Merge branch 'main' into fix/scroll-direction-pixels

2026-04-02 18:31:56 +08:00
parent 005bc8ab44 2bdb3be81c
commit 8159aa58a6
47 changed files with 978 additions and 680 deletions
--- a/packages/core/package.json
+++ b/packages/core/package.json
@@ -1,7 +1,7 @@
 {
    "name": "@page-agent/core",
    "private": false,
-    "version": "1.6.0",
+    "version": "1.7.0",
    "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": "1.6.0",
-        "@page-agent/page-controller": "1.6.0"
+        "@page-agent/llms": "1.7.0",
+        "@page-agent/page-controller": "1.7.0"
    },
    "peerDependencies": {
        "zod": "^3.25.0 || ^4.0.0"
--- a/packages/extension/docs/extension_api.md
+++ b/packages/extension/docs/extension_api.md
@@ -118,9 +118,18 @@ export interface ExecuteConfig {
  model: string
  apiKey?: string

+  // Global system-level instructions for the agent.
+  // Equivalent to AgentConfig.instructions.system.
+  systemInstruction?: string
+
  // Include the initial tab where page JS starts. Default: true.
  includeInitialTab?: boolean

+  // Control all unpinned tabs in the window instead of only the tab group.
+  // When enabled, agent sees and can switch to every non-pinned tab.
+  // Default: false. Experimental.
+  experimentalIncludeAllTabs?: boolean
+
  onStatusChange?: (status: AgentStatus) => void
  onActivity?: (activity: AgentActivity) => void
  onHistoryUpdate?: (history: HistoricalEvent[]) => void
@@ -207,7 +216,11 @@ interface ExecuteConfig {
  baseURL: string
  model: string
  apiKey?: string
+
+  systemInstruction?: string
+
  includeInitialTab?: boolean
+  experimentalIncludeAllTabs?: boolean
  onStatusChange?: (status: AgentStatus) => void
  onActivity?: (activity: AgentActivity) => void
  onHistoryUpdate?: (history: HistoricalEvent[]) => void
--- a/packages/extension/package.json
+++ b/packages/extension/package.json
@@ -1,7 +1,7 @@
 {
    "name": "@page-agent/ext",
    "private": true,
-    "version": "1.6.0",
+    "version": "1.7.0",
    "type": "module",
    "scripts": {
        "dev": "wxt",
@@ -16,31 +16,31 @@
        "@radix-ui/react-separator": "^1.1.8",
        "@radix-ui/react-slot": "^1.2.4",
        "@radix-ui/react-switch": "^1.2.6",
-        "@types/chrome": "^0.1.37",
+        "@types/chrome": "^0.1.38",
        "@types/react": "^19.2.14",
        "@types/react-dom": "^19.2.1",
        "@wxt-dev/module-react": "^1.2.2",
        "class-variance-authority": "^0.7.1",
        "clsx": "^2.1.1",
        "idb": "^8.0.3",
-        "lucide-react": "^0.577.0",
-        "motion": "^12.37.0",
+        "lucide-react": "^1.7.0",
+        "motion": "^12.38.0",
        "next-themes": "^0.4.6",
        "react": "^19.2.4",
        "react-dom": "^19.2.4",
        "rough-notation": "^0.5.1",
-        "simple-icons": "^16.12.0",
+        "simple-icons": "^16.14.0",
        "sonner": "^2.0.7",
        "tailwind-merge": "^3.5.0",
        "tailwindcss": "^4.1.14",
        "tw-animate-css": "^1.4.0",
-        "wxt": "^0.20.19"
+        "wxt": "^0.20.20"
    },
    "dependencies": {
-        "@page-agent/core": "1.6.0",
-        "@page-agent/llms": "1.6.0",
-        "@page-agent/page-controller": "1.6.0",
-        "@page-agent/ui": "1.6.0",
+        "@page-agent/core": "1.7.0",
+        "@page-agent/llms": "1.7.0",
+        "@page-agent/page-controller": "1.7.0",
+        "@page-agent/ui": "1.7.0",
        "ai-motion": "^0.4.8",
        "chalk": "^5.6.2"
    },
--- a/packages/extension/src/agent/MultiPageAgent.ts
+++ b/packages/extension/src/agent/MultiPageAgent.ts
@@ -11,13 +11,18 @@ function detectLanguage(): 'en-US' | 'zh-CN' {
 	return lang.startsWith('zh') ? 'zh-CN' : 'en-US'
 }

+interface MultiPageAgentConfig extends AgentConfig {
+	includeInitialTab?: boolean
+	experimentalIncludeAllTabs?: boolean
+}
+
 /**
 * MultiPageAgent
 * - use with extension
 * - can be used from a side panel or a content script
 */
 export class MultiPageAgent extends PageAgentCore {
-	constructor(config: AgentConfig & { includeInitialTab?: boolean }) {
+	constructor(config: MultiPageAgentConfig) {
 		// multi page controller
 		const tabsController = new TabsController()
 		const pageController = new RemotePageController(tabsController)
@@ -31,8 +36,8 @@ export class MultiPageAgent extends PageAgentCore {
 			`Default working language: **${targetLanguage}**`
 		)

-		// include initial tab for controlling
 		const includeInitialTab = config.includeInitialTab ?? true
+		const experimentalIncludeAllTabs = config.experimentalIncludeAllTabs ?? false

 		/**
 		 * When the agent is in side-panel and user closed the side-panel.
@@ -50,7 +55,7 @@ export class MultiPageAgent extends PageAgentCore {
 			customSystemPrompt: systemPrompt,

 			onBeforeTask: async (agent) => {
-				await tabsController.init(agent.task, includeInitialTab)
+				await tabsController.init(agent.task, { includeInitialTab, experimentalIncludeAllTabs })

 				heartBeatInterval = window.setInterval(() => {
 					chrome.storage.local.set({
--- a/packages/extension/src/agent/RemotePageController.background.ts
+++ b/packages/extension/src/agent/RemotePageController.background.ts
@@ -10,9 +10,7 @@ export function handlePageControlMessage(
 ): true | undefined {
 	const PREFIX = '[RemotePageController.background]'

-	function debug(...messages: any[]) {
-		console.debug(`\x1b[90m${PREFIX}\x1b[0m`, ...messages)
-	}
+	const debug = console.debug.bind(console, `\x1b[90m${PREFIX}\x1b[0m`)

 	const { action, payload, targetTabId } = message

--- a/packages/extension/src/agent/RemotePageController.ts
+++ b/packages/extension/src/agent/RemotePageController.ts
@@ -4,9 +4,7 @@ import type { TabsController } from './TabsController'

 const PREFIX = '[RemotePageController]'

