Agent

The class representing an AI agent configured with instructions, tools, guardrails, handoffs and more.

We strongly recommend passing instructions, which is the “system prompt” for the agent. In addition, you can pass handoffDescription, which is a human-readable description of the agent, used when the agent is used inside tools/handoffs.

Agents are generic on the context type. The context is a (mutable) object you create. It is passed to tool functions, handoffs, guardrails, etc.

Extends

AgentHooks<TContext, TOutput>

Type Parameters

Type Parameter	Default type
`TContext`	`UnknownContext`
`TOutput` extends `AgentOutputType`	`TextOutput`

Implements

AgentConfiguration<TContext, TOutput>

Constructors

Constructor

new Agent<TContext, TOutput>(config): Agent<TContext, TOutput>

Parameters

Parameter	Type	Description
`config`	{ `handoffDescription`: `string`; `handoffOutputTypeWarningEnabled`: `boolean`; `handoffs`: ( \| `Agent`<`any`, `any`> \| `Handoff`<`any`, `TOutput`>)[]; `inputGuardrails`: `InputGuardrail`[]; `instructions`: `string` \| (`runContext`, `agent`) => `string` \| `Promise`<`string`>; `mcpServers`: `MCPServer`[]; `model`: \| `string` \| `Model`; `modelSettings`: `ModelSettings`; `name`: `string`; `outputGuardrails`: `OutputGuardrail`<`TOutput`>[]; `outputType`: `TOutput`; `resetToolChoice`: `boolean`; `tools`: `Tool`<`TContext`>[]; `toolUseBehavior`: `ToolUseBehavior`; }	‐
`config.handoffDescription`?	`string`	A description of the agent. This is used when the agent is used as a handoff, so that an LLM knows what it does and when to invoke it.
`config.handoffOutputTypeWarningEnabled`?	`boolean`	The warning log would be enabled when multiple output types by handoff agents are detected.
`config.handoffs`?	( \| `Agent`<`any`, `any`> \| `Handoff`<`any`, `TOutput`>)[]	Handoffs are sub-agents that the agent can delegate to. You can provide a list of handoffs, and the agent can choose to delegate to them if relevant. Allows for separation of concerns and modularity.
`config.inputGuardrails`?	`InputGuardrail`[]	A list of checks that run in parallel to the agent’s execution, before generating a response. Runs only if the agent is the first agent in the chain.
`config.instructions`?	`string` \| (`runContext`, `agent`) => `string` \| `Promise`<`string`>	The instructions for the agent. Will be used as the “system prompt” when this agent is invoked. Describes what the agent should do, and how it responds. Can either be a string, or a function that dynamically generates instructions for the agent. If you provide a function, it will be called with the context and the agent instance. It must return a string.
`config.mcpServers`?	`MCPServer`[]	A list of Model Context Protocol servers the agent can use. Every time the agent runs, it will include tools from these servers in the list of available tools. NOTE: You are expected to manage the lifecycle of these servers. Specifically, you must call `server.connect()` before passing it to the agent, and `server.cleanup()` when the server is no longer needed.
`config.model`?	\| `string` \| `Model`	The model implementation to use when invoking the LLM. By default, if not set, the agent will use the default model configured in modelSettings.defaultModel
`config.modelSettings`?	`ModelSettings`	Configures model-specific tuning parameters (e.g. temperature, top_p, etc.)
`config.name`	`string`	The name of the agent.
`config.outputGuardrails`?	`OutputGuardrail`<`TOutput`>[]	A list of checks that run on the final output of the agent, after generating a response. Runs only if the agent produces a final output.
`config.outputType`?	`TOutput`	The type of the output object. If not provided, the output will be a string.
`config.resetToolChoice`?	`boolean`	Wether to reset the tool choice to the default value after a tool has been called. Defaults to `true`. This ensures that the agent doesn’t enter an infinite loop of tool usage.
`config.tools`?	`Tool`<`TContext`>[]	A list of tools the agent can use.
`config.toolUseBehavior`?	`ToolUseBehavior`	This lets you configure how tool use is handled. run_llm_again: The default behavior. Tools are run, and then the LLM receives the results and gets to respond. stop_on_first_tool: The output of the frist tool call is used as the final output. This means that the LLM does not process the result of the tool call. A list of tool names: The agent will stop running if any of the tools in the list are called. The final output will be the output of the first matching tool call. The LLM does not process the result of the tool call. A function: if you pass a function, it will be called with the run context and the list of tool results. It must return a `ToolsToFinalOutputResult`, which determines whether the tool call resulted in a final output. NOTE: This configuration is specific to `FunctionTools`. Hosted tools, such as file search, web search, etc. are always processed by the LLM

Returns

Agent<TContext, TOutput>

Overrides

AgentHooks.constructor

Properties

handoffDescription

handoffDescription: string;

A description of the agent. This is used when the agent is used as a handoff, so that an LLM knows what it does and when to invoke it.

