamEvent{T: "exit", C: -1})
+		return
+	}
+	if err := cmd.Start(); err != nil {
+		sendEvent(streamEvent{T: "exit", C: -1})
+		return
+	}
+
+	normalize := func(s string) string {
+		s = strings.ReplaceAll(s, "\r\n", "\n")
+		return strings.ReplaceAll(s, "\r", "\n")
+	}
+
+	var wg sync.WaitGroup
+	wg.Add(2)
+	go func() {
+		defer wg.Done()
+		sc := bufio.NewScanner(stdoutPipe)
+		for sc.Scan() {
+			sendEvent(streamEvent{T: "out", D: normalize(sc.Text())})
+		}
+	}()
+	go func() {
+		defer wg.Done()
+		sc := bufio.NewScanner(stderrPipe)
+		for sc.Scan() {
+			sendEvent(streamEvent{T: "err", D: normalize(sc.Text())})
+		}
+	}()
+
+	wg.Wait()
+	exitCode := 0
+	if err := cmd.Wait(); err != nil {
+		if exitErr, ok := err.(*exec.ExitError); ok {
+			exitCode = exitErr.ExitCode()
+		} else {
+			exitCode = -1
+		}
+	}
+	if ctx.Err() == context.DeadlineExceeded {
+		exitCode = -1
+	}
+	sendEvent(streamEvent{T: "exit", C: exitCode})
+}

internal/handler/terminal_ws_unix.go

@@ -0,0 +1,95 @@
+//go:build !windows
+
+package handler
+
+import (
+	"net/http"
+	"os"
+	"os/exec"
+	"time"
+
+	"github.com/creack/pty"
+	"github.com/gin-gonic/gin"
+	"github.com/gorilla/websocket"
+)
+
+// wsUpgrader 仅用于系统设置中的终端 WebSocket，会复用已有的登录保护（JWT 中间件在上层路由组）
+var wsUpgrader = websocket.Upgrader{
+	CheckOrigin: func(r *http.Request) bool {
+		// 由于已在 Gin 路由层做了认证，这里放宽 Origin，方便在同一域名下通过 HTTPS/WSS 访问
+		return true
+	},
+}
+
+// RunCommandWS 提供真正交互式 Shell：基于 WebSocket + PTY 的长会话
+// 前端建立 WebSocket 连接后，所有键盘输入都会透传到 Shell，Shell 的输出也会实时写回前端。
+func (h *TerminalHandler) RunCommandWS(c *gin.Context) {
+	conn, err := wsUpgrader.Upgrade(c.Writer, c.Request, nil)
+	if err != nil {
+		return
+	}
+	defer conn.Close()
+
+	// 启动交互式 Shell，这里优先使用 bash，找不到则退回 sh
+	shell := "bash"
+	if _, err := exec.LookPath(shell); err != nil {
+		shell = "sh"
+	}
+	cmd := exec.Command(shell)
+	cmd.Env = append(os.Environ(),
+		"COLUMNS=256",
+		"LINES=40",
+		"TERM=xterm-256color",
+	)
+
+	ptmx, err := pty.StartWithSize(cmd, &pty.Winsize{Cols: ptyCols, Rows: ptyRows})
+	if err != nil {
+		return
+	}
+	defer ptmx.Close()
+
+	// Shell -> WebSocket：将 PTY 输出实时发给前端
+	doneChan := make(chan struct{})
+	go func() {
+		buf := make([]byte, 4096)
+		for {
+			n, err := ptmx.Read(buf)
+			if n > 0 {
+				_ = conn.WriteMessage(websocket.BinaryMessage, buf[:n])
+			}
+			if err != nil {
+				break
+			}
+		}
+		close(doneChan)
+	}()
+
+	// WebSocket -> Shell：将前端输入写入 PTY（包括 sudo 密码、Ctrl+C 等）
+	conn.SetReadLimit(64 * 1024)
+	_ = conn.SetReadDeadline(time.Now().Add(terminalTimeout))
+	conn.SetPongHandler(func(string) error {
+		_ = conn.SetReadDeadline(time.Now().Add(terminalTimeout))
+		return nil
+	})
+
+	for {
+		msgType, data, err := conn.ReadMessage()
+		if err != nil {
+			_ = cmd.Process.Kill()
+			break
+		}
+		if msgType != websocket.TextMessage && msgType != websocket.BinaryMessage {
+			continue
+		}
+		if len(data) == 0 {
+			continue
+		}
+		if _, err := ptmx.Write(data); err != nil {
+			_ = cmd.Process.Kill()
+			break
+		}
+	}
+
+	<-doneChan
+}
+

internal/knowledge/embedder.go

@@ -6,39 +6,75 @@ import (
 	"fmt"
 	"net/http"
 	"strings"
+	"sync"
 	"time"
 
 	"cyberstrike-ai/internal/config"
 	"cyberstrike-ai/internal/openai"
 
 	"go.uber.org/zap"
+	"golang.org/x/time/rate"
 )
 
 // Embedder 文本嵌入器
 type Embedder struct {
-	openAIClient *openai.Client
+	openAIClient   *openai.Client
-	config       *config.KnowledgeConfig
+	config         *config.KnowledgeConfig
-	openAIConfig *config.OpenAIConfig // 用于获取API Key
+	openAIConfig   *config.OpenAIConfig // 用于获取 API Key
-	logger       *zap.Logger
+	logger         *zap.Logger
+	rateLimiter    *rate.Limiter       // 速率限制器
+	rateLimitDelay time.Duration       // 请求间隔时间
+	maxRetries     int                 // 最大重试次数
+	retryDelay     time.Duration       // 重试间隔
+	mu             sync.Mutex          // 保护 rateLimiter
 }
 
 // NewEmbedder 创建新的嵌入器
 func NewEmbedder(cfg *config.KnowledgeConfig, openAIConfig *config.OpenAIConfig, openAIClient *openai.Client, logger *zap.Logger) *Embedder {
+	// 初始化速率限制器
+	var rateLimiter *rate.Limiter
+	var rateLimitDelay time.Duration
+
+	// 如果配置了 MaxRPM，根据 RPM 计算速率限制
+	if cfg.Indexing.MaxRPM > 0 {
+		rpm := cfg.Indexing.MaxRPM
+		rateLimiter = rate.NewLimiter(rate.Every(time.Minute/time.Duration(rpm)), rpm)
+		logger.Info("知识库索引速率限制已启用", zap.Int("maxRPM", rpm))
+	} else if cfg.Indexing.RateLimitDelayMs > 0 {
+		// 如果没有配置 MaxRPM 但配置了固定延迟，使用固定延迟模式
+		rateLimitDelay = time.Duration(cfg.Indexing.RateLimitDelayMs) * time.Millisecond
+		logger.Info("知识库索引固定延迟已启用", zap.Duration("delay", rateLimitDelay))
+	}
+
+	// 重试配置
+	maxRetries := 3
+	retryDelay := 1000 * time.Millisecond
+	if cfg.Indexing.MaxRetries > 0 {
+		maxRetries = cfg.Indexing.MaxRetries
+	}
+	if cfg.Indexing.RetryDelayMs > 0 {
+		retryDelay = time.Duration(cfg.Indexing.RetryDelayMs) * time.Millisecond
+	}
+
 	return &Embedder{
-		openAIClient: openAIClient,
+		openAIClient:   openAIClient,
-		config:       cfg,
+		config:         cfg,
-		openAIConfig: openAIConfig,
+		openAIConfig:   openAIConfig,
-		logger:       logger,
+		logger:         logger,
+		rateLimiter:    rateLimiter,
+		rateLimitDelay: rateLimitDelay,
+		maxRetries:     maxRetries,
+		retryDelay:     retryDelay,
 	}
 }
 
-// EmbeddingRequest OpenAI嵌入请求
+// EmbeddingRequest OpenAI 嵌入请求
 type EmbeddingRequest struct {
 	Model string   `json:"model"`
 	Input []string `json:"input"`
 }
 
-// EmbeddingResponse OpenAI嵌入响应
+// EmbeddingResponse OpenAI 嵌入响应
 type EmbeddingResponse struct {
 	Data []EmbeddingData `json:"data"`
 	Error *EmbeddingError `json:"error,omitempty"`
@@ -56,12 +92,69 @@ type EmbeddingError struct {
 	Type    string `json:"type"`
 }
 
-// EmbedText 对文本进行嵌入
+// waitRateLimiter 等待速率限制器
-func (e *Embedder) EmbedText(ctx context.Context, text string) ([]float32, error) {
+func (e *Embedder) waitRateLimiter() {
-	if e.openAIClient == nil {
+	e.mu.Lock()
-		return nil, fmt.Errorf("OpenAI客户端未初始化")
+	defer e.mu.Unlock()
+
+	if e.rateLimiter != nil {
+		// 等待令牌
+		ctx := context.Background()
+		if err := e.rateLimiter.Wait(ctx); err != nil {
+			e.logger.Warn("速率限制器等待失败", zap.Error(err))
+		}
 	}
 
+	if e.rateLimitDelay > 0 {
+		time.Sleep(e.rateLimitDelay)
+	}
+}
+
+// EmbedText 对文本进行嵌入（带重试和速率限制）
+func (e *Embedder) EmbedText(ctx context.Context, text string) ([]float32, error) {
+	if e.openAIClient == nil {
+		return nil, fmt.Errorf("OpenAI 客户端未初始化")
+	}
+
+	var lastErr error
+	for attempt := 0; attempt < e.maxRetries; attempt++ {
+		// 速率限制
+		if attempt > 0 {
+			// 重试时等待更长时间
+			waitTime := e.retryDelay * time.Duration(attempt)
+			e.logger.Debug("重试前等待", zap.Int("attempt", attempt+1), zap.Duration("waitTime", waitTime))
+			select {
+			case <-ctx.Done():
+				return nil, ctx.Err()
+			case <-time.After(waitTime):
+			}
+		} else {
+			e.waitRateLimiter()
+		}
+
+		result, err := e.doEmbedText(ctx, text)
+		if err == nil {
+			return result, nil
+		}
+
+		lastErr = err
+
+		// 检查是否是可重试的错误（429 速率限制、5xx 服务器错误、网络错误）
+		if !e.isRetryableError(err) {
+			return nil, err
+		}
+
+		e.logger.Debug("嵌入请求失败，准备重试",
+			zap.Int("attempt", attempt+1),
+			zap.Int("maxRetries", e.maxRetries),
+			zap.Error(err))
+	}
+
+	return nil, fmt.Errorf("达到最大重试次数 (%d): %v", e.maxRetries, lastErr)
+}
+
+// doEmbedText 执行实际的嵌入请求（内部方法）
+func (e *Embedder) doEmbedText(ctx context.Context, text string) ([]float32, error) {
 	// 使用配置的嵌入模型
 	model := e.config.Embedding.Model
 	if model == "" {
@@ -73,7 +166,7 @@ func (e *Embedder) EmbedText(ctx context.Context, text string) ([]float32, error
 		Input: []string{text},
 	}
 
-	// 清理baseURL：去除前后空格和尾部斜杠
+	// 清理 baseURL：去除前后空格和尾部斜杠
 	baseURL := strings.TrimSpace(e.config.Embedding.BaseURL)
 	baseURL = strings.TrimSuffix(baseURL, "/")
 	if baseURL == "" {
@@ -83,24 +176,24 @@ func (e *Embedder) EmbedText(ctx context.Context, text string) ([]float32, error
 	// 构建请求
 	body, err := json.Marshal(req)
 	if err != nil {
-		return nil, fmt.Errorf("序列化请求失败: %w", err)
+		return nil, fmt.Errorf("序列化请求失败：%w", err)
 	}
 
 	requestURL := baseURL + "/embeddings"
 	httpReq, err := http.NewRequestWithContext(ctx, http.MethodPost, requestURL, strings.NewReader(string(body)))
 	if err != nil {
-		return nil, fmt.Errorf("创建请求失败: %w", err)
+		return nil, fmt.Errorf("创建请求失败：%w", err)
 	}
 
 	httpReq.Header.Set("Content-Type", "application/json")
-	
+
-	// 使用配置的API Key，如果没有则使用OpenAI配置的
+	// 使用配置的 API Key，如果没有则使用 OpenAI 配置的
 	apiKey := strings.TrimSpace(e.config.Embedding.APIKey)
 	if apiKey == "" && e.openAIConfig != nil {
 		apiKey = e.openAIConfig.APIKey
 	}
 	if apiKey == "" {
-		return nil, fmt.Errorf("API Key未配置")
+		return nil, fmt.Errorf("API Key 未配置")
 	}
 	httpReq.Header.Set("Authorization", "Bearer "+apiKey)
 
@@ -110,7 +203,7 @@ func (e *Embedder) EmbedText(ctx context.Context, text string) ([]float32, error
 	}
 	resp, err := httpClient.Do(httpReq)
 	if err != nil {
-		return nil, fmt.Errorf("发送请求失败: %w", err)
+		return nil, fmt.Errorf("发送请求失败：%w", err)
 	}
 	defer resp.Body.Close()
 
@@ -132,7 +225,7 @@ func (e *Embedder) EmbedText(ctx context.Context, text string) ([]float32, error
 	if len(requestBodyPreview) > 200 {
 		requestBodyPreview = requestBodyPreview[:200] + "..."
 	}
-	e.logger.Debug("嵌入API请求",
+	e.logger.Debug("嵌入 API 请求",
 		zap.String("url", httpReq.URL.String()),
 		zap.String("model", model),
 		zap.String("requestBody", requestBodyPreview),
@@ -148,12 +241,12 @@ func (e *Embedder) EmbedText(ctx context.Context, text string) ([]float32, error
 		if len(bodyPreview) > 500 {
 			bodyPreview = bodyPreview[:500] + "..."
 		}
-		return nil, fmt.Errorf("解析响应失败 (URL: %s, 状态码: %d, 响应长度: %d字节): %w\n请求体: %s\n响应内容预览: %s",
+		return nil, fmt.Errorf("解析响应失败 (URL: %s, 状态码：%d, 响应长度：%d字节): %w\n请求体：%s\n响应内容预览：%s",
 			requestURL, resp.StatusCode, len(bodyBytes), err, requestBodyPreview, bodyPreview)
 	}
 
 	if embeddingResp.Error != nil {
-		return nil, fmt.Errorf("OpenAI API错误 (状态码: %d): 类型=%s, 消息=%s",
+		return nil, fmt.Errorf("OpenAI API 错误 (状态码：%d): 类型=%s, 消息=%s",
 			resp.StatusCode, embeddingResp.Error.Type, embeddingResp.Error.Message)
 	}
 
@@ -162,7 +255,7 @@ func (e *Embedder) EmbedText(ctx context.Context, text string) ([]float32, error
 		if len(bodyPreview) > 500 {
 			bodyPreview = bodyPreview[:500] + "..."
 		}
-		return nil, fmt.Errorf("HTTP请求失败 (URL: %s, 状态码: %d): 响应内容=%s", requestURL, resp.StatusCode, bodyPreview)
+		return nil, fmt.Errorf("HTTP 请求失败 (URL: %s, 状态码：%d): 响应内容=%s", requestURL, resp.StatusCode, bodyPreview)
 	}
 
 	if len(embeddingResp.Data) == 0 {
@@ -170,11 +263,11 @@ func (e *Embedder) EmbedText(ctx context.Context, text string) ([]float32, error
 		if len(bodyPreview) > 500 {
 			bodyPreview = bodyPreview[:500] + "..."
 		}
-		return nil, fmt.Errorf("未收到嵌入数据 (状态码: %d, 响应长度: %d字节)\n响应内容: %s",
+		return nil, fmt.Errorf("未收到嵌入数据 (状态码：%d, 响应长度：%d字节)\n响应内容：%s",
 			resp.StatusCode, len(bodyBytes), bodyPreview)
 	}
 
-	// 转换为float32
+	// 转换为 float32
 	embedding := make([]float32, len(embeddingResp.Data[0].Embedding))
 	for i, v := range embeddingResp.Data[0].Embedding {
 		embedding[i] = float32(v)
@@ -183,23 +276,48 @@ func (e *Embedder) EmbedText(ctx context.Context, text string) ([]float32, error
 	return embedding, nil
 }
 
+// isRetryableError 判断是否是可重试的错误
+func (e *Embedder) isRetryableError(err error) bool {
+	if err == nil {
+		return false
+	}
+
+	errStr := err.Error()
+
+	// 429 速率限制错误
+	if strings.Contains(errStr, "429") || strings.Contains(errStr, "rate limit") {
+		return true
+	}
+
+	// 5xx 服务器错误
+	if strings.Contains(errStr, "500") || strings.Contains(errStr, "502") ||
+		strings.Contains(errStr, "503") || strings.Contains(errStr, "504") {
+		return true
+	}
+
+	// 网络错误
+	if strings.Contains(errStr, "timeout") || strings.Contains(errStr, "connection") ||
+		strings.Contains(errStr, "network") || strings.Contains(errStr, "EOF") {
+		return true
+	}
+
+	return false
+}
+
 // EmbedTexts 批量嵌入文本
 func (e *Embedder) EmbedTexts(ctx context.Context, texts []string) ([][]float32, error) {
 	if len(texts) == 0 {
 		return nil, nil
 	}
 