-function debug(...messages: any[]) {
-	console.debug(`\x1b[90m${PREFIX}\x1b[0m`, ...messages)
-}
+const debug = console.debug.bind(console, `\x1b[90m${PREFIX}\x1b[0m`)

 function sendMessage(message: {
 	type: 'PAGE_CONTROL'
--- a/packages/extension/src/agent/TabsController.background.ts
+++ b/packages/extension/src/agent/TabsController.background.ts
@@ -5,9 +5,7 @@ import type { TabAction } from './TabsController'

 const PREFIX = '[TabsController.background]'

-function debug(...messages: any[]) {
-	console.debug(`\x1b[90m${PREFIX}\x1b[0m`, ...messages)
-}
+const debug = console.debug.bind(console, `\x1b[90m${PREFIX}\x1b[0m`)

 export function handleTabControlMessage(
 	message: { type: 'TAB_CONTROL'; action: TabAction; payload: any },
@@ -20,11 +18,10 @@ export function handleTabControlMessage(
 		case 'get_active_tab': {
 			debug('get_active_tab')
 			chrome.tabs
-				.query({ active: true, currentWindow: true })
+				.query({ active: true })
 				.then((tabs) => {
-					const tabId = tabs.length > 0 ? tabs[0].id || null : null
-					debug('get_active_tab: success', tabId)
-					sendResponse({ success: true, tabId })
+					debug('get_active_tab: success', tabs)
+					sendResponse({ success: true, tab: tabs[0] })
 				})
 				.catch((error) => {
 					sendResponse({ error: error instanceof Error ? error.message : String(error) })
@@ -63,7 +60,7 @@ export function handleTabControlMessage(
 		case 'create_tab_group': {
 			debug('create_tab_group', payload)
 			chrome.tabs
-				.group({ tabIds: payload.tabIds })
+				.group({ tabIds: payload.tabIds, createProperties: { windowId: payload.windowId } })
 				.then((groupId) => {
 					debug('create_tab_group: success', groupId)
 					sendResponse({ success: true, groupId })
@@ -114,47 +111,59 @@ export function handleTabControlMessage(
 			return true // async response
 		}

+		case 'get_window_tabs': {
+			debug('get_window_tabs', payload)
+			chrome.tabs
+				.query({ windowId: payload.windowId })
+				.then((tabs) => {
+					sendResponse({ success: true, tabs })
+				})
+				.catch((error) => {
+					sendResponse({ error: error instanceof Error ? error.message : String(error) })
+				})
+			return true
+		}
+
 		default:
 			sendResponse({ error: `Unknown action: ${action}` })
 			return
 	}
 }

-export function setupTabChangeEvents() {
-	console.log('[TabsController.background] setupTabChangeEvents')
+const tabEventPorts = new Set<chrome.runtime.Port>()
+
+function broadcastTabEvent(message: object) {
+	for (const port of tabEventPorts) {
+		port.postMessage(message)
+	}
+}
+
+/**
+ * Port-based tab events: agents connect via `chrome.runtime.connect({ name: 'tab-events' })`
+ * and receive tab change events through the port. Works for both extension pages and content scripts.
+ */
+export function setupTabEventsPort() {
+	chrome.runtime.onConnect.addListener((port) => {
+		if (port.name !== 'tab-events') return
+
+		debug('port connected', port.sender?.tab?.id ?? port.sender?.url)
+		tabEventPorts.add(port)
+
+		port.onDisconnect.addListener(() => {
+			debug('port disconnected')
+			tabEventPorts.delete(port)
+		})
+	})

 	chrome.tabs.onCreated.addListener((tab) => {
-		debug('onCreated', tab)
-		chrome.runtime
-			.sendMessage({ type: 'TAB_CHANGE', action: 'created', payload: { tab } })
-			.catch((error) => {
-				debug('onCreated error:', error)
-			})
+		broadcastTabEvent({ action: 'created', payload: { tab } })
 	})

 	chrome.tabs.onRemoved.addListener((tabId, removeInfo) => {
-		debug('onRemoved', tabId, removeInfo)
-		chrome.runtime
-			.sendMessage({
-				type: 'TAB_CHANGE',
-				action: 'removed',
-				payload: { tabId, removeInfo },
-			})
-			.catch((error) => {
-				debug('onRemoved error:', error)
-			})
+		broadcastTabEvent({ action: 'removed', payload: { tabId, removeInfo } })
 	})

 	chrome.tabs.onUpdated.addListener((tabId, changeInfo, tab) => {
-		debug('onUpdated', tabId, changeInfo)
-		chrome.runtime
-			.sendMessage({
-				type: 'TAB_CHANGE',
-				action: 'updated',
-				payload: { tabId, changeInfo, tab },
-			})
-			.catch((error) => {
-				debug('onUpdated error:', error)
-			})
+		broadcastTabEvent({ action: 'updated', payload: { tabId, changeInfo, tab } })
 	})
 }
--- a/packages/extension/src/agent/TabsController.ts
+++ b/packages/extension/src/agent/TabsController.ts
@@ -2,9 +2,7 @@ import { isContentScriptAllowed } from './RemotePageController'

 const PREFIX = '[TabsController]'

-function debug(...messages: any[]) {
-	console.debug(`\x1b[90m${PREFIX}\x1b[0m`, ...messages)
-}
+const debug = console.debug.bind(console, `\x1b[90m${PREFIX}\x1b[0m`)

 function sendMessage(message: {
 	type: 'TAB_CONTROL'
@@ -22,46 +20,91 @@ function sendMessage(message: {
 * - live in the agent env (extension page or content script)
 * - no chrome apis. call sw for tab operations
 */
-export class TabsController extends EventTarget {
+export class TabsController {
 	currentTabId: number | null = null

+	private disposed = false
+	private port: chrome.runtime.Port | null = null
+	private portRetries = 0
+
+	private windowId: number | null = null
 	private tabs: TabMeta[] = []
 	private initialTabId: number | null = null
 	private tabGroupId: number | null = null
+	private experimentalIncludeAllTabs = false
 	private task: string = ''

