Enum TaskKind 

pub enum TaskKind {
    Feature,
    Debug,
    Refactor,
    Docs,
    Investigation,
}

The inferred kind of the current coding task. Classified once at intake from the task description string — deterministic keyword scan, no model call, zero allocation-heavy work.

Feature is the NEUTRAL default: it does not change weights or prefer_roles at all, so every existing ..Default::default() construction produces exactly the prior retrieval behaviour.

Precedence when multiple keyword sets match: Debug > Investigation > Refactor > Docs > Feature

Variants

Feature

Neutral / catch-all (add, implement, build, create, support, …). Must NOT alter weights or prefer_roles — keeps existing tests green.

Debug

fix, bug, error, fail, crash, panic, regression, broken, debug, stack trace, exception — up freshness, prefer failure_pattern.

Refactor

refactor, rename, cleanup, restructure, simplify, extract, deduplicate, reorganize — up scope, prefer convention.

Docs

document, readme, changelog, comment, docstring, docs, tutorial, guide — near-neutral mild adjustments.

Investigation

investigate, analyze, understand, why, explore, find out, root cause, audit, trace — up relevance, prefer fact + preference.

Trait Implementations

impl Clone for TaskKind

fn clone(&self) -> TaskKind

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for TaskKind

impl Debug for TaskKind

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

Formats the value using the given formatter.

impl Default for TaskKind

fn default() -> TaskKind

Returns the “default value” for a type.

impl Eq for TaskKind

impl PartialEq for TaskKind

fn eq(&self, other: &TaskKind) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for TaskKind