Commit Graph

44 Commits

Author SHA1 Message Date
d53995a6d4 feat(p10-1b): code-js-ast-v1 chunker + activate JavaScript in app dispatch
Chunker: duplicate-with-substitution from code-ts-ast-v1 / code-rust-ast-v1.
Dispatch: replaces JS bail! arms with JavascriptAstExtractor + CodeJsAstV1Chunker.
Integration test javascript_file_ingests_and_searches_as_code_citation asserts
citation.lang=javascript, symbol=src/Bar.Bar.baz, code_lang=javascript.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-20 01:16:07 +00:00
31245a4328 fix(p10-1b): TS parser_version code-typescript-v1 → code-ts-v1 (naming consistency)
Task H implementer chose code-typescript-v1 but plan + design §3.3 use the
short form (chunker is code-ts-ast-v1 / code-js-ast-v1). Aligning parser
versions to match: rust=code-rust-v1 / python=code-python-v1 / ts=code-ts-v1
/ js=code-js-v1 (Task K). Fixes 2 sites: const PARSER_VERSION + integration
test assertion.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-20 01:05:17 +00:00
acb61b6830 feat(p10-1b): activate TypeScript in ingest_one_code_asset dispatch
Replaces TS bail! arms with TypescriptAstExtractor + CodeTsAstV1Chunker.
Adds typescript_file_ingests_and_searches_as_code_citation integration test —
asserts citation.lang=typescript, symbol=src/Foo.Foo.bar, code_lang=typescript.
JS arms remain bail!() (Task L).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-20 00:59:41 +00:00
1815091247 feat(p10-1b): activate Python in ingest_one_code_asset dispatch
Replaces Python bail! arms with PythonAstExtractor + CodePythonAstV1Chunker.
Adds python_file_ingests_and_searches_as_code_citation integration test —
asserts citation.lang=python, symbol=kebab_eval.metrics.compute_mrr,
code_lang=python. TS/JS arms remain bail!() (Tasks J/L).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-20 00:49:01 +00:00
b5d1fe8c1e feat(p10-1a-2): backfill SearchHit.repo from doc metadata (Task 8b)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-19 21:13:01 +00:00
580576c2c6 feat(p10-1a-2): wire code ingest dispatch (ingest_one_code_asset)
Add `MediaType::Code("rust")` dispatch arm in `ingest_one_asset`,
`ingest_one_code_asset` fn (faithful mirror of `ingest_one_pdf_asset`),
and `backfill_code_lang` post-processing in `App::search_uncached`.
Integration test `code_ingest_smoke.rs` verifies full pipeline:
ingest `.rs` → Citation::Code hit with lang/symbol/line_start.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-19 20:14:59 +00:00
th-kim0823
231d80e82d feat(stats): media/lang/bytes/stale fields on schema.v1.stats (fb-37)
Extends CountSummary with media_breakdown, lang_breakdown, stale_doc_count
fields populated via stats_ext::breakdowns(). Adds count_summary_with_threshold
for callers that need real stale counts. Mirrors all new fields onto the
wire-bound Stats struct in kebab-app::schema with #[serde(default)] for
backwards-compat. Also fixes search_budget_integration.rs for the trace field
added to SearchOpts in Task 1.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-10 12:34:57 +09:00
th-kim0823
b86b763dfb fix(fb-35): address PR #126 round 2 review
- wire schema: relax effective_end.minimum 1 → 0 + expand
  description to cover line-clamp + out-of-range sentinel
  (panic-fix R1 emits Some(0) when line_start=1 and range is
  beyond doc end — schema must accept it)
- tests: tighten first-chunk-target boundary test to assert ≤ 2
  total neighbors (3-chunk doc, N=2). Strict "first chunk →
  context_before empty" not assertable until chunks.ordinal
  column lands (R1 #9 architectural caveat)
- store: trim contradiction in list_chunk_ids_for_doc warning
  comment — drop "good enough for sequentially chunked
  markdown" phrase that conflicts with "hash sort dominates"
  paragraph above

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-10 00:55:29 +09:00
th-kim0823
7dddc1d706 fix(fb-35): address PR #126 round 1 review
- fetch_span: panic-fix on line_start > total / empty doc
  (return empty text + effective_end = line_start - 1 instead of
  out-of-bounds slice)
- truncated: reserved for budget-driven truncation only; line
  range clamp signaled via effective_end < line_end
- spec / SKILL.md / README: align rejection wording to "PDF /
  audio" (matches code; Image OCR allowed for span)
- store: warning comment on list_chunk_ids_for_doc — chunk_id
  hash sort does NOT preserve document position; real fix is a
  chunks.ordinal column, tracked as follow-up
- surrounding_chunks: saturating_add to defend against u32::MAX
  context arg on 32-bit targets
- tests: line_start > total returns empty + chunk context at
  doc boundary clamps lower bound

Deferred nits (follow-up): table-separator strict CommonMark form;
MCP per-mode strict validation; CLI chunk_id truncation in plain
output. None block correctness.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-10 00:45:29 +09:00
th-kim0823
1b9d89eb3a feat(app): App::fetch span mode + PDF/audio rejection (fb-35)
Line-based slice over fmt_canonical_to_markdown output.
PDF / audio source_type → span_not_supported StructuredError.
Out-of-range line_end clamps to total; effective_end reflects
post-budget trim. invalid_input on zero / inverted bounds.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-09 23:54:22 +09:00
th-kim0823
7d1f855f7e feat(app): App::fetch doc mode with budget (fb-35)
Walks CanonicalDocument blocks, serializes to markdown, applies
chars/4 budget when opts.max_tokens is set. doc_not_found
preserved through StructuredError.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-09 23:48:40 +09:00
th-kim0823
610d29f053 feat(app): App::fetch chunk mode + markdown serializer (fb-35)
Chunk mode + +-N context. doc / span modes return placeholder
errors (filled by subsequent tasks). fmt_canonical_to_markdown
helper introduced now since doc mode (Task 4) consumes it.
Errors are typed StructuredError so classify preserves
chunk_not_found / doc_not_found through the wire layer.

