chore: bump version 0.16.1 → 0.17.0

v0.17.0 release cut — PR-A (한국어 trigram FTS tokenizer + lexical
builder + hint surface) + PR-B (C typedef alias unit + parser_version
cascade + orphan purge) + PR-C (code_lang_chunk_breakdown additive
wire field) 셋 머지 후.

Breaking changes:
- V007 migration (chunks_fts unicode61 → trigram) — chunks 원본 /
  embedding / vector 불변, FTS shadow 자동 backfill. 사용자는 다음
  open 시 V007 즉시 적용 (re-ingest 불필요). kebab.sqlite 파일 크기
  ~2-5배 또는 수백 MB 증가.
- 영어 lexical 검색이 substring 매칭으로 동작 변경 (token →
  tokenization/tokenizer 도 hit, recall ↑ / 단어 경계 ↓).
- C parser_version code-c-v1 → code-c-v2 (typedef alias 추출
  cascade). 같은 file 의 옛 doc/chunks/vector 는 same-workspace_path
  orphan purge 가 자동 정리.

Additive (backwards-compat):
- SearchResponse.hint additive field — 한국어 2자 query 등 trigram
  비호환 시 안내.
- schema.v1.stats.code_lang_chunk_breakdown additive field — chunk
  단위 언어별 분포.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Cargo.lock

@@ -4127,7 +4127,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-app"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "base64 0.22.1",
@@ -4172,12 +4172,13 @@ dependencies = [
 
 [[package]]
 name = "kebab-chunk"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "blake3",
  "kebab-core",
  "kebab-normalize",
+ "kebab-parse-code",
  "kebab-parse-md",
  "serde_json",
  "serde_json_canonicalizer",
@@ -4188,7 +4189,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-cli"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "clap",
@@ -4209,7 +4210,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-config"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "dirs 5.0.1",
@@ -4224,7 +4225,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-core"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4238,7 +4239,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-embed"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4252,7 +4253,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-embed-local"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "fastembed",
@@ -4265,7 +4266,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-eval"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "kebab-app",
@@ -4284,7 +4285,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-llm"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "kebab-core",
@@ -4293,7 +4294,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-llm-local"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "kebab-config",
@@ -4310,7 +4311,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-mcp"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "kebab-app",
@@ -4328,7 +4329,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-normalize"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "kebab-core",
@@ -4343,7 +4344,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-code"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "gix",
@@ -4353,6 +4354,8 @@ dependencies = [
  "time",
  "tracing",
  "tree-sitter",
+ "tree-sitter-c",
+ "tree-sitter-cpp",
  "tree-sitter-go",
  "tree-sitter-java",
  "tree-sitter-javascript",
@@ -4364,7 +4367,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-image"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "ab_glyph",
  "anyhow",
@@ -4388,7 +4391,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-md"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "kebab-core",
@@ -4405,7 +4408,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-pdf"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4418,7 +4421,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-types"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "kebab-core",
  "serde",
@@ -4426,7 +4429,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-rag"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4447,7 +4450,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-search"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "globset",
@@ -4466,7 +4469,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-source-fs"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4485,7 +4488,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-store-sqlite"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4506,7 +4509,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-store-vector"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "arrow",
@@ -4530,7 +4533,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-tui"
-version = "0.15.0"
+version = "0.17.0"
 dependencies = [
  "anyhow",
  "crossterm",
@@ -8531,6 +8534,26 @@ dependencies = [
  "tree-sitter-language",
 ]
 
+[[package]]
+name = "tree-sitter-c"
+version = "0.24.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a9b2eb57a55fed6b00812912e730b7a275cf4fe98bfd6a5d76263d4438371728"
+dependencies = [
+ "cc",
+ "tree-sitter-language",
+]
+
+[[package]]
+name = "tree-sitter-cpp"
+version = "0.23.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "df2196ea9d47b4ab4a31b9297eaa5a5d19a0b121dceb9f118f6790ad0ab94743"
+dependencies = [
+ "cc",
+ "tree-sitter-language",
+]
+
 [[package]]
 name = "tree-sitter-go"
 version = "0.25.0"

Cargo.toml

@@ -31,7 +31,7 @@ edition       = "2024"
 rust-version  = "1.85"
 license       = "MIT OR Apache-2.0"
 repository    = "https://github.com/altair823/kebab"
-version       = "0.15.0"
+version       = "0.17.0"
 
 [workspace.dependencies]
 anyhow       = "1"
@@ -99,6 +99,9 @@ tree-sitter-go         = "0.25.0"
 # JVM family grammars for code ingest (kebab-parse-code, p10-1C-JK).
 tree-sitter-java       = "0.23.5"
 tree-sitter-kotlin-ng  = "1.1.0"   # bare tree-sitter-kotlin requires ts <0.23; -ng uses tree-sitter-language 0.1 (ts 0.26 compat)
+# C/C++ family grammars for code ingest (kebab-parse-code, p10-1D).
+tree-sitter-c         = "0.24.2"
+tree-sitter-cpp       = "0.23.4"
 
 # Disk-footprint trim for dev / test builds. Codegen, opt-level, and
 # behavior are unchanged — only DWARF debug info is reduced (line

HANDOFF.md

@@ -4,7 +4,7 @@
 
 ## 한 줄 요약
 
-P0–P5 + P6 + P7 + P9-1/2/3/4 (Library / Search / Ask / Inspect) 머지 완료. `kebab ingest` 가 markdown / image / PDF / 소스코드 (Rust / Python / TS / JS / Go / Java / Kotlin) / Tier 2 리소스 파일 (yaml/k8s / dockerfile / toml / json / xml / groovy / go-mod) + Tier 3 paragraph fallback (shell / 비-k8s YAML / AST 실패 케이스) 처리. `kebab search` / `kebab ask` 가 매체 가로질러 결과 + page / code citation 반환. `kebab tui` 가 4 패널 (Library + Search + Ask + Inspect) 제공. P10-3 (Tier 3 paragraph fallback) 완료 — 다음 후보 = P10-1D (C/C++) 또는 P9-5 (desktop tauri) 또는 보류 중인 P8 (audio).
+P0–P5 + P6 + P7 + P9-1/2/3/4 (Library / Search / Ask / Inspect) + P10 전체 머지 완료 (현재 **v0.16.1**). `kebab ingest` 가 markdown / image / PDF / 소스코드 (Rust / Python / TS / JS / Go / Java / Kotlin / C / C++) / Tier 2 리소스 파일 (yaml/k8s / dockerfile / toml / json / xml / groovy / go-mod) + Tier 3 paragraph fallback (shell / 비-k8s YAML / AST 실패 케이스) 처리. `kebab search` / `kebab ask` 가 매체 가로질러 결과 + page / code citation 반환. `kebab tui` 가 4 패널 (Library + Search + Ask + Inspect) 제공. P10-1D (C + C++) 완료로 Tier 1 chunker family 마무리 + 직후 도그푸딩 round 2 의 k8s multi-resource chunk_id 충돌을 v0.16.1 핫픽스로 해결 — 구조적으로 남은 component 는 P9-5 (desktop tauri) 하나뿐, P8 (audio) 는 사용자 보류.
 
 ## Phase 로드맵
 
@@ -20,7 +20,7 @@ P0–P5 + P6 + P7 + P9-1/2/3/4 (Library / Search / Ask / Inspect) 머지 완료.
 | **P7** | PDF text + page citation | `kebab-parse-pdf` | P5 | ✅ 완료 (3/3 component, page-level chunker + ingest wiring) |
 | **P8** | 음성 transcription + timestamp citation | `kebab-parse-audio` | P5 | ⏸ 보류 (whisper-rs 시스템 dep brainstorm 필요) |
 | **P9** | TUI + desktop app | `kebab-tui`, `kebab-desktop` | P5 | 🟡 진행 (4/5 component — P9-1/2/3/4 완료 [Library / Search / Ask / Inspect], P9-5 desktop 예정 · 도그푸딩 피드백 **20/20 ✅**) |
-| **P10** | code ingest framework | `kebab-parse-code` | P5 | 🟡 진행 중 — 1A-1 ✅ (wire schema + parse-code skeleton + filter flags), 1A-2 ✅ (Rust AST chunker, `code-rust-ast-v1` — v0.7.0), 1B ✅ (Python/TS/JS AST chunkers — v0.8.0 이후), **1C-Go ✅ (Go AST chunker, `code-go-ast-v1` — v0.12.0)**, **1C-JavaKotlin ✅ (Java + Kotlin AST chunkers, `code-java-ast-v1` / `code-kotlin-ast-v1` — v0.13.0)**, **2 ✅ (Tier 2 resource-aware: yaml/k8s + dockerfile + manifest, `k8s-manifest-resource-v1` / `dockerfile-file-v1` / `manifest-file-v1` — v0.14.0)**, **3 ✅ (Tier 3 paragraph fallback: code-text-paragraph-v1 — v0.15.0)** |
+| **P10** | code ingest framework | `kebab-parse-code` | P5 | 🟡 진행 중 — 1A-1 ✅ (wire schema + parse-code skeleton + filter flags), 1A-2 ✅ (Rust AST chunker, `code-rust-ast-v1` — v0.7.0), 1B ✅ (Python/TS/JS AST chunkers — v0.8.0 이후), **1C-Go ✅ (Go AST chunker, `code-go-ast-v1` — v0.12.0)**, **1C-JavaKotlin ✅ (Java + Kotlin AST chunkers, `code-java-ast-v1` / `code-kotlin-ast-v1` — v0.13.0)**, **2 ✅ (Tier 2 resource-aware: yaml/k8s + dockerfile + manifest, `k8s-manifest-resource-v1` / `dockerfile-file-v1` / `manifest-file-v1` — v0.14.0)**, **3 ✅ (Tier 3 paragraph fallback: code-text-paragraph-v1 — v0.15.0)**, **1D ✅ (C + C++ AST chunkers, code-c-ast-v1 + code-cpp-ast-v1 — v0.16.0)** |
 
 P0~P5 직렬. P6~P9 P5 이후 병렬 가능.
 
@@ -32,6 +32,8 @@ P0~P5 직렬. P6~P9 P5 이후 병렬 가능.
 
 머지 후 발견된 모든 deviation / hotfix 의 dated 로그는 [tasks/HOTFIXES.md](tasks/HOTFIXES.md). 본 요약은 \"누군가가 인수받을 때 알아두면 시간을 많이 절약하는\" 항목만:
 
+- **2026-05-24 v0.17.0 한국어 trigram tokenizer 채택 (closure of 2026-05-22 한국어 lexical)** — `chunks_fts` 가 FTS5 `unicode61` → `trigram` 으로 V007 migration (자동 backfill, re-ingest 불필요). `lexical.rs::build_match_string` trigram-aware 재설계 — multi-token 한국어 query (`해시 충돌`) 가 whole-phrase 후보로 hit, 한영 혼합 (`Rust 충돌은`) 도 OR-combined. 2자 이하 query 는 0-hit + CLI/TUI/wire `hint` 안내. 영어 lexical 도 substring 매칭으로 바뀜 (recall ↑ / 단어 경계 ↓). `kebab.sqlite` 크기 ~2-5배 증가 (trigram index). 자세한 내용: `tasks/HOTFIXES.md` (2026-05-24).
+- **2026-05-22 P10 종합 도그푸딩 round 2 (한국어 lexical 검색 한계)** — `kebab search --mode lexical` 의 한국어 query 가 FTS5 `unicode61` 토크나이저에서 거의 0 hit (어절 단위 토큰화 → 부분 매칭 불가). 기본 hybrid 모드는 `multilingual-e5-small` vector 가 carry 해 한국어 검색 정상. **closure**: 위 2026-05-24 v0.17.0 entry.
 - **2026-05-20 P10-1B (Rust 1A symbol path 비일관 + expression-level 함수 미방출)** — (a) Rust `code-rust-ast-v1` 은 file-scope nesting 만 (workspace path prefix 없음), 1B 의 Python/TypeScript/JavaScript 는 workspace 경로 → module path prefix 사용 (비일관 수용, retrofit = chunker_version bump + reindex 필요, 사용자 명시 요청까지 보류); (b) TS/JS 의 `const foo = () => {...}` 같은 expression-level 함수는 `<top-level>` glue 로 처리됨 (declaration-level 단위만 1B 1차 범위). 자세한 내용: `tasks/HOTFIXES.md` (2026-05-20) 두 항목.
 - **2026-05-19 P10-1A-2 (code_rust_ast_v1.rs + SourceType)** — `AST_CHUNK_MAX_LINES` 상수가 `IngestCodeCfg.ast_chunk_max_lines` 를 읽지 않고 모듈 상수 200 고정 (Chunker trait 이 per-medium config 미노출); `SourceType::Code` variant 부재로 code 파일이 `SourceType::Note` 로 분류됨 — 두 항목 모두 `tasks/HOTFIXES.md` (2026-05-19) 에 기록.
 - **2026-05-07 fb-26 (progress.rs)** — `Aborted` unconditional writeln (TTY duplicate) + `Completed` TTY no summary fixed; `KEBAB_PROGRESS=plain` env + quiet suppression added
@@ -81,13 +83,13 @@ P0~P5 직렬. P6~P9 P5 이후 병렬 가능.
 
 ## 다음 task 후보
 
-- **P9-2 TUI search** — `App.search` slot 채움. Library 의 `/` 가 enable 됨.
-- **P9-3 TUI ask** — `App.ask` slot 채움. `?` enable.
-- **P9-4 TUI inspect** — `App.inspect` slot 채움. `Enter` enable.
-- **P9-5 desktop tauri** — 별도 분기. PDF citation rendering UI 가치 큼.
-- **P8 audio brainstorm** — whisper-rs 시스템 dep 받을지 / 외부 transcription endpoint 사용할지 사용자 결정 필요. 사용자 패턴 (책+PDF 위주, audio 의향 없음) 상 후순위.
+구조적으로 미완인 component 는 P9-5 하나뿐. 나머지는 도그푸딩 follow-up (아래 "P10 dogfooding 백로그") 또는 사용자 결정 대기.
 
-P9-2/3/4 는 P9-1 의 parallel-safety contract (sub-state slot 패턴) 덕에 병렬 진행 가능 — 같은 `App` 손대지 않음.
+- **P9-5 desktop tauri** — 마지막 남은 P9 component. `kebab-desktop` crate + Tauri 앱, 별도 분기. PDF citation rendering UI 가치 큼. 사용자 우선순위 (P9 우선 · 책/PDF 위주) 와 부합.
+- **P10 도그푸딩 round 2 follow-up** — 한국어 lexical tokenizer ✅ v0.17.0. 잔여: code_lang_breakdown chunk 단위 집계 (LOW, PR-C) / C typedef-wrapped struct (LOW, PR-B). 상세는 아래 "P10 dogfooding 백로그" 절.
+- **P8 audio brainstorm** — whisper-rs 시스템 dep 받을지 / 외부 transcription endpoint 사용할지 사용자 결정 필요. 사용자 패턴 (책+PDF 위주, audio 의향 없음) 상 보류.
+- **fb-41 multi-hop reasoning** — ⏳ 미구현, XL, eval 인프라 선행 + brainstorm 필요.
+- **Rust symbol path retrofit** — Rust `code-rust-ast-v1` symbol 이 file-scope-only (1B+ 는 module prefix). `code-rust-ast-v2` bump + Rust corpus re-ingest 비용 → 사용자 명시 요청까지 보류. HOTFIXES `2026-05-20`.
 
 ### P9 dogfooding 백로그 (fb-26 ~ fb-42) — release 분할
 
@@ -96,11 +98,19 @@ P9-2/3/4 는 P9-1 의 parallel-safety contract (sub-state slot 패턴) 덕에
 - **0.3.0 — agent foundation** ✅ cut 2026-05-07: fb-26 (log), fb-27 (introspection/error wire), fb-28 (readonly/quiet). ~~fb-29 (daemon)~~ → 🚫 **deferred** — fb-30 stdio MCP 가 동일 가치를 daemon 복잡도 없이 제공.
 - **0.4.0 — agent integration (MCP)** ✅ cut: fb-30 (MCP stdio), fb-31 (single-file/stdin ingest).
 - **0.5.0 — agent surface refinement (additive)** ✅ cut 2026-05-10: fb-32 (stale doc indicator), fb-33 (streaming ask), fb-34 (output budget controls), fb-35 (verbatim fetch), fb-36 (search filter args), fb-37 (trace + stats). 모두 wire schema additive minor.
-- **0.6.0 — RAG quality** 🟡 진행: fb-38 (score semantics) ✅ 머지 (2026-05-10), fb-40 (fact-grounded answer / rag-v2 prompt) ✅ 머지 (2026-05-10), fb-39 (retrieval precision tuning, embedding_version cascade) — 미진행 (eval golden set 선행 필요).
-- **0.7.0 또는 P+**: fb-41 (multi-hop reasoning, XL), fb-42 (bulk multi-query / rerank, Nice).
+- **0.6.0 — RAG quality** ✅ 대부분 머지 (2026-05-10): fb-38 (score semantics) ✅, fb-39 (eval foundation — `precision_at_k_chunk` metric) ✅, fb-39b (embedding upgrade — multilingual-e5-large default) ✅, fb-40 (fact-grounded answer / rag-v2 prompt) ✅. 잔여 = fb-39 의 retrieval precision lever 실제 적용 (eval golden set 확장 선행 필요).
+- **0.7.0 또는 P+**: fb-41 (multi-hop reasoning, XL) — ⏳ 미구현 · brainstorm 필요; fb-42 (bulk multi-query) ✅ 머지 (2026-05-10, bulk only — rerank hint 은 deferred).
 
 각 fb spec frontmatter 의 `target_version` 필드가 source of truth. INDEX.md 의 release subheader 도 동일 grouping.
 
+### P10 dogfooding 백로그 (2026-05-22 round 2)
+
+P10 종합 도그푸딩 round 2 (`/build/cache/dogfood-p10b/`, OSS 8 repo + 한국어 위키 문서 10편) 에서 발견된 follow-up 후보. 자세한 내용 + 우선순위 근거는 `tasks/HOTFIXES.md` (2026-05-22).
+
+- **한국어 lexical tokenizer** — ✅ v0.17.0 (2026-05-24) 머지. V007 trigram migration 자동 backfill + `build_match_string` 재설계 + CLI/TUI/wire hint. HOTFIXES `2026-05-24` 참조.
+- **code_lang_breakdown chunk 단위 집계 (LOW)** — `schema.v1.stats` 의 언어별 분포를 doc 수 → chunk 수로. 소규모, wire additive 필드.
+- **ranking glue chunk 편향 (deferred)** — 자동 heuristic 은 user intent misalignment 위험. 사용자 명시 요청 전까지 surface 변경 0 유지. 1주+ 실사용 후 재 brainstorm.
+
 ## 검증된 운영 동작 (release binary, fastembed enabled)
 
 P7-3 머지 직후 25 시나리오 smoke 통과 — markdown + image + PDF 5 자산 워크스페이스에서 doctor / ingest / list / inspect / search (lex/vec/hybrid) / re-ingest / byte-edit re-ingest / corrupt PDF / RAG ask + page citation 모두. 자세한 시나리오 표는 conversation 기록 참조; 워크스페이스에 직접 돌려보는 절차는 [docs/SMOKE.md](docs/SMOKE.md).

README.md

@@ -70,8 +70,8 @@ kebab doctor
 | 명령 | 동작 |
 |------|------|
 | `kebab init` | XDG 경로에 데이터 디렉토리 + config.toml 생성 |
-| `kebab ingest [<path>]` | Markdown / 이미지 / PDF / Rust 소스코드 색인 (idempotent). TTY 에서는 stderr 진행 바, non-TTY (CI / pipe) 는 stderr 한 줄씩, `--json` 은 stdout 에 `ingest_progress.v1` 라인 streaming 후 마지막에 `ingest_report.v1`. Ctrl-C 한 번이면 현재 asset 마무리 후 abort (부분 commit 보존, idempotent re-run), 두 번째 Ctrl-C 는 hard exit. Markdown title 이 frontmatter 에 없어도 첫 H1 → H2 → 첫 paragraph 80 자 → 파일명 순으로 자동 채움 (parser_version `md-frontmatter-v2`) — 기존 색인된 doc 도 다음 ingest 에서 새 title 로 갱신. **Incremental** (p9-fb-23): 두 번째 이후의 ingest 는 변하지 않은 doc (blake3 + parser/chunker/embedder version 모두 동일) 의 parse/chunk/embed/vector upsert 를 자동 스킵. final summary 에 `N unchanged` 카운트 표시. `--force-reingest` 로 skip 무시 강제 재처리. **지원 형식** (extractor 자동 결정 — config 에 명시 불가): Markdown (`.md`), 이미지 (`.png` / `.jpg` / `.jpeg`, OCR + caption), PDF (`.pdf`), **소스코드** (`.rs` → `code-rust-ast-v1`, `.py` → `code-python-ast-v1`, `.ts`/`.tsx` → `code-ts-ast-v1`, `.js`/`.mjs`/`.cjs`/`.jsx` → `code-js-ast-v1`, `.go` → `code-go-ast-v1`, `.java` → `code-java-ast-v1`, `.kt`/`.kts` → `code-kotlin-ast-v1` — 모두 tree-sitter AST chunker; **Tier 2 리소스 파일**: `.yaml`/`.yml` → `k8s-manifest-resource-v1` (apiVersion+kind 파싱), `Dockerfile`/`Dockerfile.*`/`*.dockerfile` → `dockerfile-file-v1` (전체 파일), `Cargo.toml`/`pyproject.toml`/`.toml`/`package.json`/`tsconfig.json`/`.json`/`pom.xml`/`.xml`/`build.gradle`/`.gradle`/`go.mod` → `manifest-file-v1` (전체 파일) — yaml (k8s) / dockerfile / toml / json / xml / groovy / go-mod 지원); **Tier 3 paragraph fallback** (`.sh`/`.bash`/`.zsh` → `code-text-paragraph-v1`, blank-line paragraph split + 80-line/20-overlap line-window. Tier 1/2 가 0 chunk 또는 Err 시 자동 fallback — 비-k8s YAML 같은 케이스 picked up. symbol = None, lang 은 원본 보존.). 다른 확장자는 자동 skip — `IngestItem.warnings` 에 사유 (`"unsupported media type: .docx"` 등), `IngestReport.skipped_by_extension` 에 카운트 분류, CLI / TUI summary 에 breakdown 표시. 코드 chunk 는 `citation.kind = "code"` 에 `citation.lang = "<lang>"` + `symbol` + line range 를 담고, SearchHit top-level 에 `code_lang` + `repo` (`.git/` walk-up 의 디렉토리 이름) 가 backfill 됨. `--code-lang rust` / `--code-lang python` / `--code-lang typescript` / `--code-lang javascript` / `--code-lang go` / `--code-lang java` / `--code-lang kotlin` / `--code-lang yaml` / `--code-lang dockerfile` / `--code-lang toml` / `--code-lang json` / `--code-lang xml` / `--code-lang groovy` / `--code-lang go-mod` / `--code-lang shell` / `--media code` filter 로 언어별·코드 전용 검색 가능 (p10-1A-1 filter flags). Python symbol 은 workspace 경로 → dotted module path prefix (예: `kebab_eval.metrics.compute_mrr`), TS/JS symbol 은 slash-style module path prefix (예: `src/Foo.Foo.search`), Go symbol 은 `package.Func` / `package.(*Receiver).Method` 형식, Java / Kotlin symbol 은 `com.foo.Foo.bar` 형식 (패키지 + 클래스 + 메서드/필드). |
-| `kebab search --mode {lexical,vector,hybrid} "<query>" [--no-cache] [--max-tokens N] [--snippet-chars N] [--cursor <opaque>] [--tag T] [--lang L] [--path-glob G] [--trust-min LEVEL] [--media TYPE] [--ingested-after RFC3339] [--doc-id ID] [--trace] [--bulk] [--repo NAME ...] [--code-lang LIST]` | 검색. hybrid는 RRF fusion, citation 포함. 같은 process 안에서 동일 query (NFKC + trim + lowercase 정규화) 반복 시 in-process LRU 캐시 hit (capacity = `[search] cache_capacity`, default 256). `--no-cache` 로 강제 bypass — 디버깅용. ingest commit 발생 시 `kv['corpus_revision']` bump 으로 모든 entry 자동 stale. **`--max-tokens` / `--snippet-chars` / `--cursor` (p9-fb-34)** — agent budget controls. `--json` 출력은 `search_response.v1` wrapper (`{hits, next_cursor, truncated}`) — pre-fb-34 의 bare array 와 호환 안 됨. mismatched cursor → `error.v1.code = stale_cursor`. **filter flags (p9-fb-36):** `--tag` 는 반복 가능 flag (`--tag rust --tag async`) 로 OR 매칭, `--media` 는 `,` 구분 다중 값 OR 매칭, 나머지 flags 간은 AND 조합. `--trust-min` 은 `primary\|secondary\|generated` 중 하나 (해당 level 이상 포함). `--ingested-after` 는 RFC3339 UTC — 파싱 실패 시 `error.v1.code = config_invalid` (exit 2). `--media md` 는 `markdown` alias 로 정규화. 알 수 없는 `--media` 값은 무조건 empty hits (오류 아님). **`--trace` (p9-fb-37)** — `search_response.v1.trace` 에 lexical / vector pre-fusion 후보 + RRF union + per-stage timing (`lexical_ms` / `vector_ms` / `fusion_ms` / `total_ms`) 노출. trace 요청은 캐시 우회 (`--no-cache` 없이도 항상 cold). **`--bulk` (p9-fb-42)** — stdin ndjson 으로 N query 한 번에 실행. `--json` 면 stdout per-query ndjson (`bulk_search_item.v1`) + stderr summary (`bulk_summary: total=N succeeded=S failed=F`). Cap 100. agent 가 query decomposition 후 sub-query 일괄 실행 시 single round-trip — App instance 재사용으로 캐시 / embedder cold-start 비용 한 번만. Per-query failure 는 item 의 `error` (error.v1) 에 격리, 다른 query 계속 진행. **code corpus filters (p10-1A-1):** `--repo` 는 반복 가능 (`--repo kebab --repo other`) OR 매칭. `--code-lang` 는 반복 또는 comma 다중 값 (`--code-lang rust,python`), 알 수 없는 값은 빈 hits. `--media code` 는 Tier 1/2/3 모든 code chunk 포함. 1A-1 시점에서는 indexed 된 code chunk 가 없어 filter 가 항상 빈 결과 — 1A-2 (Rust AST chunker) 머지 이후 실효. |
+| `kebab ingest [<path>]` | Markdown / 이미지 / PDF / Rust 소스코드 색인 (idempotent). TTY 에서는 stderr 진행 바, non-TTY (CI / pipe) 는 stderr 한 줄씩, `--json` 은 stdout 에 `ingest_progress.v1` 라인 streaming 후 마지막에 `ingest_report.v1`. Ctrl-C 한 번이면 현재 asset 마무리 후 abort (부분 commit 보존, idempotent re-run), 두 번째 Ctrl-C 는 hard exit. Markdown title 이 frontmatter 에 없어도 첫 H1 → H2 → 첫 paragraph 80 자 → 파일명 순으로 자동 채움 (parser_version `md-frontmatter-v2`) — 기존 색인된 doc 도 다음 ingest 에서 새 title 로 갱신. **Incremental** (p9-fb-23): 두 번째 이후의 ingest 는 변하지 않은 doc (blake3 + parser/chunker/embedder version 모두 동일) 의 parse/chunk/embed/vector upsert 를 자동 스킵. final summary 에 `N unchanged` 카운트 표시. `--force-reingest` 로 skip 무시 강제 재처리. **지원 형식** (extractor 자동 결정 — config 에 명시 불가): Markdown (`.md`), 이미지 (`.png` / `.jpg` / `.jpeg`, OCR + caption), PDF (`.pdf`), **소스코드** (`.rs` → `code-rust-ast-v1`, `.py` → `code-python-ast-v1`, `.ts`/`.tsx` → `code-ts-ast-v1`, `.js`/`.mjs`/`.cjs`/`.jsx` → `code-js-ast-v1`, `.go` → `code-go-ast-v1`, `.java` → `code-java-ast-v1`, `.kt`/`.kts` → `code-kotlin-ast-v1`, `.c`/`.h` → `code-c-ast-v1`, `.cpp`/`.cc`/`.cxx`/`.hpp`/`.hh`/`.hxx` → `code-cpp-ast-v1` — 모두 tree-sitter AST chunker; **Tier 2 리소스 파일**: `.yaml`/`.yml` → `k8s-manifest-resource-v1` (apiVersion+kind 파싱), `Dockerfile`/`Dockerfile.*`/`*.dockerfile` → `dockerfile-file-v1` (전체 파일), `Cargo.toml`/`pyproject.toml`/`.toml`/`package.json`/`tsconfig.json`/`.json`/`pom.xml`/`.xml`/`build.gradle`/`.gradle`/`go.mod` → `manifest-file-v1` (전체 파일) — yaml (k8s) / dockerfile / toml / json / xml / groovy / go-mod 지원); **Tier 3 paragraph fallback** (`.sh`/`.bash`/`.zsh` → `code-text-paragraph-v1`, blank-line paragraph split + 80-line/20-overlap line-window. Tier 1/2 가 0 chunk 또는 Err 시 자동 fallback — 비-k8s YAML 같은 케이스 picked up. symbol = None, lang 은 원본 보존.). 다른 확장자는 자동 skip — `IngestItem.warnings` 에 사유 (`"unsupported media type: .docx"` 등), `IngestReport.skipped_by_extension` 에 카운트 분류, CLI / TUI summary 에 breakdown 표시. 코드 chunk 는 `citation.kind = "code"` 에 `citation.lang = "<lang>"` + `symbol` + line range 를 담고, SearchHit top-level 에 `code_lang` + `repo` (`.git/` walk-up 의 디렉토리 이름) 가 backfill 됨. `--code-lang rust` / `--code-lang python` / `--code-lang typescript` / `--code-lang javascript` / `--code-lang go` / `--code-lang java` / `--code-lang kotlin` / `--code-lang yaml` / `--code-lang dockerfile` / `--code-lang toml` / `--code-lang json` / `--code-lang xml` / `--code-lang groovy` / `--code-lang go-mod` / `--code-lang shell` / `--code-lang c` / `--code-lang cpp` / `--media code` filter 로 언어별·코드 전용 검색 가능 (p10-1A-1 filter flags). Python symbol 은 workspace 경로 → dotted module path prefix (예: `kebab_eval.metrics.compute_mrr`), TS/JS symbol 은 slash-style module path prefix (예: `src/Foo.Foo.search`), Go symbol 은 `package.Func` / `package.(*Receiver).Method` 형식, Java / Kotlin symbol 은 `com.foo.Foo.bar` 형식 (패키지 + 클래스 + 메서드/필드). |
+| `kebab search --mode {lexical,vector,hybrid} "<query>" [--no-cache] [--max-tokens N] [--snippet-chars N] [--cursor <opaque>] [--tag T] [--lang L] [--path-glob G] [--trust-min LEVEL] [--media TYPE] [--ingested-after RFC3339] [--doc-id ID] [--trace] [--bulk] [--repo NAME ...] [--code-lang LIST]` | 검색. hybrid는 RRF fusion, citation 포함. 같은 process 안에서 동일 query (NFKC + trim + lowercase 정규화) 반복 시 in-process LRU 캐시 hit (capacity = `[search] cache_capacity`, default 256). `--no-cache` 로 강제 bypass — 디버깅용. ingest commit 발생 시 `kv['corpus_revision']` bump 으로 모든 entry 자동 stale. **`--max-tokens` / `--snippet-chars` / `--cursor` (p9-fb-34)** — agent budget controls. `--json` 출력은 `search_response.v1` wrapper (`{hits, next_cursor, truncated}`) — pre-fb-34 의 bare array 와 호환 안 됨. mismatched cursor → `error.v1.code = stale_cursor`. **filter flags (p9-fb-36):** `--tag` 는 반복 가능 flag (`--tag rust --tag async`) 로 OR 매칭, `--media` 는 `,` 구분 다중 값 OR 매칭, 나머지 flags 간은 AND 조합. `--trust-min` 은 `primary\|secondary\|generated` 중 하나 (해당 level 이상 포함). `--ingested-after` 는 RFC3339 UTC — 파싱 실패 시 `error.v1.code = config_invalid` (exit 2). `--media md` 는 `markdown` alias 로 정규화. 알 수 없는 `--media` 값은 무조건 empty hits (오류 아님). **`--trace` (p9-fb-37)** — `search_response.v1.trace` 에 lexical / vector pre-fusion 후보 + RRF union + per-stage timing (`lexical_ms` / `vector_ms` / `fusion_ms` / `total_ms`) 노출. trace 요청은 캐시 우회 (`--no-cache` 없이도 항상 cold). **`--bulk` (p9-fb-42)** — stdin ndjson 으로 N query 한 번에 실행. `--json` 면 stdout per-query ndjson (`bulk_search_item.v1`) + stderr summary (`bulk_summary: total=N succeeded=S failed=F`). Cap 100. agent 가 query decomposition 후 sub-query 일괄 실행 시 single round-trip — App instance 재사용으로 캐시 / embedder cold-start 비용 한 번만. Per-query failure 는 item 의 `error` (error.v1) 에 격리, 다른 query 계속 진행. **code corpus filters (p10-1A-1):** `--repo` 는 반복 가능 (`--repo kebab --repo other`) OR 매칭. `--code-lang` 는 반복 또는 comma 다중 값 (`--code-lang rust,python`), 알 수 없는 값은 빈 hits. `--media code` 는 Tier 1/2/3 모든 code chunk 포함. 1A-1 시점에서는 indexed 된 code chunk 가 없어 filter 가 항상 빈 결과 — 1A-2 (Rust AST chunker) 머지 이후 실효. **v0.17.0 trigram tokenizer (한국어 + 영어 동작 변경):** `chunks_fts` 가 FTS5 `trigram` 으로 동작 — 한국어 query 는 3자 이상 substring 매칭 (`해시 충돌` 같은 multi-token 도 whole-phrase 후보로 hit), 영어도 substring 매칭 (`token` 이 `tokenizer` 도 hit, recall ↑ / 단어 경계 ↓). 2자 이하 query 는 0-hit + stderr `[hint] 3자 이상 키워드 권장` + `search_response.v1.hint` 필드 (raw FTS5 mode `'...'` 제외). `kebab.sqlite` 파일 크기는 trigram index 비대화로 ~2-5배 또는 수백 MB 증가 (V007 자동 backfill, re-ingest 불필요). |
 | `kebab list docs` | 색인된 문서 목록 |
 | `kebab inspect doc <id>` / `kebab inspect chunk <id>` | raw record 보기 |
 | `kebab fetch chunk <id> [--context N]` / `kebab fetch doc <id> [--max-tokens N]` / `kebab fetch span <doc_id> <ls> <le> [--max-tokens N]` | (p9-fb-35) verbatim text fetch from indexed corpus. wire = `fetch_result.v1` (kind discriminator). chunk: target + ±N ordinal-context chunks. doc: full normalized markdown. span: 1-based line range (PDF/audio rejected as `error.v1.code = span_not_supported`). chars/4 budget on doc/span. |
@@ -132,7 +132,7 @@ flowchart TB
 
     subgraph Pipeline["도메인 + 파이프라인"]
         parse["parse-md / parse-pdf / parse-image / parse-code"]
-        chunker["chunker (md-heading-v1, pdf-page-v1, code-{rust,python,ts,js,go,java,kotlin}-ast-v1, k8s-manifest-resource-v1, dockerfile-file-v1, manifest-file-v1, code-text-paragraph-v1)"]
+        chunker["chunker (md-heading-v1, pdf-page-v1, code-{rust,python,ts,js,go,java,kotlin,c,cpp}-ast-v1, k8s-manifest-resource-v1, dockerfile-file-v1, manifest-file-v1, code-text-paragraph-v1)"]
         embedder["embedder (fastembed multilingual-e5-large)"]
         retriever["retriever (lexical / vector / hybrid RRF)"]
         rag["RAG pipeline"]

crates/kebab-app/src/app.rs

@@ -73,6 +73,37 @@ pub struct SearchResponse {
     /// p9-fb-37: present when caller passed `SearchOpts.trace = true`.
     /// Consumers that ignore trace should leave this `None`.
     pub trace: Option<kebab_core::SearchTrace>,
+    /// v0.17.0 A5 Step 4b: human / agent-readable advisory string set
+    /// when the empty hit list is likely due to a query shorter than the
+    /// FTS5 trigram tokenizer's 3-char minimum. `None` otherwise. CLI
+    /// surfaces it on stderr (text mode); MCP / `--json` consumers
+    /// surface it however they prefer. See
+    /// `docs/superpowers/specs/2026-05-22-korean-trigram-tokenizer-design.md`
+    /// §3.3.
+    pub hint: Option<String>,
+}
+
+/// v0.17.0 A5 Step 4b: decide whether to attach a "3자 이상 키워드 권장"
+/// hint to a `SearchResponse`. Fires only when the result set is empty
+/// *and* the trimmed query is shorter than the trigram tokenizer can
+/// resolve. Raw FTS5 mode (`'...'`) opts out — the user explicitly
+/// invoked FTS5 syntax. Identical condition powers the CLI stderr line
+/// and (separately) the TUI status bar.
+pub fn short_query_hint(query_text: &str, hits_empty: bool) -> Option<String> {
+    if !hits_empty {
+        return None;
+    }
+    let trimmed = query_text.trim();
+    let bytes = trimmed.as_bytes();
+    // Raw single-quote mode: user opted into FTS5 syntax, no advisory.
+    if bytes.len() >= 2 && bytes[0] == b'\'' && bytes[bytes.len() - 1] == b'\'' {
+        return None;
+    }
+    if trimmed.chars().count() < 3 {
+        Some("3자 이상 키워드 권장 (trigram tokenizer 제약)".to_string())
+    } else {
+        None
+    }
 }
 
 /// Facade state — see module docs for lifetime rules.
@@ -418,11 +449,13 @@ impl App {
 
             // Trace path skips the budget loop. Caller will inspect
             // `hits.len()` and `trace.timing` rather than paginate.
+            let hint = short_query_hint(&query.text, hits.is_empty());
             return Ok(SearchResponse {
                 hits,
                 next_cursor: None,
                 truncated: false,
                 trace: Some(trace),
+                hint,
             });
         }
 
@@ -505,11 +538,13 @@ impl App {
             None
         };
 
+        let hint = short_query_hint(&query.text, hits.is_empty());
         Ok(SearchResponse {
             hits,
             next_cursor,
             truncated,
             trace: None,
+            hint,
         })
     }
 

crates/kebab-app/src/bulk.rs

@@ -96,6 +96,11 @@ fn serialize_search_response(r: &SearchResponse) -> Value {
             None => Value::Null,
         };
         map.insert("trace".to_string(), trace_v);
+        // v0.17.0 A5 Step 4b: only emit `hint` when set — matches
+        // the CLI wire wrapper's additive emit pattern.
+        if let Some(hint) = &r.hint {
+            map.insert("hint".to_string(), Value::String(hint.clone()));
+        }
     }
     v
 }

crates/kebab-app/src/lib.rs

@@ -39,7 +39,7 @@ use std::sync::Arc;
 use anyhow::{Context, anyhow};
 use serde::{Deserialize, Serialize};
 
-use kebab_chunk::{CodeGoAstV1Chunker, CodeJavaAstV1Chunker, CodeJsAstV1Chunker, CodeKotlinAstV1Chunker, CodePythonAstV1Chunker, CodeRustAstV1Chunker, CodeTextParagraphV1Chunker, CodeTsAstV1Chunker, DockerfileFileV1Chunker, K8sManifestResourceV1Chunker, ManifestFileV1Chunker, MdHeadingV1Chunker, PdfPageV1Chunker};
+use kebab_chunk::{CodeCAstV1Chunker, CodeCppAstV1Chunker, CodeGoAstV1Chunker, CodeJavaAstV1Chunker, CodeJsAstV1Chunker, CodeKotlinAstV1Chunker, CodePythonAstV1Chunker, CodeRustAstV1Chunker, CodeTextParagraphV1Chunker, CodeTsAstV1Chunker, DockerfileFileV1Chunker, K8sManifestResourceV1Chunker, ManifestFileV1Chunker, MdHeadingV1Chunker, PdfPageV1Chunker};
 use kebab_core::{
     Answer, Block, CanonicalDocument, Chunk, ChunkId, ChunkPolicy, ChunkerVersion, Chunker,
     DocFilter, DocSummary, DocumentId, DocumentStore, Embedder, EmbeddingInput,
@@ -50,7 +50,7 @@ use kebab_core::{
 use kebab_llm_local::OllamaLanguageModel;
 use kebab_normalize::build_canonical_document;
 use kebab_parse_image::{ImageExtractor, OllamaVisionOcr, apply_caption, apply_ocr};
-use kebab_parse_code::{GoAstExtractor, JavaAstExtractor, JavascriptAstExtractor, KotlinAstExtractor, PythonAstExtractor, RustAstExtractor, TypescriptAstExtractor};
+use kebab_parse_code::{CAstExtractor, CppAstExtractor, GoAstExtractor, JavaAstExtractor, JavascriptAstExtractor, KotlinAstExtractor, PythonAstExtractor, RustAstExtractor, TypescriptAstExtractor};
 use kebab_parse_pdf::PdfTextExtractor;
 use kebab_parse_md::{BodyHints, parse_blocks, parse_frontmatter};
 use kebab_source_fs::FsSourceConnector;
@@ -69,7 +69,7 @@ pub mod reset;
 pub mod schema;
 mod staleness;
 
-pub use app::{App, SearchResponse};
+pub use app::{App, SearchResponse, short_query_hint};
 pub use ingest_progress::{AggregateCounts, IngestEvent, render_skipped_breakdown};
 pub use reset::{ResetReport, ResetScope, enumerate_orphans};
 pub use error_wire::{ERROR_V1_ID, ErrorV1, StructuredError, classify};
@@ -795,6 +795,7 @@ fn try_skip_unchanged(
     current_chunker_version: &ChunkerVersion,
     current_embedding_version: Option<&kebab_core::EmbeddingVersion>,
     force_reingest: bool,
+    fallback_chunker_version: Option<&ChunkerVersion>, // p10-3 fix
 ) -> anyhow::Result<Option<kebab_core::IngestItem>> {
     if force_reingest {
         return Ok(None);
@@ -829,12 +830,72 @@ fn try_skip_unchanged(
     if existing_doc.source_asset_id != asset.asset_id {
         return Ok(None);
     }
+    // p10-3 fix: detect "stored doc was previously Tier 3 fallback".
+    // When a Tier 1/2 extractor emits empty chunks, the fallback wrapper
+    // retries with CodeTextParagraphV1Chunker and stores
+    // last_chunker_version = "code-text-paragraph-v1" + parser_version = "none-v1".
+    // On the next ingest the caller computes current_parser_version /
+    // current_chunker_version from the Tier 1/2 dispatch (e.g.
+    // "k8s-manifest-resource-v1"), which can never match the stored
+    // fallback values, causing spurious re-ingests. Detect this case
+    // and bypass the parser/chunker equality checks — only the embedder
+    // version still must match.
+    let stored_is_tier3_fallback = fallback_chunker_version.is_some_and(|fbv| {
+        existing_doc.last_chunker_version.as_ref() == Some(fbv)
+            && existing_doc.parser_version.0 == "none-v1"
+    });
+
+    if stored_is_tier3_fallback {
+        // Embedder version still must match.
+        let embedder_match = existing_doc.last_embedding_version.as_ref()
+            == current_embedding_version;
+        if !embedder_match {
+            return Ok(None);
+        }
+        let candidate_doc_id = existing_doc.doc_id.clone();
+        tracing::debug!(
+            target: "kebab-app::ingest",
+            path = %asset.workspace_path.0,
+            doc_id = %candidate_doc_id.0,
+            "skip-unchanged: tier 3 fallback state detected; bypassing parser/chunker equality"
+        );
+        return Ok(Some(kebab_core::IngestItem {
+            kind: kebab_core::IngestItemKind::Unchanged,
+            doc_id: Some(candidate_doc_id),
+            doc_path: asset.workspace_path.clone(),
+            asset_id: Some(asset.asset_id.clone()),
+            byte_len: Some(asset.byte_len),
+            block_count: u32::try_from(existing_doc.blocks.len()).ok(),
+            chunk_count: None,
+            parser_version: Some(existing_doc.parser_version.clone()),
+            chunker_version: existing_doc.last_chunker_version.clone(),
+            warnings: Vec::new(),
+            error: None,
+        }));
+    }
+
     // 2. Parser unchanged: parser_version is baked into id_for_doc so
     //    a version bump yields a different doc_id and the row above
     //    would have been missing. Checking here explicitly keeps the
     //    logic self-documenting and guards against future id_for_doc
     //    changes.
     if existing_doc.parser_version != *current_parser_version {
+        // v0.17.0 PR-B: parser_version bump cascade. Same bytes (same
+        // asset_id) → asset-keyed `stale_chunk_ids_at` is a no-op, but
+        // the stale `documents` row at this workspace_path still
+        // collides with `idx_docs_workspace_path` on the next INSERT
+        // and the LanceDB rows under the old chunk_ids orphan. Sweep
+        // both stores here, before returning Ok(None), so the caller's
+        // full-ingest path lands a clean slate. The `keep_doc_id = ""`
+        // sentinel removes every doc at this path (the new doc_id is
+        // not yet known here — it's computed downstream from the new
+        // PARSER_VERSION).
+        purge_workspace_path_for_parser_bump(app, asset).with_context(|| {
+            format!(
+                "parser-bump orphan purge at {}",
+                asset.workspace_path.0
+            )
+        })?;
         return Ok(None);
     }
     // 3. Chunker unchanged.
@@ -948,12 +1009,12 @@ fn ingest_one_asset(
                 force_reingest,
             );
         }
-        // p10-1A-2 / 1B: code ingest dispatch. p10-2: Tier 2 langs added. p10-3: shell added.
+        // p10-1A-2 / 1B: code ingest dispatch. p10-2: Tier 2 langs added. p10-3: shell added. p10-1D: c/cpp added.
         MediaType::Code(lang)
             if matches!(lang.as_str(),
                 "rust" | "python" | "typescript" | "javascript" | "go" | "java" | "kotlin"
                 | "yaml" | "dockerfile" | "toml" | "json" | "xml" | "groovy" | "go-mod"
-                | "shell") =>
+                | "shell" | "c" | "cpp") =>
         {
             return ingest_one_code_asset(
                 app,
@@ -1017,6 +1078,7 @@ fn ingest_one_asset(
         &MdHeadingV1Chunker.chunker_version(),
         embedder.map(|e| e.model_version()).as_ref(),
         force_reingest,
+        None,
     )? {
         return Ok(item);
     }
@@ -1211,6 +1273,7 @@ fn ingest_one_image_asset(
         &MdHeadingV1Chunker.chunker_version(),
         embedder.map(|e| e.model_version()).as_ref(),
         force_reingest,
+        None,
     )? {
         return Ok(item);
     }
@@ -1439,6 +1502,53 @@ fn record_image_analysis_failure(
     warning_notes.push(note);
 }
 
+/// v0.17.0 PR-B: parser-bump cascade. When a code extractor ships a
+/// new `PARSER_VERSION` (e.g. `code-c-v1` → `code-c-v2`), the same
+/// (workspace_path, asset_id) pair re-emerges with a fresh `doc_id`.
+/// The existing asset-keyed [`purge_vector_orphans_for_workspace_path`]
+/// only fires on asset_id changes (file bytes edited) and is a no-op
+/// here. Without an explicit doc-keyed sweep the next INSERT raises
+/// `idx_docs_workspace_path` UNIQUE and the LanceDB rows under the
+/// stale chunk_ids orphan. This helper:
+///
+/// 1. Fetches every stale chunk_id at `workspace_path` from SQLite
+///    (`keep_doc_id = ""` means "all existing docs are stale" —
+///    `try_skip_unchanged` calls this before the new doc_id is
+///    computed).
+/// 2. Deletes the matching vectors from every Lance table (no-op if
+///    embeddings are disabled).
+/// 3. Sweeps the SQLite `documents` row (CASCADE drops `blocks` /
+///    `chunks` / `embedding_records`). The `assets` row stays — same
+///    bytes, same asset_id, only the derived `doc_id` changed.
+fn purge_workspace_path_for_parser_bump(
+    app: &App,
+    asset: &RawAsset,
+) -> anyhow::Result<()> {
+    let path = &asset.workspace_path.0;
+    let stale = app
+        .sqlite
+        .stale_chunk_ids_for_workspace_path_except_doc_id(path, "")
+        .context("SqliteStore::stale_chunk_ids_for_workspace_path_except_doc_id")?;
+    if !stale.is_empty() {
+        if let Some(vec_store) = app.vector().context("App::vector")? {
+            use kebab_core::VectorStore as _;
+            vec_store
+                .delete_by_chunk_ids(&stale)
+                .context("VectorStore::delete_by_chunk_ids (parser-bump orphans)")?;
+        }
+    }
+    app.sqlite
+        .purge_document_at_workspace_path_except_doc_id(path, "")
+        .context("SqliteStore::purge_document_at_workspace_path_except_doc_id")?;
+    tracing::debug!(
+        target: "kebab-app",
+        path = %path,
+        count = stale.len(),
+        "purged orphan vectors + document for parser_version bump"
+    );
+    Ok(())
+}
+
 /// HOTFIXES 2026-05-02 P7-3 follow-up: when a tracked file's bytes
 /// change, `purge_orphan_at_workspace_path` (in `kebab-store-sqlite`)
 /// sweeps the SQLite chain (documents → blocks / chunks / embedding_records)
@@ -1657,6 +1767,7 @@ fn ingest_one_pdf_asset(
         &PdfPageV1Chunker.chunker_version(),
         embedder.map(|e| e.model_version()).as_ref(),
         force_reingest,
+        None,
     )? {
         return Ok(item);
     }
@@ -1838,6 +1949,9 @@ fn ingest_one_code_asset(
             => ParserVersion("none-v1".to_string()),
         // p10-3: shell direct routes to Tier 3 (no parse step).
         "shell" => ParserVersion("none-v1".to_string()),
+        // p10-1D: C + C++ AST extractors.
+        "c"   => ParserVersion(kebab_parse_code::C_PARSER_VERSION.to_string()),
+        "cpp" => ParserVersion(kebab_parse_code::CPP_PARSER_VERSION.to_string()),
         other => anyhow::bail!("unsupported code_lang: {other}"),
     };
 
@@ -1857,9 +1971,24 @@ fn ingest_one_code_asset(
                      => ManifestFileV1Chunker.chunker_version(),
         // p10-3:
         "shell"      => CodeTextParagraphV1Chunker.chunker_version(),
+        // p10-1D: C + C++ AST chunkers.
+        "c"          => CodeCAstV1Chunker.chunker_version(),
+        "cpp"        => CodeCppAstV1Chunker.chunker_version(),
         other => anyhow::bail!("unreachable chunker_version: {other}"),
     };
 
