feat(ext): add includeInitialTab option; change main world API

packages/extension/src/agent/MultiPageAgent.ts

@@ -17,7 +17,7 @@ function detectLanguage(): 'en-US' | 'zh-CN' {
  * - can be used from a side panel or a content script
  */
 export class MultiPageAgent extends PageAgentCore {
-	constructor(config: Omit<PageAgentConfig, 'pageController'>) {
+	constructor(config: Omit<PageAgentConfig, 'pageController'> & { includeInitialTab?: boolean }) {
 		// multi page controller
 		const tabsController = new TabsController()
 		const pageController = new RemotePageController(tabsController)
@@ -31,6 +31,9 @@ export class MultiPageAgent extends PageAgentCore {
 			`Default working language: **${targetLanguage}**`
 		)
 
+		// include initial tab for controlling
+		const includeInitialTab = config.includeInitialTab ?? true
+
 		/**
 		 * When the agent is in side-panel and user closed the side-panel.
 		 * There is no chance for isAgentRunning to be set false.
@@ -47,7 +50,7 @@ export class MultiPageAgent extends PageAgentCore {
 			customSystemPrompt: systemPrompt,
 
 			onBeforeTask: async (agent) => {
-				await tabsController.init(agent.task)
+				await tabsController.init(agent.task, includeInitialTab)
 
 				heartBeatInterval = window.setInterval(() => {
 					chrome.storage.local.set({

packages/extension/src/agent/TabsController.ts

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

packages/extension/src/entrypoints/content.ts

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

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

@@ -1,19 +1,24 @@
 import type { AgentActivity, AgentStatus, ExecutionResult, HistoricalEvent } from '@page-agent/core'
-import type { LLMConfig } from '@page-agent/llms'
 
-export interface ExecuteHooks {
+export type Execute = (task: string, config: ExecuteConfig) => Promise<ExecutionResult>
+
+export interface ExecuteConfig {
+	baseURL: string
+	apiKey: string
+	model: string
+
+	/**
+	 * Whether to include the initial tab (that holds this main world script) in the task.
+	 * @default true
+	 */
+	includeInitialTab?: boolean
+
 	onStatusChange?: (status: AgentStatus) => void
 	onActivity?: (activity: AgentActivity) => void
 	onHistoryUpdate?: (history: HistoricalEvent[]) => void
 	onDispose?: () => void
 }
 
-export type Execute = (
-	task: string,
-	llmConfig: LLMConfig,
-	hooks?: ExecuteHooks
-) => Promise<ExecutionResult>
-
 export default defineUnlistedScript(() => {
 	let _lastId = 0
 	function getId() {
@@ -21,13 +26,13 @@ export default defineUnlistedScript(() => {
 		return _lastId
 	}
 
-	const execute: Execute = async (task, llmConfig, hooks) => {
+	const execute: Execute = async (task, config) => {
 		if (typeof task !== 'string') throw new Error('Task must be a string')
 		if (task.trim().length === 0) throw new Error('Task cannot be empty')
-		if (!llmConfig) throw new Error('LLM config is required')
-		if (!llmConfig.baseURL) throw new Error('LLM config must have a baseURL')
-		if (!llmConfig.apiKey) throw new Error('LLM config must have an apiKey')
-		if (!llmConfig.model) throw new Error('LLM config must have a model')
+		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()
 
@@ -40,30 +45,31 @@ export default defineUnlistedScript(() => {
 
 				// events
 
-				if (data.action === 'status_change_event' && hooks?.onStatusChange) {
-					hooks.onStatusChange(data.payload)
+				if (data.action === 'status_change_event' && config.onStatusChange) {
+					config.onStatusChange(data.payload)
 					return
 				}
 
-				if (data.action === 'activity_event' && hooks?.onActivity) {
-					hooks.onActivity(data.payload)
+				if (data.action === 'activity_event' && config.onActivity) {
+					config.onActivity(data.payload)
 					return
 				}
 
-				if (data.action === 'history_change_event' && hooks?.onHistoryUpdate) {
-					hooks.onHistoryUpdate(data.payload)
+				if (data.action === 'history_change_event' && config.onHistoryUpdate) {
+					config.onHistoryUpdate(data.payload)
 					return
 				}
 
-				if (data.action === 'dispose_event' && hooks?.onDispose) {
-					hooks.onDispose()
+				if (data.action === 'dispose_event' && config.onDispose) {
+					config.onDispose()
+					window.removeEventListener('message', handleMessage)
 					return
 				}
 
-				// result
-
 				if (data.action !== 'execute_result') return
 
+				// execute_result
+
 				window.removeEventListener('message', handleMessage)
 
 				if (data.error) {
@@ -73,6 +79,7 @@ export default defineUnlistedScript(() => {
 				}
 			}
 
+			// @note will be removed on dispose or result
 			window.addEventListener('message', handleMessage)
 		})
 
@@ -81,7 +88,15 @@ export default defineUnlistedScript(() => {
 				channel: 'PAGE_AGENT_EXT_REQUEST',
 				id,
 				action: 'execute',
-				payload: { task, llmConfig },
+				payload: {
+					task,
+					config: {
+						baseURL: config.baseURL,
+						apiKey: config.apiKey,
+						model: config.model,
+						includeInitialTab: config.includeInitialTab,
+					},
+				},
 			},
 			'*'
 		)