-	// OpenAI API支持批量，但为了简单起见，我们逐个处理
-	// 实际可以使用批量API以提高效率
 	embeddings := make([][]float32, len(texts))
 	for i, text := range texts {
 		embedding, err := e.EmbedText(ctx, text)
 		if err != nil {
-			return nil, fmt.Errorf("嵌入文本[%d]失败: %w", i, err)
+			return nil, fmt.Errorf("嵌入文本 [%d] 失败：%w", i, err)
 		}
 		embeddings[i] = embedding
 	}
 
 	return embeddings, nil
 }
-

internal/knowledge/indexer.go

@@ -10,56 +10,133 @@ import (
 	"sync"
 	"time"
 
+	"cyberstrike-ai/internal/config"
+
 	"github.com/google/uuid"
 	"go.uber.org/zap"
 )
 
 // Indexer 索引器，负责将知识项分块并向量化
 type Indexer struct {
-	db        *sql.DB
+	db             *sql.DB
-	embedder  *Embedder
+	embedder       *Embedder
-	logger    *zap.Logger
+	logger         *zap.Logger
-	chunkSize int // 每个块的最大token数（估算）
+	chunkSize      int // 每个块的最大 token 数（估算）
-	overlap   int // 块之间的重叠token数
+	overlap        int // 块之间的重叠 token 数
-	
+	maxChunks      int // 单个知识项的最大块数量（0 表示不限制）
+
 	// 错误跟踪
-	mu           sync.RWMutex
+	mu            sync.RWMutex
-	lastError    string    // 最近一次错误信息
+	lastError     string    // 最近一次错误信息
 	lastErrorTime time.Time // 最近一次错误时间
-	errorCount   int       // 连续错误计数
+	errorCount    int       // 连续错误计数
+
+	// 重建索引状态跟踪
+	rebuildMu          sync.RWMutex
+	isRebuilding       bool      // 是否正在重建索引
+	rebuildTotalItems  int       // 重建总项数
+	rebuildCurrent     int       // 当前已处理项数
+	rebuildFailed      int       // 重建失败项数
+	rebuildStartTime   time.Time // 重建开始时间
+	rebuildLastItemID  string    // 最近处理的项 ID
+	rebuildLastChunks  int       // 最近处理的项的分块数
 }
 
 // NewIndexer 创建新的索引器
-func NewIndexer(db *sql.DB, embedder *Embedder, logger *zap.Logger) *Indexer {
+func NewIndexer(db *sql.DB, embedder *Embedder, logger *zap.Logger, indexingCfg *config.IndexingConfig) *Indexer {
+	chunkSize := 512
+	overlap := 50
+	maxChunks := 0
+	if indexingCfg != nil {
+		if indexingCfg.ChunkSize > 0 {
+			chunkSize = indexingCfg.ChunkSize
+		}
+		if indexingCfg.ChunkOverlap >= 0 {
+			overlap = indexingCfg.ChunkOverlap
+		}
+		if indexingCfg.MaxChunksPerItem > 0 {
+			maxChunks = indexingCfg.MaxChunksPerItem
+		}
+	}
 	return &Indexer{
 		db:        db,
 		embedder:  embedder,
 		logger:    logger,
-		chunkSize: 512, // 默认512 tokens
+		chunkSize: chunkSize,
-		overlap:   50,  // 默认50 tokens重叠
+		overlap:   overlap,
+		maxChunks: maxChunks,
 	}
 }
 
-// ChunkText 将文本分块（支持重叠）
+// ChunkText 将文本分块（支持重叠，保留标题上下文）
 func (idx *Indexer) ChunkText(text string) []string {
-	// 按Markdown标题分割
+	// 按 Markdown 标题分割，获取带标题的块
-	chunks := idx.splitByMarkdownHeaders(text)
+	sections := idx.splitByMarkdownHeadersWithContent(text)
 
-	// 如果块太大，进一步分割
+	// 处理每个块
 	result := make([]string, 0)
-	for _, chunk := range chunks {
+	for _, section := range sections {
-		if idx.estimateTokens(chunk) <= idx.chunkSize {
+		// 构建父级标题路径（不包含最后一级标题，因为内容中已经包含）
-			result = append(result, chunk)
+		// 例如：["# A", "## B", "### C"] -> "[# A > ## B]"
+		var parentHeaderPath string
+		if len(section.HeaderPath) > 1 {
+			parentHeaderPath = strings.Join(section.HeaderPath[:len(section.HeaderPath)-1], " > ")
+		}
+
+		// 提取内容的第一行作为标题（如 "# Prompt Injection"）
+		firstLine, remainingContent := extractFirstLine(section.Content)
+
+		// 如果剩余内容为空或只有空白，说明这个块只有标题没有正文，跳过
+		if strings.TrimSpace(remainingContent) == "" {
+			continue
+		}
+
+		// 如果块太大，进一步分割
+		if idx.estimateTokens(section.Content) <= idx.chunkSize {
+			// 块大小合适，添加父级标题前缀
+			if parentHeaderPath != "" {
+				result = append(result, fmt.Sprintf("[%s] %s", parentHeaderPath, section.Content))
+			} else {
+				result = append(result, section.Content)
+			}
 		} else {
-			// 按段落分割
+			// 块太大，按子标题或段落分割，保持标题上下文
-			subChunks := idx.splitByParagraphs(chunk)
+			// 首先尝试按子标题分割（保留子标题结构）
-			for _, subChunk := range subChunks {
+			subSections := idx.splitBySubHeaders(section.Content, firstLine, parentHeaderPath)
-				if idx.estimateTokens(subChunk) <= idx.chunkSize {
+			if len(subSections) > 1 {
-					result = append(result, subChunk)
+				// 成功按子标题分割，递归处理每个子块
-				} else {
+				for _, sub := range subSections {
-					// 按句子分割（支持重叠）
+					if idx.estimateTokens(sub) <= idx.chunkSize {
-					chunksWithOverlap := idx.splitBySentencesWithOverlap(subChunk)
+						result = append(result, sub)
-					result = append(result, chunksWithOverlap...)
+					} else {
+						// 子块仍然太大，按段落分割（保留标题前缀）
+						paragraphs := idx.splitByParagraphsWithHeader(sub, parentHeaderPath)
+						for _, para := range paragraphs {
+							if idx.estimateTokens(para) <= idx.chunkSize {
+								result = append(result, para)
+							} else {
+								// 段落仍太大，按句子分割
+								sentenceChunks := idx.splitBySentencesWithOverlap(para)
+								for _, chunk := range sentenceChunks {
+									result = append(result, chunk)
+								}
+							}
+						}
+					}
+				}
+			} else {
+				// 没有子标题，按段落分割（保留标题前缀）
+				paragraphs := idx.splitByParagraphsWithHeader(section.Content, parentHeaderPath)
+				for _, para := range paragraphs {
+					if idx.estimateTokens(para) <= idx.chunkSize {
+						result = append(result, para)
+					} else {
+						// 段落仍太大，按句子分割
+						sentenceChunks := idx.splitBySentencesWithOverlap(para)
+						for _, chunk := range sentenceChunks {
+							result = append(result, chunk)
+						}
+					}
 				}
 			}
 		}
@@ -68,43 +145,183 @@ func (idx *Indexer) ChunkText(text string) []string {
 	return result
 }
 
-// splitByMarkdownHeaders 按Markdown标题分割
+// extractFirstLine 提取第一行内容和剩余内容
-func (idx *Indexer) splitByMarkdownHeaders(text string) []string {
+func extractFirstLine(content string) (firstLine, remaining string) {
-	// 匹配Markdown标题 (# ## ### 等)
+	lines := strings.SplitN(content, "\n", 2)
+	if len(lines) == 0 {
+		return "", ""
+	}
+	if len(lines) == 1 {
+		return lines[0], ""
+	}
+	return lines[0], lines[1]
+}
+
+// splitBySubHeaders 尝试按子标题分割内容（用于处理大块内容）
+// headerPrefix 是父级标题路径，用于添加到每个子块
+func (idx *Indexer) splitBySubHeaders(content, headerPrefix, parentPath string) []string {
+	// 匹配 Markdown 子标题（## 及以上）
+	subHeaderRegex := regexp.MustCompile(`(?m)^#{2,6}\s+.+$`)
+	matches := subHeaderRegex.FindAllStringIndex(content, -1)
+
+	if len(matches) == 0 {
+		// 没有子标题，返回原始内容
+		return []string{content}
+	}
+
+	result := make([]string, 0, len(matches))
+	for i, match := range matches {
+		start := match[0]
+		nextStart := len(content)
+		if i+1 < len(matches) {
+			nextStart = matches[i+1][0]
+		}
+
+		subContent := strings.TrimSpace(content[start:nextStart])
+
+		// 添加父级路径前缀
+		if parentPath != "" {
+			result = append(result, fmt.Sprintf("[%s] %s", parentPath, subContent))
+		} else {
+			result = append(result, subContent)
+		}
+	}
+
+	return result
+}
+
+// splitByParagraphsWithHeader 按段落分割，每个段落添加标题前缀（用于保持上下文）
+func (idx *Indexer) splitByParagraphsWithHeader(content, parentPath string) []string {
+	// 提取第一行作为标题
+	firstLine, _ := extractFirstLine(content)
+
+	paragraphs := strings.Split(content, "\n\n")
+	result := make([]string, 0)
+
+	for i, p := range paragraphs {
+		trimmed := strings.TrimSpace(p)
+		if trimmed == "" {
+			continue
+		}
+
+		// 过滤掉只有标题的段落（没有实际内容）
+		if strings.TrimSpace(trimmed) == strings.TrimSpace(firstLine) {
+			continue
+		}
+
+		// 第一个段落已经包含标题，不需要重复添加
+		if i == 0 && strings.Contains(trimmed, firstLine) {
+			if parentPath != "" {
+				result = append(result, fmt.Sprintf("[%s] %s", parentPath, trimmed))
+			} else {
+				result = append(result, trimmed)
+			}
+		} else {
+			// 其他段落添加标题前缀以保持上下文
+			if parentPath != "" {
+				result = append(result, fmt.Sprintf("[%s] %s\n%s", parentPath, firstLine, trimmed))
+			} else {
+				result = append(result, fmt.Sprintf("%s\n%s", firstLine, trimmed))
+			}
+		}
+	}
+
+	return result
+}
+
+// Section 表示一个带标题路径的文本块
+type Section struct {
+	HeaderPath []string // 标题路径（如 ["# SQL 注入", "## 检测方法"]）
+	Content    string   // 块内容
+}
+
+// splitByMarkdownHeadersWithContent 按 Markdown 标题分割，返回带标题路径的块
+// 每个块的内容包含自己的标题，用于向量化检索
+//
+// 例如，对于以下 Markdown:
+//   # Prompt Injection
+//   引言内容
+//   ## Summary
+//   目录内容
+//
+// 返回：
+//   [{HeaderPath: ["# Prompt Injection"], Content: "# Prompt Injection\n引言内容"},
+//    {HeaderPath: ["# Prompt Injection", "## Summary"], Content: "## Summary\n目录内容"}]
+func (idx *Indexer) splitByMarkdownHeadersWithContent(text string) []Section {
+	// 匹配 Markdown 标题 (# ## ### 等)
 	headerRegex := regexp.MustCompile(`(?m)^#{1,6}\s+.+$`)
 
 	// 找到所有标题位置
 	matches := headerRegex.FindAllStringIndex(text, -1)
 	if len(matches) == 0 {
-		return []string{text}
+		// 没有标题，返回整个文本
+		return []Section{{HeaderPath: []string{}, Content: text}}
 	}
 
-	chunks := make([]string, 0)
+	sections := make([]Section, 0, len(matches))
-	lastPos := 0
+	currentHeaderPath := []string{}
 
-	for _, match := range matches {
+	for i, match := range matches {
 		start := match[0]
-		if start > lastPos {
+		end := match[1]
-			chunks = append(chunks, strings.TrimSpace(text[lastPos:start]))
+		nextStart := len(text)
-		}
-		lastPos = start
-	}
 
-	// 添加最后一部分
+		// 找到下一个标题的位置
-	if lastPos < len(text) {
+		if i+1 < len(matches) {
-		chunks = append(chunks, strings.TrimSpace(text[lastPos:]))
+			nextStart = matches[i+1][0]
+		}
+
+		// 提取当前标题
+		headerLine := strings.TrimSpace(text[start:end])
+
+		// 计算标题层级（# 的数量）
+		level := 0
+		for _, ch := range headerLine {
+			if ch == '#' {
+				level++
+			} else {
+				break
+			}
+		}
+
+		// 更新标题路径：移除比当前层级深或等于的子标题，然后添加当前标题
+		newPath := make([]string, 0, len(currentHeaderPath)+1)
+		for _, h := range currentHeaderPath {
+			hLevel := 0
+			for _, ch := range h {
+				if ch == '#' {
+					hLevel++
+				} else {
+					break
+				}
+			}
+			if hLevel < level {
+				newPath = append(newPath, h)
+			}
+		}
+		newPath = append(newPath, headerLine)
+		currentHeaderPath = newPath
+
+		// 提取当前标题到下一个标题之间的内容（包含当前标题）
+		content := strings.TrimSpace(text[start:nextStart])
+
+		// 创建块，使用当前标题路径（包含当前标题）
+		sections = append(sections, Section{
+			HeaderPath: append([]string(nil), currentHeaderPath...),
+			Content:    content,
+		})
 	}
 
 	// 过滤空块
-	result := make([]string, 0)
+	result := make([]Section, 0, len(sections))
-	for _, chunk := range chunks {
+	for _, section := range sections {
-		if strings.TrimSpace(chunk) != "" {
+		if strings.TrimSpace(section.Content) != "" {
-			result = append(result, chunk)
+			result = append(result, section)
 		}
 	}
 
 	if len(result) == 0 {
-		return []string{text}
+		return []Section{{HeaderPath: []string{}, Content: text}}
 	}
 
 	return result
@@ -124,8 +341,12 @@ func (idx *Indexer) splitByParagraphs(text string) []string {
 
 // splitBySentences 按句子分割（用于内部，不包含重叠逻辑）
 func (idx *Indexer) splitBySentences(text string) []string {
-	// 简单的句子分割（按句号、问号、感叹号）
+	// 简单的句子分割（按句号、问号、感叹号，支持中英文）
-	sentenceRegex := regexp.MustCompile(`[.!?]+\s+`)
+	// . ! ? = 英文标点
+	// \u3002 = 。(中文句号)
+	// \uFF01 = ！(中文叹号)
+	// \uFF1F = ？(中文问号)
+	sentenceRegex := regexp.MustCompile(`[.!?\x{3002}\x{FF01}\x{FF1F}]+`)
 	sentences := sentenceRegex.Split(text, -1)
 	result := make([]string, 0)
 	for _, s := range sentences {
@@ -221,13 +442,13 @@ func (idx *Indexer) splitBySentencesSimple(text string) []string {
 	return result
 }
 
-// extractLastTokens 从文本末尾提取指定token数量的内容
+// extractLastTokens 从文本末尾提取指定 token 数量的内容
 func (idx *Indexer) extractLastTokens(text string, tokenCount int) string {
 	if tokenCount <= 0 || text == "" {
 		return ""
 	}
 
-	// 估算字符数（1 token ≈ 4字符）
+	// 估算字符数（1 token ≈ 4 字符）
 	charCount := tokenCount * 4
 	runes := []rune(text)
 
@@ -236,12 +457,11 @@ func (idx *Indexer) extractLastTokens(text string, tokenCount int) string {
 	}
 
 	// 从末尾提取指定数量的字符
-	// 尝试在句子边界处截断，避免截断句子中间
 	startPos := len(runes) - charCount
 	extracted := string(runes[startPos:])
 
-	// 尝试找到第一个句子边界（句号、问号、感叹号后的空格）
+	// 尝试找到第一个句子边界（支持中英文标点）
-	sentenceBoundary := regexp.MustCompile(`[.!?]+\s+`)
+	sentenceBoundary := regexp.MustCompile(`[.!?\x{3002}\x{FF01}\x{FF1F}]+`)
 	matches := sentenceBoundary.FindStringIndex(extracted)
 	if len(matches) > 0 && matches[0] > 0 {
 		// 在句子边界处截断，保留完整句子
@@ -251,41 +471,51 @@ func (idx *Indexer) extractLastTokens(text string, tokenCount int) string {
 	return strings.TrimSpace(extracted)
 }
 
-// estimateTokens 估算token数（简单估算：1 token ≈ 4字符）
+// estimateTokens 估算 token 数（简单估算：1 token ≈ 4 字符）
 func (idx *Indexer) estimateTokens(text string) int {
 	return len([]rune(text)) / 4
 }
 
 // IndexItem 索引知识项（分块并向量化）
 func (idx *Indexer) IndexItem(ctx context.Context, itemID string) error {
-	// 获取知识项（包含category和title，用于向量化）
+	// 获取知识项（包含 category 和 title，用于向量化）
 	var content, category, title string
 	err := idx.db.QueryRow("SELECT content, category, title FROM knowledge_base_items WHERE id = ?", itemID).Scan(&content, &category, &title)
 	if err != nil {
-		return fmt.Errorf("获取知识项失败: %w", err)
+		return fmt.Errorf("获取知识项失败：%w", err)
 	}
 
