config.workspace.include was completely ignored by the walker — connector.rs
log_scope_include_warning literally said "handled by extractor router" but
no extractor router exists. Dogfooding (PR #142 1B + multi-root corpus
kebab-docs + httpx + zod + lodash) showed user-set include of code+md still
ingested 84 .png + 8 .pdf files.
Fix: walker treats scope.include as an allow-list — empty Vec preserves
backward-compat (all files pass), non-empty requires file path to match at
least one pattern (AND with the existing exclude rules). Removed the
misleading debug log.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
dogfood-discovered code_lang/repo filter bug (PR #144) fix lands in
production. patch bump because:
- 1A-1 advertised CLI flags --code-lang / --repo were live but inert
(SearchFilters fields propagated but never applied to retriever SQL)
- fix restores intended behavior; no new wire surface
- user has dogfooded against httpx + zod + lodash and re-validating
needs the fixed binary
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
Tasks 5-8: new `kebab-parse-code` crate with three infrastructure modules
for the code ingest framework. Ships lang.rs (extension→language identifier
mapping), repo.rs (.git walk-up via gix 0.70 for RepoMeta), and skip.rs
(BUILTIN_BLACKLIST, is_generated_file, is_oversized). 14 integration tests
across three test files, all passing; clippy -D warnings clean.
Note: gix pinned to 0.70 (not 0.83 as originally suggested) because 0.83
fails to compile against Rust 1.94.1 due to non-exhaustive match patterns
in gix-hash. 0.70 resolves cleanly and has identical head_name/head_id API.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
PR #127 added time = { workspace = true } to kebab-mcp/Cargo.toml
but Cargo.lock entry was not regenerated before merge. cargo build
on main locally regenerates the +time line under kebab-mcp.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
fb-32 머지로 wire schema 가 search_hit.v1 / citation.v1 의 required
필드를 두 개 (indexed_at, stale) 확장 — additive minor 로 분류했지만
strict validator 입장에서는 한 번 깨진 셈이라 minor bump.
surface 변경 (사용자 도그푸딩 영향):
- 모든 search hit / RAG citation 의 wire JSON 에 indexed_at (RFC3339) +
stale (bool) 두 필드 추가
- CLI plain 출력 — stale doc 의 doc_path 옆에 [stale] tag (TTY = 노란색)
- TUI Search/Inspect/Ask pane — stale doc 의 doc_path 좌측에 [STALE] 배지
(Theme::Warning role)
- config.toml [search] stale_threshold_days 신규 (default 30, 0 = 비활성)
- env KEBAB_SEARCH_STALE_THRESHOLD_DAYS
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Yellow when TTY, plain when not. JSON path inherits via serde
on the domain type; no CLI-side wire change needed there.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
JOIN documents.updated_at. stale defaults to false; App facade
post-processes against config threshold.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
agent integration MVP (fb-30 MCP server stdio) 머지 후 patch bump.
trigger:
- 신규 CLI surface `kebab mcp` (additive, 기존 명령 동작 무영향)
- new crate `kebab-mcp` (lib only, transitive 만)
- capability flag `mcp_server: false → true` (additive on schema.v1)
- design §10.2 MCP transport 절 추가 (additive subsection)
CLAUDE.md release 규약상 wire schema additive / surface 추가는
minor bump 영역이지만, pre-1.0 (0.x.y) 단계에서는 fb-26~31 group
누적 시까지 0.3.x patch 로 묶고, 큰 jump 시 0.4.0 cut 으로 운용.
fb-30 단독으로 break 없는 additive 라 0.3.1 patch 적정.
후속 fb-26 / 28 / 31 머지 시점에 추가 0.3.x patch 누적, breaking
schema 변경 시 0.4.0 minor.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Wires kebab_mcp::serve_stdio into kebab-cli. `--config <path>` honored
via the established Config::load pattern.
Updated serve_stdio signature to (Config, Option<PathBuf>) so the doctor
tool's path-aware behavior works correctly via KebabAppState.
