chore(version): bump version to 1.1.2

chore(deps-dev): bump eslint-plugin-react-refresh from 0.4.26 to 0.5.0 in the development-dependencies group across 1 directory

README-zh.md

@@ -40,7 +40,7 @@
 
 ```html
 <script
-    src="https://registry.npmmirror.com/page-agent/1.1.0/files/dist/iife/page-agent.demo.js"
+    src="https://registry.npmmirror.com/page-agent/1.1.2/files/dist/iife/page-agent.demo.js"
     crossorigin="true"
 ></script>
 ```
@@ -50,8 +50,8 @@
 
 | Mirrors | URL                                                                                |
 | ------- | ---------------------------------------------------------------------------------- |
-| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.1.0/dist/iife/page-agent.demo.js         |
+| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.1.2/dist/iife/page-agent.demo.js         |
-| China   | https://registry.npmmirror.com/page-agent/1.1.0/files/dist/iife/page-agent.demo.js |
+| China   | https://registry.npmmirror.com/page-agent/1.1.2/files/dist/iife/page-agent.demo.js |
 
 ### NPM 安装
 

README.md

@@ -40,7 +40,7 @@ Fastest way to try PageAgent with our free Demo LLM:
 
 ```html
 <script
-    src="https://cdn.jsdelivr.net/npm/page-agent@1.1.0/dist/iife/page-agent.demo.js"
+    src="https://cdn.jsdelivr.net/npm/page-agent@1.1.2/dist/iife/page-agent.demo.js"
     crossorigin="true"
 ></script>
 ```
@@ -50,8 +50,8 @@ Fastest way to try PageAgent with our free Demo LLM:
 
 | Mirrors | URL                                                                                |
 | ------- | ---------------------------------------------------------------------------------- |
-| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.1.0/dist/iife/page-agent.demo.js         |
+| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.1.2/dist/iife/page-agent.demo.js         |
-| China   | https://registry.npmmirror.com/page-agent/1.1.0/files/dist/iife/page-agent.demo.js |
+| China   | https://registry.npmmirror.com/page-agent/1.1.2/files/dist/iife/page-agent.demo.js |
 
 ### NPM Installation
 

package.json

@@ -1,7 +1,7 @@
 {
     "name": "root",
     "private": true,
-    "version": "1.1.0",
+    "version": "1.1.2",
     "type": "module",
     "workspaces": [
         "packages/page-controller",
@@ -42,13 +42,14 @@
         "@microsoft/api-extractor": "^7.55.2",
         "@trivago/prettier-plugin-sort-imports": "^6.0.2",
         "@types/node": "^25.0.9",
+        "chalk": "^5.6.2",
         "concurrently": "^9.2.1",
         "dotenv": "^17.2.3",
         "eslint": "^9.39.2",
         "eslint-config-prettier": "^10.1.8",
         "eslint-plugin-react-dom": "^2.7.2",
         "eslint-plugin-react-hooks": "^7.0.1",
-        "eslint-plugin-react-refresh": "^0.4.26",
+        "eslint-plugin-react-refresh": "^0.5.0",
         "eslint-plugin-react-x": "^2.7.2",
         "globals": "^17.0.0",
         "husky": "^9.1.7",
@@ -58,7 +59,8 @@
         "typescript-eslint": "^8.54.0",
         "unplugin-dts": "^1.0.0-beta.6",
         "vite": "^7.3.1",
-        "vite-plugin-css-injected-by-js": "^3.5.2"
+        "vite-plugin-css-injected-by-js": "^3.5.2",
+        "vite-bundle-analyzer": "^1.3.6"
     },
     "overrides": {
         "typescript": "^5.9.3"

packages/core/package.json

@@ -1,7 +1,7 @@
 {
     "name": "@page-agent/core",
     "private": false,
-    "version": "1.1.0",
+    "version": "1.1.2",
     "type": "module",
     "main": "./dist/esm/page-agent-core.js",
     "module": "./dist/esm/page-agent-core.js",
@@ -45,7 +45,7 @@
     "dependencies": {
         "chalk": "^5.6.2",
         "zod": "^4.3.5",
-        "@page-agent/llms": "1.1.0",
+        "@page-agent/llms": "1.1.2",
-        "@page-agent/page-controller": "1.1.0"
+        "@page-agent/page-controller": "1.1.2"
     }
 }

packages/core/src/PageAgentCore.ts

@@ -5,13 +5,13 @@
 import { InvokeError, LLM, type Tool } from '@page-agent/llms'
 import type { PageController } from '@page-agent/page-controller'
 import chalk from 'chalk'
-import zod from 'zod'
+import * as zod from 'zod'
 
 import { type PageAgentConfig } from './config'
 import { DEFAULT_MAX_STEPS } from './config/constants'
 import SYSTEM_PROMPT from './prompts/system_prompt.md?raw'
 import { tools } from './tools'
-import {
+import type {
 	AgentActivity,
 	AgentReflection,
 	AgentStatus,
@@ -21,8 +21,7 @@ import {
 	MacroToolInput,
 	MacroToolResult,
 } from './types'
-import { normalizeResponse, trimLines, uid, waitFor } from './utils'
+import { assert, normalizeResponse, trimLines, uid, waitFor } from './utils'
-import { assert } from './utils/assert'
 
 export { type PageAgentConfig }
 export { tool, type PageAgentTool } from './tools'
@@ -209,20 +208,20 @@ export class PageAgentCore extends EventTarget {
 			lastURL: '',
 		}
 
-		try {
+		let step = 0
-			let step = 0
+
+		while (true) {
+			try {
+				console.group(`step: ${step}`)
 
-			while (true) {
 				await this.#generateObservations(step)
 
 				await onBeforeStep?.(this, step)
 
-				console.group(`step: ${step}`)
-
 				// abort
 				if (this.#abortController.signal.aborted) throw new Error('AbortError')
 
-				// Thinking
+				// status
 				console.log(chalk.blue('Thinking...'))
 				this.#emitActivity({ type: 'thinking' })
 
@@ -270,22 +269,13 @@ export class PageAgentCore extends EventTarget {
 
 				//
 
+				await onAfterStep?.(this, this.history)
+
 				console.log(chalk.green('Step finished:'), actionName)
 				console.groupEnd()
 
-				await onAfterStep?.(this, this.history)
+				// finish task if done
 
-				step++
-				if (step > this.config.maxSteps) {
-					this.#onDone(false)
-					const result: ExecutionResult = {
-						success: false,
-						data: 'Step count exceeded maximum limit',
-						history: this.history,
-					}
-					await onAfterTask?.(this, result)
-					return result
-				}
 				if (actionName === 'done') {
 					const success = action.input?.success ?? false
 					const text = action.input?.text || 'no text provided'
@@ -299,19 +289,32 @@ export class PageAgentCore extends EventTarget {
 					await onAfterTask?.(this, result)
 					return result
 				}
+			} catch (error: unknown) {
+				console.groupEnd() // to prevent nested groups
+				console.error('Task failed', error)
+				const errorMessage = String(error)
+				this.#emitActivity({ type: 'error', message: errorMessage })
+				this.#onDone(false)
+				const result: ExecutionResult = {
+					success: false,
+					data: errorMessage,
+					history: this.history,
+				}
+				await onAfterTask?.(this, result)
+				return result
 			}
-		} catch (error: unknown) {
+
-			console.error('Task failed', error)
+			step++
-			const errorMessage = String(error)
+			if (step > this.config.maxSteps) {
-			this.#emitActivity({ type: 'error', message: errorMessage })
+				this.#onDone(false)
-			this.#onDone(false)
+				const result: ExecutionResult = {
-			const result: ExecutionResult = {
+					success: false,
-				success: false,
+					data: 'Step count exceeded maximum limit',
-				data: errorMessage,
+					history: this.history,
-				history: this.history,
+				}
+				await onAfterTask?.(this, result)
+				return result
 			}
-			await onAfterTask?.(this, result)
-			return result
 		}
 	}
 
@@ -417,10 +420,8 @@ export class PageAgentCore extends EventTarget {
 			return this.config.customSystemPrompt
 		}
 
-		let systemPrompt = SYSTEM_PROMPT
-
 		const targetLanguage = this.config.language === 'zh-CN' ? '中文' : 'English'
-		systemPrompt = systemPrompt.replace(
+		const systemPrompt = SYSTEM_PROMPT.replace(
 			/Default working language: \*\*.*?\*\*/,
 			`Default working language: **${targetLanguage}**`
 		)

packages/core/src/prompts/system_prompt.md

@@ -10,7 +10,7 @@ You excel at following tasks:
 </intro>
 
 <language_settings>
-- Default working language: **中文**
+- Default working language: **English**
 - Use the language that user is using. Return in user's language.
 </language_settings>
 
@@ -144,12 +144,12 @@ Here are examples of good output patterns. Use them as reference but never copy
 </examples>
 
 <output>
-You must ALWAYS respond with a valid JSON in this exact format:
-
 {
   "evaluation_previous_goal": "Concise one-sentence analysis of your last action. Clearly state success, failure, or uncertain.",
   "memory": "1-3 concise sentences of specific memory of this step and overall progress. You should put here everything that will help you track progress in future steps. Like counting pages visited, items found, etc.",
-  "next_goal": "State the next immediate goal and action to achieve it, in one clear sentence."
+  "next_goal": "State the next immediate goal and action to achieve it, in one clear sentence.",
-  "action":{"action": {// action-specific parameter}}
+  "action":{
+    "Action name": {// Action parameters}
+  }
 }
 </output>

packages/core/src/tools/index.ts

@@ -2,7 +2,7 @@
  * Internal tools for PageAgent.
  * @note Adapted from browser-use
  */
-import zod, { type z } from 'zod'
+import * as zod from 'zod'
 
 import type { PageAgentCore } from '../PageAgentCore'
 import { waitFor } from '../utils'
@@ -13,7 +13,7 @@ import { waitFor } from '../utils'
 export interface PageAgentTool<TParams = any> {
 	// name: string
 	description: string
-	inputSchema: z.ZodType<TParams>
+	inputSchema: zod.ZodType<TParams>
 	execute: (this: PageAgentCore, args: TParams) => Promise<string>
 }
 

packages/core/src/utils/assert.ts

@@ -1,17 +0,0 @@
-import chalk from 'chalk'
-
-/**
- * Simple assertion function that throws an error if the condition is falsy
- * @param condition - The condition to assert
- * @param message - Optional error message
- * @throws Error if condition is falsy
- */
-export function assert(condition: unknown, message?: string, silent?: boolean): asserts condition {
-	if (!condition) {
-		const errorMessage = message ?? 'Assertion failed'
-
-		if (!silent) console.error(chalk.red(`❌ assert: ${errorMessage}`))
-
-		throw new Error(errorMessage)
-	}
-}

packages/core/src/utils/index.ts

@@ -1,3 +1,5 @@
+import chalk from 'chalk'
+
 export { normalizeResponse } from './autoFixer'
 