 	// 删除旧的向量（在 RebuildIndex 中已经统一清空，这里保留是为了单独调用 IndexItem 时的兼容性）
 	_, err = idx.db.Exec("DELETE FROM knowledge_embeddings WHERE item_id = ?", itemID)
 	if err != nil {
-		return fmt.Errorf("删除旧向量失败: %w", err)
+		return fmt.Errorf("删除旧向量失败：%w", err)
 	}
 
 	// 分块
 	chunks := idx.ChunkText(content)
+
+	// 应用最大块数限制
+	if idx.maxChunks > 0 && len(chunks) > idx.maxChunks {
+		idx.logger.Info("知识项块数量超过限制，已截断",
+			zap.String("itemId", itemID),
+			zap.Int("originalChunks", len(chunks)),
+			zap.Int("maxChunks", idx.maxChunks))
+		chunks = chunks[:idx.maxChunks]
+	}
+
 	idx.logger.Info("知识项分块完成", zap.String("itemId", itemID), zap.Int("chunks", len(chunks)))
 
 	// 跟踪该知识项的错误
 	itemErrorCount := 0
 	var firstError error
 	firstErrorChunkIndex := -1
-	
+
-	// 向量化每个块（包含category和title信息，以便向量检索时能匹配到风险类型）
+	// 向量化每个块（包含 category 和 title 信息，以便向量检索时能匹配到风险类型）
 	for i, chunk := range chunks {
-		// 将category和title信息包含到向量化的文本中
+		// 将 category 和 title 信息包含到向量化的文本中
-		// 格式："[风险类型: {category}] [标题: {title}]\n{chunk内容}"
+		// 格式："[风险类型：{category}] [标题：{title}]\n{chunk 内容}"
-		// 这样向量嵌入就会包含风险类型信息，即使SQL过滤失败，向量相似度也能帮助匹配
+		// 这样向量嵌入就会包含风险类型信息，即使 SQL 过滤失败，向量相似度也能帮助匹配
-		textForEmbedding := fmt.Sprintf("[风险类型: %s] [标题: %s]\n%s", category, title, chunk)
+		textForEmbedding := fmt.Sprintf("[风险类型：%s] [标题：%s]\n%s", category, title, chunk)
 
 		embedding, err := idx.embedder.EmbedText(ctx, textForEmbedding)
 		if err != nil {
@@ -305,18 +535,30 @@ func (idx *Indexer) IndexItem(ctx context.Context, itemID string) error {
 					zap.String("chunkPreview", chunkPreview),
 					zap.Error(err),
 				)
-				
+
 				// 更新全局错误跟踪
-				errorMsg := fmt.Sprintf("向量化失败 (知识项: %s): %v", itemID, err)
+				errorMsg := fmt.Sprintf("向量化失败 (知识项：%s): %v", itemID, err)
 				idx.mu.Lock()
 				idx.lastError = errorMsg
 				idx.lastErrorTime = time.Now()
 				idx.mu.Unlock()
 			}
-			
+
-			// 如果连续失败2个块，立即停止处理该知识项（降低阈值，更快停止）
+			// 如果连续失败 5 个块，立即停止处理该知识项
-			// 这样可以避免继续浪费API调用，同时也能更快地检测到配置问题
+			// 这样可以避免继续浪费 API 调用，同时也能更快地检测到配置问题
-			if itemErrorCount >= 2 {
+			// 对于大文档（超过 10 个块），允许失败比例不超过 50%
+			maxConsecutiveFailures := 5
+			if len(chunks) > 10 && itemErrorCount > len(chunks)/2 {
+				idx.logger.Error("知识项向量化失败比例过高，停止处理",
+					zap.String("itemId", itemID),
+					zap.Int("totalChunks", len(chunks)),
+					zap.Int("failedChunks", itemErrorCount),
+					zap.Int("firstErrorChunkIndex", firstErrorChunkIndex),
+					zap.Error(firstError),
+				)
+				return fmt.Errorf("知识项向量化失败比例过高 (%d/%d个块失败): %v", itemErrorCount, len(chunks), firstError)
+			}
+			if itemErrorCount >= maxConsecutiveFailures {
 				idx.logger.Error("知识项连续向量化失败，停止处理",
 					zap.String("itemId", itemID),
 					zap.Int("totalChunks", len(chunks)),
@@ -344,6 +586,13 @@ func (idx *Indexer) IndexItem(ctx context.Context, itemID string) error {
 	}
 
 	idx.logger.Info("知识项索引完成", zap.String("itemId", itemID), zap.Int("chunks", len(chunks)))
+
+	// 更新重建状态中的最近处理信息
+	idx.rebuildMu.Lock()
+	idx.rebuildLastItemID = itemID
+	idx.rebuildLastChunks = len(chunks)
+	idx.rebuildMu.Unlock()
+
 	return nil
 }
 
@@ -352,23 +601,38 @@ func (idx *Indexer) HasIndex() (bool, error) {
 	var count int
 	err := idx.db.QueryRow("SELECT COUNT(*) FROM knowledge_embeddings").Scan(&count)
 	if err != nil {
-		return false, fmt.Errorf("检查索引失败: %w", err)
+		return false, fmt.Errorf("检查索引失败：%w", err)
 	}
 	return count > 0, nil
 }
 
 // RebuildIndex 重建所有索引
 func (idx *Indexer) RebuildIndex(ctx context.Context) error {
+	// 设置重建状态
+	idx.rebuildMu.Lock()
+	idx.isRebuilding = true
+	idx.rebuildTotalItems = 0
+	idx.rebuildCurrent = 0
+	idx.rebuildFailed = 0
+	idx.rebuildStartTime = time.Now()
+	idx.rebuildLastItemID = ""
+	idx.rebuildLastChunks = 0
+	idx.rebuildMu.Unlock()
+
 	// 重置错误跟踪
 	idx.mu.Lock()
 	idx.lastError = ""
 	idx.lastErrorTime = time.Time{}
 	idx.errorCount = 0
 	idx.mu.Unlock()
-	
+
 	rows, err := idx.db.Query("SELECT id FROM knowledge_base_items")
 	if err != nil {
-		return fmt.Errorf("查询知识项失败: %w", err)
+		// 重置重建状态
+		idx.rebuildMu.Lock()
+		idx.isRebuilding = false
+		idx.rebuildMu.Unlock()
+		return fmt.Errorf("查询知识项失败：%w", err)
 	}
 	defer rows.Close()
 
@@ -376,34 +640,36 @@ func (idx *Indexer) RebuildIndex(ctx context.Context) error {
 	for rows.Next() {
 		var id string
 		if err := rows.Scan(&id); err != nil {
-			return fmt.Errorf("扫描知识项ID失败: %w", err)
+			// 重置重建状态
+			idx.rebuildMu.Lock()
+			idx.isRebuilding = false
+			idx.rebuildMu.Unlock()
+			return fmt.Errorf("扫描知识项 ID 失败：%w", err)
 		}
 		itemIDs = append(itemIDs, id)
 	}
 
+	idx.rebuildMu.Lock()
+	idx.rebuildTotalItems = len(itemIDs)
+	idx.rebuildMu.Unlock()
+
 	idx.logger.Info("开始重建索引", zap.Int("totalItems", len(itemIDs)))
 
-	// 在开始重建前，先清空所有旧的向量，确保进度从0开始
+	// 注意：不再清空所有旧索引，而是按增量方式更新
-	// 这样 GetIndexStatus 可以准确反映重建进度
+	// 每个知识项在 IndexItem 中会先删除自己的旧向量，然后插入新向量
-	_, err = idx.db.Exec("DELETE FROM knowledge_embeddings")
+	// 这样配置更新后只重新索引变化的知识项，保留其他知识项的索引
-	if err != nil {
-		idx.logger.Warn("清空旧索引失败", zap.Error(err))
-		// 继续执行，即使清空失败也尝试重建
-	} else {
-		idx.logger.Info("已清空旧索引，开始重建")
-	}
 
 	failedCount := 0
 	consecutiveFailures := 0
-	maxConsecutiveFailures := 2 // 连续失败2次后立即停止（降低阈值，更快停止）
+	maxConsecutiveFailures := 5 // 连续失败 5 次后立即停止（允许偶尔的临时错误）
 	firstFailureItemID := ""
 	var firstFailureError error
-	
+
 	for i, itemID := range itemIDs {
 		if err := idx.IndexItem(ctx, itemID); err != nil {
 			failedCount++
 			consecutiveFailures++
-			
+
 			// 只在第一个失败时记录详细日志
 			if consecutiveFailures == 1 {
 				firstFailureItemID = itemID
@@ -414,15 +680,15 @@ func (idx *Indexer) RebuildIndex(ctx context.Context) error {
 					zap.Error(err),
 				)
 			}
-			
+
 			// 如果连续失败过多，可能是配置问题，立即停止索引
 			if consecutiveFailures >= maxConsecutiveFailures {
-				errorMsg := fmt.Sprintf("连续 %d 个知识项索引失败，可能存在配置问题（如嵌入模型配置错误、API密钥无效、余额不足等）。第一个失败项: %s, 错误: %v", consecutiveFailures, firstFailureItemID, firstFailureError)
+				errorMsg := fmt.Sprintf("连续 %d 个知识项索引失败，可能存在配置问题（如嵌入模型配置错误、API 密钥无效、余额不足等）。第一个失败项：%s, 错误：%v", consecutiveFailures, firstFailureItemID, firstFailureError)
 				idx.mu.Lock()
 				idx.lastError = errorMsg
 				idx.lastErrorTime = time.Now()
 				idx.mu.Unlock()
-				
+
 				idx.logger.Error("连续索引失败次数过多，立即停止索引",
 					zap.Int("consecutiveFailures", consecutiveFailures),
 					zap.Int("totalItems", len(itemIDs)),
@@ -430,17 +696,17 @@ func (idx *Indexer) RebuildIndex(ctx context.Context) error {
 					zap.String("firstFailureItemId", firstFailureItemID),
 					zap.Error(firstFailureError),
 				)
-				return fmt.Errorf("连续索引失败次数过多: %v", firstFailureError)
+				return fmt.Errorf("连续索引失败次数过多：%v", firstFailureError)
 			}
-			
+
-			// 如果失败的知识项过多，记录警告但继续处理（降低阈值到30%）
+			// 如果失败的知识项过多，记录警告但继续处理（降低阈值到 30%）
 			if failedCount > len(itemIDs)*3/10 && failedCount == len(itemIDs)*3/10+1 {
-				errorMsg := fmt.Sprintf("索引失败的知识项过多 (%d/%d)，可能存在配置问题。第一个失败项: %s, 错误: %v", failedCount, len(itemIDs), firstFailureItemID, firstFailureError)
+				errorMsg := fmt.Sprintf("索引失败的知识项过多 (%d/%d)，可能存在配置问题。第一个失败项：%s, 错误：%v", failedCount, len(itemIDs), firstFailureItemID, firstFailureError)
 				idx.mu.Lock()
 				idx.lastError = errorMsg
 				idx.lastErrorTime = time.Now()
 				idx.mu.Unlock()
-				
+
 				idx.logger.Error("索引失败的知识项过多，可能存在配置问题",
 					zap.Int("failedCount", failedCount),
 					zap.Int("totalItems", len(itemIDs)),
@@ -450,20 +716,31 @@ func (idx *Indexer) RebuildIndex(ctx context.Context) error {
 			}
 			continue
 		}
-		
+
 		// 成功时重置连续失败计数和第一个失败信息
 		if consecutiveFailures > 0 {
 			consecutiveFailures = 0
 			firstFailureItemID = ""
 			firstFailureError = nil
 		}
-		
+
-		// 减少进度日志频率（每10个或每10%记录一次）
+		// 更新重建进度
+		idx.rebuildMu.Lock()
+		idx.rebuildCurrent = i + 1
+		idx.rebuildFailed = failedCount
+		idx.rebuildMu.Unlock()
+
+		// 减少进度日志频率（每 10 个或每 10% 记录一次）
 		if (i+1)%10 == 0 || (len(itemIDs) > 0 && (i+1)*100/len(itemIDs)%10 == 0 && (i+1)*100/len(itemIDs) > 0) {
 			idx.logger.Info("索引进度", zap.Int("current", i+1), zap.Int("total", len(itemIDs)), zap.Int("failed", failedCount))
 		}
 	}
 
+	// 重置重建状态
+	idx.rebuildMu.Lock()
+	idx.isRebuilding = false
+	idx.rebuildMu.Unlock()
+
 	idx.logger.Info("索引重建完成", zap.Int("totalItems", len(itemIDs)), zap.Int("failedCount", failedCount))
 	return nil
 }
@@ -474,3 +751,10 @@ func (idx *Indexer) GetLastError() (string, time.Time) {
 	defer idx.mu.RUnlock()
 	return idx.lastError, idx.lastErrorTime
 }
+
+// GetRebuildStatus 获取重建索引状态
+func (idx *Indexer) GetRebuildStatus() (isRebuilding bool, totalItems int, current int, failed int, lastItemID string, lastChunks int, startTime time.Time) {
+	idx.rebuildMu.RLock()
+	defer idx.rebuildMu.RUnlock()
+	return idx.isRebuilding, idx.rebuildTotalItems, idx.rebuildCurrent, idx.rebuildFailed, idx.rebuildLastItemID, idx.rebuildLastChunks, idx.rebuildStartTime
+}

internal/knowledge/manager.go

@@ -657,7 +657,7 @@ func (m *Manager) UpdateItem(id, category, title, content string) (*KnowledgeIte
 
 		// 删除旧目录（如果为空）
 		oldDir := filepath.Dir(item.FilePath)
-		if entries, err := os.ReadDir(oldDir); err == nil && len(entries) == 0 {
+		if isEmpty, _ := isEmptyDir(oldDir); isEmpty {
 			// 只有当目录不是知识库根目录时才删除（避免删除根目录）
 			if oldDir != m.basePath {
 				if err := os.Remove(oldDir); err != nil {
@@ -712,7 +712,7 @@ func (m *Manager) DeleteItem(id string) error {
 
 	// 删除空目录（如果为空）
 	dir := filepath.Dir(filePath)
-	if entries, err := os.ReadDir(dir); err == nil && len(entries) == 0 {
+	if isEmpty, _ := isEmptyDir(dir); isEmpty {
 		// 只有当目录不是知识库根目录时才删除（避免删除根目录）
 		if dir != m.basePath {
 			if err := os.Remove(dir); err != nil {
@@ -724,6 +724,21 @@ func (m *Manager) DeleteItem(id string) error {
 	return nil
 }
 
+// isEmptyDir 检查目录是否为空（忽略隐藏文件和 . 开头的文件）
+func isEmptyDir(dir string) (bool, error) {
+	entries, err := os.ReadDir(dir)
+	if err != nil {
+		return false, err
+	}
+	for _, entry := range entries {
+		// 忽略隐藏文件（以 . 开头）
+		if !strings.HasPrefix(entry.Name(), ".") {
+			return false, nil
+		}
+	}
+	return true, nil
+}
+
 // LogRetrieval 记录检索日志
 func (m *Manager) LogRetrieval(conversationID, messageID, query, riskType string, retrievedItems []string) error {
 	id := uuid.New().String()

internal/knowledge/retriever.go

@@ -69,8 +69,8 @@ func cosineSimilarity(a, b []float32) float64 {
 	return dotProduct / (math.Sqrt(normA) * math.Sqrt(normB))
 }
 
-// bm25Score 计算BM25分数（改进版，更接近标准BM25）
+// bm25Score 计算 BM25 分数（带缓存的改进版本）
-// 注意：这是单文档版本的BM25，缺少全局IDF，但比之前的简化版本更准确
+// 注意：由于缺少全局文档统计，使用简化 IDF 计算
 func (r *Retriever) bm25Score(query, text string) float64 {
 	queryTerms := strings.Fields(strings.ToLower(query))
 	if len(queryTerms) == 0 {
@@ -83,44 +83,56 @@ func (r *Retriever) bm25Score(query, text string) float64 {
 		return 0.0
 	}
 
-	// BM25参数
+	// BM25 参数（标准值）
-	k1 := 1.5             // 词频饱和度参数
+	k1 := 1.2             // 词频饱和度参数（标准范围 1.2-2.0）
-	b := 0.75             // 长度归一化参数
+	b := 0.75             // 长度归一化参数（标准值）
-	avgDocLength := 100.0 // 估算的平均文档长度（用于归一化）
+	avgDocLength := 150.0 // 估算的平均文档长度（基于典型知识块大小）
 	docLength := float64(len(textTerms))
 
-	score := 0.0
+	// 计算词频映射
-	for _, term := range queryTerms {
+	textTermFreq := make(map[string]int, len(textTerms))
-		// 计算词频（TF）
+	for _, term := range textTerms {
-		termFreq := 0
+		textTermFreq[term]++
-		for _, textTerm := range textTerms {
-			if textTerm == term {
-				termFreq++
-			}
-		}
-
-		if termFreq > 0 {
-			// BM25公式的核心部分
-			// TF部分：termFreq / (termFreq + k1 * (1 - b + b * (docLength / avgDocLength)))
-			tf := float64(termFreq)
-			lengthNorm := 1 - b + b*(docLength/avgDocLength)
-			tfScore := tf / (tf + k1*lengthNorm)
-
-			// 简化IDF：使用词长度作为权重（短词通常更重要）
-			// 实际BM25需要全局文档统计，这里用简化版本
-			idfWeight := 1.0
-			if len(term) > 2 {
-				// 长词稍微降低权重（但实际BM25中，罕见词IDF更高）
-				idfWeight = 1.0 + math.Log(1.0+float64(len(term))/10.0)
-			}
-
-			score += tfScore * idfWeight
-		}
 	}
 