Smoke test spawns the binary + sends initialize + initialized +
tools/list over stdin, asserts 4 tools returned. Confirms the MCP
server boots end-to-end via the real binary (rmcp 1.6 has no
in-memory test transport, so this is the only end-to-end assertion).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Empty lib + serve_stdio entry that bails until Task 3 wires rmcp. Adds
rmcp 1.6 to workspace dependencies (server + macros + transport-io +
schemars features) + tokio multi-thread/io-util/io-std local extensions.
schemars declared as "1" (resolved to 1.2.1) — matches rmcp 1.6's ^1.0
requirement (verified via crates.io /dependencies; plan literal was 0.9
which would conflict). Path-style refs for kebab-app / kebab-config /
kebab-core follow workspace convention.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
fb-30 의 새 crate `kebab-mcp` 가 동일 classify 모듈 사용 — UI crate 끼리
import 는 facade rule 위반이므로 kebab-app 으로 promotion. fb-27 commit
c91228e 의 코드 그대로 이전 (struct + classify + classify_llm + 7 unit
test). reqwest dev-dep 도 함께 이동.
kebab-cli 는 `kebab_app::ErrorV1` / `kebab_app::classify` 로 import 경로
1줄 변경 + wire.rs 의 `&crate::error_classify::ErrorV1` 1줄 교체. 동작
무영향.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`error_classify::classify` maps anyhow::Error → ErrorV1 wire record by
downcasting to known typed errors (LlmError + ConfigInvalid + NotIndexed
re-exported from kebab_app::error_signal, plus std::io::Error chain).
Generic fallback emits `code: "generic"` with the chain in `details` when
verbose.
wire.rs adds wire_schema (idempotent re-tag, mirrors wire_doctor pattern
since SchemaV1 carries its own schema_version field) and wire_error_v1
(simple tag_object). Tests pin both wrappers + 7 classify code paths.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Wraps every error path in `Config::from_file` (read failure, TOML parse,
validation) so downstream callers can `downcast_ref::<ConfigInvalid>()`
to build the `error.v1` wire record. kebab-app re-exports the type via
its `error_signal` module.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
v0.1.0 release tagged on 2026-05-05 — first official release covering
P0~P4 + P5 + P6~P7 + P9 (UI) 의 도그푸딩 사이클 1회 완성.
이후 도그푸딩 follow-up (p9-fb-21 ~ p9-fb-24) 까지 v0.1.0 에 포함:
- p9-fb-22: TUI input cursor mid-string editing + Ask follow-tail.
- p9-fb-23: incremental ingest (skip unchanged docs).
- p9-fb-24: TUI status/key bar + Library 컬럼 헤더 + PgUp/PgDn.
다음 dev cycle 부터 0.2.0. minor bump rationale (semver pre-1.0):
- Wire schema additive (`IngestReport.unchanged`, `IngestEvent` 의
`Unchanged` variant) — backward-compat 유지 but 신규 surface.
- 신규 CLI flag (`--force-reingest`).
- 신규 SQLite migration V006 (incremental ingest 컬럼).
- TUI surface 변경 (status bar 항상 노출, Library 헤더 row, PgUp/PgDn,
cursor 편집).
- IngestOpts struct 도입 (AskOpts 패턴) — 기존 wrapper 보존하므로
caller breaking 은 없음.
기존 ~723 워크스페이스 테스트 무수정 통과 (CARGO_PKG_VERSION 가 env!
로 동적 — TUI status bar 테스트 자동 추적).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
- `Config.source_dir` 를 `pub(crate)` 로 좁힘. invariant ("from_file
/ load 만이 정당한 setter") 가 외부 mutation 으로 깨지지 않도록.
대신 `pub fn source_dir(&self) -> Option<&Path>` (read-only) +
`pub fn with_source_dir(self, dir) -> Self` (builder) 노출 — 테스트
/ 프로그래마틱 사용은 builder 통과.
- `resolve_workspace_root` 의 `current_dir()` 실패 fallback 에
`tracing::warn!` 추가. chroot / deleted-cwd / permission 문제로
cwd 가 안 잡힐 때 silently `./root` 로 떨어지지 않고 로그가 남음.
`tracing` 을 kebab-config 의 deps 에 추가 (workspace dep).
테스트 27 통과 + 워크스페이스 clippy clean.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
도그푸딩 item 9 — TUI Ask 답변 본문이 raw `**bold**` / `# Title` /
` ```code``` ` 그대로 보여 가독성 떨어지던 문제 해소. pulldown-cmark
파싱 → ratatui Span/Line 변환.
