zoushiyang/page-agent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: unify zod imports

Browse Source
This commit is contained in:
Simon
2026-02-25 16:18:56 +08:00
parent 49bdc70c78
commit 22fe448d95
4 changed files with 46 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
packages/core/src/PageAgentCore.ts
View File

@@ -5,7 +5,7 @@
import { InvokeError, LLM, type Tool } from '@page-agent/llms'
import type { BrowserState, PageController } from '@page-agent/page-controller'
import chalk from 'chalk'
import * as zod from 'zod'
import * as z from 'zod'
import { type PageAgentConfig, type SupportedLanguage } from './config'
import { DEFAULT_MAX_STEPS } from './config/constants'
@@ -358,24 +358,22 @@ export class PageAgentCore extends EventTarget {
const tools = this.tools
const actionSchemas = Array.from(tools.entries()).map(([toolName, tool]) => {
return zod.object({ [toolName]: tool.inputSchema }).describe(tool.description)
return z.object({ [toolName]: tool.inputSchema }).describe(tool.description)
})
const actionSchema = zod.union(
actionSchemas as unknown as [zod.ZodType, zod.ZodType, ...zod.ZodType[]]
)
const actionSchema = z.union(actionSchemas as unknown as [z.ZodType, z.ZodType, ...z.ZodType[]])
const macroToolSchema = zod.object({
// thinking: zod.string().optional(),
evaluation_previous_goal: zod.string().optional(),
memory: zod.string().optional(),
next_goal: zod.string().optional(),
const macroToolSchema = z.object({
// thinking: z.string().optional(),
evaluation_previous_goal: z.string().optional(),
memory: z.string().optional(),
next_goal: z.string().optional(),
action: actionSchema,
})
return {
description: 'You MUST call this tool every step!',
inputSchema: macroToolSchema as zod.ZodType<MacroToolInput>,
inputSchema: macroToolSchema as z.ZodType<MacroToolInput>,
execute: async (input: MacroToolInput): Promise<MacroToolResult> => {
// abort
if (this.#abortController.signal.aborted) throw new Error('AbortError')

56
packages/core/src/tools/index.ts
View File

@@ -2,7 +2,7 @@
* Internal tools for PageAgent.
* @note Adapted from browser-use
*/
import * as zod from 'zod'
import * as z from 'zod'
import type { PageAgentCore } from '../PageAgentCore'
import { waitFor } from '../utils'
@@ -13,7 +13,7 @@ import { waitFor } from '../utils'
export interface PageAgentTool<TParams = any> {
// name: string
description: string
inputSchema: zod.ZodType<TParams>
inputSchema: z.ZodType<TParams>
execute: (this: PageAgentCore, args: TParams) => Promise<string>
}
@@ -32,9 +32,9 @@ tools.set(
tool({
description:
'Complete task. Text is your final response to the user — keep it concise unless the user explicitly asks for detail.',
inputSchema: zod.object({
text: zod.string(),
success: zod.boolean().default(true),
inputSchema: z.object({
text: z.string(),
success: z.boolean().default(true),
}),
execute: async function (this: PageAgentCore, input) {
// @note main loop will handle this one
@@ -47,8 +47,8 @@ tools.set(
'wait',
tool({
description: 'Wait for x seconds. Can be used to wait until the page or data is fully loaded.',
inputSchema: zod.object({
seconds: zod.number().min(1).max(10).default(1),
inputSchema: z.object({
seconds: z.number().min(1).max(10).default(1),
}),
execute: async function (this: PageAgentCore, input) {
// try to subtract LLM calling time from the actual wait time
@@ -67,8 +67,8 @@ tools.set(
tool({
description:
'Ask the user a question and wait for their answer. Use this if you need more information or clarification.',
inputSchema: zod.object({
question: zod.string(),
inputSchema: z.object({
question: z.string(),
}),
execute: async function (this: PageAgentCore, input) {
if (!this.onAskUser) {
@@ -84,8 +84,8 @@ tools.set(
'click_element_by_index',
tool({
description: 'Click element by index',
inputSchema: zod.object({
index: zod.int().min(0),
inputSchema: z.object({
index: z.int().min(0),
}),
execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.clickElement(input.index)
@@ -98,9 +98,9 @@ tools.set(
'input_text',
tool({
description: 'Click and type text into an interactive input element',
inputSchema: zod.object({
index: zod.int().min(0),
text: zod.string(),
inputSchema: z.object({
index: z.int().min(0),
text: z.string(),
}),
execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.inputText(input.index, input.text)
@@ -114,9 +114,9 @@ tools.set(
tool({
description:
'Select dropdown option for interactive element index by the text of the option you want to select',
inputSchema: zod.object({
index: zod.int().min(0),
text: zod.string(),
inputSchema: z.object({
index: z.int().min(0),
text: z.string(),
}),
execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.selectOption(input.index, input.text)
@@ -132,11 +132,11 @@ tools.set(
'scroll',
tool({
description: 'Scroll the page vertically. Use index for scroll elements (dropdowns/custom UI).',
inputSchema: zod.object({
down: zod.boolean().default(true),
num_pages: zod.number().min(0).max(10).optional().default(0.1),
pixels: zod.number().int().min(0).optional(),
index: zod.number().int().min(0).optional(),
inputSchema: z.object({
down: z.boolean().default(true),
num_pages: z.number().min(0).max(10).optional().default(0.1),
pixels: z.number().int().min(0).optional(),
index: z.number().int().min(0).optional(),
}),
execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.scroll({
@@ -156,10 +156,10 @@ tools.set(
tool({
description:
'Scroll the page horizontally, or within a specific element by index. Useful for wide tables.',
inputSchema: zod.object({
right: zod.boolean().default(true),
pixels: zod.number().int().min(0),
index: zod.number().int().min(0).optional(),
inputSchema: z.object({
right: z.boolean().default(true),
pixels: z.number().int().min(0),
index: z.number().int().min(0).optional(),
}),
execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.scrollHorizontally(input)
@@ -173,8 +173,8 @@ tools.set(
tool({
description:
'Execute JavaScript code on the current page. Supports async/await syntax. Use with caution!',
inputSchema: zod.object({
script: zod.string(),
inputSchema: z.object({
script: z.string(),
}),
execute: async function (this: PageAgentCore, input) {
const result = await this.pageController.executeJavascript(input.script)