 /**
@@ -85,3 +87,19 @@ export function uid() {
 	ids.push(id)
 	return id
 }
+
+/**
+ * Simple assertion function that throws an error if the condition is falsy
+ * @param condition - The condition to assert
+ * @param message - Optional error message
+ * @throws Error if condition is falsy
+ */
+export function assert(condition: unknown, message?: string, silent?: boolean): asserts condition {
+	if (!condition) {
+		const errorMessage = message ?? 'Assertion failed'
+
+		if (!silent) console.error(chalk.red(`❌ assert: ${errorMessage}`))
+
+		throw new Error(errorMessage)
+	}
+}

packages/extension/docs/extension_api.md

@@ -0,0 +1,291 @@
+# Page Agent Extension API
+
+This document describes how to integrate the Page Agent browser extension into your web application.
+
+## Installation
+
+### 1. Install the browser extension
+
+Install the Page Agent extension from the Chrome Web Store.
+
+### 2. Install type definitions (recommended)
+
+```bash
+npm install @page-agent/core --save-dev
+```
+
+### 3. Set up authentication
+
+The extension only injects APIs when it detects a valid token in `localStorage`.
+
+1. Open the extension's side panel to get your authorization token
+2. Set the token in your page:
+
+```typescript
+localStorage.setItem('PageAgentExtUserAuthToken', 'your-token')
+```
+
+## Quick Start
+
+```typescript
+import type {
+  AgentActivity,
+  AgentStatus,
+  ExecutionResult,
+  HistoricalEvent,
+} from '@page-agent/core'
+
+// Wait for extension injection (up to 1 second)
+async function waitForExtension(timeout = 1000): Promise<boolean> {
+  const start = Date.now()
+  while (Date.now() - start < timeout) {
+    if (window.PAGE_AGENT_EXT) return true
+    await new Promise((r) => setTimeout(r, 100))
+  }
+  return false
+}
+
+// Usage
+if (await waitForExtension()) {
+  const result = await window.PAGE_AGENT_EXT!.execute('Click the login button', {
+    baseURL: 'https://api.openai.com/v1',
+    apiKey: 'your-api-key',
+    model: 'gpt-5.2',
+    onStatusChange: (status) => console.log('Status:', status),
+    onActivity: (activity) => console.log('Activity:', activity),
+  })
+  console.log('Result:', result)
+}
+```
+
+## Global API
+
+The extension injects the following APIs into the `window` object:
+
+### `window.PAGE_AGENT_EXT_VERSION`
+
+Extension version string (e.g., `"1.0.0"`). This is exposed separately to allow version checking before accessing the main API object.
+
+### `window.PAGE_AGENT_EXT`
+
+Main API namespace object containing:
+
+#### `PAGE_AGENT_EXT.execute(task, config)`
+
+Execute an agent task.
+
+**Parameters:**
+
+| Name | Type | Required | Description |
+|------|------|----------|-------------|
+| `task` | `string` | Yes | Task description |
+| `config` | `ExecuteConfig` | Yes | Execution configuration (LLM settings, options, and event callbacks) |
+
+**Returns:** `Promise<ExecutionResult>`
+
+#### `PAGE_AGENT_EXT.dispose()`
+
+Stop and destroy the current running agent.
+
+## Types
+
+Install `@page-agent/core` for full type definitions:
+
+```typescript
+import type {
+  AgentActivity,
+  AgentStatus,
+  ExecutionResult,
+  HistoricalEvent,
+} from '@page-agent/core'
+
+export interface ExecuteConfig {
+  baseURL: string
+  apiKey: string
+  model: string
+
+  /**
+   * Whether to include the initial tab (that holds this main world script) in the task.
+   * @default true
+   */
+  includeInitialTab?: boolean
+
+  onStatusChange?: (status: AgentStatus) => void
+  onActivity?: (activity: AgentActivity) => void
+  onHistoryUpdate?: (history: HistoricalEvent[]) => void
+  onDispose?: () => void
+}
+
+export type Execute = (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
+```
+
+### AgentStatus
+
+```typescript
+type AgentStatus = 'idle' | 'running' | 'completed' | 'error'
+```
+
+| Status | Description |
+|--------|-------------|
+| `idle` | Agent is idle, ready to execute |
+| `running` | Agent is executing a task |
+| `completed` | Task completed successfully |
+| `error` | Task failed with an error |
+
+### AgentActivity
+
+```typescript
+type AgentActivity =
+  | { type: 'thinking' }
+  | { type: 'executing'; tool: string; input: unknown }
+  | { type: 'executed'; tool: string; input: unknown; output: string; duration: number }
+  | { type: 'retrying'; attempt: number; maxAttempts: number }
+  | { type: 'error'; message: string }
+```
+
+| Type | Description |
+|------|-------------|
+| `thinking` | Agent is analyzing the page and planning |
+| `executing` | Agent is executing a tool action |
+| `executed` | Tool execution completed |
+| `retrying` | Retrying after a failure |
+| `error` | An error occurred |
+
+### HistoricalEvent
+
+```typescript
+type HistoricalEvent =
+  | { type: 'step'; stepIndex: number; reflection: AgentReflection; action: Action }
+  | { type: 'observation'; content: string }
+  | { type: 'user_takeover' }
+  | { type: 'retry'; message: string; attempt: number; maxAttempts: number }
+  | { type: 'error'; message: string; rawResponse?: unknown }
+```
+
+### ExecutionResult
+
+```typescript
+interface ExecutionResult {
+  success: boolean
+  data: string
+  history: HistoricalEvent[]
+}
+```
+
+## Usage Examples
+
+### Basic Execution
+
+```typescript
+const result = await window.PAGE_AGENT_EXT!.execute(
+  'Fill in the email field with test@example.com and click Submit',
+  {
+    baseURL: 'https://api.openai.com/v1',
+    apiKey: process.env.OPENAI_API_KEY!,
+    model: 'gpt-5.2',
+  }
+)
+
+if (result.success) {
+  console.log('Task completed:', result.data)
+} else {
+  console.error('Task failed')
+}
+```
+
+### Exclude Initial Tab
+
+By default, the agent includes the initial tab (where the script runs) in the task. Set `includeInitialTab: false` to exclude it:
+
+```typescript
+const result = await window.PAGE_AGENT_EXT!.execute(
+  'Open a new tab and search for page-agent on GitHub',
+  {
+    baseURL: 'https://api.openai.com/v1',
+    apiKey: process.env.OPENAI_API_KEY!,
+    model: 'gpt-5.2',
+    includeInitialTab: false,  // Agent will open new tabs only
+  }
+)
+```
+
+### With Event Callbacks
+
+```typescript
+await window.PAGE_AGENT_EXT!.execute('Navigate to the settings page', {
+  baseURL: 'https://api.openai.com/v1',
+  apiKey: process.env.OPENAI_API_KEY!,
+  model: 'gpt-5.2',
+  onStatusChange: (status) => {
+    updateUI({ agentStatus: status })
+  },
+  onActivity: (activity) => {
+    switch (activity.type) {
+      case 'thinking':
+        showSpinner('Agent is thinking...')
+        break
+      case 'executing':
+        showSpinner(`Executing: ${activity.tool}`)
+        break
+      case 'executed':
+        log(`${activity.tool} completed in ${activity.duration}ms`)
+        break
+      case 'error':
+        showError(activity.message)
+        break
+    }
+  },
+  onHistoryUpdate: (history) => {
+    renderHistory(history)
+  },
+})
+```
+
+### Stop Execution
+
+```typescript
+// Start a task
+window.PAGE_AGENT_EXT!.execute('Scroll through all pages', {
+  baseURL: 'https://api.openai.com/v1',
+  apiKey: process.env.OPENAI_API_KEY!,
+  model: 'gpt-5.2',
+})
+
+// Later, stop it
+window.PAGE_AGENT_EXT!.dispose()
+```
+
+## Window Type Declaration
+
+If not using `@page-agent/core`, add this to your project:
+
+```typescript
+import type {
+  AgentActivity,
+  AgentStatus,
+  ExecutionResult,
+  HistoricalEvent,
+} from '@page-agent/core'
+
+interface ExecuteConfig {
+  baseURL: string
+  apiKey: string
+  model: string
+  includeInitialTab?: boolean
+  onStatusChange?: (status: AgentStatus) => void
+  onActivity?: (activity: AgentActivity) => void
+  onHistoryUpdate?: (history: HistoricalEvent[]) => void
+  onDispose?: () => void
+}
+
+declare global {
+  interface Window {
+    PAGE_AGENT_EXT_VERSION?: string
+    PAGE_AGENT_EXT?: {
+      version: string
+      execute: (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
+      dispose: () => void
+    }
+  }
+}
+```

