Files

altair823 78bf78c8be docs(p3-5): add app-wiring task spec; INDEX + phase-3 updates

P1–P3 shipped libraries but kb-app facade is still all `bail!("not yet
wired")` stubs, so the CLI is structurally complete but unusable.
Insert p3-5 between P3-4 and P4-1 to swap the facade bodies — ingest,
search, list_docs, inspect_doc, inspect_chunk — into real
compositions of the libraries shipped through P3-4. `ask` stays
stubbed; P4-3 owns it.

After p3-5 merges:
- `kb index` walks a workspace and persists chunks (SQLite +
  optionally LanceDB).
- `kb search --mode {lexical,vector,hybrid}` returns real SearchHits
  with citations.
- `kb list` / `kb inspect doc|chunk` round-trip from the store.

Updates:
- New task spec at tasks/p3/p3-5-app-wiring.md (depends_on
  p1-6/p2-2/p3-2/p3-3/p3-4; unblocks p4-3/p9-1/p9-2/p9-4).
- tasks/INDEX.md bumps P3 component count 4 → 5 and adds the link.
- tasks/phase-3-vector-hybrid.md replaces the speculative
  `embed_index` facade signature with the actual frozen kb-app
  surface and updates the phase completion checklist.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-01 11:32:42 +00:00

4.5 KiB

Raw Blame History

title, source, date

title	source	date
KB 작업 단위 인덱스	kb_local_rust_report.md	2026-04-27

KB 작업 단위 인덱스

kb_local_rust_report.md 의 Phase 로드맵을 아키텍처 수준 작업 단위로 분해. 각 task 문서는 독립적으로 착수/검수 가능한 단위.

의존 그래프

P0 ── P1 ── P2 ── P3 ── P4 ── P5
                              │
                              ├─ P6 (image)
                              ├─ P7 (pdf)
                              ├─ P8 (audio)
                              └─ P9 (TUI/desktop)

P0~~P5 는 직렬. P6~~P9 는 P5 이후 병렬 가능.

작업 단위

#	코드	제목	핵심 산출 crate	선행
P0	phase-0-skeleton.md	Workspace 뼈대 + 도메인 계약	kb-core, kb-parse-types, kb-config, kb-app, kb-cli	–
P1	phase-1-markdown-ingestion.md	Markdown ingestion 파이프라인	kb-source-fs, kb-parse-md, kb-normalize, kb-chunk, kb-store-sqlite	P0
P2	phase-2-lexical-search.md	SQLite FTS5 lexical 검색 + citation	kb-search (lexical)	P1
P3	phase-3-vector-hybrid.md	Local embedding + LanceDB + hybrid	kb-embed, kb-embed-local, kb-store-vector, kb-search	P2
P4	phase-4-local-llm-rag.md	Local LLM + RAG + grounded answer	kb-llm, kb-llm-local, kb-rag	P3
P5	phase-5-evaluation.md	Golden query / regression eval	kb-eval	P4
P6	phase-6-image.md	이미지 ingestion (OCR + caption)	kb-parse-image	P5
P7	phase-7-pdf.md	PDF text + page citation	kb-parse-pdf	P5
P8	phase-8-audio.md	음성 transcription + timestamp citation	kb-parse-audio	P5
P9	phase-9-ui.md	TUI + desktop app	kb-tui, kb-desktop	P5

Component task decomposition (per phase)

각 phase 의 component-level 분해. AI sub-agent 1세션 = 1 task 가 sweet spot.

P0 — p0/ — 1 component
- p0-1 skeleton
P1 — p1/ — 6 components
P2 — p2/ — 2 components
- p2-1 fts-schema
- p2-2 lexical-retriever
P3 — p3/ — 5 components
P4 — p4/ — 3 components
P5 — p5/ — 2 components
- p5-1 golden-fixture-runner
- p5-2 metrics-compare
P6 — p6/ — 3 components
P7 — p7/ — 2 components
- p7-1 pdf-text-extractor
- p7-2 pdf-page-chunker
P8 — p8/ — 2 components
- p8-1 whisper-adapter
- p8-2 segment-chunker
P9 — p9/ — 5 components

모든 task 공통 규약

의존성 경계 (Allowed / Forbidden) 위반 금지. report §19 참조.
citation 없는 검색 결과 / RAG 응답 금지.
원본 파일 파괴 금지. 파생물만 재생성.
모든 record 에 version (parser/chunker/embedding/index/prompt) 기록.
각 phase 완료 = cargo check --workspace && cargo test --workspace 통과 + 해당 phase 의 완료 조건 CLI 데모 통과.

4.5 KiB Raw Blame History Unescape Escape