fix(core): Core and PageAgent use different config types; improve code structure
This commit is contained in:
@@ -7,12 +7,11 @@ import type { BrowserState, PageController } from '@page-agent/page-controller'
|
||||
import chalk from 'chalk'
|
||||
import * as z from 'zod'
|
||||
|
||||
import { type PageAgentConfig, type SupportedLanguage } from './config'
|
||||
import { DEFAULT_MAX_STEPS } from './config/constants'
|
||||
import SYSTEM_PROMPT from './prompts/system_prompt.md?raw'
|
||||
import { tools } from './tools'
|
||||
import type {
|
||||
AgentActivity,
|
||||
AgentConfig,
|
||||
AgentReflection,
|
||||
AgentStatus,
|
||||
AgentStepEvent,
|
||||
@@ -23,11 +22,11 @@ import type {
|
||||
} from './types'
|
||||
import { assert, fetchLlmsTxt, normalizeResponse, uid, waitFor } from './utils'
|
||||
|
||||
export { type PageAgentConfig }
|
||||
export type { SupportedLanguage }
|
||||
export { tool, type PageAgentTool } from './tools'
|
||||
export type * from './types'
|
||||
|
||||
export type PageAgentCoreConfig = AgentConfig & { pageController: PageController }
|
||||
|
||||
/**
|
||||
* AI agent for browser automation.
|
||||
*
|
||||
@@ -60,7 +59,7 @@ export type * from './types'
|
||||
*/
|
||||
export class PageAgentCore extends EventTarget {
|
||||
readonly id = uid()
|
||||
readonly config: PageAgentConfig & { maxSteps: number }
|
||||
readonly config: PageAgentCoreConfig & { maxSteps: number }
|
||||
readonly tools: typeof tools
|
||||
/** PageController for DOM operations */
|
||||
readonly pageController: PageController
|
||||
@@ -94,10 +93,10 @@ export class PageAgentCore extends EventTarget {
|
||||
browserState: null as BrowserState | null,
|
||||
}
|
||||
|
||||
constructor(config: PageAgentConfig & { pageController: PageController }) {
|
||||
constructor(config: PageAgentCoreConfig) {
|
||||
super()
|
||||
|
||||
this.config = { ...config, maxSteps: config.maxSteps || DEFAULT_MAX_STEPS }
|
||||
this.config = { ...config, maxSteps: config.maxSteps || 20 }
|
||||
|
||||
this.#llm = new LLM(this.config)
|
||||
this.tools = new Map(tools)
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
export const DEFAULT_MAX_STEPS = 20
|
||||
@@ -1,160 +0,0 @@
|
||||
import type { LLMConfig } from '@page-agent/llms'
|
||||
import type { PageControllerConfig } from '@page-agent/page-controller'
|
||||
|
||||
import type { PageAgentCore } from '../PageAgentCore'
|
||||
import type { PageAgentTool } from '../tools'
|
||||
import type { ExecutionResult, HistoricalEvent } from '../types'
|
||||
|
||||
export type { LLMConfig }
|
||||
|
||||
/** Supported UI languages */
|
||||
export type SupportedLanguage = 'en-US' | 'zh-CN'
|
||||
|
||||
export interface AgentConfig {
|
||||
// theme?: 'light' | 'dark'
|
||||
language?: SupportedLanguage
|
||||
|
||||
/**
|
||||
* Maximum number of steps the agent can take per task.
|
||||
* @default 20
|
||||
*/
|
||||
maxSteps?: number
|
||||
|
||||
/**
|
||||
* Custom tools to extend PageAgent capabilities
|
||||
* @experimental
|
||||
* @note You can also override or remove internal tools by using the same name.
|
||||
* @see PageAgentTool
|
||||
*
|
||||
* @example
|
||||
* // override internal tool
|
||||
* import { tool } from 'page-agent'
|
||||
* const customTools = {
|
||||
* ask_user: tool({
|
||||
* description:
|
||||
* 'Ask the user or parent model a question and wait for their answer. Use this if you need more information or clarification.',
|
||||
* inputSchema: zod.object({
|
||||
* question: zod.string(),
|
||||
* }),
|
||||
* execute: async function (this: PageAgent, input) {
|
||||
* const answer = await do_some_thing(input.question)
|
||||
* return "✅ Received user answer: " + answer
|
||||
* },
|
||||
* })
|
||||
* }
|
||||
*
|
||||
* @example
|
||||
* // remove internal tool
|
||||
* const customTools = {
|
||||
* ask_user: null // never ask user questions
|
||||
* }
|
||||
*/
|
||||
customTools?: Record<string, PageAgentTool | null>
|
||||
|
||||
/**
|
||||
* Instructions to guide the agent's behavior
|
||||
*/
|
||||
instructions?: {
|
||||
/**
|
||||
* Global system-level instructions, applied to all tasks
|
||||
*/
|
||||
system?: string
|
||||
|
||||
/**
|
||||
* Dynamic page-level instructions callback
|
||||
* Called before each step to get instructions for the current page
|
||||
* @param url - Current page URL (window.location.href)
|
||||
* @returns Instructions string, or undefined/null to skip
|
||||
*/
|
||||
getPageInstructions?: (url: string) => string | undefined | null
|
||||
}
|
||||
|
||||
/**
|
||||
* Lifecycle hooks for task execution.
