chore(version): bump version to 1.6.1

chore(page-controller): export actions as internal methods

README.md

@@ -25,8 +25,8 @@ The GUI Agent Living in Your Webpage. Control web interfaces with natural langua
 - **📖 Text-based DOM manipulation**
     - No screenshots. No multi-modal LLMs or special permissions needed.
 - **🧠 Bring your own LLMs**
-- **🎨 Pretty UI with human-in-the-loop**
 - **🐙 Optional [chrome extension](https://alibaba.github.io/page-agent/docs/features/chrome-extension) for multi-page tasks.**
+    - [MCP Server (Beta)](https://alibaba.github.io/page-agent/docs/features/mcp-server)
 
 ## 💡 Use Cases
 
@@ -49,8 +49,8 @@ Fastest way to try PageAgent with our free Demo LLM:
 
 | Mirrors | URL                                                                                |
 | ------- | ---------------------------------------------------------------------------------- |
-| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.5.9/dist/iife/page-agent.demo.js         |
+| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.6.1/dist/iife/page-agent.demo.js         |
-| China   | https://registry.npmmirror.com/page-agent/1.5.9/files/dist/iife/page-agent.demo.js |
+| China   | https://registry.npmmirror.com/page-agent/1.6.1/files/dist/iife/page-agent.demo.js |
 
 ### NPM Installation
 

docs/CHANGELOG.md

@@ -5,6 +5,31 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.6.0] - 2026-03-21
+
+### Features
+
+- **Beta MCP support** - New `@page-agent/mcp` package lets MCP clients such as Claude Desktop and Copilot control the browser through the Page Agent extension
+- **Better iframe handling** - Same-origin iframe elements are handled more reliably during DOM extraction and actions
+- **Extension history workflows** - Users can rerun past tasks, export history sessions as JSON, and approve MCP-triggered tasks before execution
+
+### Improvements
+
+- **Unified versioning across packages** - The extension now follows the root workspace version. Changelog entries are no longer split into a separate extension version section
+- **Configurable `stepDelay`** - Agent pacing between steps is now configurable via `stepDelay`
+- **Optional API key** - `apiKey` can now be omitted for compatible deployments that do not require one
+- **Optional named tool choice** - Tool invocation can disable named tool choice for providers that behave better without it
+- **Better rich-text input support** - Improved `contenteditable` handling with better event dispatching and `execCommand` fallback for more editors
+- **More flexible DOM extraction** - `includeAttributes` now supports wildcards, `contenteditable` is included by default, and heuristically interactive elements expose more useful attributes
+- **MiniMax model support** - Added MiniMax compatibility, with the default recommendation updated to `MiniMax-M2.7`
+
+### Bug Fixes
+
+- Fixed Safari issues when `requestIdleCallback` is unavailable
+- Avoid throwing when `webgl2` initialization fails
+- Improved OpenAI-compatible request patches for GPT-5.4 chat tools and MiniMax temperature/tool-call compatibility
+- Fixed several UI polish issues in the extension and website, including cursor and layout regressions
+
 ## [1.5.1] - 2026-03-05
 
 ### Breaking Changes
@@ -153,42 +178,6 @@ PageAgent is now ready for production use. The API is stable and breaking change
 - **Ask User Tool** - Agent can ask users for clarification
 - **i18n Support** - English and Chinese localization
 
-### Configuration 
-
-```typescript
-// Version 1.0.0
-interface PageAgentConfig {
-    // LLM Configuration (required)
-    baseURL: string
-    apiKey: string
-    model: string
-    temperature?: number
-    maxRetries?: number
-    customFetch?: typeof fetch
-
-    // Agent Configuration
-    language?: 'en-US' | 'zh-CN'
-    maxSteps?: number // default: 20
-    customTools?: Record<string, PageAgentTool> // experimental
-    instructions?: InstructionsConfig
-    transformPageContent?: (content: string) => string | Promise<string>
-    experimentalScriptExecutionTool?: boolean // default: false
-
-    // Lifecycle Hooks (experimental)
-    onBeforeTask?: (agent, result) => void
-    onAfterTask?: (agent, result) => void
-    onBeforeStep?: (agent, stepCount) => void
-    onAfterStep?: (agent, history) => void
-    onDispose?: (agent, reason?) => void
-
-    // Page Controller Configuration
-    enableMask?: boolean // default: true
-    viewportExpansion?: number
-    interactiveBlacklist?: Element[]
-    interactiveWhitelist?: Element[]
-}
-```
-
 ### Packages
 
 | Package                       | Description                        |

docs/README-zh.md

@@ -20,17 +20,16 @@
 ## ✨ Features
 
 - **🎯 轻松集成**
-    - 无需 `浏览器插件` / `Python` / `无头浏览器`。
+    - 无需 `浏览器插件` / `Python` / `无头浏览器`，纯页面内 JavaScript
-    - 纯页面内 JavaScript，一切都在你的网页中完成。
 - **📖 基于文本的 DOM 操作**
-    - 无需截图，无需多模态模型或特殊权限。
+    - 无需截图，无需多模态模型或特殊权限
-- **🧠 用你自己的 LLM**
+- **🧠 自备 LLM**
-- **🎨 精美 UI，支持人机协同**
+- 🐙 可选的 [Chrome 扩展](https://alibaba.github.io/page-agent/docs/features/chrome-extension)，支持跨页面任务
-- **🐙 可选的 [Chrome 扩展](https://alibaba.github.io/page-agent/docs/features/chrome-extension)，支持跨页面任务。**
+    - [MCP Server (Beta)](https://alibaba.github.io/page-agent/docs/features/mcp-server)
 
 ## 💡 应用场景
 
-- **SaaS AI 副驾驶** — 几行代码为你的产品加上 AI 副驾驶，无需重写后端。
+- **SaaS AI Copilot** — 几行代码为你的产品加上 AI 副驾驶，无需重写后端。
 - **智能表单填写** — 把 20 次点击变成一句话。ERP、CRM、管理后台的最佳拍档。
 - **无障碍增强** — 用自然语言让任何网页无障碍。语音指令、屏幕阅读器，零门槛。
 - **跨页面 Agent** — 通过可选的 [Chrome 扩展](https://alibaba.github.io/page-agent/docs/features/chrome-extension)，让你自己的 Agent 跨标签页工作。
@@ -49,8 +48,8 @@
 
 | Mirrors | URL                                                                                |
 | ------- | ---------------------------------------------------------------------------------- |
-| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.5.9/dist/iife/page-agent.demo.js         |
+| Global  | https://cdn.jsdelivr.net/npm/page-agent@1.6.1/dist/iife/page-agent.demo.js         |
-| China   | https://registry.npmmirror.com/page-agent/1.5.9/files/dist/iife/page-agent.demo.js |
+| China   | https://registry.npmmirror.com/page-agent/1.6.1/files/dist/iife/page-agent.demo.js |
 
 ### NPM 安装
 

package-lock.json

@@ -1,12 +1,12 @@
 {
     "name": "root",
-    "version": "1.5.9",
+    "version": "1.6.1",
     "lockfileVersion": 3,
     "requires": true,
     "packages": {
         "": {
             "name": "root",
-            "version": "1.5.9",
+            "version": "1.6.1",
             "license": "MIT",
             "workspaces": [
                 "packages/page-controller",
@@ -11799,11 +11799,11 @@
         },
         "packages/core": {
             "name": "@page-agent/core",
-            "version": "1.5.9",
+            "version": "1.6.1",
             "license": "MIT",
             "dependencies": {
-                "@page-agent/llms": "1.5.9",
+                "@page-agent/llms": "1.6.1",
-                "@page-agent/page-controller": "1.5.9",
+                "@page-agent/page-controller": "1.6.1",
                 "chalk": "^5.6.2"
             },
             "devDependencies": {
@@ -11815,13 +11815,13 @@
         },
         "packages/extension": {
             "name": "@page-agent/ext",
-            "version": "1.5.9",
+            "version": "1.6.1",
             "hasInstallScript": true,
             "dependencies": {
-                "@page-agent/core": "1.5.9",
+                "@page-agent/core": "1.6.1",
-                "@page-agent/llms": "1.5.9",
+                "@page-agent/llms": "1.6.1",
-                "@page-agent/page-controller": "1.5.9",
+                "@page-agent/page-controller": "1.6.1",
-                "@page-agent/ui": "1.5.9",
+                "@page-agent/ui": "1.6.1",
                 "ai-motion": "^0.4.8",
                 "chalk": "^5.6.2"
             },
@@ -11832,7 +11832,6 @@
                 "@radix-ui/react-separator": "^1.1.8",
                 "@radix-ui/react-slot": "^1.2.4",
                 "@radix-ui/react-switch": "^1.2.6",
-                "@radix-ui/react-tooltip": "^1.2.8",
                 "@types/chrome": "^0.1.37",
                 "@types/react": "^19.2.14",
                 "@types/react-dom": "^19.2.1",
@@ -11859,7 +11858,7 @@
         },
         "packages/llms": {
             "name": "@page-agent/llms",
-            "version": "1.5.9",
+            "version": "1.6.1",
             "license": "MIT",
             "dependencies": {
                 "chalk": "^5.6.2"
@@ -11873,7 +11872,7 @@
         },
         "packages/mcp": {
             "name": "@page-agent/mcp",
-            "version": "1.5.9",
+            "version": "1.6.1",
             "license": "MIT",
             "dependencies": {
                 "@modelcontextprotocol/sdk": "^1.27.1",
@@ -11888,13 +11887,13 @@
             }
         },
         "packages/page-agent": {
-            "version": "1.5.9",
+            "version": "1.6.1",
             "license": "MIT",
             "dependencies": {
-                "@page-agent/core": "1.5.9",
+                "@page-agent/core": "1.6.1",
-                "@page-agent/llms": "1.5.9",
+                "@page-agent/llms": "1.6.1",
-                "@page-agent/page-controller": "1.5.9",
+                "@page-agent/page-controller": "1.6.1",
-                "@page-agent/ui": "1.5.9",
+                "@page-agent/ui": "1.6.1",
                 "chalk": "^5.6.2"
             },
             "devDependencies": {
@@ -11906,7 +11905,7 @@
         },
         "packages/page-controller": {
             "name": "@page-agent/page-controller",
-            "version": "1.5.9",
+            "version": "1.6.1",
             "license": "MIT",
             "dependencies": {
                 "ai-motion": "^0.4.8"
@@ -11914,12 +11913,12 @@
         },
         "packages/ui": {
             "name": "@page-agent/ui",
-            "version": "1.5.9",
+            "version": "1.6.1",
             "license": "MIT"
         },
         "packages/website": {
             "name": "@page-agent/website",
-            "version": "1.5.9",
+            "version": "1.6.1",
             "devDependencies": {
                 "@radix-ui/react-icons": "^1.3.2",
                 "@radix-ui/react-separator": "^1.1.8",

package.json

@@ -1,7 +1,7 @@
 {
     "name": "root",
     "private": true,
-    "version": "1.5.9",
+    "version": "1.6.1",
     "type": "module",
     "workspaces": [
         "packages/page-controller",

packages/core/package.json

@@ -1,7 +1,7 @@
 {
     "name": "@page-agent/core",
     "private": false,
-    "version": "1.5.9",
+    "version": "1.6.1",
     "type": "module",
     "main": "./dist/esm/page-agent-core.js",
     "module": "./dist/esm/page-agent-core.js",
@@ -44,8 +44,8 @@
     },
     "dependencies": {
         "chalk": "^5.6.2",
-        "@page-agent/llms": "1.5.9",
+        "@page-agent/llms": "1.6.1",
-        "@page-agent/page-controller": "1.5.9"
+        "@page-agent/page-controller": "1.6.1"
     },
     "peerDependencies": {
         "zod": "^3.25.0 || ^4.0.0"

packages/extension/docs/extension_api.md

@@ -115,8 +115,8 @@ import type {
 
 export interface ExecuteConfig {
   baseURL: string
-  apiKey: string
   model: string
+  apiKey?: string
 
