Ir para o conteúdo principal

Interface: EvalResult

Interface: EvalResult

The outcome of running one eval.

Properties

assertions

assertions: AssertionResult[];

description?

optional description: string;

error?

optional error: string;

Set when the eval threw before completing.


id

id: string;

infraFailure?

optional infraFailure: boolean;

A turn failed at the transport/agent level (succeeded: false), not on an assertion — a retryable infra flake, distinct from error.


passed

passed: boolean;

True when all gates passed (and, under strict, all soft assertions too).


skipped?

optional skipped: {
  reason?: string;
};

Set when the eval called t.skip.

reason?

optional reason: string;

traceId?

optional traceId: string;

MLflow trace id of the eval's last turn, for attaching assessments.

Databricks Developer Hub

Pronto para lançar seu próximo aplicativo baseado em agentes em minutos?

Ler a documentação