feat: 添加飞书机器人集成 (#13)
* feat: add Feishu bot integration - Add fsapp.py: Feishu bot webhook handler (root directory) - Add assets/SETUP_FEISHU.md: Setup guide for Feishu integration - Add assets/install_python_windows.bat: Windows Python installer script * fix: 历史注入仅在飞书场景生效,避免混入本地CLI历史 * fix: fsapp调用put_task时传source='feishu'以触发历史注入 --------- Co-authored-by: 张洲嘉 <zhangzhoujia@zhangzhoujiadeMacBook-Air.local>
This commit is contained in:
@@ -102,7 +102,12 @@ class GeneraticAgent:
|
|||||||
handler.key_info += '\n[SYSTEM] 若开始新任务,先更新或清除工作记忆\n'
|
handler.key_info += '\n[SYSTEM] 若开始新任务,先更新或清除工作记忆\n'
|
||||||
self.handler = handler
|
self.handler = handler
|
||||||
self.llmclient.backend = self.llmclient.backends[self.llm_no]
|
self.llmclient.backend = self.llmclient.backends[self.llm_no]
|
||||||
gen = agent_runner_loop(self.llmclient, sys_prompt, raw_query,
|
# 如果有历史记录且来自飞书,注入到首轮 user_input 中(支持/restore恢复上下文)
|
||||||
|
user_input = raw_query
|
||||||
|
if source == 'feishu' and len(self.history) > 1: # 飞书场景且有之前的对话记录
|
||||||
|
h_str = "\n".join(self.history[-20:])
|
||||||
|
user_input = f"### [WORKING MEMORY]\n<history>\n{h_str}\n</history>\n\n### 用户当前消息\n{raw_query}"
|
||||||
|
gen = agent_runner_loop(self.llmclient, sys_prompt, user_input,
|
||||||
handler, TOOLS_SCHEMA, max_turns=40, verbose=self.verbose)
|
handler, TOOLS_SCHEMA, max_turns=40, verbose=self.verbose)
|
||||||
try:
|
try:
|
||||||
full_resp = ""; last_pos = 0
|
full_resp = ""; last_pos = 0
|
||||||
|
|||||||
301
assets/SETUP_FEISHU.md
Normal file
301
assets/SETUP_FEISHU.md
Normal file
@@ -0,0 +1,301 @@
|
|||||||
|
# 飞书 Agent 配置指南
|
||||||
|
|
||||||
|
> 让你的个人电脑变成飞书机器人的大脑,随时随地通过飞书对话控制你的电脑。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 📋 目录
|
||||||
|
|
||||||
|
1. [前置条件](#前置条件)
|
||||||
|
2. [方案选择](#方案选择)
|
||||||
|
3. [企业用户配置](#企业用户配置)
|
||||||
|
4. [个人用户配置](#个人用户配置)
|
||||||
|
5. [项目配置](#项目配置)
|
||||||
|
6. [运行与测试](#运行与测试)
|
||||||
|
7. [常见问题](#常见问题)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 前置条件
|
||||||
|
|
||||||
|
### 必需环境
|
||||||
|
|
||||||
|
- Python 3.8+
|
||||||
|
- 本项目完整代码
|
||||||
|
- LLM API 密钥(Claude/OpenAI 等,已在 `sidercall/mykeys` 中配置)
|
||||||
|
|
||||||
|
### 安装依赖
|
||||||
|
|
||||||
|
```bash
|
||||||
|
pip install lark-oapi
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 方案选择
|
||||||
|
|
||||||
|
| 你的情况 | 推荐方案 | 预计耗时 |
|
||||||
|
| ------------------ | -------------------------- | --------- |
|
||||||
|
| 公司已有飞书企业版 | [企业用户配置](#企业用户配置) | 5-10分钟 |
|
||||||
|
| 个人用户/学习测试 | [个人用户配置](#个人用户配置) | 10-15分钟 |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 企业用户配置
|
||||||
|
|
||||||
|
> 适用于:你的公司使用飞书,你有权限创建应用或联系管理员审批
|
||||||
|
|
||||||
|
### 步骤 1:创建应用
|
||||||
|
|
||||||
|
1. 访问 [飞书开放平台](https://open.feishu.cn/)
