Struct SelectorWeights 

pub struct SelectorWeights {
    pub category_weights: BTreeMap<String, f32>,
    pub min_score: f32,
    pub diversity_bias: f32,
    pub epistemic_weight: f32,
}

Learned weights that a selector implementation may use.

Callers persist this across sessions.

Fields

category_weights: BTreeMap<String, f32>

Weight multiplier by input category.

min_score: f32

Minimum score threshold (inputs below this are excluded even if budget allows).

diversity_bias: f32

Preference for diversity vs. relevance (0.0 = pure relevance, 1.0 = pure diversity).

epistemic_weight: f32

Weight for epistemic (uncertainty-reducing) selection.

The effective selection score is pragmatic_score + epistemic_weight * information_gain. Default 0.0 (pure pragmatic). Higher values prefer candidates that reduce uncertainty. When 0.0, behavior is identical to ADR-058 (backwards-compatible, ADR-059).

Trait Implementations

impl Clone for SelectorWeights

fn clone(&self) -> SelectorWeights

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for SelectorWeights

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

Formats the value using the given formatter.

impl Default for SelectorWeights

fn default() -> SelectorWeights

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for SelectorWeights

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for SelectorWeights

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

where __S: Serializer,

Serialize this value into the given Serde serializer.