Adds SqliteStore::list_chunk_ids_for_doc so the facade can derive
+-N neighbors without leaking direct rusqlite usage into kebab-app.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-09 23:44:51 +09:00
th-kim0823
e084b306e5 fix(fb-34): align next_cursor semantics with docs (PR #125 round 2)
Previous round-1 fix dropped the speculative cursor branch on
the truncated path, leaving a contradiction with the docs:
- snippet-only shrunk → cursor emitted (returned == k_effective)
- k-popped → cursor null (returned < k_effective)
But docs promised the opposite.

R2 resolution: emit cursor whenever more hits may be reachable
(either retriever filled the page OR budget popped hits — the
popped ones remain fetchable from offset+returned). Drop the
artificial "widen vs paginate" copy; truncated and next_cursor
are now independent signals — caller may do either or both.

Updates: app.rs::search_with_opts logic + SearchResponse doc +
schema description + SKILL.md two bullets + max_tokens=0 test
asserts cursor IS emitted on k-pop case.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-09 21:07:04 +09:00
th-kim0823
f485608108 fix(fb-34): address PR #125 round 1 review
- error_wire: StructuredError wrapper preserves ErrorV1 through
  anyhow → classify pipeline. Adds downcast short-circuit so
  cursor::decode's typed code = "stale_cursor" reaches the wire
  instead of being string-formatted to code = "generic".
- app: search_with_opts now wraps cursor::decode error in
  StructuredError instead of anyhow! string format.
- test: error_wire pins both negative (bare anyhow → not
  stale_cursor) AND positive (StructuredError → stale_cursor)
  invariants. CLI integration test runs end-to-end and asserts
  error.v1.code on stderr.
- app: next_cursor only emitted on full-page (k-pop) path; drop
  speculative emit on snippet-only truncation that would point at
  a different page than the agent expected.
- cursor: differentiate malformed-base64 / malformed-payload /
  revision-mismatch error messages; all keep code = stale_cursor.
- test: cursor_rejected fixture uses .expect() to fail loud on
  cursor non-emission instead of silent skip.
- test: max_tokens=0 → 1-hit floor + truncated=true.
- docs: SKILL.md + schema description distinguish snippet-shrink
  (widen) vs k-pop (paginate) truncated cases. HOTFIXES notes
  --no-cache semantic shift (cached path + clear vs uncached path).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-09 20:49:27 +09:00
th-kim0823
af80cedd81 feat(app): App::search_with_opts + SearchResponse (fb-34)
Budget loop: snippet shorten → k pop → ≥1 hit floor. Cursor
encode/decode threads corpus_revision; mismatch surfaces as
stale_cursor anyhow error. App::search retained as thin wrapper.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-09 17:59:48 +09:00
th-kim0823
ebbc3a46ae feat(app): cursor encode/decode for paginated search (fb-34)
Opaque base64(JSON{offset, corpus_revision}). Mismatch or
malformed input returns ErrorV1 with code = stale_cursor.
base64 promoted to workspace dep.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-09 17:49:23 +09:00
th-kim0823
dfef65f196 feat(app): staleness module + post-process search hits (fb-32)
compute_stale: strict > boundary, threshold=0 disables, future
timestamps treated as fresh (clock skew safety). App::search
re-stamps on cache hit so config threshold changes take effect
without flushing the cache.

Also unblocks the workspace build by plugging placeholder
indexed_at/stale into the two AnswerCitation construction
sites in kebab-rag/pipeline.rs (the score-gate refusal path
forwards from SearchHit; the LLM-citation path uses
UNIX_EPOCH/false until Task 7 wires the real values through
pack_context).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-09 01:30:10 +09:00
th-kim0823
7f5739d8fb 🏗️ refactor(fb-31): apply round 1 review nits
- ingest_file_with_config: lowercase normalize ext (caller-side) +
  early error on unsupported extension (`.docx` etc. now Err with
  helpful message instead of silent skipped_by_extension counter).
  New test ingest_file_errors_on_unsupported_extension.
- ingest_stdin_with_config: doc comment explaining intentional
  double-call of ensure helpers (idempotent + ~ms negligible).
- external::inject_frontmatter: simplify precheck via single
  trim_start binding + add CR-only line ending edge case.
- external::inject_frontmatter: doc note on yaml_quote escape
  contract (agent-supplied titles with special chars are safe).

Round 1 review summary: #111 (comment)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 18:46:55 +09:00
th-kim0823
a42f907640 🧪 test(kebab-app): ingest_stdin_with_config integration (fb-31)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 18:04:52 +09:00
th-kim0823
73ee64c73f 🧪 test(kebab-app): ingest_file_with_config integration (fb-31)
Three scenarios — copies external md + reports new=1, idempotent on
second call (unchanged=1), errors on missing path.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 18:02:52 +09:00
th-kim0823
366b647a1a feat(kebab-app): capability flag mcp_server: false → true (fb-30)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 16:12:23 +09:00
th-kim0823
3e33daaa9b 🧪 test(kebab-app): assert chunk_count + asset_count in schema_report (fb-27)
Plug coverage hole flagged in code review — test 1 was asserting only
doc_count + last_ingest_at, leaving count_summary's chunk_count and
asset_count queries un-pinned.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 12:06:04 +09:00
th-kim0823
ab96335174 🧪 test(kebab-app): schema_with_config integration coverage (fb-27)
Two scenarios: freshly-ingested 2-doc KB (stats reflect counts +
last_ingest_at populated) and empty-but-initialized KB (counts zero,
last_ingest_at None). The empty case runs ingest_with_config over an
empty workspace dir to seed kebab.sqlite before calling schema_with_config,
since open_existing (used internally) returns NotIndexed if the DB is absent.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 12:02:20 +09:00
9545367904 feat(kebab-app): p9-fb-25 task 5 — Skipped warnings + skipped_by_extension aggregation
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 12:13:13 +00:00
d64282433c feat(kebab-app): p9-fb-25 task 3 — init_workspace header lists supported extensions
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 11:55:38 +00:00
ef5d0770ae review(p9-fb-25-task1): fix kebab-app test references to removed WorkspaceCfg.include
reviewer-flagged: task 1 missed test files using cfg.workspace.include.