|
||||||
|
2. 登录你的企业飞书账号
|
||||||
|
3. 点击右上角「创建应用」→「企业自建应用」
|
||||||
|
4. 填写应用信息:
|
||||||
|
- 应用名称:`我的Agent助手`(可自定义)
|
||||||
|
- 应用描述:`个人AI助手`
|
||||||
|
- 应用图标:可选
|
||||||
|
|
||||||
|
### 步骤 2:添加机器人能力
|
||||||
|
|
||||||
|
1. 进入应用详情页
|
||||||
|
2. 左侧菜单选择「添加应用能力」
|
||||||
|
3. 找到「机器人」,点击「添加」
|
||||||
|
4. 配置机器人信息(可保持默认)
|
||||||
|
|
||||||
|
### 步骤 3:配置权限
|
||||||
|
|
||||||
|
1. 左侧菜单「权限管理」→「API 权限」
|
||||||
|
2. 搜索并开通以下权限:
|
||||||
|
- `im:message` - 获取与发送单聊、群组消息
|
||||||
|
- `im:message:send_as_bot` - 以应用身份发送消息
|
||||||
|
- `contact:user.id:readonly` - 获取用户 ID
|
||||||
|
|
||||||
|
### 步骤 4:获取凭证
|
||||||
|
|
||||||
|
1. 左侧菜单「凭证与基础信息」
|
||||||
|
2. 记录以下信息:
|
||||||
|
- **App ID**:`cli_xxxxxxxx`
|
||||||
|
- **App Secret**:`xxxxxxxxxxxxxxxx`
|
||||||
|
|
||||||
|
### 步骤 5:发布应用
|
||||||
|
|
||||||
|
1. 左侧菜单「版本管理与发布」
|
||||||
|
2. 点击「创建版本」
|
||||||
|
3. 填写版本信息,提交审核
|
||||||
|
4. **联系企业管理员审批**(或自己是管理员直接审批)
|
||||||
|
|
||||||
|
### 步骤 6:获取你的 Open ID
|
||||||
|
|
||||||
|
1. 应用审批通过后,在飞书中搜索你的机器人
|
||||||
|
2. 给机器人发送任意消息
|
||||||
|
3. 运行以下代码获取你的 Open ID:
|
||||||
|
|
||||||
|
```python
|
||||||
|
# 临时运行一次,获取 open_id
|
||||||
|
import lark_oapi as lark
|
||||||
|
from lark_oapi.api.im.v1 import *
|
||||||
|
|
||||||
|
client = lark.Client.builder().app_id("你的APP_ID").app_secret("你的APP_SECRET").build()
|
||||||
|
|
||||||
|
# 监听消息,打印发送者的 open_id
|
||||||
|
def handle(data):
|
||||||
|
print(f"你的 Open ID: {data.event.sender.sender_id.open_id}")
|
||||||
|
|
||||||
|
# ... 或者查看 fsapp.py 运行时的日志输出
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 个人用户配置
|
||||||
|
|
||||||
|
> 适用于:没有企业飞书账号,想个人测试使用
|
||||||
|
|
||||||
|
### 步骤 1:创建测试企业
|
||||||
|
|
||||||
|
1. 访问 [飞书开放平台](https://open.feishu.cn/)
|
||||||
|
2. 使用个人手机号注册/登录
|
||||||
|
3. 点击右上角头像 →「创建测试企业」
|
||||||
|
4. 填写企业名称(如:`我的测试工作区`)
|
||||||
|
5. 创建完成后,你就是这个测试企业的**管理员**
|
||||||
|
|
||||||
|
### 步骤 2:创建应用
|
||||||
|
|
||||||
|
> 与企业用户步骤相同
|
||||||
|
|
||||||
|
1. 点击「创建应用」→「企业自建应用」
|
||||||
|
2. 填写应用信息
|
||||||
|
|
||||||
|
### 步骤 3:添加机器人能力
|
||||||
|
|
||||||
|
1. 进入应用详情页
|
||||||
|
2. 「添加应用能力」→「机器人」→「添加」
|
||||||
|
|
||||||
|
### 步骤 4:配置权限
|
||||||
|
|
||||||
|
1. 「权限管理」→「API 权限」
|
||||||
|
2. 开通权限:
|
||||||
|
- `im:message`
|
||||||
|
- `im:message:send_as_bot`
|
||||||
|
- `contact:user.id:readonly`
|
||||||
|
|
||||||
|
### 步骤 5:获取凭证
|
||||||
|
|
||||||
|
1. 「凭证与基础信息」
|
||||||
|
2. 复制 **App ID** 和 **App Secret**
|
||||||
|
|
||||||
|
### 步骤 6:发布应用(测试企业可自审批)
|
||||||
|
|
||||||
|
1. 「版本管理与发布」→「创建版本」
|
||||||
|
2. 提交后,进入 [飞书管理后台](https://feishu.cn/admin)
|
||||||
|
3. 「工作台」→「应用审核」→ 通过你的应用
|
||||||
|
|
||||||
|
### 步骤 7:在飞书客户端使用
|
||||||
|
|
||||||
|
1. 下载 [飞书客户端](https://www.feishu.cn/download)
|
||||||
|
2. 登录你的测试企业账号
|
||||||
|
3. 搜索你创建的机器人名称
|
||||||
|
4. 开始对话!