-	// 归一化到0-1范围
+	score := 0.0
+	matchedQueryTerms := 0
+
+	for _, term := range queryTerms {
+		termFreq, exists := textTermFreq[term]
+		if !exists || termFreq == 0 {
+			continue
+		}
+		matchedQueryTerms++
+
+		// BM25 TF 计算公式
+		tf := float64(termFreq)
+		lengthNorm := 1 - b + b*(docLength/avgDocLength)
+		tfScore := tf / (tf + k1*lengthNorm)
+
+		// 改进的 IDF 计算：使用词长度和出现频率估算
+		// 短词（2-3 字符）通常更重要，长词 IDF 略低
+		idfWeight := 1.0
+		termLen := len(term)
+		if termLen <= 2 {
+			// 极短词（如 go, js）给予更高权重
+			idfWeight = 1.2 + math.Log(1.0+float64(termFreq)/20.0)
+		} else if termLen <= 4 {
+			// 短词（4 字符）标准权重
+			idfWeight = 1.0 + math.Log(1.0+float64(termFreq)/15.0)
+		} else {
+			// 长词稍微降低权重
+			idfWeight = 0.9 + math.Log(1.0+float64(termFreq)/10.0)
+		}
+
+		score += tfScore * idfWeight
+	}
+
+	// 归一化：考虑匹配的查询词比例
 	if len(queryTerms) > 0 {
-		score = score / float64(len(queryTerms))
+		// 使用匹配比例作为额外因子
+		matchRatio := float64(matchedQueryTerms) / float64(len(queryTerms))
+		score = (score / float64(len(queryTerms))) * (1 + matchRatio) / 2
 	}
 
 	return math.Min(score, 1.0)
@@ -173,7 +185,7 @@ func (r *Retriever) Search(ctx context.Context, req *SearchRequest) ([]*Retrieva
 			SELECT e.id, e.item_id, e.chunk_index, e.chunk_text, e.embedding, i.category, i.title
 			FROM knowledge_embeddings e
 			JOIN knowledge_base_items i ON e.item_id = i.id
-			WHERE i.category = ? COLLATE NOCASE
+			WHERE TRIM(i.category) = TRIM(?) COLLATE NOCASE
 		`, req.RiskType)
 	} else {
 		rows, err = r.db.Query(`
@@ -357,7 +369,10 @@ func (r *Retriever) Search(ctx context.Context, req *SearchRequest) ([]*Retrieva
 			zap.Float64("threshold", threshold),
 			zap.Float64("maxSimilarity", maxSimilarity),
 		)
-	} else if len(filteredCandidates) > topK {
+	}
+
+	// 统一在最终返回前严格限制 Top-K 数量
+	if len(filteredCandidates) > topK {
 		// 如果过滤后结果太多，只取Top-K
 		filteredCandidates = filteredCandidates[:topK]
 	}

internal/knowledge/types.go

@@ -5,6 +5,14 @@ import (
 	"time"
 )
 
+// formatTime 格式化时间为 RFC3339 格式，零时间返回空字符串
+func formatTime(t time.Time) string {
+	if t.IsZero() {
+		return ""
+	}
+	return t.Format(time.RFC3339)
+}
+
 // KnowledgeItem 知识库项
 type KnowledgeItem struct {
 	ID        string    `json:"id"`
@@ -22,12 +30,12 @@ type KnowledgeItemSummary struct {
 	Category  string    `json:"category"`
 	Title     string    `json:"title"`
 	FilePath  string    `json:"filePath"`
-	Content   string    `json:"content,omitempty"` // 可选：内容预览（如果提供，通常只包含前150字符）
+	Content   string    `json:"content,omitempty"` // 可选：内容预览（如果提供，通常只包含前 150 字符）
 	CreatedAt time.Time `json:"createdAt"`
 	UpdatedAt time.Time `json:"updatedAt"`
 }
 
-// MarshalJSON 自定义JSON序列化，确保时间格式正确
+// MarshalJSON 自定义 JSON 序列化，确保时间格式正确
 func (k *KnowledgeItemSummary) MarshalJSON() ([]byte, error) {
 	type Alias KnowledgeItemSummary
 	aux := &struct {
@@ -37,25 +45,12 @@ func (k *KnowledgeItemSummary) MarshalJSON() ([]byte, error) {
 	}{
 		Alias: (*Alias)(k),
 	}
-
+	aux.CreatedAt = formatTime(k.CreatedAt)
-	// 格式化创建时间
+	aux.UpdatedAt = formatTime(k.UpdatedAt)
-	if k.CreatedAt.IsZero() {
-		aux.CreatedAt = ""
-	} else {
-		aux.CreatedAt = k.CreatedAt.Format(time.RFC3339)
-	}
-
-	// 格式化更新时间
-	if k.UpdatedAt.IsZero() {
-		aux.UpdatedAt = ""
-	} else {
-		aux.UpdatedAt = k.UpdatedAt.Format(time.RFC3339)
-	}
-
 	return json.Marshal(aux)
 }
 
-// MarshalJSON 自定义JSON序列化，确保时间格式正确
+// MarshalJSON 自定义 JSON 序列化，确保时间格式正确
 func (k *KnowledgeItem) MarshalJSON() ([]byte, error) {
 	type Alias KnowledgeItem
 	aux := &struct {
@@ -65,21 +60,8 @@ func (k *KnowledgeItem) MarshalJSON() ([]byte, error) {
 	}{
 		Alias: (*Alias)(k),
 	}
-
+	aux.CreatedAt = formatTime(k.CreatedAt)
-	// 格式化创建时间
+	aux.UpdatedAt = formatTime(k.UpdatedAt)
-	if k.CreatedAt.IsZero() {
-		aux.CreatedAt = ""
-	} else {
-		aux.CreatedAt = k.CreatedAt.Format(time.RFC3339)
-	}
-
-	// 格式化更新时间
-	if k.UpdatedAt.IsZero() {
-		aux.UpdatedAt = ""
-	} else {
-		aux.UpdatedAt = k.UpdatedAt.Format(time.RFC3339)
-	}
-
 	return json.Marshal(aux)
 }
 
@@ -89,7 +71,7 @@ type KnowledgeChunk struct {
 	ItemID     string    `json:"itemId"`
 	ChunkIndex int       `json:"chunkIndex"`
 	ChunkText  string    `json:"chunkText"`
-	Embedding  []float32 `json:"-"` // 向量嵌入，不序列化到JSON
+	Embedding  []float32 `json:"-"` // 向量嵌入，不序列化到 JSON
 	CreatedAt  time.Time `json:"createdAt"`
 }
 
@@ -108,11 +90,11 @@ type RetrievalLog struct {
 	MessageID      string    `json:"messageId,omitempty"`
 	Query          string    `json:"query"`
 	RiskType       string    `json:"riskType,omitempty"`
-	RetrievedItems []string  `json:"retrievedItems"` // 检索到的知识项ID列表
+	RetrievedItems []string  `json:"retrievedItems"` // 检索到的知识项 ID 列表
 	CreatedAt      time.Time `json:"createdAt"`
 }
 
-// MarshalJSON 自定义JSON序列化，确保时间格式正确
+// MarshalJSON 自定义 JSON 序列化，确保时间格式正确
 func (r *RetrievalLog) MarshalJSON() ([]byte, error) {
 	type Alias RetrievalLog
 	return json.Marshal(&struct {
@@ -120,21 +102,21 @@ func (r *RetrievalLog) MarshalJSON() ([]byte, error) {
 		CreatedAt string `json:"createdAt"`
 	}{
 		Alias:     (*Alias)(r),
-		CreatedAt: r.CreatedAt.Format(time.RFC3339),
+		CreatedAt: formatTime(r.CreatedAt),
 	})
 }
 
 // CategoryWithItems 分类及其下的知识项（用于按分类分页）
 type CategoryWithItems struct {
-	Category string                `json:"category"`           // 分类名称
+	Category  string                `json:"category"`           // 分类名称
-	ItemCount int                  `json:"itemCount"`          // 该分类下的知识项总数
+	ItemCount int                   `json:"itemCount"`          // 该分类下的知识项总数
-	Items     []*KnowledgeItemSummary `json:"items"`          // 该分类下的知识项列表
+	Items     []*KnowledgeItemSummary `json:"items"`            // 该分类下的知识项列表
 }
 
 // SearchRequest 搜索请求
 type SearchRequest struct {
 	Query     string  `json:"query"`
 	RiskType  string  `json:"riskType,omitempty"`  // 可选：指定风险类型
-	TopK      int     `json:"topK,omitempty"`      // 返回Top-K结果，默认5
+	TopK      int     `json:"topK,omitempty"`      // 返回 Top-K 结果，默认 5
-	Threshold float64 `json:"threshold,omitempty"` // 相似度阈值，默认0.7
+	Threshold float64 `json:"threshold,omitempty"` // 相似度阈值，默认 0.7
 }

internal/logger/logger.go

@@ -55,6 +55,14 @@ func New(level, output string) *Logger {
 }
 
 func (l *Logger) Fatal(msg string, fields ...interface{}) {
-	l.Logger.Fatal(msg, zap.Any("fields", fields))
+    zapFields := make([]zap.Field, 0, len(fields))
+    for _, f := range fields {
+        switch v := f.(type) {
+        case error:
+            zapFields = append(zapFields, zap.Error(v))
+        default:
+            zapFields = append(zapFields, zap.Any("field", v))
+        }
+    }
+    l.Logger.Fatal(msg, zapFields...)
 }
-

internal/robot/conn.go

@@ -0,0 +1,6 @@
+package robot
+
+// MessageHandler 供飞书/钉钉长连接调用的消息处理接口（由 handler.RobotHandler 实现）
+type MessageHandler interface {
+	HandleMessage(platform, userID, text string) string
+}

internal/robot/ding.go

@@ -0,0 +1,137 @@
+package robot
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"net/http"
+	"strings"
+	"time"
+
+	"cyberstrike-ai/internal/config"
+
+	"github.com/open-dingtalk/dingtalk-stream-sdk-go/chatbot"
+	"github.com/open-dingtalk/dingtalk-stream-sdk-go/client"
+	dingutils "github.com/open-dingtalk/dingtalk-stream-sdk-go/utils"
+	"go.uber.org/zap"
+)
+
+const (
+	dingReconnectInitial = 5 * time.Second  // 首次重连间隔
+	dingReconnectMax     = 60 * time.Second // 最大重连间隔
+)
+
+// StartDing 启动钉钉 Stream 长连接（无需公网），收到消息后调用 handler 并通过 SessionWebhook 回复。
+// 断线（如笔记本睡眠、网络中断）后会自动重连；ctx 被取消时退出，便于配置变更时重启。
+func StartDing(ctx context.Context, cfg config.RobotDingtalkConfig, h MessageHandler, logger *zap.Logger) {
+	if !cfg.Enabled || cfg.ClientID == "" || cfg.ClientSecret == "" {
+		return
+	}
+	go runDingLoop(ctx, cfg, h, logger)
+}
+
+// runDingLoop 循环维持钉钉长连接：断开且 ctx 未取消时按退避间隔重连。
+func runDingLoop(ctx context.Context, cfg config.RobotDingtalkConfig, h MessageHandler, logger *zap.Logger) {
+	backoff := dingReconnectInitial
+	for {
+		streamClient := client.NewStreamClient(
+			client.WithAppCredential(client.NewAppCredentialConfig(cfg.ClientID, cfg.ClientSecret)),
+			client.WithSubscription(dingutils.SubscriptionTypeKCallback, "/v1.0/im/bot/messages/get",
+				chatbot.NewDefaultChatBotFrameHandler(func(ctx context.Context, msg *chatbot.BotCallbackDataModel) ([]byte, error) {
+					go handleDingMessage(ctx, msg, h, logger)
+					return nil, nil
+				}).OnEventReceived),
+		)
+		logger.Info("钉钉 Stream 正在连接…", zap.String("client_id", cfg.ClientID))
+		err := streamClient.Start(ctx)
+		if ctx.Err() != nil {
+			logger.Info("钉钉 Stream 已按配置重启关闭")
+			return
+		}
+		if err != nil {
+			logger.Warn("钉钉 Stream 长连接断开（如睡眠/断网），将自动重连", zap.Error(err), zap.Duration("retry_after", backoff))
+		}
+		select {
+		case <-ctx.Done():
+			return
+		case <-time.After(backoff):
+			// 下次重连间隔递增，上限 60 秒，避免频繁重试
+			if backoff < dingReconnectMax {
+				backoff *= 2
+				if backoff > dingReconnectMax {
+					backoff = dingReconnectMax
+				}
+			}
+		}
+	}
+}
+
+func handleDingMessage(ctx context.Context, msg *chatbot.BotCallbackDataModel, h MessageHandler, logger *zap.Logger) {
+	if msg == nil || msg.SessionWebhook == "" {
+		return
+	}
+	content := ""
+	if msg.Text.Content != "" {
+		content = strings.TrimSpace(msg.Text.Content)
+	}
+	if content == "" && msg.Msgtype == "richText" {
+		if cMap, ok := msg.Content.(map[string]interface{}); ok {
+			if rich, ok := cMap["richText"].([]interface{}); ok {
+				for _, c := range rich {
+					if m, ok := c.(map[string]interface{}); ok {
+						if txt, ok := m["text"].(string); ok {
+							content = strings.TrimSpace(txt)
+							break
+						}
+					}
+				}
+			}
+		}
+	}
+	if content == "" {
+		logger.Debug("钉钉消息内容为空，已忽略", zap.String("msgtype", msg.Msgtype))
+		return
+	}
+	logger.Info("钉钉收到消息", zap.String("sender", msg.SenderId), zap.String("content", content))
+	userID := msg.SenderId
+	if userID == "" {
+		userID = msg.ConversationId
+	}
+	reply := h.HandleMessage("dingtalk", userID, content)
+	// 使用 markdown 类型以便正确展示标题、列表、代码块等格式
+	title := reply
+	if idx := strings.IndexAny(reply, "\n"); idx > 0 {
+		title = strings.TrimSpace(reply[:idx])
+	}
+	if len(title) > 50 {
+		title = title[:50] + "…"
+	}
+	if title == "" {
+		title = "回复"
+	}
+	body := map[string]interface{}{
+		"msgtype": "markdown",
+		"markdown": map[string]string{
+			"title": title,
+			"text":  reply,
+		},
+	}
+	bodyBytes, _ := json.Marshal(body)
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost, msg.SessionWebhook, bytes.NewReader(bodyBytes))
+	if err != nil {
+		logger.Warn("钉钉构造回复请求失败", zap.Error(err))
+		return
+	}
+	req.Header.Set("Content-Type", "application/json")
+	resp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		logger.Warn("钉钉回复请求失败", zap.Error(err))
+		return
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != http.StatusOK {
+		logger.Warn("钉钉回复非 200", zap.Int("status", resp.StatusCode))
+		return
+	}
+	logger.Debug("钉钉回复成功", zap.String("content_preview", reply))
+}