- crates/kebab-app/tests/common/mod.rs: SourceScope literal switched
  to ..Default::default().
- crates/kebab-app/tests/image_pipeline.rs (×3): drop dead-no-op
  cfg.workspace.include.push(...) calls; comment explains removal.
- crates/kebab-app/tests/pdf_pipeline.rs: same treatment.

Pre-fb-25 these pushes were no-ops (include was dead config field
not enforced anywhere). Removal is purely mechanical.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 11:53:19 +00:00
0e6d6073e7 feat(kebab-app): p9-fb-23 task 7 — early-skip Unchanged path in ingest
Adds the per-asset incremental-ingest skip block to all three flows
(markdown / image / pdf). When `IngestOpts::force_reingest = false`
AND the asset's blake3 checksum + parser/chunker/embedding versions
all match the existing DB record, ingest emits
`AssetFinished { result: Unchanged }`, bumps `aggregate.unchanged`,
and skips parse / chunk / embed / vector upsert entirely.

Shared `try_skip_unchanged` helper performs the four checks; per-flow
callers supply the active parser_version + chunker_version + optional
embedding_version. `force_reingest = true` bypasses the skip path so
`incremental_ingest::force_reingest_bypasses_skip` still sees `Updated`.

Tests:
- new `incremental_ingest.rs` covers both paths.
- existing `ingest_idempotent_on_second_run` /
  `re_ingest_image_produces_*` / `re_ingest_identical_pdf_produces_*`
  updated to assert `Unchanged` on identical-bytes re-ingest (the
  pre-task behaviour was `Updated`).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-04 18:12:47 +00:00
4874304d5d refactor(kebab-app): p9-fb-23 task 6 — IngestOpts struct + ingest_with_config_opts entry
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-04 18:04:50 +00:00
a16e9c9215 feat(kebab-app): p9-fb-23 task 5 — stamp chunker + embedding versions on CanonicalDocument before put_document
All three ingest flows (markdown, image, pdf) now set
last_chunker_version and last_embedding_version on the CanonicalDocument
before calling put_document, giving Task 7's skip detection the data it
needs on the second run. No skip path is added yet.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-04 18:01:48 +00:00
3f0b00439a review(p9-fb-10-task5): promote lexical_query to common + tighten Korean hit assertion
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-03 10:14:17 +00:00
60e583252e test(kebab-app): Korean query → FTS5 smoke pin
p9-fb-10: verifies that a Korean (Hangul) token survives the
ingest → FTS5 lexical search round-trip via the kebab-app facade.
NFC normalization is wired upstream in kebab-normalize; this test
only exercises end-to-end correctness — no AVX, no fastembed required.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-03 10:08:32 +00:00
0e408fb1b5 feat(kebab-app + kebab-store-sqlite): p9-fb-19 search LRU cache + corpus_revision
도그푸딩 item 15 — TUI / 같은 process 안에서 동일 query 반복 시 SQLite
FTS + Lance + RRF 재계산이 매번 발생하던 비용 해소. in-process LRU
캐시 + 모노토닉 corpus_revision 카운터로 ingest commit 발생 시 모든
entry 자동 stale.

## 핵심 변경

- **SQLite V004 migration**: `kv (key TEXT PRIMARY KEY, value TEXT)
  STRICT` + `corpus_revision = '0'` seed. 미래의 다른 scalar 도 같은
  테이블에 들어갈 수 있는 generic shape.
- **`SqliteStore::corpus_revision()` / `bump_corpus_revision()`** —
  `UPDATE ... CAST AS INTEGER + 1` atomic. INSERT-OR-IGNORE 도 함께
  실행 (V004 seed 가 무슨 이유로 누락된 케이스 paranoid).
- **`kebab-app::ingest_with_config_cancellable`** — `new + updated > 0`
  시 bump, no-op (skipped-only) reingest 는 cache 보존.
- **`App.search_cache: Option<Mutex<LruCache<SearchCacheKey, Vec<
  SearchHit>>>>`** — `config.search.cache_capacity` (default 256, 0
  비활성). `lru = "0.12"` workspace dep 추가.
- **`SearchCacheKey`** = `query_norm` (NFKC + trim + lowercase) +
  `mode` + `k` + `snippet_chars` + `embedding_version` (vector/hybrid
  만, lexical 은 빈 문자열) + `chunker_version` + `corpus_revision`
  snapshot.
- **`App::search`** rewrite — cache 활성 시 lookup → miss 면 기존
  `search_uncached` 호출 후 put. cache 비활성이거나 lock 실패면
  straight-line.
- **`App::search_uncached`** (rename of pre-fb-19 `search` body) +
  `search_uncached_with_config` facade — CLI `kebab search --no-cache`
  로 진입.
- **`Config.search.cache_capacity: usize`** field, `#[serde(default)]`
  로 기존 config 호환.
- **CLI `--no-cache`** flag — 디버깅용 (CLI 는 매 호출이 새 process
  라 사실상 no-op 이지만 spec 명시 + 향후 long-lived process 호환).
- **frozen design §9 versioning** 표에 `corpus_revision` row 추가
  (기존 `index_version` 라벨과 다른 차원: 라벨은 retrieval 형상,
  corpus_revision 은 ingest commit ack).

