Struct EvaluationReport 

pub struct EvaluationReport {
    pub evaluation_id: EvaluationId,
    pub scope: EvaluationScope,
    pub comparison: ComparisonDesign,
    pub verdict: EvaluationVerdict,
    pub score: Option<String>,
    pub confidence: EvaluationConfidence,
    pub judgments: Vec<EvaluatorJudgment>,
    pub metric_deltas: Vec<EvaluationMetricDelta>,
    pub evidence_refs: Vec<EntityRef>,
    pub usage: EvaluationUsage,
    pub redacted_summary: String,
    pub limitations: Vec<String>,
}

Top-level report returned by an evaluator.

Fields

evaluation_id: EvaluationId

Stable evaluation id.

scope: EvaluationScope

Scope this report evaluates.

comparison: ComparisonDesign

Comparison design actually used.

verdict: EvaluationVerdict

Top-level verdict.

score: Option<String>

Optional top-level score.

confidence: EvaluationConfidence

Top-level confidence.

judgments: Vec<EvaluatorJudgment>

Per-subject or per-criterion judgments.

metric_deltas: Vec<EvaluationMetricDelta>

Metric deltas for measured evaluations.

evidence_refs: Vec<EntityRef>

Evidence refs used by this report.

usage: EvaluationUsage

Usage captured during evaluation.

redacted_summary: String

Bounded report summary.

limitations: Vec<String>

Limitations or validation notes.

Implementations

impl EvaluationReport

pub fn new( evaluation_id: EvaluationId, scope: EvaluationScope, comparison: ComparisonDesign, verdict: EvaluationVerdict, confidence: EvaluationConfidence, redacted_summary: impl Into<String>, ) -> Self

Creates a report with no metric deltas.

pub fn with_usage(self, usage: EvaluationUsage) -> Self

Returns this report with usage attached.

pub fn with_judgment(self, judgment: EvaluatorJudgment) -> Self

Returns this report with one judgment appended.

pub fn with_metric_delta(self, metric_delta: EvaluationMetricDelta) -> Self

Returns this report with one metric delta appended.

pub fn validate_confidence_contract(&self) -> Result<(), AgentError>

Validates that measured confidence is backed by comparison evidence and metric deltas.

pub fn validate_confidence_contract_for_request( &self, request: &EvaluationRequest, ) -> Result<(), AgentError>

Validates measured confidence against request-owned metric deltas.

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

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 Eq for EvaluationReport

impl StructuralPartialEq for EvaluationReport