Module scoring 

Composite memory scoring — ported from the archived internal service (v1 archive).

Provides a fully-tunable scoring pipeline:

1. ScoringConfig — all knobs, all pub, all serde-friendly for agent sweeps.
2. calculate_score — multiplicative formula: w_rel × relevance × (1 + w_temp × recency) × (1 + w_imp × salience).
3. ScoreAdjustment — declarative conditional rules applied after the base formula.
4. normalize_rrf_scores / normalize_rank_fusion_scores — RRF and raw-cosine normalization.
5. normalize_min_score — dual-scale input (0.0–1.0 fraction or 0–100 integer).
6. is_meaningful_query — noise gate before embedding compute.
7. contains_cjk — CJK routing decision.

Structs

CandidateContext

Context passed to condition evaluation — properties of the candidate + query.

ScoreAdjustment

A conditional score adjustment: if condition matches, apply operation.

ScoreInput

Input data for calculate_score — groups per-candidate fields to stay within clippy’s 7-argument limit.

ScoringConfig

Complete, fully-tunable scoring configuration for the memory recall pipeline.

ScoringWeights

Weights for the combined memory score (multiplicative model).

Enums

AdjustmentCondition

A condition that determines whether a score adjustment applies to a candidate.

AdjustmentOp

The operation to apply when a condition matches.

Constants

MAX_RECALL_CANDIDATES

Maximum candidates a caller may request (server-side cap).

MAX_RECALL_LIMIT

Maximum result limit a caller may request (server-side cap).

MAX_TOKEN_BUDGET

Maximum token budget a caller may request (server-side cap).

Functions

calculate_score

Composite score for a single memory candidate.

contains_cjk

Returns true when >15% of the query’s characters are CJK.

default_adjustments

Default score adjustments: episodic recency bonus, semantic age penalty, entity boost.

is_cjk_char

Returns true if c is a CJK character (Unified, Extension A/B, Hiragana, Katakana, Hangul).

is_meaningful_query

Returns true if the query has enough semantic content to produce meaningful recall.

normalize_min_score

Normalize min_score from caller-supplied value.

normalize_rank_fusion_scores

Normalize raw-cosine or BM25 scores (single-source) into a calibrated relevance band.

normalize_rrf_scores

Normalize RRF-fused scores (dual-source) into a calibrated relevance band.