Struct FirstDivergence 

pub struct FirstDivergence {
    pub baseline_turn: usize,
    pub candidate_turn: usize,
    pub kind: DivergenceKind,
    pub primary_axis: Axis,
    pub explanation: String,
    pub confidence: f64,
}

First meaningful divergence between two traces.

Fields

baseline_turn: usize

0-based index in the baseline’s chat_response sequence. For an insertion on the candidate side, this is the baseline index where the insertion appeared (effectively a “between” marker).

candidate_turn: usize

Same for the candidate side. May differ from baseline_turn when gaps are present on the alignment path.

kind: DivergenceKind

Classification (Style / Decision / Structural).

primary_axis: Axis

Primary axis the divergence surfaces on (semantic, trajectory, safety, conformance). Provides a machine-readable hint for grouping regressions by root cause.

explanation: String

One-line human-readable explanation. Designed to be embeddable in a PR comment without additional context.

confidence: f64

Confidence in 0..1. Higher means “the signal exceeds the noise floor by a wide margin”. Callers can gate display on >= 0.5.

Trait Implementations

impl Clone for FirstDivergence

fn clone(&self) -> FirstDivergence

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FirstDivergence

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for FirstDivergence

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for FirstDivergence

fn eq(&self, other: &FirstDivergence) -> 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 FirstDivergence

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 FirstDivergence