packages/extension/docs/extension_api_zh.md

@@ -0,0 +1,291 @@
+# Page Agent 浏览器插件 API
+
+本文档介绍如何在网页应用中接入 Page Agent 浏览器插件。
+
+## 安装
+
+### 1. 安装浏览器插件
+
+从 Chrome 应用商店安装 Page Agent 插件。
+
+### 2. 安装类型定义（推荐）
+
+```bash
+npm install @page-agent/core --save-dev
+```
+
+### 3. 配置认证
+
+插件在页面加载后检测 `localStorage` 中的 token，匹配时才会注入 API。
+
+1. 打开插件的侧边栏面板，获取授权 token
+2. 在页面中设置 token：
+
+```typescript
+localStorage.setItem('PageAgentExtUserAuthToken', 'your-token')
+```
+
+## 快速开始
+
+```typescript
+import type {
+  AgentActivity,
+  AgentStatus,
+  ExecutionResult,
+  HistoricalEvent,
+} from '@page-agent/core'
+
+// 等待插件注入（最多 1 秒）
+async function waitForExtension(timeout = 1000): Promise<boolean> {
+  const start = Date.now()
+  while (Date.now() - start < timeout) {
+    if (window.PAGE_AGENT_EXT) return true
+    await new Promise((r) => setTimeout(r, 100))
+  }
+  return false
+}
+
+// 使用
+if (await waitForExtension()) {
+  const result = await window.PAGE_AGENT_EXT!.execute('点击登录按钮', {
+    baseURL: 'https://api.openai.com/v1',
+    apiKey: 'your-api-key',
+    model: 'gpt-5.2',
+    onStatusChange: (status) => console.log('状态:', status),
+    onActivity: (activity) => console.log('活动:', activity),
+  })
+  console.log('结果:', result)
+}
+```
+
+## 全局 API
+
+插件在 `window` 对象上注入以下 API：
+
+### `window.PAGE_AGENT_EXT_VERSION`
+
+插件版本号字符串（例如 `"1.0.0"`）。单独暴露版本号，方便在访问主 API 对象前进行版本检查。
+
+### `window.PAGE_AGENT_EXT`
+
+主 API 命名空间对象，包含：
+
+#### `PAGE_AGENT_EXT.execute(task, config)`
+
+执行 Agent 任务。
+
+**参数：**
+
+| 名称 | 类型 | 必填 | 说明 |
+|------|------|------|------|
+| `task` | `string` | 是 | 任务描述 |
+| `config` | `ExecuteConfig` | 是 | 执行配置（LLM 设置、选项和事件回调） |
+
+**返回：** `Promise<ExecutionResult>`
+
+#### `PAGE_AGENT_EXT.dispose()`
+
+停止并销毁当前运行的 Agent。
+
+## 类型定义
+
+安装 `@page-agent/core` 获取完整类型：
+
+```typescript
+import type {
+  AgentActivity,
+  AgentStatus,
+  ExecutionResult,
+  HistoricalEvent,
+} from '@page-agent/core'
+
+export interface ExecuteConfig {
+  baseURL: string
+  apiKey: string
+  model: string
+
+  /**
+   * 是否将初始标签页（运行此脚本的页面）包含在任务中。
+   * @default true
+   */
+  includeInitialTab?: boolean
+
+  onStatusChange?: (status: AgentStatus) => void
+  onActivity?: (activity: AgentActivity) => void
+  onHistoryUpdate?: (history: HistoricalEvent[]) => void
+  onDispose?: () => void
+}
+
+export type Execute = (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
+```
+
+### AgentStatus
+
+```typescript
+type AgentStatus = 'idle' | 'running' | 'completed' | 'error'
+```
+
+| 状态 | 说明 |
+|------|------|
+| `idle` | 空闲，准备执行 |
+| `running` | 正在执行任务 |
+| `completed` | 任务成功完成 |
+| `error` | 任务执行失败 |
+
+### AgentActivity
+
+```typescript
+type AgentActivity =
+  | { type: 'thinking' }
+  | { type: 'executing'; tool: string; input: unknown }
+  | { type: 'executed'; tool: string; input: unknown; output: string; duration: number }
+  | { type: 'retrying'; attempt: number; maxAttempts: number }
+  | { type: 'error'; message: string }
+```
+
+| 类型 | 说明 |
+|------|------|
+| `thinking` | Agent 正在分析页面并规划 |
+| `executing` | 正在执行工具操作 |
+| `executed` | 工具执行完成 |
+| `retrying` | 失败后重试 |
+| `error` | 发生错误 |
+
+### HistoricalEvent
+
+```typescript
+type HistoricalEvent =
+  | { type: 'step'; stepIndex: number; reflection: AgentReflection; action: Action }
+  | { type: 'observation'; content: string }
+  | { type: 'user_takeover' }
+  | { type: 'retry'; message: string; attempt: number; maxAttempts: number }
+  | { type: 'error'; message: string; rawResponse?: unknown }
+```
+
+### ExecutionResult
+
+```typescript
+interface ExecutionResult {
+  success: boolean
+  data: string
+  history: HistoricalEvent[]
+}
+```
+
+## 使用示例
+
+### 基础执行
+
+```typescript
+const result = await window.PAGE_AGENT_EXT!.execute(
+  '在邮箱输入框填入 test@example.com 然后点击提交',
+  {
+    baseURL: 'https://api.openai.com/v1',
+    apiKey: process.env.OPENAI_API_KEY!,
+    model: 'gpt-5.2',
+  }
+)
+
+if (result.success) {
+  console.log('任务完成:', result.data)
+} else {
+  console.error('任务失败')
+}
+```
+
+### 排除初始标签页
+
+默认情况下，Agent 会将初始标签页（运行脚本的页面）包含在任务中。设置 `includeInitialTab: false` 可以排除它：
+
+```typescript
+const result = await window.PAGE_AGENT_EXT!.execute(
+  '打开新标签页并在 GitHub 上搜索 page-agent',
+  {
+    baseURL: 'https://api.openai.com/v1',
+    apiKey: process.env.OPENAI_API_KEY!,
+    model: 'gpt-5.2',
+    includeInitialTab: false,  // Agent 只会打开新标签页
+  }
+)
+```
+
+### 使用事件回调
+
+```typescript
+await window.PAGE_AGENT_EXT!.execute('导航到设置页面', {
+  baseURL: 'https://api.openai.com/v1',
+  apiKey: process.env.OPENAI_API_KEY!,
+  model: 'gpt-5.2',
+  onStatusChange: (status) => {
+    updateUI({ agentStatus: status })
+  },
+  onActivity: (activity) => {
+    switch (activity.type) {
+      case 'thinking':
+        showSpinner('Agent 正在思考...')
+        break
+      case 'executing':
+        showSpinner(`正在执行: ${activity.tool}`)
+        break
+      case 'executed':
+        log(`${activity.tool} 完成，耗时 ${activity.duration}ms`)
+        break
+      case 'error':
+        showError(activity.message)
+        break
+    }
+  },
+  onHistoryUpdate: (history) => {
+    renderHistory(history)
+  },
+})
+```
+
+### 停止执行
+
+```typescript
+// 启动任务
+window.PAGE_AGENT_EXT!.execute('滚动浏览所有页面', {
+  baseURL: 'https://api.openai.com/v1',
+  apiKey: process.env.OPENAI_API_KEY!,
+  model: 'gpt-5.2',
+})
+
+// 稍后停止
+window.PAGE_AGENT_EXT!.dispose()
+```
+
+## Window 类型声明
+
+如果不使用 `@page-agent/core`，可以添加以下声明：
+
+```typescript
+import type {
+  AgentActivity,
+  AgentStatus,
+  ExecutionResult,
+  HistoricalEvent,
+} from '@page-agent/core'
+
+interface ExecuteConfig {
+  baseURL: string
+  apiKey: string
+  model: string
+  includeInitialTab?: boolean
+  onStatusChange?: (status: AgentStatus) => void
+  onActivity?: (activity: AgentActivity) => void
+  onHistoryUpdate?: (history: HistoricalEvent[]) => void
+  onDispose?: () => void
+}
+
+declare global {
+  interface Window {
+    PAGE_AGENT_EXT_VERSION?: string
+    PAGE_AGENT_EXT?: {
+      version: string
+      execute: (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
+      dispose: () => void
+    }
+  }
+}
+```

packages/extension/package.json

@@ -1,7 +1,7 @@
 {
     "name": "@page-agent/ext",
     "private": true,
-    "version": "0.1.0",
+    "version": "0.1.3",
     "type": "module",
     "scripts": {
         "dev": "wxt",
@@ -16,21 +16,17 @@
         "@types/react-dom": "^19.2.1",
         "@vitejs/plugin-react-swc": "^4.1.0",
         "@wxt-dev/module-react": "^1.1.5",
-        "i18next": "^25.7.4",
-        "i18next-browser-languagedetector": "^8.2.0",
         "react": "^19.2.4",
         "react-dom": "^19.2.4",
-        "react-i18next": "^16.5.2",
         "tailwindcss": "^4.1.14",
         "tw-animate-css": "^1.4.0",
-        "wouter": "^3.9.0",
         "wxt": "^0.20.13"
     },
     "dependencies": {
-        "@page-agent/core": "1.1.0",
+        "@page-agent/core": "1.1.2",
-        "@page-agent/llms": "1.1.0",
+        "@page-agent/llms": "1.1.2",
-        "@page-agent/page-controller": "1.1.0",
+        "@page-agent/page-controller": "1.1.2",
-        "@page-agent/ui": "1.1.0",
+        "@page-agent/ui": "1.1.2",
         "@radix-ui/react-hover-card": "^1.1.15",
         "@radix-ui/react-icons": "^1.3.2",
         "@radix-ui/react-label": "^2.1.8",
@@ -41,10 +37,10 @@
         "class-variance-authority": "^0.7.1",
         "clsx": "^2.1.1",
         "lucide-react": "^0.563.0",
-        "motion": "^12.29.2",
+        "motion": "^12.30.0",
         "next-themes": "^0.4.6",
         "rough-notation": "^0.5.1",
-        "simple-icons": "^16.5.0",
+        "simple-icons": "^16.7.0",
         "sonner": "^2.0.7",
         "tailwind-merge": "^3.4.0"
     }

packages/extension/src/agent/MultiPageAgent.ts

@@ -5,17 +5,35 @@ import { TabsController } from './TabsController'
 import SYSTEM_PROMPT from './system_prompt.md?raw'
 import { createTabTools } from './tabTools'
 
+/** Detect user language from browser settings */
+function detectLanguage(): 'en-US' | 'zh-CN' {
+	const lang = navigator.language || navigator.languages?.[0] || 'en-US'
+	return lang.startsWith('zh') ? 'zh-CN' : 'en-US'
+}
+
 /**
  * MultiPageAgent
  * - use with extension
  * - can be used from a side panel or a content script
  */
 export class MultiPageAgent extends PageAgentCore {
-	constructor(config: Omit<PageAgentConfig, 'pageController'>) {
+	constructor(config: Omit<PageAgentConfig, 'pageController'> & { includeInitialTab?: boolean }) {
+		// multi page controller
 		const tabsController = new TabsController()
 		const pageController = new RemotePageController(tabsController)
 		const customTools = createTabTools(tabsController)
 
+		// system prompt - auto-detect language if not specified
+		const language = config.language ?? detectLanguage()
+		const targetLanguage = language === 'zh-CN' ? '中文' : 'English'
+		const systemPrompt = SYSTEM_PROMPT.replace(
+			/Default working language: \*\*.*?\*\*/,
+			`Default working language: **${targetLanguage}**`
+		)
+
+		// include initial tab for controlling
+		const includeInitialTab = config.includeInitialTab ?? true
+
 		/**
 		 * When the agent is in side-panel and user closed the side-panel.
 		 * There is no chance for isAgentRunning to be set false.
@@ -29,10 +47,10 @@ export class MultiPageAgent extends PageAgentCore {
 			...config,
 			pageController: pageController as any,
 			customTools: customTools,
-			customSystemPrompt: SYSTEM_PROMPT,
+			customSystemPrompt: systemPrompt,
 
 			onBeforeTask: async (agent) => {
-				await tabsController.init(agent.task)
+				await tabsController.init(agent.task, includeInitialTab)
 
 				heartBeatInterval = window.setInterval(() => {
 					chrome.storage.local.set({

packages/extension/src/agent/TabsController.ts

@@ -12,7 +12,7 @@ export class TabsController extends EventTarget {
 	private task: string = ''
 	private windowId: number | null = null
 
-	async init(task: string) {
+	async init(task: string, includeInitialTab: boolean = true) {
 		this.task = task
 		this.tabs = []
 		this.currentTabId = null
@@ -26,17 +26,19 @@ export class TabsController extends EventTarget {
 		})
 
 		this.initialTabId = result.tabId
-		this.currentTabId = result.tabId
-
-		this.tabs.push({
-			id: result.tabId,
-			isInitial: true,
-		})
 
 		if (!this.initialTabId) {
 			throw new Error('Failed to get initial tab ID')
 		}
 
