StreamedRunResult

The result of an agent run in streaming mode.

Extends

• RunResultBase<TContext, TAgent>

Type Parameters

Type Parameter
TContext
TAgent extends Agent<TContext, AgentOutputType>

Implements

• AsyncIterable<RunStreamEvent>

Constructors

Constructor

new StreamedRunResult<TContext, TAgent>(result): StreamedRunResult<TContext, TAgent>;

Parameters

Parameter	Type
result	{ signal?: AbortSignal; state: RunState<TContext, TAgent>; }
result.signal?	AbortSignal
result.state	RunState<TContext, TAgent>

Returns

StreamedRunResult<TContext, TAgent>

Overrides

RunResultBase<TContext, TAgent>.constructor

Properties

currentTurn

currentTurn: number = 0;

The current turn number

---

maxTurns

maxTurns: undefined | number;

The maximum number of turns that can be run

---

state

readonly state: RunState<TContext, TAgent>;

The state of the run.

Inherited from

RunResultBase.state

Accessors

cancelled

Get Signature

get cancelled(): boolean;

Returns true if the stream has been cancelled.

Returns

boolean

---

completed

Get Signature

get completed(): Promise<void>;

Await this promise to ensure that the stream has been completed if you are not consuming the stream directly.

Returns

Promise<void>

---

currentAgent

Get Signature

get currentAgent(): undefined | TAgent;

The current agent that is running

Returns

undefined | TAgent

---

error

Get Signature

get error(): unknown;

Error thrown during the run, if any.

Returns

unknown

---

finalOutput

Get Signature

get finalOutput(): undefined | ResolvedAgentOutput<TAgent["outputType"]>;

The final output of the agent. If the output type was set to anything other than text, this will be parsed either as JSON or using the Zod schema you provided.

Returns

undefined | ResolvedAgentOutput<TAgent["outputType"]>

Inherited from

RunResultBase.finalOutput

---

history

Get Signature

get history(): AgentInputItem[];

The history of the agent run. This includes the input items and the new items generated during the agent run.

This can be used as inputs for the next agent run.

Returns

AgentInputItem[]

Inherited from

RunResultBase.history

---

input

Get Signature

get input():
  | string
  | AgentInputItem[];

A copy of the original input items.

Returns

| string | AgentInputItem[]

Inherited from

RunResultBase.input

---

inputGuardrailResults

Get Signature

get inputGuardrailResults(): InputGuardrailResult[];

Guardrail results for the input messages.

Returns

InputGuardrailResult[]

Inherited from

RunResultBase.inputGuardrailResults

---

interruptions

Get Signature

get interruptions(): RunToolApprovalItem[];

Any interruptions that occurred during the agent run for example for tool approvals.

Returns

RunToolApprovalItem[]

Inherited from

RunResultBase.interruptions

---

lastAgent

Get Signature

get lastAgent(): undefined | TAgent;

The last agent that was run

Returns

undefined | TAgent

Inherited from

RunResultBase.lastAgent

---

lastResponseId

Get Signature

get lastResponseId(): undefined | string;

The last response ID generated by the model during the agent run.

Returns

undefined | string

Inherited from

RunResultBase.lastResponseId

---

newItems

Get Signature

get newItems(): RunItem[];

The run items generated during the agent run. This associates the model data with the agents.

For the model data that can be used as inputs for the next agent run, use the output property.

Returns

RunItem[]

Inherited from

RunResultBase.newItems

---

output

Get Signature

get output(): AgentOutputItem[];

The new items generated during the agent run. These include things like new messages, tool calls and their outputs, etc.

It does not include information about the agents and instead represents the model data.

For the output including the agents, use the newItems property.

Returns

AgentOutputItem[]

Inherited from

RunResultBase.output

---

outputGuardrailResults

Get Signature

get outputGuardrailResults(): OutputGuardrailResult<OutputGuardrailMetadata, "text">[];

Guardrail results for the final output of the agent.

Returns

OutputGuardrailResult<OutputGuardrailMetadata, "text">[]

Inherited from

RunResultBase.outputGuardrailResults

---

rawResponses

Get Signature

get rawResponses(): ModelResponse[];

The raw LLM responses generated by the model during the agent run.

Returns

ModelResponse[]

Inherited from

RunResultBase.rawResponses

Methods

[asyncIterator]()

asyncIterator: AsyncIterator<RunStreamEvent>;

Returns

AsyncIterator<RunStreamEvent>

Implementation of

AsyncIterable.[asyncIterator]

---

toStream()

toStream(): ReadableStream<RunStreamEvent>;

Returns the underlying readable stream.

Returns

ReadableStream<RunStreamEvent>

A readable stream of the agent run.

---

toTextStream()

Call Signature

toTextStream(): ReadableStream<string>;

Returns a readable stream of the final text output of the agent run.

Returns

ReadableStream<string>

A readable stream of the final output of the agent run.

Call Signature

toTextStream(options?): Readable;

Returns a readable stream of the final text output of the agent run.

Parameters

Parameter	Type	Description
options?	{ compatibleWithNodeStreams: true; }	Options for the stream.
options.compatibleWithNodeStreams?	true	Whether to use Node.js streams or web standard streams.

Returns

Readable

A readable stream of the final output of the agent run.

Call Signature

toTextStream(options?): ReadableStream<string>;

Returns a readable stream of the final text output of the agent run.

Parameters

Parameter	Type	Description
options?	{ compatibleWithNodeStreams?: false; }	Options for the stream.
options.compatibleWithNodeStreams?	false	Whether to use Node.js streams or web standard streams.

Returns

ReadableStream<string>

A readable stream of the final output of the agent run.