## 핵심 변경
- **`kebab-tui::markdown::render(text, &Theme) -> Vec<Line<'static>>`**
신규. pulldown-cmark = "0.13" (이미 kebab-parse-md 가 사용 중인
버전) 위에 build.
inline:
- `**bold**` / `__bold__` → `Modifier::BOLD`
- `*italic*` / `_italic_` → `Modifier::ITALIC`
- `~~strike~~` → `Modifier::CROSSED_OUT`
- `` `code` `` → `Role::Hint` (DIM 스타일 — 터미널 호환성 위해 bg
color 보다 안전)
- `[text](url)` → `Role::CitationMarker` + `Modifier::UNDERLINED`
block:
- heading H1/H2 → `Role::Heading` (Cyan + BOLD), H3-H6 → `Role::Title`
(White + BOLD)
- bullet list `-`/`*` → `- ` + 깊이별 indent
- ordered list `1.` → 실제 번호 prefix + indent
- fenced code block ``` ``` ``` → ` ` indented + `Role::Hint`
- blockquote `>` → 좌측 `▎` bar (중첩 시 반복) + `Role::Hint`
- table `| col |` → `| col1 | col2 |` 식 줄, `|` separator 색 강조
- horizontal rule `---` → `─` × 40
- **streaming 안전성**: 매 frame 재 parse 가 spec — pulldown
토크나이저가 µs/KB 라 비용 무시. unterminated `**` (사용자가 한창
입력 중인 inline 가 닫히기 전) 은 pulldown 이 Text 로 처리 →
literal `**` 그대로 표시 (글자 누락 X).
- **`ask::push_turn_lines` 통합**: grounded 답변에서만 markdown
렌더 사용. refusal turn (`Role::Warning` override) 와 streaming
turn (`Role::Hint`) 은 raw 로 두어 role color 시그널이 markdown
스타일에 묻히지 않도록. body line 들은 ` ` indent 로 transcript
에서 답변 본문 시각 구분.
- **CLI `kebab ask` 출력은 raw markdown** — 터미널 호환성 + pipe
처리 시 안정성 위해 (ANSI escape 없이 plain text).
## 테스트 (markdown.rs 14 unit)
- empty input → 빈 라인 1 줄 (caller scroll/measure 안전)
- plain text → 단일 라인 + paragraph blank
- bold / italic / strikethrough / inline code → 해당 modifier 검증
- link → UNDERLINED 검증
- heading H1 → BOLD 텍스트 span
- bullet list `-` / numbered list `1./2.` → prefix 검증
- code fence body → 줄별 ` ` indent 보존
- blockquote → `▎` prefix
- 2x2 table → `|`-separated 줄 검증
- unterminated `**` → 글자 누락 없음 (streaming 안전성 회귀 방지)
- composite (heading + para + list + code) → 문서 순서 보존
기존 75 TUI 테스트 + 신규 14 markdown = 89 통과. clippy clean.
## 문서
- README `kebab tui` 행에 markdown 렌더 안내 + CLI 는 raw 명시
- HANDOFF: 2026-05-03 entry
- spec status planned → in_progress
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
`kebab ingest` 가 진행 상황을 사용자에게 보여주는 두 surface 추가:
- **사람 모드 (TTY)**: indicatif `ProgressBar` on stderr — scan 중에는
spinner, ScanCompleted 후 bar 로 전환, 매 asset 마다 message 갱신.
- **사람 모드 (non-TTY, CI/pipe)**: indicatif draw target 을 hidden
으로 두고 stderr 에 한 줄씩 (`ingest: scanning`, `ingest: 1/N path`,
`ingest: complete (...)`).
- **`--json` 모드**: stderr 비우고 stdout 에 line-delimited
`ingest_progress.v1` JSON 을 emit. 마지막 줄은 기존
`ingest_report.v1` 그대로 (외부 wrapper backward-compat).
구현:
- 신규 `crates/kebab-cli/src/progress.rs` — `ProgressMode::{Json,
Human { tty }}`, `ProgressDisplay` (background thread 가 channel
drain + 모드별 render), `now_rfc3339` helper. mode 가 무엇이든 ts
는 wire emit 시점에 stamp.
- `crates/kebab-cli/src/wire.rs` 에 `wire_ingest_progress` 추가.
serde tag (`kind`) 위에 `schema_version` + `ts` 두 필드 더해 spec
§2.4a wire shape 완성.
- `Cmd::Ingest` 핸들러: mpsc channel 만들고 background thread 가
display 돌리는 동안 main 이 `ingest_with_config_progress` 호출.
ingest 반환 시 Sender drop → display thread 정상 종료. join 후
최종 ingest_report 출력.
- 새 dep: `indicatif` 0.17 (TTY 전용 진행 바, non-TTY/--json 에서는
hidden draw target).
