P9-1~P9-4 머지 후 사용자가 직접 도그푸딩 하며 수집한 16 항목 UX
피드백을 20 개 single-PR 사이즈 task spec 으로 분해. 각 spec 은
frontmatter (depends_on / unblocks / source_feedback), Goal,
Allowed deps, Public surface, Behavior contract, Test plan, DoD,
Out of scope 절 포함.
추가:
- p9-fb-01 ~ 20-*.md: 분해된 task spec 20 개
- p9-dogfooding-feedback.md: master index + 우선순위 + 권장 실행 순서
+ spec PR vs impl PR 절
- INDEX.md: p9-fb-01 ~ 20 link 추가
- docs/superpowers/plans/2026-05-02-p9-fb-06-reset-command.md:
첫 후속 작업 (kebab reset 명령) 의 6-task 구현 plan
- .gitignore: .worktrees/ 추가 (superpowers worktree skill 용)
피드백 항목 → task spec 매핑은 p9-dogfooding-feedback.md 의 표 참조.
실행 시작 task: p9-fb-06 (reset 명령) — 도그푸딩 막힘 강도 1위.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
P7-1 (`PdfTextExtractor`) + P7-2 (`PdfPageV1Chunker`) 의 라이브러리는
완성됐지만 `kebab-app::ingest` 가 `MediaType::Pdf` 를 dispatch 하지 않아
CLI 에서 PDF 가 보이지 않는 상태. P7-3 이 그 와이어링을 다룬다 — P6-4
의 image wiring 패턴과 평행.
핵심 결정 (spec 본문):
- 새 private fn `ingest_one_pdf_asset` (P6-4 의 `ingest_one_image_asset`
와 평행). `ingest_one_asset` match 에 `MediaType::Pdf` arm 추가.
- per-medium chunker 선택: PDF 는 `PdfPageV1Chunker` 하드코딩 (md 는
`MdHeadingV1Chunker` 그대로). `config.chunking.chunker_version` 은 PDF
ingest 에서 무시 (deviation, HOTFIXES 추가 예정).
- encrypted PDF / corrupt PDF → `errors+=1` + `IngestItem.error` 에 P7-1
의 `qpdf --decrypt` 안내 그대로 보존.
- 빈/scanned candidate 페이지 → asset 인덱싱, 빈 페이지 0 chunk, P7-1
emit 한 `Provenance::Warning` 그대로 통과. 향후 OCR fallback 까지는
검색 불가 (out of scope).
- determinism stress: extract → chunk 사이에 `now()` 추가 호출 금지
(P6-4 와 동일 invariant).
- 11 통합 테스트 + smoke 업데이트 (별도 implementation PR).
`tasks/INDEX.md` P7 components 2 → 3 반영.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
P6-1 / P6-2 / P6-3 의 라이브러리 파이프라인 (`ImageExtractor`,
`OllamaVisionOcr`, `apply_caption`) 이 모두 머지되어 있지만
`kebab-app::ingest_with_config` 의 dispatch 가 markdown 만 처리하므로
CLI 에서 이미지 자산이 색인되지 않는 미완 구간 존재. 본 spec 은
그 wiring 을 별도 component task 로 잡아 P6-1/2/3 의 frozen contract
는 보존하고 통합만 본 task 의 contract 로 진행되게 한다.
핵심 결정 (사용자 brainstorming 반영):
- 청킹 옵션 A — `kebab-chunk::md_heading_v1` 에 image-only document
분기 추가, 단일 합성 청크 emit.
- 청크 텍스트 포맷 (β) — `<alt>\n\n<ocr.joined>\n\n<caption.text>`
plain concatenation. 라벨 없음. 빈 부분 drop.
- 실패 정책 (b) Lenient — extract 성공이면 doc 저장, OCR/caption
부분 실패는 Provenance Warning + `errors` 카운터 미증가.
- LM 인스턴스 — ingest 세션당 1회 빌드, `&dyn LanguageModel` 공유.
