Skip to main content

run_suite

eval_core::runner

Function run_suite 

Source 
pub fn run_suite(
    agent: &impl Agent,
    cases: &[EvalCase<(), Expectation>],
) -> EvalReport
Expand description

The easy path: run a suite of Expectation-based cases against an Agent, scoring with the built-in BuiltinScorer — no World, no Setup, no host Scorer impl.

Implement Agent::run for your harness, author EvalCase<(), Expectation> cases (in RON or inline), and call this; you get back the same EvalReport as the full path. Uses default RunMeta; for a backend/temperature label use run_suite_with_meta.