Test:
- 3 lib unit (mode resolution + RFC 3339 round-trip).
- 3 integration (--json line-delimited / non-TTY stderr text /
ts+kind 검증). 16 PASS 전체 회귀 0.
Plan 갱신:
- p9-fb-01: status `in_progress` → `completed` (PR #52 머지 후속).
- p9-fb-02: status `planned` → `in_progress`. 머지 후 별도 한 줄
commit 으로 `completed` flip.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two follow-ups after PR #49 (kebab reset) merged:
- Cargo.lock: kebab-cli's new dev-dep `tempfile` was committed in the
feature PR but the lockfile entry was not regenerated, leaving main
with a stale lock. `cargo metadata` regenerates the one-line addition
to kebab-cli's dependency list.
- tasks/p9/p9-fb-06-data-reset-command.md: status `in_progress` →
`completed`, per the plan's task 6 commitment to flip in a separate
one-line commit only after the implementation PR merges.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
새 crate `kebab-tui` 가 §8 facade rule 따라 `kebab-app` 만 import.
Ratatui 0.28 + crossterm 0.28 기반 shell 이 다음을 제공:
- `App` 구조체: config + focus + library + 3 Option sub-state slot
(search/ask/inspect — p9-2/3/4 가 자기 모듈에서 채우는 parallel-safety
contract). p9-1 외에 App 정의 손대지 않음.
- `Pane` enum (Library/Search/Ask/Inspect/Jobs).
- `KeyOutcome` (Continue/Quit/SwitchPane/Refresh).
- `LibraryState` + 내부 inner: docs / list_state / filter / filter_edit /
needs_refresh / loading / pending_g.
- `render_library` (Frame, area, &App) — heading/body, filter overlay
toggleable, Korean/wide-char 너비는 unicode-width 로 계산.
- `handle_key_library`: j/k/Down/Up 이동, gg/G 끝, f 필터 overlay,
/=>Search ?=>Ask Enter=>Inspect, q/Esc 종료. error overlay 가 켜
있으면 어떤 키든 dismiss.
- 필터 overlay: tags_any (CSV) + lang 두 필드, Tab cycle, Enter
apply→Refresh, Esc cancel.
- `ErrorOverlay`: anyhow chain 캡쳐 후 popup 렌더 (Clear + 빨간 border).
- 터미널 lifecycle: `TuiTerminal` 가 enter raw mode + alt screen,
Drop 이 종료 시 (panic 포함) restore — 사용자 쉘 깨지지 않게.
- 비동기 없음: facade 호출은 main thread 동기. v1 의 brief hang 수용.
CLI: `kebab tui` 서브커맨드 추가, --config 받아 App::new + run.
테스트 10건 (`tests/library.rs`, TestBackend 사용):
- 빈 library / 3-doc render / q,Esc quit / / Search 전환 / ? Ask 전환
- Enter 빈 list 무동작 / Enter Inspect 전환 / j 이동 (3-step clamp) /
f 필터 overlay → 입력 → Enter Refresh.
Test seam: `App::populate_library_for_testing` (#[doc(hidden)]) 가
`pub(crate)` inner 를 우회. spec parallel-safety contract 그대로 유지.
Spec deviation (HOTFIXES `2026-05-02 P9-1`):
- `render_library` 의 `<B: Backend>` generic 제거 — ratatui 0.28 의 Frame
이 backend-agnostic.
- `populate_library_for_testing` 추가 (test seam, 공식 API 아님).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
- Cargo.toml: 사용하지 않는 deps 제거 (`kebab-config`, `thiserror`,
`pdf-extract`, dev `tempfile` / `serde_json` / `serde`). 특히
`pdf-extract` 가 끌어오던 transitive ~150 crate (pom, postscript,
type1-encoding-parser, adobe-cmap-parser, euclid, chrono, md5,
linked-hash-map …) 가 모두 사라짐. lopdf 만 남음.
- info.rs: BOM 없는 PDFDocEncoded Title 디코드 버그 수정. `from_utf8_lossy`
는 0x80–0xFF 를 U+FFFD 로 치환해 "Café" 같은 레거시 타이틀을 망가뜨림.
byte → `char` 직접 캐스팅 (Latin-1 디코더) 로 교체. 회귀 테스트
`info_dict_title_pdfdocencoding_latin1_high_bytes_decoded` 추가.
