Files
kebab/tasks/p3/p3-1-embedder-trait.md
altair823 f9714aa5cb docs(rename): kb → kebab — README, tasks/, docs/, design doc, report
마지막 commit. 모든 .md 안의 `kb` 단어 일괄 갱신.

- 19 개 crate 이름 (`kb-core`, `kb-app`, …) → `kebab-*` (Rust 모듈
  path 표기 `kb_*` → `kebab_*` 포함).
- 미래 component (`kb-tui`, `kb-desktop`, `kb-asr-whisper`, `kb-ocr`,
  `kb-mcp`, `kb-vlm`, `kb-rerank`, `kb-vision-ocr`, `kb-index`,
  `kb-smoke`, `kb-architecture`) → `kebab-*` (P6+ 가 시작될 때
  같은 prefix 사용).
- CLI 명령 예제: `kb ingest` / `kb search` / `kb ask` / `kb init` /
  `kb doctor` / `kb inspect` / `kb list` / `kb eval` →
  `kebab <verb>`. fenced code block + 인라인 backtick 모두.
- XDG paths + env vars + binary 경로 (`target/release/kb` →
  `target/release/kebab`) 동기화.
- design doc / 최초 보고서 / SMOKE / HOTFIXES / phase epic / task
  spec 모든 reference 통일.
- task-decomposition.md 의 `git -c user.name=kb` 는 과거 git history
  기록용 author 정보라 그대로 유지 (실제 git history 의 author 는
  변경 불가).
- `tasks/phase-5-evaluation.md` 의 `status: planned` →
  `completed` 도 같이 (P5-1 + P5-2 PR 머지 후 미반영분).

## 검증

- `grep -rEn "\bkb-[a-z]|\bkb_[a-z]|\.config/kb\b|kb\.sqlite|\bKB_[A-Z]"
   --include="*.md"` 0 hits (task-decomposition.md 의 git author
  제외).
- 모든 file path reference 살아있음 (renamed file 들 모두 새 path
  로 update).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 04:01:55 +00:00

4.5 KiB

phase, component, task_id, title, status, depends_on, unblocks, contract_source, contract_sections
phase component task_id title status depends_on unblocks contract_source contract_sections
P3 kebab-embed (trait crate) p3-1 Embedder trait + EmbeddingInput/Kind validation completed
p0-1
p3-2
p3-3
p3-4
../../docs/superpowers/specs/2026-04-27-kebab-final-form-design.md
design §3.7 SearchHit.embedding_model
design §7.1 EmbeddingInput/Kind
design §7.2 Embedder
report §11 LLM/embedding split

p3-1 — Embedder trait crate

Goal

Provide the kebab-embed crate that re-exports Embedder trait, EmbeddingInput/EmbeddingKind, and offers a mock implementation for downstream tests. This task is trait-only; concrete adapters live in p3-2.

Why now / why this size

Concrete adapters (fastembed, ollama-embed, candle) need a stable trait surface. Owning the trait + a mock implementation in a tiny crate keeps kebab-store-vector and kebab-search testable without touching real models.

Allowed dependencies

  • kebab-core
  • kebab-config
  • serde
  • thiserror
  • tracing
  • [features] mock = [] — opt-in feature flag exposing MockEmbedder. Default OFF. Release builds (omit --features mock) compile MockEmbedder out entirely.

Forbidden dependencies

  • fastembed, ort, tokenizers, kebab-source-fs, kebab-parse-md, kebab-normalize, kebab-chunk, kebab-store-*, kebab-search, kebab-llm*, kebab-rag, kebab-tui, kebab-desktop

Inputs

input type source
EmbeddingInput kebab_core::EmbeddingInput<'_> callers (parser-side or query-side)
model identity (EmbeddingModelId, EmbeddingVersion, dimensions) adapter at construction

Outputs

output type downstream
Vec<Vec<f32>> row-aligned with input kebab-store-vector, kebab-search (vector mode)

Public surface (signatures only — no new types)

pub use kebab_core::{EmbeddingInput, EmbeddingKind, EmbeddingModelId, EmbeddingVersion, Embedder};

/// Test-only mock that produces deterministic vectors. Compiled only when `mock` feature is on.
#[cfg(feature = "mock")]
pub struct MockEmbedder { /* internal: model_id, dims, seed */ }
#[cfg(feature = "mock")]
impl MockEmbedder {
    pub fn new(model_id: kebab_core::EmbeddingModelId, version: kebab_core::EmbeddingVersion, dimensions: usize) -> Self;
}
#[cfg(feature = "mock")]
impl kebab_core::Embedder for MockEmbedder { /* per §7.2 */ }

Behavior contract

  • MockEmbedder::embed produces vectors deterministically from (text, kind): e.g., vector[i] = hash_to_unit_float(text, kind, i, seed) so two identical inputs produce identical vectors and different inputs produce nearly-orthogonal vectors. Used by downstream tests.
  • MockEmbedder must respect EmbeddingKind::Document vs Query — different prefix mixed into the hash so query embeddings differ from document embeddings of the same text (mirrors real e5 behavior).
  • dimensions() returns the value passed at construction; callers must trust it.
  • Real adapters (p3-2) MUST NOT implement Embedder here.
  • The crate may expose a tiny helper pub fn assert_vector_shape(vecs: &[Vec<f32>], expected_dims: usize) for downstream tests.

Storage / wire effects

  • None.

Test plan

kind description fixture / data
unit trait dyn dispatch via Box<dyn Embedder> works inline
unit MockEmbedder produces identical vector for identical input inline
unit EmbeddingKind::Document vs Query for same text yield different vectors inline
unit dimensions match construction-time value inline
contract property test: 100 random inputs, each vector has length == dimensions, all finite floats inline (proptest)

All tests under cargo test -p kebab-embed.

Definition of Done

  • cargo check -p kebab-embed passes
  • cargo test -p kebab-embed passes
  • No external embedding dep present
  • PR links design §7.2 Embedder, §11

Out of scope

  • Real adapter (kebab-embed-local is p3-2).
  • Reranker traits (P+).

Risks / notes

  • MockEmbedder is gated by mock feature (default OFF). Downstream tests opt in via [dev-dependencies] kebab-embed = { path = "...", features = ["mock"] }. CI build of release binary (cargo build --release without --features mock) MUST NOT include MockEmbedder symbol — verifiable via cargo bloat or nm symbol scan.
  • Trait re-exports keep the call site stable even if kebab-core reorganizes; downstream crates should use kebab_embed::Embedder rather than use kebab_core::Embedder.