Struct DecisionJudgeConfig 

pub struct DecisionJudgeConfig {
    pub cutoff: f64,
    pub instructions: Option<Value>,
    pub candidates: BTreeMap<String, ModelId>,
    pub evidence: Value,
}

Evidence and policy for a relative-advantage decision judge.

Candidate labels keep model names out of the generated context. Evidence must use the same labels, with unknown outcomes left unknown. Only the first runtime capable and efficient targets are compared; extra candidates do not add routes.

Fields

cutoff: f64

Route capable only when its advantage score is strictly above this cutoff. This score is not a calibrated solve probability. Choose a cutoff from evaluations.

instructions: Option<Value>

Replaces the packaged structured instructions; must keep the meaning of advantage (capable succeeds and efficient fails) and no_advantage.

candidates: BTreeMap<String, ModelId>

Maps anonymous labels used in evidence (e.g. "a") to runtime model IDs. Every compared target needs a unique label; extra candidates provide context.

evidence: Value

JSON passed unchanged to the judge, such as candidate descriptions, reference cases, outcome/cost summaries, and selection notes. The judge interprets it using the instructions; the router neither reads its fields nor derives statistics.

Trait Implementations

impl Clone for DecisionJudgeConfig

fn clone(&self) -> DecisionJudgeConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for DecisionJudgeConfig

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

Formats the value using the given formatter.