- info.rs: 모듈 doc 의 "Latin-1 superset" 부정확 표현 정정 — PDFDocEncoding
은 0x18–0x1F / 0x80–0x9F 영역에서 Latin-1 과 다름.
- lib.rs: `saturating_sub(1)` 가 page=0 케이스를 silent 흡수하던 부분에
`debug_assert!` 추가. release 는 saturating fallback 유지 (panic 보다
garbled order 가 운영에 유리).
- tests: UTF-16 surrogate pair 커버리지 갭 보완 — 🥙 (U+1F959) 가 포함된
타이틀로 `String::from_utf16_lossy` 의 페어-결합 경로 검증.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`PdfTextExtractor`(MediaType::Pdf) lopdf 기반 per-page 텍스트 추출.
페이지마다 `Block::Paragraph` + `SourceSpan::Page { page, char_start, char_end }`
emit. 본문이 비거나 추출 panic 인 페이지는 빈 paragraph + `Provenance::Warning`
("scanned candidate") 로 표시 — 이후 OCR fallback (별도 task) 의 입력.
핵심 동작:
- `lopdf::Document::load_mem` + `is_encrypted()` → 암호화 PDF 는 명시 에러
(`qpdf --decrypt` 안내).
- 페이지 단위 `extract_text(&[page])` 를 `catch_unwind` 로 감싸 malformed
page panic 을 recoverable warning 으로 변환.
- `/Info` dict 에서 Title/Producer/Creator best-effort 추출. UTF-16BE BOM
prefixed 문자열도 디코드 (한국어 등 non-ASCII Title 정상 처리).
- 9개 통합 테스트: 3-page emit, scanned-mixed warning, encrypted refuse,
corrupt header error, page_count 메타, UTF-16BE Title, filename
fallback, determinism, snapshot.
`parser_version = "pdf-text-v1"`. Allowed deps: `lopdf 0.32` + `pdf-extract 0.7`
(원본 spec 그대로). 본문 다국어 OCR fallback 은 §9.2 후속 task (out of scope).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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.
- 새 모듈 `crates/kebab-parse-image/src/ocr.rs` 추가. spec 의 `OcrEngine`
trait 그대로 + `OllamaVisionOcr` default 구현 + `apply_ocr` 헬퍼.
- `OllamaVisionOcr`: `<endpoint>/api/generate` 비스트리밍 호출,
`images: [base64]` 필드로 이미지 전달, 프롬프트는 언어 힌트
+ 화이트리스트 언어 목록 포함. 응답 prose 를 `OcrText.joined` 로,
prepared image 전체 영역 단일 region (confidence 1.0) 으로 wrap.
기본 모델 `gemma4:e4b`. endpoint 비어 있으면 `models.llm.endpoint`
로 fallback.
- 이미지 전처리: long-edge `config.image.ocr.max_pixels` (기본 1600,
256~4096 클램프) 초과 시 PNG 로 재인코딩 (image::imageops::resize,
Triangle filter). PNG 입력이 max 이내면 zero-copy passthrough.
- `apply_ocr` 는 OCR 성공 시 block.ocr 를 Some 으로 채우고
ProvenanceKind::OcrApplied 이벤트 추가. 실패 시 block.ocr 는
None 그대로 + provenance 미기록 (부분 상태 누출 금지).
- `kebab-config`: 새 `ImageCfg.ocr: OcrCfg` 블록 (enabled/engine/model
/endpoint/languages/max_pixels). `#[serde(default)]` 로 pre-P6
TOML 호환. `KEBAB_IMAGE_OCR_*` 환경변수 5종 추가.
## Spec deviation
원래 P6-2 spec 은 Tesseract 를 default OCR 엔진으로 지정했으나, dev /
CI 호스트에서 `libtesseract-dev` 시스템 패키지 설치를 피하려고
Ollama-vision 으로 default 를 교체. `OcrEngine` trait 추상화는 spec
그대로 보존 — Tesseract / Apple Vision / PaddleOCR 어댑터는 같은
trait 으로 추후 feature-gate 추가 가능. 자세한 내역은
`tasks/HOTFIXES.md` 2026-05-02 항목 참조.
Trust 측면: vision LM 은 hallucinate 가능. `OcrText.engine = "ollama-vision"`
필드로 consumer 가 엔진 별 신뢰 분기 가능.