   // Include the initial tab where page JS starts. Default: true.
   includeInitialTab?: boolean
@@ -205,8 +205,8 @@ import type {
 
 interface ExecuteConfig {
   baseURL: string
-  apiKey: string
   model: string
+  apiKey?: string
   includeInitialTab?: boolean
   onStatusChange?: (status: AgentStatus) => void
   onActivity?: (activity: AgentActivity) => void

packages/extension/package.json

@@ -1,7 +1,7 @@
 {
     "name": "@page-agent/ext",
     "private": true,
-    "version": "1.5.9",
+    "version": "1.6.1",
     "type": "module",
     "scripts": {
         "dev": "wxt",
@@ -16,7 +16,6 @@
         "@radix-ui/react-separator": "^1.1.8",
         "@radix-ui/react-slot": "^1.2.4",
         "@radix-ui/react-switch": "^1.2.6",
-        "@radix-ui/react-tooltip": "^1.2.8",
         "@types/chrome": "^0.1.37",
         "@types/react": "^19.2.14",
         "@types/react-dom": "^19.2.1",
@@ -38,10 +37,10 @@
         "wxt": "^0.20.19"
     },
     "dependencies": {
-        "@page-agent/core": "1.5.9",
+        "@page-agent/core": "1.6.1",
-        "@page-agent/llms": "1.5.9",
+        "@page-agent/llms": "1.6.1",
-        "@page-agent/page-controller": "1.5.9",
+        "@page-agent/page-controller": "1.6.1",
-        "@page-agent/ui": "1.5.9",
+        "@page-agent/ui": "1.6.1",
         "ai-motion": "^0.4.8",
         "chalk": "^5.6.2"
     },

packages/extension/src/agent/MultiPageAgent.ts

@@ -75,6 +75,7 @@ export class MultiPageAgent extends PageAgentCore {
 			},
 
 			onBeforeStep: async (agent) => {
+				if (!tabsController.currentTabId) return
 				// make sure the current tab is loaded before the step starts
 				await tabsController.waitUntilTabLoaded(tabsController.currentTabId!)
 			},

packages/extension/src/agent/RemotePageController.ts

@@ -58,8 +58,6 @@ export class RemotePageController {
 	}
 
 	async getBrowserState(): Promise<BrowserState> {
-		if (!this.currentTabId) throw new Error('tabsController not initialized.')
-
 		let browserState = {} as BrowserState
 		debug('getBrowserState', this.currentTabId)
 
@@ -178,7 +176,7 @@ interface DomActionReturn {
 /**
  * Check if a URL can run content scripts.
  */
-function isContentScriptAllowed(url: string | undefined): boolean {
+export function isContentScriptAllowed(url: string | undefined): boolean {
 	if (!url) return false
 
 	const restrictedPatterns = [

packages/extension/src/agent/TabsController.ts

@@ -1,3 +1,5 @@
+import { isContentScriptAllowed } from './RemotePageController'
+
 const PREFIX = '[TabsController]'
 
 function debug(...messages: any[]) {
@@ -49,23 +51,25 @@ export class TabsController extends EventTarget {
 		}
 
 		if (includeInitialTab) {
-			this.currentTabId = this.initialTabId
-
 			const info = await sendMessage({
 				type: 'TAB_CONTROL',
 				action: 'get_tab_info',
 				payload: { tabId: this.initialTabId },
 			})
 
-			this.tabs.push({
+			if (isContentScriptAllowed(info.url)) {
-				id: result.tabId,
+				this.currentTabId = this.initialTabId
-				isInitial: true,
-				url: info.url,
-				title: info.title,
-				status: info.status,
-			})
 
-			await this.createTabGroup([this.initialTabId])
+				this.tabs.push({
+					id: result.tabId,
+					isInitial: true,
+					url: info.url,
+					title: info.title,
+					status: info.status,
+				})
+
+				await this.createTabGroup([this.initialTabId])
+			}
 		}
 
 		await this.updateCurrentTabId(this.currentTabId)

packages/extension/src/agent/constants.ts

@@ -3,12 +3,12 @@ import type { LLMConfig } from '@page-agent/llms'
 // Demo LLM for testing
 export const DEMO_MODEL = 'qwen3.5-plus'
 export const DEMO_BASE_URL = 'https://page-ag-testing-ohftxirgbn.cn-shanghai.fcapp.run'
-export const DEMO_API_KEY = 'NA'
+// export const DEMO_API_KEY = 'NA'
 
 export const DEMO_CONFIG: LLMConfig = {
-	apiKey: DEMO_API_KEY,
 	baseURL: DEMO_BASE_URL,
 	model: DEMO_MODEL,
+	// apiKey: DEMO_API_KEY,
 }
 
 /** Legacy testing endpoints that should be auto-migrated to DEMO_BASE_URL */

packages/extension/src/agent/useAgent.ts

@@ -21,6 +21,7 @@ export interface AdvancedConfig {
 	maxSteps?: number
 	systemInstruction?: string
 	experimentalLlmsTxt?: boolean
+	disableNamedToolChoice?: boolean
 }
 
 export interface ExtConfig extends LLMConfig, AdvancedConfig {
@@ -124,6 +125,7 @@ export function useAgent(): UseAgentResult {
 			maxSteps,
 			systemInstruction,
 			experimentalLlmsTxt,
+			disableNamedToolChoice,
 			...llmConfig
 		}: ExtConfig) => {
 			await chrome.storage.local.set({ llmConfig })
@@ -132,7 +134,12 @@ export function useAgent(): UseAgentResult {
 			} else {
 				await chrome.storage.local.remove('language')
 			}
-			const advancedConfig: AdvancedConfig = { maxSteps, systemInstruction, experimentalLlmsTxt }
+			const advancedConfig: AdvancedConfig = {
+				maxSteps,
+				systemInstruction,
+				experimentalLlmsTxt,
+				disableNamedToolChoice,
+			}
 			await chrome.storage.local.set({ advancedConfig })
 			setConfig({ ...llmConfig, ...advancedConfig, language })
 		},

packages/extension/src/components/ConfigPanel.tsx

@@ -1,18 +1,20 @@
 import {
-	ChevronDown,
 	Copy,
 	CornerUpLeft,
+	ExternalLink,
 	Eye,
 	EyeOff,
+	FoldVertical,
 	HatGlasses,
 	Home,
 	Loader2,
 	Scale,
+	UnfoldVertical,
 } from 'lucide-react'
 import { useEffect, useState } from 'react'
 import { siGithub } from 'simple-icons'
 
-import { DEMO_API_KEY, DEMO_BASE_URL, DEMO_MODEL, isTestingEndpoint } from '@/agent/constants'
+import { DEMO_BASE_URL, DEMO_MODEL, isTestingEndpoint } from '@/agent/constants'
 import type { ExtConfig, LanguagePreference } from '@/agent/useAgent'
 import { Button } from '@/components/ui/button'
 import { Input } from '@/components/ui/input'
@@ -25,15 +27,18 @@ interface ConfigPanelProps {
 }
 
 export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
-	const [apiKey, setApiKey] = useState(config?.apiKey || DEMO_API_KEY)
 	const [baseURL, setBaseURL] = useState(config?.baseURL || DEMO_BASE_URL)
 	const [model, setModel] = useState(config?.model || DEMO_MODEL)
+	const [apiKey, setApiKey] = useState(config?.apiKey)
 	const [language, setLanguage] = useState<LanguagePreference>(config?.language)
 	const [maxSteps, setMaxSteps] = useState<number | undefined>(config?.maxSteps)
 	const [systemInstruction, setSystemInstruction] = useState(config?.systemInstruction ?? '')
 	const [experimentalLlmsTxt, setExperimentalLlmsTxt] = useState(
 		config?.experimentalLlmsTxt ?? false
 	)
+	const [disableNamedToolChoice, setDisableNamedToolChoice] = useState(
+		config?.disableNamedToolChoice ?? false
+	)
 	const [advancedOpen, setAdvancedOpen] = useState(false)
 	const [saving, setSaving] = useState(false)
 	const [userAuthToken, setUserAuthToken] = useState<string>('')
@@ -42,13 +47,14 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 	const [showApiKey, setShowApiKey] = useState(false)
 
 	useEffect(() => {
-		setApiKey(config?.apiKey || DEMO_API_KEY)
 		setBaseURL(config?.baseURL || DEMO_BASE_URL)
 		setModel(config?.model || DEMO_MODEL)
+		setApiKey(config?.apiKey)
 		setLanguage(config?.language)
 		setMaxSteps(config?.maxSteps)
 		setSystemInstruction(config?.systemInstruction ?? '')
 		setExperimentalLlmsTxt(config?.experimentalLlmsTxt ?? false)
+		setDisableNamedToolChoice(config?.disableNamedToolChoice ?? false)
 	}, [config])
 
 	// Poll for user auth token every second until found
@@ -94,6 +100,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 				maxSteps: maxSteps || undefined,
 				systemInstruction: systemInstruction || undefined,
 				experimentalLlmsTxt,
+				disableNamedToolChoice,
 			})
 		} finally {
 			setSaving(false)
@@ -153,6 +160,16 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 				</div>
 			</div>
 
+			{/* Hub link */}
+			<a
+				href="/hub.html"
+				target="_blank"
+				className="flex items-center justify-between p-3 rounded-md border bg-muted/50 text-xs font-medium text-muted-foreground hover:text-foreground hover:border-foreground/20 transition-colors"
+			>
+				Manage Page Agent Hub
+				<ExternalLink className="size-3" />
+			</a>
+
 			<div className="flex flex-col gap-1.5">
 				<label className="text-xs text-muted-foreground">Base URL</label>
 				<Input
@@ -167,7 +184,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 			{isTestingEndpoint(baseURL) && (
 				<div className="p-2.5 rounded-md border border-amber-500/30 bg-amber-500/5 text-[11px] text-muted-foreground leading-relaxed">
 					<Scale className="size-3 inline-block mr-1 -mt-0.5 text-amber-600" />
-					You are using the free testing API. By using this service you agree to the{' '}
+					You are using our testing API. By using this you agree to the{' '}
 					<a
 						href="https://github.com/alibaba/page-agent/blob/main/docs/terms-and-privacy.md"
 						target="_blank"
@@ -176,14 +193,13 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 					>
 						Terms of Use & Privacy Policy
 					</a>
-					. No sensitive data. No guaranteed availability.
 				</div>
 			)}
 
 			<div className="flex flex-col gap-1.5">
 				<label className="text-xs text-muted-foreground">Model</label>
 				<Input
-					placeholder="gpt-5.2"
+					placeholder="gpt-5.1"
 					value={model}
 					onChange={(e) => setModel(e.target.value)}
 					className="text-xs h-8"
@@ -195,7 +211,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 				<div className="flex gap-2 items-center">
 					<Input
 						type={showApiKey ? 'text' : 'password'}
-						placeholder="sk-..."
+						// placeholder="sk-..."
 						value={apiKey}
 						onChange={(e) => setApiKey(e.target.value)}
 						className="text-xs h-8"
@@ -212,7 +228,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 			</div>
 