+    // p10-3 fix: if this lang can fall back to Tier 3, compute the fallback
+    // chunker_version so try_skip_unchanged can detect the stored-as-Tier-3
+    // state and skip parser/chunker equality checks.
+    let tier3_fallback_cv: Option<ChunkerVersion> = match code_lang {
+        "rust" | "python" | "typescript" | "javascript"
+        | "go" | "java" | "kotlin"
+        | "yaml" | "dockerfile" | "toml" | "json" | "xml" | "groovy" | "go-mod"
+        | "c" | "cpp" // p10-1D
+            => Some(CodeTextParagraphV1Chunker.chunker_version()),
+        _ => None,
+    };
+
     if let Some(item) = try_skip_unchanged(
         app,
         asset,
@@ -1867,6 +1996,7 @@ fn ingest_one_code_asset(
         &chunker_version,
         embedder.map(|e| e.model_version()).as_ref(),
         force_reingest,
+        tier3_fallback_cv.as_ref(),
     )? {
         return Ok(item);
     }
@@ -1911,6 +2041,13 @@ fn ingest_one_code_asset(
         }
         // p10-3: shell reuses the same synthesizer.
         "shell" => synthesize_tier2_document(asset, &bytes, "shell", &parser_version),
+        // p10-1D: C + C++ AST extractors.
+        "c" => CAstExtractor::new()
+            .extract(&ctx, &bytes)
+            .context("kebab-parse-code::CAstExtractor::extract (code:c)"),
+        "cpp" => CppAstExtractor::new()
+            .extract(&ctx, &bytes)
+            .context("kebab-parse-code::CppAstExtractor::extract (code:cpp)"),
         other => anyhow::bail!("unreachable (extract): {other}"),
     };
 
@@ -1987,6 +2124,13 @@ fn ingest_one_code_asset(
             "shell" => CodeTextParagraphV1Chunker
                 .chunk(&canonical, chunk_policy)
                 .context("kb-chunk::CodeTextParagraphV1Chunker::chunk (code:shell)"),
+            // p10-1D: C + C++ AST chunkers.
+            "c" => CodeCAstV1Chunker
+                .chunk(&canonical, chunk_policy)
+                .context("kebab-chunk::CodeCAstV1Chunker::chunk (code:c)"),
+            "cpp" => CodeCppAstV1Chunker
+                .chunk(&canonical, chunk_policy)
+                .context("kebab-chunk::CodeCppAstV1Chunker::chunk (code:cpp)"),
             other => anyhow::bail!("unreachable (chunk): {other}"),
         }
     };

crates/kebab-app/src/schema.rs

@@ -63,14 +63,26 @@ pub struct Stats {
     /// p9-fb-37: docs whose `updated_at` exceeds the staleness threshold.
     #[serde(default)]
     pub stale_doc_count: u64,
-    /// p10-1A-1: code language breakdown (chunk counts by canonical lowercase
-    /// language identifier). Empty until 1A-2 produces code chunks.
+    /// p10-1A-1: code language breakdown (**doc** counts by canonical
+    /// lowercase language identifier). Empty until 1A-2 produces code
+    /// docs. v0.17.0 PR-C: doc-count semantics corrected here (the
+    /// previous "chunk counts" wording was a longstanding mis-label —
+    /// implementation has always been `COUNT(*) FROM documents
+    /// GROUP BY code_lang`). Use `code_lang_chunk_breakdown` for the
+    /// chunk-level companion.
     #[serde(default)]
     pub code_lang_breakdown: std::collections::BTreeMap<String, u32>,
-    /// p10-1A-1: repo breakdown (chunk counts by `metadata.repo` value).
-    /// Empty until 1A-2 produces code chunks.
+    /// p10-1A-1: repo breakdown (**doc** counts by `metadata.repo`
+    /// value). Empty until 1A-2 produces code docs. v0.17.0 PR-C:
+    /// doc-count wording corrected (mirror of code_lang_breakdown).
     #[serde(default)]
     pub repo_breakdown: std::collections::BTreeMap<String, u32>,
+    /// v0.17.0 PR-C: sister of [`Self::code_lang_breakdown`] returning
+    /// chunk counts instead of doc counts. Indexing-pressure metric —
+    /// one PDF spec → 200 chunks vs one Rust file → 5 chunks shows up
+    /// here in a way `code_lang_breakdown` (doc count) hides.
+    #[serde(default)]
+    pub code_lang_chunk_breakdown: std::collections::BTreeMap<String, u32>,
 }
 
 const KEBAB_VERSION: &str = env!("CARGO_PKG_VERSION");
@@ -171,6 +183,9 @@ fn collect_stats(
         // p10-1A-2 follow-up: dogfooding (2026-05-20) revealed this was a
         // placeholder — mirror of code_lang_breakdown for the repo field.
         repo_breakdown: store.repo_breakdown()?,
+        // v0.17.0 PR-C: chunk-level companion (closes HOTFIXES
+        // 2026-05-22 "code_lang_breakdown chunk granularity" LOW).
+        code_lang_chunk_breakdown: store.code_lang_chunk_breakdown()?,
     })
 }
 
@@ -210,6 +225,11 @@ mod tests_stats_ext {
             v.get("repo_breakdown").is_some(),
             "Stats JSON must include repo_breakdown: {v}"
         );
+        // v0.17.0 PR-C: chunk-level companion field.
+        assert!(
+            v.get("code_lang_chunk_breakdown").is_some(),
+            "Stats JSON must include code_lang_chunk_breakdown (v0.17.0 PR-C): {v}"
+        );
         // Empty BTreeMap serializes as `{}` — confirm it's an object, not null.
         assert!(
             v["code_lang_breakdown"].is_object(),
@@ -219,6 +239,10 @@ mod tests_stats_ext {
             v["repo_breakdown"].is_object(),
             "repo_breakdown must be an object: {v}"
         );
+        assert!(
+            v["code_lang_chunk_breakdown"].is_object(),
+            "code_lang_chunk_breakdown must be an object: {v}"
+        );
     }
 
     #[test]

crates/kebab-app/tests/code_ingest_smoke.rs

@@ -1064,3 +1064,328 @@ fn rust_file_re_ingest_is_unchanged() {
     );
     assert_eq!(item2.doc_id, item1.doc_id);
 }
+
+/// p10-3 fix regression: a docker-compose YAML that falls back to Tier 3
+/// (k8s chunker returns empty, CodeTextParagraphV1Chunker retries) must
+/// report Unchanged on the second ingest rather than re-processing.
+/// Before the fix, try_skip_unchanged returned None because the stored
+/// last_chunker_version ("code-text-paragraph-v1" / parser_version
+/// "none-v1") never matched the caller's dispatch values.
+#[test]
+fn tier3_yaml_fallback_reingest_is_unchanged() {
+    let env = TestEnv::lexical_only();
+
+    std::fs::write(
+        env.workspace_root.join("docker-compose.yml"),
+        "version: '3'\nservices:\n  api:\n    image: nginx:latest\n",
+    )
+    .unwrap();
+
+    let report1 =
+        kebab_app::ingest_with_config(env.config.clone(), env.scope(), false)
+            .expect("first ingest");
+    let item1 = report1
+        .items
+        .as_ref()
+        .expect("items present")
+        .iter()
+        .find(|i| i.doc_path.0.ends_with("docker-compose.yml"))
+        .expect("docker-compose.yml in first report");
+    assert!(
+        matches!(item1.kind, IngestItemKind::New),
+        "first ingest must be New, got {:?}", item1.kind
+    );
+    assert_eq!(
+        item1.chunker_version.as_ref().map(|c| c.0.as_str()),
+        Some("code-text-paragraph-v1"),
+        "first ingest must use Tier 3 fallback chunker"
+    );
+
+    let report2 =
+        kebab_app::ingest_with_config(env.config.clone(), env.scope(), false)
+            .expect("second ingest");
+    let item2 = report2
+        .items
+        .as_ref()
+        .expect("items present")
+        .iter()
+        .find(|i| i.doc_path.0.ends_with("docker-compose.yml"))
+        .expect("docker-compose.yml in second report");
+    assert!(
+        matches!(item2.kind, IngestItemKind::Unchanged),
+        "second ingest must be Unchanged, got {:?}", item2.kind
+    );
+}
+
+/// p10-1d Task G: a `.c` file with a single top-level function is ingested
+/// and the resulting `Citation::Code` hit must carry `lang="c"`,
+/// `symbol="parse_record"` (function name only — no nesting in C), and
+/// `chunker_version = "code-c-ast-v1"`.
+#[test]
+fn tier1_c_ingest_searchable() {
+    let env = TestEnv::lexical_only();
+
+    std::fs::write(
+        env.workspace_root.join("parser.c"),
+        "#include <stdio.h>\n\nint parse_record(const char *line) {\n    if (line == NULL) return -1;\n    return 0;\n}\n",
+    )
+    .unwrap();
+
+    let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), false)
+        .expect("ingest must succeed");
+    assert_eq!(report.errors, 0, "no ingest errors: {report:?}");
+    assert!(report.new >= 1, "c file ingested: {report:?}");
+
+    let c_item = report
+        .items
+        .as_ref()
+        .expect("items present")
+        .iter()
+        .find(|i| i.doc_path.0.ends_with("parser.c"))
+        .expect("parser.c item present");
+    assert_eq!(
+        c_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        Some("code-c-v2"),
+        "parser_version must be code-c-v2 (v0.17.0 PR-B: typedef-wrapped struct/enum/union 이 typedef alias unit 으로 방출)"
+    );
+    assert_eq!(
+        c_item.chunker_version.as_ref().map(|c| c.0.as_str()),
+        Some("code-c-ast-v1"),
+        "chunker_version must be code-c-ast-v1"
+    );
+
+    let query = kebab_core::SearchQuery {
+        text: "parse_record".to_string(),
+        mode: kebab_core::SearchMode::Lexical,
+        k: 10,
+        filters: kebab_core::SearchFilters {
+            code_lang: vec!["c".to_string()],
+            ..Default::default()
+        },
+    };
+    let hits = kebab_app::search_with_config(env.config.clone(), query)
+        .expect("search must succeed");
+
+    let h = hits
+        .iter()
+        .find(|h| matches!(&h.citation, Citation::Code { .. }))
+        .expect("at least one Citation::Code hit for 'parse_record'");
+
+    match &h.citation {
+        Citation::Code {
+            lang,
+            symbol,
+            line_start,
+            ..
+        } => {
+            assert_eq!(lang.as_deref(), Some("c"), "citation.lang must be 'c'");
+            assert_eq!(
+                symbol.as_deref(),
+                Some("parse_record"),
+                "C symbol must be function name only (no nesting)"
+            );
+            assert!(*line_start >= 1, "line_start must be >=1");
+        }
+        _ => unreachable!(),
+    }
+
+    assert_eq!(
+        h.code_lang.as_deref(),
+        Some("c"),
+        "SearchHit.code_lang must be 'c'"
+    );
+    assert_eq!(
+        h.chunker_version.0.as_str(),
+        "code-c-ast-v1",
+        "C chunks must be stamped with code-c-ast-v1"
+    );
+}
+
+/// p10-1d Task G: a `.cpp` file with nested namespace + class is ingested
+/// and the resulting `Citation::Code` hit must carry `lang="cpp"`, a
+/// `symbol` that starts with `"kebab::chunk::Foo"` (namespace::Class or
+/// namespace::Class::method), and `chunker_version = "code-cpp-ast-v1"`.
+#[test]
+fn tier1_cpp_ingest_searchable() {
+    let env = TestEnv::lexical_only();
+
+    std::fs::write(
+        env.workspace_root.join("chunker.cpp"),
+        "namespace kebab {\nnamespace chunk {\nclass Foo {\npublic:\n    void bar() { /* impl */ }\n};\n}\n}\n",
+    )
+    .unwrap();
+
+    let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), false)
+        .expect("ingest must succeed");
+    assert_eq!(report.errors, 0, "no ingest errors: {report:?}");
+    assert!(report.new >= 1, "cpp file ingested: {report:?}");
+
+    let cpp_item = report
+        .items
+        .as_ref()
+        .expect("items present")
+        .iter()
+        .find(|i| i.doc_path.0.ends_with("chunker.cpp"))
+        .expect("chunker.cpp item present");
+    assert_eq!(
+        cpp_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        Some("code-cpp-v1"),
+        "parser_version must be code-cpp-v1"
+    );
+    assert_eq!(
+        cpp_item.chunker_version.as_ref().map(|c| c.0.as_str()),
+        Some("code-cpp-ast-v1"),
+        "chunker_version must be code-cpp-ast-v1"
+    );
+
+    let query = kebab_core::SearchQuery {
+        text: "bar".to_string(),
+        mode: kebab_core::SearchMode::Lexical,
+        k: 10,
+        filters: kebab_core::SearchFilters {
+            code_lang: vec!["cpp".to_string()],
+            ..Default::default()
+        },
+    };
+    let hits = kebab_app::search_with_config(env.config.clone(), query)
+        .expect("search must succeed");
+
+    let h = hits
+        .iter()
+        .find(|h| matches!(&h.citation, Citation::Code { .. }))
+        .expect("at least one Citation::Code hit for 'bar'");
+
+    match &h.citation {
+        Citation::Code {
+            lang,
+            symbol,
+            line_start,
+            ..
+        } => {
+            assert_eq!(lang.as_deref(), Some("cpp"), "citation.lang must be 'cpp'");
+            // Symbol could be "kebab::chunk::Foo" (class) or "kebab::chunk::Foo::bar"
+            // (method) depending on which chunk ranks first.
+            assert!(
+                symbol.as_deref().is_some_and(|s| s.starts_with("kebab::chunk::Foo")),
+                "C++ symbol must start with namespace::Class prefix, got {:?}", symbol
+            );
+            assert!(*line_start >= 1, "line_start must be >=1");
+        }
+        _ => unreachable!(),
+    }
+
+    assert_eq!(
+        h.code_lang.as_deref(),
+        Some("cpp"),
+        "SearchHit.code_lang must be 'cpp'"
+    );
+    assert_eq!(
+        h.chunker_version.0.as_str(),
+        "code-cpp-ast-v1",
+        "C++ chunks must be stamped with code-cpp-ast-v1"
+    );
+}
+
+/// P10 dogfood regression: a k8s YAML with 2 documents (Deployment + Service
+/// separated by `---`) must ingest without a UNIQUE constraint violation.
+/// Before the fix, push_chunks_with_oversize emitted split_key=None for each
+/// resource, giving every resource chunk the same id_hash → identical chunk_id
+/// → SQLite UNIQUE constraint failure on the second resource.
+#[test]
+fn tier2_k8s_multi_resource_yaml_ingests_without_collision() {
+    let env = TestEnv::lexical_only();
+
+    let k8s_dir = env.workspace_root.join("k8s");
+    std::fs::create_dir_all(&k8s_dir).unwrap();
+    std::fs::write(
+        k8s_dir.join("k8s-multi.yaml"),
+        "apiVersion: apps/v1\nkind: Deployment\nmetadata:\n  name: api\n  namespace: prod\nspec:\n  replicas: 2\n---\napiVersion: v1\nkind: Service\nmetadata:\n  name: api\n  namespace: prod\nspec:\n  selector:\n    app: api\n",
+    )
+    .unwrap();
+
+    let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), false)
+        .expect("ingest must succeed");
+
+    // The bug: this would land in report with an error + UNIQUE constraint message.
+    let item = report
+        .items
+        .as_ref()
+        .expect("items present")
+        .iter()
+        .find(|i| i.doc_path.0.ends_with("k8s-multi.yaml"))
+        .expect("k8s-multi.yaml in report");
+    assert!(
+        item.error.is_none(),
+        "multi-resource k8s yaml must ingest without error, got: {:?}",
+        item.error
+    );
+    assert!(
+        matches!(item.kind, IngestItemKind::New),
+        "expected New, got {:?}",
+        item.kind
+    );
+
+    // Both resources must be searchable (≥2 hits: Deployment/prod/api + Service/prod/api).
+    let query = kebab_core::SearchQuery {
+        text: "api".to_string(),
+        mode: kebab_core::SearchMode::Lexical,
+        k: 10,
+        filters: kebab_core::SearchFilters {
+            code_lang: vec!["yaml".to_string()],
+            ..Default::default()
+        },
+    };
+    let hits = kebab_app::search_with_config(env.config.clone(), query)
+        .expect("search must succeed");
+    assert!(
+        hits.len() >= 2,
+        "expected ≥2 hits (Deployment + Service), got {}",
+        hits.len()
+    );
+}
+
+/// p10-3 fix regression: a shell file (direct Tier 3, not a fallback)
+/// must also report Unchanged on re-ingest. Shell goes straight to
+/// CodeTextParagraphV1Chunker so `stored_is_tier3_fallback` is false
+/// (parser_version is "none-v1" and chunker matches the current dispatch),
+/// but the normal equality path should pass regardless.
+#[test]
+fn tier3_shell_reingest_is_unchanged() {
+    let env = TestEnv::lexical_only();
+
+    std::fs::write(
+        env.workspace_root.join("deploy.sh"),
+        "#!/usr/bin/env bash\nset -e\necho hello\n",
+    )
+    .unwrap();
+
+    let report1 =
+        kebab_app::ingest_with_config(env.config.clone(), env.scope(), false)
+            .expect("first ingest");
+    let item1 = report1
+        .items
+        .as_ref()
+        .expect("items present")
+        .iter()
+        .find(|i| i.doc_path.0.ends_with("deploy.sh"))
+        .expect("deploy.sh in first report");
+    assert!(
+        matches!(item1.kind, IngestItemKind::New),
+        "first ingest must be New, got {:?}", item1.kind
+    );
+
+    let report2 =
+        kebab_app::ingest_with_config(env.config.clone(), env.scope(), false)
+            .expect("second ingest");
+    let item2 = report2
+        .items
+        .as_ref()
+        .expect("items present")
+        .iter()
+        .find(|i| i.doc_path.0.ends_with("deploy.sh"))
+        .expect("deploy.sh in second report");
+    assert!(
+        matches!(item2.kind, IngestItemKind::Unchanged),
+        "shell reingest must be Unchanged, got {:?}", item2.kind
+    );
+}

crates/kebab-app/tests/fetch_integration.rs

@@ -38,12 +38,16 @@ fn fetch_chunk_returns_target_only_when_no_context() {
 #[test]
 fn fetch_chunk_with_context_returns_neighbors() {
     let env = common::TestEnv::new();
-    let body = "# H1\n\nA1\n\n# H2\n\nA2\n\n# H3\n\nA3\n\n# H4\n\nA4\n\n# H5\n\nA5\n";
+    // v0.17.0 trigram tokenizer: terms must be ≥3 Unicode chars to
+    // match. The earlier fixture used 2-char tokens like `A1`/`A3` for
+    // section bodies — those zero-hit under trigram. Use 5-char unique
+    // words per section so the query can pin one chunk deterministically.
+    let body = "# H1\n\napples\n\n# H2\n\nbanana\n\n# H3\n\ncherry\n\n# H4\n\ndurian\n\n# H5\n\nelder\n";
     common::ingest_md(&env, "multi.md", body);
     let app = env.app();
 
     let q = kebab_core::SearchQuery {
-        text: "A3".to_string(),
+        text: "cherry".to_string(),
         mode: kebab_core::SearchMode::Lexical,
         k: 1,
         filters: kebab_core::SearchFilters::default(),

crates/kebab-app/tests/search_korean.rs

@@ -46,3 +46,88 @@ fn korean_lexical_query_returns_korean_document() {
         hits.iter().map(|h| &h.doc_path.0).collect::<Vec<_>>()
     );
 }
+
+/// A4 Step 1c — multi-token Korean query (`해시 충돌`) must hit when
+/// the lexical builder routes it through a whole-phrase MATCH candidate.
+///
+/// Expected: FAIL until A5 (`build_match_string` redesign) lands — the
+/// current builder emits `"해시" "충돌"` AND, but FTS5 trigram tokenizer
+/// has no 2-char terms so each side is 0-hit. A5 introduces a whole-
+/// phrase candidate (`"해시 충돌"`) OR'd with the token AND, restoring
+/// hits for the dominant Korean usage pattern.
+#[test]
+fn lexical_multi_token_korean_query_hits() {
+    let env = TestEnv::lexical_only();
+
+    // Copy the synthetic Korean fixture (introduced in A4 Step 0) into
+    // the test workspace. The fixture contains the exact phrase
+    // "해시 충돌" multiple times.
+    let dest = env.workspace_root.join("hash-table.md");
+    let src = std::path::PathBuf::from(env!("CARGO_MANIFEST_DIR"))
+        .join("..")
+        .join("..")
+        .join("fixtures")
+        .join("search")
+        .join("korean")
+        .join("hash-table.md");
+    std::fs::copy(&src, &dest).expect("copy korean fixture");
+
+    kebab_app::ingest_with_config(env.config.clone(), env.scope(), true)
+        .expect("ingest must succeed");
+
+    let hits = kebab_app::search_with_config(
+        env.config.clone(),
+        common::lexical_query("해시 충돌"),
+    )
+    .expect("search must succeed");
+
+    assert!(
+        !hits.is_empty(),
+        "multi-token Korean query '해시 충돌' must hit the hash-table fixture; got {:?}",
+        hits.iter().map(|h| &h.doc_path.0).collect::<Vec<_>>()
+    );
+    let any_hash_table = hits.iter().any(|h| h.doc_path.0.contains("hash-table"));
+    assert!(
+        any_hash_table,
+        "expected at least one hit on the hash-table fixture, got: {:?}",
+        hits.iter().map(|h| &h.doc_path.0).collect::<Vec<_>>()
+    );
+}
+
+/// A4 Step 1c — mixed Korean+English multi-token query (`Rust 충돌은`).
+/// Both tokens are ≥3 chars, so the redesigned builder (A5) emits
+/// `("Rust 충돌은") OR ("Rust" AND "충돌은")`. With trigram tokenizer
+/// each side has substring coverage in the document, so the AND branch
+/// alone is enough. Expected: FAIL pre-A5, PASS post-A5.
+#[test]
+fn lexical_mixed_korean_english_multi_token_query_hits() {
+    let env = TestEnv::lexical_only();
+    let doc_path = env.workspace_root.join("rust-hash.md");
+    std::fs::write(
+        &doc_path,
+        "# Rust 해시 테이블\n\nRust 의 std::collections::HashMap 에서 \
+         해시 충돌은 SipHash 로 완화한다.\n",
+    )
+    .expect("write rust-hash fixture");
+
+    kebab_app::ingest_with_config(env.config.clone(), env.scope(), true)
+        .expect("ingest must succeed");
+
+    let hits = kebab_app::search_with_config(
+        env.config.clone(),
+        common::lexical_query("Rust 충돌은"),
+    )
+    .expect("search must succeed");
+
+    assert!(
+        !hits.is_empty(),
+        "mixed Korean+English multi-token query 'Rust 충돌은' must hit the rust-hash fixture; got {:?}",
+        hits.iter().map(|h| &h.doc_path.0).collect::<Vec<_>>()
+    );
+    let any_rust_hash = hits.iter().any(|h| h.doc_path.0.contains("rust-hash"));
+    assert!(
+        any_rust_hash,
+        "expected at least one hit on the rust-hash fixture, got: {:?}",
+        hits.iter().map(|h| &h.doc_path.0).collect::<Vec<_>>()
+    );
+}

crates/kebab-chunk/Cargo.toml

@@ -16,12 +16,13 @@ tracing                    = { workspace = true }
 serde_yaml                 = { workspace = true }
 
 [dev-dependencies]
-# kb-parse-md / kb-normalize are dev-only — used by the snapshot integration
-# test to build a CanonicalDocument from a fixture Markdown file. Forbidden as
-# regular deps per design §8 (chunker consumes CanonicalDocument from kb-core
-# only); `cargo tree -p kb-chunk --depth 1` (default scope, excludes dev-deps)
-# confirms this.
-kebab-parse-md = { path = "../kebab-parse-md" }
-kebab-normalize = { path = "../kebab-normalize" }
-serde_json      = { workspace = true }
-time            = { workspace = true }
+# kb-parse-md / kb-normalize / kb-parse-code are dev-only — used by the
+# snapshot integration tests to build a CanonicalDocument from fixture files.
+# Forbidden as regular deps per design §8 (chunker consumes CanonicalDocument
+# from kb-core only); `cargo tree -p kb-chunk --depth 1` (default scope,
+# excludes dev-deps) confirms this.
+kebab-parse-md   = { path = "../kebab-parse-md" }
+kebab-parse-code = { path = "../kebab-parse-code" }
+kebab-normalize  = { path = "../kebab-normalize" }
+serde_json       = { workspace = true }
+time             = { workspace = true }

crates/kebab-chunk/src/code_c_ast_v1.rs

@@ -0,0 +1,322 @@
+//! `code-c-ast-v1` — maps a tree-sitter-derived C AST
+//! `CanonicalDocument` (one `Block::Code` per semantic unit, each with
+//! `SourceSpan::Code`) to chunks 1:1. A unit longer than
+//! `AST_CHUNK_MAX_LINES` is split into `<symbol> [part i/N]` sub-chunks
+//! at blank-line paragraph boundaries (design §9.1 oversize fallback).
+//!
+//! tree-sitter is intentionally NOT a dependency here: AST work is
+//! parser-side (`kebab-parse-code`, design §6.3). This chunker only
+//! consumes the `CanonicalDocument`.
+//!
+//! `AST_CHUNK_MAX_LINES` is a constant matching
+//! `IngestCodeCfg::default().ast_chunk_max_lines` (200). Per-medium
+//! config threading needs a chunker registry (P+); same deviation
+//! pattern as `pdf-page-v1`'s pinned `chunker_version`
+//! (`tasks/HOTFIXES.md`).
+
+use kebab_core::{
+    Block, BlockId, CanonicalDocument, Chunk, ChunkPolicy, Chunker, ChunkerVersion, DocumentId,
+    SourceSpan, id_for_chunk,
+};
+
+const VERSION_LABEL: &str = "code-c-ast-v1";
+const BYTES_PER_TOKEN: usize = 3;
+const POLICY_HASH_HEX_LEN: usize = 16;
+const AST_CHUNK_MAX_LINES: u32 = 200;
+
+#[derive(Clone, Copy, Debug, Default)]
+pub struct CodeCAstV1Chunker;
+
+impl Chunker for CodeCAstV1Chunker {
+    fn chunker_version(&self) -> ChunkerVersion {
+        ChunkerVersion(VERSION_LABEL.to_string())
+    }
+
+    fn policy_hash(&self, policy: &ChunkPolicy) -> String {
+        let bytes = serde_json_canonicalizer::to_vec(policy)
+            .expect("canonical JSON serialization of ChunkPolicy must not fail");
+        let hex = blake3::hash(&bytes).to_hex().to_string();
+        hex[..POLICY_HASH_HEX_LEN].to_string()
+    }
+
+    fn chunk(
+        &self,
+        doc: &CanonicalDocument,
+        policy: &ChunkPolicy,
+    ) -> anyhow::Result<Vec<Chunk>> {
+        for b in &doc.blocks {
+            let c = match b {
+                Block::Code(c) => c,
+                _ => anyhow::bail!(
+                    "CodeCAstV1Chunker only handles code docs (got non-Code block)"
+                ),
+            };
+            if !matches!(c.common.source_span, SourceSpan::Code { .. }) {
+                anyhow::bail!(
+                    "CodeCAstV1Chunker only handles code docs (got non-Code source_span)"
+                );
+            }
+        }
+
+        let base_policy_hash = self.policy_hash(policy);
+        let chunker_version = self.chunker_version();
+        let mut out: Vec<Chunk> = Vec::new();
+
+        for b in &doc.blocks {
+            let cb = match b {
+                Block::Code(c) => c,
+                _ => unreachable!("validated above"),
+            };
+            let (ls, le, symbol, lang) = match &cb.common.source_span {
+                SourceSpan::Code { line_start, line_end, symbol, lang } => {
+                    (*line_start, *line_end, symbol.clone(), lang.clone())
+                }
+                _ => unreachable!("validated above"),
+            };
+            let block_ids: Vec<BlockId> = vec![cb.common.block_id.clone()];
+            let span_lines = le.saturating_sub(ls) + 1;
+
+            if span_lines <= AST_CHUNK_MAX_LINES {
+                let span = SourceSpan::Code {
+                    line_start: ls,
+                    line_end: le,
+                    symbol: symbol.clone(),
+                    lang: lang.clone(),
+                };
+                out.push(make_chunk(
+                    doc, &chunker_version, &block_ids, &base_policy_hash,
+                    None, span, cb.code.clone(),
+                ));
+            } else {
+                let parts = split_oversize(&cb.code);
+                let n = parts.len();
+                for (i, (off_start, off_end, text)) in parts.into_iter().enumerate() {
+                    let part_ls = ls + off_start;
+                    let part_le = ls + off_end;
+                    let part_sym = symbol
+                        .as_ref()
+                        .map(|s| format!("{s} [part {}/{n}]", i + 1));
+                    let span = SourceSpan::Code {
+                        line_start: part_ls,
+                        line_end: part_le,
+                        symbol: part_sym,
+                        lang: lang.clone(),
+                    };
+                    out.push(make_chunk(
+                        doc, &chunker_version, &block_ids, &base_policy_hash,
+                        Some(part_ls), span, text,
+                    ));
+                }
+            }
+        }
+
+        tracing::debug!(
+            target: "kebab-chunk",
+            doc_id = %doc.doc_id,
+            chunks = out.len(),
+            "code-c-ast-v1 chunked",
+        );
+        Ok(out)
+    }
+}
+
+#[allow(clippy::too_many_arguments)]
+fn make_chunk(
+    doc: &CanonicalDocument,
+    chunker_version: &ChunkerVersion,
+    block_ids: &[BlockId],
+    base_policy_hash: &str,
+    split_key: Option<u32>,
+    span: SourceSpan,
+    text: String,
+) -> Chunk {
+    let id_hash = match split_key {
+        Some(k) => format!("{base_policy_hash}#L{k}"),
+        None => base_policy_hash.to_string(),
+    };
+    let chunk_id = id_for_chunk(&doc.doc_id, chunker_version, block_ids, &id_hash);
+    let token_estimate = text.len().div_ceil(BYTES_PER_TOKEN);
+    Chunk {
+        chunk_id,
+        doc_id: DocumentId(doc.doc_id.0.clone()),
+        block_ids: block_ids.to_vec(),
+        text,
+        heading_path: Vec::new(),
+        source_spans: vec![span],
+        token_estimate,
+        chunker_version: chunker_version.clone(),
+        policy_hash: base_policy_hash.to_string(),
+    }
+}
+
+/// Split an oversize unit at blank-line paragraph boundaries, greedily
+/// gluing paragraphs until ~`AST_CHUNK_MAX_LINES` lines accumulate.
+/// Returns `(line_offset_start, line_offset_end, text)` where offsets are
+/// 0-based within the unit (caller adds the unit's absolute `line_start`).
+fn split_oversize(code: &str) -> Vec<(u32, u32, String)> {
+    let lines: Vec<&str> = code.split('\n').collect();
+    let total = lines.len() as u32;
+    let mut out: Vec<(u32, u32, String)> = Vec::new();
+    let mut start: u32 = 0;
+    while start < total {
+        let mut end = (start + AST_CHUNK_MAX_LINES).min(total);
+        let floor = start + (AST_CHUNK_MAX_LINES * 4 / 5);
+        if end < total {
+            if let Some(b) = (floor.min(end)..end)
+                .rev()
+                .find(|&i| lines[i as usize].trim().is_empty())
+            {
+                end = b + 1;
+            }
+        }
+        let text = lines[start as usize..end as usize].join("\n");
+        out.push((start, end.saturating_sub(1), text));
+        start = end;
+    }
+    if out.is_empty() {
+        out.push((0, total.saturating_sub(1), code.to_string()));
+    }
+    out
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use kebab_core::{
+        Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock, CommonBlock,
+        SourceSpan, id_for_block, id_for_doc, AssetId, Lang, Metadata, ParserVersion, Provenance,
+        SourceType, TrustLevel, WorkspacePath,
+    };
+    use time::OffsetDateTime;
+
+    fn code_doc(units: &[(&str, u32, u32, &str)]) -> CanonicalDocument {
+        let wp = WorkspacePath("crates/x/src/a.c".into());
+        let aid = AssetId("a".repeat(64));
+        let pv = ParserVersion("code-c-v1".into());
+        let doc_id = id_for_doc(&wp, &aid, &pv);
+        let blocks = units
+            .iter()
+            .enumerate()
+            .map(|(i, (sym, ls, le, code))| {
+                let span = SourceSpan::Code {
+                    line_start: *ls,
+                    line_end: *le,
+                    symbol: Some((*sym).to_string()),
+                    lang: Some("c".into()),
+                };
+                let bid = id_for_block(&doc_id, "code", &[], i as u32, &span);
+                Block::Code(CodeBlock {
+                    common: CommonBlock { block_id: bid, heading_path: vec![], source_span: span },
+                    lang: Some("c".into()),
+                    code: (*code).to_string(),
+                })
+            })
+            .collect();
+        CanonicalDocument {
+            doc_id, source_asset_id: aid, workspace_path: wp, title: "a".into(),
+            lang: Lang("und".into()), blocks,
+            metadata: Metadata {
+                aliases: vec![], tags: vec![],
+                created_at: OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
+                updated_at: OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
+                source_type: SourceType::Note, trust_level: TrustLevel::Primary,
+                user_id_alias: None, user: Default::default(),
+                repo: Some("kebab".into()), git_branch: Some("main".into()),
+                git_commit: Some("0".repeat(40)), code_lang: Some("c".into()),
+            },
+            provenance: Provenance { events: vec![] },
+            parser_version: pv, schema_version: 1, doc_version: 1,
+            last_chunker_version: None, last_embedding_version: None,
+        }
+    }
+    fn policy() -> ChunkPolicy {
+        ChunkPolicy { target_tokens: 500, overlap_tokens: 80,
+            respect_markdown_headings: false,
+            chunker_version: ChunkerVersion(VERSION_LABEL.into()) }
+    }
+
+    #[test]
+    fn chunker_version_is_code_c_ast_v1() {
+        assert_eq!(CodeCAstV1Chunker.chunker_version(),
+            ChunkerVersion("code-c-ast-v1".into()));
+    }
+
+    #[test]
+    fn one_chunk_per_unit_preserves_code_span() {
+        let doc = code_doc(&[
+            ("parse", 1, 3, "int parse() {\n\t// x\n}"),
+            ("print", 5, 7, "void print() {\n\t//\n\treturn;\n}"),
+        ]);
+        let chunks = CodeCAstV1Chunker.chunk(&doc, &policy()).unwrap();
+        assert_eq!(chunks.len(), 2);
+        for c in &chunks {
+            assert_eq!(c.source_spans.len(), 1);
+            assert!(matches!(c.source_spans[0], SourceSpan::Code { .. }));
+            assert_eq!(c.heading_path, Vec::<String>::new());
+            assert_eq!(c.chunker_version.0, "code-c-ast-v1");
+        }
+        match &chunks[0].source_spans[0] {
+            SourceSpan::Code { symbol, line_start, line_end, .. } => {
+                assert_eq!(symbol.as_deref(), Some("parse"));
+                assert_eq!((*line_start, *line_end), (1, 3));
+            }
+            _ => unreachable!(),
+        }
+    }
+
+    #[test]
+    fn oversize_unit_splits_into_parts_with_unique_ids() {
+        let body = (0..500).map(|i| format!("\tx{i} = {i};\n")).collect::<Vec<_>>().join("");
+        let code = format!("int big() {{\n{body}\n}}");
+        let doc = code_doc(&[("big", 1, 502, &code)]);
+        let chunks = CodeCAstV1Chunker.chunk(&doc, &policy()).unwrap();
+        assert!(chunks.len() >= 2, "oversize unit must split, got {}", chunks.len());
+        for c in &chunks {
+            match &c.source_spans[0] {
+                SourceSpan::Code { symbol, .. } => {
+                    assert!(symbol.as_deref().unwrap().starts_with("big [part "),
+                        "part-numbered symbol, got {symbol:?}");
+                }
+                _ => unreachable!(),
+            }
+        }
+        let mut ids: Vec<&str> = chunks.iter().map(|c| c.chunk_id.0.as_str()).collect();
+        let n = ids.len(); ids.sort(); ids.dedup();
+        assert_eq!(ids.len(), n, "chunk_ids unique across split parts");
+    }
+
+    #[test]
+    fn non_code_doc_errors() {
+        use kebab_core::TextBlock;
+        let mut doc = code_doc(&[("parse", 1, 1, "int parse() {}")]);
+        doc.blocks = vec![Block::Paragraph(TextBlock {
+            common: CommonBlock {
+                block_id: kebab_core::BlockId("b".into()),
+                heading_path: vec![],
+                source_span: SourceSpan::Line { start: 1, end: 1 },
+            },
+            text: "x".into(), inlines: vec![],
+        })];
+        let err = CodeCAstV1Chunker.chunk(&doc, &policy()).unwrap_err();
+        assert!(err.to_string().contains("CodeCAstV1Chunker"));
+    }
+
+    #[test]
+    fn deterministic_chunk_ids_1000() {
+        let doc = code_doc(&[("parse", 1, 2, "int parse() {}\n")]);
+        let base: Vec<String> = CodeCAstV1Chunker.chunk(&doc, &policy())
+            .unwrap().into_iter().map(|c| c.chunk_id.0).collect();
+        for _ in 0..1000 {
+            let again: Vec<String> = CodeCAstV1Chunker.chunk(&doc, &policy())
+                .unwrap().into_iter().map(|c| c.chunk_id.0).collect();
+            assert_eq!(again, base);
+        }
+    }
+
+    #[test]
+    fn policy_hash_matches_md_heading_v1() {
+        let p = policy();
+        assert_eq!(CodeCAstV1Chunker.policy_hash(&p),
+            crate::MdHeadingV1Chunker.policy_hash(&p));
+    }
+}

crates/kebab-chunk/src/code_cpp_ast_v1.rs

@@ -0,0 +1,322 @@
+//! `code-cpp-ast-v1` — maps a tree-sitter-derived C++ AST
+//! `CanonicalDocument` (one `Block::Code` per semantic unit, each with
+//! `SourceSpan::Code`) to chunks 1:1. A unit longer than
+//! `AST_CHUNK_MAX_LINES` is split into `<symbol> [part i/N]` sub-chunks
+//! at blank-line paragraph boundaries (design §9.1 oversize fallback).
+//!
+//! tree-sitter is intentionally NOT a dependency here: AST work is
+//! parser-side (`kebab-parse-code`, design §6.3). This chunker only
+//! consumes the `CanonicalDocument`.
+//!
+//! `AST_CHUNK_MAX_LINES` is a constant matching
+//! `IngestCodeCfg::default().ast_chunk_max_lines` (200). Per-medium
+//! config threading needs a chunker registry (P+); same deviation
+//! pattern as `pdf-page-v1`'s pinned `chunker_version`
+//! (`tasks/HOTFIXES.md`).
+
+use kebab_core::{
+    Block, BlockId, CanonicalDocument, Chunk, ChunkPolicy, Chunker, ChunkerVersion, DocumentId,
+    SourceSpan, id_for_chunk,
+};
+
+const VERSION_LABEL: &str = "code-cpp-ast-v1";
+const BYTES_PER_TOKEN: usize = 3;
+const POLICY_HASH_HEX_LEN: usize = 16;
+const AST_CHUNK_MAX_LINES: u32 = 200;
+
+#[derive(Clone, Copy, Debug, Default)]
+pub struct CodeCppAstV1Chunker;
+
+impl Chunker for CodeCppAstV1Chunker {
+    fn chunker_version(&self) -> ChunkerVersion {
+        ChunkerVersion(VERSION_LABEL.to_string())
+    }
+
+    fn policy_hash(&self, policy: &ChunkPolicy) -> String {
+        let bytes = serde_json_canonicalizer::to_vec(policy)
+            .expect("canonical JSON serialization of ChunkPolicy must not fail");
+        let hex = blake3::hash(&bytes).to_hex().to_string();
+        hex[..POLICY_HASH_HEX_LEN].to_string()
+    }
+
+    fn chunk(
+        &self,
+        doc: &CanonicalDocument,
+        policy: &ChunkPolicy,
+    ) -> anyhow::Result<Vec<Chunk>> {
+        for b in &doc.blocks {
+            let c = match b {
+                Block::Code(c) => c,
+                _ => anyhow::bail!(
+                    "CodeCppAstV1Chunker only handles code docs (got non-Code block)"
+                ),
+            };
+            if !matches!(c.common.source_span, SourceSpan::Code { .. }) {
+                anyhow::bail!(
+                    "CodeCppAstV1Chunker only handles code docs (got non-Code source_span)"
+                );
+            }
+        }
+
+        let base_policy_hash = self.policy_hash(policy);
+        let chunker_version = self.chunker_version();
+        let mut out: Vec<Chunk> = Vec::new();
+
+        for b in &doc.blocks {
+            let cb = match b {
+                Block::Code(c) => c,
+                _ => unreachable!("validated above"),
+            };
+            let (ls, le, symbol, lang) = match &cb.common.source_span {
+                SourceSpan::Code { line_start, line_end, symbol, lang } => {
+                    (*line_start, *line_end, symbol.clone(), lang.clone())
+                }
+                _ => unreachable!("validated above"),
+            };
+            let block_ids: Vec<BlockId> = vec![cb.common.block_id.clone()];
+            let span_lines = le.saturating_sub(ls) + 1;
+
+            if span_lines <= AST_CHUNK_MAX_LINES {
+                let span = SourceSpan::Code {
+                    line_start: ls,
+                    line_end: le,
+                    symbol: symbol.clone(),
+                    lang: lang.clone(),
+                };
+                out.push(make_chunk(
+                    doc, &chunker_version, &block_ids, &base_policy_hash,
+                    None, span, cb.code.clone(),
+                ));
+            } else {
+                let parts = split_oversize(&cb.code);
+                let n = parts.len();
+                for (i, (off_start, off_end, text)) in parts.into_iter().enumerate() {
+                    let part_ls = ls + off_start;
+                    let part_le = ls + off_end;
+                    let part_sym = symbol
+                        .as_ref()
+                        .map(|s| format!("{s} [part {}/{n}]", i + 1));
+                    let span = SourceSpan::Code {
+                        line_start: part_ls,
+                        line_end: part_le,
+                        symbol: part_sym,
+                        lang: lang.clone(),
+                    };
+                    out.push(make_chunk(
+                        doc, &chunker_version, &block_ids, &base_policy_hash,
+                        Some(part_ls), span, text,
+                    ));
+                }
+            }
+        }
+
+        tracing::debug!(
+            target: "kebab-chunk",
+            doc_id = %doc.doc_id,
+            chunks = out.len(),
+            "code-cpp-ast-v1 chunked",
+        );
+        Ok(out)
+    }
+}
+
+#[allow(clippy::too_many_arguments)]
+fn make_chunk(
+    doc: &CanonicalDocument,
+    chunker_version: &ChunkerVersion,
+    block_ids: &[BlockId],
+    base_policy_hash: &str,
+    split_key: Option<u32>,
+    span: SourceSpan,
+    text: String,
+) -> Chunk {
+    let id_hash = match split_key {
+        Some(k) => format!("{base_policy_hash}#L{k}"),
+        None => base_policy_hash.to_string(),
+    };
+    let chunk_id = id_for_chunk(&doc.doc_id, chunker_version, block_ids, &id_hash);
+    let token_estimate = text.len().div_ceil(BYTES_PER_TOKEN);
+    Chunk {
+        chunk_id,
+        doc_id: DocumentId(doc.doc_id.0.clone()),
+        block_ids: block_ids.to_vec(),
+        text,
+        heading_path: Vec::new(),
+        source_spans: vec![span],
+        token_estimate,
+        chunker_version: chunker_version.clone(),
+        policy_hash: base_policy_hash.to_string(),
+    }
+}
+
+/// Split an oversize unit at blank-line paragraph boundaries, greedily
+/// gluing paragraphs until ~`AST_CHUNK_MAX_LINES` lines accumulate.
+/// Returns `(line_offset_start, line_offset_end, text)` where offsets are
+/// 0-based within the unit (caller adds the unit's absolute `line_start`).
+fn split_oversize(code: &str) -> Vec<(u32, u32, String)> {
+    let lines: Vec<&str> = code.split('\n').collect();
+    let total = lines.len() as u32;
+    let mut out: Vec<(u32, u32, String)> = Vec::new();
+    let mut start: u32 = 0;
+    while start < total {
+        let mut end = (start + AST_CHUNK_MAX_LINES).min(total);
+        let floor = start + (AST_CHUNK_MAX_LINES * 4 / 5);
+        if end < total {
+            if let Some(b) = (floor.min(end)..end)
+                .rev()
+                .find(|&i| lines[i as usize].trim().is_empty())
+            {
+                end = b + 1;
+            }
+        }
+        let text = lines[start as usize..end as usize].join("\n");
+        out.push((start, end.saturating_sub(1), text));
+        start = end;
+    }
+    if out.is_empty() {
+        out.push((0, total.saturating_sub(1), code.to_string()));
+    }
+    out
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use kebab_core::{
+        Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock, CommonBlock,
+        SourceSpan, id_for_block, id_for_doc, AssetId, Lang, Metadata, ParserVersion, Provenance,
+        SourceType, TrustLevel, WorkspacePath,
+    };
+    use time::OffsetDateTime;
+
+    fn code_doc(units: &[(&str, u32, u32, &str)]) -> CanonicalDocument {
+        let wp = WorkspacePath("crates/x/src/a.cpp".into());
+        let aid = AssetId("a".repeat(64));
+        let pv = ParserVersion("code-cpp-v1".into());
+        let doc_id = id_for_doc(&wp, &aid, &pv);
+        let blocks = units
+            .iter()
+            .enumerate()
+            .map(|(i, (sym, ls, le, code))| {
+                let span = SourceSpan::Code {
+                    line_start: *ls,
+                    line_end: *le,
+                    symbol: Some((*sym).to_string()),
+                    lang: Some("cpp".into()),
+                };
+                let bid = id_for_block(&doc_id, "code", &[], i as u32, &span);
+                Block::Code(CodeBlock {
+                    common: CommonBlock { block_id: bid, heading_path: vec![], source_span: span },
+                    lang: Some("cpp".into()),
+                    code: (*code).to_string(),
+                })
+            })
+            .collect();
+        CanonicalDocument {
+            doc_id, source_asset_id: aid, workspace_path: wp, title: "a".into(),
+            lang: Lang("und".into()), blocks,
+            metadata: Metadata {
+                aliases: vec![], tags: vec![],
+                created_at: OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
+                updated_at: OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
+                source_type: SourceType::Note, trust_level: TrustLevel::Primary,
+                user_id_alias: None, user: Default::default(),
+                repo: Some("kebab".into()), git_branch: Some("main".into()),
+                git_commit: Some("0".repeat(40)), code_lang: Some("cpp".into()),
+            },
+            provenance: Provenance { events: vec![] },
+            parser_version: pv, schema_version: 1, doc_version: 1,
+            last_chunker_version: None, last_embedding_version: None,
+        }
+    }
+    fn policy() -> ChunkPolicy {
+        ChunkPolicy { target_tokens: 500, overlap_tokens: 80,
+            respect_markdown_headings: false,
+            chunker_version: ChunkerVersion(VERSION_LABEL.into()) }
+    }
+
+    #[test]
+    fn chunker_version_is_code_cpp_ast_v1() {
+        assert_eq!(CodeCppAstV1Chunker.chunker_version(),
+            ChunkerVersion("code-cpp-ast-v1".into()));
+    }
+
+    #[test]
+    fn one_chunk_per_unit_preserves_code_span() {
+        let doc = code_doc(&[
+            ("parse", 1, 3, "int parse() {\n\t// x\n}"),
+            ("print", 5, 7, "void print() {\n\t//\n\treturn;\n}"),
+        ]);
+        let chunks = CodeCppAstV1Chunker.chunk(&doc, &policy()).unwrap();
+        assert_eq!(chunks.len(), 2);
+        for c in &chunks {
+            assert_eq!(c.source_spans.len(), 1);
+            assert!(matches!(c.source_spans[0], SourceSpan::Code { .. }));
+            assert_eq!(c.heading_path, Vec::<String>::new());
+            assert_eq!(c.chunker_version.0, "code-cpp-ast-v1");
+        }
+        match &chunks[0].source_spans[0] {
+            SourceSpan::Code { symbol, line_start, line_end, .. } => {
+                assert_eq!(symbol.as_deref(), Some("parse"));
+                assert_eq!((*line_start, *line_end), (1, 3));
+            }
+            _ => unreachable!(),
+        }
+    }
+
+    #[test]
+    fn oversize_unit_splits_into_parts_with_unique_ids() {
+        let body = (0..500).map(|i| format!("\tx{i} = {i};\n")).collect::<Vec<_>>().join("");
+        let code = format!("int big() {{\n{body}\n}}");
+        let doc = code_doc(&[("big", 1, 502, &code)]);
+        let chunks = CodeCppAstV1Chunker.chunk(&doc, &policy()).unwrap();
+        assert!(chunks.len() >= 2, "oversize unit must split, got {}", chunks.len());
+        for c in &chunks {
+            match &c.source_spans[0] {
+                SourceSpan::Code { symbol, .. } => {
+                    assert!(symbol.as_deref().unwrap().starts_with("big [part "),
+                        "part-numbered symbol, got {symbol:?}");
+                }
+                _ => unreachable!(),
+            }
+        }
+        let mut ids: Vec<&str> = chunks.iter().map(|c| c.chunk_id.0.as_str()).collect();
+        let n = ids.len(); ids.sort(); ids.dedup();
+        assert_eq!(ids.len(), n, "chunk_ids unique across split parts");
+    }
+
+    #[test]
+    fn non_code_doc_errors() {
+        use kebab_core::TextBlock;
+        let mut doc = code_doc(&[("parse", 1, 1, "int parse() {}")]);
+        doc.blocks = vec![Block::Paragraph(TextBlock {
+            common: CommonBlock {
+                block_id: kebab_core::BlockId("b".into()),
+                heading_path: vec![],
+                source_span: SourceSpan::Line { start: 1, end: 1 },
+            },
+            text: "x".into(), inlines: vec![],
+        })];
+        let err = CodeCppAstV1Chunker.chunk(&doc, &policy()).unwrap_err();
+        assert!(err.to_string().contains("CodeCppAstV1Chunker"));
+    }
+
+    #[test]
+    fn deterministic_chunk_ids_1000() {
+        let doc = code_doc(&[("parse", 1, 2, "int parse() {}\n")]);
+        let base: Vec<String> = CodeCppAstV1Chunker.chunk(&doc, &policy())
+            .unwrap().into_iter().map(|c| c.chunk_id.0).collect();
+        for _ in 0..1000 {
+            let again: Vec<String> = CodeCppAstV1Chunker.chunk(&doc, &policy())
+                .unwrap().into_iter().map(|c| c.chunk_id.0).collect();
+            assert_eq!(again, base);
+        }
+    }
+
+    #[test]
+    fn policy_hash_matches_md_heading_v1() {
+        let p = policy();
+        assert_eq!(CodeCppAstV1Chunker.policy_hash(&p),
+            crate::MdHeadingV1Chunker.policy_hash(&p));
+    }
+}

crates/kebab-chunk/src/dockerfile_file_v1.rs

@@ -43,6 +43,7 @@ impl Chunker for DockerfileFileV1Chunker {
             "<dockerfile>",
             "dockerfile",
             VERSION_LABEL,
+            None,
         )?;
 
         tracing::debug!(

crates/kebab-chunk/src/k8s_manifest_resource_v1.rs

@@ -85,6 +85,7 @@ impl Chunker for K8sManifestResourceV1Chunker {
                 &symbol,
                 "yaml",
                 VERSION_LABEL,
+                Some(slice.line_start),
             )?;
         }
 

crates/kebab-chunk/src/lib.rs

@@ -15,6 +15,8 @@
 //! embedder, the retriever, the LLM, the RAG layer, or the UI layers.
 //! It consumes `CanonicalDocument` purely through `kb-core` types.
 