## 테스트
- 신규 (`tests/ocr.rs`, 8 + 1 ignored):
- 200 happy → OcrText 디코딩 (joined / engine / engine_version /
region count / bbox / confidence)
- 빈 응답 → 빈 regions
- 5xx → Err with status + body 포함
- 200 error envelope → Err
- apply_ocr → block.ocr Some + Provenance OcrApplied 1건
- apply_ocr error → block.ocr None 유지 + events 미기록
- 4000×3000 PNG → max_pixels=1024 까지 다운스케일, aspect ratio 보존
- from_parts max_pixels 클램프
- opt-in `KEBAB_OCR_INTEGRATION=1` 통합 (실제 192.168.0.47 Ollama
`gemma4:e4b` 로 \"Hello World 2026\" 전사 검증 완료)
- 신규 (`src/ocr.rs` unit): truncate, build_prompt 언어/힌트 처리
- `kebab-config` 테스트 +3: defaults, env override, pre-P6 TOML 호환
전체: `cargo test -p kebab-parse-image` 28 pass + 1 ignored,
`cargo test -p kebab-config` 20 pass,
`cargo clippy --workspace --all-targets -- -D warnings` pass.
contract: docs/superpowers/specs/2026-04-27-kebab-final-form-design.md
sections: §3.4 ImageRefBlock.ocr, §3.7a OcrText / OcrRegion, §9.1 OCR
vs caption provenance.
P4 terminal task. Implements the user-facing payoff: retrieve →
score gate → pack → render → generate → cite-validate → persist.
After this commit, `kb ask` actually works against an Ollama
backend; the pipeline grounds the answer in retrieved chunks and
refuses cleanly when the gate trips or the model self-judges.
New crate kb-rag:
- pub struct RagPipeline { retriever, llm, docs, config } — all
Arc<dyn Trait + Send + Sync> so the pipeline shares + Sync.
- pub fn ask(query, opts) -> Result<Answer> drives the nine-stage
flow per spec §1.
- pub struct AskOpts { k, explain, mode, temperature, seed,
stream_sink: Option<mpsc::Sender<String>> }. k acts as a floor
over config.search.default_k so a low-k caller can't starve
retrieval (documented in field doc).
Pipeline stages:
1. Retrieve via the injected dyn Retriever.
2. Score gate: empty hits → NoChunks refusal (no LLM call); top-1 <
config.rag.score_gate → ScoreGate refusal (no LLM call) with
top-3 candidates listed in the synthesized answer text.
3. Pack: budget = config.rag.max_context_tokens.saturating_sub
(prompt overhead). Per-hit `[#n] doc=… heading=… span=…\n<text>`
with deterministic enumeration. If every hit's chunk is
unfetchable from the store (deleted between search and pack),
fall back to NoChunks refusal with a tracing::warn rather than
feeding an empty [근거] to the LLM.
4. Render rag-v1 prompt with the spec's verbatim Korean system
string + `[질문]/[근거]` user template.
5. Generate via dyn LanguageModel. Single-thread token loop owns
the iterator; tokens optionally forward to opts.stream_sink (a
`mpsc::Sender<String>`). SendError silently dropped — caller
cancellation never panics the pipeline. After Done the loop
reads (acc, finish_reason, usage) in lockstep with no race.
max_completion = llm.context_tokens().saturating_sub
(used_for_input).max(64) — explicitly NOT capped by
config.rag.max_context_tokens (that's the packing budget for
[근거], not the LM completion ceiling).
6. Citation extract via STRICT regex `\[#(\d{1,3})\]` (compiled
once via OnceLock). Loose forms `[1]`, `[ #1 ]`, `[#foo]`,
`[#1234]`, `vec![1]` are all rejected to prevent prose
false-positives.
7. Citation validate covers four cases:
- unknown marker (e.g. `[#7]` when only 3 packed) →
LlmSelfJudge refusal.
- empty answer with hits → LlmSelfJudge.
- non-empty + no marker + matches `근거 (가|이) 부족` regex →
LlmSelfJudge (model self-refused with the canonical phrase;
phrase match logged via tracing::debug for observability).
- non-empty + no marker + no refusal phrase → LlmSelfJudge
(silent ungrounded answers are still refusals).
- non-empty + ≥1 valid marker → grounded = true.
8. Build Answer per kb_core::Answer shape:
- citations: filter packed list to exactly the markers cited.
Wire format `marker: Some("[1]")` (square-bracketed bare
index) per design §2.3, distinct from the prompt-side
`[#n]` grammar.