-	async init(task: string, includeInitialTab: boolean = true) {
-		debug('init', task, includeInitialTab)
+	async init(task: string, options: TabsInitOptions = {}) {
+		const { includeInitialTab = true, experimentalIncludeAllTabs = false } = options
+		debug('init', task, options)
+
+		if (this.disposed) {
+			throw new Error('TabsController already disposed')
+		}

-		this.task = task
-		this.tabs = []
 		this.currentTabId = null
+		this.disposed = false
+		this.port = null
+		this.portRetries = 0
+
+		this.windowId = null
+		this.tabs = []
 		this.tabGroupId = null
 		this.initialTabId = null
+		this.experimentalIncludeAllTabs = experimentalIncludeAllTabs
+		this.task = task

-		const result = await sendMessage({
+		const activeTabResult = await sendMessage({
 			type: 'TAB_CONTROL',
 			action: 'get_active_tab',
 		})

-		this.initialTabId = result.tabId
+		this.initialTabId = activeTabResult.tab?.id
+		this.windowId = activeTabResult.tab?.windowId

-		if (!this.initialTabId) {
-			throw new Error('Failed to get initial tab ID')
+		if (!this.initialTabId || !this.windowId) {
+			if (activeTabResult.error) {
+				throw new Error(activeTabResult.error)
+			} else {
+				throw new Error('Failed to get active tab')
+			}
 		}

-		if (includeInitialTab) {
+		this.connectTabEvents()
+
+		if (experimentalIncludeAllTabs) {
+			const allTabs = await sendMessage({
+				type: 'TAB_CONTROL',
+				action: 'get_window_tabs',
+				payload: { windowId: this.windowId },
+			})
+			for (const tab of allTabs.tabs as chrome.tabs.Tab[]) {
+				if (tab.id && !tab.pinned && isContentScriptAllowed(tab.url)) {
+					this.addTab({
+						id: tab.id,
+						isInitial: tab.id === this.initialTabId,
+						url: tab.url,
+						title: tab.title,
+						status: tab.status,
+					})
+				}
+			}
+			if (this.tabs.find((t) => t.id === this.initialTabId)) {
+				this.currentTabId = this.initialTabId
+				await this.createTabGroup([this.initialTabId])
+			}
+		} else if (includeInitialTab) {
 			const info = await sendMessage({
 				type: 'TAB_CONTROL',
 				action: 'get_tab_info',
 				payload: { tabId: this.initialTabId },
 			})

-			if (isContentScriptAllowed(info.url)) {
+			if (isContentScriptAllowed(info.url) && !info.pinned) {
 				this.currentTabId = this.initialTabId

-				this.tabs.push({
-					id: result.tabId,
+				this.addTab({
+					id: this.initialTabId,
 					isInitial: true,
 					url: info.url,
 					title: info.title,
@@ -73,52 +116,6 @@ export class TabsController extends EventTarget {
 		}

 		await this.updateCurrentTabId(this.currentTabId)
-
-		const tabChangeHandler = (message: any): void => {
-			if (message.type !== 'TAB_CHANGE') {
-				// throw new Error(`[TabsController]: Invalid message type: ${message.type}`)
-				return
-			}
-
-			if (message.action === 'created') {
-				const tab = message.payload.tab as chrome.tabs.Tab
-				if (tab.groupId === this.tabGroupId && tab.id != null) {
-					// Tab created in our controlled group
-					if (!this.tabs.find((t) => t.id === tab.id)) {
-						this.tabs.push({ id: tab.id, isInitial: false })
-					}
-					this.switchToTab(tab.id)
-				}
-			} else if (message.action === 'removed') {
-				const { tabId } = message.payload as { tabId: number }
-				const targetTab = this.tabs.find((t) => t.id === tabId)
-				if (targetTab) {
-					this.tabs = this.tabs.filter((t) => t.id !== tabId)
-					if (this.currentTabId === tabId) {
-						const newCurrentTab = this.tabs[this.tabs.length - 1] || null
-						if (newCurrentTab) {
-							this.switchToTab(newCurrentTab.id)
-						} else {
-							this.updateCurrentTabId(null)
-						}
-					}
-				}
-			} else if (message.action === 'updated') {
-				const { tabId, tab } = message.payload as { tabId: number; tab: chrome.tabs.Tab }
-				const targetTab = this.tabs.find((t) => t.id === tabId)
-				if (targetTab) {
-					targetTab.url = tab.url
-					targetTab.title = tab.title
-					targetTab.status = tab.status
-				}
-			}
-		}
-
-		chrome.runtime.onMessage.addListener(tabChangeHandler)
-
-		this.addEventListener('dispose', () => {
-			chrome.runtime.onMessage.removeListener(tabChangeHandler)
-		})
 	}

 	async openNewTab(url: string): Promise<string> {
@@ -136,7 +133,7 @@ export class TabsController extends EventTarget {

 		const tabId = result.tabId as number

-		this.tabs.push({
+		this.addTab({
 			id: tabId,
 			isInitial: false,
 		})
@@ -209,7 +206,7 @@ export class TabsController extends EventTarget {
 		const result = await sendMessage({
 			type: 'TAB_CONTROL',
 			action: 'create_tab_group',
-			payload: { tabIds },
+			payload: { tabIds, windowId: this.windowId },
 		})

 		if (!result?.success) {
@@ -232,6 +229,11 @@ export class TabsController extends EventTarget {
 		})
 	}

+	private addTab(meta: TabMeta) {
+		if (this.tabs.find((t) => t.id === meta.id)) return
+		this.tabs.push(meta)
+	}
+
 	async updateCurrentTabId(tabId: number | null) {
 		debug('updateCurrentTabId', tabId)

@@ -288,9 +290,77 @@ export class TabsController extends EventTarget {
 		await waitUntil(() => tab.status === 'complete', 4_000)
 	}

