Merge pull request 'fix(ingest): ingest 설정 변경 시 영향 자산 자동 재색인' (#205) from fix/ingest-config-invalidation into main

Reviewed-on: #205

.gitignore

@@ -1,6 +1,7 @@
 .superpowers/
 .worktrees/
 .claude/
-/target/
+.omc/
+/target
 **/*.rs.bk
 Cargo.lock.bak

AGENTS.md

@@ -0,0 +1 @@
+CLAUDE.md

CLAUDE.md

@@ -4,7 +4,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 ## Project
 
-Single-user local-first knowledge base + RAG. Rust 2024 workspace, ~20 crates, single binary (`kebab`). All inference is local (Ollama + fastembed + whisper.cpp).
+Single-user local-first knowledge base + RAG. Rust 2024 workspace, ~21 crates, single binary (`kebab`). All inference is local (Ollama + fastembed + whisper.cpp).
 
 The repo's documentation is split by audience — don't duplicate across them:
 
@@ -27,7 +27,7 @@ cargo build --release                          # produces target/release/kebab
 
 `-j 1` for the full workspace test isn't optional: 18 integration-test binaries each link `lance` + `datafusion` + `arrow` + `tantivy` and the parallel link step exhausts memory (linker gets SIGKILL'd, build silently fails partway). Per-crate runs are fine in parallel.
 
-`target/` is 6–10 GB after a fresh build (DataFusion + Lance + fastembed + 18 × test-binary debug info). The dev/test profile is already trimmed (`debug = "line-tables-only"`, `split-debuginfo = "unpacked"` — see workspace `Cargo.toml`). Run `cargo clean` after phase merges if disk pressure shows up; backtraces still resolve to function + line.
+`target/` is 6–10 GB after a fresh build but **balloons to 90+ GB after a few task cycles** (each fb-* batch adds incremental compile artifacts on top of the existing 18 × test-binary debug info). The dev/test profile is already trimmed (`debug = "line-tables-only"`, `split-debuginfo = "unpacked"` — see workspace `Cargo.toml`). Run `cargo clean` **routinely after each merged PR**, not just "if pressure shows up" — disk space is tight and recovery via `cargo clean` is cheap (one re-link per crate on next build). Verified pattern: 92 GB → 0 GB in seconds, backtraces still resolve to function + line.
 
 ## The facade rule
 
@@ -54,13 +54,13 @@ Each task spec lists `Allowed dependencies` and `Forbidden dependencies` per des
 
 - `kebab-core` MUST NOT depend on any other `kebab-*` crate. Domain types only.
 - `kebab-eval`'s `metrics` and `compare` modules MUST NOT import retrieval / embedding / LLM crates directly. The runner is allowed to use `kebab-app`'s facade (P5-1 inheritance — see deviations in that task spec).
-- UI crates (`kebab-cli`, future `kebab-tui`, `kebab-desktop`) MUST NOT import `kebab-store-*` / `kebab-llm-*` / `kebab-parse-*` directly — only `kebab-app`.
+- UI crates (`kebab-cli`, `kebab-mcp`, `kebab-tui`, future `kebab-desktop`) MUST NOT import `kebab-store-*` / `kebab-llm-*` / `kebab-parse-*` directly — only `kebab-app`.
 
 Read the relevant task spec's deps section before adding an import. New crates inherit the same boundary rules.
 
 ## Wire schema v1
 
-All `--json` output carries a `schema_version` field. Current schemas: `ingest_report.v1`, `ingest_progress.v1`, `search_hit.v1`, `answer.v1`, `doctor.v1`, `reset_report.v1`, `eval_run.v1`, `eval_compare.v1`, `list_docs.v1`, `schema.v1`, `error.v1`. Schemas live in `docs/wire-schema/v1/`. The wire shape is the contract for external integrations (Claude Code skills, MCP, etc.); breaking it requires a `*.v2` major bump and parallel-running both for one phase. In `--json` mode, fatal errors emit `error.v1` to stderr as ndjson (non-`--json` mode keeps plain stderr text); exit codes 0/1/2/3 are unchanged — `error.v1.code` provides fine-grained agent branching.
+All `--json` output carries a `schema_version` field. Current schemas: `ingest_report.v1`, `ingest_progress.v1`, `search_hit.v1`, `answer.v1`, `doctor.v1`, `reset_report.v1`, `schema.v1`, `error.v1`, `chunk_inspection.v1`, `citation.v1`, `doc_summary.v1`. Schemas live in `docs/wire-schema/v1/`. The wire shape is the contract for external integrations (Claude Code skills, MCP, etc.); breaking it requires a `*.v2` major bump and parallel-running both for one phase. In `--json` mode, fatal errors emit `error.v1` to stderr as ndjson (non-`--json` mode keeps plain stderr text); exit codes 0/1/2/3 are unchanged — `error.v1.code` provides fine-grained agent branching.
 
 In-tree integration packages live under `integrations/<host>/` — currently `integrations/claude-code/kebab/` (a Claude Code skill that calls `kebab search --json` / `kebab ask --json`). Any wire schema major bump (v1→v2) MUST update each shipped integration in the same PR, same as the version-cascade rule below. Per-user trigger keywords (team / system / acronym) belong in the user's local copy of the skill, not in the repo-shipped frontmatter — keep `integrations/claude-code/kebab/SKILL.md`'s `description` generic.
 
@@ -81,11 +81,71 @@ Bump 자체는 단순 minor / patch 한 줄 수정 (`Cargo.toml` workspace `vers
 Release 절차:
 
 1. `gitea-release v<X.Y.Z>` (gitea-ops skill) 으로 tag + push + release notes.
-2. release notes 는 사용자 도그푸딩에 영향 가는 surface 변경 위주 — wire schema 추가, CLI flag 신규, TUI 키 변경, V00X migration 등.
-3. 프리-1.0 (`0.x.y`) 단계: minor bump 시 wire schema additive / surface 변경 누적, patch bump 시 bug fix only.
+2. release notes 는 사용자 도그푸딩에 영향이 가는 surface 변경을 위주로 — wire schema 추가, CLI flag 신규, TUI 키 변경, V00X migration 등 — 다룬다. 이때 추가된 기능과 변경사항은 유저가 이해할 수 있도록 친절하고 자세하게 풀어서 설명해야 하며, 단순히 commit subject 를 나열하는 형태로 끝내면 안 된다. 필요하다면 도그푸딩이나 테스트 결과도 함께 적어 둔다.
+3. 프리-1.0 (`0.x.y`) 단계 bump 규칙 — **기능(behavior) 또는 인터페이스(interface) 변경 여부**로 판정:
+   - **minor bump** (`0.x.0`): 기능 또는 인터페이스에 *실질적* 변경이 있을 때. 인터페이스 = 신규/변경/삭제된 CLI subcommand·flag, config 키, wire schema 의 **breaking** 변경, 임베딩/검색/RAG 등 사용자가 받는 **결과·동작**의 변화, V00X migration, frozen 설계 변경. 기능 = 새 source 형식·검색 모드·백엔드 등 *할 수 있는 일*의 추가/변경.
+   - **patch bump** (`0.x.y`): 기능·인터페이스 변경이 **없을** 때. bug fix, 내부 refactor, 성능 개선, 로깅/진행표시 등 **관측성(observability) 개선**, **additive-only wire 변경**(backward-compat 신규 필드/이벤트라 기존 소비자 무영향), 문서. ← 즉 "결과가 같고 새 명령/플래그/config 도 없으면 patch".
+   - 경계 예: 진행 로그에 phase/파일명 추가 + additive wire 이벤트(asset_phase) = **patch** (검색·색인 결과 불변, 새 명령/플래그/config 없음). arctic 임베더 provider + 신규 config 키 = **minor** (인터페이스 추가). 별칭 기능 제거 + migration = **minor** (동작·인터페이스 변경).
 
 **bump 시점 = release 시점 같은 commit**. 즉 commit `chore: bump version 0.x → 0.y` 직후 같은 commit 에 tag. v0.1.0 (`2319206`) 처럼 bump 없이 tag 만 찍는 패턴은 후속 release 가 대상 commit 을 헷갈리게 함 — pre-release snapshot 은 SHA reference 로 충분.
 
+## Dogfood trigger
+
+도그푸딩 = 새 binary 를 실제 KB / 실제 query 로 돌려보고 user-visible 동작이 spec 의 의도와 일치하는지 확인하는 종단 검증. unit / integration test 가 못 잡는 회귀 (UX 어색함, performance regression, 의외의 token 처리, embedding drift, RAG hallucination) 를 catch 함. PR 머지 전 또는 머지 직후 release notes 작성 전에 실시.
+
+### 도그푸딩이 필요한 시점
+
+다음 트리거 중 하나라도 hit 시 도그푸딩 필수. **모두 release-level 또는 user-visible behavior 변경 임**.
+
+**Schema / migration**:
+- 신규 V00X migration (예: V007 trigram, V008 OCR mirror, V009 morphological) — `corpus_revision` cascade + auto-backfill 정책의 사용자 경험 확인.
+- frozen design contract 변경 (`docs/superpowers/specs/2026-04-27-kebab-final-form-design.md` §X 갱신) — verbatim CI diff-check 외의 user-visible side effect 확인.
+
+**Wire schema / CLI surface**:
+- 신규 `--json` 필드, exit code 변경, 또는 schema major bump (v1 → v2) — agent / external integration 의 호환성 검증.
+- `kebab` 의 subcommand 또는 flag 추가/삭제/rename — agent skill / muscle memory 영향.
+
+**Search / RAG behavior**:
+- FTS5 tokenizer / chunker / embedder 모델 / RAG prompt template 변경 — 같은 query 의 hit ordering, snippet, RAG citation 패턴이 자연스럽게 변화하는지.
+- score gate, RRF fusion ratio, NLI threshold 같은 ranking 파라미터 default 변경.
+
+**Performance**:
+- ingest / search / ask latency 의 의도된 변화 (예: lindera tokenize, OCR 추가, multi-hop RAG) — actual wall-clock 측정 + release notes 에 명시.
+- 대용량 KB (수천 doc / 만 chunk) 의 first-boot eager backfill 시간이 사용자 hang 인지에 영향 안 가는지.
+
+**Language / locale**:
+- 한국어 / 일본어 / 중국어 lexical 동작 변경 (V007 trigram, V009 morphological, future N-gram).
+- 영어 substring 매칭 같은 ad-hoc 부산물의 회귀.
+
+**File / asset surface**:
+- 신규 source 형식 (PDF OCR, audio, video) — extractor / chunker 의 실제 corpus 동작.
+- `.kebabignore` / `_external/` 같은 workspace 정책 변경.
+
+**Release-level**: 위 트리거 중 하나가 hit 되어 `Cargo.toml` workspace `version` bump 가 필요하면, **bump commit 이전에 도그푸딩 evidence 가 HOTFIXES + release notes 에 명시** 되어 있어야 함. evidence 없는 release 는 사용자가 "왜 bump 했는지" 추적 불가.
+
+### 도그푸딩 데이터 보관소
+
+모든 도그푸딩 source 문서 + KB state + 로그는 `/build/dogfood/` 한 디렉토리에 누적 보관한다. **분류는 문서 의미 / 종류 / 형식 기준만** — kebab version, 생성 시점, scenario name 같은 prefix 금지 (`v0.20.1-dogfood/`, `dogfood-v018/` 같은 디렉토리 신설 X). 자세한 layout 은 `/build/dogfood/README.md` 참조.
+
+- `/build/dogfood/corpus/` — source 문서 (read-only). format 별 분류 (`markdown/`, `code/`, `html/`, `images/`, `pdf/`, `manifest/`, `resources/`) + 각 format 내 category 별 (예: `markdown/{korean,english,bilingual,tech-docs,coding-md-corpus,topics,notes,edge-cases}`, `code/{rust,python,...}`). 새 fixture 는 적절한 category subdir 에 추가.
+- `/build/dogfood/kb/` — 도그푸딩 run 의 KB 출력 (SQLite + LanceDB + assets + models). 매 run 마다 reset 가능. 별 KB 디렉토리 신설 X.
+- `/build/dogfood/logs/` — 누적 실행 로그 (ndjson + stderr + summary).
+- `/build/dogfood/config.toml` — canonical 도그푸딩 config (없으면 `kebab init` 후 path override).
+- `/build/dogfood/_archive/` — regeneratable stale state (이전 run 의 sqlite/lancedb, XDG snapshot). 디스크 압박 시 wipe 가능.
+
+`/tmp/kebab-smoke/`, `/tmp/kebab-*`, `/build/cache/dogfood*`, `/home/altair823/KnowledgeBase`, `~/.config/kebab/`, `~/.local/share/kebab/`, `~/.local/state/kebab/` 같은 위치 신규 사용 금지 — 모두 `/build/dogfood/` 로 일관. ad-hoc fixture 가 필요하면 `corpus/<format>/<category>/` 에 추가.
+
+### 도그푸딩 결과 기록
+
+도그푸딩 evidence 는 두 곳에 cascade:
+
+1. **`tasks/HOTFIXES.md` 의 dated entry** — 시나리오 별 hit count 표 + snippet evidence + known limitation. 미래에 spec drift 의심 시 git history 외 immediate reference 가 됨.
+2. **`docs/release-notes/v<X.Y.Z>-draft.md`** (또는 gitea release body) — 사용자 도그푸딩 영향에 영향이 가는 surface 변경을 4 단락 (변경 사실 / trade-off / mitigation / upgrade 절차) 으로 풀어서 설명. evidence link.
+
+도그푸딩 단계에서 *발견된 bug* (spec 과 실제 동작의 mismatch, performance regression, UX 어색함) 는 즉시 fix → re-dogfood. fix 가 별 PR 으로 빠지면 머지 후 HOTFIXES 에 dated entry. 
+
+DOGFOOD scenario catalog (§1~§13) 는 `docs/DOGFOOD.md`. 신규 release 마다 §관련 section 의 scenario list 갱신 + 신규 scenario 추가.
+
 ## Naming + paths
 
 - Crate prefix: `kebab-` (kebab-case package, `kebab_` snake_case in Rust modules).
@@ -94,6 +154,7 @@ Release 절차:
 - XDG paths: `~/.config/kebab/`, `~/.local/share/kebab/`, `~/.cache/kebab/`, `~/.local/state/kebab/`.
 - SQLite filename: `kebab.sqlite` (under `data_dir`).
 - Workspace ignore: `.kebabignore` (per directory).
+- `_external/` (under `workspace.root`): single-file / stdin ingest 가 외부 file 을 deterministic 명명 (`<blake3-12>.<ext>`) 으로 copy. 첫 생성 시 `.kebabignore` 자동 append.
 
 The migration from the old `kb` name lives in commits `911fb49 / f1a448d / f9714aa`. If you spot a leftover `kb` reference, treat it as a leftover and fix it (the rename PR sweep covered crates/, docs/, tasks/, README, design doc, fixtures — but workspace root `Cargo.toml` comments needed a follow-up; assume similar misses are possible).
 

Cargo.toml

@@ -2,17 +2,17 @@
 resolver = "3"
 members = [
     "crates/kebab-core",
-    "crates/kebab-parse-types",
     "crates/kebab-config",
     "crates/kebab-source-fs",
     "crates/kebab-parse-md",
-    "crates/kebab-normalize",
     "crates/kebab-chunk",
     "crates/kebab-store-sqlite",
     "crates/kebab-store-vector",
     "crates/kebab-search",
     "crates/kebab-embed",
     "crates/kebab-embed-local",
+    "crates/kebab-embed-candle",
+    "crates/kebab-embed-ollama",
     "crates/kebab-llm",
     "crates/kebab-llm-local",
     "crates/kebab-rag",
@@ -22,6 +22,9 @@ members = [
     "crates/kebab-parse-image",
     "crates/kebab-parse-pdf",
     "crates/kebab-tui",
+    "crates/kebab-mcp",
+    "crates/kebab-parse-code",
+    "crates/kebab-nli",
 ]
 
 [workspace.package]
@@ -29,7 +32,95 @@ edition       = "2024"
 rust-version  = "1.85"
 license       = "MIT OR Apache-2.0"
 repository    = "https://github.com/altair823/kebab"
-version       = "0.3.0"
+version       = "0.26.2"   # v0.26.2 — ingest 설정 변경 시 영향 자산 자동 재색인: ingest 산출에 영향 주는 설정(청킹/이미지 OCR·caption/pdf.ocr/[ingest.code])의 결정적 서명을 effective parser_version(skip 비교 + 저장 doc 필드 양쪽)에 폴딩 → 해당 설정 변경 시 `--force-reingest` 없이 영향 자산만 자동 재색인. 비산출 설정(search/rag/ui/log + max_pixels/languages/timeout 등)은 제외(과도 무효화 회피). doc_id 는 base parser_version 으로 안정 유지(orphan churn 회피). 결과 포맷·CLI·wire 불변(내부 skip 판정 정정) → patch. — CLAUDE.md §Release
+
+# pre-v0.18 workspace-wide cleanup: enable clippy::pedantic group with
+# intentional allow-list. The allowed lints are either cosmetic (doc style),
+# informational (function size), or carry intentional truncation we accept
+# (numeric casts in tokenizer/ONNX inputs, hash modular reduction, etc).
+[workspace.lints.clippy]
+pedantic = { level = "warn", priority = -1 }
+# Intentional u32 ↔ i64 casts in kebab-nli (ONNX i64 inputs from tokenizer u32 ids).
+# u64 ↔ usize across kebab-store-sqlite row counts. Wide truncation is auditable
+# at use site, not lint-wide.
+cast_possible_truncation = "allow"
+cast_possible_wrap       = "allow"
+cast_sign_loss           = "allow"
+cast_precision_loss      = "allow"
+# Doc markdown style is cosmetic; we run rustdoc on demand.
+doc_markdown            = "allow"
+missing_errors_doc      = "allow"
+missing_panics_doc      = "allow"
+# Informational only — splitting a long pipeline function isn't always cleaner.
+too_many_lines          = "allow"
+# `Foo::default()` is concise and idiomatic here; `<Foo as Default>::default()`
+# adds noise without surfacing intent.
+default_trait_access    = "allow"
+# Module name prefix on public items keeps the wire/log surface readable
+# (`refusal_reason::no_chunks` etc).
+module_name_repetitions = "allow"
+# We use `#[must_use]` deliberately on public results, not blanket.
+must_use_candidate      = "allow"
+# `String` arg sometimes signals "I'll consume this" — let signature decide.
+needless_pass_by_value  = "allow"
+# Idiomatic single-line bindings stay; let-else expansion isn't always clearer.
+manual_let_else         = "allow"
+# `use` after `let` is a common kebab pattern (scoped imports next to use site).
+items_after_statements  = "allow"
+# Naming pairs like `chunk_id` / `chunks_id` are intentional domain terms.
+similar_names           = "allow"
+# `iter.map(format!).collect::<String>()` is idiomatic when the per-element
+# string is genuinely independent — `fold` only wins on accumulation patterns.
+format_collect          = "allow"
+# Exhaustive `match` with explicit variant arms (vs `_`) catches future
+# variant additions at compile time (kebab core's `RefusalReason` pattern).
+match_wildcard_for_single_variants = "allow"
+# Copy types under `&self` keep call-site discipline; auto-deref noise > tiny perf gain.
+trivially_copy_pass_by_ref = "allow"
+# `unnecessary_wraps` flags helpers that could drop `Result`, but keeping the
+# Result allows future error variants without churning callers.
+unnecessary_wraps        = "allow"
+# NLI score / RRF fusion / similarity threshold comparisons are intentional —
+# floats live in the `[0, 1]` band and are compared with explicit thresholds.
+float_cmp                = "allow"
+# File-extension dispatch is keyed on ASCII conventions; case sensitivity
+# is part of the spec for `.md`, `.pdf`, etc.
+case_sensitive_file_extension_comparisons = "allow"
+# Config / opts structs intentionally bundle boolean flags (ingest options,
+# search modes, etc) — splitting them into enums would obscure the wire shape.
+struct_excessive_bools   = "allow"
+# `bytecount` crate would be a new dep just for one-off ASCII counts.
+naive_bytecount          = "allow"
+# `#[ignore]` annotations on tests document via the test name + nearby comment.
+ignore_without_reason    = "allow"
+# `format!` push patterns are a hot path for kebab-tui's progressive rendering;
+# `write!` rewrite needs a verified-equal benchmark before swapping.
+format_push_string       = "allow"
+# Builder-style `with_*` methods return `Self`; the existing `#[must_use]`
+# discipline lives on aggregate constructors, not every chainable setter.
+return_self_not_must_use = "allow"
+# Match arms grouped by side-effect over body equality (e.g. snake_case wire
+# label tables) — fanning them out keeps adding a new variant trivial.
+match_same_arms          = "allow"
+# Remaining style-only warnings: trailing `continue` is sometimes clearer than
+# rewriting, `_x` underscored bindings document intent at the use site, and
+# `!(a == b)` reads better than `a != b` when paired with a complementary check.
+needless_continue        = "allow"
+used_underscore_binding  = "allow"
+nonminimal_bool          = "allow"
+# Other one-off cosmetic items: large literal formatting, doc link quoting,
+# `Clone::clone_from` swap, `str::replace` chaining, `Iterator::any` ergonomics.
+unreadable_literal           = "allow"
+many_single_char_names       = "allow"
+doc_link_with_quotes         = "allow"
+assigning_clones             = "allow"
+collapsible_str_replace      = "allow"
+trivial_regex                = "allow"
+elidable_lifetime_names      = "allow"
+range_plus_one               = "allow"
+explicit_iter_loop           = "allow"
+implicit_hasher              = "allow"
+ref_option                   = "allow"
 
 [workspace.dependencies]
 anyhow       = "1"
@@ -52,6 +143,7 @@ proptest     = "1"
 # p9-fb-19: LRU cache for `App::search` results. Bounded capacity
 # from `config.search.cache_capacity` (default 256, ~1.3 MB cap).
 lru          = "0.12"
+lopdf        = "0.32"
 # fastembed-rs ships ONNX runtime via the `ort-download-binaries` feature
 # in its default set (which also pulls `hf-hub` for first-run model
 # downloads). Pinned to the 4.x line per task p3-2 (current 5.x release
@@ -71,10 +163,52 @@ futures      = "0.3"
 # pass; pulled into the workspace deps so future crates can share the
 # same major.
 regex        = "1"
+# MCP (Model Context Protocol) SDK. server + macros + transport-io provide
+# stdio JSON-RPC transport for `kebab-mcp` (p9-fb-30). schemars feature
+# exposes the derive macro used by tool input schemas.
+rmcp         = { version = "1.6", default-features = false, features = ["server", "macros", "transport-io", "schemars"] }
 # Dev-only HTTP mock server for kebab-llm-local Ollama adapter tests. Requires
 # a tokio runtime to host its mock server (the runtime adapter crate stays
 # sync via reqwest::blocking — wiremock is dev-only there).
 wiremock     = "0.6"
+base64       = "0.22"
+# Pure-Rust git library for repo metadata detection (kebab-parse-code).
+# No `git` binary required. Default features include thread-safety + most
+# object-reading capabilities needed for HEAD name + commit SHA queries.
+gix          = { version = "0.70", default-features = false, features = ["revision"] }
+# Rust source parsing for code ingest (kebab-parse-code, p10-1A-2). The
+# chunker stays tree-sitter-free — AST work is parser-side per design §6.3.
+tree-sitter      = "0.26"
+tree-sitter-rust = "0.24"
+# Python / TS / JS grammars for code ingest (kebab-parse-code, p10-1B).
+tree-sitter-python     = "0.25.0"
+tree-sitter-typescript = "0.23.2"
+tree-sitter-javascript = "0.25.0"
+# Go grammar for code ingest (kebab-parse-code, p10-1C-Go).
+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"
+# fb-41 PR-9 (kebab-nli): mDeBERTa-v3 XNLI verifier deps. Versions match
+# the fastembed 4.9 transitive set so the ONNX Runtime + tokenizer stack
+# stays single-versioned across the workspace. ort `default-features=false`
+# drops the bundled binary downloader (fastembed already provides one);
+# tokenizers `default-features=false, onig` swaps the default `esaxx` regex
+# backend for `onig` so the build doesn't need libstdc++ headers (verified
+# via PR-9a pre-flight: SentencePiece tokenizer.json loads + KR/EN encode).
+# hf-hub uses `ureq + rustls-tls` to stay aligned with kebab-embed-local's
+# pure-Rust TLS stack.
+ort          = { version = "=2.0.0-rc.9", default-features = false, features = ["ndarray"] }
+tokenizers   = { version = "0.21", default-features = false, features = ["onig"] }
+hf-hub       = { version = "0.4", default-features = false, features = ["ureq", "rustls-tls"] }
+ndarray      = "0.16"
+# Korean morphological tokenizer (FTS v0.20.x, §6.1). lindera-ko-dic bundles
+# the KO-DIC dictionary as an embedded blob via the embed-ko-dic feature.
+lindera        = "3"
+lindera-ko-dic = "3"
 
 # Disk-footprint trim for dev / test builds. Codegen, opt-level, and
 # behavior are unchanged — only DWARF debug info is reduced (line

GEMINI.md

@@ -0,0 +1 @@
+CLAUDE.md

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 모두 처리. `kebab search` / `kebab ask` 가 매체 가로질러 결과 + page citation 반환. `kebab tui` 가 4 패널 (Library + Search + Ask + Inspect) 제공 — 사용자가 `?` 로 ask, `/` 로 search, Library Enter / Search `i` 로 inspect, Search `g` 로 editor jump. 다음 후보 = P9-5 (desktop tauri) 또는 보류 중인 P8 (audio) 의 시스템 dep brainstorm.
+P0–P5 + P6 + P7 + P9-1/2/3/4 (Library / Search / Ask / Inspect) + P10 전체 머지 완료 (현재 **v0.18.0**). `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. **v0.17.0 cut (2026-05-24)**: 한국어 trigram FTS5 tokenizer (PR #159) + C typedef alias unit (PR #160) + `code_lang_chunk_breakdown` additive (PR #161). **v0.17.1 cut (2026-05-25)**: 확장 도그푸딩 후 `[models.llm] request_timeout_secs` config 노브 (PR #162) + sudo 없이 ollama 설치 + `kebab ask --stream` UX 권장 docs (PR #163). **v0.17.2 cut (2026-05-25)**: v0.17.1 post-dogfood polish — `[image.ocr] request_timeout_secs` 별 노브 (PR #164, v0.17.1 미진행 closure) + `heading_path` FTS5 column filter 로 text-only 매칭 + raw-mode escape hatch (PR #165, 2026-05-24 v0.17.0 trigram entry 의 JSON 노이즈 closure). **v0.18.0 cut (2026-05-26)**: fb-41 multi-hop RAG + NLI verification ship (PR #176-180) — `kebab ask --multi-hop` 의 decompose → decide → synthesize loop + mDeBERTa-v3 XNLI ONNX post-synthesize entailment 검사. dogfood S7 caffeine hallucination 의 silent LLM-self-judge ceiling 해결 (nli_score 0.0035 graceful refuse). 추가 `chore: workspace-wide cleanup + post-PR9 refactor` (PR #181) — clippy::pedantic baseline + H1 config wiring + 9 new tests. 자세한 영향은 [v0.17.0 release notes](https://gitea.altair823.xyz/altair823-org/kebab/releases/tag/v0.17.0) + [v0.17.1 release notes](https://gitea.altair823.xyz/altair823-org/kebab/releases/tag/v0.17.1) + [v0.17.2 release notes](https://gitea.altair823.xyz/altair823-org/kebab/releases/tag/v0.17.2) + [v0.18.0 release notes](https://gitea.altair823.xyz/altair823-org/kebab/releases/tag/v0.18.0). 구조적으로 남은 component 는 P9-5 (desktop tauri) 하나뿐, P8 (audio) 는 사용자 보류.
 
 ## Phase 로드맵
 
@@ -17,20 +17,47 @@ P0–P5 + P6 + P7 + P9-1/2/3/4 (Library / Search / Ask / Inspect) 머지 완료.
 | **P4** | Local LLM + RAG + grounded answer | `kebab-llm`, `kebab-llm-local`, `kebab-rag` | P3 | ✅ 완료 |
 | **P5** | Golden query / regression eval | `kebab-eval` | P4 | ✅ 완료 |
 | **P6** | 이미지 ingestion (OCR + caption) | `kebab-parse-image` | P5 | ✅ 완료 (4/4 component, OCR/caption Ollama-vision) |
-| **P7** | PDF text + page citation | `kebab-parse-pdf` | P5 | ✅ 완료 (3/3 component, page-level chunker + ingest wiring) |
+| **P7** | PDF text + page citation + scanned OCR (v0.20.0 sub-item 1) | `kebab-parse-pdf` + `kebab-app::pdf_ocr_apply` | P5 + P6 | ✅ 완료 (3/3 component, page-level chunker + ingest wiring + post-extract OCR enrichment via qwen2.5vl:3b vision LLM) |
 | **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)**, **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.
 
 ## Component 카운트
 
-총 33 component task — spec 시점 31 개 + 후속 wiring task 3 (P3-5 / P6-4 / P7-3) 가 머지 시점에 추가됨. per-component 진행 + status 는 [tasks/INDEX.md](tasks/INDEX.md).
+총 33 component task — spec 시점 31 개 + 후속 wiring task 3 (P3-5 / P6-4 / P7-3) 가 머지 시점에 추가됨. v0.18.0 cut 시점에 fb-41 multi-hop RAG + NLI verification (PR-9 5 sub-PRs) 가 P9 추가 component 로 ship — `kebab-nli` 신규 crate (mDeBERTa-v3 XNLI ONNX verifier) + `kebab-rag::ask_multi_hop` (decompose/decide/synthesize loop + step 8.5 NLI hook). per-component 진행 + status 는 [tasks/INDEX.md](tasks/INDEX.md).
 
 ## 머지 후 발견된 버그 / 결정 (요약)
 
+- **candle 임베딩 백엔드 다변화** (2026-06-01, Track 1, v0.22.0): `provider = "candle"` opt-in 추가 — 같은 `multilingual-e5-large` 모델을 순수 Rust(candle)로 돌려 듀얼소켓 NUMA 서버의 onnxruntime 48-스레드 double-free 를 회피. `[models.embedding].num_threads`(+env `KEBAB_EMBED_THREADS`)로 CPU 스레드 캡. fastembed default 동작·벡터 불변, `embedding_version` 유지(재색인 0). Phase 0 스파이크 패리티 cosine 1.000000. 상세 HOTFIXES 동일 일자.
+- **config 마이그레이션** (2026-05-31, PR #198): `kebab config migrate` 추가 — 기존 config.toml 에 빠진 섹션을 주석과 함께 채우고 deprecated 정리(멱등·`.bak`·dry-run, 값/주석 보존). `schema_version` 1→2, `init` 도 섹션 주석 포함, doctor 에 `config_migration` 체크. 상세 HOTFIXES 동일 일자.
+
 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:
 
+- **2026-06-03 ingest 설정 변경 자동 재색인** — v0.26.2. ingest 산출에 영향 주는 설정(청킹/이미지 OCR·caption/pdf.ocr/`[ingest.code]`)을 변경하면 `--force-reingest` 없이 영향 자산만 자동 재색인. 그 설정들의 결정적 서명(`ingest_config_signature`)을 effective parser_version(skip 비교 + 저장 doc 필드 양쪽)에 폴딩 → 다음 ingest 비교가 mismatch. 비산출 설정(search/rag/ui/log + max_pixels/languages/timeout)은 제외(과도 무효화 회피), doc_id 는 base 로 안정 유지. **업그레이드 후 첫 ingest 는 전 자산 1회 재색인**(저장된 상수 parser_version ≠ 새 composite; embedding 은 V012 캐시 히트). 결과 포맷·CLI·wire 불변(내부 skip 판정 정정). 자세한 내용: `tasks/HOTFIXES.md` (2026-06-03 ingest 설정 변경 자동 재색인), spec/plan `docs/superpowers/{specs,plans}/2026-06-03-*invalidation*.md`.
+- **2026-06-03 ingest 진행 로그 개선** — v0.26.1. 이미지/PDF + OCR/caption on 볼트 ingest 가 "멈춘 듯" 보이던 문제 해소: TTY 진행바에 현재 파일명 + 느린 phase(ocr/caption/embed)+모델명 + 경과초 `(Ns)` heartbeat, 종료 시 최장 소요 파일 top-5 요약. 신규 wire `asset_phase{idx,total,phase,model}` + `asset_timings.ocr_ms`/`caption_ms`(additive, `ingest_progress.v1` 유지, serde default 0). 이미지·PDF 경로도 `asset_timings` emit(이전 markdown 만). 기본 동작 불변. 자세한 내용: `tasks/HOTFIXES.md` (2026-06-03 ingest 진행 로그), spec/plan `docs/superpowers/{specs,plans}/2026-06-03-ingest-log-improve-*.md`.
+- **2026-06-03 arctic-embed-l-v2.0 임베더 통합** — v0.26.0. 별칭 제거 후 설명형 query recall 보강(측정 recall@10 130/132, e5 +7). `kebab-embed-candle` 모델 레지스트리화(e5 mean + `snowflake-arctic-embed-l-v2.0` CLS, 모델별 pooling/prefix) + 신규 `kebab-embed-ollama`(`provider="ollama"`, `/api/embed`). config `endpoint: Option<String>` 추가. 기본 e5 유지(opt-in), arctic 전환은 embedding_version cascade → 재색인. candle↔Ollama cosine>0.99 게이트로 pooling/prefix 정확성 고정(`#[ignore]`). 자세한 내용: `tasks/HOTFIXES.md` (2026-06-03 arctic), spec `docs/superpowers/specs/2026-06-03-arctic-embedder-spec.md`.
+- **2026-06-03 doc-side expansion(별칭) 기능 완전 제거** — v0.25.0. 아래 2026-05-31 항목의 색인-시 청크당 LLM 별칭 생성 + 별칭 검색 채널을 **전부 제거**(ROI 음수: cross-lingual 은 e5-large 단독으로 충분, 기여는 설명형 +2 그룹뿐인데 대가가 청크당 색인-시 LLM). `Chunk.aliases`/`expansion.rs`/`IngestExpansionCfg`/alias lexical arm/`expansion_progress` wire kind 제거, 신규 마이그레이션 **V013** 이 `chunk_aliases_fts`+`chunks.aliases` DROP. 별칭 default-off 였어 사용자 체감 0, 기존 KB 도 재색인 불요(잔존 별칭 벡터는 `strip_alias_suffix` graceful 매핑/`reset` 정리). `AssetTimings.expansion_ms` 는 wire 호환 위해 값 0 으로 유지. 자세한 내용: `tasks/HOTFIXES.md` (2026-06-03), spec `docs/superpowers/specs/2026-06-03-remove-doc-expansion-spec.md`.
+- **2026-05-31 Phase 2 doc-side expansion 별칭(개별 dense 벡터) + 파생물 캐시(V012)** — v0.21.0 cut. 색인 시 LLM 이 청크별 별칭("같은 의미 다른 표현")을 생성, 줄별 **개별 dense 벡터**(sentinel `{chunk}#alias#N`)로 색인 (묶음 1벡터는 평균화 희석으로 회귀 → 폐기) + boilerplate 청크 skip. `[ingest.expansion]` default off. 측정(나무위키 ~1000 문서 CS corpus): 변형 일관성 14/18 → **16/18**, spread 0.222→0.111, 대조군 false-positive 별칭 무죄. 비용 병목(별칭 18문서 2.5h)은 **파생물 캐시(V012, 청크 내용 해시 키)**로 해소 — 정답 3개 cold 1879s → warm 13s **≈ 145배**, embedding+별칭 LLM 캐싱, version_key cascade 정합. search/ask 가 `kebab.sqlite`+`lancedb` 만으로 동작 → 외부 서버 색인 후 DB 만 복사하는 이식 워크플로 가능. **결정/known limitation**: grounded/refusal 판정이 부분 인용을 grounded 로 오분류(정직한 거부가 false-positive 로 집계) — 별도 개선 후보. stack·svm 설명형 2개 잔존. 자세한 내용: `tasks/HOTFIXES.md` (2026-05-31), 측정: `docs/superpowers/handoffs/2026-05-31-namu-wiki-alias-cache-study.md`.
+- **2026-05-29 v0.20.2 dogfood findings + 검색 품질 baseline** — 8-finding 라운드 완료. (1) Ask 응답언어: rag-v3 default (질문 언어 = 답변 언어). (2) eval `--config` facade 패치 로 dogfood KB 직접 eval 가능. (3) 검색 품질 baseline — hybrid hit@3=1.0 / MRR=0.833, lexical hit@3=1.0 / MRR=0.7 (golden 10 query). **O-2 known limitation**: 소형 모델(gemma4:e4b) refusal 메시지의 query 언어 불일치 가능 — 판정은 정상, 표시 문구만 해당. 자세한 내용: `tasks/HOTFIXES.md` (2026-05-29).
+- **v0.20 sub-item 1 (scanned PDF OCR via qwen2.5vl:3b)**: post-extract enrichment pattern (`kebab-app::pdf_ocr_apply`, H-1 resolution), DCTDecode-only v1 scope (FlateDecode/CCITTFax page 는 warning + skip), parser_version `"pdf-text-v1"` 보존 + force-reingest UX 명문 (H-4).
+- **2026-05-26 kebab-normalize + kebab-parse-types 흡수 (24 → 22 crates, design §3.7b 재작성)** — v0.19.0 cut. 4 parser 중 markdown 한 갈래만 lift 를 경유하는 reality 가 design §3.7b 의 fan-in ≥ 2 가정과 diverge → thin layer (`kebab-parse-types`) + `kebab-normalize` 두 crate 가 `kebab-parse-md` 로 흡수. 5 사용 type + 3 forward-declared struct 모두 `kebab-parse-md::{types,normalize}` module 의 `pub` re-export 로 보존. wire / surface impact = 0 (CLI / TUI / MCP / `--json` / config / XDG / parser_version 모두 unchanged). 자세한 내용: `tasks/HOTFIXES.md` (2026-05-26 design deviation entry).
+- **2026-05-26 v0.18.0 fb-41 multi-hop RAG + NLI verification ship (PR #176-180) + post-PR9 cleanup (PR #181)** — pre-v0.18.0 dogfood (`/build/cache/dogfood-v018/`, 33 assets / 205 chunks, gemma3:4b CPU only / 16 GB RAM) 에서 발견된 S7 caffeine hallucination 의 root cause = LLM-self-judge ceiling (synthesize 가 chunks 와 무관한 Adam optimizer gradient 식을 silent emit, self-judge 가 reject 못함). 학계 표준 (Self-RAG, CRAG, Auto-GDA, MedTrust-RAG) 결론 = deterministic post-synthesis verification. mDeBERTa-v3 XNLI ONNX (280 MB, Xenova HF) 가 `(packed_chunks, answer)` entailment 검사 — `[rag] nli_threshold > 0` (default 0.0 = disabled, production 권장 0.5) 일 때 활성. dogfood retest 측정 — S7 PR-8 baseline `grounded=true + Adam hallucination` → PR-9 `nli_verification_failed, nli_score 0.0035`. wire additive minor — `answer.v1.verification` field + `refusal_reason` 의 `nli_verification_failed` / `nli_model_unavailable` 추가, pre-v0.18 reader 무영향. 5 sub-PR 시퀀스 + cleanup PR (clippy::pedantic baseline + 의도적 30+ allow + H1 `[models.nli].model` config wiring + 9 new tests). post-refactor retest = PR-9d byte-identical (deterministic 확인). 자세한 내용: `tasks/HOTFIXES.md` (2026-05-25 fb-41 PR-9 closure entry + S3 follow-up).
+- **2026-05-25 v0.17.2 post-v0.17.1 polish (PR #164 + #165)** — v0.17.1 의 두 follow-up closure. (1) `[image.ocr] request_timeout_secs` 별 노브 — `crates/kebab-parse-image/src/ocr.rs::REQUEST_TIMEOUT` hard 300s 제거, LLM 쪽 패턴 (PR #162) 을 OCR 어댑터에 동일 적용. 사용자 결정으로 별 노브 분리 (OCR vs LLM 의 cold start 패턴이 달라 독립 조절). v0.17.1 미진행 항목 closure. (2) `chunks_fts` 의 `heading_path` 컬럼이 JSON 표기 + path 세그먼트 까지 trigram 색인 → query false positive 가능 문제 closure. `lexical.rs::build_match_string` 가 non-raw 분기 결과를 `text : (<expr>)` 로 wrap — heading 색인 V007 verbatim 유지, 매칭만 text 한정. 사용자가 명시 heading 검색 하려면 raw mode `'heading_path : <token>'` escape hatch (SKILL.md 갱신). 둘 다 additive (옛 config 호환) / re-ingest 불필요. 자세한 내용: `tasks/HOTFIXES.md` (2026-05-25 v0.17.2 두 entry).
+- **2026-05-25 v0.17.1 post-dogfood (PR #162 + #163)** — 확장 도그푸딩 (16 GB CPU only, gemma4:e4b 시도) 에서 발견된 두 follow-up 한 묶음. (1) `crates/kebab-llm-local/src/ollama.rs::REQUEST_TIMEOUT` hard 300s → `[models.llm] request_timeout_secs` config + env override (additive, default 300, `=0` 은 disable 아닌 "즉시 timeout" 이라 doc 명시). (2) README + SMOKE 에 sudo / systemd 없이 ollama 설치 + ≤4B Q4 권장 모델 + `kebab ask --stream` UX 권장 docs. additive only — 옛 config / wire 호환. 자세한 내용: `tasks/HOTFIXES.md` (2026-05-25).
+- **2026-05-24 v0.17.0 PR-C `code_lang_chunk_breakdown` additive (closure of 2026-05-22 LOW)** — `schema.v1.stats` 에 chunk 수 집계 신규 키. 기존 `code_lang_breakdown` (doc count) 와 sister. 또 기존 두 필드 JSON schema description 의 "chunk count" 오기재 → "doc count" 로 정정. wire additive — schema_version bump 불필요. 자세한 내용: `tasks/HOTFIXES.md` (2026-05-24 PR-C).
+- **2026-05-24 v0.17.0 PR-B C typedef alias unit (closure of 2026-05-21)** — `kebab-parse-code::c::extract_blocks` 의 `type_definition` 분기로 inner anonymous struct/enum/union → declarator 의 typedef alias 이름으로 synthetic unit 방출. `PARSER_VERSION code-c-v1` → `code-c-v2` bump + 같은-asset/다른-doc_id 케이스용 `purge_workspace_path_for_parser_bump` cascade (`stale_chunk_ids_for_workspace_path_except_doc_id` + `purge_document_at_workspace_path_except_doc_id` helper 신규). 사용자 작업 불필요 (다음 ingest 가 자동 재처리). 자세한 내용: `tasks/HOTFIXES.md` (2026-05-24 PR-B).
+- **2026-05-24 v0.17.0 PR-A 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
+- **2026-05-07 fb-28 (main.rs)** — `--readonly` (KEBAB_READONLY) blocks Ingest/IngestFile/IngestStdin/Reset; `--quiet` suppresses progress stderr; error.v1 code: "readonly_mode"
+
+- **2026-05-07 macOS XDG path collision (config 사라지는 버그)** — `dirs` crate 가 macOS 에서 `config_dir()` 과 `data_dir()` 둘 다 `~/Library/Application Support/` 반환 → `reset --data-only` 가 config 파일까지 삭제. Fix: `~/.config`, `~/.local/share`, `~/.cache` 직접 사용. 새 경로: config `~/.config/kebab/`, data `~/.local/share/kebab/`, cache `~/.cache/kebab/`. `Config::load(None)` 이 macOS legacy path 에서 자동 마이그레이션. 자세한 내용: `tasks/HOTFIXES.md`.
+- **2026-05-07 P9 post-도그푸딩 (p9-fb-31)** — `kebab ingest-file <path>` + `kebab ingest-stdin --title <T>` 두 신규 subcommand + MCP tool `ingest_file` / `ingest_stdin` (4 → 6 tool). agent 가 fetch 한 web markdown / 외부 file 을 KB 에 즉시 저장. workspace 외부 file 은 `<workspace.root>/_external/<blake3-12>.<ext>` 로 copy (deterministic 명명 → idempotent). `_external/` 디렉토리 첫 생성 시 `.kebabignore` 자동 append (walk 무한 루프 방지). stdin 은 markdown 전용 + flag (`--title`, `--source-uri`) → frontmatter 자동 prepend. .kebabignore 매치 시 stderr warn 후 진행 (explicit ingest = bypass intent). fb-30 의 v1 read-only MCP 정책 변경 — 첫 mutation tool 도입. spec: `tasks/p9/p9-fb-31-single-file-stdin-ingest.md`. design: `docs/superpowers/specs/2026-05-07-p9-fb-31-single-file-stdin-ingest-design.md`.
+- **2026-05-07 P9 post-도그푸딩 (p9-fb-30)** — `kebab mcp` 신규 subcommand + new crate `kebab-mcp` (lib only) — stdio JSON-RPC server. 4 read-only tool (`search` / `ask` / `schema` / `doctor`) 가 `kebab-app` facade 위에 build. rmcp 1.6 SDK 채택, manual `tools/list` + `tools/call` dispatch (rmcp 의 `#[tool_router]` 매크로 대신). `error_classify` 모듈을 `kebab-cli` → `kebab-app::error_wire` 로 promotion (UI crate 끼리 import 회피, facade 룰 준수). `ErrorV1` 에 `schema_version: String` 필드 추가 — kebab-mcp 의 직접 serialize 경로에서도 wire 정합. `KebabAppState` 가 `(Config, Option<PathBuf>)` carry — doctor tool 의 path-aware behavior 위해. ask + search arm 의 `tokio::task::spawn_blocking` wrap — `OllamaLanguageModel` 의 reqwest blocking client 가 async 안에서 panic 회피. capability flag `mcp_server` `false` → `true`. agent integration MVP 완성 — Claude Code / Cursor / OpenAI Agents 등 host-agnostic 사용 가능. spec: `tasks/p9/p9-fb-30-mcp-server.md`. design: `docs/superpowers/specs/2026-05-07-p9-fb-30-mcp-server-design.md`.
 - **P3-5 / P4-3 `--config` 누락** — `kebab-cli` 가 `--config <path>` 를 honor 하려면 `kebab_app::*_with_config` companion 을 호출해야 함. 두 번 같은 모양으로 회귀했음.
 - **P6-2 OCR 기본 엔진** — spec literal 의 Tesseract 가 시스템 dep 부담으로 거부됨, Ollama vision LM 으로 대체. `OcrEngine` trait 그대로라 future swap 가능.
 - **P6-3 caption** — `GenerateRequest.images` 필드를 `kebab-core::LanguageModel` trait 에 신설. 기존 caller 모두 `images: Vec::new()` 로 마이그레이션.
@@ -72,25 +99,88 @@ 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** — ✅ v0.17.0 cut (2026-05-24) 으로 세 항목 모두 closure (한국어 trigram PR-A + C typedef alias PR-B + code_lang_chunk_breakdown additive PR-C). 상세 cross-link: 아래 "P10 dogfooding 백로그" 절 + `tasks/HOTFIXES.md` (2026-05-24 PR-A/B/C).
+- **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) — 4 minor release 분할
+### v0.20.0 sub-item 1 (PDF scanned OCR) 머지 후 priorities (2026-05-28, 사용자 결정)
 
-2026-05-06 도그푸딩 누적 피드백 + "AI agent 가 kebab 을 쓰게 한다" 궁극 목표용 surface 확장. 17 항목 모두 **status: open + brainstorm 선행 필요**. 각 spec 상단 banner 명시. cascade 영향 / 분량 고려해 한 minor 에 묶지 않고 4 분할. 2026-05-06 renumber — **번호 = release 순서**:
+PR #189 (2026-05-28 머지, commit `09333d0`) 으로 PDF scanned OCR (qwen2.5vl:3b vision LLM) + 4 round bugfix (#2/#3/#4/#6/#7/#9/#10/#11/#13/#14) + ingest log feature 가 main 으로 진입. 다음 작업 순서 = **C → B → A → G**.
 
