Struct EvaluationReport 

pub struct EvaluationReport {
    pub dataset_name: String,
    pub dataset_version: String,
    pub candidate_version: String,
    pub execution_success_rate: f64,
    pub cases: Vec<EvaluationCaseResult>,
    pub summaries: Vec<EvaluationScoreSummary>,
}

Deterministic candidate evaluation report.

Fields

dataset_name: String

Dataset name.

dataset_version: String

Dataset version.

candidate_version: String

Candidate model, prompt, Agent, or application version.

execution_success_rate: f64

Target executions that produced output.

cases: Vec<EvaluationCaseResult>

Case results in dataset order.

summaries: Vec<EvaluationScoreSummary>

Score summaries sorted by scorer name.

Implementations

impl EvaluationReport

pub fn to_json_pretty(&self) -> Result<String, Error>

Serializes this output-free report as stable, pretty JSON.

Errors

Returns a JSON error only if serialization unexpectedly fails.

pub fn compare( &self, baseline: &Self, policy: &RegressionPolicy, ) -> Result<RegressionComparison, EvaluationError>

Compares this candidate with a baseline of the same dataset identity.

Errors

Returns EvaluationError::DatasetMismatch when dataset identities differ.

pub fn validate(&self) -> Result<(), EvaluationError>

Validates a report loaded from an external artifact.

Errors

Returns an error for empty identities, invalid ratios, or duplicate score summaries.

Trait Implementations

impl Clone for EvaluationReport

fn clone(&self) -> EvaluationReport

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for EvaluationReport

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for EvaluationReport

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for EvaluationReport

fn eq(&self, other: &EvaluationReport) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl Serialize for EvaluationReport

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for EvaluationReport