- 책 / 스캔 PDF — P6-4 scope 외, P7 PDF 라인이 책임.
- P6-5 (image-scale-hardening) 미시작 — 사용자 시나리오가
\"다이어그램 / 스크린샷 / 카메라 사진\" 으로 좁아져 불필요.
INDEX.md: P6 \"3 components\" → \"4 components\".
contract: docs/superpowers/specs/2026-04-27-kebab-final-form-design.md
sections: §3.4 ImageRefBlock, §6.1 ingest pipeline, §7.2
Extractor/Chunker traits, §9.1 image extraction policy.
## Bug
config.rag.score_gate default 0.05 was incompatible with hybrid RRF
fusion_score: raw RRF tops out at num_retrievers / (k_rrf + 1) ≈
0.0328 at the default k_rrf=60, so every hybrid `kb ask` tripped
ScoreGate refusal even when the top hit was perfectly aligned across
both retrievers. Symptomatic on the post-P4-3 manual smoke at
/tmp/kb-smoke/ pointed at 192.168.0.47 Ollama:
$ kb ask "Rust ownership 모델의 핵심 규칙은 뭐야?" --mode hybrid
근거 부족. KB에 해당 내용 없음. # top fusion_score = 0.0164
Per-mode score_gate (lexical_score_gate / vector_score_gate /
hybrid_score_gate) was rejected because it forces every consumer
(CLI, eval, TUI) to know which mode picks which threshold. Score
normalization solves it at the source.
## Fix
crates/kb-search/src/hybrid.rs divides every fused score by
2 / (k_rrf + 1), the theoretical RRF maximum with two retrievers
each contributing rank 1. After normalization:
- both retrievers agree on rank 1 → fusion_score = 1.0
- only one retriever finds the chunk → caps near 0.5
- typical mixed ranks → falls between 0 and 0.5
RRF's rank-ordering invariants are preserved (every score divides
by the same positive constant), so sort + tiebreak behaviour is
unchanged. Wire schema label `fusion_score` keeps its slot in
RetrievalDetail; only the magnitude shifts, and only for hybrid
mode (lexical / vector were already in [0, 1]).
Verification: re-ran the four-scenario smoke at /tmp/kb-smoke/ with
default score_gate = 0.05 — all four (Korean→Korean, English→
English, cross-language Korean↔English, out-of-corpus) succeed
with the expected grounded / refusal classification, top
fusion_score now ≈ 0.5.
## Tests
One unit test (rrf_formula_matches_known_value) updated to expect
the normalized value `(1/61 + 1/62) / (2/61) ≈ 0.9919` instead of
the raw `1/61 + 1/62 ≈ 0.0325`. The integration snapshot fixture
crates/kb-search/tests/fixtures/search/hybrid/run-1.json already
used presence checks (fusion_score_positive: true) rather than
absolute values, so it doesn't need regeneration. Workspace 319
tests pass; clippy clean across both feature configs.
## Docs
This commit also adds tasks/HOTFIXES.md as a dated post-merge log
covering this fix and the two earlier --config-flag regressions
(P3-5 hotfix #20 across ingest/search/list/inspect/doctor; P4-3
follow-up #24 for kb ask). Original task specs in tasks/p<N>/
*.md stay frozen as the historical contract; HOTFIXES.md is the
live source of truth for post-merge deltas. Each affected task
spec gets a "Risks/notes" addendum pointing back to HOTFIXES.md
so a reader landing on the spec sees the active behaviour:
- tasks/INDEX.md gains a "Post-merge 핫픽스" section.
- tasks/phase-3-vector-hybrid.md updates the RRF formula text to
show the normalized form.
- tasks/p3/p3-4-hybrid-fusion.md "Behavior contract" RRF bullet
notes the normalization and reason.
- tasks/p3/p3-5-app-wiring.md "Risks/notes" notes the --config
fix.
- tasks/p4/p4-3-rag-pipeline.md "Risks/notes" notes the kb-ask
--config fix and the score_gate-RRF incompatibility (closed by
the normalization in p3-4).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
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