|
||||
* @experimental API may change in future versions.
|
||||
*
|
||||
* All hooks receive the agent instance as first parameter.
|
||||
*/
|
||||
|
||||
/**
|
||||
* Called before each step execution.
|
||||
* @experimental
|
||||
* @param agent - The PageAgentCore instance
|
||||
* @param stepCount - Current step number (0-indexed)
|
||||
*/
|
||||
onBeforeStep?: (agent: PageAgentCore, stepCount: number) => Promise<void> | void
|
||||
|
||||
/**
|
||||
* Called after each step execution.
|
||||
* @experimental
|
||||
* @param agent - The PageAgentCore instance
|
||||
* @param history - Current history of events
|
||||
*/
|
||||
onAfterStep?: (agent: PageAgentCore, history: HistoricalEvent[]) => Promise<void> | void
|
||||
|
||||
/**
|
||||
* Called before task execution starts.
|
||||
* @experimental
|
||||
* @param agent - The PageAgentCore instance
|
||||
*/
|
||||
onBeforeTask?: (agent: PageAgentCore) => Promise<void> | void
|
||||
|
||||
/**
|
||||
* Called after task execution completes (success or failure).
|
||||
* @experimental
|
||||
* @param agent - The PageAgentCore instance
|
||||
* @param result - The execution result
|
||||
*/
|
||||
onAfterTask?: (agent: PageAgentCore, result: ExecutionResult) => Promise<void> | void
|
||||
|
||||
/**
|
||||
* Called when the agent is disposed.
|
||||
* @experimental
|
||||
* @note This hook can block the disposal process if it's async.
|
||||
* @param agent - The PageAgentCore instance
|
||||
* @param reason - Optional reason for disposal
|
||||
*/
|
||||
onDispose?: (agent: PageAgentCore, reason?: string) => void
|
||||
|
||||
// page behavior hooks
|
||||
|
||||
/**
|
||||
* @experimental
|
||||
* Enable the experimental script execution tool that allows executing generated JavaScript code on the page.
|
||||
* @note Can cause unpredictable side effects.
|
||||
* @note May bypass some safe guards and data-masking mechanisms.
|
||||
*/
|
||||
experimentalScriptExecutionTool?: boolean
|
||||
|
||||
/**
|
||||
* @experimental
|
||||
* Fetch /llms.txt from current site origin and include as context.
|
||||
* Only fetched once per origin per task.
|
||||
* @default false
|
||||
*/
|
||||
experimentalLlmsTxt?: boolean
|
||||
|
||||
/**
|
||||
* Transform page content before sending to LLM.
|
||||
* Called after DOM extraction and simplification, before LLM invocation.
|
||||
* Use cases: inspect extraction results, modify page info, mask sensitive data.
|
||||
*
|
||||
* @param content - Simplified page content that will be sent to LLM
|
||||
* @returns Transformed content
|
||||
*
|
||||
* @example
|
||||
* // Mask phone numbers
|
||||
* transformPageContent: async (content) => {
|
||||
* return content.replace(/1[3-9]\d{9}/g, '***********')
|
||||
* }
|
||||
*/
|
||||
transformPageContent?: (content: string) => Promise<string> | string
|
||||
|
||||
/**
|
||||
* Completely override the default system prompt.
|
||||
* @experimental Use with caution - incorrect prompts may break agent behavior.
|
||||
*/
|
||||
customSystemPrompt?: string
|
||||
}
|
||||
|
||||
export type PageAgentConfig = LLMConfig & AgentConfig & PageControllerConfig
|
||||
@@ -1,3 +1,158 @@
|
||||
import type { LLMConfig } from '@page-agent/llms'
|
||||
|
||||
// @note circular dependency but okay
|
||||
import type { PageAgentCore } from './PageAgentCore'
|
||||
import type { PageAgentTool } from './tools'
|
||||
|
||||
/** Supported UI languages */
|
||||
export type SupportedLanguage = 'en-US' | 'zh-CN'
|
||||
|
||||
export interface AgentConfig extends LLMConfig {
|
||||
language?: SupportedLanguage
|
||||
|
||||
/**
|
||||
* Maximum number of steps the agent can take per task.
|
||||
* @default 20
|
||||
*/
|
||||
maxSteps?: number
|
||||
|
||||
/**
|
||||
* Custom tools to extend PageAgent capabilities
|
||||
* @experimental
|
||||
* @note You can also override or remove internal tools by using the same name.