+		if (includeInitialTab) {
+			this.currentTabId = this.initialTabId
+			this.tabs.push({
+				id: result.tabId,
+				isInitial: true,
+			})
+		}
+
 		await this.updateCurrentTabId(this.currentTabId)
 
 		const tabChangeHandler = (message: any): void => {
@@ -230,6 +232,10 @@ export class TabsController extends EventTarget {
 				`| ${tab.id} | ${url} | ${title} | ${this.currentTabId === tab.id ? '✅' : ''} |`
 			)
 		}
+		if (!this.tabs.length) {
+			summaries.push('\nNo tabs available. Open a tab if needed.')
+		}
+
 		return summaries.join('\n')
 	}
 

packages/extension/src/agent/system_prompt.md

@@ -10,7 +10,7 @@ You excel at following tasks:
 </intro>
 
 <language_settings>
-- Default working language: **中文**
+- Default working language: **English**
 - Use the language that user is using. Return in user's language.
 </language_settings>
 
@@ -136,12 +136,12 @@ Here are examples of good output patterns. Use them as reference but never copy
 </examples>
 
 <output>
-You must ALWAYS respond with a valid JSON in this exact format:
-
 {
   "evaluation_previous_goal": "Concise one-sentence analysis of your last action. Clearly state success, failure, or uncertain.",
   "memory": "1-3 concise sentences of specific memory of this step and overall progress. You should put here everything that will help you track progress in future steps. Like counting pages visited, items found, etc.",
-  "next_goal": "State the next immediate goal and action to achieve it, in one clear sentence."
+  "next_goal": "State the next immediate goal and action to achieve it, in one clear sentence.",
-  "action":{"action_name": {// action-specific parameter}}
+  "action":{
+    "Action name": {// Action parameters}
+  }
 }
 </output>

packages/extension/src/agent/tabTools.ts

@@ -6,7 +6,7 @@
  * - switch_to_tab: Switch to an existing tab
  * - close_tab: Close a tab (optionally switch to another)
  */
-import zod from 'zod'
+import * as zod from 'zod'
 
 import type { TabsController } from './TabsController'
 

packages/extension/src/agent/useAgent.ts

@@ -88,6 +88,7 @@ export function useAgent(): UseAgentResult {
 	}, [])
 
 	const configure = useCallback(async (newConfig: LLMConfig) => {
+		await chrome.storage.local.set({ llmConfig: newConfig })
 		setConfig(newConfig)
 	}, [])
 

packages/extension/src/assets/index.css

@@ -40,7 +40,7 @@
 }
 
 .dark {
-	--background: oklch(0.145 0 0);
+	--background: oklch(0.19 0 0);
 	--foreground: oklch(0.985 0 0);
 	--card: oklch(0.145 0 0);
 	--card-foreground: oklch(0.985 0 0);

packages/extension/src/entrypoints/content.ts

@@ -69,11 +69,11 @@ async function exposeAgentToPage() {
 				}
 
 				try {
-					const { task, llmConfig } = payload
+					const { task, config } = payload
 
 					// create when used
 
-					multiPageAgent = new MultiPageAgent(llmConfig)
+					multiPageAgent = new MultiPageAgent(config)
 
 					// events
 

packages/extension/src/entrypoints/main-world.ts

@@ -1,35 +1,38 @@
 import type { AgentActivity, AgentStatus, ExecutionResult, HistoricalEvent } from '@page-agent/core'
-import type { LLMConfig } from '@page-agent/llms'
 
-export interface ExecuteHooks {
+export type Execute = (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
+
+export interface ExecuteConfig {
+	baseURL: string
+	apiKey: string
+	model: string
+
+	/**
+	 * Whether to include the initial tab (that holds this main world script) in the task.
+	 * @default true
+	 */
+	includeInitialTab?: boolean
+
 	onStatusChange?: (status: AgentStatus) => void
 	onActivity?: (activity: AgentActivity) => void
 	onHistoryUpdate?: (history: HistoricalEvent[]) => void
 	onDispose?: () => void
 }
 
-export type Execute = (
-	task: string,
-	llmConfig: LLMConfig,
-	hooks?: ExecuteHooks
-) => Promise<ExecutionResult>
-
 export default defineUnlistedScript(() => {
-	const w = window as any
-
 	let _lastId = 0
 	function getId() {
 		_lastId += 1
 		return _lastId
 	}
 
-	w.execute = async (task: string, llmConfig: LLMConfig, hooks?: ExecuteHooks) => {
+	const execute: Execute = async (task, config) => {
 		if (typeof task !== 'string') throw new Error('Task must be a string')
 		if (task.trim().length === 0) throw new Error('Task cannot be empty')
-		if (!llmConfig) throw new Error('LLM config is required')
+		if (!config) throw new Error('Config is required')
-		if (!llmConfig.baseURL) throw new Error('LLM config must have a baseURL')
+		if (!config.baseURL) throw new Error('Config must have a baseURL')
-		if (!llmConfig.apiKey) throw new Error('LLM config must have an apiKey')
+		if (!config.apiKey) throw new Error('Config must have an apiKey')
-		if (!llmConfig.model) throw new Error('LLM config must have a model')
+		if (!config.model) throw new Error('Config must have a model')
 
 		const id = getId()
 
@@ -42,30 +45,31 @@ export default defineUnlistedScript(() => {
 
 				// events
 
-				if (data.action === 'status_change_event' && hooks?.onStatusChange) {
+				if (data.action === 'status_change_event' && config.onStatusChange) {
-					hooks.onStatusChange(data.payload)
+					config.onStatusChange(data.payload)
 					return
 				}
 
-				if (data.action === 'activity_event' && hooks?.onActivity) {
+				if (data.action === 'activity_event' && config.onActivity) {
-					hooks.onActivity(data.payload)
+					config.onActivity(data.payload)
 					return
 				}
 
-				if (data.action === 'history_change_event' && hooks?.onHistoryUpdate) {
+				if (data.action === 'history_change_event' && config.onHistoryUpdate) {
-					hooks.onHistoryUpdate(data.payload)
+					config.onHistoryUpdate(data.payload)
 					return
 				}
 
-				if (data.action === 'dispose_event' && hooks?.onDispose) {
+				if (data.action === 'dispose_event' && config.onDispose) {
-					hooks.onDispose()
+					config.onDispose()
+					window.removeEventListener('message', handleMessage)
 					return
 				}
 
-				// result
-
 				if (data.action !== 'execute_result') return
 
+				// execute_result
+
 				window.removeEventListener('message', handleMessage)
 
 				if (data.error) {
@@ -75,6 +79,7 @@ export default defineUnlistedScript(() => {
 				}
 			}
 
+			// @note will be removed on dispose or result
 			window.addEventListener('message', handleMessage)
 		})
 
@@ -83,7 +88,15 @@ export default defineUnlistedScript(() => {
 				channel: 'PAGE_AGENT_EXT_REQUEST',
 				id,
 				action: 'execute',
-				payload: { task, llmConfig },
+				payload: {
+					task,
+					config: {
+						baseURL: config.baseURL,
+						apiKey: config.apiKey,
+						model: config.model,
+						includeInitialTab: config.includeInitialTab,
+					},
+				},
 			},
 			'*'
 		)
@@ -91,7 +104,7 @@ export default defineUnlistedScript(() => {
 		return promise
 	}
 
-	w.dispose = () => {
+	const dispose = () => {
 		const id = getId()
 
 		window.postMessage(
@@ -103,4 +116,11 @@ export default defineUnlistedScript(() => {
 			'*'
 		)
 	}
+
+	;(window as any).PAGE_AGENT_EXT_VERSION = __EXT_VERSION__
+	;(window as any).PAGE_AGENT_EXT = {
+		version: __EXT_VERSION__,
+		execute,
+		dispose,
+	}
 })

packages/extension/src/entrypoints/sidepanel/App.tsx

@@ -30,7 +30,7 @@ export default function App() {
 	}, [history, activity])
 
 	const handleSubmit = useCallback(
-		(e?: React.FormEvent) => {
+		(e?: React.SyntheticEvent) => {
 			e?.preventDefault()
 			if (!inputValue.trim() || status === 'running') return
 
@@ -82,7 +82,12 @@ export default function App() {
 				</div>
 				<div className="flex items-center gap-3">
 					<StatusDot status={status} />
-					<Button variant="ghost" size="icon-sm" onClick={() => setShowConfig(true)}>
+					<Button
+						variant="ghost"
+						size="icon-sm"
+						onClick={() => setShowConfig(true)}
+						className="cursor-pointer"
+					>
 						<Settings className="size-3.5" />
 					</Button>
 				</div>
@@ -142,7 +147,7 @@ export default function App() {
 								variant="default"
 								onClick={() => handleSubmit()}
 								disabled={!inputValue.trim()}
-								className="size-7"
+								className="size-7 cursor-pointer"
 							>
 								<Send className="size-3" />
 							</InputGroupButton>

packages/extension/src/entrypoints/sidepanel/components/ConfigPanel.tsx

@@ -1,6 +1,7 @@
 import type { LLMConfig } from '@page-agent/llms'
-import { Copy, Loader2 } from 'lucide-react'
+import { Copy, CornerUpLeft, Eye, EyeOff, HatGlasses, Home, Loader2, Scale } from 'lucide-react'
 import { useEffect, useState } from 'react'
+import { siGithub } from 'simple-icons'
 
 import { DEMO_API_KEY, DEMO_BASE_URL, DEMO_MODEL } from '@/agent/constants'
 import { Button } from '@/components/ui/button'
@@ -19,6 +20,8 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 	const [saving, setSaving] = useState(false)
 	const [userAuthToken, setUserAuthToken] = useState<string>('')
 	const [copied, setCopied] = useState(false)
+	const [showToken, setShowToken] = useState(false)
+	const [showApiKey, setShowApiKey] = useState(false)
 
 	// Update local state when config prop changes
 	useEffect(() => {
@@ -69,8 +72,18 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 	}
 
 	return (
-		<div className="flex flex-col gap-4 p-4">
+		<div className="flex flex-col gap-4 p-4 relative">
-			<h2 className="text-base font-semibold">Settings</h2>
+			<div className="flex items-center justify-between">
+				<h2 className="text-base font-semibold">Settings</h2>
+				<Button
+					variant="ghost"
+					size="icon-sm"
+					onClick={onClose}
+					className="absolute top-2 right-3 cursor-pointer"
+				>
+					<CornerUpLeft className="size-3.5" />
+				</Button>
+			</div>
 
