Struct TrajectoryEvaluator 

pub struct TrajectoryEvaluator {
    pub strict_order: bool,
    /* private fields */
}

Evaluates the tool-call trajectory of agent invocations.

Compares actual tool calls (names and order) against expected tool calls to assess whether the agent followed the correct reasoning path.

Fields

strict_order: bool

Whether to enforce strict ordering of tool calls.

Implementations

impl TrajectoryEvaluator

pub fn new(strict_order: bool) -> Self

Create a new trajectory evaluator.

pub fn with_metric_name(self, name: impl Into<String>) -> Self

Set a custom metric name.

Trait Implementations

impl Clone for TrajectoryEvaluator

fn clone(&self) -> TrajectoryEvaluator

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for TrajectoryEvaluator

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for TrajectoryEvaluator

fn default() -> Self

Returns the “default value” for a type.

impl Evaluator for TrajectoryEvaluator

fn evaluate<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, actual: &'life1 [Invocation], expected: Option<&'life2 [Invocation]>, ) -> Pin<Box<dyn Future<Output = Result<EvalResult, EvalError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Evaluate agent invocations.