+mod code_c_ast_v1;
+mod code_cpp_ast_v1;
 mod code_go_ast_v1;
 mod code_java_ast_v1;
 mod code_js_ast_v1;
@@ -30,6 +32,8 @@ pub mod dockerfile_file_v1;
 pub mod manifest_file_v1;
 pub mod code_text_paragraph_v1;
 
+pub use code_c_ast_v1::CodeCAstV1Chunker;
+pub use code_cpp_ast_v1::CodeCppAstV1Chunker;
 pub use code_go_ast_v1::CodeGoAstV1Chunker;
 pub use code_java_ast_v1::CodeJavaAstV1Chunker;
 pub use code_js_ast_v1::CodeJsAstV1Chunker;

crates/kebab-chunk/src/manifest_file_v1.rs

@@ -44,6 +44,7 @@ impl Chunker for ManifestFileV1Chunker {
             "<manifest>",
             lang,
             VERSION_LABEL,
+            None,
         )?;
 
         tracing::debug!(

crates/kebab-chunk/src/tier2_shared.rs

@@ -25,6 +25,13 @@ pub(crate) fn policy_hash(policy: &ChunkPolicy) -> String {
 /// Emit one chunk for `(text, line_start..=line_end, symbol, lang)`, splitting
 /// into line-windows of at most `AST_CHUNK_MAX_LINES` if the slice is oversize.
 /// Mirrors the oversize path in `code_rust_ast_v1`'s `chunk` impl.
+///
+/// `base_split_key` is used as the `split_key` for the non-oversize single-chunk
+/// case. Callers that emit multiple chunks from the same document (e.g.
+/// `K8sManifestResourceV1Chunker` — one call per k8s resource) MUST pass
+/// `Some(line_start)` so that each call produces a distinct `chunk_id`.
+/// Single-chunk callers (dockerfile-file-v1, manifest-file-v1) pass `None` to
+/// keep chunk_ids stable (no sibling can collide when there's only one chunk).
 #[allow(clippy::too_many_arguments)]
 pub(crate) fn push_chunks_with_oversize(
     out: &mut Vec<Chunk>,
@@ -36,6 +43,7 @@ pub(crate) fn push_chunks_with_oversize(
     symbol: &str,
     lang: &str,
     chunker_version: &str,
+    base_split_key: Option<u32>,
 ) -> Result<()> {
     let n_lines = (line_end - line_start + 1).max(1);
     let cv = ChunkerVersion(chunker_version.to_string());
@@ -51,7 +59,7 @@ pub(crate) fn push_chunks_with_oversize(
             line_end,
             symbol,
             lang,
-            None,
+            base_split_key,
         ));
         return Ok(());
     }

crates/kebab-chunk/tests/code_c_ast_snapshot.rs

@@ -0,0 +1,196 @@
+//! Snapshot test pinning the `Vec<Chunk>` JSON for a
+//! representative C code `CanonicalDocument`.
+//!
+//! This is an integration test. `kebab-parse-code` is intentionally NOT
+//! a dev-dep (design §6.3 / §8 boundary: AST extraction is parser-side).
+//! The `CanonicalDocument` is built inline from hand-crafted `Block::Code`
+//! units, which is the same pattern used in `code_go_ast_v1.rs`'s
+//! internal `code_doc` test helper.
+//!
+//! Set `UPDATE_SNAPSHOTS=1` to re-bake the baseline.
+
+use std::path::PathBuf;
+
+use kebab_chunk::CodeCAstV1Chunker;
+use kebab_core::{
+    AssetId, Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock, CommonBlock,
+    Lang, Metadata, ParserVersion, Provenance, SourceSpan, SourceType, TrustLevel, WorkspacePath,
+    id_for_block, id_for_doc,
+};
+use serde_json::Value;
+use time::OffsetDateTime;
+
+fn fixtures_dir() -> PathBuf {
+    PathBuf::from(env!("CARGO_MANIFEST_DIR"))
+        .join("tests")
+        .join("fixtures")
+}
+
+fn fixed_doc() -> CanonicalDocument {
+    let wp = WorkspacePath("projects/record.c".into());
+    let aid = AssetId("c".repeat(64));
+    // Pin parser_version so doc_id / block_ids are reproducible.
+    let pv = ParserVersion("code-c-v1".into());
+    let doc_id = id_for_doc(&wp, &aid, &pv);
+
+    // Representative units:
+    //  0. imports + defines              (lines 1–4,   ≤200)
+    //  1. status_t enum typedef          (lines 6–9,   ≤200)
+    //  2. record_t struct typedef        (lines 11–16, ≤200)
+    //  3. static counter decl glue       (line 18,     ≤200)
+    //  4. parse_record fn                (lines 20–23, ≤200)
+    //  5. print_record fn                (lines 25–27, ≤200)
+    //  6. main fn                        (lines 29–33, ≤200)
+    let raw_units: Vec<(&str, u32, u32, String)> = vec![
+        (
+            "<top-level>",
+            1,
+            18,
+            "#include <stdio.h>\n#include <stdlib.h>\n\n#define MAX_BUF 4096\n\ntypedef enum {\n    OK = 0,\n    ERR_PARSE,\n    ERR_IO,\n} status_t;\n\ntypedef struct {\n    int id;\n    char name[64];\n    status_t status;\n} record_t;\n\nstatic int counter = 0;".to_string(),
+        ),
+        (
+            "parse_record",
+            20,
+            23,
+            "int parse_record(const char *line, record_t *out) {\n    if (line == NULL || out == NULL) return ERR_PARSE;\n    return OK;\n}".to_string(),
+        ),
+        (
+            "print_record",
+            25,
+            27,
+            "void print_record(const record_t *r) {\n    printf(\"[%d] %s (status=%d)\\n\", r->id, r->name, r->status);\n}".to_string(),
+        ),
+        (
+            "main",
+            29,
+            33,
+            "int main(void) {\n    record_t r = { .id = 1, .name = \"foo\", .status = OK };\n    print_record(&r);\n    return 0;\n}".to_string(),
+        ),
+    ];
+
+    let blocks: Vec<Block> = raw_units
+        .iter()
+        .enumerate()
+        .map(|(i, (sym, ls, le, code))| {
+            let span = SourceSpan::Code {
+                line_start: *ls,
+                line_end: *le,
+                symbol: Some((*sym).to_string()),
+                lang: Some("c".into()),
+            };
+            let bid = id_for_block(&doc_id, "code", &[], i as u32, &span);
+            Block::Code(CodeBlock {
+                common: CommonBlock {
+                    block_id: bid,
+                    heading_path: vec![],
+                    source_span: span,
+                },
+                lang: Some("c".into()),
+                code: code.clone(),
+            })
+        })
+        .collect();
+
+    CanonicalDocument {
+        doc_id,
+        source_asset_id: aid,
+        workspace_path: wp,
+        title: "record.c".into(),
+        lang: Lang("und".into()),
+        blocks,
+        metadata: Metadata {
+            aliases: vec![],
+            tags: vec![],
+            created_at: OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
+            updated_at: OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
+            source_type: SourceType::Note,
+            trust_level: TrustLevel::Primary,
+            user_id_alias: None,
+            user: Default::default(),
+            repo: Some("kebab".into()),
+            git_branch: Some("main".into()),
+            git_commit: Some("0".repeat(40)),
+            code_lang: Some("c".into()),
+        },
+        provenance: Provenance { events: vec![] },
+        parser_version: pv,
+        schema_version: 1,
+        doc_version: 1,
+        last_chunker_version: None,
+        last_embedding_version: None,
+    }
+}
+
+fn fixed_policy() -> ChunkPolicy {
+    ChunkPolicy {
+        target_tokens: 500,
+        overlap_tokens: 80,
+        respect_markdown_headings: false,
+        chunker_version: ChunkerVersion("code-c-ast-v1".into()),
+    }
+}
+
+#[test]
+fn code_c_ast_chunks_snapshot() {
+    let doc = fixed_doc();
+    let policy = fixed_policy();
+
+    let chunks = CodeCAstV1Chunker.chunk(&doc, &policy).expect("chunk");
+    let actual = serde_json::to_value(&chunks).unwrap();
+
+    let dir = fixtures_dir();
+    let baseline_path = dir.join("code-sample.c.chunks.snapshot.json");
+    let baseline_text = match std::fs::read_to_string(&baseline_path) {
+        Ok(s) => s,
+        Err(_) if std::env::var("UPDATE_SNAPSHOTS").is_ok() => {
+            std::fs::create_dir_all(&dir).unwrap();
+            let pretty = serde_json::to_string_pretty(&actual).unwrap();
+            std::fs::write(&baseline_path, format!("{pretty}\n")).unwrap();
+            return;
+        }
+        Err(e) => panic!(
+            "missing baseline {}; run with UPDATE_SNAPSHOTS=1 to create: {e}",
+            baseline_path.display()
+        ),
+    };
+    let expected: Value = serde_json::from_str(&baseline_text).expect("baseline parses as json");
+
+    if actual != expected {
+        if std::env::var("UPDATE_SNAPSHOTS").is_ok() {
+            let pretty = serde_json::to_string_pretty(&actual).unwrap();
+            std::fs::write(&baseline_path, format!("{pretty}\n")).unwrap();
+            eprintln!("updated baseline {}", baseline_path.display());
+            return;
+        }
+        let pretty = serde_json::to_string_pretty(&actual).unwrap();
+        panic!(
+            "code-c-ast-v1 chunks snapshot drift\n\
+             --- expected ({}) ---\n{baseline_text}\n\
+             --- actual ---\n{pretty}\n\
+             If intentional, re-run with UPDATE_SNAPSHOTS=1.",
+            baseline_path.display()
+        );
+    }
+}
+
+/// Determinism cross-check: re-running the same pipeline yields the same
+/// chunk_ids byte-for-byte.
+#[test]
+fn code_c_ast_chunks_are_deterministic() {
+    let policy = fixed_policy();
+    let baseline: Vec<String> = CodeCAstV1Chunker
+        .chunk(&fixed_doc(), &policy)
+        .unwrap()
+        .into_iter()
+        .map(|c| c.chunk_id.0)
+        .collect();
+    for _ in 0..5 {
+        let again: Vec<String> = CodeCAstV1Chunker
+            .chunk(&fixed_doc(), &policy)
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        assert_eq!(again, baseline);
+    }
+}

crates/kebab-chunk/tests/code_cpp_ast_snapshot.rs

@@ -0,0 +1,325 @@
+//! Snapshot test pinning the `Vec<Chunk>` JSON for a
+//! representative C++ code `CanonicalDocument`.
+//!
+//! Two complementary tests:
+//! 1. `code_cpp_ast_chunks_snapshot` — hand-built `fixed_doc()` validates the
+//!    chunker's 1:1 mapping (design §6.3 / §8 boundary: no parse-code dep needed).
+//! 2. `code_cpp_ast_extractor_snapshot` — invokes `CppAstExtractor` against the
+//!    real `tests/fixtures/sample.cpp` fixture, validating the extractor → chunker
+//!    end-to-end pipeline. `kebab-parse-code` is a dev-dep (same pattern as
+//!    `kebab-parse-md` in Markdown snapshot tests).
+//!
+//! Set `UPDATE_SNAPSHOTS=1` to re-bake the baseline.
+
+use std::path::PathBuf;
+
+use kebab_chunk::CodeCppAstV1Chunker;
+use kebab_core::{
+    AssetId, Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock, CommonBlock,
+    Lang, Metadata, ParserVersion, Provenance, SourceSpan, SourceType, TrustLevel, WorkspacePath,
+    id_for_block, id_for_doc,
+};
+use kebab_parse_code::CppAstExtractor;
+use serde_json::Value;
+use time::OffsetDateTime;
+
+fn fixtures_dir() -> PathBuf {
+    PathBuf::from(env!("CARGO_MANIFEST_DIR"))
+        .join("tests")
+        .join("fixtures")
+}
+
+fn fixed_doc() -> CanonicalDocument {
+    let wp = WorkspacePath("projects/record.cpp".into());
+    let aid = AssetId("c".repeat(64));
+    // Pin parser_version so doc_id / block_ids are reproducible.
+    let pv = ParserVersion("code-cpp-v1".into());
+    let doc_id = id_for_doc(&wp, &aid, &pv);
+
+    // Representative units (C++ specific):
+    //  0. includes + namespace opening  (lines 1–4,   ≤200)
+    //  1. class definition              (lines 6–20,  ≤200)
+    //  2. template function             (lines 22–25, ≤200)
+    //  3. namespace closing + free fn   (lines 27–29, ≤200)
+    //  4. main fn                       (lines 31–34, ≤200)
+    let raw_units: Vec<(&str, u32, u32, String)> = vec![
+        (
+            "<top-level>",
+            1,
+            4,
+            "#include <string>\n#include <vector>\n\nnamespace kebab {".to_string(),
+        ),
+        (
+            "kebab::chunk::MdHeadingV1Chunker",
+            6,
+            20,
+            "class MdHeadingV1Chunker {\npublic:\n    MdHeadingV1Chunker() = default;\n    ~MdHeadingV1Chunker() = default;\n\n    std::string chunk_doc(const std::string& doc) {\n        return doc;\n    }\n\n    int operator()(int x) const {\n        return x * 2;\n    }\n\nprivate:\n    int counter_ = 0;\n};".to_string(),
+        ),
+        (
+            "kebab::identity",
+            22,
+            25,
+            "template <typename T>\nT identity(T value) {\n    return value;\n}".to_string(),
+        ),
+        (
+            "kebab::global_helper",
+            27,
+            29,
+            "void global_helper() {\n    // free function in kebab namespace\n}".to_string(),
+        ),
+        (
+            "main",
+            31,
+            34,
+            "int main() {\n    kebab::chunk::MdHeadingV1Chunker c;\n    return 0;\n}".to_string(),
+        ),
+    ];
+
+    let blocks: Vec<Block> = raw_units
+        .iter()
+        .enumerate()
+        .map(|(i, (sym, ls, le, code))| {
+            let span = SourceSpan::Code {
+                line_start: *ls,
+                line_end: *le,
+                symbol: Some((*sym).to_string()),
+                lang: Some("cpp".into()),
+            };
+            let bid = id_for_block(&doc_id, "code", &[], i as u32, &span);
+            Block::Code(CodeBlock {
+                common: CommonBlock {
+                    block_id: bid,
+                    heading_path: vec![],
+                    source_span: span,
+                },
+                lang: Some("cpp".into()),
+                code: code.clone(),
+            })
+        })
+        .collect();
+
+    CanonicalDocument {
+        doc_id,
+        source_asset_id: aid,
+        workspace_path: wp,
+        title: "record.cpp".into(),
+        lang: Lang("und".into()),
+        blocks,
+        metadata: Metadata {
+            aliases: vec![],
+            tags: vec![],
+            created_at: OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
+            updated_at: OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
+            source_type: SourceType::Note,
+            trust_level: TrustLevel::Primary,
+            user_id_alias: None,
+            user: Default::default(),
+            repo: Some("kebab".into()),
+            git_branch: Some("main".into()),
+            git_commit: Some("0".repeat(40)),
+            code_lang: Some("cpp".into()),
+        },
+        provenance: Provenance { events: vec![] },
+        parser_version: pv,
+        schema_version: 1,
+        doc_version: 1,
+        last_chunker_version: None,
+        last_embedding_version: None,
+    }
+}
+
+fn fixed_policy() -> ChunkPolicy {
+    ChunkPolicy {
+        target_tokens: 500,
+        overlap_tokens: 80,
+        respect_markdown_headings: false,
+        chunker_version: ChunkerVersion("code-cpp-ast-v1".into()),
+    }
+}
+
+// ---------------------------------------------------------------------------
+// Helper: run the real CppAstExtractor against tests/fixtures/sample.cpp
+// ---------------------------------------------------------------------------
+
+fn extract_cpp_fixture() -> CanonicalDocument {
+    use kebab_core::{
+        AssetId, AssetStorage, Checksum, ExtractConfig, ExtractContext, Extractor, RawAsset,
+        SourceUri, WorkspacePath,
+    };
+    use std::path::PathBuf;
+
+    let bytes = std::fs::read(fixtures_dir().join("sample.cpp")).expect("read sample.cpp fixture");
+    let src = String::from_utf8(bytes).expect("fixture is valid UTF-8");
+    let wp = WorkspacePath("tests/fixtures/sample.cpp".to_string());
+    let asset = RawAsset {
+        asset_id: AssetId("e".repeat(64)),
+        source_uri: SourceUri::File(PathBuf::from("tests/fixtures/sample.cpp")),
+        workspace_path: wp,
+        media_type: kebab_core::MediaType::Code("cpp".to_string()),
+        byte_len: src.len() as u64,
+        checksum: Checksum("f".repeat(64)),
+        discovered_at: time::OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
+        stored: AssetStorage::Reference {
+            path: PathBuf::from("tests/fixtures/sample.cpp"),
+            sha: Checksum("f".repeat(64)),
+        },
+    };
+    let cfg = ExtractConfig::default();
+    let root = PathBuf::from("/tmp");
+    let ctx = ExtractContext {
+        asset: &asset,
+        workspace_root: &root,
+        config: &cfg,
+    };
+    CppAstExtractor::new().extract(&ctx, src.as_bytes()).unwrap()
+}
+
+// ---------------------------------------------------------------------------
+// Test 1 (hand-built): chunker-only 1:1 mapping validation
+// ---------------------------------------------------------------------------
+
+#[test]
+fn code_cpp_ast_chunks_snapshot() {
+    let doc = fixed_doc();
+    let policy = fixed_policy();
+
+    let chunks = CodeCppAstV1Chunker.chunk(&doc, &policy).expect("chunk");
+    let actual = serde_json::to_value(&chunks).unwrap();
+
+    let dir = fixtures_dir();
+    let baseline_path = dir.join("code-sample.cpp.chunks.snapshot.json");
+    let baseline_text = match std::fs::read_to_string(&baseline_path) {
+        Ok(s) => s,
+        Err(_) if std::env::var("UPDATE_SNAPSHOTS").is_ok() => {
+            std::fs::create_dir_all(&dir).unwrap();
+            let pretty = serde_json::to_string_pretty(&actual).unwrap();
+            std::fs::write(&baseline_path, format!("{pretty}\n")).unwrap();
+            return;
+        }
+        Err(e) => panic!(
+            "missing baseline {}; run with UPDATE_SNAPSHOTS=1 to create: {e}",
+            baseline_path.display()
+        ),
+    };
+    let expected: Value = serde_json::from_str(&baseline_text).expect("baseline parses as json");
+
+    if actual != expected {
+        if std::env::var("UPDATE_SNAPSHOTS").is_ok() {
+            let pretty = serde_json::to_string_pretty(&actual).unwrap();
+            std::fs::write(&baseline_path, format!("{pretty}\n")).unwrap();
+            eprintln!("updated baseline {}", baseline_path.display());
+            return;
+        }
+        let pretty = serde_json::to_string_pretty(&actual).unwrap();
+        panic!(
+            "code-cpp-ast-v1 chunks snapshot drift\n\
+             --- expected ({}) ---\n{baseline_text}\n\
+             --- actual ---\n{pretty}\n\
+             If intentional, re-run with UPDATE_SNAPSHOTS=1.",
+            baseline_path.display()
+        );
+    }
+}
+
+/// Determinism cross-check: re-running the same pipeline yields the same
+/// chunk_ids byte-for-byte.
+#[test]
+fn code_cpp_ast_chunks_are_deterministic() {
+    let policy = fixed_policy();
+    let baseline: Vec<String> = CodeCppAstV1Chunker
+        .chunk(&fixed_doc(), &policy)
+        .unwrap()
+        .into_iter()
+        .map(|c| c.chunk_id.0)
+        .collect();
+    for _ in 0..5 {
+        let again: Vec<String> = CodeCppAstV1Chunker
+            .chunk(&fixed_doc(), &policy)
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        assert_eq!(again, baseline);
+    }
+}
+
+// ---------------------------------------------------------------------------
+// Test 2 (real extractor): end-to-end extractor → chunker pipeline
+// ---------------------------------------------------------------------------
+
+/// Validates that the real `CppAstExtractor` processes `sample.cpp` and
+/// emits the expected set of symbols through the full chunker pipeline.
+///
+/// `sample.cpp` contains:
+/// - `#include` directives + nested namespace `kebab::chunk` → glue + struct unit
+/// - `class MdHeadingV1Chunker` with methods (ctor, dtor, chunk_doc, operator())
+/// - `template <typename T> T identity(T value)` (template fn)
+/// - `void kebab::global_helper()` (free fn in namespace)
+/// - `int main()` (global free fn)
+#[test]
+fn code_cpp_ast_extractor_snapshot() {
+    let doc = extract_cpp_fixture();
+
+    // Verify the extractor emits all expected named units.
+    let block_syms: Vec<Option<String>> = doc.blocks.iter().filter_map(|b| match b {
+        Block::Code(c) => match &c.common.source_span {
+            SourceSpan::Code { symbol, .. } => Some(symbol.clone()),
+            _ => None,
+        },
+        _ => None,
+    }).collect();
+
+    // Must include namespace-qualified class and its methods
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("kebab::chunk::MdHeadingV1Chunker")),
+        "class unit missing: {block_syms:?}"
+    );
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("kebab::chunk::MdHeadingV1Chunker::MdHeadingV1Chunker")),
+        "ctor unit missing: {block_syms:?}"
+    );
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("kebab::chunk::MdHeadingV1Chunker::~MdHeadingV1Chunker")),
+        "dtor unit missing: {block_syms:?}"
+    );
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("kebab::chunk::MdHeadingV1Chunker::chunk_doc")),
+        "chunk_doc unit missing: {block_syms:?}"
+    );
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("kebab::chunk::MdHeadingV1Chunker::operator()")),
+        "operator() unit missing: {block_syms:?}"
+    );
+    // Template function (inside kebab::chunk namespace in the fixture)
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("kebab::chunk::identity")),
+        "identity template fn unit missing: {block_syms:?}"
+    );
+    // Free function in outer namespace
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("kebab::global_helper")),
+        "global_helper unit missing: {block_syms:?}"
+    );
+    // Global main
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("main")),
+        "main unit missing: {block_syms:?}"
+    );
+}
+
+/// End-to-end chunker output from real extractor is deterministic.
+#[test]
+fn code_cpp_ast_extractor_chunks_deterministic() {
+    let doc1 = extract_cpp_fixture();
+    let doc2 = extract_cpp_fixture();
+    assert_eq!(doc1.blocks, doc2.blocks, "extractor output non-deterministic");
+
+    let policy = fixed_policy();
+    let chunks1 = CodeCppAstV1Chunker.chunk(&doc1, &policy).unwrap();
+    let chunks2 = CodeCppAstV1Chunker.chunk(&doc2, &policy).unwrap();
+    assert_eq!(
+        chunks1.iter().map(|c| c.chunk_id.0.clone()).collect::<Vec<_>>(),
+        chunks2.iter().map(|c| c.chunk_id.0.clone()).collect::<Vec<_>>(),
+        "chunker output non-deterministic"
+    );
+}

crates/kebab-chunk/tests/fixtures/code-sample.c.chunks.snapshot.json

@@ -0,0 +1,86 @@
+[
+  {
+    "block_ids": [
+      "8149e12ca002489acb4a0f74c97a061a"
+    ],
+    "chunk_id": "ec3cf06ae56c8e9796bbc9196438b7c5",
+    "chunker_version": "code-c-ast-v1",
+    "doc_id": "6bec42dd593920a060541db16c4e8e45",
+    "heading_path": [],
+    "policy_hash": "ecfad2ec1223662d",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "c",
+        "line_end": 18,
+        "line_start": 1,
+        "symbol": "<top-level>"
+      }
+    ],
+    "text": "#include <stdio.h>\n#include <stdlib.h>\n\n#define MAX_BUF 4096\n\ntypedef enum {\n    OK = 0,\n    ERR_PARSE,\n    ERR_IO,\n} status_t;\n\ntypedef struct {\n    int id;\n    char name[64];\n    status_t status;\n} record_t;\n\nstatic int counter = 0;",
+    "token_estimate": 78
+  },
+  {
+    "block_ids": [
+      "1baaa89f21a47b2f32d6396a24a85454"
+    ],
+    "chunk_id": "c2d7a81c898106733ef2e703774a6a4a",
+    "chunker_version": "code-c-ast-v1",
+    "doc_id": "6bec42dd593920a060541db16c4e8e45",
+    "heading_path": [],
+    "policy_hash": "ecfad2ec1223662d",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "c",
+        "line_end": 23,
+        "line_start": 20,
+        "symbol": "parse_record"
+      }
+    ],
+    "text": "int parse_record(const char *line, record_t *out) {\n    if (line == NULL || out == NULL) return ERR_PARSE;\n    return OK;\n}",
+    "token_estimate": 41
+  },
+  {
+    "block_ids": [
+      "8d0e14cbcc6d1e92d7878ab796ea68b8"
+    ],
+    "chunk_id": "0e4d7b131ab64eba03b51903b5d8f96d",
+    "chunker_version": "code-c-ast-v1",
+    "doc_id": "6bec42dd593920a060541db16c4e8e45",
+    "heading_path": [],
+    "policy_hash": "ecfad2ec1223662d",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "c",
+        "line_end": 27,
+        "line_start": 25,
+        "symbol": "print_record"
+      }
+    ],
+    "text": "void print_record(const record_t *r) {\n    printf(\"[%d] %s (status=%d)\\n\", r->id, r->name, r->status);\n}",
+    "token_estimate": 35
+  },
+  {
+    "block_ids": [
+      "9c2ede84423871b615d48c38fefb1853"
+    ],
+    "chunk_id": "e076f8edb2ff141d7e99b4106bb95157",
+    "chunker_version": "code-c-ast-v1",
+    "doc_id": "6bec42dd593920a060541db16c4e8e45",
+    "heading_path": [],
+    "policy_hash": "ecfad2ec1223662d",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "c",
+        "line_end": 33,
+        "line_start": 29,
+        "symbol": "main"
+      }
+    ],
+    "text": "int main(void) {\n    record_t r = { .id = 1, .name = \"foo\", .status = OK };\n    print_record(&r);\n    return 0;\n}",
+    "token_estimate": 38
+  }
+]

crates/kebab-chunk/tests/fixtures/code-sample.cpp.chunks.snapshot.json

@@ -0,0 +1,107 @@
+[
+  {
+    "block_ids": [
+      "53292605459065d170cd36c118e20546"
+    ],
+    "chunk_id": "50a5b324300d9082eac4ce2a422810e1",
+    "chunker_version": "code-cpp-ast-v1",
+    "doc_id": "fff1e1f0a7ff70ef682937470e5d1d28",
+    "heading_path": [],
+    "policy_hash": "71f3c07bb9ec1d09",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "cpp",
+        "line_end": 4,
+        "line_start": 1,
+        "symbol": "<top-level>"
+      }
+    ],
+    "text": "#include <string>\n#include <vector>\n\nnamespace kebab {",
+    "token_estimate": 18
+  },
+  {
+    "block_ids": [
+      "f349acad94c9fa4cf9ad1c0a93e83610"
+    ],
+    "chunk_id": "0e6bc7c522665af8a4b0f66afb9d29c8",
+    "chunker_version": "code-cpp-ast-v1",
+    "doc_id": "fff1e1f0a7ff70ef682937470e5d1d28",
+    "heading_path": [],
+    "policy_hash": "71f3c07bb9ec1d09",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "cpp",
+        "line_end": 20,
+        "line_start": 6,
+        "symbol": "kebab::chunk::MdHeadingV1Chunker"
+      }
+    ],
+    "text": "class MdHeadingV1Chunker {\npublic:\n    MdHeadingV1Chunker() = default;\n    ~MdHeadingV1Chunker() = default;\n\n    std::string chunk_doc(const std::string& doc) {\n        return doc;\n    }\n\n    int operator()(int x) const {\n        return x * 2;\n    }\n\nprivate:\n    int counter_ = 0;\n};",
+    "token_estimate": 95
+  },
+  {
+    "block_ids": [
+      "8b9811387717d0bd4abf84abcc35b8b1"
+    ],
+    "chunk_id": "d9326d252905b665b2adb9a416c20451",
+    "chunker_version": "code-cpp-ast-v1",
+    "doc_id": "fff1e1f0a7ff70ef682937470e5d1d28",
+    "heading_path": [],
+    "policy_hash": "71f3c07bb9ec1d09",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "cpp",
+        "line_end": 25,
+        "line_start": 22,
+        "symbol": "kebab::identity"
+      }
+    ],
+    "text": "template <typename T>\nT identity(T value) {\n    return value;\n}",
+    "token_estimate": 21
+  },
+  {
+    "block_ids": [
+      "1754cb6b971f6a4cb292f144a4f0570b"
+    ],
+    "chunk_id": "56ee5f991de4a413c016da8dc4acfc35",
+    "chunker_version": "code-cpp-ast-v1",
+    "doc_id": "fff1e1f0a7ff70ef682937470e5d1d28",
+    "heading_path": [],
+    "policy_hash": "71f3c07bb9ec1d09",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "cpp",
+        "line_end": 29,
+        "line_start": 27,
+        "symbol": "kebab::global_helper"
+      }
+    ],
+    "text": "void global_helper() {\n    // free function in kebab namespace\n}",
+    "token_estimate": 22
+  },
+  {
+    "block_ids": [
+      "14b5f3393d6d25f822f5b70763d24acd"
+    ],
+    "chunk_id": "c0d7c043cdd575c530db3909b54cc906",
+    "chunker_version": "code-cpp-ast-v1",
+    "doc_id": "fff1e1f0a7ff70ef682937470e5d1d28",
+    "heading_path": [],
+    "policy_hash": "71f3c07bb9ec1d09",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "cpp",
+        "line_end": 34,
+        "line_start": 31,
+        "symbol": "main"
+      }
+    ],
+    "text": "int main() {\n    kebab::chunk::MdHeadingV1Chunker c;\n    return 0;\n}",
+    "token_estimate": 23
+  }
+]

crates/kebab-chunk/tests/fixtures/sample.c

@@ -0,0 +1,33 @@
+#include <stdio.h>
+#include <stdlib.h>
+
+#define MAX_BUF 4096
+
+typedef enum {
+    OK = 0,
+    ERR_PARSE,
+    ERR_IO,
+} status_t;
+
+typedef struct {
+    int id;
+    char name[64];
+    status_t status;
+} record_t;
+
+static int counter = 0;
+
+int parse_record(const char *line, record_t *out) {
+    if (line == NULL || out == NULL) return ERR_PARSE;
+    return OK;
+}
+
+void print_record(const record_t *r) {
+    printf("[%d] %s (status=%d)\n", r->id, r->name, r->status);
+}
+
+int main(void) {
+    record_t r = { .id = 1, .name = "foo", .status = OK };
+    print_record(&r);
+    return 0;
+}

crates/kebab-chunk/tests/fixtures/sample.cpp

@@ -0,0 +1,40 @@
+#include <string>
+#include <vector>
+
+namespace kebab {
+namespace chunk {
+
+class MdHeadingV1Chunker {
+public:
+    MdHeadingV1Chunker() = default;
+    ~MdHeadingV1Chunker() = default;
+
+    std::string chunk_doc(const std::string& doc) {
+        return doc;
+    }
+
+    int operator()(int x) const {
+        return x * 2;
+    }
+
+private:
+    int counter_ = 0;
+};
+
+template <typename T>
+T identity(T value) {
+    return value;
+}
+
+}  // namespace chunk
+
+void global_helper() {
+    // free function in kebab namespace
+}
+
+}  // namespace kebab
+
+int main() {
+    kebab::chunk::MdHeadingV1Chunker c;
+    return 0;
+}

crates/kebab-chunk/tests/k8s_manifest_resource_v1.rs

@@ -140,6 +140,17 @@ fn k8s_multi_doc_emits_one_chunk_per_resource() {
     for chunk in &chunks {
         assert_eq!(chunk.chunker_version.0, "k8s-manifest-resource-v1");
     }
+
+    // Every chunk from a multi-resource file must have a distinct chunk_id.
+    // Without the fix, all non-oversize resources get split_key=None which
+    // collapses to the same id_hash (= base_policy_hash) → UNIQUE constraint
+    // violation on the second resource.
+    let ids: std::collections::HashSet<_> = chunks.iter().map(|c| c.chunk_id.clone()).collect();
+    assert_eq!(
+        ids.len(),
+        chunks.len(),
+        "every k8s resource chunk must have a distinct chunk_id (multi-resource collision regression)"
+    );
 }
 
 /// A YAML document with an indentation error (tab in a space-indented context)

crates/kebab-cli/src/main.rs

@@ -933,6 +933,15 @@ fn run(cli: &Cli) -> anyhow::Result<()> {
                     let next = resp.next_cursor.as_deref().unwrap_or("(none)");
                     eprintln!("[truncated; use --cursor {next} for the next page]");
                 }
+                // v0.17.0 A5 Step 4: short-query advisory. `resp.hint`
+                // is `Some` only when the result list is empty and the
+                // trimmed query is shorter than the trigram tokenizer
+                // can resolve (raw FTS5 mode opts out). stderr so it
+                // doesn't pollute the stdout hit list. `--json` skips
+                // this branch entirely; the field rides the wire.
+                if let Some(hint) = &resp.hint {
+                    eprintln!("[hint] {hint}");
+                }
                 if *trace {
                     if let Some(t) = &resp.trace {
                         eprintln!();

crates/kebab-cli/src/wire.rs

@@ -92,6 +92,14 @@ pub fn wire_search_response(r: &kebab_app::SearchResponse) -> Value {
             map.insert("trace".to_string(), trace_v);
         }
     }
+    // v0.17.0 A5 Step 4b: emit `hint` only when set. Keeps responses
+    // that don't carry a hint backward-compatible with v0 consumers
+    // that don't know the field.
+    if let Some(hint) = &r.hint {
+        if let Value::Object(ref mut map) = v {
+            map.insert("hint".to_string(), Value::String(hint.clone()));
+        }
+    }
     tag_object(v, "search_response.v1")
 }
 
@@ -292,6 +300,7 @@ mod tests {
             next_cursor: Some("opaque-cursor-abc".to_string()),
             truncated: true,
             trace: None,
+            hint: None,
         };
         let v = wire_search_response(&r);
         assert_eq!(schema_of(&v), Some("search_response.v1"));
@@ -405,6 +414,7 @@ mod tests {
                 }],
                 timing: TraceTiming { lexical_ms: 5, vector_ms: 0, fusion_ms: 1, total_ms: 7 },
             }),
+            hint: None,
         };
         let v = wire_search_response(&r);
         assert_eq!(schema_of(&v), Some("search_response.v1"));
@@ -420,6 +430,7 @@ mod tests {
             next_cursor: None,
             truncated: false,
             trace: None,
+            hint: None,
         };
         let v = wire_search_response(&r);
         assert!(v.get("trace").is_none(), "trace field absent when None");

crates/kebab-cli/tests/wire_search_response.rs

@@ -47,8 +47,20 @@ fn search_json_emits_search_response_v1_wrapper() {
 fn search_json_truncates_with_max_tokens() {
     let dir = tempfile::tempdir().unwrap();
     let (cfg, workspace, _data) = common::write_config(dir.path(), 30);
-    let body: String = "rust ownership is a memory model. ".repeat(10);
-    fs::write(workspace.join("a.md"), format!("# T\n\n{body}\n")).unwrap();
+    // v0.17.0 trigram tokenizer makes FTS5 snippet() tokens 3-char wide
+    // (was full words under unicode61), so an individual snippet stays
+    // around ~60 chars — too short to ever exceed the snippet-shorten
+    // budget cap on a single-hit fixture. To still exercise the budget
+    // loop deterministically, we ingest multiple hits and pick a budget
+    // small enough that the loop has to *pop* hits, which flips
+    // truncated=true regardless of snippet length.
+    for i in 0..5 {
+        fs::write(
+            workspace.join(format!("d{i}.md")),
+            format!("# T{i}\n\nrust ownership is a memory model.\n"),
+        )
+        .unwrap();
+    }
     common::ingest(&cfg, &workspace);
 
     let (stdout, _stderr) = common::run_search_with_args(
@@ -211,8 +223,15 @@ fn search_stale_cursor_returns_error_v1_with_stale_cursor_code() {
 fn search_plain_emits_truncated_hint_to_stderr() {
     let dir = tempfile::tempdir().unwrap();
     let (cfg, workspace, _data) = common::write_config(dir.path(), 30);
-    let body: String = "rust ownership is a memory model. ".repeat(10);
-    fs::write(workspace.join("a.md"), format!("# T\n\n{body}\n")).unwrap();
+    // v0.17.0 trigram tokenizer — same multi-doc rationale as
+    // `search_json_truncates_with_max_tokens` above.
+    for i in 0..5 {
+        fs::write(
+            workspace.join(format!("d{i}.md")),
+            format!("# T{i}\n\nrust ownership is a memory model.\n"),
+        )
+        .unwrap();
+    }
     common::ingest(&cfg, &workspace);
 
     let (_stdout, stderr) = common::run_search_with_args(
@@ -224,3 +243,76 @@ fn search_plain_emits_truncated_hint_to_stderr() {
         "stderr must carry truncated hint: {stderr:?}"
     );
 }
+
+#[test]
+fn search_plain_emits_short_query_hint_to_stderr() {
+    // v0.17.0 A5 Step 6: 2-char query under trigram tokenizer emits
+    // empty hits + stderr `[hint]` advisory. Empty workspace is enough
+    // — hits are always empty so the hint condition depends only on
+    // query length (<3 chars trimmed) + non-raw mode + hits.is_empty.
+    let dir = tempfile::tempdir().unwrap();
+    let (cfg, workspace, _data) = common::write_config(dir.path(), 30);
+    common::ingest(&cfg, &workspace);
+
+    let (_stdout, stderr) = common::run_search_with_args(
+        &cfg,
+        &["--mode", "lexical", "ab"],
+    );
+    assert!(
+        stderr.contains("[hint]"),
+        "stderr must carry short-query hint: {stderr:?}"
+    );
+    assert!(
+        stderr.contains("3자 이상"),
+        "hint message must mention '3자 이상' (Korean advisory): {stderr:?}"
+    );
+}
+
+#[test]
+fn search_json_emits_hint_field_for_short_query() {
+    // v0.17.0 A5 Step 6: --json mode carries the same advisory on the
+    // `search_response.v1.hint` additive field. Empty hits + 2-char
+    // query + non-raw mode trips the helper. Verifies the MCP-visible
+    // surface (agents read the field instead of parsing stderr).
+    let dir = tempfile::tempdir().unwrap();
+    let (cfg, workspace, _data) = common::write_config(dir.path(), 30);
+    common::ingest(&cfg, &workspace);
+
+    let (stdout, _stderr) = common::run_search_with_args(
+        &cfg,
+        &["--json", "--mode", "lexical", "ab"],
+    );
+    let v: Value = serde_json::from_str(stdout.trim())
+        .unwrap_or_else(|e| panic!("not JSON: {stdout:?}: {e}"));
+    assert!(
+        v["hits"].as_array().unwrap().is_empty(),
+        "empty hits expected for short query in empty KB: {v}"
+    );
+    assert_eq!(
+        v["hint"].as_str().expect("hint field set on short empty result"),
+        "3자 이상 키워드 권장 (trigram tokenizer 제약)",
+        "hint must carry the standard advisory: {v}"
+    );
+}
+
+#[test]
+fn search_json_omits_hint_field_when_query_is_long_enough() {
+    // v0.17.0 A5 Step 6 (negative case): 3+ char query never trips
+    // hint, even on an empty KB. Verifies `serialize_search_response`
+    // omits the additive `hint` field when `None` so existing wire
+    // consumers stay backward-compatible.
+    let dir = tempfile::tempdir().unwrap();
+    let (cfg, workspace, _data) = common::write_config(dir.path(), 30);
+    common::ingest(&cfg, &workspace);
+
+    let (stdout, _stderr) = common::run_search_with_args(
+        &cfg,
+        &["--json", "--mode", "lexical", "abc"],
+    );
+    let v: Value = serde_json::from_str(stdout.trim())
+        .unwrap_or_else(|e| panic!("not JSON: {stdout:?}: {e}"));
+    assert!(
+        v.get("hint").is_none(),
+        "hint must be absent for ≥3-char queries: {v}"
+    );
+}

crates/kebab-eval/tests/fixtures/eval/run-1.json

@@ -5,7 +5,7 @@
       "chunk_id": "chunk000000000000000000000000000000",
       "doc_id": "doc00000000000000000000000000000000",
       "heading_path": [],
-      "score": 0.3429983854293823
+      "score": 0.35202541947364807
     },
     "has_answer": false,
     "hits_count": 1,
@@ -19,7 +19,7 @@
       "chunk_id": "chunk000000000000000000000000000002",
       "doc_id": "doc00000000000000000000000000000002",
       "heading_path": [],
-      "score": 0.3585492968559265
+      "score": 0.3414848744869232
     },
     "has_answer": false,
     "hits_count": 1,

crates/kebab-parse-code/Cargo.toml

@@ -22,6 +22,8 @@ tree-sitter-javascript = { workspace = true }
 tree-sitter-go         = { workspace = true }
 tree-sitter-java       = { workspace = true }
 tree-sitter-kotlin-ng  = { workspace = true }
+tree-sitter-c          = { workspace = true }
+tree-sitter-cpp        = { workspace = true }
 