 			{/* User Auth Token Section */}
 			<div className="flex flex-col gap-1.5 p-3 bg-muted/50 rounded-md border">
@@ -81,9 +94,24 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 				<div className="flex gap-2 items-center">
 					<Input
 						readOnly
-						value={userAuthToken || 'Loading...'}
+						value={
+							userAuthToken
+								? showToken
+									? userAuthToken
+									: `${userAuthToken.slice(0, 4)}${'•'.repeat(userAuthToken.length - 8)}${userAuthToken.slice(-4)}`
+								: 'Loading...'
+						}
 						className="text-xs h-8 font-mono bg-background"
 					/>
+					<Button
+						variant="outline"
+						size="icon"
+						className="h-8 w-8 shrink-0 cursor-pointer"
+						onClick={() => setShowToken(!showToken)}
+						disabled={!userAuthToken}
+					>
+						{showToken ? <EyeOff className="size-3" /> : <Eye className="size-3" />}
+					</Button>
 					<Button
 						variant="outline"
 						size="icon"
@@ -118,23 +146,98 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 
 			<div className="flex flex-col gap-1.5">
 				<label className="text-xs text-muted-foreground">API Key</label>
-				<Input
+				<div className="flex gap-2 items-center">
-					type="password"
+					<Input
-					placeholder="sk-..."
+						type={showApiKey ? 'text' : 'password'}
-					value={apiKey}
+						placeholder="sk-..."
-					onChange={(e) => setApiKey(e.target.value)}
+						value={apiKey}
-					className="text-xs h-8"
+						onChange={(e) => setApiKey(e.target.value)}
-				/>
+						className="text-xs h-8"
+					/>
+					<Button
+						variant="outline"
+						size="icon"
+						className="h-8 w-8 shrink-0 cursor-pointer"
+						onClick={() => setShowApiKey(!showApiKey)}
+					>
+						{showApiKey ? <EyeOff className="size-3" /> : <Eye className="size-3" />}
+					</Button>
+				</div>
 			</div>
 
 			<div className="flex gap-2 mt-2">
-				<Button variant="outline" onClick={onClose} className="flex-1 h-8 text-xs">
+				<Button variant="outline" onClick={onClose} className="flex-1 h-8 text-xs cursor-pointer">
 					Cancel
 				</Button>
-				<Button onClick={handleSave} disabled={saving} className="flex-1 h-8 text-xs">
+				<Button
+					onClick={handleSave}
+					disabled={saving}
+					className="flex-1 h-8 text-xs cursor-pointer"
+				>
 					{saving ? <Loader2 className="size-3 animate-spin" /> : 'Save'}
 				</Button>
 			</div>
+
+			{/* Footer */}
+			<div className="mt-4 mb-4 pt-4 border-t border-border/50 flex gap-2 justify-between text-[10px] text-muted-foreground">
+				<div className="flex flex-col justify-between">
+					<a
+						href="https://github.com/alibaba/page-agent"
+						target="_blank"
+						rel="noopener noreferrer"
+						className="flex items-center gap-1 hover:text-foreground"
+					>
+						<svg role="img" viewBox="0 0 24 24" className="size-3 fill-current">
+							<path d={siGithub.path} />
+						</svg>
+						<span>Source Code</span>
+					</a>
+
+					<a
+						href="https://alibaba.github.io/page-agent/"
+						target="_blank"
+						rel="noopener noreferrer"
+						className="flex items-center gap-1 hover:text-foreground"
+					>
+						<Home className="size-3" />
+						<span>Home Page</span>
+					</a>
+
+					<a
+						href="https://github.com/alibaba/page-agent/blob/main/packages/extension/PRIVACY.md"
+						target="_blank"
+						rel="noopener noreferrer"
+						className="flex items-center gap-1 hover:text-foreground"
+					>
+						<HatGlasses className="size-3" />
+						<span>Privacy Policy</span>
+					</a>
+				</div>
+
+				<div className="flex flex-col items-end">
+					<span>
+						Extension <span className="font-mono">v{__EXT_VERSION__}</span>
+					</span>
+					<span>
+						PageAgent <span className="font-mono">v{__CORE_VERSION__}</span>
+					</span>
+				</div>
+			</div>
+
+			{/* attribute */}
+			<div className="text-[10px] text-muted-foreground bg-background fixed bottom-0 w-full flex justify-around">
+				<span className="leading-loose">
+					Built with ♥️ by{' '}
+					<a
+						href="https://github.com/gaomeng1900"
+						target="_blank"
+						rel="noopener noreferrer"
+						className="underline hover:text-foreground"
+					>
+						@Simon
+					</a>
+				</span>
+			</div>
 		</div>
 	)
 }

packages/extension/src/entrypoints/sidepanel/components/cards.tsx

@@ -315,9 +315,7 @@ export function EventCard({ event }: { event: HistoricalEvent }) {
 				<ResultCard
 					success={input?.success ?? true}
 					text={input?.text || event.action.output || ''}
-				>
+				/>
-					<RawSection rawRequest={event.rawRequest} rawResponse={event.rawResponse} />
-				</ResultCard>
 			</>
 		)
 	}

packages/extension/src/entrypoints/sidepanel/main.tsx

@@ -6,6 +6,16 @@ import { ErrorBoundary } from './components/ErrorBoundary'
 
 import '@/assets/index.css'
 
+// Sync dark mode with system preference
+const syncDarkMode = () => {
+	document.documentElement.classList.toggle(
+		'dark',
+		matchMedia('(prefers-color-scheme: dark)').matches
+	)
+}
+syncDarkMode()
+matchMedia('(prefers-color-scheme: dark)').addEventListener('change', syncDarkMode)
+
 ReactDOM.createRoot(document.getElementById('root')!).render(
 	<React.StrictMode>
 		<ErrorBoundary>

packages/extension/src/types/globals.d.ts

@@ -0,0 +1,2 @@
+declare const __EXT_VERSION__: string
+declare const __CORE_VERSION__: string

packages/extension/wxt.config.js

@@ -1,10 +1,12 @@
 import tailwindcss from '@tailwindcss/vite'
-import { mkdirSync } from 'node:fs'
+import { mkdirSync, readFileSync } from 'node:fs'
 import { defineConfig } from 'wxt'
 
 const chromeProfile = '.wxt/chrome-data'
 mkdirSync(chromeProfile, { recursive: true })
 
+const pkg = JSON.parse(readFileSync('./package.json', 'utf-8'))
+
 // See https://wxt.dev/api/config.html
 export default defineConfig({
 	srcDir: 'src',
@@ -16,6 +18,10 @@ export default defineConfig({
 	},
 	vite: () => ({
 		plugins: [tailwindcss()],
+		define: {
+			__EXT_VERSION__: JSON.stringify(pkg.version),
+			__CORE_VERSION__: JSON.stringify(pkg.dependencies['@page-agent/core']),
+		},
 		optimizeDeps: {
 			force: true,
 		},

packages/llms/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@page-agent/llms",
-    "version": "1.1.0",
+    "version": "1.1.2",
     "type": "module",
     "main": "./dist/lib/page-agent-llms.js",
     "module": "./dist/lib/page-agent-llms.js",

packages/llms/src/utils.ts

@@ -2,7 +2,7 @@
  * Utility functions for LLM integration
  */
 import chalk from 'chalk'
-import { z } from 'zod'
+import * as z from 'zod'
 
 import type { Tool } from './types'
 
@@ -74,6 +74,10 @@ export function modelPatch(body: Record<string, any>) {
 		} else if (modelName.startsWith('gpt-51')) {
 			debug('Applying GPT-51 patch: disable reasoning')
 			body.reasoning_effort = 'none'
+		} else if (modelName.startsWith('gpt-5-mini')) {
+			debug('Applying GPT-5-mini patch: set reasoning effort to low, temperature to 1')
+			body.reasoning_effort = 'low'
+			body.temperature = 1
 		} else if (modelName.startsWith('gpt-5')) {
 			debug('Applying GPT-5 patch: set reasoning effort to low')
 			body.reasoning_effort = 'low'

packages/page-agent/package.json

@@ -1,7 +1,7 @@
 {
     "name": "page-agent",
     "private": false,
-    "version": "1.1.0",
+    "version": "1.1.2",
     "type": "module",
     "main": "./dist/esm/page-agent.js",
     "module": "./dist/esm/page-agent.js",
@@ -44,11 +44,11 @@
         "postpublish": "node -e \"['README.md','LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
     },
     "dependencies": {
+        "@page-agent/core": "1.1.2",
+        "@page-agent/llms": "1.1.2",
+        "@page-agent/page-controller": "1.1.2",
+        "@page-agent/ui": "1.1.2",
         "chalk": "^5.6.2",
-        "zod": "^4.3.5",
+        "zod": "^4.3.5"
-        "@page-agent/llms": "1.1.0",
-        "@page-agent/page-controller": "1.1.0",
-        "@page-agent/core": "1.1.0",
-        "@page-agent/ui": "1.1.0"
     }
 }

packages/page-agent/vite.iife.config.js

@@ -3,6 +3,7 @@ import { config as dotenvConfig } from 'dotenv'
 import { dirname, resolve } from 'path'
 import { fileURLToPath } from 'url'
 import { defineConfig } from 'vite'
+// import { analyzer } from 'vite-bundle-analyzer'
 import cssInjectedByJsPlugin from 'vite-plugin-css-injected-by-js'
 
 const __dirname = dirname(fileURLToPath(import.meta.url))
@@ -14,8 +15,11 @@ dotenvConfig({ path: resolve(__dirname, '../../.env') })
 // - alias all local packages so that they can be build in
 // - no external
 // - no d.ts. dts does not work with monorepo aliasing
-export default defineConfig(({ mode }) => ({
+export default defineConfig(() => ({
-	plugins: [cssInjectedByJsPlugin({ relativeCSSInjection: true })],
+	plugins: [
+		cssInjectedByJsPlugin({ relativeCSSInjection: true }),
+		// analyzer()
+	],
 	publicDir: false,
 	esbuild: {
 		keepNames: true,

packages/page-controller/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@page-agent/page-controller",
-    "version": "1.1.0",
+    "version": "1.1.2",
     "type": "module",
     "main": "./dist/lib/page-controller.js",
     "module": "./dist/lib/page-controller.js",

packages/ui/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@page-agent/ui",
-    "version": "1.1.0",
+    "version": "1.1.2",
     "type": "module",
     "main": "./dist/lib/page-agent-ui.js",
     "module": "./dist/lib/page-agent-ui.js",

packages/website/package.json

@@ -1,7 +1,7 @@
 {
     "name": "@page-agent/website",
     "private": true,
-    "version": "1.1.0",
+    "version": "1.1.2",
     "type": "module",
     "scripts": {
         "dev": "vite --host 0.0.0.0",
@@ -29,10 +29,10 @@
         "class-variance-authority": "^0.7.1",
         "clsx": "^2.1.1",
         "lucide-react": "^0.563.0",
-        "motion": "^12.29.2",
+        "motion": "^12.30.0",
         "next-themes": "^0.4.6",
         "rough-notation": "^0.5.1",
-        "simple-icons": "^16.6.0",
+        "simple-icons": "^16.7.0",
         "sonner": "^2.0.7",
         "tailwind-merge": "^3.4.0"
     }

packages/website/src/constants.ts

@@ -1,8 +1,8 @@
 // Demo build (auto-init with demo LLM, for quick testing)
 export const CDN_DEMO_URL =
-	'https://cdn.jsdelivr.net/npm/page-agent@1.1.0/dist/iife/page-agent.demo.js'
+	'https://cdn.jsdelivr.net/npm/page-agent@1.1.2/dist/iife/page-agent.demo.js'
 export const CDN_DEMO_CN_URL =
-	'https://registry.npmmirror.com/page-agent/1.1.0/files/dist/iife/page-agent.demo.js'
+	'https://registry.npmmirror.com/page-agent/1.1.2/files/dist/iife/page-agent.demo.js'
 