-- **0.3.0 — agent foundation**: fb-26 (log), fb-27 (introspection/error wire), fb-28 (readonly/quiet), fb-29 (daemon), fb-30 (MCP), fb-31 (single-file ingest). agent 통합 MVP.
-- **0.4.0 — agent surface refinement (additive)**: fb-32 (stale), fb-33 (streaming), fb-34 (budget), fb-35 (verbatim fetch), fb-36 (filters), fb-37 (trace/stats).
-- **0.5.0 — RAG quality (cascade 동반)**: fb-38 (score semantics), fb-39 (precision tuning, embedding_version cascade + V00X), fb-40 (fact-grounded, prompt_template_version cascade).
-- **0.6.0 또는 P+**: fb-41 (multi-hop, XL), fb-42 (bulk/rerank, Nice).
+- **C — 한국어 morphological tokenizer (Bug #8 follow-up)** ✅ **v0.20.1 머지 완료**.
+  - V007 trigram 의 ≥3 char query 제약 (HOTFIXES `2026-05-22`) — '한국' 같은 2-char 한국어 query 0 hit → V009 migration + lindera-ko-dic tokenizer + tokenized_korean_text column + first-boot eager backfill 으로 해소. branch `feat/korean-morphological-tokenizer` (8 commit + 5 follow-up).
+  - scope: search index 재빌드 cascade (corpus_revision bump) + V007 trigram 보존 (backward-compat).
+  - 사용자 surface: `kebab search` 의 한국어 2자 query ('한국', '서울') 매칭. README + SKILL + release notes 반영.
+
+- **B — OCR dense page coverage** ⏳ C 다음.
+  - metro-korea.pdf page 8/13 timeout (180s, dense newspaper article). vision LLM 의 output token 과대 → 정상 timeout.
+  - 가능한 path: (a) per-page `max_pixels` 동적 조정 (high-resolution page 만 축소), (b) column-level sub-region OCR (newspaper layout 분할 후 OCR call 분리), (c) model upgrade (qwen2.5vl:7b — Ollama 모델 변경 + max_pixels trade-off), (d) OCR timeout 점진 축소 (180s → 120s → 90s) — round 마다 p90 측정 후.
+  - mojibake.pdf `pdf_ocr_pages: 0` (round 1 부터 동일) — text-detect path fallback 강화 검토.
+  - 별 sub-item.
+
+- **A — v0.20 의 deferred sub-items (frozen design contract)** ⏳ B 다음.
+  - **sub-item 2** — Multi-region image dispatch (`OcrText.regions` bbox 분리) — image OCR + PDF column-aware OCR.
+  - **sub-item 3** — PDF normalize integration (`ParsedPdfPage` production caller + `build_canonical_document_from_pdf_pages` + cross-page reference graph).
+  - **TODO #4** — Per-page image / table extraction (PDF figure / table extract).
+  - **TODO #5** — Enricher trait 도입 — OCR + caption 의 `Extractor` trait 통합 (post-extract enrichment 의 generalization).
+  - 각 sub-item 별 spec/plan/executor cycle.
+
+- **G — v0.20.1 patch release + release notes** ⏳ A 머지 후 (또는 C/B 시점에 따라 조기 cut).
+  - CLAUDE.md release 룰 — sub-item 1 base + bugfix1-4 + log feature + logging r2 누적 → minor surface 변경 다수 + wire schema additive minor + config 신규 → **v0.20.1 patch bump + release notes**.
+  - 핵심 surface (사용자 도그푸딩 가이드 형식):
+    - **한국어 2자 query 지원** (`kebab search` 에서 '한국', '서울' 같은 2자 단어 매칭 — V009 morphological tokenizer). 
+    - OCR timeout default 180s (HOTFIXES 2026-05-28).
+    - `[logging]` config section (default enabled) + `{state_dir}/logs/ingest-{run_id}.ndjson` 자동 생성.
+    - `[logging] keep_recent_runs` (100) + `retention_days` (30) — OR-on-stale cleanup.
+    - `ingest_progress.v1.pdf_ocr_finished` 의 4 추가 field (image_byte_size, image_width, image_height, failure_reason) — image_w/h 가 round 2 (PR #190) 에서 실제 capture.
+    - `schema.v1.models` 의 `active_parsers` + `active_chunkers` (additive minor).
+    - V008 migration — `pdf_ocr_events` table (per-OCR-call historical record).
+    - 새 wire schemas — `ocr_stats.v1` + `ocr_failures.v1` (CLI inspect 의 emit).
+    - CLI `kebab inspect ocr-stats` + `kebab inspect ocr-failures` — sweet-spot 점진 분석.
+    - CLI `--media code` first-class, empty query → `invalid_input`, `--config` missing → `config_not_found` + exit 2.
+    - capabilities.streaming_ask + single_file_ingest 가 true (이전 false 거짓 정정).
+  - bump 작업: workspace `Cargo.toml` version → 0.20.1, tag, gitea-release.
+
+### v0.20 후속 bug catalog (non-blocking known)
+
+본 PR #189 dogfood 에서 **falsified** 또는 **design constraint** 로 분류 — fix 안 함:
+- Bug #8 (V007 trigram 2-char query 한계) → 위 C 항목.
+- Bug #12 (Code block wire `.code` field, `.text` 가 아닌 jq fallback artifact) — falsified.
+- ask 한국어 query phrasing-sensitive refusal — RAG corner case / NLI gate behavior. 별도 brainstorm.
+
+### Logging feature enhancements — ✅ closed (PR #190, 2026-05-28 merged commit `7bbdc89a`)
+
+logging round 2 (PR #190) 으로 4 enhancement 모두 closed:
+- ✅ `image_width` + `image_height` capture (raster JPEG decode).
+- ✅ SQLite mirror (V008 `pdf_ocr_events` table + dual-write).
+- ✅ CLI query (`kebab inspect ocr-stats` + `ocr-failures` — `ocr_stats.v1` + `ocr_failures.v1` wire schemas).
+- ✅ log retention (`keep_recent_runs` + `retention_days` — file + SQLite cleanup).
+
+### P9 dogfooding 백로그 (fb-26 ~ fb-42) — release 분할
+
+2026-05-06 도그푸딩 누적 피드백 + "AI agent 가 kebab 을 쓰게 한다" 궁극 목표용 surface 확장. cascade 영향 / 분량 고려해 한 minor 에 묶지 않고 분할.
+
+- **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** ✅ 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) PR-A 머지 (#159). V007 trigram migration 자동 backfill + `build_match_string` 재설계 + CLI/TUI/wire hint. HOTFIXES `2026-05-24 PR-A` 참조.
+- **code_lang_chunk_breakdown chunk 단위 집계 (LOW)** — ✅ v0.17.0 (2026-05-24) PR-C 머지 (#161). `schema.v1.stats` additive 필드. HOTFIXES `2026-05-24 PR-C` 참조.
+- **C typedef-wrapped struct (LOW)** — ✅ v0.17.0 (2026-05-24) PR-B 머지 (#160). `type_definition` 분기 + `PARSER_VERSION code-c-v2` bump + orphan purge cascade. HOTFIXES `2026-05-24 PR-B` 참조.
+- **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

@@ -1,89 +1,196 @@
-# kebab — Local-first Knowledge Base
+# kebab — Local-first Knowledge Base + RAG
 
-`kebab` 는 개인용 로컬 knowledge base + RAG 도구다. Markdown / PDF / 이미지를 한 곳에 색인하고, 의미 검색 + page-단위 citation 포함 LLM 답변을 단일 binary 로 제공한다. 모든 추론은 로컬 (Ollama / fastembed) 에서 돌아간다. 대상 하드웨어: M4 48GB MacBook 1대, 사용자 1명.
-
-## 사전 요구
-
-- **Rust toolchain** ≥ 1.85 (workspace 가 edition 2024 + resolver 3 사용). [rustup](https://rustup.rs) 권장.
-- **Ollama** — `kebab ask` 와 이미지 OCR/caption 가 사용. `https://ollama.com/download` 에서 설치 후 `ollama serve` 실행. 기본 LLM 은 gemma4 계열 (`ollama pull gemma4:e4b`) — OCR / caption 도 같은 family 라 모델 하나만 pull 하면 됨. 더 큰 variant 원하면 `gemma4:26b` 등으로 config override. config 의 `[models.llm].endpoint` 에 host:port 명시.
-- **빌드 디스크** — 첫 빌드 시 `target/` 가 6–10 GB (Lance + DataFusion + fastembed). 여유 확인.
-- **fastembed 모델** — 첫 `kebab ingest` 시 `multilingual-e5-small` (~470 MB) 자동 다운로드.
-
-## 설치
-
-표준 경로는 `cargo install` — `~/.cargo/bin/kebab` 가 PATH 에 있는지만 확인하면 끝.
-
-```bash
-# 1) repo clone
-git clone https://gitea.altair823.xyz/altair823-org/kebab.git
-cd kebab
-
-# 2) binary 빌드 + 설치 (~/.cargo/bin/kebab)
-cargo install --path crates/kebab-cli --locked
-
-# 3) PATH 확인 (아직 추가 안 했으면 ~/.bashrc / ~/.zshrc 에 추가)
-which kebab          # → /Users/<you>/.cargo/bin/kebab 같은 경로
-kebab --version      # → kebab 0.1.0
-```
-
-git URL 직접 install 도 가능 (clone 없이):
-
-```bash
-cargo install --git https://gitea.altair823.xyz/altair823-org/kebab.git --bin kebab --locked
-```
-
-업데이트는 `git pull && cargo install --path crates/kebab-cli --locked --force` 또는 git URL 형식의 경우 `cargo install --git ... --force`.
-
-제거는 `cargo uninstall kebab-cli`. 이 명령은 binary 만 지우고 워크스페이스 데이터는 그대로 남는다. 데이터까지 정리하려면 `kebab reset --all --yes` (config + data + cache + state 4 개 XDG 경로 모두 wipe — **irreversible**, 재시작 시 `kebab init` 다시 실행). 부분 wipe 는 `kebab reset --data-only` (config 보존), `kebab reset --vector-only` (Lance + `embedding_records` 만, 다음 ingest 가 re-embed) 등.
+`kebab` 는 개인용 로컬 knowledge base + RAG 도구다. Markdown · PDF · 이미지 · 소스코드를 한 곳에 색인하고, 하이브리드 의미 검색과 근거 인용을 포함한 LLM 답변을 **단일 binary** 로 제공한다. 모든 추론은 로컬 (Ollama + fastembed) 에서 돌아간다.
 
 ## Quick start
 
+사전 요구는 두 가지뿐이다.
+
+- **Rust toolchain** ≥ 1.85 (workspace 가 edition 2024 사용). [rustup](https://rustup.rs).
+- **Ollama** — `kebab ask` 와 이미지/PDF OCR 가 사용. [공식 설치 안내](https://ollama.com/download) 참고 후 `ollama serve` 실행. 기본 LLM family 는 gemma4 (`ollama pull gemma4:e4b`) — OCR/caption 도 같은 family 라 모델 하나면 된다. CPU-only 환경이면 소형 모델 (예: `gemma3:4b`) 을 권장.
+
 ```bash
-# 첫 실행 — XDG 경로에 데이터 디렉토리 + config.toml 생성
+# 1) 빌드 + 설치 (~/.cargo/bin/kebab)
+git clone https://gitea.altair823.xyz/altair823-org/kebab.git
+cd kebab
+cargo install --path crates/kebab-cli --locked
+
+# 2) 데이터 디렉토리 + config.toml 생성 (XDG 경로)
 kebab init
 
-# config 손보고 — workspace.root, 모델 endpoint 등 설정 (지원 형식은 md / png / jpg / pdf 로 고정)
+# 3) config 최소 손보기 — workspace.root (색인할 폴더) 와 LLM endpoint
 ${EDITOR:-vi} ~/.config/kebab/config.toml
 
-# 색인 (Markdown / 이미지 / PDF 모두 한 번에)
+# 4) 색인 (Markdown · PDF · 이미지 · 소스코드 한 번에)
 kebab ingest
 
-# 검색 (citation 의 source_span 이 매체별로 line / region / page)
-kebab search "Markdown chunking 규칙" --mode hybrid
+# 5) 검색 (hybrid = lexical + vector RRF, citation 포함)
+kebab search "Markdown chunking 규칙"
 
-# 질문 (Ollama 필요, PDF 인용 시 page 번호 surface)
+# 6) 질문 (RAG 답변 + 근거 인용, Ollama 필요)
 kebab ask "내 KB 설계에서 저장소 전략은?"
-
-# Ratatui 셸 (Library + Search + Ask + Inspect 패널, desktop 진행 중)
-kebab tui
-
-# 헬스 체크 (config 경로 / 데이터 디렉토리 쓰기 가능 여부)
-kebab doctor
 ```
 
-격리된 임시 워크스페이스로 돌려보는 절차는 [docs/SMOKE.md](docs/SMOKE.md) — `--config <path>` 로 분리. 이미지 / PDF fixture 가 필요하면 두 example 바이너리 (`cargo run --release --example gen_smoke_pdf -p kebab-parse-pdf` / `gen_smoke_png -p kebab-parse-image`) 로 시스템 dep 없이 in-tree 생성 가능.
+clone 없이 git URL 로 바로 설치할 수도 있다: `cargo install --git https://gitea.altair823.xyz/altair823-org/kebab.git --bin kebab --locked`. 업데이트는 동일 명령에 `--force`. 제거는 `cargo uninstall kebab-cli` (데이터는 보존 — 데이터까지 지우려면 `kebab reset --all --yes`).
 
-설치 없이 dev 흐름으로 돌려볼 때는 `cargo run --release -p kebab-cli -- <subcommand>` 또는 `cargo build --release && ./target/release/kebab <subcommand>`.
+설치 없이 dev 흐름으로 돌려볼 때는 `cargo run --release -p kebab-cli -- <subcommand>`. 격리된 임시 워크스페이스로 검증하는 절차는 [docs/SMOKE.md](docs/SMOKE.md) (`--config <path>` 로 분리).
+
+## 핵심 기능
+
+### 하이브리드 검색 + citation
+
+lexical (FTS5 BM25) 과 vector (cosine) 두 채널을 **RRF fusion** 으로 합쳐 검색한다. 모든 hit 은 출처 위치를 매체별로 정확히 담는다 — Markdown/코드는 line, 이미지는 region, PDF 는 page. `--tag` · `--media` · `--lang` · `--path-glob` 등 다양한 필터와 `--max-tokens` · `--cursor` 같은 agent budget flag 를 지원한다.
+
+### 파생물 캐시 (자동)
+
+embedding 벡터를 청크 **내용 해시** 로 캐싱한다 (`derivation_cache`). 재색인·갱신 시 내용이 같은 청크는 재계산을 건너뛴다. 캐시 키에 모델·차원 버전이 포함돼 버전 변경 시 자동 무효화된다 (cascade 안전). 별도 설정 없이 투명하게 동작한다. (현재 TTL/LRU 자동 정리는 미구현 — 누적된 캐시는 `kebab reset` 으로만 정리.)
+
+### 외부 계산 + 로컬 검색 워크플로
+
+search/ask 는 원본 파일 없이 KB 산출물만으로 동작한다 (청크 본문이 SQLite 에 저장되고 문서 경로는 상대경로로 기록됨). 비싼 색인(임베딩·OCR)을 성능 좋은 머신에서 수행한 뒤(예: Apple Silicon 맥에서 candle Metal GPU), **두 산출물만** 다른 머신(예: NUMA 서버)으로 복사하면 그대로 검색·질문할 수 있다.
+
+**무엇을 복사하나 — `[storage]` 에서 정의된 두 경로:**
+
+| 복사 대상 | config 키 (`[storage]`) | 기본 경로 | 내용 |
+|-----------|------------------------|-----------|------|
+| `kebab.sqlite` | `sqlite = "{data_dir}/kebab.sqlite"` | `{data_dir}/kebab.sqlite` | 문서·청크·본문·FTS5·메타 |
+| `lancedb/` | `vector_dir = "{data_dir}/lancedb"` | `{data_dir}/lancedb/` | 임베딩 벡터 |
+
+`{data_dir}` 는 `[storage].data_dir` (예: `~/.local/share/kebab`). `models/`(`model_dir`)·`assets/`(`asset_dir`)는 **복사 불필요** — 모델은 각 머신이 자기 캐시를 받고, asset 원본 바이트는 검색·질문에 쓰이지 않는다 (단일파일/`stdin` 색인의 원본 재읽기·재색인까지 보존하려면 `assets/` 도 함께 복사).
+
+```bash
+# ingest 가 끝난(쓰기 없는) 상태에서 복사
+rsync -a <src-data_dir>/kebab.sqlite  user@server:<dst-data_dir>/
+rsync -a <src-data_dir>/lancedb/      user@server:<dst-data_dir>/lancedb/
+```
+
+조건: **양쪽 동일 `kebab` 버전 + 동일 임베딩 모델/차원** (`[models.embedding].model`·`dimensions`). provider 는 달라도 됨 (예: 맥 `candle`/Metal ↔ 서버 `candle`/CPU 또는 `fastembed` — 같은 모델이면 벡터 호환). 복사는 반드시 ingest 가 돌지 않을 때.
+
+### 멀티미디어 색인
+
+Markdown · PDF · 이미지(OCR + caption) · 소스코드(Rust/Python/TS/JS/Go/Java/Kotlin/C/C++ AST) · 리소스(YAML/Dockerfile/TOML/JSON/XML 등)를 확장자에 따라 자동으로 적절한 chunker 에 라우팅한다. embedded text 가 없는 scanned PDF 는 `[pdf.ocr]` 로 page-단위 OCR (opt-in). 전체 확장자→chunker 매핑은 [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md).
+
+### RAG (근거 인용 + 거절)
+
+검색 결과를 근거로 LLM 답변을 생성하고 [#번호] 인용을 단다. 근거가 부족하면 답을 지어내지 않고 거절한다. compound 질문은 `--multi-hop` 으로 분해→synthesize. 답변의 groundedness 는 mDeBERTa XNLI 로 검증할 수 있다 (`[rag] nli_threshold`, default off).
+
+### TUI
+
+`kebab tui` 는 Ratatui 셸 — Library / Search / Ask / Inspect 패널을 vim-style 모드로 다룬다. 키 매핑은 앱 내 `F1` cheatsheet 가 권위 소스다.
 
 ## 명령
 
 | 명령 | 동작 |
 |------|------|
 | `kebab init` | XDG 경로에 데이터 디렉토리 + config.toml 생성 |
-| `kebab ingest [<path>]` | Markdown / 이미지 / PDF 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`). 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. |
-| `kebab search --mode {lexical,vector,hybrid} "<query>" [--no-cache]` | 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 |
+| `kebab ingest [<path>]` | 워크스페이스 스캔 후 새/변경 문서 색인 (idempotent · incremental, `--force-reingest` 로 강제 재처리). 미지원 확장자는 자동 skip. 진행바는 현재 **파일명** · 느린 **phase(ocr/caption/embed)+모델명** · **경과초**`(Ns)` · 문서별 청크 수 · phase별 소요시간(parse/chunk/ocr/caption/embed/store)을 표시하고, 종료 시 **최장 소요 파일 top-5** 를 요약한다 (`--json` 은 `asset_phase`/`asset_chunked`/`asset_timings` 이벤트로, 사람용 요약은 미출력) |
+| `kebab ingest-file <path>` | 단일 파일 ingest (workspace 외부 가능 — `_external/` 로 deterministic copy) |
+| `kebab ingest-stdin --title <T>` | stdin 의 markdown 본문 ingest |
+| `kebab search --mode {lexical,vector,hybrid} "<query>" [flags]` | 검색 (default hybrid = RRF fusion, citation 포함). 필터/budget flag 는 `--help` |
+| `kebab ask "<query>" [flags]` | RAG 답변 + 근거 인용 (Ollama 필요). `--session` (multi-turn) · `--stream` · `--multi-hop` |
 | `kebab list docs` | 색인된 문서 목록 |
-| `kebab inspect doc <id>` / `kebab inspect chunk <id>` | raw record 보기 |
-| `kebab ask "<query>" [--show-citations / --hide-citations] [--session <id>]` | RAG 답변 + 근거 인용. 답변 후 `근거:` block 으로 full path / line range / score 한 줄씩 (default ON — `--hide-citations` 로 끄기, pipe 시 유용). 근거 부족 시 거절. Ollama 필요. `--session <id>` 로 multi-turn — 첫 호출에서 SQLite `chat_sessions` 에 자동 생성, 이후 호출은 prior turns 를 history 로 받아 follow-up. session id 는 사용자 지정 (e.g. `kb-rust-async-2026-05`) — `kebab reset --data-only` 로 모든 session wipe |
-| `kebab doctor` | 설정/모델/DB 헬스 체크 |
-| `kebab tui` | Ratatui 셸 (Library + Search + Ask + Inspect 패널, desktop 진행 중). Library 에서 `r` 키로 background ingest 시작 — 화면 하단 status bar 가 진행 표시, 완료/abort 시 final 라인 잠시 유지 후 자동 hide. ingest 진행 중 `Esc` / `Ctrl-C` 가 cancel signal (그 외에는 quit). vim-style mode (header 우측 `-- NORMAL --` / `-- INSERT --`) — Library/Inspect 는 자동 NORMAL, Search/Ask 는 자동 INSERT. `i` 로 Normal→Insert (모든 pane — p9-fb-21), `Esc` 로 Insert→Normal 어디서나. mode-authoritative dispatch — Search 의 `j/k/o/g`, Ask 의 `e/j/k` 는 NORMAL 모드에서만 명령으로 동작, INSERT 에서는 입력 문자로 typing. (Search 의 chunk inspect 키는 `i`→`o` 로 rebind — `i` 가 universal Insert toggle.) **`F1` 로 cheatsheet popup** (현재 pane 의 키 매핑 + global 토글 표) — `Esc` / `F1` 로 닫기. Search 패널은 200ms debounce 후 background worker 가 검색 — 키 입력으로 UI freeze 안 됨, 사용자가 계속 타이핑하면 stale 결과 자동 폐기 (generation counter). Ask 패널은 multi-turn — 같은 conversation 안에서 Q1/A1, Q2/A2 transcript 누적, 다음 질문이 이전 턴을 history 로 받아 답변. 답변 본문은 markdown 렌더 (bold/italic/inline code/heading/list/code fence/table/blockquote, raw `**bold**` 가 실제 굵게 표시). `Ctrl-L` 로 새 conversation 시작. Search 의 `g` 키가 `$EDITOR` (기본 `vi`) 로 hit 의 citation 위치 열기 — 종료 후 TUI 화면이 자동으로 깨끗이 redraw. CLI `kebab ask` 는 raw markdown 그대로 (terminal 호환성 위해). Library 의 doc-list 가 한글 / 일본어 / 중국어 (CJK) 제목을 wide-char 정확한 column width 로 truncate — 한글 제목이 한 줄을 넘기지 않음 (CJK 1 자 = 2 col). Search/Ask/Filter 입력의 cursor 가 wide char 위에서 column 단위로 정렬 — 한글 입력 시 caret 이 글자 옆에 정확히 놓임. `← / →` 로 입력 문자열 중간 cursor 이동 (한글 한 글자 = 2 column 이라도 한 번에 이동), `Home / End` 로 양 끝 점프, `Delete` 로 cursor 위치 char 삭제 — 모든 input pane (Ask / Search / Library filter overlay) 동일 (p9-fb-22). Ask 트랜스크립트는 새 답변이 viewport 아래로 누적될 때 자동으로 tail 을 따라감 (auto-scroll); `j` / `k` 로 위로 스크롤하면 freeze, `Shift-G` 로 다시 bottom + auto-tail 재개. 화면 하단 hint line 은 한국어 동사구로 (`"위로"` / `"아래로"` / `"필터"` / `"타이핑 검색어"` / `"Esc 로 NORMAL 모드"` / `"i 입력모드"` 등) + 현재 (pane, mode) 조합에 맞춰 자동 분기, **첫 fragment 가 항상 `F1 도움말`** (cheatsheet 발견성 보장). 모든 모드에서 항상 떠 있는 상태바 — `kebab v<version> │ <pane> │ <docs> docs │ <state>` (state: streaming/searching/indexing/idle, ingest 진행 중에는 progress 가 같은 자리에 흡수됨). Ask 진입 시 conversation id 8 자 prefix 도 함께 표시. Ask 트랜스크립트와 Inspect 양쪽에서 `PgUp / PgDn` 으로 10 줄씩 페이지 스크롤. Library 의 doc list 위에는 `TITLE / TAGS / UPDATED / CHUNKS` 컬럼 헤더 행 표시 (display-width 정렬, Hangul / CJK 안전). |
-| `kebab reset [--all / --data-only / --vector-only / --config-only] [--yes]` | XDG 데이터 wipe. **Irreversible.** TTY 면 confirm prompt, 아니면 `--yes` 필수. `--vector-only` 는 SQLite `embedding_records` 도 함께 truncate (orphan 방지) |
-| `kebab eval run / compare` | golden query 회귀 측정 |
-| `kebab schema [--json]` | introspection — wire schemas / capabilities / models / stats 한 번에. `--json` 은 `schema.v1` wire; 사람 모드는 서식 출력. |
+| `kebab inspect doc <id>` / `inspect chunk <id>` | raw record 보기 |
+| `kebab fetch chunk\|doc\|span <id> [flags]` | indexed corpus 에서 verbatim text fetch |
+| `kebab eval run \| aggregate \| compare \| variants` | golden query 회귀 측정 + 변형 일관성 진단 |
+| `kebab schema [--json]` | introspection — wire schemas / capabilities / models / stats |
+| `kebab doctor` | 설정 / 모델 / DB 헬스 체크 |
+| `kebab tui` | Ratatui 셸 (Library / Search / Ask / Inspect) |
+| `kebab mcp` | MCP stdio server (`search` / `bulk_search` / `ask` / `fetch` / `schema` / `doctor` / `ingest_file` / `ingest_stdin`) |
+| `kebab reset [--all \| --data-only \| --vector-only \| --config-only \| --orphans-only] [--yes]` | XDG 데이터 wipe (**irreversible**) |
 
-모든 명령에 `--json` 플래그. 출력은 frozen wire schema v1 (`schema_version` 항상 포함, 예: `ingest_report.v1`, `ingest_progress.v1`, `search_hit.v1`, `answer.v1`, `doctor.v1`, `reset_report.v1`, `schema.v1`). `--json` 모드에서 fatal error 는 stderr 에 `error.v1` ndjson 으로 emit (exit code 0/1/2/3 unchanged).
+모든 명령에 `--json` 플래그가 있고, 출력은 frozen **wire schema v1** 을 따른다 (`schema_version` 항상 포함). `--json` 모드에서 fatal error 는 stderr 에 `error.v1` ndjson 으로 emit (exit code 0/1/2/3 불변). 글로벌 flag: `--readonly` (write-path 비활성화), `--quiet` (human stderr 억제), env `KEBAB_PROGRESS=plain`. 전체 flag·wire 의미는 `kebab <cmd> --help` 와 [docs/wire-schema/v1/](docs/wire-schema/v1/). 외부 agent 통합(Claude Code skill / MCP)은 [docs/mcp-usage.md](docs/mcp-usage.md) 와 [integrations/](integrations/).
 
-## 논리 아키텍처
+## Configuration
+
+`~/.config/kebab/config.toml` 은 `kebab init` 가 XDG 경로에 생성한다. 핵심 노브만 정리한다 (전체 절은 생성된 파일 주석 참고, 예시는 [docs/SMOKE.md](docs/SMOKE.md)).
+
+```toml
+[workspace]
+root = "~/KnowledgeBase"   # 색인할 폴더. 절대 / tilde / env / 상대 경로 가능.
+                          # 상대 경로의 base 는 config.toml 위치 (cwd 무관).
+
+[models.embedding]
+provider = "fastembed"            # "fastembed"(기본, onnxruntime) / "candle"(순수 Rust)
+                                  # / "ollama"(원격 HTTP) / "none"(lexical-only).
+                                  # candle 는 같은 모델·같은 벡터를 순수 Rust 로 돌려
+                                  # NUMA 서버의 onnxruntime 48-스레드 double-free 를 피하는
+                                  # opt-in 백엔드 (e5 는 재색인 불필요).
+model = "multilingual-e5-large"   # 다국어 sentence embedding (1024-dim).
+                                  # 첫 ingest 시 ONNX (~1.3GB) 자동 다운로드.
+                                  # candle provider 는 safetensors (~2GB) 다운로드.
+                                  # candle/ollama 는 "snowflake-arctic-embed-l-v2.0"
+                                  # (설명형 query 의 recall 보강) 도 지원 — 아래 참고.
+dimensions = 1024                 # config 와 LanceDB stored dim 불일치 시 검색 0건.
+num_threads = 0                   # candle 전용 CPU 스레드 캡 (0=auto=#cores).
+                                  # env KEBAB_EMBED_THREADS 가 우선. NUMA 노드 바인딩은
+                                  # numactl 과 조합. fastembed provider 는 무시.
+# endpoint = "http://127.0.0.1:11434"  # provider="ollama" 전용 HTTP endpoint.
+                                  # 생략 시 [models.llm].endpoint 로 폴백.
+                                  # fastembed/candle provider 는 무시.
+```
+
+**arctic-embed-l-v2.0 (설명형 query recall 보강)**: 기본 e5-large 대신
+Snowflake `arctic-embed-l-v2.0` 임베더를 쓸 수 있다 (1024-dim, opt-in). 측정에서
+설명형/약어/영문 용어 query 의 recall@10 이 e5 대비 향상됐다. 두 경로:
+
+```toml
+# (A) candle 백엔드 — 순수 Rust, in-process (NUMA 안전, Metal GPU 가능):
+[models.embedding]
+provider = "candle"
+model    = "snowflake-arctic-embed-l-v2.0"   # CLS pooling, query 에 "query: " 접두어
+                                             # (문서는 무접두어). safetensors ~2GB 다운로드.
+
+# (B) ollama 백엔드 — 원격/로컬 Ollama 데몬에 위임 (POST /api/embed):
+[models.embedding]
+provider = "ollama"
+model    = "snowflake-arctic-embed2"          # Ollama 모델 태그 (ollama pull 필요)
+endpoint = "http://127.0.0.1:11434"           # 생략 시 [models.llm].endpoint
+```
+
+> ⚠️ e5 → arctic 전환은 `embedding_version` cascade 를 트리거한다 (모델이 다르면
+> 벡터도 다름). 기존 e5 KB 와 혼용 불가 — 전환 시 **재색인** 필요 (`kebab reset`
+> 후 재 ingest). 기본값은 e5 라 기존 사용자는 영향 없음.
+
+**Apple Silicon GPU 가속 (candle / macOS)**: M-시리즈 맥에서 candle 임베딩을
+GPU(Metal)로 돌리면 CPU 대비 대용량 ingest 가 크게 빨라진다. 빌드 또는 설치 시
+`embed_metal` feature 를 켠다:
+
+```bash
+# 빌드만:
+cargo build --release --features embed_metal
+# 전역 설치 (~/.cargo/bin/kebab):
+cargo install --path crates/kebab-cli --features embed_metal --locked
+```
+
+벡터는 CPU candle 과 동일 모델이라 호환되므로, 맥에서 GPU 로 색인한
+`kebab.sqlite` + `lancedb/` 를 그대로 Linux 서버(CPU candle)로 복사해 질의할 수
+있다. 색인 로그에 `candle device = Metal (GPU)` 가 보이면 GPU 사용 중. metal
+feature 는 macOS 전용 (Linux/서버는 기본 CPU 빌드).
+
+```toml
+
+[models.llm]
+endpoint = "http://localhost:11434"   # Ollama host:port
+model = "gemma4:e4b"
+# request_timeout_secs = 300          # 큰 모델은 늘림. 0 은 disable 이 아니라 "즉시 timeout".
+
+[search]
+stale_threshold_days = 30   # search hit / citation 의 stale 플래그 기준 (0 = off).
+
+[rag]
+prompt_template_version = "rag-v3"   # 답변 언어 = 질문 언어. rag-v1/v2 는 legacy.
+nli_threshold = 0.0                  # >0 (예: 0.5) 면 mDeBERTa XNLI groundedness 검증.
+```
+
+- **파생물 캐시** — embedding 결과를 내용 해시로 자동 캐싱한다 (위 「핵심 기능」 참고). 설정 항목 없음.
+- **`[ingest.code]`** — code ingest 의 skip 정책 (`skip_generated_header`, `max_file_bytes`, `extra_skip_globs`). `.gitignore` 자동 honor, `.kebabignore` 는 추가 layer.
+- **`[pdf.ocr]`** — scanned PDF 의 page-단위 OCR (default off / opt-in, page 당 ~수십 초 cost). 활성화 후 v0.19 시절 색인분은 `kebab ingest --force-reingest` 로 재처리.
+- **`--config <path>`** — 임시 워크스페이스 / 격리 테스트용 (CLI · TUI 모두 honor).
+- **`kebab config migrate`** — 새 버전에서 추가된 config 섹션을 기존 `config.toml` 에 설명 주석과 함께 채워 넣는다 (사용자가 손본 값·주석·순서는 보존, 멱등, 변경 시 자동 `.bak` 백업). `--dry-run` 으로 변경 미리보기. `kebab doctor` 가 갱신 필요 시 안내한다. `kebab init` 으로 새로 생성되는 config.toml 도 섹션별 주석을 포함한다.
+- **`KEBAB_*` env** — 일부 키 override (`KEBAB_RAG_SCORE_GATE`, `KEBAB_EVAL_GOLDEN` 등).
+- **XDG layout**: `~/.config/kebab/`, `~/.local/share/kebab/`, `~/.cache/kebab/`, `~/.local/state/kebab/`.
+
+## 아키텍처
 
 ```mermaid
 flowchart TB
@@ -99,9 +206,9 @@ flowchart TB
     end
 
     subgraph Pipeline["도메인 + 파이프라인"]
-        parse["parse-md / parse-pdf / parse-image"]
-        chunker["chunker (md-heading-v1, pdf-page-v1)"]
-        embedder["embedder (fastembed multilingual-e5-small)"]
+        parse["parse-md / parse-pdf / parse-image / parse-code"]
+        chunker["chunker (md / pdf / code-AST / manifest)"]
+        embedder["embedder (fastembed multilingual-e5-large)"]
         retriever["retriever (lexical / vector / hybrid RRF)"]
         rag["RAG pipeline"]
     end
@@ -142,40 +249,22 @@ flowchart TB
     rag --> ollama
 ```
 
-`kebab-app` 가 facade — UI binary 가 store / parse / search / llm / rag 를 직접 참조하지 않는다 (frozen 설계 §8). 자세한 crate-level 의존성 + 디렉토리 + 핵심 기술 결정은 [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md).
+v0.21.0 기준 핵심 설계:
 
-## Configuration
+- **crate facade** — `kebab-app` 가 유일한 facade다. UI binary (`kebab-cli` / `kebab-tui`) 는 store / parse / search / llm / rag 를 직접 참조하지 않는다 (frozen 설계 §8). 각 user-facing 엔트리는 `*_with_config(cfg, …)` 동반 함수로 explicit config 를 thread 한다.
+- **chunk_id 는 위치 기반** — chunk 의 정체성은 문서 내 위치(ordinal + span)다. 반면 파생물 캐시 키는 **내용 해시**라, 내용이 같으면 위치·문서가 달라도 동일 캐시를 재사용한다.
+- **wire schema v1** — 모든 `--json` 출력은 `schema_version` 을 담는 frozen contract다. 깨는 변경은 `*.v2` major bump을 요구한다.
+- **versioning cascade** — `parser_version` / `chunker_version` / `embedding_version` / `prompt_template_version` / `index_version` 변경은 downstream record(청크·임베딩·캐시·eval)를 무효화한다.
 
-- `~/.config/kebab/config.toml` — `kebab init` 가 XDG 경로에 생성. `[workspace]` (root, exclude — include 필드는 제거됨, 지원 형식은 자동 결정), `[storage]`, `[chunking]`, `[models.embedding]`, `[models.llm]`, `[image.ocr]`, `[image.caption]`, `[search]`, `[rag]`, `[ui]` 절. `[ui] theme = "dark" | "light"` 로 TUI 팔레트 선택 (default `"dark"`, 알 수 없는 값은 dark fallback). 옛 config 의 `workspace.include = [...]` 은 silently 무시 + 단발 deprecation warning (p9-fb-25).
-- `--config <path>` flag — 임시 워크스페이스 / 격리 테스트 시 사용. CLI / TUI 모두 honor.
-- `KEBAB_*` env — 일부 키 override (`KEBAB_RAG_SCORE_GATE`, `KEBAB_EVAL_GOLDEN`, `KEBAB_COMMIT_HASH` 등).
-- XDG layout: `~/.config/kebab/`, `~/.local/share/kebab/`, `~/.cache/kebab/`, `~/.local/state/kebab/`.
-- `workspace.root` 경로 형식: 절대 (`/foo/bar`) / tilde (`~/KnowledgeBase`, default) / env (`${XDG_DATA_HOME}/kebab`) / 상대 (`./notes`, `notes`, `../shared/x`) 모두 가능. **상대 경로의 base 는 config.toml 자체가 위치한 디렉토리** — 사용자의 `cwd` 와 무관 (`--config /tmp/cfg.toml` + `root = "kb"` → `/tmp/kb`). p9-fb-05 정책.
-
-config 예시는 [docs/SMOKE.md](docs/SMOKE.md) 의 `/tmp/kebab-smoke/config.toml` 블록 참조.
-
-## 외부 AI 통합
-
-`--json` 출력 + frozen wire schema v1 가 stable contract. 통합 옵션:
-
-- **Claude Code skill** — repo 의 [`integrations/claude-code/`](integrations/claude-code/) 가 ship-ready skill. `cp -r integrations/claude-code/kebab ~/.claude/skills/` 한 번이면 새 Claude Code 세션부터 자동 trigger (내부 시스템 / 위키 lookup / 사내 runbook 질문). multi-turn 은 `kebab ask --session <id> --json` 으로 영속 — skill 이 conversation id 관리하면 외부 agent 도 `--repl` 없이 stateful 대화 가능 (p9-fb-18).
-- **Codex / 기타 agent host** — `--json` + frozen wire schema v1 가 stable contract. 동일 패턴으로 ~50줄 wrapper 작성 가능. `integrations/<host>/` 에 추가 PR 환영.
-- **MCP server** — stdio JSON-RPC 로 `kebab-app` facade 1:1 노출.
-- **HTTP wrapper** — `kebab serve --bind 127.0.0.1:7711` (P+, local-only 가치 신중).
+crate-level 의존성 그래프 · 디렉토리 트리 · 확장자→chunker 전체 매핑 · 핵심 기술 결정은 [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md), 진척도는 [HANDOFF.md](HANDOFF.md).
 
 ## 비-목표
 
-다중 사용자 SaaS / K8s / 원격 vector DB / enterprise RBAC / 실시간 협업 / 모든 파일 포맷의 완벽한 parsing / agent 임의 파일 수정 / multi-workspace / LLM-as-judge eval / CLIP 시각 embedding / `kebab://` protocol handler — frozen 설계 §11 / §0 참조.
+다중 사용자 SaaS / K8s / 원격 vector DB / enterprise RBAC / 실시간 협업 / agent 임의 파일 수정 / multi-workspace / LLM-as-judge eval / CLIP 시각 embedding — frozen 설계 §0 / §11 참조.
 
-## 라이선스
+## 버전 / 라이선스 / 참고
 
-`MIT OR Apache-2.0` (workspace `Cargo.toml` 의 `license` 필드).
-
-## 참고
-
-- 진척도: [HANDOFF.md](HANDOFF.md)
-- 아키텍처: [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md)
-- Frozen 설계: [docs/superpowers/specs/2026-04-27-kebab-final-form-design.md](docs/superpowers/specs/2026-04-27-kebab-final-form-design.md)
-- Task 인덱스: [tasks/INDEX.md](tasks/INDEX.md)
-- 머지 후 hotfix 로그: [tasks/HOTFIXES.md](tasks/HOTFIXES.md)
-- Smoke 절차: [docs/SMOKE.md](docs/SMOKE.md)
+- **버전**: v0.21.0 (`kebab --version` 으로 확인).
+- **라이선스**: `MIT OR Apache-2.0`.
+- 진척도: [HANDOFF.md](HANDOFF.md) · 아키텍처: [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) · Frozen 설계: [docs/superpowers/specs/2026-04-27-kebab-final-form-design.md](docs/superpowers/specs/2026-04-27-kebab-final-form-design.md)
+- Task 인덱스: [tasks/INDEX.md](tasks/INDEX.md) · Hotfix 로그: [tasks/HOTFIXES.md](tasks/HOTFIXES.md) · Smoke 절차: [docs/SMOKE.md](docs/SMOKE.md) · MCP 사용: [docs/mcp-usage.md](docs/mcp-usage.md)

crates/kebab-app/Cargo.toml

@@ -12,17 +12,22 @@ kebab-core = { path = "../kebab-core" }
 kebab-config = { path = "../kebab-config" }
 kebab-source-fs = { path = "../kebab-source-fs" }
 kebab-parse-md = { path = "../kebab-parse-md" }
-kebab-parse-types = { path = "../kebab-parse-types" }
-kebab-normalize = { path = "../kebab-normalize" }
 kebab-chunk = { path = "../kebab-chunk" }
 kebab-store-sqlite = { path = "../kebab-store-sqlite" }
 kebab-store-vector = { path = "../kebab-store-vector" }
 kebab-search = { path = "../kebab-search" }
 kebab-embed = { path = "../kebab-embed" }
 kebab-embed-local = { path = "../kebab-embed-local" }
+kebab-embed-candle = { path = "../kebab-embed-candle" }
+kebab-embed-ollama = { path = "../kebab-embed-ollama" }
 kebab-llm = { path = "../kebab-llm" }
 kebab-llm-local = { path = "../kebab-llm-local" }
 kebab-rag = { path = "../kebab-rag" }
+# p9-fb-41 PR-9c-2: facade construction of OnnxNliVerifier when
+# `[rag] nli_threshold > 0`. Trait-only consumption via kebab-rag's
+# `with_verifier`; no kebab-nli internals leak into kebab-app code
+# beyond the construction site in `open_with_config`.
+kebab-nli = { path = "../kebab-nli" }
 # P6-4: image extractor + OCR + caption adapters live here. App
 # threads them into the per-asset dispatch (see `ingest_one_asset`
 # image branch). Trait-only consumption — no `kebab-parse-image`
@@ -32,11 +37,21 @@ kebab-parse-image = { path = "../kebab-parse-image" }
 # per-asset dispatch (see `ingest_one_asset` PDF branch) and runs the
 # resulting `CanonicalDocument` through `kebab-chunk::PdfPageV1Chunker`.
 kebab-parse-pdf = { path = "../kebab-parse-pdf" }
+lopdf            = { workspace = true }
+# Enhancement 1 (v0.20.x r2): JPEG dimension decode in pdf_ocr_apply.rs.
+# jpeg feature added explicitly (F3 closure-r1) rather than relying on
+# feature unification via kebab-parse-image.
+image            = { version = "0.25", default-features = false, features = ["png", "jpeg"] }
+# p10-1A-2: Rust AST extractor lives here. App threads it into the
+# per-asset dispatch (see `ingest_one_asset` Code branch) and runs the
+# resulting `CanonicalDocument` through `kebab-chunk::CodeRustAstV1Chunker`.
+kebab-parse-code = { path = "../kebab-parse-code" }
 anyhow               = { workspace = true }
 blake3               = { workspace = true }
 serde                = { workspace = true }
 serde_json           = { workspace = true }
 time                 = { workspace = true }
+uuid                 = { workspace = true }
 tracing              = { workspace = true }
 tracing-subscriber   = { version = "0.3", features = ["env-filter", "fmt", "json"] }
 tracing-appender     = "0.2"
@@ -49,18 +64,45 @@ lru                  = { workspace = true }
 # `" foo "` collapse to one entry. Same crate kebab-normalize +
 # kebab-core already use, no version drift.
 unicode-normalization = "0.1"
+# p9-fb-31: GitignoreBuilder for .kebabignore matching in ingest_file_with_config.
+# Same version as kebab-source-fs (0.4) to avoid duplicate dep versions.
+ignore               = "0.4"
+# p9-fb-34: opaque pagination cursor encodes payload as base64.
+base64               = { workspace = true }
+# Enhancement 3 (v0.20.x r2): direct SQL queries for inspect_ocr_stats/failures.
+rusqlite             = { workspace = true }
 
 [dev-dependencies]
+kebab-config = { path = "../kebab-config" }
+# doc-side expansion (Phase 2) Task 4: ExpansionGenerator unit tests build
+# MockLanguageModel (gated behind kebab-llm's `mock` feature, default OFF in
+# [dependencies]). Enabling it here turns it on for the test build only.
+kebab-llm            = { path = "../kebab-llm", features = ["mock"] }
 rusqlite             = { workspace = true }
+filetime             = "0.2"
 tempfile             = { workspace = true }
 # Image-pipeline integration tests use wiremock to stub Ollama for OCR
 # / caption HTTP calls. Async runtime to host the mock server only;
 # the kb-app code under test stays sync.
 wiremock             = { workspace = true }
 tokio                = { workspace = true, features = ["rt-multi-thread"] }
-image                = { version = "0.25", default-features = false, features = ["png"] }
+image                = { version = "0.25", default-features = false, features = ["png", "jpeg"] }
 # P7-3 PDF integration tests build in-memory PDF fixtures via the same
 # lopdf builder pattern `kebab-parse-pdf::tests::common` uses; pinned
 # to the same major (0.32) so byte output is identical between the two
 # fixture surfaces.
-lopdf                = "0.32"
+lopdf                = { workspace = true }
+# error_wire::tests::llm_unreachable_classifies_to_model_unreachable needs a real
+# reqwest::Error (private constructor) — built from a connect-refused call.
+reqwest      = { version = "0.12", default-features = false, features = ["blocking", "rustls-tls"] }
+
+[features]
+# Marker feature — spec §6.3 Option A (단순): lindera 는 kebab-chunk 가 default dep 으로 소유.
+# disable path 없음; 이 feature 는 spec §6.3 명시를 honor 하는 role 만.
+default = ["fts_korean_morphological"]
+fts_korean_morphological = []
+# opt-in (macOS): candle embedder runs on the Apple Silicon GPU. See kebab-embed-candle.
+embed_metal = ["kebab-embed-candle/metal"]
+
+[lints]
+workspace = true

crates/kebab-app/src/bulk.rs

@@ -0,0 +1,321 @@
+//! p9-fb-42: bulk multi-query facade. Sequential for-loop reusing
+//! one App instance so embedder cold-start + LRU cache amortize
+//! across the N queries.
+
+use anyhow::Context;
+use kebab_core::{
+    BulkSearchItem, BulkSearchSummary, DocumentId, Lang, SearchFilters, SearchHit, SearchMode,
+    SearchOpts, SearchQuery, TrustLevel,
+};
+use serde_json::Value;
+
+use crate::{App, SearchResponse};
+
+/// Hard cap on items per bulk call. Documented in spec — agents that
+/// hit this should batch-split.
+pub const BULK_QUERIES_MAX: usize = 100;
+
+/// p9-fb-42: bulk search facade. Returns `(items, summary)` always
+/// — per-query failures embed `error.v1` JSON in the item rather
+/// than aborting the bulk call. Returns `Err` only for input
+/// validation failures (e.g. >100 queries).
+#[doc(hidden)]
+pub fn bulk_search_with_config(
+    config: kebab_config::Config,
+    raw_items: Vec<Value>,
+) -> anyhow::Result<(Vec<BulkSearchItem>, BulkSearchSummary)> {
+    if raw_items.len() > BULK_QUERIES_MAX {
+        anyhow::bail!(
+            "queries: max {} items, got {}",
+            BULK_QUERIES_MAX,
+            raw_items.len()
+        );
+    }
+
+    let app = App::open_with_config(config).context("kebab-app: open for bulk_search")?;
+
+    let mut results: Vec<BulkSearchItem> = Vec::with_capacity(raw_items.len());
+    let mut succeeded: u32 = 0;
+    let mut failed: u32 = 0;
+
+    for raw in raw_items {
+        let item = run_one(&app, raw);
+        if item.error.is_some() {
+            failed += 1;
+        } else {
+            succeeded += 1;
+        }
+        results.push(item);
+    }
+
+    let summary = BulkSearchSummary {
+        total: succeeded + failed,
+        succeeded,
+        failed,
+    };
+    Ok((results, summary))
+}
+
+fn run_one(app: &App, raw: Value) -> BulkSearchItem {
+    let echo = raw.clone();
+    match parse_one(&raw) {
+        Ok((query, opts)) => match app.search_with_opts(query, opts) {
+            Ok(resp) => BulkSearchItem {
+                query: echo,
+                response: Some(serialize_search_response(&resp)),
+                error: None,
+            },
+            Err(e) => BulkSearchItem {
+                query: echo,
+                response: None,
+                error: Some(error_v1_json("retrieval_error", &format!("{e:#}"), None)),
+            },
+        },
+        Err(msg) => BulkSearchItem {
+            query: echo,
+            response: None,
+            error: Some(error_v1_json("invalid_input", &msg, None)),
+        },
+    }
+}
+
+/// Mirror of `kebab-cli::wire::wire_search_response` — `SearchResponse`
+/// itself is not `Serialize`, so we build the `search_response.v1`-shaped
+/// JSON manually. Each hit also gets `score` promoted from
+/// `retrieval.fusion_score` per §2.2, matching the CLI wire layer.
+fn serialize_search_response(r: &SearchResponse) -> Value {
+    let mut v = serde_json::json!({
+        "schema_version": "search_response.v1",
+        "hits": r.hits.iter().map(serialize_search_hit).collect::<Vec<_>>(),
+        "next_cursor": r.next_cursor,
+        "truncated": r.truncated,
+    });
+    if let Value::Object(ref mut map) = v {
+        let trace_v = match &r.trace {
+            Some(t) => serde_json::to_value(t).unwrap_or(Value::Null),
+            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
+}
+
+fn serialize_search_hit(h: &SearchHit) -> Value {
+    let mut v = serde_json::to_value(h).unwrap_or(Value::Null);
+    if let Value::Object(ref mut map) = v {
+        if let Some(Value::Object(retrieval)) = map.get("retrieval") {
+            if let Some(score) = retrieval.get("fusion_score").cloned() {
+                map.insert("score".to_string(), score);
+            }
+        }
+        map.insert(
+            "schema_version".to_string(),
+            Value::String("search_hit.v1".to_string()),
+        );
+    }
+    v
+}
+
+fn parse_one(raw: &Value) -> Result<(SearchQuery, SearchOpts), String> {
+    let obj = raw.as_object().ok_or("expected JSON object")?;
+    let text = obj
+        .get("query")
+        .and_then(|v| v.as_str())
+        .ok_or(
+            "missing required field: query \
+             (expected {\"query\":\"<text>\",\"mode\":\"lexical|vector|hybrid\",\"k\":3,...})",
+        )?
+        .to_string();
+
+    let mode = match obj.get("mode").and_then(|v| v.as_str()) {
+        None => SearchMode::Hybrid,
+        Some("hybrid") => SearchMode::Hybrid,
+        Some("lexical") => SearchMode::Lexical,
+        Some("vector") => SearchMode::Vector,
+        Some(other) => return Err(format!("invalid mode: {other:?}")),
+    };
+
+    let k = obj
+        .get("k")
+        .and_then(serde_json::Value::as_u64)
+        .map_or(0, |n| n as usize); // 0 → use config default in app
+
+    let trust_min = match obj.get("trust_min").and_then(|v| v.as_str()) {
+        None => None,
+        Some("primary") => Some(TrustLevel::Primary),
+        Some("secondary") => Some(TrustLevel::Secondary),
+        Some("generated") => Some(TrustLevel::Generated),
+        Some(other) => return Err(format!("invalid trust_min: {other:?}")),
+    };
+
+    let ingested_after = match obj.get("ingested_after").and_then(|v| v.as_str()) {
+        None => None,
+        Some(s) => Some(
+            time::OffsetDateTime::parse(s, &time::format_description::well_known::Rfc3339)
+                .map_err(|e| format!("invalid ingested_after RFC3339 {s:?}: {e}"))?,
+        ),
+    };
+
+    let media: Vec<String> = obj
+        .get("media")
+        .and_then(|v| v.as_array())
+        .map(|arr| {
+            arr.iter()
+                .filter_map(|x| x.as_str().map(normalize_media_alias))
+                .collect()
+        })
+        .unwrap_or_default();
+
+    let tags_any: Vec<String> = obj
+        .get("tag")
+        .and_then(|v| v.as_array())
+        .map(|arr| {
+            arr.iter()
+                .filter_map(|x| x.as_str().map(String::from))
+                .collect()
+        })
+        .unwrap_or_default();
+
+    let lang = obj
+        .get("lang")
+        .and_then(|v| v.as_str())
+        .map(|s| Lang(s.to_string()));
+
+    let path_glob = obj
+        .get("path_glob")
+        .and_then(|v| v.as_str())
+        .map(String::from);
+
+    let doc_id = obj
+        .get("doc_id")
+        .and_then(|v| v.as_str())
+        .map(|s| DocumentId(s.to_string()));
+
+    let filters = SearchFilters {
+        tags_any,
+        lang,
+        path_glob,
+        trust_min,
+        media,
+        ingested_after,
+        doc_id,
+        repo: vec![],
+        code_lang: vec![],
+    };
+
+    let opts = SearchOpts {
+        max_tokens: obj
+            .get("max_tokens")
+            .and_then(serde_json::Value::as_u64)
+            .map(|n| n as usize),
+        snippet_chars: obj
+            .get("snippet_chars")
+            .and_then(serde_json::Value::as_u64)
+            .map(|n| n as usize),
+        cursor: obj.get("cursor").and_then(|v| v.as_str()).map(String::from),
+        trace: obj
+            .get("trace")
+            .and_then(serde_json::Value::as_bool)
+            .unwrap_or(false),
+    };
+
+    Ok((
+        SearchQuery {
+            text,
+            mode,
+            k,
+            filters,
+        },
+        opts,
+    ))
+}
+
+fn normalize_media_alias(s: &str) -> String {
+    match s.to_ascii_lowercase().as_str() {
+        "md" => "markdown".to_string(),
+        other => other.to_string(),
+    }
+}
+
+fn error_v1_json(code: &str, message: &str, hint: Option<&str>) -> Value {
+    serde_json::json!({
+        "schema_version": "error.v1",
+        "code": code,
+        "message": message,
+        "hint": hint,
+    })
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn open_temp() -> kebab_config::Config {
+        let dir = tempfile::tempdir().unwrap();
+        let mut cfg = kebab_config::Config::defaults();
+        cfg.storage.data_dir = dir.path().to_string_lossy().into_owned();
+        // Bring up migrations so SqliteStore::open_existing succeeds inside App::open.
+        let store = kebab_store_sqlite::SqliteStore::open(&cfg).unwrap();
+        store.run_migrations().unwrap();
+        drop(store);
+        // Leak the tempdir into a static — tests are short-lived; not worth threading.
+        std::mem::forget(dir);
+        cfg
+    }
+
+    #[test]
+    fn empty_input_returns_empty_summary() {
+        let cfg = open_temp();
+        let (items, summary) = bulk_search_with_config(cfg, vec![]).unwrap();
+        assert!(items.is_empty());
+        assert_eq!(summary.total, 0);
+        assert_eq!(summary.succeeded, 0);
+        assert_eq!(summary.failed, 0);
+    }
+
+    #[test]
+    fn over_cap_returns_err() {
+        let cfg = open_temp();
+        let raw: Vec<Value> = (0..101)
+            .map(|_| serde_json::json!({"query": "x"}))
+            .collect();
+        let err = bulk_search_with_config(cfg, raw).unwrap_err();
+        let msg = format!("{err:#}");
+        assert!(msg.contains("max 100"));
+    }
+
+    #[test]
+    fn invalid_item_emits_error_keeps_total_count() {
+        let cfg = open_temp();
+        let raw = vec![
+            serde_json::json!({"query": "ok", "mode": "lexical"}),
+            serde_json::json!({"mode": "lexical"}), // missing required `query`
+        ];
+        let (items, summary) = bulk_search_with_config(cfg, raw).unwrap();
+        assert_eq!(items.len(), 2);
+        assert_eq!(summary.total, 2);
+        // First item: lexical mode against empty corpus succeeds with empty hits.
+        assert!(items[0].error.is_none());
+        // Second item: missing required field.
+        assert!(items[1].error.is_some());
+        assert_eq!(items[1].error.as_ref().unwrap()["code"], "invalid_input");
+    }
+
+    #[test]
+    fn missing_query_error_message_includes_shape_hint() {
+        let cfg = open_temp();
+        let raw = vec![serde_json::json!({"mode": "lexical"})];
+        let (items, _summary) = bulk_search_with_config(cfg, raw).unwrap();
+        let err = items[0].error.as_ref().unwrap();
+        let msg = err["message"].as_str().unwrap();
+        assert!(
+            msg.contains("query") && msg.contains("mode"),
+            "missing shape hint in error message: {msg}"
+        );
+    }
+}