 			<div className="flex flex-col gap-1.5">
-				<label className="text-xs text-muted-foreground">Language</label>
+				<label className="text-xs text-muted-foreground">Response Language</label>
 				<select
 					value={language ?? ''}
 					onChange={(e) => setLanguage((e.target.value || undefined) as LanguagePreference)}
@@ -231,10 +247,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 				className="flex items-center gap-1 text-xs text-muted-foreground hover:text-foreground cursor-pointer mt-1 font-bold"
 			>
 				Advanced
-				<ChevronDown
+				{advancedOpen ? <FoldVertical className="size-3" /> : <UnfoldVertical className="size-3" />}
-					className="size-3 transition-transform"
-					style={{ transform: advancedOpen ? 'rotate(0deg)' : 'rotate(90deg)' }}
-				/>
 			</button>
 
 			{advancedOpen && (
@@ -263,6 +276,11 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 						/>
 					</div>
 
+					<label className="flex items-center justify-between cursor-pointer">
+						<span className="text-xs text-muted-foreground">Disable named tool_choice</span>
+						<Switch checked={disableNamedToolChoice} onCheckedChange={setDisableNamedToolChoice} />
+					</label>
+
 					<label className="flex items-center justify-between cursor-pointer">
 						<span className="text-xs text-muted-foreground">Experimental llms.txt support</span>
 						<Switch checked={experimentalLlmsTxt} onCheckedChange={setExperimentalLlmsTxt} />

packages/extension/src/components/HistoryDetail.tsx

@@ -1,12 +1,20 @@
-import { ArrowLeft } from 'lucide-react'
+import { ArrowLeft, RotateCcw, Trash2 } from 'lucide-react'
 import { useEffect, useState } from 'react'
 
 import { Button } from '@/components/ui/button'
-import { type SessionRecord, getSession } from '@/lib/db'
+import { type SessionRecord, deleteSession, getSession } from '@/lib/db'
 
 import { EventCard } from './cards'
 
-export function HistoryDetail({ sessionId, onBack }: { sessionId: string; onBack: () => void }) {
+export function HistoryDetail({
+	sessionId,
+	onBack,
+	onRerun,
+}: {
+	sessionId: string
+	onBack: () => void
+	onRerun: (task: string) => void
+}) {
 	const [session, setSession] = useState<SessionRecord | null>(null)
 
 	useEffect(() => {
@@ -37,6 +45,27 @@ export function HistoryDetail({ sessionId, onBack }: { sessionId: string; onBack
 				<div className="text-xs font-medium" title={session.task}>
 					{session.task}
 				</div>
+				<div className="mt-2 flex items-center gap-2">
+					<button
+						type="button"
+						onClick={() => onRerun(session.task)}
+						className="flex items-center gap-1 text-[10px] text-muted-foreground hover:text-foreground transition-colors cursor-pointer disabled:opacity-50 disabled:cursor-not-allowed"
+					>
+						<RotateCcw className="size-3" />
+						Run again
+					</button>
+					<button
+						type="button"
+						onClick={async () => {
+							await deleteSession(sessionId)
+							onBack()
+						}}
+						className="flex items-center gap-1 text-[10px] text-muted-foreground hover:text-destructive transition-colors cursor-pointer"
+					>
+						<Trash2 className="size-3" />
+						Delete
+					</button>
+				</div>
 			</div>
 
 			{/* Events (read-only) */}

packages/extension/src/components/HistoryList.tsx

@@ -1,8 +1,9 @@
-import { ArrowLeft, CheckCircle, Trash2, XCircle } from 'lucide-react'
+import { ArrowDownToLine, ArrowLeft, CheckCircle, RotateCcw, Trash2, XCircle } from 'lucide-react'
 import { useCallback, useEffect, useState } from 'react'
 
 import { Button } from '@/components/ui/button'
 import { type SessionRecord, clearSessions, deleteSession, listSessions } from '@/lib/db'
+import { downloadHistoryExport } from '@/lib/history-export'
 
 function timeAgo(ts: number): string {
 	const seconds = Math.floor((Date.now() - ts) / 1000)
@@ -18,9 +19,11 @@ function timeAgo(ts: number): string {
 export function HistoryList({
 	onSelect,
 	onBack,
+	onRerun,
 }: {
 	onSelect: (id: string) => void
 	onBack: () => void
+	onRerun: (task: string) => void
 }) {
 	const [sessions, setSessions] = useState<SessionRecord[]>([])
 	const [loading, setLoading] = useState(true)
@@ -41,6 +44,16 @@ export function HistoryList({
 		setSessions((prev) => prev.filter((s) => s.id !== id))
 	}
 
+	const handleExport = (e: React.MouseEvent, session: SessionRecord) => {
+		e.stopPropagation()
+		downloadHistoryExport(session.task, session.createdAt, session.history)
+	}
+
+	const handleRerun = (e: React.MouseEvent, task: string) => {
+		e.stopPropagation()
+		onRerun(task)
+	}
+
 	return (
 		<div className="flex flex-col h-screen bg-background">
 			{/* Header */}
@@ -85,7 +98,6 @@ export function HistoryList({
 						role="button"
 						tabIndex={0}
 						onClick={() => onSelect(session.id)}
-						onKeyDown={(e) => e.key === 'Enter' && onSelect(session.id)}
 						className="w-full text-left px-3 py-2.5 border-b hover:bg-muted/50 transition-colors cursor-pointer flex items-start gap-2 group"
 					>
 						{/* Status icon */}
@@ -98,19 +110,41 @@ export function HistoryList({
 						{/* Content */}
 						<div className="flex-1 min-w-0">
 							<p className="text-xs font-medium truncate">{session.task}</p>
-							<p className="text-[10px] text-muted-foreground mt-0.5">
+							<div className="flex items-center mt-0.5">
-								{timeAgo(session.createdAt)} · {session.history.length} steps
+								<p className="text-[10px] text-muted-foreground">
-							</p>
+									{timeAgo(session.createdAt)} · {session.history.length} steps
+								</p>
+								<div className="flex items-center gap-0.5 ml-auto opacity-0 group-hover:opacity-100 transition-opacity">
+									<button
+										type="button"
+										onClick={(e) => handleRerun(e, session.task)}
+										className="p-0.5 text-muted-foreground hover:text-foreground transition-colors cursor-pointer"
+										title="Run task again"
+										aria-label={`Run history task again: ${session.task}`}
+									>
+										<RotateCcw className="size-3" />
+									</button>
+									<button
+										type="button"
+										onClick={(e) => handleExport(e, session)}
+										className="p-1 text-muted-foreground hover:text-foreground transition-colors cursor-pointer"
+										title="Export history JSON"
+										aria-label={`Export history for ${session.task}`}
+									>
+										<ArrowDownToLine className="size-3" />
+									</button>
+									<button
+										type="button"
+										onClick={(e) => handleDelete(e, session.id)}
+										className="p-0.5 text-muted-foreground hover:text-destructive transition-colors cursor-pointer"
+										title="Delete history"
+										aria-label={`Delete history for ${session.task}`}
+									>
+										<Trash2 className="size-3" />
+									</button>
+								</div>
+							</div>
 						</div>
-
-						{/* Delete */}
-						<button
-							type="button"
-							onClick={(e) => handleDelete(e, session.id)}
-							className="opacity-0 group-hover:opacity-100 transition-opacity p-1 hover:text-destructive cursor-pointer shrink-0"
-						>
-							<Trash2 className="size-3" />
-						</button>
 					</div>
 				))}
 			</div>

packages/extension/src/components/misc.tsx

@@ -84,7 +84,7 @@ export function MotionOverlay({ active }: { active: boolean }) {
 	return (
 		<div
 			ref={containerRef}
-			className="pointer-events-none absolute inset-0 z-10 opacity-60"
+			className="pointer-events-none absolute inset-0 z-10 opacity-60 overflow-hidden"
 			style={{ display: active ? undefined : 'none' }}
 		/>
 	)

packages/extension/src/components/ui/switch.tsx

@@ -8,7 +8,7 @@ function Switch({ className, ...props }: React.ComponentProps<typeof SwitchPrimi
 		<SwitchPrimitive.Root
 			data-slot="switch"
 			className={cn(
-				'peer data-[state=checked]:bg-primary data-[state=unchecked]:bg-input focus-visible:border-ring focus-visible:ring-ring/50 dark:data-[state=unchecked]:bg-input/80 inline-flex h-[1.15rem] w-8 shrink-0 items-center rounded-full border border-transparent shadow-xs transition-all outline-none focus-visible:ring-[3px] disabled:cursor-not-allowed disabled:opacity-50',
+				'peer data-[state=checked]:bg-primary data-[state=unchecked]:bg-input focus-visible:border-ring focus-visible:ring-ring/50 dark:data-[state=unchecked]:bg-input/80 inline-flex h-[1.15rem] w-8 shrink-0 cursor-pointer items-center rounded-full border border-transparent shadow-xs transition-all outline-none focus-visible:ring-[3px] disabled:cursor-not-allowed disabled:opacity-50',
 				className
 			)}
 			{...props}

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

@@ -1,10 +1,11 @@
-import { Plug, PlugZap, Square, Unplug } from 'lucide-react'
+import { FoldVertical, Plug, PlugZap, Square, UnfoldVertical, Unplug } from 'lucide-react'
-import { useEffect, useRef } from 'react'
+import { useEffect, useRef, useState } from 'react'
 
 import { useAgent } from '@/agent/useAgent'
 import { ActivityCard, EventCard } from '@/components/cards'
 import { Logo, MotionOverlay, StatusDot } from '@/components/misc'
 import { Button } from '@/components/ui/button'
+import { Switch } from '@/components/ui/switch'
 
 import { useHubWs } from './hub-ws'
 
@@ -25,33 +26,72 @@ export default function App() {
 	const wsLabel = {
 		connected: 'Connected',
 		connecting: 'Connecting…',
-		disconnected: new URLSearchParams(location.search).get('ws') ? 'Disconnected' : 'Standalone',
+		disconnected: new URLSearchParams(location.search).get('ws') ? 'Disconnected' : 'No connection',
 	}[wsState]
 
 	return (
 		<div className="flex h-screen bg-background">
-			<MotionOverlay active={isRunning} />
-
 			{/* Left — Protocol docs */}
 			<aside className="w-80 shrink-0 border-r flex flex-col bg-muted/20">
-				<div className="flex items-center gap-2 px-5 py-4 border-b">
+				<a
+					href="https://alibaba.github.io/page-agent/"
+					target="_blank"
+					rel="noopener noreferrer"
+					className="flex items-center gap-2 px-5 h-12 border-b hover:bg-muted/30 transition-colors"
+				>
 					<Logo className="size-5" />
 					<span className="text-sm font-semibold tracking-tight">Page Agent Hub</span>
+					<span className="text-[9px] font-medium uppercase tracking-wider text-amber-600 bg-amber-500/10 border border-amber-500/30 rounded px-1.5 py-0.5">
+						Beta
+					</span>
+				</a>
+
+				<div className="flex-1 overflow-y-auto px-5 py-4 space-y-6">
+					<div className="text-xs text-muted-foreground leading-relaxed space-y-2">
+						<p>
+							Page Agent Hub lets local apps (e.g. MCP servers) control the Page Agent extension via
+							WebSocket.
+						</p>
+						<p>
+							Check out the official{' '}
+							<a
+								href="https://github.com/alibaba/page-agent/tree/main/packages/mcp"
+								target="_blank"
+								rel="noopener noreferrer"
+								className="underline hover:text-foreground"
+							>
+								MCP server package
+							</a>
+							.
+						</p>
+					</div>
+
+					<HubConfig />
+
+					<ProtocolDocsCollapsible />
 				</div>
 