Implementation of

AgentConfiguration.handoffDescription

handoffs

handoffs: (
  | Agent<any, TOutput>
  | Handoff<any, TOutput>)[];

Handoffs are sub-agents that the agent can delegate to. You can provide a list of handoffs, and the agent can choose to delegate to them if relevant. Allows for separation of concerns and modularity.

Implementation of

AgentConfiguration.handoffs

inputGuardrails

inputGuardrails: InputGuardrail[];

A list of checks that run in parallel to the agent’s execution, before generating a response. Runs only if the agent is the first agent in the chain.

Implementation of

AgentConfiguration.inputGuardrails

instructions

instructions: string | (runContext, agent) => string | Promise<string>;

The instructions for the agent. Will be used as the “system prompt” when this agent is invoked. Describes what the agent should do, and how it responds.

Can either be a string, or a function that dynamically generates instructions for the agent. If you provide a function, it will be called with the context and the agent instance. It must return a string.

Implementation of

AgentConfiguration.instructions

mcpServers

mcpServers: MCPServer[];

A list of Model Context Protocol servers the agent can use. Every time the agent runs, it will include tools from these servers in the list of available tools.

NOTE: You are expected to manage the lifecycle of these servers. Specifically, you must call server.connect() before passing it to the agent, and server.cleanup() when the server is no longer needed.

Implementation of

AgentConfiguration.mcpServers

model

model:
  | string
  | Model;

The model implementation to use when invoking the LLM. By default, if not set, the agent will use the default model configured in modelSettings.defaultModel

Implementation of

AgentConfiguration.model

modelSettings

modelSettings: ModelSettings;

Configures model-specific tuning parameters (e.g. temperature, top_p, etc.)

Implementation of

AgentConfiguration.modelSettings

name

name: string;

The name of the agent.

Implementation of

AgentConfiguration.name

outputGuardrails

outputGuardrails: OutputGuardrail<AgentOutputType<unknown>>[];

A list of checks that run on the final output of the agent, after generating a response. Runs only if the agent produces a final output.

Implementation of

AgentConfiguration.outputGuardrails

outputType

outputType: TOutput;

The type of the output object. If not provided, the output will be a string.

Implementation of

AgentConfiguration.outputType

resetToolChoice

resetToolChoice: boolean;

Wether to reset the tool choice to the default value after a tool has been called. Defaults to true. This ensures that the agent doesn’t enter an infinite loop of tool usage.

Implementation of

AgentConfiguration.resetToolChoice

tools

tools: Tool<TContext>[];

A list of tools the agent can use.

Implementation of

AgentConfiguration.tools

toolUseBehavior

toolUseBehavior: ToolUseBehavior;

This lets you configure how tool use is handled.

run_llm_again: The default behavior. Tools are run, and then the LLM receives the results and gets to respond.
stop_on_first_tool: The output of the frist tool call is used as the final output. This means that the LLM does not process the result of the tool call.
A list of tool names: The agent will stop running if any of the tools in the list are called. The final output will be the output of the first matching tool call. The LLM does not process the result of the tool call.
A function: if you pass a function, it will be called with the run context and the list of tool results. It must return a ToolsToFinalOutputResult, which determines whether the tool call resulted in a final output.

NOTE: This configuration is specific to FunctionTools. Hosted tools, such as file search, web search, etc. are always processed by the LLM

Implementation of

AgentConfiguration.toolUseBehavior

Accessors

outputSchemaName

Get Signature

get outputSchemaName(): string

Ouput schema name

Returns

string

Methods

asTool()

asTool(options): FunctionTool

Transform this agent into a tool, callable by other agents.

This is different from handoffs in two ways:

In handoffs, the new agent receives the conversation history. In this tool, the new agent receives generated input.
In handoffs, the new agent takes over the conversation. In this tool, the new agent is called as a tool, and the conversation is continued by the original agent.