internal/robot/lark.go

@@ -0,0 +1,111 @@
+package robot
+
+import (
+	"context"
+	"encoding/json"
+	"strings"
+	"time"
+
+	"cyberstrike-ai/internal/config"
+
+	lark "github.com/larksuite/oapi-sdk-go/v3"
+	larkcore "github.com/larksuite/oapi-sdk-go/v3/core"
+	"github.com/larksuite/oapi-sdk-go/v3/event/dispatcher"
+	larkim "github.com/larksuite/oapi-sdk-go/v3/service/im/v1"
+	larkws "github.com/larksuite/oapi-sdk-go/v3/ws"
+	"go.uber.org/zap"
+)
+
+const (
+	larkReconnectInitial = 5 * time.Second  // 首次重连间隔
+	larkReconnectMax     = 60 * time.Second // 最大重连间隔
+)
+
+type larkTextContent struct {
+	Text string `json:"text"`
+}
+
+// StartLark 启动飞书长连接（无需公网），收到消息后调用 handler 并回复。
+// 断线（如笔记本睡眠、网络中断）后会自动重连；ctx 被取消时退出，便于配置变更时重启。
+func StartLark(ctx context.Context, cfg config.RobotLarkConfig, h MessageHandler, logger *zap.Logger) {
+	if !cfg.Enabled || cfg.AppID == "" || cfg.AppSecret == "" {
+		return
+	}
+	go runLarkLoop(ctx, cfg, h, logger)
+}
+
+// runLarkLoop 循环维持飞书长连接：断开且 ctx 未取消时按退避间隔重连。
+func runLarkLoop(ctx context.Context, cfg config.RobotLarkConfig, h MessageHandler, logger *zap.Logger) {
+	backoff := larkReconnectInitial
+	for {
+		larkClient := lark.NewClient(cfg.AppID, cfg.AppSecret)
+		eventHandler := dispatcher.NewEventDispatcher("", "").OnP2MessageReceiveV1(func(ctx context.Context, event *larkim.P2MessageReceiveV1) error {
+			go handleLarkMessage(ctx, event, h, larkClient, logger)
+			return nil
+		})
+		wsClient := larkws.NewClient(cfg.AppID, cfg.AppSecret,
+			larkws.WithEventHandler(eventHandler),
+			larkws.WithLogLevel(larkcore.LogLevelInfo),
+		)
+		logger.Info("飞书长连接正在连接…", zap.String("app_id", cfg.AppID))
+		err := wsClient.Start(ctx)
+		if ctx.Err() != nil {
+			logger.Info("飞书长连接已按配置重启关闭")
+			return
+		}
+		if err != nil {
+			logger.Warn("飞书长连接断开（如睡眠/断网），将自动重连", zap.Error(err), zap.Duration("retry_after", backoff))
+		}
+		select {
+		case <-ctx.Done():
+			return
+		case <-time.After(backoff):
+			if backoff < larkReconnectMax {
+				backoff *= 2
+				if backoff > larkReconnectMax {
+					backoff = larkReconnectMax
+				}
+			}
+		}
+	}
+}
+
+func handleLarkMessage(ctx context.Context, event *larkim.P2MessageReceiveV1, h MessageHandler, client *lark.Client, logger *zap.Logger) {
+	if event == nil || event.Event == nil || event.Event.Message == nil || event.Event.Sender == nil || event.Event.Sender.SenderId == nil {
+		return
+	}
+	msg := event.Event.Message
+	msgType := larkcore.StringValue(msg.MessageType)
+	if msgType != larkim.MsgTypeText {
+		logger.Debug("飞书暂仅处理文本消息", zap.String("msg_type", msgType))
+		return
+	}
+	var textBody larkTextContent
+	if err := json.Unmarshal([]byte(larkcore.StringValue(msg.Content)), &textBody); err != nil {
+		logger.Warn("飞书消息 Content 解析失败", zap.Error(err))
+		return
+	}
+	text := strings.TrimSpace(textBody.Text)
+	if text == "" {
+		return
+	}
+	userID := ""
+	if event.Event.Sender.SenderId.UserId != nil {
+		userID = *event.Event.Sender.SenderId.UserId
+	}
+	messageID := larkcore.StringValue(msg.MessageId)
+	reply := h.HandleMessage("lark", userID, text)
+	contentBytes, _ := json.Marshal(larkTextContent{Text: reply})
+	_, err := client.Im.Message.Reply(ctx, larkim.NewReplyMessageReqBuilder().
+		MessageId(messageID).
+		Body(larkim.NewReplyMessageReqBodyBuilder().
+			MsgType(larkim.MsgTypeText).
+			Content(string(contentBytes)).
+			Build()).
+		Build())
+	if err != nil {
+		logger.Warn("飞书回复失败", zap.String("message_id", messageID), zap.Error(err))
+		return
+	}
+	logger.Debug("飞书已回复", zap.String("message_id", messageID))
+}

tools/radare2.yaml

@@ -46,8 +46,9 @@ parameters:
       **注意事项：**
       - 必需参数，不能为空
       - 如果指定进程ID，需要配合 -d 参数使用
+      - 注意：radare2 要求文件路径必须是最后一个参数，因此 target 使用 position 1
     required: true
-    position: 0
+    position: 1
     format: "positional"
   - name: "commands"
     type: "string"

web/static/css/style.css

@@ -1582,12 +1582,106 @@ header {
     box-sizing: border-box;
 }
 
+.chat-input-container > .chat-input-with-files {
+    flex: 1;
+    display: flex;
+    flex-direction: column;
+    min-width: 0;
+    gap: 6px;
+}
+
 .chat-input-container > .chat-input-field {
     flex: 1;
     display: flex;
     min-width: 0;
 }
 
+.chat-file-list {
+    display: flex;
+    flex-wrap: wrap;
+    gap: 6px;
+    align-items: center;
+    min-height: 0;
+}
+
+.chat-file-chip {
+    display: inline-flex;
+    align-items: center;
+    gap: 6px;
+    padding: 4px 10px;
+    background: rgba(0, 102, 255, 0.08);
+    border: 1px solid rgba(0, 102, 255, 0.2);
+    border-radius: 8px;
+    font-size: 12px;
+    color: var(--text-primary);
+    max-width: 200px;
+}
+
+.chat-file-chip-name {
+    overflow: hidden;
+    text-overflow: ellipsis;
+    white-space: nowrap;
+}
+
+.chat-file-chip-remove {
+    flex-shrink: 0;
+    width: 18px;
+    height: 18px;
+    padding: 0;
+    border: none;
+    background: rgba(0, 0, 0, 0.08);
+    border-radius: 50%;
+    cursor: pointer;
+    color: var(--text-muted);
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    transition: background 0.2s, color 0.2s;
+}
+
+.chat-file-chip-remove:hover {
+    background: rgba(0, 0, 0, 0.12);
+    color: var(--text-primary);
+}
+
+.chat-file-input-hidden {
+    position: absolute;
+    width: 0;
+    height: 0;
+    opacity: 0;
+    overflow: hidden;
+    pointer-events: none;
+}
+
+.chat-upload-btn {
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    width: 40px;
+    height: 40px;
+    padding: 0;
+    border: 1px solid rgba(0, 0, 0, 0.1);
+    border-radius: 12px;
+    background: #ffffff;
+    color: var(--text-muted);
+    cursor: pointer;
+    transition: border-color 0.2s, color 0.2s, background 0.2s;
+    flex-shrink: 0;
+}
+
+.chat-upload-btn:hover {
+    border-color: var(--accent-color);
+    color: var(--accent-color);
+    background: rgba(0, 102, 255, 0.04);
+}
+
+.chat-input-container.drag-over {
+    background: rgba(0, 102, 255, 0.06);
+    border-radius: 12px;
+    outline: 2px dashed rgba(0, 102, 255, 0.35);
+    outline-offset: -2px;
+}
+
 .chat-input-field {
     flex: 1;
     position: relative;
@@ -2142,6 +2236,10 @@ header {
     -webkit-background-clip: text;
     -webkit-text-fill-color: transparent;
     background-clip: text;
+    /* 允许标题在 flex 中收缩/换行，避免把右侧按钮挤压变形 */
+    flex: 1 1 auto;
+    min-width: 0;
+    overflow-wrap: anywhere;
 }
 
 .modal-close {
@@ -3034,6 +3132,164 @@ header {
     line-height: 1.6;
 }
 
+/* 系统设置 - 终端 */
+.terminal-wrapper {
+    border: 1px solid var(--border-color);
+    border-radius: 6px;
+    overflow: hidden;
+    background: #0d1117;
+}
+
+.terminal-tabs {
+    display: flex;
+    align-items: center;
+    flex-wrap: wrap;
+    gap: 0;
+    padding: 6px 10px 0;
+    background: #161b22;
+    border-bottom: 1px solid var(--border-color);
+    min-height: 36px;
+}
+
+.terminal-tab {
+    display: flex;
+    align-items: center;
+    gap: 6px;
+    padding: 5px 8px 5px 12px;
+    font-size: 0.8125rem;
+    color: #8b949e;
+    background: transparent;
+    border: none;
+    border-radius: 4px 4px 0 0;
+    cursor: pointer;
+    margin-right: 2px;
+}
+
+.terminal-tab-label {
+    cursor: pointer;
+}
+
+.terminal-tab-close {
+    padding: 0;
+    width: 18px;
+    height: 18px;
+    font-size: 1.1rem;
+    line-height: 1;
+    color: #8b949e;
+    background: transparent;
+    border: none;
+    border-radius: 4px;
+    cursor: pointer;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+}
+
+.terminal-tab-close:hover {
+    color: #ff7b72;
+    background: rgba(255, 123, 114, 0.15);
+}
+
+.terminal-tab:hover {
+    color: #e6edf3;
+    background: rgba(255, 255, 255, 0.06);
+}
+
+.terminal-tab.active {
+    color: #e6edf3;
+    background: #0d1117;
+    font-weight: 500;
+}
+
+.terminal-tab-new {
+    margin-left: 4px;
+    width: 28px;
+    height: 28px;
+    font-size: 1.125rem;
+    line-height: 1;
+    color: #8b949e;
+    background: transparent;
+    border: 1px solid transparent;
+    border-radius: 6px;
+    cursor: pointer;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+}
+
+.terminal-tab-new:hover {
+    color: #58a6ff;
+    background: rgba(88, 166, 255, 0.1);
+    border-color: rgba(88, 166, 255, 0.3);
+}
+
+.terminal-toolbar {
+    display: flex;
+    align-items: center;
+    justify-content: space-between;
+    padding: 10px 16px;
+    background: #161b22;
+    border-bottom: 1px solid var(--border-color);
+}
+
+.terminal-toolbar-title {
+    font-size: 0.8125rem;
+    font-weight: 600;
+    color: #8b949e;
+    letter-spacing: 0.02em;
+}
+
+.terminal-btn {
+    padding: 6px 12px;
+    font-size: 0.8125rem;
+    color: var(--text-secondary);
+    background: transparent;
+    border: 1px solid var(--border-color);
+    border-radius: 6px;
+    cursor: pointer;
+    transition: color 0.15s, background 0.15s, border-color 0.15s;
+}
+
+.terminal-btn:hover {
+    color: var(--text-primary);
+    background: rgba(255, 255, 255, 0.06);
+    border-color: #8b949e;
+}
+
+.terminal-panes {
+    position: relative;
+    min-height: 400px;
+}
+
+.terminal-pane {
+    display: none;
+    min-height: 400px;
+}
+
+.terminal-pane.active {
+    display: block;
+}
+
+.terminal-container {
+    min-height: 400px;
+    padding: 8px;
+    box-sizing: border-box;
+}
+
+.terminal-container .xterm {
+    padding: 0;
+}
+
+.terminal-container .xterm-viewport {
+    border-radius: 0;
+}
+
+.terminal-error {
+    color: #ff7b72;
+    padding: 16px;
+    font-size: 0.875rem;
+}
+
 .settings-section {
     margin-bottom: 32px;
 }
@@ -7838,6 +8094,27 @@ header {
     color: var(--accent-color);
 }
 
+/* 批量队列详情弹窗：标题很长时避免挤压右侧按钮 */
+#batch-queue-detail-modal .modal-header {
+    align-items: flex-start;
+    gap: 12px;
+}
+
+#batch-queue-detail-modal .modal-header > div {
+    flex-shrink: 0;
+}
+
+#batch-queue-detail-modal .modal-header-actions {
+    flex-direction: row;
+    width: auto;
+    flex-wrap: wrap;
+    justify-content: flex-end;
+}
+
+#batch-queue-detail-modal .modal-header-actions button {
+    white-space: nowrap;
+}
+
 .batch-queue-tasks-list {
     max-height: 500px;
     overflow-y: auto;
@@ -7877,12 +8154,13 @@ header {
 }
 
 .batch-task-header .btn-small {
-    margin-left: auto;
+    margin-left: 0;
     flex-shrink: 0;
 }
 
 .batch-task-header .batch-task-edit-btn {
-    margin-left: 8px;
+    /* 仅把“编辑”(首个操作按钮)推到最右，避免多个按钮都 margin-left:auto 导致挤压/错位 */
+    margin-left: auto;
 }
 
 .batch-task-header .batch-task-delete-btn {
@@ -9333,6 +9611,13 @@ header {
         width: 100%;
         gap: 6px;
     }
+
+    /* 批量队列详情弹窗：即使在窄屏也保持按钮不“变形” */
+    #batch-queue-detail-modal .modal-header-actions {
+        flex-direction: row;
+        width: auto;
+        gap: 8px;
+    }
     
     .attack-chain-action-btn {
         width: 100%;

web/static/js/chat.js

@@ -22,6 +22,12 @@ const DRAFT_STORAGE_KEY = 'cyberstrike-chat-draft';
 let draftSaveTimer = null;
 const DRAFT_SAVE_DELAY = 500; // 500ms防抖延迟
 
+// 对话文件上传相关（后端会拼接路径与内容发给大模型，前端不再重复发文件列表）
+const MAX_CHAT_FILES = 10;
+const CHAT_FILE_DEFAULT_PROMPT = '请根据上传的文件内容进行分析。';
+/** @type {{ fileName: string, content: string, mimeType: string }[]} */
+let chatAttachments = [];
+
 // 保存输入框草稿到localStorage（防抖版本）
 function saveChatDraftDebounced(content) {
     // 清除之前的定时器
@@ -107,14 +113,22 @@ function adjustTextareaHeight(textarea) {
 // 发送消息
 async function sendMessage() {
     const input = document.getElementById('chat-input');
-    const message = input.value.trim();
+    let message = input.value.trim();
-    
+    const hasAttachments = chatAttachments && chatAttachments.length > 0;
-    if (!message) {
+
+    if (!message && !hasAttachments) {
         return;
     }
-    
+    // 有附件且用户未输入时，发一句简短默认提示即可（后端会拼接路径和文件内容给大模型）
-    // 显示用户消息
+    if (hasAttachments && !message) {
-    addMessage('user', message);
+        message = CHAT_FILE_DEFAULT_PROMPT;
+    }
+
+    // 显示用户消息（含附件名，便于用户确认）
+    const displayMessage = hasAttachments
+        ? message + '\n' + chatAttachments.map(a => '📎 ' + a.fileName).join('\n')
+        : message;
+    addMessage('user', displayMessage);
     
     // 清除防抖定时器，防止在清空输入框后重新保存草稿
     if (draftSaveTimer) {
@@ -135,7 +149,24 @@ async function sendMessage() {
     input.value = '';
     // 强制重置输入框高度为初始高度（40px）
     input.style.height = '40px';
-    
+
+    // 构建请求体（含附件）
+    const body = {
+        message: message,
+        conversationId: currentConversationId,
+        role: typeof getCurrentRole === 'function' ? getCurrentRole() : ''
+    };
+    if (hasAttachments) {
+        body.attachments = chatAttachments.map(a => ({
+            fileName: a.fileName,
+            content: a.content,
+            mimeType: a.mimeType || ''
+        }));
+    }
+    // 发送后清空附件列表
+    chatAttachments = [];
+    renderChatFileChips();
+
     // 创建进度消息容器（使用详细的进度展示）
     const progressId = addProgressMessage();
     const progressElement = document.getElementById(progressId);
@@ -145,19 +176,12 @@ async function sendMessage() {
     let mcpExecutionIds = [];
     
     try {
-        // 获取当前选中的角色（从 roles.js 的函数获取）
-        const roleName = typeof getCurrentRole === 'function' ? getCurrentRole() : '';
-
         const response = await apiFetch('/api/agent-loop/stream', {
             method: 'POST',
             headers: {
                 'Content-Type': 'application/json',
             },
-            body: JSON.stringify({ 
+            body: JSON.stringify(body),
-                message: message,
-                conversationId: currentConversationId,
-                role: roleName || undefined
-            }),
         });
         
         if (!response.ok) {
@@ -222,6 +246,130 @@ async function sendMessage() {
     }
 }
 
+// ---------- 对话文件上传 ----------
+function renderChatFileChips() {
+    const list = document.getElementById('chat-file-list');
+    if (!list) return;
+    list.innerHTML = '';
+    if (!chatAttachments.length) return;
+    chatAttachments.forEach((a, i) => {
+        const chip = document.createElement('div');
+        chip.className = 'chat-file-chip';
+        chip.setAttribute('role', 'listitem');
+        const name = document.createElement('span');
+        name.className = 'chat-file-chip-name';
+        name.title = a.fileName;
+        name.textContent = a.fileName;
+        const remove = document.createElement('button');
+        remove.type = 'button';
+        remove.className = 'chat-file-chip-remove';
+        remove.title = '移除';
+        remove.innerHTML = '×';
+        remove.setAttribute('aria-label', '移除 ' + a.fileName);
+        remove.addEventListener('click', () => removeChatAttachment(i));
+        chip.appendChild(name);
+        chip.appendChild(remove);
+        list.appendChild(chip);
+    });
+}
+
+function removeChatAttachment(index) {
+    chatAttachments.splice(index, 1);
+    renderChatFileChips();
+}
+
+// 有附件且输入框为空时，填入一句默认提示（可编辑）；后端会单独拼接路径与内容给大模型
+function appendChatFilePrompt() {
+    const input = document.getElementById('chat-input');
+    if (!input || !chatAttachments.length) return;
+    if (!input.value.trim()) {
+        input.value = CHAT_FILE_DEFAULT_PROMPT;
+        adjustTextareaHeight(input);
+    }
+}
+
+function readFileAsAttachment(file) {
+    return new Promise((resolve, reject) => {
+        const mimeType = file.type || '';
+        const isTextLike = /^text\//i.test(mimeType) || /^(application\/(json|xml|javascript)|image\/svg\+xml)/i.test(mimeType);
+        const reader = new FileReader();
+        reader.onload = () => {
+            let content = reader.result;
+            if (typeof content === 'string' && content.startsWith('data:')) {
+                content = content.replace(/^data:[^;]+;base64,/, '');
+            }
+            resolve({ fileName: file.name, content: content, mimeType: mimeType });
+        };
+        reader.onerror = () => reject(reader.error);
+        if (isTextLike) {
+            reader.readAsText(file, 'UTF-8');
+        } else {
+            reader.readAsDataURL(file);
+        }
+    });
+}
+
+function addFilesToChat(files) {
+    if (!files || !files.length) return;
+    const next = Array.from(files);
+    if (chatAttachments.length + next.length > MAX_CHAT_FILES) {
+        alert('最多同时上传 ' + MAX_CHAT_FILES + ' 个文件，当前已选 ' + chatAttachments.length + ' 个。');
+        return;
+    }
+    const addOne = (file) => {
+        return readFileAsAttachment(file).then((a) => {
+            chatAttachments.push(a);
+            renderChatFileChips();
+            appendChatFilePrompt();
+        }).catch(() => {
+            alert('读取文件失败：' + file.name);
+        });
+    };
+    let p = Promise.resolve();
+    next.forEach((file) => { p = p.then(() => addOne(file)); });
+    p.then(() => {});
+}
+
+function setupChatFileUpload() {
+    const inputEl = document.getElementById('chat-file-input');
+    const container = document.getElementById('chat-input-container') || document.querySelector('.chat-input-container');
+    if (!inputEl || !container) return;
+
+    inputEl.addEventListener('change', function () {
+        const files = this.files;
+        if (files && files.length) {
+            addFilesToChat(files);
+        }
+        this.value = '';
+    });
+
+    container.addEventListener('dragover', function (e) {
+        e.preventDefault();
+        e.stopPropagation();
+        this.classList.add('drag-over');
+    });
+    container.addEventListener('dragleave', function (e) {
+        e.preventDefault();
+        e.stopPropagation();
+        if (!this.contains(e.relatedTarget)) {
+            this.classList.remove('drag-over');
+        }
+    });
+    container.addEventListener('drop', function (e) {
+        e.preventDefault();
+        e.stopPropagation();
+        this.classList.remove('drag-over');
+        const files = e.dataTransfer && e.dataTransfer.files;
+        if (files && files.length) addFilesToChat(files);
+    });
+}
+
+// 确保 chat-input-container 有 id（若模板未写）
+function ensureChatInputContainerId() {
+    const c = document.querySelector('.chat-input-container');
+    if (c && !c.id) c.id = 'chat-input-container';
+}
+
 function setupMentionSupport() {
     mentionSuggestionsEl = document.getElementById('mention-suggestions');
     if (mentionSuggestionsEl) {
@@ -799,6 +947,8 @@ function initializeChatUI() {
     }
     activeTaskInterval = setInterval(() => loadActiveTasks(), ACTIVE_TASK_REFRESH_INTERVAL);
     setupMentionSupport();
+    ensureChatInputContainerId();
+    setupChatFileUpload();
 }
 