- embedding ModelRef: read from config.models.embedding for
Vector/Hybrid; None for Lexical. Documented deviation since
the Retriever trait doesn't expose the embedder. For
ScoreGate/NoChunks refusals on Vector/Hybrid the embedding
model is still recorded — the vector retriever WAS consulted
even when the gate tripped.
- TraceId minted as `ret_<8-hex>` from blake3(query, top_score,
model_id, ns).
- retrieval AnswerRetrievalSummary populated.
- usage from the final Done chunk; latency_ms wall-clock
fallback when the LLM reports zero.
- created_at OffsetDateTime::now_utc().
9. Persist via SqliteStore::put_answer (new inherent method on
SqliteStore, not on the DocumentStore trait — answers aren't
documents and adding to kb-core was forbidden). Always inserts,
refusals included. packed_chunks_json is null unless
opts.explain == true.
kb-store-sqlite extension:
- pub fn put_answer(&Answer, query, packed_chunks_json) ->
Result<AnswerId>. Maps all 22 fields of the answers table per
V001 schema in a single INSERT under a transaction.
kb-app::ask wired:
- bail!("not yet wired (P4-3)") replaced with a real body that
builds the retriever per opts.mode (Lexical | Vector | Hybrid),
instantiates OllamaLanguageModel from config, constructs
RagPipeline, calls pipeline.ask. AskOpts moves to kb-rag and is
re-exported via `pub use kb_rag::AskOpts` so kb-cli's
`use kb_app::AskOpts` keeps working.
- kb-app/Cargo.toml gains kb-rag, kb-llm, kb-llm-local. P3-5's
forbids on these are lifted by P4-3 spec — kb-app is the
orchestrator and ask requires both the trait crate and the
Ollama adapter.
- kb-cli/main.rs's AskOpts literal updated with stream_sink: None
for the CLI path (TUI in P9 will plumb a real sink).
Tests (kb-rag: 18; kb-app: 1 ignored):
- 3 unit in src/pipeline.rs: marker regex strictness (rejects all
loose forms with byte-equal expectations), Send+Sync compile
check, embedding_ref_for behavior across modes.
- 15 integration in tests/pipeline.rs covering every spec test row
+ the new "all chunks unfetchable falls back to NoChunks" guard:
empty-hits, score-gate, grounded happy path, unknown-marker,
prose-`[1]` rejection, `vec![1]` rejection, refusal-phrase,
packing-budget overflow, streaming-forwards-to-mpsc, dropped-
receiver-no-panic, usage-from-final-Done, answers-row-inserted-
for-each-refusal-kind, determinism temp=0 seed=0, Answer JSON
shape, unfetchable-chunks-fall-back-to-no-chunks (the new
M3 test).
- kb-app/tests/ask_smoke.rs: 1 #[ignore]'d real-Ollama smoke that
drives the wired ask end-to-end against `localhost:11434`.
Workspace: 319 passed / 26 ignored / 0 failed. cargo clippy
--workspace --all-targets -- -D warnings clean.
Allowed deps respected (kb-core, kb-config, kb-search, kb-llm,
kb-store-sqlite, serde, serde_json, regex, time, tracing,
thiserror) plus forced waivers anyhow (Retriever / LanguageModel
trait return types) and blake3 (TraceId minting). Forbidden
(kb-source-fs, kb-parse-md, kb-normalize, kb-chunk, kb-store-
vector direct, kb-embed* direct, kb-llm-local direct, kb-tui,
kb-desktop) all absent from `cargo tree -p kb-rag` — concrete
adapters reach the pipeline only through trait objects.
Out of scope: reranker between retrieve and pack (P+), multi-turn
chat memory (P+), LLM-as-judge eval (P5 uses rule-based
must_contain), --json streaming (buffers per §0 Q5 hybrid).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
First real LanguageModel implementation. Wraps Ollama's local HTTP
API at POST {endpoint}/api/generate with stream:true, parses the
NDJSON streaming response into TokenChunk events, and maps Ollama
error states to a thiserror-derived LlmError with actionable hints.
Synchronous trait surface; reqwest::blocking handles the HTTP I/O.
Public surface:
- pub struct OllamaLanguageModel
- pub fn new(config: &Config) -> Result<Self> — lazy connect; never
hits the network. Spec line 96.
- pub enum LlmError { Unreachable, ModelNotPulled, Timeout, Stream,
Malformed }. Lives in this crate per spec — kb-core / kb-llm stay
free of error taxonomy.
- impl kb_core::LanguageModel via re-export from kb-llm.