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 项目配置
|
||||||
|
|
||||||
|
### 配置飞书凭证
|
||||||
|
|
||||||
|
编辑项目根目录的 `mykey.py`,添加:
|
||||||
|
|
||||||
|
```python
|
||||||
|
# 飞书应用凭证
|
||||||
|
fs_app_id = "cli_xxxxxxxxxxxxxxxx" # 替换为你的 App ID
|
||||||
|
fs_app_secret = "xxxxxxxxxxxxxxxx" # 替换为你的 App Secret
|
||||||
|
|
||||||
|
# 允许使用的用户 Open ID 列表(可选,留空则允许所有人)
|
||||||
|
fs_allowed_users = [
|
||||||
|
"ou_xxxxxxxxxxxxxxxxxxxxxxxx", # 你的 Open ID
|
||||||
|
]
|
||||||
|
```
|
||||||
|
|
||||||
|
### 确认 LLM 配置
|
||||||
|
|
||||||
|
确保 `sidercall/mykeys` 中已配置 LLM API 密钥:
|
||||||
|
|
||||||
|
```python
|
||||||
|
# 示例:Claude API
|
||||||
|
claude_config = {
|
||||||
|
'apikey': 'sk-ant-xxxxx',
|
||||||
|
'apibase': 'https://api.anthropic.com',
|
||||||
|
'model': 'claude-sonnet-4-20250514'
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 运行与测试
|
||||||
|
|
||||||
|
### 启动服务
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cd /path/to/pc-agent-loop
|
||||||
|
python fsapp.py
|
||||||
|
```
|
||||||
|
|
||||||
|
### 预期输出
|
||||||
|
|
||||||
|
```
|
||||||
|
==================================================
|
||||||
|
飞书 Agent 已启动(长连接模式)
|
||||||
|
App ID: cli_xxxxxxxxxxxxxxxx
|
||||||
|
等待消息...
|
||||||
|
==================================================
|
||||||
|
```
|
||||||
|
|
||||||
|
### 测试对话
|
||||||
|
|
||||||
|
1. 打开飞书客户端
|
||||||
|
2. 找到你的机器人
|
||||||
|
3. 发送:`你好`
|
||||||
|
4. 等待回复(首次可能需要几秒)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 可用命令
|
||||||
|
|
||||||
|
在与机器人对话时,可以使用以下特殊命令:
|
||||||
|
|
||||||
|
| 命令 | 说明 |
|
||||||
|
| ---- | ---- |
|
||||||
|
| `/new` | 开始新对话,清除当前上下文 |
|
||||||
|
| `/stop` | 中止当前正在执行的任务 |
|
||||||
|
| `/restore <关键词>` | 恢复之前的对话上下文(根据关键词搜索历史记录) |
|
||||||
|
|
||||||
|
### 命令示例
|
||||||
|
|
||||||
|
```
|
||||||
|
/new # 清空对话,重新开始
|
||||||
|
/stop # 停止正在运行的任务
|
||||||
|
/restore 昨天的任务 # 恢复包含"昨天的任务"关键词的历史对话
|
||||||
|
```
|
||||||
|
|
||||||
|
### 消息显示说明
|
||||||
|
|
||||||
|
- ⏳ 表示任务正在执行中
|
||||||
|
- 消息会实时更新,无需等待完成
|
||||||
|
- 超长回复会自动分段发送
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 常见问题
|
||||||
|
|
||||||
|
### Q: 提示「应用未发布」或「无权限」
|
||||||
|
|
||||||
|
**A:** 确保应用已发布且管理员已审批。测试企业用户需要在管理后台手动审批。
|
||||||
|
|
||||||
|
### Q: 发送消息后没有回复
|
||||||
|
|
||||||
|
**A:** 检查:
|
||||||
|
|
||||||
|
1. `fsapp.py` 是否在运行
|
||||||
|
2. 终端是否有错误日志
|
||||||
|
3. LLM API 密钥是否配置正确
|
||||||
|
|
||||||
|
### Q: 提示「invalid app_id」
|
||||||
|
|
||||||
|
**A:** 检查 `mykey.py` 中的 `fs_app_id` 是否正确复制(包含 `cli_` 前缀)
|
||||||
|
|
||||||
|
### Q: 如何获取自己的 Open ID?
|
||||||
|
|
||||||
|
**A:** 运行 `fsapp.py` 后给机器人发消息,查看终端日志中的 `open_id`
|
||||||
|
|
||||||
|
### Q: 能否多人同时使用?
|
||||||
|
|
||||||
|
**A:** 不能。一个应用只能有一个长连接,连接到一台电脑。每个人需要创建自己的应用。
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 架构说明
|
||||||
|
|
||||||
|
```
|
||||||
|
你的飞书 ←→ 飞书云 ←→ 长连接 ←→ fsapp.py ←→ Agent ←→ 你的电脑
|
||||||
|
↑
|
||||||
|
运行在你电脑上
|
||||||
|
```
|
||||||
|
|
||||||
|
- 消息通过飞书云转发到你电脑上运行的 `fsapp.py`
|
||||||
|
- Agent 处理请求后,通过飞书 API 回复消息
|
||||||
|
- **你的电脑必须保持运行** `fsapp.py` 才能响应消息
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 下一步
|
||||||
|
|
||||||
|
- 自定义 Agent 行为:编辑 `assets/sys_prompt.txt`
|
||||||
|
- 添加新工具:编辑 `assets/tools_schema.json`
|
||||||
|
- 查看日志:运行时观察终端输出
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
*文档版本:v1.1 | 更新日期:2026-03-07*
|
||||||
|
|
||||||
|
**v1.1 更新内容:**
|
||||||
|
- 新增「可用命令」章节(/new, /stop, /restore)
|
||||||
|
- 新增消息显示说明(⏳ 进行中标记、实时更新等)
|
||||||
111
assets/install_python_windows.bat
Normal file
111
assets/install_python_windows.bat
Normal file
@@ -0,0 +1,111 @@
|
|||||||
|
@echo off
|
||||||
|
setlocal enabledelayedexpansion
|
||||||
|
title Python One-Click Installer
|
||||||
|
color 0A
|
||||||
|
|
||||||
|
echo.
|
||||||
|
echo ========================================
|
||||||
|
echo Python One-Click Installer (Windows)
|
||||||
|
echo ========================================
|
||||||
|
echo.
|
||||||
|
|
||||||
|
net session >nul 2>&1
|
||||||
|
if %errorlevel% neq 0 (
|
||||||
|
echo [!] Administrator privileges required. Restarting with elevation...
|
||||||
|
powershell -Command "Start-Process '%~f0' -Verb RunAs"
|
||||||
|
exit /b
|
||||||
|
)
|
||||||
|
|
||||||
|
echo [OK] Administrator privileges confirmed
|
||||||
|
echo.
|
||||||
|
|
||||||
|
python --version >nul 2>&1
|
||||||
|
if %errorlevel% equ 0 (
|
||||||
|
echo [OK] Python already installed:
|
||||||
|
python --version
|
||||||
|
echo.
|
||||||
|
choice /C YN /M "Install latest version anyway? (Y=Yes / N=Exit)"
|
||||||
|
if errorlevel 2 goto :end
|
||||||
|
)
|
||||||
|
|
||||||
|
set PYTHON_VERSION=3.12.9
|
||||||
|
set MIRROR_URL=https://npmmirror.com/mirrors/python/3.12.9/python-3.12.9-amd64.exe
|
||||||
|
set OFFICIAL_URL=https://www.python.org/ftp/python/3.12.9/python-3.12.9-amd64.exe
|
||||||
|
set INSTALLER=%TEMP%\python_installer.exe
|
||||||
|
|
||||||
|
echo [*] Preparing to download Python %PYTHON_VERSION%
|
||||||
|
echo [*] Trying mirror source first...