crates/kebab-app/src/cursor.rs

@@ -0,0 +1,75 @@
+//! p9-fb-34 opaque pagination cursor.
+//!
+//! Format: base64(JSON({offset: usize, corpus_revision: string})).
+//! Opaque to callers — they MUST NOT decode the contents themselves;
+//! the schema is internal and may change without notice.
+
+use base64::Engine;
+use base64::engine::general_purpose::URL_SAFE_NO_PAD;
+use serde::{Deserialize, Serialize};
+use serde_json::Value;
+
+use crate::error_wire::ErrorV1;
+
+#[derive(Serialize, Deserialize)]
+struct Payload {
+    offset: usize,
+    corpus_revision: String,
+}
+
+/// Encode `(offset, corpus_revision)` as an opaque base64 string.
+pub fn encode(offset: usize, corpus_revision: &str) -> String {
+    let payload = Payload {
+        offset,
+        corpus_revision: corpus_revision.to_string(),
+    };
+    let json = serde_json::to_vec(&payload).expect("Payload serializes");
+    URL_SAFE_NO_PAD.encode(&json)
+}
+
+/// Decode an opaque cursor against the expected `corpus_revision`.
+/// Mismatch or malformed input returns an `ErrorV1` with
+/// `code = "stale_cursor"`.
+//
+// p9-fb-34: ErrorV1 is the workspace-wide wire error struct (~200B
+// after monomorphization with Value + String fields). Boxing here
+// would force every call site to deref through a Box for no win —
+// the err-path is rare. Single allow at the function level.
+//
+// p9-fb-34 round-1 review: differentiate the three failure modes
+// (base64 / JSON / revision mismatch) with distinct messages — all
+// keep `code = "stale_cursor"` so the agent's branching logic stays
+// the same, but humans reading the message get a precise hint.
+#[allow(clippy::result_large_err)]
+pub fn decode(s: &str, expected_revision: &str) -> Result<usize, ErrorV1> {
+    let bytes = URL_SAFE_NO_PAD.decode(s.as_bytes()).map_err(|_| ErrorV1 {
+        schema_version: "error.v1".to_string(),
+        code: "stale_cursor".to_string(),
+        message: "cursor is not valid base64. Re-issue search to obtain a fresh cursor."
+            .to_string(),
+        details: Value::Null,
+        hint: None,
+    })?;
+    let payload: Payload = serde_json::from_slice(&bytes).map_err(|_| ErrorV1 {
+        schema_version: "error.v1".to_string(),
+        code: "stale_cursor".to_string(),
+        message: "cursor payload is malformed. Re-issue search to obtain a fresh cursor."
+            .to_string(),
+        details: Value::Null,
+        hint: None,
+    })?;
+    if payload.corpus_revision != expected_revision {
+        return Err(ErrorV1 {
+            schema_version: "error.v1".to_string(),
+            code: "stale_cursor".to_string(),
+            message: format!(
+                "cursor was issued against corpus_revision '{}'; current revision is \
+                 '{}'. Re-issue search to obtain a fresh cursor.",
+                payload.corpus_revision, expected_revision
+            ),
+            details: Value::Null,
+            hint: None,
+        });
+    }
+    Ok(payload.offset)
+}

crates/kebab-app/src/derivation_payload.rs

@@ -0,0 +1,61 @@
+//! Derivation-cache payload encoding helpers (design 2026-05-31 §3.3).
+//!
+//! - embedding: `dimensions × f32` little-endian bytes (1024×4 = 4096 B/chunk).
+//! - alias / korean_tokens: UTF-8 as-is (handled inline by the caller — no
+//!   helper needed, `String::as_bytes` / `String::from_utf8`).
+
+/// Encode an embedding vector as a little-endian `f32` byte string (§3.3).
+pub fn encode_embedding(vector: &[f32]) -> Vec<u8> {
+    let mut out = Vec::with_capacity(vector.len() * 4);
+    for &v in vector {
+        out.extend_from_slice(&v.to_le_bytes());
+    }
+    out
+}
+
+/// Decode a little-endian `f32` byte string back into a vector (§3.3).
+///
+/// Returns `None` if the payload length is not a multiple of 4 (corrupt
+/// entry) — the caller treats this as a cache miss and recomputes, so a bad
+/// payload never produces a wrong vector.
+pub fn decode_embedding(payload: &[u8]) -> Option<Vec<f32>> {
+    if payload.len() % 4 != 0 {
+        return None;
+    }
+    Some(
+        payload
+            .chunks_exact(4)
+            .map(|c| f32::from_le_bytes([c[0], c[1], c[2], c[3]]))
+            .collect(),
+    )
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn roundtrips_vector() {
+        let v = vec![0.0_f32, 1.5, -2.25, 3.125e10, f32::MIN, f32::MAX];
+        let bytes = encode_embedding(&v);
+        assert_eq!(bytes.len(), v.len() * 4);
+        assert_eq!(decode_embedding(&bytes), Some(v));
+    }
+
+    #[test]
+    fn empty_vector_roundtrips() {
+        assert_eq!(encode_embedding(&[]), Vec::<u8>::new());
+        assert_eq!(decode_embedding(&[]), Some(vec![]));
+    }
+
+    #[test]
+    fn misaligned_payload_is_none() {
+        assert_eq!(decode_embedding(&[1, 2, 3]), None);
+    }
+
+    #[test]
+    fn little_endian_layout_is_fixed() {
+        // 1.0_f32 == 0x3F800000, little-endian bytes [0x00,0x00,0x80,0x3F].
+        assert_eq!(encode_embedding(&[1.0]), vec![0x00, 0x00, 0x80, 0x3F]);
+    }
+}

crates/kebab-app/src/error_signal.rs

@@ -10,6 +10,6 @@
 
 pub use crate::doctor_signal::{DoctorUnhealthy, NoHitSignal, RefusalSignal};
 
+pub use kebab_config::{ConfigInvalid, ConfigNotFound};
 pub use kebab_llm_local::LlmError;
-pub use kebab_config::ConfigInvalid;
 pub use kebab_store_sqlite::NotIndexed;

crates/kebab-app/src/error_wire.rs

@@ -9,19 +9,53 @@
 use serde::{Deserialize, Serialize};
 use serde_json::{Value, json};
 
-use kebab_app::error_signal::{ConfigInvalid, LlmError, NotIndexed};
+use crate::error_signal::{ConfigInvalid, ConfigNotFound, LlmError, NotIndexed};
+
+// p9-fb-34: `stale_cursor` is constructed directly by `cursor::decode`
+// and surfaced through `StructuredError` (an anyhow-friendly wrapper
+// that carries the typed `ErrorV1` payload without lossy string
+// formatting). `classify` short-circuits on it at the top of the
+// function so the typed `code = "stale_cursor"` reaches the wire.
+
+/// Wire schema id for [`ErrorV1`]. Single source of truth — kebab-cli
+/// + kebab-mcp use this via `kebab_app::ERROR_V1_ID`.
+pub const ERROR_V1_ID: &str = "error.v1";
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct ErrorV1 {
+    pub schema_version: String,
     pub code: String,
     pub message: String,
     pub details: Value,
     pub hint: Option<String>,
 }
 
+/// p9-fb-34: typed wrapper around an [`ErrorV1`] so callers that
+/// surface `anyhow::Error` can downcast back to the structured wire
+/// payload instead of losing it to string formatting. Constructed by
+/// the cursor code path (`cursor::decode` → `App::search_with_opts`)
+/// and short-circuited inside [`classify`].
+#[derive(Debug)]
+pub struct StructuredError(pub ErrorV1);
+
+impl std::fmt::Display for StructuredError {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        write!(f, "[{}] {}", self.0.code, self.0.message)
+    }
+}
+
+impl std::error::Error for StructuredError {}
+
 pub fn classify(err: &anyhow::Error, verbose: bool) -> ErrorV1 {
+    // p9-fb-34: structured wrapper short-circuits — preserves the
+    // typed payload that callers (cursor::decode) constructed
+    // instead of falling through to `code = "generic"`.
+    if let Some(s) = err.downcast_ref::<StructuredError>() {
+        return s.0.clone();
+    }
     if let Some(s) = err.downcast_ref::<ConfigInvalid>() {
         return ErrorV1 {
+            schema_version: ERROR_V1_ID.to_string(),
             code: "config_invalid".to_string(),
             message: s.to_string(),
             details: json!({
@@ -31,8 +65,23 @@ pub fn classify(err: &anyhow::Error, verbose: bool) -> ErrorV1 {
             hint: Some("check `--config <path>` and TOML syntax".to_string()),
         };
     }
+    if let Some(s) = err.downcast_ref::<ConfigNotFound>() {
+        return ErrorV1 {
+            schema_version: ERROR_V1_ID.to_string(),
+            code: "config_not_found".to_string(),
+            message: s.to_string(),
+            details: json!({
+                "path": s.path.to_string_lossy(),
+            }),
+            hint: Some(
+                "verify --config <path>; pass an existing toml file or omit --config to use XDG default"
+                    .to_string(),
+            ),
+        };
+    }
     if let Some(s) = err.downcast_ref::<NotIndexed>() {
         return ErrorV1 {
+            schema_version: ERROR_V1_ID.to_string(),
             code: "not_indexed".to_string(),
             message: s.to_string(),
             details: json!({
@@ -47,6 +96,7 @@ pub fn classify(err: &anyhow::Error, verbose: bool) -> ErrorV1 {
     }
     if let Some(io) = err.downcast_ref::<std::io::Error>() {
         return ErrorV1 {
+            schema_version: ERROR_V1_ID.to_string(),
             code: "io_error".to_string(),
             message: io.to_string(),
             details: json!({"kind": format!("{:?}", io.kind())}),
@@ -55,10 +105,11 @@ pub fn classify(err: &anyhow::Error, verbose: bool) -> ErrorV1 {
     }
     let mut details = json!({});
     if verbose {
-        let chain: Vec<String> = err.chain().map(|c| c.to_string()).collect();
+        let chain: Vec<String> = err.chain().map(std::string::ToString::to_string).collect();
         details = json!({"chain": chain});
     }
     ErrorV1 {
+        schema_version: ERROR_V1_ID.to_string(),
         code: "generic".to_string(),
         message: err.to_string(),
         details,
@@ -69,6 +120,7 @@ pub fn classify(err: &anyhow::Error, verbose: bool) -> ErrorV1 {
 fn classify_llm(s: &LlmError) -> ErrorV1 {
     match s {
         LlmError::Unreachable { endpoint, source } => ErrorV1 {
+            schema_version: ERROR_V1_ID.to_string(),
             code: "model_unreachable".to_string(),
             message: format!("ollama unreachable at {endpoint}"),
             details: json!({
@@ -78,24 +130,28 @@ fn classify_llm(s: &LlmError) -> ErrorV1 {
             hint: Some(format!("ensure `ollama serve` is reachable at {endpoint}")),
         },
         LlmError::ModelNotPulled(model) => ErrorV1 {
+            schema_version: ERROR_V1_ID.to_string(),
             code: "model_not_pulled".to_string(),
             message: format!("ollama model `{model}` is not pulled"),
             details: json!({"model": model}),
             hint: Some(format!("run `ollama pull {model}`")),
         },
         LlmError::Timeout(e) => ErrorV1 {
+            schema_version: ERROR_V1_ID.to_string(),
             code: "timeout".to_string(),
             message: format!("ollama timeout: {e}"),
             details: json!({"source": e.to_string()}),
             hint: Some("increase timeout or check Ollama load".to_string()),
         },
         LlmError::Stream(body) => ErrorV1 {
+            schema_version: ERROR_V1_ID.to_string(),
             code: "generic".to_string(),
             message: format!("ollama HTTP error: {body}"),
             details: json!({"body": body}),
             hint: None,
         },
         LlmError::Malformed(line) => ErrorV1 {
+            schema_version: ERROR_V1_ID.to_string(),
             code: "generic".to_string(),
             message: format!("malformed response line: {line}"),
             details: json!({"line": line}),
@@ -116,7 +172,10 @@ mod tests {
         });
         let v1 = classify(&err, false);
         assert_eq!(v1.code, "config_invalid");
-        assert_eq!(v1.details.get("path").and_then(|p| p.as_str()), Some("/tmp/x.toml"));
+        assert_eq!(
+            v1.details.get("path").and_then(|p| p.as_str()),
+            Some("/tmp/x.toml")
+        );
         assert!(v1.hint.is_some());
     }
 
@@ -140,7 +199,8 @@ mod tests {
         // the resulting LlmError::Unreachable maps to "model_unreachable".
         let client = reqwest::blocking::Client::builder()
             .timeout(std::time::Duration::from_millis(500))
-            .build().unwrap();
+            .build()
+            .unwrap();
         let err = client.get("http://127.0.0.1:1").send().unwrap_err();
         let llm = LlmError::Unreachable {
             endpoint: "http://127.0.0.1:1".to_string(),
@@ -156,7 +216,10 @@ mod tests {
         let llm = LlmError::ModelNotPulled("gemma4:e4b".to_string());
         let v1 = classify(&anyhow::Error::new(llm), false);
         assert_eq!(v1.code, "model_not_pulled");
-        assert_eq!(v1.details.get("model").and_then(|p| p.as_str()), Some("gemma4:e4b"));
+        assert_eq!(
+            v1.details.get("model").and_then(|p| p.as_str()),
+            Some("gemma4:e4b")
+        );
     }
 
     #[test]
@@ -183,4 +246,39 @@ mod tests {
         let v1 = classify(&err, false);
         assert_eq!(v1.code, "io_error");
     }
+
+    #[test]
+    fn stale_cursor_is_not_routed_through_classify() {
+        use anyhow::anyhow;
+        let err: anyhow::Error = anyhow!("stale_cursor: rev mismatch");
+        let v1 = classify(&err, false);
+        // p9-fb-34: stale_cursor is constructed directly by cursor::decode
+        // (single source of truth). classify must not pattern-match on
+        // anyhow string contents — that would create two sources of
+        // truth. The bare anyhow string falls through to "generic".
+        assert_ne!(
+            v1.code, "stale_cursor",
+            "classify must not produce stale_cursor from bare anyhow string"
+        );
+    }
+
+    #[test]
+    fn stale_cursor_propagates_through_structured_wrapper() {
+        // p9-fb-34: positive-side contract for the structured-wrapper
+        // path. cursor::decode constructs a typed ErrorV1, the call site
+        // wraps it in `StructuredError`, anyhow carries it, and classify
+        // short-circuits via downcast — preserving the typed code +
+        // message instead of falling through to "generic".
+        let original = ErrorV1 {
+            schema_version: ERROR_V1_ID.to_string(),
+            code: "stale_cursor".to_string(),
+            message: "test stale cursor".to_string(),
+            details: Value::Null,
+            hint: None,
+        };
+        let err: anyhow::Error = anyhow::Error::new(StructuredError(original));
+        let v1 = classify(&err, false);
+        assert_eq!(v1.code, "stale_cursor");
+        assert_eq!(v1.message, "test stale cursor");
+    }
 }

crates/kebab-app/src/external.rs

@@ -0,0 +1,243 @@
+//! Helpers for the `_external/` workspace subdirectory used by
+//! `ingest_file_with_config` and `ingest_stdin_with_config` (p9-fb-31).
+//!
+//! - `ensure_external_dir`: create `<workspace.root>/_external/` if absent.
+//! - `ensure_kebabignore_entry`: append `_external/` to `<workspace.root>/.kebabignore`
+//!   if missing — prevents subsequent `kebab ingest` workspace walks from
+//!   re-walking files that were imported via single-file ingest.
+//! - `copy_to_external`: write bytes to `_external/<blake3-12>.<ext>`, idempotent.
+//! - `inject_frontmatter`: prepend a YAML frontmatter block to a markdown body
+//!   string (used by `ingest_stdin_with_config`).
+
+use std::fs;
+use std::io::Write;
+use std::path::{Path, PathBuf};
+
+use anyhow::{Context, Result};
+
+pub const EXTERNAL_DIR: &str = "_external";
+const KEBABIGNORE_LINE: &str = "_external/";
+
+/// Ensure `<workspace_root>/_external/` exists. Returns the directory path.
+pub fn ensure_external_dir(workspace_root: &Path) -> Result<PathBuf> {
+    let dir = workspace_root.join(EXTERNAL_DIR);
+    fs::create_dir_all(&dir)
+        .with_context(|| format!("create _external dir at {}", dir.display()))?;
+    Ok(dir)
+}
+
+/// Append `_external/` line to `<workspace_root>/.kebabignore` if not already
+/// present. Idempotent — checks for the exact line before appending.
+pub fn ensure_kebabignore_entry(workspace_root: &Path) -> Result<()> {
+    let path = workspace_root.join(".kebabignore");
+    let existing = if path.exists() {
+        fs::read_to_string(&path)
+            .with_context(|| format!("read existing .kebabignore at {}", path.display()))?
+    } else {
+        String::new()
+    };
+    let already = existing.lines().any(|line| line.trim() == KEBABIGNORE_LINE);
+    if already {
+        return Ok(());
+    }
+    let mut file = fs::OpenOptions::new()
+        .create(true)
+        .append(true)
+        .open(&path)
+        .with_context(|| format!("open .kebabignore for append at {}", path.display()))?;
+    if !existing.is_empty() && !existing.ends_with('\n') {
+        file.write_all(b"\n")?;
+    }
+    writeln!(file, "{KEBABIGNORE_LINE}")?;
+    Ok(())
+}
+
+/// Copy bytes to `<external_dir>/<blake3-12>.<ext>`. Idempotent — if the
+/// destination file already exists with the expected hash, the existing
+/// file is reused (no second write). Returns the destination path.
+pub fn copy_to_external(external_dir: &Path, bytes: &[u8], ext: &str) -> Result<PathBuf> {
+    let hash = blake3::hash(bytes);
+    let hex = hash.to_hex();
+    let prefix = &hex.as_str()[..12];
+    let filename = format!("{prefix}.{ext}");
+    let dest = external_dir.join(&filename);
+    if !dest.exists() {
+        fs::write(&dest, bytes)
+            .with_context(|| format!("write external file at {}", dest.display()))?;
+    }
+    Ok(dest)
+}
+
+/// Prepend a YAML frontmatter block to a markdown body. Returns the wrapped
+/// markdown string. Errors if `body` already starts with `---` (the user
+/// should use `ingest_file_with_config` for files that already carry
+/// frontmatter).
+///
+/// Internal `yaml_quote` always uses double-quoted YAML form with backslash
+/// escapes for `"` / `\` / control chars — agent-supplied titles with
+/// special characters are safe.
+pub fn inject_frontmatter(body: &str, title: &str, source_uri: Option<&str>) -> Result<String> {
+    let head = body.trim_start();
+    if head.starts_with("---\n") || head.starts_with("---\r\n") || head.starts_with("---\r") {
+        anyhow::bail!(
+            "stdin already has frontmatter; use `kebab ingest-file` for files with metadata"
+        );
+    }
+    let title_yaml = yaml_quote(title);
+    let mut header = String::new();
+    header.push_str("---\n");
+    header.push_str(&format!("title: {title_yaml}\n"));
+    if let Some(uri) = source_uri {
+        let uri_yaml = yaml_quote(uri);
+        header.push_str(&format!("source_uri: {uri_yaml}\n"));
+    }
+    header.push_str("---\n\n");
+    header.push_str(body);
+    Ok(header)
+}
+
+/// YAML-quote a string. Always uses double-quoted form with backslash-escape
+/// for `"` and `\`. Defensive against agent-supplied titles that contain
+/// quotes / control chars.
+fn yaml_quote(s: &str) -> String {
+    let mut out = String::with_capacity(s.len() + 2);
+    out.push('"');
+    for c in s.chars() {
+        match c {
+            '"' => out.push_str("\\\""),
+            '\\' => out.push_str("\\\\"),
+            '\n' => out.push_str("\\n"),
+            '\r' => out.push_str("\\r"),
+            c if (c as u32) < 0x20 => out.push_str(&format!("\\u{:04x}", c as u32)),
+            c => out.push(c),
+        }
+    }
+    out.push('"');
+    out
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use tempfile::tempdir;
+
+    #[test]
+    fn ensure_external_dir_creates_dir() {
+        let dir = tempdir().unwrap();
+        let result = ensure_external_dir(dir.path()).unwrap();
+        assert_eq!(result, dir.path().join("_external"));
+        assert!(result.is_dir());
+    }
+
+    #[test]
+    fn ensure_external_dir_is_idempotent() {
+        let dir = tempdir().unwrap();
+        let _ = ensure_external_dir(dir.path()).unwrap();
+        let result = ensure_external_dir(dir.path()).unwrap();
+        assert!(result.is_dir());
+    }
+
+    #[test]
+    fn ensure_kebabignore_entry_creates_file_with_line() {
+        let dir = tempdir().unwrap();
+        ensure_kebabignore_entry(dir.path()).unwrap();
+        let content = fs::read_to_string(dir.path().join(".kebabignore")).unwrap();
+        assert!(content.lines().any(|l| l.trim() == "_external/"));
+    }
+
+    #[test]
+    fn ensure_kebabignore_entry_appends_to_existing() {
+        let dir = tempdir().unwrap();
+        fs::write(dir.path().join(".kebabignore"), "*.tmp\n").unwrap();
+        ensure_kebabignore_entry(dir.path()).unwrap();
+        let content = fs::read_to_string(dir.path().join(".kebabignore")).unwrap();
+        let lines: Vec<&str> = content.lines().collect();
+        assert!(lines.contains(&"*.tmp"));
+        assert!(lines.contains(&"_external/"));
+    }
+
+    #[test]
+    fn ensure_kebabignore_entry_idempotent() {
+        let dir = tempdir().unwrap();
+        ensure_kebabignore_entry(dir.path()).unwrap();
+        ensure_kebabignore_entry(dir.path()).unwrap();
+        let content = fs::read_to_string(dir.path().join(".kebabignore")).unwrap();
+        let count = content.lines().filter(|l| l.trim() == "_external/").count();
+        assert_eq!(count, 1, "should not duplicate");
+    }
+
+    #[test]
+    fn ensure_kebabignore_entry_handles_missing_trailing_newline() {
+        let dir = tempdir().unwrap();
+        fs::write(dir.path().join(".kebabignore"), "*.tmp").unwrap(); // no \n
+        ensure_kebabignore_entry(dir.path()).unwrap();
+        let content = fs::read_to_string(dir.path().join(".kebabignore")).unwrap();
+        let lines: Vec<&str> = content.lines().collect();
+        assert!(lines.contains(&"*.tmp"));
+        assert!(lines.contains(&"_external/"));
+    }
+
+    #[test]
+    fn copy_to_external_writes_with_hash_prefix_filename() {
+        let dir = tempdir().unwrap();
+        let ext_dir = ensure_external_dir(dir.path()).unwrap();
+        let path = copy_to_external(&ext_dir, b"hello", "md").unwrap();
+        assert!(path.exists());
+        assert!(path.file_name().unwrap().to_string_lossy().ends_with(".md"));
+        let stem = path.file_stem().unwrap().to_string_lossy();
+        assert_eq!(stem.len(), 12);
+    }
+
+    #[test]
+    fn copy_to_external_is_idempotent_for_same_bytes() {
+        let dir = tempdir().unwrap();
+        let ext_dir = ensure_external_dir(dir.path()).unwrap();
+        let p1 = copy_to_external(&ext_dir, b"hello", "md").unwrap();
+        let p2 = copy_to_external(&ext_dir, b"hello", "md").unwrap();
+        assert_eq!(p1, p2);
+    }
+
+    #[test]
+    fn copy_to_external_different_bytes_produce_different_filenames() {
+        let dir = tempdir().unwrap();
+        let ext_dir = ensure_external_dir(dir.path()).unwrap();
+        let p1 = copy_to_external(&ext_dir, b"hello", "md").unwrap();
+        let p2 = copy_to_external(&ext_dir, b"world", "md").unwrap();
+        assert_ne!(p1, p2);
+    }
+
+    #[test]
+    fn inject_frontmatter_basic() {
+        let out = inject_frontmatter("## Body", "Article X", None).unwrap();
+        assert!(out.starts_with("---\ntitle: \"Article X\"\n---\n\n## Body"));
+    }
+
+    #[test]
+    fn inject_frontmatter_with_source_uri() {
+        let out = inject_frontmatter("## Body", "X", Some("https://example.com/x")).unwrap();
+        assert!(out.contains("title: \"X\""));
+        assert!(out.contains("source_uri: \"https://example.com/x\""));
+        assert!(out.contains("\n## Body"));
+    }
+
+    #[test]
+    fn inject_frontmatter_errors_on_existing_frontmatter() {
+        let body = "---\ntitle: Existing\n---\n\n## Body";
+        let err = inject_frontmatter(body, "New", None).unwrap_err();
+        assert!(err.to_string().contains("already has frontmatter"));
+    }
+
+    #[test]
+    fn inject_frontmatter_errors_on_existing_frontmatter_crlf() {
+        let body = "---\r\ntitle: Existing\r\n---\r\n\r\n## Body";
+        let err = inject_frontmatter(body, "New", None).unwrap_err();
+        assert!(err.to_string().contains("already has frontmatter"));
+    }
+
+    #[test]
+    fn yaml_quote_escapes_quotes_and_backslashes() {
+        assert_eq!(yaml_quote("hello \"world\""), "\"hello \\\"world\\\"\"");
+        assert_eq!(yaml_quote("path\\to"), "\"path\\\\to\"");
+        assert_eq!(yaml_quote("line\nbreak"), "\"line\\nbreak\"");
+    }
+}

crates/kebab-app/src/fetch.rs

@@ -0,0 +1,449 @@
+//! p9-fb-35 verbatim fetch implementation.
+//!
+//! [`App::fetch`] is the facade entry point. It dispatches on
+//! [`FetchQuery`] variants:
+//!
+//! - `Chunk(id)` — return the chunk row from `chunks.text`, optionally
+//!   with ±N surrounding chunks (`FetchOpts::context`).
+//! - `Doc(id)` — return the entire document re-serialized to markdown.
+//!   (Implemented in Task 4.)
+//! - `Span { doc_id, line_start, line_end }` — return a contiguous line
+//!   slice. (Implemented in Task 5.)
+//!
+//! Errors are surfaced as [`StructuredError`] (anyhow-friendly wrapper
+//! around `ErrorV1`) so the CLI / MCP wire layer's `classify` keeps the
+//! typed `code` (`chunk_not_found` / `doc_not_found` /
+//! `span_not_supported`) instead of falling through to `code =
+//! "generic"`.
+
+use anyhow::Result;
+use time::OffsetDateTime;
+
+use kebab_core::{
+    Block, CanonicalDocument, Chunk, ChunkId, DocumentId, DocumentStore, FetchKind, FetchOpts,
+    FetchQuery, FetchResult,
+};
+
+use crate::App;
+use crate::error_wire::{ERROR_V1_ID, ErrorV1, StructuredError};
+use crate::staleness::compute_stale;
+
+impl App {
+    /// p9-fb-35: verbatim fetch facade. Returns text from
+    /// `chunks.text` / `CanonicalDocument` based on the requested
+    /// mode. Errors surface as `StructuredError(ErrorV1)` with one
+    /// of `chunk_not_found` / `doc_not_found` / `span_not_supported`
+    /// so the wire-layer classifier preserves the typed code.
+    pub fn fetch(&self, query: FetchQuery, opts: FetchOpts) -> Result<FetchResult> {
+        match query {
+            FetchQuery::Chunk(id) => fetch_chunk(self, id, opts),
+            FetchQuery::Doc(id) => fetch_doc(self, id, opts),
+            FetchQuery::Span {
+                doc_id,
+                line_start,
+                line_end,
+            } => fetch_span(self, doc_id, line_start, line_end, opts),
+        }
+    }
+}
+
+fn fetch_chunk(app: &App, id: ChunkId, opts: FetchOpts) -> Result<FetchResult> {
+    let target = <kebab_store_sqlite::SqliteStore as DocumentStore>::get_chunk(&app.sqlite, &id)?
+        .ok_or_else(|| {
+        anyhow::Error::new(StructuredError(ErrorV1 {
+            schema_version: ERROR_V1_ID.to_string(),
+            code: "chunk_not_found".to_string(),
+            message: format!("chunk_id '{}' not found", id.0),
+            details: serde_json::Value::Null,
+            hint: None,
+        }))
+    })?;
+
+    let doc_id = target.doc_id.clone();
+    let doc =
+        <kebab_store_sqlite::SqliteStore as DocumentStore>::get_document(&app.sqlite, &doc_id)?
+            .ok_or_else(|| {
+                anyhow::Error::new(StructuredError(ErrorV1 {
+                    schema_version: ERROR_V1_ID.to_string(),
+                    code: "doc_not_found".to_string(),
+                    message: format!(
+                        "doc_id '{}' (parent of chunk '{}') not found",
+                        doc_id.0, id.0
+                    ),
+                    details: serde_json::Value::Null,
+                    hint: None,
+                }))
+            })?;
+
+    let (context_before, context_after) = match opts.context {
+        Some(n) if n > 0 => surrounding_chunks(app, &doc_id, &id, n)?,
+        _ => (Vec::new(), Vec::new()),
+    };
+
+    let now = OffsetDateTime::now_utc();
+    let stale = compute_stale(
+        doc_metadata_updated_at(&doc),
+        now,
+        app.config.search.stale_threshold_days,
+    );
+
+    Ok(FetchResult {
+        kind: FetchKind::Chunk,
+        doc_id: doc.doc_id.clone(),
+        doc_path: doc.workspace_path.clone(),
+        indexed_at: doc_metadata_updated_at(&doc),
+        stale,
+        chunk: Some(target),
+        context_before,
+        context_after,
+        text: None,
+        line_start: None,
+        line_end: None,
+        effective_end: None,
+        truncated: false,
+    })
+}
+
+fn fetch_doc(app: &App, id: DocumentId, opts: FetchOpts) -> Result<FetchResult> {
+    let doc = <kebab_store_sqlite::SqliteStore as DocumentStore>::get_document(&app.sqlite, &id)?
+        .ok_or_else(|| {
+        anyhow::Error::new(StructuredError(ErrorV1 {
+            schema_version: ERROR_V1_ID.to_string(),
+            code: "doc_not_found".to_string(),
+            message: format!("doc_id '{}' not found", id.0),
+            details: serde_json::Value::Null,
+            hint: None,
+        }))
+    })?;
+
+    let mut text = fmt_canonical_to_markdown(&doc);
+    let mut truncated = false;
+    if let Some(max_tokens) = opts.max_tokens {
+        let max_chars = max_tokens.saturating_mul(4);
+        if text.chars().count() > max_chars {
+            text = trim_to_chars(&text, max_chars);
+            truncated = true;
+        }
+    }
+
+    let now = OffsetDateTime::now_utc();
+    let stale = compute_stale(
+        doc_metadata_updated_at(&doc),
+        now,
+        app.config.search.stale_threshold_days,
+    );
+
+    Ok(FetchResult {
+        kind: FetchKind::Doc,
+        doc_id: doc.doc_id.clone(),
+        doc_path: doc.workspace_path.clone(),
+        indexed_at: doc_metadata_updated_at(&doc),
+        stale,
+        chunk: None,
+        context_before: Vec::new(),
+        context_after: Vec::new(),
+        text: Some(text),
+        line_start: None,
+        line_end: None,
+        effective_end: None,
+        truncated,
+    })
+}
+
+/// p9-fb-35: trim string to N chars (Unicode-safe). Mirrors fb-34's
+/// helper at `crates/kebab-app/src/app.rs` — kept local to avoid
+/// re-exporting an internal helper.
+fn trim_to_chars(s: &str, n: usize) -> String {
+    if s.chars().count() <= n {
+        return s.to_string();
+    }
+    let mut out = String::with_capacity(n * 4);
+    for (i, c) in s.chars().enumerate() {
+        if i >= n {
+            break;
+        }
+        out.push(c);
+    }
+    out
+}
+
+fn fetch_span(
+    app: &App,
+    id: DocumentId,
+    line_start: u32,
+    line_end: u32,
+    opts: FetchOpts,
+) -> Result<FetchResult> {
+    let doc = <kebab_store_sqlite::SqliteStore as DocumentStore>::get_document(&app.sqlite, &id)?
+        .ok_or_else(|| {
+        anyhow::Error::new(StructuredError(ErrorV1 {
+            schema_version: ERROR_V1_ID.to_string(),
+            code: "doc_not_found".to_string(),
+            message: format!("doc_id '{}' not found", id.0),
+            details: serde_json::Value::Null,
+            hint: None,
+        }))
+    })?;
+
+    // Reject line-incompatible media types (PDF / audio). `SourceType`
+    // (markdown / note / paper / reference / inbox) is the *user-facing*
+    // category, not the rendering format — the actual byte-level format
+    // lives on the source `RawAsset.media_type`. Look it up via
+    // doc.source_asset_id (PRIMARY KEY) so twin files (identical content
+    // at different paths) always read *this* document's own asset row,
+    // not whichever twin last wrote `assets.workspace_path`.
+    if let Some(asset) = <kebab_store_sqlite::SqliteStore as DocumentStore>::get_asset(
+        &app.sqlite,
+        &doc.source_asset_id,
+    )? {
+        if matches!(
+            asset.media_type,
+            kebab_core::MediaType::Pdf | kebab_core::MediaType::Audio(_)
+        ) {
+            return Err(anyhow::Error::new(StructuredError(ErrorV1 {
+                schema_version: ERROR_V1_ID.to_string(),
+                code: "span_not_supported".to_string(),
+                message: format!(
+                    "doc '{}' has media_type {:?}; line-based span fetch unsupported. \
+                     Use `fetch chunk` or `fetch doc` instead.",
+                    id.0, asset.media_type
+                ),
+                details: serde_json::Value::Null,
+                hint: Some("kind = chunk or kind = doc instead".to_string()),
+            })));
+        }
+    }
+
+    if line_start == 0 || line_end == 0 || line_end < line_start {
+        return Err(anyhow::Error::new(StructuredError(ErrorV1 {
+            schema_version: ERROR_V1_ID.to_string(),
+            code: "invalid_input".to_string(),
+            message: format!(
+                "line_start ({line_start}) and line_end ({line_end}) must be 1-based with start <= end"
+            ),
+            details: serde_json::Value::Null,
+            hint: None,
+        })));
+    }
+
+    let full = fmt_canonical_to_markdown(&doc);
+    let lines: Vec<&str> = full.lines().collect();
+    let total = lines.len() as u32;
+
+    // p9-fb-35 round-1 review fix: empty / out-of-range request must
+    // not slice. Returning empty text + `effective_end = line_start - 1`
+    // lets the caller detect "no lines fetched" via
+    // `text.is_empty() && effective_end < line_start`. `truncated`
+    // stays false because line-range clamp is NOT a budget event —
+    // budget-driven truncation is the only thing `truncated` signals.
+    if total == 0 || line_start > total {
+        let now = OffsetDateTime::now_utc();
+        let stale = compute_stale(
+            doc_metadata_updated_at(&doc),
+            now,
+            app.config.search.stale_threshold_days,
+        );
+        return Ok(FetchResult {
+            kind: FetchKind::Span,
+            doc_id: doc.doc_id.clone(),
+            doc_path: doc.workspace_path.clone(),
+            indexed_at: doc_metadata_updated_at(&doc),
+            stale,
+            chunk: None,
+            context_before: Vec::new(),
+            context_after: Vec::new(),
+            text: Some(String::new()),
+            line_start: Some(line_start),
+            line_end: Some(line_end),
+            // saturating_sub: when line_start = 1 we end at 0, signaling
+            // "no lines fetched" without underflowing u32.
+            effective_end: Some(line_start.saturating_sub(1)),
+            truncated: false,
+        });
+    }
+
+    let effective_end_raw = line_end.min(total);
+    let lo = (line_start - 1) as usize;
+    let hi = effective_end_raw as usize;
+    let mut text = lines[lo..hi].join("\n");
+
+    // p9-fb-35 round-1 review fix: `truncated` is reserved for
+    // budget-driven truncation only. Line-range clamp (line_end >
+    // total) is signaled via `effective_end < line_end`, not via
+    // `truncated`.
+    let mut truncated = false;
+    let mut effective_end = effective_end_raw;
+    if let Some(max_tokens) = opts.max_tokens {
+        let max_chars = max_tokens.saturating_mul(4);
+        if text.chars().count() > max_chars {
+            text = trim_to_chars(&text, max_chars);
+            truncated = true;
+            let kept = text.lines().count() as u32;
+            effective_end = (line_start - 1) + kept;
+        }
+    }
+
+    let now = OffsetDateTime::now_utc();
+    let stale = compute_stale(
+        doc_metadata_updated_at(&doc),
+        now,
+        app.config.search.stale_threshold_days,
+    );
+
+    Ok(FetchResult {
+        kind: FetchKind::Span,
+        doc_id: doc.doc_id.clone(),
+        doc_path: doc.workspace_path.clone(),
+        indexed_at: doc_metadata_updated_at(&doc),
+        stale,
+        chunk: None,
+        context_before: Vec::new(),
+        context_after: Vec::new(),
+        text: Some(text),
+        line_start: Some(line_start),
+        line_end: Some(line_end),
+        effective_end: Some(effective_end),
+        truncated,
+    })
+}
+
+/// p9-fb-35: list chunks for a document in ordinal order, return
+/// `(before, after)` slices around the target chunk_id. `n` caps each
+/// side independently — the worst case is `2n` total neighbors when
+/// the target sits in the middle of the doc.
+fn surrounding_chunks(
+    app: &App,
+    doc_id: &DocumentId,
+    target: &ChunkId,
+    n: u32,
+) -> Result<(Vec<Chunk>, Vec<Chunk>)> {
+    let chunks = list_chunks_in_order(app, doc_id)?;
+    let target_idx = chunks
+        .iter()
+        .position(|c| c.chunk_id == *target)
+        .ok_or_else(|| anyhow::anyhow!("chunk not found in doc chunk list"))?;
+    let n = n as usize;
+    let lo = target_idx.saturating_sub(n);
+    let hi = target_idx
+        .saturating_add(n)
+        .saturating_add(1)
+        .min(chunks.len());
+    let before: Vec<Chunk> = chunks[lo..target_idx].to_vec();
+    let after: Vec<Chunk> = chunks[target_idx + 1..hi].to_vec();
+    Ok((before, after))
+}
+
+/// p9-fb-35: chunks have no explicit ordinal column, so the underlying
+/// helper sorts by `(created_at, chunk_id)` which matches insertion
+/// order produced by the chunker (deterministic). The actual SQL lives
+/// inside `kebab-store-sqlite` (`SqliteStore::list_chunk_ids_for_doc`)
+/// to keep the facade crate free of direct rusqlite usage.
+fn list_chunks_in_order(app: &App, doc_id: &DocumentId) -> Result<Vec<Chunk>> {
+    let chunk_ids = app.sqlite.list_chunk_ids_for_doc(doc_id)?;
+    let mut out: Vec<Chunk> = Vec::with_capacity(chunk_ids.len());
+    for cid in chunk_ids {
+        if let Some(chunk) =
+            <kebab_store_sqlite::SqliteStore as DocumentStore>::get_chunk(&app.sqlite, &cid)?
+        {
+            out.push(chunk);
+        }
+    }
+    Ok(out)
+}
+
+fn doc_metadata_updated_at(doc: &CanonicalDocument) -> OffsetDateTime {
+    doc.metadata.updated_at
+}
+
+/// p9-fb-35: serialize a `CanonicalDocument` back to markdown. Best-
+/// effort round-trip — inline-styled spans (Strong/Emph children)
+/// flatten to plain text via the already-flattened `TextBlock.text`
+/// field. Good enough for an agent reading verbatim context. Used by
+/// Task 4 (doc mode) and Task 5 (span mode).
+pub(crate) fn fmt_canonical_to_markdown(doc: &CanonicalDocument) -> String {
+    let mut out = String::with_capacity(1024);
+    for (i, block) in doc.blocks.iter().enumerate() {
+        if i > 0 {
+            out.push_str("\n\n");
+        }
+        match block {
+            Block::Heading(h) => {
+                let level = h.level.clamp(1, 6) as usize;
+                for _ in 0..level {
+                    out.push('#');
+                }
+                out.push(' ');
+                out.push_str(&h.text);
+            }
+            Block::Paragraph(t) => out.push_str(&t.text),
+            Block::Quote(t) => {
+                // Prefix every line with `> ` so block-quote round-trips.
+                for (li, line) in t.text.split('\n').enumerate() {
+                    if li > 0 {
+                        out.push('\n');
+                    }
+                    out.push_str("> ");
+                    out.push_str(line);
+                }
+            }
+            Block::List(l) => {
+                for (idx, item) in l.items.iter().enumerate() {
+                    if idx > 0 {
+                        out.push('\n');
+                    }
+                    if l.ordered {
+                        out.push_str(&format!("{}. {}", idx + 1, item.text));
+                    } else {
+                        out.push_str(&format!("- {}", item.text));
+                    }
+                }
+            }
+            Block::Code(c) => {
+                out.push_str("```");
+                if let Some(lang) = &c.lang {
+                    out.push_str(lang);
+                }
+                out.push('\n');
+                out.push_str(&c.code);
+                if !c.code.ends_with('\n') {
+                    out.push('\n');
+                }
+                out.push_str("```");
+            }
+            Block::Table(t) => {
+                out.push_str(&t.headers.join(" | "));
+                out.push('\n');
+                // Markdown table separator — N copies of `---|` is
+                // acceptable for a verbatim re-serialization (renderer
+                // tolerates trailing pipe).
+                out.push_str(&"---|".repeat(t.headers.len()));
+                for row in &t.rows {
+                    out.push('\n');
+                    out.push_str(&row.join(" | "));
+                }
+            }
+            Block::ImageRef(img) => {
+                out.push_str(&format!("![{}]({})", img.alt, img.src));
+            }
+            Block::AudioRef(_a) => {
+                // Canonical doc carries the transcript on AudioRefBlock,
+                // but markdown has no native audio embed. Emit a stub
+                // marker so the agent sees something ran here.
+                out.push_str("(audio reference)");
+            }
+        }
+    }
+    out
+}
+
+/// p9-fb-35: free-function entry for CLI / MCP. Mirrors the
+/// `*_with_config` pattern documented in the kebab-app crate root —
+/// `kebab-cli` calls this so a `--config <path>` flag is honored.
+#[doc(hidden)]
+pub fn fetch_with_config(
+    config: kebab_config::Config,
+    query: FetchQuery,
+    opts: FetchOpts,
+) -> Result<FetchResult> {
+    App::open_with_config(config)?.fetch(query, opts)
+}