-				<div className="flex-1 overflow-y-auto px-5 py-4">
+				<div className="border-t px-5 py-3 text-[10px] text-muted-foreground/60 flex items-center justify-between">
-					<ProtocolDocs />
+					<span className="font-mono">v{__VERSION__}</span>
-				</div>
+					<span>
-
+						Built with ♥️ by{' '}
-				<div className="border-t px-5 py-3 text-[11px] text-muted-foreground/60">
+						<a
-					Connect via <code className="text-[10px]">hub.html?ws=PORT</code>
+							href="https://github.com/gaomeng1900"
+							target="_blank"
+							rel="noopener noreferrer"
+							className="underline hover:text-foreground"
+						>
+							@Simon
+						</a>
+					</span>
 				</div>
 			</aside>
 
 			{/* Right — Live session */}
-			<main className="flex-1 flex flex-col min-w-0">
+			<main className="flex-1 flex flex-col min-w-0 relative">
-				{/* Header bar */}
+				<MotionOverlay active={isRunning} />
-				<header className="flex items-center justify-between border-b px-5 py-3">
+
+				<header className="flex items-center justify-between border-b px-5 h-12">
 					<div className="flex items-center gap-2 text-xs text-muted-foreground">
 						<WsIcon className="size-3.5" />
 						<span>{wsLabel}</span>
@@ -104,49 +144,108 @@ export default function App() {
 	)
 }
 
-function ProtocolDocs() {
+function HubConfig() {
+	const [allowAll, setAllowAll] = useState(false)
+
+	useEffect(() => {
+		chrome.storage.local.get('allowAllHubConnection').then((r) => {
+			setAllowAll(r.allowAllHubConnection === true)
+		})
+	}, [])
+
+	const toggle = (checked: boolean) => {
+		setAllowAll(checked)
+		chrome.storage.local.set({ allowAllHubConnection: checked })
+	}
+
 	return (
-		<div className="space-y-5 text-xs text-muted-foreground">
+		<div>
-			<section>
+			<h3 className="text-[11px] font-semibold text-foreground/80 uppercase tracking-wider mb-2">
-				<h3 className="text-[11px] font-semibold text-foreground/80 uppercase tracking-wider mb-2">
+				Config
-					Caller → Hub
+			</h3>
-				</h3>
+			<div className="group/hub relative">
-				<pre className="bg-muted/50 rounded-md p-3 font-mono text-[10px] leading-relaxed whitespace-pre-wrap">
+				<label
-					{`{ type: "execute", task: string, config?: object }
+					className={`flex items-center justify-between p-3 rounded-md border cursor-pointer text-xs ${allowAll ? 'bg-amber-500/10 border-amber-500/30 text-amber-600' : 'bg-muted/50 text-muted-foreground'}`}
-{ type: "stop" }`}
+				>
-				</pre>
+					Auto-approve connections
-			</section>
+					<Switch
+						checked={allowAll}
+						onCheckedChange={toggle}
+						className={allowAll ? 'data-[state=checked]:bg-amber-500' : ''}
+					/>
+				</label>
 
-			<section>
+				{/* hide with invisible absolute opacity-0*/}
-				<h3 className="text-[11px] font-semibold text-foreground/80 uppercase tracking-wider mb-2">
+				<div className="group-hover/hub:visible group-hover/hub:opacity-100 transition-opacity duration-150  left-0 right-0 top-full z-10 pt-2">
-					Hub → Caller
+					<div className="relative p-2.5 rounded-md border border-border bg-background/60 backdrop-blur-md shadow-2xl text-muted-foreground text-xs leading-relaxed">
-				</h3>
+						<div className="absolute -top-1.5 left-5 size-3 rotate-45 rounded-[1px] border-l border-t border-border bg-background/60 backdrop-blur-md" />
-				<pre className="bg-muted/50 rounded-md p-3 font-mono text-[10px] leading-relaxed whitespace-pre-wrap">
+						By default, each connection requires your approval before running tasks. <br />
-					{`{ type: "ready" }
+						Enable this to skip per-session approval.
-{ type: "result", success: boolean, data: string }
+						<br />
-{ type: "error", message: string }`}
+						<span className="font-semibold">* Use with caution!</span>
-				</pre>
+					</div>
-			</section>
+				</div>
-
+			</div>
-			<section>
+		</div>
-				<h3 className="text-[11px] font-semibold text-foreground/80 uppercase tracking-wider mb-2">
+	)
-					Flow
+}
-				</h3>
+
-				<ol className="list-decimal list-inside space-y-1 text-[11px] leading-relaxed">
+function ProtocolDocsCollapsible() {
-					<li>Hub opens WS to caller's server</li>
+	const [open, setOpen] = useState(false)
-					<li>
+
-						Sends <code className="text-[10px]">ready</code>
+	return (
-					</li>
+		<div>
-					<li>
+			<button
-						Caller sends <code className="text-[10px]">execute</code> with task
+				type="button"
-					</li>
+				onClick={() => setOpen(!open)}
-					<li>Hub runs agent, streams events</li>
+				className="flex items-center gap-1 text-[11px] font-semibold text-foreground/80 uppercase tracking-wider cursor-pointer"
-					<li>
+			>
-						Hub sends <code className="text-[10px]">result</code> or{' '}
+				Docs
-						<code className="text-[10px]">error</code>
+				{open ? <FoldVertical className="size-3" /> : <UnfoldVertical className="size-3" />}
-					</li>
+			</button>
-				</ol>
+
-			</section>
+			{open && (
+				<div className="mt-3 space-y-4 text-xs text-muted-foreground">
+					<p className="text-[10px]">
+						Connect via <code className="text-[10px]">hub.html?ws=PORT</code>
+					</p>
+
+					<section>
+						<h4 className="text-[11px] font-medium text-foreground/60 mb-1.5">Flow</h4>
+						<ol className="list-decimal list-inside space-y-1 text-[11px] leading-relaxed">
+							<li>Hub opens WS to caller's server</li>
+							<li>
+								Sends <code className="text-[10px]">ready</code>
+							</li>
+							<li>
+								Caller sends <code className="text-[10px]">execute</code> with task
+							</li>
+							<li>Hub runs agent, streams events</li>
+							<li>
+								Hub sends <code className="text-[10px]">result</code> or{' '}
+								<code className="text-[10px]">error</code>
+							</li>
+						</ol>
+					</section>
+
+					<section>
+						<h4 className="text-[11px] font-medium text-foreground/60 mb-1.5">Caller → Hub</h4>
+						<pre className="bg-muted/50 rounded-md p-3 font-mono text-[10px] leading-relaxed whitespace-pre-wrap">
+							{`{ type: "execute", task: string, config?: object }
+{ type: "stop" }`}
+						</pre>
+					</section>
+
+					<section>
+						<h4 className="text-[11px] font-medium text-foreground/60 mb-1.5">Hub → Caller</h4>
+						<pre className="bg-muted/50 rounded-md p-3 font-mono text-[10px] leading-relaxed whitespace-pre-wrap">
+							{`{ type: "ready" }
+{ type: "result", success: boolean, data: string }
+{ type: "error", message: string }`}
+						</pre>
+					</section>
+				</div>
+			)}
 		</div>
 	)
 }

packages/extension/src/entrypoints/hub/hub-ws.ts

@@ -70,6 +70,7 @@ export class HubWs {
 	#ws: WebSocket | null = null
 	#state: HubWsState = 'disconnected'
 	#busy = false
+	#approved = false
 	#handlers: HubWsHandlers
 	#port: number
 	#onStateChange: (state: HubWsState) => void
@@ -103,6 +104,7 @@ export class HubWs {
 		ws.addEventListener('close', () => {
 			this.#ws = null
 			this.#busy = false
+			this.#approved = false
 			this.#setState('disconnected')
 		})
 
@@ -115,6 +117,7 @@ export class HubWs {
 		this.#ws?.close()
 		this.#ws = null
 		this.#busy = false
+		this.#approved = false
 		this.#setState('disconnected')
 	}
 
@@ -130,7 +133,7 @@ export class HubWs {
 		}
 	}
 
-	#handleMessage(raw: string) {
+	async #handleMessage(raw: string) {
 		let msg: InboundMessage
 		try {
 			msg = JSON.parse(raw)
@@ -138,6 +141,11 @@ export class HubWs {
 			return
 		}
 
+		if (!(await this.#checkApproval())) {
+			this.#send({ type: 'error', message: 'User denied the connection request.' })
+			return
+		}
+
 		switch (msg.type) {
 			case 'execute':
 				this.#handleExecute(msg)
@@ -148,6 +156,22 @@ export class HubWs {
 		}
 	}
 
+	async #checkApproval(): Promise<boolean> {
+		if (this.#approved) return true
+
+		const { allowAllHubConnection } = await chrome.storage.local.get('allowAllHubConnection')
+		if (allowAllHubConnection === true) {
+			this.#approved = true
+			return true
+		}
+
+		const ok = window.confirm(
+			'An external application is requesting to control your browser via Page Agent Ext.\nAllow this session?'
+		)
+		if (ok) this.#approved = true
+		return ok
+	}
+
 	async #handleExecute(msg: ExecuteMessage) {
 		if (this.#busy) {
 			this.#send({ type: 'error', message: 'Hub is busy with another task' })

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

@@ -4,8 +4,8 @@ export type Execute = (task: string, config: ExecuteConfig) => Promise<Execution
 
 export interface ExecuteConfig {
 	baseURL: string
-	apiKey: string
 	model: string
+	apiKey?: string
 
 	/**
 	 * Whether to include the initial tab (that holds this main world script) in the task.
@@ -30,7 +30,6 @@ export default defineUnlistedScript(() => {
 		if (task.trim().length === 0) throw new Error('Task cannot be empty')
 		if (!config) throw new Error('Config is required')
 		if (!config.baseURL) throw new Error('Config must have a baseURL')
-		if (!config.apiKey) throw new Error('Config must have an apiKey')
 		if (!config.model) throw new Error('Config must have a model')
 
 		const id = getId()
@@ -85,8 +84,8 @@ export default defineUnlistedScript(() => {
 					task,
 					config: {
 						baseURL: config.baseURL,
-						apiKey: config.apiKey,
 						model: config.model,
+						apiKey: config.apiKey,
 						includeInitialTab: config.includeInitialTab,
 					},
 				},

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

@@ -56,19 +56,27 @@ export default function App() {
 		}
 	}, [history, activity])
 
-	const handleSubmit = useCallback(
+	const runTask = useCallback(
-		(e?: React.SyntheticEvent) => {
+		(task: string) => {
-			e?.preventDefault()
+			const normalizedTask = task.trim()
-			if (!inputValue.trim() || status === 'running') return
+			if (!normalizedTask || status === 'running') return
 
-			const taskToExecute = inputValue.trim()
 			setInputValue('')
+			setView({ name: 'chat' })
 
-			execute(taskToExecute).catch((error) => {
+			execute(normalizedTask).catch((error) => {
 				console.error('[SidePanel] Failed to execute task:', error)
 			})
 		},
-		[inputValue, status, execute]
+		[execute, status]
+	)
+
+	const handleSubmit = useCallback(
+		(e?: React.SyntheticEvent) => {
+			e?.preventDefault()
+			runTask(inputValue)
+		},
+		[inputValue, runTask]
 	)
 
 	const handleStop = useCallback(() => {
@@ -103,12 +111,19 @@ export default function App() {
 			<HistoryList
 				onSelect={(id) => setView({ name: 'history-detail', sessionId: id })}
 				onBack={() => setView({ name: 'chat' })}
+				onRerun={runTask}
 			/>
 		)
 	}
 
 	if (view.name === 'history-detail') {
-		return <HistoryDetail sessionId={view.sessionId} onBack={() => setView({ name: 'history' })} />
+		return (
+			<HistoryDetail
+				sessionId={view.sessionId}
+				onBack={() => setView({ name: 'history' })}
+				onRerun={runTask}
+			/>
+		)
 	}
 
