导航|地址|刷新
Configuration

Skip to contentDocumentation Index
Fetch the complete documentation index at: https://developers.cloudflare.com/agents/llms.txt
Use this file to discover all available pages before exploring further.

Docs Directory API SDKs Changelog

Search

Log in

Agents

/

Overview

Getting started

Quick start

Add to existing project

Testing your Agents

Concepts

What are agents?

Conversation state and memory

Tools

Calling LLMs

Using Agents with Workflows

Agentic patterns

Overview

Human-in-the-loop patterns

Long-running agents

Communication channels

Chat

Chat agents

Autonomous responses

Client SDK

Voice

Email

Slack

Webhooks

Overview

Push notifications

Tools

Sandbox

MCP

Browser

AI Search

Agentic Payments

Overview

Charge for HTTP content

x402

Overview

Charge for HTTP content

Charge for MCP tools

Pay from Agents SDK

Pay from coding tools

MPP (Machine Payments Protocol)

Code Mode

Overview

Create a durable Code Mode runtime

AI SDK integration

Use Code Mode with TanStack AI

Browser-owned tools

MCP

OpenAPI

How Code Mode works

Code Mode API reference

Harnesses

Overview

Think

Overview

Getting started

Configuration

Tools

Actions

Lifecycle hooks

Client tools

Messengers

Channels

Scheduled tasks

Workflows

Sub-agent RPC and programmatic turns

Programmatic submissions

Durable recovery

Runtime

Agents API

Lifecycle

Agent class internals

Callable methods

Store and sync state

Sessions

getCurrentAgent()

Communication

Routing

WebSockets

HTTP and Server-Sent Events

Chat SDK

Protocol messages

Readonly connections

Execution

Sub-agents

Schedule tasks

Durable execution with fibers

Queue tasks

Retries

Run Workflows

Agents as tools

Agent Skills

Operations

Configuration

Cross-domain authentication

Using AI Models

Observability

Examples

Chat agent

Slack agent

Voice agent

Browser agent

Email agent

Model Context Protocol (MCP)

Overview

APIs

MCP handler APIs

McpAgent

McpClient

Protocol

Tools

Authorization

Transport

MCP governance

Guides

Build MCP client

Build a Remote MCP server

Test a Remote MCP Server

Securing MCP servers

Connect to an MCP server

Handle OAuth with MCP servers

Migrate to MCP SDK v2

Build a single-tool Code Mode MCP server

Build a search and execute MCP server

Cloudflare

MCP server portals ↗

Cloudflare's own MCP servers

Overview

Cloudflare Community MCP Server

Code Mode MCP server patterns

Platform

Limits

Agent resources

Agent setup ↗

Cloudflare Skills ↗

Code Mode MCP Server ↗

Domain-specific MCP Servers ↗MCP

Agents llms.txt ↗

Agents llms-full.txt ↗

Cloudflare Docs llms.txt ↗

Cloudflare Docs llms-full.txt ↗

Home

/Agents

/…
Harnesses

/Think

/Configuration

Configuration

Last updated Jul 22, 2026|Copy as Markdown|View as Markdown|Agent setup

OverviewConfiguration overridesDynamic configurationSession integrationPackage exportsDependencies

Think is configured by overriding methods and properties on your Think subclass. Most agents only override getModel().

Configuration overrides

Method / Property Default Description
getModel() throws Return the LanguageModel to use
getSystemPrompt() "You are a helpful assistant." System prompt (fallback when no context blocks)
getTools() {} AI SDK ToolSet for the agentic loop
getScheduledTasks() {} Code-declared recurring prompts or handlers — refer to Scheduled tasks
getDefaultTimezone() undefined Default timezone for wall-clock scheduled tasks
getMessengers() {} Messenger ingress and delivery declarations — refer to Messengers
maxSteps 10 Max tool-call rounds per turn
sendReasoning true Send reasoning chunks to chat clients
configureSession() identity Add context blocks, compaction, search, skills — refer to Sessions
getSkills() [] Return Agent Skills sources for on-demand skill activation — refer to Agent Skills
getSkillScriptRunner() null Enable the optional run_skill_script tool
workspaceBash true Include or configure the default workspace bash tool — refer to Tools
messageConcurrency "queue" How overlapping submits behave — refer to Client tools
includeMcpTools true Convert connected MCP tools to AI SDK tools and add them to model turns. Refer to MCP tools
waitForMcpConnections false Wait for MCP servers before inference
chatRecovery true Wrap WebSocket, sub-agent, programmatic, and continuation turns in runFiber for durable execution. Set to a configuration object with maxAttempts, stableTimeoutMs, terminalMessage, and onExhausted to tune bounded recovery
chatStreamStallTimeoutMs 0 (off) Opt-in inactivity watchdog: abort a turn whose model stream produces no chunk for this long (measures the gap between chunks, including tool execution). With chatRecovery on, a stall routes into bounded recovery
contextOverflow undefined Opt-in mid-turn context-overflow handling with reactive, maxRetries, and proactive options. Requires classifyChatError plus a session compaction function — refer to Context-window overflow recovery

For chatRecovery and chatStreamStallTimeoutMs behavior, refer to Durable recovery.