crates/kebab-app/src/ingest_log.rs

@@ -0,0 +1,446 @@
+//! Per-ingest-run structured ndjson log writer (v0.20.x ingest log feature).
+//!
+//! Each `kebab ingest` run produces one `ingest-{run_id}.ndjson` file in
+//! `config.logging.ingest_log_dir`. Records are appended line by line; the
+//! last record is always `kind="summary"`. `IngestLogWriter::open` returns
+//! `Ok(None)` when `ingest_log_enabled = false` so callers need not branch.
+
+use std::fs::File;
+use std::io::{BufWriter, Write};
+use std::path::{Path, PathBuf};
+use std::time::SystemTime;
+
+use serde::{Deserialize, Serialize};
+use time::format_description::well_known::Rfc3339;
+
+pub struct IngestLogWriter {
+    file: BufWriter<File>,
+    path: PathBuf,
+    run_id: String,
+    started_at: SystemTime,
+}
+
+impl IngestLogWriter {
+    /// Open a new log file. Returns `Ok(None)` when `cfg.ingest_log_enabled == false` (AC-6).
+    pub fn open(cfg: &kebab_config::LoggingCfg) -> anyhow::Result<Option<Self>> {
+        if !cfg.ingest_log_enabled {
+            return Ok(None);
+        }
+        let run_id = generate_run_id();
+        let log_dir = expand_log_dir(&cfg.ingest_log_dir);
+        std::fs::create_dir_all(&log_dir)?;
+        // Cleanup before creating the new file (non-critical: warn on error).
+        if let Err(e) = cleanup_old_logs(&log_dir, cfg.keep_recent_runs, cfg.retention_days) {
+            tracing::warn!(target: "kebab-app", "ingest log cleanup failed: {e}");
+        }
+        let path = log_dir.join(format!("ingest-{run_id}.ndjson"));
+        let file = BufWriter::new(File::create(&path)?);
+        Ok(Some(Self {
+            file,
+            path,
+            run_id,
+            started_at: SystemTime::now(),
+        }))
+    }
+
+    pub fn write_event(&mut self, event: &LogEvent<'_>) -> anyhow::Result<()> {
+        serde_json::to_writer(&mut self.file, event)?;
+        writeln!(self.file)?;
+        Ok(())
+    }
+
+    pub fn write_summary(&mut self, summary: &IngestSummary) -> anyhow::Result<()> {
+        serde_json::to_writer(&mut self.file, summary)?;
+        writeln!(self.file)?;
+        Ok(())
+    }
+
+    pub fn flush(&mut self) -> anyhow::Result<()> {
+        self.file.flush()?;
+        Ok(())
+    }
+
+    pub fn run_id(&self) -> &str {
+        &self.run_id
+    }
+
+    pub fn path(&self) -> &Path {
+        &self.path
+    }
+
+    pub fn started_at(&self) -> SystemTime {
+        self.started_at
+    }
+}
+
+impl Drop for IngestLogWriter {
+    fn drop(&mut self) {
+        let _ = self.file.flush();
+    }
+}
+
+/// ISO 8601 compact timestamp + uuid v7 suffix: `20260528T013000Z-abc123de`.
+/// uuid v7 is the workspace dep (Cargo.toml); `rand` is not added (spec §6 R-5).
+fn generate_run_id() -> String {
+    use time::macros::format_description;
+    let now = time::OffsetDateTime::now_utc();
+    let ts = now
+        .format(format_description!(
+            "[year][month][day]T[hour][minute][second]Z"
+        ))
+        .unwrap_or_else(|_| "19700101T000000Z".to_string());
+    let uid = uuid::Uuid::now_v7().simple().to_string();
+    let suffix = &uid[uid.len() - 8..];
+    format!("{ts}-{suffix}")
+}
+
+/// Expand `{state_dir}` placeholder → XDG state dir (spec §6 R-3).
+/// Other tilde/env expansion is delegated to `kebab_config::expand_path`.
+fn expand_log_dir(path: &Path) -> PathBuf {
+    let path_str = path.to_string_lossy();
+    if path_str.contains("{state_dir}") {
+        let state_dir = kebab_config::Config::xdg_state_dir();
+        PathBuf::from(path_str.replace("{state_dir}", &state_dir.to_string_lossy()))
+    } else {
+        path.to_path_buf()
+    }
+}
+
+/// RFC 3339 UTC timestamp for log records.
+#[allow(dead_code)]
+pub(crate) fn now_ts() -> String {
+    time::OffsetDateTime::now_utc()
+        .format(&Rfc3339)
+        .unwrap_or_else(|_| "1970-01-01T00:00:00Z".to_string())
+}
+
+/// Ingest event record (ndjson line). `kind` is the discriminator.
+#[derive(Serialize, Deserialize)]
+#[serde(tag = "kind", rename_all = "snake_case")]
+pub enum LogEvent<'a> {
+    Ocr {
+        ts: String,
+        /// v0.20.x r2: additive field — doc_id for dual-write SQLite correlation.
+        /// Round 1 ndjson logs deserialize with doc_id=None (Serde Option default).
+        #[serde(skip_serializing_if = "Option::is_none")]
+        doc_id: Option<&'a str>,
+        doc_path: &'a str,
+        page: u32,
+        image_byte_size: Option<u64>,
+        image_width: Option<u32>,
+        image_height: Option<u32>,
+        ms: u64,
+        chars: u32,
+        success: bool,
+        reason: Option<&'a str>,
+        ocr_engine: &'a str,
+    },
+    ParseError {
+        ts: String,
+        doc_path: &'a str,
+        reason: &'a str,
+        message: &'a str,
+    },
+    Skip {
+        ts: String,
+        doc_path: &'a str,
+        reason: &'a str,
+        detail: Option<&'a str>,
+    },
+    Error {
+        ts: String,
+        code: &'a str,
+        message: &'a str,
+    },
+}
+
+/// Final summary record — always the last line of the log file.
+/// Explicit `kind` field serializes to `"kind": "summary"`.
+#[derive(Serialize, Deserialize)]
+pub struct IngestSummary {
+    pub kind: String,
+    pub ts: String,
+    pub run_id: String,
+    pub scanned: u32,
+    pub new: u32,
+    pub errors: u32,
+    pub ocr_pages: u32,
+    pub ocr_failures: u32,
+    pub ocr_p50_ms: Option<u64>,
+    pub ocr_p90_ms: Option<u64>,
+    pub ocr_max_ms: Option<u64>,
+    pub duration_ms: u64,
+}
+
+impl IngestSummary {
+    #[allow(clippy::too_many_arguments)]
+    pub fn new(
+        ts: String,
+        run_id: String,
+        scanned: u32,
+        new: u32,
+        errors: u32,
+        ocr_pages: u32,
+        ocr_failures: u32,
+        ocr_ms_samples: &[u64],
+        duration_ms: u64,
+    ) -> Self {
+        let (p50, p90, _p99, max) = percentiles(ocr_ms_samples);
+        Self {
+            kind: "summary".to_string(),
+            ts,
+            run_id,
+            scanned,
+            new,
+            errors,
+            ocr_pages,
+            ocr_failures,
+            ocr_p50_ms: p50,
+            ocr_p90_ms: p90,
+            ocr_max_ms: max,
+            duration_ms,
+        }
+    }
+}
+
+/// Simple percentile extraction on a sorted copy of `samples`.
+/// Returns `(p50, p90, p99, max)`. All `None` when samples is empty.
+/// p99 surfaces via `inspect ocr-stats`; `IngestSummary` uses p50/p90/max only.
+pub(crate) fn percentiles(samples: &[u64]) -> (Option<u64>, Option<u64>, Option<u64>, Option<u64>) {
+    if samples.is_empty() {
+        return (None, None, None, None);
+    }
+    let mut sorted = samples.to_vec();
+    sorted.sort_unstable();
+    let n = sorted.len();
+    let p50 = sorted[(n.saturating_sub(1) * 50) / 100];
+    let p90 = sorted[(n.saturating_sub(1) * 90) / 100];
+    let p99 = sorted[(n.saturating_sub(1) * 99) / 100];
+    let max = *sorted.last().unwrap();
+    (Some(p50), Some(p90), Some(p99), Some(max))
+}
+
+/// Delete old ingest log files from `log_dir`.
+///
+/// **Retention rule (§3.4 OR-on-stale semantics):**
+/// Keep a file iff BOTH conditions hold: (idx < keep_recent) AND (modified > cutoff).
+/// Delete iff (idx >= keep_recent) OR (modified <= cutoff) — either stale condition
+/// triggers deletion. Files are indexed newest-first so `idx=0` is the most recent.
+pub(crate) fn cleanup_old_logs(
+    log_dir: &Path,
+    keep_recent: u32,
+    retention_days: u32,
+) -> anyhow::Result<()> {
+    let mut entries: Vec<_> = std::fs::read_dir(log_dir)?
+        .filter_map(Result::ok)
+        .filter(|e| {
+            e.path()
+                .file_name()
+                .and_then(|n| n.to_str())
+                .is_some_and(|s| s.starts_with("ingest-") && s.ends_with(".ndjson"))
+        })
+        .collect();
+
+    // Sort newest-first by mtime (files without mtime go to the end).
+    entries.sort_by_key(|e| std::cmp::Reverse(e.metadata().ok().and_then(|m| m.modified().ok())));
+
+    let cutoff = SystemTime::now()
+        .checked_sub(std::time::Duration::from_secs(
+            u64::from(retention_days) * 86400,
+        ))
+        .unwrap_or(SystemTime::UNIX_EPOCH);
+
+    for (idx, entry) in entries.into_iter().enumerate() {
+        let modified = entry
+            .metadata()
+            .ok()
+            .and_then(|m| m.modified().ok())
+            .unwrap_or(SystemTime::UNIX_EPOCH);
+        // Keep iff (idx < keep_recent) AND (modified > cutoff).
+        if (idx as u32) < keep_recent && modified > cutoff {
+            continue;
+        }
+        if let Err(e) = std::fs::remove_file(entry.path()) {
+            tracing::warn!(
+                target: "kebab-app",
+                "failed to remove old log {}: {e}",
+                entry.path().display()
+            );
+        }
+    }
+    Ok(())
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use kebab_config::LoggingCfg;
+    use std::time::SystemTime;
+    use tempfile::TempDir;
+
+    #[test]
+    fn generate_run_id_has_iso_prefix_and_8_hex_suffix() {
+        let id = generate_run_id();
+        // Format: YYYYMMDDTHHmmssZ-xxxxxxxx (total len = 16+1+8 = 25)
+        assert_eq!(id.len(), 25, "run_id len should be 25: {id}");
+        let (prefix, suffix) = id.split_once('-').expect("run_id should contain '-'");
+        assert_eq!(prefix.len(), 16, "prefix should be 16 chars: {prefix}");
+        assert!(prefix.contains('T'), "prefix should contain T: {prefix}");
+        assert!(prefix.ends_with('Z'), "prefix should end with Z: {prefix}");
+        assert_eq!(suffix.len(), 8, "suffix should be 8 chars: {suffix}");
+        assert!(
+            suffix.chars().all(|c| c.is_ascii_hexdigit()),
+            "suffix should be hex: {suffix}"
+        );
+    }
+
+    #[test]
+    fn expand_log_dir_substitutes_state_dir_placeholder() {
+        let input = PathBuf::from("{state_dir}/logs");
+        let expanded = expand_log_dir(&input);
+        let expected = kebab_config::Config::xdg_state_dir().join("logs");
+        assert_eq!(expanded, expected);
+        assert!(!expanded.to_string_lossy().contains("{state_dir}"));
+    }
+
+    #[test]
+    fn writer_disabled_returns_none() {
+        let cfg = LoggingCfg {
+            ingest_log_enabled: false,
+            ingest_log_dir: PathBuf::from("/tmp/should-not-exist"),
+            ..Default::default()
+        };
+        let result = IngestLogWriter::open(&cfg).expect("open should not error");
+        assert!(result.is_none(), "disabled writer should return None");
+    }
+
+    #[test]
+    fn writer_writes_one_event_per_line_with_kind_discriminator() {
+        let tmp = TempDir::new().unwrap();
+        let cfg = LoggingCfg {
+            ingest_log_enabled: true,
+            ingest_log_dir: tmp.path().to_path_buf(),
+            ..Default::default()
+        };
+        let mut writer = IngestLogWriter::open(&cfg).unwrap().unwrap();
+        let path = writer.path().to_path_buf();
+
+        writer
+            .write_event(&LogEvent::Skip {
+                ts: now_ts(),
+                doc_path: "a.zip",
+                reason: "builtin_blacklist",
+                detail: Some(".zip extension"),
+            })
+            .unwrap();
+        writer
+            .write_event(&LogEvent::Error {
+                ts: now_ts(),
+                code: "ingest_fatal",
+                message: "something bad",
+            })
+            .unwrap();
+        writer
+            .write_event(&LogEvent::ParseError {
+                ts: now_ts(),
+                doc_path: "weird.pdf",
+                reason: "lopdf_error",
+                message: "unexpected EOF",
+            })
+            .unwrap();
+        writer.flush().unwrap();
+
+        let contents = std::fs::read_to_string(&path).unwrap();
+        let lines: Vec<&str> = contents.lines().collect();
+        assert_eq!(lines.len(), 3, "expected 3 lines, got: {}", lines.len());
+        for line in &lines {
+            assert!(
+                line.starts_with('{'),
+                "each line should be JSON object: {line}"
+            );
+            assert!(
+                line.contains("\"kind\""),
+                "each line should have 'kind': {line}"
+            );
+        }
+    }
+
+    #[test]
+    fn drop_flushes_pending_buffer() {
+        let tmp = TempDir::new().unwrap();
+        let cfg = LoggingCfg {
+            ingest_log_enabled: true,
+            ingest_log_dir: tmp.path().to_path_buf(),
+            ..Default::default()
+        };
+        let mut writer = IngestLogWriter::open(&cfg).unwrap().unwrap();
+        let path = writer.path().to_path_buf();
+        writer
+            .write_event(&LogEvent::Error {
+                ts: now_ts(),
+                code: "test",
+                message: "drop flush test",
+            })
+            .unwrap();
+        // Drop without explicit flush — Drop impl should flush BufWriter.
+        drop(writer);
+        let contents = std::fs::read_to_string(&path).unwrap();
+        assert!(
+            contents.lines().count() >= 1,
+            "file should have at least 1 line after drop"
+        );
+    }
+
+    /// AC-7: keep_recent=3 with 5 files, oldest 2 should be deleted.
+    #[test]
+    fn cleanup_keeps_recent_n_drops_old() {
+        let tmp = TempDir::new().unwrap();
+        let dir = tmp.path();
+        // Create 5 files with mtime spread across 60 days
+        for i in 0..5u64 {
+            let path = dir.join(format!("ingest-file{i}.ndjson"));
+            std::fs::write(&path, b"x").unwrap();
+            // Set mtime: file 0 = newest, file 4 = 60 days old
+            let age_days = i * 15; // 0, 15, 30, 45, 60 days old
+            let mtime = SystemTime::now()
+                .checked_sub(std::time::Duration::from_secs(age_days * 86400))
+                .unwrap();
+            filetime::set_file_mtime(&path, filetime::FileTime::from_system_time(mtime)).unwrap();
+        }
+        // keep_recent=3, retention_days=90 (no time-based deletion)
+        cleanup_old_logs(dir, 3, 90).unwrap();
+        let remaining: Vec<_> = std::fs::read_dir(dir)
+            .unwrap()
+            .filter_map(Result::ok)
+            .collect();
+        assert_eq!(remaining.len(), 3, "expected 3 files after cleanup");
+    }
+
+    /// F5 OR-on-stale: files within keep_recent count but older than retention_days
+    /// must still be deleted.
+    #[test]
+    fn cleanup_drops_stale_even_within_count() {
+        let tmp = TempDir::new().unwrap();
+        let dir = tmp.path();
+        // 2 files, both 90 days old — well past retention_days=30
+        for i in 0..2u64 {
+            let path = dir.join(format!("ingest-old{i}.ndjson"));
+            std::fs::write(&path, b"x").unwrap();
+            let mtime = SystemTime::now()
+                .checked_sub(std::time::Duration::from_secs(90 * 86400))
+                .unwrap();
+            filetime::set_file_mtime(&path, filetime::FileTime::from_system_time(mtime)).unwrap();
+        }
+        // keep_recent=10 (both within count) but retention_days=30 → both stale
+        cleanup_old_logs(dir, 10, 30).unwrap();
+        let remaining: Vec<_> = std::fs::read_dir(dir)
+            .unwrap()
+            .filter_map(Result::ok)
+            .collect();
+        assert_eq!(
+            remaining.len(),
+            0,
+            "stale files must be deleted even within keep_recent"
+        );
+    }
+}

crates/kebab-app/src/ingest_progress.rs

@@ -46,10 +46,21 @@ pub struct AggregateCounts {
 /// Ordering invariant per design §2.4a:
 ///
 /// ```text
-/// ScanStarted < ScanCompleted < (AssetStarted < AssetFinished)*
-///                             < (Completed | Aborted)
+/// ScanStarted < ScanCompleted
+///   < ( AssetStarted
+///         [< (PdfOcrStarted < PdfOcrFinished)*]
+///         [< AssetChunked]
+///         [< AssetTimings]
+///       < AssetFinished )*
+///   < (Completed | Aborted)
 /// ```
 ///
+/// `[]` = optional. `PdfOcr*` is per-PDF asset only (v0.20.0 sub-item 1).
+/// `AssetChunked` / `AssetTimings` are the v0.24.0 asset-internal phase
+/// events: `AssetChunked` fires once right after chunking (markdown /
+/// image / PDF); `AssetTimings` reports per-phase wall-clock once
+/// (markdown only).
+///
 /// Embed-batch events (`embed_batch_started` / `embed_batch_finished`
 /// in §2.4a) are reserved for a future iteration and are not emitted
 /// by this task; the spec calls them out as "임의 위치" (optional).
@@ -79,12 +90,82 @@ pub enum IngestEvent {
         result: IngestItemKind,
         chunks: u32,
     },
+    /// v0.24.0 (additive): emitted right after an asset is chunked, before
+    /// expansion / embed / store. Surfaces "this document is N chunks"
+    /// immediately so a single large document no longer looks frozen at
+    /// `idx/total` while its per-chunk phases churn. `chunks` is the chunk
+    /// count for asset `idx`.
+    AssetChunked { idx: u32, total: u32, chunks: u32 },
+    /// v0.26.1 (additive): emitted when an asset enters a *slow* internal
+    /// phase, so the interactive progress bar can show **which** phase
+    /// (and which model) is currently running instead of looking frozen.
+    /// `phase` ∈ {`"ocr"`, `"caption"`, `"embed"`}; short phases
+    /// (parse / chunk / store) are intentionally *not* emitted to avoid
+    /// noise. `model` is the model performing the phase — the vision LLM
+    /// id for `ocr` / `caption`, the embedder `model_id` for `embed`
+    /// (`None` when the phase runs without a configured model, e.g. embed
+    /// with no embedder wired). Emitted once per (asset, phase); no
+    /// throttle needed (low frequency). Wire v1 consumers that predate
+    /// this variant simply ignore the unknown `asset_phase` kind.
+    AssetPhase {
+        idx: u32,
+        total: u32,
+        phase: String,
+        model: Option<String>,
+    },
+    /// v0.24.0 (additive): per-phase wall-clock (milliseconds) for asset
+    /// `idx`, emitted once the asset's pipeline finishes. Lets a user see
+    /// *where* the time went (parse / chunk / ocr / caption / embed /
+    /// store) without parsing logs. The markdown path leaves `ocr_ms` /
+    /// `caption_ms` at 0 (no image analysis); the image / PDF paths fill
+    /// them so the slowest-asset summary attributes vision-model time
+    /// correctly. `expansion_ms` is retained for wire compatibility but is
+    /// always 0 since doc-side expansion was removed (HOTFIXES 2026-06-03).
+    /// `ocr_ms` / `caption_ms` (v0.26.1) are additive with serde default 0
+    /// so pre-v0.26.1 consumers deserialize cleanly.
+    AssetTimings {
+        idx: u32,
+        total: u32,
+        parse_ms: u64,
+        chunk_ms: u64,
+        expansion_ms: u64,
+        embed_ms: u64,
+        store_ms: u64,
+        #[serde(default)]
+        ocr_ms: u64,
+        #[serde(default)]
+        caption_ms: u64,
+    },
     /// Run finished normally. `counts` is the final aggregate.
     Completed { counts: AggregateCounts },
     /// Run finished by user cancellation. `counts` is the partial
     /// aggregate at the cancel boundary. Emitted by `p9-fb-04`; this
     /// task never produces `Aborted`.
     Aborted { counts: AggregateCounts },
+    /// PDF page 별 OCR 시작 시 emit. v0.20.0 sub-item 1.
+    PdfOcrStarted { page: u32 },
+    /// PDF page 별 OCR 종료 시 emit. v0.20.0 sub-item 1.
+    /// `skipped` = `true` 일 시 OCR 미수행 (DCTDecode 부재 또는 engine 실패).
+    /// `chars = 0` 만으로는 "skip" 과 "0-char OCR result" 구분 불가, `skipped` field 가 명시적.
+    PdfOcrFinished {
+        page: u32,
+        ms: u64,
+        chars: u32,
+        ocr_engine: String,
+        skipped: bool,
+        /// v0.20.x ingest log: raster image byte size (additive minor, optional).
+        #[serde(skip_serializing_if = "Option::is_none")]
+        image_byte_size: Option<u64>,
+        /// v0.20.x ingest log: raster image width in pixels (additive minor, optional).
+        #[serde(skip_serializing_if = "Option::is_none")]
+        image_width: Option<u32>,
+        /// v0.20.x ingest log: raster image height in pixels (additive minor, optional).
+        #[serde(skip_serializing_if = "Option::is_none")]
+        image_height: Option<u32>,
+        /// v0.20.x ingest log: OCR failure reason (additive minor, optional).
+        #[serde(skip_serializing_if = "Option::is_none")]
+        failure_reason: Option<String>,
+    },
 }
 
 /// Map a `MediaType` to the short label used by `IngestEvent::AssetStarted`.
@@ -96,6 +177,7 @@ pub fn media_label(media: &kebab_core::MediaType) -> &'static str {
         kebab_core::MediaType::Pdf => "pdf",
         kebab_core::MediaType::Image(_) => "image",
         kebab_core::MediaType::Audio(_) => "audio",
+        kebab_core::MediaType::Code(_) => "code",
         kebab_core::MediaType::Other(_) => "other",
     }
 }
@@ -117,10 +199,7 @@ pub fn render_skipped_breakdown(map: &std::collections::BTreeMap<String, u32>) -
 /// Best-effort send into an optional `mpsc::Sender`. A dropped receiver
 /// is silently absorbed — the ingest hot path must not stall on a slow
 /// consumer. Logged at `trace` for diagnostics.
-pub(crate) fn emit(
-    progress: Option<&std::sync::mpsc::Sender<IngestEvent>>,
-    event: IngestEvent,
-) {
+pub(crate) fn emit(progress: Option<&std::sync::mpsc::Sender<IngestEvent>>, event: IngestEvent) {
     if let Some(tx) = progress {
         if tx.send(event).is_err() {
             tracing::trace!(
@@ -148,6 +227,7 @@ mod tests {
             media_label(&MediaType::Audio(kebab_core::AudioType::Wav)),
             "audio"
         );
+        assert_eq!(media_label(&MediaType::Code("rust".into())), "code");
         assert_eq!(media_label(&MediaType::Other("x".into())), "other");
     }
 
@@ -163,13 +243,131 @@ mod tests {
             media: "markdown".into(),
         };
         let v = serde_json::to_value(&ev).unwrap();
-        assert_eq!(v.get("kind").and_then(|s| s.as_str()), Some("asset_started"));
-        assert_eq!(v.get("idx").and_then(|n| n.as_u64()), Some(1));
-        assert_eq!(v.get("total").and_then(|n| n.as_u64()), Some(10));
+        assert_eq!(
+            v.get("kind").and_then(|s| s.as_str()),
+            Some("asset_started")
+        );
+        assert_eq!(v.get("idx").and_then(serde_json::Value::as_u64), Some(1));
+        assert_eq!(v.get("total").and_then(serde_json::Value::as_u64), Some(10));
         assert_eq!(v.get("path").and_then(|s| s.as_str()), Some("notes/foo.md"));
         assert_eq!(v.get("media").and_then(|s| s.as_str()), Some("markdown"));
     }
 
+    #[test]
+    fn asset_chunked_serializes_with_discriminator() {
+        // v0.24.0 additive variant — `kind` must be snake_case
+        // `asset_chunked` so wire v1 consumers branch on it cleanly.
+        let ev = IngestEvent::AssetChunked {
+            idx: 3,
+            total: 10,
+            chunks: 142,
+        };
+        let v = serde_json::to_value(&ev).unwrap();
+        assert_eq!(
+            v.get("kind").and_then(|s| s.as_str()),
+            Some("asset_chunked")
+        );
+        assert_eq!(v.get("idx").and_then(serde_json::Value::as_u64), Some(3));
+        assert_eq!(
+            v.get("chunks").and_then(serde_json::Value::as_u64),
+            Some(142)
+        );
+    }
+
+    #[test]
+    fn asset_timings_serializes_all_phase_fields() {
+        let ev = IngestEvent::AssetTimings {
+            idx: 2,
+            total: 7,
+            parse_ms: 12,
+            chunk_ms: 3,
+            expansion_ms: 45_000,
+            embed_ms: 800,
+            store_ms: 20,
+            ocr_ms: 1_200,
+            caption_ms: 3_400,
+        };
+        let v = serde_json::to_value(&ev).unwrap();
+        assert_eq!(
+            v.get("kind").and_then(|s| s.as_str()),
+            Some("asset_timings")
+        );
+        // All phase fields are present (plain u64, always serialized).
+        for (field, want) in [
+            ("parse_ms", 12u64),
+            ("chunk_ms", 3),
+            ("expansion_ms", 45_000),
+            ("embed_ms", 800),
+            ("store_ms", 20),
+            ("ocr_ms", 1_200),
+            ("caption_ms", 3_400),
+        ] {
+            assert_eq!(
+                v.get(field).and_then(serde_json::Value::as_u64),
+                Some(want),
+                "field {field}"
+            );
+        }
+    }
+
+    #[test]
+    fn asset_timings_ocr_caption_default_to_zero_for_legacy_wire() {
+        // v0.26.1 additive: a pre-v0.26.1 wire payload omits ocr_ms /
+        // caption_ms; serde `default` must fill 0 so old producers stay
+        // compatible.
+        let legacy = serde_json::json!({
+            "kind": "asset_timings",
+            "idx": 1, "total": 1,
+            "parse_ms": 5, "chunk_ms": 2, "expansion_ms": 0,
+            "embed_ms": 10, "store_ms": 3
+        });
+        let ev: IngestEvent = serde_json::from_value(legacy).unwrap();
+        match ev {
+            IngestEvent::AssetTimings {
+                ocr_ms,
+                caption_ms,
+                embed_ms,
+                ..
+            } => {
+                assert_eq!(ocr_ms, 0);
+                assert_eq!(caption_ms, 0);
+                assert_eq!(embed_ms, 10);
+            }
+            other => panic!("unexpected event: {other:?}"),
+        }
+    }
+
+    #[test]
+    fn asset_phase_serializes_with_discriminator() {
+        // v0.26.1 additive variant — `kind` must be snake_case
+        // `asset_phase`, `phase` is the slow-phase label, `model` the
+        // model id (nullable).
+        let ev = IngestEvent::AssetPhase {
+            idx: 4,
+            total: 12,
+            phase: "ocr".into(),
+            model: Some("gemma4:e4b".into()),
+        };
+        let v = serde_json::to_value(&ev).unwrap();
+        assert_eq!(v.get("kind").and_then(|s| s.as_str()), Some("asset_phase"));
+        assert_eq!(v.get("idx").and_then(serde_json::Value::as_u64), Some(4));
+        assert_eq!(v.get("phase").and_then(|s| s.as_str()), Some("ocr"));
+        assert_eq!(v.get("model").and_then(|s| s.as_str()), Some("gemma4:e4b"));
+    }
+
+    #[test]
+    fn asset_phase_model_none_serializes_as_null() {
+        let ev = IngestEvent::AssetPhase {
+            idx: 1,
+            total: 1,
+            phase: "embed".into(),
+            model: None,
+        };
+        let v = serde_json::to_value(&ev).unwrap();
+        assert_eq!(v.get("phase").and_then(|s| s.as_str()), Some("embed"));
+        assert!(v.get("model").is_some_and(serde_json::Value::is_null));
+    }
+
     #[test]
     fn ingest_event_completed_has_counts() {
         let ev = IngestEvent::Completed {
@@ -182,8 +380,14 @@ mod tests {
         let v = serde_json::to_value(&ev).unwrap();
         assert_eq!(v.get("kind").and_then(|s| s.as_str()), Some("completed"));
         let counts = v.get("counts").unwrap();
-        assert_eq!(counts.get("scanned").and_then(|n| n.as_u64()), Some(5));
-        assert_eq!(counts.get("new").and_then(|n| n.as_u64()), Some(2));
+        assert_eq!(
+            counts.get("scanned").and_then(serde_json::Value::as_u64),
+            Some(5)
+        );
+        assert_eq!(
+            counts.get("new").and_then(serde_json::Value::as_u64),
+            Some(2)
+        );
     }
 
     #[test]

crates/kebab-app/src/logging.rs

@@ -26,7 +26,9 @@ pub fn init(level: LogLevel) -> Result<WorkerGuard> {
     let (nb, guard) = tracing_appender::non_blocking(file_appender);
 
     let env_filter = match level {
-        LogLevel::Default => EnvFilter::try_from_default_env().unwrap_or_else(|_| EnvFilter::new("warn")),
+        LogLevel::Default => {
+            EnvFilter::try_from_default_env().unwrap_or_else(|_| EnvFilter::new("warn"))
+        }
         LogLevel::Verbose => EnvFilter::new("info"),
         LogLevel::Debug => EnvFilter::new("debug"),
     };

crates/kebab-app/src/pdf_ocr_apply.rs

@@ -0,0 +1,362 @@
+// crates/kebab-app/src/pdf_ocr_apply.rs
+//
+// PDF post-extract OCR enrichment. parser isolation 보존 — kebab-parse-pdf 가
+// kebab-parse-image::OcrEngine 을 import 하지 않도록, helper 는 kebab-app 에 둠.
+// image path 의 apply_ocr (kebab-parse-image::ocr::apply_ocr) 의
+// PDF page 변형 — image 는 ImageRefBlock.ocr 를 mutate, PDF 는
+// Block::Paragraph.text / inlines 를 in-place mutate (단일 OCR fallback) 또는
+// 새 Block::Paragraph 를 push (always_on dual-block).
+
+use std::sync::Arc;
+use std::sync::atomic::AtomicBool;
+use std::time::Instant;
+
+use anyhow::{Context, Result};
+use kebab_core::{
+    Block, CanonicalDocument, CommonBlock, Inline, Lang, ProvenanceEvent, ProvenanceKind,
+    SourceSpan, TextBlock, id_for_block,
+};
+use kebab_parse_image::OcrEngine;
+use kebab_parse_pdf::{compute_valid_char_ratio, extract_dctdecode_page_image};
+use lopdf::Document as LopdfDocument;
+use time::OffsetDateTime;
+use tracing::warn;
+
+/// Extract width/height from a JPEG (or any image format) byte slice.
+/// Returns `None` on corrupt / unsupported data — callers fall back to
+/// `(None, None)` so OCR results remain valid (R-4 mitigation).
+fn extract_image_dimensions(bytes: &[u8]) -> Option<(u32, u32)> {
+    use image::ImageReader;
+    ImageReader::new(std::io::Cursor::new(bytes))
+        .with_guessed_format()
+        .ok()?
+        .into_dimensions()
+        .ok()
+}
+
+/// Per-page OCR knobs threaded through [`apply_ocr_to_pdf_pages`].
+/// Mirrors the `[pdf.ocr]` config block (spec §4.5); the facade
+/// (`kebab_app::ingest_one_pdf_asset`) fills these from
+/// `kebab_config::Config::pdf::ocr` plus runtime flags (CLI / SIGINT).
+pub struct PdfOcrOpts {
+    /// Master switch. `false` short-circuits to
+    /// `PdfOcrSummary { pages_ocrd: 0, ms_total: 0 }` without lopdf reparse.
+    pub enabled: bool,
+    /// `true` → 모든 page OCR (dual-block path, new `Block::Paragraph` push).
+    /// `false` → text-detect block 의 `min_char_count` 또는
+    /// `valid_ratio_threshold` 미달인 page 만 OCR (in-place mutate).
+    pub always_on: bool,
+    /// 0.0..=1.0. text-detect block 의 `compute_valid_char_ratio` 가
+    /// 본 임계 미만이면 OCR fallback. Default `0.5`.
+    pub valid_ratio_threshold: f32,
+    /// text-detect block 의 char count 가 본 임계 미만이면 OCR fallback.
+    /// empty page (cover, blank separator) 자동 skip. Default `20`.
+    pub min_char_count: u32,
+    /// OCR engine 에 전달할 언어 힌트 (예: `Lang("kor".into())`).
+    /// `None` → no hint passed to engine.
+    pub lang_hint: Option<Lang>,
+    /// Optional per-page cancellation handle. checked at start of each page
+    /// loop iteration; set→true 시 `cancelled mid-PDF` error 반환. plan §6 E4
+    /// + verifier LOW L-1 resolution + spec §4.8 line 1159 명시.
+    pub cancel: Option<Arc<AtomicBool>>,
+}
+
+/// OCR run summary returned by [`apply_ocr_to_pdf_pages`] for the caller's
+/// `IngestItem.pdf_ocr_pages` + `pdf_ocr_ms_total` wire fields (§4.6.2).
+#[derive(Debug)]
+pub struct PdfOcrSummary {
+    /// Number of pages 가 OCR pipeline 을 실제 통과 (skipped page 제외).
+    pub pages_ocrd: u32,
+    /// Cumulative wall-clock duration of successful OCR engine calls (ms).
+    /// `saturating_add` 사용 — 24-day cumulative 까지 overflow-safe.
+    pub ms_total: u64,
+}
+
+/// Post-extract OCR enrichment for PDF. Walks `canonical.blocks` page-by-page,
+/// classifies each page via `text_quality::compute_valid_char_ratio` +
+/// `min_char_count`, and either:
+/// - skips (vector PDF + sufficient text + `always_on=false`),
+/// - mutates the text-detect `Block::Paragraph` in-place with OCR output
+///   (scanned/mojibake page), or
+/// - pushes a new `Block::Paragraph` with dual ordinal (`always_on=true` +
+///   vector page).
+///
+/// Errors:
+/// - cancel handle (`opts.cancel = Some(true)`) → `Err("PDF OCR cancelled mid-PDF at page N")`.
+/// - lopdf re-parse failure → `Err(...)`.
+/// - per-page OCR engine failure 또는 DCTDecode 부재 → `ProvenanceKind::Warning`
+///   event push + `emit_progress(Finished { skipped: true })` + continue
+///   (no `Err` propagation).
+///
+/// See spec §4.1 + §4.4 for the full pipeline.
+pub fn apply_ocr_to_pdf_pages<F>(
+    canonical: &mut CanonicalDocument,
+    engine: &dyn OcrEngine,
+    pdf_bytes: &[u8],
+    opts: &PdfOcrOpts,
+    mut emit_progress: F,
+) -> Result<PdfOcrSummary>
+where
+    F: FnMut(PdfOcrProgress),
+{
+    if !opts.enabled {
+        return Ok(PdfOcrSummary {
+            pages_ocrd: 0,
+            ms_total: 0,
+        });
+    }
+    let pdf_doc = LopdfDocument::load_mem(pdf_bytes)
+        .context("kb-app::pdf_ocr_apply: re-parse PDF for image extract")?;
+    let page_count = pdf_doc.get_pages().len() as u32;
+
+    let mut new_events: Vec<ProvenanceEvent> = Vec::new();
+    let mut ocr_blocks: Vec<Block> = Vec::new();
+    let mut pages_ocrd: u32 = 0;
+    let mut ms_total: u64 = 0;
+
+    // canonical.blocks 의 page → block index map (text-detect block 의 in-place
+    // mutate 또는 dual-block push 결정용).
+    // PdfTextExtractor 가 page 마다 1 Block::Paragraph + SourceSpan::Page 를
+    // 생성 (§1.4) — 그 invariant 사용.
+    for page_num in 1..=page_count {
+        if let Some(cancel) = &opts.cancel {
+            if cancel.load(std::sync::atomic::Ordering::Relaxed) {
+                anyhow::bail!("PDF OCR cancelled mid-PDF at page {page_num}");
+            }
+        }
+
+        let text_block_idx = find_paragraph_block_idx(&canonical.blocks, page_num);
+        let text = match &canonical.blocks[text_block_idx] {
+            Block::Paragraph(tb) => tb.text.clone(),
+            _ => String::new(),
+        };
+        let chars = text.chars().count() as u32;
+        let valid_ratio = compute_valid_char_ratio(&text);
+        let needs_ocr = chars < opts.min_char_count || valid_ratio < opts.valid_ratio_threshold;
+
+        // 결정 matrix:
+        //   always_on=true → 모든 page OCR (dual-block).
+        //   always_on=false + needs_ocr → in-place OCR (text-detect block mutate).
+        //   needs_ocr=false → skip.
+        let do_ocr = opts.always_on || needs_ocr;
+        if !do_ocr {
+            continue;
+        }
+
+        emit_progress(PdfOcrProgress::Started { page: page_num });
+
+        let page_image_bytes = if let Some(b) = extract_dctdecode_page_image(&pdf_doc, page_num)? {
+            b
+        } else {
+            let note = format!(
+                "page={page_num} skipped: no DCTDecode image XObject (vector PDF page or unsupported /Filter — v1 supports DCTDecode passthrough only; see release notes for normalization guidance)"
+            );
+            warn!(target: "kebab-app", "{}", note);
+            new_events.push(ProvenanceEvent {
+                at: OffsetDateTime::now_utc(),
+                agent: "kb-parse-pdf".to_string(),
+                kind: ProvenanceKind::Warning,
+                note: Some(note),
+            });
+            emit_progress(PdfOcrProgress::Finished {
+                page: page_num,
+                ms: 0,
+                chars: 0,
+                skipped: true,
+                image_byte_size: None,
+                image_width: None,
+                image_height: None,
+                failure_reason: None,
+            });
+            continue;
+        };
+
+        let start = Instant::now();
+        let ocr = match engine.recognize(&page_image_bytes, opts.lang_hint.as_ref()) {
+            Ok(t) => t,
+            Err(e) => {
+                // OCR failure: warning event + skip (text-detect block 그대로).
+                let note = format!(
+                    "page={} OCR failed engine={} version={} err={}",
+                    page_num,
+                    engine.engine_name(),
+                    engine.engine_version(),
+                    e
+                );
+                warn!(target: "kebab-app", "{}", note);
+                new_events.push(ProvenanceEvent {
+                    at: OffsetDateTime::now_utc(),
+                    agent: "kb-parse-pdf".to_string(),
+                    kind: ProvenanceKind::Warning,
+                    note: Some(note),
+                });
+                let (image_width, image_height) = extract_image_dimensions(&page_image_bytes)
+                    .map_or((None, None), |(w, h)| (Some(w), Some(h)));
+                emit_progress(PdfOcrProgress::Finished {
+                    page: page_num,
+                    ms: start.elapsed().as_millis() as u64,
+                    chars: 0,
+                    skipped: true,
+                    image_byte_size: Some(page_image_bytes.len() as u64),
+                    image_width,
+                    image_height,
+                    failure_reason: Some("ocr_error".to_string()),
+                });
+                continue;
+            }
+        };
+        let elapsed_ms = start.elapsed().as_millis() as u64;
+        let chars_ocr = ocr.joined.chars().count() as u32;
+
+        pages_ocrd = pages_ocrd.saturating_add(1);
+        ms_total = ms_total.saturating_add(elapsed_ms);
+
+        if opts.always_on && !needs_ocr {
+            // dual-block path: 새 Block::Paragraph push, ordinal = page-1 + page_count.
+            let ocr_ordinal = (page_num - 1) + page_count;
+            let span_ocr = SourceSpan::Page {
+                page: page_num,
+                char_start: Some(0),
+                char_end: Some(chars_ocr),
+            };
+            let block_id =
+                id_for_block(&canonical.doc_id, "paragraph", &[], ocr_ordinal, &span_ocr);
+            let common = CommonBlock {
+                block_id,
+                heading_path: Vec::new(),
+                source_span: span_ocr,
+            };
+            ocr_blocks.push(Block::Paragraph(TextBlock {
+                common,
+                text: ocr.joined.clone(),
+                inlines: if ocr.joined.is_empty() {
+                    Vec::new()
+                } else {
+                    vec![Inline::Text {
+                        text: ocr.joined.clone(),
+                    }]
+                },
+            }));
+        } else {
+            // in-place mutate: text-detect block (빈 또는 low-valid) 의 text/inlines 교체.
+            // block_id / ordinal 보존 — span 의 char_end 만 갱신.
+            if let Block::Paragraph(tb) = &mut canonical.blocks[text_block_idx] {
+                tb.text = ocr.joined.clone();
+                tb.inlines = if ocr.joined.is_empty() {
+                    Vec::new()
+                } else {
+                    vec![Inline::Text {
+                        text: ocr.joined.clone(),
+                    }]
+                };
+                if let SourceSpan::Page { char_end, .. } = &mut tb.common.source_span {
+                    *char_end = Some(chars_ocr);
+                }
+            }
+        }
+
+        new_events.push(ProvenanceEvent {
+            at: OffsetDateTime::now_utc(),
+            agent: "kb-parse-pdf".to_string(),
+            kind: ProvenanceKind::OcrApplied,
+            note: Some(format!(
+                "page={} engine={} version={} regions={} ms={} chars={}",
+                page_num,
+                engine.engine_name(),
+                engine.engine_version(),
+                ocr.regions.len(),
+                elapsed_ms,
+                chars_ocr
+            )),
+        });
+
+        let (image_width, image_height) = extract_image_dimensions(&page_image_bytes)
+            .map_or((None, None), |(w, h)| (Some(w), Some(h)));
+        emit_progress(PdfOcrProgress::Finished {
+            page: page_num,
+            ms: elapsed_ms,
+            chars: chars_ocr,
+            skipped: false,
+            image_byte_size: Some(page_image_bytes.len() as u64),
+            image_width,
+            image_height,
+            failure_reason: None,
+        });
+    }
+
+    canonical.blocks.extend(ocr_blocks);
+    canonical.provenance.events.extend(new_events);
+    Ok(PdfOcrSummary {
+        pages_ocrd,
+        ms_total,
+    })
+}
+
+fn find_paragraph_block_idx(blocks: &[Block], page_num: u32) -> usize {
+    blocks
+        .iter()
+        .position(|b| match b {
+            Block::Paragraph(tb) => matches!(
+                tb.common.source_span,
+                SourceSpan::Page { page, .. } if page == page_num
+            ),
+            _ => false,
+        })
+        .expect("PdfTextExtractor emits 1 Block::Paragraph per page (invariant)")
+}
+
+/// Per-page OCR progress event 가 caller 의 `emit_progress` closure 호출 시 emit.
+/// Step 6 의 ingest_one_pdf_asset 가 IngestEvent::PdfOcrStarted / PdfOcrFinished
+/// 로 carry (spec §4.6.1 wire schema).
+pub enum PdfOcrProgress {
+    /// page 별 OCR 시작 시 emit. `engine.recognize` 호출 직전.
+    Started {
+        /// 1-based PDF page number.
+        page: u32,
+    },
+    /// page 별 OCR 종료 시 emit (성공 / skip / failure 모두).
+    Finished {
+        /// 1-based PDF page number.
+        page: u32,
+        /// `engine.recognize` wall-clock duration. skip path 의 의미는 mixed
+        /// (DCTDecode 부재 시 `0`, OCR engine 실패 시 actual latency before bail).
+        ms: u64,
+        /// OCR result text 의 char count. skip 시 `0`.
+        chars: u32,
+        /// `true` = DCTDecode 부재 또는 OCR engine 실패 로 skip.
+        /// `false` = 정상 OCR 완료.
+        skipped: bool,
+        /// v0.20.x ingest log: raster image byte size (additive, optional).
+        image_byte_size: Option<u64>,
+        /// v0.20.x ingest log: raster image width in pixels (additive, optional).
+        image_width: Option<u32>,
+        /// v0.20.x ingest log: raster image height in pixels (additive, optional).
+        image_height: Option<u32>,
+        /// v0.20.x ingest log: failure reason string when OCR failed (additive, optional).
+        /// Values: "timeout" | "ocr_error" | "network_error" | None (success).
+        failure_reason: Option<String>,
+    },
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn extract_image_dimensions_valid_jpeg() {
+        let img = image::RgbImage::new(16, 12);
+        let mut bytes = Vec::new();
+        image::DynamicImage::from(img)
+            .write_to(
+                &mut std::io::Cursor::new(&mut bytes),
+                image::ImageFormat::Jpeg,
+            )
+            .expect("encode jpeg");
+        assert_eq!(extract_image_dimensions(&bytes), Some((16, 12)));
+    }
+
+    #[test]
+    fn extract_image_dimensions_corrupt_returns_none() {
+        assert_eq!(extract_image_dimensions(b"not a jpeg"), None);
+    }
+}

crates/kebab-app/src/reset.rs

@@ -9,13 +9,19 @@
 //!
 //! `--vector-only` additionally truncates `embedding_records` in SQLite
 //! so the next `kebab ingest` re-embeds cleanly without orphan rows.
+//!
+//! `--orphans-only` purges stored docs that are outside the current walker
+//! scope (config narrowing / removed sub-directory). No filesystem paths are
+//! removed — this is purely a store-level reconciliation.
 
+use std::collections::HashSet;
 use std::path::PathBuf;
 
 use anyhow::{Context, Result};
 use serde::{Deserialize, Serialize};
 
 use kebab_config::{Config, expand_path};
+use kebab_core::WorkspacePath;
 
 /// What the user asked to remove. Mutually exclusive — picked by the CLI
 /// from a clap `ArgGroup`.
@@ -32,6 +38,13 @@ pub enum ResetScope {
     VectorOnly,
     /// Wipe only the config dir.
     ConfigOnly,
+    /// Purge stored docs that are outside the current walker scope (no
+    /// filesystem paths are removed). Filesystem existence is NOT checked —
+    /// anything the current walker would not visit is considered an orphan.
+    /// The explicit complement to the conservative `sweep_deleted_files`
+    /// that runs during ingest (which leaves on-disk-but-out-of-scope docs
+    /// alone for data safety).
+    OrphansOnly,
 }
 
 /// Result of a successful wipe — emitted as `reset_report.v1` by the
@@ -41,6 +54,16 @@ pub struct ResetReport {
     pub scope: ResetScope,
     pub removed_paths: Vec<PathBuf>,
     pub embedding_rows_truncated: u64,
+    /// Number of stored docs purged because they are outside the current
+    /// walker scope. Non-zero only when `scope == OrphansOnly`.
+    /// `#[serde(default)]` preserves back-compat with older callers that
+    /// do not include this field.
+    #[serde(default)]
+    pub orphans_purged: u32,
+    /// Paths of the orphaned docs that were purged. Sorted for deterministic
+    /// output. Non-empty only when `scope == OrphansOnly`.
+    #[serde(default)]
+    pub purged_paths: Vec<WorkspacePath>,
 }
 
 /// Compute the absolute on-disk paths a given scope will wipe, given a
@@ -62,11 +85,14 @@ pub fn enumerate_paths(scope: ResetScope, cfg: &Config) -> Vec<PathBuf> {
         ResetScope::All => vec![cfg_dir, data_dir, cache_dir, state_dir],
         ResetScope::DataOnly => vec![data_dir, cache_dir, state_dir],
         ResetScope::VectorOnly => {
-            let vector_dir =
-                expand_path(&cfg.storage.vector_dir, &data_dir.to_string_lossy());
+            let vector_dir = expand_path(&cfg.storage.vector_dir, &data_dir.to_string_lossy());
             vec![vector_dir]
         }
         ResetScope::ConfigOnly => vec![cfg_dir],
+        // OrphansOnly operates purely at the store level — no filesystem paths
+        // are removed. Return empty so `estimate_size_bytes` stays zero and
+        // the existing confirm UI path for directory wipes is skipped.
+        ResetScope::OrphansOnly => vec![],
     }
 }
 
@@ -96,16 +122,79 @@ pub fn estimate_size_bytes(paths: &[PathBuf]) -> u64 {
     paths.iter().map(|p| walk(p)).sum()
 }
 
+/// Compute the workspace paths stored in SQLite that are NOT visited by
+/// the current walker scope (i.e. they are "orphans" — on disk but
+/// outside the configured include/exclude rules, or from a sub-directory
+/// that has since been removed from the workspace).
+///
+/// Does NOT check filesystem existence — `OrphansOnly` is the explicit
+/// "I know what I'm doing" variant; callers that want the conservative
+/// fs-aware sweep should use `sweep_deleted_files` inside ingest.
+///
+/// Returns the list sorted for deterministic output. Called twice by the
+/// CLI path (once for the confirm UI preview, once inside `execute`);
+/// the double scan is acceptable for a rare destructive operation.
+pub fn enumerate_orphans(cfg: &Config) -> Result<Vec<WorkspacePath>> {
+    use kebab_core::DocumentStore as _;
+    use kebab_core::SourceScope;
+    use kebab_source_fs::FsSourceConnector;
+
+    let store = kebab_store_sqlite::SqliteStore::open(cfg)
+        .context("enumerate_orphans: open SqliteStore")?;
+
+    let stored = store
+        .all_workspace_paths()
+        .context("enumerate_orphans: all_workspace_paths")?;
+
+    if stored.is_empty() {
+        return Ok(Vec::new());
+    }
+
+    // Build the same SourceScope the CLI's ingest path uses: root from
+    // config, exclude list from config, no include override (full scope).
+    let root = cfg.resolve_workspace_root();
+    let scope = SourceScope {
+        root: root.clone(),
+        exclude: cfg.workspace.exclude.clone(),
+        ..Default::default()
+    };
+
+    let connector =
+        FsSourceConnector::new(cfg).context("enumerate_orphans: build FsSourceConnector")?;
+    let (assets, _skips) = connector
+        .scan_with_skips(&scope)
+        .context("enumerate_orphans: scan workspace")?;
+
+    let scanned: HashSet<WorkspacePath> = assets.into_iter().map(|a| a.workspace_path).collect();
+
+    let mut orphans: Vec<WorkspacePath> = stored
+        .into_iter()
+        .filter(|p| !scanned.contains(p))
+        .collect();
+    orphans.sort_by(|a, b| a.0.cmp(&b.0));
+    Ok(orphans)
+}
+
 /// Wipe every path from `enumerate_paths(scope, cfg)`. For
 /// `ResetScope::VectorOnly`, also truncates the SQLite
 /// `embedding_records` table so the store doesn't point at the Lance
 /// rows we just removed off-disk.
 ///
+/// For `ResetScope::OrphansOnly`, no filesystem directories are removed.
+/// Instead the store is reconciled: stored docs outside the current walker
+/// scope are purged from SQLite (+ vector store when configured). The
+/// caller is expected to have already shown the confirm UI using
+/// `enumerate_orphans`.
+///
 /// Idempotent: a missing path is treated as already-removed (success).
 /// Returns a `ResetReport` listing exactly what was removed (paths that
 /// existed before the call) so `--json` callers see the truth, not the
 /// request.
 pub fn execute(scope: ResetScope, cfg: &Config) -> Result<ResetReport> {
+    if matches!(scope, ResetScope::OrphansOnly) {
+        return execute_orphans_only(cfg);
+    }
+
     let paths = enumerate_paths(scope, cfg);
     let mut removed = Vec::new();
 
@@ -113,8 +202,7 @@ pub fn execute(scope: ResetScope, cfg: &Config) -> Result<ResetReport> {
         if !p.exists() {
             continue;
         }
-        std::fs::remove_dir_all(p)
-            .with_context(|| format!("remove {}", p.display()))?;
+        std::fs::remove_dir_all(p).with_context(|| format!("remove {}", p.display()))?;
         removed.push(p.clone());
     }
 
@@ -128,9 +216,99 @@ pub fn execute(scope: ResetScope, cfg: &Config) -> Result<ResetReport> {
         scope,
         removed_paths: removed,
         embedding_rows_truncated,
+        orphans_purged: 0,
+        purged_paths: Vec::new(),
     })
 }
 
+/// Execute the `OrphansOnly` variant: reconcile stored docs against the
+/// current walker scope without touching any filesystem directory.
+fn execute_orphans_only(cfg: &Config) -> Result<ResetReport> {
+    let orphans = enumerate_orphans(cfg).context("execute_orphans_only: enumerate orphans")?;
+
+    if orphans.is_empty() {
+        return Ok(ResetReport {
+            scope: ResetScope::OrphansOnly,
+            removed_paths: Vec::new(),
+            embedding_rows_truncated: 0,
+            orphans_purged: 0,
+            purged_paths: Vec::new(),
+        });
+    }
+
+    let store = std::sync::Arc::new(
+        kebab_store_sqlite::SqliteStore::open(cfg)
+            .context("execute_orphans_only: open SqliteStore")?,
+    );
+
+    // Open vector store if configured. Mirror the same guard the ingest
+    // path uses: only construct when the provider is not "none" / dims > 0.
+    let vector_store: Option<kebab_store_vector::LanceVectorStore> =
+        open_vector_store_if_configured(cfg, store.clone())?;
+
+    let mut purged_paths: Vec<WorkspacePath> = Vec::new();
+
+    for path in &orphans {
+        let chunk_ids = kebab_store_sqlite::purge_deleted_workspace_path(&store, path)
+            .with_context(|| format!("execute_orphans_only: purge {}", path.0))?;
+
+        if let Some(ref vs) = vector_store {
+            if !chunk_ids.is_empty() {
+                use kebab_core::VectorStore as _;
+                if let Err(e) = vs.delete_by_chunk_ids(&chunk_ids) {
+                    tracing::warn!(
+                        target: "kebab-app",
+                        path = %path.0,
+                        count = chunk_ids.len(),
+                        error = %e,
+                        "reset --orphans-only: vector delete failed; SQLite side already cleaned"
+                    );
+                }
+            }
+        }
+
+        tracing::info!(
+            target: "kebab-app",
+            path = %path.0,
+            "reset --orphans-only: purged orphan document"
+        );
+        purged_paths.push(path.clone());
+    }
+
+    let orphans_purged = u32::try_from(purged_paths.len()).unwrap_or(u32::MAX);
+
+    Ok(ResetReport {
+        scope: ResetScope::OrphansOnly,
+        removed_paths: Vec::new(),
+        embedding_rows_truncated: 0,
+        orphans_purged,
+        purged_paths,
+    })
+}
+
+/// Open the Lance vector store if the configured embedding provider is
+/// active (non-"none", dimensions > 0). Returns `None` for lexical-only
+/// configs. Mirrors the guard in `App::vector`.
+fn open_vector_store_if_configured(
+    cfg: &Config,
+    store: std::sync::Arc<kebab_store_sqlite::SqliteStore>,
+) -> Result<Option<kebab_store_vector::LanceVectorStore>> {
+    if cfg.models.embedding.provider == "none" || cfg.models.embedding.dimensions == 0 {
+        return Ok(None);
+    }
+    match kebab_store_vector::LanceVectorStore::new(cfg, store) {
+        Ok(vs) => Ok(Some(vs)),
+        Err(e) => {
+            tracing::warn!(
+                target: "kebab-app",
+                error = %e,
+                "reset --orphans-only: could not open vector store; skipping vector delete"
+            );
+            Ok(None)
+        }
+    }
+}
+
 /// Open the SQLite store at the configured path and run
 /// `truncate_embedding_records`. Returns the count of truncated rows
 /// (the helper itself reports `DELETE` rowcount). If the SQLite file
@@ -200,4 +378,14 @@ mod tests {
         let bytes = estimate_size_bytes(&[dir.path().to_path_buf()]);
         assert_eq!(bytes, 5 + 6);
     }
+
+    #[test]
+    fn enumerate_orphans_only_returns_empty_paths() {
+        let cfg = Config::defaults();
+        let paths = enumerate_paths(ResetScope::OrphansOnly, &cfg);
+        assert!(
+            paths.is_empty(),
+            "OrphansOnly must return empty vec from enumerate_paths"
+        );
+    }
 }

crates/kebab-app/src/schema.rs

@@ -32,24 +32,65 @@ pub struct Capabilities {
     pub http_daemon: bool,
     pub mcp_server: bool,
     pub single_file_ingest: bool,
+    pub bulk_search: bool,
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct Models {
     pub parser_version: String,
     pub chunker_version: String,
+    /// v0.20.1+ (Bug #13). Corpus 안 활성 parser version 전체.
+    /// 빈 corpus → empty Vec. backward compat: `parser_version` field 보존.
+    #[serde(default)]
+    pub active_parsers: Vec<String>,
+    /// v0.20.1+ (Bug #13). Corpus 안 활성 chunker version 전체.
+    /// 빈 corpus → empty Vec.
+    #[serde(default)]
+    pub active_chunkers: Vec<String>,
     pub embedding_version: String,
     pub prompt_template_version: String,
     pub index_version: String,
     pub corpus_revision: u64,
 }
 