 // 消息计数器，确保ID唯一

web/static/js/info-collect.js

@@ -652,6 +652,50 @@ function showInlineToast(text, options) {
     return { el: toast, remove };
 }
 
+function truncateForPreview(value, maxLen) {
+    const s = value == null ? '' : String(value);
+    if (maxLen <= 0 || s.length <= maxLen) return s;
+    return s.slice(0, maxLen) + '...（已截断）';
+}
+
+function formatFofaRowSummary(row, fields) {
+    const r = row && typeof row === 'object' ? row : {};
+    const order = [];
+    const seen = new Set();
+
+    const preferred = Array.isArray(fields) ? fields : [];
+    preferred.forEach(k => {
+        const key = String(k || '').trim();
+        if (!key || seen.has(key)) return;
+        seen.add(key);
+        order.push(key);
+    });
+
+    Object.keys(r).sort().forEach(k => {
+        if (seen.has(k)) return;
+        seen.add(k);
+        order.push(k);
+    });
+
+    if (order.length === 0) return '-';
+
+    const lines = order.map((k) => {
+        const v = r[k];
+        let text = '';
+        if (v === null) text = 'null';
+        else if (v === undefined) text = '';
+        else if (typeof v === 'string') text = v === '' ? '""' : v;
+        else if (typeof v === 'number' || typeof v === 'boolean') text = String(v);
+        else {
+            try { text = JSON.stringify(v); } catch (e) { text = String(v); }
+        }
+        text = truncateForPreview(text, 800);
+        return `- ${k}: ${text}`;
+    });
+
+    return lines.join('\n');
+}
+
 function scanFofaRow(encodedRowJson, clickEvent) {
     let row = {};
     try {
@@ -674,7 +718,7 @@ function scanFofaRow(encodedRowJson, clickEvent) {
         window.location.hash = 'chat';
     }
 
-    const message = buildScanMessage(target, row);
+    const message = buildScanMessage(target, row, { fields });
     const autoSend = !!(clickEvent && (clickEvent.ctrlKey || clickEvent.metaKey));
 
     setTimeout(async () => {
@@ -709,15 +753,12 @@ function scanFofaRow(encodedRowJson, clickEvent) {
     }, 250);
 }
 
-function buildScanMessage(target, row) {
+function buildScanMessage(target, row, options) {
-    const title = row && row.title != null ? String(row.title).trim() : '';
+    const opts = options && typeof options === 'object' ? options : {};
-    const server = row && row.server != null ? String(row.server).trim() : '';
+    const fields = Array.isArray(opts.fields) ? opts.fields : [];
-    const hintParts = [];
-    if (title) hintParts.push(`title="${title}"`);
-    if (server) hintParts.push(`server="${server}"`);
-    const hint = hintParts.length ? `（FOFA提示：${hintParts.join(', ')}）` : '';
 
-    return `对以下目标做信息收集与基础扫描：\n${target}\n\n要求：\n1) 识别服务/框架与关键指纹\n2) 枚举开放端口与常见管理入口\n3) 用 httpx/指纹/目录探测等方式快速确认可访问面\n4) 输出可复现的命令与结论\n\n${hint}`.trim();
+    const summary = formatFofaRowSummary(row || {}, fields);
+    return `对以下目标做信息收集与基础扫描：\n${target}\n\n要求：\n1) 识别服务/框架与关键指纹\n2) 枚举开放端口与常见管理入口\n3) 用 httpx/指纹/目录探测等方式快速确认可访问面\n4) 输出可复现的命令与结论\n\n已知信息（来自 FOFA 该行全部字段）：\n${summary}`.trim();
 }
 
 function bindFofaTableEvents() {
@@ -892,14 +933,32 @@ function exportFofaResults(format) {
         return;
     }
 
-    // csv：默认导出可见字段（更符合“列隐藏”直觉）
+    if (format === 'xlsx') {
+        // 使用 SheetJS 生成 XLSX（需在页面中引入 xlsx 库）
+        if (typeof XLSX === 'undefined') {
+            alert('未加载 XLSX 库，请刷新页面后重试');
+            return;
+        }
+        const aoa = [visibleFields].concat(p.results.map(row => {
+            const r = row && typeof row === 'object' ? row : {};
+            return visibleFields.map(f => r[f] != null ? r[f] : '');
+        }));
+        const ws = XLSX.utils.aoa_to_sheet(aoa);
+        const wb = XLSX.utils.book_new();
+        XLSX.utils.book_append_sheet(wb, ws, 'FOFA结果');
+        XLSX.writeFile(wb, `fofa_results_${ts}.xlsx`);
+        return;
+    }
+
+    // csv：默认导出可见字段，带 UTF-8 BOM 以兼容 Excel 中文
     const header = visibleFields;
     const rows = p.results.map(row => {
         const r = row && typeof row === 'object' ? row : {};
         return header.map(f => csvEscape(r[f]));
     });
     const csv = [header.map(csvEscape).join(','), ...rows.map(cols => cols.join(','))].join('\n');
-    downloadBlob(csv, `fofa_results_${ts}.csv`, 'text/csv;charset=utf-8');
+    const csvWithBom = '\uFEFF' + csv;
+    downloadBlob(csvWithBom, `fofa_results_${ts}.csv`, 'text/csv;charset=utf-8');
 }
 
 function csvEscape(value) {
@@ -935,6 +994,7 @@ async function batchScanSelectedFofaRows() {
     const fields = p.fields || [];
     const tasks = [];
     const skipped = [];
+
     selected.forEach(idx => {
         const row = p.results[idx];
         const target = inferTargetFromRow(row || {}, fields);
@@ -942,7 +1002,10 @@ async function batchScanSelectedFofaRows() {
             skipped.push(idx + 1);
             return;
         }
-        tasks.push(buildScanMessage(target, row || {}));
+        // 批量任务：与单条一致，只带“该行全部字段”的摘要（避免重复与超长）
+        tasks.push(buildScanMessage(target, row || {}, {
+            fields
+        }));
     });
 
     if (tasks.length === 0) {

web/static/js/knowledge.js

@@ -459,6 +459,9 @@ async function updateIndexProgress() {
         const isComplete = status.is_complete || false;
         const lastError = status.last_error || '';
         
+        // 检查是否正在重建索引（优先使用重建状态）
+        const isRebuilding = status.is_rebuilding || false;
+        
         if (totalItems === 0) {
             // 没有知识项，隐藏进度条
             progressContainer.style.display = 'none';
@@ -524,6 +527,45 @@ async function updateIndexProgress() {
             return;
         }
         
+
+        // 优先处理重建状态
+        if (isRebuilding) {
+            const rebuildTotal = status.rebuild_total || totalItems;
+            const rebuildCurrent = status.rebuild_current || 0;
+            const rebuildFailed = status.rebuild_failed || 0;
+            const rebuildLastItemID = status.rebuild_last_item_id || '';
+            const rebuildLastChunks = status.rebuild_last_chunks || 0;
+            const rebuildStartTime = status.rebuild_start_time || '';
+
+            // 计算进度百分比（使用重建进度）
+            let rebuildProgress = progressPercent;
+            if (rebuildTotal > 0) {
+                rebuildProgress = (rebuildCurrent / rebuildTotal) * 100;
+            }
+
+            progressContainer.innerHTML = `
+                <div class="knowledge-index-progress">
+                    <div class="progress-header">
+                        <span class="progress-icon">🔨</span>
+                        <span class="progress-text">正在重建索引：${rebuildCurrent}/${rebuildTotal} (${rebuildProgress.toFixed(1)}%) - 失败：${rebuildFailed}</span>
+                    </div>
+                    <div class="progress-bar-container">
+                        <div class="progress-bar" style="width: ${rebuildProgress}%"></div>
+                    </div>
+                    <div class="progress-hint">
+                        ${rebuildLastItemID ? `正在处理：${escapeHtml(rebuildLastItemID.substring(0, 36))}... (${rebuildLastChunks} chunks)` : '正在处理...'}
+                        ${rebuildStartTime ? `<br>开始时间：${new Date(rebuildStartTime).toLocaleString()}` : ''}
+                    </div>
+                </div>
+            `;
+
+            // 重建中时继续轮询
+            if (!indexProgressInterval) {
+                indexProgressInterval = setInterval(updateIndexProgress, 2000);
+            }
+            return;
+        }
+        
         if (isComplete) {
             progressContainer.innerHTML = `
                 <div class="knowledge-index-progress-complete">

web/static/js/settings.js

@@ -46,6 +46,9 @@ function switchSettingsSection(section) {
     if (activeContent) {
         activeContent.classList.add('active');
     }
+    if (section === 'terminal' && typeof initTerminal === 'function') {
+        setTimeout(initTerminal, 0);
+    }
 }
 
 // 打开设置
@@ -169,7 +172,76 @@ async function loadConfig(loadTools = true) {
                 // 允许0.0值，只有undefined/null时才使用默认值
                 retrievalWeightInput.value = (hybridWeight !== undefined && hybridWeight !== null) ? hybridWeight : 0.7;
             }
+
+            // 索引配置
+            const indexing = knowledge.indexing || {};
+            const chunkSizeInput = document.getElementById('knowledge-indexing-chunk-size');
+            if (chunkSizeInput) {
+                chunkSizeInput.value = indexing.chunk_size || 512;
+            }
+
+            const chunkOverlapInput = document.getElementById('knowledge-indexing-chunk-overlap');
+            if (chunkOverlapInput) {
+                chunkOverlapInput.value = indexing.chunk_overlap ?? 50;
+            }
+
+            const maxChunksPerItemInput = document.getElementById('knowledge-indexing-max-chunks-per-item');
+            if (maxChunksPerItemInput) {
+                maxChunksPerItemInput.value = indexing.max_chunks_per_item ?? 0;
+            }
+
+            const maxRpmInput = document.getElementById('knowledge-indexing-max-rpm');
+            if (maxRpmInput) {
+                maxRpmInput.value = indexing.max_rpm ?? 0;
+            }
+
+            const rateLimitDelayInput = document.getElementById('knowledge-indexing-rate-limit-delay-ms');
+            if (rateLimitDelayInput) {
+                rateLimitDelayInput.value = indexing.rate_limit_delay_ms ?? 300;
+            }
+
+            const maxRetriesInput = document.getElementById('knowledge-indexing-max-retries');
+            if (maxRetriesInput) {
+                maxRetriesInput.value = indexing.max_retries ?? 3;
+            }
+
+            const retryDelayInput = document.getElementById('knowledge-indexing-retry-delay-ms');
+            if (retryDelayInput) {
+                retryDelayInput.value = indexing.retry_delay_ms ?? 1000;
+            }
         }
+
+        // 填充机器人配置
+        const robots = currentConfig.robots || {};
+        const wecom = robots.wecom || {};
+        const dingtalk = robots.dingtalk || {};
+        const lark = robots.lark || {};
+        const wecomEnabled = document.getElementById('robot-wecom-enabled');
+        if (wecomEnabled) wecomEnabled.checked = wecom.enabled === true;
+        const wecomToken = document.getElementById('robot-wecom-token');
+        if (wecomToken) wecomToken.value = wecom.token || '';
+        const wecomAes = document.getElementById('robot-wecom-encoding-aes-key');
+        if (wecomAes) wecomAes.value = wecom.encoding_aes_key || '';
+        const wecomCorp = document.getElementById('robot-wecom-corp-id');
+        if (wecomCorp) wecomCorp.value = wecom.corp_id || '';
+        const wecomSecret = document.getElementById('robot-wecom-secret');
+        if (wecomSecret) wecomSecret.value = wecom.secret || '';
+        const wecomAgentId = document.getElementById('robot-wecom-agent-id');
+        if (wecomAgentId) wecomAgentId.value = wecom.agent_id || '0';
+        const dingtalkEnabled = document.getElementById('robot-dingtalk-enabled');
+        if (dingtalkEnabled) dingtalkEnabled.checked = dingtalk.enabled === true;
+        const dingtalkClientId = document.getElementById('robot-dingtalk-client-id');
+        if (dingtalkClientId) dingtalkClientId.value = dingtalk.client_id || '';
+        const dingtalkClientSecret = document.getElementById('robot-dingtalk-client-secret');
+        if (dingtalkClientSecret) dingtalkClientSecret.value = dingtalk.client_secret || '';
+        const larkEnabled = document.getElementById('robot-lark-enabled');
+        if (larkEnabled) larkEnabled.checked = lark.enabled === true;
+        const larkAppId = document.getElementById('robot-lark-app-id');
+        if (larkAppId) larkAppId.value = lark.app_id || '';
+        const larkAppSecret = document.getElementById('robot-lark-app-secret');
+        if (larkAppSecret) larkAppSecret.value = lark.app_secret || '';
+        const larkVerify = document.getElementById('robot-lark-verify-token');
+        if (larkVerify) larkVerify.value = lark.verify_token || '';
         
         // 只有在需要时才加载工具列表（MCP管理页面需要，系统设置页面不需要）
         if (loadTools) {
@@ -693,9 +765,19 @@ async function applySettings() {
                     const val = parseFloat(document.getElementById('knowledge-retrieval-hybrid-weight')?.value);
                     return isNaN(val) ? 0.7 : val; // 允许0.0值，只有NaN时才使用默认值
                 })()
+            },
+            indexing: {
+                chunk_size: parseInt(document.getElementById("knowledge-indexing-chunk-size")?.value) || 512,
+                chunk_overlap: parseInt(document.getElementById("knowledge-indexing-chunk-overlap")?.value) ?? 50,
+                max_chunks_per_item: parseInt(document.getElementById("knowledge-indexing-max-chunks-per-item")?.value) ?? 0,
+                max_rpm: parseInt(document.getElementById("knowledge-indexing-max-rpm")?.value) ?? 0,
+                rate_limit_delay_ms: parseInt(document.getElementById("knowledge-indexing-rate-limit-delay-ms")?.value) ?? 300,
+                max_retries: parseInt(document.getElementById("knowledge-indexing-max-retries")?.value) ?? 3,
+                retry_delay_ms: parseInt(document.getElementById("knowledge-indexing-retry-delay-ms")?.value) ?? 1000
             }
         };
         
