Struct ContextRequest 

pub struct ContextRequest {

    pub include_fact_evidence: bool,
    pub defer_fact_budget: bool,
    pub stage: String,
    pub query: String,
    pub budget_tokens: u32,
    pub fusion: String,
    pub normalization: String,
    pub tags: Vec<String>,
    pub min_score: f32,
    pub max_capsules: usize,
    pub prefer_roles: Vec<String>,
    pub kinds: Vec<String>,
    pub min_semantic_score: f32,
    pub min_semantic_score_override: Option<f32>,
    pub min_lexical_coverage: f32,
    pub min_lexical_coverage_override: Option<f32>,
    pub task_kind: TaskKind,
    pub abstain_evidence: f32,
    pub abstain_evidence_override: Option<f32>,
}

Fields

include_fact_evidence: bool

Hydrate structured evidence only for consumers that explicitly request it.

defer_fact_budget: bool

Defer intermediate budgeting to a final evidence-aware renderer; requires a bounded pool.

stage: String

query: String

budget_tokens: u32

fusion: String

v2.6: per-request override for how the lexical and semantic rankings are merged ("linear" / "rrf"; see crate::fusion).

Empty (the default) means “use [broker] fusion”. This exists so kimetsu brain tune can sweep the two rules against one corpus in one process — the reason the shipped default is still linear is that nothing had measured the alternative on a real brain.

normalization: String

v2.6: per-request override for how raw_relevance is normalized into the relevance term ("per_kind" / "global"; see Normalization).

Empty (the default) means “use [broker] normalization”. Exists for the same reason fusion does: the alternative had to be measurable on one corpus in one process before it could be argued for.

tags: Vec<String>

v0.6: domain-hint tags. Capsules whose text or kind contains any of these strings receive a 1.4× score boost, pushing on-domain capsules above the min_score threshold when they would otherwise be filtered out.

min_score: f32

v0.6: minimum composite score for inclusion. When > 0.0 and the top-scoring capsule falls below this threshold, ContextBundle is returned with skipped: true and an empty capsule list — zero tokens injected. 0.0 (default) disables the check.

max_capsules: usize

v0.6: hard cap on returned capsules regardless of token budget. 0 = no cap (budget-only limit, prior behaviour).

prefer_roles: Vec<String>

v0.6: role-preference boost. Capsules whose kind matches one of these strings receive an additional 1.3× multiplier after the tag boost (e.g. ["semantic_operator", "anti_pattern"] for bench).

kinds: Vec<String>

v0.8: hard kind filter applied BEFORE scoring + capping. When non-empty, only candidates whose capsule kind is in this list survive — so a higher-ranked repo file or off-kind memory can’t consume a (often single) slot. Used by the proactive engine to restrict recall to actionable kinds (failure_pattern, command, convention). Empty (default) keeps all kinds, prior behaviour.

min_semantic_score: f32

D1e: absolute cosine-similarity floor. On embeddings builds, memory candidates whose cosine to the query is below this threshold are dropped before budgeting. 0.0 (default) disables the floor — matches pre-D1e behaviour. Repo-file and manifest candidates are unaffected (they have no cosine score). Populated from BrokerSection.min_semantic_score by the pipeline; callers that don’t set it get the prior behaviour automatically.

min_semantic_score_override: Option<f32>

Explicit public override: None preserves legacy zero=inherited; Some(0) disables, Some(-1) selects model auto, Some(positive) sets a floor.

min_lexical_coverage: f32

v1.0.0: absolute lexical relevance floor for memory candidates, as the fraction of the query’s IDF-weighted discriminating power a memory must cover. Unlike min_semantic_score this needs no query embedding, so it protects the FTS-only hook path. When > 0.0, memory candidates below the floor are dropped BEFORE scoring (so they don’t even set the per-kind normalization max). Repo-file/manifest candidates are unaffected. 0.0 (default) disables it — every existing ..Default::default() construction is unchanged. Populated from BrokerSection.min_lexical_coverage by the pipeline.

min_lexical_coverage_override: Option<f32>

Some(0) explicitly disables the lexical floor; None inherits legacy behavior.

task_kind: TaskKind

E3: inferred kind of the current task. Defaults to Feature (the neutral kind) so every existing ..Default::default() construction is unchanged — Feature does NOT alter weights or prefer_roles. Set by the pipeline via classify_task at intake.

abstain_evidence: f32

v2.7: ABSOLUTE abstention floor. min_score above compares against the normalized composite, whose top candidate always carries relevance 1.0 — it can rank candidates but cannot express “nothing here is genuinely relevant”, so it never abstains on a plausible-but-wrong corpus (the workflow benchmark measured false-injection 1.00 at a 60-memory brain). This floor gates on absolute evidence instead: the best raw cosine any memory candidate achieved. When > 0.0 and no cosine-backed memory candidate clears it — and the bundle would contain only memory capsules — the retrieval returns skipped: true with zero tokens injected. Lexical-only and cross-model candidates are unmeasured on this scale and therefore exempt. Repo-file/manifest capsules also suppress the gate: an FTS hit on real repo content is its own evidence the bundle is useful. 0.0 (default) disables the gate. Populated from BrokerSection.abstain_min_score by the pipeline.

abstain_evidence_override: Option<f32>

Some(0) disables abstention; Some(-1) uses model auto; None inherits.

Trait Implementations

impl Clone for ContextRequest

fn clone(&self) -> ContextRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ContextRequest

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

Formats the value using the given formatter.

impl Default for ContextRequest

fn default() -> ContextRequest

Returns the “default value” for a type.