 [dev-dependencies]
 tempfile = { workspace = true }

crates/kebab-parse-code/src/c.rs

@@ -0,0 +1,720 @@
+//! `kebab-parse-code::c` — tree-sitter C AST extractor (P10-1D Task B).
+//!
+//! Implements [`kebab_core::Extractor`] for [`MediaType::Code("c")`].
+//! Walks the tree-sitter parse tree and emits one [`Block::Code`] per
+//! top-level AST semantic unit:
+//!
+//! - `function_definition` → 1 unit, symbol = function name (extracted
+//!   from the declarator's innermost `identifier`, handles pointer-returning
+//!   functions where the declarator is wrapped in `pointer_declarator`).
+//! - `struct_specifier` (named) → 1 unit, symbol = struct name.
+//! - `enum_specifier` (named) → 1 unit, symbol = enum name.
+//! - `union_specifier` (named) → 1 unit, symbol = union name.
+//!
+//! Everything else (`declaration`, `preproc_*`, `type_definition`,
+//! `linkage_specification`, etc.) collapses into a single `<top-level>`
+//! glue chunk. If the file produces zero units **and** zero glue, the
+//! `<module>` post-pass emits one unit covering the whole file (1A-2
+//! pattern).
+//!
+//! C symbol = function name only — no namespace, no class nesting
+//! (design §3.4 C row). Per design §3.4 / §9.1 / §9 versioning.
+
+use anyhow::Result;
+use kebab_core::{
+    Block, CanonicalDocument, CodeBlock, CommonBlock, Extractor, Lang, MediaType, Metadata,
+    ParserVersion, Provenance, ProvenanceEvent, ProvenanceKind, SourceSpan, SourceType, TrustLevel,
+    id_for_block, id_for_doc,
+};
+use serde_json::Map;
+use time::OffsetDateTime;
+
+use crate::scaffold::{filename_from_workspace_path, strip_extension};
+
+pub const PARSER_VERSION: &str = "code-c-v2";
+
+/// C AST extractor. Per-unit blocks via tree-sitter-c 0.24.2
+/// (`LANGUAGE: LanguageFn`) parsed by tree-sitter 0.26.
+pub struct CAstExtractor;
+
+impl CAstExtractor {
+    pub fn new() -> Self {
+        Self
+    }
+}
+
+impl Default for CAstExtractor {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl Extractor for CAstExtractor {
+    fn supports(&self, m: &MediaType) -> bool {
+        matches!(m, MediaType::Code(l) if l == "c")
+    }
+
+    fn parser_version(&self) -> ParserVersion {
+        ParserVersion(PARSER_VERSION.to_string())
+    }
+
+    fn extract(
+        &self,
+        ctx: &kebab_core::ExtractContext<'_>,
+        bytes: &[u8],
+    ) -> Result<CanonicalDocument> {
+        let asset = ctx.asset;
+        if !self.supports(&asset.media_type) {
+            anyhow::bail!(
+                "kebab-parse-code: unsupported media_type for CAstExtractor: {:?}",
+                asset.media_type
+            );
+        }
+
+        let parser_version = self.parser_version();
+        let doc_id = id_for_doc(&asset.workspace_path, &asset.asset_id, &parser_version);
+
+        let source = String::from_utf8(bytes.to_vec())
+            .map_err(|e| anyhow::anyhow!("kebab-parse-code: C source is not valid UTF-8: {e}"))?;
+
+        let blocks = build_blocks(&source, &doc_id)?;
+        let unit_count = blocks.len() as u32;
+
+        let now = OffsetDateTime::now_utc();
+        let mut events: Vec<ProvenanceEvent> = Vec::with_capacity(2);
+        events.push(ProvenanceEvent {
+            at: asset.discovered_at,
+            agent: "kb-source-fs".to_string(),
+            kind: ProvenanceKind::Discovered,
+            note: None,
+        });
+        events.push(ProvenanceEvent {
+            at: now,
+            agent: "kb-parse-code".to_string(),
+            kind: ProvenanceKind::Parsed,
+            note: Some(format!(
+                "parser_version={}; unit_count={}",
+                parser_version.0, unit_count
+            )),
+        });
+
+        let title = {
+            let fname = filename_from_workspace_path(&asset.workspace_path.0);
+            strip_extension(&fname)
+        };
+
+        let abs_path = match &asset.source_uri {
+            kebab_core::SourceUri::File(p) => {
+                if p.is_absolute() {
+                    p.clone()
+                } else {
+                    ctx.workspace_root.join(p)
+                }
+            }
+            kebab_core::SourceUri::Kb(_) => ctx.workspace_root.to_path_buf(),
+        };
+        let (repo, git_branch, git_commit) = match crate::repo::detect_repo(&abs_path) {
+            Some(r) => (Some(r.name), r.branch, r.commit),
+            None => (None, None, None),
+        };
+
+        let metadata = Metadata {
+            aliases: Vec::new(),
+            tags: Vec::new(),
+            created_at: asset.discovered_at,
+            updated_at: asset.discovered_at,
+            source_type: SourceType::Note,
+            trust_level: TrustLevel::Primary,
+            user_id_alias: None,
+            user: Map::new(),
+            repo,
+            git_branch,
+            git_commit,
+            code_lang: Some("c".to_string()),
+        };
+
+        tracing::debug!(
+            target: "kebab-parse-code",
+            "extracted C doc_id={} workspace_path={} units={}",
+            doc_id.0,
+            asset.workspace_path.0,
+            unit_count
+        );
+
+        Ok(CanonicalDocument {
+            doc_id,
+            source_asset_id: asset.asset_id.clone(),
+            workspace_path: asset.workspace_path.clone(),
+            title,
+            lang: Lang("und".to_string()),
+            blocks,
+            metadata,
+            provenance: Provenance { events },
+            parser_version,
+            schema_version: 1,
+            doc_version: 1,
+            last_chunker_version: None,
+            last_embedding_version: None,
+        })
+    }
+}
+
+/// Walk down the declarator chain of a `function_definition` to find
+/// the innermost `identifier` — the function name.
+///
+/// The tree for `int *foo(int x) { ... }` looks like:
+/// ```text
+/// function_definition
+///   type: primitive_type  "int"
+///   declarator: pointer_declarator
+///     declarator: function_declarator
+///       declarator: identifier  "foo"
+///       parameters: parameter_list
+///   body: compound_statement
+/// ```
+/// We walk `declarator` fields recursively until we reach an `identifier`
+/// or run out of nodes. Returns `None` if no identifier is found
+/// (malformed / unsupported declarator shape).
+fn extract_fn_name<'a>(decl_node: tree_sitter::Node, src: &'a str) -> Option<&'a str> {
+    let mut cur = decl_node;
+    loop {
+        match cur.kind() {
+            "identifier" => return Some(&src[cur.start_byte()..cur.end_byte()]),
+            // pointer_declarator, function_declarator, array_declarator,
+            // attributed_declarator, parenthesized_declarator —
+            // all carry a `declarator` field pointing deeper.
+            _ => {
+                if let Some(inner) = cur.child_by_field_name("declarator") {
+                    cur = inner;
+                } else {
+                    // No further `declarator` field; give up.
+                    return None;
+                }
+            }
+        }
+    }
+}
+
+fn build_blocks(
+    source: &str,
+    doc_id: &kebab_core::DocumentId,
+) -> anyhow::Result<Vec<kebab_core::Block>> {
+    let mut parser = tree_sitter::Parser::new();
+    parser
+        .set_language(&tree_sitter_c::LANGUAGE.into())
+        .map_err(|e| anyhow::anyhow!("set tree-sitter-c language: {e}"))?;
+    let tree = parser
+        .parse(source.as_bytes(), None)
+        .ok_or_else(|| anyhow::anyhow!("tree-sitter failed to parse C source"))?;
+    let lines: Vec<&str> = source.split('\n').collect();
+
+    let root = tree.root_node();
+
+    // units: (symbol, line_start, line_end, is_real_semantic_unit).
+    // Glue is accumulated as (start, end) pairs and flushed into one
+    // "<top-level>" block (or "<module>" if no real unit exists).
+    let mut units: Vec<(String, u32, u32, bool)> = Vec::new();
+    let mut glue: Vec<(u32, u32)> = Vec::new();
+
+    /// Walk preceding `comment` siblings to extend the unit's line range
+    /// upward, folding doc / line comments into the unit (1B pattern).
+    fn unit_start(n: &tree_sitter::Node) -> u32 {
+        let mut start = n.start_position().row as u32 + 1;
+        let mut prev = n.prev_sibling();
+        while let Some(p) = prev {
+            if p.kind() == "comment" {
+                start = p.start_position().row as u32 + 1;
+                prev = p.prev_sibling();
+            } else {
+                break;
+            }
+        }
+        start
+    }
+
+    let mut cur = root.walk();
+    for child in root.named_children(&mut cur) {
+        let s = unit_start(&child);
+        let e = child.end_position().row as u32 + 1;
+
+        match child.kind() {
+            "function_definition" => {
+                if let Some(decl) = child.child_by_field_name("declarator") {
+                    if let Some(name) = extract_fn_name(decl, source) {
+                        flush_glue(&mut glue, &mut units);
+                        units.push((name.to_string(), s, e, true));
+                    } else {
+                        // Could not extract name — treat as glue.
+                        glue.push((s, e));
+                    }
+                } else {
+                    glue.push((s, e));
+                }
+            }
+            "struct_specifier" | "enum_specifier" | "union_specifier" => {
+                if let Some(name_node) = child.child_by_field_name("name") {
+                    let name = &source[name_node.start_byte()..name_node.end_byte()];
+                    flush_glue(&mut glue, &mut units);
+                    units.push((name.to_string(), s, e, true));
+                } else {
+                    // Anonymous struct/enum/union at the top level (not
+                    // wrapped in typedef) — glue. typedef-wrapped case
+                    // is recovered in the `type_definition` arm below.
+                    glue.push((s, e));
+                }
+            }
+            "type_definition" => {
+                // v0.17.0 PR-B: typedef-wrapped anonymous aggregate
+                // recovery. `typedef struct { ... } Foo;` exposes only
+                // the alias `Foo` as a useful symbol — the inner
+                // struct_specifier has no `name` field. Pre-v0.17.0
+                // this whole construct collapsed into glue and hid the
+                // alias from search (HOTFIXES 2026-05-21). v2 recovers
+                // the alias from the `declarator` field and emits a
+                // synthetic unit so `Citation::Code.symbol = "Foo"`.
+                // Plain `typedef int MyInt;` (no inner aggregate) stays
+                // glue — there's no struct body to name.
+                if let Some(name) = recover_typedef_alias(child, source) {
+                    flush_glue(&mut glue, &mut units);
+                    units.push((name, s, e, true));
+                } else {
+                    glue.push((s, e));
+                }
+            }
+            // Everything else: preprocessor directives, plain declarations
+            // (global var / fn prototype), linkage_specification, etc.
+            // — all collapse into glue.
+            _ => {
+                glue.push((s, e));
+            }
+        }
+    }
+    flush_glue(&mut glue, &mut units);
+
+    // Post-pass: if the file has no real semantic unit (only glue, or
+    // completely empty), rename the single glue unit to "<module>" and
+    // emit it. If there are zero units AND zero glue, synthesise a
+    // one-line "<module>" covering the whole file.
+    let has_real_unit = units.iter().any(|(_, _, _, is_real)| *is_real);
+
+    if units.is_empty() {
+        // Completely empty file or whitespace/comments only.
+        let total = lines.len() as u32;
+        units.push((
+            "<module>".to_string(),
+            1,
+            total.max(1),
+            false,
+        ));
+    }
+    // If there is only glue (no real unit) the single pushed "<top-level>"
+    // label should be "<module>" — rename it now.
+    if !has_real_unit {
+        for (sym, _, _, _) in units.iter_mut() {
+            if sym == "<top-level>" {
+                *sym = "<module>".to_string();
+            }
+        }
+    }
+
+    let total_lines = lines.len() as u32;
+    let mut blocks = Vec::with_capacity(units.len());
+    for (ordinal, (symbol, ls, le, _is_real)) in units.into_iter().enumerate() {
+        let line_start = ls.max(1);
+        let line_end = le.min(total_lines.max(1));
+        let span = SourceSpan::Code {
+            line_start,
+            line_end,
+            symbol: Some(symbol),
+            lang: Some("c".to_string()),
+        };
+        let block_id = id_for_block(doc_id, "code", &[], ordinal as u32, &span);
+        let code = lines[(line_start as usize - 1)..=(line_end as usize - 1)].join("\n");
+        blocks.push(Block::Code(CodeBlock {
+            common: CommonBlock {
+                block_id,
+                heading_path: Vec::new(),
+                source_span: span,
+            },
+            lang: Some("c".to_string()),
+            code,
+        }));
+    }
+    Ok(blocks)
+}
+
+/// v0.17.0 PR-B: try to recover the typedef alias name from a
+/// `type_definition` node *iff* the inner type-specifier is an
+/// anonymous struct/enum/union. Returns `None` for any other shape
+/// (named aggregate handled elsewhere, plain type alias has no body
+/// worth naming).
+fn recover_typedef_alias(node: tree_sitter::Node, source: &str) -> Option<String> {
+    let mut has_anon_aggregate = false;
+    let mut cursor = node.walk();
+    for sub in node.children(&mut cursor) {
+        match sub.kind() {
+            "struct_specifier" | "enum_specifier" | "union_specifier" => {
+                if sub.child_by_field_name("name").is_none() {
+                    has_anon_aggregate = true;
+                } else {
+                    // Named inner aggregate (e.g. `typedef struct Pt {...} P;`)
+                    // — the named struct itself is the primary symbol and
+                    // is *not* extracted at the top level today (it lives
+                    // inside `type_definition`, not as a sibling
+                    // `struct_specifier`). For v2 we keep behavior conservative:
+                    // return None so the type_definition stays glue, matching
+                    // pre-v2 behavior for this minor case. Real-world C tends
+                    // to use one of: bare named struct, typedef alias only,
+                    // or typedef on anonymous body — the latter is what we fix.
+                    return None;
+                }
+            }
+            _ => {}
+        }
+    }
+    if !has_anon_aggregate {
+        return None;
+    }
+    let decl = node.child_by_field_name("declarator")?;
+    extract_typedef_alias_name(decl, source).map(str::to_string)
+}
+
+/// Extract the typedef alias identifier from a declarator subtree.
+/// Handles the common shapes: direct `type_identifier`, or one wrapped
+/// in pointer / function declarator nodes (the alias is always the
+/// rightmost `type_identifier` descendant).
+fn extract_typedef_alias_name<'a>(
+    decl: tree_sitter::Node,
+    source: &'a str,
+) -> Option<&'a str> {
+    if decl.kind() == "type_identifier" {
+        return Some(&source[decl.start_byte()..decl.end_byte()]);
+    }
+    let mut cursor = decl.walk();
+    for sub in decl.children(&mut cursor) {
+        if let Some(found) = extract_typedef_alias_name(sub, source) {
+            return Some(found);
+        }
+    }
+    None
+}
+
+fn flush_glue(glue: &mut Vec<(u32, u32)>, units: &mut Vec<(String, u32, u32, bool)>) {
+    if glue.is_empty() {
+        return;
+    }
+    let s = glue.iter().map(|(a, _)| *a).min().unwrap();
+    let e = glue.iter().map(|(_, b)| *b).max().unwrap();
+    units.push(("<top-level>".to_string(), s, e, false));
+    glue.clear();
+}
+
+// ---------------------------------------------------------------------------
+// Tests
+// ---------------------------------------------------------------------------
+
+#[cfg(test)]
+pub(crate) mod tests_support {
+    use kebab_core::*;
+    use std::path::PathBuf;
+    use time::OffsetDateTime;
+
+    pub fn fixed_code_asset(workspace_path: &str, lang: &str) -> RawAsset {
+        RawAsset {
+            asset_id: AssetId("a".repeat(64)),
+            source_uri: SourceUri::File(PathBuf::from(workspace_path)),
+            workspace_path: WorkspacePath(workspace_path.to_string()),
+            media_type: MediaType::Code(lang.to_string()),
+            byte_len: 0,
+            checksum: Checksum("b".repeat(64)),
+            discovered_at: OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
+            stored: AssetStorage::Reference {
+                path: PathBuf::from(workspace_path),
+                sha: Checksum("b".repeat(64)),
+            },
+        }
+    }
+
+    pub fn extract_c(src: &str, path: &str) -> kebab_core::CanonicalDocument {
+        use super::CAstExtractor;
+        use kebab_core::Extractor;
+        let asset = fixed_code_asset(path, "c");
+        let cfg = ExtractConfig::default();
+        let root = PathBuf::from("/tmp");
+        let ctx = ExtractContext {
+            asset: &asset,
+            workspace_root: &root,
+            config: &cfg,
+        };
+        CAstExtractor::new().extract(&ctx, src.as_bytes()).unwrap()
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use kebab_core::{Block, MediaType, SourceSpan};
+
+    fn syms(doc: &kebab_core::CanonicalDocument) -> Vec<String> {
+        doc.blocks
+            .iter()
+            .filter_map(|b| match b {
+                Block::Code(c) => match &c.common.source_span {
+                    SourceSpan::Code { symbol, .. } => symbol.clone(),
+                    _ => None,
+                },
+                _ => None,
+            })
+            .collect()
+    }
+
+    #[test]
+    fn extractor_supports_only_media_code_c() {
+        let e = CAstExtractor::new();
+        assert!(e.supports(&MediaType::Code("c".into())));
+        assert!(!e.supports(&MediaType::Code("cpp".into())));
+        assert!(!e.supports(&MediaType::Code("rust".into())));
+        assert!(!e.supports(&MediaType::Markdown));
+    }
+
+    #[test]
+    fn c_extractor_simple_function() {
+        let src = "int add(int a, int b) { return a + b; }\n";
+        let doc = tests_support::extract_c(src, "x/math.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "add"), "got {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_pointer_return_function() {
+        let src = "int *find(int *arr, int n) { return arr; }\n";
+        let doc = tests_support::extract_c(src, "x/find.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "find"), "ptr-return fn missing: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_static_function() {
+        let src = "static void helper(void) {}\n";
+        let doc = tests_support::extract_c(src, "x/helper.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "helper"), "static fn missing: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_extern_function() {
+        let src = "extern int compute(int x);\n";
+        // extern prototype is a declaration → glue
+        let doc = tests_support::extract_c(src, "x/compute.c");
+        let s = syms(&doc);
+        // declaration (prototype) falls into glue → "<module>"
+        assert!(
+            s.iter().any(|x| x == "<module>"),
+            "expected <module> for extern proto: {s:?}"
+        );
+    }
+
+    #[test]
+    fn c_extractor_inline_function() {
+        let src = "inline int square(int x) { return x * x; }\n";
+        let doc = tests_support::extract_c(src, "x/square.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "square"), "inline fn missing: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_named_struct() {
+        let src = "struct Point { int x; int y; };\n";
+        let doc = tests_support::extract_c(src, "x/point.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "Point"), "struct missing: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_named_enum() {
+        let src = "enum Color { RED, GREEN, BLUE };\n";
+        let doc = tests_support::extract_c(src, "x/color.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "Color"), "enum missing: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_named_union() {
+        let src = "union Data { int i; float f; };\n";
+        let doc = tests_support::extract_c(src, "x/data.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "Data"), "union missing: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_anonymous_struct_falls_into_glue() {
+        // Anonymous struct (no name field) → glue → "<module>" (only glue, no real unit)
+        let src = "struct { int x; int y; } origin;\n";
+        let doc = tests_support::extract_c(src, "x/anon.c");
+        let s = syms(&doc);
+        // anonymous struct is a declaration containing anonymous struct_specifier → glue
+        assert!(
+            s.iter().any(|x| x == "<module>"),
+            "expected <module> for anon struct: {s:?}"
+        );
+        // Must NOT emit a unit named after anything else
+        assert!(
+            !s.iter().any(|x| x == "origin"),
+            "unexpected 'origin' unit: {s:?}"
+        );
+    }
+
+    #[test]
+    fn c_extractor_typedef_struct_emits_unit() {
+        // v0.17.0 PR-B: `typedef struct { ... } Foo;` was previously a
+        // hotfix-tracked deviation (HOTFIXES.md 2026-05-21) — the inner
+        // struct_specifier is anonymous so the named-struct arm didn't
+        // fire, dropping the whole construct into glue and hiding the
+        // `Foo` alias from symbol search. The v2 extractor recovers the
+        // typedef alias from the `declarator` field on the
+        // `type_definition` node and emits a synthetic unit with that
+        // name. parser_version bumped `code-c-v1` → `code-c-v2`.
+        let src = "typedef struct { int x; int y; } Point;\n";
+        let doc = tests_support::extract_c(src, "x/typedef.c");
+        let s = syms(&doc);
+        // The typedef alias surfaces as a Code symbol.
+        assert!(
+            s.iter().any(|x| x == "Point"),
+            "expected 'Point' unit from typedef alias: {s:?}"
+        );
+        // No `<module>` (the file has exactly one semantic unit now,
+        // the typedef alias — no glue-only fallback needed).
+        assert!(
+            !s.iter().any(|x| x == "<module>"),
+            "no <module> fallback expected when typedef emits a unit: {s:?}"
+        );
+    }
+
+    #[test]
+    fn c_extractor_typedef_enum_emits_unit() {
+        // Parallel coverage for enum_specifier — same typedef-alias
+        // synthesis path. `typedef enum { A, B } Color;` → unit `Color`.
+        let src = "typedef enum { A, B } Color;\n";
+        let doc = tests_support::extract_c(src, "x/typedef_enum.c");
+        let s = syms(&doc);
+        assert!(
+            s.iter().any(|x| x == "Color"),
+            "expected 'Color' unit from typedef enum alias: {s:?}"
+        );
+    }
+
+    #[test]
+    fn c_extractor_typedef_union_emits_unit() {
+        // Parallel coverage for union_specifier.
+        let src = "typedef union { int i; float f; } IntOrFloat;\n";
+        let doc = tests_support::extract_c(src, "x/typedef_union.c");
+        let s = syms(&doc);
+        assert!(
+            s.iter().any(|x| x == "IntOrFloat"),
+            "expected 'IntOrFloat' unit from typedef union alias: {s:?}"
+        );
+    }
+
+    #[test]
+    fn c_extractor_typedef_to_existing_type_stays_glue() {
+        // Negative case: `typedef int MyInt;` has no inner struct/enum/
+        // union — there's no struct body to attach the alias to, so the
+        // construct falls into glue (becomes `<module>` when alone).
+        // Confirms the new arm only fires for anonymous-struct typedef.
+        let src = "typedef int MyInt;\n";
+        let doc = tests_support::extract_c(src, "x/typedef_alias.c");
+        let s = syms(&doc);
+        assert!(
+            s.iter().any(|x| x == "<module>"),
+            "expected <module> for plain typedef alias: {s:?}"
+        );
+        assert!(
+            !s.iter().any(|x| x == "MyInt"),
+            "plain typedef alias must not emit a unit: {s:?}"
+        );
+    }
+
+    #[test]
+    fn c_extractor_preprocessor_directives_are_glue() {
+        let src = "#include <stdio.h>\n#define MAX 100\n#ifdef DEBUG\n#endif\n";
+        let doc = tests_support::extract_c(src, "x/macros.c");
+        let s = syms(&doc);
+        // Only preprocessor → no real unit → "<module>"
+        assert!(
+            s.iter().any(|x| x == "<module>"),
+            "expected <module> for preproc-only file: {s:?}"
+        );
+        assert_eq!(s.len(), 1, "expected exactly 1 block: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_multiple_functions_correct_count() {
+        let src = "int foo(void) { return 1; }\nint bar(void) { return 2; }\nint baz(void) { return 3; }\n";
+        let doc = tests_support::extract_c(src, "x/multi.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "foo"), "foo missing: {s:?}");
+        assert!(s.iter().any(|x| x == "bar"), "bar missing: {s:?}");
+        assert!(s.iter().any(|x| x == "baz"), "baz missing: {s:?}");
+        assert_eq!(s.len(), 3, "expected 3 units: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_empty_file_produces_module() {
+        let src = "";
+        let doc = tests_support::extract_c(src, "x/empty.c");
+        let s = syms(&doc);
+        assert_eq!(s, vec!["<module>"], "expected <module>: got {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_preprocessor_only_produces_module() {
+        let src = "#include <stdlib.h>\n#define VERSION \"1.0\"\n";
+        let doc = tests_support::extract_c(src, "x/header.c");
+        let s = syms(&doc);
+        assert!(
+            s.iter().any(|x| x == "<module>"),
+            "expected <module> for preproc-only file: {s:?}"
+        );
+    }
+
+    #[test]
+    fn c_extractor_mixed_functions_and_glue() {
+        let src = r#"#include <stdio.h>
+
+int compute(int x) {
+    return x * 2;
+}
+
+extern int lookup(int key);
+
+void print_result(int v) {
+    printf("%d\n", v);
+}
+"#;
+        let doc = tests_support::extract_c(src, "x/mixed.c");
+        let s = syms(&doc);
+        // Two real functions + one glue block
+        assert!(s.iter().any(|x| x == "compute"), "compute missing: {s:?}");
+        assert!(s.iter().any(|x| x == "print_result"), "print_result missing: {s:?}");
+        assert!(
+            s.iter().any(|x| x == "<top-level>"),
+            "<top-level> glue missing: {s:?}"
+        );
+    }
+
+    #[test]
+    fn c_extractor_deterministic_across_runs() {
+        let src = r#"
+struct Node { int val; };
+int sum(int a, int b) { return a + b; }
+void noop(void) {}
+"#;
+        let a = tests_support::extract_c(src, "x/det.c");
+        for _ in 0..20 {
+            assert_eq!(
+                tests_support::extract_c(src, "x/det.c").blocks,
+                a.blocks
+            );
+        }
+    }
+}

crates/kebab-parse-code/src/cpp.rs

@@ -0,0 +1,883 @@
+//! `kebab-parse-code::cpp` — tree-sitter C++ AST extractor (P10-1D Task C).
+//!
+//! Implements [`kebab_core::Extractor`] for [`MediaType::Code("cpp")`].
+//! Walks the tree-sitter parse tree and emits one [`Block::Code`] per
+//! top-level AST semantic unit, each carrying [`SourceSpan::Code`] with
+//! the unit's `::` separated symbol path (design §3.4 C++ row).
+//!
+//! ## Symbol formation
+//!
+//! Symbol = `namespace::Class::method` via recursive `build_blocks`:
+//!
+//! - `namespace_definition` (named) → push namespace name, recurse into body.
+//! - Anonymous namespace (`namespace { ... }`) → push `<anonymous>`, recurse.
+//! - `nested_namespace_specifier` (`outer::inner`) → push all segments, recurse.
+//! - `class_specifier` / `struct_specifier` (named) → emit class unit + recurse
+//!   into body with class name pushed.
+//! - `function_definition` → emit method/function unit. Symbol is built from
+//!   the prefix chain + the extracted declarator name component.
+//! - Out-of-class method def (`void Foo::bar() {}`) — the declarator's inner
+//!   node is a `qualified_identifier`; its scope chain is prepended to the
+//!   current prefix to form the full symbol.
+//! - `template_declaration` → recurse into named children with same prefix;
+//!   the inner function/class body is matched by its own arm. Template params
+//!   are NOT included in the symbol.
+//! - `enum_specifier` (named) → emit type unit.
+//! - `concept_definition` (C++20) → emit type unit.
+//! - `linkage_specification` (extern "C") → recurse into body with same prefix.
+//!
+//! ## Constructor / destructor / operator overload
+//!
+//! - Constructor: `function_declarator > identifier` matching the class name.
+//!   Symbol = `Class::Class` (name duplicated, same convention as Java).
+//! - Destructor: `function_declarator > destructor_name`. Symbol = `Class::~Foo`.
+//! - Operator overload: `function_declarator > operator_name`. Symbol = `Class::operator+`.
+//! - Conversion operator: `function_definition.declarator` is `operator_cast`.
+//!   Symbol = `Class::operator <type>` (e.g. `Class::operator bool`).
+//!
+//! ## Glue
+//!
+//! Everything not in the unit list collapses into a single `<top-level>` glue
+//! chunk (preproc, declarations, using, typedef, etc.). If the file produces
+//! zero units AND zero glue, the `<module>` post-pass emits one unit covering
+//! the whole file.
+//!
+//! Per design §3.4 / §9.1 / §9 versioning.
+
+use anyhow::Result;
+use kebab_core::{
+    Block, CanonicalDocument, CodeBlock, CommonBlock, Extractor, Lang, MediaType, Metadata,
+    ParserVersion, Provenance, ProvenanceEvent, ProvenanceKind, SourceSpan, SourceType, TrustLevel,
+    id_for_block, id_for_doc,
+};
+use serde_json::Map;
+use time::OffsetDateTime;
+
+use crate::scaffold::{filename_from_workspace_path, strip_extension};
+
+pub const PARSER_VERSION: &str = "code-cpp-v1";
+
+/// C++ AST extractor. Per-unit blocks via tree-sitter-cpp 0.23.4
+/// (`LANGUAGE: LanguageFn`) parsed by tree-sitter 0.26.
+pub struct CppAstExtractor;
+
+impl CppAstExtractor {
+    pub fn new() -> Self {
+        Self
+    }
+}
+
+impl Default for CppAstExtractor {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl Extractor for CppAstExtractor {
+    fn supports(&self, m: &MediaType) -> bool {
+        matches!(m, MediaType::Code(l) if l == "cpp")
+    }
+
+    fn parser_version(&self) -> ParserVersion {
+        ParserVersion(PARSER_VERSION.to_string())
+    }
+
+    fn extract(
+        &self,
+        ctx: &kebab_core::ExtractContext<'_>,
+        bytes: &[u8],
+    ) -> Result<CanonicalDocument> {
+        let asset = ctx.asset;
+        if !self.supports(&asset.media_type) {
+            anyhow::bail!(
+                "kebab-parse-code: unsupported media_type for CppAstExtractor: {:?}",
+                asset.media_type
+            );
+        }
+
+        let parser_version = self.parser_version();
+        let doc_id = id_for_doc(&asset.workspace_path, &asset.asset_id, &parser_version);
+
+        let source = String::from_utf8(bytes.to_vec()).map_err(|e| {
+            anyhow::anyhow!("kebab-parse-code: C++ source is not valid UTF-8: {e}")
+        })?;
+
+        let blocks = build_blocks_top(&source, &doc_id)?;
+        let unit_count = blocks.len() as u32;
+
+        let now = OffsetDateTime::now_utc();
+        let mut events: Vec<ProvenanceEvent> = Vec::with_capacity(2);
+        events.push(ProvenanceEvent {
+            at: asset.discovered_at,
+            agent: "kb-source-fs".to_string(),
+            kind: ProvenanceKind::Discovered,
+            note: None,
+        });
+        events.push(ProvenanceEvent {
+            at: now,
+            agent: "kb-parse-code".to_string(),
+            kind: ProvenanceKind::Parsed,
+            note: Some(format!(
+                "parser_version={}; unit_count={}",
+                parser_version.0, unit_count
+            )),
+        });
+
+        let title = {
+            let fname = filename_from_workspace_path(&asset.workspace_path.0);
+            strip_extension(&fname)
+        };
+
+        let abs_path = match &asset.source_uri {
+            kebab_core::SourceUri::File(p) => {
+                if p.is_absolute() {
+                    p.clone()
+                } else {
+                    ctx.workspace_root.join(p)
+                }
+            }
+            kebab_core::SourceUri::Kb(_) => ctx.workspace_root.to_path_buf(),
+        };
+        let (repo, git_branch, git_commit) = match crate::repo::detect_repo(&abs_path) {
+            Some(r) => (Some(r.name), r.branch, r.commit),
+            None => (None, None, None),
+        };
+
+        let metadata = Metadata {
+            aliases: Vec::new(),
+            tags: Vec::new(),
+            created_at: asset.discovered_at,
+            updated_at: asset.discovered_at,
+            source_type: SourceType::Note,
+            trust_level: TrustLevel::Primary,
+            user_id_alias: None,
+            user: Map::new(),
+            repo,
+            git_branch,
+            git_commit,
+            code_lang: Some("cpp".to_string()),
+        };
+
+        tracing::debug!(
+            target: "kebab-parse-code",
+            "extracted C++ doc_id={} workspace_path={} units={}",
+            doc_id.0,
+            asset.workspace_path.0,
+            unit_count
+        );
+
+        Ok(CanonicalDocument {
+            doc_id,
+            source_asset_id: asset.asset_id.clone(),
+            workspace_path: asset.workspace_path.clone(),
+            title,
+            lang: Lang("und".to_string()),
+            blocks,
+            metadata,
+            provenance: Provenance { events },
+            parser_version,
+            schema_version: 1,
+            doc_version: 1,
+            last_chunker_version: None,
+            last_embedding_version: None,
+        })
+    }
+}
+
+// ---------------------------------------------------------------------------
+// Core block-building logic
+// ---------------------------------------------------------------------------
+
+/// Top-level entry: parse source, walk the `translation_unit` root, assemble
+/// units + glue, apply the `<module>` post-pass, and emit `Block::Code`s.
+fn build_blocks_top(
+    source: &str,
+    doc_id: &kebab_core::DocumentId,
+) -> anyhow::Result<Vec<kebab_core::Block>> {
+    let mut parser = tree_sitter::Parser::new();
+    parser
+        .set_language(&tree_sitter_cpp::LANGUAGE.into())
+        .map_err(|e| anyhow::anyhow!("set tree-sitter-cpp language: {e}"))?;
+    let tree = parser
+        .parse(source.as_bytes(), None)
+        .ok_or_else(|| anyhow::anyhow!("tree-sitter failed to parse C++ source"))?;
+    let lines: Vec<&str> = source.split('\n').collect();
+    let root = tree.root_node();
+
+    // units: (symbol, line_start, line_end, is_real_semantic_unit).
+    // Glue is accumulated as (start, end) pairs and flushed into one
+    // "<top-level>" block (or "<module>" if no real unit exists).
+    let mut units: Vec<(String, u32, u32, bool)> = Vec::new();
+    let mut glue: Vec<(u32, u32)> = Vec::new();
+
+    build_blocks(root, source, &[], &mut units, &mut glue);
+    flush_glue(&mut glue, &mut units);
+
+    // Post-pass: if the file has no real semantic unit (only glue, or
+    // completely empty), rename the single glue unit to "<module>".
+    // If there are zero units AND zero glue, synthesize a one-line
+    // "<module>" covering the whole file.
+    let has_real_unit = units.iter().any(|(_, _, _, is_real)| *is_real);
+
+    if units.is_empty() {
+        let total = lines.len() as u32;
+        units.push(("<module>".to_string(), 1, total.max(1), false));
+    }
+    if !has_real_unit {
+        for (sym, _, _, _) in units.iter_mut() {
+            if sym == "<top-level>" {
+                *sym = "<module>".to_string();
+            }
+        }
+    }
+
+    let total_lines = lines.len() as u32;
+    let mut blocks = Vec::with_capacity(units.len());
+    for (ordinal, (symbol, ls, le, _is_real)) in units.into_iter().enumerate() {
+        let line_start = ls.max(1);
+        let line_end = le.min(total_lines.max(1));
+        let span = SourceSpan::Code {
+            line_start,
+            line_end,
+            symbol: Some(symbol),
+            lang: Some("cpp".to_string()),
+        };
+        let block_id = id_for_block(doc_id, "code", &[], ordinal as u32, &span);
+        let code = lines[(line_start as usize - 1)..=(line_end as usize - 1)].join("\n");
+        blocks.push(Block::Code(CodeBlock {
+            common: CommonBlock {
+                block_id,
+                heading_path: Vec::new(),
+                source_span: span,
+            },
+            lang: Some("cpp".to_string()),
+            code,
+        }));
+    }
+    Ok(blocks)
+}
+
+/// Walk preceding `comment` siblings to extend the unit's line range upward,
+/// folding leading doc / line comments into the unit (1B pattern).
+fn unit_start(n: &tree_sitter::Node) -> u32 {
+    let mut start = n.start_position().row as u32 + 1;
+    let mut prev = n.prev_sibling();
+    while let Some(p) = prev {
+        if p.kind() == "comment" {
+            start = p.start_position().row as u32 + 1;
+            prev = p.prev_sibling();
+        } else {
+            break;
+        }
+    }
+    start
+}
+
+fn flush_glue(glue: &mut Vec<(u32, u32)>, units: &mut Vec<(String, u32, u32, bool)>) {
+    if glue.is_empty() {
+        return;
+    }
+    let s = glue.iter().map(|(a, _)| *a).min().unwrap();
+    let e = glue.iter().map(|(_, b)| *b).max().unwrap();
+    units.push(("<top-level>".to_string(), s, e, false));
+    glue.clear();
+}
+
+/// Walk a scope node (translation_unit, declaration_list, field_declaration_list)
+/// emitting unit + glue blocks. `prefix` is the current namespace/class chain
+/// (e.g. `["kebab", "Chunk", "Foo"]`).
+///
+/// After returning, any pending glue in `glue` is NOT flushed — callers
+/// responsible for flushing at the scope boundary (top-level flush in
+/// `build_blocks_top`). Within recursive scope bodies (namespace/class) we
+/// do flush before returning so that glue doesn't leak across scopes.
+fn build_blocks(
+    node: tree_sitter::Node,
+    source: &str,
+    prefix: &[String],
+    units: &mut Vec<(String, u32, u32, bool)>,
+    glue: &mut Vec<(u32, u32)>,
+) {
+    let mut cur = node.walk();
+    for child in node.named_children(&mut cur) {
+        let s = unit_start(&child);
+        let e = child.end_position().row as u32 + 1;
+
+        match child.kind() {
+            "namespace_definition" => {
+                // Flush pending glue before starting this namespace block.
+                flush_glue(glue, units);
+
+                let name_node = child.child_by_field_name("name");
+                let body = child
+                    .child_by_field_name("body")
+                    .unwrap_or(child);
+
+                match name_node {
+                    None => {
+                        // Anonymous namespace: push "<anonymous>", recurse.
+                        let mut new_prefix = prefix.to_vec();
+                        new_prefix.push("<anonymous>".to_string());
+                        build_blocks(body, source, &new_prefix, units, glue);
+                        flush_glue(glue, units);
+                    }
+                    Some(nn) => match nn.kind() {
+                        "namespace_identifier" => {
+                            let name = &source[nn.start_byte()..nn.end_byte()];
+                            let mut new_prefix = prefix.to_vec();
+                            new_prefix.push(name.to_string());
+                            build_blocks(body, source, &new_prefix, units, glue);
+                            flush_glue(glue, units);
+                        }
+                        "nested_namespace_specifier" => {
+                            // e.g. `namespace outer::inner { ... }`
+                            // All named children are namespace_identifier nodes.
+                            let mut new_prefix = prefix.to_vec();
+                            let mut nc = nn.walk();
+                            for seg in nn.named_children(&mut nc) {
+                                new_prefix.push(source[seg.start_byte()..seg.end_byte()].to_string());
+                            }
+                            build_blocks(body, source, &new_prefix, units, glue);
+                            flush_glue(glue, units);
+                        }
+                        _ => {
+                            // Unknown name kind — treat entire namespace as glue.
+                            glue.push((s, e));
+                        }
+                    },
+                }
+            }
+
+            "class_specifier" | "struct_specifier" => {
+                let name_node = child.child_by_field_name("name");
+                let Some(nn) = name_node else {
+                    // Anonymous class/struct — glue.
+                    glue.push((s, e));
+                    continue;
+                };
+                let name = match nn.kind() {
+                    "type_identifier" => &source[nn.start_byte()..nn.end_byte()],
+                    _ => {
+                        // template_type or qualified_identifier — use full text
+                        // as the symbol segment (includes template args).
+                        &source[nn.start_byte()..nn.end_byte()]
+                    }
+                };
+
+                flush_glue(glue, units);
+                let sym = build_symbol(prefix, &[name]);
+                units.push((sym, s, e, true));
+
+                if let Some(body) = child.child_by_field_name("body") {
+                    let mut new_prefix = prefix.to_vec();
+                    new_prefix.push(name.to_string());
+                    build_blocks(body, source, &new_prefix, units, glue);
+                    flush_glue(glue, units);
+                }
+            }
+
+            "function_definition" => {
+                let decl = child.child_by_field_name("declarator");
+                let Some(decl_node) = decl else {
+                    glue.push((s, e));
+                    continue;
+                };
+
+                match extract_fn_symbol(decl_node, source, prefix) {
+                    Some(sym) => {
+                        flush_glue(glue, units);
+                        units.push((sym, s, e, true));
+                    }
+                    None => {
+                        glue.push((s, e));
+                    }
+                }
+            }
+
+            "template_declaration" => {
+                // Unwrap: recurse into named children with same prefix.
+                // The inner function/class/concept will be matched by their own
+                // arms. template_parameter_list is not a unit; it will fall
+                // through to glue (it's not a named child of the template_declaration
+                // that matches any of our arms).
+                build_blocks(child, source, prefix, units, glue);
+                // Do NOT flush glue here — template body may be part of a glue group.
+            }
+
+            "enum_specifier" => {
+                if let Some(nn) = child.child_by_field_name("name") {
+                    let name = &source[nn.start_byte()..nn.end_byte()];
+                    flush_glue(glue, units);
+                    let sym = build_symbol(prefix, &[name]);
+                    units.push((sym, s, e, true));
+                } else {
+                    // Anonymous enum — glue.
+                    glue.push((s, e));
+                }
+            }
+
+            "concept_definition" => {
+                // C++20. Has required "name" field (identifier).
+                if let Some(nn) = child.child_by_field_name("name") {
+                    let name = &source[nn.start_byte()..nn.end_byte()];
+                    flush_glue(glue, units);
+                    let sym = build_symbol(prefix, &[name]);
+                    units.push((sym, s, e, true));
+                } else {
+                    glue.push((s, e));
+                }
+            }
+
+            "linkage_specification" => {
+                // extern "C" { ... } — glue-wrapper, but recurse into body
+                // with same prefix so inner definitions are extracted.
+                let body = child.child_by_field_name("body").unwrap_or(child);
+                // The linkage_spec itself is glue; inner defs handled by recursion.
+                // Don't emit the wrapper as a unit; but also don't push it as glue
+                // since recursion will push its inner children individually.
+                build_blocks(body, source, prefix, units, glue);
+            }
+
+            // Everything else: preproc, declarations, using, typedef, etc.
+            _ => {
+                glue.push((s, e));
+            }
+        }
+    }
+}
+
+/// Join prefix + extras into a `::` separated symbol.
+fn build_symbol(prefix: &[String], extras: &[&str]) -> String {
+    let mut parts: Vec<&str> = prefix.iter().map(String::as_str).collect();
+    parts.extend_from_slice(extras);
+    parts.join("::")
+}
+
+/// Extract the symbol for a `function_definition` given its top-level
+/// `declarator` node. Returns `None` if the name cannot be determined.
+///
+/// The declarator chain may be:
+/// - `function_declarator` (plain fn or method)
+/// - `pointer_declarator` wrapping `function_declarator` (fn returning pointer)
+/// - `reference_declarator` wrapping `function_declarator` (fn returning ref)
+/// - `operator_cast` (conversion operator — e.g. `operator bool`)
+///
+/// The inner `function_declarator.declarator` is one of:
+/// - `identifier` → free fn or constructor, symbol = `prefix::name`
+/// - `field_identifier` → method in class body, symbol = `prefix::name`
+/// - `destructor_name` → `~Foo`, symbol = `prefix::~Foo`
+/// - `operator_name` → `operator+` etc., symbol = `prefix::operator+`
+/// - `qualified_identifier` → out-of-class def `Foo::bar` or `ns::Foo::bar`;
+///   the scope chain is extracted and prepended to prefix.
+///
+/// For `qualified_identifier`, the scope hierarchy (which may itself be a
+/// `qualified_identifier`) is flattened into a list of segments. These
+/// segments REPLACE the current prefix (since out-of-class defs carry their
+/// full scope explicitly). Example: `void ns::Foo::bar() {}` at top level
+/// with prefix=[] → segments=[ns, Foo, bar] → symbol = `ns::Foo::bar`.
+fn extract_fn_symbol(
+    decl_node: tree_sitter::Node,
+    source: &str,
+    prefix: &[String],
+) -> Option<String> {
+    // Walk down pointer/reference wrapper layers to reach the
+    // function_declarator (or operator_cast at definition level).
+    let fn_decl = unwrap_to_fn_declarator(decl_node, source)?;
+
+    match fn_decl.kind() {
+        "operator_cast" => {
+            // e.g. `operator bool() const` — the function_definition.declarator
+            // IS the operator_cast (no function_declarator wrapper).
+            // Symbol = `prefix::operator <type>`.
+            let type_node = fn_decl.child_by_field_name("type")?;
+            let type_text = &source[type_node.start_byte()..type_node.end_byte()];
+            Some(build_symbol(prefix, &[&format!("operator {type_text}")]))
+        }
+        "function_declarator" => {
+            let inner = fn_decl.child_by_field_name("declarator")?;
+            extract_name_node(inner, source, prefix)
+        }
+        _ => None,
+    }
+}
+
+/// Walk pointer_declarator / reference_declarator chains down to the
+/// first `function_declarator` or `operator_cast` node.
+///
+/// Returns `None` if no such node is found (e.g. a function definition
+/// whose declarator is malformed or unknown).
+fn unwrap_to_fn_declarator<'a>(
+    mut node: tree_sitter::Node<'a>,
+    _source: &str,
+) -> Option<tree_sitter::Node<'a>> {
+    loop {
+        match node.kind() {
+            "function_declarator" | "operator_cast" => return Some(node),
+            "pointer_declarator" => {
+                node = node.child_by_field_name("declarator")?;
+            }
+            "reference_declarator" | "rvalue_reference_declarator" => {
+                // reference_declarator has no `declarator` field; its child
+                // is in the unnamed children list.
+                let mut walker = node.walk();
+                node = node.named_children(&mut walker).next()?;
+            }
+            _ => return None,
+        }
+    }
+}
+
+/// Given the innermost name node of a function_declarator, produce the symbol.
+fn extract_name_node(
+    inner: tree_sitter::Node,
+    source: &str,
+    prefix: &[String],
+) -> Option<String> {
+    match inner.kind() {
+        "identifier" | "field_identifier" => {
+            let name = &source[inner.start_byte()..inner.end_byte()];
+            Some(build_symbol(prefix, &[name]))
+        }
+        "destructor_name" => {
+            // destructor_name text includes the `~` prefix (e.g. "~Foo").
+            let full = &source[inner.start_byte()..inner.end_byte()];
+            Some(build_symbol(prefix, &[full]))
+        }
+        "operator_name" => {
+            // Full text e.g. "operator+", "operator->", "operator()".
+            let full = &source[inner.start_byte()..inner.end_byte()];
+            Some(build_symbol(prefix, &[full]))
+        }
+        "template_function" | "template_method" => {
+            // Template function like `foo<int>()`. Use the `name` field
+            // (the identifier / field_identifier before `<`).
+            let name_node = inner.child_by_field_name("name")?;
+            let name = &source[name_node.start_byte()..name_node.end_byte()];
+            Some(build_symbol(prefix, &[name]))
+        }
+        "qualified_identifier" => {
+            // Out-of-class method definition. Flatten the nested
+            // qualified_identifier chain into ordered segments.
+            // Example: `ns::Foo::method`
+            //   qualified_identifier {
+            //     scope: namespace_identifier "ns"
+            //     name: qualified_identifier {
+            //       scope: namespace_identifier "Foo"
+            //       name: identifier "method"
+            //     }
+            //   }
+            // → ["ns", "Foo", "method"]
+            //
+            // These segments are combined with the current prefix so that a
+            // top-level out-of-class def `void Foo::bar() {}` inside a
+            // namespace body with prefix=["ns"] produces `ns::Foo::bar`.
+            let mut segments: Vec<String> = Vec::new();
+            flatten_qualified_id(inner, source, &mut segments);
+            if segments.is_empty() {
+                return None;
+            }
+            // Build: prefix + all segments (scope chain + leaf).
+            let mut all: Vec<&str> = prefix.iter().map(String::as_str).collect();
+            for seg in &segments {
+                all.push(seg.as_str());
+            }
+            Some(all.join("::"))
+        }
+        _ => None,
+    }
+}
+
+/// Recursively flatten a `qualified_identifier` node into ordered string
+/// segments. For `ns::Foo::method` this produces `["ns", "Foo", "method"]`.
+fn flatten_qualified_id(node: tree_sitter::Node, source: &str, out: &mut Vec<String>) {
+    // A qualified_identifier has:
+    //   scope: namespace_identifier | (None for global-scope `::foo`)
+    //   name:  identifier | field_identifier | destructor_name |
+    //          operator_name | qualified_identifier | template_function |
+    //          template_method | ...
+    let scope_node = node.child_by_field_name("scope");
+    let name_node = node.child_by_field_name("name");
+
+    if let Some(s) = scope_node {
+        out.push(source[s.start_byte()..s.end_byte()].to_string());
+    }
+
+    match name_node {
+        Some(n) if n.kind() == "qualified_identifier" => {
+            // Recurse: more nesting.
+            flatten_qualified_id(n, source, out);
+        }
+        Some(n) => {
+            // Leaf name — push its text.
+            out.push(source[n.start_byte()..n.end_byte()].to_string());
+        }
+        None => {}
+    }
+}
+
+// ---------------------------------------------------------------------------
+// Tests
+// ---------------------------------------------------------------------------
+
+#[cfg(test)]
+pub(crate) mod tests_support {
+    use kebab_core::*;
+    use std::path::PathBuf;
+    use time::OffsetDateTime;
+
+    pub fn fixed_code_asset(workspace_path: &str, lang: &str) -> RawAsset {
+        RawAsset {
+            asset_id: AssetId("a".repeat(64)),
+            source_uri: SourceUri::File(PathBuf::from(workspace_path)),
+            workspace_path: WorkspacePath(workspace_path.to_string()),
+            media_type: MediaType::Code(lang.to_string()),
+            byte_len: 0,
+            checksum: Checksum("b".repeat(64)),
+            discovered_at: OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
+            stored: AssetStorage::Reference {
+                path: PathBuf::from(workspace_path),
+                sha: Checksum("b".repeat(64)),
+            },
+        }
+    }
+
+    pub fn extract_cpp(src: &str, path: &str) -> kebab_core::CanonicalDocument {
+        use super::CppAstExtractor;
+        use kebab_core::Extractor;
+        let asset = fixed_code_asset(path, "cpp");
+        let cfg = ExtractConfig::default();
+        let root = PathBuf::from("/tmp");
+        let ctx = ExtractContext {
+            asset: &asset,
+            workspace_root: &root,
+            config: &cfg,
+        };
+        CppAstExtractor::new().extract(&ctx, src.as_bytes()).unwrap()
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use kebab_core::{Block, MediaType, SourceSpan};
+
+    fn syms(doc: &kebab_core::CanonicalDocument) -> Vec<String> {
+        let mut s: Vec<String> = doc
+            .blocks
+            .iter()
+            .filter_map(|b| match b {
+                Block::Code(c) => match &c.common.source_span {
+                    SourceSpan::Code { symbol, .. } => symbol.clone(),
+                    _ => None,
+                },
+                _ => None,
+            })
+            .collect();
+        s.sort();
+        s
+    }
+
+    #[test]
+    fn extractor_supports_only_media_code_cpp() {
+        let e = CppAstExtractor::new();
+        assert!(e.supports(&MediaType::Code("cpp".into())));
+        assert!(!e.supports(&MediaType::Code("c".into())));
+        assert!(!e.supports(&MediaType::Code("rust".into())));
+        assert!(!e.supports(&MediaType::Markdown));
+    }
+
+    #[test]
+    fn free_function() {
+        let src = "void foo() {}\n";
+        let doc = tests_support::extract_cpp(src, "x/foo.cpp");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "foo"), "got {s:?}");
+    }
+
+    #[test]
+    fn namespace_and_class() {
+        let src = r#"
+namespace ns {
+    class Foo {
+    public:
+        void method() {}
+        Foo() {}
+        ~Foo() {}
+        int operator+(const Foo& o) { return 0; }
+    };
+}
+"#;
+        let doc = tests_support::extract_cpp(src, "x/foo.cpp");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "ns::Foo"), "ns::Foo missing: {s:?}");
+        assert!(s.iter().any(|x| x == "ns::Foo::method"), "method missing: {s:?}");
+        assert!(s.iter().any(|x| x == "ns::Foo::Foo"), "ctor missing: {s:?}");
+        assert!(s.iter().any(|x| x == "ns::Foo::~Foo"), "dtor missing: {s:?}");
+        assert!(s.iter().any(|x| x == "ns::Foo::operator+"), "op+ missing: {s:?}");
+    }
+
+    #[test]
+    fn anonymous_namespace() {
+        let src = r#"
+namespace {
+    void hidden_fn() {}
+}
+"#;
+        let doc = tests_support::extract_cpp(src, "x/foo.cpp");
+        let s = syms(&doc);
+        assert!(
+            s.iter().any(|x| x == "<anonymous>::hidden_fn"),
+            "anon fn missing: {s:?}"
+        );
+    }
+
+    #[test]
+    fn nested_namespace_specifier() {
+        let src = r#"
+namespace outer::inner {
+    void fn_in_nested() {}
+}
+"#;
+        let doc = tests_support::extract_cpp(src, "x/foo.cpp");
+        let s = syms(&doc);
+        assert!(
+            s.iter().any(|x| x == "outer::inner::fn_in_nested"),
+            "nested ns fn missing: {s:?}"
+        );
+    }
+
+    #[test]
+    fn out_of_class_method_def() {
+        let src = r#"
+void ns::Foo::method() { }
+"#;
+        let doc = tests_support::extract_cpp(src, "x/foo.cpp");
+        let s = syms(&doc);
+        assert!(
+            s.iter().any(|x| x == "ns::Foo::method"),
+            "out-of-class method missing: {s:?}"
+        );
+    }
+
+    #[test]
+    fn template_declaration() {
+        let src = r#"
+template<typename T>
+class Bar {
+    void tmpl_method() {}
+};
+
+template<typename T>
+void tmpl_free_fn(T x) {}
+"#;
+        let doc = tests_support::extract_cpp(src, "x/foo.cpp");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "Bar"), "Bar class missing: {s:?}");
+        assert!(
+            s.iter().any(|x| x == "Bar::tmpl_method"),
+            "Bar::tmpl_method missing: {s:?}"
+        );
+        assert!(
+            s.iter().any(|x| x == "tmpl_free_fn"),
+            "tmpl_free_fn missing: {s:?}"
+        );
+    }
+
+    #[test]
+    fn enum_and_concept() {
+        let src = r#"
+enum class Color { Red, Green };
+
+template<typename T>
+concept Printable = requires(T t) { t.print(); };
+"#;
+        let doc = tests_support::extract_cpp(src, "x/foo.cpp");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "Color"), "Color missing: {s:?}");
+        assert!(s.iter().any(|x| x == "Printable"), "Printable missing: {s:?}");
+    }
+
+    #[test]
+    fn extern_c_block() {
+        let src = r#"
+extern "C" {
+    void c_fn1() {}
+    void c_fn2() {}
+}
+"#;
+        let doc = tests_support::extract_cpp(src, "x/foo.cpp");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "c_fn1"), "c_fn1 missing: {s:?}");
+        assert!(s.iter().any(|x| x == "c_fn2"), "c_fn2 missing: {s:?}");
+    }
+
+    #[test]
+    fn conversion_operator() {
+        let src = r#"
+class Foo {
+    operator bool() const { return true; }
+};
+"#;
+        let doc = tests_support::extract_cpp(src, "x/foo.cpp");
+        let s = syms(&doc);
+        assert!(
+            s.iter().any(|x| x == "Foo::operator bool"),
+            "conversion op missing: {s:?}"
+        );
+    }
+
+    #[test]
+    fn empty_file_produces_module() {
+        let src = "";
+        let doc = tests_support::extract_cpp(src, "x/empty.cpp");
+        let s = syms(&doc);
+        assert_eq!(s, vec!["<module>"], "expected <module>: got {s:?}");
+    }
+
+    #[test]
+    fn glue_only_produces_module() {
+        let src = "#include <vector>\nusing namespace std;\n";
+        let doc = tests_support::extract_cpp(src, "x/glue.cpp");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "<module>"), "expected <module>: got {s:?}");
+    }
+
+    #[test]
+    fn ptr_returning_function() {
+        let src = "int* ptr_fn(int x) { return &x; }\n";
+        let doc = tests_support::extract_cpp(src, "x/foo.cpp");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "ptr_fn"), "ptr_fn missing: {s:?}");
+    }
+
+    #[test]
+    fn ref_returning_operator() {
+        let src = r#"
+class Foo {
+    Foo& operator=(const Foo& o) { return *this; }
+};
+"#;
+        let doc = tests_support::extract_cpp(src, "x/foo.cpp");
+        let s = syms(&doc);
+        assert!(
+            s.iter().any(|x| x == "Foo::operator="),
+            "operator= missing: {s:?}"
+        );
+    }
+
+    #[test]
+    fn deterministic_across_runs() {
+        let src = r#"
+namespace ns {
+    class Foo {
+        void method() {}
+    };
+}
+void free_fn() {}
+"#;
+        let a = tests_support::extract_cpp(src, "x/foo.cpp");
+        for _ in 0..20 {
+            assert_eq!(tests_support::extract_cpp(src, "x/foo.cpp").blocks, a.blocks);
+        }
+    }
+}

crates/kebab-parse-code/src/lib.rs

@@ -13,6 +13,8 @@
 //! `kebab-parse-*` crates per design §8: must NOT depend on store / embed
 //! / llm / rag.
 