Dynamic configuration

Think's class generics match Agent<Env, State, Props>. Persisted runtime configuration is typed at the configure<T>() and getConfig<T>() call sites, stored in SQLite, and survives hibernation and restarts.

export class MyAgent extends Think { getModel() { const tier = this.getConfig()?.modelTier ?? "fast"; const models = { fast: "@cf/moonshotai/kimi-k2.6", capable: "@cf/meta/llama-4-scout-17b-16e-instruct", }; return createWorkersAI({ binding: this.env.AI })(models[tier]); }}

type MyConfig = { modelTier: "fast" | "capable"; theme: string };export class MyAgent extends Think<Env> { getModel() { const tier = this.getConfig<MyConfig>()?.modelTier ?? "fast"; const models = { fast: "@cf/moonshotai/kimi-k2.6", capable: "@cf/meta/llama-4-scout-17b-16e-instruct", }; return createWorkersAI({ binding: this.env.AI })(models[tier]); }}

Method Description
configure<T>(config: T) Persist a typed configuration object
getConfig<T>(): T | null Read the persisted configuration, or null if never configured

Expose configuration to the client via @callable:

import { callable } from "agents";export class MyAgent extends Think { getModel() { /* ... */ } @callable() updateConfig(config) { this.configure(config); }}

import { callable } from "agents";export class MyAgent extends Think<Env> { getModel() { /* ... */ } @callable() updateConfig(config: MyConfig) { this.configure<MyConfig>(config); }}

Session integration

Think stores conversations in a Session — the storage layer that holds your messages and gives the model writable memory. Two concepts come up here: context blocks are labelled sections of the system prompt the model can read and update (for example, a memory block of facts about the user), and compaction summarizes older messages so long conversations stay within the model's context window. Override configureSession to add persistent memory, compaction, search, and skills:

import { Think, Session } from "@cloudflare/think";export class MyAgent extends Think { getModel() { /* ... */ } configureSession(session) { return session .withContext("soul", { provider: { get: async () => "You are a helpful coding assistant." }, }) .withContext("memory", { description: "Important facts learned during conversation.", maxTokens: 2000, }) .withCachedPrompt(); }}

import { Think, Session } from "@cloudflare/think";export class MyAgent extends Think<Env> { getModel() { /* ... */ } configureSession(session: Session) { return session .withContext("soul", { provider: { get: async () => "You are a helpful coding assistant." }, }) .withContext("memory", { description: "Important facts learned during conversation.", maxTokens: 2000, }) .withCachedPrompt(); }}

When configureSession adds context blocks, Think builds the system prompt from those blocks instead of using getSystemPrompt(). Think's this.messages getter reads directly from Session's tree-structured storage.

For the full Session API — context blocks, compaction, search, skills, and multi-session support — refer to the Sessions documentation.

Package exports

Export Description
@cloudflare/think Think, Session, Workspace, skills namespace
@cloudflare/think/messengers Messenger contracts, Chat SDK bridge, state agent, delivery
@cloudflare/think/messengers/telegram Telegram messenger provider and delivery helpers
@cloudflare/think/workflows ThinkWorkflow, step.prompt() — Workflow prompts
@cloudflare/think/tools/workspace createWorkspaceTools() — for custom storage backends
@cloudflare/think/tools/execute createExecuteTool() — sandboxed code execution via Code Mode
@cloudflare/think/tools/browser createBrowserTools() — Chrome DevTools Protocol tools
@cloudflare/think/tools/extensions createExtensionTools() — LLM-driven extension loading
@cloudflare/think/extensions ExtensionManager, HostBridgeLoopback — extension runtime

Dependencies

Peer dependencies you provide:

Package Required Notes
agents yes Cloudflare Agents SDK
ai yes AI SDK v6
zod yes Schema validation (v4)
@chat-adapter/telegram optional Required for Telegram messengers

Bundled with @cloudflare/think:

Package Notes
@cloudflare/shell Workspace filesystem
@cloudflare/codemode Code execution for createExecuteTool()
just-bash Sandboxed shell for the default workspace bash tool

The Agent Skills engine and its script runner live in agents/skills, so skill scripts pull @cloudflare/worker-bundler and just-bash through agents, not Think.