-#[derive(Debug, Clone, Serialize, Deserialize)]
+#[derive(Debug, Clone, Default, Serialize, Deserialize)]
 pub struct Stats {
     pub doc_count: u64,
     pub chunk_count: u64,
     pub asset_count: u64,
     pub last_ingest_at: Option<String>,
+    /// p9-fb-37: per-media-kind doc count (5 keys, zero-padded).
+    #[serde(default)]
+    pub media_breakdown: std::collections::BTreeMap<String, u64>,
+    /// p9-fb-37: per-language doc count, NULL keyed as `"null"`.
+    #[serde(default)]
+    pub lang_breakdown: std::collections::BTreeMap<String, u64>,
+    /// p9-fb-37: on-disk byte sums.
+    #[serde(default)]
+    pub index_bytes: kebab_core::IndexBytes,
+    /// p9-fb-37: docs whose `updated_at` exceeds the staleness threshold.
+    #[serde(default)]
+    pub stale_doc_count: u64,
+    /// 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 (**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");
@@ -63,15 +104,22 @@ pub const SCHEMA_V1_ID: &str = "schema.v1";
 const WIRE_SCHEMAS: &[&str] = &[
     "answer.v1",
     "search_hit.v1",
+    "search_response.v1",
     "doc_summary.v1",
     "chunk_inspection.v1",
     "doctor.v1",
+    "config_migration.v1",
     "ingest_report.v1",
     "ingest_progress.v1",
     "reset_report.v1",
     "citation.v1",
     "schema.v1",
     "error.v1",
+    "bulk_search_item.v1",
+    "bulk_search_response.v1",
+    // v0.20.x r2 Enhancement 3: OCR statistics + failures introspection.
+    "ocr_stats.v1",
+    "ocr_failures.v1",
 ];
 
 /// Build a [`SchemaV1`] introspection report for the given config.
@@ -84,7 +132,7 @@ const WIRE_SCHEMAS: &[&str] = &[
 #[doc(hidden)]
 pub fn schema_with_config(cfg: &Config) -> anyhow::Result<SchemaV1> {
     let store = open_store_for_stats(cfg)?;
-    let stats = collect_stats(&store)?;
+    let stats = collect_stats(cfg, &store)?;
     let models = collect_models(cfg, &store);
     Ok(SchemaV1 {
         schema_version: SCHEMA_V1_ID.to_string(),
@@ -106,10 +154,11 @@ fn capabilities_snapshot() -> Capabilities {
         rag_multi_turn: true,
         search_cache: true,
         incremental_ingest: true,
-        streaming_ask: false,
+        streaming_ask: true,
         http_daemon: false,
-        mcp_server: false,
-        single_file_ingest: false,
+        mcp_server: true,
+        single_file_ingest: true,
+        bulk_search: true,
     }
 }
 
@@ -123,23 +172,42 @@ fn open_store_for_stats(cfg: &Config) -> anyhow::Result<kebab_store_sqlite::Sqli
     kebab_store_sqlite::SqliteStore::open_existing(&db_path)
 }
 
-fn collect_stats(store: &kebab_store_sqlite::SqliteStore) -> anyhow::Result<Stats> {
-    let counts = store.count_summary()?;
+fn collect_stats(cfg: &Config, store: &kebab_store_sqlite::SqliteStore) -> anyhow::Result<Stats> {
+    let counts = store.count_summary_with_threshold(u64::from(cfg.search.stale_threshold_days))?;
+    let data_dir = kebab_config::expand_path(&cfg.storage.data_dir, "");
+    let index_bytes = kebab_store_sqlite::stats_ext::index_bytes(&data_dir)
+        .map_err(|e| anyhow::anyhow!("index_bytes: {e}"))?;
     Ok(Stats {
         doc_count: counts.doc_count,
         chunk_count: counts.chunk_count,
         asset_count: counts.asset_count,
         last_ingest_at: counts.last_ingest_at,
+        media_breakdown: counts.media_breakdown,
+        lang_breakdown: counts.lang_breakdown,
+        index_bytes,
+        stale_doc_count: counts.stale_doc_count,
+        // p10-1A-2: populated by the store query added in this task.
+        code_lang_breakdown: store.code_lang_breakdown()?,
+        // 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()?,
     })
 }
 
 fn collect_models(cfg: &Config, store: &kebab_store_sqlite::SqliteStore) -> Models {
+    let active_parsers = store.fetch_distinct_parser_versions().unwrap_or_default();
+    let active_chunkers = store.fetch_distinct_chunker_versions().unwrap_or_default();
     Models {
         // markdown parser only — pdf-page-v1 (P7) / image extractors (P6)
         // maintain their own versions; surface those when SchemaV1.models
         // becomes a multi-medium map (P+).
         parser_version: kebab_parse_md::PARSER_VERSION.to_string(),
         chunker_version: cfg.chunking.chunker_version.clone(),
+        active_parsers,
+        active_chunkers,
         // EmbeddingModelCfg uses `.model` (not `.id`) — adapt from plan.
         embedding_version: cfg.models.embedding.model.clone(),
         prompt_template_version: cfg.rag.prompt_template_version.clone(),
@@ -149,3 +217,90 @@ fn collect_models(cfg: &Config, store: &kebab_store_sqlite::SqliteStore) -> Mode
         corpus_revision: store.corpus_revision(),
     }
 }
+
+#[cfg(test)]
+mod tests_stats_ext {
+    use super::*;
+
+    /// p10-1A-1: Stats must serialize `code_lang_breakdown` and
+    /// `repo_breakdown` so downstream consumers (MCP skill, Claude Code)
+    /// can branch on their presence.
+    #[test]
+    fn stats_includes_code_lang_and_repo_breakdown_fields() {
+        let stats = Stats::default();
+        let v = serde_json::to_value(&stats).unwrap();
+        assert!(
+            v.get("code_lang_breakdown").is_some(),
+            "Stats JSON must include code_lang_breakdown: {v}"
+        );
+        assert!(
+            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(),
+            "code_lang_breakdown must be an object: {v}"
+        );
+        assert!(
+            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]
+    fn stats_includes_breakdowns_and_bytes_on_fresh_corpus() {
+        let dir = tempfile::tempdir().unwrap();
+        let mut cfg = kebab_config::Config::defaults();
+        cfg.storage.data_dir = dir.path().to_string_lossy().into_owned();
+        // Bring up migrations so the sqlite file is created.
+        let store = kebab_store_sqlite::SqliteStore::open(&cfg).unwrap();
+        store.run_migrations().unwrap();
+        drop(store);
+
+        let s = schema_with_config(&cfg).unwrap();
+        // 5 keys padded.
+        assert_eq!(s.stats.media_breakdown.len(), 5);
+        assert_eq!(s.stats.media_breakdown.get("markdown"), Some(&0));
+        assert_eq!(s.stats.media_breakdown.get("pdf"), Some(&0));
+        // lang map empty on empty corpus.
+        assert!(s.stats.lang_breakdown.is_empty());
+        // sqlite bytes positive after migrations, lancedb 0.
+        assert!(s.stats.index_bytes.sqlite > 0);
+        assert_eq!(s.stats.index_bytes.lancedb, 0);
+        assert_eq!(s.stats.stale_doc_count, 0);
+    }
+}
+
+#[cfg(test)]
+mod tests_capabilities {
+    use super::*;
+
+    #[test]
+    fn capabilities_streaming_ask_matches_cli_surface() {
+        // Bug #9: kebab ask --stream 가 answer_event.v1 ndjson 191 event 정상 emit →
+        // capabilities.streaming_ask 가 true 여야 함.
+        let caps = capabilities_snapshot();
+        assert!(caps.streaming_ask, "streaming_ask must be true (Bug #9)");
+    }
+
+    #[test]
+    fn capabilities_single_file_ingest_matches_cli_surface() {
+        // Bug #9: kebab ingest-file <path> + kebab ingest-stdin --title <T> 양쪽 모두
+        // ingest_report.v1 정상 emit → capabilities.single_file_ingest 가 true 여야 함.
+        let caps = capabilities_snapshot();
+        assert!(
+            caps.single_file_ingest,
+            "single_file_ingest must be true (Bug #9)"
+        );
+    }
+}

crates/kebab-app/src/staleness.rs

@@ -0,0 +1,69 @@
+//! p9-fb-32 staleness helpers.
+
+use time::{Duration, OffsetDateTime};
+
+use kebab_core::SearchHit;
+
+/// Returns `true` iff `now - indexed_at > threshold_days * 24h`.
+/// `threshold_days = 0` always returns `false` (feature disabled).
+/// Strict `>` so that exactly `threshold_days` old returns `false`.
+///
+/// p9-fb-32: mirrored in `kebab_rag::pipeline::compute_stale` (dep-boundary
+/// rule prevents `kebab-rag → kebab-app`). Update both together.
+pub fn compute_stale(indexed_at: OffsetDateTime, now: OffsetDateTime, threshold_days: u32) -> bool {
+    if threshold_days == 0 {
+        return false;
+    }
+    let threshold = Duration::days(i64::from(threshold_days));
+    (now - indexed_at) > threshold
+}
+
+/// Sets `stale` on each hit in place using `compute_stale`.
+pub fn mark_stale_in_place(hits: &mut [SearchHit], now: OffsetDateTime, threshold_days: u32) {
+    for h in hits {
+        h.stale = compute_stale(h.indexed_at, now, threshold_days);
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use time::macros::datetime;
+
+    fn now() -> OffsetDateTime {
+        datetime!(2026-05-09 12:00:00 UTC)
+    }
+
+    #[test]
+    fn threshold_zero_always_fresh() {
+        let very_old = datetime!(2020-01-01 00:00:00 UTC);
+        assert!(!compute_stale(very_old, now(), 0));
+    }
+
+    #[test]
+    fn just_under_threshold_is_fresh() {
+        // 29 days, 23h, 59m old — under 30d.
+        let indexed = now() - Duration::days(29) - Duration::hours(23) - Duration::minutes(59);
+        assert!(!compute_stale(indexed, now(), 30));
+    }
+
+    #[test]
+    fn exactly_threshold_is_fresh() {
+        // strict `>` boundary: exactly 30d old is still fresh.
+        let indexed = now() - Duration::days(30);
+        assert!(!compute_stale(indexed, now(), 30));
+    }
+
+    #[test]
+    fn one_minute_past_threshold_is_stale() {
+        let indexed = now() - Duration::days(30) - Duration::minutes(1);
+        assert!(compute_stale(indexed, now(), 30));
+    }
+
+    #[test]
+    fn future_indexed_at_is_fresh() {
+        // clock skew safety: future timestamps must not be stale.
+        let future = now() + Duration::hours(1);
+        assert!(!compute_stale(future, now(), 30));
+    }
+}

crates/kebab-app/tests/ask_smoke.rs

@@ -33,6 +33,7 @@ fn ask_lexical_smoke() {
         history: Vec::new(),
         conversation_id: None,
         turn_index: None,
+        multi_hop: false,
     };
     // The fixture workspace contains "ownership" content; the model's
     // citation behavior depends on its training, so we don't assert on

crates/kebab-app/tests/common/mock_ocr.rs

@@ -0,0 +1,60 @@
+use std::sync::Mutex;
+
+use anyhow::Result;
+use kebab_core::{Lang, OcrText};
+use kebab_parse_image::OcrEngine;
+
+pub struct MockOcrEngine {
+    expected_texts: Vec<String>,
+    call_index: Mutex<usize>,
+    fail: bool,
+}
+
+impl MockOcrEngine {
+    /// Single text (backward-compat ctor for pdf_ocr_apply.rs 10 sites).
+    pub fn single(text: impl Into<String>, fail: bool) -> Self {
+        Self {
+            expected_texts: vec![text.into()],
+            call_index: Mutex::new(0),
+            fail,
+        }
+    }
+
+    /// Per-page texts (cursor advances per recognize call).
+    pub fn per_page(texts: Vec<String>, fail: bool) -> Self {
+        Self {
+            expected_texts: texts,
+            call_index: Mutex::new(0),
+            fail,
+        }
+    }
+}
+
+impl OcrEngine for MockOcrEngine {
+    fn engine_name(&self) -> &'static str {
+        "mock-ocr"
+    }
+
+    fn engine_version(&self) -> String {
+        "mock-v1".to_string()
+    }
+
+    fn recognize(&self, _img: &[u8], _hint: Option<&Lang>) -> Result<OcrText> {
+        if self.fail {
+            anyhow::bail!("mock failure");
+        }
+        let mut idx = self.call_index.lock().unwrap();
+        let text = self
+            .expected_texts
+            .get(*idx)
+            .cloned()
+            .unwrap_or_else(|| self.expected_texts.last().cloned().unwrap_or_default());
+        *idx += 1;
+        Ok(OcrText {
+            joined: text,
+            regions: vec![],
+            engine: "mock-ocr".to_string(),
+            engine_version: "mock-v1".to_string(),
+        })
+    }
+}

crates/kebab-app/tests/common/mod.rs

@@ -79,6 +79,36 @@ impl TestEnv {
             ..Default::default()
         }
     }
+
+    /// p9-fb-34 alias — tests added in fb-34 invoke `TestEnv::new()`
+    /// per the plan; route to the existing lexical-only constructor
+    /// so the lane stays AVX-free without churning all the existing
+    /// callers.
+    pub fn new() -> Self {
+        Self::lexical_only()
+    }
+
+    /// p9-fb-34: open a fresh `App` against this env's config. Used
+    /// by integration tests that need to call `App::search_with_opts`
+    /// directly. Caller can invoke this multiple times to simulate
+    /// re-opening the binary after a corpus revision bump.
+    pub fn app(&self) -> kebab_app::App {
+        kebab_app::App::open_with_config(self.config.clone()).expect("App::open_with_config")
+    }
+}
+
+/// p9-fb-34: write `content` into the env's workspace at
+/// `relative_path`, then run a full ingest so the document is
+/// searchable. Mirrors the convenience helpers used by other
+/// `TestEnv`-driven crates.
+pub fn ingest_md(env: &TestEnv, relative_path: &str, content: &str) {
+    let path = env.workspace_root.join(relative_path);
+    if let Some(parent) = path.parent() {
+        std::fs::create_dir_all(parent).expect("create parent dirs");
+    }
+    std::fs::write(&path, content).expect("write workspace file");
+    kebab_app::ingest_with_config(env.config.clone(), env.scope(), true)
+        .expect("ingest_with_config");
 }
 
 /// Test helper: build a `SearchQuery` for lexical mode at k=10. Used
@@ -94,6 +124,29 @@ pub fn lexical_query(text: &str) -> kebab_core::SearchQuery {
     }
 }
 
+/// p9-fb-32: rewrite `documents.updated_at` for one workspace path
+/// to `now - days_ago` (RFC3339 UTC). Used by staleness integration
+/// tests to simulate aged-out docs without faking system time. Caller
+/// is responsible for ingesting the doc *before* calling this — the
+/// row must already exist.
+pub fn backdate_document_updated_at(env: &TestEnv, workspace_path: &str, days_ago: i64) {
+    let backdated = (time::OffsetDateTime::now_utc() - time::Duration::days(days_ago))
+        .format(&time::format_description::well_known::Rfc3339)
+        .expect("format backdated updated_at");
+    let db_path = PathBuf::from(&env.config.storage.data_dir).join("kebab.sqlite");
+    let conn = rusqlite::Connection::open(&db_path).expect("open kebab.sqlite");
+    let updated = conn
+        .execute(
+            "UPDATE documents SET updated_at = ?1 WHERE workspace_path = ?2",
+            rusqlite::params![backdated, workspace_path],
+        )
+        .expect("UPDATE documents.updated_at");
+    assert_eq!(
+        updated, 1,
+        "backdate_document_updated_at: expected to update exactly 1 row for {workspace_path}, got {updated}"
+    );
+}
+
 fn copy_fixture_workspace(dest: &Path) {
     let src = PathBuf::from(env!("CARGO_MANIFEST_DIR"))
         .join("tests")
@@ -115,3 +168,5 @@ fn copy_dir_recursive(src: &Path, dest: &Path) {
         }
     }
 }
+
+pub mod mock_ocr;

crates/kebab-app/tests/config_invalidation.rs

@@ -0,0 +1,148 @@
+//! v0.26.2: ingest-config invalidation — changing a setting that affects
+//! ingest output auto-re-indexes the affected assets on the next ingest
+//! (no `--force-reingest`), while changing an unrelated setting does not.
+//!
+//! These end-to-end tests exercise the model-free signals (chunking +
+//! `[ingest.code]` options vs `search` settings). The exhaustive per-setting
+//! mapping (image OCR / caption, pdf.ocr, code options, search/rag/ui
+//! invariance) is unit-tested in
+//! `kebab-app/src/lib.rs::ingest_config_signature_tests` — those toggles
+//! (OCR/caption) require a live vision endpoint to ingest, so the wiring is
+//! verified here via the signature-driven chunking path that shares the same
+//! `effective_parser_version` plumbing.
+
+mod common;
+
+use common::TestEnv;
+
+use kebab_app::{IngestOpts, ingest_with_config, ingest_with_config_opts};
+use kebab_core::IngestItemKind;
+
+/// Seed a workspace with a markdown + a rust file so both the markdown and
+/// the code ingest paths are exercised. Returns the first-ingest report.
+fn seed_and_first_ingest(env: &TestEnv) -> kebab_core::IngestReport {
+    std::fs::write(
+        env.workspace_root.join("demo.rs"),
+        "/// adds two integers\npub fn add(a: i32, b: i32) -> i32 {\n    a + b\n}\n",
+    )
+    .unwrap();
+    let first = ingest_with_config(env.config.clone(), env.scope(), false).expect("first ingest");
+    assert_eq!(first.errors, 0, "first ingest must not error: {first:?}");
+    assert!(first.new >= 1, "first ingest creates docs: {first:?}");
+    assert_eq!(first.unchanged, 0, "first ingest has no unchanged: {first:?}");
+    first
+}
+
+fn reingest(env: &TestEnv) -> kebab_core::IngestReport {
+    ingest_with_config_opts(env.config.clone(), env.scope(), false, IngestOpts::default())
+        .expect("re-ingest")
+}
+
+/// Re-running with the identical config skips every asset (no spurious
+/// re-index). Regression guard for over-invalidation.
+#[test]
+fn identical_config_skips_all_assets() {
+    let env = TestEnv::lexical_only();
+    let first = seed_and_first_ingest(&env);
+    let scanned = first.scanned;
+
+    let second = reingest(&env);
+    assert_eq!(second.scanned, scanned);
+    assert_eq!(second.new, 0, "no new docs: {second:?}");
+    assert_eq!(second.updated, 0, "nothing re-indexed: {second:?}");
+    assert_eq!(second.unchanged, scanned, "every doc Unchanged: {second:?}");
+    assert_eq!(second.errors, 0);
+}
+
+/// Changing a common chunking parameter re-indexes EVERY media type
+/// (markdown + code here) without `--force-reingest`.
+#[test]
+fn chunking_change_reindexes_all_types() {
+    let mut env = TestEnv::lexical_only();
+    let first = seed_and_first_ingest(&env);
+    let scanned = first.scanned;
+
+    // Bump target_tokens — folds into every type's signature.
+    env.config.chunking.target_tokens += 100;
+
+    let second = reingest(&env);
+    assert_eq!(second.scanned, scanned);
+    assert_eq!(second.new, 0, "no new docs: {second:?}");
+    assert_eq!(
+        second.unchanged, 0,
+        "chunking change must re-index all: {second:?}"
+    );
+    assert_eq!(
+        second.updated, scanned,
+        "every doc re-indexed as Updated: {second:?}"
+    );
+    assert_eq!(second.errors, 0);
+}
+
+/// Changing an `[ingest.code]` option re-indexes only the code asset; the
+/// markdown assets stay Unchanged.
+#[test]
+fn code_option_change_reindexes_code_only() {
+    let mut env = TestEnv::lexical_only();
+    let first = seed_and_first_ingest(&env);
+    let scanned = first.scanned;
+
+    // Raise max_file_lines (keeps the tiny demo.rs in-scope; only the code
+    // signature changes).
+    env.config.ingest.code.max_file_lines += 1000;
+
+    let second = reingest(&env);
+    assert_eq!(second.scanned, scanned);
+    assert_eq!(second.new, 0, "no new docs: {second:?}");
+    assert_eq!(second.errors, 0);
+    assert_eq!(
+        second.updated, 1,
+        "exactly the code asset re-indexed: {second:?}"
+    );
+    assert_eq!(
+        second.unchanged,
+        scanned - 1,
+        "all markdown assets stay Unchanged: {second:?}"
+    );
+
+    let items = second.items.as_ref().expect("items present");
+    let code = items
+        .iter()
+        .find(|i| i.doc_path.0.ends_with("demo.rs"))
+        .expect("demo.rs item");
+    assert_eq!(
+        code.kind,
+        IngestItemKind::Updated,
+        "demo.rs must be re-indexed: {code:?}"
+    );
+    for i in items.iter().filter(|i| i.doc_path.0.ends_with(".md")) {
+        assert_eq!(
+            i.kind,
+            IngestItemKind::Unchanged,
+            "markdown must be Unchanged: {i:?}"
+        );
+    }
+}
+
+/// Regression guard: changing a non-ingest setting (`search.default_k`) does
+/// NOT re-index anything.
+#[test]
+fn search_setting_change_reindexes_nothing() {
+    let mut env = TestEnv::lexical_only();
+    let first = seed_and_first_ingest(&env);
+    let scanned = first.scanned;
+
+    env.config.search.default_k += 5;
+    env.config.search.snippet_chars += 50;
+    env.config.rag.score_gate = 0.5;
+
+    let second = reingest(&env);
+    assert_eq!(second.scanned, scanned);
+    assert_eq!(
+        second.unchanged, scanned,
+        "search/rag changes must not re-index: {second:?}"
+    );
+    assert_eq!(second.updated, 0, "nothing re-indexed: {second:?}");
+    assert_eq!(second.new, 0);
+    assert_eq!(second.errors, 0);
+}

crates/kebab-app/tests/config_migrate.rs

@@ -0,0 +1,85 @@
+use std::fs;
+
+#[test]
+fn migrate_writes_backup_and_atomic_with_dry_run_noop() {
+    let dir = tempfile::tempdir().unwrap();
+    let cfg = dir.path().join("config.toml");
+    fs::write(
+        &cfg,
+        "schema_version = 1\n\n[workspace]\nroot = \"/n\"\ninclude = [\"*.md\"]\n",
+    )
+    .unwrap();
+
+    // dry-run: 파일·백업 미변경.
+    let report = kebab_app::config_migrate_with_config_path(Some(&cfg), true).unwrap();
+    assert!(report.changed);
+    assert!(report.dry_run);
+    assert!(report.backup_path.is_none());
+    assert!(!dir.path().join("config.toml.bak").exists());
+    assert!(
+        fs::read_to_string(&cfg).unwrap().contains("include"),
+        "dry-run modified file"
+    );
+
+    // 실제 적용: 백업 생성 + 파일 갱신.
+    let report = kebab_app::config_migrate_with_config_path(Some(&cfg), false).unwrap();
+    assert!(report.changed);
+    assert!(!report.dry_run);
+    assert!(report.backup_path.is_some());
+    assert!(dir.path().join("config.toml.bak").exists());
+    let new = fs::read_to_string(&cfg).unwrap();
+    assert!(!new.contains("include"));
+    assert!(new.contains("[ingest.code]"));
+
+    // 멱등: 재실행 changed=false.
+    let report = kebab_app::config_migrate_with_config_path(Some(&cfg), false).unwrap();
+    assert!(!report.changed);
+}
+
+#[test]
+fn migrate_missing_file_errors() {
+    let dir = tempfile::tempdir().unwrap();
+    let cfg = dir.path().join("nope.toml");
+    assert!(kebab_app::config_migrate_with_config_path(Some(&cfg), false).is_err());
+}
+
+#[test]
+fn annotated_default_serialization_contains_section_comments() {
+    let doc = kebab_config::migrate::annotated_default_document();
+    let text = doc.to_string();
+    assert!(
+        text.contains("code ingest skip 정책"),
+        "section comment missing:\n{text}"
+    );
+    assert!(text.contains("[ingest.code]"));
+}
+
+#[test]
+fn doctor_flags_outdated_config() {
+    let dir = tempfile::tempdir().unwrap();
+    let cfg = dir.path().join("config.toml");
+    fs::write(
+        &cfg,
+        "schema_version = 1\n\n[workspace]\nroot = \"/n\"\ninclude=[\"*.md\"]\n",
+    )
+    .unwrap();
+    let report = kebab_app::doctor_with_config_path(Some(&cfg)).unwrap();
+    let check = report
+        .checks
+        .iter()
+        .find(|c| c.name == "config_migration")
+        .unwrap();
+    assert!(!check.ok, "outdated config should fail check");
+    assert!(check.hint.as_deref().unwrap().contains("config migrate"));
+    assert!(!report.ok, "overall doctor should be false");
+
+    // migrate 후엔 통과.
+    kebab_app::config_migrate_with_config_path(Some(&cfg), false).unwrap();
+    let report = kebab_app::doctor_with_config_path(Some(&cfg)).unwrap();
+    let check = report
+        .checks
+        .iter()
+        .find(|c| c.name == "config_migration")
+        .unwrap();
+    assert!(check.ok, "after migrate should pass");
+}

crates/kebab-app/tests/cursor.rs

@@ -0,0 +1,24 @@
+//! p9-fb-34: cursor encode/decode round-trip + corpus_revision mismatch.
+
+use kebab_app::cursor;
+
+#[test]
+fn cursor_roundtrip_preserves_offset() {
+    let encoded = cursor::encode(5, "rev-abc");
+    let offset = cursor::decode(&encoded, "rev-abc").unwrap();
+    assert_eq!(offset, 5);
+}
+
+#[test]
+fn cursor_decode_rejects_mismatched_revision() {
+    let encoded = cursor::encode(7, "rev-old");
+    let err = cursor::decode(&encoded, "rev-new").unwrap_err();
+    assert_eq!(err.code, "stale_cursor");
+    assert!(err.message.contains("rev-old") || err.message.contains("rev-new"));
+}
+
+#[test]
+fn cursor_decode_rejects_garbage_input() {
+    let err = cursor::decode("not-base64!!!", "any").unwrap_err();
+    assert_eq!(err.code, "stale_cursor");
+}

crates/kebab-app/tests/fetch_integration.rs

@@ -0,0 +1,344 @@
+//! p9-fb-35 App::fetch integration tests.
+
+mod common;
+
+use kebab_app::App;
+use kebab_core::{FetchKind, FetchOpts, FetchQuery};
+
+fn open(env: &common::TestEnv) -> App {
+    env.app()
+}
+
+#[test]
+fn fetch_chunk_returns_target_only_when_no_context() {
+    let env = common::TestEnv::new();
+    common::ingest_md(
+        &env,
+        "a.md",
+        "# Title\n\nFirst paragraph.\n\n## Section\n\nSecond.\n",
+    );
+    let app = open(&env);
+
+    // Find a chunk via search to obtain its id.
+    let q = kebab_core::SearchQuery {
+        text: "First".to_string(),
+        mode: kebab_core::SearchMode::Lexical,
+        k: 1,
+        filters: kebab_core::SearchFilters::default(),
+    };
+    let hits = app.search(q).unwrap();
+    let chunk_id = hits[0].chunk_id.clone();
+
+    let result = app
+        .fetch(FetchQuery::Chunk(chunk_id), FetchOpts::default())
+        .unwrap();
+    assert_eq!(result.kind, FetchKind::Chunk);
+    assert!(result.chunk.is_some(), "target chunk populated");
+    assert!(result.context_before.is_empty());
+    assert!(result.context_after.is_empty());
+    assert!(!result.truncated);
+}
+
+#[test]
+fn fetch_chunk_with_context_returns_neighbors() {
+    let env = common::TestEnv::new();
+    // 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: "cherry".to_string(),
+        mode: kebab_core::SearchMode::Lexical,
+        k: 1,
+        filters: kebab_core::SearchFilters::default(),
+    };
+    let hits = app.search(q).unwrap();
+    let chunk_id = hits[0].chunk_id.clone();
+
+    let result = app
+        .fetch(
+            FetchQuery::Chunk(chunk_id),
+            FetchOpts {
+                context: Some(2),
+                max_tokens: None,
+            },
+        )
+        .unwrap();
+    assert_eq!(result.kind, FetchKind::Chunk);
+    assert!(result.chunk.is_some());
+    let total = result.context_before.len() + result.context_after.len();
+    assert!(total >= 1, "at least one neighbor expected");
+    assert!(total <= 4, "context capped at +-2 ⇒ max 4 neighbors");
+}
+
+#[test]
+fn fetch_chunk_unknown_id_returns_chunk_not_found() {
+    let env = common::TestEnv::new();
+    let app = env.app();
+    let err = app
+        .fetch(
+            FetchQuery::Chunk(kebab_core::ChunkId("nonexistent-id".to_string())),
+            FetchOpts::default(),
+        )
+        .unwrap_err();
+    let msg = err.to_string();
+    assert!(
+        msg.contains("chunk_not_found") || msg.contains("nonexistent-id"),
+        "expected chunk_not_found error, got: {msg}"
+    );
+}
+
+#[test]
+fn fetch_doc_returns_serialized_markdown() {
+    let env = common::TestEnv::new();
+    let body = "# Heading One\n\nFirst paragraph.\n\n## Sub\n\nSecond.\n";
+    common::ingest_md(&env, "doc.md", body);
+    let app = env.app();
+
+    // Discover doc_id via search hit (avoids depending on list_docs API shape).
+    let q = kebab_core::SearchQuery {
+        text: "First".to_string(),
+        mode: kebab_core::SearchMode::Lexical,
+        k: 1,
+        filters: kebab_core::SearchFilters::default(),
+    };
+    let hits = app.search(q).unwrap();
+    let doc_id = hits[0].doc_id.clone();
+
+    let result = app
+        .fetch(FetchQuery::Doc(doc_id), FetchOpts::default())
+        .unwrap();
+    assert_eq!(result.kind, FetchKind::Doc);
+    let text = result.text.expect("doc text");
+    assert!(
+        text.contains("Heading One"),
+        "doc text contains heading: {text:?}"
+    );
+    assert!(text.contains("First paragraph"), "doc text contains body");
+    assert!(!result.truncated);
+}
+
+#[test]
+fn fetch_doc_unknown_id_returns_doc_not_found() {
+    let env = common::TestEnv::new();
+    let app = env.app();
+    let err = app
+        .fetch(
+            FetchQuery::Doc(kebab_core::DocumentId("nonexistent-doc".to_string())),
+            FetchOpts::default(),
+        )
+        .unwrap_err();
+    assert!(err.to_string().contains("doc_not_found"), "got: {err}");
+}
+
+#[test]
+fn fetch_doc_with_max_tokens_truncates() {
+    let env = common::TestEnv::new();
+    let p = "Lorem ipsum dolor sit amet consectetur adipiscing elit. ".repeat(20);
+    let body = format!("# Big\n\n{p}\n");
+    common::ingest_md(&env, "big.md", &body);
+    let app = env.app();
+    let q = kebab_core::SearchQuery {
+        text: "Lorem".to_string(),
+        mode: kebab_core::SearchMode::Lexical,
+        k: 1,
+        filters: kebab_core::SearchFilters::default(),
+    };
+    let hits = app.search(q).unwrap();
+    let doc_id = hits[0].doc_id.clone();
+
+    let result = app
+        .fetch(
+            FetchQuery::Doc(doc_id),
+            FetchOpts {
+                context: None,
+                max_tokens: Some(20), // ~80 chars
+            },
+        )
+        .unwrap();
+    assert!(result.truncated);
+    let text = result.text.expect("doc text");
+    assert!(
+        text.chars().count() <= 100,
+        "trimmed text len {}",
+        text.chars().count()
+    );
+}
+
+#[test]
+fn fetch_span_returns_line_range() {
+    let env = common::TestEnv::new();
+    // Use a list so the canonical-to-markdown roundtrip emits 5
+    // single-line entries joined by `\n` (paragraphs would be joined by
+    // `\n\n`, and CommonMark soft breaks inside one paragraph collapse to
+    // spaces — see crates/kebab-parse-md/src/blocks.rs `Event::SoftBreak`).
+    let body = "- Line one.\n- Line two.\n- Line three.\n- Line four.\n- Line five.\n";
+    common::ingest_md(&env, "lines.md", body);
+    let app = env.app();
+
+    let q = kebab_core::SearchQuery {
+        text: "Line".to_string(),
+        mode: kebab_core::SearchMode::Lexical,
+        k: 1,
+        filters: kebab_core::SearchFilters::default(),
+    };
+    let hits = app.search(q).unwrap();
+    let doc_id = hits[0].doc_id.clone();
+
+    let result = app
+        .fetch(
+            FetchQuery::Span {
+                doc_id,
+                line_start: 2,
+                line_end: 4,
+            },
+            FetchOpts::default(),
+        )
+        .unwrap();
+    assert_eq!(result.kind, FetchKind::Span);
+    let text = result.text.expect("span text");
+    let line_count = text.lines().count();
+    assert_eq!(line_count, 3, "span should be 3 lines: {text:?}");
+    assert_eq!(result.line_start, Some(2));
+    assert_eq!(result.line_end, Some(4));
+    assert_eq!(result.effective_end, Some(4));
+    assert!(!result.truncated);
+}
+
+#[test]
+fn fetch_span_clamps_line_end_when_out_of_range() {
+    let env = common::TestEnv::new();
+    common::ingest_md(&env, "short.md", "Line one.\nLine two.\n");
+    let app = env.app();
+    let q = kebab_core::SearchQuery {
+        text: "Line".to_string(),
+        mode: kebab_core::SearchMode::Lexical,
+        k: 1,
+        filters: kebab_core::SearchFilters::default(),
+    };
+    let hits = app.search(q).unwrap();
+    let doc_id = hits[0].doc_id.clone();
+
+    let result = app
+        .fetch(
+            FetchQuery::Span {
+                doc_id,
+                line_start: 1,
+                line_end: 999,
+            },
+            FetchOpts::default(),
+        )
+        .unwrap();
+    let text = result.text.expect("span text");
+    let actual_lines = text.lines().count();
+    assert_eq!(result.effective_end, Some(actual_lines as u32));
+    assert!(actual_lines < 999);
+}
+
+#[test]
+fn fetch_span_invalid_input_when_zero_lines() {
+    let env = common::TestEnv::new();
+    common::ingest_md(&env, "a.md", "Line one.\n");
+    let app = env.app();
+    let q = kebab_core::SearchQuery {
+        text: "Line".to_string(),
+        mode: kebab_core::SearchMode::Lexical,
+        k: 1,
+        filters: kebab_core::SearchFilters::default(),
+    };
+    let hits = app.search(q).unwrap();
+    let doc_id = hits[0].doc_id.clone();
+
+    let err = app
+        .fetch(
+            FetchQuery::Span {
+                doc_id,
+                line_start: 0,
+                line_end: 0,
+            },
+            FetchOpts::default(),
+        )
+        .unwrap_err();
+    assert!(err.to_string().contains("invalid_input"), "got: {err}");
+}
+
+#[test]
+fn fetch_span_line_start_beyond_total_returns_empty_text() {
+    let env = common::TestEnv::new();
+    let body = "- Line one.\n- Line two.\n";
+    common::ingest_md(&env, "two_lines.md", body);
+    let app = env.app();
+    let q = kebab_core::SearchQuery {
+        text: "Line".to_string(),
+        mode: kebab_core::SearchMode::Lexical,
+        k: 1,
+        filters: kebab_core::SearchFilters::default(),
+    };
+    let hits = app.search(q).unwrap();
+    let doc_id = hits[0].doc_id.clone();
+
+    let result = app
+        .fetch(
+            FetchQuery::Span {
+                doc_id,
+                line_start: 100,
+                line_end: 200,
+            },
+            FetchOpts::default(),
+        )
+        .unwrap();
+    let text = result.text.expect("text field");
+    assert!(text.is_empty(), "out-of-range request returns empty text");
+    assert!(
+        !result.truncated,
+        "out-of-range is NOT truncated (budget-only flag)"
+    );
+}
+
+#[test]
+fn fetch_chunk_context_at_first_chunk_clamps_lower_bound() {
+    let env = common::TestEnv::new();
+    // Multi-chunk markdown so context ±N has neighbors.
+    let body = "# H1\n\nFirst chunk text body.\n\n# H2\n\nSecond chunk.\n\n# H3\n\nThird chunk.\n";
+    common::ingest_md(&env, "boundary.md", body);
+    let app = env.app();
+    let q = kebab_core::SearchQuery {
+        text: "First".to_string(),
+        mode: kebab_core::SearchMode::Lexical,
+        k: 1,
+        filters: kebab_core::SearchFilters::default(),
+    };
+    let hits = app.search(q).unwrap();
+    let chunk_id = hits[0].chunk_id.clone();
+
+    let result = app
+        .fetch(
+            FetchQuery::Chunk(chunk_id),
+            FetchOpts {
+                context: Some(2),
+                max_tokens: None,
+            },
+        )
+        .unwrap();
+    // p9-fb-35 R2: doc has 3 chunks; ±2 should clamp the total
+    // neighbor count to ≤ 2 + 1 (= excludes target).
+    //
+    // ⚠ Strict "first-chunk → context_before is empty" cannot be
+    // asserted here yet because chunks.ordinal column does not exist
+    // — `list_chunk_ids_for_doc` orders by `(created_at, chunk_id)`
+    // and chunk_id is a blake3 hash, so the "First chunk" content
+    // may land at any hash-order position within the doc. The clamp
+    // logic itself is correct (target_idx ± n → [0..len]); we just
+    // can't pin which chunk is hash-order-first. Tracked as
+    // follow-up: V007 chunks.ordinal migration.
+    let total = result.context_before.len() + result.context_after.len();
+    assert!(
+        total <= 2,
+        "doc with 3 chunks ±2 → at most 2 neighbors (excludes target), got {total}"
+    );
+}

crates/kebab-app/tests/file_deletion_auto_purge.rs

@@ -0,0 +1,171 @@
+//! Dogfood: auto-purge stored docs for filesystem-deleted files.
+//!
+//! Two tests:
+//!
+//! 1. `file_deletion_auto_purge` — ingest 2 files, delete one, re-ingest.
+//!    The re-ingest must report `purged_deleted_files = 1`, the deleted
+//!    file must no longer appear in `list_docs`, and lexical search for
+//!    its unique content must return no hits.
+//!
+//! 2. `include_scope_narrowing_does_not_purge` — ingest 2 files under a
+//!    wide glob, narrow the walker scope to only one file, re-ingest.
+//!    The narrowed ingest must NOT purge the out-of-scope file because
+//!    the file is still on disk (just excluded from this run). Protects
+//!    users against accidental data loss via config edits.
+
+mod common;
+
+use common::TestEnv;
+use kebab_app::IngestOpts;
+use kebab_app::ingest_with_config_opts;
+use kebab_core::{DocFilter, DocumentStore, SearchMode, SearchQuery, SourceScope};
+
+/// Helper: open the store via `TestEnv` and run `list_documents`.
+fn list_doc_paths(env: &TestEnv) -> Vec<String> {
+    use kebab_store_sqlite::SqliteStore;
+    let store = SqliteStore::open(&env.config).unwrap();
+    store.run_migrations().unwrap();
+    store
+        .list_documents(&DocFilter::default())
+        .unwrap()
+        .into_iter()
+        .map(|d| d.doc_path.0)
+        .collect()
+}
+
+#[test]
+fn file_deletion_auto_purge() {
+    let env = TestEnv::lexical_only();
+
+    // Write two .rs files into the workspace.
+    let a_path = env.workspace_root.join("a.rs");
+    let b_path = env.workspace_root.join("b.rs");
+    std::fs::write(&a_path, "// file a\nfn alpha() {}\n").unwrap();
+    std::fs::write(&b_path, "// file b\nfn bravo() {}\n").unwrap();
+
+    // First ingest — both must be New.
+    let first = ingest_with_config_opts(
+        env.config.clone(),
+        env.scope(),
+        false,
+        IngestOpts::default(),
+    )
+    .expect("first ingest must succeed");
+    // Only count the .rs files we added (there may be fixture files too).
+    let first_new = first.new;
+    assert!(first_new >= 2, "expected at least 2 new docs: {first:?}");
+    assert_eq!(
+        first.purged_deleted_files, 0,
+        "no purges on first ingest: {first:?}"
+    );
+    assert_eq!(first.errors, 0, "no errors on first ingest: {first:?}");
+
+    // Delete one file from the filesystem.
+    std::fs::remove_file(&b_path).expect("remove b.rs");
+
+    // Second ingest — scanned count drops by 1; b.rs should be purged.
+    let second = ingest_with_config_opts(
+        env.config.clone(),
+        env.scope(),
+        false,
+        IngestOpts::default(),
+    )
+    .expect("second ingest must succeed");
+
+    assert_eq!(
+        second.purged_deleted_files, 1,
+        "exactly 1 file should be purged: {second:?}"
+    );
+    assert_eq!(second.new, 0, "no new docs after deletion: {second:?}");
+    assert_eq!(second.updated, 0, "no updated docs: {second:?}");
+    assert_eq!(second.errors, 0, "no errors: {second:?}");
+
+    // b.rs must no longer appear in list_docs.
+    let doc_paths = list_doc_paths(&env);
+    let b_ws_path = "b.rs";
+    assert!(
+        !doc_paths.iter().any(|p| p == b_ws_path),
+        "b.rs must be gone from list_docs; got: {doc_paths:?}"
+    );
+    // a.rs must still be present.
+    let a_ws_path = "a.rs";
+    assert!(
+        doc_paths.iter().any(|p| p == a_ws_path),
+        "a.rs must still be in list_docs; got: {doc_paths:?}"
+    );
+
+    // Lexical search for b.rs's unique content returns no hits.
+    let app = env.app();
+    let query = SearchQuery {
+        text: "bravo".to_string(),
+        mode: SearchMode::Lexical,
+        k: 10,
+        filters: kebab_core::SearchFilters::default(),
+    };
+    let hits = app.search(query).expect("search must not error");
+    assert!(
+        hits.is_empty(),
+        "search for deleted file's content must return no hits; got: {hits:?}"
+    );
+}
+
+#[test]
+fn include_scope_narrowing_does_not_purge() {
+    let env = TestEnv::lexical_only();
+
+    // Write two .rs files.
+    let a_path = env.workspace_root.join("a_narrow.rs");
+    let b_path = env.workspace_root.join("b_narrow.rs");
+    std::fs::write(&a_path, "// narrow a\nfn alpha_narrow() {}\n").unwrap();
+    std::fs::write(&b_path, "// narrow b\nfn bravo_narrow() {}\n").unwrap();
+
+    // Wide scope: first ingest — both must be New.
+    let wide_scope = SourceScope {
+        root: env.workspace_root.clone(),
+        include: vec!["**/*.rs".to_string()],
+        exclude: env.config.workspace.exclude.clone(),
+    };
+    let first =
+        ingest_with_config_opts(env.config.clone(), wide_scope, false, IngestOpts::default())
+            .expect("first ingest (wide) must succeed");
+    assert!(first.new >= 2, "expected at least 2 new docs: {first:?}");
+    assert_eq!(
+        first.purged_deleted_files, 0,
+        "no purges on first ingest: {first:?}"
+    );
+
+    // Narrow scope: only a_narrow.rs in include — b_narrow.rs is still
+    // on disk but excluded from the walker scope.
+    let narrow_scope = SourceScope {
+        root: env.workspace_root.clone(),
+        include: vec!["a_narrow.rs".to_string()],
+        exclude: env.config.workspace.exclude.clone(),
+    };
+    let second = ingest_with_config_opts(
+        env.config.clone(),
+        narrow_scope,
+        false,
+        IngestOpts::default(),
+    )
+    .expect("second ingest (narrow) must succeed");
+
+    // CRITICAL: b_narrow.rs is still on disk — must NOT be purged.
+    assert_eq!(
+        second.purged_deleted_files, 0,
+        "scope-narrowing must NOT purge on-disk files; got: {second:?}"
+    );
+    assert_eq!(second.errors, 0, "no errors: {second:?}");
+
+    // b_narrow.rs must still exist in the store.
+    let doc_paths = list_doc_paths(&env);
+    let b_ws_path = "b_narrow.rs";
+    assert!(
+        doc_paths.iter().any(|p| p == b_ws_path),
+        "b_narrow.rs must still be in list_docs after scope narrowing; got: {doc_paths:?}"
+    );
+    // And the file must still be on disk.
+    assert!(
+        b_path.exists(),
+        "b_narrow.rs must still be on disk (we didn't delete it)"
+    );
+}

crates/kebab-app/tests/image_pipeline.rs

@@ -24,8 +24,7 @@ use wiremock::{Mock, MockServer, ResponseTemplate};
 /// inspectable in stored DB rows.
 fn write_red_png(root: &Path, name: &str) -> std::path::PathBuf {
     use image::{ImageBuffer, Rgb};
-    let img: ImageBuffer<Rgb<u8>, _> =
-        ImageBuffer::from_fn(100, 50, |_, _| Rgb([255, 0, 0]));
+    let img: ImageBuffer<Rgb<u8>, _> = ImageBuffer::from_fn(100, 50, |_, _| Rgb([255, 0, 0]));
     let path = root.join(name);
     img.save(&path).expect("write PNG fixture");
     path
@@ -80,7 +79,12 @@ async fn ingest_image_with_ocr_produces_chunk_containing_ocr_text() {
 
     // Counters: scanned should include the PNG; new ≥ 1 (markdown
     // fixtures from the workspace tree may also count).
-    assert!(report.scanned >= 1, "scanned={}, items={:?}", report.scanned, report.items);
+    assert!(
+        report.scanned >= 1,
+        "scanned={}, items={:?}",
+        report.scanned,
+        report.items
+    );
     assert_eq!(report.errors, 0, "no errors on lenient OCR path");
 
     // Locate the image doc in the report items.
@@ -94,7 +98,11 @@ async fn ingest_image_with_ocr_produces_chunk_containing_ocr_text() {
         kebab_core::IngestItemKind::New,
         "image asset must be classified New on first ingest"
     );
-    assert_eq!(img_item.chunk_count, Some(1), "image emits exactly one chunk");
+    assert_eq!(
+        img_item.chunk_count,
+        Some(1),
+        "image emits exactly one chunk"
+    );
 
     // Inspect the stored chunk text via kb-app's inspect_chunk facade.
     let doc_id = img_item.doc_id.clone().expect("image doc id");
@@ -117,10 +125,12 @@ async fn ingest_image_with_ocr_produces_chunk_containing_ocr_text() {
 
     // Sanity: the doc was actually persisted into SQLite (kb-app's
     // list_docs facade reads the same store the chunker writes to).
-    let summaries = kebab_app::list_docs_with_config(cfg, kebab_core::DocFilter::default())
-        .expect("list_docs");
+    let summaries =
+        kebab_app::list_docs_with_config(cfg, kebab_core::DocFilter::default()).expect("list_docs");
     assert!(
-        summaries.iter().any(|s| s.doc_path.0.ends_with("diagram.png")),
+        summaries
+            .iter()
+            .any(|s| s.doc_path.0.ends_with("diagram.png")),
         "image doc must appear in list_docs"
     );
 
@@ -171,8 +181,7 @@ async fn ingest_image_with_ocr_and_caption_populates_both_fields() {
         .iter()
         .find(|i| i.doc_path.0.ends_with("diagram.png"))
         .unwrap();
-    let doc = kebab_app::inspect_doc_with_config(cfg, img_item.doc_id.as_ref().unwrap())
-        .unwrap();
+    let doc = kebab_app::inspect_doc_with_config(cfg, img_item.doc_id.as_ref().unwrap()).unwrap();
     let block = match &doc.blocks[0] {
         kebab_core::Block::ImageRef(b) => b,
         _ => unreachable!(),
@@ -267,8 +276,7 @@ async fn image_indexed_with_filename_when_ocr_and_caption_disabled() {
     let cfg_clone = cfg.clone();
     let scope = env.scope();
     let report = spawn_blocking(move || {
-        kebab_app::ingest_with_config(cfg_clone, scope, false)
-            .expect("ingest with no OCR/caption")
+        kebab_app::ingest_with_config(cfg_clone, scope, false).expect("ingest with no OCR/caption")
     })
     .await
     .expect("task");
@@ -282,8 +290,7 @@ async fn image_indexed_with_filename_when_ocr_and_caption_disabled() {
         .find(|i| i.doc_path.0.ends_with("raw.png"))
         .unwrap();
     assert_eq!(img_item.chunk_count, Some(1), "image emits one chunk");
-    let doc = kebab_app::inspect_doc_with_config(cfg, img_item.doc_id.as_ref().unwrap())
-        .unwrap();
+    let doc = kebab_app::inspect_doc_with_config(cfg, img_item.doc_id.as_ref().unwrap()).unwrap();
     let block = match &doc.blocks[0] {
         kebab_core::Block::ImageRef(b) => b,
         _ => unreachable!(),
@@ -392,16 +399,12 @@ async fn re_ingest_image_produces_unchanged_with_same_doc_id() {
     let scope1 = scope.clone();
     let scope2 = scope.clone();
 
