yiyan-browser-agent 1.4.10 → 1.5.0

package/README.md

@@ -11,7 +11,7 @@
 
 It drives a real browser to talk to [Yiyan (文心一言)](https://yiyan.baidu.com), giving you a Claude Code / Cursor-style coding agent powered by Baidu's AI models at zero cost.
 
-[Installation](#-installation) · [Quick Start](#-quick-start) · [Usage](#-usage) · [Configuration](#-configuration) · [Tools](#-available-tools) · [Contributing](#-contributing)
+[Installation](#-installation) · [Quick Start](#-quick-start) · [Usage](#-usage) · [HTTP API](#-http-api) · [Configuration](#-configuration) · [Tools](#-available-tools) · [Contributing](#-contributing)
 
 ---
 
@@ -47,30 +47,76 @@ Your Terminal
 
 ## 📦 Installation
 
-```bash
+### Windows
+
+```powershell
+# 安装 Node.js (如果没有)
+# 从 https://nodejs.org 下载安装，或使用 winget:
+winget install OpenJS.NodeJS.LTS
+
+# 全局安装 yiyan-browser-agent
 npm install -g yiyan-browser-agent
+
+# 安装 Chromium 浏览器 (首次安装后自动执行，约 150MB)
+npx playwright install chromium
 ```
 
-> Chromium downloads automatically after install (~150 MB, one time only).
+### Ubuntu / Linux
+
+```bash
+# 安装 Node.js (如果没有)
+curl -fsSL https://deb.nodesource.com/setup_20.x | sudo -E bash -
+sudo apt install -y nodejs
+
+# 全局安装 yiyan-browser-agent
+npm install -g yiyan-browser-agent
+
+# 安装 Chromium 和依赖
+npx playwright install chromium
+npx playwright install-deps chromium  # 安装系统依赖
+```
 
-**Requirements:** Node.js ≥ 18
+> **Requirements:** Node.js ≥ 18
 
 ---
 
 ## 🚀 Quick Start
 
-**1. First run — log in to Yiyan:**
+### Windows
+
+**1. 首次运行 — 登录文心一言:**
+```powershell
+yiyan-agent -i
+```
+浏览器窗口打开后，登录你的百度账号，然后回到终端按 Enter。会话会保存 — 只需登录一次。
+
+**2. 给任务:**
+```powershell
+yiyan-agent "创建一个 Express REST API，带用户认证"
+```
+
+**3. 发送任务到已运行的服务器:**
+```powershell
+# 终端 1: 启动交互模式 (作为 HTTP 服务器)
+yiyan-agent -i
+
+# 终端 2: 发送任务 (转发到服务器，不启动新浏览器)
+yiyan-agent "上海天气，20个字"
+```
+
+### Ubuntu / Linux
+
+**1. 首次运行 — 登录文心一言:**
 ```bash
-yiyan-agent --interactive
+yiyan-agent -i
 ```
-A browser window opens. Log in to your Yiyan (文心一言) account, then come back to the terminal and press **Enter**. Your session is saved — you only do this once.
 
-**2. Give it a task:**
+**2. 给任务:**
 ```bash
 yiyan-agent "build a REST API in Express with user authentication"
 ```
 
-**3. Use the short alias `ya` from any project folder:**
+**3. 从任意目录使用短别名 `ya`:**
 ```bash
 cd ~/my-project
 ya "add input validation to all my API routes"
@@ -84,11 +130,10 @@ ya "add input validation to all my API routes"
 yiyan-agent [OPTIONS] [TASK]
 
   -t, --task <task>    Task to run (or just type it as the last argument)
-  -i, --interactive    Keep browser open, run multiple tasks in a session
+  -i, --interactive    Keep browser open, run multiple tasks (starts HTTP server)
   -d, --dir <path>     Set working directory (default: current directory)
   --debug              Print raw AI responses to the terminal
-  --headless           Run browser invisibly (requires prior login)
-  --save-log           Save full session log to ~/.yiyan-agent/logs/
+  --show-browser       Show browser window (non-interactive mode)
   --calibrate          Auto-detect DOM selectors (run if agent breaks)
   -h, --help           Show help
 