 // Demo LLM for website testing
 export const DEMO_MODEL = 'PAGE-AGENT-FREE-TESTING-RANDOM'

packages/website/src/pages/docs/Layout.tsx

@@ -30,6 +30,10 @@ export default function DocsLayout({ children }: DocsLayoutProps) {
 				{ title: isZh ? '概览' : 'Overview', path: '/introduction/overview' },
 				{ title: isZh ? '快速开始' : 'Quick Start', path: '/introduction/quick-start' },
 				{ title: isZh ? '使用限制' : 'Limitations', path: '/introduction/limitations' },
+				{
+					title: isZh ? '故障排查' : 'Troubleshooting',
+					path: '/introduction/troubleshooting',
+				},
 				{
 					title: '🚧 ' + (isZh ? '最佳实践' : 'Best Practices'),
 					path: '/integration/best-practices',

packages/website/src/pages/docs/features/chrome-extension/page.tsx

@@ -103,13 +103,13 @@ export default function ChromeExtension() {
 							isZh
 								? `// 1. 用户安装扩展并在扩展设置中配置 auth token
 // 2. 你的页面读取相同的 token 并存入 localStorage
-// 3. Token 匹配后，扩展会暴露 window.execute() 和 window.dispose()
+// 3. Token 匹配后，扩展会暴露 window.PAGE_AGENT_EXT 对象
 
 // ⚠️ 请在扩展弹窗中查看你的 auth token，然后填入下方
 localStorage.setItem('PageAgentExtUserAuthToken', '<从扩展中获取的-token>')`
 								: `// 1. User installs extension and sets an auth token in extension settings
 // 2. Your page reads the same token and stores it in localStorage
-// 3. After token match, extension exposes window.execute() and window.dispose()
+// 3. After token match, extension exposes window.PAGE_AGENT_EXT object
 
 // ⚠️ Check your extension popup for the auth token
 localStorage.setItem('PageAgentExtUserAuthToken', '<your-token-from-extension>')`
@@ -122,25 +122,54 @@ localStorage.setItem('PageAgentExtUserAuthToken', '<your-token-from-extension>')
 				<section>
 					<h2 className="text-2xl font-bold mb-4">{isZh ? 'API 参考' : 'API Reference'}</h2>
 
-					<h3 className="text-xl font-semibold mb-3">window.execute(task, llmConfig, hooks?)</h3>
+					{/* AI Assistant Instructions */}
+					<section className="p-4 bg-purple-50 dark:bg-purple-900/20 rounded-lg">
+						<h3 className="text-lg font-semibold text-purple-900 dark:text-purple-300 mb-2">
+							🤖 {isZh ? '给 AI 编程助手的文档' : 'Instructions for Your AI Assistant'}
+						</h3>
+						<p className="text-gray-600 dark:text-gray-300 mb-3 text-sm">
+							{isZh
+								? '如果你在使用 AI 编程助手（如 Cursor、GitHub Copilot），可以将以下文档链接提供给它，让它更好地理解和使用 Page Agent 扩展 API：'
+								: 'If you are using an AI coding assistant (like Cursor, GitHub Copilot), share these documentation links with it for better understanding of Page Agent Extension API:'}
+						</p>
+						<div className="space-y-2">
+							<a
+								href="https://github.com/alibaba/page-agent/blob/main/packages/extension/docs/extension_api.md"
+								target="_blank"
+								rel="noopener noreferrer"
+								className="block text-sm text-blue-600 hover:text-blue-700 dark:text-blue-400 dark:hover:text-blue-300 hover:underline"
+							>
+								📄 {isZh ? '英文版 API 文档' : 'API Documentation (English)'}
+							</a>
+							<a
+								href="https://github.com/alibaba/page-agent/blob/main/packages/extension/docs/extension_api_zh.md"
+								target="_blank"
+								rel="noopener noreferrer"
+								className="block text-sm text-blue-600 hover:text-blue-700 dark:text-blue-400 dark:hover:text-blue-300 hover:underline"
+							>
+								📄 {isZh ? '中文版 API 文档' : 'API Documentation (Chinese)'}
+							</a>
+						</div>
+					</section>
+
+					<h3 className="text-xl font-semibold my-3">PAGE_AGENT_EXT.execute(task, config)</h3>
 					<p className="text-gray-600 dark:text-gray-300 mb-4">
 						{isZh
-							? '使用 LLM 配置执行任务。返回一个 Promise，在任务完成时 resolve。可选的 hooks 参数用于监听任务执行过程中的事件。'
+							? '使用配置执行任务。返回一个 Promise，在任务完成时 resolve。config 参数包含 LLM 设置、选项和事件回调。'
-							: 'Execute a task with LLM configuration. Returns a Promise that resolves when the task completes. Optional hooks parameter for listening to events during task execution.'}
+							: 'Execute a task with configuration. Returns a Promise that resolves when the task completes. Config includes LLM settings, options, and event callbacks.'}
 					</p>
 
 					<CodeEditor
 						code={
 							isZh
-								? `// 使用 LLM 配置和 hooks 执行任务
+								? `// 使用配置执行任务
-const result = await window.execute(
+const result = await window.PAGE_AGENT_EXT.execute(
 	'在 GitHub 上搜索 "page-agent" 并打开第一个结果',
 	{
 		baseURL: 'https://api.openai.com/v1',
 		apiKey: 'your-api-key',
-		model: 'gpt-5-2'
+		model: 'gpt-5-2',
-	},
+		// includeInitialTab: false, // 设为 false 排除初始标签页
-	{
 		onStatusChange: status => console.log('状态变化:', status),
 		onActivity: activity => console.log('活动:', activity),
 		onHistoryUpdate: history => console.log('历史更新:', history),
@@ -149,15 +178,14 @@ const result = await window.execute(
 )
 
 console.log(result) // 任务执行结果`
-								: `// Execute a task with LLM configuration and hooks
+								: `// Execute a task with configuration
-const result = await window.execute(
+const result = await window.PAGE_AGENT_EXT.execute(
 	'Search for "page-agent" on GitHub and open the first result',
 	{
 		baseURL: 'https://api.openai.com/v1',
 		apiKey: 'your-api-key',
-		model: 'gpt-5-2'
+		model: 'gpt-5-2',
-	},
+		// includeInitialTab: false, // Set to false to exclude initial tab
-	{
 		onStatusChange: status => console.log('Status change:', status),
 		onActivity: activity => console.log('Activity:', activity),
 		onHistoryUpdate: history => console.log('History update:', history),
@@ -170,7 +198,7 @@ console.log(result) // Task execution result`
 						language="javascript"
 					/>
 
-					<h3 className="text-xl font-semibold mt-6 mb-3">window.dispose()</h3>
+					<h3 className="text-xl font-semibold mt-6 mb-3">PAGE_AGENT_EXT.dispose()</h3>
 					<p className="text-gray-600 dark:text-gray-300 mb-4">
 						{isZh
 							? '停止当前正在运行的任务。停止后 Agent 可以重新使用。'
@@ -181,49 +209,34 @@ console.log(result) // Task execution result`
 						code={
 							isZh
 								? `// 停止当前任务
-window.dispose()`
+window.PAGE_AGENT_EXT.dispose()`
 								: `// Stop current task execution
-window.dispose()`
+window.PAGE_AGENT_EXT.dispose()`
 						}
 						language="javascript"
 					/>
 				</section>
 
-				{/* LLM Config */}
+				{/* ExecuteConfig */}
 				<section>
-					<h2 className="text-2xl font-bold mb-4">{isZh ? 'LLM 配置' : 'LLM Configuration'}</h2>
+					<h2 className="text-2xl font-bold mb-4">{isZh ? '执行配置' : 'Execute Configuration'}</h2>
-
-					<CodeEditor
-						code={
-							isZh
-								? `interface LLMConfig {
-	baseURL: string   // LLM API 端点
-	apiKey: string    // API 密钥
-	model: string     // 模型名称
-}`
-								: `interface LLMConfig {
-	baseURL: string   // LLM API endpoint
-	apiKey: string    // API key
-	model: string     // Model name
-}`
-						}
-						language="typescript"
-					/>
-				</section>
-
-				{/* Execute Hooks */}
-				<section>
-					<h2 className="text-2xl font-bold mb-4">{isZh ? 'Execute Hooks' : 'Execute Hooks'}</h2>
 					<p className="text-gray-600 dark:text-gray-300 mb-4">
 						{isZh
-							? '通过 hooks 参数，你可以监听任务执行过程中的各种事件，实现实时更新 UI、日志记录等功能。'
+							? 'config 参数包含 LLM 设置、选项和事件回调，用于控制任务执行行为。'
-							: 'With hooks parameter, you can listen to various events during task execution for real-time UI updates, logging, and more.'}
+							: 'The config parameter includes LLM settings, options, and event callbacks to control task execution behavior.'}
 					</p>
 
 					<CodeEditor
 						code={
 							isZh
-								? `interface ExecuteHooks {
+								? `interface ExecuteConfig {
+	baseURL: string   // LLM API 端点
+	apiKey: string    // API 密钥
+	model: string     // 模型名称
+
+	// 是否将初始标签页包含在任务中，默认 true
+	includeInitialTab?: boolean
+
 	// Agent 状态变化时调用（idle, running, error, completed 等）
 	onStatusChange?: (status: AgentStatus) => void
 
@@ -236,7 +249,14 @@ window.dispose()`
 	// Agent 被停止时调用
 	onDispose?: () => void
 }`
-								: `interface ExecuteHooks {
+								: `interface ExecuteConfig {
+	baseURL: string   // LLM API endpoint
+	apiKey: string    // API key
+	model: string     // Model name
+
+	// Whether to include the initial tab in the task, default true
+	includeInitialTab?: boolean
+
 	// Called when agent status changes (idle, running, error, completed, etc.)
 	onStatusChange?: (status: AgentStatus) => void
 

packages/website/src/pages/docs/features/custom-tools/page.tsx

@@ -25,7 +25,7 @@ export default function CustomTools() {
 					</p>
 
 					<CodeEditor
-						code={`import zod from 'zod'
+						code={`import * as zod from 'zod'
 import { PageAgent, tool } from 'page-agent'
 
 // override internal tool

packages/website/src/pages/docs/features/models/page.tsx

@@ -1,34 +1,49 @@
+import { Fragment } from 'react'
+
 import CodeEditor from '@/components/CodeEditor'
 import { useLanguage } from '@/i18n/context'
 