## 테스트

- `kebab-store-sqlite` 신규 3 unit (fresh=0, monotonic bump, persist
  across reopen)
- `kebab-app` 신규 4 integration (cached repeat 같은 hits, NFKC 정규화
  로 case/whitespace collapse, --no-cache parity, first ingest bumps
  corpus_revision)
- 워크스페이스 전체 `cargo test --workspace --no-fail-fast -j 1` exit 0
- `cargo clippy --workspace --all-targets -- -D warnings` clean

## 문서

- README `kebab search` 행: 캐시 동작 + `--no-cache` 안내 + corpus_
  revision 무효화 메커니즘
- docs/SMOKE.md `[search]` 절에 `cache_capacity` 라인 추가
- HANDOFF: 2026-05-03 entry
- spec status planned → in_progress

## Out of scope

- patch-and-merge incremental (RRF 정규화 전체 hit set 기준이라 어려움)
- SQLite 영속 cache (P+)
- 다른 process 간 cache 공유 (in-process 만 — corpus_revision 이
  cross-process 무효화는 O(1))

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-03 05:01:31 +00:00
2c058ab175 feat(rag): multi-turn ask — Turn struct + ask_with_history + token budget (p9-fb-15)
Spec PR #59 의 §3.8 multi-turn behaviour 구현. RAG facade 가 prior
turns 받아 prompt 에 prepend, retrieval query expansion 적용,
Answer 에 conversation_id / turn_index 채움.

신규 (kebab-core):
- Answer 에 conversation_id (Option<String>) / turn_index (Option<u32>)
  field 추가. serde skip_serializing_if 로 single-shot 의 wire
  output 변경 0 (기존 외부 wrapper 영향 없음).
- Turn struct (question + answer + citations + created_at).
- RefusalReason::LlmStreamAborted variant.

신규 (kebab-rag):
- AskOpts 에 history (Vec<Turn>) / conversation_id / turn_index 3 field.
- AskOpts::single_shot(mode) helper.
- RagPipeline::ask_with_history(query, history, conversation_id,
  turn_index, opts) — combined opts 로 ask 호출.
- expand_query_with_history: history.last() 의 answer 첫 200 자
  concat 해 SearchQuery.text 확장 (spec §3.8 의 \"cheap concat\";
  LLM-based standalone-question rewriting 은 P+).
- serialize_history + remaining_history_budget_chars: spec 의 priority
  enforcement — system+question 필수, retrieved chunks 가 차지한
  뒤 남은 char budget 안에서 newest 우선, oldest drop.
- ask 본문: history 가 비어있지 않으면 [이전 대화] 블록을 user
  prompt 위에 prepend. Answer 생성 site 3 곳 (정상 / NoChunks /
  ScoreGate refuse) 모두 conversation_id / turn_index 채움.

신규 (kebab-store-sqlite):
- refusal_reason_label 가 LlmStreamAborted → 'llm_stream_aborted'.

기존 caller 변경 (single-shot 동작 동일):
- kebab-cli main.rs Cmd::Ask: AskOpts 에 history=Vec::new(),
  conversation_id=None, turn_index=None 명시 (CLI multi-turn 은
  p9-fb-18 의 --session/--repl 가 채움).
- kebab-tui src/ask.rs spawn site 동일 (multi-turn UI 는 p9-fb-16).
- kebab-eval runner.rs golden eval 동일 (single-shot per query).
- kebab-app tests/ask_smoke.rs / kebab-tui tests/ask.rs / kebab-rag
  tests/pipeline.rs / kebab-eval metrics.rs Answer literal 갱신.

Test:
- 9 신규 lib unit (expand_query 4 / serialize_history 3 / remaining_budget 2).
- 기존 12 PASS 회귀 0.

Plan 갱신:
- p9-fb-15 status planned → in_progress. 머지 후 한 줄 commit
  으로 completed flip.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 23:09:46 +00:00
6260df5b30 review(회차1): SIGNAL_COUNT lifetime 명시 + cancel-mid race 코멘트
회차 1 actionable 2건 반영 + 1건 (CLI Ctrl-C integration test)
은 본 PR 에서 별도 task 로 미룸 (signal handler subprocess test 의
flaky 위험 + facade 3 PASS + tui lib 3 PASS 가 안정 surface).

- cancel.rs::install_sigint_cancel: SIGNAL_COUNT 위에 process-lifetime
  invariant 코멘트 — multi-install 차단 (ctrlc::set_handler) 덕분에
  reset 불필요. 미래 다중 caller 가 같은 cancel token 공유하려면
  install 함수 분리 필요.
- ingest_cancel.rs::cancel_mid_loop: redundant `report.new == 1 || 0
  || 2` 제거, race timing 의도 코멘트로 대체 (0=listener 승, 1=first
  only, 2=extra slipped in 모두 valid; 3 = cancel never propagated
  = 유일한 fail).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 21:39:39 +00:00
fa02a7c68d feat: ingest cooperative cancellation (p9-fb-04)
Ctrl-C / Esc 가 ingest 를 즉시 중단. 현재 in-flight asset 마무리 후
이후 asset 미실행, IngestEvent::Aborted { partial_counts } 발신,
Ok(IngestReport) 정상 반환 (Err 아님). 부분 commit 보존, 다음 ingest
가 idempotent 재개.

신규 facade: kebab-app::ingest_with_config_cancellable(.., progress,
cancel: Option<Arc<AtomicBool>>). 기존 _progress 가 cancel=None
forwarding wrapper. asset loop 시작 boundary 마다 atomic load —
true 면 break + Aborted emit + 정상 종료. Lock 없음.

CLI: ctrlc crate 신규 dep. SIGINT handler 가 첫 신호에 cancel.store(true)
+ stderr hint, 두 번째 신호에 std::process::exit(130) (canonical SIGINT
exit code). install_sigint_cancel() helper 가 Arc<AtomicBool> 반환,
Cmd::Ingest 가 facade 에 전달.

TUI: IngestState 에 cancel: Arc<AtomicBool> field 추가 (회차 1 review
결과의 reshape 정확). start_ingest 가 둘 다 만들어 worker 에 clone
move. cancel_running_ingest(&app) helper — Esc / Ctrl-C 가
ingest 진행 중일 때만 cancel 우선, 그 외에는 quit.