Streaming:
- POST body shape per spec §11.2: model, prompt = system + "\n\n" +
user, stream: true, options { temperature, seed, num_ctx, stop }.
- OllamaStream owns BufReader<reqwest::blocking::Response>, reads
NDJSON lines via read_until(b'\n'), parses each as
{response, done, done_reason?, prompt_eval_count?, eval_count?,
total_duration?}. Token frame → TokenChunk::Token; done frame →
TokenChunk::Done { finish_reason, usage }.
- done_reason mapping: "length" → Length, "abort" → Aborted,
"stop" / missing / unknown → Stop (forward-compat with future
Ollama tags).
- Missing prompt_eval_count / eval_count default to 0 + tracing::warn
(do NOT fail). Spec line 135.
- EOF without a done line synthesizes Done { Aborted, zeros } so
downstream pipelines never deadlock waiting for a terminal frame.
- UTF-8: line-delimited framing means each JSON line is a complete
UTF-8 sequence — no cross-HTTP-chunk codepoint splits to worry
about. read_until accumulates whole lines regardless of how the
underlying reqwest body chunks.
Error mapping (LlmError):
- reqwest::Error::is_connect() → Unreachable { endpoint, source }
with hint "ensure `ollama serve` is running and reachable at
<endpoint>".
- reqwest::Error::is_timeout() → Timeout.
- 200 with non-NDJSON first line (e.g., transparent-proxy HTML
error page) → Stream(truncated body) — distinguished from
Malformed by the iterator's has_emitted flag.
- 404 with body containing model_id (case-insensitive) OR English
"model" + "not found" → ModelNotPulled(model_id) with hint
"ollama pull <model_id>". Tightened beyond spec to survive
Ollama localizing the error message (Korean / Japanese / etc.)
while keeping the original English-substring fallback.
- Other 4xx/5xx → Stream(truncated body).
- Mid-stream JSON parse failure (after at least one valid line) →
Malformed(line). Truncate all error bodies to 512 chars
(chars-based, multibyte safe) so an nginx 500 page can't blow up
the diagnostic.
- Trailing slash in endpoint stripped before formatting the URL —
endpoint = "http://x:1234/" produces .../api/generate, not
.../api//generate. Pinned by trailing-slash test.
Tokio note: reqwest 0.12's blocking feature internally wraps a
private current-thread tokio runtime, so cargo tree --edges normal
shows tokio. The auditable invariant is "no top-level tokio dep +
no async surface exposed to callers" — verified: src/ has zero
async/await/tokio::*. default-features = false drops default-tls
(rustls only) but does NOT drop tokio. Documented honestly in
Cargo.toml + lib.rs. Switching to ureq would remove tokio
entirely; deferred since reqwest is the spec's allowed dep.
Tests (24 total: 23 default + 1 ignored):
- 7 unit in src/ollama.rs: prompt-build, options-build, finish-
reason mapping, truncate_body bounds (under_cap / over_cap_marker
/ multibyte_chars_not_bytes), 404+model-id heuristic.
- 3 in tests/construction.rs: ModelRef shape, context_tokens
passthrough, lazy-connect proven via port-1 pointing.
- 13 in tests/streaming.rs: streamed tokens then Done, multibyte
chars within a line round-trip (renamed from "split across
chunks" to honestly reflect what's tested), Unreachable-with-
hint, 4xx→Stream, 404→ModelNotPulled, concat-equals-canned,
done_reason length / abort, missing eval counts default to zero,
missing done_reason defaults to Stop, determinism-by-mock,
trailing-slash endpoint, non-NDJSON 200 body → Stream not
Malformed.
- 1 #[ignore] in tests/integration.rs: real Ollama on
localhost:11434 with the configured model. Opt-in via
cargo test -p kb-llm-local -- --ignored after `ollama serve`
+ `ollama pull`.
Workspace: 288 passed / 25 ignored / 0 failed. cargo clippy
--workspace --all-targets -- -D warnings clean. No native-tls,
no openssl in the dep graph.
Allowed deps respected: kb-core, kb-config, kb-llm, reqwest 0.12
(default-features=false; blocking, json, rustls-tls), serde,
serde_json, tracing, thiserror plus anyhow (forced by trait return
type). wiremock + tokio in [dev-dependencies] only.
Out of scope: llama.cpp / candle adapters (P+), Ollama embed
endpoint (separate adapter inside kb-embed-local if requested),
cancellation / abort tokens (P+), connection-pool tuning.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