+pub mod c;
+pub mod cpp;
 pub mod go;
 pub mod java;
 pub mod javascript;
@@ -25,6 +27,8 @@ pub(crate) mod scaffold;
 pub mod skip;
 pub mod typescript;
 
+pub use c::{PARSER_VERSION as C_PARSER_VERSION, CAstExtractor};
+pub use cpp::{PARSER_VERSION as CPP_PARSER_VERSION, CppAstExtractor};
 pub use go::{PARSER_VERSION as GO_PARSER_VERSION, GoAstExtractor};
 pub use java::{PARSER_VERSION as JAVA_PARSER_VERSION, JavaAstExtractor};
 pub use javascript::{PARSER_VERSION as JS_PARSER_VERSION, JavascriptAstExtractor};

crates/kebab-search/src/lexical.rs

@@ -162,18 +162,35 @@ impl Retriever for LexicalRetriever {
 
 /// Translate a user-typed query into an FTS5 match string.
 ///
-/// Rules (from the task spec):
+/// v0.17.0 — trigram-aware redesign (see design §5.5 + plan
+/// `docs/superpowers/plans/2026-05-22-korean-trigram-tokenizer.md`
+/// Task A5). The FTS5 tokenizer is `trigram` so any term shorter than
+/// three Unicode chars has no index entry and would zero out an AND
+/// branch. Korean compounds typically split into 2-char eojeols (e.g.
+/// `해시 충돌`), so a naive token AND drops the dominant usage pattern.
 ///
-/// - The query is wrapped in a single pair of `'...'` → strip the quotes
-///   and pass the inner text through verbatim. The user has explicitly
-///   opted into FTS5 syntax (e.g. `'rust AND cargo'`, `'foo*'`).
+/// Rules:
 ///
-/// - Otherwise: split on whitespace, escape every token by wrapping it
-///   in `"..."` (FTS5 string literal), with any inner `"` doubled. Join
-///   with spaces — FTS5 default operator is implicit AND.
+/// - Raw mode (unchanged): the query is wrapped in a single pair of
+///   `'...'` → strip the quotes and pass the inner text through verbatim.
+///   The user has explicitly opted into FTS5 syntax (e.g.
+///   `'rust AND cargo'`, `'foo*'`).
 ///
-/// - An empty / whitespace-only token list → return `None` (caller
-///   short-circuits to `Ok(vec![])`).
+/// - Otherwise build up to two MATCH candidates:
+///   1. **whole-phrase**: the entire trimmed input wrapped as one FTS5
+///      string literal, *only* if it has ≥3 Unicode chars. FTS5 treats
+///      a quoted string with spaces as a phrase match.
+///   2. **token AND**: whitespace-split tokens, kept only when each has
+///      ≥3 Unicode chars (shorter ones are dropped — they would zero
+///      out the AND under trigram).
+///
+/// - Combine: `(whole) OR (token_and)` when both exist *and differ*;
+///   either alone when only one exists; `None` when neither exists
+///   (caller short-circuits to `Ok(vec![])`, avoiding an FTS5 syntax
+///   error from an empty MATCH).
+///
+/// - A single-token long query (`러스트`, `foo`) yields `whole == token_and`
+///   → return the bare quoted form so the OR doesn't duplicate.
 fn build_match_string(text: &str) -> Option<String> {
     let trimmed = text.trim();
     if trimmed.is_empty() {
@@ -186,14 +203,27 @@ fn build_match_string(text: &str) -> Option<String> {
         }
         return Some(inner_trim.to_string());
     }
-    let tokens: Vec<String> = trimmed
-        .split_whitespace()
-        .map(escape_fts5_token)
-        .collect();
-    if tokens.is_empty() {
-        None
-    } else {
-        Some(tokens.join(" "))
+
+    const MIN_TRIGRAM_CHARS: usize = 3;
+
+    let whole_candidate: Option<String> = (trimmed.chars().count() >= MIN_TRIGRAM_CHARS)
+        .then(|| escape_fts5_token(trimmed));
+
+    let token_and_candidate: Option<String> = {
+        let toks: Vec<String> = trimmed
+            .split_whitespace()
+            .filter(|t| t.chars().count() >= MIN_TRIGRAM_CHARS)
+            .map(escape_fts5_token)
+            .collect();
+        (!toks.is_empty()).then(|| toks.join(" "))
+    };
+
+    match (whole_candidate, token_and_candidate) {
+        (None, None) => None,
+        (Some(w), None) => Some(w),
+        (None, Some(a)) => Some(a),
+        (Some(w), Some(a)) if w == a => Some(w),
+        (Some(w), Some(a)) => Some(format!("({w}) OR ({a})")),
     }
 }
 
@@ -555,30 +585,31 @@ mod tests {
     }
 
     #[test]
-    fn build_match_string_default_is_quoted_and_anded() {
+    fn build_match_string_default_emits_or_of_phrase_and_and() {
+        // Two long tokens: both whole-phrase and token-AND candidates
+        // exist and differ, so the builder combines them with OR.
         let s = build_match_string("rust cargo").unwrap();
-        // Two tokens, each quoted, joined by a space (implicit AND).
-        assert_eq!(s, r#""rust" "cargo""#);
+        assert_eq!(s, r#"("rust cargo") OR ("rust" "cargo")"#);
     }
 
     #[test]
     fn build_match_string_escapes_special_chars() {
         // `*`, `(`, `)`, `:`, `^`, `"` should all be wrapped inside
         // FTS5 string-literal quotes so they're treated as literal
-        // text rather than FTS5 operators.
+        // text rather than FTS5 operators. Every token is ≥3 chars,
+        // so both the whole-phrase and token-AND candidates exist.
         let s = build_match_string(r#"foo* (bar) baz:qux ^head he"llo"#).unwrap();
         assert_eq!(
             s,
-            r#""foo*" "(bar)" "baz:qux" "^head" "he""llo""#
+            r#"("foo* (bar) baz:qux ^head he""llo") OR ("foo*" "(bar)" "baz:qux" "^head" "he""llo")"#
         );
         // The doubled `""` is FTS5's way of embedding a literal quote
-        // inside a string literal.
+        // inside a string literal. Appears in both whole-phrase and
+        // token-AND halves.
         assert!(s.contains(r#"he""llo"#));
-        // Sanity: every special character lives between matching `"`
-        // delimiters — there is no bare-token (unquoted) span anywhere.
-        // We check this by confirming the string starts and ends with `"`
-        // and the count of unescaped `"` is even (each token is wrapped).
-        assert!(s.starts_with('"') && s.ends_with('"'));
+        // Sanity: the combined expression is `(...) OR (...)` so it
+        // starts with `(` and ends with `)`.
+        assert!(s.starts_with('(') && s.ends_with(')'));
     }
 
     #[test]
@@ -588,6 +619,55 @@ mod tests {
         assert_eq!(s, "foo OR bar*");
     }
 
+    // ── v0.17.0 trigram-aware redesign coverage ──────────────────────────
+
+    /// 2-char Korean query (`충돌`) yields neither a whole-phrase nor a
+    /// token-AND candidate → `None`. Caller short-circuits to an empty
+    /// hit list rather than executing an FTS5 syntax error on `""` MATCH.
+    #[test]
+    fn build_match_string_short_korean_returns_none() {
+        assert!(build_match_string("충돌").is_none());
+        assert!(build_match_string("키").is_none());
+        assert!(build_match_string(" 충돌 ").is_none());
+    }
+
+    /// `해시 충돌` — both tokens are 2 chars (dropped from the AND), but
+    /// the whole-phrase candidate (`"해시 충돌"`, 5 chars total) survives.
+    /// This is the dominant Korean usage pattern targeted by A5.
+    #[test]
+    fn build_match_string_whole_phrase_only_when_all_tokens_short() {
+        let s = build_match_string("해시 충돌").unwrap();
+        assert_eq!(s, r#""해시 충돌""#);
+    }
+
+    /// Single long token: whole-phrase and token-AND candidates collapse
+    /// to the same string. The builder returns the bare quoted form so
+    /// the MATCH expression doesn't carry a redundant `(x) OR (x)`.
+    #[test]
+    fn build_match_string_single_long_token_no_duplicate_or() {
+        assert_eq!(build_match_string("러스트").unwrap(), r#""러스트""#);
+        assert_eq!(build_match_string("rust").unwrap(), r#""rust""#);
+    }
+
+    /// Mixed Korean+English multi-token query where every token is ≥3
+    /// chars: both candidates exist and differ, OR-combined.
+    #[test]
+    fn build_match_string_mixed_lang_emits_or_of_phrase_and_and() {
+        let s = build_match_string("Rust 충돌은").unwrap();
+        assert_eq!(s, r#"("Rust 충돌은") OR ("Rust" "충돌은")"#);
+    }
+
+    /// One ≥3 token + one <3 token: short token is dropped from the
+    /// AND, leaving a single long token there; whole-phrase exists
+    /// independently. Both candidates differ → OR-combined.
+    #[test]
+    fn build_match_string_drops_short_token_in_and_keeps_whole() {
+        // "키" (1 char) dropped from AND; "해시테이블" (5 chars) kept.
+        // Whole phrase "키 해시테이블" (7 chars) keeps the short token.
+        let s = build_match_string("키 해시테이블").unwrap();
+        assert_eq!(s, r#"("키 해시테이블") OR ("해시테이블")"#);
+    }
+
     #[test]
     fn normalize_bm25_top_score_in_unit_interval() {
         // A "perfect" hit is bm25 = -1.0 → normalized 0.5.

crates/kebab-search/tests/fixtures/search/lexical/run-1.json

@@ -19,9 +19,9 @@
     "indexed_at": "2024-01-01T00:00:00Z",
     "rank": 1,
     "retrieval": {
-      "fusion_score": 1.4490997273242101e-6,
+      "fusion_score": 1.4615362715630908e-6,
       "lexical_rank": 1,
-      "lexical_score": 1.4490997273242101e-6,
+      "lexical_score": 1.4615362715630908e-6,
       "method": "lexical",
       "vector_rank": null,
       "vector_score": null
@@ -51,9 +51,9 @@
     "indexed_at": "2024-01-01T00:00:00Z",
     "rank": 2,
     "retrieval": {
-      "fusion_score": 9.641424867368187e-7,
+      "fusion_score": 9.207039965986041e-7,
       "lexical_rank": 2,
-      "lexical_score": 9.641424867368187e-7,
+      "lexical_score": 9.207039965986041e-7,
       "method": "lexical",
       "vector_rank": null,
       "vector_score": null

crates/kebab-store-sqlite/src/store.rs

@@ -464,6 +464,74 @@ impl SqliteStore {
         }
         Ok(out)
     }
+
+    /// v0.17.0 PR-B: sister of [`Self::stale_chunk_ids_at`] for the
+    /// `parser_version` bump cascade. When `doc_id` depends on
+    /// `parser_version` (design §9) and an extractor ships a new
+    /// `PARSER_VERSION`, the next ingest computes a fresh `doc_id` for
+    /// the *same* `(workspace_path, asset_id)` pair. The existing
+    /// asset_id-keyed [`Self::stale_chunk_ids_at`] does NOT fire (same
+    /// asset), so the legacy `chunks` rows and their LanceDB shadows
+    /// would orphan. This helper queries by `workspace_path` instead,
+    /// excluding the freshly-computed `keep_doc_id` so a re-entry
+    /// during the same ingest doesn't re-sweep the new row.
+    ///
+    /// Caller usage: pass the *new* `doc_id` if known; pass an empty
+    /// string when called before the new INSERT (the case in
+    /// `try_skip_unchanged`) — all existing docs at `workspace_path`
+    /// are then collected as stale.
+    pub fn stale_chunk_ids_for_workspace_path_except_doc_id(
+        &self,
+        workspace_path: &str,
+        keep_doc_id: &str,
+    ) -> Result<Vec<kebab_core::ChunkId>> {
+        let conn = self.lock_conn();
+        let mut stmt = conn
+            .prepare(
+                "SELECT c.chunk_id
+                 FROM chunks c
+                 INNER JOIN documents d ON c.doc_id = d.doc_id
+                 WHERE d.workspace_path = ?1 AND d.doc_id != ?2",
+            )
+            .map_err(StoreError::from)?;
+        let rows = stmt
+            .query_map(params![workspace_path, keep_doc_id], |row| {
+                row.get::<_, String>(0)
+            })
+            .map_err(StoreError::from)?;
+        let mut out: Vec<kebab_core::ChunkId> = Vec::new();
+        for row in rows {
+            let id = row.map_err(StoreError::from)?;
+            out.push(kebab_core::ChunkId(id));
+        }
+        Ok(out)
+    }
+
+    /// v0.17.0 PR-B: sweep the SQLite document chain (`documents` →
+    /// `blocks` / `chunks` / `embedding_records` via CASCADE) for every
+    /// row at `workspace_path` whose `doc_id` differs from `keep_doc_id`.
+    /// Pair with [`Self::stale_chunk_ids_for_workspace_path_except_doc_id`]
+    /// — caller fetches the chunk_ids first, hands them to
+    /// `VectorStore::delete_by_chunk_ids`, then calls this sweep.
+    /// `assets` row is preserved (same bytes, same asset_id — only the
+    /// derived `doc_id` changed).
+    ///
+    /// `keep_doc_id = ""` deletes every doc at `workspace_path`
+    /// (semantics mirror the sister helper above — used by
+    /// `try_skip_unchanged` before the new INSERT exists).
+    pub fn purge_document_at_workspace_path_except_doc_id(
+        &self,
+        workspace_path: &str,
+        keep_doc_id: &str,
+    ) -> Result<()> {
+        let conn = self.lock_conn();
+        conn.execute(
+            "DELETE FROM documents WHERE workspace_path = ?1 AND doc_id != ?2",
+            params![workspace_path, keep_doc_id],
+        )
+        .map_err(StoreError::from)?;
+        Ok(())
+    }
 }
 
 /// Sweep stale `assets` + `documents` + downstream rows when the file
@@ -824,6 +892,45 @@ impl SqliteStore {
         Ok(out)
     }
 
+    /// v0.17.0 PR-C: per-code-language **chunk** count for
+    /// `schema.v1.stats`. Companion to [`Self::code_lang_breakdown`] —
+    /// that one returns *document* counts. Stats observers wanting
+    /// indexing-pressure granularity (a single PDF spec → 200 chunks,
+    /// vs a single Rust file → 5 chunks) need the chunk-level view.
+    ///
+    /// SQL joins `chunks → documents`, reads
+    /// `metadata_json->'$.code_lang'` on the doc side, groups by the
+    /// language, and skips rows where `code_lang IS NULL`. Returns
+    /// `BTreeMap<String, u32>` mirroring the doc-count helper above
+    /// so callers can serialize both with the same shape.
+    pub fn code_lang_chunk_breakdown(
+        &self,
+    ) -> anyhow::Result<std::collections::BTreeMap<String, u32>> {
+        use anyhow::Context;
+        let conn = self.read_conn();
+        let mut stmt = conn
+            .prepare(
+                "SELECT json_extract(d.metadata_json, '$.code_lang') AS cl, \
+                        COUNT(c.chunk_id) \
+                 FROM chunks c \
+                 INNER JOIN documents d ON c.doc_id = d.doc_id \
+                 WHERE cl IS NOT NULL \
+                 GROUP BY cl",
+            )
+            .context("prepare code_lang_chunk_breakdown")?;
+        let rows = stmt
+            .query_map([], |r| {
+                Ok((r.get::<_, String>(0)?, r.get::<_, i64>(1)? as u32))
+            })
+            .context("query code_lang_chunk_breakdown")?;
+        let mut out = std::collections::BTreeMap::new();
+        for row in rows {
+            let (k, v) = row.context("read code_lang_chunk_breakdown row")?;
+            out.insert(k, v);
+        }
+        Ok(out)
+    }
+
     /// p10-1A-2 follow-up (dogfooding 2026-05-20): per-repo doc count for
     /// `schema.v1`.
     ///
@@ -973,6 +1080,108 @@ mod tests {
         assert_eq!(bd.len(), 1, "expected exactly 1 entry, got: {bd:?}");
     }
 
+    /// v0.17.0 PR-C: `code_lang_chunk_breakdown` counts *chunks* (not
+    /// docs) grouped by `documents.metadata_json.code_lang`. Differs
+    /// from `code_lang_breakdown` (doc count) by joining `chunks` and
+    /// summing chunk rows so one Rust file with 3 chunks reports
+    /// `rust=3` here vs `rust=1` in the doc-count helper.
+    ///
+    /// Uses a side rusqlite connection (FK enforcement off) so a single
+    /// doc + multiple chunks fixture can be inserted without standing
+    /// up `assets` companions.
+    #[test]
+    fn code_lang_chunk_breakdown_counts_chunks_not_docs() {
+        let (dir, store) = open_fresh_store();
+        let db_path = dir.path().join("kebab.sqlite");
+        let conn = rusqlite::Connection::open(&db_path).unwrap();
+        conn.pragma_update(None, "foreign_keys", "OFF").unwrap();
+
+        // 1 Rust doc + 3 chunks → chunk_breakdown rust=3 / doc_breakdown rust=1.
+        conn.execute(
+            "INSERT INTO documents (
+                doc_id, asset_id, workspace_path,
+                source_type, trust_level, parser_version,
+                doc_version, schema_version,
+                metadata_json, provenance_json,
+                created_at, updated_at
+            ) VALUES (
+                'doc-rust-1', 'asset-1', 'src/main.rs',
+                'reference', 'primary', 'test-v1',
+                1, 1,
+                '{\"code_lang\":\"rust\"}', '{}',
+                '2024-01-01T00:00:00Z', '2024-01-01T00:00:00Z'
+            )",
+            [],
+        )
+        .unwrap();
+        for i in 0..3u32 {
+            conn.execute(
+                "INSERT INTO chunks (
+                    chunk_id, doc_id, text, heading_path_json, section_label,
+                    source_spans_json, token_estimate, chunker_version,
+                    policy_hash, block_ids_json, created_at
+                ) VALUES (?, 'doc-rust-1', ?, '[]', NULL, '[]', 0, 'cv1', 'h', '[]', '2024-01-01T00:00:00Z')",
+                rusqlite::params![format!("rust-chunk-{i:0>26}"), format!("body {i}")],
+            )
+            .unwrap();
+        }
+
+        // 1 markdown doc + 1 chunk → code_lang = null → must be skipped.
+        conn.execute(
+            "INSERT INTO documents (
+                doc_id, asset_id, workspace_path,
+                source_type, trust_level, parser_version,
+                doc_version, schema_version,
+                metadata_json, provenance_json,
+                created_at, updated_at
+            ) VALUES (
+                'doc-md-1', 'asset-2', 'notes/readme.md',
+                'markdown', 'primary', 'test-v1',
+                1, 1,
+                '{\"code_lang\":null}', '{}',
+                '2024-01-01T00:00:00Z', '2024-01-01T00:00:00Z'
+            )",
+            [],
+        )
+        .unwrap();
+        conn.execute(
+            "INSERT INTO chunks (
+                chunk_id, doc_id, text, heading_path_json, section_label,
+                source_spans_json, token_estimate, chunker_version,
+                policy_hash, block_ids_json, created_at
+            ) VALUES ('md-chunk-00000000000000000000000', 'doc-md-1', 'm', '[]', NULL, '[]', 0, 'cv1', 'h', '[]', '2024-01-01T00:00:00Z')",
+            [],
+        )
+        .unwrap();
+
+        drop(conn);
+
+        let chunk_bd = store.code_lang_chunk_breakdown().unwrap();
+        assert_eq!(
+            chunk_bd.get("rust"),
+            Some(&3u32),
+            "expected rust=3 chunks (1 doc × 3 chunks): {chunk_bd:?}"
+        );
+        assert!(
+            !chunk_bd.contains_key("null"),
+            "null code_lang must be skipped: {chunk_bd:?}"
+        );
+        assert_eq!(
+            chunk_bd.len(),
+            1,
+            "expected exactly 1 language entry: {chunk_bd:?}"
+        );
+
+        // Sanity: the existing doc-count helper still returns 1 for rust,
+        // proving the two metrics differ as intended.
+        let doc_bd = store.code_lang_breakdown().unwrap();
+        assert_eq!(
+            doc_bd.get("rust"),
+            Some(&1u32),
+            "doc-count helper unchanged: {doc_bd:?}"
+        );
+    }
+
     /// p10-1A-2 follow-up: `repo_breakdown` counts docs by
     /// `metadata_json.repo`.
     ///

crates/kebab-store-sqlite/tests/fts.rs

@@ -370,17 +370,19 @@ fn extract_design_5_5_fts_block() -> String {
     fts_slice[..last_end + "END;".len()].to_string()
 }
 
-/// Extract the §5.5 verbatim block from the V002 migration, between the
-/// `── §5.5 verbatim block ──` anchor markers the file already carries.
+/// Extract the §5.5 verbatim block from the V007 migration (replaced V002
+/// 's unicode61 tokenizer with trigram — V002 stays in place for
+/// historical cold-upgrade replay but V007 is now the source of truth),
+/// between the `── §5.5 verbatim block ──` anchor markers V007 carries.
 fn extract_migration_5_5_verbatim_block() -> String {
-    let migration = include_str!("../../../migrations/V002__fts.sql");
+    let migration = include_str!("../../../migrations/V007__fts_trigram.sql");
     // The opening anchor line ends with `── §5.5 verbatim block ─...`.
     let open_marker = "§5.5 verbatim block";
     let close_marker = "End §5.5 verbatim block";
 
     let open_idx = migration
         .find(open_marker)
-        .expect("V002 must carry the `§5.5 verbatim block` opening anchor");
+        .expect("V007 must carry the `§5.5 verbatim block` opening anchor");
     let after_open_line = open_idx
         + migration[open_idx..]
             .find('\n')
@@ -389,7 +391,7 @@ fn extract_migration_5_5_verbatim_block() -> String {
 
     let close_idx = migration[after_open_line..]
         .find(close_marker)
-        .expect("V002 must carry the `End §5.5 verbatim block` closing anchor")
+        .expect("V007 must carry the `End §5.5 verbatim block` closing anchor")
         + after_open_line;
     // Walk back from the close marker to the start of its comment line.
     let close_line_start = migration[..close_idx]
@@ -400,12 +402,14 @@ fn extract_migration_5_5_verbatim_block() -> String {
     migration[after_open_line..close_line_start].to_string()
 }
 
-/// CI diff guard: the §5.5 block in `migrations/V002__fts.sql` must
-/// match the design doc verbatim (whitespace-normalized). If the
-/// design doc moves the section, renames the heading, or edits the
-/// SQL, this test fails first. Same for migration drift.
+/// CI diff guard: the §5.5 block in `migrations/V007__fts_trigram.sql`
+/// must match the design doc verbatim (whitespace-normalized). V007
+/// replaced V002 's unicode61 tokenizer with trigram (2026-05-23).
+/// V002 stays in place for historical replay of cold-upgrade paths
+/// but is no longer compared against the design doc — V007 is now
+/// the source of truth.
 #[test]
-fn fts_v002_matches_design_section_5_5_verbatim() {
+fn fts_v007_matches_design_section_5_5_verbatim() {
     let design = extract_design_5_5_fts_block();
     let migration_block = extract_migration_5_5_verbatim_block();
 
@@ -428,7 +432,7 @@ fn fts_v002_matches_design_section_5_5_verbatim() {
     let migration_n = normalize_ws(&migration_block);
     assert_eq!(
         design_n, migration_n,
-        "V002__fts.sql §5.5 block must match design doc §5.5 verbatim \
+        "V007__fts_trigram.sql §5.5 block must match design doc §5.5 verbatim \
          (whitespace-normalized). If you intentionally changed one, \
          update the other in the same commit."
     );
@@ -477,3 +481,115 @@ fn fts_store_drop_releases_wal_files() {
             .expect("main DB file should be removable after store drop");
     }
 }
+
+// ── 7. Trigram tokenizer behavior (V007) — Korean + English ──────────
+
+/// V007 의 trigram tokenizer 가 한국어 3자 이상 연속 substring 을
+/// 매칭하는지. Codex round 1/2 가 sqlite 3.45.1 로 검증한 동작을 pin:
+/// - raw query 가 3자 이상 공백 없는 substring 인 경우 hit.
+/// - raw query 가 공백을 포함하면 FTS5 가 토큰 경계로 분리 →
+///   양 토큰이 3자 미만이면 0-hit.
+/// - quoted phrase ("..." 안에 공백 포함) 는 통째로 substring 매칭.
+#[test]
+fn fts_trigram_korean_3char_substring_hits() {
+    let env = common::TestEnv::new();
+    let store = SqliteStore::open(&env.config()).unwrap();
+    store.run_migrations().unwrap();
+
+    let conn = raw_conn_no_fk(&env);
+    insert_chunk(
+        &conn,
+        &"k".repeat(32),
+        &"d".repeat(32),
+        "[]",
+        "해시 충돌은 키와 값을 매핑할 때 발생한다",
+    );
+
+    // raw 3+ chars 공백 없는 연속 substring → hit.
+    assert_eq!(
+        count_match(&conn, "충돌은"),
+        1,
+        "raw 3-char 공백 없는 substring '충돌은' must hit"
+    );
+    assert_eq!(
+        count_match(&conn, "발생한"),
+        1,
+        "raw 3-char 공백 없는 substring '발생한' must hit"
+    );
+
+    // quoted phrase (공백 포함) → substring 매칭으로 hit.
+    assert_eq!(
+        count_match(&conn, "\"해시 충돌\""),
+        1,
+        "quoted whole phrase '해시 충돌' (5 chars including space)"
+    );
+    assert_eq!(
+        count_match(&conn, "\"시 충\""),
+        1,
+        "quoted phrase '시 충' across the space boundary"
+    );
+
+    // raw with no whitespace but substring not present in source → 0-hit.
+    assert_eq!(
+        count_match(&conn, "해시충"),
+        0,
+        "원문에 공백 없는 '해시충' trigram 이 없으므로 0-hit"
+    );
+}
+
+/// V007 trigram 의 핵심 제약: 3 Unicode chars 미만 query 는 색인 단위가
+/// 없어 항상 0-hit. design §3.4 + 사용자 결정 (lexical core 정상 0-hit,
+/// CLI/TUI wrapper 가 안내 메시지 출력). 회귀 감지 — trigram 구조 변경
+/// 또는 다른 tokenizer 도입 시 이 test 가 먼저 fail 한다.
+#[test]
+fn fts_trigram_korean_short_query_zero_hit_pinned() {
+    let env = common::TestEnv::new();
+    let store = SqliteStore::open(&env.config()).unwrap();
+    store.run_migrations().unwrap();
+
+    let conn = raw_conn_no_fk(&env);
+    insert_chunk(
+        &conn,
+        &"k".repeat(32),
+        &"d".repeat(32),
+        "[]",
+        "해시 충돌은 키와 값을 매핑할 때 발생한다",
+    );
+
+    // 2자 한국어 query — 도그푸딩에서 보고된 핵심 케이스 ('충돌'/'값').
+    assert_eq!(count_match(&conn, "충돌"), 0, "2-char Korean query");
+    // 1자 한국어 query.
+    assert_eq!(count_match(&conn, "키"), 0, "1-char Korean query");
+}
+
+/// V007 trigram 은 영어에도 substring 매칭으로 동작 — recall ↑, 단어
+/// 경계 정밀도 ↓. design §3.4 의 동작 변경을 명시적으로 핀.
+#[test]
+fn fts_trigram_english_substring_hits() {
+    let env = common::TestEnv::new();
+    let store = SqliteStore::open(&env.config()).unwrap();
+    store.run_migrations().unwrap();
+
+    let conn = raw_conn_no_fk(&env);
+    insert_chunk(
+        &conn,
+        &"e".repeat(32),
+        &"d".repeat(32),
+        "[]",
+        "the tokenizer normalizes whitespace before matching",
+    );
+
+    // trigram substring — 'token' hits inside 'tokenizer'.
+    assert_eq!(
+        count_match(&conn, "token"),
+        1,
+        "substring of 'tokenizer' — trigram recall"
+    );
+    assert_eq!(
+        count_match(&conn, "izer"),
+        1,
+        "substring of 'tokenizer'"
+    );
+    // 3-char-minimum applies to English too.
+    assert_eq!(count_match(&conn, "to"), 0, "2-char English query");
+}

crates/kebab-tui/src/app.rs

@@ -153,6 +153,12 @@ pub struct SearchState {
     /// `Ctrl-L`); the previous draft kept one for "symmetry" but
     /// it was dead code.
     pub worker_rx: Option<std::sync::mpsc::Receiver<SearchWorkerMessage>>,
+    /// v0.17.0 A5 Step 5: advisory text shown when the last completed
+    /// search returned no hits and the (trimmed) query is shorter than
+    /// the FTS5 trigram tokenizer's 3-char minimum. `None` whenever
+    /// the input changes (so a stale hint never overlaps a fresh
+    /// typing session) or the next search returns ≥1 hit.
+    pub short_query_hint: Option<String>,
 }
 
 /// p9-fb-08: payload posted by the search worker on completion.
@@ -179,6 +185,7 @@ impl Default for SearchState {
             preview: None,
             generation: 0,
             worker_rx: None,
+            short_query_hint: None,
         }
     }
 }

crates/kebab-tui/src/run.rs

@@ -393,6 +393,20 @@ fn dynamic_status(app: &App) -> String {
     if app.search.as_ref().map(|s| s.searching).unwrap_or(false) {
         return "searching…".to_string();
     }
+    // v0.17.0 A5 Step 5: short-query advisory has higher priority than
+    // the idle slot but lower than active operations (streaming /
+    // searching / ingest progress) — the user should always see what
+    // is happening *now* before reading guidance about the last
+    // empty result. Slot only fires while focused on Search.
+    if app.focus == Pane::Search {
+        if let Some(hint) = app
+            .search
+            .as_ref()
+            .and_then(|s| s.short_query_hint.as_deref())
+        {
+            return hint.to_string();
+        }
+    }
     if let Some(state) = app.ingest_state.as_ref() {
         return crate::ingest_progress::status_line(state);
     }

crates/kebab-tui/src/search.rs

@@ -333,7 +333,7 @@ pub fn handle_key_search(state: &mut App, key: KeyEvent) -> KeyOutcome {
             s.mode = cycle_mode(s.mode);
             // Force re-search at the new mode if there's a query.
             if !s.input.as_str().trim().is_empty() {
-                s.input_dirty_at = Some(time::OffsetDateTime::now_utc());
+                mark_input_changed(s);
             }
             KeyOutcome::Continue
         }
@@ -360,7 +360,7 @@ pub fn handle_key_search(state: &mut App, key: KeyEvent) -> KeyOutcome {
         (KeyCode::Backspace, _) => {
             if !s.input.is_empty() {
                 s.input.pop_char();
-                s.input_dirty_at = Some(time::OffsetDateTime::now_utc());
+                mark_input_changed(s);
             }
             KeyOutcome::Continue
         }
@@ -388,7 +388,7 @@ pub fn handle_key_search(state: &mut App, key: KeyEvent) -> KeyOutcome {
         }
         (KeyCode::Delete, _) => {
             if s.input.delete_after().is_some() {
-                s.input_dirty_at = Some(time::OffsetDateTime::now_utc());
+                mark_input_changed(s);
             }
             KeyOutcome::Continue
         }
@@ -402,7 +402,7 @@ pub fn handle_key_search(state: &mut App, key: KeyEvent) -> KeyOutcome {
                 s.preview = None;
             } else {
                 s.input.push_char('j');
-                s.input_dirty_at = Some(time::OffsetDateTime::now_utc());
+                mark_input_changed(s);
             }
             KeyOutcome::Continue
         }
@@ -412,7 +412,7 @@ pub fn handle_key_search(state: &mut App, key: KeyEvent) -> KeyOutcome {
                 s.preview = None;
             } else {
                 s.input.push_char('k');
-                s.input_dirty_at = Some(time::OffsetDateTime::now_utc());
+                mark_input_changed(s);
             }
             KeyOutcome::Continue
         }
@@ -426,7 +426,7 @@ pub fn handle_key_search(state: &mut App, key: KeyEvent) -> KeyOutcome {
             // bindings (and don't currently match any Search
             // command, so they're a safe fall-through to Continue).
             s.input.push_char(c);
-            s.input_dirty_at = Some(time::OffsetDateTime::now_utc());
+            mark_input_changed(s);
             KeyOutcome::Continue
         }
         // Normal mode + un-handled Char → no-op (no typing in
@@ -435,6 +435,16 @@ pub fn handle_key_search(state: &mut App, key: KeyEvent) -> KeyOutcome {
     }
 }
 
+/// v0.17.0 A5 Step 5: every input-mutation site in `handle_key_search`
+/// funnels through this helper so the debounce stamp and the
+/// short-query advisory stay in sync. Reset is eager — the stale
+/// advisory from the previous result set must not visually overlap
+/// with a fresh typing session.
+fn mark_input_changed(s: &mut crate::app::SearchState) {
+    s.input_dirty_at = Some(time::OffsetDateTime::now_utc());
+    s.short_query_hint = None;
+}
+
 fn cycle_mode(m: SearchMode) -> SearchMode {
     match m {
         SearchMode::Lexical => SearchMode::Vector,
@@ -603,6 +613,11 @@ pub(crate) fn fire_search(state: &mut App) -> anyhow::Result<()> {
         s.generation = s.generation.wrapping_add(1);
         s.searching = true;
         s.input_dirty_at = None;
+        // v0.17.0 A5 Step 5: hint belongs to the *prior* result set —
+        // a fresh worker spawn invalidates it so the status bar
+        // doesn't keep showing the old advisory while the new
+        // query is in flight.
+        s.short_query_hint = None;
         let q_text = s.input.as_str().to_string();
         s.last_query = Some((q_text.clone(), s.mode));
         (q_text, s.mode, s.generation)
@@ -676,6 +691,18 @@ pub fn poll_worker(state: &mut App) {
             s.searching = false;
             match result {
                 Ok(hits) => {
+                    // v0.17.0 A5 Step 5: stale-aware short-query hint.
+                    // The worker carries no copy of the query text;
+                    // we ground the advisory on `s.last_query` which
+                    // was snapshotted at `fire_search` time and (by
+                    // the generation guard above) still matches what
+                    // the user submitted for *this* result set. If
+                    // input has drifted since spawn, the gen-check
+                    // already returned early.
+                    let q_text =
+                        s.last_query.as_ref().map(|(t, _)| t.as_str()).unwrap_or("");
+                    s.short_query_hint =
+                        kebab_app::short_query_hint(q_text, hits.is_empty());
                     s.hits = hits;
                     s.selected_hit = 0;
                     s.preview = None;
@@ -683,6 +710,7 @@ pub fn poll_worker(state: &mut App) {
                 Err(e) => {
                     s.hits.clear();
                     s.selected_hit = 0;
+                    s.short_query_hint = None;
                     state.error_overlay =
                         Some(crate::error_popup::ErrorOverlay::from_anyhow(&e));
                 }

docs/ARCHITECTURE.md

@@ -22,7 +22,7 @@ Cargo workspace, 함수 호출 기반 모듈러 모놀리스. UI binary (`kebab-
 | OCR | Ollama vision LM (default `gemma4:e4b`) — `OcrEngine` trait 으로 Tesseract / Apple Vision 등 future swap (HOTFIXES P6-2) |
 | Image caption | Ollama vision LM, runtime gate `image.caption.enabled` (default OFF) |
 | PDF parser | `lopdf` per-page 텍스트, `chunker_version = "pdf-page-v1"` 가 PDF 자산에 하드코딩 (HOTFIXES P7-3) |
-| code parser | `tree-sitter` + `tree-sitter-rust` / `tree-sitter-python` / `tree-sitter-typescript` / `tree-sitter-javascript` / `tree-sitter-go` / `tree-sitter-java` / `tree-sitter-kotlin-ng` — **parser-side** (`kebab-parse-code`), chunker-side 아님 (design §6.3). chunker versions: Rust = `code-rust-ast-v1`, Python = `code-python-ast-v1`, TypeScript = `code-ts-ast-v1`, JavaScript = `code-js-ast-v1`, Go = `code-go-ast-v1`, Java = `code-java-ast-v1`, Kotlin = `code-kotlin-ast-v1`. `ast_chunk_max_lines = 200` 상수 고정 (HOTFIXES 2026-05-19 — Chunker trait 이 per-medium config 미노출). Kotlin grammar 은 `tree-sitter-kotlin-ng` 사용 — bare `tree-sitter-kotlin` 은 tree-sitter 0.21–0.23 에 고착되어 있어 사용 불가. **Tier 2 (p10-2)**: YAML/k8s → `serde_yaml` + `k8s-manifest-resource-v1` (apiVersion+kind per resource), Dockerfile → `dockerfile-file-v1` (whole-file), Cargo.toml/go.mod/.json/.xml/.groovy → `manifest-file-v1` (whole-file). Tier 2 chunkers live in `kebab-chunk`; no tree-sitter grammar needed (structure from file type, not AST). **Tier 3 (p10-3)**: shell scripts (`.sh`/`.bash`/`.zsh`) direct → `code-text-paragraph-v1` (blank-line paragraph segmentation + 80-line / 20-overlap line-window for oversize). Same chunker also serves as fallback when Tier 1/2 emit 0 chunks or Err — non-k8s YAML / invalid YAML / AST extractor failures all picked up. symbol = None; lang preserved from input doc. |
+| code parser | `tree-sitter` + `tree-sitter-rust` / `tree-sitter-python` / `tree-sitter-typescript` / `tree-sitter-javascript` / `tree-sitter-go` / `tree-sitter-java` / `tree-sitter-kotlin-ng` — **parser-side** (`kebab-parse-code`), chunker-side 아님 (design §6.3). chunker versions: Rust = `code-rust-ast-v1`, Python = `code-python-ast-v1`, TypeScript = `code-ts-ast-v1`, JavaScript = `code-js-ast-v1`, Go = `code-go-ast-v1`, Java = `code-java-ast-v1`, Kotlin = `code-kotlin-ast-v1`. `ast_chunk_max_lines = 200` 상수 고정 (HOTFIXES 2026-05-19 — Chunker trait 이 per-medium config 미노출). Kotlin grammar 은 `tree-sitter-kotlin-ng` 사용 — bare `tree-sitter-kotlin` 은 tree-sitter 0.21–0.23 에 고착되어 있어 사용 불가. **Tier 2 (p10-2)**: YAML/k8s → `serde_yaml` + `k8s-manifest-resource-v1` (apiVersion+kind per resource), Dockerfile → `dockerfile-file-v1` (whole-file), Cargo.toml/go.mod/.json/.xml/.groovy → `manifest-file-v1` (whole-file). Tier 2 chunkers live in `kebab-chunk`; no tree-sitter grammar needed (structure from file type, not AST). **Tier 3 (p10-3)**: shell scripts (`.sh`/`.bash`/`.zsh`) direct → `code-text-paragraph-v1` (blank-line paragraph segmentation + 80-line / 20-overlap line-window for oversize). Same chunker also serves as fallback when Tier 1/2 emit 0 chunks or Err — non-k8s YAML / invalid YAML / AST extractor failures all picked up. symbol = None; lang preserved from input doc. **Tier 1 family complete (p10-1D)**: C (`tree-sitter-c`, `code-c-ast-v1`, `.c`/`.h`) + C++ (`tree-sitter-cpp`, `code-cpp-ast-v1`, `.cpp`/`.cc`/`.cxx`/`.hpp`/`.hh`/`.hxx`). C symbol = function name only; C++ symbol = `namespace::Class::method` (recursive nesting). `.h` 가 C++ syntax 만나면 tree-sitter-c parse 실패 → Tier 3 fallback. |
 | 1B symbol path | workspace path → module path: Python = dotted prefix (`kebab_eval.metrics.compute_mrr`), TypeScript/JavaScript = slash-style prefix (`src/Foo.Foo.search`). Rust 1A-2 는 file-scope nesting 만 (workspace prefix 없음, 비일관 수용 — HOTFIXES 2026-05-20). |
 | TUI | Ratatui + crossterm — P9-1 Library 패널, P9-2/3/4 진행 예정 |
 | Desktop | Tauri 2 + `pdfjs-dist` (native PDF render backend 금지) — P9-5 |
@@ -52,7 +52,7 @@ flowchart TB
         ppdf["kebab-parse-pdf"]
         pimg["kebab-parse-image"]
         paud["kebab-parse-audio<br/>(P8 보류)"]
-        pcode["kebab-parse-code<br/>(P10-1A-2 + P10-1B + P10-1C-Go + P10-1C-JK + P10-2 + P10-3)"]
+        pcode["kebab-parse-code<br/>(P10-1A-2 + P10-1B + P10-1C-Go + P10-1C-JK + P10-2 + P10-3 + P10-1D)"]
         ptypes["kebab-parse-types"]
         norm["kebab-normalize"]
         chunk["kebab-chunk"]
@@ -127,7 +127,7 @@ flowchart TB
 
 UI → store/llm/parse 직접 의존 금지. 모든 user-facing 진입은 `kebab-app` facade 만 통한다 (frozen 설계 §8). `kebab-cli` 가 `--config <path>` flag 를 honor 하려면 `kebab_app::*_with_config(cfg, …)` companion 을 통해 Config 을 명시적으로 thread 하는 패턴 — 자세한 이유는 [tasks/HOTFIXES.md](../tasks/HOTFIXES.md) 의 `--config` 항목.
 
-`kebab-parse-code` 의 외부 tree-sitter grammar crate 의존: P10-1A-2 에서 `tree-sitter-rust` 추가, P10-1B 에서 `tree-sitter-python` / `tree-sitter-typescript` / `tree-sitter-javascript` 추가, P10-1C-Go 에서 `tree-sitter-go` 추가, P10-1C-JK 에서 `tree-sitter-java` / `tree-sitter-kotlin-ng` 추가. 모두 `kebab-parse-code` 에만 격리 (facade 룰 — UI crate / chunker 가 직접 import 금지). Kotlin 은 `tree-sitter-kotlin-ng` 사용 (bare `tree-sitter-kotlin` 은 tree-sitter 0.21–0.23 에 고착 — 사용 불가).
+`kebab-parse-code` 의 외부 tree-sitter grammar crate 의존: P10-1A-2 에서 `tree-sitter-rust` 추가, P10-1B 에서 `tree-sitter-python` / `tree-sitter-typescript` / `tree-sitter-javascript` 추가, P10-1C-Go 에서 `tree-sitter-go` 추가, P10-1C-JK 에서 `tree-sitter-java` / `tree-sitter-kotlin-ng` 추가, P10-1D 에서 `tree-sitter-c` / `tree-sitter-cpp` 추가. 모두 `kebab-parse-code` 에만 격리 (facade 룰 — UI crate / chunker 가 직접 import 금지). Kotlin 은 `tree-sitter-kotlin-ng` 사용 (bare `tree-sitter-kotlin` 은 tree-sitter 0.21–0.23 에 고착 — 사용 불가).
 
 ## 디렉토리 구조
 
@@ -165,9 +165,11 @@ kebab/
 │   ├── kebab-source-fs/                               # 워크스페이스 walk + checksum (P1-1)
 │   ├── kebab-parse-md/                                # Markdown frontmatter + blocks (P1-2/3)
 │   ├── kebab-normalize/                               # ParsedBlock → CanonicalDocument (P1-4)
-│   ├── kebab-chunk/                                   # heading-aware + pdf-page-v1 + code-*-ast-v1 (Tier 1) + k8s-manifest-resource-v1 + dockerfile-file-v1 + manifest-file-v1 + tier2_shared (P10-2) + code-text-paragraph-v1 (P10-3) chunker (P1-5, P7-2, P10-1A-2, P10-1B, P10-1C-Go, P10-1C-JK, P10-2, P10-3)
+│   ├── kebab-chunk/                                   # heading-aware + pdf-page-v1 + code-*-ast-v1 (Tier 1) + k8s-manifest-resource-v1 + dockerfile-file-v1 + manifest-file-v1 + tier2_shared (P10-2) + code-text-paragraph-v1 (P10-3) chunker (P1-5, P7-2, P10-1A-2, P10-1B, P10-1C-Go, P10-1C-JK, P10-2, P10-3, P10-1D)
 │   │   └── src/
-│   │       ├── code_*_ast_v1.rs              # Tier 1 AST chunkers (rust/python/ts/js/go/java/kotlin)
+│   │       ├── code_*_ast_v1.rs              # Tier 1 AST chunkers (rust/python/ts/js/go/java/kotlin/c/cpp)
+│   │       ├── code_c_ast_v1.rs              # Tier 1 (p10-1D): C top-level fn / struct / enum / union
+│   │       ├── code_cpp_ast_v1.rs            # Tier 1 (p10-1D): C++ namespace::Class::method (recursive nesting)
 │   │       ├── k8s_manifest_resource_v1.rs   # Tier 2 (p10-2): YAML multi-doc, apiVersion+kind per resource
 │   │       ├── dockerfile_file_v1.rs         # Tier 2 (p10-2): whole-file Dockerfile
 │   │       ├── manifest_file_v1.rs           # Tier 2 (p10-2): whole-file Cargo.toml / go.mod / .json / .xml / .groovy
@@ -182,7 +184,7 @@ kebab/
 │   ├── kebab-eval/                                    # golden query runner + metrics (P5-1, P5-2)
 │   ├── kebab-parse-image/                             # ImageExtractor + Ollama OCR + caption (P6)
 │   ├── kebab-parse-pdf/                               # lopdf per-page text extractor (P7-1)
-│   ├── kebab-parse-code/                              # tree-sitter AST extractors: Rust (P10-1A-2), Python + TypeScript + JavaScript (P10-1B), Go (P10-1C-Go), Java + Kotlin (P10-1C-JK — java.rs + kotlin.rs); chunker lives in kebab-chunk
+│   ├── kebab-parse-code/                              # tree-sitter AST extractors: Rust (P10-1A-2), Python + TypeScript + JavaScript (P10-1B), Go (P10-1C-Go), Java + Kotlin (P10-1C-JK — java.rs + kotlin.rs), C + C++ (P10-1D — c.rs + cpp.rs); chunker lives in kebab-chunk
 │   ├── kebab-app/                                     # facade (P0 시그니처 + P3-5/P6-4/P7-3 본체)
 │   ├── kebab-tui/                                     # Ratatui shell + Library 패널 (P9-1)
 │   ├── kebab-mcp/                                     # stdio MCP server — tools: schema, doctor, search, ask (P9-FB-30)