@@ -102,38 +147,116 @@ Aliases:
 # Single task — runs and exits
 yiyan-agent "create a Python script that scrapes Hacker News"
 
-# Interactive mode — keeps browser open between tasks
-yiyan-agent --interactive
+# Interactive mode — keeps browser open, starts HTTP server on port 9527
+yiyan-agent -i
 
 # Run on a specific project
 ya --dir ~/projects/my-app "refactor all callbacks to async/await"
 
-### Process Communication (v1.4.8+)
+# Debug mode (shows what Yiyan is actually outputting)
+ya --debug "build a calculator"
 
-When interactive mode (`-i`) is running, other `yiyan-agent` processes automatically detect and forward tasks to it, avoiding repeated browser startup:
+# In interactive mode, type 'quit' or 'q' to exit:
+❯ quit
+```
+
+---
+
+## 🌐 HTTP API (v1.5.0+)
+
+When interactive mode (`-i`) is running, an HTTP server starts on port **9527**, allowing external services to send tasks.
+
+### Process Communication
 
 ```bash
-# Terminal 1: Start interactive mode (acts as server)
+# Terminal 1: Start interactive mode (HTTP server)
 yiyan-agent -i
 # → Server listening on port 9527
 
 # Terminal 2: Send task (forwarded to server, no new browser)
 yiyan-agent "北京天气，15个字"
-# → Found running server, forwarding task...
+# → Found running server on port 9527, forwarding task...
 ```
 
-Lock file: `~/.yiyan-agent/server.lock`
+### HTTP POST API
 
-# Debug mode (shows what Yiyan is actually outputting)
-ya --debug "build a calculator"
+**Endpoint:** `POST http://localhost:9527/task`
+
+**Request Body:**
+```json
+{
+  "task": "你的任务描述",
+  "newChat": true  // 可选，是否开启新对话，默认 true
+}
+```
+
+**Response:**
+```json
+{
+  "question": "上海天气，20个字",
+  "answer": "上海今日晴，气温25°C...",
+  "duration": 5234,
+  "status": "success"
+}
+```
+
+### Windows CMD (curl)
+
+```cmd
+curl -X POST http://localhost:9527/task -H "Content-Type: application/json" -d "{\"task\":\"上海天气，20个字\"}"
+```
 
-# Headless mode (faster — browser runs in background)
-ya --headless "write unit tests for utils.js"
+### PowerShell
 
-# In interactive mode, type 'new' to start a fresh chat:
-❯ Task: new
+```powershell
+Invoke-RestMethod -Uri "http://localhost:9527/task" -Method POST -Body '{"task":"上海天气"}' -ContentType "application/json"
+```
+
+### Ubuntu / Linux (curl)
+
+```bash
+curl -X POST http://localhost:9527/task -H "Content-Type: application/json" -d '{"task":"上海天气，20个字"}'
 ```
 
+### From Other Programming Languages
+
+**Python:**
+```python
+import requests
+import json
+
+response = requests.post(
+    'http://localhost:9527/task',
+    json={'task': '上海天气，20个字'}
+)
+result = response.json()
+print(result)
+```
+
+**Node.js:**
+```javascript
+const http = require('http');
+
+const body = JSON.stringify({ task: '上海天气，20个字' });
+
+const req = http.request({
+  hostname: 'localhost',
+  port: 9527,
+  path: '/task',
+  method: 'POST',
+  headers: { 'Content-Type': 'application/json' }
+}, (res) => {
+  let data = '';
+  res.on('data', chunk => data += chunk);
+  res.on('end', () => console.log(JSON.parse(data)));
+});
+
+req.write(body);
+req.end();
+```
+
+**Lock file:** `~/.yiyan-agent/server.lock`
+
 ---
 
 ## ⚙️ Configuration
@@ -209,6 +332,7 @@ Everything lives in `~/.yiyan-agent/` in your home directory:
 ~/.yiyan-agent/
 ├── session/        ← Browser cookies (login once, runs forever)
 ├── logs/           ← Session logs (only saved with --save-log)
+├── server.lock     ← HTTP server process lock
 └── config.json     ← Your global settings
 ```
 
