Runner

A Runner is responsible for running an agent workflow.

Extends

• RunHooks<any, AgentOutputType<unknown>>

Constructors

Constructor

new Runner(config?): Runner

Parameters

Parameter	Type
config?	Partial<RunConfig>

Returns

Runner

Overrides

RunHooks<any, AgentOutputType<unknown>>.constructor

Properties

config

readonly config: RunConfig;

Methods

emit()

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

Type Parameters

Type Parameter
K extends keyof RunHookEvents<any, AgentOutputType<unknown>>

Parameters

Parameter	Type
type	K
…args	RunHookEvents<any, AgentOutputType<unknown>>[K]

Returns

boolean

Inherited from

RunHooks.emit

---

off()

off<K>(type, listener): EventEmitter<EventTypes>

Type Parameters

Type Parameter
K extends keyof RunHookEvents<any, AgentOutputType<unknown>>

Parameters

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

Returns

EventEmitter<EventTypes>

Inherited from

RunHooks.off

---

on()

on<K>(type, listener): EventEmitter<EventTypes>

Type Parameters

Type Parameter
K extends keyof RunHookEvents<any, AgentOutputType<unknown>>

Parameters

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

Returns

EventEmitter<EventTypes>

Inherited from

RunHooks.on

---

once()

once<K>(type, listener): EventEmitter<EventTypes>

Type Parameters

Type Parameter
K extends keyof RunHookEvents<any, AgentOutputType<unknown>>

Parameters

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

Returns

EventEmitter<EventTypes>

Inherited from

RunHooks.once

---

run()

Call Signature

run<TAgent, TContext>(
   agent,
   input,
options?): Promise<RunResult<TContext, TAgent>>

Run a workflow starting at the given agent. The agent will run in a loop until a final output is generated. The loop runs like so:

1. The agent is invoked with the given input.
2. If there is a final output (i.e. the agent produces something of type agent.outputType, the loop terminates.
3. If there’s a handoff, we run the loop again, with the new agent.
4. Else, we run tool calls (if any), and re-run the loop.

In two cases, the agent may raise an exception:

1. If the maxTurns is exceeded, a MaxTurnsExceeded exception is raised.
2. If a guardrail tripwire is triggered, a GuardrailTripwireTriggered exception is raised.

Note that only the first agent’s input guardrails are run.

Type Parameters

Type Parameter	Default type
TAgent extends Agent<any, any>	‐
TContext	undefined

Parameters

Parameter	Type	Description
agent	TAgent	The starting agent to run.
input	| string | AgentInputItem[] | RunState<TContext, TAgent>	The initial input to the agent. You can pass a string or an array of AgentInputItem.
options?	NonStreamRunOptions<TContext>	The options for the run.

Returns

Promise<RunResult<TContext, TAgent>>

The result of the run.

Call Signature

run<TAgent, TContext>(
   agent,
   input,
options?): Promise<StreamedRunResult<TContext, TAgent>>

Run a workflow starting at the given agent. The agent will run in a loop until a final output is generated. The loop runs like so:

1. The agent is invoked with the given input.
2. If there is a final output (i.e. the agent produces something of type agent.outputType, the loop terminates.
3. If there’s a handoff, we run the loop again, with the new agent.
4. Else, we run tool calls (if any), and re-run the loop.

In two cases, the agent may raise an exception:

1. If the maxTurns is exceeded, a MaxTurnsExceeded exception is raised.
2. If a guardrail tripwire is triggered, a GuardrailTripwireTriggered exception is raised.

Note that only the first agent’s input guardrails are run.

Type Parameters

Type Parameter	Default type
TAgent extends Agent<any, any>	‐
TContext	undefined

Parameters

Parameter	Type	Description
agent	TAgent	The starting agent to run.
input	| string | AgentInputItem[] | RunState<TContext, TAgent>	The initial input to the agent. You can pass a string or an array of AgentInputItem.
options?	StreamRunOptions<TContext>	The options for the run.

Returns

Promise<StreamedRunResult<TContext, TAgent>>

The result of the run.