 	// --- Chat view ---

packages/extension/src/lib/history-export.ts

@@ -0,0 +1,60 @@
+import type { HistoricalEvent } from '@page-agent/core'
+
+const EXPORT_FILE_PREFIX = 'page-agent-history'
+const MAX_TASK_SLUG_LENGTH = 40
+
+export function serializeHistoryExport(history: HistoricalEvent[]): string {
+	return `${JSON.stringify(history, null, 2)}\n`
+}
+
+export function buildHistoryExportFilename(task: string, createdAt: number): string {
+	const taskSlug = sanitizeTaskForFilename(task)
+	const timestamp = formatTimestampForFilename(createdAt)
+
+	return taskSlug
+		? `${EXPORT_FILE_PREFIX}-${taskSlug}-${timestamp}.json`
+		: `${EXPORT_FILE_PREFIX}-${timestamp}.json`
+}
+
+export function downloadHistoryExport(
+	task: string,
+	createdAt: number,
+	history: HistoricalEvent[]
+): void {
+	const filename = buildHistoryExportFilename(task, createdAt)
+	const content = serializeHistoryExport(history)
+	const blob = new Blob([content], { type: 'application/json;charset=utf-8' })
+	const url = URL.createObjectURL(blob)
+	const link = document.createElement('a')
+
+	link.href = url
+	link.download = filename
+	link.click()
+
+	URL.revokeObjectURL(url)
+}
+
+function sanitizeTaskForFilename(task: string): string {
+	return task
+		.trim()
+		.toLowerCase()
+		.replace(/[^a-z0-9]+/g, '-')
+		.replace(/^-+|-+$/g, '')
+		.slice(0, MAX_TASK_SLUG_LENGTH)
+}
+
+function formatTimestampForFilename(createdAt: number): string {
+	const date = new Date(createdAt)
+	const year = date.getFullYear()
+	const month = pad(date.getMonth() + 1)
+	const day = pad(date.getDate())
+	const hours = pad(date.getHours())
+	const minutes = pad(date.getMinutes())
+	const seconds = pad(date.getSeconds())
+
+	return `${year}-${month}-${day}_${hours}-${minutes}-${seconds}`
+}
+
+function pad(value: number): string {
+	return value.toString().padStart(2, '0')
+}

packages/llms/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@page-agent/llms",
-    "version": "1.5.9",
+    "version": "1.6.1",
     "type": "module",
     "main": "./dist/lib/page-agent-llms.js",
     "module": "./dist/lib/page-agent-llms.js",

packages/llms/src/OpenAIClient.ts

@@ -29,16 +29,19 @@ export class OpenAIClient implements LLMClient {
 		const openaiTools = Object.entries(tools).map(([name, t]) => zodToOpenAITool(name, t))
 
 		// Build request body
+
+		let toolChoice: unknown = 'required'
+		if (options?.toolChoiceName && !this.config.disableNamedToolChoice) {
+			toolChoice = { type: 'function', function: { name: options.toolChoiceName } }
+		}
+
 		const requestBody: Record<string, unknown> = {
 			model: this.config.model,
 			temperature: this.config.temperature,
 			messages,
 			tools: openaiTools,
 			parallel_tool_calls: false,
-			// Require tool call: specific tool if provided, otherwise any tool
+			tool_choice: toolChoice,
-			tool_choice: options?.toolChoiceName
-				? { type: 'function', function: { name: options.toolChoiceName } }
-				: 'required',
 		}
 
 		modelPatch(requestBody)
@@ -50,7 +53,7 @@ export class OpenAIClient implements LLMClient {
 				method: 'POST',
 				headers: {
 					'Content-Type': 'application/json',
-					Authorization: `Bearer ${this.config.apiKey}`,
+					...(this.config.apiKey && { Authorization: `Bearer ${this.config.apiKey}` }),
 				},
 				body: JSON.stringify(requestBody),
 				signal: abortSignal,

packages/llms/src/index.ts

@@ -8,19 +8,20 @@ export type { InvokeOptions, InvokeResult, LLMClient, LLMConfig, Message, Tool }
 
 export function parseLLMConfig(config: LLMConfig): Required<LLMConfig> {
 	// Runtime validation as defensive programming (types already guarantee these)
-	if (!config.baseURL || !config.apiKey || !config.model) {
+	if (!config.baseURL || !config.model) {
 		throw new Error(
-			'[PageAgent] LLM configuration required. Please provide: baseURL, apiKey, model. ' +
+			'[PageAgent] LLM configuration required. Please provide: baseURL, model. ' +
 				'See: https://alibaba.github.io/page-agent/docs/features/models'
 		)
 	}
 
 	return {
 		baseURL: config.baseURL,
-		apiKey: config.apiKey,
 		model: config.model,
+		apiKey: config.apiKey || '',
 		temperature: config.temperature ?? DEFAULT_TEMPERATURE,
 		maxRetries: config.maxRetries ?? LLM_MAX_RETRIES,
+		disableNamedToolChoice: config.disableNamedToolChoice ?? false,
 		customFetch: (config.customFetch ?? fetch).bind(globalThis), // fetch will be illegal unless bound
 	}
 }

packages/llms/src/types.ts

@@ -89,12 +89,18 @@ export interface InvokeResult<TResult = unknown> {
  */
 export interface LLMConfig {
 	baseURL: string
-	apiKey: string
 	model: string
+	apiKey?: string
 
 	temperature?: number
 	maxRetries?: number
 
+	/**
+	 * remove the tool_choice field from the request.
+	 * @note fix "Invalid tool_choice type: 'object'" for some LLMs.
+	 */
+	disableNamedToolChoice?: boolean
+
 	/**
 	 * Custom fetch function for LLM API requests.
 	 * Use this to customize headers, credentials, proxy, etc.

packages/mcp/package.json

@@ -1,7 +1,7 @@
 {
     "name": "@page-agent/mcp",
-    "private": true,
+    "private": false,
-    "version": "1.5.9",
+    "version": "1.6.1",
     "type": "module",
     "bin": {
         "page-agent-mcp": "src/index.js"

packages/mcp/src/index.js

@@ -12,9 +12,9 @@ const port = parseInt(env.PORT || '38401')
 
 /** @type {Record<string, string>} */
 const llmConfig = {}
-if (env.LLM_API_KEY) llmConfig.apiKey = env.LLM_API_KEY
 if (env.LLM_BASE_URL) llmConfig.baseURL = env.LLM_BASE_URL
 if (env.LLM_MODEL_NAME) llmConfig.model = env.LLM_MODEL_NAME
+if (env.LLM_API_KEY) llmConfig.apiKey = env.LLM_API_KEY
 
 // --- Hub bridge (HTTP + WebSocket) ---
 
@@ -35,11 +35,14 @@ const mcpServer = new McpServer({ name: 'page-agent', version: '1.5.8' })
 mcpServer.registerTool(
 	'execute_task',
 	{
-		description:
+		description: "Execute a task in user's browser.",
-			'Execute a browser automation task described in natural language. ' +
+		inputSchema: {
-			'The Page Agent extension will control the browser to complete the task. ' +
+			task: z
-			'Blocks until the task is complete.',
+				.string()
-		inputSchema: { task: z.string().describe('Task description in natural language') },
+				.describe(
+					'Task description. Give specific instructions for the task. Steps preferable. And the information you want to get after the task is done.'
+				),
+		},
 	},
 	async ({ task }) => {
 		try {
@@ -50,7 +53,7 @@ mcpServer.registerTool(
 					{
 						type: 'text',
 						text: result.success
-							? `Task completed successfully.\n\n${result.data}`
+							? `Task completed.\n\n${result.data}`
 							: `Task failed.\n\n${result.data}`,
 					},
 				],
@@ -67,7 +70,7 @@ mcpServer.registerTool(
 mcpServer.registerTool(
 	'get_status',
 	{
-		description: 'Check the current status of the Page Agent hub connection and agent.',
+		description: 'Check the current status of the Page Agent hub.',
 	},
 	async () => ({
 		content: [

packages/mcp/src/launcher.html

@@ -1,9 +1,10 @@
 <!doctype html>
-<html lang="en">
+<html>
 	<head>
 		<meta charset="UTF-8" />
 		<meta name="viewport" content="width=device-width, initial-scale=1.0" />
-		<title>Page Agent – Connecting</title>
+		<link rel="icon" href="https://img.alicdn.com/imgextra/i1/O1CN01mRGret1QrKiu7CFJI_!!6000000002029-2-tps-64-64.png" />
+		<title>Page Agent MCP Launcher</title>
 		<style>
 			* {
 				margin: 0;
@@ -15,7 +16,7 @@
 					system-ui,
 					-apple-system,
 					sans-serif;
-				background: #0a0a0a;
+				background: #09090b;
 				color: #e5e5e5;
 				display: flex;
 				align-items: center;
@@ -24,23 +25,37 @@
 			}
 			.card {
 				text-align: center;
-				max-width: 420px;
+				max-width: 480px;
 				padding: 3rem 2rem;
 			}
+			.logo {
+				width: 72px;
+				height: 72px;
+				border-radius: 18px;
+				margin-bottom: 1rem;
+			}
+			.badge {
+				font-size: 0.6875rem;
+				font-weight: 500;
+				color: #52525b;
+				letter-spacing: 0.05em;
+				text-transform: uppercase;
+				margin-bottom: 1.5rem;
+			}
 			h1 {
-				font-size: 1.25rem;
+				font-size: 1.35rem;
 				font-weight: 600;
 				margin-bottom: 0.5rem;
 			}
-			p {
+			.sub {
 				font-size: 0.875rem;
-				color: #a3a3a3;
+				color: #a1a1aa;
-				line-height: 1.6;
+				line-height: 1.7;
 			}
 			.spinner {
 				width: 32px;
 				height: 32px;
-				border: 3px solid #333;
+				border: 3px solid #27272a;
 				border-top-color: #fff;
 				border-radius: 50%;
 				animation: spin 0.8s linear infinite;
@@ -58,72 +73,165 @@
 			a:hover {
 				text-decoration: underline;
 			}
+
 			.install {
 				display: none;
 			}
 			.install.show {
 				display: block;
 			}
-			.btn {
+
-				display: inline-block;
+			.tips {
-				margin-top: 1rem;
+				margin-top: 1.75rem;
-				padding: 0.5rem 1.25rem;
+				text-align: left;
+				background: #18181b;
+				border: 1px solid #27272a;
+				border-radius: 12px;
+				padding: 1.25rem 1.5rem;
+			}
+			.tips li {
+				font-size: 0.8125rem;
+				color: #a1a1aa;
+				line-height: 1.7;
+				margin-left: 1rem;
+			}
+			.tips li + li {
+				margin-top: 0.35rem;
+			}
+
+			.store-btn {
+				display: inline-flex;
+				align-items: center;
+				gap: 0.625rem;
+				margin-top: 1.5rem;
+				padding: 0.625rem 1.5rem;
 				background: #2563eb;
 				color: #fff;
-				border-radius: 0.5rem;
+				border-radius: 10px;
 				font-size: 0.875rem;
 				font-weight: 500;
+				transition: background 0.15s;
 			}
-			.btn:hover {
+			.store-btn:hover {
 				background: #1d4ed8;
 				text-decoration: none;
 			}
+			.store-btn img {
+				width: 20px;
+				height: 20px;
+			}
+
+			.links {
+				margin-top: 1.75rem;
+				display: flex;
+				justify-content: center;
+				gap: 1.5rem;
+				font-size: 0.8125rem;
+			}
+			.links a {
+				color: #71717a;
+				transition: color 0.15s;
+			}
+			.links a:hover {
+				color: #a1a1aa;
+				text-decoration: none;
+			}
 		</style>
 	</head>
 	<body>
 		<div class="card">
+			<img
+				class="logo"
+				src="https://img.alicdn.com/imgextra/i3/O1CN01JPT4Fj1FJTfmHfNxO_!!6000000000466-49-tps-512-512.webp"
+				alt="Page Agent"
+			/>
+			<div class="badge">Page Agent MCP Launcher</div>
+
 			<div id="connecting">
 				<div class="spinner"></div>
-				<h1>Connecting to Page Agent</h1>
+				<h1 data-i18n="connecting_title">Connecting to Page Agent</h1>
-				<p>Opening the hub in your browser...</p>
+				<p class="sub" data-i18n="connecting_sub">Opening the hub in your browser…</p>
 			</div>
+
 			<div id="install" class="install">
-				<h1>Extension Not Found</h1>
+				<h1 data-i18n="install_title">Extension Required</h1>
-				<p>The Page Agent browser extension is required.<br />Install it and try again.</p>
+				<p class="sub" data-i18n="install_sub">
-				<a class="btn" href="__STORE_URL__" target="_blank">Install Extension</a>
+					Page Agent requires the latest browser extension to work.
-				<p style="margin-top: 1.5rem; font-size: 0.75rem">
-					After installing, restart the MCP server or refresh this page.
 				</p>
+
+				<a class="store-btn" href="__STORE_URL__" target="_blank">
+					<img
+						src="https://img.alicdn.com/imgextra/i3/O1CN01JpW0Vo1sR3FpiZKFM_!!6000000005762-55-tps-192-192.svg"
+						alt=""
+					/>
+					<span data-i18n="install_btn">Install from Chrome Web Store</span>
+				</a>
+
+				<ul class="tips">
+					<li data-i18n="tip_outdated">
+						If the extension is outdated, please update it to the latest version.
+					</li>
+					<li data-i18n="tip_other_browser">
+						If the extension is not installed in this browser, open this page from the
+						browser that has it installed.
+					</li>
+					<li data-i18n="tip_refresh">Refresh this page after installing or updating.</li>
+				</ul>
+			</div>
+
+			<div class="links">
+				<a href="https://alibaba.github.io/page-agent/docs/introduction/overview" target="_blank" data-i18n="link_docs">Docs</a>
+				<a href="https://github.com/alibaba/page-agent/issues" target="_blank" data-i18n="link_issues">Report an Issue</a>
 			</div>
 		</div>
-		<script>
-			;(function () {
-				var EXT_ID = '__EXT_ID__'
-				var wsPort = __WS_PORT__
 