-// Recommended models: lightweight with excellent tool call capabilities
+const BASELINE = new Set([
-const MODELS = {
+	'gpt-5.1',
-	recommended: [
+	'claude-haiku-4.5',
-		'gpt-4.1-mini',
+	'gemini-3-flash',
-		'claude-haiku-4.5',
+	'deepseek-3.2',
-		'gemini-3-flash',
+	'qwen3-coder-next',
-		'deepseek-3.2',
+])
-		'gpt-5.2',
+
-		'qwen-3-max',
+// Models grouped by brand, newest first
-	],
+const MODEL_GROUPS: Record<string, string[]> = {
-	verified: [
+	OpenAI: ['gpt-5.2', 'gpt-5.1', 'gpt-5', 'gpt-5-mini', 'gpt-4.1', 'gpt-4.1-mini'],
-		'qwen-3-plus',
+	Google: ['gemini-3-pro', 'gemini-3-flash', 'gemini-2.5'],
-		'gpt-4.1',
+	Qwen: ['qwen3-coder-next', 'qwen-3-max', 'qwen-3-plus', 'qwen3:14b (ollama)'],
-		'gpt-5',
+	DeepSeek: ['deepseek-3.2'],
-		'gpt-5-mini',
+	Anthropic: [
-		'grok-4',
+		'claude-opus-4.6',
-		'grok-code-fast',
-		'claude-sonnet-3.5',
-		'claude-sonnet-4.5',
 		'claude-opus-4.5',
-		'gemini-2.5',
+		'claude-sonnet-4.5',
-		'gemini-3-pro',
+		'claude-haiku-4.5',
+		'claude-sonnet-3.5',
 	],
+	xAI: ['grok-4.1-fast', 'grok-4', 'grok-code-fast'],
+	MoonshotAI: ['kimi-k2.5'],
+	'Z.AI': ['glm-4.7'],
 }
 
+const ModelBadge = ({ model, baseline }: { model: string; baseline?: boolean }) => (
+	<div
+		className={`px-3 py-1.5 rounded-md text-xs font-medium font-mono transition-colors ${
+			baseline
+				? 'bg-emerald-500 text-white shadow-sm'
+				: 'bg-white/80 dark:bg-gray-800/80 text-gray-800 dark:text-gray-200 border border-gray-300 dark:border-gray-600'
+		}`}
+	>
+		{model}
+		{baseline && <span className="ml-1">⭐</span>}
+	</div>
+)
+
 export default function Models() {
 	const { isZh } = useLanguage()
-	const allModels = [...MODELS.recommended, ...MODELS.verified]
 
 	return (
 		<div className="max-w-4xl">
@@ -45,28 +60,23 @@ export default function Models() {
 				<p className="text-sm text-gray-600 dark:text-gray-400 mb-4">
 					{isZh
 						? '推荐使用 ToolCall 能力强的轻量级模型。'
-						: 'Recommended: Lightweight models with strong ToolCall capabilities.'}
+						: 'Recommended: Fast, lightweight models with strong ToolCall capabilities.'}
 				</p>
 				<div className="bg-linear-to-br from-emerald-50 to-cyan-50 dark:from-emerald-950/30 dark:to-cyan-950/30 rounded-xl p-6 border border-emerald-200/50 dark:border-emerald-800/50">
-					<div className="flex flex-wrap gap-2">
+					<div className="grid grid-cols-[5rem_1fr] gap-x-3 gap-y-3 items-start">
-						{allModels.map((model) => {
+						{Object.entries(MODEL_GROUPS).map(([brand, models]) => (
-							const isRecommended = MODELS.recommended.includes(model)
+							<Fragment key={brand}>
-							return (
+								<span className="text-xs font-semibold text-gray-500 dark:text-gray-400 pt-2">
-								<div
+									{brand}
-									key={model}
+								</span>
-									className={`px-3 py-1.5 rounded-md text-sm font-medium font-mono transition-colors ${
+								<div className="flex flex-wrap gap-2">
-										isRecommended
+									{models.map((model) => (
-											? 'bg-emerald-500 text-white shadow-sm'
+										<ModelBadge key={model} model={model} baseline={BASELINE.has(model)} />
-											: 'bg-white/80 dark:bg-gray-800/80 text-gray-800 dark:text-gray-200 border border-gray-300 dark:border-gray-600'
+									))}
-									}`}
-								>
-									{model}
-									{isRecommended && <span className="ml-1">⭐</span>}
 								</div>
-							)
+							</Fragment>
-						})}
+						))}
 					</div>
-					<p className="text-xs text-gray-600 dark:text-gray-400 mt-5">⭐ baseline models</p>
 				</div>
 			</section>
 

packages/website/src/pages/docs/index.tsx

@@ -20,6 +20,7 @@ import Limitations from './introduction/limitations/page'
 // Introduction
 import Overview from './introduction/overview/page'
 import QuickStart from './introduction/quick-start/page'
+import Troubleshooting from './introduction/troubleshooting/page'
 
 function DocsPage({ children }: { children: React.ReactNode }) {
 	return (
@@ -51,6 +52,11 @@ export default function DocsRouter() {
 					<Limitations />
 				</DocsPage>
 			</Route>
+			<Route path="/introduction/troubleshooting">
+				<DocsPage>
+					<Troubleshooting />
+				</DocsPage>
+			</Route>
 