docs/SMOKE.md

@@ -140,6 +140,37 @@ KB ask "이 KB 안에서 ..." --mode hybrid --k 5     # 9. RAG 답변 (Ollama
 KB --json ask "..." --mode hybrid                  # 10. 기계 친화 출력 검증
 ```
 
+### 한국어 trigram 검색 (v0.17.0)
+
+`chunks_fts` 가 FTS5 `trigram` tokenizer 로 동작 — 한국어 query 는 3자 이상 substring 매칭. V007 자동 backfill 이라 기존 KB 의 binary 만 v0.17.0+ 로 교체하면 즉시 적용 (re-ingest 불필요). `kebab.sqlite` 파일 크기가 trigram index 비대화로 ~2-5배 또는 수백 MB 증가.
+
+`fixtures/search/korean/hash-table.md` (또는 등가) 를 워크스페이스에 두고 ingest 한 후:
+
+```bash
+# 3자 연속 substring (raw, 원문에 "해시 충돌은" / "충돌은 발생" 가 있음)
+KB search --mode lexical "충돌은"
+
+# multi-token Korean — builder 가 ("해시 충돌") OR ("해시" "충돌") 으로
+# 변환 (각 토큰 2자라 token-AND 후보는 trigram 비호환, whole-phrase 가 hit)
+KB search --mode lexical "해시 충돌"
+
+# 한영 혼합 — 둘 다 3자 이상이라 whole-phrase + token-AND 모두 후보
+KB search --mode lexical "Rust 충돌은"
+
+# 2자 query — 정상 0 hit + stderr `[hint] 3자 이상 키워드 권장`
+KB search --mode lexical "충돌"
+
+# 동일 케이스의 --json 출력에는 search_response.v1.hint 필드 포함
+KB search --mode lexical "충돌" --json | jq '.hits | length, .hint'
+# → 0
+# → "3자 이상 키워드 권장 (trigram tokenizer 제약)"
+
+# raw FTS5 mode (single quote 로 감싼 입력) — 사용자 명시 의도, hint 미출력
+KB search --mode lexical "'충돌'"
+```
+
+영어 lexical 도 substring 매칭으로 바뀜 — `KB search --mode lexical "token"` 이 `tokenizer` / `tokenize` 도 hit (recall ↑, 단어 경계 정밀도 ↓).
+
 ### Stale doc indicator
 
 Each search hit and RAG citation carries `indexed_at` (RFC3339 of the doc's last
@@ -548,6 +579,54 @@ KB --json schema | jq '.stats.code_lang_breakdown'
 
 **Tier 3 citation.symbol 컨벤션**: 항상 `null`. 의미 단위 식별 안 함. `lang` 은 원본 lang 보존 (shell → `"shell"`, yaml → `"yaml"` 등).
 
+## P10-1D C + C++ AST chunkers
+
+P10-3 와 동일한 격리 KB 설정. `.c` 와 `.cpp` 파일이 각자의 AST chunker 로 처리된다.
+
+```bash
+# 1) C 파일 — top-level function symbol
+cat > /tmp/kebab-smoke/workspace/parser.c <<'EOF'
+#include <stdio.h>
+
+int parse_record(const char *line) {
+    if (line == NULL) return -1;
+    return 0;
+}
+EOF
+
+# 2) C++ 파일 — namespace::Class::method symbol
+cat > /tmp/kebab-smoke/workspace/chunker.cpp <<'EOF'
+namespace kebab {
+namespace chunk {
+
+class Foo {
+public:
+    void bar() { /* impl */ }
+};
+
+}  // namespace chunk
+}  // namespace kebab
+EOF
+
+# 3) ingest
+KB ingest
+
+# 4) 언어별 검색 (citation.symbol 확인)
+KB search --mode hybrid "parse_record" --code-lang c --json | \
+  jq '{hits: [.hits[] | {symbol: .citation.symbol, lang: .citation.lang}]}'
+# 기대: symbol = "parse_record" (function name only), lang = "c"
+
+KB search --mode hybrid "bar" --code-lang cpp --json | \
+  jq '{hits: [.hits[] | {symbol: .citation.symbol, lang: .citation.lang}]}'
+# 기대: symbol = "kebab::chunk::Foo" 또는 "kebab::chunk::Foo::bar" (namespace::Class[::method]), lang = "cpp"
+
+# 5) schema stats 에 C/C++ 카운트 확인
+KB --json schema | jq '.stats.code_lang_breakdown'
+# 기대: {"c": N, "cpp": M, ...}
+```
+
+**Tier 1 (p10-1D) citation.symbol 컨벤션**: C 는 function name only (`parse_record` 같이 nesting 없음). C++ 는 `namespace::Class::method` (recursive namespace + class nesting). `.h` 파일이 C++ syntax (namespace / template / class) 만나면 tree-sitter-c parse 실패 → p10-3 Tier 3 fallback (`code-text-paragraph-v1`) 으로 자동 picked up.
+
 ## 검증 체크리스트
 
 - `kebab doctor` 가 `--config` path 를 honor 하고 그 안의 `storage.data_dir` 를 출력 (XDG default 가 아님).
@@ -584,6 +663,7 @@ rm -rf /tmp/kebab-smoke              # 통째로 정리
 - (P10-1C-JK) `.java` 파일은 `code-java-ast-v1`, `.kt`/`.kts` 파일은 `code-kotlin-ast-v1` 로 처리. `--code-lang java` / `--code-lang kotlin` 검색이 `citation.symbol` 에 `com.foo.Foo.bar` 형식 결과를 반환하면 wiring 정상. `kebab schema --json | jq .stats.code_lang_breakdown` 에 `"java": N` / `"kotlin": N` 등장 확인.
 - (P10-2) `.yaml`/`.yml` 파일은 apiVersion+kind 파싱으로 k8s resource 별 chunk 생성 (`k8s-manifest-resource-v1`). `Dockerfile`/`Dockerfile.*` 는 전체 파일 단일 chunk (`dockerfile-file-v1`). `.toml`/`.json`/`.xml`/`.groovy`/`go.mod` 는 전체 파일 단일 chunk (`manifest-file-v1`). `--code-lang yaml` / `--code-lang dockerfile` / `--code-lang toml` 검색이 `citation.symbol` 에 각각 `Deployment/default/my-app` / `<dockerfile>` / `<manifest>` 형식 결과를 반환하면 wiring 정상. `kebab schema --json | jq .stats.code_lang_breakdown` 에 `"yaml": N` / `"dockerfile": N` / `"toml": N` 등장 확인.
 - (P10-3) `.sh`/`.bash`/`.zsh` 파일은 direct Tier 3 (`code-text-paragraph-v1`). 비-k8s YAML (apiVersion+kind 없는 yaml) 은 k8s chunker 가 0 chunk → Tier 3 fallback 으로 picked up. `--code-lang shell` / `--code-lang yaml` 검색이 `citation.symbol = null`, `chunker_version = "code-text-paragraph-v1"` 결과를 반환하면 wiring 정상. `kebab schema --json | jq .stats.code_lang_breakdown` 에 `"shell": N` 등장 확인.
+- (P10-1D) `.c` / `.h` 파일은 `code-c-ast-v1` (function name only symbol). `.cpp`/`.cc`/`.cxx`/`.hpp`/`.hh`/`.hxx` 는 `code-cpp-ast-v1` (`namespace::Class::method` symbol). `--code-lang c` / `--code-lang cpp` 검색 동작 + `kebab schema --json | jq .stats.code_lang_breakdown` 에 `"c": N` / `"cpp": M` 등장 확인. `.h` 파일이 C++ 내용 (namespace 등) 갖고 있으면 자동으로 Tier 3 (`code-text-paragraph-v1`) fallback 으로 picked up.
 - (P7-3 + follow-up) 동일 path 에 byte 가 다른 PDF 를 두 번째 ingest 하면 `purge_vector_orphans_for_workspace_path` 가 옛 chunk_id 를 LanceDB 에서 먼저 삭제, 이어서 `purge_orphan_at_workspace_path` 가 옛 doc / chunks / embedding_records 를 SQLite 에서 sweep. 새 byte 가 새 `doc_id` 로 색인됨. `IngestReport` 에 그 자산만 `new+=1` (다른 자산은 `updated`). 두 store 모두 정합 — 옛 본문 검색 시 옛 chunks 가 더 이상 surface 되지 않음.
 
 ### Embedding upgrade (fb-39b)

docs/superpowers/plans/2026-05-21-p10-1d-c-cpp-ast-chunker.md

@@ -0,0 +1,930 @@
+# p10-1D C + C++ AST Chunkers Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Activate C + C++ code ingest end-to-end. P10 Tier 1 chunker family final entry.
+
+**Architecture:** Same shape as 1B (multi-language single PR) and 1C-JK (JVM family). 2 new tree-sitter grammars + 2 extractors + 2 chunkers + media routing (delegated via `code_lang_for_path`, no change) + app dispatch arms. C symbol = function name only; C++ symbol = `namespace::Class::method` via recursive class/namespace nesting (Java/Kotlin + Python hybrid).
+
+**Tech Stack:** Rust 2024 workspace, `tree-sitter` 0.26 (already), `tree-sitter-c` + `tree-sitter-cpp` (NEW). 1A-2/1B/1C/p10-2/p10-3 infrastructure unchanged.
+
+**Memory note:** Host has been OOM'd previously (재부팅 사례). Per-crate cargo only. ONE full-suite + clippy invocation in Task J. NO `cargo test --workspace` outside that gate.
+
+---
+
+## Pre-flight
+
+Branch `feat/p10-1d-c-cpp` already exists (spec commit `8add684`).
+
+- [ ] **Disk hygiene**: `df -h /` 점검. 80% 넘으면 `cargo clean`.
+
+Reference files:
+- 1C-JK extractor: `crates/kebab-parse-code/src/{java,kotlin}.rs` — closest template for source-side identifier prefix (package vs namespace).
+- 1B Python extractor: `crates/kebab-parse-code/src/python.rs` — class-nesting recursion model (relevant for C++ class nesting).
+- 1A-2 chunker: `crates/kebab-chunk/src/code_rust_ast_v1.rs` — duplicate-with-substitution pattern.
+- 1B/1C/p10-2/p10-3 dispatch generalization: `crates/kebab-app/src/lib.rs::ingest_one_code_asset` (~L1796–2116). Current allowlist + 4-arm match.
+- spec: `tasks/p10/p10-1d-c-cpp-ast-chunker.md`.
+
+---
+
+## Task A: Workspace deps (tree-sitter-c + tree-sitter-cpp)
+
+**Files:**
+- Modify: `Cargo.toml` (`[workspace.dependencies]`, after `tree-sitter-kotlin-ng`)
+- Modify: `crates/kebab-parse-code/Cargo.toml`
+
+- [ ] **Step 1**: `cargo add tree-sitter-c tree-sitter-cpp -p kebab-parse-code`. If either crate's actively-maintained name differs (e.g. `tree-sitter-cpp` vs `tree-sitter-cpp-ng`), verify on crates.io. The `tree-sitter-c` 0.24 / `tree-sitter-cpp` 0.23 line is the most common; verify compatibility with workspace `tree-sitter = "0.26"` (likely already supported via the `tree-sitter-language` shim).
+
+- [ ] **Step 2**: Lift the two resolved versions into `[workspace.dependencies]` (after `tree-sitter-kotlin-ng`):
+
+```toml
+# C/C++ family grammars for code ingest (kebab-parse-code, p10-1D).
+tree-sitter-c          = "<resolved>"
+tree-sitter-cpp        = "<resolved>"
+```
+
+Switch crate's `Cargo.toml` entries to `{ workspace = true }`.
+
+- [ ] **Step 3**: `cargo build -p kebab-parse-code` → clean. Unused dep warning is fine.
+
+- [ ] **Step 4**: Commit:
+
+```bash
+git add Cargo.toml Cargo.lock crates/kebab-parse-code/Cargo.toml
+git commit -m "$(cat <<'EOF'
+build(p10-1d): add tree-sitter-c + tree-sitter-cpp workspace deps
+
+Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
+EOF
+)"
+```
+
+If a crate's resolved name has a non-obvious fork suffix (e.g. `tree-sitter-cpp-ng`), document it in the commit body.
+
+---
+
+## Task B: C AST extractor (`kebab-parse-code/src/c.rs`)
+
+**Files:**
+- Create: `crates/kebab-parse-code/src/c.rs`
+- Modify: `crates/kebab-parse-code/src/lib.rs` (pub mod + `C_PARSER_VERSION` const)
+
+- [ ] **Step 1**: Create `crates/kebab-parse-code/src/c.rs`. Mirror `crates/kebab-parse-code/src/go.rs` (closest template — single-language, no namespace/package nesting, top-level units). Replace tree-sitter-go with tree-sitter-c:
+
+```rust
+//! p10-1D: C AST extractor.
+
+use crate::traits::{Extractor, ExtractContext};
+use anyhow::{Context, Result};
+use kebab_core::{Block, BlockId, CanonicalDocument, CodeBlock, CommonBlock, /*..*/, SourceSpan, id_for_block, id_for_doc};
+use tree_sitter::Parser;
+
+pub const C_PARSER_VERSION: &str = concat!("tree-sitter-c-", env!("CARGO_PKG_VERSION"));
+// Or use the tree-sitter-c crate version: better to hardcode for stability.
+// Look at how go.rs / rust.rs / etc. set their PARSER_VERSION.
+
+pub struct CAstExtractor {
+    parser: Parser,
+}
+
+impl CAstExtractor {
+    pub fn new() -> Self {
+        let mut parser = Parser::new();
+        parser.set_language(&tree_sitter_c::LANGUAGE.into()).expect("load tree-sitter-c");
+        Self { parser }
+    }
+}
+
+impl Extractor for CAstExtractor {
+    fn extract(&mut self, ctx: &ExtractContext, bytes: &[u8]) -> Result<CanonicalDocument> {
+        // ... mirror go.rs:
+        //   1. parse the tree
+        //   2. iterate source_file's named_children
+        //   3. for each top-level node:
+        //      - function_definition → emit unit (symbol = fn name)
+        //      - struct_specifier (named) → emit unit (symbol = struct name)
+        //      - enum_specifier (named) → emit unit (symbol = enum name)
+        //      - union_specifier (named) → emit unit (symbol = union name)
+        //      - declaration → glue
+        //      - preproc_include / preproc_def / preproc_function_def / preproc_ifdef → glue
+        //      - else → glue
+        //   4. <top-level> glue chunk if any glue accumulated
+        //   5. <module> post-pass if 0 units
+        // ...
+        todo!("mirror go.rs structure with C-specific node-kind names")
+    }
+}
+```
+
+**ACTION**: Read `crates/kebab-parse-code/src/go.rs` in full first. It's the closest template — single-language, no namespace prefix to thread through (C is even simpler than Go since there's no `package`). Port the structure: parse → iterate top-level → match on node-kind → emit units or accumulate glue.
+
+Node-kind name reference (tree-sitter-c): `function_definition`, `struct_specifier`, `enum_specifier`, `union_specifier`, `declaration`, `preproc_*`. Confirm by checking the crate's `node-types.json` if uncertain.
+
+**Function name extraction**: `function_definition` has a `declarator` field. The innermost `identifier` of that declarator is the function name. Mirror how go.rs extracts function names — it uses tree-sitter field traversal.
+
+- [ ] **Step 2**: Register the module in `crates/kebab-parse-code/src/lib.rs`:
+
+```rust
+pub mod c;
+pub use c::{CAstExtractor, C_PARSER_VERSION};
+```
+
+- [ ] **Step 3**: Build:
+
+```bash
+cargo build -p kebab-parse-code 2>&1 | tail -5
+```
+
+Expected: clean.
+
+- [ ] **Step 4**: Commit (no test yet — Task D adds the snapshot test):
+
+```bash
+git add crates/kebab-parse-code/src/c.rs crates/kebab-parse-code/src/lib.rs
+git commit -m "$(cat <<'EOF'
+feat(p10-1d): C AST extractor (tree-sitter-c)
+
+Top-level units: function_definition (symbol = fn name), struct_specifier,
+enum_specifier, union_specifier (each emits 1 unit with the symbol being
+the named identifier). Preprocessor directives + top-level declarations
+group into a <top-level> glue chunk. Empty file or zero units → <module>
+post-pass.
+
+C symbol = function name only — no namespace, no class nesting (design §3.4).
+
+Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
+EOF
+)"
+```
+
+---
+
+## Task C: C++ AST extractor (`kebab-parse-code/src/cpp.rs`)
+
+**Files:**
+- Create: `crates/kebab-parse-code/src/cpp.rs`
+- Modify: `crates/kebab-parse-code/src/lib.rs`
+
+- [ ] **Step 1**: Create `crates/kebab-parse-code/src/cpp.rs`. The closest template is `crates/kebab-parse-code/src/java.rs` (1C-JK) — it handles package prefix + class nesting via recursion. C++ adds namespace nesting (multiple levels possible).
+
+Pseudocode:
+
+```rust
+//! p10-1D: C++ AST extractor.
+
+use crate::traits::{Extractor, ExtractContext};
+use anyhow::{Context, Result};
+use kebab_core::{/* ... */};
+use tree_sitter::{Node, Parser};
+
+pub const CPP_PARSER_VERSION: &str = "tree-sitter-cpp-<resolved>";
+
+pub struct CppAstExtractor { parser: Parser }
+
+impl CppAstExtractor {
+    pub fn new() -> Self {
+        let mut parser = Parser::new();
+        parser.set_language(&tree_sitter_cpp::LANGUAGE.into()).expect("load tree-sitter-cpp");
+        Self { parser }
+    }
+
+    fn visit(&self, node: Node, source: &[u8], prefix: &[&str], units: &mut Vec<(String, Node)>, glue: &mut Vec<Node>) {
+        // prefix is the namespace/class chain so far (e.g. ["kebab", "chunk", "MdHeadingV1Chunker"]).
+        for child in node.named_children(&mut node.walk()) {
+            match child.kind() {
+                "namespace_definition" => {
+                    let name = child.child_by_field_name("name")
+                        .and_then(|n| n.utf8_text(source).ok())
+                        .unwrap_or("<anonymous>");
+                    let mut new_prefix = prefix.to_vec();
+                    new_prefix.push(name);
+                    let body = child.child_by_field_name("body").unwrap_or(child);
+                    self.visit(body, source, &new_prefix, units, glue);
+                }
+                "class_specifier" | "struct_specifier" if child.child_by_field_name("name").is_some() => {
+                    let name = child.child_by_field_name("name")
+                        .and_then(|n| n.utf8_text(source).ok())
+                        .unwrap_or("<anonymous>");
+                    // Emit the class itself as a unit.
+                    let symbol = build_symbol(prefix, &[], name);  // e.g. "kebab::chunk::Foo"
+                    units.push((symbol, child));
+                    // Recurse for nested classes / methods.
+                    let mut new_prefix = prefix.to_vec();
+                    new_prefix.push(name);
+                    let body = child.child_by_field_name("body").unwrap_or(child);
+                    self.visit(body, source, &new_prefix, units, glue);
+                }
+                "function_definition" => {
+                    // declarator may be qualified_identifier (out-of-class def) or plain identifier.
+                    let symbol = extract_fn_symbol(child, source, prefix);
+                    units.push((symbol, child));
+                    // Do NOT recurse into function body — inner classes/lambdas left to a future revision.
+                }
+                "template_declaration" => {
+                    // Recurse: unwrap to inner declarator (function_definition or class_specifier)
+                    // and treat it as if it were directly there. Template params NOT in symbol.
+                    self.visit(child, source, prefix, units, glue);
+                }
+                "enum_specifier" if child.child_by_field_name("name").is_some() => {
+                    let name = child.child_by_field_name("name").and_then(|n| n.utf8_text(source).ok()).unwrap_or("<anonymous>");
+                    let symbol = build_symbol(prefix, &[], name);
+                    units.push((symbol, child));
+                }
+                "concept_definition" => {
+                    let name = /* extract */;
+                    let symbol = build_symbol(prefix, &[], &name);
+                    units.push((symbol, child));
+                }
+                _ => glue.push(child),
+            }
+        }
+    }
+}
+
+fn build_symbol(prefix: &[&str], extras: &[&str], leaf: &str) -> String {
+    // Join with ::
+    let mut parts: Vec<&str> = prefix.iter().copied().collect();
+    parts.extend_from_slice(extras);
+    parts.push(leaf);
+    parts.join("::")
+}
+
+fn extract_fn_symbol(node: Node, source: &[u8], prefix: &[&str]) -> String {
+    // function_definition.declarator may be a function_declarator wrapping a
+    // qualified_identifier (out-of-class def like `void Foo::bar(){}`) or a
+    // plain identifier (free fn or in-namespace fn).
+    // Need to walk down to the leaf identifier and any qualifier chain.
+    // For qualified_identifier "Foo::bar::baz", break into ["Foo", "bar"] qualifier + "baz" leaf.
+    // ...
+    todo!("walk declarator → qualified_identifier → assemble symbol with prefix")
+}
+
+// Extractor impl: parse, visit(root, ...), emit chunks-of-blocks per (symbol, node) pair + <top-level> glue + <module> fallback.
+```
+
+This is the most intricate extractor in p10-1D. **Action**: read `crates/kebab-parse-code/src/java.rs` for the recursion pattern, then `crates/kebab-parse-code/src/python.rs` for the class-nesting pattern, and combine. tree-sitter-cpp's node-types.json (or a quick `tree-sitter parse` against a sample file) confirms exact node-kind names.
+
+- [ ] **Step 2**: Register in `crates/kebab-parse-code/src/lib.rs`:
+
+```rust
+pub mod cpp;
+pub use cpp::{CppAstExtractor, CPP_PARSER_VERSION};
+```
+
+- [ ] **Step 3**: Build:
+
+```bash
+cargo build -p kebab-parse-code 2>&1 | tail -5
+```
+
+Expected: clean.
+
+- [ ] **Step 4**: Commit:
+
+```bash
+git add crates/kebab-parse-code/src/cpp.rs crates/kebab-parse-code/src/lib.rs
+git commit -m "$(cat <<'EOF'
+feat(p10-1d): C++ AST extractor (tree-sitter-cpp)
+
+Symbol = namespace::Class::method via recursive visit. namespace_definition
+pushes namespace name (anonymous → <anonymous>). class_specifier / struct_specifier
+(named) emit class unit + recurse with class name pushed. function_definition
+emits method unit (symbol may include qualified_identifier prefix for
+out-of-class definitions). template_declaration unwraps to inner declarator
+(template params NOT in symbol). enum_specifier + concept_definition emit
+type-level units. extern "C" block content + using/include/define → glue.
+
+Constructor / destructor symbols use Class::Class / Class::~Class
+convention. Operator overloads keep operator+ form.
+
+Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
+EOF
+)"
+```
+
+---
+
+## Task D: C chunker + snapshot test
+
+**Files:**
+- Create: `crates/kebab-chunk/src/code_c_ast_v1.rs`
+- Create: `crates/kebab-chunk/tests/fixtures/sample.c`
+- Create: `crates/kebab-chunk/tests/code_c_ast_snapshot.rs`
+- Modify: `crates/kebab-chunk/src/lib.rs`
+
+- [ ] **Step 1**: Create `crates/kebab-chunk/src/code_c_ast_v1.rs`. **Mirror `crates/kebab-chunk/src/code_go_ast_v1.rs`** (closest 1-extractor pattern, no nesting):
+
+```rust
+//! p10-1D: C AST chunker.
+
+use crate::tier2_shared::build_chunk;
+use crate::{Chunker, ChunkPolicy};
+use anyhow::Result;
+use kebab_core::{Block, Chunk, Document};
+
+pub const VERSION_LABEL: &str = "code-c-ast-v1";
+
+pub struct CodeCAstV1Chunker;
+
+impl Chunker for CodeCAstV1Chunker {
+    fn chunker_version(&self) -> &'static str { VERSION_LABEL }
+    fn policy_hash(&self, policy: &ChunkPolicy) -> String {
+        crate::tier2_shared::policy_hash(policy)
+    }
+    fn chunk(&self, doc: &Document, policy: &ChunkPolicy) -> Result<Vec<Chunk>> {
+        // Mirror code_go_ast_v1.rs's body — iterate doc.blocks, each Block::Code
+        // contributes 1 chunk via build_chunk. Apply oversize fallback per block
+        // via tier2_shared::push_chunks_with_oversize.
+        // ...
+        todo!("mirror code_go_ast_v1.rs verbatim, substituting VERSION_LABEL")
+    }
+}
+```
+
+Read `code_go_ast_v1.rs` and port verbatim — the language-agnostic body iterates `doc.blocks` and emits chunks. Only the `VERSION_LABEL` and (potentially) symbol formatting helper change.
+
+- [ ] **Step 2**: Create `tests/fixtures/sample.c` (~30 lines, includes top-level fn, struct, enum, preprocessor):
+
+```c
+#include <stdio.h>
+#include <stdlib.h>
+
+#define MAX_BUF 4096
+
+typedef enum {
+    OK = 0,
+    ERR_PARSE,
+    ERR_IO,
+} status_t;
+
+typedef struct {
+    int id;
+    char name[64];
+    status_t status;
+} record_t;
+
+static int counter = 0;
+
+int parse_record(const char *line, record_t *out) {
+    if (line == NULL || out == NULL) return ERR_PARSE;
+    return OK;
+}
+
+void print_record(const record_t *r) {
+    printf("[%d] %s (status=%d)\n", r->id, r->name, r->status);
+}
+
+int main(void) {
+    record_t r = { .id = 1, .name = "foo", .status = OK };
+    print_record(&r);
+    return 0;
+}
+```
+
+Expected snapshot: 3 function units (`parse_record`, `print_record`, `main`) + 1 enum unit (`status_t`) + 1 struct unit (`record_t`) + 1 `<top-level>` glue (preproc + global var). Total ~6 chunks.
+
+- [ ] **Step 3**: Create `tests/code_c_ast_snapshot.rs` mirroring `tests/code_go_ast_snapshot.rs`. Assertions:
+
+```rust
+// Pseudocode:
+// 1. Load fixture sample.c
+// 2. Run CAstExtractor → Document
+// 3. Run CodeCAstV1Chunker.chunk(&doc, &policy)
+// 4. Assert chunks.len() == expected (6).
+// 5. Assert symbols (from chunks[i].source_spans[0]::SourceSpan::Code.symbol) match expected list:
+//    ["status_t", "record_t", "parse_record", "print_record", "main", "<top-level>"]
+//    (order matches AST traversal order — verify by running once.)
+// 6. Assert all chunks have lang = Some("c").
+```
+
+- [ ] **Step 4**: Register module in `crates/kebab-chunk/src/lib.rs`:
+
+```rust
+pub mod code_c_ast_v1;
+pub use code_c_ast_v1::CodeCAstV1Chunker;
+```
+
+- [ ] **Step 5**: Run test:
+
+```bash
+cargo test -p kebab-chunk --test code_c_ast_snapshot -- --nocapture 2>&1 | tail -25
+```
+
+Expected: PASS. If chunk count or symbol order differs from expectation, INSPECT the actual output and update the test's expected list to match (run once to learn, codify on second run).
+
+- [ ] **Step 6**: Clippy + commit:
+
+```bash
+cargo clippy -p kebab-chunk --all-targets -- -D warnings
+git add crates/kebab-chunk/src/code_c_ast_v1.rs \
+        crates/kebab-chunk/src/lib.rs \
+        crates/kebab-chunk/tests/fixtures/sample.c \
+        crates/kebab-chunk/tests/code_c_ast_snapshot.rs
+git commit -m "$(cat <<'EOF'
+feat(p10-1d): code-c-ast-v1 chunker + snapshot test
+
+Mirrors code-go-ast-v1's chunker pattern (1 chunk per AST unit + <top-level>
+glue + oversize fallback). Snapshot test against tests/fixtures/sample.c
+(function + struct + enum + preprocessor) verifies symbol order + lang=c
+stamping.
+
+Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
+EOF
+)"
+```
+
+---
+
+## Task E: C++ chunker + snapshot test
+
+**Files:**
+- Create: `crates/kebab-chunk/src/code_cpp_ast_v1.rs`
+- Create: `crates/kebab-chunk/tests/fixtures/sample.cpp`
+- Create: `crates/kebab-chunk/tests/code_cpp_ast_snapshot.rs`
+- Modify: `crates/kebab-chunk/src/lib.rs`
+
+- [ ] **Step 1**: Create `code_cpp_ast_v1.rs`. **Mirror `code_c_ast_v1.rs`** verbatim, only VERSION_LABEL differs:
+
+```rust
+pub const VERSION_LABEL: &str = "code-cpp-ast-v1";
+
+pub struct CodeCppAstV1Chunker;
+
+impl Chunker for CodeCppAstV1Chunker {
+    fn chunker_version(&self) -> &'static str { VERSION_LABEL }
+    // ... identical body — both languages use the same Block::Code → Chunk emission ...
+}
+```
+
+The actual symbol-formatting work happens in the EXTRACTOR (Task C). The chunker's job is to iterate blocks the extractor produced and emit Chunks. Both C and C++ chunkers are essentially identical bodies.
+
+- [ ] **Step 2**: Create `tests/fixtures/sample.cpp` (~50 lines, includes namespace + nested class + method + free fn + template):
+
+```cpp
+#include <string>
+#include <vector>
+
+namespace kebab {
+namespace chunk {
+
+class MdHeadingV1Chunker {
+public:
+    MdHeadingV1Chunker() = default;
+    ~MdHeadingV1Chunker() = default;
+
+    std::string chunk_doc(const std::string& doc) {
+        return doc;
+    }
+
+    int operator()(int x) const {
+        return x * 2;
+    }
+
+private:
+    int counter_ = 0;
+};
+
+template <typename T>
+T identity(T value) {
+    return value;
+}
+
+}  // namespace chunk
+
+void global_helper() {
+    // free function in kebab namespace
+}
+
+}  // namespace kebab
+
+int main() {
+    kebab::chunk::MdHeadingV1Chunker c;
+    return 0;
+}
+```
+
+Expected snapshot symbols (verify on first run, then codify):
+- `kebab::chunk::MdHeadingV1Chunker` (class unit)
+- `kebab::chunk::MdHeadingV1Chunker::MdHeadingV1Chunker` (constructor)
+- `kebab::chunk::MdHeadingV1Chunker::~MdHeadingV1Chunker` (destructor)
+- `kebab::chunk::MdHeadingV1Chunker::chunk_doc`
+- `kebab::chunk::MdHeadingV1Chunker::operator()`
+- `kebab::chunk::identity` (template fn)
+- `kebab::global_helper`
+- `main` (free fn, no namespace)
+- `<top-level>` (include + using)
+
+~9 chunks total.
+
+- [ ] **Step 3**: Create `tests/code_cpp_ast_snapshot.rs` mirroring `code_c_ast_snapshot.rs`. Assert symbol list matches expected (run once to learn the actual order, codify).
+
+- [ ] **Step 4**: Register module in `lib.rs`:
+
+```rust
+pub mod code_cpp_ast_v1;
+pub use code_cpp_ast_v1::CodeCppAstV1Chunker;
+```
+
+- [ ] **Step 5**: Run test:
+
+```bash
+cargo test -p kebab-chunk --test code_cpp_ast_snapshot -- --nocapture 2>&1 | tail -30
+```
+
+Expected: PASS.
+
+- [ ] **Step 6**: Clippy + commit:
+
+```bash
+cargo clippy -p kebab-chunk --all-targets -- -D warnings
+git add crates/kebab-chunk/src/code_cpp_ast_v1.rs \
+        crates/kebab-chunk/src/lib.rs \
+        crates/kebab-chunk/tests/fixtures/sample.cpp \
+        crates/kebab-chunk/tests/code_cpp_ast_snapshot.rs
+git commit -m "$(cat <<'EOF'
+feat(p10-1d): code-cpp-ast-v1 chunker + snapshot test
+
+Identical chunker body to code-c-ast-v1; per-language work happens in the
+CppAstExtractor (Task C). Snapshot fixture covers nested namespace +
+class + ctor/dtor + method + operator overload + template fn + free fn +
+top-level main, verifying namespace::Class::method symbol convention per
+design §3.4.
+
+Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
+EOF
+)"
+```
+
+---
+
+## Task F: ingest_one_code_asset dispatch + tier3 fallback list extension
+
+**Files:**
+- Modify: `crates/kebab-app/src/lib.rs`
+
+- [ ] **Step 1**: Top-of-file `use kebab_chunk::{...}` extend with `CodeCAstV1Chunker` + `CodeCppAstV1Chunker`:
+
+```rust
+use kebab_chunk::{
+    /* existing items */,
+    CodeCAstV1Chunker,
+    CodeCppAstV1Chunker,
+};
+```
+
+- [ ] **Step 2**: Allowlist (around line 953) extend:
+
+```rust
+if matches!(lang.as_str(),
+    "rust" | "python" | "typescript" | "javascript" | "go" | "java" | "kotlin"
+    | "yaml" | "dockerfile" | "toml" | "json" | "xml" | "groovy" | "go-mod"
+    | "shell"
+    | "c" | "cpp")
+```
+
+- [ ] **Step 3**: `parser_version` match — add C/C++ arms (Tier 1, so they DO get a real parser version):
+
+```rust
+let parser_version = match code_lang {
+    // ... existing 7 Tier 1 + Tier 2 + shell arms ...
+    "c"   => ParserVersion(kebab_parse_code::C_PARSER_VERSION.to_string()),
+    "cpp" => ParserVersion(kebab_parse_code::CPP_PARSER_VERSION.to_string()),
+    other => anyhow::bail!("unsupported code_lang: {other}"),
+};
+```
+
+- [ ] **Step 4**: `chunker_version` match — add C/C++ arms:
+
+```rust
+let chunker_version = match code_lang {
+    // ... existing arms ...
+    "c"   => CodeCAstV1Chunker.chunker_version(),
+    "cpp" => CodeCppAstV1Chunker.chunker_version(),
+    other => anyhow::bail!("unreachable chunker_version: {other}"),
+};
+```
+
+- [ ] **Step 5**: `canonical_result` extract match — add C/C++ arms:
+
+```rust
+let canonical_result: anyhow::Result<CanonicalDocument> = match code_lang {
+    "rust"   => RustAstExtractor::new().extract(&ctx, &bytes).context("..."),
+    // ... existing ...
+    "c"      => CAstExtractor::new().extract(&ctx, &bytes)
+                  .context("kb-parse-code::CAstExtractor::extract (code:c)"),
+    "cpp"    => CppAstExtractor::new().extract(&ctx, &bytes)
+                  .context("kb-parse-code::CppAstExtractor::extract (code:cpp)"),
+    // ... Tier 2 + shell ...
+    other => anyhow::bail!("unreachable (extract): {other}"),
+};
+```
+
+(Add `use kebab_parse_code::{CAstExtractor, CppAstExtractor};` at the top if not already wildcard-imported.)
+
+- [ ] **Step 6**: `chunks_result` match — add C/C++ arms:
+
+```rust
+let chunks_result: anyhow::Result<Vec<Chunk>> = if extract_fell_back {
+    // ... existing ...
+} else {
+    match code_lang {
+        "rust"   => CodeRustAstV1Chunker.chunk(&canonical, chunk_policy).context("..."),
+        // ... existing ...
+        "c"      => CodeCAstV1Chunker.chunk(&canonical, chunk_policy)
+                      .context("kb-chunk::CodeCAstV1Chunker::chunk (code:c)"),
+        "cpp"    => CodeCppAstV1Chunker.chunk(&canonical, chunk_policy)
+                      .context("kb-chunk::CodeCppAstV1Chunker::chunk (code:cpp)"),
+        // ... existing ...
+        other => anyhow::bail!("unreachable (chunk): {other}"),
+    }
+};
+```
+
+- [ ] **Step 7**: `tier3_fallback_cv` (p10-3 Critical fix) — C/C++ are fallback-eligible (extract may fail on `.h` C++ headers or malformed code):
+
+```rust
+let tier3_fallback_cv = match code_lang {
+    "rust" | "python" | "typescript" | "javascript"
+    | "go" | "java" | "kotlin"
+    | "yaml" | "dockerfile" | "toml" | "json" | "xml" | "groovy" | "go-mod"
+    | "c" | "cpp"   // p10-1d:
+        => Some(CodeTextParagraphV1Chunker.chunker_version()),
+    _ => None,
+};
+```
+
+(The exact location of this match is in `ingest_one_code_asset` between ~lines 1921-1927 per the p10-3 critical fix.)
+
+- [ ] **Step 8**: Build:
+
+```bash
+cargo build -p kebab-app 2>&1 | tail -5
+```
+
+Expected: clean.
+
+- [ ] **Step 9**: Per-crate test (no regression):
+
+```bash
+cargo test -p kebab-app --lib -- --nocapture 2>&1 | tail -10
+```
+
+Expected: 52 PASS (existing baseline).
+
+- [ ] **Step 10**: Clippy + commit:
+
+```bash
+cargo clippy -p kebab-app --all-targets -- -D warnings
+git add crates/kebab-app/src/lib.rs
+git commit -m "$(cat <<'EOF'
+feat(p10-1d): activate C + C++ in ingest_one_code_asset dispatch
+
+Extends 4-arm match (parser_version / chunker_version / extract / chunks)
++ allowlist + tier3_fallback_cv list with "c" + "cpp" arms. C uses
+CAstExtractor + CodeCAstV1Chunker; C++ uses CppAstExtractor +
+CodeCppAstV1Chunker. Both langs are Tier 3-fallback-eligible (e.g. .h
+file with C++ syntax may fail tree-sitter-c parse → Tier 3 paragraph
+fallback).
+
+Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
+EOF
+)"
+```
+
+---
+
+## Task G: code_ingest_smoke integration tests (C + C++)
+
+**Files:**
+- Modify: `crates/kebab-app/tests/code_ingest_smoke.rs`
+
+- [ ] **Step 1**: Append 2 tests at the end of the file (mirror the existing tier1 tests `c_ast_v1_*` if present; if not, mirror `rust_ast_v1_*` or `go_ast_v1_*`):
+
+```rust
+#[test]
+fn tier1_c_ingest_searchable() {
+    let env = TestEnv::lexical_only();
+    let workspace = env.workspace_root();
+    std::fs::write(
+        workspace.join("parser.c"),
+        "#include <stdio.h>\n\nint parse_record(const char *line) {\n    if (line == NULL) return -1;\n    return 0;\n}\n",
+    )
+    .unwrap();
+
+    let report = env.ingest().expect("ingest");
+    assert!(report.new_docs >= 1, "expected at least 1 new doc");
+
+    let hits = env.search_code_lang("c", "parse_record").expect("search");
+    assert!(!hits.is_empty(), "expected at least 1 c hit");
+
+    match &hits[0].citation {
+        Citation::Code { symbol, lang, .. } => {
+            assert_eq!(symbol.as_deref(), Some("parse_record"), "C symbol must be function name only");
+            assert_eq!(lang.as_deref(), Some("c"));
+        }
+        other => panic!("expected Citation::Code, got {other:?}"),
+    }
+    assert_eq!(
+        hits[0].chunker_version.as_ref().map(|c| c.0.as_str()),
+        Some("code-c-ast-v1"),
+    );
+}
+
+#[test]
+fn tier1_cpp_ingest_searchable() {
+    let env = TestEnv::lexical_only();
+    let workspace = env.workspace_root();
+    std::fs::write(
+        workspace.join("chunker.cpp"),
+        "namespace kebab {\nnamespace chunk {\nclass Foo {\npublic:\n    void bar() { /* impl */ }\n};\n}\n}\n",
+    )
+    .unwrap();
+
+    let report = env.ingest().expect("ingest");
+    assert!(report.new_docs >= 1);
+
+    let hits = env.search_code_lang("cpp", "bar").expect("search");
+    assert!(!hits.is_empty(), "expected at least 1 cpp hit");
+
+    match &hits[0].citation {
+        Citation::Code { symbol, lang, .. } => {
+            // Symbol could be "kebab::chunk::Foo::bar" or "kebab::chunk::Foo" depending on which chunk hits first.
+            assert!(
+                symbol.as_deref().map_or(false, |s| s.starts_with("kebab::chunk::Foo")),
+                "C++ symbol must start with namespace::Class prefix, got {:?}", symbol
+            );
+            assert_eq!(lang.as_deref(), Some("cpp"));
+        }
+        other => panic!("expected Citation::Code, got {other:?}"),
+    }
+    assert_eq!(
+        hits[0].chunker_version.as_ref().map(|c| c.0.as_str()),
+        Some("code-cpp-ast-v1"),
+    );
+}
+```
+
+- [ ] **Step 2**: Run tests:
+
+```bash
+cargo test -p kebab-app --test code_ingest_smoke tier1_c_ingest tier1_cpp_ingest -- --nocapture 2>&1 | tail -30
+```
+
+Expected: 2 PASS.
+
+- [ ] **Step 3**: Full smoke regression:
+
+```bash
+cargo test -p kebab-app --test code_ingest_smoke -- --nocapture 2>&1 | tail -30
+```
+
+Expected: 18 PASS (16 existing + 2 new).
+
+- [ ] **Step 4**: Clippy + commit:
+
+```bash
+cargo clippy -p kebab-app --tests -- -D warnings
+git add crates/kebab-app/tests/code_ingest_smoke.rs
+git commit -m "$(cat <<'EOF'
+test(p10-1d): integration smoke tests for C + C++
+
+Verifies end-to-end ingest + search + Citation::Code shape:
+- tier1_c_ingest_searchable: .c file → --code-lang c search → symbol
+  = function name (no nesting), lang = "c", chunker_version = "code-c-ast-v1".
+- tier1_cpp_ingest_searchable: .cpp file → --code-lang cpp search →
+  symbol starts with namespace::Class prefix, lang = "cpp",
+  chunker_version = "code-cpp-ast-v1".
+
+Brings code_ingest_smoke to 18 tests (Rust 3 + Python 1 + TS 1 + JS 1 +
+Go 1 + Java 1 + Kotlin 1 + yaml 1 + dockerfile 1 + manifest 1 + shell 1 +
+yaml-fallback 1 + 2 reingest-unchanged regression + c 1 + cpp 1).
+
+Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
+EOF
+)"
+```
+
+---
+
+## Task H: frozen design §10 activation log
+
+**Files:**
+- Modify: `docs/superpowers/specs/2026-04-27-kebab-final-form-design.md`
+
+- [ ] **Step 1**: Find §10 activation log. Add p10-1D entry right after the p10-3 entry:
+
+```
+**p10-1D 활성화 (C + C++) (2026-05-21)**: Tier 1 chunker family 완료 — C (`code-c-ast-v1`, `.c`/`.h`) + C++ (`code-cpp-ast-v1`, `.cpp`/`.cc`/`.cxx`/`.hpp`/`.hh`/`.hxx`) AST chunker 활성화. C symbol = function name only; C++ symbol = `namespace::Class::method` (recursive namespace + class nesting). `.h` 가 C++ syntax 만나면 tree-sitter-c parse 실패 → p10-3 Tier 3 fallback 으로 자동 picked up.
+```
+
+- [ ] **Step 2**: Commit:
+
+```bash
+git add docs/superpowers/specs/2026-05-15-kebab-code-ingest-design.md \
+        docs/superpowers/specs/2026-04-27-kebab-final-form-design.md 2>/dev/null
+git add docs/superpowers/specs/2026-04-27-kebab-final-form-design.md
+git commit -m "$(cat <<'EOF'
+docs(p10-1d): activate C + C++ in frozen design §10
+
+P10 Tier 1 chunker family complete.
+
+Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
+EOF
+)"
+```
+
+---
+
+## Task I: README + HANDOFF + ARCHITECTURE + SMOKE + tasks/INDEX + tasks/p10/INDEX
+
+**Files:**
+- Modify: `README.md` (Mermaid + ingest row), `HANDOFF.md`, `docs/ARCHITECTURE.md`, `docs/SMOKE.md`, `tasks/INDEX.md`, `tasks/p10/INDEX.md`
+
+- [ ] **Step 1 — README.md**: Update the `kebab ingest` row's supported-langs list to include `.c` / `.h` → `code-c-ast-v1` and `.cpp`/`.cc`/`.cxx`/`.hpp`/`.hh`/`.hxx` → `code-cpp-ast-v1`. Extend `--code-lang c` / `--code-lang cpp` in the enumeration. Update the Mermaid `chunker[...]` node to include `code-c-ast-v1, code-cpp-ast-v1` in the brace.
+
+- [ ] **Step 2 — HANDOFF.md**: P10 row append `, **1D ✅ (C + C++ AST chunkers, code-c-ast-v1 + code-cpp-ast-v1 — v0.16.0)**`. Update 한 줄 요약 to include C/C++. Update 다음 후보 (drop p10-1D; remaining: P9-5 desktop / P8 audio).
+
+- [ ] **Step 3 — docs/ARCHITECTURE.md**: code parser table row: append C + C++ row mention. Flowchart `pcode` node: append `+ P10-1D`. Directory tree chunkers list: add `code_c_ast_v1.rs` + `code_cpp_ast_v1.rs`.
+
+- [ ] **Step 4 — docs/SMOKE.md**: Add a "## P10-1D C + C++ AST chunker" section after the P10-3 section. Walkthrough with sample.c + sample.cpp ingest + `--code-lang c` / `--code-lang cpp` search assertions. Append verification checklist entry.
+
+- [ ] **Step 5 — tasks/INDEX.md + tasks/p10/INDEX.md**: Flip p10-1D row ⏳ → ✅ (v0.16.0).
+
+- [ ] **Step 6**: Commit:
+
+```bash
+git add README.md HANDOFF.md docs/ARCHITECTURE.md docs/SMOKE.md tasks/INDEX.md tasks/p10/INDEX.md
+git commit -m "$(cat <<'EOF'
+docs(p10-1d): README/HANDOFF/ARCHITECTURE/SMOKE/INDEX sync
+
+P10 Tier 1 chunker family complete (Rust + Python + TS + JS + Go + Java +
+Kotlin + C + C++). Tier 2 (k8s + dockerfile + manifest) and Tier 3
+(paragraph fallback) already active. p10-1D 활성화 + ✅ flip.
+
+Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
+EOF
+)"
+```
+
+---
+
+## Task J: workspace test gate + clippy
+
+- [ ] **Step 1**: Disk check (`df -h /`) + optional `cargo clean`.
+
+- [ ] **Step 2**: `cargo test --workspace --no-fail-fast -j 1 2>&1 | tail -80`. Expected: all PASS.
+
+- [ ] **Step 3**: `cargo clippy --workspace --all-targets -- -D warnings 2>&1 | tail -30`. Expected: clean.
+
+---
+
+## Task K: version bump + gitea PR + release
+
+**Files:**
+- Modify: `Cargo.toml`
+
+- [ ] **Step 1**: Workspace `version = "0.15.0"` → `"0.16.0"`.
+
+- [ ] **Step 2**: `cargo build -p kebab-cli` to refresh Cargo.lock.
+
+- [ ] **Step 3**: Commit:
+
+```bash
+git add Cargo.toml Cargo.lock
+git commit -m "$(cat <<'EOF'
+chore: bump version 0.15.0 → 0.16.0 (p10-1d C + C++ AST chunkers)
+
+Minor bump — additive new chunker_versions code-c-ast-v1 + code-cpp-ast-v1
++ new routing langs c / cpp + new tree-sitter-c / tree-sitter-cpp workspace
+deps. P10 Tier 1 chunker family complete. No DB migration, no wire schema
+major bump.
+
+Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
+EOF
+)"
+```
+
+- [ ] **Step 4**: Push branch + open gitea PR via REST API. Title: `feat(p10-1d): C + C++ AST chunkers — P10 Tier 1 chunker family complete`.
+
+- [ ] **Step 5**: Wait for code-reviewer APPROVE → merge via gitea REST API → cut `gitea-release v0.16.0`.
+
+---
+
+## Verification matrix
+
+| 검증 | 명령 | 기대 |
+|------|------|------|
+| C symbol | `kebab search --code-lang c --json` | `Citation::Code.symbol = "<fn_name>"` |
+| C++ symbol | `kebab search --code-lang cpp --json` | `Citation::Code.symbol = "namespace::Class::method"` |
+| .h fallback | `.h` with C++ syntax → ingest | Tier 3 fallback: `chunker_version = "code-text-paragraph-v1"`, lang = c |
+| code_lang_breakdown | `kebab schema --json` | `"c": N`, `"cpp": M` |
+
+---
+
+## Risks reminder (구현 중 주의)
+
+- **tree-sitter grammar version resolution**: tree-sitter 0.26 호환 grammar. crates.io 최신 버전 default.
+- **tree-sitter-cpp 의 node-kind 명**: spec 의 가정 (`namespace_definition`, `class_specifier`, `function_definition`, `template_declaration`, `concept_definition`, etc.) 이 실제 grammar 와 일치하는지 fixture parse 로 검증.
+- **out-of-class method def 의 prefix 복원**: `void Foo::bar()` 의 declarator 가 `function_declarator > qualified_identifier > namespace_identifier "Foo" + identifier "bar"`. spec 의 `extract_fn_symbol` 이 이 chain 정확히 walk.
+- **Operator overload**: tree-sitter-cpp 의 `operator_name` 또는 `field_identifier` "operator+" 형태. fixture 로 검증.
+- **머지 후 deviation** 은 `tasks/HOTFIXES.md` dated 로그.

docs/superpowers/plans/2026-05-22-korean-trigram-tokenizer.md

@@ -0,0 +1,396 @@
+# 한국어 trigram FTS tokenizer + dogfood 버그픽스 구현 Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** kebab 의 FTS5 tokenizer 를 `unicode61` → `trigram` 으로 교체해 한국어 lexical 검색을 가능하게 하고, 같은 도그푸딩 라운드의 작은 버그 둘(C typedef struct 미노출, code_lang_breakdown 집계 단위)을 함께 닫는다.
+
+**Architecture:** 3개 독립 변경을 별도 PR(A/B/C)로 진행. PR-A 는 V007 migration 으로 `chunks_fts` shadow 테이블만 재구축(원본 `chunks`·embedding 불변) + `lexical.rs::build_match_string()` trigram 대응 재설계 + CLI/TUI 짧은 query 안내. PR-B 는 C extractor 에 typedef alias unit 방출 추가 + **`parser_version` `code-c-v1`→`code-c-v2` bump + same-workspace_path orphan purge** (Codex round 2 검증으로 추가). PR-C 는 wire additive 필드 + 기존 stats 필드 설명 정정. 셋 머지 후 v0.17.0 release cut.
+
+**Tech Stack:** Rust 2024, SQLite FTS5, refinery migrations, tree-sitter-c, cargo test.
+
+**작업 방식:** 코드는 Claude(`executor` agent), 각 PR diff 는 Codex + Gemini 가 리뷰(`/ask codex`·`/ask gemini`), PR 은 gitea-ops. design: `docs/superpowers/specs/2026-05-22-korean-trigram-tokenizer-design.md`.
+
+---
+
+## File Structure
+
+**생성:**
+- `migrations/V007__fts_trigram.sql` — chunks_fts 를 trigram tokenizer 로 재구축 + backfill
+
+**수정:**
+- `docs/superpowers/specs/2026-04-27-kebab-final-form-design.md` — §5.5 verbatim SQL 블록 + contentless 표현 정정
+- `crates/kebab-store-sqlite/tests/fts.rs` — CI diff-check 테스트 + 한국어 trigram (3자 이상) + 2자 query 0-hit 핀 + 영어 substring 테스트
+- `crates/kebab-search/src/lexical.rs` — `build_match_string()` 재설계 (필수) + BM25 snapshot 갱신
+- `crates/kebab-cli/src/main.rs` (또는 search wrapper) — 2자 미만 query + 0 결과 시 안내 메시지
+- `crates/kebab-tui/src/search.rs` — 동일 안내
+- `crates/kebab-parse-code/src/c.rs` — typedef-wrapped struct → synthetic unit + `PARSER_VERSION` bump
+- `crates/kebab-app/src/lib.rs` — ingest 경로의 same-workspace_path orphan purge (parser_version mismatch + asset 동일 케이스)
+- `crates/kebab-store-sqlite/src/fts.rs` — 모듈 헤더 주석의 "contentless FTS5" 표현 정정 (실제는 일반 FTS5 shadow)
+- `crates/kebab-store-sqlite/src/store.rs` — `code_lang_chunk_breakdown()` (JOIN documents)
+- `crates/kebab-app/src/schema.rs` — `Stats.code_lang_chunk_breakdown`
+- `docs/wire-schema/v1/schema.schema.json` — `code_lang_chunk_breakdown` additive 필드
+- `docs/SMOKE.md` — 한국어 검색 시나리오 추가
+- `README.md`, `HANDOFF.md`, `tasks/HOTFIXES.md`, `tasks/p10/p10-1d-c-cpp-ast-chunker.md`
+- `Cargo.toml` — workspace `version`
+
+(`crates/kebab-cli/src/wire.rs` 는 수정하지 않음 — `wire_schema()` 가 `SchemaV1` 을 serde 로 통째 직렬화하므로 변경 2 의 새 필드가 자동 포함됨.)
+
+---
+
+## PR-A — FTS5 trigram tokenizer
+
+브랜치: `feat/korean-trigram-tokenizer`. design doc 도 이 PR 에 포함(아직 main 에 commit 안 됨).
+
+### Task A1: 현재 query builder 동작 파악 + SQLite 버전 확인
+
+Codex 리뷰로 현재 `build_match_string()` (lexical.rs:177) 이 trigram 비호환이라는 점은 이미 확정 (whitespace split → `"..."` AND 결합 → 한국어 multi-token 0-hit). 본 task 는 builder 의 정확한 동작 기록과 SQLite 버전 확인이 목적이며, 재설계 자체는 Task A5 (필수).
+
+**Files:**
+- Read: `crates/kebab-search/src/lexical.rs` (`build_match_string()` 본문, MATCH query 빌드 라인 260-290, lexical snapshot 라인 506 부근)
+
+- [x] **Step 1: builder 동작 기록** — `build_match_string()` (lexical.rs:177-200) baseline:
+  1. `text.trim()` → trimmed. 빈 → `None` 반환.
+  2. `strip_single_quotes(trimmed)` 매치 시 (= `'...'` 전체 감싸기, closing quote 가 trimmed 의 마지막 char) → inner.trim() 빈 아니면 `Some(inner.to_string())` (raw FTS5 verbatim mode).
+  3. 그 외 → `trimmed.split_whitespace().map(escape_fts5_token).collect()` → 빈이면 `None`, 아니면 ` ` join (FTS5 default implicit AND).
+  - `escape_fts5_token` (lexical.rs:218): 토큰을 `"..."` 으로 wrap, inner `"` 은 doubling.
+  - prefix `*` 별도 처리 없음 — 사용자가 raw mode 로 입력해야.
+  - raw mode 진입 조건: 사용자가 single quote `'...'` 로 trimmed 전체를 감싼 경우 (`lexical.rs:167` 주석에 명시).
+  - MATCH 호출: lexical.rs:281 `WHERE chunks_fts MATCH ?` (bound parameter).
+
+- [x] **Step 2: SQLite 버전 확인** — `Cargo.toml`: `rusqlite = { version = "0.32", features = ["bundled"] }` + `Cargo.lock` `libsqlite3-sys = "0.30.1"` (system sqlite 무관, in-tree 빌드). libsqlite3-sys 0.30.1 의 번들 SQLite ~3.46.x — trigram (3.34+) 사용 가능. design 결정대로 `tokenize = 'trigram'` 단독 사용 (case-insensitive 기본). `remove_diacritics` 옵션 미사용.
+
+- [x] **Step 3: lexical snapshot 위치 확인** — Codex round 1 의 "lexical.rs:506" 은 `fn normalize_bm25` (BM25 score → (0,1] mapping) 였음 — numerical transformation 이라 token stream 영향 없음. 진짜 snapshot 은:
+  - `crates/kebab-search/tests/lexical.rs:1012` `lexical_snapshot_run_1` — fixture 기반, `KEBAB_UPDATE_SNAPSHOTS=1` env 로 regenerate, "baseline snapshot must exist; run with KEBAB_UPDATE_SNAPSHOTS=1 to seed".
+  - `crates/kebab-search/tests/hybrid.rs:121` `hybrid_snapshot_run_1` — 동일 패턴 (`hybrid_snapshot drift`). 한국어 trigram 영향 받음 (token stream 변경).
+  - inline `crates/kebab-search/src/lexical.rs:592` `normalize_bm25_top_score_in_unit_interval` — numerical, 영향 없음 (회귀 없음 확인만).
+  Task A4 Step 5 에서 lexical_snapshot_run_1 + hybrid_snapshot_run_1 둘 다 regenerate.
+
+### Task A2: V007 migration 작성
+
+**Files:**
+- Create: `migrations/V007__fts_trigram.sql`
+- Read: `migrations/V002__fts.sql` (trigger 본문 verbatim 복사용)
+
+- [x] **Step 1: V007 작성** — 아래 내용으로 생성. 컬럼 구성은 V002 와 동일, `tokenize` 만 교체. trigger 본문은 V002 와 동일.
+
+```sql
+-- V007__fts_trigram.sql
+-- Replace the chunks_fts tokenizer: unicode61 -> trigram.
+-- Korean is agglutinative; unicode61 tokenizes whole eojeol (with
+-- particles attached) so substring matching fails. trigram indexes
+-- 3-character grams, enabling Korean partial matches. See design §5.5
+-- and tasks/HOTFIXES.md (2026-05-22).
+--
+-- chunks_fts is a shadow of chunks; this migration rebuilds it in
+-- place and backfills from chunks, so no re-ingest is required.
+
+DROP TRIGGER IF EXISTS chunks_au;
+DROP TRIGGER IF EXISTS chunks_ad;
+DROP TRIGGER IF EXISTS chunks_ai;
+DROP TABLE IF EXISTS chunks_fts;
+
+CREATE VIRTUAL TABLE chunks_fts USING fts5(
+  chunk_id     UNINDEXED,
+  doc_id       UNINDEXED,
+  heading_path,
+  text,
+  tokenize = 'trigram'
+);
+
+CREATE TRIGGER chunks_ai AFTER INSERT ON chunks BEGIN
+  INSERT INTO chunks_fts(chunk_id, doc_id, heading_path, text)
+  VALUES (new.chunk_id, new.doc_id, new.heading_path_json, new.text);
+END;
+CREATE TRIGGER chunks_ad AFTER DELETE ON chunks BEGIN
+  DELETE FROM chunks_fts WHERE chunk_id = old.chunk_id;
+END;
+CREATE TRIGGER chunks_au AFTER UPDATE ON chunks BEGIN
+  DELETE FROM chunks_fts WHERE chunk_id = old.chunk_id;
+  INSERT INTO chunks_fts(chunk_id, doc_id, heading_path, text)
+  VALUES (new.chunk_id, new.doc_id, new.heading_path_json, new.text);
+END;
+
+INSERT INTO chunks_fts(chunk_id, doc_id, heading_path, text)
+  SELECT chunk_id, doc_id, heading_path_json, text FROM chunks;
+```
+
+> Step 1 전에 `migrations/V002__fts.sql` 의 `CREATE VIRTUAL TABLE` 컬럼 목록과 trigger 본문을 실제로 대조해, 위 SQL 이 V002 와 trigger 본문·컬럼명(`heading_path_json` 등)에서 정확히 일치하는지 확인한다. 다르면 V002 를 source 로 맞춘다.
+
+- [x] **Step 2: migration 적용 확인** — `cargo test -p kebab-store-sqlite` 통과 (10/10 fts tests + 모든 store test PASS). V007 backfill 도 정상 동작.
+
+### Task A3: design §5.5 verbatim + CI diff-check 갱신
+
+**Files:**
+- Modify: `docs/superpowers/specs/2026-04-27-kebab-final-form-design.md` (§5.5, 라인 ~1024-1043)
+- Modify: `crates/kebab-store-sqlite/tests/fts.rs` (`fts_v002_matches_design_section_5_5_verbatim`, 라인 ~408-435)
+
+- [x] **Step 1: diff-check 테스트 baseline 확인** — A2 검증에서 `fts_v002_matches_design_section_5_5_verbatim` 는 PASS (V002 vs design 둘 다 unicode61 시점이라 match). V007 추가 자체는 기존 test 안 깨뜨림.
+
+- [x] **Step 2: design §5.5 갱신** — `tokenize = 'unicode61 remove_diacritics 2'` → `'trigram'`. §5.5 본문 위에 한국어 trigram 채택 사유 + trade-off + "contentless 가 아님" 명시 prose 한 단락 추가.
+
+- [x] **Step 3: diff-check 테스트를 V007 대상으로 갱신** — `extract_migration_5_5_verbatim_block()` 의 `include_str!` path 를 `V007__fts_trigram.sql` 로, 함수명 `fts_v002_matches_design_section_5_5_verbatim` → `fts_v007_matches_design_section_5_5_verbatim`, assertion msg 갱신.
+
+- [x] **Step 4: 테스트 통과 확인** — `cargo test -p kebab-store-sqlite --test fts` → 10/10 PASS (`fts_v007_matches_design_section_5_5_verbatim` 포함).
+
+- [ ] **Step 5: Commit** — A2 + A3 한 묶음으로 commit.
+
+### Task A4: 한국어/영어 trigram 매칭 테스트
+
+**Files:**
+- Create: `fixtures/search/korean/hash-table.md` (또는 동등) — 도그푸딩 한국어 문서 복사
+- Modify: `crates/kebab-store-sqlite/tests/fts.rs`
+- Modify: `crates/kebab-app/tests/search_korean.rs` (회귀 핀 + multi-token assert + fixture 통합)
+- Update: lexical BM25 snapshot (A1 Step 3 위치)
+
+- [x] **Step 0: 한국어 fixture 도입 (Gemini round 3 medium)** — 도그푸딩 실 문서 (`/build/cache/dogfood-p10b/workspace/docs/hash-table.md`, 한국어 위키 mediawiki HTML 출력 4512줄, CC-BY-SA) 는 크기·라이선스 부담으로 직접 commit 회피. 대신 도그푸딩 query 들 (`충돌은`/`해시 충돌`/`시 충`/`해시충`/`충돌`) 을 모두 cover 하는 **합성 fixture** `fixtures/search/korean/hash-table.md` 작성 + commit. 검증 query 별 기대 동작:
+  - raw `MATCH '충돌은'` → hit (`해시 충돌은 발생한다` 가 원문에 있음)
+  - quoted `MATCH '"해시 충돌"'` → hit (whole phrase)
+  - quoted `MATCH '"시 충"'` → hit (phrase)
+  - raw `MATCH '해시충'` → 0-hit (원문에 공백 없는 `해시충` 연속 없음)
+  - raw `MATCH '충돌'` (2자) → 0-hit (trigram 구조)
+  실 위키 문서 fixture 가 필요한 후속 검증은 별도 task 로 deferral.
+
+- [x] **Step 1: 한국어 trigram 매칭 테스트** — `fts_trigram_korean_3char_substring_hits` (fts.rs §7). 5개 assert (raw 3자 hit, quoted phrase hit, `해시충` 0-hit) 모두 통과.
+
+- [x] **Step 1b: 2자 query 0-hit 핀** — `fts_trigram_korean_short_query_zero_hit_pinned` (`충돌`/`키` 0-hit).
+
+- [ ] **Step 1c: multi-token 한국어 query 테스트** — `crates/kebab-search` 또는 `crates/kebab-app` 통합 레벨. 사용자 query `해시 충돌` 이 `build_match_string()` 을 통해 hit. Expected: A4 시점 FAIL (현재 builder 가 `"해시" "충돌"` AND 로 trigram 0-hit), Task A5 builder 재설계 후 PASS.
+
+- [x] **Step 2: 영어 substring 동작 핀** — `fts_trigram_english_substring_hits` (`token`→`tokenizer`, `to` 0-hit).
+
+- [x] **Step 3: 통과 확인 (부분)** — `cargo test -p kebab-store-sqlite --test fts` → 13/13 PASS (Step 1/1b/2 + 기존 10). Step 1c 는 A5 후.
+
+- [ ] **Step 4: 통합 회귀 확인** — `cargo test -p kebab-app search_korean` (`러스트` 3자라 trigram 으로도 통과). `search_korean.rs` 에 `해시 충돌` multi-token assert 추가 (A5 후 통과).
+
+- [ ] **Step 5: lexical BM25 snapshot 갱신** — A1 Step 3 에서 식별한 snapshot 파일을 trigram token stream 기준으로 갱신 (`cargo insta accept` 또는 수동). snippet token 단위가 trigram 으로 바뀌므로 word budget 관련 테스트 기대값도 함께 검토.
+
+- [ ] **Step 6: Commit** — `git commit` (test: korean + english trigram matching + bm25 snapshot).
+
+### Task A5: lexical.rs query builder 재설계 (필수)
+
+Codex 검증: 현재 `build_match_string()` (lexical.rs:177) 은 whitespace split 후 각 토큰을 `"..."` 로 감싸 implicit AND 결합. 각 토큰이 2자 이하면 trigram MATCH 가 0-hit → `해시 충돌` 같은 multi-token 한국어 query 가 깨짐. 본 task 는 builder 를 trigram 대응으로 재설계.
+
+**사용자 결정** (2자 이하 한국어 query 정책): lexical core 는 정상 0-hit (변경 없음), 안내 메시지는 CLI/TUI 레이어가 출력 ("3자 이상 키워드 권장").
+
+**A1 baseline 노트** (Task A1 Step 1 에서 채움):
+
+`build_match_string(text: &str) -> Option<String>` (lexical.rs:177-200) baseline:
+
+1. `text.trim()` → trimmed. 빈 → `None`.
+2. `strip_single_quotes(trimmed)` 매치 시 (single quote `'...'` 가 trimmed 전체 감쌈, closing quote 가 마지막 char — `'foo' bar` 는 raw 아님) → inner.trim() 빈 아니면 `Some(inner.to_string())` (raw FTS5 verbatim).
+3. 그 외 → `trimmed.split_whitespace().map(escape_fts5_token).collect()` → 빈이면 `None`, 아니면 ` ` join (FTS5 default implicit AND).
+
+`escape_fts5_token(tok)` (lexical.rs:218): `"..."` wrap + inner `"` doubling.
+
+재설계 시 회귀 방지 — raw mode (single quote `'...'`) 진입 조건은 그대로 유지. escape_fts5_token 도 그대로 (trigram 도 FTS5 special char escape 필요). 변경은 비-raw 경로의 토큰 합성만.
+
+SQLite: rusqlite 0.32 + libsqlite3-sys 0.30.1 **bundled** (in-tree). SQLite ~3.46.x → trigram 사용 가능.
+
+Snapshot: `crates/kebab-search/tests/lexical.rs::lexical_snapshot_run_1` + `crates/kebab-search/tests/hybrid.rs::hybrid_snapshot_run_1` (둘 다 `KEBAB_UPDATE_SNAPSHOTS=1` 로 regenerate). inline `normalize_bm25_top_score_in_unit_interval` 는 numerical 영향 없음.
+
+**Files:**
+- Modify: `crates/kebab-search/src/lexical.rs` (`build_match_string()`)
+- Modify: `crates/kebab-cli/src/main.rs` 또는 search 결과 처리 wrapper — 안내 메시지
+- Modify: `crates/kebab-tui/src/search.rs` 또는 결과 렌더 — 안내 메시지
+
+- [ ] **Step 1: builder 재설계 테스트 작성 (실패 확인)** — `해시 충돌` multi-token 한국어 query + 한영 혼합 query (`Rust 충돌은`) 가 hit 하는 테스트. raw FTS mode 진입 (사용자가 single quote `'...'` 로 감싼 경우, `lexical.rs:167`) 회귀 테스트. Expected: FAIL.
+
+- [ ] **Step 2: `build_match_string()` 재설계** — Codex round 2 권장안 (검증된 알고리즘):
+  1. raw single-quote mode (사용자가 single quote `'...'` 로 감싼 경우, `lexical.rs:167`) 는 기존 유지.
+  2. `whole = escape_fts5_phrase(trimmed)` 를 항상 첫 후보로 — 단 `trimmed.chars().count() >= 3` 일 때만.
+  3. whitespace 로 분리된 토큰 중 `chars().count() >= 3` 만 escaped token AND 후보 생성.
+  4. 후보가 둘 다 있으면 `(<whole>) OR (<token_and>)`, 하나만 있으면 그대로.
+  5. **후보가 하나도 없으면 `None` 반환 (빈 MATCH 금지 — FTS5 syntax error).** 호출자는 None 시 SQL 실행 자체를 회피하고 빈 결과를 반환.
+  이러면 `해시 충돌` (각 토큰 2자, whole 5자) → whole phrase 후보로 hit, `충돌` (whole 2자, token 0개) → None → 0-hit, `Rust 충돌은` (token 2개 모두 ≥3) → AND + whole 모두 후보 → OR hit. escape 는 trigram 도 `"`, `*` 처리 필요 — 기존 로직 보강.
+
+- [ ] **Step 3: 테스트 통과 확인** — Step 1 신규 + Task A4 Step 1c·4 (`해시 충돌`) PASS.
+
+- [ ] **Step 4: 안내 메시지 — CLI** — `crates/kebab-cli/src/main.rs` 의 `kebab search` 결과 처리에서, 결과가 비어 있고 **`query.trim().chars().count() < 3`** (trimmed 전체 기준) 일 때 stderr 에 "3자 이상 키워드 권장 (trigram tokenizer 제약)" 한 줄. **"모든 토큰이 3자 미만" 조건은 사용 금지** (Codex round 3 medium) — `해시 충돌` 같은 valid whole-phrase query 에 false trigger 회피. `--json` 모드에서는 stderr 안내 미출력 (wire hint 는 Step 4b 에서 별도 전달).
+
+- [ ] **Step 4b: wire `search_response.v1` 에 `hint` 필드 추가 (MCP 가시성, Gemini round 3 high)** — `--json` 모드와 MCP 가 사용하는 search response 에도 hint 가 전달돼야 LLM/agent 가 "0 결과 + 3자 미만" 케이스를 이해함. 변경:
+  - `crates/kebab-app/src/schema.rs` (또는 search 응답 type 정의 위치) 의 `SearchResponse` 에 `hint: Option<String>` additive 필드 추가.
+  - search 실행 결과가 비어 있고 query trimmed.chars().count() < 3 일 때 `hint = Some("3자 이상 키워드 권장 (trigram tokenizer 제약)")`, 그 외 None.
+  - `crates/kebab-mcp` 의 `search` tool 결과 직렬화에 hint 포함 (serde 자동이면 OK, 확인).
+  - `docs/wire-schema/v1/search_response.schema.json` (또는 search 응답 스키마 파일) 에 `hint: { type: ["string", "null"] }` additive 필드 명세.
+  - CLI 의 Step 4 stderr 안내는 사람 가시성, wire hint 는 agent 가시성 — 둘은 보완적, 같은 조건 사용.
+
+- [ ] **Step 5: 안내 메시지 — TUI** — Codex round 2/3 권장 구현 (`search.rs`/`app.rs`/`run.rs` 실제 구조 기반):
+  - `SearchState` (`crates/kebab-tui/src/app.rs:116` 근처) 에 `short_query_hint: Option<String>` 필드 추가.
+  - **Stale hint 방지 (Codex round 3 high)**: 현재 generation 은 `fire_search` 때만 증가하고 input mutation 때는 증가 안 함 — `poll_worker` 가 worker 결과 수신 시 `last_query == 현재 SearchState.input.content && last_mode == 현재 mode` 일치 시만 hint 를 세팅한다. 불일치 시 (사용자가 새 query 입력 중) hint 세팅 skip — stale worker 결과로 새 input 화면이 덮이지 않게.
+  - 추가로 input 이 변경되면 (`set_input` 등) `short_query_hint = None` reset.
+  - hint 세팅 조건: `last_query.trim().chars().count() < 3` (trimmed 전체 기준, Codex round 3 medium 으로 통일 — 토큰 기반 분기 사용 금지) + hits 비어 있음 + raw mode 아님.
+  - 표시: `dynamic_status` (`crates/kebab-tui/src/run.rs:389` 근처) 또는 Search pane 의 결과 영역 empty render 분기에서 `short_query_hint` 가 Some 일 때 한 줄 표시.
+
+- [ ] **Step 6: 안내 메시지 테스트** — CLI stderr 캡처 + 미출력 케이스 (`--json`, 3자 이상 query, 결과 ≥ 1) 각각 테스트. TUI 안내 표시 unit 테스트.
+
+- [ ] **Step 7: 전체 검증** — `cargo test -p kebab-search -p kebab-cli -p kebab-tui` → 신규 + 기존 PASS.
+
+- [ ] **Step 8: Commit** — `git commit` (feat: trigram-aware query builder + short-query guidance).
+
+### Task A6: 사용자 문서 동기화
+
+**Files:**
+- Modify: `README.md`, `HANDOFF.md`, `tasks/HOTFIXES.md`, `docs/SMOKE.md`
+
+- [ ] **Step 1: README** — 검색/Configuration 절에 한 줄: 한국어 포함 KB 의 `--mode lexical`/`hybrid` 가 trigram 3-gram substring 으로 동작 (3자 이상 query 권장). SQLite 파일 (`kebab.sqlite`) 크기가 trigram 인덱스 비대화로 증가 (도그푸딩 KB 기준 ~2-5배 또는 수백 MB 단위, Gemini round 3 low) 한 줄.
+
+- [ ] **Step 2: HANDOFF** — "머지 후 발견된 버그/결정" 절의 2026-05-22 한국어 lexical 항목을 "v0.17.0 trigram 으로 해소" 로 갱신. "P10 dogfooding 백로그" 의 한국어 tokenizer 항목 상태 갱신.
+
+- [ ] **Step 3: HOTFIXES** — 2026-05-22 한국어 lexical 항목의 "Next step (미진행)" 을 v0.17.0 / V007 으로 closure 처리. trigram 채택, 영어 동작 변경, 디스크 용량 증가, `heading_path` JSON 노이즈 후속을 dated 항목으로 기록.
+
+- [ ] **Step 4: SMOKE.md** — 한국어 검색 시나리오 추가 (Codex round 3 high: hit query 가 자기 단언과 모순되지 않게):
+  - fixture: A4 Step 0 에서 commit 한 `fixtures/search/korean/hash-table.md` (또는 동등) 를 ingest.
+  - `kebab search --mode lexical '충돌은'` (원문에 공백 없이 3자 연속 substring) → hit 확인.
+  - `kebab search '해시 충돌'` (multi-token, builder 가 whole phrase 후보로 hit) → hit 확인.
+  - `kebab search --mode lexical '충돌'` (2자) → 0-hit + "3자 이상 키워드 권장" stderr 안내 확인.
+  - `kebab search --mode lexical '충돌' --json` → 결과 hits 빈 배열 + `hint` 필드 (Step 4b) 포함 확인.
+  - V007 자동 backfill (re-ingest 불필요) + SQLite 파일 크기 증가 안내 (도그푸딩 KB 기준 ~2-5배 또는 수백 MB).
+
+- [ ] **Step 4b: SKILL.md (Gemini round 3 medium)** — `integrations/claude-code/kebab/SKILL.md` 의 `mcp__kebab__search` 섹션 또는 Don't 섹션에 한 줄 추가: "한국어 lexical 검색 시 3자 이상의 키워드를 사용하는 것이 검색 품질·recall 측면에서 유리. 2자 이하 한국어 query (예: '값', '키', '충돌') 는 trigram tokenizer 구조상 lexical 0-hit — search_response 의 `hint` 필드 확인 권장."
+
+- [ ] **Step 5: Commit** — `git commit` (docs: trigram tokenizer — README/HANDOFF/HOTFIXES/SMOKE/SKILL).
+
+### Task A7: PR-A 생성 + 리뷰 루프
+
+- [ ] **Step 1: 전체 검증** — `cargo test --workspace --no-fail-fast -j 1` + `cargo clippy --workspace --all-targets -- -D warnings`. 둘 다 통과 확인.
+- [ ] **Step 2: PR 생성** — gitea-ops 로 `feat/korean-trigram-tokenizer` → main PR. 본문에 design doc 링크 + V007 자동 backfill(re-ingest 불필요) 명시.
+- [ ] **Step 3: 리뷰** — PR diff 를 `/ask codex` + `/ask gemini` 로 리뷰. 두 리뷰 종합 후 반영 — 반영 시 같은 브랜치에 commit, 재검증.
+- [ ] **Step 4: 머지** — 리뷰 반영 완료 + CI green 후 머지.
+
+---
+
+## PR-B — C typedef-wrapped struct fix
+
+브랜치: `feat/c-typedef-struct-unit`.
+
+### Task B1: typedef extractor fix (TDD)
+
+**Files:**
+- Modify: `crates/kebab-parse-code/src/c.rs` (extractor 라인 ~254-262, `PARSER_VERSION` 라인 34, 테스트 라인 ~492-505)
+
+- [ ] **Step 1: 기존 테스트 재작성(실패 확인)** — `c_extractor_typedef_struct_falls_into_glue` 를 `c_extractor_typedef_struct_emits_unit` 으로 바꾼다. `typedef struct { int x; int y; } Point;` 입력에서 `Point` 라는 이름의 unit 이 방출되는지 assert. Expected: FAIL (현재는 glue 로 빠짐).
+
+- [ ] **Step 2: extractor 수정** — top-level `type_definition` 노드 처리: 내부에 anonymous `struct_specifier`/`enum_specifier`/`union_specifier`(name 필드 없음)가 있으면, `type_definition` 의 `declarator`(typedef alias)에서 이름을 추출해 그 이름으로 unit 을 방출한다. named struct 경로는 그대로 둔다. 코드 변경 전 `c.rs` 의 현재 노드 분기(`struct_specifier | enum_specifier | union_specifier` arm)와 tree-sitter-c 의 `type_definition` 자식 구조를 읽고 맞춘다.
+
+- [ ] **Step 3: 테스트 통과 확인** — `cargo test -p kebab-parse-code c_extractor_typedef` → PASS.
+
+- [ ] **Step 4: named struct 회귀 확인** — `cargo test -p kebab-parse-code` 전체 → 기존 C extractor 테스트(named struct, glue 등) 모두 PASS.
+
+- [ ] **Step 5: parser_version bump** — `crates/kebab-parse-code/src/c.rs:34` 의 `PARSER_VERSION = "code-c-v1"` 을 `"code-c-v2"` 로 bump. **chunker (`crates/kebab-chunk/src/code_c_ast_v1.rs` 의 `code-c-ast-v1`) 는 건드리지 않는다** — extractor output 만 바뀌고 chunker 로직 동일. C extractor 스냅샷/통합 테스트가 `parser_version` 문자열을 assert 하면 `code-c-v2` 로 갱신.
+
+- [ ] **Step 5b: same-workspace_path orphan purge (Codex round 2 critical)** — parser_version bump 만으로 doc_id 가 갱신되지만, **파일 bytes 동일 (asset_id 동일) 케이스에서 기존 ingest 의 `stale_chunk_ids_at` (asset_id 변경 기반) 가 발동하지 않아 옛 doc_id row + 옛 chunk row + Lance vector 가 orphan 으로 남고 `idx_docs_workspace_path` UNIQUE 충돌이 날 수 있다**. 보강:
+  - **신규 helper 도입 (Codex round 3 medium)**: P7-3 의 `stale_chunk_ids_at` (`store.rs:440`) / `purge_orphan_at_workspace_path` (`store.rs:497`) 는 `asset_id != new_asset_id` 전용이라 parser-only bump 케이스에 no-op. 기존 helper 그대로 호출/확장보다 새 helper 두 개를 `crates/kebab-store-sqlite/src/store.rs` 에 추가:
+    - `stale_chunk_ids_for_workspace_path_except_doc_id(workspace_path, new_doc_id) -> Vec<ChunkId>` — 같은 workspace_path 의 다른 doc_id 가 가진 chunk_ids 수집.
+    - `purge_document_at_workspace_path_except_doc_id(workspace_path, new_doc_id)` — 같은 workspace_path 의 다른 doc_id row 와 그 chunks 제거.
+  - `crates/kebab-app/src/lib.rs` 의 code asset ingest 분기 (parser mismatch 판정 직후, `lib.rs:812`/`882` 근처) 에서 위 두 helper 순차 호출: chunk_ids 수집 → `VectorStore::delete_by_chunk_ids` (P7-3 hotfix helper, 이건 chunk_id 기반이라 재사용 가능) → document/chunks row delete → 새 doc_id 로 정상 ingest 계속.
+  - 테스트: fixture C 파일을 `code-c-v1` 로 한 번 ingest → `PARSER_VERSION` 을 `v2` 로 모의 변경 후 같은 fixture 재 ingest → 옛 doc_id row 사라지고 새 doc_id 만 남음 + Lance vector 도 새 chunk_ids 만 존재 + UNIQUE 충돌 없음 확인.
+
+- [ ] **Step 5c: 회귀 테스트 — 다른 asset 시 기존 purge 동작 유지** — bytes 가 실제로 바뀐 케이스 (asset_id 변경) 에서 `stale_chunk_ids_at` 가 기존대로 정리하는지 확인 (Step 5b 변경이 기존 경로 안 깨뜨리는지).
+
+- [ ] **Step 6: 테스트 통과 확인** — `cargo test -p kebab-parse-code` 전체 → PASS.
+
+- [ ] **Step 7: Commit** — `git commit` (fix: C typedef-wrapped struct emits named unit, parser_version code-c-v2).
+
+### Task B2: HOTFIXES + spec 갱신, PR-B
+
+**Files:**
+- Modify: `tasks/HOTFIXES.md`, `tasks/p10/p10-1d-c-cpp-ast-chunker.md`
+
+- [ ] **Step 1: HOTFIXES** — 2026-05-21 "typedef-wrapped struct/enum in C falls into glue" 항목의 Status/Next step 을 v0.17.0 closure 로 갱신.
+- [ ] **Step 2: spec Risks** — `p10-1d-c-cpp-ast-chunker.md` 의 Risks/notes 에 typedef alias unit 방출(top-level 한정, nested 익명 struct 는 여전히 glue) 을 한 줄로 갱신. frozen spec 본문은 건드리지 않고 Risks 절만.
+- [ ] **Step 3: Commit + PR** — `git commit` (docs) → gitea-ops 로 PR-B 생성.
+- [ ] **Step 4: 리뷰 루프** — `/ask codex` + `/ask gemini` 리뷰 → 반영 → 머지.
+
+---
+
+## PR-C — code_lang_chunk_breakdown
+
+브랜치: `feat/code-lang-chunk-breakdown`.
+
+### Task C1: store 함수 추가 (TDD)
+
+**Files:**
+- Modify: `crates/kebab-store-sqlite/src/store.rs` (`code_lang_breakdown` 인접, 라인 ~801-825)
+
+- [ ] **Step 1: 테스트 작성(실패 확인)** — `code_lang_chunk_breakdown()` 이 `chunks` 테이블 기준 언어별 chunk 수를 반환하는지 보는 store 테스트 추가. 한 doc 에 여러 chunk 인 fixture 로 doc 집계와 다른 값이 나옴을 확인. Expected: FAIL (함수 미존재).
+
+- [ ] **Step 2: 함수 구현** — 기존 `code_lang_breakdown()` 패턴을 그대로 따르되 source 를 `chunks` 로: 언어 식별 컬럼을 `chunks` 에서 끌어온다. `chunks` 에 code_lang 이 직접 없으면 `chunks JOIN documents` 로 `documents` 의 code_lang 을 끌어 `COUNT(chunks)`. Step 2 전에 `chunks` 와 `documents` 스키마에서 code_lang 이 어디에 있는지 확인한다. 반환 타입은 `code_lang_breakdown` 과 동일한 `BTreeMap<String, u32>`.
+
+- [ ] **Step 3: 테스트 통과 확인** — `cargo test -p kebab-store-sqlite code_lang_chunk` → PASS.
+
+- [ ] **Step 4: Commit** — `git commit` (feat: code_lang_chunk_breakdown store query).
+
+### Task C2: wire 필드 추가 (TDD)
+
+**Files:**
+- Modify: `crates/kebab-app/src/schema.rs` (`Stats`, 라인 ~69·170·202-219)
+- Modify: `docs/wire-schema/v1/schema.schema.json` (`code_lang_chunk_breakdown` 필드)
+
+- [ ] **Step 1: stats 테스트 확장 (실패 확인)** — `schema.rs` 의 `stats_includes_code_lang_and_repo_breakdown_fields` 테스트에 `code_lang_chunk_breakdown` 필드 존재·값 검증 추가. fixture 는 한 doc 에 여러 chunks (doc count 와 chunk count 가 다른 값으로 채워지는지 확인). Expected: FAIL (필드 미존재).
+
+- [ ] **Step 2: Stats 필드 추가** — `Stats` 에 `code_lang_chunk_breakdown: BTreeMap<String, u32>` 추가, stats 빌드 지점에서 Task C1 의 `code_lang_chunk_breakdown()` 호출로 채운다. 기존 `code_lang_breakdown` 필드는 유지 (제거 시 wire breaking).
+
+- [ ] **Step 3: wire.rs 자동 직렬화 확인** — `crates/kebab-cli/src/wire.rs::wire_schema()` 는 `SchemaV1` 을 serde 로 통째 직렬화하므로 별도 코드 수정 불필요. 신규 필드가 wire JSON 출력에 자동 포함됨을 `cargo test -p kebab-cli wire` 의 기존 schema wrapper 테스트가 확인 (또는 신규 assertion 추가).
+
+- [ ] **Step 4: 테스트 통과 확인** — `cargo test -p kebab-app schema` + `cargo test -p kebab-cli` → PASS.
+
+- [ ] **Step 5: wire schema JSON 갱신 (필수) + 기존 필드 설명 정정** — `docs/wire-schema/v1/schema.schema.json` 의 `Stats` 정의에:
+  - `code_lang_chunk_breakdown` 을 기존 `code_lang_breakdown` 과 동일한 형태 (`{"type": "object", "additionalProperties": {"type": "integer", "minimum": 0}}`) 로 additive 추가.
+  - Gemini round 2 발견: 기존 `code_lang_breakdown`·`repo_breakdown` 의 description 이 "chunk count" 로 잘못 적혀 있으면 (실제 구현은 doc count) "doc count" 로 정정. 추가 필드 `code_lang_chunk_breakdown` description 은 "chunk count" 로 명시.
+  CI 가 schema-vs-impl 대조를 한다면 함께 통과 확인.
+
+- [ ] **Step 6: Commit + PR** — `git commit` (feat: code_lang_chunk_breakdown wire field) → gitea-ops 로 PR-C 생성.
+
+- [ ] **Step 7: 리뷰 루프** — `/ask codex` + `/ask gemini` 리뷰 → 반영 → 머지.
+
+---
+
+## Release — v0.17.0
+
+### Task R1: version bump + release cut
+
+- [ ] **Step 1: 선행 확인** — PR-A·B·C 셋 다 main 에 머지됐는지 확인. `git pull` 후 `cargo test --workspace --no-fail-fast -j 1` green.
+- [ ] **Step 2: version bump** — `Cargo.toml` workspace `version` `0.16.1` → `0.17.0`. `cargo build` 로 `Cargo.lock` 자동 갱신.
+- [ ] **Step 3: Commit** — `git commit` (`chore: bump version 0.16.1 → 0.17.0`).
+- [ ] **Step 4: release** — gitea-ops 의 `gitea-release v0.17.0`. release notes: 한국어 lexical 검색 trigram 동작, 영어 lexical substring 동작 변경, C typedef symbol 노출, `schema.v1.stats.code_lang_chunk_breakdown` 신규 필드, V007 자동 마이그레이션(re-ingest 불필요).
+- [ ] **Step 5: HANDOFF/INDEX** — `HANDOFF.md` 한 줄 요약의 version (`v0.17.0`)·Phase 표 갱신. `tasks/INDEX.md` 의 P10 섹션 하단에 "P10 Dogfooding Feedback" 섹션을 만들어 v0.17.0 작업 (한국어 trigram + C typedef + code_lang_chunk_breakdown) 을 listup (P9 의 fb-01~42 형식 참고, Gemini round 2 권장).
+
+---
+
+## Self-Review (Codex+Gemini 리뷰 반영 후)
+
+**Spec coverage:** design §3(변경 1)→PR-A Task A1-A7, §4(변경 2)→PR-C, §5(변경 3)→PR-B, §6(PR 구성/release)→Task R1, §8(테스트)→각 task 의 test step + A4 의 2자/multi-token/snippet, §9 Risks→A5(builder 재설계)·A4(영어 동작/heading_path 노이즈)·B1(nested typedef). §10 버전 cascade→B1 Step 5 (parser_version), R1 (workspace version). 누락 없음.
+
+**Placeholder scan:** Task A5 의 "A1 baseline 노트" 는 의도적 plan-내 동적 슬롯 — A1 Step 1 이 채워 A5 가 참조. 그 외 "TBD/TODO" 없음. V007 SQL 전문 박음. 정확한 코드 (build_match_string 재설계, c.rs typedef 노드 분기, chunks JOIN documents 위치) 는 "해당 파일을 읽어 구현" 으로 명시 — placeholder 가 아닌 실행 지시.
+
+**Type consistency:** `code_lang_chunk_breakdown` 명칭이 store 함수(C1)·Stats 필드(C2 Step 2)·wire JSON schema(C2 Step 5) 전체 동일. `BTreeMap<String, u32>` 반환 타입이 기존 `code_lang_breakdown` 과 일치. `chunks_fts` 컬럼명이 V007·design §5.5·diff-check 테스트 동일. `parser_version = "code-c-v2"` 문자열이 B1 Step 5·테스트 갱신·design §5·§10 일치.
+
+**리뷰 반영 변경 (round 1):**
+- 변경 1 본체에 `lexical.rs::build_match_string()` 재설계 추가 (A5 필수화).
+- 2자 이하 한국어 query 정책 = 0-hit + CLI/TUI 안내 (사용자 결정).
+- C typedef cascade 를 chunker_version → **parser_version** 으로 정정 (`code-c-v1` → `code-c-v2`).
+- design §3.1 의 "contentless" 표현 정정 (V002 는 일반 FTS5 shadow).
+- heading_path JSON 노이즈, 디스크 용량 증가, BM25 snapshot drift 를 Risks 등재.
+- 누락 task 추가: SMOKE.md 갱신 (A6 Step 4), `docs/wire-schema/v1/schema.schema.json` 갱신 (C2 Step 5).
+- 잘못된 task 제거: `wire.rs` 수정 (serde 자동 직렬화이므로 불필요).
+
+**리뷰 반영 변경 (round 2):**
+- **[Critical]** PR-B 에 same-workspace_path orphan purge step 추가 (B1 Step 5b/5c) — parser_version bump 만으로는 같은-asset 케이스에서 옛 doc_id/chunk/vector 가 orphan, UNIQUE 충돌 위험. design §5 본문에 실제 cascade 동작 명시.
+- **[High]** design §2 표 + plan Architecture 의 잔존 "code-c-ast-v2 chunker bump" → "code-c-v2 parser_version bump" 로 정정.
+- **[High]** A4 Step 1 의 trigram 테스트 예시를 Codex sqlite 3.45.1 검증 동작으로 정정 — quoted phrase 와 공백 없는 연속 substring 으로 (`'해시충'`/`'시 충'` 는 0-hit 가 맞음).
+- **[High]** A5 Step 2 의 builder 알고리즘을 Codex 권장안으로 — whole phrase 후보 + 3자 이상 토큰 AND → OR 결합, 후보 없음 시 `None` 반환 (빈 MATCH 금지).
+- **[Medium]** A5 Step 5 의 TUI 안내 구현을 `SearchState.short_query_hint` 필드 + `poll_worker` 세팅 + `dynamic_status` 표시로 구체화.
+- **[Low]** File Structure 에 `crates/kebab-store-sqlite/src/fts.rs` (코드 주석의 contentless 정정) 추가.
+- **[Low]** C2 Step 5 에 기존 stats 필드 (`code_lang_breakdown`·`repo_breakdown`) description 정정 추가 (실제는 doc count).
+- **[Low]** R1 Step 5 의 INDEX.md 갱신 위치를 "P10 Dogfooding Feedback" 섹션으로 구체화.
+
+**리뷰 반영 변경 (round 3):**
+- **[Codex High]** SMOKE.md 시나리오의 hit query 를 `해시충` (원문 미존재) → `충돌은` (3자 연속) + `해시 충돌` (whole phrase) 로 정정. JSON 모드 hint 필드 검증도 시나리오에 포함.
+- **[Codex High]** TUI short_query_hint 의 stale 방지 — `poll_worker` 가 `last_query == 현재 input + mode` 일치 시만 hint 세팅, input 변경 시 reset.
+- **[Gemini High]** `search_response.v1` 에 `hint: Option<String>` additive 필드 추가 (A5 Step 4b) — `--json`/MCP 가시성 보강. CLI stderr 안내와 보완적.
+- **[Codex Medium]** PR-B helper 이름 명시 — `stale_chunk_ids_for_workspace_path_except_doc_id` + `purge_document_at_workspace_path_except_doc_id` 새 helper. P7-3 helper 의 asset_id 조건 우회.
+- **[Codex Medium]** raw FTS mode 표기 single quote `'...'` 로 통일 (A1 Step 1, A5 Step 1, A5 Step 2 권장안 1) — 실제 코드 `lexical.rs:167` 기준.
+- **[Codex Medium]** short-query CLI 조건을 `query.trim().chars().count() < 3` 으로 고정 — "모든 토큰 < 3" 분기 제거 (valid whole-phrase query false trigger 회피). TUI 도 동일.
+- **[Gemini Medium]** A4 Step 0 — `fixtures/search/korean/` 으로 한국어 도그푸딩 fixture 복사·commit, LICENSE 표기.
+- **[Gemini Medium]** A6 Step 4b — `integrations/claude-code/kebab/SKILL.md` 에 3자 권장 + hint 필드 안내 한 줄.
+- **[Gemini Low]** README 디스크 용량 수치화 (~2-5배 또는 수백 MB 단위).

docs/superpowers/specs/2026-04-27-kebab-final-form-design.md

@@ -1004,6 +1004,17 @@ CREATE INDEX idx_blocks_doc_id ON blocks(doc_id);
 
 ### 5.5 Chunks + FTS5
 
+Tokenizer = `trigram` (V007, 2026-05-23). 한국어 어절(조사·어미가 붙은 단위)이
+unicode61 에서 단일 토큰화돼 lexical 부분 매칭이 불가능했던 문제를 해소
+(2자 미만 한국어 query 는 trigram 구조상 여전히 0-hit — 단일 토큰 측면에서는
+회귀 아님, multi-token query 는 `lexical.rs::build_match_string()` 가 whole-phrase
+후보 OR 결합으로 매칭). trade-off: 영어 lexical 도 substring 매칭으로 이동
+(recall↑, 단어 경계 정밀도↓), BM25 raw score 분포 변경 (RRF rank 기반 hybrid
+는 영향 미미), SQLite 파일 크기 ~2-10× 증가. 자세한 내용 = `tasks/HOTFIXES.md`
+(2026-05-22) + `docs/superpowers/specs/2026-05-22-korean-trigram-tokenizer-design.md`.
+`chunks_fts` 는 일반 FTS5 shadow table 이며 contentless 가 아님 (V002 / V007
+DDL 에 `content=''` 없음).
+
 ```sql
 CREATE TABLE chunks (
   chunk_id          TEXT PRIMARY KEY,
@@ -1026,7 +1037,7 @@ CREATE VIRTUAL TABLE chunks_fts USING fts5(
   doc_id       UNINDEXED,
   heading_path,
   text,
-  tokenize = 'unicode61 remove_diacritics 2'
+  tokenize = 'trigram'
 );
 
