Files

kb 9fa38543a8 refactor(spec): introduce kb-parse-types thin crate

PR #1 review left a design-debt note: ParsedBlock landing in kb-core would
(a) force every crate to recompile on parser-internal changes, and
(b) cause namespace pollution when P6/P7/P8 parsers add their own variants.

Resolution: a new thin crate kb-parse-types sits between kb-core and parsers.
Owns ParsedBlock + ParsedPayload + Warning + forward-refs for image/pdf/audio
parser intermediates. Depends on kb-core only (for SourceSpan / Inline).

Updates:
- design §3.7b: add new section defining kb-parse-types
- design §8: add kb-parse-types to module-boundary diagram + forbidden list
- design §3.4 Inline stays in kb-core; kb-parse-types references it (no duplication)
- p0-1 skeleton: workspace + Cargo deps + public surface block
- p1-3 parse-md-blocks: outputs Vec<kb_parse_types::ParsedBlock> directly
- p1-4 normalize: Allowed gains kb-parse-types, drops cross-coupling note
- INDEX + phase-0 epic: list kb-parse-types in P0 deliverables

2026-04-27 20:41:35 +00:00

4.4 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/ — 4 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.

4.4 KiB Raw Blame History Unescape Escape