feat: v0.20.2 — Ask 응답언어 rag-v3 + 8 dogfood findings + 검색 품질 eval baseline #192

Merged
altair823 merged 23 commits from fix/v0-20-2-dogfood-findings into main 2026-05-29 05:27:55 +00:00

23 Commits

Author SHA1 Message Date
ca8c83b1ba chore(hotfixes): PR #192 회차 1 리뷰 반영 — refusal marker 표기 정정
`<REFUSE>` marker → citation marker(`[#번호]`) 유무 기반 (pipeline.rs:463-486).
release-notes 정정과 일관.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-05-29 05:22:57 +00:00
6c611990d8 chore: bump version 0.20.1 -> 0.20.2
v0.20.2 — Ask 응답언어 자동매칭(rag-v3) + 8 dogfood findings
+ eval --config facade 패치 + 검색 품질 golden baseline
(hybrid hit@3=1.0 / MRR=0.833, lexical hit@3=1.0).
evidence: tasks/HOTFIXES.md 2026-05-29, docs/release-notes/v0.20.2-draft.md.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-05-29 05:10:42 +00:00
166b1404e4 docs(release-notes): correct refusal判정 mechanism + O-2 phrasing
leader review of writer draft: refusal 판정은 citation marker(`[#번호]`)
유무 기반이며 `<REFUSE>` 특수 마커가 아님. O-2 문구 예시도 실제 rag-v3
규칙으로 정정.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-05-29 04:58:08 +00:00
2d0168b7ab docs(sync): README + HANDOFF v0.20.2 surface 반영
CLAUDE.md docs-split 규칙에 따라 사용자 visible surface 변경 동기화.

README:
- [rag] prompt_template_version default rag-v2 → rag-v3 (v0.20.2)
- v3 규칙 설명 (답변 언어 = 질문 언어)
- O-2 known limitation (소형 모델 refusal 언어 불일치)

HANDOFF:
- 머지 후 발견된 버그/결정 에 v0.20.2 1줄 요약 추가
- 검색 품질 baseline (hybrid MRR=0.833) + O-2 known limitation 언급

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 04:54:26 +00:00
4afcaf96d2 docs(release-notes): add v0.20.2-draft (rag-v3 응답언어 + 검색 품질 eval 인프라)
v0.20.2 릴리즈 노트 초안 작성. 사용자 영향 4단락 구조로 각 finding 기술.

- Finding #1/O-2: rag-v3 응답언어 자동 매칭 + refusal 언어중립화
- Finding #2: bulk search input schema 확정 (15필드)
- Finding #3: list docs human-readable path 보강
- Finding #7: index_version 두 곳 구분 (vector vs FTS5)
- eval --config facade + 검색 품질 baseline (hybrid hit@3=1.0 / MRR=0.833)
- Finding #4/#5/#6/#8: docs/schema 정비
- version cascade 주의 (rag-v3 → eval compare)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 04:54:19 +00:00
16c4579399 docs(hotfixes): add 2026-05-29 v0.20.2 dogfood findings + 검색 품질 baseline
8-finding 도그푸딩 라운드 및 검색 품질 baseline 결과를 HOTFIXES 에 기록.

- 8 findings 요약 표 (rag-v3, bulk schema, list docs, index_version 등)
- Finding O-2 known limitation (소형 모델 refusal 언어 불일치)
- 검색 품질 baseline 표 (hybrid MRR=0.833, lexical MRR=0.7)
- golden 큐레이션 교훈 (dispatch.py 정답 정정 → hit@3 0.9→1.0)
- eval logs cross-link

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 04:54:11 +00:00
40d7faee71 docs(dogfood): add §10.2 search quality baseline scenario (v0.20.2 golden suite)
eval --config facade 패치로 dogfood KB 직접 평가 가능해짐에 따라
§10 Eval 에 §10.2 검색 품질 baseline 섹션 추가.