|
||||
* @see PageAgentTool
|
||||
*
|
||||
* @example
|
||||
* // override internal tool
|
||||
* import { tool } from 'page-agent'
|
||||
* const customTools = {
|
||||
* ask_user: tool({
|
||||
* description:
|
||||
* 'Ask the user or parent model a question and wait for their answer. Use this if you need more information or clarification.',
|
||||
* inputSchema: zod.object({
|
||||
* question: zod.string(),
|
||||
* }),
|
||||
* execute: async function (this: PageAgent, input) {
|
||||
* const answer = await do_some_thing(input.question)
|
||||
* return "✅ Received user answer: " + answer
|
||||
* },
|
||||
* })
|
||||
* }
|
||||
*
|
||||
* @example
|
||||
* // remove internal tool
|
||||
* const customTools = {
|
||||
* ask_user: null // never ask user questions
|
||||
* }
|
||||
*/
|
||||
customTools?: Record<string, PageAgentTool | null>
|
||||
|
||||
/**
|
||||
* Instructions to guide the agent's behavior
|
||||
*/
|
||||
instructions?: {
|
||||
/**
|
||||
* Global system-level instructions, applied to all tasks
|
||||
*/
|
||||
system?: string
|
||||
|
||||
/**
|
||||
* Dynamic page-level instructions callback
|
||||
* Called before each step to get instructions for the current page
|
||||
* @param url - Current page URL (window.location.href)
|
||||
* @returns Instructions string, or undefined/null to skip
|
||||
*/
|
||||
getPageInstructions?: (url: string) => string | undefined | null
|
||||
}
|
||||
|
||||
/**
|
||||
* Lifecycle hooks for task execution.
|
||||
* @experimental API may change in future versions.
|
||||
*
|
||||
* All hooks receive the agent instance as first parameter.
|
||||
*/
|
||||
|
||||
/**
|
||||
* Called before each step execution.
|
||||
* @experimental
|
||||
* @param agent - The PageAgentCore instance
|
||||
* @param stepCount - Current step number (0-indexed)
|
||||
*/
|
||||
onBeforeStep?: (agent: PageAgentCore, stepCount: number) => Promise<void> | void
|
||||
|
||||
/**
|
||||
* Called after each step execution.
|
||||
* @experimental
|
||||
* @param agent - The PageAgentCore instance
|
||||
* @param history - Current history of events
|
||||
*/
|
||||
onAfterStep?: (agent: PageAgentCore, history: HistoricalEvent[]) => Promise<void> | void
|
||||
|
||||
/**
|
||||
* Called before task execution starts.
|
||||
* @experimental
|
||||
* @param agent - The PageAgentCore instance
|
||||
*/
|
||||
onBeforeTask?: (agent: PageAgentCore) => Promise<void> | void
|
||||
|
||||
/**
|
||||
* Called after task execution completes (success or failure).
|
||||
* @experimental
|
||||
* @param agent - The PageAgentCore instance
|
||||
* @param result - The execution result
|
||||
*/
|
||||
onAfterTask?: (agent: PageAgentCore, result: ExecutionResult) => Promise<void> | void
|
||||
|
||||
/**
|
||||
* Called when the agent is disposed.
|
||||
* @experimental
|
||||
* @note This hook can block the disposal process if it's async.
|
||||
* @param agent - The PageAgentCore instance
|
||||
* @param reason - Optional reason for disposal
|
||||
*/
|
||||
onDispose?: (agent: PageAgentCore, reason?: string) => void
|
||||
|
||||
// page behavior hooks
|
||||
|
||||
/**
|
||||
* @experimental
|
||||
* Enable the experimental script execution tool that allows executing generated JavaScript code on the page.
|
||||
* @note Can cause unpredictable side effects.
|
||||
* @note May bypass some safe guards and data-masking mechanisms.
|
||||
*/
|
||||
experimentalScriptExecutionTool?: boolean
|
||||
|
||||
/**
|
||||
* @experimental
|
||||
* Fetch /llms.txt from current site origin and include as context.
|
||||
* Only fetched once per origin per task.
|
||||
* @default false
|
||||
*/
|
||||
experimentalLlmsTxt?: boolean
|
||||
|
||||
/**
|
||||
* Transform page content before sending to LLM.
|
||||
* Called after DOM extraction and simplification, before LLM invocation.
|
||||
* Use cases: inspect extraction results, modify page info, mask sensitive data.
|
||||
*
|
||||
* @param content - Simplified page content that will be sent to LLM
|
||||
* @returns Transformed content
|
||||
*
|
||||
* @example
|
||||
* // Mask phone numbers
|
||||
* transformPageContent: async (content) => {
|
||||
* return content.replace(/1[3-9]\d{9}/g, '***********')
|
||||
* }
|
||||
*/
|
||||
transformPageContent?: (content: string) => Promise<string> | string
|
||||
|
||||
/**
|
||||
* Completely override the default system prompt.
|
||||
* @experimental Use with caution - incorrect prompts may break agent behavior.
|
||||
*/
|
||||
customSystemPrompt?: string
|
||||
}
|
||||
|
||||
/**
|
||||
* Agent reflection state - the reflection-before-action model
|
||||
*
|
||||
|
||||
Reference in New Issue
Block a user