Test:
- 3 facade integration (cancel-before / cancel-mid / no-cancel
  default).
- 3 tui lib unit (cancel_running_ingest no-state / in-flight /
  terminated).

Plan 갱신: p9-fb-04 status planned → in_progress. 머지 후 한 줄
commit 으로 completed flip.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 21:36:17 +00:00
eb331f9b29 feat(app): add IngestEvent + ingest_with_config_progress (p9-fb-01)
Streaming progress channel for ingest. Facade emits one IngestEvent per
step boundary into an optional `mpsc::Sender<IngestEvent>` injected by
the caller. CLI (p9-fb-02), TUI (p9-fb-03), and future desktop UI all
consume the same stream.

신규:
- crates/kebab-app/src/ingest_progress.rs: `IngestEvent` enum (`#[serde(tag
  = "kind", rename_all = "snake_case")]` matching wire schema
  ingest_progress.v1) + `AggregateCounts` struct + `media_label` helper
  + best-effort `emit` helper.
- ingest_with_config_progress(cfg, scope, summary_only, progress) —
  존재 시 `mpsc::Sender<IngestEvent>` 로 ScanStarted → ScanCompleted →
  (AssetStarted < AssetFinished)* → Completed 발신. dropped receiver
  는 silent absorb (hot path stall 금지).
- 기존 ingest_with_config 가 `progress=None` forwarding wrapper.

미적용 (계약 상 향후 task 가 채움):
- IngestEvent::Aborted: cancel token wiring 은 p9-fb-04.
- embed_batch_started / embed_batch_finished: spec 의 \"asset 이벤트 사이
  임의 위치\" 에 해당. v1 단순화 — asset 단위 해상도면 CLI / TUI 충분.

Test:
- 6 lib unit (media_label / serde discriminator / emit corner cases).
- 3 integration (이벤트 sequence 가 §2.4a invariant 준수 / forwarding
  wrapper / dropped receiver tolerance).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 19:44:34 +00:00
3a57cab1eb fix(kebab-store-sqlite): purge stale assets row on workspace_path orphan + smoke
P7-3 통합 테스트가 노출한 storage 레이어 버그 fix.
`assets.workspace_path` 의 UNIQUE 제약과 `upsert_asset_row` 의
`ON CONFLICT(asset_id)` 만 처리하던 gap 사이 — byte 가 변경된 자산
re-ingest 시 새 asset_id 가 같은 workspace_path 에서 secondary UNIQUE
충돌. md / image / pdf 모두 영향.

Fix:
- 새 helper `purge_orphan_at_workspace_path` 가 같은 `workspace_path`
  의 *다른* `asset_id` 를 발견하면 documents → assets 순서로 sweep.
  documents 의 ON DELETE RESTRICT 회피 + CASCADE 로 blocks / chunks /
  embedding_records 정리. copied 모드면 storage_path 의 byte 파일도
  best-effort 삭제.
- `put_asset_with_bytes` 의 두 분기 (copy / reference) + `DocumentStore
  ::put_asset` 모두 호출.
- 회귀 테스트 `put_asset_with_bytes_sweeps_workspace_path_orphan` (이전
  의 "UPSERT 실패시 orphan 청소" 테스트가 더 이상 doable 하지 않으므로
  대체).
- `re_ingest_edited_pdf_produces_new_doc_id` integration `#[ignore]` 해제 →
  9 통합 테스트 모두 default 로 통과.

Vector store orphan 은 별도 P+ task — LanceDB 가 SQLite cascade 와 무관하게
운영되므로 stale chunk_id vector 가 디스크에 남음. 검색에는 영향 없음 (search 가
SQLite join 통해 surface).

Smoke 검증 (release binary, markdown 2 + image 1 + PDF 2):
- doctor pass
- 첫 ingest: 5 new
- list docs: 5 docs all media types
- search lexical "pdf-page-v1 chunker" → whitepaper.pdf hit
- search hybrid → cross-media 결과
- inspect doc PDF: parser_version=pdf-text-v1, blocks 가 SourceSpan::Page
- 동일 byte re-ingest: 5 updated, 0 errors (P1 idempotency)
- byte 수정 후 re-ingest: 1 new (해당 PDF) + 4 updated, 0 errors (storage fix)
- corrupt PDF 추가: errors+=1 + IngestItem.error 메시지 정확, 다른 자산 영향 0
- 정리 후 다시 ingest: errors=0
- RAG ask: PDF 인용 + `citations[].citation` 에 `kind: "page"` + `page: <N>` +
  `path: <pdf_path>` 정확히 노출

운영 fixture 보조:
- `crates/kebab-parse-pdf/examples/gen_smoke_pdf.rs` — `cargo run --release
  --example gen_smoke_pdf -p kebab-parse-pdf -- <out.pdf> <text-pages>` 로
  reportlab/qpdf 없이 in-tree PDF 생성.
- `crates/kebab-parse-image/examples/gen_smoke_png.rs` — 동일 방식의 PNG
  fixture 생성.
- SMOKE.md 가 두 example 사용법 + 갱신된 HOTFIXES 동작 (byte 수정 시
  errors+=1 → new+=1) 반영.