+        const wecomAgentIdVal = document.getElementById('robot-wecom-agent-id')?.value.trim();
         const config = {
             openai: {
                 api_key: apiKey,
@@ -711,6 +793,27 @@ async function applySettings() {
                 max_iterations: parseInt(document.getElementById('agent-max-iterations').value) || 30
             },
             knowledge: knowledgeConfig,
+            robots: {
+                wecom: {
+                    enabled: document.getElementById('robot-wecom-enabled')?.checked === true,
+                    token: document.getElementById('robot-wecom-token')?.value.trim() || '',
+                    encoding_aes_key: document.getElementById('robot-wecom-encoding-aes-key')?.value.trim() || '',
+                    corp_id: document.getElementById('robot-wecom-corp-id')?.value.trim() || '',
+                    secret: document.getElementById('robot-wecom-secret')?.value.trim() || '',
+                    agent_id: parseInt(wecomAgentIdVal, 10) || 0
+                },
+                dingtalk: {
+                    enabled: document.getElementById('robot-dingtalk-enabled')?.checked === true,
+                    client_id: document.getElementById('robot-dingtalk-client-id')?.value.trim() || '',
+                    client_secret: document.getElementById('robot-dingtalk-client-secret')?.value.trim() || ''
+                },
+                lark: {
+                    enabled: document.getElementById('robot-lark-enabled')?.checked === true,
+                    app_id: document.getElementById('robot-lark-app-id')?.value.trim() || '',
+                    app_secret: document.getElementById('robot-lark-app-secret')?.value.trim() || '',
+                    verify_token: document.getElementById('robot-lark-verify-token')?.value.trim() || ''
+                }
+            },
             tools: []
         };
         

web/static/js/tasks.js

@@ -1197,7 +1197,8 @@ async function showBatchQueueDetail(queueId) {
         batchQueuesState.currentQueueId = queueId;
         
         if (title) {
-            title.textContent = queue.title ? `批量任务队列 - ${escapeHtml(queue.title)}` : '批量任务队列';
+            // textContent 本身会做转义；这里不要再 escapeHtml，否则会把 && 显示成 &...（看起来像“变形/乱码”）
+            title.textContent = queue.title ? `批量任务队列 - ${String(queue.title)}` : '批量任务队列';
         }
         
         // 更新按钮显示

web/static/js/terminal.js

@@ -0,0 +1,419 @@
+/**
+ * 系统设置 - 终端：多标签、流式输出、命令历史、Ctrl+L 清屏、长时间可取消
+ */
+(function () {
+    var getContext = HTMLCanvasElement.prototype.getContext;
+    HTMLCanvasElement.prototype.getContext = function (type, attrs) {
+        if (type === '2d') {
+            attrs = (attrs && typeof attrs === 'object') ? Object.assign({ willReadFrequently: true }, attrs) : { willReadFrequently: true };
+            return getContext.call(this, type, attrs);
+        }
+        return getContext.apply(this, arguments);
+    };
+
+    var terminals = [];
+    var currentTabId = 1;
+    var inited = false;
+    var tabIdCounter = 1;
+    var PROMPT = ''; // 真实 Shell 自己输出提示符，这里不再自定义
+    var HISTORY_MAX = 100;
+    var CANCEL_AFTER_MS = 125000;
+
+    function getCurrent() {
+        for (var i = 0; i < terminals.length; i++) {
+            if (terminals[i].id === currentTabId) return terminals[i];
+        }
+        return terminals[0] || null;
+    }
+
+    var WELCOME_LINE = 'CyberStrikeAI 终端 - 真实 Shell 会话，直接输入命令；Ctrl+L 清屏\r\n';
+
+    function writePrompt(tab) {
+        // 提示符交由后端 Shell 自行输出，这里仅保留占位函数，避免旧代码报错
+    }
+
+    function redrawTabDisplay(t) {
+        if (!t || !t.term) return;
+        t.term.clear();
+        t.term.write(WELCOME_LINE);
+    }
+
+    function writeln(tabOrS, s) {
+        var t, text;
+        if (arguments.length === 1) { text = tabOrS; t = getCurrent(); } else { t = tabOrS; text = s; }
+        if (!t || !t.term) return;
+        if (text) t.term.writeln(text);
+        else t.term.writeln('');
+    }
+
+    function writeOutput(tab, text, isError) {
+        var t = tab || getCurrent();
+        if (!t || !t.term || !text) return;
+        var s = String(text).replace(/\r\n/g, '\n').replace(/\r/g, '\n');
+        var lines = s.split('\n');
+        var prefix = isError ? '\x1b[31m' : '';
+        var suffix = isError ? '\x1b[0m' : '';
+        t.term.write(prefix);
+        for (var i = 0; i < lines.length; i++) {
+            var line = lines[i].replace(/\r/g, '');
+            t.term.writeln(line);
+        }
+        t.term.write(suffix);
+    }
+
+    // 从本地存储中获取当前登录 token（与 auth.js 使用的结构保持一致）
+    function getStoredAuthToken() {
+        try {
+            var raw = localStorage.getItem('cyberstrike-auth');
+            if (!raw) return null;
+            var o = JSON.parse(raw);
+            if (o && o.token) return o.token;
+        } catch (e) {}
+        return null;
+    }
+
+    // WebSocket 地址构造（兼容 http/https，并通过 query 传递 token 以通过后端鉴权）
+    function buildTerminalWSURL() {
+        var proto = (window.location.protocol === 'https:') ? 'wss://' : 'ws://';
+        var url = proto + window.location.host + '/api/terminal/ws';
+        var token = getStoredAuthToken();
+        if (token) {
+            url += '?token=' + encodeURIComponent(token);
+        }
+        return url;
+    }
+
+    function ensureTerminalWS(tab) {
+        if (tab.ws && (tab.ws.readyState === WebSocket.OPEN || tab.ws.readyState === WebSocket.CONNECTING)) {
+            return;
+        }
+        try {
+            var ws = new WebSocket(buildTerminalWSURL());
+            tab.ws = ws;
+            tab.running = true;
+
+            ws.onopen = function () {
+                if (tab.term) {
+                    tab.term.focus();
+                }
+            };
+
+            ws.onmessage = function (ev) {
+                if (!tab.term) return;
+                // 处理二进制消息和文本消息
+                if (ev.data instanceof ArrayBuffer) {
+                    var decoder = new TextDecoder('utf-8');
+                    tab.term.write(decoder.decode(ev.data));
+                } else if (ev.data instanceof Blob) {
+                    // Blob 类型，需要异步读取
+                    var reader = new FileReader();
+                    reader.onload = function () {
+                        var decoder = new TextDecoder('utf-8');
+                        tab.term.write(decoder.decode(reader.result));
+                    };
+                    reader.readAsArrayBuffer(ev.data);
+                } else {
+                    // 字符串类型
+                    tab.term.write(ev.data);
+                }
+            };
+
+            ws.onclose = function () {
+                tab.running = false;
+                if (tab.term) {
+                    tab.term.writeln('\r\n\x1b[2m[会话已关闭]\x1b[0m');
+                }
+            };
+
+            ws.onerror = function () {
+                tab.running = false;
+                if (tab.term) {
+                    tab.term.writeln('\r\n\x1b[31m[终端连接出错]\x1b[0m');
+                }
+            };
+        } catch (e) {
+            if (tab.term) {
+                tab.term.writeln('\r\n\x1b[31m[无法连接终端服务: ' + String(e) + ']\x1b[0m');
+            }
+        }
+    }
+
+    function createTerminalInContainer(container, tab) {
+        if (typeof Terminal === 'undefined') return null;
+        if (!tab.history) tab.history = [];
+        if (tab.historyIndex === undefined) tab.historyIndex = -1;
+        if (tab.cursorIndex === undefined) tab.cursorIndex = 0;
+
+        var term = new Terminal({
+            cursorBlink: true,
+            cursorStyle: 'bar',
+            fontSize: 13,
+            fontFamily: 'Menlo, Monaco, "Courier New", monospace',
+            lineHeight: 1.2,
+            scrollback: 1000,
+            theme: {
+                background: '#0d1117',
+                foreground: '#e6edf3',
+                cursor: '#58a6ff',
+                cursorAccent: '#0d1117',
+                selection: 'rgba(88, 166, 255, 0.3)',
+                black: '#484f58',
+                red: '#ff7b72',
+                green: '#3fb950',
+                yellow: '#d29922',
+                blue: '#58a6ff',
+                magenta: '#bc8cff',
+                cyan: '#39c5cf',
+                white: '#e6edf3',
+                brightBlack: '#6e7681',
+                brightRed: '#ffa198',
+                brightGreen: '#56d364',
+                brightYellow: '#e3b341',
+                brightBlue: '#79c0ff',
+                brightMagenta: '#d2a8ff',
+                brightCyan: '#56d4dd',
+                brightWhite: '#f0f6fc'
+            }
+        });
+        var fitAddon = null;
+        if (typeof FitAddon !== 'undefined') {
+            var FitCtor = (FitAddon.FitAddon || FitAddon);
+            fitAddon = new FitCtor();
+            term.loadAddon(fitAddon);
+        }
+        term.open(container);
+        term.write(WELCOME_LINE);
+        container.addEventListener('click', function () {
+            switchTerminalTab(tab.id);
+            if (term) term.focus();
+        });
+        container.setAttribute('tabindex', '0');
+        container.title = '点击此处后输入命令';
+
+        function sendToWS(data) {
+            ensureTerminalWS(tab);
+            if (tab.ws && tab.ws.readyState === WebSocket.OPEN) {
+                try {
+                    tab.ws.send(data);
+                } catch (e) {}
+            }
+        }
+
+        term.onData(function (data) {
+            // Ctrl+L：本地清屏，同时把 ^L 也发给后端
+            if (data === '\x0c') {
+                term.clear();
+                sendToWS(data);
+                return;
+            }
+            sendToWS(data);
+        });
+
+        tab.term = term;
+        tab.fitAddon = fitAddon;
+        return term;
+    }
+
+    function switchTerminalTab(id) {
+        var prevId = currentTabId;
+        currentTabId = id;
+        document.querySelectorAll('.terminal-tab').forEach(function (el) {
+            el.classList.toggle('active', parseInt(el.getAttribute('data-tab-id'), 10) === id);
+        });
+        document.querySelectorAll('.terminal-pane').forEach(function (el) {
+            var paneId = el.getAttribute('id');
+            var match = paneId && paneId.match(/terminal-pane-(\d+)/);
+            var paneTabId = match ? parseInt(match[1], 10) : 0;
+            el.classList.toggle('active', paneTabId === id);
+        });
+        var t = getCurrent();
+        if (t && t.term) {
+            if (prevId !== id) {
+                requestAnimationFrame(function () {
+                    if (currentTabId === id && t.term) t.term.focus();
+                });
+            } else {
+                t.term.focus();
+            }
+        }
+    }
+
+    function addTerminalTab() {
+        if (typeof Terminal === 'undefined') return;
+        tabIdCounter += 1;
+        var id = tabIdCounter;
+        var paneId = 'terminal-pane-' + id;
+        var containerId = 'terminal-container-' + id;
+        var tabsEl = document.querySelector('.terminal-tabs');
+        var panesEl = document.querySelector('.terminal-panes');
+        if (!tabsEl || !panesEl) return;
+
+        var tabDiv = document.createElement('div');
+        tabDiv.className = 'terminal-tab';
+        tabDiv.setAttribute('data-tab-id', String(id));
+        var label = document.createElement('span');
+        label.className = 'terminal-tab-label';
+        label.textContent = '终端 ' + id;
+        label.onclick = function () { switchTerminalTab(id); };
+        var closeBtn = document.createElement('button');
+        closeBtn.type = 'button';
+        closeBtn.className = 'terminal-tab-close';
+        closeBtn.title = '关闭';
+        closeBtn.textContent = '×';
+        closeBtn.onclick = function (e) { e.stopPropagation(); removeTerminalTab(id); };
+        tabDiv.appendChild(label);
+        tabDiv.appendChild(closeBtn);
+        var plusBtn = tabsEl.querySelector('.terminal-tab-new');
+        tabsEl.insertBefore(tabDiv, plusBtn);
+
+        var paneDiv = document.createElement('div');
+        paneDiv.id = paneId;
+        paneDiv.className = 'terminal-pane';
+        var containerDiv = document.createElement('div');
+        containerDiv.id = containerId;
+        containerDiv.className = 'terminal-container';
+        paneDiv.appendChild(containerDiv);
+        panesEl.appendChild(paneDiv);
+
+        var tab = { id: id, paneId: paneId, containerId: containerId, lineBuffer: '', cursorIndex: 0, running: false, term: null, fitAddon: null, history: [], historyIndex: -1 };
+        terminals.push(tab);
+        createTerminalInContainer(containerDiv, tab);
+        switchTerminalTab(id);
+        updateTerminalTabCloseVisibility();
+        setTimeout(function () {
+            try { if (tab.fitAddon) tab.fitAddon.fit(); if (tab.term) tab.term.focus(); } catch (e) {}
+        }, 50);
+    }
+
+    function updateTerminalTabCloseVisibility() {
+        var tabsEl = document.querySelector('.terminal-tabs');
+        if (!tabsEl) return;
+        var tabDivs = tabsEl.querySelectorAll('.terminal-tab');
+        var showClose = terminals.length > 1;
+        for (var i = 0; i < tabDivs.length; i++) {
+            var btn = tabDivs[i].querySelector('.terminal-tab-close');
+            if (btn) btn.style.display = showClose ? '' : 'none';
+        }
+    }
+
+    function removeTerminalTab(id) {
+        if (terminals.length <= 1) return;
+        var idx = -1;
+        for (var i = 0; i < terminals.length; i++) { if (terminals[i].id === id) { idx = i; break; } }
+        if (idx < 0) return;
+
+        var deletingCurrent = (currentTabId === id);
+        var switchToIndex = deletingCurrent ? (idx > 0 ? idx - 1 : 0) : -1;
+
+        var tab = terminals[idx];
+        if (tab.term && tab.term.dispose) tab.term.dispose();
+        tab.term = null;
+        tab.fitAddon = null;
+        terminals.splice(idx, 1);
+
+        var tabDiv = document.querySelector('.terminal-tab[data-tab-id="' + id + '"]');
+        var paneDiv = document.getElementById('terminal-pane-' + id);
+        if (tabDiv && tabDiv.parentNode) tabDiv.parentNode.removeChild(tabDiv);
+        if (paneDiv && paneDiv.parentNode) paneDiv.parentNode.removeChild(paneDiv);
+
+        var curIdxBeforeRenumber = -1;
+        if (!deletingCurrent) {
+            for (var i = 0; i < terminals.length; i++) {
+                if (terminals[i].id === currentTabId) { curIdxBeforeRenumber = i; break; }
+            }
+        }
+
+        for (var i = 0; i < terminals.length; i++) {
+            var t = terminals[i];
+            t.id = i + 1;
+            t.paneId = 'terminal-pane-' + (i + 1);
+            t.containerId = 'terminal-container-' + (i + 1);
+        }
+        tabIdCounter = terminals.length;
+        if (curIdxBeforeRenumber >= 0) currentTabId = terminals[curIdxBeforeRenumber].id;
+
+        var tabsEl = document.querySelector('.terminal-tabs');
+        var panesEl = document.querySelector('.terminal-panes');
+        if (tabsEl) {
+            var tabDivs = tabsEl.querySelectorAll('.terminal-tab');
+            for (var i = 0; i < tabDivs.length; i++) {
+                var t = terminals[i];
+                tabDivs[i].setAttribute('data-tab-id', String(t.id));
+                var lbl = tabDivs[i].querySelector('.terminal-tab-label');
+                if (lbl) lbl.textContent = '终端 ' + t.id;
+                if (lbl) lbl.onclick = (function (tid) { return function () { switchTerminalTab(tid); }; })(t.id);
+                var cb = tabDivs[i].querySelector('.terminal-tab-close');
+                if (cb) cb.onclick = (function (tid) { return function (e) { e.stopPropagation(); removeTerminalTab(tid); }; })(t.id);
+            }
+        }
+        if (panesEl) {
+            var paneDivs = panesEl.querySelectorAll('.terminal-pane');
+            for (var i = 0; i < paneDivs.length; i++) {
+                var t = terminals[i];
+                paneDivs[i].id = t.paneId;
+                var cont = paneDivs[i].querySelector('.terminal-container');
+                if (cont) cont.id = t.containerId;
+            }
+        }
+
+        updateTerminalTabCloseVisibility();
+
+        if (deletingCurrent && terminals.length > 0) {
+            currentTabId = terminals[switchToIndex].id;
+            switchTerminalTab(currentTabId);
+        }
+    }
+
+    function initTerminal() {
+        var pane1 = document.getElementById('terminal-pane-1');
+        var container1 = document.getElementById('terminal-container-1');
+        if (!pane1 || !container1) return;
+        if (inited) {
+            var t = getCurrent();
+            if (t && t.term) t.term.focus();
+            terminals.forEach(function (tab) { try { if (tab.fitAddon) tab.fitAddon.fit(); } catch (e) {} });
+            return;
+        }
+        inited = true;
+
+        if (typeof Terminal === 'undefined') {
+            container1.innerHTML = '<p class="terminal-error">未加载 xterm.js，请刷新页面或检查网络。</p>';
+            return;
+        }
+
+        currentTabId = 1;
+        var tab = { id: 1, paneId: 'terminal-pane-1', containerId: 'terminal-container-1', lineBuffer: '', cursorIndex: 0, running: false, term: null, fitAddon: null, history: [], historyIndex: -1 };
+        terminals.push(tab);
+        createTerminalInContainer(container1, tab);
+
+        updateTerminalTabCloseVisibility();
+
+        setTimeout(function () {
+            try { if (tab.fitAddon) tab.fitAddon.fit(); if (tab.term) tab.term.focus(); } catch (e) {}
+        }, 100);
+
+        var resizeTimer;
+        window.addEventListener('resize', function () {
+            clearTimeout(resizeTimer);
+            resizeTimer = setTimeout(function () {
+                terminals.forEach(function (t) { try { if (t.fitAddon) t.fitAddon.fit(); } catch (e) {} });
+            }, 150);
+        });
+    }
+
+    function terminalClear() {
+        var t = getCurrent();
+        if (!t || !t.term) return;
+        t.term.clear();
+        t.lineBuffer = '';
+        if (t.cursorIndex !== undefined) t.cursorIndex = 0;
+        writePrompt(t);
+        t.term.focus();
+    }
+
+    window.initTerminal = initTerminal;
+    window.terminalClear = terminalClear;
+    window.switchTerminalTab = switchTerminalTab;
+    window.addTerminalTab = addTerminalTab;
+    window.removeTerminalTab = removeTerminalTab;
+})();