-				function showInstall() {
+		<script>
+			{
+				const EXT_ID = '__EXT_ID__'
+				const wsPort = __WS_PORT__
+
+				const zh = {
+					connecting_title: '正在连接 Page Agent',
+					connecting_sub: '正在浏览器中打开 Hub…',
+					install_title: '需要安装浏览器插件',
+					install_sub: 'Page Agent 需要安装最新版浏览器插件才能运行。',
+					install_btn: '从 Chrome 应用商店安装',
+					tip_outdated: '如果插件版本过旧，请更新到最新版本。',
+					tip_other_browser:
+						'如果该浏览器中未安装插件，请从装有插件的浏览器打开此页面。',
+					tip_refresh: '安装或更新后，请刷新此页面。',
+					link_docs: '文档',
+					link_issues: '问题反馈',
+				}
+
+				if (/^zh\b/i.test(navigator.language)) {
+					document.querySelectorAll('[data-i18n]').forEach((el) => {
+						const key = el.getAttribute('data-i18n')
+						if (zh[key]) el.textContent = zh[key]
+					})
+				}
+
+				const showInstall = () => {
 					document.getElementById('connecting').style.display = 'none'
 					document.getElementById('install').classList.add('show')
 				}
 
 				try {
-					if (typeof chrome === 'undefined' || !chrome.runtime || !chrome.runtime.sendMessage) {
+					if (!globalThis.chrome?.runtime?.sendMessage) {
 						showInstall()
-						return
+					} else {
-					}
+						chrome.runtime.sendMessage(
-					chrome.runtime.sendMessage(
+							EXT_ID,
-						EXT_ID,
+							{ type: 'OPEN_HUB', wsPort },
-						{ type: 'OPEN_HUB', wsPort: wsPort },
+							(response) => {
-						function (response) {
+								if (chrome.runtime.lastError || !response?.ok) showInstall()
-							if (chrome.runtime.lastError || !response || !response.ok) {
-								showInstall()
 							}
-						}
+						)
-					)
+					}
-				} catch (e) {
+				} catch {
 					showInstall()
 				}
-			})()
+			}
 		</script>
 	</body>
 </html>

packages/page-agent/package.json

@@ -1,7 +1,7 @@
 {
     "name": "page-agent",
     "private": false,
-    "version": "1.5.9",
+    "version": "1.6.1",
     "type": "module",
     "main": "./dist/esm/page-agent.js",
     "module": "./dist/esm/page-agent.js",
@@ -44,10 +44,10 @@
         "postpublish": "node -e \"['README.md','LICENSE'].forEach(f=>{try{require('fs').unlinkSync(f)}catch{}})\""
     },
     "dependencies": {
-        "@page-agent/core": "1.5.9",
+        "@page-agent/core": "1.6.1",
-        "@page-agent/llms": "1.5.9",
+        "@page-agent/llms": "1.6.1",
-        "@page-agent/page-controller": "1.5.9",
+        "@page-agent/page-controller": "1.6.1",
-        "@page-agent/ui": "1.5.9",
+        "@page-agent/ui": "1.6.1",
         "chalk": "^5.6.2"
     },
     "peerDependencies": {

packages/page-controller/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@page-agent/page-controller",
-    "version": "1.5.9",
+    "version": "1.6.1",
     "type": "module",
     "main": "./dist/lib/page-controller.js",
     "module": "./dist/lib/page-controller.js",

packages/page-controller/src/PageController.ts

@@ -18,6 +18,7 @@ import * as dom from './dom'
 import type { FlatDomTree, InteractiveElementDomNode } from './dom/dom_tree/type'
 import { getPageInfo } from './dom/getPageInfo'
 import { patchReact } from './patches/react'
+import { isAnchorElement } from './utils'
 
 /**
  * Configuration for PageController
@@ -243,7 +244,7 @@ export class PageController extends EventTarget {
 			await clickElement(element)
 
 			// Handle links that open in new tabs
-			if (element instanceof HTMLAnchorElement && element.target === '_blank') {
+			if (isAnchorElement(element) && element.target === '_blank') {
 				return {
 					success: true,
 					message: `✅ Clicked element (${elemText ?? index}). ⚠️ Link opened in a new tab.`,
@@ -423,3 +424,5 @@ export class PageController extends EventTarget {
 		this.mask = null
 	}
 }
+
+export * from './actions'

packages/page-controller/src/actions.ts

@@ -3,27 +3,19 @@
  * All rights reserved.
  */
 import type { InteractiveElementDomNode } from './dom/dom_tree/type'
-
+import {
-// ======= general utils =======
+	getNativeValueSetter,
-
+	isHTMLElement,
-async function waitFor(seconds: number): Promise<void> {
+	isInputElement,
-	await new Promise((resolve) => setTimeout(resolve, seconds * 1000))
+	isSelectElement,
-}
+	isTextAreaElement,
-
+	movePointerToElement,
-// ======= dom utils =======
+	waitFor,
-
+} from './utils'
-export async function movePointerToElement(element: HTMLElement) {
-	const rect = element.getBoundingClientRect()
-	const x = rect.left + rect.width / 2
-	const y = rect.top + rect.height / 2
-
-	window.dispatchEvent(new CustomEvent('PageAgent::MovePointerTo', { detail: { x, y } }))
-
-	await waitFor(0.3)
-}
 
 /**
  * Get the HTMLElement by index from a selectorMap.
+ * @private Internal method, subject to change at any time.
  */
 export function getElementByIndex(
 	selectorMap: Map<number, InteractiveElementDomNode>,
@@ -39,7 +31,7 @@ export function getElementByIndex(
 		throw new Error(`Element at index ${index} does not have a reference`)
 	}
 
-	if (!(element instanceof HTMLElement)) {
+	if (!isHTMLElement(element)) {
 		throw new Error(`Element at index ${index} is not an HTMLElement`)
 	}
 
@@ -54,20 +46,30 @@ function blurLastClickedElement() {
 		lastClickedElement.dispatchEvent(
 			new MouseEvent('mouseout', { bubbles: true, cancelable: true })
 		)
+		lastClickedElement.dispatchEvent(
+			new MouseEvent('mouseleave', { bubbles: false, cancelable: true })
+		)
 		lastClickedElement = null
 	}
 }
 
 /**
  * Simulate a click on the element
+ * @private Internal method, subject to change at any time.
  */
 export async function clickElement(element: HTMLElement) {
 	blurLastClickedElement()
 
 	lastClickedElement = element
+
 	await scrollIntoViewIfNeeded(element)
+	// Scroll the iframe element itself into view if needed
+	const frame = element.ownerDocument.defaultView?.frameElement
+	if (frame) await scrollIntoViewIfNeeded(frame)
+
 	await movePointerToElement(element)
 	window.dispatchEvent(new CustomEvent('PageAgent::ClickPointer'))
+
 	await waitFor(0.1)
 
 	// hover it
@@ -89,25 +91,12 @@ export async function clickElement(element: HTMLElement) {
 	await waitFor(0.2) // Wait to ensure click event processing completes
 }
 
-// eslint-disable-next-line @typescript-eslint/unbound-method
+/**
-const nativeInputValueSetter = Object.getOwnPropertyDescriptor(
+ * @private Internal method, subject to change at any time.
-	window.HTMLInputElement.prototype,
+ */
-	'value'
-)!.set!
-
-// eslint-disable-next-line @typescript-eslint/unbound-method
-const nativeTextAreaValueSetter = Object.getOwnPropertyDescriptor(
-	window.HTMLTextAreaElement.prototype,
-	'value'
-)!.set!
-
 export async function inputTextElement(element: HTMLElement, text: string) {
 	const isContentEditable = element.isContentEditable
-	if (
+	if (!isInputElement(element) && !isTextAreaElement(element) && !isContentEditable) {
-		!(element instanceof HTMLInputElement) &&
-		!(element instanceof HTMLTextAreaElement) &&
-		!isContentEditable
-	) {
 		throw new Error('Element is not an input, textarea, or contenteditable')
 	}
 
@@ -119,9 +108,12 @@ export async function inputTextElement(element: HTMLElement, text: string) {
 		// - Monaco/CodeMirror: Require direct JS instance access. No universal way to obtain.
 		// - Draft.js: Not responsive to synthetic/execCommand/Range/DataTransfer. Unmaintained.
 		//
+		// Strategy: Try Plan A (synthetic events) first, then verify and fall back
+		// to Plan B (execCommand) if the text wasn't actually inserted.
+		//
 		// Plan A: Dispatch synthetic events
-		// Works: LinkedIn, React contenteditable, Quill.
+		// Works: React contenteditable, Quill.
-		// Fails: Slate.js
+		// Fails: Slate.js, some contenteditable editors that ignore synthetic events.
 		// Sequence: beforeinput -> mutation -> input -> change -> blur
 