@@ -235,8 +359,15 @@ yiyan-agent --interactive
 ```
 
 ### Chromium didn't download automatically
+**Windows:**
+```powershell
+npx playwright install chromium
+```
+
+**Ubuntu / Linux:**
 ```bash
 npx playwright install chromium
+npx playwright install-deps chromium
 ```
 
 ### Response times out on long tasks
@@ -245,6 +376,20 @@ Increase the timeout in your config:
 { "RESPONSE_TIMEOUT": 300000, "STABLE_DELAY": 4000 }
 ```
 
+### HTTP server not detected by other processes
+The lock file may be stale. Kill the old process and restart:
+```bash
+# Check process
+cat ~/.yiyan-agent/server.lock
+
+# Kill if needed
+kill <PID>  # Linux
+taskkill /PID <PID> /F  # Windows
+
+# Restart
+yiyan-agent -i
+```
+
 ---
 
 ## 🗂️ Project Structure
@@ -255,6 +400,8 @@ yiyan-browser-agent/
 │   ├── index.js          ← CLI entry point and argument parsing
 │   ├── agent.js          ← Core agent loop (send → wait → parse → execute)
 │   ├── browser.js        ← Playwright controller for yiyan.baidu.com
+│   ├── server.js         ← HTTP server for process communication (v1.5.0+)
+│   ├── client.js         ← HTTP client to forward tasks (v1.5.0+)
 │   ├── tools.js          ← All 15 filesystem and shell tools
 │   ├── parser.js         ← Extracts tool calls from AI responses (6 strategies)
 │   ├── prompt.js         ← System prompt and conversation history manager
@@ -289,7 +436,6 @@ node src/index.js --interactive
 - 🎨 **UI selector resilience** — Yiyan updates their UI occasionally; better selector strategies are welcome
 - 🔌 **More tools** — image generation, browser control, database tools, etc.
 - 🌐 **Other AI frontends** — adapting the browser layer to work with other free AI chats
-- 📦 **Windows support** — currently tested on Linux; Windows path handling may need fixes
 - 📝 **Better error messages** — making failures easier to diagnose
 
 ### How to contribute
@@ -329,4 +475,4 @@ MIT — see [LICENSE](./LICENSE) for details.
 
 If this project helped you, consider giving it a ⭐ on GitHub!
 
-</div>
+</div>

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "yiyan-browser-agent",
-  "version": "1.4.10",
+  "version": "1.5.0",
   "description": "AI coding agent powered by Yiyan (文心一言) via browser automation — no API key needed",
   "main": "src/index.js",
   "bin": {

package/src/client.js

@@ -1,8 +1,8 @@
 #!/usr/bin/env node
-// src/client.js — TCP client for sending tasks to running server
+// src/client.js — HTTP client for sending tasks to running server
 'use strict';
 
-const net = require('net');
+const http = require('http');
 const fs = require('fs');
 const path = require('path');
 const os = require('os');
@@ -46,45 +46,50 @@ class AgentClient {
     return false;
   }
 
-  // 发送任务到服务器
+  // 发送任务到服务器（HTTP POST）
   async sendTask(task, options = {}) {
     return new Promise((resolve, reject) => {
-      const socket = net.connect(this.port, 'localhost');
       const timeout = options.timeout || 180000; // 3分钟
 
-      let data = '';
-      let timer = setTimeout(() => {
-        socket.destroy();
-        reject(new Error('Connection timeout'));
-      }, timeout);
+      const requestBody = JSON.stringify({
+        task,
+        newChat: options.newChat !== false
+      });
 
-      socket.on('connect', () => {
-        clearTimeout(timer);
-        // 发送任务
-        const request = JSON.stringify({
-          task,
-          newChat: options.newChat !== false
+      const req = http.request({
+        hostname: 'localhost',
+        port: this.port,
+        path: '/task',
+        method: 'POST',
+        headers: {
+          'Content-Type': 'application/json',
+          'Content-Length': Buffer.byteLength(requestBody)
+        },
+        timeout
+      }, (res) => {
+        let data = '';
+        res.on('data', chunk => { data += chunk.toString(); });
+        res.on('end', () => {
+          try {
+            const result = JSON.parse(data);
+            resolve(result);
+          } catch (err) {
+            reject(new Error(`Invalid response: ${data}`));
+          }
         });
-        socket.end(request);
       });
 