Parameters

Parameter	Type	Description
`options`	{ `customOutputExtractor`: (`output`) => `string` \| `Promise`<`string`>; `toolDescription`: `string`; `toolName`: `string`; }	Options for the tool.
`options.customOutputExtractor`?	(`output`) => `string` \| `Promise`<`string`>	A function that extracts the output text from the agent. If not provided, the last message from the agent will be used.
`options.toolDescription`?	`string`	The description of the tool, which should indicate what the tool does and when to use it.
`options.toolName`?	`string`	The name of the tool. If not provided, the name of the agent will be used.

Returns

FunctionTool

A tool that runs the agent and returns the output text.

clone()

clone(config): Agent<TContext, TOutput>

Makes a copy of the agent, with the given arguments changed. For example, you could do:

const newAgent = agent.clone({ instructions: 'New instructions' })

Parameters

Parameter	Type	Description
`config`	`Partial`<`AgentConfiguration`<`TContext`, `TOutput`>>	A partial configuration to change.

Returns

Agent<TContext, TOutput>

A new agent with the given changes.

emit()

emit<K>(type, ...args): boolean

Type Parameters

Type Parameter
`K` extends keyof `AgentHookEvents`<`TContext`, `TOutput`>

Parameters

Parameter	Type
`type`	`K`
…`args`	`AgentHookEvents`<`TContext`, `TOutput`>[`K`]

Returns

boolean

Inherited from

AgentHooks.emit

getAllTools()

getAllTools(): Promise<Tool<TContext>[]>

ALl agent tools, including the MCPl and function tools.

Returns

Promise<Tool<TContext>[]>

all configured tools

getMcpTools()

getMcpTools(): Promise<Tool<TContext>[]>

Fetches the available tools from the MCP servers.

Returns

Promise<Tool<TContext>[]>

the MCP powered tools

getSystemPrompt()

getSystemPrompt(runContext): Promise<undefined | string>

Returns the system prompt for the agent.

If the agent has a function as its instructions, this function will be called with the runContext and the agent instance.

Parameters

Parameter	Type
`runContext`	`RunContext`<`TContext`>

Returns

Promise<undefined | string>

off()

off<K>(type, listener): EventEmitter<AgentHookEvents<TContext, TOutput>>

Type Parameters

Type Parameter
`K` extends keyof `AgentHookEvents`<`TContext`, `TOutput`>

Parameters

Parameter	Type
`type`	`K`
`listener`	(…`args`) => `void`

Returns

EventEmitter<AgentHookEvents<TContext, TOutput>>

Inherited from

AgentHooks.off

on()

on<K>(type, listener): EventEmitter<AgentHookEvents<TContext, TOutput>>

Type Parameters

Type Parameter
`K` extends keyof `AgentHookEvents`<`TContext`, `TOutput`>

Parameters

Parameter	Type
`type`	`K`
`listener`	(…`args`) => `void`

Returns

EventEmitter<AgentHookEvents<TContext, TOutput>>

Inherited from

AgentHooks.on

once()

once<K>(type, listener): EventEmitter<AgentHookEvents<TContext, TOutput>>

Type Parameters

Type Parameter
`K` extends keyof `AgentHookEvents`<`TContext`, `TOutput`>

Parameters

Parameter	Type
`type`	`K`
`listener`	(…`args`) => `void`

Returns

EventEmitter<AgentHookEvents<TContext, TOutput>>

Inherited from

AgentHooks.once

processFinalOutput()

processFinalOutput(output): ResolvedAgentOutput<TOutput>

Processes the final output of the agent.

Parameters

Parameter	Type	Description
`output`	`string`	The output of the agent.

Returns

ResolvedAgentOutput<TOutput>

The parsed out.

toJSON()

toJSON(): object

Returns a JSON representation of the agent, which is serializable.

Returns

object

A JSON object containing the agent’s name.

name

name: string;

create()

static create<TOutput, Handoffs>(config): Agent<unknown, TOutput | HandoffsOutputUnion<Handoffs>>

Create an Agent with handoffs and automatically infer the union type for TOutput from the handoff agents’ output types.

Type Parameters

Type Parameter	Default type
`TOutput` extends `AgentOutputType`<`unknown`>	`"text"`
`Handoffs` extends readonly ( \| `Agent`<`any`, `any`> \| `Handoff`<`any`, `any`>)[]	[]

Parameters

Parameter	Type
`config`	`AgentConfigWithHandoffs`<`TOutput`, `Handoffs`>

Returns

Agent<unknown, TOutput | HandoffsOutputUnion<Handoffs>>