Struct EvaluationResult 

pub struct EvaluationResult {
    pub eval_id: String,
    pub passed: bool,
    pub scores: HashMap<String, f64>,
    pub failures: Vec<Failure>,
    pub duration: Duration,
    pub turn_results: Vec<TurnResult>,
    pub cost_metrics: Option<CostMetrics>,
    pub trace_analysis: Option<TraceAnalysis>,
    pub verdicts: Vec<StructuredVerdict>,
}

Available on crate feature eval only.

Result for a single test case

Fields

eval_id: String

Test case identifier

passed: bool

Whether the test passed all criteria

scores: HashMap<String, f64>

Scores for each criterion

failures: Vec<Failure>

Failures (criteria that didn’t meet threshold)

duration: Duration

Execution duration

turn_results: Vec<TurnResult>

Detailed turn results

cost_metrics: Option<CostMetrics>

Cost and latency metrics (populated when CostTracker is active)

trace_analysis: Option<TraceAnalysis>

Trace analysis results (populated when TraceAnalyzer is active)

verdicts: Vec<StructuredVerdict>

Structured verdicts from the judge

Implementations

impl EvaluationResult

pub fn passed( eval_id: &str, scores: HashMap<String, f64>, duration: Duration, ) -> EvaluationResult

Create a passed result

pub fn failed( eval_id: &str, scores: HashMap<String, f64>, failures: Vec<Failure>, duration: Duration, ) -> EvaluationResult

Create a failed result

pub fn with_turn_results( self, turn_results: Vec<TurnResult>, ) -> EvaluationResult

Add turn results

Trait Implementations

impl Clone for EvaluationResult

fn clone(&self) -> EvaluationResult

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for EvaluationResult

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for EvaluationResult

fn deserialize<__D>( __deserializer: __D, ) -> Result<EvaluationResult, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for EvaluationResult

fn serialize<__S>( &self, __serializer: __S, ) -> Result<<__S as Serializer>::Ok, <__S as Serializer>::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.