-	dispose() {
-		this.dispatchEvent(new Event('dispose'))
+	/**
+	 * Connect to background SW via port to receive tab change events.
+	 *
+	 * @note Port is 1:1 (runtime.connect → background SW has no frames),
+	 * so onDisconnect fires exactly once and we can safely reconnect.
+	 * Reconnection may miss events during the gap.
+	 * TODO: refresh this.tabs from background after reconnect to stay consistent.
+	 */
+	private connectTabEvents() {
+		this.port = chrome.runtime.connect({ name: 'tab-events' })
+
+		this.port.onMessage.addListener((message: any) => {
+			if (this.disposed) return
+			this.portRetries = 0
+
+			if (message.action === 'created') {
+				const tab = message.payload.tab as chrome.tabs.Tab
+				const shouldTrack = this.experimentalIncludeAllTabs || tab.groupId === this.tabGroupId
+				if (shouldTrack && tab.id != null) {
+					this.addTab({ id: tab.id, isInitial: false })
+					this.switchToTab(tab.id)
+				}
+			} else if (message.action === 'removed') {
+				const { tabId } = message.payload as { tabId: number }
+				const targetTab = this.tabs.find((t) => t.id === tabId)
+				if (targetTab) {
+					this.tabs = this.tabs.filter((t) => t.id !== tabId)
+					if (this.currentTabId === tabId) {
+						const newCurrentTab = this.tabs[this.tabs.length - 1] || null
+						if (newCurrentTab) {
+							this.switchToTab(newCurrentTab.id)
+						} else {
+							this.updateCurrentTabId(null)
+						}
+					}
+				}
+			} else if (message.action === 'updated') {
+				const { tabId, tab } = message.payload as { tabId: number; tab: chrome.tabs.Tab }
+				const targetTab = this.tabs.find((t) => t.id === tabId)
+				if (targetTab) {
+					targetTab.url = tab.url
+					targetTab.title = tab.title
+					targetTab.status = tab.status
+				}
+			}
+		})
+
+		this.port.onDisconnect.addListener(() => {
+			this.port = null
+			if (this.disposed) return
+			if (this.portRetries >= 7) {
+				console.error(PREFIX, 'tab events port failed after 7 retries, giving up')
+				return
+			}
+			debug('port disconnected, reconnecting...')
+			this.portRetries++
+			this.connectTabEvents()
+		})
 	}
+
+	dispose() {
+		debug('dispose')
+		this.disposed = true
+		this.port?.disconnect()
+		this.port = null
+	}
+}
+
+export interface TabsInitOptions {
+	includeInitialTab?: boolean
+	experimentalIncludeAllTabs?: boolean
 }

 export type TabAction =
@@ -302,6 +372,7 @@ export type TabAction =
 	| 'add_tab_to_group'
 	| 'close_tab'
 	| 'get_tab_title'
+	| 'get_window_tabs'

 interface TabMeta {
 	id: number
--- a/packages/extension/src/agent/useAgent.ts
+++ b/packages/extension/src/agent/useAgent.ts
@@ -21,6 +21,7 @@ export interface AdvancedConfig {
 	maxSteps?: number
 	systemInstruction?: string
 	experimentalLlmsTxt?: boolean
+	experimentalIncludeAllTabs?: boolean
 	disableNamedToolChoice?: boolean
 }

@@ -125,6 +126,7 @@ export function useAgent(): UseAgentResult {
 			maxSteps,
 			systemInstruction,
 			experimentalLlmsTxt,
+			experimentalIncludeAllTabs,
 			disableNamedToolChoice,
 			...llmConfig
 		}: ExtConfig) => {
@@ -138,6 +140,7 @@ export function useAgent(): UseAgentResult {
 				maxSteps,
 				systemInstruction,
 				experimentalLlmsTxt,
+				experimentalIncludeAllTabs,
 				disableNamedToolChoice,
 			}
 			await chrome.storage.local.set({ advancedConfig })
--- a/packages/extension/src/components/ConfigPanel.tsx
+++ b/packages/extension/src/components/ConfigPanel.tsx
@@ -31,17 +31,20 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 	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 [maxSteps, setMaxSteps] = useState(config?.maxSteps)
 	const [systemInstruction, setSystemInstruction] = useState(config?.systemInstruction ?? '')
 	const [experimentalLlmsTxt, setExperimentalLlmsTxt] = useState(
 		config?.experimentalLlmsTxt ?? false
 	)
+	const [experimentalIncludeAllTabs, setExperimentalIncludeAllTabs] = useState(
+		config?.experimentalIncludeAllTabs ?? false
+	)
 	const [disableNamedToolChoice, setDisableNamedToolChoice] = useState(
 		config?.disableNamedToolChoice ?? false
 	)
 	const [advancedOpen, setAdvancedOpen] = useState(false)
 	const [saving, setSaving] = useState(false)
-	const [userAuthToken, setUserAuthToken] = useState<string>('')
+	const [userAuthToken, setUserAuthToken] = useState('')
 	const [copied, setCopied] = useState(false)
 	const [showToken, setShowToken] = useState(false)
 	const [showApiKey, setShowApiKey] = useState(false)
@@ -54,6 +57,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 		setMaxSteps(config?.maxSteps)
 		setSystemInstruction(config?.systemInstruction ?? '')
 		setExperimentalLlmsTxt(config?.experimentalLlmsTxt ?? false)
+		setExperimentalIncludeAllTabs(config?.experimentalIncludeAllTabs ?? false)
 		setDisableNamedToolChoice(config?.disableNamedToolChoice ?? false)
 	}, [config])

@@ -100,6 +104,7 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 				maxSteps: maxSteps || undefined,
 				systemInstruction: systemInstruction || undefined,
 				experimentalLlmsTxt,
+				experimentalIncludeAllTabs,
 				disableNamedToolChoice,
 			})
 		} finally {
@@ -285,6 +290,14 @@ export function ConfigPanel({ config, onSave, onClose }: ConfigPanelProps) {
 						<span className="text-xs text-muted-foreground">Experimental llms.txt support</span>
 						<Switch checked={experimentalLlmsTxt} onCheckedChange={setExperimentalLlmsTxt} />
 					</label>
+
+					<label className="flex items-center justify-between cursor-pointer">
+						<span className="text-xs text-muted-foreground">Experimental include all tabs</span>
+						<Switch
+							checked={experimentalIncludeAllTabs}
+							onCheckedChange={setExperimentalIncludeAllTabs}
+						/>
+					</label>
 				</>
 			)}

--- a/packages/extension/src/components/misc.tsx
+++ b/packages/extension/src/components/misc.tsx
@@ -111,6 +111,7 @@ export function EmptyState() {
 					]}
 					cursorStyle="underscore"
 					loop
+					startOnView={false}
 					typeSpeed={20}
 					deleteSpeed={10}
 					pauseDelay={3000}
--- a/packages/extension/src/entrypoints/background.ts
+++ b/packages/extension/src/entrypoints/background.ts
@@ -1,12 +1,12 @@
 import { handlePageControlMessage } from '@/agent/RemotePageController.background'
-import { handleTabControlMessage, setupTabChangeEvents } from '@/agent/TabsController.background'
+import { handleTabControlMessage, setupTabEventsPort } from '@/agent/TabsController.background'

 export default defineBackground(() => {
 	console.log('[Background] Service Worker started')