|
||||||
|
echo.
|
||||||
|
|
||||||
|
powershell -NoProfile -Command "[Net.ServicePointManager]::SecurityProtocol=[Net.SecurityProtocolType]::Tls12; $ProgressPreference='SilentlyContinue'; Invoke-WebRequest -Uri '%MIRROR_URL%' -OutFile '%INSTALLER%' -UseBasicParsing"
|
||||||
|
|
||||||
|
if not exist "%INSTALLER%" goto :official
|
||||||
|
for %%A in ("%INSTALLER%") do if %%~zA lss 1000000 goto :official
|
||||||
|
echo [OK] Mirror download complete
|
||||||
|
goto :install
|
||||||
|
|
||||||
|
:official
|
||||||
|
echo [!] Mirror failed, switching to official source...
|
||||||
|
powershell -NoProfile -Command "[Net.ServicePointManager]::SecurityProtocol=[Net.SecurityProtocolType]::Tls12; $ProgressPreference='SilentlyContinue'; Invoke-WebRequest -Uri '%OFFICIAL_URL%' -OutFile '%INSTALLER%' -UseBasicParsing"
|
||||||
|
|
||||||
|
if not exist "%INSTALLER%" (
|
||||||
|
echo [x] Download failed. Please check your network connection and retry.
|
||||||
|
pause
|
||||||
|
goto :end
|
||||||
|
)
|
||||||
|
for %%A in ("%INSTALLER%") do if %%~zA lss 1000000 (
|
||||||
|
echo [x] Downloaded file is incomplete. Please check your network and retry.
|
||||||
|
pause
|
||||||
|
goto :end
|
||||||
|
)
|
||||||
|
echo [OK] Official source download complete
|
||||||
|
|
||||||
|
:install
|
||||||
|
echo.
|
||||||
|
echo [*] Installing Python %PYTHON_VERSION% (this may take 2-5 minutes^)...
|
||||||
|
echo.
|
||||||
|
|
||||||
|
start /wait "" "%INSTALLER%" /passive InstallAllUsers=1 PrependPath=1 Include_test=0 Include_pip=1
|
||||||
|
|
||||||
|
set INSTALL_CODE=%errorlevel%
|
||||||
|
del /f /q "%INSTALLER%" >nul 2>&1
|
||||||
|
|
||||||
|
if %INSTALL_CODE% neq 0 (
|
||||||
|
echo [x] Installation failed with error code: %INSTALL_CODE%
|
||||||
|
pause
|
||||||
|
goto :end
|
||||||
|
)
|
||||||
|
|
||||||
|
echo [+] Installation complete!
|
||||||
|
echo.
|
||||||
|
|
||||||
|
timeout /t 3 /nobreak >nul
|
||||||
|
|
||||||
|
set "PATH=C:\Program Files\Python312;C:\Program Files\Python312\Scripts;%PATH%"
|
||||||
|
|
||||||
|
python --version >nul 2>&1
|
||||||
|
if %errorlevel% equ 0 (
|
||||||
|
echo [OK] Python installed successfully:
|
||||||
|
python --version
|
||||||
|
echo.
|
||||||
|
echo [OK] pip version:
|
||||||
|
pip --version
|
||||||
|
echo.
|
||||||
|
echo [*] Configuring pip mirror (Tsinghua^)...
|
||||||
|
pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
|
||||||
|
pip config set global.trusted-host pypi.tuna.tsinghua.edu.cn
|
||||||
|
echo.
|
||||||
|
echo [*] Installing requests...
|
||||||
|
pip install requests
|
||||||
|
echo.
|
||||||
|
echo ========================================
|
||||||
|
echo All done! Open a new terminal to use
|
||||||
|
echo python and pip commands.
|
||||||
|
echo ========================================
|
||||||
|
) else (
|
||||||
|
echo [!] PATH not yet refreshed. Please close this window and open a new terminal.
|
||||||
|
)
|
||||||
|
|
||||||
|
:end
|
||||||
|
echo.