web/templates/index.html

@@ -7,6 +7,7 @@
     <link rel="icon" type="image/png" href="/static/logo.png">
     <link rel="shortcut icon" type="image/png" href="/static/favicon.ico">
     <link rel="stylesheet" href="/static/css/style.css">
+    <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/xterm@4.19.0/css/xterm.css">
 </head>
 <body>
     <div id="login-overlay" class="login-overlay" style="display: none;">
@@ -499,7 +500,7 @@
                             </div>
                             <div id="active-tasks-bar" class="active-tasks-bar"></div>
                             <div id="chat-messages" class="chat-messages"></div>
-                            <div class="chat-input-container">
+                            <div id="chat-input-container" class="chat-input-container">
                                 <div class="role-selector-wrapper">
                                     <button id="role-selector-btn" class="role-selector-btn" onclick="toggleRoleSelectionPanel()" title="选择角色">
                                         <span id="role-selector-icon" class="role-selector-icon">🔵</span>
@@ -521,10 +522,19 @@
                                         <div id="role-selection-list" class="role-selection-list-main"></div>
                                     </div>
                                 </div>
-                                <div class="chat-input-field">
+                                <div class="chat-input-with-files">
-                                    <textarea id="chat-input" placeholder="输入测试目标或命令... (输入 @ 选择工具 | Shift+Enter 换行，Enter 发送)" rows="1"></textarea>
+                                    <div id="chat-file-list" class="chat-file-list" aria-label="已选文件列表"></div>
-                                    <div id="mention-suggestions" class="mention-suggestions" role="listbox" aria-label="工具提及候选"></div>
+                                    <div class="chat-input-field">
+                                        <textarea id="chat-input" placeholder="输入测试目标或命令... (输入 @ 选择工具 | Shift+Enter 换行，Enter 发送)" rows="1"></textarea>
+                                        <div id="mention-suggestions" class="mention-suggestions" role="listbox" aria-label="工具提及候选"></div>
+                                    </div>
                                 </div>
+                                <input type="file" id="chat-file-input" class="chat-file-input-hidden" multiple accept="*" title="选择文件">
+                                <button type="button" class="chat-upload-btn" onclick="document.getElementById('chat-file-input').click()" title="上传文件（可多选或拖拽到此处）">
+                                    <svg width="18" height="18" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
+                                        <path d="M21 15v4a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2v-4M17 8l-5-5-5 5M12 3v12" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"/>
+                                    </svg>
+                                </button>
                                 <button class="send-btn" onclick="sendMessage()">
                                     <span>发送</span>
                                     <svg width="14" height="14" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
@@ -803,8 +813,9 @@
                                 <div class="info-collect-results-toolbar" aria-label="结果工具条">
                                     <div class="info-collect-selected" id="fofa-selected-meta">已选择 0 条</div>
                                     <button class="btn-secondary btn-small" type="button" onclick="toggleFofaColumnsPanel()" title="显示/隐藏字段">列</button>
-                                    <button class="btn-secondary btn-small" type="button" onclick="exportFofaResults('csv')" title="导出当前结果为 CSV">导出 CSV</button>
+                                    <button class="btn-secondary btn-small" type="button" onclick="exportFofaResults('csv')" title="导出当前结果为 CSV（UTF-8，兼容中文）">导出 CSV</button>
                                     <button class="btn-secondary btn-small" type="button" onclick="exportFofaResults('json')" title="导出当前结果为 JSON">导出 JSON</button>
+                                    <button class="btn-secondary btn-small" type="button" onclick="exportFofaResults('xlsx')" title="导出当前结果为 Excel">导出 XLSX</button>
                                     <button class="btn-primary btn-small" type="button" onclick="batchScanSelectedFofaRows()" title="将所选行创建为批量任务队列">批量扫描</button>
                                 </div>
                             </div>
@@ -1061,6 +1072,12 @@
                                 <div class="settings-nav-item active" data-section="basic" onclick="switchSettingsSection('basic')">
                                     <span>基本设置</span>
                                 </div>
+                                <div class="settings-nav-item" data-section="robots" onclick="switchSettingsSection('robots')">
+                                    <span>机器人设置</span>
+                                </div>
+                                <div class="settings-nav-item" data-section="terminal" onclick="switchSettingsSection('terminal')">
+                                    <span>终端</span>
+                                </div>
                                 <div class="settings-nav-item" data-section="security" onclick="switchSettingsSection('security')">
                                     <span>安全设置</span>
                                 </div>
@@ -1186,6 +1203,157 @@
                                             <small class="form-hint">向量检索的权重（0-1），1.0表示纯向量检索，0.0表示纯关键词检索</small>
                                         </div>
                                     </div>
+                                        <div class="settings-subsection-header">
+                                            <h5>索引配置</h5>
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="knowledge-indexing-chunk-size">分块大小（Chunk Size）</label>
+                                            <input type="number" id="knowledge-indexing-chunk-size" min="128" max="4096" placeholder="512" />
+                                            <small class="form-hint">每个块的最大 token 数（默认 512），长文本会被分割成多个块</small>
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="knowledge-indexing-chunk-overlap">分块重叠（Chunk Overlap）</label>
+                                            <input type="number" id="knowledge-indexing-chunk-overlap" min="0" max="512" placeholder="50" />
+                                            <small class="form-hint">块之间的重叠 token 数（默认 50），保持上下文连贯性</small>
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="knowledge-indexing-max-chunks-per-item">单个知识项最大块数</label>
+                                            <input type="number" id="knowledge-indexing-max-chunks-per-item" min="0" max="1000" placeholder="0" />
+                                            <small class="form-hint">单个知识项的最大块数量（0 表示不限制），防止单个文件消耗过多 API 配额</small>
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="knowledge-indexing-max-rpm">每分钟最大请求数（Max RPM）</label>
+                                            <input type="number" id="knowledge-indexing-max-rpm" min="0" max="1000" placeholder="0" />
+                                            <small class="form-hint">每分钟最大请求数（默认 0 表示不限制），如 OpenAI 默认 200 RPM</small>
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="knowledge-indexing-rate-limit-delay-ms">请求间隔延迟（毫秒）</label>
+                                            <input type="number" id="knowledge-indexing-rate-limit-delay-ms" min="0" max="10000" placeholder="300" />
+                                            <small class="form-hint">请求间隔毫秒数（默认 300），用于避免 API 速率限制，设为 0 不限制</small>
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="knowledge-indexing-max-retries">最大重试次数</label>
+                                            <input type="number" id="knowledge-indexing-max-retries" min="0" max="10" placeholder="3" />
+                                            <small class="form-hint">最大重试次数（默认 3），遇到速率限制或服务器错误时自动重试</small>
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="knowledge-indexing-retry-delay-ms">重试间隔（毫秒）</label>
+                                            <input type="number" id="knowledge-indexing-retry-delay-ms" min="0" max="10000" placeholder="1000" />
+                                            <small class="form-hint">重试间隔毫秒数（默认 1000），每次重试会递增延迟</small>
+                                        </div>                                </div>
+
+                                <div class="settings-actions">
+                                    <button class="btn-primary" onclick="applySettings()">应用配置</button>
+                                </div>
+                            </div>
+
+                            <!-- 机器人设置 -->
+                            <div id="settings-section-robots" class="settings-section-content">
+                                <div class="settings-section-header">
+                                    <h3>机器人设置</h3>
+                                    <p class="settings-description">配置企业微信、钉钉、飞书等机器人，在手机端直接与 CyberStrikeAI 对话，无需在服务器上打开网页。</p>
+                                </div>
+
+                                <!-- 企业微信 -->
+                                <div class="settings-subsection">
+                                    <h4>企业微信</h4>
+                                    <div class="settings-form">
+                                        <div class="form-group">
+                                            <label class="checkbox-label">
+                                                <input type="checkbox" id="robot-wecom-enabled" class="modern-checkbox" />
+                                                <span class="checkbox-custom"></span>
+                                                <span class="checkbox-text">启用企业微信机器人</span>
+                                            </label>
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="robot-wecom-token">Token</label>
+                                            <input type="text" id="robot-wecom-token" placeholder="Token" autocomplete="off" />
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="robot-wecom-encoding-aes-key">EncodingAESKey</label>
+                                            <input type="text" id="robot-wecom-encoding-aes-key" placeholder="EncodingAESKey（明文模式可留空）" autocomplete="off" />
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="robot-wecom-corp-id">CorpID</label>
+                                            <input type="text" id="robot-wecom-corp-id" placeholder="企业 ID" autocomplete="off" />
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="robot-wecom-secret">Secret</label>
+                                            <input type="password" id="robot-wecom-secret" placeholder="应用 Secret" autocomplete="off" />
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="robot-wecom-agent-id">AgentID</label>
+                                            <input type="number" id="robot-wecom-agent-id" placeholder="应用 AgentId" />
+                                        </div>
+                                    </div>
+                                </div>
+
+                                <!-- 钉钉 -->
+                                <div class="settings-subsection">
+                                    <h4>钉钉</h4>
+                                    <div class="settings-form">
+                                        <div class="form-group">
+                                            <label class="checkbox-label">
+                                                <input type="checkbox" id="robot-dingtalk-enabled" class="modern-checkbox" />
+                                                <span class="checkbox-custom"></span>
+                                                <span class="checkbox-text">启用钉钉机器人</span>
+                                            </label>
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="robot-dingtalk-client-id">Client ID (AppKey)</label>
+                                            <input type="text" id="robot-dingtalk-client-id" placeholder="钉钉应用 AppKey" autocomplete="off" />
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="robot-dingtalk-client-secret">Client Secret</label>
+                                            <input type="password" id="robot-dingtalk-client-secret" placeholder="钉钉应用 Secret" autocomplete="off" />
+                                            <small class="form-hint">需开启机器人能力并配置流式接入</small>
+                                        </div>
+                                    </div>
+                                </div>
+
+                                <!-- 飞书 -->
+                                <div class="settings-subsection">
+                                    <h4>飞书 (Lark)</h4>
+                                    <div class="settings-form">
+                                        <div class="form-group">
+                                            <label class="checkbox-label">
+                                                <input type="checkbox" id="robot-lark-enabled" class="modern-checkbox" />
+                                                <span class="checkbox-custom"></span>
+                                                <span class="checkbox-text">启用飞书机器人</span>
+                                            </label>
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="robot-lark-app-id">App ID</label>
+                                            <input type="text" id="robot-lark-app-id" placeholder="飞书应用 App ID" autocomplete="off" />
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="robot-lark-app-secret">App Secret</label>
+                                            <input type="password" id="robot-lark-app-secret" placeholder="飞书应用 App Secret" autocomplete="off" />
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="robot-lark-verify-token">Verify Token（可选）</label>
+                                            <input type="text" id="robot-lark-verify-token" placeholder="事件订阅 Verification Token" autocomplete="off" />
+                                        </div>
+                                    </div>
+                                </div>
+
+                                <div class="settings-subsection">
+                                    <h4>机器人命令说明</h4>
+                                    <p class="settings-description">在对话中可发送以下命令（支持中英文）：</p>
+                                    <ul style="color: var(--text-muted); font-size: 13px; line-height: 1.8; margin: 8px 0 0 16px;">
+                                        <li><code>帮助</code> <code>help</code> — 显示本帮助 | Show this help</li>
+                                        <li><code>列表</code> <code>list</code> — 列出所有对话标题与 ID | List conversations</li>
+                                        <li><code>切换 &lt;ID&gt;</code> <code>switch &lt;ID&gt;</code> — 指定对话继续 | Switch to conversation</li>
+                                        <li><code>新对话</code> <code>new</code> — 开启新对话 | Start new conversation</li>
+                                        <li><code>清空</code> <code>clear</code> — 清空当前上下文 | Clear context</li>
+                                        <li><code>当前</code> <code>current</code> — 显示当前对话 ID 与标题 | Show current conversation</li>
+                                        <li><code>停止</code> <code>stop</code> — 中断当前任务 | Stop running task</li>
+                                        <li><code>角色</code> <code>roles</code> — 列出所有可用角色 | List roles</li>
+                                        <li><code>角色 &lt;名&gt;</code> <code>role &lt;name&gt;</code> — 切换当前角色 | Switch role</li>
+                                        <li><code>删除 &lt;ID&gt;</code> <code>delete &lt;ID&gt;</code> — 删除指定对话 | Delete conversation</li>
+                                        <li><code>版本</code> <code>version</code> — 显示当前版本号 | Show version</li>
+                                    </ul>
+                                    <p class="settings-description" style="margin-top: 8px;">除以上命令外，直接输入内容将发送给 AI 进行渗透测试/安全分析。Otherwise, send any text for AI penetration testing / security analysis.</p>
                                 </div>
 
                                 <div class="settings-actions">
@@ -1193,6 +1361,25 @@
                                 </div>
                             </div>
 
+                            <!-- 终端 -->
+                            <div id="settings-section-terminal" class="settings-section-content">
+                                <div class="settings-section-header">
+                                    <h3>终端</h3>
+                                    <p class="settings-description">在服务器上执行命令，便于运维与调试。命令在服务端执行，请勿执行敏感或破坏性操作。</p>
+                                </div>
+                                <div class="terminal-wrapper">
+                                    <div class="terminal-tabs">
+                                        <div class="terminal-tab active" data-tab-id="1"><span class="terminal-tab-label" onclick="switchTerminalTab(1)">终端 1</span><button type="button" class="terminal-tab-close" onclick="removeTerminalTab(1); event.stopPropagation();" title="关闭">×</button></div>
+                                        <button type="button" class="terminal-tab-new" onclick="addTerminalTab()" title="新终端">+</button>
+                                    </div>
+                                    <div class="terminal-panes">
+                                        <div id="terminal-pane-1" class="terminal-pane active">
+                                            <div id="terminal-container-1" class="terminal-container"></div>
+                                        </div>
+                                    </div>
+                                </div>
+                            </div>
+
                             <!-- 安全设置 -->
                             <div id="settings-section-security" class="settings-section-content">
                                 <div class="settings-section-header">
@@ -1472,6 +1659,8 @@
     <script src="https://cdn.jsdelivr.net/npm/cytoscape@3.27.0/dist/cytoscape.min.js"></script>
     <!-- ELK.js for high-quality DAG layout (reduces edge crossings) -->
     <script src="https://cdn.jsdelivr.net/npm/elkjs@0.9.2/lib/elk.bundled.js"></script>
+    <!-- SheetJS for XLSX export (info-collect) -->
+    <script src="https://cdn.jsdelivr.net/npm/xlsx@0.18.5/dist/xlsx.full.min.js"></script>
     <script>
         // 确保ELK对象全局可用
         if (typeof ELK === 'undefined' && typeof elk !== 'undefined') {
@@ -1770,10 +1959,10 @@ version: 1.0.0<br>
                 <h2 id="batch-queue-detail-title">批量任务队列详情</h2>
                 <div style="display: flex; align-items: center; gap: 12px;">
                     <div class="modal-header-actions">
-                        <button class="btn-secondary" id="batch-queue-add-task-btn" onclick="showAddBatchTaskModal()" style="display: none;">添加任务</button>
+                        <button class="btn-secondary btn-small" id="batch-queue-add-task-btn" onclick="showAddBatchTaskModal()" style="display: none;">添加任务</button>
-                        <button class="btn-primary" id="batch-queue-start-btn" onclick="startBatchQueue()" style="display: none;">开始执行</button>
+                        <button class="btn-primary btn-small" id="batch-queue-start-btn" onclick="startBatchQueue()" style="display: none;">开始执行</button>
-                        <button class="btn-secondary" id="batch-queue-pause-btn" onclick="pauseBatchQueue()" style="display: none;">暂停队列</button>
+                        <button class="btn-secondary btn-small" id="batch-queue-pause-btn" onclick="pauseBatchQueue()" style="display: none;">暂停队列</button>
-                        <button class="btn-secondary btn-danger" id="batch-queue-delete-btn" onclick="deleteBatchQueue()" style="display: none;">删除队列</button>
+                        <button class="btn-secondary btn-small btn-danger" id="batch-queue-delete-btn" onclick="deleteBatchQueue()" style="display: none;">删除队列</button>
                     </div>
                     <span class="modal-close" onclick="closeBatchQueueDetailModal()">&times;</span>
                 </div>
@@ -2015,6 +2204,9 @@ version: 1.0.0<br>
     <script src="/static/js/monitor.js"></script>
     <script src="/static/js/chat.js"></script>
     <script src="/static/js/settings.js"></script>
+    <script src="https://cdn.jsdelivr.net/npm/xterm@4.19.0/lib/xterm.js"></script>
+    <script src="https://cdn.jsdelivr.net/npm/xterm-addon-fit@0.5.0/lib/xterm-addon-fit.js"></script>
+    <script src="/static/js/terminal.js"></script>
     <script src="/static/js/knowledge.js"></script>
     <script src="/static/js/skills.js"></script>
     <script src="/static/js/vulnerability.js?v=4"></script>