 	// tab change events

-	setupTabChangeEvents()
+	setupTabEventsPort()

 	// generate user auth token

--- a/packages/extension/src/entrypoints/content.ts
+++ b/packages/extension/src/entrypoints/content.ts
@@ -70,11 +70,15 @@ async function exposeAgentToPage() {

 				try {
 					const { task, config } = payload
+					const { systemInstruction, ...agentConfig } = config

 					// Dispose old instance before creating new one
 					multiPageAgent?.dispose()

-					multiPageAgent = new MultiPageAgent(config)
+					multiPageAgent = new MultiPageAgent({
+						...agentConfig,
+						instructions: systemInstruction ? { system: systemInstruction } : undefined,
+					})

 					// events

--- a/packages/extension/src/entrypoints/main-world.ts
+++ b/packages/extension/src/entrypoints/main-world.ts
@@ -7,12 +7,21 @@ export interface ExecuteConfig {
 	model: string
 	apiKey?: string

+	/**
+	 * Global system-level instructions for the agent.
+	 * Equivalent to `AgentConfig.instructions.system`.
+	 */
+	systemInstruction?: string
+
 	/**
 	 * Whether to include the initial tab (that holds this main world script) in the task.
 	 * @default true
 	 */
 	includeInitialTab?: boolean

+	/** Control all unpinned tabs in the window instead of only the tab group. */
+	experimentalIncludeAllTabs?: boolean
+
 	onStatusChange?: (status: AgentStatus) => void
 	onActivity?: (activity: AgentActivity) => void
 	onHistoryUpdate?: (history: HistoricalEvent[]) => void
@@ -86,7 +95,9 @@ export default defineUnlistedScript(() => {
 						baseURL: config.baseURL,
 						model: config.model,
 						apiKey: config.apiKey,
+						systemInstruction: config.systemInstruction,
 						includeInitialTab: config.includeInitialTab,
+						experimentalIncludeAllTabs: config.experimentalIncludeAllTabs,
 					},
 				},
 			},
--- a/packages/llms/package.json
+++ b/packages/llms/package.json
@@ -1,6 +1,6 @@
 {
    "name": "@page-agent/llms",
-    "version": "1.6.0",
+    "version": "1.7.0",
    "type": "module",
    "main": "./dist/lib/page-agent-llms.js",
    "module": "./dist/lib/page-agent-llms.js",
--- a/packages/mcp/package.json
+++ b/packages/mcp/package.json
@@ -1,7 +1,7 @@
 {
    "name": "@page-agent/mcp",
    "private": false,
-    "version": "1.6.0",
+    "version": "1.7.0",
    "type": "module",
    "bin": {
        "page-agent-mcp": "src/index.js"
@@ -28,8 +28,8 @@
        "node": ">=20"
    },
    "dependencies": {
-        "@modelcontextprotocol/sdk": "^1.27.1",
-        "ws": "^8.19.0",
+        "@modelcontextprotocol/sdk": "^1.29.0",
+        "ws": "^8.20.0",
        "zod": "^4.3.5"
    }
 }
--- a/packages/mcp/src/index.js
+++ b/packages/mcp/src/index.js
@@ -35,11 +35,14 @@ const mcpServer = new McpServer({ name: 'page-agent', version: '1.5.8' })
 mcpServer.registerTool(
 	'execute_task',
 	{
-		description:
-			'Execute a browser automation task described in natural language. ' +
-			'The Page Agent extension will control the browser to complete the task. ' +
-			'Blocks until the task is complete.',
-		inputSchema: { task: z.string().describe('Task description in natural language') },
+		description: "Execute a task in user's browser.",
+		inputSchema: {
+			task: z
+				.string()
+				.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: [
--- a/packages/page-agent/package.json
+++ b/packages/page-agent/package.json
@@ -1,7 +1,7 @@
 {
    "name": "page-agent",
    "private": false,
-    "version": "1.6.0",
+    "version": "1.7.0",
    "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": "1.6.0",
-        "@page-agent/llms": "1.6.0",
-        "@page-agent/page-controller": "1.6.0",
-        "@page-agent/ui": "1.6.0",
+        "@page-agent/core": "1.7.0",
+        "@page-agent/llms": "1.7.0",
+        "@page-agent/page-controller": "1.7.0",
+        "@page-agent/ui": "1.7.0",
        "chalk": "^5.6.2"
    },
    "peerDependencies": {
--- a/packages/page-agent/src/PageAgent.ts
+++ b/packages/page-agent/src/PageAgent.ts
@@ -4,11 +4,11 @@
 */
 import { type AgentConfig, PageAgentCore } from '@page-agent/core'
 import { PageController, type PageControllerConfig } from '@page-agent/page-controller'
-import { Panel } from '@page-agent/ui'
+import { Panel, type PanelConfig } from '@page-agent/ui'

 export * from '@page-agent/core'

-export type PageAgentConfig = AgentConfig & PageControllerConfig
+export type PageAgentConfig = AgentConfig & PageControllerConfig & Omit<PanelConfig, 'language'>

 export class PageAgent extends PageAgentCore {
 	panel: Panel
@@ -23,6 +23,7 @@ export class PageAgent extends PageAgentCore {

 		this.panel = new Panel(this, {
 			language: config.language,
+			promptForNextTask: config.promptForNextTask,
 		})
 	}
 }
--- a/packages/page-agent/src/demo.ts
+++ b/packages/page-agent/src/demo.ts
@@ -17,9 +17,10 @@ const DEMO_MODEL = 'qwen3.5-plus'
 const DEMO_BASE_URL = 'https://page-ag-testing-ohftxirgbn.cn-shanghai.fcapp.run'
 const DEMO_API_KEY = 'NA'

+const currentScript = document.currentScript as HTMLScriptElement | null
+
 // in case document.x is not ready yet
 setTimeout(() => {
-	const currentScript = document.currentScript as HTMLScriptElement | null
 	let config: PageAgentConfig

 	if (currentScript) {
--- a/packages/page-controller/package.json
+++ b/packages/page-controller/package.json
@@ -1,6 +1,6 @@
 {
    "name": "@page-agent/page-controller",
-    "version": "1.6.0",
+    "version": "1.7.0",
    "type": "module",
    "main": "./dist/lib/page-controller.js",
    "module": "./dist/lib/page-controller.js",
--- a/packages/page-controller/src/PageController.ts
+++ b/packages/page-controller/src/PageController.ts
@@ -218,6 +218,7 @@ export class PageController extends EventTarget {
 	 * Clean up all element highlights
 	 */
 	async cleanUpHighlights(): Promise<void> {
+		console.log('[PageController] cleanUpHighlights')
 		dom.cleanUpHighlights()
 	}

