Struct ScoreBreakdown 

pub struct ScoreBreakdown {
    pub bm25: f32,
    pub title_boost: f32,
    pub field_weights: HashMap<String, f32>,
    pub expansion_decay: Option<f32>,
}

Per-hit score components surfaced so agents can understand ranking.

Note: this is illustrative feedback, not a numerically authoritative decomposition — tantivy’s Explanation for BoostQuery over BooleanQuery does not always sum cleanly. Agents should treat these as proportions, not exact sums.

Fields

bm25: f32

title_boost: f32

field_weights: HashMap<String, f32>

expansion_decay: Option<f32>

Some(f32) on expanded hits only, carrying the depth-based decay factor (0.5.powi(depth)). None on primary hits.

Trait Implementations

impl Clone for ScoreBreakdown

fn clone(&self) -> ScoreBreakdown

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ScoreBreakdown

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

Formats the value using the given formatter.

impl JsonSchema for ScoreBreakdown

fn schema_name() -> Cow<'static, str>

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn inline_schema() -> bool

Whether JSON Schemas generated for this type should be included directly in parent schemas, rather than being re-used where possible using the $ref keyword.

impl Serialize for ScoreBreakdown

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

where __S: Serializer,

Serialize this value into the given Serde serializer.