-      socket.on('data', (chunk) => {
-        data += chunk.toString();
+      req.on('error', (err) => {
+        reject(err);
       });
 
-      socket.on('end', () => {
-        try {
-          const result = JSON.parse(data);
-          resolve(result);
-        } catch (err) {
-          reject(new Error(`Invalid response: ${data}`));
-        }
+      req.on('timeout', () => {
+        req.destroy();
+        reject(new Error('Request timeout'));
       });
 
-      socket.on('error', (err) => {
-        clearTimeout(timer);
-        reject(err);
-      });
+      req.write(requestBody);
+      req.end();
     });
   }
 }

package/src/server.js

@@ -1,8 +1,8 @@
 #!/usr/bin/env node
-// src/server.js — TCP server for accepting tasks from other processes
+// src/server.js — HTTP server for accepting tasks from other processes/services
 'use strict';
 
-const net = require('net');
+const http = require('http');
 const fs = require('fs');
 const path = require('path');
 const os = require('os');
@@ -23,15 +23,13 @@ class AgentServer {
       throw new Error(`Server already running on port ${this.port}`);
     }
 
-    this.server = net.createServer((socket) => {
-      this._handleConnection(socket);
+    this.server = http.createServer((req, res) => {
+      this._handleRequest(req, res);
     });
 
     await new Promise((resolve, reject) => {
-      this.server.listen(this.port, (err) => {
-        if (err) reject(err);
-        else resolve();
-      });
+      this.server.on('error', reject);
+      this.server.listen(this.port, resolve);
     });
 
     // 写锁文件
@@ -56,7 +54,6 @@ class AgentServer {
         const lock = JSON.parse(fs.readFileSync(LOCK_FILE, 'utf8'));
         // 检查进程是否还活着（Windows 兼容）
         try {
-          // Windows: tasklist 检查, Unix: process.kill(0)
           if (process.platform === 'win32') {
             const result = require('child_process').execSync(
               `tasklist /FI "PID eq ${lock.pid}" /NH`,
@@ -99,29 +96,31 @@ class AgentServer {
     } catch {}
   }
 
-  async _handleConnection(socket) {
-    let data = '';
+  async _handleRequest(req, res) {
+    const logger = require('./logger');
 
-    socket.on('data', (chunk) => {
-      data += chunk.toString();
-    });
+    // 只接受 POST /task
+    if (req.method !== 'POST') {
+      res.writeHead(405, { 'Content-Type': 'application/json' });
+      res.end(JSON.stringify({ status: 'error', answer: 'Method not allowed, use POST' }));
+      return;
+    }
 
-    socket.on('end', async () => {
+    // 读取请求体
+    let body = '';
+    req.on('data', chunk => { body += chunk.toString(); });
+    req.on('end', async () => {
       try {
-        const request = JSON.parse(data);
+        const request = JSON.parse(body);
         const result = await this._executeTask(request);
-        socket.end(JSON.stringify(result));
+        res.writeHead(200, { 'Content-Type': 'application/json' });
+        res.end(JSON.stringify(result));
       } catch (err) {
-        socket.end(JSON.stringify({
-          status: 'error',
-          answer: `Server error: ${err.message}`
-        }));
+        logger.error(`[HTTP Error] ${err.message}`);
+        res.writeHead(400, { 'Content-Type': 'application/json' });
+        res.end(JSON.stringify({ status: 'error', answer: `Bad request: ${err.message}` }));
       }
     });
-
-    socket.on('error', (err) => {
-      // 连接错误，忽略
-    });
   }
 
   async _executeTask(request) {
@@ -131,6 +130,9 @@ class AgentServer {
       return { status: 'error', answer: 'No task provided' };
     }
 
+    const logger = require('./logger');
+    logger.info(`[Remote Task] ${task}`);
+
     try {
       // 可选：开启新对话
       if (newChat) {
@@ -138,8 +140,10 @@ class AgentServer {
       }
 
       const result = await this.agent.run(task);
+      logger.info(`[Remote Task Done] ${result.status} (${result.duration}ms)`);
       return result;
     } catch (err) {
+      logger.error(`[Remote Task Error] ${err.message}`);
       return {
         question: task,
         answer: `Error: ${err.message}`,