@@ -424,3 +425,5 @@ export class PageController extends EventTarget {
 		this.mask = null
 	}
 }
+
+export * from './actions'
--- a/packages/page-controller/src/actions.ts
+++ b/packages/page-controller/src/actions.ts
@@ -4,6 +4,9 @@
 */
 import type { InteractiveElementDomNode } from './dom/dom_tree/type'
 import {
+	clickPointer,
+	disablePassThrough,
+	enablePassThrough,
 	getNativeValueSetter,
 	isHTMLElement,
 	isInputElement,
@@ -15,6 +18,7 @@ import {

 /**
 * Get the HTMLElement by index from a selectorMap.
+ * @private Internal method, subject to change at any time.
 */
 export function getElementByIndex(
 	selectorMap: Map<number, InteractiveElementDomNode>,
@@ -41,19 +45,21 @@ let lastClickedElement: HTMLElement | null = null

 function blurLastClickedElement() {
 	if (lastClickedElement) {
+		lastClickedElement.dispatchEvent(new PointerEvent('pointerout', { bubbles: true }))
+		lastClickedElement.dispatchEvent(new PointerEvent('pointerleave', { bubbles: false }))
+		lastClickedElement.dispatchEvent(new MouseEvent('mouseout', { bubbles: true }))
+		lastClickedElement.dispatchEvent(new MouseEvent('mouseleave', { bubbles: false }))
 		lastClickedElement.blur()
-		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
+ * Simulate a full click following W3C Pointer Events + UI Events spec order:
+ * pointerover/enter → mouseover/enter → pointerdown → mousedown → [focus] →
+ * pointerup → mouseup → click
+ *
+ * @private Internal method, subject to change at any time.
 */
 export async function clickElement(element: HTMLElement) {
 	blurLastClickedElement()
@@ -61,34 +67,67 @@ export async function clickElement(element: HTMLElement) {
 	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'))
+	const rect = element.getBoundingClientRect()
+	const x = rect.left + rect.width / 2
+	const y = rect.top + rect.height / 2
+
+	await movePointerToElement(element, x, y)
+	await clickPointer()

 	await waitFor(0.1)

-	// hover it
-	element.dispatchEvent(new MouseEvent('mouseenter', { bubbles: true, cancelable: true }))
-	element.dispatchEvent(new MouseEvent('mouseover', { bubbles: true, cancelable: true }))
+	// Hit-test to find the deepest element at click coordinates, matching
+	// real browser behavior where events target the innermost element.
+	// @note This may hit a element in the blacklist
+	// TODO: This is a temporary workaround. Should have been handled during dom extraction.
+	const doc = element.ownerDocument
+	await enablePassThrough()
+	const hitTarget = doc.elementFromPoint(x, y)
+	await disablePassThrough()
+	const target =
+		hitTarget instanceof HTMLElement && element.contains(hitTarget) ? hitTarget : element

-	// dispatch a sequence of events to ensure all listeners are triggered
-	element.dispatchEvent(new MouseEvent('mousedown', { bubbles: true, cancelable: true }))
+	const pointerOpts = {
+		bubbles: true,
+		cancelable: true,
+		clientX: x,
+		clientY: y,
+		pointerType: 'mouse',
+	}
+	const mouseOpts = { bubbles: true, cancelable: true, clientX: x, clientY: y, button: 0 }

-	// focus it to ensure it gets the click event
-	element.focus()
+	// Hover — pointer events first, then mouse events (spec order)
+	target.dispatchEvent(new PointerEvent('pointerover', pointerOpts))
+	target.dispatchEvent(new PointerEvent('pointerenter', { ...pointerOpts, bubbles: false }))
+	target.dispatchEvent(new MouseEvent('mouseover', mouseOpts))
+	target.dispatchEvent(new MouseEvent('mouseenter', { ...mouseOpts, bubbles: false }))

-	element.dispatchEvent(new MouseEvent('mouseup', { bubbles: true, cancelable: true }))
-	element.dispatchEvent(new MouseEvent('click', { bubbles: true, cancelable: true }))
+	// Press
+	target.dispatchEvent(new PointerEvent('pointerdown', pointerOpts))
+	target.dispatchEvent(new MouseEvent('mousedown', mouseOpts))

-	// dispatch a click event
-	// element.click()
+	// Focus is not part of the standard pointer/mouse event sequence
+	// "undefined and varies between user agents".
+	// We focus the original element (nearest focusable ancestor), not the hit-test target, matching browser behavior.
+	element.focus({ preventScroll: true })

-	await waitFor(0.2) // Wait to ensure click event processing completes
+	// Release
+	target.dispatchEvent(new PointerEvent('pointerup', pointerOpts))
+	target.dispatchEvent(new MouseEvent('mouseup', mouseOpts))
+
+	// Click — activation behavior (navigation, form submit, etc.) triggers
+	// via bubbling from target up to the interactive ancestor.
+	target.click()
+
+	await waitFor(0.2)
 }

+/**
+ * @private Internal method, subject to change at any time.
+ */
 export async function inputTextElement(element: HTMLElement, text: string) {
 	const isContentEditable = element.isContentEditable
 	if (!isInputElement(element) && !isTextAreaElement(element) && !isContentEditable) {
@@ -196,6 +235,7 @@ 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 (!isSelectElement(selectElement)) {
@@ -219,6 +259,9 @@ interface ScrollableElement extends Element {
 	scrollIntoViewIfNeeded?: (centerIfNeeded?: boolean) => void
 }