HOTFIXES `2026-05-02 P7-3` entry 가 \"deferred\" → \"fixed in same PR\" 로
업데이트, vector store orphan caveat 만 남음.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 11:41:23 +00:00
4ad4ef271e review(p7-3): 회차 1 지적 반영
- `IngestItem.warnings` 가 PDF path 에서 빈 vec 였던 갭 해소. P7-1 의
  Provenance Warning (scanned candidate / extract panic 흡수) 노트들을
  `IngestItem.warnings` 로 surface — md path 의 `fm_warns + blk_warns`
  patten 과 평행. 사용자가 ingest summary 에서 "이 PDF page 2 가 스캔
  이라 검색 불가" 를 즉시 확인 가능.
- `mixed_page_pdf_stores_asset_with_scanned_candidate_warning` 에
  `IngestItem.warnings` 단정 추가 (정확히 1건 + 노트 내용 검증).
- `encrypted_pdf` / `corrupt_pdf` 테스트의 `errors >= 1` → `errors == 1`
  strict 단정. 미래에 다른 source 가 errors 늘리면 즉시 빨개짐.
- `re_ingest_identical_pdf` 에 `chunk_count` 동일성 단정 추가. P1
  idempotency contract 의 chunk-단위 axis 검증 (chunk_id 전체 set 비교는
  pdf-page-v1 의 `deterministic_chunk_ids_1000` 가 잠그고 있어 chunk_count
  가 가벼운 proxy 로 충분).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 09:31:55 +00:00
5f3a37cafa feat(kebab-app): P7-3 PDF ingest wiring — kebab ingest 가 PDF 자산도 처리
P7-1 (`PdfTextExtractor`) + P7-2 (`PdfPageV1Chunker`) 의 라이브러리를
`kebab-app::ingest_with_config` 에 와이어링. `kebab-source-fs` 가 이미
`*.pdf` 를 `MediaType::Pdf` 로 분류하던 자산이 이제 검색 가능한 doc 으로
색인됨. P6-4 image wiring 패턴과 평행 — `ingest_one_asset` 에 `MediaType::Pdf`
arm 추가, 새 private fn `ingest_one_pdf_asset` 로 분기.

핵심 동작:
- per-medium chunker 선택: PDF 자산은 `PdfPageV1Chunker` 하드코딩 (compile-time
  match 기반). `config.chunking.chunker_version` 은 markdown 만 represent —
  PDF 는 항상 `pdf-page-v1`. HOTFIXES entry `2026-05-02 P7-3` 에 deviation 기록.
- encrypted PDF / corrupt PDF → `errors+=1` + P7-1 의 `qpdf --decrypt` hint
  를 `IngestItem.error` 에 verbatim 보존.
- 빈/scanned candidate 페이지 → 0 chunk, P7-1 의 `Provenance::Warning` 그대로
  통과. v1 에서는 검색 불가, P+ scanned-PDF OCR fallback 대기.
- determinism stress: extract → chunk 사이 `now()` 추가 호출 없음 (P6-4 invariant
  계승). PDF doc/chunk_id 모두 결정적.

통합 테스트 (`tests/pdf_pipeline.rs`, 8 passed + 1 ignored):
- 3-page text PDF → 1 doc + 3 chunk + Page span 검증
- identical re-ingest → Updated, doc_id 동일
- encrypted PDF → Error + `qpdf` hint 보존
- corrupt header PDF → Error + 미저장
- mixed page (page 2 빈) → 2 chunk + Warning 1개
- IngestReport 산술 invariant
- 50-page 긴 PDF → ≥50 chunk
- inspect doc → SourceSpan::Page round-trip
- (ignored) edited bytes re-ingest → storage UNIQUE bug 노출, P+ fix 대기

추가 발견 (HOTFIXES `2026-05-02 P7-3`): `assets.workspace_path` 의 UNIQUE
제약과 `upsert_asset_row` 의 `ON CONFLICT(asset_id)` 만 처리하는 부분 사이에
gap 존재. byte 변경 시 새 asset_id → 같은 workspace_path 충돌. md / image / pdf
모두 영향. P7-3 통합 테스트가 처음 노출. 본 PR 은 fix 안 함 — P+ storage task.

`docs/SMOKE.md` 에 PDF 섹션 + 검증 체크리스트 + 알려진 동작 4건 추가.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 09:28:06 +00:00
6e4884aff8 fix(kebab-app): IngestReport.errors double-count regression — increment only in match item.kind { Error => ... } arm
수동 스모크 검증 (12 PNG + 손상 PNG) 중 발견. `IngestReport.errors`
가 자산 한 장당 2회 증가해서 `scanned = new + updated + skipped +
errors` invariant 가 깨짐:

- `garbage.png` (이미지 아닌 바이트, .png 확장자만) 1장 + 정상 자산
  3장 → 기대 `scanned=4 errors=1`, 실제 `scanned=4 errors=2`.
- 원인: `match item { Err(e) => { error_count += 1; IngestItem {...} }
  }` 에서 1회 증가 후, 직후 `match item.kind { Error => { error_count
  += 1 } }` arm 에서 또 1회 증가.
- markdown 경로의 `ingest_one_asset` Err 가 거의 발생 안 해서 P6-4
  머지 전까지 표면화 안 됐던 기존 결함. 이미지 dispatch 가 garbage
  bytes 를 Err 로 흘려보내며 처음으로 노출.

수정: `Err(e)` 분기의 `error_count.saturating_add(1)` 제거. 단일
증가 지점은 `match item.kind { Error => ... }` arm. 코멘트로 의도
명시.

회귀 테스트 추가 (`tests/image_pipeline.rs`):
- `garbage_png_increments_errors_counter_exactly_once` — 정확히 1
  증가 + `scanned == new + updated + skipped + errors` invariant
  검증.