- golden suite 실행 명령 (hybrid + lexical eval run → aggregate)
- v0.20.2 metric baseline 표 (hybrid hit@3=1.0 / MRR=0.833)
- 정성 체크리스트 (한국어 2자 hit@3, empty=0, MRR 임계치)
- golden 큐레이션 절차 + dispatch.py 오류 교훈
- §10.1 로 기존 basic eval run 재구성

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 04:54:03 +00:00
a3bb2580bf test(rag): add rag-v3 dispatch integration test + refresh stale rag-v2 docs (code-review)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 04:46:27 +00:00
2429189447 docs(spec): reflect search-quality critic round-1 (eval --config, lang-filter non-goal, curation)
Incorporates all critic (opus) round-1 findings into the dogfood
search-quality eval design spec:

BLOCKER-1: §4.4 execution commands now use --config /build/dogfood/config.toml
  (Task A facade-rule patch makes this the canonical path).  §5.1 re-titled
  from "(후속 패치)" to "Task A로 적용됨 — 권장 운영 경로"; XDG workarounds
  demoted to "패치 전 fallback".  Intro paragraph updated accordingly.

MAJOR-1: §3 Non-Goals gains an explicit bullet: lang/media/code_lang
  SearchFilters validation is out of scope for this harness (runner uses
  SearchFilters::default(), runner.rs:151).  §4.1 "code 검색" row no longer
  claims code_lang filter coverage.

MINOR-1: §4.3 step 3 now names kebab inspect doc <id> as the primary
  chunk-selection path (breaks chunk-level curation loop); search hits
  demoted to "보조 확인용".

MINOR-2: §4.1 golden category table gains two new rows — 한국어 N-gram
  fallback query (복합어/신조어 coverage) and 영어 whole-token exact query
  (separates substring artefacts).

MINOR-3: §4.1 YAML header note added: record corpus_revision in golden
  file so stale-bail root cause is immediately traceable.

NIT: §9 References line numbers corrected (runner.rs:31, metrics.rs:116/144);
  runner.rs:151 SearchFilters::default() reference added.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 03:43:00 +00:00
d93b757cf1 fix(cli): thread --config through kebab eval run/aggregate/compare (facade-rule)
Cmd::Eval now loads Config via cli.config (same pattern as all other
subcommands) before dispatching to the inner match.  Each arm now calls
the *_with_config variant:

  run_eval(&opts)             → run_eval_with_config(&cfg, &opts)
  compute_aggregate(run_id)   → compute_aggregate_with_config(&cfg, run_id)
  store_aggregate(run_id, ..) → store_aggregate_with_config(&cfg, run_id, ..)
  Compare already called compare_runs_with_config but sourced cfg from
  Config::load(None) — that redundant load is removed; cfg comes from
  the shared binding above.

Fixes the same facade-rule regression pattern as P3-5 / P4-3: previously
`kebab --config /build/dogfood/config.toml eval run` silently evaluated
the XDG-default (empty) KB instead of the dogfood KB.

Also fixes runner.rs test that hardcoded rag-v2 after commit 5719969
bumped the default prompt_template_version to rag-v3.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 03:42:40 +00:00
571996938c docs(contract): bump default prompt_template_version to rag-v3 (Todo #1)
line 899: V1만 legacy → V1/V2 둘 다 legacy, v0.20.2 부터 rag-v3 default 선언.
line 1349 (★): config 예시 default rag-v2 → rag-v3.
line 1533 (★): §9 cascade table 코드 상수 rag-v2 → rag-v3.
line 287 이후: answer.v1 예시 블록에 historical snapshot 주석 추가 (n1 — model+ptv stale, 값 변경 안 함).
task spec grep 판단: tasks/p9/p9-fb-15 의 rag-v2 언급 2줄은 rag-v2 도입 시점 historical 기술 → frozen 유지.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 02:45:13 +00:00
be79bdb83d docs(#7): distinguish vector-store vs FTS5 index_version (Todo #7)
schema.schema.json models.index_version: vector store (LanceDB) version 임을 명시.
search_hit.schema.json index_version: lexical (FTS5) version 임을 명시.
search_hit.schema.json retrieval: 내부 필드 목록 + hybrid 전용 fusion 설명 추가 (hunk 공유).
README kebab schema 행: index_version 두 곳의 의미가 다름을 주의 표기 추가.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 02:45:04 +00:00
4e76f103c1 docs(#5,#6): clarify retrieval.* nesting + single-mode score relation (Todo #5/#6)
README Score 해석 절에 score ↔ retrieval.* 구조 설명 추가:
- fusion_score/lexical_score/vector_score/lexical_rank/vector_rank 는 retrieval 내부 (top-level 아님).
- single-mode 에서 score==fusion_score==lexical/vector_score 가 같은 값인 것은 정상 (Finding X).
search_hit.schema.json score 필드에 score_kind 관계 + single-mode 동일값 이유 설명 추가.
search_hit.schema.json retrieval/index_version 설명은 Task 12 커밋에 포함 (같은 hunk).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 02:44:56 +00:00
4fd672193f docs(#4): clarify lang vs code_lang semantic and und=code (Todo #4)
lang_breakdown description에 code 문서는 자연어 감지 미수행(lang="und" 정상) 사실 추가.
README에 lang vs code_lang 설명 절 신규 추가.
task spec grep: tasks/p9/p9-fb-15 의 rag-v2 언급은 historical 기술 → frozen 유지.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 02:44:34 +00:00
1454321b12 fix(rag): rag-v3 refusal/hedge phrasing follows answer language (Finding O-2)
SYSTEM_PROMPT_RAG_V3: 한국어 리터럴 refusal/hedge 문구를 언어 중립으로 교체.
- 근거가 부족하면 "근거가 부족하다"고 답한다. → 답변 언어로 근거가 부족함을 밝히고 [#번호] 인용 없이 답한다.
- 근거가 모호하면 "확실하지 않다" 라고 명시한다. → 근거가 모호하면 답변 언어로 불확실함을 명시한다.

