Agent

Defined in: src/agent/agent.ts:182

Orchestrates the interaction between a model, a set of tools, and MCP clients. The Agent is responsible for managing the lifecycle of tools and clients and invoking the core decision-making loop.

Implements

• AgentData

Constructors

Constructor

new Agent(config?): Agent;

Defined in: src/agent/agent.ts:236

Creates an instance of the Agent.

Parameters

Parameter	Type	Description
config?	AgentConfig	The configuration for the agent.

Returns

Agent

Properties

messages

readonly messages: Message[];

Defined in: src/agent/agent.ts:186

The conversation history of messages between user and assistant.

Implementation of

AgentData.messages

---

state

readonly state: AppState;

Defined in: src/agent/agent.ts:191

App state storage accessible to tools and application logic. State is not passed to the model during inference.

Implementation of

AgentData.state

---

model

model: Model;

Defined in: src/agent/agent.ts:197

The model provider used by the agent for inference.

---

systemPrompt?

optional systemPrompt: SystemPrompt;

Defined in: src/agent/agent.ts:202

The system prompt to pass to the model provider.

---

name

readonly name: string;

Defined in: src/agent/agent.ts:207

The name of the agent.

---

agentId

readonly agentId: string;

Defined in: src/agent/agent.ts:212

The unique identifier of the agent instance.

---

description?

readonly optional description: string;

Defined in: src/agent/agent.ts:217

Optional description of what the agent does.

Accessors

tools

Get Signature

get tools(): Tool[];

Defined in: src/agent/agent.ts:352

The tools this agent can use.

Returns

Tool[]

---

toolRegistry

Get Signature

get toolRegistry(): ToolRegistry;

Defined in: src/agent/agent.ts:359

The tool registry for managing the agent’s tools.

Returns

ToolRegistry

The tool registry for registering tools with the agent.

Implementation of

AgentData.toolRegistry

Methods

addHook()

addHook<T>(eventType, callback): HookCleanup;

Defined in: src/agent/agent.ts:306

Register a hook callback for a specific event type.

Type Parameters

Type Parameter
T extends HookableEvent

Parameters

Parameter	Type	Description
eventType	HookableEventConstructor<T>	The event class constructor to register the callback for
callback	HookCallback<T>	The callback function to invoke when the event occurs

Returns

HookCleanup

Cleanup function that removes the callback when invoked

Example

const agent = new Agent({ model })

const cleanup = agent.addHook(BeforeInvocationEvent, (event) => {
  console.log('Invocation started')
})

// Later, to remove the hook:
cleanup()

Implementation of

AgentData.addHook

---

initialize()

initialize(): Promise<void>;

Defined in: src/agent/agent.ts:310

Returns

Promise<void>

---

invoke()

invoke(args, options?): Promise<AgentResult>;

Defined in: src/agent/agent.ts:381

Invokes the agent and returns the final result.

This is a convenience method that consumes the stream() method and returns only the final AgentResult. Use stream() if you need access to intermediate streaming events.

Parameters

Parameter	Type	Description
args	InvokeArgs	Arguments for invoking the agent
options?	InvokeOptions	Optional per-invocation options

Returns

Promise<AgentResult>

Promise that resolves to the final AgentResult

Example

const agent = new Agent({ model, tools })
const result = await agent.invoke('What is 2 + 2?')
console.log(result.lastMessage) // Agent's response

---

stream()

stream(args, options?): AsyncGenerator<AgentStreamEvent, AgentResult, undefined>;

Defined in: src/agent/agent.ts:420

Streams the agent execution, yielding events and returning the final result.

The agent loop manages the conversation flow by:

1. Streaming model responses and yielding all events
2. Executing tools when the model requests them
3. Continuing the loop until the model completes without tool use

Use this method when you need access to intermediate streaming events. For simple request/response without streaming, use invoke() instead.

An explicit goal of this method is to always leave the message array in a way that the agent can be reinvoked with a user prompt after this method completes. To that end assistant messages containing tool uses are only added after tool execution succeeds with valid toolResponses

Parameters

Parameter	Type	Description
args	InvokeArgs	Arguments for invoking the agent
options?	InvokeOptions	Optional per-invocation options

Returns

AsyncGenerator<AgentStreamEvent, AgentResult, undefined>

Async generator that yields AgentStreamEvent objects and returns AgentResult

Example

const agent = new Agent({ model, tools })

for await (const event of agent.stream('Hello')) {
  console.log('Event:', event.type)
}
// Messages array is mutated in place and contains the full conversation