Merge branch 'main' of https://github.com/alibaba/page-agent

packages/core/src/PageAgentCore.ts

@@ -344,7 +344,7 @@ export class PageAgentCore extends EventTarget {
 				return result
 			}
 
-			await waitFor(0.4) // @TODO: configurable
+			await waitFor(this.config.stepDelay ?? 0.4)
 		}
 	}
 
@@ -512,7 +512,8 @@ export class PageAgentCore extends EventTarget {
 		// Accumulated wait time warning
 		if (this.#states.totalWaitTime >= 3) {
 			this.pushObservation(
-				`You have waited ${this.#states.totalWaitTime} seconds accumulatively. DO NOT wait any longer unless you have a good reason.`
+				`You have waited ${this.#states.totalWaitTime} seconds accumulatively. ` +
+					`DO NOT wait any longer unless you have a good reason.`
 			)
 		}
 
@@ -528,7 +529,8 @@ export class PageAgentCore extends EventTarget {
 		const remaining = this.config.maxSteps - step
 		if (remaining === 5) {
 			this.pushObservation(
-				`⚠️ Only ${remaining} steps remaining. Consider wrapping up or calling done with partial results.`
+				`⚠️ Only ${remaining} steps remaining. ` +
+					`Consider wrapping up or calling done with partial results.`
 			)
 		} else if (remaining === 2) {
 			this.pushObservation(

packages/core/src/types.ts

@@ -152,6 +152,12 @@ export interface AgentConfig extends LLMConfig {
 	 * @experimental Use with caution - incorrect prompts may break agent behavior.
 	 */
 	customSystemPrompt?: string
+
+	/**
+	 * Delay between steps in seconds.
+	 * @default 0.4
+	 */
+	stepDelay?: number
 }
 
 /**

packages/page-controller/src/actions.ts

@@ -213,14 +213,18 @@ export async function selectOptionElement(selectElement: HTMLSelectElement, opti
 	await waitFor(0.1) // Wait to ensure change event processing completes
 }
 
+interface ScrollableElement extends HTMLElement {
+	scrollIntoViewIfNeeded?: (centerIfNeeded?: boolean) => void
+}
+
 export async function scrollIntoViewIfNeeded(element: HTMLElement) {
-	const el = element as any
+	const el = element as ScrollableElement
-	if (el.scrollIntoViewIfNeeded) {
+	if (typeof el.scrollIntoViewIfNeeded === 'function') {
 		el.scrollIntoViewIfNeeded()
 		// await waitFor(0.5) // Animation playback
 	} else {
 		// @todo visibility check
-		el.scrollIntoView({ behavior: 'auto', block: 'center', inline: 'nearest' })
+		element.scrollIntoView({ behavior: 'auto', block: 'center', inline: 'nearest' })
 		// await waitFor(0.5) // Animation playback
 	}
 }