-    let r1 = spawn_blocking(move || {
-        kebab_app::ingest_with_config(cfg1, scope1, false).unwrap()
-    })
-    .await
-    .unwrap();
-    let r2 = spawn_blocking(move || {
-        kebab_app::ingest_with_config(cfg2, scope2, false).unwrap()
-    })
-    .await
-    .unwrap();
+    let r1 = spawn_blocking(move || kebab_app::ingest_with_config(cfg1, scope1, false).unwrap())
+        .await
+        .unwrap();
+    let r2 = spawn_blocking(move || kebab_app::ingest_with_config(cfg2, scope2, false).unwrap())
+        .await
+        .unwrap();
 
     let id1 = r1
         .items

crates/kebab-app/tests/incremental_ingest.rs

@@ -21,11 +21,16 @@ fn second_ingest_of_unchanged_corpus_marks_all_unchanged() {
     // First ingest — populates the DB. Use the legacy entry so the
     // assertions cover the "previously ingested" set without needing
     // IngestOpts::default() to behave identically.
-    let first =
-        ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
+    let first = ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
     assert_eq!(first.errors, 0, "first ingest must not error: {first:?}");
-    assert!(first.new >= 1, "first ingest must create new docs: {first:?}");
-    assert_eq!(first.unchanged, 0, "first ingest cannot have unchanged: {first:?}");
+    assert!(
+        first.new >= 1,
+        "first ingest must create new docs: {first:?}"
+    );
+    assert_eq!(
+        first.unchanged, 0,
+        "first ingest cannot have unchanged: {first:?}"
+    );
 
     let scanned = first.scanned;
 
@@ -38,9 +43,15 @@ fn second_ingest_of_unchanged_corpus_marks_all_unchanged() {
         IngestOpts::default(),
     )
     .unwrap();
-    assert_eq!(second.scanned, scanned, "second scanned matches first: {second:?}");
+    assert_eq!(
+        second.scanned, scanned,
+        "second scanned matches first: {second:?}"
+    );
     assert_eq!(second.new, 0, "no new docs on re-ingest: {second:?}");
-    assert_eq!(second.updated, 0, "nothing should be marked updated: {second:?}");
+    assert_eq!(
+        second.updated, 0,
+        "nothing should be marked updated: {second:?}"
+    );
     assert_eq!(
         second.unchanged, scanned,
         "every doc must be Unchanged: {second:?}"
@@ -52,10 +63,12 @@ fn second_ingest_of_unchanged_corpus_marks_all_unchanged() {
 fn force_reingest_bypasses_skip() {
     let env = TestEnv::lexical_only();
 
-    let first =
-        ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
+    let first = ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
     assert_eq!(first.errors, 0, "first ingest must not error: {first:?}");
-    assert!(first.new >= 1, "first ingest must create new docs: {first:?}");
+    assert!(
+        first.new >= 1,
+        "first ingest must create new docs: {first:?}"
+    );
     let scanned = first.scanned;
 
     let second = ingest_with_config_opts(

crates/kebab-app/tests/ingest_cancel.rs

@@ -107,13 +107,9 @@ fn cancel_none_is_uncancellable_default() {
     // ingest_with_config_progress (no cancel) runs to completion.
     let env = TestEnv::lexical_only();
     let (tx, rx) = mpsc::channel::<IngestEvent>();
-    let report = kebab_app::ingest_with_config_progress(
-        env.config.clone(),
-        env.scope(),
-        true,
-        Some(tx),
-    )
-    .unwrap();
+    let report =
+        kebab_app::ingest_with_config_progress(env.config.clone(), env.scope(), true, Some(tx))
+            .unwrap();
     assert_eq!(report.scanned, 3);
     assert_eq!(report.new, 3);
 

crates/kebab-app/tests/ingest_file.rs

@@ -0,0 +1,114 @@
+//! Integration: kebab_app::ingest_file_with_config copies external file
+//! to _external/, ingests as single asset, idempotent on second call.
+
+use std::fs;
+
+use kebab_config::Config;
+
+#[test]
+fn ingest_file_copies_external_md_and_reports_new() {
+    let dir = tempfile::tempdir().unwrap();
+    let workspace = dir.path().join("notes");
+    let data = dir.path().join("data");
+    fs::create_dir_all(&workspace).unwrap();
+    fs::create_dir_all(&data).unwrap();
+
+    let mut cfg = Config::defaults();
+    cfg.workspace.root = workspace.to_string_lossy().into_owned();
+    cfg.storage.data_dir = data.to_string_lossy().into_owned();
+    cfg.models.embedding.provider = "none".to_string();
+    cfg.models.embedding.dimensions = 0;
+
+    // Source file outside the workspace.
+    let external_src = dir.path().join("source.md");
+    fs::write(&external_src, "# Hello\n\nbody.").unwrap();
+
+    let report = kebab_app::ingest_file_with_config(cfg.clone(), &external_src).unwrap();
+    assert_eq!(report.scanned, 1, "{report:?}");
+    assert_eq!(report.new, 1, "{report:?}");
+    assert_eq!(report.unchanged, 0, "{report:?}");
+
+    // _external/ dir created, file copied with hash prefix.
+    let ext_dir = workspace.join("_external");
+    assert!(ext_dir.is_dir());
+    let entries: Vec<_> = fs::read_dir(&ext_dir)
+        .unwrap()
+        .filter_map(std::result::Result::ok)
+        .collect();
+    assert_eq!(entries.len(), 1, "exactly one file in _external/");
+    let name = entries[0].file_name().to_string_lossy().into_owned();
+    assert!(name.ends_with(".md"));
+
+    // .kebabignore has _external/ line.
+    let ki = fs::read_to_string(workspace.join(".kebabignore")).unwrap();
+    assert!(ki.lines().any(|l| l.trim() == "_external/"));
+}
+
+#[test]
+fn ingest_file_idempotent_on_second_call() {
+    let dir = tempfile::tempdir().unwrap();
+    let workspace = dir.path().join("notes");
+    let data = dir.path().join("data");
+    fs::create_dir_all(&workspace).unwrap();
+    fs::create_dir_all(&data).unwrap();
+
+    let mut cfg = Config::defaults();
+    cfg.workspace.root = workspace.to_string_lossy().into_owned();
+    cfg.storage.data_dir = data.to_string_lossy().into_owned();
+    cfg.models.embedding.provider = "none".to_string();
+    cfg.models.embedding.dimensions = 0;
+
+    let src = dir.path().join("doc.md");
+    fs::write(&src, "# A\n\nbody.").unwrap();
+
+    let r1 = kebab_app::ingest_file_with_config(cfg.clone(), &src).unwrap();
+    assert_eq!(r1.new, 1);
+
+    let r2 = kebab_app::ingest_file_with_config(cfg.clone(), &src).unwrap();
+    assert_eq!(r2.new, 0, "{r2:?}");
+    assert_eq!(r2.unchanged, 1, "{r2:?}");
+}
+
+#[test]
+fn ingest_file_errors_on_missing_path() {
+    let dir = tempfile::tempdir().unwrap();
+    let workspace = dir.path().join("notes");
+    let data = dir.path().join("data");
+    fs::create_dir_all(&workspace).unwrap();
+    fs::create_dir_all(&data).unwrap();
+
+    let mut cfg = Config::defaults();
+    cfg.workspace.root = workspace.to_string_lossy().into_owned();
+    cfg.storage.data_dir = data.to_string_lossy().into_owned();
+    cfg.models.embedding.provider = "none".to_string();
+    cfg.models.embedding.dimensions = 0;
+
+    let nonexistent = dir.path().join("nope.md");
+    let err = kebab_app::ingest_file_with_config(cfg, &nonexistent).unwrap_err();
+    assert!(err.to_string().contains("does not exist"), "{err}");
+}
+
+#[test]
+fn ingest_file_errors_on_unsupported_extension() {
+    let dir = tempfile::tempdir().unwrap();
+    let workspace = dir.path().join("notes");
+    let data = dir.path().join("data");
+    fs::create_dir_all(&workspace).unwrap();
+    fs::create_dir_all(&data).unwrap();
+
+    let mut cfg = Config::defaults();
+    cfg.workspace.root = workspace.to_string_lossy().into_owned();
+    cfg.storage.data_dir = data.to_string_lossy().into_owned();
+    cfg.models.embedding.provider = "none".to_string();
+    cfg.models.embedding.dimensions = 0;
+
+    let docx = dir.path().join("doc.docx");
+    fs::write(&docx, b"fake docx bytes").unwrap();
+
+    let err = kebab_app::ingest_file_with_config(cfg, &docx).unwrap_err();
+    assert!(err.to_string().contains("unsupported extension"), "{err}");
+    assert!(
+        err.to_string().contains(".docx") || err.to_string().contains("docx"),
+        "{err}"
+    );
+}

crates/kebab-app/tests/ingest_lexical.rs

@@ -8,8 +8,7 @@ use common::TestEnv;
 #[test]
 fn ingest_then_list_inspects_round_trip() {
     let env = TestEnv::lexical_only();
-    let report =
-        kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
+    let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
 
     // The fixture has 3 markdown files; first ingest should label them
     // all as New.
@@ -27,17 +26,14 @@ fn ingest_then_list_inspects_round_trip() {
     }
 
     // list_docs returns the 3 docs.
-    let docs = kebab_app::list_docs_with_config(
-        env.config.clone(),
-        kebab_core::DocFilter::default(),
-    )
-    .unwrap();
+    let docs =
+        kebab_app::list_docs_with_config(env.config.clone(), kebab_core::DocFilter::default())
+            .unwrap();
     assert_eq!(docs.len(), 3, "docs: {docs:?}");
 
     // inspect_doc round-trips one of them.
     let any_doc_id = docs[0].doc_id.clone();
-    let canonical = kebab_app::inspect_doc_with_config(env.config.clone(), &any_doc_id)
-        .unwrap();
+    let canonical = kebab_app::inspect_doc_with_config(env.config.clone(), &any_doc_id).unwrap();
     assert_eq!(canonical.doc_id, any_doc_id);
     assert!(!canonical.blocks.is_empty(), "blocks empty");
 }
@@ -46,12 +42,10 @@ fn ingest_then_list_inspects_round_trip() {
 fn ingest_idempotent_on_second_run() {
     let env = TestEnv::lexical_only();
 
-    let r1 =
-        kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
+    let r1 = kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
     assert_eq!(r1.new, 3);
 
-    let r2 =
-        kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
+    let r2 = kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
     // Same files re-ingested — p9-fb-23 task 7 introduced the early-skip
     // path: when checksum + parser/chunker/embedding versions all match,
     // the second run reports `Unchanged` rather than `Updated`. Pre-p9-fb-23
@@ -63,19 +57,16 @@ fn ingest_idempotent_on_second_run() {
     assert_eq!(r2.unchanged, 3, "second run unchanged: {r2:?}");
 
     // list_docs still has 3 docs (no duplicates).
-    let docs = kebab_app::list_docs_with_config(
-        env.config.clone(),
-        kebab_core::DocFilter::default(),
-    )
-    .unwrap();
+    let docs =
+        kebab_app::list_docs_with_config(env.config.clone(), kebab_core::DocFilter::default())
+            .unwrap();
     assert_eq!(docs.len(), 3);
 }
 
 #[test]
 fn ingest_summary_only_drops_items() {
     let env = TestEnv::lexical_only();
-    let report =
-        kebab_app::ingest_with_config(env.config.clone(), env.scope(), true).unwrap();
+    let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), true).unwrap();
     assert_eq!(report.scanned, 3);
     assert!(report.items.is_none(), "summary-only should null items");
 }
@@ -87,12 +78,10 @@ fn ingest_records_ingest_runs_row_with_aggregate_counts() {
     // of every run. `summary_only=true` writes `items_json=NULL`; the
     // counts MUST still be present.
     let env = TestEnv::lexical_only();
-    let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), true)
-        .unwrap();
+    let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), true).unwrap();
     assert_eq!(report.scanned, 3);
 
-    let db_path = std::path::PathBuf::from(&env.config.storage.data_dir)
-        .join("kebab.sqlite");
+    let db_path = std::path::PathBuf::from(&env.config.storage.data_dir).join("kebab.sqlite");
     let conn = rusqlite::Connection::open(&db_path).expect("open kebab.sqlite");
     let (scanned, new_c, updated, skipped, errors, items_json): (
         i64,
@@ -141,25 +130,18 @@ fn ingest_provider_none_skips_lance() {
     // tree shape (no `<data_dir>/lancedb` directory, or no `*.lance`
     // tables under it).
     let env = TestEnv::lexical_only();
-    let report =
-        kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
+    let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
     assert_eq!(report.errors, 0, "lexical-only run must not error");
     assert_eq!(report.new, 3);
 
-    let lance_dir = std::path::PathBuf::from(&env.config.storage.data_dir)
-        .join("lancedb");
+    let lance_dir = std::path::PathBuf::from(&env.config.storage.data_dir).join("lancedb");
     if lance_dir.exists() {
         // If the dir was created (e.g., by an earlier consumer touching
         // the path), it MUST contain no `.lance` tables.
         let mut had_lance_table = false;
         for entry in std::fs::read_dir(&lance_dir).expect("read lance_dir") {
             let entry = entry.unwrap();
-            if entry
-                .path()
-                .extension()
-                .and_then(|s| s.to_str())
-                == Some("lance")
-            {
+            if entry.path().extension().and_then(|s| s.to_str()) == Some("lance") {
                 had_lance_table = true;
                 break;
             }
@@ -189,8 +171,7 @@ fn list_docs_filters_by_tags_any() {
         tags_any: vec!["rust".to_string()],
         ..Default::default()
     };
-    let rust_docs =
-        kebab_app::list_docs_with_config(env.config.clone(), rust_filter).unwrap();
+    let rust_docs = kebab_app::list_docs_with_config(env.config.clone(), rust_filter).unwrap();
     // intro.md and notes/cargo.md both tag "rust".
     assert_eq!(rust_docs.len(), 2, "expected 2 rust docs: {rust_docs:?}");
 }
@@ -198,8 +179,9 @@ fn list_docs_filters_by_tags_any() {
 #[test]
 fn inspect_doc_not_found_returns_actionable_error() {
     let env = TestEnv::lexical_only();
-    let bogus =
-        kebab_core::DocumentId("0000000000000000000000000000000000000000000000000000000000000000".to_string());
+    let bogus = kebab_core::DocumentId(
+        "0000000000000000000000000000000000000000000000000000000000000000".to_string(),
+    );
     let err = kebab_app::inspect_doc_with_config(env.config.clone(), &bogus).unwrap_err();
     let msg = format!("{err:#}");
     assert!(
@@ -218,8 +200,7 @@ fn inspect_chunk_not_found_returns_actionable_error() {
     let bogus = kebab_core::ChunkId(
         "0000000000000000000000000000000000000000000000000000000000000000".to_string(),
     );
-    let err = kebab_app::inspect_chunk_with_config(env.config.clone(), &bogus)
-        .unwrap_err();
+    let err = kebab_app::inspect_chunk_with_config(env.config.clone(), &bogus).unwrap_err();
     let msg = format!("{err:#}");
     assert!(msg.contains("not found"), "got: {msg}");
 }
@@ -251,22 +232,18 @@ fn ingest_with_config_opts_default_matches_legacy_behaviour() {
 #[test]
 fn ingest_stamps_chunker_version_on_document() {
     let env = TestEnv::lexical_only();
-    let report =
-        kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
+    let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
     assert!(report.new >= 1, "expected at least one new doc: {report:?}");
     assert_eq!(report.errors, 0, "no errors expected: {report:?}");
 
-    let docs = kebab_app::list_docs_with_config(
-        env.config.clone(),
-        kebab_core::DocFilter::default(),
-    )
-    .unwrap();
+    let docs =
+        kebab_app::list_docs_with_config(env.config.clone(), kebab_core::DocFilter::default())
+            .unwrap();
     assert!(!docs.is_empty(), "no docs after ingest");
 
     for doc_entry in &docs {
         let canonical =
-            kebab_app::inspect_doc_with_config(env.config.clone(), &doc_entry.doc_id)
-                .unwrap();
+            kebab_app::inspect_doc_with_config(env.config.clone(), &doc_entry.doc_id).unwrap();
         assert!(
             canonical.last_chunker_version.is_some(),
             "last_chunker_version must be stamped for doc {}: got {:?}",

crates/kebab-app/tests/ingest_log_smoke.rs

@@ -0,0 +1,171 @@
+// crates/kebab-app/tests/ingest_log_smoke.rs
+//
+// Integration tests for ingest_log feature (v0.20.x). Spec §5 AC-9 + AC-6.
+
+use std::path::PathBuf;
+
+use kebab_app::{IngestOpts, ingest_with_config_opts};
+use kebab_config::{Config, LoggingCfg};
+use kebab_core::SourceScope;
+use serde_json::Value;
+use tempfile::TempDir;
+
+fn minimal_config(workspace: &std::path::Path, log_dir: &std::path::Path) -> Config {
+    let data_dir = workspace.parent().unwrap().join("data");
+    std::fs::create_dir_all(&data_dir).unwrap();
+    let model_dir = workspace.parent().unwrap().join("models");
+    std::fs::create_dir_all(&model_dir).unwrap();
+
+    let mut cfg = Config::defaults();
+    cfg.workspace.root = workspace.to_string_lossy().into_owned();
+    cfg.workspace.exclude.clear();
+    cfg.storage.data_dir = data_dir.to_string_lossy().into_owned();
+    cfg.storage.model_dir = model_dir.to_string_lossy().into_owned();
+    cfg.models.embedding.provider = "none".to_string();
+    cfg.models.embedding.dimensions = 0;
+    cfg.chunking.target_tokens = 80;
+    cfg.chunking.overlap_tokens = 20;
+    cfg.logging = LoggingCfg {
+        ingest_log_enabled: true,
+        ingest_log_dir: log_dir.to_path_buf(),
+        ..Default::default()
+    };
+    cfg
+}
+
+/// AC-9: ingest → log file exists + each line valid JSON + last line kind=summary + scanned>0.
+#[test]
+fn ingest_log_smoke() {
+    let tmp = TempDir::new().unwrap();
+    let workspace = tmp.path().join("kb");
+    std::fs::create_dir_all(&workspace).unwrap();
+    let log_dir = tmp.path().join("logs");
+
+    // 1. Minimal corpus: 1 markdown + 1 scanned PDF (OCR disabled — no Ollama needed).
+    std::fs::write(
+        workspace.join("hello.md"),
+        "# Hello\n\nThis is a smoke test.\n",
+    )
+    .unwrap();
+    let pdf_src = PathBuf::from("../kebab-parse-pdf/tests/fixtures/scanned_page1.pdf");
+    if pdf_src.exists() {
+        std::fs::copy(&pdf_src, workspace.join("scanned.pdf")).unwrap();
+    }
+
+    // 2. Config with logging enabled.
+    let cfg = minimal_config(&workspace, &log_dir);
+    let scope = SourceScope {
+        root: workspace.clone(),
+        exclude: vec![],
+        ..Default::default()
+    };
+
+    // 3. Run ingest.
+    ingest_with_config_opts(cfg, scope, false, IngestOpts::default())
+        .expect("ingest should succeed");
+
+    // 4. Assert log file exists in log_dir.
+    let log_files: Vec<_> = std::fs::read_dir(&log_dir)
+        .unwrap()
+        .filter_map(Result::ok)
+        .filter(|e| {
+            e.file_name().to_string_lossy().starts_with("ingest-")
+                && e.file_name().to_string_lossy().ends_with(".ndjson")
+        })
+        .collect();
+    assert_eq!(
+        log_files.len(),
+        1,
+        "expected exactly 1 ingest-*.ndjson file, found: {log_files:?}"
+    );
+
+    // 5. Parse each line as JSON — assert kind field present and valid.
+    let body = std::fs::read_to_string(log_files[0].path()).unwrap();
+    let lines: Vec<&str> = body.lines().collect();
+    assert!(!lines.is_empty(), "log file should not be empty");
+
+    let valid_kinds = ["ocr", "parse_error", "skip", "error", "summary"];
+    for line in &lines {
+        let v: Value = serde_json::from_str(line)
+            .unwrap_or_else(|e| panic!("line is not valid JSON: {e}\nline: {line}"));
+        let kind = v
+            .get("kind")
+            .and_then(|k| k.as_str())
+            .unwrap_or_else(|| panic!("line missing 'kind' field: {line}"));
+        assert!(
+            valid_kinds.contains(&kind),
+            "unexpected kind '{kind}' in line: {line}"
+        );
+    }
+
+    // 6. Last line must be kind=summary with scanned > 0.
+    let last = lines.last().unwrap();
+    let last_v: Value = serde_json::from_str(last).unwrap();
+    assert_eq!(
+        last_v.get("kind").and_then(|k| k.as_str()),
+        Some("summary"),
+        "last line must be kind=summary, got: {last}"
+    );
+    let scanned = last_v.get("scanned").and_then(Value::as_u64).unwrap_or(0);
+    assert!(scanned > 0, "summary.scanned should be > 0, got: {last}");
+}
+
+/// AC-6: ingest_log_enabled=false → no log file created.
+#[test]
+fn ingest_log_disabled_emits_no_file() {
+    let tmp = TempDir::new().unwrap();
+    let workspace = tmp.path().join("kb");
+    std::fs::create_dir_all(&workspace).unwrap();
+    let log_dir = tmp.path().join("logs");
+
+    std::fs::write(
+        workspace.join("hello.md"),
+        "# Hello\n\nDisabled log test.\n",
+    )
+    .unwrap();
+
+    let data_dir = tmp.path().join("data");
+    std::fs::create_dir_all(&data_dir).unwrap();
+    let model_dir = tmp.path().join("models");
+    std::fs::create_dir_all(&model_dir).unwrap();
+
+    let mut cfg = Config::defaults();
+    cfg.workspace.root = workspace.to_string_lossy().into_owned();
+    cfg.workspace.exclude.clear();
+    cfg.storage.data_dir = data_dir.to_string_lossy().into_owned();
+    cfg.storage.model_dir = model_dir.to_string_lossy().into_owned();
+    cfg.models.embedding.provider = "none".to_string();
+    cfg.models.embedding.dimensions = 0;
+    cfg.logging = LoggingCfg {
+        ingest_log_enabled: false,
+        ingest_log_dir: log_dir.clone(),
+        ..Default::default()
+    };
+
+    let scope = SourceScope {
+        root: workspace.clone(),
+        exclude: vec![],
+        ..Default::default()
+    };
+
+    ingest_with_config_opts(cfg, scope, false, IngestOpts::default())
+        .expect("ingest should succeed");
+
+    // log_dir should either not exist or contain 0 ingest-*.ndjson files.
+    let log_file_count = if log_dir.exists() {
+        std::fs::read_dir(&log_dir)
+            .unwrap()
+            .filter_map(Result::ok)
+            .filter(|e| {
+                e.file_name().to_string_lossy().starts_with("ingest-")
+                    && e.file_name().to_string_lossy().ends_with(".ndjson")
+            })
+            .count()
+    } else {
+        0
+    };
+    assert_eq!(
+        log_file_count, 0,
+        "no ingest-*.ndjson file should be created when disabled"
+    );
+}

crates/kebab-app/tests/ingest_pdf_ocr_smoke.rs

@@ -0,0 +1,117 @@
+//! Integration smoke tests for the PDF OCR pipeline (§ Acceptance §9 #1 + #2).
+//!
+//! Tests 1 and 2 require a live Ollama endpoint — `#[ignore]` by default.
+//! Manual invoke:
+//!   KEBAB_PDF_OCR_ENDPOINT=http://192.168.0.47:11434 \
+//!     cargo test -p kebab-app --test ingest_pdf_ocr_smoke --ignored -j 4
+//!
+//! Test 3 (cancel) uses a dummy endpoint + pre-set cancel — runs by default
+//! to verify the cancel wiring doesn't panic/deadlock.
+
+mod common;
+
+use std::path::PathBuf;
+use std::sync::Arc;
+use std::sync::atomic::AtomicBool;
+
+use common::TestEnv;
+
+fn ollama_endpoint() -> String {
+    std::env::var("KEBAB_PDF_OCR_ENDPOINT").unwrap_or_else(|_| "http://localhost:11434".to_string())
+}
+
+fn make_ocr_env_real() -> TestEnv {
+    let mut env = TestEnv::lexical_only();
+    env.config.pdf.ocr.enabled = true;
+    env.config.pdf.ocr.endpoint = Some(ollama_endpoint());
+    env.config.models.embedding.provider = "none".to_string();
+
+    let src = PathBuf::from(env!("CARGO_MANIFEST_DIR"))
+        .parent()
+        .unwrap()
+        .join("kebab-parse-pdf/tests/fixtures/scanned_page1.pdf");
+    let dest = env.workspace_root.join("scanned_page1.pdf");
+    std::fs::copy(&src, &dest).expect("copy scanned_page1.pdf to workspace");
+
+    env
+}
+
+/// § Acceptance §9 #1 — real Ollama OCR + IngestItem.pdf_ocr_pages = Some(1).
+#[test]
+#[ignore = "real Ollama qwen2.5vl:3b dependency"]
+fn ingest_with_mock_ocr_yields_pdf_ocr_summary() {
+    let env = make_ocr_env_real();
+
+    let report =
+        kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).expect("ingest");
+
+    assert!(report.new >= 1, "at least one PDF ingested: {report:?}");
+
+    let items = report.items.unwrap_or_default();
+    let pdf_item = items.iter().find(|i| i.doc_path.0.ends_with(".pdf"));
+    assert!(
+        pdf_item.is_some(),
+        "PDF item must appear in ingest report items: {items:?}"
+    );
+    let pdf_item = pdf_item.unwrap();
+    assert!(
+        pdf_item.pdf_ocr_pages.is_some(),
+        "pdf_ocr_pages must be set for scanned PDF: {pdf_item:?}"
+    );
+    assert_eq!(
+        pdf_item.pdf_ocr_pages.unwrap(),
+        1,
+        "scanned_page1.pdf has exactly 1 page"
+    );
+}
+
+/// § Acceptance §9 #2 — OCR text indexed and retrievable via lexical search.
+#[test]
+#[ignore = "real Ollama qwen2.5vl:3b dependency"]
+fn ocr_text_indexed_and_searchable() {
+    let env = make_ocr_env_real();
+
+    kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).expect("ingest");
+
+    // Search for a Korean morpheme expected to appear in qwen2.5vl:3b OCR
+    // output of the PoC ground-truth page. "다음" is a high-frequency token
+    // in page1.txt truth file.
+    let query = common::lexical_query("다음");
+    let hits = kebab_app::search_with_config(env.config.clone(), query).expect("search");
+
+    assert!(
+        !hits.is_empty(),
+        "OCR-indexed text must surface in lexical search results"
+    );
+}
+
+/// Production cancel wiring smoke — pre-set cancel exits before any OCR call.
+/// Dummy endpoint (port 1 = connection-refused) means OCR HTTP calls would
+/// fail, but cancel=true prevents the loop from reaching OCR at all.
+/// Verifies no panic/deadlock regardless of Ok/Err outcome.
+#[test]
+fn ingest_with_cancel_aborts_mid_pdf() {
+    let mut env = TestEnv::lexical_only();
+    env.config.pdf.ocr.enabled = true;
+    env.config.pdf.ocr.endpoint = Some("http://127.0.0.1:1".to_string());
+
+    let src = PathBuf::from(env!("CARGO_MANIFEST_DIR"))
+        .parent()
+        .unwrap()
+        .join("kebab-parse-pdf/tests/fixtures/scanned_page1.pdf");
+    let dest = env.workspace_root.join("scanned_page1.pdf");
+    std::fs::copy(&src, &dest).expect("copy scanned_page1.pdf to workspace");
+
+    let cancel = Arc::new(AtomicBool::new(true)); // pre-set — abort immediately
+
+    let result = kebab_app::ingest_with_config_cancellable(
+        env.config.clone(),
+        env.scope(),
+        false,
+        None,
+        Some(cancel),
+    );
+    // Both Ok (pre-cancel exit) and Err (eager OCR engine fail) are acceptable —
+    // key assertion is no panic/deadlock.
+    let _ = result;
+}

crates/kebab-app/tests/ingest_progress.rs

@@ -13,13 +13,9 @@ use kebab_core::IngestItemKind;
 fn run_with_progress() -> Vec<IngestEvent> {
     let env = TestEnv::lexical_only();
     let (tx, rx) = mpsc::channel::<IngestEvent>();
-    let report = kebab_app::ingest_with_config_progress(
-        env.config.clone(),
-        env.scope(),
-        false,
-        Some(tx),
-    )
-    .unwrap();
+    let report =
+        kebab_app::ingest_with_config_progress(env.config.clone(), env.scope(), false, Some(tx))
+            .unwrap();
     assert_eq!(report.scanned, 3);
     assert_eq!(report.new, 3);
 
@@ -73,40 +69,74 @@ fn progress_event_sequence_matches_design_section_2_4a() {
         other => panic!("expected Completed last, got {other:?}"),
     }
 
-    // Middle: 3 AssetStarted/AssetFinished pairs in monotonic idx order.
-    let asset_events: Vec<&IngestEvent> = events[2..events.len() - 1].iter().collect();
-    assert_eq!(
-        asset_events.len(),
-        6,
-        "expected 3 (Started + Finished) pairs, got {asset_events:?}"
-    );
-    for (chunk_idx, pair) in asset_events.chunks(2).enumerate() {
-        let expected_idx = chunk_idx as u32 + 1;
-        match (pair[0], pair[1]) {
-            (
-                IngestEvent::AssetStarted {
-                    idx: si,
-                    total: st,
-                    media,
-                    ..
-                },
-                IngestEvent::AssetFinished {
-                    idx: fi,
-                    total: ft,
-                    result,
-                    chunks,
-                },
-            ) => {
-                assert_eq!(*si, expected_idx, "Started idx mismatch: {pair:?}");
-                assert_eq!(*fi, expected_idx, "Finished idx mismatch: {pair:?}");
-                assert_eq!(*st, 3, "Started total mismatch");
-                assert_eq!(*ft, 3, "Finished total mismatch");
-                assert_eq!(media, "markdown", "fixture is markdown only");
-                assert_eq!(*result, IngestItemKind::New, "first ingest → New");
-                assert!(*chunks >= 1, "chunks: {pair:?}");
+    // Middle (v0.24.0 ordering invariant §2.4a): per asset the stream is
+    //   AssetStarted < AssetChunked < [ExpansionProgress*] < AssetTimings
+    //     < AssetFinished
+    // Expansion is disabled in the lexical fixture, so no ExpansionProgress
+    // frames appear here — but AssetChunked + AssetTimings are emitted for
+    // every markdown asset.
+    let middle = &events[2..events.len() - 1];
+
+    // 3 AssetStarted events, monotonic idx 1..=3, all markdown, total = 3.
+    let started: Vec<u32> = middle
+        .iter()
+        .filter_map(|e| match e {
+            IngestEvent::AssetStarted {
+                idx, total, media, ..
+            } => {
+                assert_eq!(*total, 3, "Started total mismatch: {e:?}");
+                assert_eq!(media, "markdown", "fixture is markdown only: {e:?}");
+                Some(*idx)
             }
-            other => panic!("expected Started+Finished pair, got {other:?}"),
-        }
+            _ => None,
+        })
+        .collect();
+    assert_eq!(started, vec![1, 2, 3], "AssetStarted idx order: {middle:?}");
+
+    // 3 AssetFinished events, monotonic idx 1..=3, each New with ≥1 chunk.
+    let finished: Vec<u32> = middle
+        .iter()
+        .filter_map(|e| match e {
+            IngestEvent::AssetFinished {
+                idx,
+                total,
+                result,
+                chunks,
+            } => {
+                assert_eq!(*total, 3, "Finished total mismatch: {e:?}");
+                assert_eq!(*result, IngestItemKind::New, "first ingest → New: {e:?}");
+                assert!(*chunks >= 1, "chunks: {e:?}");
+                Some(*idx)
+            }
+            _ => None,
+        })
+        .collect();
+    assert_eq!(finished, vec![1, 2, 3], "AssetFinished idx order: {middle:?}");
+
+    // v0.24.0 additive events: exactly one AssetChunked + one AssetTimings
+    // per asset, each strictly bracketed by that asset's Started / Finished.
+    for target in 1u32..=3 {
+        let started_at = middle
+            .iter()
+            .position(|e| matches!(e, IngestEvent::AssetStarted { idx, .. } if *idx == target))
+            .unwrap_or_else(|| panic!("missing AssetStarted for idx {target}: {middle:?}"));
+        let finished_at = middle
+            .iter()
+            .position(|e| matches!(e, IngestEvent::AssetFinished { idx, .. } if *idx == target))
+            .unwrap_or_else(|| panic!("missing AssetFinished for idx {target}: {middle:?}"));
+        let chunked_at = middle
+            .iter()
+            .position(|e| matches!(e, IngestEvent::AssetChunked { idx, chunks, .. } if *idx == target && *chunks >= 1))
+            .unwrap_or_else(|| panic!("missing AssetChunked for idx {target}: {middle:?}"));
+        let timings_at = middle
+            .iter()
+            .position(|e| matches!(e, IngestEvent::AssetTimings { idx, .. } if *idx == target))
+            .unwrap_or_else(|| panic!("missing AssetTimings for idx {target}: {middle:?}"));
+        assert!(
+            started_at < chunked_at && chunked_at < timings_at && timings_at < finished_at,
+            "idx {target} ordering: started={started_at} chunked={chunked_at} \
+             timings={timings_at} finished={finished_at}: {middle:?}"
+        );
     }
 }
 
@@ -116,13 +146,9 @@ fn ingest_with_config_progress_none_matches_ingest_with_config() {
     // `ingest_with_config_progress(..., None)` must produce identical
     // reports modulo wall-clock duration.
     let env = TestEnv::lexical_only();
-    let r_none = kebab_app::ingest_with_config_progress(
-        env.config.clone(),
-        env.scope(),
-        true,
-        None,
-    )
-    .unwrap();
+    let r_none =
+        kebab_app::ingest_with_config_progress(env.config.clone(), env.scope(), true, None)
+            .unwrap();
     assert_eq!(r_none.scanned, 3);
     assert_eq!(r_none.new, 3);
 }
@@ -134,12 +160,77 @@ fn dropped_receiver_does_not_panic_or_fail_ingest() {
     let env = TestEnv::lexical_only();
     let (tx, rx) = mpsc::channel::<IngestEvent>();
     drop(rx);
-    let report = kebab_app::ingest_with_config_progress(
-        env.config.clone(),
-        env.scope(),
-        true,
-        Some(tx),
-    )
-    .unwrap();
+    let report =
+        kebab_app::ingest_with_config_progress(env.config.clone(), env.scope(), true, Some(tx))
+            .unwrap();
     assert_eq!(report.scanned, 3);
 }
+
+/// v0.20.0 sub-item 1: pdf_ocr_started + pdf_ocr_finished events 가 PDF asset 의
+/// OCR-enabled ingest 시 emit 됨을 검증. real Ollama 의존 — `#[ignore]` default.
+///
+/// Manual invoke:
+/// ```
+/// KEBAB_PDF_OCR_ENABLED=true \
+///   KEBAB_PDF_OCR_ENDPOINT=http://192.168.0.47:11434 \
+///   cargo test -p kebab-app --test ingest_progress \
+///   --ignored pdf_ocr_progress_emits_started_finished_events
+/// ```
+#[test]
+#[ignore = "real Ollama dependency — manual invoke via KEBAB_PDF_OCR_ENABLED=true"]
+fn pdf_ocr_progress_emits_started_finished_events() {
+    // F1 fixture (DCTDecode JPEG passthrough) 을 tmpdir 의 workspace 로 copy.
+    let tmpdir = tempfile::tempdir().expect("create tmpdir");
+    let workspace = tmpdir.path().join("workspace");
+    std::fs::create_dir_all(&workspace).expect("create workspace dir");
+    let f1_src = std::path::PathBuf::from(env!("CARGO_MANIFEST_DIR"))
+        .join("../kebab-parse-pdf/tests/fixtures/scanned_page1.pdf");
+    let f1 = std::fs::read(&f1_src).expect("F1 fixture present");
+    std::fs::write(workspace.join("page1.pdf"), &f1).expect("copy F1");
+
+    let data_dir = tmpdir.path().join("data");
+    std::fs::create_dir_all(&data_dir).expect("create data dir");
+
+    let mut config = kebab_config::Config::defaults();
+    config.workspace.root = workspace.to_string_lossy().into_owned();
+    config.storage.data_dir = data_dir.to_string_lossy().into_owned();
+    config.models.embedding.provider = "none".to_string();
+    config.models.embedding.dimensions = 0;
+    config.pdf.ocr.enabled = true;
+    if let Ok(endpoint) = std::env::var("KEBAB_PDF_OCR_ENDPOINT") {
+        config.pdf.ocr.endpoint = Some(endpoint);
+    }
+
+    let scope = kebab_core::SourceScope {
+        root: workspace.clone(),
+        ..Default::default()
+    };
+
+    let (tx, rx) = mpsc::channel::<IngestEvent>();
+    let _report = kebab_app::ingest_with_config_progress(config, scope, false, Some(tx))
+        .expect("ingest_with_config_progress");
+
+    let events: Vec<_> = rx.iter().collect();
+
+    let started_count = events
+        .iter()
+        .filter(|e| matches!(e, IngestEvent::PdfOcrStarted { .. }))
+        .count();
+    let finished_count = events
+        .iter()
+        .filter(|e| matches!(e, IngestEvent::PdfOcrFinished { .. }))
+        .count();
+
+    assert!(
+        started_count >= 1,
+        "PdfOcrStarted 가 ≥ 1 emit 됨 (got {started_count})"
+    );
+    assert!(
+        finished_count >= 1,
+        "PdfOcrFinished 가 ≥ 1 emit 됨 (got {finished_count})"
+    );
+    assert_eq!(
+        started_count, finished_count,
+        "Started 와 Finished 의 count 일치"
+    );
+}

crates/kebab-app/tests/ingest_stdin.rs

@@ -0,0 +1,77 @@
+//! Integration: kebab_app::ingest_stdin_with_config injects frontmatter,
+//! writes to _external/, ingests as single asset.
+
+use std::fs;
+
+use kebab_config::Config;
+
+fn fresh_cfg(dir: &std::path::Path) -> Config {
+    let workspace = dir.join("notes");
+    let data = dir.join("data");
+    fs::create_dir_all(&workspace).unwrap();
+    fs::create_dir_all(&data).unwrap();
+
+    let mut cfg = Config::defaults();
+    cfg.workspace.root = workspace.to_string_lossy().into_owned();
+    cfg.storage.data_dir = data.to_string_lossy().into_owned();
+    cfg.models.embedding.provider = "none".to_string();
+    cfg.models.embedding.dimensions = 0;
+    cfg
+}
+
+#[test]
+fn ingest_stdin_writes_frontmatter_and_reports_new() {
+    let dir = tempfile::tempdir().unwrap();
+    let cfg = fresh_cfg(dir.path());
+
+    let report = kebab_app::ingest_stdin_with_config(
+        cfg.clone(),
+        "## Body content\n\nMore.",
+        "Article X",
+        Some("https://example.com/x"),
+    )
+    .unwrap();
+    assert_eq!(report.new, 1, "{report:?}");
+
+    // _external/ contains exactly one .md file with frontmatter.
+    let ext_dir = std::path::PathBuf::from(&cfg.workspace.root).join("_external");
+    let entries: Vec<_> = fs::read_dir(&ext_dir)
+        .unwrap()
+        .filter_map(std::result::Result::ok)
+        .collect();
+    assert_eq!(entries.len(), 1);
+    let content = fs::read_to_string(entries[0].path()).unwrap();
+    assert!(content.starts_with("---\n"));
+    assert!(content.contains("title: \"Article X\""));
+    assert!(content.contains("source_uri: \"https://example.com/x\""));
+    assert!(content.contains("## Body content"));
+}
+
+#[test]
+fn ingest_stdin_without_source_uri() {
+    let dir = tempfile::tempdir().unwrap();
+    let cfg = fresh_cfg(dir.path());
+
+    let report =
+        kebab_app::ingest_stdin_with_config(cfg.clone(), "## Body", "Title", None).unwrap();
+    assert_eq!(report.new, 1);
+
+    let ext_dir = std::path::PathBuf::from(&cfg.workspace.root).join("_external");
+    let entries: Vec<_> = fs::read_dir(&ext_dir)
+        .unwrap()
+        .filter_map(std::result::Result::ok)
+        .collect();
+    let content = fs::read_to_string(entries[0].path()).unwrap();
+    assert!(content.contains("title: \"Title\""));
+    assert!(!content.contains("source_uri"));
+}
+
+#[test]
+fn ingest_stdin_errors_on_existing_frontmatter() {
+    let dir = tempfile::tempdir().unwrap();
+    let cfg = fresh_cfg(dir.path());
+
+    let body = "---\ntitle: Already\n---\n\n## Body";
+    let err = kebab_app::ingest_stdin_with_config(cfg, body, "New", None).unwrap_err();
+    assert!(err.to_string().contains("already has frontmatter"), "{err}");
+}

crates/kebab-app/tests/init_template.rs

@@ -17,9 +17,8 @@ fn init_workspace_header_lists_supported_extensions() {
     }
     kebab_app::init_workspace(true).expect("init_workspace");
     let cfg_path = kebab_config::Config::xdg_config_path();
-    let body = std::fs::read_to_string(&cfg_path).unwrap_or_else(|e| {
-        panic!("read config at {}: {e}", cfg_path.display())
-    });
+    let body = std::fs::read_to_string(&cfg_path)
+        .unwrap_or_else(|e| panic!("read config at {}: {e}", cfg_path.display()));
     assert!(
         body.contains("처리 가능한 형식"),
         "header lists supported types section: body=\n{body}"

crates/kebab-app/tests/multi_scanned_pdf_ingest_no_chunk_id_collision.rs

@@ -0,0 +1,122 @@
+//! Bug #3 regression: multi-scanned PDF ingest must produce globally unique chunk_ids.
+//! v0.20.0 sub-item 1 bugfix.
+//!
+//! Strategy: helper-level chain test (apply_ocr_to_pdf_pages → PdfPageV1Chunker).
+//! Facade mock injection is unavailable (kebab-app hardcodes OllamaVisionOcr), so
+//! this test covers the full OCR→chunk pipeline with real PDF fixtures + MockOcrEngine,
+//! adding value beyond kebab-chunk unit test B5 (which tests PdfPageV1Chunker alone).
+
+mod common;
+
+use std::collections::HashSet;
+use std::path::{Path, PathBuf};
+
+use common::mock_ocr::MockOcrEngine;
+use kebab_app::pdf_ocr_apply::{PdfOcrOpts, apply_ocr_to_pdf_pages};
+use kebab_chunk::PdfPageV1Chunker;
+use kebab_core::{
+    AssetStorage, Checksum, ChunkPolicy, Chunker, ExtractConfig, ExtractContext, Extractor,
+    MediaType, RawAsset, SourceUri, WorkspacePath, id_for_asset,
+};
+use kebab_parse_image::OcrEngine;
+use kebab_parse_pdf::PdfTextExtractor;
+use time::OffsetDateTime;
+
+fn make_pdf_asset(path: &str, hash_char: char, byte_len: u64) -> RawAsset {
+    let fake_hash: String = hash_char.to_string().repeat(64);
+    let asset_id = id_for_asset(&fake_hash);
+    RawAsset {
+        asset_id,
+        source_uri: SourceUri::File(PathBuf::from(path)),
+        workspace_path: WorkspacePath::new(path.to_string()).unwrap(),
+        media_type: MediaType::Pdf,
+        byte_len,
+        checksum: Checksum(fake_hash),
+        discovered_at: OffsetDateTime::UNIX_EPOCH,
+        stored: AssetStorage::Copied {
+            path: PathBuf::from(path),
+        },
+    }
+}
+
+fn extract_and_ocr(
+    bytes: &[u8],
+    path: &str,
+    hash_char: char,
+    engine: &dyn OcrEngine,
+) -> kebab_core::CanonicalDocument {
+    let asset = make_pdf_asset(path, hash_char, bytes.len() as u64);
+    let workspace_root = Path::new("/");
+    let config = ExtractConfig::default();
+    let ctx = ExtractContext {
+        asset: &asset,
+        workspace_root,
+        config: &config,
+    };
+    let mut canonical = PdfTextExtractor::new().extract(&ctx, bytes).unwrap();
+    let opts = PdfOcrOpts {
+        enabled: true,
+        always_on: false,
+        valid_ratio_threshold: 0.5,
+        min_char_count: 20,
+        lang_hint: None,
+        cancel: None,
+    };
+    apply_ocr_to_pdf_pages(&mut canonical, engine, bytes, &opts, |_| {}).unwrap();
+    canonical
+}
+
+#[test]
+fn multi_scanned_pdf_ingest_no_chunk_id_collision() {
+    let f1_bytes = std::fs::read("../kebab-parse-pdf/tests/fixtures/scanned_page1.pdf")
+        .expect("F1 fixture missing");
+    let f2_bytes = std::fs::read("../kebab-parse-pdf/tests/fixtures/scanned_page2.pdf")
+        .expect("F2 fixture missing");
+
+    // Bug #3 trigger shape: 10-char early segment + ". " + 500-char tail.
+    // byte_len = 10*3 + 2 + 500*3 = 1532 > target_bytes=1500 → multi-chunk.
+    // overlap_bytes = min(240, 750) = 240 / chars=80 → second chunk's actual_start
+    // collapses to prev_min=0 without the fix → same #c0 suffix → chunk_id collision.
+    let trigger_text = format!("{}. {}", "가".repeat(10), "나".repeat(500));
+
+    let f1_engine = MockOcrEngine::single("F1 mock OCR page text", false);
+    let f2_engine = MockOcrEngine::single(&trigger_text, false);
+
+    let f1_canonical = extract_and_ocr(&f1_bytes, "page1.pdf", '1', &f1_engine);
+    let f2_canonical = extract_and_ocr(&f2_bytes, "page2.pdf", '2', &f2_engine);
+
+    let chunk_policy = ChunkPolicy {
+        target_tokens: 500,
+        overlap_tokens: 80,
+        respect_markdown_headings: false,
+        chunker_version: PdfPageV1Chunker.chunker_version(),
+    };
+
+    let f1_chunks = PdfPageV1Chunker
+        .chunk(&f1_canonical, &chunk_policy)
+        .unwrap();
+    let f2_chunks = PdfPageV1Chunker
+        .chunk(&f2_canonical, &chunk_policy)
+        .unwrap();
+
+    assert!(
+        f2_chunks.len() >= 2,
+        "F2 trigger text must produce ≥2 chunks for the collision to be possible; got {}",
+        f2_chunks.len()
+    );
+
+    let all_ids: Vec<&str> = f1_chunks
+        .iter()
+        .chain(f2_chunks.iter())
+        .map(|c| c.chunk_id.0.as_str())
+        .collect();
+    let total = all_ids.len();
+    let unique: HashSet<&str> = all_ids.iter().copied().collect();
+    assert_eq!(
+        unique.len(),
+        total,
+        "all chunk_ids must be globally unique across F1 + F2 ({} unique vs {} total — collision detected)",
+        unique.len(),
+        total,
+    );
+}

crates/kebab-app/tests/ocr_inspect_smoke.rs

@@ -0,0 +1,156 @@
+//! Integration smoke tests for `kebab inspect ocr-stats / ocr-failures`.
+//! AC-4, AC-5, AC-6, AC-11 (ocr_inspect_smoke binary), AC-13.
+
+mod common;
+
+use common::TestEnv;
+use kebab_app::App;
+use kebab_store_sqlite::SqliteStore;
+
+/// Insert synthetic pdf_ocr_events rows directly so the test runs without
+/// a live Ollama endpoint.
+fn seed_ocr_events(env: &TestEnv, store: &SqliteStore) {
+    // Success rows
+    for i in 0..3u32 {
+        store
+            .record_pdf_ocr_event(
+                "run-aaa",
+                &format!("2026-05-28T0{i}:00:00Z"),
+                Some("doc-abc"),
+                "path/scanned.pdf",
+                i + 1,
+                Some(50_000),
+                Some(200),
+                Some(150),
+                100 + u64::from(i) * 20,
+                42,
+                true,
+                None,
+                "qwen2.5vl",
+            )
+            .expect("seed success row");
+    }
+    // Failure row
+    store
+        .record_pdf_ocr_event(
+            "run-bbb",
+            "2026-05-28T10:00:00Z",
+            Some("doc-abc"),
+            "path/scanned.pdf",
+            4,
+            Some(30_000),
+            Some(200),
+            Some(150),
+            9999,
+            0,
+            false,
+            Some("ocr_error"),
+            "qwen2.5vl",
+        )
+        .expect("seed failure row");
+    // Row for different doc
+    store
+        .record_pdf_ocr_event(
+            "run-ccc",
+            "2026-05-28T11:00:00Z",
+            Some("doc-xyz"),
+            "path/other.pdf",
+            1,
+            None,
+            None,
+            None,
+            200,
+            10,
+            true,
+            None,
+            "qwen2.5vl",
+        )
+        .expect("seed doc-xyz row");
+    // Trigger migration (no-op if already done via App::open_with_config)
+    let _ = env;
+}
+
+fn open_app_with_seeded_events(env: &TestEnv) -> App {
+    let app = env.app();
+    let store = SqliteStore::open(&env.config).expect("open store for seed");
+    store.run_migrations().expect("run migrations for seed");
+    seed_ocr_events(env, &store);
+    app
+}
+
+/// AC-4: `inspect_ocr_stats` returns `schema_version = "ocr_stats.v1"`,
+/// `total_events >= 1`, `0 ≤ success_rate ≤ 1`.
+#[test]
+fn ocr_stats_after_seeded_events() {
+    let env = TestEnv::lexical_only();
+    let app = open_app_with_seeded_events(&env);
+
+    let stats = app.inspect_ocr_stats().expect("inspect_ocr_stats");
+
+    assert_eq!(stats.schema_version, "ocr_stats.v1");
+    assert!(stats.total_events >= 1, "total_events should be >= 1");
+    assert!(
+        (0.0..=1.0).contains(&stats.success_rate),
+        "success_rate must be in [0, 1]: {}",
+        stats.success_rate
+    );
+    assert!(stats.total_runs >= 1, "total_runs should be >= 1");
+    // by_engine should have at least one entry
+    assert!(!stats.by_engine.is_empty(), "by_engine must be non-empty");
+}
+
+/// AC-6: `inspect_ocr_failures` (no doc_id, corpus-wide) returns failures list.
+#[test]
+fn ocr_failures_corpus_wide() {
+    let env = TestEnv::lexical_only();
+    let app = open_app_with_seeded_events(&env);
+
+    let result = app
+        .inspect_ocr_failures(None, 10)
+        .expect("inspect_ocr_failures");
+
+    assert_eq!(result.schema_version, "ocr_failures.v1");
+    assert!(result.failure_count >= 1, "expected at least 1 failure");
+    assert!(
+        !result.failures.is_empty(),
+        "failures list must be non-empty"
+    );
+}
+
+/// AC-5: `inspect_ocr_failures` with doc_id filter returns matching rows.
+#[test]
+fn ocr_failures_filter_by_doc_id() {
+    let env = TestEnv::lexical_only();
+    let app = open_app_with_seeded_events(&env);
+
+    let result = app
+        .inspect_ocr_failures(Some("doc-abc"), 10)
+        .expect("inspect_ocr_failures by doc_id");
+
+    assert_eq!(result.schema_version, "ocr_failures.v1");
+    assert_eq!(
+        result.doc_id.as_deref(),
+        Some("doc-abc"),
+        "doc_id must be echoed back"
+    );
+    // All rows must belong to doc-abc (no cross-doc leak)
+    for row in &result.failures {
+        // rows are failure rows for doc-abc only (reason = ocr_error)
+        assert_eq!(row.reason, "ocr_error");
+    }
+}
+
+/// AC-13: SKILL.md lists both new wire schemas.
+#[test]
+fn skill_md_lists_new_schemas() {
+    let skill_md = std::fs::read_to_string("../../integrations/claude-code/kebab/SKILL.md")
+        .expect("read SKILL.md");
+    assert!(
+        skill_md.contains("ocr_stats.v1"),
+        "SKILL.md must mention ocr_stats.v1"
+    );
+    assert!(
+        skill_md.contains("ocr_failures.v1"),
+        "SKILL.md must mention ocr_failures.v1"
+    );
+}