 			{/* Features */}
 			<Route path="/features/custom-tools">

packages/website/src/pages/docs/introduction/troubleshooting/page.tsx

@@ -0,0 +1,424 @@
+import { useEffect, useRef, useState } from 'react'
+import { Link } from 'wouter'
+
+import CodeEditor from '@/components/CodeEditor'
+import { useLanguage } from '@/i18n/context'
+
+// ---------------------------------------------------------------------------
+// Data: each section is a typed object for easy extension
+// ---------------------------------------------------------------------------
+
+interface TroubleshootingSection {
+	id: string
+	title: { en: string; zh: string }
+	symptom: { en: string; zh: string }
+	color: 'red' | 'amber' | 'orange' | 'violet'
+	content: (isZh: boolean) => React.ReactNode
+}
+
+const SECTIONS: TroubleshootingSection[] = [
+	{
+		id: 'format-errors',
+		title: { en: 'Model Response Format Errors', zh: '模型返回格式错误' },
+		symptom: {
+			en: 'The model returns malformed tool calls, plain text, or unexpected JSON instead of structured actions.',
+			zh: '模型返回了格式错误的 tool call、纯文本或非预期的 JSON，而非结构化的操作指令。',
+		},
+		color: 'amber',
+		content: FormatErrorsContent,
+	},
+	{
+		id: 'low-success-rate',
+		title: { en: 'Low Task Success Rate', zh: '任务成功率低' },
+		symptom: {
+			en: 'The agent appears to understand the task but frequently fails to complete it, or produces incorrect results.',
+			zh: 'Agent 似乎理解了任务，但频繁执行失败或产生不正确的结果。',
+		},
+		color: 'amber',
+		content: LowSuccessRateContent,
+	},
+	{
+		id: 'wrong-element',
+		title: { en: "Can't Hit Target Elements", zh: '无法点击目标元素' },
+		symptom: {
+			en: 'The agent repeatedly retries but keeps interacting with the wrong element, or fails to locate the correct one.',
+			zh: 'Agent 反复重试，但始终点击在错误的元素上，或无法定位到正确的目标元素。',
+		},
+		color: 'amber',
+		content: WrongElementContent,
+	},
+	{
+		id: 'api-errors',
+		title: { en: 'API Request Errors', zh: 'API 请求错误' },
+		symptom: {
+			en: 'HTTP 400 Bad Request or similar errors when calling the LLM API.',
+			zh: '调用 LLM API 时出现 HTTP 400 Bad Request 或类似的参数错误。',
+		},
+		color: 'amber',
+		content: ApiErrorsContent,
+	},
+]
+
+// ---------------------------------------------------------------------------
+// Section content components
+// ---------------------------------------------------------------------------
+
+function FormatErrorsContent(isZh: boolean) {
+	return (
+		<ol className="list-decimal pl-5 space-y-4 text-gray-700 dark:text-gray-300">
+			<li>
+				<strong>{isZh ? '确认模型是否支持' : 'Verify model compatibility'}</strong>
+				<p className="mt-1">
+					{isZh
+						? '并非所有模型都能正确处理 page-agent 的 tool 定义。请查看'
+						: 'Not all models can handle page-agent tool definitions correctly. Check the '}
+					<Link
+						href="/features/models"
+						className="text-blue-600 dark:text-blue-400 underline underline-offset-2"
+					>
+						{isZh ? '已测试模型列表' : 'tested models list'}
+					</Link>
+					{isZh ? '。' : '.'}
+				</p>
+			</li>
+			<li>
+				<strong>
+					{isZh ? '检查代理/网关的参数转发' : 'Check proxy/gateway parameter forwarding'}
+				</strong>
+				<p className="mt-1">
+					{isZh
+						? '如果使用了 API 代理或网关，请确保请求中的 '
+						: 'If using an API proxy or gateway, make sure the '}
+					<code>tools</code>
+					{isZh
+						? ' 字段被完整、无修改地转发给模型供应商。部分代理可能会剥离或修改此字段。'
+						: ' parameter is forwarded to the model provider intact. Some proxies may strip or alter this field.'}
+				</p>
+			</li>
+			<li>
+				<strong>{isZh ? '寻求社区帮助' : 'Get community help'}</strong>
+				<p className="mt-1">
+					{isZh ? (
+						<>
+							如果以上步骤无法解决问题，欢迎在{' '}
+							<a
+								href="https://github.com/alibaba/page-agent/discussions"
+								target="_blank"
+								rel="noopener noreferrer"
+								className="text-blue-600 dark:text-blue-400 underline underline-offset-2"
+							>
+								GitHub Discussions
+							</a>{' '}
+							中反馈，附上模型名称和错误信息。
+						</>
+					) : (
+						<>
+							If the above steps don't help, join the{' '}
+							<a
+								href="https://github.com/alibaba/page-agent/discussions"
+								target="_blank"
+								rel="noopener noreferrer"
+								className="text-blue-600 dark:text-blue-400 underline underline-offset-2"
+							>
+								GitHub Discussions
+							</a>{' '}
+							with your model name and error details.
+						</>
+					)}
+				</p>
+			</li>
+		</ol>
+	)
+}
+
+function LowSuccessRateContent(isZh: boolean) {
+	return (
+		<>
+			<p className="text-sm text-gray-500 dark:text-gray-400 mb-4 italic">
+				{isZh
+					? '按以下顺序逐步排查，从最简单的情况开始：'
+					: 'Follow this diagnostic funnel from simplest to most advanced:'}
+			</p>
+			<ol className="list-decimal pl-5 space-y-4 text-gray-700 dark:text-gray-300">
+				<li>
+					<strong>{isZh ? '先从简单指令开始' : 'Start with a simple instruction'}</strong>
+					<p className="mt-1">
+						{isZh
+							? '给一个具体的、单步的简单指令（如"点击登录按钮"），看 Agent 能否完成。如果连简单操作都失败了，问题可能不在模型能力上。'
+							: 'Give a concrete, single-step instruction (e.g. "click the login button"). If even simple actions fail, the issue is likely not model capability.'}
+					</p>
+				</li>
+				<li>
+					<strong>{isZh ? '尝试最强模型' : 'Try the strongest model available'}</strong>
+					<p className="mt-1">
+						{isZh
+							? '切换到你能获取到的最先进、最大的模型，以排除是否是模型智能水平不足导致的问题。'
+							: "Switch to the most capable model you have access to, to isolate whether it's a model intelligence issue."}
+					</p>
+				</li>
+				<li>
+					<strong>{isZh ? '优化指令质量' : 'Improve instruction quality'}</strong>
+					<p className="mt-1">
+						{isZh
+							? '给出尽可能具体的指令。对于复杂任务，建议使用另一个 LLM 来预先拆分和细化用户的需求，然后逐步执行。'
+							: "Be as specific as possible. For complex tasks, consider using another LLM to decompose and refine the user's request before execution."}
+					</p>
+				</li>
+				<li>
+					<strong>{isZh ? '提供充足的上下文' : 'Provide sufficient context'}</strong>
+					<p className="mt-1">
+						{isZh
+							? '通过 instructions 配置注入网站背景描述、关键术语解释等上下文信息，帮助 Agent 更好地理解页面。'
+							: 'Use the instructions config to inject website descriptions, key terminology, and background context to help the agent understand the page.'}
+					</p>
+				</li>
+				<li>
+					<strong>{isZh ? '检查 HTML 清洗结果' : 'Check HTML sanitization output'}</strong>
+					<p className="mt-1">
+						{isZh
+							? '使用开发者工具检查清洗后的 HTML，确认关键信息、文本和可操作元素是否被正确保留。'
+							: 'Inspect the sanitized HTML in dev tools to confirm that key information, text, and interactive elements are preserved correctly.'}
+					</p>
+				</li>
+			</ol>
+		</>
+	)
+}
+
+function WrongElementContent(isZh: boolean) {
+	return (
+		<ol className="list-decimal pl-5 space-y-4 text-gray-700 dark:text-gray-300">
+			<li>
+				<strong>{isZh ? '了解现实局限' : 'Understand the reality'}</strong>
+				<p className="mt-1">
+					{isZh
+						? '并非所有网站都提供了完善的语义化 HTML 和 accessibility 标签。对于此类网站，DOM 清洗可能无法产出足够好的结果。'
+						: 'Not all websites provide proper semantic HTML and accessibility labels. For such sites, DOM sanitization may not produce good enough results.'}
+				</p>
+			</li>
+			<li>
+				<strong>{isZh ? '检查目标元素类型' : 'Check target element type'}</strong>
+				<p className="mt-1">
+					{isZh
+						? '确认目标元素是否为图片、Canvas、或需要复杂交互（如拖拽、基于坐标的点击）的元素。这些本身就超出了当前的能力范围。'
+						: 'Verify if the target is an image, Canvas, or requires complex interactions (drag-and-drop, coordinate-based clicking). These are beyond current capabilities.'}
+				</p>
+			</li>
+			<li>
+				<strong>{isZh ? '检查清洗后的 HTML' : 'Inspect sanitized HTML'}</strong>
+				<p className="mt-1">
+					{isZh
+						? '检查清洗结果中是否存在关键信息丢失、可操作元素未被编号等问题。'
+						: 'Look for missing key information or unnumbered interactive elements in the sanitized output.'}
+				</p>
+			</li>
+			<li>
+				<strong>{isZh ? '注入 accessibility 增强' : 'Inject accessibility improvements'}</strong>
+				<p className="mt-1">
+					{isZh
+						? '通过注入脚本为网站添加 aria-label、语义化标签等 accessibility 属性，改善 DOM 清洗质量。'
+						: 'Inject scripts to add aria-labels, semantic attributes, and other a11y improvements to enhance DOM sanitization quality.'}
+				</p>
+			</li>
+			<li>
+				<strong>{isZh ? '开发专用 Tool' : 'Build a custom Tool'}</strong>
+				<p className="mt-1">
+					{isZh ? (
+						<>
+							对于特定的、持续难以操作的元素，考虑开发{' '}
+							<Link
+								href="/features/custom-tools"
+								className="text-blue-600 dark:text-blue-400 underline underline-offset-2"
+							>
+								自定义 Tool
+							</Link>{' '}
+							来直接操作这些元素。
+						</>
+					) : (
+						<>
+							For consistently difficult elements, consider building a{' '}
+							<Link
+								href="/features/custom-tools"
+								className="text-blue-600 dark:text-blue-400 underline underline-offset-2"
+							>
+								custom Tool
+							</Link>{' '}
+							to interact with them directly.
+						</>
+					)}
+				</p>
+			</li>
+		</ol>
+	)
+}
+
+function ApiErrorsContent(isZh: boolean) {
+	return (
+		<div className="space-y-4 text-gray-700 dark:text-gray-300">
+			<p>
+				{isZh
+					? '一些 LLM 供应商使用了与 OpenAI 不完全兼容的参数格式，导致请求参数校验失败。'
+					: 'Some LLM providers use parameter formats that are not fully compatible with the OpenAI spec, causing request validation failures.'}
+			</p>
+			<div className="bg-gray-50 dark:bg-gray-800/50 rounded-lg p-4">
+				<p className="font-medium mb-2">
+					{isZh ? '解决方案：使用 customFetch' : 'Solution: use customFetch'}
+				</p>
+				<p className="text-sm mb-3">
+					{isZh
+						? '通过 customFetch 配置拦截请求，在发送前调整参数格式以适配目标供应商的要求。'
+						: 'Use the customFetch config to intercept requests and adapt parameters before sending them to the target provider.'}
+				</p>
+				<CodeEditor
+					code={`const agent = new PageAgent({
+  // ...
+  customFetch: async (url, init) => {
+    const body = JSON.parse(init.body)
+    // Adapt parameters for your provider
+    delete body.stream_options
+    return fetch(url, { ...init, body: JSON.stringify(body) })
+  },
+})`}
+				/>
+			</div>
+			<p className="text-sm">
+				{isZh ? '参见 ' : 'See '}
+				<Link
+					href="/advanced/page-agent-core"
+					className="text-blue-600 dark:text-blue-400 underline underline-offset-2"
+				>
+					PageAgentCore API
+				</Link>
+				{isZh ? ' 了解 customFetch 的完整用法。' : ' for full customFetch documentation.'}
+			</p>
+		</div>
+	)
+}
+
+// ---------------------------------------------------------------------------
+// Color mapping for symptom callouts
+// ---------------------------------------------------------------------------
+
+const SYMPTOM_COLORS = {
+	red: 'border-red-400 bg-red-50 dark:bg-red-900/15 text-red-800 dark:text-red-200',
+	amber: 'border-amber-400 bg-amber-50 dark:bg-amber-900/15 text-amber-800 dark:text-amber-200',
+	orange:
+		'border-orange-400 bg-orange-50 dark:bg-orange-900/15 text-orange-800 dark:text-orange-200',
+	violet:
+		'border-violet-400 bg-violet-50 dark:bg-violet-900/15 text-violet-800 dark:text-violet-200',
+} as const
+
+// ---------------------------------------------------------------------------
+// Right-side TOC with IntersectionObserver
+// ---------------------------------------------------------------------------
+
+function useActiveSection(ids: string[]) {
+	const [activeId, setActiveId] = useState(ids[0])
+	const observerRef = useRef<IntersectionObserver | null>(null)
+
+	useEffect(() => {
+		observerRef.current?.disconnect()
+
+		const visibleEntries = new Map<string, number>()
+
+		observerRef.current = new IntersectionObserver(
+			(entries) => {
+				for (const entry of entries) {
+					if (entry.isIntersecting) {
+						visibleEntries.set(entry.target.id, entry.intersectionRatio)
+					} else {
+						visibleEntries.delete(entry.target.id)
+					}
+				}
+				// Pick the first visible section in document order
+				const firstVisible = ids.find((id) => visibleEntries.has(id))
+				if (firstVisible) setActiveId(firstVisible)
+			},
+			{ rootMargin: '-80px 0px -60% 0px', threshold: [0, 0.25] }
+		)
+
+		for (const id of ids) {
+			const el = document.getElementById(id)
+			if (el) observerRef.current.observe(el)
+		}
+
+		return () => observerRef.current?.disconnect()
+	}, [ids])
+
+	return activeId
+}
+
+// ---------------------------------------------------------------------------
+// Page component
+// ---------------------------------------------------------------------------
+
+export default function TroubleshootingPage() {
+	const { isZh } = useLanguage()
+	const sectionIds = SECTIONS.map((s) => s.id)
+	const activeId = useActiveSection(sectionIds)
+
+	return (
+		<div className="max-w-5xl mx-auto">
+			{/* Header */}
+			<div className="mb-10">
+				<h1 className="text-4xl font-bold mb-4 text-gray-900 dark:text-white">Troubleshooting</h1>
+			</div>
+
+			{/* Two-column: content + TOC */}
+			<div className="flex gap-8">
+				{/* Main content */}
+				<div className="flex-1 min-w-0 space-y-12">
+					{SECTIONS.map((section) => (
+						<section key={section.id} id={section.id} className="scroll-mt-24">
+							<h2 className="text-2xl font-bold mb-4 text-gray-900 dark:text-white">
+								{isZh ? section.title.zh : section.title.en}
+							</h2>
+
+							{/* Symptom callout */}
+							<div
+								className={`border-l-4 px-4 py-3 rounded-r-lg mb-6 ${SYMPTOM_COLORS[section.color]}`}
+							>
+								<span className="text-xs font-semibold uppercase tracking-wider opacity-70">
+									{isZh ? '症状' : 'Symptom'}
+								</span>
+								<p className="mt-1 text-sm">{isZh ? section.symptom.zh : section.symptom.en}</p>
+							</div>
+
+							{/* Diagnostic steps */}
+							<div className="prose-sm">{section.content(isZh)}</div>
+						</section>
+					))}
+				</div>
+
+				{/* Right TOC */}
+				<aside className="hidden lg:block w-48 shrink-0">
+					<div className="sticky top-24">
+						<h4 className="text-xs font-semibold text-gray-400 dark:text-gray-500 uppercase tracking-wider mb-3">
+							{isZh ? '目录' : 'On this page'}
+						</h4>
+						<nav className="space-y-1">
+							{SECTIONS.map((section) => (
+								<button
+									key={section.id}
+									type="button"
+									onClick={() =>
+										document
+											.getElementById(section.id)
+											?.scrollIntoView({ behavior: 'smooth', block: 'start' })
+									}
+									className={`block text-sm py-1 text-left transition-colors ${
+										activeId === section.id
+											? 'text-blue-600 dark:text-blue-400 font-medium'
+											: 'text-gray-500 dark:text-gray-400 hover:text-gray-900 dark:hover:text-gray-200'
+									}`}
+								>
+									{isZh ? section.title.zh : section.title.en}
+								</button>
+							))}
+						</nav>
+					</div>
+				</aside>
+			</div>
+		</div>
+	)
+}

tsconfig.base.json

@@ -8,7 +8,7 @@
         "skipLibCheck": true,
         "allowJs": true,
 
-        // "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo",
+        "tsBuildInfoFile": "./node_modules/.tmp/tsconfig.tsbuildinfo",
         // "baseUrl": "src",
         "baseUrl": ".",
         "outDir": "dist",