altair823-org/kebab
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 45 Wiki Activity
1,242 Commits 7 Branches 45 Tags
bee1ace06ba7831d4f21e7c7bea7b07ab330ad19
Commit Graph

7 Commits

Author SHA1 Message Date
altair823
24ec86c515 feat(rag): rag-v4 — RAG provenance 라벨 (source/trust + 신뢰도 우선 지시) 
RAG 프롬프트의 각 [근거] 청크 머리에 출처/trust 라벨을 붙이고
(`[#n] source=jira trust=secondary doc=…`), system prompt 에 "저신뢰 출처를 권위
출처와 충돌 시 discount 하고 [#번호]로 귀속" 2규칙을 더한다. 출처 필터
(`--source`/`--trust-min`)가 못 잡는 생성 측 실패 — 저신뢰(jira) 청크가 권위(wiki)
청크를 답변에서 덮어쓰는 것 — 를 다룬다.

- SearchHit 에 source_id/trust_level(additive optional). lexical/vector build_hit
  가 documents 조인에서 채움(both 동일: trust_level lowercase TEXT →
  serde lowercase round-trip, doc_summary read-back 과 동형). hybrid fusion 전파.
- pack_context 라벨 렌더(버전 무관 항상). SYSTEM_PROMPT_RAG_V4 = rag-v3 8규칙
  verbatim + 2규칙. config 기본 rag-v3→rag-v4. multi-hop synth 도 2규칙 →
  rag-multi-hop-v1→v2(prompt 변경 = 버전 bump, design §9).
- wire: search_hit.v1 에 두 필드 optional additive(required 아님,
  skip_serializing_if=None → 구 소비자 무영향, v2 bump 아님).
- source_id 는 RAG 헤더에 렌더되므로 validate_sources 에 [A-Za-z0-9._-] char 검증.
- opt-out: rag-v3 핀 = v3 system prompt 선택(discount 지시 빠짐, 라벨은 무해히 잔존).

검증: kebab-core/search/rag/config/eval 전 테스트 green(25 바이너리), clippy 0.
독립 코드 리뷰 APPROVE(7위험 PASS — trust round-trip 실 DB 확인; MEDIUM rag-v3
opt-out doc + multi-hop 버전 / LOW source_id 검증 반영). 도그푸딩: 라벨 메커니즘
end-to-end 검증(search --json 이 competing 쿼리에 wiki/primary + jira/secondary 둘
다 정확 라벨로 노출). LLM-judge(답변 비교)는 instruction LLM 부재로 보류(.2/.47
다운 + lemonade /api/generate it-model template 미적용) — 인프라, .2 복구 시 측정.
버전 bump 은 follow-up 들과 배치 릴리스에서 일괄.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012Mc6W1fgsrbFKTsqA6P8La
 2026-06-24 05:48:34 +00:00
altair823
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
altair823
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
th-kim0823
7bbd2c0cbf docs(p10-1a-1): wire schema + frozen design + README/HANDOFF/SMOKE + task index 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-15 17:41:26 +09:00
th-kim0823
c864bd007f docs(fb-38): wire schema + README + design + SKILL + INDEX 2026-05-10 18:21:55 +09:00
th-kim0823
cc41adabb5 feat(wire): search_hit.v1 + citation.v1 require indexed_at + stale (fb-32) 
Additive minor — schema_version unchanged. Existing v1 consumers
that ignore unknown fields stay compatible; consumers that validate
strictly will reject pre-fb-32 payloads, which matches the wire
contract escape hatch (recipient version >= producer required).

Cross-task placeholders: kebab-eval / kebab-tui synthetic test
fixtures pin UNIX_EPOCH + stale=false (same pattern as
hybrid.rs / vector.rs). These don't exercise staleness — Task 11
adds dedicated TUI staleness rendering tests.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-09 02:17:15 +09:00
altair823
a166b7051c p0-1: wire-schema stubs, doc/spec stubs, V001 migration, fixtures 
- docs/wire-schema/v1/ ships 7 schema stubs (citation, search_hit,
  answer, ingest_report, doc_summary, chunk_inspection, doctor) that
  pin schema_version + required fields per design §2. Full property
  validation lands in later phases.
- docs/spec/ ships 7 markdown stubs each linking to the canonical
  frozen design (domain-model, ids, canonical-document, chunk-policy,
  citation-policy, module-boundaries, ai-generation-guidelines).
- migrations/V001__init.sql contains only schema_meta + migrations
  tables per design §5.1; data tables ship in P1-6/P2-1/P3-3.
- fixtures/ has the 11 subdirectories every downstream task references
  (markdown, source-fs, search/{lexical,hybrid}, embed, vector, rag,
  eval, image, pdf, audio). Empty subdirs use .gitkeep so they track.
  fixtures/markdown/ ships the 3 phase-0 fixtures: simple-note.md,
  nested-headings.md, code-and-table.md.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-30 05:17:32 +00:00