 		// Dispatch beforeinput + mutation + input for clearing
@@ -164,22 +156,37 @@ export async function inputTextElement(element: HTMLElement, text: string) {
 			)
 		}
 
+		// Verify Plan A worked by checking if the text was actually inserted
+		const planASucceeded = element.innerText.trim() === text.trim()
+
+		if (!planASucceeded) {
+			// Plan B: execCommand fallback (deprecated but widely supported)
+			// Works: Quill, Slate.js, react contenteditable components.
+			// This approach integrates with the browser's undo stack and is handled
+			// natively by most rich-text editors.
+			element.focus()
+
+			// Select all existing content and delete it
+			const doc = element.ownerDocument
+			const selection = (doc.defaultView || window).getSelection()
+			const range = doc.createRange()
+			range.selectNodeContents(element)
+			selection?.removeAllRanges()
+			selection?.addRange(range)
+
+			// eslint-disable-next-line @typescript-eslint/no-deprecated
+			doc.execCommand('delete', false)
+			// eslint-disable-next-line @typescript-eslint/no-deprecated
+			doc.execCommand('insertText', false, text)
+		}
+
 		// Dispatch change event (for good measure)
 		element.dispatchEvent(new Event('change', { bubbles: true }))
 
 		// Trigger blur for validation
 		element.blur()
-
-		// Plan B: execCommand (deprecated but works better for some editors)
-		// Works: LinkedIn, Quill, Slate.js, react contenteditable components
-		//
-		// document.execCommand('selectAll')
-		// document.execCommand('delete')
-		// document.execCommand('insertText', false, text)
-	} else if (element instanceof HTMLTextAreaElement) {
-		nativeTextAreaValueSetter.call(element, text)
 	} else {
-		nativeInputValueSetter.call(element, text)
+		getNativeValueSetter(element as HTMLInputElement | HTMLTextAreaElement).call(element, text)
 	}
 
 	// Only dispatch shared input event for non-contenteditable (contenteditable has its own)
@@ -194,9 +201,10 @@ export async function inputTextElement(element: HTMLElement, text: string) {
 
 /**
  * @todo browser-use version is very complex and supports menu tags, need to follow up
+ * @private Internal method, subject to change at any time.
  */
 export async function selectOptionElement(selectElement: HTMLSelectElement, optionText: string) {
-	if (!(selectElement instanceof HTMLSelectElement)) {
+	if (!isSelectElement(selectElement)) {
 		throw new Error('Element is not a select element')
 	}
 
@@ -213,11 +221,14 @@ export async function selectOptionElement(selectElement: HTMLSelectElement, opti
 	await waitFor(0.1) // Wait to ensure change event processing completes
 }
 
-interface ScrollableElement extends HTMLElement {
+interface ScrollableElement extends Element {
 	scrollIntoViewIfNeeded?: (centerIfNeeded?: boolean) => void
 }
 
-export async function scrollIntoViewIfNeeded(element: HTMLElement) {
+/**
+ * @private Internal method, subject to change at any time.
+ */
+export async function scrollIntoViewIfNeeded(element: Element) {
 	const el = element as ScrollableElement
 	if (typeof el.scrollIntoViewIfNeeded === 'function') {
 		el.scrollIntoViewIfNeeded()
@@ -229,6 +240,9 @@ export async function scrollIntoViewIfNeeded(element: HTMLElement) {
 	}
 }
 
+/**
+ * @private Internal method, subject to change at any time.
+ */
 export async function scrollVertically(
 	down: boolean,
 	scroll_amount: number,
@@ -357,6 +371,9 @@ export async function scrollVertically(
 	}
 }
 
+/**
+ * @private Internal method, subject to change at any time.
+ */
 export async function scrollHorizontally(
 	right: boolean,
 	scroll_amount: number,

packages/page-controller/src/utils/index.ts

@@ -0,0 +1,62 @@
+// ======= type guards =======
+// @note instanceof fails for elements inside iframes
+
+export function isHTMLElement(el: unknown): el is HTMLElement {
+	// @todo either specify to HTMLElement or allow Element here.
+	return !!el && (el as Node).nodeType === 1
+}
+
+export function isInputElement(el: Element): el is HTMLInputElement {
+	return el?.nodeType === 1 && el.tagName === 'INPUT'
+}
+
+export function isTextAreaElement(el: Element): el is HTMLTextAreaElement {
+	return el?.nodeType === 1 && el.tagName === 'TEXTAREA'
+}
+
+export function isSelectElement(el: Element): el is HTMLSelectElement {
+	return el?.nodeType === 1 && el.tagName === 'SELECT'
+}
+
+export function isAnchorElement(el: Element): el is HTMLAnchorElement {
+	return el?.nodeType === 1 && el.tagName === 'A'
+}
+
+// ======= iframe helpers =======
+
+/** Iframe offset for translating element coordinates to top-frame viewport. */
+export function getIframeOffset(element: HTMLElement): { x: number; y: number } {
+	const frame = element.ownerDocument.defaultView?.frameElement as HTMLElement | null
+	if (!frame) return { x: 0, y: 0 }
+	const rect = frame.getBoundingClientRect()
+	return { x: rect.left, y: rect.top }
+}
+
+/**
+ * Get native value setter from the element's own prototype (iframe-safe).
+ * @note for React
+ */
+export function getNativeValueSetter(element: HTMLInputElement | HTMLTextAreaElement) {
+	// eslint-disable-next-line @typescript-eslint/unbound-method
+	return Object.getOwnPropertyDescriptor(Object.getPrototypeOf(element) as object, 'value')!
+		.set as (v: string) => void
+}
+
+// ======= general utils =======
+
+export async function waitFor(seconds: number): Promise<void> {
+	await new Promise((resolve) => setTimeout(resolve, seconds * 1000))
+}
+
+// ======= dom utils =======
+
+export async function movePointerToElement(element: HTMLElement) {
+	const rect = element.getBoundingClientRect()
+	const offset = getIframeOffset(element)
+	const x = rect.left + rect.width / 2 + offset.x
+	const y = rect.top + rect.height / 2 + offset.y
+
+	window.dispatchEvent(new CustomEvent('PageAgent::MovePointerTo', { detail: { x, y } }))
+
+	await waitFor(0.3)
+}

packages/ui/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@page-agent/ui",
-    "version": "1.5.9",
+    "version": "1.6.1",
     "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": "1.5.9",
+    "version": "1.6.1",
     "type": "module",
     "scripts": {
         "dev": "vite --host 0.0.0.0",

packages/website/src/components/LanguageSwitcher.tsx

@@ -8,8 +8,8 @@ export default function LanguageSwitcher() {
 	const dropdownRef = useRef<HTMLDivElement>(null)
 
 	const languages = [
-		{ code: 'zh-CN' as const, label: '中文' },
 		{ code: 'en-US' as const, label: 'English' },
+		{ code: 'zh-CN' as const, label: '中文' },
 	]
 
 	const currentLanguage = languages.find((lang) => lang.code === language) || languages[0]

packages/website/src/constants.ts

@@ -1,10 +1,10 @@
 // Demo build (auto-init with demo LLM, for quick testing)
 export const CDN_DEMO_URL =
-	'https://cdn.jsdelivr.net/npm/page-agent@1.5.9/dist/iife/page-agent.demo.js'
+	'https://cdn.jsdelivr.net/npm/page-agent@1.6.1/dist/iife/page-agent.demo.js'
 export const CDN_DEMO_CN_URL =
-	'https://registry.npmmirror.com/page-agent/1.5.9/files/dist/iife/page-agent.demo.js'
+	'https://registry.npmmirror.com/page-agent/1.6.1/files/dist/iife/page-agent.demo.js'
 
 // Demo LLM for website testing (homepage quick trial uses flash)
 export const DEMO_MODEL = 'qwen3.5-flash'
 export const DEMO_BASE_URL = 'https://page-ag-testing-ohftxirgbn.cn-shanghai.fcapp.run'
-export const DEMO_API_KEY = 'NA'
+// export const DEMO_API_KEY = ''

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

@@ -45,6 +45,7 @@ export default function DocsLayout({ children }: DocsLayoutProps) {
 				{ title: isZh ? '知识注入' : 'Instructions', path: '/features/custom-instructions' },
 				{ title: isZh ? '数据脱敏' : 'Data Masking', path: '/features/data-masking' },
 				{ title: isZh ? 'Chrome 扩展' : 'Chrome Extension', path: '/features/chrome-extension' },
+				{ title: 'MCP Server (Beta)', path: '/features/mcp-server' },
 				{
 					title: isZh ? '接入第三方 Agent' : 'Third-party Agent',
 					path: '/features/third-party-agent',

packages/website/src/pages/docs/advanced/page-agent-core/page.tsx

@@ -129,12 +129,6 @@ const result = await agent.execute('Fill in the form with test data')`}
 								? 'LLM API 的基础 URL（如 https://api.openai.com/v1）'
 								: 'Base URL of the LLM API (e.g., https://api.openai.com/v1)',
 						},
-						{
-							name: 'apiKey',
-							type: 'string',
-							required: true,
-							description: isZh ? 'API 密钥' : 'API key for authentication',
-						},
 						{
 							name: 'model',
 							type: 'string',
@@ -143,6 +137,12 @@ const result = await agent.execute('Fill in the form with test data')`}
 								? '模型名称（如 gpt-5.2, anthropic/claude-4.5-haiku）'
 								: 'Model name (e.g., gpt-5.2, anthropic/claude-4.5-haiku)',
 						},
+						{
+							name: 'apiKey',
+							type: 'string',
+							required: false,
+							description: 'LLM AK',
+						},
 						{
 							name: 'temperature',
 							type: 'number',
@@ -156,6 +156,14 @@ const result = await agent.execute('Fill in the form with test data')`}
 							defaultValue: '3',
 							description: isZh ? 'API 调用失败时的最大重试次数' : 'Maximum retries on API failure',
 						},
+						{
+							name: 'disableNamedToolChoice',
+							type: 'boolean',
+							defaultValue: 'false',
+							description: isZh
+								? '禁用命名 tool_choice，始终使用 "required" 字符串。适用于不支持 tool_choice 对象格式的 LLM 服务。'
+								: 'Disable named tool_choice, always use "required" string. For LLM services that don\'t support the object format of tool_choice.',
+						},
 						{
 							name: 'customFetch',
 							type: 'typeof fetch',

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

@@ -187,39 +187,7 @@ localStorage.setItem('PageAgentExtUserAuthToken', '<your-token-from-extension>')
 					</p>
 
