Interface ScenarioExecutionLike

Readonlymessages

ReadonlythreadId

agent

• agent(content?: string | ModelMessage): Promise<void>

  Adds an agent message to the conversation. If no content is provided, the agent under test will generate a message.

  Parameters

  • Optionalcontent: string | ModelMessage

    The content of the agent message.

  Returns Promise<void>

OptionalagentNonBlocking

• agentNonBlocking?(content?: string | ModelMessage): void

  Voice-only: fire an agent turn WITHOUT awaiting it — the non-blocking primitive behind agent({ wait: false }) (PRD §4.4). The executor tracks the in-flight turn so a subsequent user call lands as a mid-stream barge-in (interruption) rather than a separate turn. Optional: text-only executors may omit it, in which case the { wait: false } step falls back to a fire-and-forget agent() with no barge-in coordination.

  Parameters

  • Optionalcontent: string | ModelMessage

  Returns void

fail

• fail(reasoning?: string): Promise<ScenarioResult>

  Ends the scenario with a failure.

  Parameters

  • Optionalreasoning: string

    Optional reasoning for the failure.

  Returns Promise<ScenarioResult>

  The final result of the scenario.

judge

• judge(options?: { criteria?: string[] }): Promise<ScenarioResult | null>

  Invokes the judge agent to evaluate the current state.

  Parameters

  • Optionaloptions: { criteria?: string[] }

    Optional options with inline criteria to evaluate as a checkpoint.

  Returns Promise<ScenarioResult | null>

  The result of the scenario if the judge makes a final decision.

message

• message(message: ModelMessage): Promise<void>

  Adds a message to the conversation.

  Parameters

  • message: ModelMessage

    The message to add.

  Returns Promise<void>

proceed

• proceed(
      turns?: number,
      onTurn?: (state: ScenarioExecutionStateLike) => void | Promise<void>,
      onStep?: (state: ScenarioExecutionStateLike) => void | Promise<void>,
  ): Promise<ScenarioResult | null>

  Proceeds with the scenario automatically for a number of turns.

  Parameters

  • Optionalturns: number

    The number of turns to proceed. Defaults to running until the scenario ends.

  • OptionalonTurn: (state: ScenarioExecutionStateLike) => void | Promise<void>

    Optional callback executed at the end of each turn.

  • OptionalonStep: (state: ScenarioExecutionStateLike) => void | Promise<void>

    Optional callback executed after each agent interaction.

  Returns Promise<ScenarioResult | null>

  The result of the scenario if it ends.

succeed

• succeed(reasoning?: string): Promise<ScenarioResult>

  Ends the scenario with a success.

  Parameters

  • Optionalreasoning: string

    Optional reasoning for the success.

  Returns Promise<ScenarioResult>

  The final result of the scenario.

user

• user(content?: string | ModelMessage): Promise<void>

  Adds a user message to the conversation. If no content is provided, the user simulator will generate a message.

  Parameters

  • Optionalcontent: string | ModelMessage

    The content of the user message.

  Returns Promise<void>