16
packages/extension/src/agent/tabTools.ts
View File

@@ -6,14 +6,14 @@
* - switch_to_tab: Switch to an existing tab
* - close_tab: Close a tab (optionally switch to another)
*/
import * as zod from 'zod'
import * as z from 'zod'
import type { TabsController } from './TabsController'
/** Tool definition compatible with PageAgentCore customTools */
interface TabTool {
description: string
inputSchema: zod.ZodType
inputSchema: z.ZodType
execute: (input: unknown) => Promise<string>
}
@@ -26,8 +26,8 @@ export function createTabTools(tabsController: TabsController): Record<string, T
open_new_tab: {
description:
'Open a new browser tab with the specified URL. The new tab becomes the current tab for all subsequent page operations.',
inputSchema: zod.object({
url: zod.string().describe('The URL to open in the new tab'),
inputSchema: z.object({
url: z.string().describe('The URL to open in the new tab'),
}),
execute: async (input: unknown) => {
const { url } = input as { url: string }
@@ -42,8 +42,8 @@ export function createTabTools(tabsController: TabsController): Record<string, T
switch_to_tab: {
description:
'Switch to an existing tab by its ID. After switching, all page operations will target the new current tab. You can only switch to tabs in the tab list shown in browser state.',
inputSchema: zod.object({
tab_id: zod.number().int().describe('The tab ID to switch to'),
inputSchema: z.object({
tab_id: z.number().int().describe('The tab ID to switch to'),
}),
execute: async (input: unknown) => {
const { tab_id } = input as { tab_id: number }
@@ -58,8 +58,8 @@ export function createTabTools(tabsController: TabsController): Record<string, T
close_tab: {
description:
'Close a tab by its ID. Cannot close the initial tab. Optionally specify which tab to switch to after closing.',
inputSchema: zod.object({
tab_id: zod.number().int().describe('The tab ID to close'),
inputSchema: z.object({
tab_id: z.number().int().describe('The tab ID to close'),
}),
execute: async (input: unknown) => {
const { tab_id } = input as { tab_id: number }

2
packages/llms/src/types.ts
View File

@@ -1,7 +1,7 @@
/**
* Core types for LLM integration
*/
import type { z } from 'zod'
import type * as z from 'zod'
/**
* Message format - OpenAI standard (industry standard)