검증 — release binary + 실 Ollama (192.168.0.47 / gemma4:e4b):

```
$ kebab --json ingest
scanned=4 new=3 updated=0 skipped=0 errors=1
  error    garbage.png       (extract Err — unrecognised format)
  new      intro.md
  new      normal.png        (OCR success)
  new      truncated.png     (OcrFailed warning, asset still indexed)
```

cargo test --workspace --no-fail-fast -j 1 — 전부 pass.
cargo clippy --workspace --all-targets -- -D warnings — pass.
cargo test -p kebab-app --test image_pipeline — 6 pass (5 기존 + 1 회귀).
2026-05-02 08:13:41 +00:00
469a1a34ec review(p6-4): 회차 1 지적 반영
- src/lib.rs:
  • `ingest_one_asset` 의 doc-comment 가 새 `ImagePipeline` struct 와
    합쳐지던 (rustdoc 가 두 doc 을 struct 의 것으로 합치던) 문제
    해소 — 두 doc-comment 위치 교환 + 빈 줄 분리.
  • `if let Some(Block::ImageRef(...)) = blocks.first_mut()` 의
    silent-skip 분기를 `match` 의 `other` arm 으로 명시 — 미래에
    P6-1 contract 가 깨지면 `tracing::warn!` + Provenance Warning +
    `IngestItem.warnings` 에 \"ImageDispatchAnomaly\" 노트로 즉시
    가시화. 운영 디버깅 단서 제공.
  • OCR 실패 분기 + caption 실패 분기의 ~25줄 boilerplate 를
    `record_image_analysis_failure` 헬퍼로 추출 — 두 호출이 한 줄로
    줄고 미래 ProvenanceEvent 필드 변경이 한 곳에서 끝남.
  • 분석 단계 Warning 이벤트가 fn 진입 시 캡처한 단일
    `OffsetDateTime::now_utc()` 를 공유 — spec Risks/notes 의
    \"Determinism stress: must not introduce a second `now()` call
    between extract and apply_ocr/caption\" 약속 회복.
  • 경고 라벨을 markdown 경로의 `WarningKind` 컨벤션 (`{kind}: {note}`)
    에 맞춤 — `\"ocr_failed: ...\"` → `\"OcrFailed: ...\"`,
    `\"caption_failed: ...\"` → `\"CaptionFailed: ...\"`. 같은 wire
    필드 (`IngestItem.warnings`) 가 두 갈래의 다른 형식을 갖던
    inconsistency 해소.
- tests/image_pipeline.rs:
  • 회귀 테스트의 \"ocr_failed\" assertion 을 \"OcrFailed\" 로 갱신.

cargo test -p kebab-app -p kebab-chunk — 전부 pass.
cargo clippy --workspace --all-targets -- -D warnings — pass.
2026-05-02 07:42:44 +00:00
ca0567c72b feat(kebab-app): P6-4 image ingest wiring — kebab ingest 가 PNG/JPEG 자산도 처리
P6-1/P6-2/P6-3 의 라이브러리 (`ImageExtractor`, `OllamaVisionOcr`,
`apply_caption`) 가 그동안 CLI 에서 보이지 않던 미완 구간을 완성.
이제 `kebab ingest` 가 markdown 외에 이미지 자산을 end-to-end 로
색인하고, `kebab search` / `kebab ask` 가 OCR 텍스트 + caption 으로
이미지를 매칭/인용한다.

## kebab-app

- `[dependencies]` 에 `kebab-parse-image` 추가.
- `ingest_with_config` 진입 시 `image.ocr.enabled` / `image.caption.enabled`
  플래그에 따라 `OllamaVisionOcr` / `OllamaLanguageModel` 을 **ingest
  세션당 1회** 빌드. 자산 루프에서 trait object 로 공유.
  reqwest::blocking::Client 의 내부 Arc 덕분에 알로케이션 비용은
  자산 수와 무관.
- 두 어댑터 + ImageExtractor 를 한 묶음으로 `ImagePipeline` 구조체에
  담아 `ingest_one_asset` 매개변수 폭증 차단 (clippy::too_many_arguments
  대응).
- `ingest_one_asset` 의 markdown-only 가드를 `match media_type` 으로
  교체 — Markdown 은 기존 경로, Image(_) 는 새 `ingest_one_image_asset`
  로 분기, PDF/Audio/Other 는 종전대로 skipped.
- 신규 `ingest_one_image_asset`:
  - bytes 읽기 → `ImageExtractor::extract` (실패 시 caller 가 errors+=1)
  - `apply_ocr` (Lenient — 실패 시 ProvenanceKind::Warning 이벤트 +
    `IngestItem.warnings` 에 \"ocr_failed: ...\", `block.ocr` 는 None
    유지)
  - `apply_caption` (동일 Lenient 정책)
  - 기존 `MdHeadingV1Chunker` 호출 — 청커는 이미 `Block::ImageRef` 를
    단일 청크로 emit
  - 기존 persist + embed 시퀀스 그대로 (markdown 과 byte-identical)
- `lang_hint_from_doc` — `Lang(\"und\")` 또는 빈 문자열을 None 으로
  매핑 (image-pipeline 어댑터의 build_prompt 가 \"und\" 를 silent drop
  하지 않도록 caller 측에서 미리).

## kebab-chunk

- `render_block_text` 의 `Block::ImageRef` 분기를 P6-4 (β) plain
  concat 정책으로 교체 — `[alt, ocr.joined, caption.text]` 를 `\\n\\n`
  로 join, 빈 부분은 drop. alt 가 비면 `src` 의 basename 으로 fallback
  (P6-1 contract 의 defensive guard).
- 신규 unit 테스트 `image_ref_p6_4_plain_concat_drops_empty_parts` —
  alt-only / alt+ocr / alt+caption / alt+ocr+caption / 빈 alt → src
  fallback 다섯 케이스 모두 검증.
- 기존 `image_ref_emits_own_chunk_zero_tokens` 그대로 통과 — 청커의
  per-block dispatch 는 변경 없음, text 렌더링만 갱신.

## 통합 테스트 (kebab-app/tests/image_pipeline.rs)

wiremock 으로 Ollama 를 stub. 5건:

1. OCR-only happy path — 1 PNG + ocr.enabled → 1 doc + 1 chunk emit,
   `block.ocr.joined` 가 mock 의 \"Hello World 2026\".
2. OCR + caption 동시 활성 — 두 필드 모두 채워지고 chunk text 에
   alt + ocr + caption 세 부분 모두 포함.
3. Lenient 실패 검증 — OCR 503 시 자산은 indexed (kind=New),
   `errors=0`, ProvenanceKind::Warning attributed to \"kb-app\",
   `IngestItem.warnings` 에 \"ocr_failed:\" 노트.
4. 양쪽 비활성 — `image.ocr.enabled=false && image.caption.enabled=false`
   여도 자산은 chunk 1개로 indexed (chunk text=filename), EXIF +
   dimensions 그대로 채워짐.
5. 결정성 (re-ingest) — 동일 PNG 두 번 ingest 시 두 번째는
   `Updated` + 동일 `doc_id`.

