evaluate_node
junjo.evaluate_node
Kind: Function
SDK version: 0.69.0
Documentation channel: Stable release
Signature
Section titled “Signature”evaluate_node(*, node: Node, store: BaseStore[StateT], correlation: ExecutionCorrelation | None = None) -> NodeEvaluationResult[StateT]Execute one real Node with production Node and Store lifecycle evidence.
This helper is a one-shot envelope for live application evals. Construct a
fresh node and initialized store for every case. Junjo executes them
inside a generated single-Node Workflow so tracing, state transitions,
lifecycle dispatch, cancellation, failures, and execution correlation use
the same public runtime as production Workflows.
This low-level helper executes a Node; it does not select dataset cases or
judge their outputs. For repeatable experiments recorded in Junjo AI Studio,
register a NodeTarget in an
EvaluationHarness. Your application runs the
targets and evaluators while Studio stores the datasets, outcomes, and
linked execution evidence. Workflow and Agent targets use their respective
WorkflowTarget and
AgentTarget wrappers. Direct execute() calls
remain appropriate for lower-level application tests.
Parameters
Section titled “Parameters”| Name | Type | Description | Default |
|---|---|---|---|
node |
Node |
Fresh Node instance to evaluate. | |
store |
BaseStore[StateT] |
Fresh initialized Store containing the eval case input. | |
correlation |
ExecutionCorrelation | None |
Optional trusted application identity for this eval run. | None |
Returns
Section titled “Returns”NodeEvaluationResult[StateT]: Detached final state and exact execution identities.