|
||||||
|
pause
|
||||||
103
fsapp.py
Normal file
103
fsapp.py
Normal file
@@ -0,0 +1,103 @@
|
|||||||
|
import os, sys, threading, asyncio, time, re, json
|
||||||
|
import queue as Q
|
||||||
|
PROJECT_ROOT = os.path.dirname(os.path.abspath(__file__))
|
||||||
|
sys.path.insert(0, PROJECT_ROOT); os.chdir(PROJECT_ROOT)
|
||||||
|
import lark_oapi as lark
|
||||||
|
from lark_oapi.api.im.v1 import *
|
||||||
|
from lark_oapi.api.contact.v3 import *
|
||||||
|
from agentmain import GeneraticAgent
|
||||||
|
import mykey
|
||||||
|
_TAG_PATS = [r'<' + t + r'>.*?</' + t + r'>' for t in ('thinking', 'summary', 'tool_use', 'file_content')]
|
||||||
|
def _clean(t):
|
||||||
|
for p in _TAG_PATS: t = re.sub(p, '', t, flags=re.DOTALL)
|
||||||
|
return re.sub(r'\n{3,}', '\n\n', t).strip() or '...'
|
||||||
|
APP_ID, APP_SECRET = getattr(mykey, 'fs_app_id', None), getattr(mykey, 'fs_app_secret', None)
|
||||||
|
ALLOWED_USERS = set(getattr(mykey, 'fs_allowed_users', []))
|
||||||
|
agent = GeneraticAgent()
|
||||||
|
threading.Thread(target=agent.run, daemon=True).start()
|
||||||
|
client, user_tasks = None, {}
|
||||||
|
def create_client():
|
||||||
|
return lark.Client.builder().app_id(APP_ID).app_secret(APP_SECRET).log_level(lark.LogLevel.INFO).build()
|
||||||
|
_card = lambda t: json.dumps({"config": {"wide_screen_mode": True}, "elements": [{"tag": "markdown", "content": t}]})
|
||||||
|
def send_message(open_id, content, msg_type="text", use_card=False):
|
||||||
|
ct, mt = (_card(content), "interactive") if use_card else (json.dumps({"text": content}), "text")
|
||||||
|
body = CreateMessageRequest.builder().receive_id_type("open_id").request_body(
|
||||||
|
CreateMessageRequestBody.builder().receive_id(open_id).msg_type(mt).content(ct).build()).build()
|
||||||
|
r = client.im.v1.message.create(body)
|
||||||
|
return r.data.message_id if r.success() else (print(f"发送失败: {r.code}, {r.msg}"), None)[1]
|
||||||
|
def update_message(message_id, content):
|
||||||
|
body = PatchMessageRequest.builder().message_id(message_id).request_body(
|
||||||
|
PatchMessageRequestBody.builder().content(_card(content)).build()).build()
|
||||||
|
r = client.im.v1.message.patch(body)
|
||||||
|
if not r.success(): print(f"[ERROR] update_message 失败: {r.code}, {r.msg}")
|
||||||
|
return r.success()
|
||||||
|
def handle_message(data):
|
||||||
|
event, message, sender = data.event, data.event.message, data.event.sender
|
||||||
|
open_id, msg_type = sender.sender_id.open_id, message.message_type
|
||||||
|
if ALLOWED_USERS and open_id not in ALLOWED_USERS: return print(f"未授权用户: {open_id}")
|
||||||
|
if msg_type != "text": return send_message(open_id, "⚠️ 目前只支持文本消息")
|
||||||
|
text = json.loads(message.content).get("text", "").strip()
|
||||||
|
if not text: return
|
||||||
|
print(f"收到消息 [{open_id}]: {text}")
|
||||||
|
if text.startswith("/"): return handle_command(open_id, text)
|
||||||
|
def run_agent():
|
||||||
|
user_tasks[open_id] = {'running': True}
|
||||||
|
try:
|
||||||
|
msg_id, dq, last_text = send_message(open_id, "思考中...", use_card=True), agent.put_task(text, source='feishu'), ""
|
||||||
|
while user_tasks.get(open_id, {}).get('running', False):