 CREATE TRIGGER chunks_ai AFTER INSERT ON chunks BEGIN
@@ -1553,6 +1564,8 @@ transitional 형태) 의 source of truth.
 
 **p10-3 활성화 (Tier 3 paragraph fallback) (2026-05-21)**: Tier 3 chunker `code-text-paragraph-v1` 활성화. shell script (`.sh`/`.bash`/`.zsh`) direct routing + Tier 1/2 가 0 chunk 또는 Err 시 자동 fallback 으로 retry. 비-k8s YAML / invalid YAML / AST 실패 케이스 모두 picked up. lang 은 입력 보존 (shell → "shell", yaml → "yaml" 등), symbol 은 항상 None.
 
+**p10-1D 활성화 (C + C++) (2026-05-21)**: P10 Tier 1 chunker family 완료 — C (`code-c-ast-v1`, `.c`/`.h`) + C++ (`code-cpp-ast-v1`, `.cpp`/`.cc`/`.cxx`/`.hpp`/`.hh`/`.hxx`) AST chunker 활성화. C symbol = function name only (no nesting); C++ symbol = `namespace::Class::method` (recursive namespace + class nesting). `.h` 가 C++ syntax 만나면 tree-sitter-c parse 실패 → p10-3 Tier 3 fallback 으로 자동 picked up.
+
 ### 10.2 MCP server transport (fb-30)
 
 `kebab mcp` 가 stdio JSON-RPC server. Rust SDK = `rmcp 1.6`. Tool surface

docs/superpowers/specs/2026-05-22-korean-trigram-tokenizer-design.md

@@ -0,0 +1,143 @@
+---
+title: "v0.17.0 설계 — 한국어 trigram FTS tokenizer + P10 round-2 dogfood 버그픽스"
+date: 2026-05-22
+status: draft
+contract_sections: ["§5.5", "§9"]
+---
+
+# v0.17.0 설계 — 한국어 trigram FTS tokenizer + P10 round-2 dogfood 버그픽스
+
+## 1. 배경
+
+P10 종합 도그푸딩 round 2 (2026-05-22, `tasks/HOTFIXES.md`) 에서 세 가지가 드러났다:
+
+- 한국어 `kebab search --mode lexical` 이 FTS5 `unicode61` 토크나이저에서 거의 0 hit. unicode61 은 공백·구두점 경계로만 토큰을 끊어, 한국어 어절(조사·어미 포함)이 통째로 한 토큰이 되고 부분 매칭이 안 된다.
+- `code_lang_breakdown` 이 chunk 가 아닌 doc 수를 집계 — 코드가 많은 KB 에서 언어별 chunk 분포 granularity 가 떨어진다.
+- C `typedef struct {...} Foo;` 의 alias 가 검색 symbol 로 노출되지 않는다.
+
+이 설계는 셋을 v0.17.0 한 release 사이클에 묶어 처리한다. 본체는 한국어 tokenizer (변경 1), 나머지 둘은 같은 도그푸딩 라운드의 작은 버그픽스 (변경 2·3).
+
+## 2. 범위
+
+| # | 변경 | crate | cascade |
+|---|------|-------|---------|
+| 1 | FTS5 `unicode61` → `trigram` tokenizer | kebab-store-sqlite, migrations | V007 migration, design §5.5 갱신, release cut |
+| 2 | `code_lang_chunk_breakdown` wire 필드 | kebab-store-sqlite, kebab-app, kebab-cli | wire additive (release 트리거 아님) |
+| 3 | C typedef-wrapped struct → synthetic unit | kebab-parse-code, kebab-app(ingest), kebab-store-sqlite(purge) | **`parser_version`** bump (`code-c-v1`→`code-c-v2`) + same-workspace_path orphan purge |
+
+3개는 서로 독립적인 코드 경로다. 각각 별도 PR 로, 한 작업 세션에서 연속 진행하고, 셋 다 머지된 뒤 v0.17.0 release 를 한 번 cut 한다.
+
+## 3. 변경 1 — FTS5 trigram tokenizer (본체)
+
+### 3.1 현재 상태
+
+`migrations/V002__fts.sql` 의 `chunks_fts` 는 FTS5 가상 테이블 (V002 DDL 에 `content=''` 가 없어 contentless 가 아닌 일반 FTS5 shadow table) 이고 `tokenize = 'unicode61 remove_diacritics 2'` 로 생성된다. `chunks` 테이블의 INSERT/UPDATE/DELETE 가 trigger (`chunks_ai` / `chunks_ad` / `chunks_au`) 로 `chunks_fts` 와 동기화된다. 즉 `chunks` 가 source-of-truth, `chunks_fts` 는 검색용 shadow 다.
+
+design §5.5 (`docs/superpowers/specs/2026-04-27-kebab-final-form-design.md` 라인 1024-1043) 에 동일한 SQL 이 verbatim 으로 박혀 있고, 테스트 `fts_v002_matches_design_section_5_5_verbatim` (`crates/kebab-store-sqlite/tests/fts.rs`) 이 둘을 whitespace-normalized 로 대조하는 CI diff-check 다.
+
+### 3.2 변경 내용
+
+새 마이그레이션 `migrations/V007__fts_trigram.sql`:
+
+1. `DROP TRIGGER` (`chunks_ai`/`chunks_ad`/`chunks_au`) + `DROP TABLE chunks_fts;` — 가상 테이블과 연결 trigger 를 명시적으로 제거.
+2. `CREATE VIRTUAL TABLE chunks_fts USING fts5(..., tokenize = 'trigram');` — 컬럼 구성(`chunk_id`/`doc_id` UNINDEXED, `heading_path`, `text`)은 V002 와 동일, tokenizer 만 교체.
+3. `chunks_ai`/`chunks_ad`/`chunks_au` trigger 재생성 — V002 와 동일 본문.
+4. `INSERT INTO chunks_fts(chunk_id, doc_id, heading_path, text) SELECT chunk_id, doc_id, heading_path_json, text FROM chunks;` — 기존 chunk 전부 재색인 (V002 backfill 과 동일 패턴).
+
+`chunks` 원본·embedding·vector index 는 전혀 건드리지 않는다. 마이그레이션이 FTS shadow 만 재구축하므로 **사용자는 `kebab ingest` 를 다시 돌릴 필요가 없다** — 0.17.0 바이너리가 기존 DB 를 열면 V007 이 자동 적용되며 backfill 까지 끝난다. 비싼 fastembed 재계산이 없다.
+
+### 3.3 동반 갱신
+
+- design §5.5 verbatim 블록을 V007 의 SQL 로 갱신한다. frozen design 변경이므로 release 트리거 중 하나다. design 본문 어디든 "contentless" 표현이 있으면 함께 "shadow / non-contentless" 로 정정.
+- CI diff-check 테스트: 함수명에 `v002` 가 박혀 있으므로 `fts_v007_matches_design_section_5_5_verbatim` 으로 갱신하고, 대조 대상을 V007 파일로 바꾼다.
+- `crates/kebab-store-sqlite/src/fts.rs` 의 `rebuild_chunks_fts` 는 컬럼 구성이 동일하므로 코드 변경이 불필요하다 (tokenizer 는 테이블 DDL 에만 존재). 동작만 확인.
+- `crates/kebab-search/src/lexical.rs:177` 의 `build_match_string()` **재설계가 본 PR 의 본체다**. Codex 리뷰 검증 결과: 현재 builder 는 whitespace split 후 각 토큰을 `"..."` 로 감싸 implicit AND 결합 → trigram 에서 2자 이하 토큰 (예: `해시`, `충돌`) 은 매칭 불가 → `해시 충돌` 같은 multi-token 한국어 query 가 0-hit. trigram 대응 재설계 필요 — 권장: 3자 미만 토큰을 drop 또는 raw 처리, 전체 query 가 3자 이상이면 전체 query phrase 도 OR 후보로 추가.
+- **2자 이하 한국어 query 정책 (사용자 결정)**: lexical core 는 정상 0-hit (변경 없음), CLI/TUI 레이어가 결과 0 + query 3자 미만일 때 "3자 이상 키워드 권장 (trigram tokenizer 제약)" 한 줄 안내. `--json` 모드는 wire 무결성 위해 안내 미출력. hybrid 모드는 vector 가 결과를 받쳐 안내가 안 나오는 케이스가 많다.
+- `crates/kebab-search/src/lexical.rs:506` 부근의 lexical BM25 snapshot 테스트 갱신 — token stream 이 word → trigram 으로 바뀌어 raw score 분포·`snippet()` token 단위가 달라진다.
+- `docs/wire-schema/v1/schema.schema.json` 에 변경 2 의 `code_lang_chunk_breakdown` 추가 (PR-C 에서 처리).
+- `docs/SMOKE.md` 에 한국어 검색 시나리오 추가 (PR-A 에서 처리).
+
+### 3.4 trade-off
+
+- trigram 은 3자 (Unicode chars) 이상 substring 만 색인한다 (Codex 가 sqlite 3.45.1 로 검증). 3자 미만 query (`값`/`키`/`충돌`) 는 lexical 0-hit — unicode61 에서도 어절 단위 토큰화라 단일 토큰 부분 매칭은 안 됐으므로 단일 토큰 측면은 회귀가 아니다.
+- 단 multi-token 한국어 query (`해시 충돌`) 는 §3.3 의 query builder 재설계가 동반돼야 hit 한다. builder 재설계가 본 PR 의 본체.
+- 2자 이하 query 0-hit 시 CLI/TUI 가 안내 출력 (§3.3, 사용자 결정).
+- 영어 lexical 검색도 substring 매칭으로 바뀐다: recall 상승, 단어 경계 정밀도 하락 가능. lexical-only KB 의 영어 검색 동작이 변경된다 — 의도된 동작 변경, 테스트로 핀.
+- **BM25 score 분포 변경**: 알고리즘은 유지되지만 token stream 이 word → overlapping trigram 으로 바뀌어 raw score, term frequency, document length 모두 달라진다. lexical snapshot 갱신 (§3.3). `snippet()` 의 token 도 trigram 기준이라 word budget 의미가 달라진다. hybrid (RRF) 는 rank 기반이라 ranking 자체 영향은 미미, 단 `retrieval.lexical_score` 노출값은 변동.
+- **DB 디스크 용량 증가**: trigram 인덱스는 unicode61 대비 통상 2-10배 크다 (chunk 본문 + heading_path 모두 trigram 색인). 기존 KB 가 V007 적용 후 `kebab.sqlite` 파일 크기 증가. release notes 명시.
+- **`heading_path_json` JSON 노이즈**: trigram 이 JSON 표기 (`[`, `"`, `,`) 와 그 안의 단어 (예: `app`, `src`) 까지 3-gram 색인 → query 가 우연히 JSON 구문이나 흔한 경로 단어와 겹쳐 false positive 가능. v0.17.0 에서는 컬럼 구성 유지 (column filter / 평문 heading 변환 결정은 도그푸딩 후), Risks 등재.
+- `remove_diacritics` 는 trigram tokenizer 에서 SQLite 버전 의존 (3.45.0+). 호환성 위해 `tokenize = 'trigram'` 단독 사용 (case-insensitive 기본). 빌드 환경 SQLite 버전은 plan 단계에서 확인.
+
+### 3.5 사용자 영향
+
+- 옛 binary (≤0.16.x) 는 V007 적용 DB 와 비호환 → v0.17.0 release cut 이 필요하다 (CLAUDE.md release cascade: V00X migration 트리거).
+- 한국어 문서 KB 에서 `--mode lexical` / `--mode hybrid` 가 정상 동작한다 (3자 이상 substring). 도그푸딩에서 확인된 "한국어 hybrid 의 lexical 기여가 0" 문제가 해소된다.
+- `kebab.sqlite` 파일 크기가 trigram 인덱스 비대화로 증가한다 (V007 자동 backfill 후). release notes 에 안내.
+- 2자 이하 query 검색 시 lexical 0-hit + CLI/TUI 안내 메시지 표시 (§3.3).
+
+## 4. 변경 2 — code_lang_chunk_breakdown
+
+`crates/kebab-store-sqlite/src/store.rs` 의 기존 `code_lang_breakdown()` (doc 수, `documents` GROUP BY) 는 그대로 두고, `code_lang_chunk_breakdown()` 을 추가한다. `chunks` 테이블에는 `code_lang` 컬럼이 직접 없으므로 `chunks JOIN documents ON chunks.doc_id = documents.doc_id` 로 `documents.metadata_json` 의 `code_lang` 을 끌어와 `COUNT(chunks.chunk_id)` GROUP BY. 반환 타입은 기존과 동일 `BTreeMap<String, u32>`.
+
+`crates/kebab-app/src/schema.rs` 의 `Stats` 에 `code_lang_chunk_breakdown: BTreeMap<String, u32>` 필드를 추가하고, stats 빌드 지점에서 신규 함수 호출로 채운다. `crates/kebab-cli/src/wire.rs::wire_schema()` 는 `SchemaV1` 을 serde 로 통째 직렬화하므로 **별도 수정 불필요** — 신규 필드가 자동으로 wire 출력에 포함된다. 단 `docs/wire-schema/v1/schema.schema.json` 에 `code_lang_chunk_breakdown` 을 additive 로 추가 (필수).
+
+기존 `code_lang_breakdown` 필드는 유지 (제거 시 wire breaking). additive 추가 → migration·`schema_version` bump 불필요, release 트리거 아님.
+
+## 5. 변경 3 — C typedef-wrapped struct fix
+
+`crates/kebab-parse-code/src/c.rs` 의 extractor 가 top-level `type_definition` 노드를 만나면, 그 내부의 anonymous `struct_specifier`/`enum_specifier`/`union_specifier` 를 탐지해 **typedef alias 이름** (`type_definition` 의 `declarator` 에서 추출) 으로 synthetic unit 을 방출한다. named struct 는 기존 경로를 그대로 유지한다.
+
+**`parser_version` bump** (`crates/kebab-parse-code/src/c.rs:34` 의 `PARSER_VERSION = "code-c-v1"` → `"code-c-v2"`) 가 본 변경의 cascade 키다 — extractor output 이 바뀌기 때문이다. design §9 cascade: `doc_id` 는 `(workspace_path, asset_id, parser_version)` 기반이라 parser_version bump 만으로 doc_id 가 갱신된다. chunker (`crates/kebab-chunk/src/code_c_ast_v1.rs` 의 `code-c-ast-v1`) 는 **건드리지 않는다** — chunker 로직 동일.
+
+**Cascade 실제 동작 (Codex round 2 검증)**: parser_version 만 바뀌고 파일 bytes 가 동일하면 `asset_id` 가 같아 기존 ingest 경로의 `stale_chunk_ids_at` (asset_id 변경 기반) 가 발동하지 않는다. 새 doc_id 로 `documents` INSERT 시 `idx_docs_workspace_path` UNIQUE 가 충돌하거나, 옛 doc_id row 와 옛 chunk/vector row 가 orphan 으로 잔존한다. 따라서 본 PR 은 **same-workspace_path orphan purge** 를 동반해야 한다 — ingest 의 parser-mismatch 분기에서 `(workspace_path, 다른 doc_id)` 옛 row 의 chunk_id 를 수집해 `VectorStore::delete_by_chunk_ids` (P7-3 hotfix helper) 호출 + `documents` row 교체. plan B1 에 별도 step.
+
+현재는 dogfood 단계라 prod KB 가 없다.
+
+기존 테스트 `c_extractor_typedef_struct_falls_into_glue` 는 동작이 반대로 바뀌므로 `c_extractor_typedef_struct_emits_unit` 으로 재작성한다. HOTFIXES 2026-05-21 항목을 closure 로 갱신하고, spec `tasks/p10/p10-1d-c-cpp-ast-chunker.md` 의 Risks/notes 를 갱신한다.
+
+## 6. PR 구성 / release
+
+- **PR-A**: 변경 1 (trigram tokenizer). `feat/*` 브랜치 — 코드 + V007 migration + design §5.5 + task spec 을 한 PR 에 (design 변경과 그것을 참조하는 task spec 은 같은 PR 규칙).
+- **PR-B**: 변경 3 (C typedef). `feat/*` 브랜치.
+- **PR-C**: 변경 2 (code_lang_chunk_breakdown). `feat/*` 브랜치.
+- 셋 머지 후 `chore: bump version 0.16.1 → 0.17.0` 같은 commit 직후 같은 commit 에 `gitea-release v0.17.0`. release notes 는 도그푸딩 영향 surface 위주 — 한국어 lexical 검색 동작, C symbol 노출, `schema.v1.stats` 신규 필드.
+
+PR-A 가 design 변경을 포함하므로 README/HANDOFF/ARCHITECTURE sync 규칙이 적용된다 — 한국어 검색 동작을 README 검색/Configuration 절에 한 줄, HANDOFF "머지 후 발견된 버그/결정" 절, HOTFIXES round-2 항목 status 갱신.
+
+## 7. 작업 방식 (team)
+
+- **코드 작성**: Claude Code — OMC `executor` agent, migration·extractor 같은 복잡 부분은 `model=opus`.
+- **리뷰**: Codex + Gemini 가 각 PR 의 diff 를 리뷰한다 (`/ask codex`, `/ask gemini` — OMC ask 라우팅). Claude 가 두 리뷰를 종합해 반영한다.
+- **PR 생성·머지**: gitea-ops skill (Gitea REST API).
+- 각 PR = 구현 → codex+gemini 리뷰 → 반영 → 머지 루프.
+
+## 8. 테스트 전략
+
+- 변경 1:
+  - `crates/kebab-store-sqlite/tests/fts.rs`: V007 ↔ design §5.5 diff-check (테스트명 `fts_v007_matches_design_section_5_5_verbatim` 으로 rename).
+  - 한국어 trigram 매칭 테스트 — **3자 이상 연속 substring 만 hit**. fixture `"해시 충돌은 키와 값을 매핑할 때 발생한다"` 기준 (Codex sqlite 3.45.1 검증): raw `MATCH '충돌은'` hit (공백 없는 3자 연속), `MATCH '"해시 충돌"'` quoted phrase hit, `MATCH '"시 충"'` quoted phrase hit; 반면 raw `MATCH '해시충'`/`MATCH '시 충'` 은 0-hit (전자는 원문에 해당 trigram 없음, 후자는 FTS5 가 raw 입력의 공백을 토큰 경계로 처리). quoted phrase 또는 공백 없는 연속 substring 으로 테스트.
+  - **2자 query 0-hit 핀 테스트** — `MATCH '충돌'` 같은 2자 query 가 반드시 0 결과 (trigram 구조 회귀 감지).
+  - **multi-token 한국어 query 테스트** (kebab-search / kebab-app 통합) — 사용자 query `해시 충돌` 이 재설계된 `build_match_string()` 을 거쳐 hit (whole phrase 후보 `"해시 충돌"` 경로). A4 작성 시점 FAIL, A5 후 PASS.
+  - 영어 substring 동작 핀 (`token` query 가 `tokenizer`/`testbed` 등 hit).
+  - lexical BM25 snapshot (`crates/kebab-search/src/lexical.rs:506` 근처 또는 `crates/kebab-search/tests/`) 갱신.
+  - 기존 `crates/kebab-app/tests/search_korean.rs` 회귀 핀 (`러스트` 3자) + `해시 충돌` multi-token assert 추가.
+  - CLI/TUI 안내 메시지 (3자 미만 query + 0 결과) 테스트 — `kebab-cli` stderr 검증, `kebab-tui` Search pane 단위 테스트.
+- 변경 2: `crates/kebab-app/src/schema.rs` stats 테스트에 `code_lang_chunk_breakdown` 필드 검증 (한 doc 다중 chunks fixture 로 doc count 와 다른 값). `docs/wire-schema/v1/schema.schema.json` JSON 검증.
+- 변경 3: `c.rs` typedef 테스트 재작성 (`Point` alias 가 unit 방출), `parser_version = "code-c-v2"` 확인, named struct 회귀 없음.
+- 전체: `cargo test --workspace --no-fail-fast -j 1`, `cargo clippy --workspace --all-targets -- -D warnings`.
+
+## 9. Risks / notes
+
+- `lexical.rs::build_match_string()` 재설계가 본 PR 의 본체 — multi-token 한국어 query, 3자 미만 토큰 정책, lexical snapshot drift. Codex 검증으로 현재 builder 가 trigram 비호환임이 확정됨 (`해시 충돌` 0-hit). 빈 MATCH 는 FTS5 syntax error 이므로 후보 없음 시 `None` 반환 (SQL 미실행).
+- PR-B 의 parser_version cascade — 같은 bytes + parser bump 케이스 (orphan vector/document row) 가 ingest 의 기존 asset_id 기반 purge 로 정리 안 됨 (Codex round 2 검증). same-workspace_path 명시 purge 가 PR-B 의 구성 요소. (미래의 모든 parser_version bump 에도 같은 보강이 필요할 수 있는 일반 케이스.)
+- `heading_path_json` JSON 노이즈 — v0.17.0 에서는 컬럼 구성 유지, 도그푸딩 후 column filter (lexical query 를 `{text} : <q>` 한정) 또는 평문 heading 변환 재검토. HOTFIXES 후속 entry 로 등재.
+- SQLite 파일 크기 증가 (trigram 인덱스) — release notes 명시. 검색 정확도와 무관.
+- 영어 lexical 동작 변경 (substring 매칭) — release notes 명시.
+- lexical BM25 raw score 분포 변경 — hybrid (RRF) 는 rank 기반이라 ranking 영향 미미, 단 `retrieval.lexical_score` 노출값 변동. wire schema 는 그대로지만 score 값 비교 기반 외부 도구가 있다면 영향.
+- C typedef fix synthetic unit naming: nested typedef (`typedef struct { struct {...} inner; } Outer;`) 의 inner 익명 struct 는 여전히 glue. 1차 범위는 top-level typedef alias 만. spec Risks 명시.
+
+## 10. contract_sections / 버전 cascade
+
+- design §5.5 (Chunks + FTS5) — 변경 1 이 갱신 (tokenize 값 + "shadow / non-contentless" 표현).
+- design §9 (versioning cascade) — 변경 3 의 **`parser_version` bump** (`code-c-v1` → `code-c-v2`) 가 cascade 사례. doc_id 가 `(workspace_path, asset_id, parser_version)` 기반이라 parser bump 만으로 다음 ingest 가 전체 재처리. chunker_version 은 chunk_id 에만 영향이라 본 fix 에는 불필요.
+- 버전: workspace `Cargo.toml` 의 `version` 을 0.16.1 → 0.17.0 (minor bump, pre-1.0 단계 surface 변경 누적).