PreviousGetting startedNextTools

Was this helpful?

YesNo

Edit pageReport issue

On this page

Overview

Configuration overrides

Dynamic configuration

Session integration

Package exports

Dependencies

Edit pageReport issue

Getting started
PlansContact salesPartnersFind a partnerStartupsUnder attack?Domain name search

Company
AboutCareersInvestorsPressPress kitGlobal network

Public interest
Project GalileoAthenian ProjectCloudflare for CampaignsProject FairshotImpact/ESG

Compliance
Compliance resourcesTrust HubData ProtectionResponsible AITransparency reportReport abuse

Resources
App innovation reportCloudflare RadarCase studiesStatusSupportEventsBlog

Developers
DocumentationLearning centerCommunity

Solutions
SSE and SASE platformCloudflare AI CloudAI SecurityFrontend Development PlatformMulti-Tenant Platform DevelopmentWeb Security Platform

Start BuildingLog In

© 2026 Cloudflare, Inc.

Privacy policy|Report security issues|Terms of use|Trademark
|
Your privacy choices

Docs

------
导航页打开网址

Method / Property	Default	Description
getModel()	throws	Return the LanguageModel to use
getSystemPrompt()	"You are a helpful assistant."	System prompt (fallback when no context blocks)
getTools()	{}	AI SDK ToolSet for the agentic loop
getScheduledTasks()	{}	Code-declared recurring prompts or handlers — refer to Scheduled tasks
getDefaultTimezone()	undefined	Default timezone for wall-clock scheduled tasks
getMessengers()	{}	Messenger ingress and delivery declarations — refer to Messengers
maxSteps	10	Max tool-call rounds per turn
sendReasoning	true	Send reasoning chunks to chat clients
configureSession()	identity	Add context blocks, compaction, search, skills — refer to Sessions
getSkills()	[]	Return Agent Skills sources for on-demand skill activation — refer to Agent Skills
getSkillScriptRunner()	null	Enable the optional run_skill_script tool
workspaceBash	true	Include or configure the default workspace bash tool — refer to Tools
messageConcurrency	"queue"	How overlapping submits behave — refer to Client tools
includeMcpTools	true	Convert connected MCP tools to AI SDK tools and add them to model turns. Refer to MCP tools
waitForMcpConnections	false	Wait for MCP servers before inference
chatRecovery	true	Wrap WebSocket, sub-agent, programmatic, and continuation turns in runFiber for durable execution. Set to a configuration object with maxAttempts, stableTimeoutMs, terminalMessage, and onExhausted to tune bounded recovery
chatStreamStallTimeoutMs	0 (off)	Opt-in inactivity watchdog: abort a turn whose model stream produces no chunk for this long (measures the gap between chunks, including tool execution). With chatRecovery on, a stall routes into bounded recovery
contextOverflow	undefined	Opt-in mid-turn context-overflow handling with reactive, maxRetries, and proactive options. Requires classifyChatError plus a session compaction function — refer to Context-window overflow recovery

Method	Description
configure<T>(config: T)	Persist a typed configuration object
getConfig<T>(): T \| null	Read the persisted configuration, or null if never configured

Export	Description
@cloudflare/think	Think, Session, Workspace, skills namespace
@cloudflare/think/messengers	Messenger contracts, Chat SDK bridge, state agent, delivery
@cloudflare/think/messengers/telegram	Telegram messenger provider and delivery helpers
@cloudflare/think/workflows	ThinkWorkflow, step.prompt() — Workflow prompts
@cloudflare/think/tools/workspace	createWorkspaceTools() — for custom storage backends
@cloudflare/think/tools/execute	createExecuteTool() — sandboxed code execution via Code Mode
@cloudflare/think/tools/browser	createBrowserTools() — Chrome DevTools Protocol tools
@cloudflare/think/tools/extensions	createExtensionTools() — LLM-driven extension loading
@cloudflare/think/extensions	ExtensionManager, HostBridgeLoopback — extension runtime

Package	Required	Notes
agents	yes	Cloudflare Agents SDK
ai	yes	AI SDK v6
zod	yes	Schema validation (v4)
@chat-adapter/telegram	optional	Required for Telegram messengers

Package	Notes
@cloudflare/shell	Workspace filesystem
@cloudflare/codemode	Code execution for createExecuteTool()
just-bash	Sandboxed shell for the default workspace bash tool