|
||||||
|
time.sleep(3)
|
||||||
|
item = None
|
||||||
|
try:
|
||||||
|
while True: item = dq.get_nowait()
|
||||||
|
except: pass
|
||||||
|
if item is None: continue
|
||||||
|
raw, done = item.get("done") or item.get("next", ""), "done" in item
|
||||||
|
show = _clean(raw)
|
||||||
|
if len(show) > 3500:
|
||||||
|
# 智能截断:避免切断代码块
|
||||||
|
cut = show[-3000:]
|
||||||
|
if cut.count('```') % 2 == 1: cut = '```\n' + cut # 补开头
|
||||||
|
msg_id, last_text, show = send_message(open_id, "(继续...)", use_card=True), "", cut
|
||||||
|
display = show if done else show + " ⏳"
|
||||||
|
if display != last_text and msg_id: update_message(msg_id, display); last_text = display
|
||||||
|
if done: break
|
||||||
|
if not user_tasks.get(open_id, {}).get('running', True): send_message(open_id, "⏹️ 已停止")
|
||||||
|
except Exception as e:
|
||||||
|
import traceback; print(f"[ERROR] run_agent 异常: {e}"); traceback.print_exc()
|
||||||
|
send_message(open_id, f"❌ 错误: {str(e)}")
|
||||||
|
finally: user_tasks.pop(open_id, None)
|
||||||
|
threading.Thread(target=run_agent, daemon=True).start()
|
||||||
|
def handle_command(open_id, cmd):
|
||||||
|
import glob
|
||||||
|
if cmd == "/stop":
|
||||||
|
if open_id in user_tasks: user_tasks[open_id]['running'] = False
|
||||||
|
agent.abort(); send_message(open_id, "⏹️ 正在停止...")
|
||||||
|
elif cmd == "/help":
|
||||||
|
send_message(open_id, "📖 命令列表:\n/stop - 停止当前任务\n/status - 查看状态\n/restore - 恢复上次对话历史\n/new - 开启新对话\n/help - 显示帮助")
|
||||||
|
elif cmd == "/status":
|
||||||
|
send_message(open_id, f"状态: {'🟢 空闲' if not agent.is_busy() else '🔴 运行中'}")
|
||||||
|
elif cmd == "/restore":
|
||||||
|
try:
|
||||||
|
files = glob.glob('./temp/model_responses_*.txt')
|
||||||
|
if not files: return send_message(open_id, "❌ 没有找到历史记录")
|
||||||
|
latest = max(files, key=os.path.getmtime)
|
||||||
|
with open(latest, 'r', encoding='utf-8') as f: content = f.read()
|
||||||
|
users = re.findall(r'=== USER ===\n(.+?)(?==== |$)', content, re.DOTALL)
|
||||||
|
resps = re.findall(r'=== Response ===.*?\n(.+?)(?==== Prompt|$)', content, re.DOTALL)
|
||||||
|
count = 0
|
||||||
|
for u, r in zip(users, resps):
|
||||||
|
u, r = u.strip(), r.strip()[:500]
|
||||||
|
if u and r: agent.history.extend([f"[USER]: {u}", f"[Agent] {r}"]); count += 1
|
||||||
|
agent.abort()
|
||||||
|
send_message(open_id, f"✅ 已恢复 {count} 轮对话\n来源: {os.path.basename(latest)}\n(仅恢复上下文,请输入新问题继续)")
|
||||||
|
except Exception as e: send_message(open_id, f"❌ 恢复失败: {e}")
|
||||||
|
else: send_message(open_id, f"❓ 未知命令: {cmd}")
|
||||||
|
def main():
|
||||||
|
global client
|
||||||
|
if not APP_ID or not APP_SECRET: print("错误: 请在 mykey.py 中配置 fs_app_id 和 fs_app_secret"); sys.exit(1)
|
||||||
|
client = create_client()
|
||||||
|
handler = lark.EventDispatcherHandler.builder("", "").register_p2_im_message_receive_v1(handle_message).build()
|
||||||
|
cli = lark.ws.Client(APP_ID, APP_SECRET, event_handler=handler, log_level=lark.LogLevel.INFO)
|
||||||
|
print("=" * 50 + "\n飞书 Agent 已启动(长连接模式)\n" + f"App ID: {APP_ID}\n等待消息...\n" + "=" * 50)
|
||||||
|
cli.start()
|
||||||
|
if __name__ == "__main__": main()
|
||||||
Reference in New Issue
Block a user