docs/wire-schema/v1/schema.schema.json

@@ -81,12 +81,17 @@
         },
         "code_lang_breakdown": {
           "type": "object",
-          "description": "p10-1A-1: per-language code chunk count. Key = lowercase language name (e.g. 'rust', 'python'). Populated after 1A-2 lands; empty on markdown-only corpora.",
+          "description": "p10-1A-1: per-language **doc** count (one entry per indexed code document). Key = lowercase language name (e.g. 'rust', 'python'). Empty on markdown-only corpora. Pair with `code_lang_chunk_breakdown` for chunk-level granularity (one file's 200 chunks vs one doc).",
           "additionalProperties": { "type": "integer", "minimum": 0 }
         },
         "repo_breakdown": {
           "type": "object",
-          "description": "p10-1A-1: per-repo code chunk count. Key = repo name as detected by kebab-parse-code::repo. Empty on markdown-only corpora.",
+          "description": "p10-1A-1: per-repo **doc** count. Key = repo name as detected by kebab-parse-code::repo. Empty on markdown-only corpora.",
+          "additionalProperties": { "type": "integer", "minimum": 0 }
+        },
+        "code_lang_chunk_breakdown": {
+          "type": "object",
+          "description": "v0.17.0 PR-C: per-language **chunk** count (closes HOTFIXES 2026-05-22 'code_lang_breakdown chunk granularity'). Companion to `code_lang_breakdown` (doc count) — chunk-level granularity is the indexing-pressure metric (a 200-chunk PDF + a 5-chunk Rust file both appear as `1 doc` but `200` vs `5` chunks). Key = lowercase language name. Empty on markdown-only corpora.",
           "additionalProperties": { "type": "integer", "minimum": 0 }
         }
       }

docs/wire-schema/v1/search_response.schema.json

@@ -29,6 +29,10 @@
           }
         }
       }
+    },
+    "hint": {
+      "type": "string",
+      "description": "v0.17.0 A5 Step 4b: advisory string set when the empty hit list is likely due to a query shorter than the FTS5 trigram tokenizer's 3-char minimum. Field is omitted when no advisory applies. Raw FTS5 mode ('...') opts out. MCP / agent consumers should surface this so users understand the empty result rather than retrying the same short query."
     }
   }
 }

fixtures/search/korean/hash-table.md

@@ -0,0 +1,27 @@
+# 해시 테이블
+
+해시 테이블은 키와 값을 매핑하는 자료 구조다. 해시 함수로 키를 인덱스로
+변환해 평균 상수 시간에 조회·삽입·삭제한다.
+
+## 해시 충돌
+
+두 개 이상의 서로 다른 키가 같은 인덱스로 매핑될 때 해시 충돌이 발생한다.
+해시 충돌은 잘 설계된 해시 함수에서도 피할 수 없으며, 적재율이 올라갈수록
+충돌 빈도가 증가한다.
+
+### 해시 충돌 해결법
+
+- **체이닝**: 같은 버킷에 연결 리스트로 충돌한 항목들을 묶는다. 구현이
+  단순하고 적재율이 1을 넘어도 동작한다.
+- **개방 주소법**: 빈 버킷을 찾아 다음 위치에 저장한다. 선형 탐사, 제곱
+  탐사, 이중 해싱이 있다.
+
+## 적재율과 재해싱
+
+적재율은 저장된 항목 수를 버킷 수로 나눈 값이다. 임계 적재율을 넘으면
+테이블을 키워 재해싱한다 — 모든 항목을 새 테이블에 다시 매핑한다.
+
+## 응용
+
+캐시, 색인, 중복 제거, 데이터베이스 인덱스, 컴파일러의 심볼 테이블 등
+광범위하게 쓰인다.

integrations/claude-code/kebab/SKILL.md

@@ -60,6 +60,7 @@ Input:
 - Cite back to the user as `doc_path § heading_path[-1]` so they can open the source.
 - When `truncated: true`, the budget loop modified the page (snippet shortening or k reduction). `next_cursor` is **independent** — non-null whenever more hits may be reachable. Caller may widen `max_tokens` (re-issue same query for fuller snippets / more hits per page) or follow `next_cursor` (advance through more hits) or both. Mismatched cursor (corpus_revision changed) returns `error.v1.code = stale_cursor` — re-issue the search to obtain a fresh one.
 - **`trace: true` (p9-fb-37)** — debug aid. Response carries an extra `trace` block: `lexical[]` + `vector[]` (pre-fusion candidates), `rrf_inputs[]` (RRF union before final cut), and `timing` (`lexical_ms`, `vector_ms`, `fusion_ms`, `total_ms`). Trace bypasses the search cache (always cold). Use sparingly — it bloats the wire response and is for diagnosing "why did this hit / not hit", not normal retrieval.
+- **`hint` (v0.17.0)** — optional advisory string on `search_response.v1`. Present only when the result is empty AND the trimmed query is shorter than the FTS5 trigram tokenizer's 3-char minimum. Surface it to the user instead of retrying the same short query. Korean lexical search benefits most from ≥3-char keywords (`충돌` zero-hit, `충돌은` substring-hit). Raw FTS5 mode (`'...'`) opts out — the user opted into FTS5 syntax. Vector / hybrid modes carry the field too but it's rarely triggered (semantic embeddings handle short queries).
 
 ### `mcp__kebab__bulk_search`
 

migrations/V007__fts_trigram.sql

@@ -0,0 +1,60 @@
+-- V007__fts_trigram.sql — Replace chunks_fts tokenizer: unicode61 → trigram.
+--
+-- Per design §5.5 (chunks_fts virtual table + chunks_ai/ad/au triggers).
+-- The CREATE VIRTUAL TABLE / CREATE TRIGGER block below is reproduced
+-- VERBATIM from `docs/superpowers/specs/2026-04-27-kebab-final-form-design.md`
+-- §5.5; CI diff-checks this against the design doc (test
+-- `fts_v007_matches_design_section_5_5_verbatim` in
+-- `crates/kebab-store-sqlite/tests/fts.rs`).
+--
+-- Tokenizer choice: trigram. Korean is agglutinative — unicode61 tokenizes
+-- whole eojeol (조사·어미 attached) so substring matching fails. trigram
+-- indexes 3-character grams, enabling Korean partial matches. Trade-offs:
+-- DB size grows (~2-10×), English lexical also moves to substring match
+-- (recall↑, precision↓), BM25 score distribution shifts. See
+-- `tasks/HOTFIXES.md` (2026-05-22) and the v0.17.0 design doc.
+--
+-- chunks_fts is a shadow of chunks (NOT contentless — V002 DDL has no
+-- `content=''`); this migration drops the old shadow, recreates it with
+-- the new tokenizer, recreates the sync triggers (verbatim from V002),
+-- and backfills from `chunks`. The `chunks` table and embeddings are
+-- untouched, so users do NOT need to re-ingest after upgrading to
+-- v0.17.0 — the migration is fully automatic.
+
+DROP TRIGGER IF EXISTS chunks_au;
+DROP TRIGGER IF EXISTS chunks_ad;
+DROP TRIGGER IF EXISTS chunks_ai;
+DROP TABLE IF EXISTS chunks_fts;
+
+-- ── §5.5 verbatim block ────────────────────────────────────────────────
+
+CREATE VIRTUAL TABLE chunks_fts USING fts5(
+  chunk_id     UNINDEXED,
+  doc_id       UNINDEXED,
+  heading_path,
+  text,
+  tokenize = 'trigram'
+);
+
+CREATE TRIGGER chunks_ai AFTER INSERT ON chunks BEGIN
+  INSERT INTO chunks_fts(chunk_id, doc_id, heading_path, text)
+  VALUES (new.chunk_id, new.doc_id, new.heading_path_json, new.text);
+END;
+CREATE TRIGGER chunks_ad AFTER DELETE ON chunks BEGIN
+  DELETE FROM chunks_fts WHERE chunk_id = old.chunk_id;
+END;
+CREATE TRIGGER chunks_au AFTER UPDATE ON chunks BEGIN
+  DELETE FROM chunks_fts WHERE chunk_id = old.chunk_id;
+  INSERT INTO chunks_fts(chunk_id, doc_id, heading_path, text)
+  VALUES (new.chunk_id, new.doc_id, new.heading_path_json, new.text);
+END;
+
+-- ── End §5.5 verbatim block ───────────────────────────────────────────
+
+-- One-shot backfill from existing chunks. Mirrors the V002 backfill
+-- pattern — direct INSERT into chunks_fts bypasses chunks_ai trigger
+-- (trigger fires on chunks INSERT, not chunks_fts INSERT), so no
+-- double-insert. Refinery runs V007 exactly once via its bookkeeping
+-- table, so this is naturally idempotent across restarts.
+INSERT INTO chunks_fts(chunk_id, doc_id, heading_path, text)
+  SELECT chunk_id, doc_id, heading_path_json, text FROM chunks;

tasks/HOTFIXES.md

@@ -14,6 +14,110 @@ historical contract that was implemented; this file accumulates the
 deltas so phase 5+ readers can find the live behavior without diffing
 git history.
 
+## 2026-05-24 — v0.17.0: 한국어 trigram FTS5 tokenizer 채택 (closure of 2026-05-22 한국어 lexical)
+
+V007 migration 으로 `chunks_fts` 의 tokenizer 를 `unicode61` → `trigram` 으로 교체. `chunks` 원본 + embedding + vector index 는 그대로, FTS shadow 만 재구축 + 자동 backfill — 사용자는 `kebab ingest` 재실행 불필요 (binary 만 교체하면 다음 open 시 V007 가 즉시 적용). 같은 라운드의 다른 두 follow-up (`code_lang_chunk_breakdown`, C typedef) 은 별 PR (PR-C / PR-B).
+
+**한국어 lexical 동작**: 3자 이상 substring 매칭. `해시 충돌` 같은 2자 토큰 multi-token query 는 `crates/kebab-search/src/lexical.rs::build_match_string` 의 trigram-aware 재설계로 `("해시 충돌") OR ("해시" "충돌")` 형태가 되어 whole-phrase 후보로 hit (각 토큰 2자라 token-AND 후보는 trigram 에서 0-hit, 자동 drop). 한영 혼합 `Rust 충돌은` (둘 다 ≥3자) 도 OR-combined. 2자 이하 query (`충돌` / `키`) 는 정상 0 hit + CLI stderr `[hint] 3자 이상 키워드 권장 (trigram tokenizer 제약)` + `search_response.v1.hint` additive 필드 + TUI status bar 동일 안내. raw FTS5 single-quote mode (`'...'`) 는 사용자 명시 의도이므로 hint 안 나옴. 회귀 핀: `lexical_multi_token_korean_query_hits` + `lexical_mixed_korean_english_multi_token_query_hits` (`crates/kebab-app/tests/search_korean.rs`).
+
+**영어 lexical 동작 변경**: substring 매칭으로 바뀜. `token` query 가 `tokenizer` 도 hit (recall ↑, 단어 경계 정밀도 ↓). 의도된 변경, 회귀 핀 = `fts_trigram_english_substring_hits` (`crates/kebab-store-sqlite/tests/fts.rs`).
+
+**lexical BM25 score 분포**: 알고리즘 동일하지만 token stream 이 word → overlapping trigram 으로 바뀌어 raw score / TF / doc-length 모두 달라짐. `crates/kebab-search/tests/lexical.rs::lexical_snapshot_run_1` + `crates/kebab-search/tests/hybrid.rs::hybrid_snapshot_run_1` 둘 다 trigram baseline 으로 regenerate. hybrid (RRF) 는 rank 기반이라 ranking 영향 미미하나 `retrieval.lexical_score` 노출값은 변동.
+
+**디스크 용량**: trigram 인덱스는 unicode61 대비 통상 2-10배. V007 자동 backfill 후 `kebab.sqlite` 파일 크기 증가 (도그푸딩 KB 기준 ~2-5배 또는 수백 MB). release notes 명시.
+
+**`heading_path_json` JSON 노이즈 (관찰, 미수정)**: trigram 이 JSON 표기 (`[`, `"`, `,`) 와 그 안의 단어 (`app`, `src`) 까지 3-gram 색인 → query 가 우연히 JSON 구문 / 흔한 경로 단어와 겹쳐 false positive 가능. v0.17.0 에서는 컬럼 구성 유지, 도그푸딩 후 column filter (`{text} : <q>` 한정) 또는 평문 heading 변환 결정. 후속 도그푸딩 entry 로 등재 예정.
+
+**MCP / agent 가시성**: `search_response.v1` 에 `hint: Option<String>` additive 필드. 결과가 비어 있고 query trimmed.chars().count() < 3 + raw mode 아닐 때만 set (helper `kebab_app::short_query_hint`). `integrations/claude-code/kebab/SKILL.md` 의 search 절에 "한국어 lexical 은 3자 이상 권장, `hint` 필드 확인" 안내 추가.
+
+Cross-link: `migrations/V007__fts_trigram.sql`, `crates/kebab-search/src/lexical.rs::build_match_string`, design §5.5, `docs/superpowers/specs/2026-05-22-korean-trigram-tokenizer-design.md`.
+
+## 2026-05-22 — p10 종합 도그푸딩 (round 2): 한국어 lexical 검색 한계 + code_lang_breakdown
+
+**Origin**: P10 종합 도그푸딩 round 2 (`/build/cache/dogfood-p10b/`). 다양한 OSS 코드베이스 8 repo (rust / python / go / ts / js / java / c / cpp) + 한국어 위키 기술 문서 10편 (pandoc HTML→gfm 변환). `multilingual-e5-small` embedding 활성화 후 ingest — `scanned=2663 updated=2080 errors=0` (k8s multi-resource chunk_id collision 은 같은 라운드에서 발견·수정 — 아래 2026-05-21 항목).
+
+### 한국어 lexical 검색이 FTS5 unicode61 토크나이저에서 무용 (vector/hybrid 가 우회)
+
+**Symptom**: `kebab search --mode lexical` 의 한국어 query 가 거의 0 hit. "충돌" 은 hash-table.md 본문에 37회(21회 단독 어절) 등장하나 lexical 0 hit. 4개 한국어 query 측정 — lexical: `충돌` 0 / `해시 충돌` 0 / `컴파일러 최적화` 0 / `트리 순회 방법` 1.
+
+**원인**: `chunks_fts` 의 `tokenize = 'unicode61 remove_diacritics 2'` (`migrations/V002__fts.sql:24`, design §5.5 verbatim 블록). unicode61 은 공백·구두점 경계로만 토큰을 끊는다 — 한국어는 어절 전체가 한 토큰이 되고 조사·어미가 붙은 채라 부분 매칭이 안 된다. V002 헤더 주석이 이미 "Korean morphological tokenizer is a P+ note" 로 예고한 사항.
+
+**검증 (vector/hybrid 우회 확인)**: 동일 4 query 를 `--mode vector` / `--mode hybrid` 로 측정 — 전부 10 hit. `multilingual-e5-small` semantic 검색이 한국어를 정상 처리. 즉 embedding 켠 KB 는 **기본 hybrid 모드에서 한국어 검색이 동작**한다. 단 hybrid 는 RRF(lexical+vector) fusion 이라 한국어 query 는 lexical 기여가 0 → 사실상 vector-only 로 reduced (score 증거: lexical 도 hit 한 `트리 순회 방법` 만 hybrid score 1.000, 나머지 한국어 query 는 0.500).
+
+**Status**: ✅ closed — v0.17.0 (2026-05-24) 에서 V007 trigram migration + `lexical.rs::build_match_string` trigram-aware 재설계로 해소. 영향은 위 2026-05-24 절 참조. 이하는 closure 전 원래 round-2 관찰 기록 (frozen).
+
+**Workaround (pre-v0.17.0)**: 한국어 문서 KB 는 embedding 활성화 (`[models.embedding] provider = "fastembed"`) 가 사실상 필수였다 — vector / hybrid 가 한국어를 carry.
+
+**Resolution (v0.17.0)**: FTS5 builtin `trigram` tokenizer 채택. `chunks_fts` 재생성 = V007 migration (`chunks` 원본 / embedding / vector 불변, FTS shadow 만 자동 backfill — re-ingest 불필요). design §5.5 verbatim 블록 + CI diff-check (`fts_v007_matches_design_section_5_5_verbatim`) 동반 갱신.
+
+### code_lang_breakdown 이 chunk 수가 아닌 doc 수를 집계
+
+**Symptom**: `schema.v1.stats.code_lang_breakdown` 이 언어별 *문서* 수를 보고. 코드가 많은 KB 에서 언어별 chunk 분포를 보려 할 때 granularity 가 doc 단위라 덜 유용.
+
+**Status**: LOW. `code_lang_breakdown` 은 p10-1A-2 가 의도적으로 doc count 로 구현 (`store.rs::code_lang_breakdown` doc 주석 + `COUNT(*) FROM documents GROUP BY code_lang`). design §3.5 의 "언어별 분포" 의도와 엄밀히는 어긋나나 통계 표시 한정 — 검색/ingest 동작 무관.
+
+**Next step**: chunk 단위 집계를 추가/교체하는 소규모 follow-up. wire schema 영향 시 additive 필드 (`code_lang_chunk_breakdown`) 로 처리 검토.
+
+### ranking — glue chunk 이 top hit (deferred 유지)
+
+multi-root 도그푸딩(2026-05-20)에서 관찰한 본문 vs 테스트 / glue chunk ranking 편향이 round 2 에서도 재확인됨. 자동 heuristic 은 user intent misalignment 위험 → 사용자 명시 요청 전까지 surface 변경 0 으로 유지 (project memory `project_ranking_deferred` 결정 그대로).
+
+Cross-link: `tasks/p10/INDEX.md`, `migrations/V002__fts.sql`, design §5.5 / §3.5.
+
+## 2026-05-24 — v0.17.0 PR-B: C typedef-wrapped struct/enum/union 이 typedef alias unit 으로 방출 (closure of 2026-05-21)
+
+`crates/kebab-parse-code/src/c.rs::extract_blocks` 에 `type_definition` 분기 추가. 내부 anonymous `struct_specifier` / `enum_specifier` / `union_specifier` (name field 없음) 인 typedef 일 때 declarator 의 typedef alias identifier 를 추출해 synthetic unit 방출. named inner aggregate (`typedef struct Pt { ... } P;`) 와 plain alias (`typedef int MyInt;`) 는 기존대로 glue (top-level typedef-wrapped anonymous aggregate 만 v2 의 1차 범위).
+
+**parser_version cascade**: `PARSER_VERSION` `code-c-v1` → `code-c-v2` bump. design §9 — `doc_id = (workspace_path, asset_id, parser_version)`. 같은 file (asset_id 불변) + 새 parser_version → 새 doc_id. 즉 같은 workspace_path 에 옛 doc_id 와 새 doc_id 가 동시 INSERT 시도 → `idx_docs_workspace_path` UNIQUE 충돌.
+
+**Same-workspace_path orphan purge (B1 Step 5b)**: `crates/kebab-store-sqlite/src/store.rs` 에 두 helper 신규 — `stale_chunk_ids_for_workspace_path_except_doc_id(workspace_path, keep_doc_id)` (chunk_ids 수집) + `purge_document_at_workspace_path_except_doc_id(workspace_path, keep_doc_id)` (CASCADE document/chunks 제거). `crates/kebab-app/src/lib.rs::try_skip_unchanged` 의 parser_mismatch 분기에서 `purge_workspace_path_for_parser_bump` wrapper 호출 → 옛 chunk_ids 의 LanceDB orphan 도 `delete_by_chunk_ids` 로 정리 후 SQLite document row 제거 → 이후 `Ok(None)` 반환 → caller 가 새 doc_id 로 INSERT. 기존 `purge_orphan_at_workspace_path` (asset_id 변경 케이스) 는 그대로 — bytes 변경 경로 회귀 없음.
+
+**사용자 영향**: 기존 v0.16.x KB 의 C 파일은 v0.17.0 binary 로 다음 ingest 시 자동 재처리 (parser_version mismatch → cleanup → 새 doc). 명시적 re-ingest 명령 불필요 (다음 `kebab ingest` 가 자연스럽게 처리). `typedef struct {...} Foo;` 가 `Citation::Code.symbol = "Foo"` 로 search 에 노출.
+
+**미해결 (Risks)**: nested typedef (`typedef struct { struct {...} inner; } Outer;`) 의 inner 익명 struct 는 여전히 glue — v2 의 1차 범위는 top-level typedef alias 만.
+
+Cross-link: `crates/kebab-parse-code/src/c.rs::recover_typedef_alias`, `tasks/p10/p10-1d-c-cpp-ast-chunker.md` Risks/notes section.
+
+## 2026-05-24 — v0.17.0 PR-C: `code_lang_chunk_breakdown` additive wire 필드 (closure of 2026-05-22 LOW)
+
+`schema.v1.stats` 에 `code_lang_chunk_breakdown: { <lang>: <chunk_count> }` additive 필드 추가. 기존 `code_lang_breakdown` (doc 수) 와 sister — chunk 수 집계로 indexing 압력 granularity 노출. 한 PDF spec → 200 chunks vs 한 Rust file → 5 chunks 가 동일한 `1 doc` 으로 보이던 한계 closure.
+
+**구현**: `crates/kebab-store-sqlite/src/store.rs::code_lang_chunk_breakdown()` — `chunks INNER JOIN documents` 후 `json_extract(d.metadata_json, '$.code_lang')` GROUP BY, `COUNT(c.chunk_id)`. `BTreeMap<String, u32>` 반환 (기존 helper 와 동일 shape). `crates/kebab-app/src/schema.rs::Stats` 에 동일 이름 필드 추가 + `collect_stats` builder 에서 호출. `docs/wire-schema/v1/schema.schema.json` 에 additive 필드 명세. **additive 변경 — wire breaking 아님, `schema_version` bump 불필요.**
+
+**Gemini round 2 권고 반영**: 기존 `code_lang_breakdown` / `repo_breakdown` 의 JSON schema description 이 "code chunk count" 로 잘못 적혀 있던 (실제는 doc count) 부분을 "doc count" 로 정정. 신규 필드만 "chunk count" 로 명시. 사용자가 두 metric 의 의미 차이를 schema 만 보고도 구분 가능.
+
+**사용자 영향**: `kebab schema --json` 출력에 신규 키 등장. MCP `schema` tool 도 동일. 옛 v0.16.x 가 보낸 호출은 그대로 동작 (additive).
+
+Cross-link: `crates/kebab-store-sqlite/src/store.rs::code_lang_chunk_breakdown`, `docs/wire-schema/v1/schema.schema.json`.
+
+## 2026-05-21 — p10-2: k8s multi-resource YAML chunk_id collision
+
+**Origin**: P10 종합 도그푸딩 (`/tmp/kebab-p10-dogfood/`, 16 파일). 한 파일에 2+ k8s document (Deployment + Service, `---` 구분) 인 YAML 이 ingest 실패.
+
+**Symptom**: `DocumentStore::put_chunks (code): UNIQUE constraint failed: chunks.chunk_id`. document row 는 생성되나 chunk 0개 → 검색 불가. p10-2 의 통합 테스트 `tier2_k8s_yaml_ingest_searchable` 가 single-Deployment fixture 만 써서 미발견.
+
+**원인**: `tier2_shared::push_chunks_with_oversize` 의 non-oversize 분기가 `split_key = None` 하드코딩. `K8sManifestResourceV1Chunker` 가 resource 마다 호출 — 같은 document 의 모든 resource 가 `doc_id` + `chunker_version` + `base_policy_hash` 공유 + `split_key = None` → 동일 `id_hash` → 동일 `chunk_id`. p10-3 의 `code_text_paragraph_v1` 가 같은 버그였고 `df3c5b8` 에서 fix 됐지만 그건 `build_chunk_no_symbol` 직접 호출 경로, `push_chunks_with_oversize` 경로는 미수정.
+
+**Fix** (PR #158, v0.16.1): `push_chunks_with_oversize` 에 `base_split_key: Option<u32>` 추가. k8s chunker 가 `Some(resource.line_start)` 전달 → resource 별 distinct chunk_id. dockerfile / manifest 는 `None` (파일당 1 chunk, 충돌 없음, chunk_id 불변).
+
+**Deviation note**: single-resource k8s YAML 의 chunk_id 도 `None → Some(1)` 으로 바뀜 (`id_hash` 가 `base_policy_hash` → `base_policy_hash#L1`). `chunker_version` (`k8s-manifest-resource-v1`) 은 의도적으로 bump 안 함 — p10-2 가 v0.14.0 (~1주 전) 머지된 dogfood 단계라 prod KB 없음. v0.14.0~v0.16.0 사이 single-resource k8s 를 색인한 KB 는 re-ingest 시 old chunk 가 orphan 될 수 있으나 (UNIQUE 충돌 아님 — 다른 id), `kebab reset` 또는 re-ingest sweep 으로 정리됨. dogfood-only 단계라 chunker_version bump (전체 re-process) 보다 가벼운 선택.
+
+Cross-link: `tasks/p10/p10-2-tier2-resource-aware.md` Risks/notes section.
+
+## 2026-05-21 — p10-1D: typedef-wrapped struct/enum in C falls into glue
+
+**Origin**: PR #156 (p10-1d) code-reviewer review. Verified during dogfood.
+
+**Symptom**: `typedef struct { ... } Foo;` in a `.c` file does NOT emit a struct-level unit. tree-sitter-c classifies the construct as a top-level `type_definition` with an *anonymous* inner `struct_specifier` (no `name` field), so the extractor's `struct_specifier` arm doesn't fire — the whole declaration falls into `<top-level>` glue. The named typedef alias `Foo` is therefore not searchable as a symbol.
+
+**Status**: ✅ closed — v0.17.0 (2026-05-24) PR-B 에서 extractor 의 `type_definition` 분기 추가로 해소. 영향은 위 2026-05-24 PR-B 절 참조. 이하는 closure 전 round-2 dogfood 관찰 기록 (frozen).
+
+**Workaround (pre-v0.17.0)**: search the struct by its field/function names, or use `--code-lang c` to broaden scope. Typedef-aliased struct names won't surface as `Citation::Code.symbol`.
+
+**Resolution (v0.17.0)**: extractor 가 top-level `type_definition` 노드를 만나 내부 anonymous `struct_specifier` / `enum_specifier` / `union_specifier` 가 있으면 `declarator` field 의 typedef alias 이름으로 synthetic unit 방출. `PARSER_VERSION` `code-c-v1` → `code-c-v2` bump. design §9 cascade 동작 — 같은 `(workspace_path, asset_id)` 의 `doc_id` 가 새 parser_version 으로 다르게 계산됨. 옛 doc/chunks row + LanceDB orphan 회피용 same-workspace_path orphan purge helper 동반 (`stale_chunk_ids_for_workspace_path_except_doc_id` + `purge_document_at_workspace_path_except_doc_id`).
+
+Cross-link: `tasks/p10/p10-1d-c-cpp-ast-chunker.md` Risks/notes section.
+
 ## 2026-05-20 — p10-1B: Rust 1A-2 symbol path is file-scope-only; 1B+ uses workspace path → module prefix
 
 **무엇이 바뀌었나**: P10-1A-2 의 Rust `code-rust-ast-v1` chunker 가 생성하는 symbol 은 file-scope mod-path nesting 만 사용한다 (예: `Foo::double`). P10-1B 이후 Python / TypeScript / JavaScript 의 symbol 은 workspace 경로 → module path prefix 를 포함한다 (예: `kebab_eval.metrics.compute_mrr`, `src/Foo.Foo.search`).

tasks/INDEX.md

@@ -144,7 +144,7 @@ P0~P5 는 직렬. P6~P9 는 P5 이후 병렬 가능.
   - [p10-1B Python + TS/JS AST chunkers](p10/p10-1b-py-ts-js-ast-chunkers.md) — 🟡 PR 오픈 (코드 완성, 머지 대기)
   - p10-1C-Go Go AST chunker — 🟡 PR 오픈 (v0.12.0, `code-go-ast-v1`)
   - p10-1C-JavaKotlin Java + Kotlin AST chunkers — 🟢 PR 오픈 (v0.13.0, `code-java-ast-v1` / `code-kotlin-ast-v1`)
-  - p10-1D C + C++ AST chunkers — ⏳
+  - p10-1D C + C++ AST chunkers — ✅ 머지 (v0.16.0, `code-c-ast-v1` + `code-cpp-ast-v1`)
   - p10-2 Tier 2 resource-aware — ✅ 머지 (v0.14.0, `k8s-manifest-resource-v1` / `dockerfile-file-v1` / `manifest-file-v1`)
   - p10-3 Tier 3 paragraph + line-window fallback — ✅ 머지 (v0.15.0, `code-text-paragraph-v1`)
 

tasks/p10/INDEX.md

@@ -7,7 +7,7 @@
 | 1B | Python + TS/JS AST chunkers | 🟡 PR 오픈 (코드 완성, 머지 대기) |
 | 1C-Go | Go AST chunker (`code-go-ast-v1`) | 🟡 PR 오픈 (v0.12.0) |
 | 1C-JavaKotlin | Java + Kotlin AST chunkers (`code-java-ast-v1` / `code-kotlin-ast-v1`) | 🟢 PR 오픈 (v0.13.0) |
-| 1D | C + C++ AST chunkers | ⏳ |
+| 1D | C + C++ AST chunkers | ✅ 머지 (v0.16.0) |
 | 2 | Tier 2 resource-aware (k8s / Dockerfile / manifest) | ✅ 머지 (v0.14.0) |
 | 3 | Tier 3 paragraph + line-window fallback | ✅ 머지 (v0.15.0) |
 

tasks/p10/p10-1d-c-cpp-ast-chunker.md

@@ -0,0 +1,120 @@
+# p10-1D — C + C++ AST chunkers
+
+**Status:** 🟡 진행 중
+**Contract sections:** §3.3 (chunker_version `code-c-ast-v1` + `code-cpp-ast-v1`), §3.4 (symbol path — C `func_name`, C++ `namespace::Class::method`), §3.5 (code_lang `c` + `cpp`, ext `.c`/`.h` / `.cpp`/`.cc`/`.cxx`/`.hpp`/`.hh`/`.hxx`), §6.1 (`kebab-parse-code/src/{c,cpp}.rs`), §6.2 (`kebab-chunk/src/code_{c,cpp}_ast_v1.rs`), §9.1 (Tier 1 AST per-language + oversize fallback), §10 (activation log).
+**Design:** [2026-05-15-kebab-code-ingest-design.md](../../docs/superpowers/specs/2026-05-15-kebab-code-ingest-design.md) §1D (C + C++ 부분).
+**Plan:** [2026-05-21-p10-1d-c-cpp-ast-chunker.md](../../docs/superpowers/plans/2026-05-21-p10-1d-c-cpp-ast-chunker.md).
+
+## Goal
+
+p10-1A-2 / 1B / 1C / p10-2 / p10-3 인프라 위에 C + C++ AST chunker 2종을 단일 PR 로 활성화. P10 의 Tier 1 chunker family 마지막. 머지 시점부터 `.c` / `.h` / `.cpp` / `.cc` / `.cxx` / `.hpp` / `.hh` / `.hxx` 파일 dogfooding 가능.
+
+`.h` 가 design 명시대로 C 매핑 — C++ 프로젝트의 `.h` 는 tree-sitter-c 의 parse 가 namespace / template 같은 C++ syntax 에 실패할 가능성. 실패 시 p10-3 의 Tier 3 fallback 으로 자동 picked up (이미 wired).
+
+## 동결된 설계 결정 (이 task 로 확정)
+
+### C extractor (`code-c-ast-v1`)
+
+- **Symbol** = function name only. design §3.4 그대로 — no nesting, no namespace. 예: `parse_blocks`.
+- **Top-level units**:
+  - `function_definition` (named) → 1 unit, symbol = function name
+  - `struct_specifier` (named, top-level) → 1 unit, symbol = struct name
+  - `enum_specifier` (named, top-level) → 1 unit, symbol = enum name
+  - `union_specifier` (named, top-level) → 1 unit, symbol = union name
+  - `declaration` (top-level — typedef / global var / fn prototype) → glue `<top-level>`
+  - `preproc_include` / `preproc_def` / `preproc_function_def` / `preproc_ifdef` 등 preprocessor → glue `<top-level>`
+- **Static / extern / inline fn**: 일반 fn 과 동일 처리 (storage class qualifier 무시 — symbol 은 declarator 의 fn name 만).
+- **Inner struct / enum 안의 nested declaration** (C 도 가능): 1B Python class-nesting 미적용 — C 의 inner type 은 흔치 않고 outer 가 typedef wrapper 인 패턴이라 top-level 만 emit.
+- **Empty file 또는 unit 0개** → `<module>` post-pass (1A-2 패턴).
+
+### C++ extractor (`code-cpp-ast-v1`)
+
+- **Symbol** = `namespace::Class::method` (design §3.4 그대로). namespace 가 없으면 `Class::method` 또는 `func_name`. 예: `kebab::chunk::MdHeadingV1Chunker::chunk_doc`.
+- **Top-level units + recursion**:
+  - `namespace_definition` (named) → recurse with namespace name pushed (Python class-nesting + Java/Kotlin package-prefix hybrid).
+  - **Anonymous namespace** (`namespace { ... }`) → namespace name = `<anonymous>` push (Python `<unnamed>` 패턴 일관).
+  - `class_specifier` / `struct_specifier` (top-level or in namespace or nested in class, named) → recurse with class name pushed.
+  - `function_definition` (top-level or in namespace or in class) → 1 unit, symbol per nesting (`namespace::Class::method` / `namespace::func` / `Class::method` / `func_name`).
+  - `template_declaration` → 내부 declarator type 따라 recurse / emit (function template → method emit, class template → class recurse). template type params (`<T>`, `<typename T>`) 는 symbol 미포함 (Go generic 처리와 동일).
+  - `enum_specifier` (named) → 1 unit, symbol per nesting.
+  - `concept_definition` (C++20) → 1 unit, symbol per nesting (treat as type-level definition).
+  - `using_declaration` / `using_directive` / `preproc_include` / `preproc_def` 등 → glue `<top-level>`.
+  - `extern "C"` 블록 안의 정의 → 일반 fn 처리 (block 자체는 glue).
+- **Method out-of-class definition** (`Class::method` 형태로 namespace 밖에서 정의): tree-sitter-cpp 의 `function_declarator` 의 `qualified_identifier` 따라 prefix 복원 — declarator 의 `Class::method` 자체에서 추출.
+- **Operator overload** (`operator+`, `operator()` 등): symbol = `Class::operator+` 그대로.
+- **Constructor / destructor**: symbol = `Class::Class` / `Class::~Class` (convention).
+- **Empty file 또는 unit 0개** → `<module>` post-pass.
+
+### 공통
+
+- **`<top-level>` glue grouping**: preprocessor + global var + using 선언 등 의미 단위 외 → 1 glue chunk per file.
+- **Oversize fallback**: 1A-2 의 `AST_CHUNK_MAX_LINES = 200` 동일.
+- **`.h` 의 fallback 보장**: C parser 실패 시 p10-3 의 Tier 3 fallback wrapper (이미 wired) 가 picked up → `Citation::Code { symbol: None, lang: "c" }` + `code-text-paragraph-v1`.
+
+### Module layout
+
+```
+crates/kebab-parse-code/src/
+├── c.rs                            [신규] — C AST extractor (PARSER_VERSION `tree-sitter-c-<ver>`)
+├── cpp.rs                          [신규] — C++ AST extractor (PARSER_VERSION `tree-sitter-cpp-<ver>`)
+└── lib.rs                          [edit] — pub use + C_PARSER_VERSION / CPP_PARSER_VERSION 상수 노출
+
+crates/kebab-chunk/src/
+├── code_c_ast_v1.rs                [신규] — VERSION_LABEL `code-c-ast-v1`. 1A-2 패턴 (canonical Document → Vec<Chunk>).
+├── code_cpp_ast_v1.rs              [신규] — VERSION_LABEL `code-cpp-ast-v1`. 동일 패턴.
+└── lib.rs                          [edit] — pub use 2개
+
+crates/kebab-source-fs/src/media.rs  [편집 불요] — code_lang_for_path 위임 패턴 그대로 (Task C of p10-2 이후 단일 source of truth).
+
+crates/kebab-parse-code/src/lang.rs  [편집 불요] — `.c`/`.h`/`.cpp` 등 매핑은 1A-1 시점부터 이미 존재.
+
+crates/kebab-app/src/lib.rs          [edit] — ingest_one_code_asset 의 allowlist + 4-arm match 에 "c" + "cpp" 추가. tier3 fallback list 에도 둘 추가.
+
+crates/kebab-chunk/tests/             [신규]
+├── fixtures/sample.c                — C fixture (top-level fn + struct)
+├── fixtures/sample.cpp              — C++ fixture (namespace + class + method)
+├── code_c_ast_snapshot.rs           — C snapshot test
+└── code_cpp_ast_snapshot.rs         — C++ snapshot test
+
+crates/kebab-app/tests/code_ingest_smoke.rs [edit] — 2 신규 integration test (c + cpp). 16 + 2 = 18.
+
+Cargo.toml workspace.dependencies   [edit] — tree-sitter-c + tree-sitter-cpp.
+crates/kebab-parse-code/Cargo.toml  [edit] — 위 2 dep 신규 entry.
+```
+
+## Acceptance criteria
+
+- `cargo test --workspace --no-fail-fast -j 1` PASS (memory-conscious `-j 1`).
+- `cargo clippy --workspace --all-targets -- -D warnings` clean.
+- C fixture (`tests/fixtures/sample.c`) + C++ fixture (`tests/fixtures/sample.cpp`) ingest → chunk snapshot 안정. C snapshot 의 chunks 가 모두 `Citation::Code { lang: "c", symbol: Some(<fn|struct|enum name>), ... }`. C++ snapshot 의 chunks 가 namespace + class nesting 포함 (`kebab::chunk::Foo::bar`).
+- 격리 TempDir KB 에 `.c` / `.cpp` 파일 두고 `kebab search --code-lang c --json` / `--code-lang cpp --json` 가 각각 `Citation::Code` 반환. integration test `tier1_c_ingest_searchable` + `tier1_cpp_ingest_searchable` (기존 16 + 2 = 18).
+- `kebab schema --json | jq .stats.code_lang_breakdown` 에 `"c"` + `"cpp"` 카운트 등장 (.c/.cpp 파일 ingest 후).
+- README + HANDOFF + docs/ARCHITECTURE + docs/SMOKE + tasks/INDEX + tasks/p10/INDEX 갱신.
+- frozen design 2026-04-27 §10 activation log 한 줄.
+- workspace `Cargo.toml` minor bump (0.15.0 → 0.16.0), gitea-release v0.16.0.
+
+## Allowed dependencies
+
+- `kebab-parse-code` 에 `tree-sitter-c` + `tree-sitter-cpp` workspace deps 추가. 기존 deps 유지.
+- `kebab-chunk` 의 새 모듈 2개 (`code_c_ast_v1.rs`, `code_cpp_ast_v1.rs`) — language-agnostic body, tree-sitter import 금지. 기존 `tier2_shared::build_chunk` (pub(crate)) 재사용.
+- `kebab-app`, `kebab-source-fs` — 새 crate dep 없음.
+
+## Forbidden dependencies
+
+- `kebab-chunk` 가 tree-sitter-c / tree-sitter-cpp 직접 import 금지 (boundary §6.3).
+- `kebab-parse-code` 가 store / embed / llm / rag 직접 import 금지.
+- UI crate (`kebab-cli` / `kebab-mcp` / `kebab-tui`) 가 `kebab-parse-code` / `kebab-chunk` 직접 import 금지 — `kebab-app` facade 만.
+
+## Risks / notes
+
+- **tree-sitter-c / tree-sitter-cpp 호환성**: tree-sitter 0.26 (현재 workspace) 과 호환 필요. resolve 시 `tree-sitter-language` shim 사용 fork (1C-JK 의 tree-sitter-kotlin-ng 패턴) 가능성 — crate.io 의 가장 활발한 maintainer 우선. 실패 시 별도 fork 검토.
+- **`.h` parse 실패**: C++ 헤더 (`namespace`, `template`, `class`) 를 C parser 가 만나면 partial parse + error nodes. 1A-2 의 extractor 패턴이 error node 무시 + recoverable parse 진행 — emit 결과가 *불완전* 할 가능성. 그럴 때 chunks 가 0 으로 떨어지면 p10-3 Tier 3 fallback 으로 자동 picked up (이미 wired). 부분 emit 시 일부만 색인 — Tier 3 fallback 안 함. dogfood 후 HOTFIXES 검토.
+- **Method out-of-class definition** (`Class::method` 형식): tree-sitter-cpp 의 `function_definition` 의 declarator 가 `qualified_identifier` 일 때 prefix 복원. fixture 로 검증.
+- **Template specialization** (`template<> class Foo<int>`): tree-sitter-cpp 의 `template_declaration` 안의 `class_specifier` name 만 추출 — `Foo` 만 symbol 에 들어가고 `<int>` 미포함. design 의 generic 무시 룰 일관.
+- **`extern "C"` block 안의 fn**: 일반 fn 처리. 외부 wrapping block 은 glue.
+- **Anonymous union / struct** (`struct { int x; }` 변수 안에): 흔치 않음 + named 만 unit. anonymous 는 glue.
+- **typedef-wrapped struct/enum idiom** (`typedef struct { ... } Foo;`) — ✅ v0.17.0 (2026-05-24) PR-B 에서 해소. extractor 의 `type_definition` 분기가 inner anonymous `struct_specifier` / `enum_specifier` / `union_specifier` 를 탐지해 declarator 의 typedef alias 이름으로 synthetic unit 방출. `PARSER_VERSION` `code-c-v1` → `code-c-v2` bump + same-workspace_path orphan purge cascade 동반. **잔여 미해결**: nested typedef (`typedef struct { struct {...} inner; } Outer;`) 의 inner 익명 struct 는 여전히 glue — v2 의 1차 범위는 top-level typedef alias 만. See [HOTFIXES.md 2026-05-21 entry](../HOTFIXES.md) (frozen 관찰) + 2026-05-24 closure entry.
+- **Macro-heavy code** (Linux kernel 등): `#define FOO(x) ...` 매크로가 function-like 라도 parser 가 fn 으로 인식 안 함. preprocessor glue 로 처리 — symbol 안 잡힘. 의도된 동작 (parser 의 macro expansion 안 함).
+- **`__attribute__((...))`** annotations: tree-sitter-c 의 attribute 노드는 declarator 옆 sibling. 무시 가능. function name 추출에 영향 없음.
+- **fixture 크기**: sample.c 는 ~30 line (top-level fn + struct + enum + preprocessor), sample.cpp 는 ~50 line (nested namespace + class + method + template + free fn). oversize fallback 의 별도 검증은 1A-2 의 long_section_snapshot 패턴이 이미 cover (필요 시 별도 fixture).
+- **머지 후 deviation** 은 `tasks/HOTFIXES.md` dated 로그 + 본 spec `Risks / notes` cross-link.

tasks/p10/p10-2-tier2-resource-aware.md

@@ -118,3 +118,4 @@ _                                 → skip (p10-3 fallback 의 자리)
 - **`pom.xml` aggregate parent POM** — 매우 큼 (수백~수천 줄). oversize fallback 으로 split. 거대 fixture 로 한 번 검증.
 - **`media.rs` 정리** — 1A-1 부터 누적된 inline `match extension` duplication 을 `code_lang_for_path` 호출로 교체. 기존 단위 테스트 동작 보존 (테스트는 결과 값만 보므로 통과해야 함).
 - **머지 후 deviation** 은 `tasks/HOTFIXES.md` dated 로그 + 본 spec `Risks / notes` 에 one-line cross-link.
+- **[HOTFIXES 2026-05-21]** multi-resource k8s YAML (2+ document) 이 `chunk_id` 충돌로 ingest 실패 — `push_chunks_with_oversize` 의 non-oversize 분기가 `split_key = None` 하드코딩. PR #158 (v0.16.1) 에서 `base_split_key` 파라미터로 fix. See `tasks/HOTFIXES.md` 2026-05-21 entry.