 					<CodeEditor
-						code={
+						code={`import type {
-							isZh
-								? `import type {
-	AgentActivity,
-	AgentStatus,
-	ExecutionResult,
-	HistoricalEvent
-} from '@page-agent/core'
-
-interface ExecuteConfig {
-	baseURL: string   // LLM API 端点
-	apiKey: string    // API 密钥
-	model: string     // 模型名称
-
-	includeInitialTab?: boolean
-	onStatusChange?: (status: AgentStatus) => void
-	onActivity?: (activity: AgentActivity) => void
-	onHistoryUpdate?: (history: HistoricalEvent[]) => void
-}
-
-type Execute = (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
-
-declare global {
-	interface Window {
-		PAGE_AGENT_EXT_VERSION?: string
-		PAGE_AGENT_EXT?: {
-			version: string
-			execute: Execute
-			stop: () => void
-		}
-	}
-}`
-								: `import type {
 	AgentActivity,
 	AgentStatus,
 	ExecutionResult,
@@ -228,8 +196,8 @@ declare global {
 
 interface ExecuteConfig {
 	baseURL: string   // LLM API endpoint
-	apiKey: string    // API key
 	model: string     // Model name
+	apiKey?: string   // LLM AK
 
 	includeInitialTab?: boolean
 	onStatusChange?: (status: AgentStatus) => void
@@ -248,8 +216,7 @@ declare global {
 			stop: () => void
 		}
 	}
-}`
+}`}
-						}
 						language="typescript"
 					/>
 

packages/website/src/pages/docs/features/mcp-server/page.tsx

@@ -0,0 +1,70 @@
+import BetaNotice from '@/components/BetaNotice'
+import CodeEditor from '@/components/CodeEditor'
+import { Heading } from '@/components/Heading'
+
+export default function McpServerPage() {
+	return (
+		<div>
+			<h1 className="text-4xl font-bold mb-6">MCP Server (Beta)</h1>
+			<BetaNotice />
+			<p className="text-xl text-gray-600 dark:text-gray-300 mb-8 leading-relaxed">
+				Use the MCP server to let your local agent send natural-language browser tasks to Page Agent
+				Ext.
+			</p>
+
+			<section className="mb-10">
+				<Heading id="quick-start" className="text-2xl font-bold mb-4">
+					How to use
+				</Heading>
+				<div className="space-y-4">
+					<div className="p-4 bg-blue-50 dark:bg-blue-950/20 rounded-lg border border-blue-200 dark:border-blue-800">
+						<p className="text-sm text-blue-900 dark:text-blue-200 leading-7">
+							1. Install Page Agent Ext in Chrome.
+							<br />
+							2. Add the MCP server to your local agent client.
+							<br />
+							3. Start the client and approve the Hub connection in the browser when prompted.
+							<br />
+							4. Ask your agent to do something in the browser. The client will call execute_task
+							for you.
+						</p>
+					</div>
+
+					<CodeEditor
+						code={`{
+  "mcpServers": {
+    "page-agent": {
+      "command": "npx",
+      "args": ["-y", "@page-agent/mcp"],
+      "env": {
+        "LLM_BASE_URL": "https://api.openai.com/v1",
+        "LLM_API_KEY": "sk-xxx",
+        "LLM_MODEL_NAME": "gpt-5.2"
+      }
+    }
+  }
+}`}
+						language="json"
+					/>
+				</div>
+			</section>
+
+			<section className="mb-10">
+				<Heading id="the-hub" className="text-2xl font-bold mb-4">
+					The Hub
+				</Heading>
+
+				<p className="text-gray-700 dark:text-gray-300 leading-relaxed">
+					The Hub is the control center for communication between Page Agent Ext and external
+					callers.
+				</p>
+				<p className="text-gray-700 dark:text-gray-300 leading-relaxed">
+					When the MCP server starts, it opens a local launcher page. The launcher asks the
+					extension to open the Hub tab, and the Hub receives tasks from your local agent. MCP uses
+					this path, but the Hub itself is the extension's general external communication entry
+					point.
+				</p>
+			</section>
+		</div>
+	)
+}

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

@@ -33,8 +33,8 @@ const MODEL_GROUPS: Record<string, string[]> = {
 		'claude-haiku-4.5',
 		'claude-sonnet-3.5',
 	],
+	MiniMax: ['MiniMax-M2.7', 'MiniMax-M2.7-highspeed', 'MiniMax-M2.5', 'MiniMax-M2.5-highspeed'],
 	xAI: ['grok-4.1-fast', 'grok-4', 'grok-code-fast'],
-	MiniMax: ['MiniMax-M2.5', 'MiniMax-M2.5-highspeed'],
 	MoonshotAI: ['kimi-k2.5'],
 	'Z.AI': ['glm-5', 'glm-4.7'],
 }
@@ -126,13 +126,12 @@ const pageAgent = new PageAgent({
 const pageAgent = new PageAgent({
   baseURL: 'https://api.minimax.io/v1',
   apiKey: 'your-minimax-api-key',
-  model: 'MiniMax-M2.5'
+  model: 'MiniMax-M2.7'
 });
 
-// Self-hosted models (e.g., Ollama)
+// Self-hosted models (e.g., Ollama) — no apiKey needed
 const pageAgent = new PageAgent({
   baseURL: 'http://localhost:11434/v1',
-  apiKey: 'NA',
   model: 'qwen3:14b'
 });
 
@@ -280,7 +279,6 @@ LLM_MODEL_NAME="qwen3:14b"`}
 				<CodeEditor
 					code={`const agent = new PageAgent({
   baseURL: '/api/llm-proxy',
-  apiKey: 'NA',
   model: 'gpt-5.1',
   customFetch: (url, init) =>
     fetch(url, { ...init, credentials: 'include' }),

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

@@ -13,6 +13,7 @@ import ChromeExtension from './features/chrome-extension/page'
 import Instructions from './features/custom-instructions/page'
 import CustomTools from './features/custom-tools/page'
 import DataMasking from './features/data-masking/page'
+import McpServerPage from './features/mcp-server/page'
 import Models from './features/models/page'
 import ThirdPartyAgent from './features/third-party-agent/page'
 import Limitations from './introduction/limitations/page'
@@ -80,6 +81,11 @@ export default function DocsRouter() {
 					<ChromeExtension />
 				</DocsPage>
 			</Route>
+			<Route path="/features/mcp-server">
+				<DocsPage>
+					<McpServerPage />
+				</DocsPage>
+			</Route>
 			<Route path="/features/third-party-agent">
 				<DocsPage>
 					<ThirdPartyAgent />

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

@@ -97,6 +97,7 @@ export default function LimitationsPage() {
 									isZh ? '点击、文本输入、选择' : 'Click, text input, select',
 									isZh ? '页面滚动（垂直 / 水平）' : 'Scroll (vertical / horizontal)',
 									isZh ? '表单提交、焦点切换' : 'Form submit, focus',
+									isZh ? '同源 iframe（仅单层）' : 'Same-origin iframe (single level only)',
 									isZh ? '执行 JavaScript（可选）' : 'Execute JavaScript (opt-in)',
 								].map((text) => (
 									<li key={text} className="flex items-center text-gray-700 dark:text-gray-300">
@@ -115,6 +116,7 @@ export default function LimitationsPage() {
 									isZh ? '悬停、拖拽、右键菜单' : 'Hover, drag & drop, right-click',
 									isZh ? '键盘快捷键' : 'Keyboard shortcuts',
 									isZh ? '坐标定位操作' : 'Position-based control',
+									isZh ? '嵌套 iframe、跨域 iframe' : 'Nested iframes, cross-origin iframes',
 									isZh ? '绘图操作' : 'Drawing',
 									isZh
 										? 'Monaco、CodeMirror 等需要通过 JS 实例控制的编辑器'

packages/website/src/pages/home/HeroSection.tsx

@@ -10,7 +10,7 @@ import { Particles } from '../../components/ui/particles'
 import {
 	CDN_DEMO_CN_URL,
 	CDN_DEMO_URL,
-	DEMO_API_KEY,
+	// DEMO_API_KEY,
 	DEMO_BASE_URL,
 	DEMO_MODEL,
 } from '../../constants'
@@ -94,7 +94,7 @@ export default function HeroSection() {
 				apiKey:
 					import.meta.env.DEV && import.meta.env.LLM_API_KEY
 						? import.meta.env.LLM_API_KEY
-						: DEMO_API_KEY,
+						: undefined,
 			})
 		}
 
@@ -103,10 +103,7 @@ export default function HeroSection() {
 	}
 
 	return (
-		<section
+		<section className="relative px-6 pt-18 pb-14 lg:pb-20 lg:pt-24" aria-labelledby="hero-heading">
-			className="relative px-6 pt-24 py-20 pb-18 lg:py-22 lg:pt-28 overflow-hidden"
-			aria-labelledby="hero-heading"
-		>
 			<div className="max-w-7xl mx-auto text-center">
 				{/* Background Pattern + Particles */}
 				<div className="absolute inset-0 opacity-30" aria-hidden="true">
@@ -122,7 +119,7 @@ export default function HeroSection() {
 				/>
 
 				<div className="relative z-10">
-					<div className="inline-flex items-center px-4 py-2 mb-8 text-sm font-medium bg-white/90 dark:bg-gray-800/90 rounded-full shadow-lg border border-gray-200 dark:border-gray-700">
+					<div className="inline-flex items-center px-4 py-2 mb-4 text-sm font-medium bg-white/90 dark:bg-gray-800/90 rounded-full shadow-lg border border-gray-200 dark:border-gray-700">
 						<span
 							className="w-2 h-2 bg-blue-500 rounded-full mr-2 animate-pulse"
 							aria-hidden="true"
@@ -134,7 +131,7 @@ export default function HeroSection() {
 
 					<h1
 						id="hero-heading"
-						className="text-5xl lg:text-7xl font-bold mb-14 mt-8 bg-linear-to-r from-blue-600 to-purple-600 bg-clip-text text-transparent pb-1"
+						className="text-5xl lg:text-7xl font-bold mb-10 mt-8 bg-linear-to-r from-blue-600 to-purple-600 bg-clip-text text-transparent pb-1"
 					>
 						{isZh ? (
 							<>

packages/website/src/pages/home/OneMoreThingSection.tsx

@@ -58,6 +58,22 @@ export default function OneMoreThingSection() {
 					</Link>
 				</div>
 
+				<div className="mb-10 rounded-2xl border border-blue-200/70 dark:border-blue-800/70 bg-linear-to-r from-blue-50 to-white dark:from-blue-950/30 dark:to-gray-900 px-5 py-4 max-w-3xl mx-auto text-left sm:text-center">
+					<p className="text-sm text-gray-700 dark:text-gray-300 leading-7">
+						{isZh
+							? '从 Claude Desktop、Copilot 或其他本地 Agent 直接发起浏览器任务？'
+							: 'Using Claude Desktop, Copilot, or another local agent? Connect it to the extension with the MCP server.'}
+					</p>
+					<p>
+						<Link
+							href="/docs/features/mcp-server"
+							className="font-medium text-blue-700 dark:text-blue-300 underline underline-offset-4"
+						>
+							{isZh ? '查看 MCP 文档' : 'Read the MCP docs'}
+						</Link>
+					</p>
+				</div>
+
 				<div className="grid sm:grid-cols-3 gap-5 text-left max-w-3xl mx-auto">
 					{[
 						{
@@ -67,16 +83,16 @@ export default function OneMoreThingSection() {
 								: 'Run tasks across multiple pages and tabs without being limited to a single page context',
 						},
 						{
-							title: isZh ? '页面内发起控制' : 'Control from Your Page',
+							title: isZh ? '从页面发起控制' : 'Control from a WebPage',
 							desc: isZh
 								? '在页面 JS 中发起任务，驱动整个浏览器完成跨标签操作'
-								: 'Trigger tasks from page JS to drive the entire browser across tabs',
+								: 'Trigger tasks from in-page JS to drive the entire browser across tabs',
 						},
 						{
-							title: isZh ? '外部发起任务' : 'External Triggers',
+							title: isZh ? '外部发起任务' : 'External Caller',
 							desc: isZh
 								? '页面 JS、本地 Agent 或云端 Agent 均可通过扩展发起任务'
-								: 'Page JS, local agents, or cloud agents can trigger tasks through the extension',
+								: 'Local agents and cloud agents can control user browser through the extension',
 						},
 					].map((item) => (
 						<MagicCard

packages/website/vite.config.js

@@ -27,6 +27,7 @@ const SPA_ROUTES = [
 	'docs/features/custom-instructions',
 	'docs/features/models',
 	'docs/features/chrome-extension',
+	'docs/features/mcp-server',
 	'docs/features/third-party-agent',
 	'docs/advanced/page-agent',
 	'docs/advanced/page-agent-core',