crates/kebab-app/tests/open_with_config_nli.rs

@@ -0,0 +1,81 @@
+//! Tests for `App::open_with_config`'s NLI verifier construction path.
+//!
+//! Coverage:
+//! 1. `open_with_config_nli_fails_when_model_dir_unwritable_and_threshold_positive` —
+//!    when `rag.nli_threshold > 0` and `storage.model_dir` is unwritable,
+//!    `open_with_config` returns `Err` with "OnnxNliVerifier" in the
+//!    error chain.
+//! 2. `open_with_config_nli_skipped_when_threshold_zero` —
+//!    same bad `model_dir`, but `rag.nli_threshold = 0.0` (gate disabled),
+//!    so `OnnxNliVerifier::new` is never called and `open_with_config`
+//!    succeeds.
+//!
+//! `/proc/1/root` is the init process's filesystem root; on Linux it is
+//! owned by root and not traversable by unprivileged users, making
+//! `create_dir_all` fail with `EACCES` — a reliable "unwritable path"
+//! that requires no test setup beyond the path literal.
+
+use kebab_config::Config;
+
+/// Return a `Config` whose `data_dir` lives in a fresh `TempDir`
+/// (so `SqliteStore::open` succeeds) and whose `model_dir` is set to
+/// `/proc/1/root` (unwritable by non-root processes on Linux).
+///
+/// The `TempDir` is returned alongside the config so the caller keeps
+/// it alive until the test completes — dropping it early would delete
+/// the data directory before any assertions run.
+fn config_with_unwritable_model_dir() -> (tempfile::TempDir, Config) {
+    let tmp = tempfile::tempdir().expect("tempdir");
+    let mut cfg = Config::defaults();
+    // Valid data_dir → SqliteStore::open + run_migrations succeed.
+    cfg.storage.data_dir = tmp.path().to_string_lossy().into_owned();
+    // /proc/1/root is only accessible to root; create_dir_all will
+    // return EACCES for any unprivileged user, which is exactly the
+    // failure mode we want to exercise.
+    cfg.storage.model_dir = "/proc/1/root".to_string();
+    (tmp, cfg)
+}
+
+// ── 1. Failure path: threshold > 0 + unwritable model_dir ─────────────────
+
+#[test]
+fn open_with_config_nli_fails_when_model_dir_unwritable_and_threshold_positive() {
+    let (_tmp, mut cfg) = config_with_unwritable_model_dir();
+    cfg.rag.nli_threshold = 0.5; // gate enabled → OnnxNliVerifier::new runs
+
+    let result = kebab_app::App::open_with_config(cfg);
+
+    let Err(err) = result else {
+        panic!(
+            "App::open_with_config must fail when model_dir is unwritable and nli_threshold > 0"
+        );
+    };
+    // The error chain must identify the OnnxNliVerifier as the source so
+    // an operator reading logs can trace the failure to the NLI config.
+    let err_chain = format!("{err:?}");
+    assert!(
+        err_chain.contains("OnnxNliVerifier"),
+        "error chain must mention OnnxNliVerifier; full chain: {err_chain}"
+    );
+}
+
+// ── 2. Success path: threshold = 0.0 → NLI verifier never constructed ──────
+
+#[test]
+fn open_with_config_nli_skipped_when_threshold_zero() {
+    let (_tmp, cfg) = config_with_unwritable_model_dir();
+    // Default nli_threshold is 0.0 — gate disabled, verifier skipped.
+    assert!(
+        (cfg.rag.nli_threshold - 0.0).abs() < f32::EPSILON,
+        "precondition: default nli_threshold must be 0.0 (gate disabled)"
+    );
+
+    // A bad model_dir must NOT cause a failure when the NLI gate is off.
+    let result = kebab_app::App::open_with_config(cfg);
+    assert!(
+        result.is_ok(),
+        "App::open_with_config must succeed when nli_threshold = 0.0 \
+         (OnnxNliVerifier is never constructed); err: {:?}",
+        result.err()
+    );
+}

crates/kebab-app/tests/pdf_ocr_apply.rs

@@ -0,0 +1,358 @@
+//! Integration tests for pdf_ocr_apply helper. spec §5.5 MockOcrEngine pattern.
+
+mod common;
+
+use std::path::{Path, PathBuf};
+use std::sync::Arc;
+use std::sync::atomic::AtomicBool;
+
+use common::mock_ocr::MockOcrEngine;
+use kebab_app::pdf_ocr_apply::{PdfOcrOpts, apply_ocr_to_pdf_pages};
+use kebab_core::{
+    AssetStorage, Block, CanonicalDocument, Checksum, ExtractConfig, ExtractContext, Extractor,
+    Inline, Lang, MediaType, RawAsset, SourceSpan, SourceUri, WorkspacePath, id_for_asset,
+};
+use kebab_parse_pdf::PdfTextExtractor;
+use time::OffsetDateTime;
+
+// ── Fixture helpers ───────────────────────────────────────────────────────
+
+fn f1_pdf_bytes() -> Vec<u8> {
+    std::fs::read("../kebab-parse-pdf/tests/fixtures/scanned_page1.pdf")
+        .expect("F1 fixture missing")
+}
+
+fn make_raw_asset(path: &str, media_type: MediaType, byte_len: u64) -> RawAsset {
+    let fake_hash = "0".repeat(64);
+    let asset_id = id_for_asset(&fake_hash);
+    RawAsset {
+        asset_id,
+        source_uri: SourceUri::File(PathBuf::from(path)),
+        workspace_path: WorkspacePath::new(path.to_string()).unwrap(),
+        media_type,
+        byte_len,
+        checksum: Checksum(fake_hash.clone()),
+        discovered_at: OffsetDateTime::UNIX_EPOCH,
+        stored: AssetStorage::Copied {
+            path: PathBuf::from(path),
+        },
+    }
+}
+
+/// Build a CanonicalDocument from raw PDF bytes using PdfTextExtractor.
+/// F1 (scanned) returns an empty-text Block::Paragraph per page.
+fn extract_canonical_from_bytes(bytes: &[u8]) -> CanonicalDocument {
+    let asset = make_raw_asset("test.pdf", MediaType::Pdf, bytes.len() as u64);
+    let workspace_root = Path::new("/");
+    let config = ExtractConfig::default();
+    let ctx = ExtractContext {
+        asset: &asset,
+        workspace_root,
+        config: &config,
+    };
+    PdfTextExtractor::new().extract(&ctx, bytes).unwrap()
+}
+
+/// F1 bytes → canonical with 1 empty Block::Paragraph for page 1.
+fn canonical_with_empty_block() -> CanonicalDocument {
+    extract_canonical_from_bytes(&f1_pdf_bytes())
+}
+
+/// F1-based canonical with block text replaced by `text` (high valid_ratio, chars≥20).
+fn canonical_with_filled_block(text: &str) -> CanonicalDocument {
+    let mut canonical = extract_canonical_from_bytes(&f1_pdf_bytes());
+    if let Some(Block::Paragraph(tb)) = canonical.blocks.first_mut() {
+        let char_count = text.chars().count() as u32;
+        tb.text = text.to_string();
+        tb.inlines = vec![Inline::Text {
+            text: text.to_string(),
+        }];
+        if let SourceSpan::Page { char_end, .. } = &mut tb.common.source_span {
+            *char_end = Some(char_count);
+        }
+    }
+    canonical
+}
+
+/// F1-based canonical with block text replaced by PUA codepoints (low valid_ratio).
+fn canonical_with_mojibake_block() -> CanonicalDocument {
+    let mut canonical = extract_canonical_from_bytes(&f1_pdf_bytes());
+    if let Some(Block::Paragraph(tb)) = canonical.blocks.first_mut() {
+        let pua = "\u{E000}".repeat(25); // 25 PUA codepoints → valid_ratio ≈ 0
+        let char_count = pua.chars().count() as u32;
+        tb.text = pua.clone();
+        tb.inlines = vec![Inline::Text { text: pua }];
+        if let SourceSpan::Page { char_end, .. } = &mut tb.common.source_span {
+            *char_end = Some(char_count);
+        }
+    }
+    canonical
+}
+
+fn default_opts(enabled: bool) -> PdfOcrOpts {
+    PdfOcrOpts {
+        enabled,
+        always_on: false,
+        valid_ratio_threshold: 0.5,
+        min_char_count: 20,
+        lang_hint: None,
+        cancel: None,
+    }
+}
+
+// ── Tests ─────────────────────────────────────────────────────────────────
+
+// Test 1: F1 + enabled=true → in-place mutate
+#[test]
+fn f1_input_with_ocr_enabled_replaces_empty_block() {
+    let bytes = f1_pdf_bytes();
+    let mut canonical = canonical_with_empty_block();
+    let engine = MockOcrEngine::single("MOCK_OCR_TEXT", false);
+    let opts = PdfOcrOpts {
+        enabled: true,
+        always_on: false,
+        valid_ratio_threshold: 0.5,
+        min_char_count: 20,
+        lang_hint: Some(Lang("kor".into())),
+        cancel: None,
+    };
+
+    let summary = apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {}).unwrap();
+
+    assert_eq!(summary.pages_ocrd, 1);
+    let first_para = canonical.blocks.iter().find_map(|b| match b {
+        Block::Paragraph(tb) => Some(tb),
+        _ => None,
+    });
+    assert!(first_para.is_some());
+    assert_eq!(first_para.unwrap().text, "MOCK_OCR_TEXT");
+}
+
+// Test 2: F3 vector (mock filled canonical) + enabled=true → OCR skip (needs_ocr=false)
+#[test]
+fn f3_input_with_ocr_enabled_keeps_text_detect_blocks() {
+    let bytes = f1_pdf_bytes(); // reuse F1 bytes; decision is based on canonical text
+    let text = "충분한 한국어 텍스트 컨텐츠입니다. This has more than twenty characters.";
+    let mut canonical = canonical_with_filled_block(text);
+    let engine = MockOcrEngine::single("SHOULD_NOT_BE_CALLED", false);
+    let opts = default_opts(true);
+
+    let summary = apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {}).unwrap();
+
+    assert_eq!(summary.pages_ocrd, 0, "vector PDF 의 OCR 호출 0");
+    let first_para = canonical.blocks.iter().find_map(|b| match b {
+        Block::Paragraph(tb) => Some(tb),
+        _ => None,
+    });
+    if let Some(tb) = first_para {
+        assert!(tb.text.starts_with("충분한"), "원본 text 보존");
+    }
+}
+
+// Test 3: F1 + enabled=false → no-op
+#[test]
+fn f1_input_with_ocr_disabled_keeps_empty_block() {
+    let bytes = f1_pdf_bytes();
+    let mut canonical = canonical_with_empty_block();
+    let engine = MockOcrEngine::single("IGNORED", false);
+    let opts = default_opts(false);
+
+    let summary = apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {}).unwrap();
+
+    assert_eq!(summary.pages_ocrd, 0);
+    assert_eq!(summary.ms_total, 0);
+}
+
+// Test 4: mojibake canonical (PUA chars) + enabled=true → in-place mutate
+#[test]
+fn f4_input_with_ocr_enabled_replaces_mojibake_block() {
+    let bytes = f1_pdf_bytes(); // F1 bytes carry DCTDecode image
+    let mut canonical = canonical_with_mojibake_block();
+    let engine = MockOcrEngine::single("OCR_MOJIBAKE_REPLACEMENT", false);
+    let opts = PdfOcrOpts {
+        enabled: true,
+        always_on: false,
+        valid_ratio_threshold: 0.5,
+        min_char_count: 20,
+        lang_hint: None,
+        cancel: None,
+    };
+
+    let summary = apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {}).unwrap();
+
+    assert_eq!(summary.pages_ocrd, 1, "mojibake page 의 OCR 호출");
+    let first_para = canonical.blocks.iter().find_map(|b| match b {
+        Block::Paragraph(tb) => Some(tb),
+        _ => None,
+    });
+    if let Some(tb) = first_para {
+        assert_eq!(tb.text, "OCR_MOJIBAKE_REPLACEMENT");
+    }
+}
+
+// Test 5: filled canonical + always_on=true → dual-block (+1 OCR block)
+#[test]
+fn f3_input_with_always_on_pushes_dual_blocks() {
+    let bytes = f1_pdf_bytes();
+    let text = "vector PDF 충분한 텍스트 컨텐츠입니다. This has enough characters for valid ratio.";
+    let mut canonical = canonical_with_filled_block(text);
+    let original_block_count = canonical.blocks.len();
+    let engine = MockOcrEngine::single("OCR_DUAL", false);
+    let opts = PdfOcrOpts {
+        enabled: true,
+        always_on: true,
+        valid_ratio_threshold: 0.5,
+        min_char_count: 20,
+        lang_hint: None,
+        cancel: None,
+    };
+
+    let summary = apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {}).unwrap();
+
+    assert_eq!(summary.pages_ocrd, 1);
+    assert_eq!(
+        canonical.blocks.len(),
+        original_block_count + 1,
+        "always_on 시 새 Block::Paragraph push"
+    );
+    let texts: Vec<&str> = canonical
+        .blocks
+        .iter()
+        .filter_map(|b| match b {
+            Block::Paragraph(tb) => Some(tb.text.as_str()),
+            _ => None,
+        })
+        .collect();
+    assert!(texts.contains(&"OCR_DUAL"), "OCR block 포함");
+    assert!(
+        texts.iter().any(|t| t.starts_with("vector")),
+        "원본 text-detect block 보존"
+    );
+}
+
+// Test 6: F6 FlateDecode → extract_dctdecode_page_image=None → skip + warning
+#[test]
+fn f6_flatedecode_skipped_with_warning() {
+    let bytes = std::fs::read("../kebab-parse-pdf/tests/fixtures/flate_raw.pdf")
+        .expect("F6 fixture missing");
+    let mut canonical = canonical_with_empty_block(); // page-1 block from F1
+    let engine = MockOcrEngine::single("SHOULD_NOT_BE_CALLED", false);
+    let opts = default_opts(true);
+
+    let summary = apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {}).unwrap();
+
+    assert_eq!(
+        summary.pages_ocrd, 0,
+        "FlateDecode page 는 skip (DCTDecode-only v1 invariant)"
+    );
+    let warning_count = canonical
+        .provenance
+        .events
+        .iter()
+        .filter(|e| e.kind == kebab_core::ProvenanceKind::Warning)
+        .count();
+    assert!(warning_count >= 1, "FlateDecode skip 시 Warning event 발행");
+}
+
+// Test 7: F7 CCITTFax → skip + warning (verifier M-4 split)
+#[test]
+fn f7_ccittfax_skipped_with_warning() {
+    let bytes =
+        std::fs::read("../kebab-parse-pdf/tests/fixtures/ccitt.pdf").expect("F7 fixture missing");
+    let mut canonical = canonical_with_empty_block(); // page-1 block from F1
+    let engine = MockOcrEngine::single("SHOULD_NOT_BE_CALLED", false);
+    let opts = default_opts(true);
+
+    let summary = apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {}).unwrap();
+
+    assert_eq!(summary.pages_ocrd, 0, "CCITTFax page 는 skip");
+    let warning_count = canonical
+        .provenance
+        .events
+        .iter()
+        .filter(|e| e.kind == kebab_core::ProvenanceKind::Warning)
+        .count();
+    assert!(warning_count >= 1, "CCITTFax skip 시 Warning event 발행");
+}
+
+// Test 8: OCR engine failure → warning event + skip
+#[test]
+fn ocr_engine_failure_surfaces_as_warning() {
+    let bytes = f1_pdf_bytes();
+    let mut canonical = canonical_with_empty_block();
+    let engine = MockOcrEngine::single("", true);
+    let opts = default_opts(true);
+
+    let summary = apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {}).unwrap();
+
+    assert_eq!(summary.pages_ocrd, 0, "OCR failure 시 pages_ocrd=0");
+    let warning_with_failure = canonical.provenance.events.iter().any(|e| {
+        e.kind == kebab_core::ProvenanceKind::Warning
+            && e.note.as_deref().unwrap_or("").contains("mock failure")
+    });
+    assert!(
+        warning_with_failure,
+        "OCR failure 의 error message 가 warning event 의 note 안"
+    );
+}
+
+// Test 9: dual-block ordinals are deterministic and unique
+#[test]
+fn dual_block_ordinals_are_deterministic_and_unique() {
+    let bytes = f1_pdf_bytes(); // 1-page PDF → page_count=1
+    let text = "vector 충분한 텍스트. This text has more than twenty characters total.";
+    let mut canonical = canonical_with_filled_block(text);
+    let engine = MockOcrEngine::single("DUAL", false);
+    let opts = PdfOcrOpts {
+        enabled: true,
+        always_on: true,
+        valid_ratio_threshold: 0.5,
+        min_char_count: 20,
+        lang_hint: None,
+        cancel: None,
+    };
+
+    apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {}).unwrap();
+
+    // page_count=1 → text-detect ordinal=0, ocr ordinal=1 (page_num-1 + page_count = 0+1=1)
+    let para_count = canonical
+        .blocks
+        .iter()
+        .filter(|b| matches!(b, Block::Paragraph(_)))
+        .count();
+    assert_eq!(para_count, 2, "dual-block: text-detect + OCR");
+
+    let all_page_1 = canonical
+        .blocks
+        .iter()
+        .filter_map(|b| match b {
+            Block::Paragraph(tb) => Some(&tb.common.source_span),
+            _ => None,
+        })
+        .all(|s| matches!(s, SourceSpan::Page { page: 1, .. }));
+    assert!(all_page_1, "두 block 모두 page=1");
+}
+
+// Test 10: cancel handle aborts mid-PDF
+#[test]
+fn cancel_handle_aborts_mid_pdf() {
+    let bytes = f1_pdf_bytes();
+    let mut canonical = canonical_with_empty_block();
+    let cancel = Arc::new(AtomicBool::new(true)); // pre-cancel
+    let engine = MockOcrEngine::single("IGNORED", false);
+    let opts = PdfOcrOpts {
+        enabled: true,
+        always_on: false,
+        valid_ratio_threshold: 0.5,
+        min_char_count: 20,
+        lang_hint: None,
+        cancel: Some(cancel.clone()),
+    };
+
+    let result = apply_ocr_to_pdf_pages(&mut canonical, &engine, &bytes, &opts, |_| {});
+    let err = result.expect_err("cancel=true 시 error 반환");
+    assert!(
+        format!("{err}").contains("cancelled mid-PDF"),
+        "error message 가 'cancelled mid-PDF' 포함: {err}"
+    );
+}

crates/kebab-app/tests/pdf_ocr_events_insert_smoke.rs

@@ -0,0 +1,139 @@
+//! Integration smoke test: dual-write (ndjson + SQLite) for PDF OCR events.
+//! AC-3: SQLite row count and doc_id matches ndjson LogEvent::Ocr.
+//!
+//! Uses wiremock to stub the Ollama `/api/generate` endpoint so the test
+//! runs without a live Ollama instance.
+
+mod common;
+
+use std::path::PathBuf;
+
+use common::TestEnv;
+use kebab_config::LoggingCfg;
+use serde_json::Value;
+use tokio::task::spawn_blocking;
+use wiremock::matchers::{method, path};
+use wiremock::{Mock, MockServer, ResponseTemplate};
+
+fn scanned_pdf_src() -> PathBuf {
+    PathBuf::from(env!("CARGO_MANIFEST_DIR"))
+        .parent()
+        .unwrap()
+        .join("kebab-parse-pdf/tests/fixtures/scanned_page1.pdf")
+}
+
+/// AC-3: ndjson OCR line count == pdf_ocr_events row count, and doc_id matches.
+#[tokio::test]
+async fn ingest_dual_write_doc_id_matches_ndjson() {
+    let src = scanned_pdf_src();
+    if !src.exists() {
+        eprintln!("skipping test: scanned_page1.pdf fixture not found");
+        return;
+    }
+
+    let server = MockServer::start().await;
+    // Stub Ollama /api/generate to return a minimal OCR response.
+    Mock::given(method("POST"))
+        .and(path("/api/generate"))
+        .respond_with(ResponseTemplate::new(200).set_body_json(serde_json::json!({
+            "model": "qwen2.5vl:3b",
+            "response": "test ocr output",
+            "done": true,
+            "done_reason": "stop"
+        })))
+        .mount(&server)
+        .await;
+
+    let mock_url = server.uri();
+
+    let result = spawn_blocking(move || {
+        let mut env = TestEnv::lexical_only();
+        // Enable PDF OCR + set up mock endpoint
+        env.config.pdf.ocr.enabled = true;
+        env.config.pdf.ocr.endpoint = Some(mock_url.clone());
+        env.config.pdf.ocr.model = "qwen2.5vl:3b".to_string();
+        // Enable ingest log
+        let log_dir = env.temp.path().join("logs");
+        std::fs::create_dir_all(&log_dir).unwrap();
+        env.config.logging = LoggingCfg {
+            ingest_log_enabled: true,
+            ingest_log_dir: log_dir.clone(),
+            ..Default::default()
+        };
+
+        // Copy scanned PDF into workspace
+        let dest = env.workspace_root.join("scanned.pdf");
+        std::fs::copy(scanned_pdf_src(), &dest).expect("copy scanned PDF");
+
+        // Run ingest
+        kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).expect("ingest");
+
+        // Read ndjson log
+        let log_files: Vec<_> = std::fs::read_dir(&log_dir)
+            .unwrap()
+            .filter_map(Result::ok)
+            .filter(|e| {
+                let name = e.file_name().to_string_lossy().to_string();
+                name.starts_with("ingest-") && name.ends_with(".ndjson")
+            })
+            .collect();
+        assert_eq!(log_files.len(), 1, "expected 1 ndjson log file");
+
+        let body = std::fs::read_to_string(log_files[0].path()).unwrap();
+        let ocr_lines: Vec<Value> = body
+            .lines()
+            .filter_map(|l| serde_json::from_str(l).ok())
+            .filter(|v: &Value| v.get("kind").and_then(Value::as_str) == Some("ocr"))
+            .collect();
+
+        // Read pdf_ocr_events from SQLite
+        let db_path = PathBuf::from(&env.config.storage.data_dir).join("kebab.sqlite");
+        let conn = rusqlite::Connection::open(&db_path).expect("open db");
+        let rows: Vec<(Option<String>, String)> = {
+            let mut stmt = conn
+                .prepare("SELECT doc_id, doc_path FROM pdf_ocr_events ORDER BY id")
+                .expect("prepare");
+            stmt.query_map([], |r| Ok((r.get(0)?, r.get(1)?)))
+                .expect("query")
+                .map(|r| r.expect("row"))
+                .collect()
+        };
+
+        (ocr_lines, rows)
+    })
+    .await
+    .expect("spawn_blocking");
+
+    let (ocr_lines, rows) = result;
+
+    // At least one OCR event must be produced
+    assert!(!ocr_lines.is_empty(), "expected ≥1 ndjson ocr line");
+    assert!(!rows.is_empty(), "expected ≥1 pdf_ocr_events row");
+
+    // Row counts must match
+    assert_eq!(
+        ocr_lines.len(),
+        rows.len(),
+        "ndjson ocr lines ({}) must equal pdf_ocr_events rows ({})",
+        ocr_lines.len(),
+        rows.len()
+    );
+
+    // doc_id in both sources must be non-null and consistent
+    for (line, (sql_doc_id, _sql_doc_path)) in ocr_lines.iter().zip(rows.iter()) {
+        let json_doc_id = line.get("doc_id").and_then(Value::as_str);
+        assert!(
+            json_doc_id.is_some(),
+            "ndjson ocr line should have doc_id: {line}"
+        );
+        assert!(
+            sql_doc_id.is_some(),
+            "pdf_ocr_events row should have doc_id"
+        );
+        assert_eq!(
+            json_doc_id,
+            sql_doc_id.as_deref(),
+            "ndjson doc_id must equal SQLite doc_id"
+        );
+    }
+}

crates/kebab-app/tests/pdf_pipeline.rs

@@ -46,17 +46,13 @@ fn build_text_pdf(pages: &[Option<&str>]) -> Vec<u8> {
                 operations: vec![
                     Operation::new("BT", vec![]),
                     Operation::new("Tf", vec!["F1".into(), 24.into()]),
-                    Operation::new(
-                        "Td",
-                        vec![Object::Integer(100), Object::Integer(700)],
-                    ),
+                    Operation::new("Td", vec![Object::Integer(100), Object::Integer(700)]),
                     Operation::new("Tj", vec![Object::string_literal(*text)]),
                     Operation::new("ET", vec![]),
                 ],
             };
             let stream_data = content.encode().expect("content encode");
-            let content_id =
-                doc.add_object(Stream::new(dictionary! {}, stream_data));
+            let content_id = doc.add_object(Stream::new(dictionary! {}, stream_data));
             page_dict.set("Contents", content_id);
         }
         let page_id = doc.add_object(page_dict);
@@ -76,8 +72,7 @@ fn build_text_pdf(pages: &[Option<&str>]) -> Vec<u8> {
             Object::Integer(842),
         ],
     };
-    doc.objects
-        .insert(pages_id, Object::Dictionary(pages_dict));
+    doc.objects.insert(pages_id, Object::Dictionary(pages_dict));
 
     let catalog_id = doc.add_object(dictionary! {
         "Type" => "Catalog",
@@ -146,9 +141,8 @@ fn ingest_3_page_pdf_produces_one_doc_and_per_page_chunks() {
     write_pdf(&env.workspace_root, "three.pdf", &bytes);
     let cfg = cfg_with_pdf(&env);
 
-    let report =
-        kebab_app::ingest_with_config(cfg.clone(), env.scope(), false)
-            .expect("PDF ingest must succeed");
+    let report = kebab_app::ingest_with_config(cfg.clone(), env.scope(), false)
+        .expect("PDF ingest must succeed");
 
     assert_eq!(report.errors, 0);
     let items = report.items.as_ref().expect("items present");
@@ -157,23 +151,30 @@ fn ingest_3_page_pdf_produces_one_doc_and_per_page_chunks() {
         .find(|i| i.doc_path.0.ends_with("three.pdf"))
         .expect("PDF item present");
     assert_eq!(pdf_item.kind, IngestItemKind::New);
-    assert_eq!(pdf_item.block_count, Some(3), "one Block::Paragraph per page");
-    assert_eq!(pdf_item.chunk_count, Some(3), "one chunk per non-empty page");
     assert_eq!(
-        pdf_item.parser_version.as_ref().map(|p| p.0.as_str()),
+        pdf_item.block_count,
+        Some(3),
+        "one Block::Paragraph per page"
+    );
+    assert_eq!(
+        pdf_item.chunk_count,
+        Some(3),
+        "one chunk per non-empty page"
+    );
+    assert_eq!(
+        pdf_item.parser_version
+            .as_ref()
+            .map(|p| p.0.split('|').next().unwrap()),
         Some("pdf-text-v1")
     );
     assert_eq!(
         pdf_item.chunker_version.as_ref().map(|c| c.0.as_str()),
-        Some("pdf-page-v1")
+        Some("pdf-page-v1.1")
     );
 
     // Inspect the stored doc to confirm SourceSpan::Page round-trip.
-    let doc = kebab_app::inspect_doc_with_config(
-        cfg,
-        pdf_item.doc_id.as_ref().unwrap(),
-    )
-    .expect("inspect_doc returns the PDF document");
+    let doc = kebab_app::inspect_doc_with_config(cfg, pdf_item.doc_id.as_ref().unwrap())
+        .expect("inspect_doc returns the PDF document");
     assert_eq!(doc.blocks.len(), 3);
     for (i, block) in doc.blocks.iter().enumerate() {
         let want_page = (i as u32) + 1;
@@ -202,8 +203,7 @@ fn re_ingest_identical_pdf_produces_unchanged_with_same_doc_id() {
     write_pdf(&env.workspace_root, "stable.pdf", &bytes);
     let cfg = cfg_with_pdf(&env);
 
-    let report1 =
-        kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
+    let report1 = kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
     let item1 = report1
         .items
         .as_ref()
@@ -214,8 +214,7 @@ fn re_ingest_identical_pdf_produces_unchanged_with_same_doc_id() {
         .unwrap();
     assert_eq!(item1.kind, IngestItemKind::New);
 
-    let report2 =
-        kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
+    let report2 = kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
     let item2 = report2
         .items
         .unwrap()
@@ -239,8 +238,7 @@ fn re_ingest_edited_pdf_produces_new_doc_id() {
     std::fs::write(&path, &bytes_v1).unwrap();
     let cfg = cfg_with_pdf(&env);
 
-    let report_v1 =
-        kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
+    let report_v1 = kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
     let id_v1 = report_v1
         .items
         .as_ref()
@@ -252,12 +250,10 @@ fn re_ingest_edited_pdf_produces_new_doc_id() {
         .clone()
         .unwrap();
 
-    let bytes_v2 =
-        build_text_pdf(&[Some("VERSION TWO entirely different body content.")]);
+    let bytes_v2 = build_text_pdf(&[Some("VERSION TWO entirely different body content.")]);
     std::fs::write(&path, &bytes_v2).unwrap();
 
-    let report_v2 =
-        kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
+    let report_v2 = kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
     let item_v2 = report_v2
         .items
         .as_ref()
@@ -282,9 +278,11 @@ fn encrypted_pdf_fails_with_qpdf_hint() {
     write_pdf(&env.workspace_root, "secret.pdf", &bytes);
     let cfg = cfg_with_pdf(&env);
 
-    let report =
-        kebab_app::ingest_with_config(cfg, env.scope(), false).unwrap();
-    assert_eq!(report.errors, 1, "encrypted PDF must increment errors exactly once");
+    let report = kebab_app::ingest_with_config(cfg, env.scope(), false).unwrap();
+    assert_eq!(
+        report.errors, 1,
+        "encrypted PDF must increment errors exactly once"
+    );
     let items = report.items.as_ref().unwrap();
     let pdf_item = items
         .iter()
@@ -310,9 +308,11 @@ fn corrupt_pdf_fails_without_storing() {
     write_pdf(&env.workspace_root, "corrupt.pdf", &bytes);
     let cfg = cfg_with_pdf(&env);
 
-    let report =
-        kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
-    assert_eq!(report.errors, 1, "corrupt PDF must increment errors exactly once");
+    let report = kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
+    assert_eq!(
+        report.errors, 1,
+        "corrupt PDF must increment errors exactly once"
+    );
     let items = report.items.as_ref().unwrap();
     let pdf_item = items
         .iter()
@@ -322,11 +322,8 @@ fn corrupt_pdf_fails_without_storing() {
 
     // Confirm the doc was NOT stored — list_docs returns nothing for
     // this path.
-    let summaries = kebab_app::list_docs_with_config(
-        cfg,
-        kebab_core::DocFilter::default(),
-    )
-    .unwrap();
+    let summaries =
+        kebab_app::list_docs_with_config(cfg, kebab_core::DocFilter::default()).unwrap();
     assert!(
         !summaries
             .iter()
@@ -341,14 +338,15 @@ fn corrupt_pdf_fails_without_storing() {
 #[test]
 fn mixed_page_pdf_stores_asset_with_scanned_candidate_warning() {
     let env = TestEnv::lexical_only();
-    let bytes =
-        build_text_pdf(&[Some("first page"), None, Some("third page")]);
+    let bytes = build_text_pdf(&[Some("first page"), None, Some("third page")]);
     write_pdf(&env.workspace_root, "mixed.pdf", &bytes);
     let cfg = cfg_with_pdf(&env);
 
-    let report =
-        kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
-    assert_eq!(report.errors, 0, "scanned candidate is a Warning, not Error");
+    let report = kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
+    assert_eq!(
+        report.errors, 0,
+        "scanned candidate is a Warning, not Error"
+    );
     let pdf_item = report
         .items
         .as_ref()
@@ -365,14 +363,10 @@ fn mixed_page_pdf_stores_asset_with_scanned_candidate_warning() {
     assert_eq!(
         pdf_item.chunk_count,
         Some(2),
-        "pdf-page-v1 emits 0 chunks for the empty page; total = 2"
+        "pdf-page-v1.1 emits 0 chunks for the empty page; total = 2"
     );
 
-    let doc = kebab_app::inspect_doc_with_config(
-        cfg,
-        pdf_item.doc_id.as_ref().unwrap(),
-    )
-    .unwrap();
+    let doc = kebab_app::inspect_doc_with_config(cfg, pdf_item.doc_id.as_ref().unwrap()).unwrap();
     let warnings: Vec<_> = doc
         .provenance
         .events
@@ -419,8 +413,7 @@ fn ingest_report_arithmetic_invariant_holds_with_corrupt_pdf() {
     write_pdf(&env.workspace_root, "broken.pdf", &corrupt_pdf());
     let cfg = cfg_with_pdf(&env);
 
-    let report =
-        kebab_app::ingest_with_config(cfg, env.scope(), false).unwrap();
+    let report = kebab_app::ingest_with_config(cfg, env.scope(), false).unwrap();
     let total = report.new + report.updated + report.skipped + report.errors;
     assert_eq!(
         report.scanned, total,
@@ -441,14 +434,12 @@ fn long_pdf_round_trips_through_lexical_pipeline() {
     let pages: Vec<String> = (1..=50)
         .map(|i| format!("Page {i} body — lorem ipsum dolor sit amet."))
         .collect();
-    let page_refs: Vec<Option<&str>> =
-        pages.iter().map(|s| Some(s.as_str())).collect();
+    let page_refs: Vec<Option<&str>> = pages.iter().map(|s| Some(s.as_str())).collect();
     let bytes = build_text_pdf(&page_refs);
     write_pdf(&env.workspace_root, "long.pdf", &bytes);
     let cfg = cfg_with_pdf(&env);
 
-    let report =
-        kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
+    let report = kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
     assert_eq!(report.errors, 0);
     let pdf_item = report
         .items
@@ -466,8 +457,7 @@ fn long_pdf_round_trips_through_lexical_pipeline() {
 
     // Round-trip: list_docs sees the long PDF.
     let summaries =
-        kebab_app::list_docs_with_config(cfg, kebab_core::DocFilter::default())
-            .unwrap();
+        kebab_app::list_docs_with_config(cfg, kebab_core::DocFilter::default()).unwrap();
     assert!(summaries.iter().any(|s| s.doc_path.0.ends_with("long.pdf")));
 }
 
@@ -476,13 +466,11 @@ fn long_pdf_round_trips_through_lexical_pipeline() {
 #[test]
 fn inspect_doc_surfaces_page_spans() {
     let env = TestEnv::lexical_only();
-    let bytes =
-        build_text_pdf(&[Some("alpha body"), Some("beta body"), Some("gamma body")]);
+    let bytes = build_text_pdf(&[Some("alpha body"), Some("beta body"), Some("gamma body")]);
     write_pdf(&env.workspace_root, "inspect.pdf", &bytes);
     let cfg = cfg_with_pdf(&env);
 
-    let report =
-        kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
+    let report = kebab_app::ingest_with_config(cfg.clone(), env.scope(), false).unwrap();
     let pdf_item = report
         .items
         .as_ref()
@@ -490,19 +478,15 @@ fn inspect_doc_surfaces_page_spans() {
         .iter()
         .find(|i| i.doc_path.0.ends_with("inspect.pdf"))
         .unwrap();
-    let doc = kebab_app::inspect_doc_with_config(
-        cfg,
-        pdf_item.doc_id.as_ref().unwrap(),
-    )
-    .unwrap();
-    assert_eq!(doc.parser_version.0, "pdf-text-v1");
+    let doc = kebab_app::inspect_doc_with_config(cfg, pdf_item.doc_id.as_ref().unwrap()).unwrap();
+    // v0.26.2: stored parser_version is now `pdf-text-v1|<ingest-config-sig>`
+    // (the signature folds chunking / pdf.ocr settings for skip detection).
+    // Assert the base identity by taking the prefix before the first '|'.
+    assert_eq!(doc.parser_version.0.split('|').next().unwrap(), "pdf-text-v1");
     assert_eq!(doc.blocks.len(), 3);
     for block in &doc.blocks {
         match block {
-            Block::Paragraph(p) => assert!(matches!(
-                p.common.source_span,
-                SourceSpan::Page { .. }
-            )),
+            Block::Paragraph(p) => assert!(matches!(p.common.source_span, SourceSpan::Page { .. })),
             other => panic!("expected Paragraph, got {other:?}"),
         }
     }

crates/kebab-app/tests/reset_orphans.rs

@@ -0,0 +1,137 @@
+//! Integration test for `kebab reset --orphans-only`.
+//!
+//! Verifies that stored docs outside the current walker scope are purged
+//! from the store without removing any files from the filesystem.
+//!
+//! Test outline:
+//! 1. Ingest 3 .rs files (a.rs, b.rs, c.rs) — all New.
+//! 2. Narrow the config `include` to `["a.rs"]` only; b.rs and c.rs are
+//!    still on disk but outside the walker scope.
+//! 3. Run `execute(ResetScope::OrphansOnly, &cfg)` — report must show
+//!    `orphans_purged == 2` and `purged_paths` contains b.rs + c.rs.
+//! 4. `list docs` must show only a.rs.
+//! 5. b.rs and c.rs must still exist on disk (no filesystem removal).
+//! 6. Second reset → `orphans_purged == 0` (idempotent).
+
+mod common;
+
+use common::TestEnv;
+use kebab_app::IngestOpts;
+use kebab_app::reset::{ResetScope, execute};
+use kebab_core::{DocFilter, DocumentStore, SourceScope};
+
+/// Open the SqliteStore and list all `workspace_path` values.
+fn list_doc_paths(env: &TestEnv) -> Vec<String> {
+    use kebab_store_sqlite::SqliteStore;
+    let store = SqliteStore::open(&env.config).unwrap();
+    store.run_migrations().unwrap();
+    store
+        .list_documents(&DocFilter::default())
+        .unwrap()
+        .into_iter()
+        .map(|d| d.doc_path.0)
+        .collect()
+}
+
+#[test]
+fn reset_orphans_only_purges_out_of_scope_docs() {
+    let env = TestEnv::lexical_only();
+
+    // Write three .rs files into the workspace.
+    let a_path = env.workspace_root.join("a.rs");
+    let b_path = env.workspace_root.join("b.rs");
+    let c_path = env.workspace_root.join("c.rs");
+    std::fs::write(&a_path, "// file a\nfn alpha() {}\n").unwrap();
+    std::fs::write(&b_path, "// file b\nfn bravo() {}\n").unwrap();
+    std::fs::write(&c_path, "// file c\nfn charlie() {}\n").unwrap();
+
+    // Ingest all three with a wide scope.
+    let wide_scope = SourceScope {
+        root: env.workspace_root.clone(),
+        include: vec!["**/*.rs".to_string()],
+        exclude: env.config.workspace.exclude.clone(),
+    };
+    let first = kebab_app::ingest_with_config_opts(
+        env.config.clone(),
+        wide_scope,
+        false,
+        IngestOpts::default(),
+    )
+    .expect("first ingest must succeed");
+    // The fixture workspace may contain other .rs files — just assert we
+    // got at least 3 new docs (our a.rs, b.rs, c.rs).
+    assert!(first.new >= 3, "expected at least 3 new docs: {first:?}");
+    assert_eq!(first.errors, 0, "no errors on first ingest");
+
+    // Narrow config to include only a.rs; b.rs + c.rs are still on disk.
+    let mut narrow_cfg = env.config.clone();
+    narrow_cfg.workspace.exclude.clear();
+    // Re-point workspace root (already correct) and restrict include via
+    // the SourceScope in the connector. The config's `workspace.root` is
+    // used by `enumerate_orphans` to build its scope — we keep that
+    // pointing at the workspace root. We simulate narrowing by setting a
+    // glob that only matches a.rs.
+    //
+    // NOTE: `kebab_config::WorkspaceCfg` does not have an `include` field
+    // (it was removed in p9-fb-25). We narrow the scope via the walker
+    // exclude list: exclude b.rs and c.rs explicitly.
+    narrow_cfg.workspace.exclude = vec!["b.rs".to_string(), "c.rs".to_string()];
+
+    // Run orphans-only reset.
+    let report =
+        execute(ResetScope::OrphansOnly, &narrow_cfg).expect("orphans-only reset must succeed");
+
+    assert_eq!(
+        report.orphans_purged, 2,
+        "expected 2 orphans purged (b.rs + c.rs): {report:?}"
+    );
+
+    let mut purged: Vec<String> = report.purged_paths.iter().map(|p| p.0.clone()).collect();
+    purged.sort();
+    assert_eq!(
+        purged,
+        vec!["b.rs".to_string(), "c.rs".to_string()],
+        "purged_paths must list b.rs and c.rs in sorted order: {purged:?}"
+    );
+
+    // list docs must show only a.rs (and any pre-existing fixture files
+    // that are not excluded by the narrow config).
+    let doc_paths = list_doc_paths(&env);
+    // The narrow_cfg excludes b.rs + c.rs — they must no longer be in store.
+    assert!(
+        !doc_paths.iter().any(|p| p == "b.rs"),
+        "b.rs must be gone from store after orphans-only reset; got: {doc_paths:?}"
+    );
+    assert!(
+        !doc_paths.iter().any(|p| p == "c.rs"),
+        "c.rs must be gone from store after orphans-only reset; got: {doc_paths:?}"
+    );
+    assert!(
+        doc_paths.iter().any(|p| p == "a.rs"),
+        "a.rs must still be in store; got: {doc_paths:?}"
+    );
+
+    // Both b.rs and c.rs must still exist on the filesystem — no file
+    // removal is performed by orphans-only.
+    assert!(
+        b_path.exists(),
+        "b.rs must still be on disk after orphans-only reset"
+    );
+    assert!(
+        c_path.exists(),
+        "c.rs must still be on disk after orphans-only reset"
+    );
+
+    // Second reset must be idempotent: nothing left to purge.
+    let second = execute(ResetScope::OrphansOnly, &narrow_cfg)
+        .expect("second orphans-only reset must succeed");
+    assert_eq!(
+        second.orphans_purged, 0,
+        "second reset must be idempotent (orphans_purged == 0): {second:?}"
+    );
+    assert!(
+        second.purged_paths.is_empty(),
+        "second reset purged_paths must be empty: {:?}",
+        second.purged_paths
+    );
+}

crates/kebab-app/tests/schema_active_versions.rs

@@ -0,0 +1,79 @@
+//! Integration tests for Bug #13: schema.v1.models.active_parsers + active_chunkers.
+
+use kebab_app::schema_with_config;
+use kebab_config::Config;
+use kebab_core::SourceScope;
+
+fn minimal_config(data_dir: &std::path::Path, workspace_root: &std::path::Path) -> Config {
+    let mut cfg = Config::defaults();
+    cfg.workspace.root = workspace_root.to_string_lossy().into_owned();
+    cfg.workspace.exclude.clear();
+    cfg.storage.data_dir = data_dir.to_string_lossy().into_owned();
+    cfg.storage.model_dir = data_dir.join("models").to_string_lossy().into_owned();
+    cfg.models.embedding.provider = "none".to_string();
+    cfg.models.embedding.dimensions = 0;
+    cfg.chunking.target_tokens = 80;
+    cfg.chunking.overlap_tokens = 20;
+    cfg
+}
+
+fn minimal_scope(workspace_root: &std::path::Path) -> SourceScope {
+    SourceScope {
+        root: workspace_root.to_path_buf(),
+        include: vec![],
+        exclude: vec![],
+    }
+}
+
+#[test]
+fn schema_models_active_arrays_empty_on_empty_corpus() {
+    let dir = tempfile::tempdir().unwrap();
+    let workspace = dir.path().join("kb");
+    std::fs::create_dir_all(&workspace).unwrap();
+    let cfg = minimal_config(dir.path(), &workspace);
+
+    let store = kebab_store_sqlite::SqliteStore::open(&cfg).unwrap();
+    store.run_migrations().unwrap();
+    drop(store);
+
+    let s = schema_with_config(&cfg).unwrap();
+    assert!(
+        s.models.active_parsers.is_empty(),
+        "empty corpus → no parsers"
+    );
+    assert!(
+        s.models.active_chunkers.is_empty(),
+        "empty corpus → no chunkers"
+    );
+    // backward compat: 기존 단일 field 는 markdown default 보존.
+    assert_eq!(s.models.parser_version, kebab_parse_md::PARSER_VERSION);
+}
+
+#[test]
+fn schema_emits_active_parsers_and_chunkers_array_after_ingest() {
+    let dir = tempfile::tempdir().unwrap();
+    let workspace = dir.path().join("kb");
+    std::fs::create_dir_all(&workspace).unwrap();
+    std::fs::write(workspace.join("a.md"), "# A\nhello world\n").unwrap();
+    let cfg = minimal_config(dir.path(), &workspace);
+    let scope = minimal_scope(&workspace);
+
+    kebab_app::ingest_with_config(cfg.clone(), scope, false).unwrap();
+
+    let s = schema_with_config(&cfg).unwrap();
+    assert!(
+        !s.models.active_parsers.is_empty(),
+        "active_parsers populated after ingest"
+    );
+    assert!(
+        !s.models.active_chunkers.is_empty(),
+        "active_chunkers populated after ingest"
+    );
+    // active arrays must be sorted (ORDER BY in SQL).
+    let mut sorted = s.models.active_parsers.clone();
+    sorted.sort();
+    assert_eq!(
+        s.models.active_parsers, sorted,
+        "active_parsers must be sorted"
+    );
+}

crates/kebab-app/tests/schema_report.rs

@@ -57,7 +57,11 @@ fn schema_report_reflects_freshly_ingested_kb() {
         schema.wire.schemas
     );
     assert!(schema.capabilities.json_mode);
-    assert!(!schema.capabilities.streaming_ask);
+    assert!(schema.capabilities.streaming_ask); // Bug #9: streaming_ask is now true
+    assert!(
+        schema.capabilities.mcp_server,
+        "mcp_server should be true after fb-30",
+    );
     assert_eq!(
         schema.stats.doc_count, 2,
         "expected 2 docs (a.md + b.md): {:?}",

crates/kebab-app/tests/search_budget_integration.rs

@@ -0,0 +1,175 @@
+//! p9-fb-34: App::search_with_opts integration tests.
+
+mod common;
+
+use kebab_app::SearchResponse;
+use kebab_core::{SearchFilters, SearchMode, SearchOpts, SearchQuery};
+
+fn lex(text: &str, k: usize) -> SearchQuery {
+    SearchQuery {
+        text: text.to_string(),
+        mode: SearchMode::Lexical,
+        k,
+        filters: SearchFilters::default(),
+    }
+}
+
+#[test]
+fn search_with_opts_no_budget_matches_search() {
+    let env = common::TestEnv::new();
+    common::ingest_md(&env, "a.md", "# T\n\napples are red\n");
+    let app = env.app();
+
+    let baseline = app.search(lex("apples", 5)).unwrap();
+    let resp: SearchResponse = app
+        .search_with_opts(lex("apples", 5), SearchOpts::default())
+        .unwrap();
+
+    assert_eq!(resp.hits.len(), baseline.len());
+    assert!(!resp.truncated);
+    assert!(
+        resp.next_cursor.is_none(),
+        "k=5 against 1 doc → no next page"
+    );
+}
+
+#[test]
+fn budget_truncates_snippets_when_below_threshold() {
+    let env = common::TestEnv::new();
+    let body: String = "rust ownership is a memory model. ".repeat(10);
+    common::ingest_md(&env, "a.md", &format!("# T\n\n{body}\n"));
+    let app = env.app();
+
+    let unrestricted = app.search(lex("rust", 5)).unwrap();
+    let unrestricted_chars: usize = unrestricted.iter().map(|h| h.snippet.chars().count()).sum();
+
+    let resp = app
+        .search_with_opts(
+            lex("rust", 5),
+            SearchOpts {
+                max_tokens: Some(50),
+                snippet_chars: None,
+                cursor: None,
+                trace: false,
+            },
+        )
+        .unwrap();
+    let limited_chars: usize = resp.hits.iter().map(|h| h.snippet.chars().count()).sum();
+
+    assert!(resp.truncated, "small budget must trip truncation");
+    assert!(limited_chars < unrestricted_chars, "snippet should shrink");
+    assert!(!resp.hits.is_empty(), "always retain ≥1 hit");
+}
+
+#[test]
+fn cursor_paginates_to_next_page() {
+    let env = common::TestEnv::new();
+    for i in 0..6 {
+        common::ingest_md(
+            &env,
+            &format!("d{i}.md"),
+            &format!("# T{i}\n\nrust topic {i}\n"),
+        );
+    }
+    let app = env.app();
+
+    let page1 = app
+        .search_with_opts(lex("rust", 2), SearchOpts::default())
+        .unwrap();
+    assert_eq!(page1.hits.len(), 2);
+    let cursor = page1.next_cursor.expect("more hits available");
+
+    let page2 = app
+        .search_with_opts(
+            lex("rust", 2),
+            SearchOpts {
+                max_tokens: None,
+                snippet_chars: None,
+                cursor: Some(cursor),
+                trace: false,
+            },
+        )
+        .unwrap();
+    assert_eq!(page2.hits.len(), 2);
+    let p1_ids: std::collections::HashSet<_> =
+        page1.hits.iter().map(|h| h.chunk_id.0.clone()).collect();
+    let p2_ids: std::collections::HashSet<_> =
+        page2.hits.iter().map(|h| h.chunk_id.0.clone()).collect();
+    assert!(
+        p1_ids.is_disjoint(&p2_ids),
+        "page 2 must not repeat page 1 hits"
+    );
+}
+
+#[test]
+fn cursor_rejected_after_corpus_revision_bump() {
+    let env = common::TestEnv::new();
+    common::ingest_md(&env, "a.md", "# T\n\napples\n");
+    let app = env.app();
+
+    let page1 = app
+        .search_with_opts(lex("apples", 1), SearchOpts::default())
+        .unwrap();
+    // p9-fb-34 round-1 review: replaced silent `if let Some(c) = ...`
+    // with `.expect(...)` so a fixture regression that breaks the
+    // cursor-emission contract fails loudly instead of passing vacuously.
+    let c = page1
+        .next_cursor
+        .expect("k=1 page must emit next_cursor — fixture too small if this fails");
+
+    common::ingest_md(&env, "b.md", "# B\n\nbananas\n");
+    let app2 = env.app();
+
+    let result = app2.search_with_opts(
+        lex("apples", 1),
+        SearchOpts {
+            max_tokens: None,
+            snippet_chars: None,
+            cursor: Some(c),
+            trace: false,
+        },
+    );
+    let err = result.unwrap_err();
+    assert!(
+        err.to_string().contains("stale_cursor"),
+        "must surface stale_cursor: {err}"
+    );
+}
+
+#[test]
+fn max_tokens_zero_returns_one_hit_truncated() {
+    // p9-fb-34 round-1 review: pin the documented "≥1 hit floor"
+    // contract — even with `max_tokens=0` (an absurdly tight budget)
+    // the budget loop must keep one hit and flip `truncated: true`.
+    // Fixture intentionally seeds multiple matches so step 2 of the
+    // budget loop (pop hits to 1) actually fires.
+    let env = common::TestEnv::new();
+    for i in 0..3 {
+        common::ingest_md(
+            &env,
+            &format!("d{i}.md"),
+            &format!("# T{i}\n\napples are red {i}\n"),
+        );
+    }
+    let app = env.app();
+
+    let resp = app
+        .search_with_opts(
+            lex("apples", 5),
+            SearchOpts {
+                max_tokens: Some(0),
+                snippet_chars: None,
+                cursor: None,
+                trace: false,
+            },
+        )
+        .unwrap();
+    assert_eq!(resp.hits.len(), 1, "max_tokens=0 collapses to 1-hit floor");
+    assert!(resp.truncated);
+    // p9-fb-34 R2: cursor IS emitted on k-pop case so the popped
+    // hits remain reachable.
+    assert!(
+        resp.next_cursor.is_some(),
+        "k-pop truncation must still emit next_cursor; popped hits at offset+returned"
+    );
+}

crates/kebab-app/tests/search_korean.rs

@@ -46,3 +46,152 @@ 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<_>>()
+    );
+}
+
+// ── S7 V009 morphological tokenizer end-to-end tests ─────────────────
+
+/// S7 — V009 morphological tokenizer: 한국어 2자 query 가 end-to-end
+/// lexical 경로에서 hit. lindera ko-dic 이 '한국어를' → '한국어' 형태소로
+/// 분해, '서울은' → '서울' 로 분해하여 tokenized_korean_text column 에
+/// 기록 → FTS5 매칭.
+#[test]
+fn korean_morphological_2char_query_lexical_mode() {
+    let env = TestEnv::lexical_only();
+    let doc_path = env.workspace_root.join("korean-wiki.md");
+    std::fs::write(
+        &doc_path,
+        "# 한국어 위키\n\n한국어를 공부합니다.\n서울은 한국의 수도입니다.\n",
+    )
+    .expect("write korean-wiki 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("한국"))
+        .expect("search 한국");
+    assert!(
+        !hits.is_empty(),
+        "'한국' 2-char Korean query must return at least one hit (V009 morphological); got {:?}",
+        hits.iter().map(|h| &h.doc_path.0).collect::<Vec<_>>()
+    );
+
+    let hits = kebab_app::search_with_config(env.config.clone(), common::lexical_query("서울"))
+        .expect("search 서울");
+    assert!(
+        !hits.is_empty(),
+        "'서울' 2-char Korean query must return at least one hit; got {:?}",
+        hits.iter().map(|h| &h.doc_path.0).collect::<Vec<_>>()
+    );
+}
+
+/// S7 — V009 morphological tokenizer: 한-영 혼합 query lexical hit.
+/// 'Rust' (English whole-token) + '최적화' (Korean morpheme) 각각 hit.
+#[test]
+fn korean_morphological_mixed_english_korean_query() {
+    let env = TestEnv::lexical_only();
+    let doc_path = env.workspace_root.join("rust-optimization.md");
+    std::fs::write(
+        &doc_path,
+        "# Rust 최적화 노트\n\nRust 최적화는 zero-cost abstraction 을 강조한다.\n",
+    )
+    .expect("write rust-optimization 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"))
+        .expect("search Rust");
+    assert!(
+        !hits.is_empty(),
+        "'Rust' English whole-token must hit; got {:?}",
+        hits.iter().map(|h| &h.doc_path.0).collect::<Vec<_>>()
+    );
+
+    let hits = kebab_app::search_with_config(env.config.clone(), common::lexical_query("최적화"))
+        .expect("search 최적화");
+    assert!(
+        !hits.is_empty(),
+        "'최적화' Korean morpheme must hit; got {:?}",
+        hits.iter().map(|h| &h.doc_path.0).collect::<Vec<_>>()
+    );
+}

crates/kebab-app/tests/search_lexical.rs

@@ -35,8 +35,8 @@ fn lexical_search_returns_hits_after_ingest() {
 fn lexical_search_empty_query_returns_empty() {
     let env = TestEnv::lexical_only();
     kebab_app::ingest_with_config(env.config.clone(), env.scope(), true).unwrap();
-    let hits = kebab_app::search_with_config(env.config.clone(), common::lexical_query("   "))
-        .unwrap();
+    let hits =
+        kebab_app::search_with_config(env.config.clone(), common::lexical_query("   ")).unwrap();
     assert!(hits.is_empty(), "blank query must short-circuit empty");
 }
 
