run Agent
abstract suspend fun runAgent(item: TrainSetItem<Input, InputLabel>, agentToRun: GraphAIAgent<Input, Output> = trackedAgent, retryPolicy: RetryPolicy? = null): Result<CompletedAgentRun<Output>>
Runs the agent on the given item.
Transient-failure retries are applied automatically per the session's retry configuration — each call returns with either a successful CompletedAgentRun or a non-transient failure (the inner retry layer has already absorbed transient blips before the result is returned). Per-attempt details for retried operations live in the resulting record's previousAttempts.
Parameters
retry Policy
override for the session-default retry policy. null (default) = use resources.retriesPolicy. RetryPolicy.None = disable transient retries for this call (useful in tests or where deterministic single-attempt behavior is required).