## SMOKE.md

`kebab search --mode lexical \"Hello World\"` 단계를 명령 시퀀스에
추가. `[image.ocr]` / `[image.caption]` config 절 예시 + ingest 시간
추정 (자산당 ~5-10초) 추가. \"책은 P7 PDF 라인으로\" 가이드를 검증
체크리스트 와 \"알려진 동작\" 양쪽에 박음.

## 실 Ollama 통합 검증

192.168.0.47 + gemma4:e4b 기준:

```
$ kebab --config /tmp/kebab-smoke/config.toml ingest
scanned 2  new 2  updated 0  skipped 0  errors 0  (18395 ms)

$ kebab inspect doc <image_doc_id>
parser_version: image-meta-v1
blocks: [{
  alt: \"hello.png\",
  ocr: \"Hello World 2026\",
  caption: \"The image displays the text \\\"Hello World 2026\\\" in a large, black, sans-serif font.\"
}]

$ kebab --json ask \"Hello World 텍스트가 어디에 있나?\" --mode hybrid
grounded: true
citations: [{marker: \"[1]\", doc_path: \"hello.png\"}]
```

## 검증

- `cargo test --workspace --no-fail-fast -j 1` — 전부 pass
- `cargo clippy --workspace --all-targets -- -D warnings` — pass
- `cargo test -p kebab-chunk image_ref` — 2 pass (P1-5 회귀 + P6-4
  신규 unit)
- `cargo test -p kebab-app --test image_pipeline` — 5 pass

## 의존성 경계

- `kebab-app` 이 `kebab-parse-image` 추가 — spec Allowed dep 그대로.
- 새 forbidden 침범 없음 (기존 `kebab-tui` / `kebab-desktop` /
  `kebab-eval` 미참조 유지).
- 본 task 가 신설하는 image-specific 비즈니스 로직 0줄 — 모두
  `kebab-parse-image` 에 위임.

`tasks/p6/p6-4-image-ingest-wiring.md` status: planned → completed.

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.
2026-05-02 07:37:56 +00:00
f1a448d6dc refactor(rename): kb → kebab — binary, env vars, XDG paths, file renames
두 번째 commit. 사용자 facing surface (CLI binary, env vars, XDG paths)
+ 코드 안 single-letter token (`KB_`, `kb.sqlite`, `/kb/`, tracing
target) 일괄 rename. 그리고 3 개 file rename:

- 디자인 doc `2026-04-27-kb-final-form-design.md` →
  `2026-04-27-kebab-final-form-design.md`
- 최초 보고서 `kb_local_rust_report.md` → `kebab_local_rust_report.md`
- workspace ignore `.kbignore` → `.kebabignore`

## 변경

- `crates/kebab-cli/Cargo.toml`: `[[bin]] name = "kb"` → `"kebab"`.
- `crates/kebab-cli/src/main.rs`: `#[command(name = "kb", …)]` →
  `name = "kebab"`.
- 모든 `KB_*` env var (코드 + doc + 테스트) → `KEBAB_*`. apply_env
  prefix 매칭 + 30+ 개 setting 키 모두.
- XDG paths: `~/.config/kb` / `~/.local/share/kb` / `~/.cache/kb` /
  `~/.local/state/kb` → `~/.config/kebab` 등. config defaults +
  expand_path tests + paths.rs 의 hardcode 모두.
- SQLite filename: `kb.sqlite` → `kebab.sqlite` (`SQLITE_FILE` const
  + 테스트 hardcode 모두).
- tracing target: `target: "kb-*"` → `"kebab-*"` (10+ 곳).
- snapshot fixture: `.kbignore` → `.kebabignore` (`fixtures/source-fs/
  tree-1.snapshot.json` 갱신).

## 검증

- `cargo test --workspace -j 1` clean (linker OOM 회피 위해 직렬).
- `cargo clippy --workspace --all-targets -- -D warnings` clean.

다음 commit 에서 docs sweep.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 04:01:35 +00:00
911fb49550 refactor(rename): kb crates → kebab — Cargo packages, folders, Rust modules
프로젝트 이름 `kb` → `kebab` rename 의 첫 단계.

- workspace `Cargo.toml`: members `crates/kb-*` → `crates/kebab-*`,
  repository URL `altair823/kb` → `altair823/kebab`.
- 18 crate 폴더 rename via `git mv` (history 보존).
- 각 crate `Cargo.toml`: `name = "kb-*"` → `"kebab-*"`, path deps
  `../kb-*` → `../kebab-*`.
- 모든 `.rs`: `kb_<id>` snake-case 모듈 path 18 개 (`kb_core`,
  `kb_config`, `kb_app`, `kb_cli`, `kb_eval`, `kb_search`, `kb_chunk`,
  `kb_normalize`, `kb_source_fs`, `kb_parse_md`, `kb_parse_types`,
  `kb_store_sqlite`, `kb_store_vector`, `kb_embed`, `kb_embed_local`,
  `kb_llm`, `kb_llm_local`, `kb_rag`) → `kebab_<id>` 일괄 sed (단어
  경계 \\b 사용해 영어 문장 안의 "kb" 약어 미오염).

CLI binary 이름 (`[[bin]] name = "kb"`), 환경변수 `KB_*`, XDG paths,
tracing target, 그리고 docs sweep 은 다음 commit 에서.

## 검증

- `cargo check --workspace` clean — 모든 crate 빌드 통과 후 commit.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-02 03:28:08 +00:00