+/**
+ * @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') {
--- a/packages/page-controller/src/dom/dom_tree/index.js
+++ b/packages/page-controller/src/dom/dom_tree/index.js
@@ -18,6 +18,7 @@
 * @edit improve `sampleRect`, filter out rects with 0 area
 * @edit exclude aria-hidden elements
 * @edit make sure attributes exist for interactive candidates.
+ * @edit fix "aria-*" attributes check
 */

 export default (
@@ -1143,6 +1144,31 @@ export default (
 	 * @param {HTMLElement} element - The element to check.
 	 * @returns {boolean} Whether the element is an interactive candidate.
 	 */
+
+	// @edit fix "aria-*" attributes check
+	const INTERACTIVE_ARIA_ATTRS = [
+		'aria-expanded',
+		'aria-checked',
+		'aria-selected',
+		'aria-pressed',
+		'aria-haspopup',
+		'aria-controls',
+		'aria-owns',
+		'aria-activedescendant',
+		'aria-valuenow',
+		'aria-valuetext',
+		'aria-valuemax',
+		'aria-valuemin',
+		'aria-autocomplete',
+	]
+
+	function hasInteractiveAria(el) {
+		for (let i = 0; i < INTERACTIVE_ARIA_ATTRS.length; i++) {
+			if (el.hasAttribute(INTERACTIVE_ARIA_ATTRS[i])) return true
+		}
+		return false
+	}
+
 	function isInteractiveCandidate(element) {
 		if (!element || element.nodeType !== Node.ELEMENT_NODE) return false

@@ -1167,7 +1193,7 @@ export default (
 			element.hasAttribute('onclick') ||
 			element.hasAttribute('role') ||
 			element.hasAttribute('tabindex') ||
-			element.hasAttribute('aria-') ||
+			hasInteractiveAria(element) ||
 			element.hasAttribute('data-action') ||
 			element.getAttribute('contenteditable') === 'true'

--- a/packages/page-controller/src/mask/SimulatorMask.ts
+++ b/packages/page-controller/src/mask/SimulatorMask.ts
@@ -5,7 +5,7 @@ import { isPageDark } from './checkDarkMode'
 import styles from './SimulatorMask.module.css'
 import cursorStyles from './cursor.module.css'

-export class SimulatorMask {
+export class SimulatorMask extends EventTarget {
 	shown: boolean = false
 	wrapper = document.createElement('div')
 	motion: Motion | null = null
@@ -19,6 +19,8 @@ export class SimulatorMask {
 	#targetCursorY = 0

 	constructor() {
+		super()
+
 		this.wrapper.id = 'page-agent-runtime_simulator-mask'
 		this.wrapper.className = styles.wrapper
 		this.wrapper.setAttribute('data-browser-use-ignore', 'true')
@@ -74,13 +76,34 @@ export class SimulatorMask {

 		this.#moveCursorToTarget()

-		window.addEventListener('PageAgent::MovePointerTo', (event: Event) => {
+		// global events
+		// @note Mask should be isolated from the rest of the code.
+		// Global events are easier to manage and cleanup.
+
+		const movePointerToListener = (event: Event) => {
 			const { x, y } = (event as CustomEvent).detail
 			this.setCursorPosition(x, y)
-		})
-
-		window.addEventListener('PageAgent::ClickPointer', (event: Event) => {
+		}
+		const clickPointerListener = () => {
 			this.triggerClickAnimation()
+		}
+		const enablePassThroughListener = () => {
+			this.wrapper.style.pointerEvents = 'none'
+		}
+		const disablePassThroughListener = () => {
+			this.wrapper.style.pointerEvents = 'auto'
+		}
+
+		window.addEventListener('PageAgent::MovePointerTo', movePointerToListener)
+		window.addEventListener('PageAgent::ClickPointer', clickPointerListener)
+		window.addEventListener('PageAgent::EnablePassThrough', enablePassThroughListener)
+		window.addEventListener('PageAgent::DisablePassThrough', disablePassThroughListener)
+
+		this.addEventListener('dispose', () => {
+			window.removeEventListener('PageAgent::MovePointerTo', movePointerToListener)
+			window.removeEventListener('PageAgent::ClickPointer', clickPointerListener)
+			window.removeEventListener('PageAgent::EnablePassThrough', enablePassThroughListener)
+			window.removeEventListener('PageAgent::DisablePassThrough', disablePassThroughListener)
 		})
 	}

@@ -177,7 +200,9 @@ export class SimulatorMask {
 	}

 	dispose() {
+		console.log('dispose SimulatorMask')
 		this.motion?.dispose()
 		this.wrapper.remove()
+		this.dispatchEvent(new Event('dispose'))
 	}
 }
--- a/packages/page-controller/src/utils/index.ts
+++ b/packages/page-controller/src/utils/index.ts
@@ -48,15 +48,33 @@ export async function waitFor(seconds: number): Promise<void> {
 	await new Promise((resolve) => setTimeout(resolve, seconds * 1000))
 }

-// ======= dom utils =======
+// ======= mask events =======

-export async function movePointerToElement(element: HTMLElement) {
-	const rect = element.getBoundingClientRect()
+/**
+ * Move the visual pointer to a position within an element.
+ * @param x - x coordinate in the element's document viewport
+ * @param y - y coordinate in the element's document viewport
+ */
+export async function movePointerToElement(element: HTMLElement, x: number, y: number) {
 	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 } }))
+	window.dispatchEvent(
+		new CustomEvent('PageAgent::MovePointerTo', {
+			detail: { x: x + offset.x, y: y + offset.y },
+		})
+	)

 	await waitFor(0.3)
 }
+
+export async function clickPointer() {
+	window.dispatchEvent(new CustomEvent('PageAgent::ClickPointer'))
+}
+
+export async function enablePassThrough() {
+	window.dispatchEvent(new CustomEvent('PageAgent::EnablePassThrough'))
+}
+
+export async function disablePassThrough() {
+	window.dispatchEvent(new CustomEvent('PageAgent::DisablePassThrough'))
+}
--- a/packages/ui/package.json
+++ b/packages/ui/package.json
@@ -1,6 +1,6 @@
 {
    "name": "@page-agent/ui",
-    "version": "1.6.0",
+    "version": "1.7.0",
    "type": "module",
    "main": "./dist/lib/page-agent-ui.js",
    "module": "./dist/lib/page-agent-ui.js",
--- a/packages/ui/src/panel/Panel.ts
+++ b/packages/ui/src/panel/Panel.ts
@@ -369,6 +369,7 @@ export class Panel {
 	}