MULTI_HOP_SYNTHESIZE_SYSTEM_PROMPT: 동일 패턴 두 곳 교체.
- 근거가 부족하면 "근거가 부족하다"고 답한다. → 답변 언어로 근거가 부족함을 밝히고 [#번호] 인용 없이 답한다.
- self-check 의 즉시 "근거가 부족하다" 라고만 답한다. → 즉시 답변 언어로 근거가 부족하다고만 답한다.

refusal 판정 로직(citation marker 기반)은 무변경 — 문구만 언어 중립화.
test rag_v3_contains_v2_rules_plus_language_rule: "확실하지 않다" assert → "불확실함" assert 로 갱신.
task spec grep: tasks/p9/p9-fb-15 의 rag-v2 언급은 도입 시점 historical 기술 → frozen 유지.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 02:43:28 +00:00
649ec35108 feat(cli): add Ollama remote-endpoint hint to kebab init (Todo #8)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 02:19:34 +00:00
dece5e89fc feat(bulk): document bulk search input schema + error shape hint (Todo #2)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 02:16:21 +00:00
3cb49f1f9b feat(cli): show title + doc_path in list docs human output (Todo #3)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-29 02:03:10 +00:00
f5ff823984 docs(dogfood): add RAG response-language scenario (Todo #1 verification) 2026-05-28 21:28:22 +00:00
b82eaec21a feat(config): default prompt_template_version rag-v2 -> rag-v3 (Todo #1) 2026-05-28 21:20:59 +00:00
6daa43375b feat(rag): add rag-v3 system prompt with response-language matching (Todo #1) 2026-05-28 21:20:18 +00:00
85efeeca3e docs(plan): v0.20.2 dogfood findings 구현 plan (15 task)
planner(opus) 작성 → critic 리뷰 시도 → leader 좌표 검증.
8 todo → 15 task: 코드 4 (rag-v3 / list docs / bulk / init) + 각 finding 후
전체 도그푸딩 검증 task 4 + docs-only 3 + contract + HOTFIXES/release-notes + version bump.

plan critic round-1 은 환경 도구 손상으로 좌표 blocker(B-1/B-2/M-1/M-2)를 오진 →
leader 가 pipeline.rs/config/cli/bulk/Cargo.toml 을 직접 grep 검증해 plan 좌표 정확 확인,
executor 용 "anchor grep 재확인" + binary 경로 주의 헤더 추가.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-05-28 21:09:39 +00:00
2b4ba8e104 docs(spec): v0.20.2 dogfood findings 설계 + round-1 critic 반영
v0.20.1 전체 도그푸딩에서 발견된 8 todo (Ask 응답언어 rag-v3 / doc.lang
docs / bulk input / list title / fusion_score·score_kind / schema
index_version / Ollama hint) 를 단일 patch release 로 설계.

writer worker 초안 → opus critic round-1 리뷰 반영:
- B1: top-level score placeholder → 확정 (score_kind 가 의미 선언, search.rs:95-99)
- M1: 이미지 caption 언어 강제 out-of-scope 명시
- M2: config default 테스트(lib.rs:1316) 갱신 필요 명시
- M3: bulk input 전체 필드 (query/mode/k/trust_min/ingested_after/media/tag/lang)
- M4: rag-v3 의 eval_runs.config_snapshot_json cascade 영향

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-05-28 20:37:42 +00:00