Merge pull request #578 from alibaba/fix/wrong-active-tab-multi-window

fix: wrong active tab/window in multi-window scenarios

packages/extension/docs/extension_api.md

@@ -96,6 +96,10 @@ Returns: `Promise<ExecutionResult>`
 
 Stop the current task.
 
+## Limitations
+
+- **Normal browser windows only.** This extension relies on tab group API which does not work for pop-up window or PWA App window.
+
 ## Types
 
 Install `@page-agent/core` for complete types:

packages/extension/src/agent/TabsController.background.ts

@@ -7,6 +7,39 @@ const PREFIX = '[TabsController.background]'
 
 const debug = console.debug.bind(console, `\x1b[90m${PREFIX}\x1b[0m`)
 
+/**
+ * Resolve active tab.
+ *
+ * - `tabs.query({ active: true })` does not work in multi-window scenarios.
+ * - Extension pages (side panel, hub tab) can resolve their own windowId.
+ *   We just find the active tab within that window.
+ * - Content scripts (PAGE_AGENT_EXT) can't self-report a windowId.
+ *   Chrome populates `sender.tab` for every content-script message,
+ *   which is the tab hosting the script.
+ */
+async function resolveActiveTab(
+	payload: { windowId?: number } | undefined,
+	sender: chrome.runtime.MessageSender
+): Promise<chrome.tabs.Tab> {
+	const windowId = payload?.windowId
+
+	if (windowId != null) {
+		debug('get_active_tab: resolving via caller-reported windowId', windowId)
+		const [tab] = await chrome.tabs.query({ active: true, windowId })
+		if (!tab) throw new Error(`No active tab found in window ${windowId}.`)
+		return tab
+	}
+
+	if (sender.tab) {
+		debug('get_active_tab: resolving via sender.tab (content script)', sender.tab.id)
+		return sender.tab
+	}
+
+	throw new Error(
+		'Cannot resolve active tab: caller reported no windowId and is not a content script (no sender.tab).'
+	)
+}
+
 export function handleTabControlMessage(
 	message: { type: 'TAB_CONTROL'; action: TabAction; payload: any },
 	sender: chrome.runtime.MessageSender,
@@ -16,12 +49,11 @@ export function handleTabControlMessage(
 
 	switch (action as TabAction) {
 		case 'get_active_tab': {
-			debug('get_active_tab')
+			debug('get_active_tab', payload)
-			chrome.tabs
+			resolveActiveTab(payload, sender)
-				.query({ active: true })
+				.then((tab) => {
-				.then((tabs) => {
+					debug('get_active_tab: success', tab)
-					debug('get_active_tab: success', tabs)
+					sendResponse({ success: true, tab })
-					sendResponse({ success: true, tab: tabs[0] })
 				})
 				.catch((error) => {
 					sendResponse({ error: error instanceof Error ? error.message : String(error) })
@@ -46,7 +78,7 @@ export function handleTabControlMessage(
 		case 'open_new_tab': {
 			debug('open_new_tab', payload)
 			chrome.tabs
-				.create({ url: payload.url, active: false })
+				.create({ url: payload.url, windowId: payload.windowId, active: false })
 				.then((newTab) => {
 					debug('open_new_tab: success', newTab)
 					sendResponse({ success: true, tabId: newTab.id })

packages/extension/src/agent/TabsController.ts

@@ -15,6 +15,20 @@ function sendMessage(message: {
 	})
 }
 
+/**
+ * Resolve the window hosting this script's own context, when knowable.
+ *
+ * Extension pages (side panel, hub tab) have `chrome.windows` access and can
+ * identify their own window directly via `getCurrent()`.
+ * Content scripts have no `chrome.windows` access; they resolve `undefined`
+ * here and the background script falls back to `sender.tab` instead.
+ */
+async function getOwnWindowId(): Promise<number | undefined> {
+	if (typeof chrome.windows === 'undefined') return undefined
+	const win = await chrome.windows.getCurrent()
+	return win.id
+}
+
 /**
  * Controller for managing browser tabs.
  * - live in the agent env (extension page or content script)
@@ -57,6 +71,7 @@ export class TabsController {
 		const activeTabResult = await sendMessage({
 			type: 'TAB_CONTROL',
 			action: 'get_active_tab',
+			payload: { windowId: await getOwnWindowId() },
 		})
 
 		this.initialTabId = activeTabResult.tab?.id
@@ -124,7 +139,7 @@ export class TabsController {
 		const result = await sendMessage({
 			type: 'TAB_CONTROL',
 			action: 'open_new_tab',
-			payload: { url },
+			payload: { url, windowId: this.windowId },
 		})
 
 		if (!result.success) {
@@ -307,7 +322,10 @@ export class TabsController {
 
 			if (message.action === 'created') {
 				const tab = message.payload.tab as chrome.tabs.Tab
-				const shouldTrack = this.experimentalIncludeAllTabs || tab.groupId === this.tabGroupId
+				const shouldTrack =
+					tab.groupId === this.tabGroupId ||
+					// @note Never track tabs from other windows.
+					(this.experimentalIncludeAllTabs && tab.windowId === this.windowId)
 				if (shouldTrack && tab.id != null) {
 					this.addTab({ id: tab.id, isInitial: false })
 					this.switchToTab(tab.id)