 	#createWrapper(): HTMLElement {
+		const taskInputMaxLength = 1000
 		const wrapper = document.createElement('div')
 		wrapper.id = 'page-agent-runtime_agent-panel'
 		wrapper.className = styles.wrapper
@@ -406,7 +407,7 @@ export class Panel {
 					<input 
 						type="text" 
 						class="${styles.taskInput}" 
-						maxlength="200"
+						maxlength="${taskInputMaxLength}"
 					/>
 				</div>
 			</div>
--- a/packages/website/package.json
+++ b/packages/website/package.json
@@ -1,7 +1,7 @@
 {
    "name": "@page-agent/website",
    "private": true,
-    "version": "1.6.0",
+    "version": "1.7.0",
    "type": "module",
    "scripts": {
        "dev": "vite --host 0.0.0.0",
@@ -19,13 +19,13 @@
        "@types/react-dom": "^19.2.1",
        "class-variance-authority": "^0.7.1",
        "clsx": "^2.1.1",
-        "lucide-react": "^0.577.0",
-        "motion": "^12.37.0",
+        "lucide-react": "^1.7.0",
+        "motion": "^12.38.0",
        "next-themes": "^0.4.6",
        "react": "^19.2.4",
        "react-dom": "^19.2.4",
        "rough-notation": "^0.5.1",
-        "simple-icons": "^16.12.0",
+        "simple-icons": "^16.14.0",
        "sonner": "^2.0.7",
        "tailwind-merge": "^3.5.0",
        "tailwindcss": "^4.1.14",
--- a/packages/website/src/components/LanguageSwitcher.tsx
+++ b/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]
--- a/packages/website/src/constants.ts
+++ b/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@1.6.0/dist/iife/page-agent.demo.js'
+	'https://cdn.jsdelivr.net/npm/page-agent@1.7.0/dist/iife/page-agent.demo.js'
 export const CDN_DEMO_CN_URL =
-	'https://registry.npmmirror.com/page-agent/1.6.0/files/dist/iife/page-agent.demo.js'
+	'https://registry.npmmirror.com/page-agent/1.7.0/files/dist/iife/page-agent.demo.js'

 // Demo LLM for website testing (homepage quick trial uses flash)
 export const DEMO_MODEL = 'qwen3.5-flash'
--- a/packages/website/src/pages/docs/Layout.tsx
+++ b/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',
--- a/packages/website/src/pages/docs/advanced/page-agent/page.tsx
+++ b/packages/website/src/pages/docs/advanced/page-agent/page.tsx
@@ -100,7 +100,7 @@ console.log(result.history) // Full execution history`}
 							>
 								AgentConfig
 							</Link>{' '}
-							和{' '}
+							、 PanelConfig 和{' '}
 							<Link
 								href="/advanced/page-controller#configuration"
 								className="text-blue-600 dark:text-blue-400 hover:underline"
@@ -125,7 +125,7 @@ console.log(result.history) // Full execution history`}
 							>
 								AgentConfig
 							</Link>{' '}
-							and{' '}
+							, PanelConfig, and{' '}
 							<Link
 								href="/advanced/page-controller#configuration"
 								className="text-blue-600 dark:text-blue-400 hover:underline"
--- a/packages/website/src/pages/docs/features/chrome-extension/page.tsx
+++ b/packages/website/src/pages/docs/features/chrome-extension/page.tsx
@@ -199,7 +199,9 @@ interface ExecuteConfig {
 	model: string     // Model name
 	apiKey?: string   // LLM AK

+	systemInstruction?: string // Global system-level instructions
 	includeInitialTab?: boolean
+	experimentalIncludeAllTabs?: boolean // Control all unpinned tabs in the window
 	onStatusChange?: (status: AgentStatus) => void
 	onActivity?: (activity: AgentActivity) => void
 	onHistoryUpdate?: (history: HistoricalEvent[]) => void
@@ -233,6 +235,7 @@ const result = await window.PAGE_AGENT_EXT.execute(
 		apiKey: 'your-api-key',
 		model: 'gpt-5.2',
 		// includeInitialTab: false, // 设为 false 排除初始标签页
+		// experimentalIncludeAllTabs: true, // 控制窗口内所有非固定标签页
 		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)
@@ -248,6 +251,7 @@ const result = await window.PAGE_AGENT_EXT.execute(
 		apiKey: 'your-api-key',
 		model: 'gpt-5.2',
 		// includeInitialTab: false, // Set to false to exclude initial tab
+		// experimentalIncludeAllTabs: true, // Control all unpinned tabs in the window
 		onStatusChange: status => console.log('Status change:', status),
 		onActivity: activity => console.log('Activity:', activity),
 		onHistoryUpdate: history => console.log('History update:', history)
--- a/packages/website/src/pages/docs/features/mcp-server/page.tsx
+++ b/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>
+	)
+}
--- a/packages/website/src/pages/docs/features/models/page.tsx
+++ b/packages/website/src/pages/docs/features/models/page.tsx
@@ -9,6 +9,7 @@ const BASELINE = new Set([
 	'claude-haiku-4.5',
 	'gemini-3-flash',
 	'deepseek-3.2',
+	'qwen3.6-plus',
 	'qwen3.5-plus',
 	'qwen3.5-flash',
 ])
@@ -16,6 +17,7 @@ const BASELINE = new Set([
 // Models grouped by brand, newest first
 const MODEL_GROUPS: Record<string, string[]> = {
 	Qwen: [
+		'qwen3.6-plus',
 		'qwen3.5-plus',
 		'qwen3.5-flash',
 		'qwen3-coder-next',
@@ -33,8 +35,8 @@ const MODEL_GROUPS: Record<string, string[]> = {
 		'claude-haiku-4.5',
 		'claude-sonnet-3.5',
 	],
-	xAI: ['grok-4.1-fast', 'grok-4', 'grok-code-fast'],
 	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'],
 	MoonshotAI: ['kimi-k2.5'],
 	'Z.AI': ['glm-5', 'glm-4.7'],
 }
@@ -181,7 +183,7 @@ const pageAgent = new PageAgent({
 						</a>
 					</p>
 					<CodeEditor
-						code={`# qwen3.5-plus (default for demos) or qwen3.5-flash (lighter)
+						code={`# qwen3.5-plus / qwen3.5-flash
 LLM_BASE_URL="https://page-ag-testing-ohftxirgbn.cn-shanghai.fcapp.run"
 LLM_MODEL_NAME="qwen3.5-plus"
 LLM_API_KEY="NA"`}
--- a/packages/website/src/pages/docs/index.tsx
+++ b/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 />
--- a/packages/website/src/pages/home/OneMoreThingSection.tsx
+++ b/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
--- a/packages/website/vite.config.js
+++ b/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',