@@ -107,20 +107,25 @@ fn search_uncached_returns_same_hits_as_cached() {
 #[test]
 fn first_ingest_bumps_corpus_revision() {
     let env = TestEnv::lexical_only();
-    let store_before =
-        kebab_store_sqlite::SqliteStore::open(&env.config).unwrap();
+    let store_before = kebab_store_sqlite::SqliteStore::open(&env.config).unwrap();
     store_before.run_migrations().unwrap();
-    assert_eq!(store_before.corpus_revision(), 0, "fresh store seeds 0");
+    // V004 seeds 0; V009 + V010 + V011 migrations each bump by 1 to
+    // invalidate stale LRU caches (spec §5.2). Baseline before ingest = 3.
+    // (V012 derivation_cache + V013 drop-chunk-aliases are structural/additive
+    // — neither bumps corpus_revision.)
+    let baseline = store_before.corpus_revision();
+    assert_eq!(baseline, 3, "fresh store post-V011 baseline = 3");
 
-    let report =
-        kebab_app::ingest_with_config(env.config.clone(), env.scope(), true).unwrap();
-    assert!(report.new + report.updated > 0, "first ingest must commit ≥1 doc");
-
-    let store_after =
-        kebab_store_sqlite::SqliteStore::open(&env.config).unwrap();
+    let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), true).unwrap();
     assert!(
-        store_after.corpus_revision() >= 1,
-        "ingest commit must bump corpus_revision (got {})",
+        report.new + report.updated > 0,
+        "first ingest must commit ≥1 doc"
+    );
+
+    let store_after = kebab_store_sqlite::SqliteStore::open(&env.config).unwrap();
+    assert!(
+        store_after.corpus_revision() > baseline,
+        "ingest commit must bump corpus_revision past baseline {baseline} (got {})",
         store_after.corpus_revision(),
     );
 }

crates/kebab-app/tests/search_stale_integration.rs

@@ -0,0 +1,91 @@
+//! p9-fb-32: `App::search` end-to-end staleness wiring.
+//!
+//! `compute_stale` itself is unit-tested in `kebab_app::staleness`; this
+//! file proves the post-process actually fires through the full
+//! retriever stack and that the cache-hit re-stamp respects the
+//! configured threshold.
+//!
+//! All three tests run lexical-only (no AVX, no fastembed download).
+
+mod common;
+
+use common::TestEnv;
+
+fn lexical_query_owner() -> kebab_core::SearchQuery {
+    common::lexical_query("ownership")
+}
+
+/// Fresh ingest at default 30-day threshold → no hit can be stale.
+/// `documents.updated_at` is stamped at ingest time (now), so the
+/// distance to `now_utc()` is sub-second.
+#[test]
+fn fresh_doc_is_not_stale_with_default_threshold() {
+    let env = TestEnv::lexical_only();
+    kebab_app::ingest_with_config(env.config.clone(), env.scope(), true).unwrap();
+
+    let app = kebab_app::App::open_with_config(env.config.clone()).unwrap();
+    let hits = app.search(lexical_query_owner()).unwrap();
+    assert!(!hits.is_empty(), "expected ≥1 hit for 'ownership'");
+    assert!(
+        hits.iter().all(|h| !h.stale),
+        "freshly-ingested doc must not be stale at default 30d threshold: {:?}",
+        hits.iter()
+            .map(|h| (h.doc_path.0.clone(), h.stale))
+            .collect::<Vec<_>>()
+    );
+}
+
+/// `stale_threshold_days = 0` disables the feature even for very old
+/// `documents.updated_at`. Backdate the row to a year ago, expect
+/// `stale: false` on every hit.
+#[test]
+fn threshold_zero_disables_staleness() {
+    let mut env = TestEnv::lexical_only();
+    env.config.search.stale_threshold_days = 0;
+
+    kebab_app::ingest_with_config(env.config.clone(), env.scope(), true).unwrap();
+    common::backdate_document_updated_at(&env, "intro.md", 365);
+
+    let app = kebab_app::App::open_with_config(env.config.clone()).unwrap();
+    let hits = app.search(lexical_query_owner()).unwrap();
+    assert!(!hits.is_empty(), "expected ≥1 hit");
+    assert!(
+        hits.iter().all(|h| !h.stale),
+        "threshold=0 disables staleness even for year-old docs: {:?}",
+        hits.iter()
+            .map(|h| (h.doc_path.0.clone(), h.stale))
+            .collect::<Vec<_>>()
+    );
+}
+
+/// At a 30-day threshold, a 60-day-old `documents.updated_at` must
+/// surface as stale on the matching hit. (Other hits — fresh fixtures
+/// not backdated — stay fresh, so we use `any` not `all`.)
+#[test]
+fn old_doc_marked_stale() {
+    let mut env = TestEnv::lexical_only();
+    env.config.search.stale_threshold_days = 30;
+
+    kebab_app::ingest_with_config(env.config.clone(), env.scope(), true).unwrap();
+    common::backdate_document_updated_at(&env, "intro.md", 60);
+
+    let app = kebab_app::App::open_with_config(env.config.clone()).unwrap();
+    let hits = app.search(lexical_query_owner()).unwrap();
+    assert!(!hits.is_empty(), "expected ≥1 hit");
+    let intro_hits: Vec<&kebab_core::SearchHit> = hits
+        .iter()
+        .filter(|h| h.doc_path.0.ends_with("intro.md"))
+        .collect();
+    assert!(
+        !intro_hits.is_empty(),
+        "expected ≥1 hit on intro.md (the backdated doc)"
+    );
+    assert!(
+        intro_hits.iter().all(|h| h.stale),
+        "60-day-old intro.md must be stale at 30d threshold: {:?}",
+        intro_hits
+            .iter()
+            .map(|h| (h.doc_path.0.clone(), h.stale))
+            .collect::<Vec<_>>()
+    );
+}

crates/kebab-app/tests/search_vector.rs

@@ -14,12 +14,11 @@ use common::TestEnv;
 fn require_avx_or_panic() {
     #[cfg(target_arch = "x86_64")]
     {
-        if !std::is_x86_feature_detected!("avx") {
-            panic!(
-                "kb-app vector integration test requires AVX-capable hardware; \
-                 host CPU lacks AVX. Run on an AVX-capable machine."
-            );
-        }
+        assert!(
+            std::is_x86_feature_detected!("avx"),
+            "kb-app vector integration test requires AVX-capable hardware; \
+             host CPU lacks AVX. Run on an AVX-capable machine."
+        );
     }
 }
 
@@ -30,8 +29,7 @@ fn ingest_then_hybrid_search_returns_hits() {
     require_avx_or_panic();
 
     let env = TestEnv::with_embeddings();
-    let report =
-        kebab_app::ingest_with_config(env.config.clone(), env.scope(), true).unwrap();
+    let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), true).unwrap();
     assert_eq!(report.errors, 0, "no per-file errors: {report:?}");
     assert_eq!(report.new, 3);
 
@@ -57,8 +55,7 @@ fn ingest_then_vector_search_carries_embedding_model() {
     require_avx_or_panic();
 
     let env = TestEnv::with_embeddings();
-    let report =
-        kebab_app::ingest_with_config(env.config.clone(), env.scope(), true).unwrap();
+    let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), true).unwrap();
     assert_eq!(report.errors, 0, "no per-file errors: {report:?}");
     assert_eq!(report.new, 3);
 

crates/kebab-app/tests/skip_reason.rs

@@ -13,11 +13,7 @@ fn unsupported_extension_skip_carries_warning_and_is_aggregated() {
     std::fs::write(workspace_root.join("legacy.docx"), b"unsupported").unwrap();
     std::fs::write(workspace_root.join("Makefile"), b"unsupported").unwrap();
 
-    let report = kebab_app::ingest_with_config(
-        env.config.clone(),
-        env.scope(),
-        false,
-    ).unwrap();
+    let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), false).unwrap();
 
     let items = report.items.as_ref().expect("items array populated");
     let docx_item = items
@@ -39,5 +35,8 @@ fn unsupported_extension_skip_carries_warning_and_is_aggregated() {
         vec!["unsupported media type: <no-ext>".to_string()],
     );
     assert_eq!(report.skipped_by_extension.get("docx").copied(), Some(1));
-    assert_eq!(report.skipped_by_extension.get("<no-ext>").copied(), Some(1));
+    assert_eq!(
+        report.skipped_by_extension.get("<no-ext>").copied(),
+        Some(1)
+    );
 }

crates/kebab-app/tests/twin_files_fetch_span.rs

@@ -0,0 +1,178 @@
+//! Regression test for the twin-file fetch_span media-type lookup bug.
+//!
+//! Twin files (identical content at different workspace paths) share one
+//! `assets` row whose PRIMARY KEY is the blake3 content hash. The old
+//! `fetch_span` implementation called
+//! `get_asset_by_workspace_path(&doc.workspace_path)` to check whether the
+//! media type was PDF/audio (and therefore reject span fetch). For a twin
+//! file that lookup could silently return the *other* twin's asset row if
+//! `assets.workspace_path` had been overwritten on the most recent ingest of
+//! the sibling — making the media-type branch decision incorrect.
+//!
+//! Fix: `fetch_span` now uses the 2-step lookup
+//!   `get_document_by_workspace_path` → `doc.source_asset_id` → `get_asset`
+//! so the result is always anchored to the requesting document, not
+//! whichever twin last updated `assets.workspace_path`.
+//!
+//! This test builds a twin-file scenario (two .md files at different paths
+//! with identical content), ingests both, then calls `fetch_span` on each
+//! twin's `doc_id` and asserts it succeeds. Before the fix, if the asset
+//! row's workspace_path happened to point at the wrong twin the span could
+//! return an incorrect `span_not_supported` for a non-PDF/audio file, or
+//! conversely allow span on a PDF twin by accident. After the fix, the
+//! lookup is always doc-specific.
+
+mod common;
+
+use common::TestEnv;
+use kebab_app::ingest_with_config;
+use kebab_core::{DocumentStore, FetchKind, FetchOpts, FetchQuery, IngestItemKind};
+
+#[test]
+fn twin_files_fetch_span_uses_correct_asset() {
+    let env = TestEnv::lexical_only();
+
+    // Write two markdown files with identical content at different paths.
+    let dir_a = env.workspace_root.join("src_a");
+    let dir_b = env.workspace_root.join("src_b");
+    std::fs::create_dir_all(&dir_a).unwrap();
+    std::fs::create_dir_all(&dir_b).unwrap();
+
+    // The content must produce at least 1 line so span fetch is non-trivial.
+    let content = "# Twin\n\nLine one.\n\nLine two.\n\nLine three.\n";
+    std::fs::write(dir_a.join("note.md"), content).unwrap();
+    std::fs::write(dir_b.join("note.md"), content).unwrap();
+
+    // Ingest all files (fixture workspace + our two new twins).
+    let report =
+        ingest_with_config(env.config.clone(), env.scope(), false).expect("ingest must succeed");
+    assert_eq!(report.errors, 0, "no ingest errors; report={report:?}");
+
+    // Both twin paths must appear as New in the report.
+    let items = report.items.as_ref().expect("items must be present");
+    let twin_items: Vec<_> = items
+        .iter()
+        .filter(|i| {
+            i.doc_path.0.ends_with("src_a/note.md") || i.doc_path.0.ends_with("src_b/note.md")
+        })
+        .collect();
+    assert_eq!(
+        twin_items.len(),
+        2,
+        "exactly 2 twin items expected; items={items:?}"
+    );
+    for item in &twin_items {
+        assert_eq!(
+            item.kind,
+            IngestItemKind::New,
+            "each twin must be New; item={item:?}"
+        );
+    }
+
+    // Resolve doc_ids for both workspace paths.
+    // The ingest layer normalises workspace_path to the path relative to
+    // workspace_root (e.g. "src_a/note.md"), so we look up by that form.
+    let store = kebab_store_sqlite::SqliteStore::open(&env.config).unwrap();
+    store.run_migrations().unwrap();
+
+    // Find the twin items by matching on suffix so the test is robust to
+    // however the workspace root is represented.
+    let items = report.items.as_ref().expect("items must be present");
+    let path_a_str = items
+        .iter()
+        .find(|i| i.doc_path.0.ends_with("src_a/note.md"))
+        .map(|i| i.doc_path.0.clone())
+        .expect("src_a/note.md must appear in ingest report");
+    let path_b_str = items
+        .iter()
+        .find(|i| i.doc_path.0.ends_with("src_b/note.md"))
+        .map(|i| i.doc_path.0.clone())
+        .expect("src_b/note.md must appear in ingest report");
+
+    let path_a = kebab_core::WorkspacePath(path_a_str);
+    let path_b = kebab_core::WorkspacePath(path_b_str);
+
+    let doc_a = store
+        .get_document_by_workspace_path(&path_a)
+        .expect("get_document_by_workspace_path path_a")
+        .expect("doc_a must exist after ingest");
+    let doc_b = store
+        .get_document_by_workspace_path(&path_b)
+        .expect("get_document_by_workspace_path path_b")
+        .expect("doc_b must exist after ingest");
+
+    // Both twins share one asset_id (same content hash).
+    assert_eq!(
+        doc_a.source_asset_id, doc_b.source_asset_id,
+        "twin files must share one asset_id"
+    );
+
+    // Open App and issue span fetch on each twin's doc_id.
+    let app = env.app();
+
+    let result_a = app
+        .fetch(
+            FetchQuery::Span {
+                doc_id: doc_a.doc_id.clone(),
+                line_start: 1,
+                line_end: 2,
+            },
+            FetchOpts::default(),
+        )
+        .expect("fetch_span on twin A must succeed for a markdown file");
+    assert_eq!(result_a.kind, FetchKind::Span);
+    assert!(
+        result_a.text.as_deref().is_some_and(|t| !t.is_empty()),
+        "span text for twin A must not be empty"
+    );
+
+    let result_b = app
+        .fetch(
+            FetchQuery::Span {
+                doc_id: doc_b.doc_id.clone(),
+                line_start: 1,
+                line_end: 2,
+            },
+            FetchOpts::default(),
+        )
+        .expect("fetch_span on twin B must succeed for a markdown file");
+    assert_eq!(result_b.kind, FetchKind::Span);
+    assert!(
+        result_b.text.as_deref().is_some_and(|t| !t.is_empty()),
+        "span text for twin B must not be empty"
+    );
+
+    // Ingest again to force the asset.workspace_path flip-flop, then
+    // re-check. Pre-fix this was the scenario that triggered the bug:
+    // after the second ingest the asset row's workspace_path could point
+    // at either twin, making one twin's span fetch behave incorrectly.
+    let report2 = ingest_with_config(env.config.clone(), env.scope(), false)
+        .expect("second ingest must succeed");
+    assert_eq!(
+        report2.errors, 0,
+        "no ingest errors on second run; report={report2:?}"
+    );
+
+    // Re-open app after second ingest and verify span still works on both.
+    let app2 = env.app();
+
+    app2.fetch(
+        FetchQuery::Span {
+            doc_id: doc_a.doc_id.clone(),
+            line_start: 1,
+            line_end: 3,
+        },
+        FetchOpts::default(),
+    )
+    .expect("fetch_span on twin A after flip-flop must still succeed");
+
+    app2.fetch(
+        FetchQuery::Span {
+            doc_id: doc_b.doc_id.clone(),
+            line_start: 1,
+            line_end: 3,
+        },
+        FetchOpts::default(),
+    )
+    .expect("fetch_span on twin B after flip-flop must still succeed");
+}

crates/kebab-app/tests/twin_files_idempotent.rs

@@ -0,0 +1,94 @@
+//! Regression test for the twin-file idempotency bug.
+//!
+//! Identical-content files at different workspace paths share one
+//! `assets` row (`asset_id` = blake3 content hash, PRIMARY KEY). The
+//! old UPSERT `ON CONFLICT(asset_id) DO UPDATE SET workspace_path =
+//! excluded.workspace_path` made each twin overwrite the other's path
+//! on every ingest, so `get_asset_by_workspace_path(path1)` returned
+//! None (or the wrong twin) → re-process every time.
+//!
+//! Fix: `try_skip_unchanged` now uses `get_document_by_workspace_path`
+//! instead.  `documents.workspace_path` is UNIQUE (V001) so each twin
+//! has its own stable document row.
+//!
+//! Assertion contract:
+//!   1st ingest → 2 New (one per twin)
+//!   2nd ingest → 0 New, 0 Updated, 2 Unchanged
+
+mod common;
+
+use common::TestEnv;
+use kebab_app::ingest_with_config;
+use kebab_core::IngestItemKind;
+
+#[test]
+fn twin_files_second_ingest_is_unchanged() {
+    let env = TestEnv::lexical_only();
+
+    // Write two files with identical content at different paths.
+    let pkg_a = env.workspace_root.join("pkg_a");
+    let pkg_b = env.workspace_root.join("pkg_b");
+    std::fs::create_dir_all(&pkg_a).unwrap();
+    std::fs::create_dir_all(&pkg_b).unwrap();
+
+    let content = b"# shared\nThis content is identical in both files.\n";
+    std::fs::write(pkg_a.join("__init__.py"), content).unwrap();
+    std::fs::write(pkg_b.join("__init__.py"), content).unwrap();
+
+    // First ingest — both files must be New.
+    let first = ingest_with_config(env.config.clone(), env.scope(), false)
+        .expect("first ingest must succeed");
+    assert_eq!(first.errors, 0, "first ingest: no errors; report={first:?}");
+
+    let items = first.items.as_ref().expect("items must be present");
+    let twin_items: Vec<_> = items
+        .iter()
+        .filter(|i| i.doc_path.0.ends_with("__init__.py"))
+        .collect();
+    assert_eq!(
+        twin_items.len(),
+        2,
+        "first ingest: expected exactly 2 __init__.py items; items={items:?}"
+    );
+    for item in &twin_items {
+        assert_eq!(
+            item.kind,
+            IngestItemKind::New,
+            "first ingest: each twin must be New; item={item:?}"
+        );
+    }
+
+    // Second ingest — same files, same content → both must be Unchanged.
+    let second = ingest_with_config(env.config.clone(), env.scope(), false)
+        .expect("second ingest must succeed");
+    assert_eq!(
+        second.errors, 0,
+        "second ingest: no errors; report={second:?}"
+    );
+    assert_eq!(
+        second.new, 0,
+        "second ingest: no new docs; report={second:?}"
+    );
+    assert_eq!(
+        second.updated, 0,
+        "second ingest: no updated docs (twin-file bug would set this to 2); report={second:?}"
+    );
+
+    let second_items = second.items.as_ref().expect("items must be present");
+    let twin_items2: Vec<_> = second_items
+        .iter()
+        .filter(|i| i.doc_path.0.ends_with("__init__.py"))
+        .collect();
+    assert_eq!(
+        twin_items2.len(),
+        2,
+        "second ingest: expected exactly 2 __init__.py items; items={second_items:?}"
+    );
+    for item in &twin_items2 {
+        assert_eq!(
+            item.kind,
+            IngestItemKind::Unchanged,
+            "second ingest: each twin must be Unchanged; item={item:?}"
+        );
+    }
+}

crates/kebab-chunk/Cargo.toml

@@ -13,14 +13,21 @@ serde_json_canonicalizer   = "0.3"
 blake3                     = { workspace = true }
 anyhow                     = { workspace = true }
 tracing                    = { workspace = true }
+serde_yaml                 = { workspace = true }
+lindera        = { workspace = true, features = ["embed-ko-dic"] }
+lindera-ko-dic = { workspace = true, features = ["embed-ko-dic"] }
 
 [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)
+# kb-parse-md / kb-parse-code are dev-only — used by the snapshot integration
+# tests to build a CanonicalDocument from fixture files. kb-parse-md absorbed
+# kb-normalize in v0.19.0 (HOTFIXES.md 2026-05-26). 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 }
+kebab-parse-md   = { path = "../kebab-parse-md" }
+kebab-parse-code = { path = "../kebab-parse-code" }
+serde_json       = { workspace = true }
+time             = { workspace = true }
+
+[lints]
+workspace = true

crates/kebab-chunk/src/code_c_ast_v1.rs

@@ -0,0 +1,375 @@
+//! `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(),
+        tokenized_korean_text: crate::tokenize_korean_morphological(&text),
+        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::{
+        AssetId, Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock,
+        CommonBlock, Lang, Metadata, ParserVersion, Provenance, SourceSpan, SourceType, TrustLevel,
+        WorkspacePath, id_for_block, id_for_doc,
+    };
+    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::<String>();
+        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_unstable();
+        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 +1,377 @@
+//! `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(),
+        tokenized_korean_text: crate::tokenize_korean_morphological(&text),
+        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::{
+        AssetId, Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock,
+        CommonBlock, Lang, Metadata, ParserVersion, Provenance, SourceSpan, SourceType, TrustLevel,
+        WorkspacePath, id_for_block, id_for_doc,
+    };
+    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::<String>();
+        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_unstable();
+        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/code_go_ast_v1.rs

@@ -0,0 +1,383 @@
+//! `code-go-ast-v1` — maps a tree-sitter-derived Go 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-go-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 CodeGoAstV1Chunker;
+
+impl Chunker for CodeGoAstV1Chunker {
+    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!("CodeGoAstV1Chunker only handles code docs (got non-Code block)")
+                }
+            };
+            if !matches!(c.common.source_span, SourceSpan::Code { .. }) {
+                anyhow::bail!(
+                    "CodeGoAstV1Chunker 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-go-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(),
+        tokenized_korean_text: crate::tokenize_korean_morphological(&text),
+        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::{
+        AssetId, Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock,
+        CommonBlock, Lang, Metadata, ParserVersion, Provenance, SourceSpan, SourceType, TrustLevel,
+        WorkspacePath, id_for_block, id_for_doc,
+    };
+    use time::OffsetDateTime;
+
+    fn code_doc(units: &[(&str, u32, u32, &str)]) -> CanonicalDocument {
+        let wp = WorkspacePath("crates/x/src/a.go".into());
+        let aid = AssetId("a".repeat(64));
+        let pv = ParserVersion("code-go-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("go".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("go".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("go".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_go_ast_v1() {
+        assert_eq!(
+            CodeGoAstV1Chunker.chunker_version(),
+            ChunkerVersion("code-go-ast-v1".into())
+        );
+    }
+
+    #[test]
+    fn one_chunk_per_unit_preserves_code_span() {
+        let doc = code_doc(&[
+            ("parse", 1, 3, "func parse() {\n\t// x\n}"),
+            (
+                "Foo.double",
+                5,
+                7,
+                "func double() int {\n\t//\n\treturn 0\n}",
+            ),
+        ]);
+        let chunks = CodeGoAstV1Chunker.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-go-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}"))
+            .collect::<Vec<_>>()
+            .join("\n");
+        let code = format!("func big() {{\n{body}\n}}");
+        let doc = code_doc(&[("big", 1, 502, &code)]);
+        let chunks = CodeGoAstV1Chunker.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_unstable();
+        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, "func 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 = CodeGoAstV1Chunker.chunk(&doc, &policy()).unwrap_err();
+        assert!(err.to_string().contains("CodeGoAstV1Chunker"));
+    }
+
+    #[test]
+    fn deterministic_chunk_ids_1000() {
+        let doc = code_doc(&[("parse", 1, 2, "func parse() {}\n")]);
+        let base: Vec<String> = CodeGoAstV1Chunker
+            .chunk(&doc, &policy())
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        for _ in 0..1000 {
+            let again: Vec<String> = CodeGoAstV1Chunker
+                .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!(
+            CodeGoAstV1Chunker.policy_hash(&p),
+            crate::MdHeadingV1Chunker.policy_hash(&p)
+        );
+    }
+}

crates/kebab-chunk/src/code_java_ast_v1.rs

@@ -0,0 +1,378 @@
+//! `code-java-ast-v1` — maps a tree-sitter-derived Java 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-java-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 CodeJavaAstV1Chunker;
+
+impl Chunker for CodeJavaAstV1Chunker {
+    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!(
+                    "CodeJavaAstV1Chunker only handles code docs (got non-Code block)"
+                ),
+            };
+            if !matches!(c.common.source_span, SourceSpan::Code { .. }) {
+                anyhow::bail!(
+                    "CodeJavaAstV1Chunker 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-java-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(),
+        tokenized_korean_text: crate::tokenize_korean_morphological(&text),
+        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::{
+        AssetId, Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock,
+        CommonBlock, Lang, Metadata, ParserVersion, Provenance, SourceSpan, SourceType, TrustLevel,
+        WorkspacePath, id_for_block, id_for_doc,
+    };
+    use time::OffsetDateTime;
+
+    fn code_doc(units: &[(&str, u32, u32, &str)]) -> CanonicalDocument {
+        let wp = WorkspacePath("crates/x/src/Main.java".into());
+        let aid = AssetId("a".repeat(64));
+        let pv = ParserVersion("code-java-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("java".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("java".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("java".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_java_ast_v1() {
+        assert_eq!(
+            CodeJavaAstV1Chunker.chunker_version(),
+            ChunkerVersion("code-java-ast-v1".into())
+        );
+    }
+
+    #[test]
+    fn one_chunk_per_unit_preserves_code_span() {
+        let doc = code_doc(&[
+            ("parse", 1, 3, "void parse() {\n\t// x\n}"),
+            ("Foo.double", 5, 7, "int double() {\n\t//\n\treturn 0;\n}"),
+        ]);
+        let chunks = CodeJavaAstV1Chunker.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-java-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!("\tint x{i} = {i};"))
+            .collect::<Vec<_>>()
+            .join("\n");
+        let code = format!("void big() {{\n{body}\n}}");
+        let doc = code_doc(&[("big", 1, 502, &code)]);
+        let chunks = CodeJavaAstV1Chunker.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_unstable();
+        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, "void 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 = CodeJavaAstV1Chunker.chunk(&doc, &policy()).unwrap_err();
+        assert!(err.to_string().contains("CodeJavaAstV1Chunker"));
+    }
+
+    #[test]
+    fn deterministic_chunk_ids_1000() {
+        let doc = code_doc(&[("parse", 1, 2, "void parse() {}\n")]);
+        let base: Vec<String> = CodeJavaAstV1Chunker
+            .chunk(&doc, &policy())
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        for _ in 0..1000 {
+            let again: Vec<String> = CodeJavaAstV1Chunker
+                .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!(
+            CodeJavaAstV1Chunker.policy_hash(&p),
+            crate::MdHeadingV1Chunker.policy_hash(&p)
+        );
+    }
+}

crates/kebab-chunk/src/code_js_ast_v1.rs

@@ -0,0 +1,383 @@
+//! `code-js-ast-v1` — maps a tree-sitter-derived JavaScript 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-js-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 CodeJsAstV1Chunker;
+
+impl Chunker for CodeJsAstV1Chunker {
+    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!("CodeJsAstV1Chunker only handles code docs (got non-Code block)")
+                }
+            };
+            if !matches!(c.common.source_span, SourceSpan::Code { .. }) {
+                anyhow::bail!(
+                    "CodeJsAstV1Chunker 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-js-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(),
+        tokenized_korean_text: crate::tokenize_korean_morphological(&text),
+        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::{
+        AssetId, Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock,
+        CommonBlock, Lang, Metadata, ParserVersion, Provenance, SourceSpan, SourceType, TrustLevel,
+        WorkspacePath, id_for_block, id_for_doc,
+    };
+    use time::OffsetDateTime;
+
+    fn code_doc(units: &[(&str, u32, u32, &str)]) -> CanonicalDocument {
+        let wp = WorkspacePath("crates/x/src/a.js".into());
+        let aid = AssetId("a".repeat(64));
+        let pv = ParserVersion("code-js-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("javascript".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("javascript".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("javascript".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_js_ast_v1() {
+        assert_eq!(
+            CodeJsAstV1Chunker.chunker_version(),
+            ChunkerVersion("code-js-ast-v1".into())
+        );
+    }
+
+    #[test]
+    fn one_chunk_per_unit_preserves_code_span() {
+        let doc = code_doc(&[
+            ("parse", 1, 3, "function parse() {\n    // x\n}"),
+            (
+                "Foo.double",
+                5,
+                7,
+                "function double() {\n    //\n    return 0;\n}",
+            ),
+        ]);
+        let chunks = CodeJsAstV1Chunker.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-js-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!("    const x{i} = {i};"))
+            .collect::<Vec<_>>()
+            .join("\n");
+        let code = format!("function big() {{\n{body}\n}}");
+        let doc = code_doc(&[("big", 1, 502, &code)]);
+        let chunks = CodeJsAstV1Chunker.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_unstable();
+        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, "function 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 = CodeJsAstV1Chunker.chunk(&doc, &policy()).unwrap_err();
+        assert!(err.to_string().contains("CodeJsAstV1Chunker"));
+    }
+
+    #[test]
+    fn deterministic_chunk_ids_1000() {
+        let doc = code_doc(&[("parse", 1, 2, "function parse() {}\n")]);
+        let base: Vec<String> = CodeJsAstV1Chunker
+            .chunk(&doc, &policy())
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        for _ in 0..1000 {
+            let again: Vec<String> = CodeJsAstV1Chunker
+                .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!(
+            CodeJsAstV1Chunker.policy_hash(&p),
+            crate::MdHeadingV1Chunker.policy_hash(&p)
+        );
+    }
+}

crates/kebab-chunk/src/code_kotlin_ast_v1.rs

@@ -0,0 +1,383 @@
+//! `code-kotlin-ast-v1` — maps a tree-sitter-derived Kotlin 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-kotlin-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 CodeKotlinAstV1Chunker;
+
+impl Chunker for CodeKotlinAstV1Chunker {
+    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!(
+                    "CodeKotlinAstV1Chunker only handles code docs (got non-Code block)"
+                ),
+            };
+            if !matches!(c.common.source_span, SourceSpan::Code { .. }) {
+                anyhow::bail!(
+                    "CodeKotlinAstV1Chunker 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-kotlin-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(),
+        tokenized_korean_text: crate::tokenize_korean_morphological(&text),
+        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::{
+        AssetId, Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock,
+        CommonBlock, Lang, Metadata, ParserVersion, Provenance, SourceSpan, SourceType, TrustLevel,
+        WorkspacePath, id_for_block, id_for_doc,
+    };
+    use time::OffsetDateTime;
+
+    fn code_doc(units: &[(&str, u32, u32, &str)]) -> CanonicalDocument {
+        let wp = WorkspacePath("crates/x/src/Main.kt".into());
+        let aid = AssetId("a".repeat(64));
+        let pv = ParserVersion("code-kotlin-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("kotlin".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("kotlin".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("kotlin".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_kotlin_ast_v1() {
+        assert_eq!(
+            CodeKotlinAstV1Chunker.chunker_version(),
+            ChunkerVersion("code-kotlin-ast-v1".into())
+        );
+    }
+
+    #[test]
+    fn one_chunk_per_unit_preserves_code_span() {
+        let doc = code_doc(&[
+            ("parse", 1, 3, "fun parse() {\n\t// x\n}"),
+            (
+                "Foo.double",
+                5,
+                7,
+                "fun double(): Int {\n\t//\n\treturn 0\n}",
+            ),
+        ]);
+        let chunks = CodeKotlinAstV1Chunker.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-kotlin-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!("\tval x{i} = {i}"))
+            .collect::<Vec<_>>()
+            .join("\n");
+        let code = format!("fun big() {{\n{body}\n}}");
+        let doc = code_doc(&[("big", 1, 502, &code)]);
+        let chunks = CodeKotlinAstV1Chunker.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_unstable();
+        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, "fun 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 = CodeKotlinAstV1Chunker.chunk(&doc, &policy()).unwrap_err();
+        assert!(err.to_string().contains("CodeKotlinAstV1Chunker"));
+    }
+
+    #[test]
+    fn deterministic_chunk_ids_1000() {
+        let doc = code_doc(&[("parse", 1, 2, "fun parse() {}\n")]);
+        let base: Vec<String> = CodeKotlinAstV1Chunker
+            .chunk(&doc, &policy())
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        for _ in 0..1000 {
+            let again: Vec<String> = CodeKotlinAstV1Chunker
+                .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!(
+            CodeKotlinAstV1Chunker.policy_hash(&p),
+            crate::MdHeadingV1Chunker.policy_hash(&p)
+        );
+    }
+}

crates/kebab-chunk/src/code_python_ast_v1.rs

@@ -0,0 +1,378 @@
+//! `code-python-ast-v1` — maps a tree-sitter-derived Python 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-python-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 CodePythonAstV1Chunker;
+
+impl Chunker for CodePythonAstV1Chunker {
+    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!(
+                    "CodePythonAstV1Chunker only handles code docs (got non-Code block)"
+                ),
+            };
+            if !matches!(c.common.source_span, SourceSpan::Code { .. }) {
+                anyhow::bail!(
+                    "CodePythonAstV1Chunker 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-python-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(),
+        tokenized_korean_text: crate::tokenize_korean_morphological(&text),
+        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::{
+        AssetId, Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock,
+        CommonBlock, Lang, Metadata, ParserVersion, Provenance, SourceSpan, SourceType, TrustLevel,
+        WorkspacePath, id_for_block, id_for_doc,
+    };
+    use time::OffsetDateTime;
+
+    fn code_doc(units: &[(&str, u32, u32, &str)]) -> CanonicalDocument {
+        let wp = WorkspacePath("crates/x/src/a.py".into());
+        let aid = AssetId("a".repeat(64));
+        let pv = ParserVersion("code-python-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("python".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("python".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("python".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_python_ast_v1() {
+        assert_eq!(
+            CodePythonAstV1Chunker.chunker_version(),
+            ChunkerVersion("code-python-ast-v1".into())
+        );
+    }
+
+    #[test]
+    fn one_chunk_per_unit_preserves_code_span() {
+        let doc = code_doc(&[
+            ("parse", 1, 3, "def parse():\n    pass\n    # x"),
+            ("Foo.double", 5, 7, "def double():\n    #\n    pass"),
+        ]);
+        let chunks = CodePythonAstV1Chunker.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-python-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!("    x{i} = {i}"))
+            .collect::<Vec<_>>()
+            .join("\n");
+        let code = format!("def big():\n{body}\n");
+        let doc = code_doc(&[("big", 1, 502, &code)]);
+        let chunks = CodePythonAstV1Chunker.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_unstable();
+        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, "def parse(): pass")]);
+        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 = CodePythonAstV1Chunker.chunk(&doc, &policy()).unwrap_err();
+        assert!(err.to_string().contains("CodePythonAstV1Chunker"));
+    }
+
+    #[test]
+    fn deterministic_chunk_ids_1000() {
+        let doc = code_doc(&[("parse", 1, 2, "def parse(): pass\n")]);
+        let base: Vec<String> = CodePythonAstV1Chunker
+            .chunk(&doc, &policy())
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        for _ in 0..1000 {
+            let again: Vec<String> = CodePythonAstV1Chunker
+                .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!(
+            CodePythonAstV1Chunker.policy_hash(&p),
+            crate::MdHeadingV1Chunker.policy_hash(&p)
+        );
+    }
+}

crates/kebab-chunk/src/code_rust_ast_v1.rs

@@ -0,0 +1,378 @@
+//! `code-rust-ast-v1` — maps a tree-sitter-derived Rust 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-rust-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 CodeRustAstV1Chunker;
+
+impl Chunker for CodeRustAstV1Chunker {
+    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!(
+                    "CodeRustAstV1Chunker only handles code docs (got non-Code block)"
+                ),
+            };
+            if !matches!(c.common.source_span, SourceSpan::Code { .. }) {
+                anyhow::bail!(
+                    "CodeRustAstV1Chunker 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-rust-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(),
+        tokenized_korean_text: crate::tokenize_korean_morphological(&text),
+        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::{
+        AssetId, Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock,
+        CommonBlock, Lang, Metadata, ParserVersion, Provenance, SourceSpan, SourceType, TrustLevel,
+        WorkspacePath, id_for_block, id_for_doc,
+    };
+    use time::OffsetDateTime;
+
+    fn code_doc(units: &[(&str, u32, u32, &str)]) -> CanonicalDocument {
+        let wp = WorkspacePath("crates/x/src/a.rs".into());
+        let aid = AssetId("a".repeat(64));
+        let pv = ParserVersion("code-rust-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("rust".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("rust".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("rust".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_rust_ast_v1() {
+        assert_eq!(
+            CodeRustAstV1Chunker.chunker_version(),
+            ChunkerVersion("code-rust-ast-v1".into())
+        );
+    }
+
+    #[test]
+    fn one_chunk_per_unit_preserves_code_span() {
+        let doc = code_doc(&[
+            ("parse", 1, 3, "pub fn parse() {}\n// x\n}"),
+            ("Foo::double", 5, 7, "fn double() {}\n//\n}"),
+        ]);
+        let chunks = CodeRustAstV1Chunker.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-rust-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!("    let x{i} = {i};"))
+            .collect::<Vec<_>>()
+            .join("\n");
+        let code = format!("pub fn big() {{\n{body}\n}}");
+        let doc = code_doc(&[("big", 1, 502, &code)]);
+        let chunks = CodeRustAstV1Chunker.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_unstable();
+        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, "fn 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 = CodeRustAstV1Chunker.chunk(&doc, &policy()).unwrap_err();
+        assert!(err.to_string().contains("CodeRustAstV1Chunker"));
+    }
+
+    #[test]
+    fn deterministic_chunk_ids_1000() {
+        let doc = code_doc(&[("parse", 1, 2, "fn parse(){}\n}")]);
+        let base: Vec<String> = CodeRustAstV1Chunker
+            .chunk(&doc, &policy())
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        for _ in 0..1000 {
+            let again: Vec<String> = CodeRustAstV1Chunker
+                .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!(
+            CodeRustAstV1Chunker.policy_hash(&p),
+            crate::MdHeadingV1Chunker.policy_hash(&p)
+        );
+    }
+}

crates/kebab-chunk/src/code_text_paragraph_v1.rs

@@ -0,0 +1,170 @@
+//! p10-3: Tier 3 paragraph + line-window fallback chunker.
+//!
+//! Splits code/text files on blank-line paragraph boundaries.  Paragraphs
+//! with more than 80 lines are further split into 80-line windows with a
+//! 20-line overlap (stride 60) — the same oversize pattern used by Tier 1/2
+//! chunkers but without AST structure, hence no symbol.
+//!
+//! Per spec §9.3: all emitted chunks carry `symbol: None`.
+
+use crate::tier2_shared::{build_chunk_no_symbol, policy_hash};
+use anyhow::Result;
+use kebab_core::{Block, CanonicalDocument, Chunk, ChunkPolicy, Chunker, ChunkerVersion};
+
+pub const VERSION_LABEL: &str = "code-text-paragraph-v1";
+
+/// Lines-per-window for the oversize fallback (Tier 3).
+const FALLBACK_LINES_PER_CHUNK: usize = 80;
+/// Overlap between consecutive windows.
+const FALLBACK_LINES_OVERLAP: usize = 20;
+// stride = FALLBACK_LINES_PER_CHUNK - FALLBACK_LINES_OVERLAP = 60.
+
+#[derive(Clone, Copy, Debug, Default)]
+pub struct CodeTextParagraphV1Chunker;
+
+impl Chunker for CodeTextParagraphV1Chunker {
+    fn chunker_version(&self) -> ChunkerVersion {
+        ChunkerVersion(VERSION_LABEL.to_string())
+    }
+
+    fn policy_hash(&self, policy: &ChunkPolicy) -> String {
+        policy_hash(policy)
+    }
+
+    fn chunk(&self, doc: &CanonicalDocument, policy: &ChunkPolicy) -> Result<Vec<Chunk>> {
+        // Expect a single Block::Code carrying the full source text.
+        let (text, lang_str) = match doc.blocks.first() {
+            Some(Block::Code(cb)) => (cb.code.as_str(), cb.lang.as_deref().unwrap_or("")),
+            _ => return Ok(vec![]),
+        };
+
+        let mut chunks = Vec::new();
+        for para in split_paragraphs(text) {
+            push_paragraph(&mut chunks, doc, policy, &para, lang_str)?;
+        }
+
+        tracing::debug!(
+            target: "kebab-chunk",
+            doc_id = %doc.doc_id,
+            chunks = chunks.len(),
+            "code-text-paragraph-v1 chunked",
+        );
+
+        Ok(chunks)
+    }
+}
+
+/// A contiguous run of non-blank lines from the source text.
+struct Paragraph {
+    /// Lines joined with `\n` (no trailing newline).
+    text: String,
+    /// 1-indexed line number of the first line in the source file.
+    line_start: u32,
+    /// 1-indexed line number of the last line in the source file.
+    line_end: u32,
+}
+
+/// Split `text` into `Paragraph`s separated by blank (all-whitespace) lines.
+///
+/// Blank lines are treated as boundaries and are NOT included in any
+/// paragraph's line range.  Paragraphs that would consist entirely of blank
+/// lines are skipped.
+fn split_paragraphs(text: &str) -> Vec<Paragraph> {
+    let mut paragraphs = Vec::new();
+    let mut current: Vec<&str> = Vec::new();
+    let mut current_start: Option<u32> = None;
+
+    for (idx, line) in text.lines().enumerate() {
+        let line_no = (idx + 1) as u32;
+        let is_blank = line.trim().is_empty();
+        if is_blank {
+            if let Some(start) = current_start.take() {
+                let end = start + current.len() as u32 - 1;
+                paragraphs.push(Paragraph {
+                    text: current.join("\n"),
+                    line_start: start,
+                    line_end: end,
+                });
+                current.clear();
+            }
+        } else {
+            if current_start.is_none() {
+                current_start = Some(line_no);
+            }
+            current.push(line);
+        }
+    }
+    // Flush any trailing paragraph not terminated by a blank line.
+    if let Some(start) = current_start {
+        let end = start + current.len() as u32 - 1;
+        paragraphs.push(Paragraph {
+            text: current.join("\n"),
+            line_start: start,
+            line_end: end,
+        });
+    }
+    paragraphs
+}
+
+/// Emit one or more chunks for a single paragraph.
+///
+/// Paragraphs with ≤ `FALLBACK_LINES_PER_CHUNK` lines become a single chunk.
+/// Larger paragraphs are split into overlapping windows of
+/// `FALLBACK_LINES_PER_CHUNK` lines with stride `FALLBACK_LINES_PER_CHUNK -
+/// FALLBACK_LINES_OVERLAP`.  The last window may be shorter.  Window starts
+/// are passed as `split_key` so `id_for_chunk` can produce distinct ids
+/// across windows.
+fn push_paragraph(
+    out: &mut Vec<Chunk>,
+    doc: &CanonicalDocument,
+    policy: &ChunkPolicy,
+    para: &Paragraph,
+    lang: &str,
+) -> Result<()> {
+    let n_lines = (para.line_end - para.line_start + 1) as usize;
+
+    if n_lines <= FALLBACK_LINES_PER_CHUNK {
+        // Use line_start as split_key so each paragraph gets a distinct
+        // chunk_id even when block_ids is empty (no symbol, no AST structure).
+        // Without this, all short paragraphs from the same doc share the same
+        // base_policy_hash and therefore the same id_for_chunk result.
+        out.push(build_chunk_no_symbol(
+            doc,
+            policy,
+            &para.text,
+            para.line_start,
+            para.line_end,
+            lang,
+            VERSION_LABEL,
+            Some(para.line_start),
+        ));
+        return Ok(());
+    }
+
+    // Oversize: line-window split with overlap.
+    let stride = FALLBACK_LINES_PER_CHUNK - FALLBACK_LINES_OVERLAP;
+    let lines: Vec<&str> = para.text.lines().collect();
+    let mut i = 0usize;
+    loop {
+        let end = (i + FALLBACK_LINES_PER_CHUNK).min(lines.len());
+        let window_text = lines[i..end].join("\n");
+        let window_start = para.line_start + i as u32;
+        let window_end = para.line_start + (end as u32) - 1;
+        // Use window_start as split_key so chunk_ids are unique across windows.
+        out.push(build_chunk_no_symbol(
+            doc,
+            policy,
+            &window_text,
+            window_start,
+            window_end,
+            lang,
+            VERSION_LABEL,
+            Some(window_start),
+        ));
+        if end == lines.len() {
+            break;
+        }
+        i += stride;
+    }
+    Ok(())
+}

crates/kebab-chunk/src/code_ts_ast_v1.rs

@@ -0,0 +1,383 @@
+//! `code-ts-ast-v1` — maps a tree-sitter-derived TypeScript 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-ts-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 CodeTsAstV1Chunker;
+
+impl Chunker for CodeTsAstV1Chunker {
+    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!("CodeTsAstV1Chunker only handles code docs (got non-Code block)")
+                }
+            };
+            if !matches!(c.common.source_span, SourceSpan::Code { .. }) {
+                anyhow::bail!(
+                    "CodeTsAstV1Chunker 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-ts-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(),
+        tokenized_korean_text: crate::tokenize_korean_morphological(&text),
+        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::{
+        AssetId, Block, CanonicalDocument, ChunkPolicy, Chunker, ChunkerVersion, CodeBlock,
+        CommonBlock, Lang, Metadata, ParserVersion, Provenance, SourceSpan, SourceType, TrustLevel,
+        WorkspacePath, id_for_block, id_for_doc,
+    };
+    use time::OffsetDateTime;
+
+    fn code_doc(units: &[(&str, u32, u32, &str)]) -> CanonicalDocument {
+        let wp = WorkspacePath("crates/x/src/a.ts".into());
+        let aid = AssetId("a".repeat(64));
+        let pv = ParserVersion("code-ts-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("typescript".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("typescript".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("typescript".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_ts_ast_v1() {
+        assert_eq!(
+            CodeTsAstV1Chunker.chunker_version(),
+            ChunkerVersion("code-ts-ast-v1".into())
+        );
+    }
+
+    #[test]
+    fn one_chunk_per_unit_preserves_code_span() {
+        let doc = code_doc(&[
+            ("parse", 1, 3, "function parse(): void {\n    // x\n}"),
+            (
+                "Foo.double",
+                5,
+                7,
+                "function double(): number {\n    //\n    return 0;\n}",
+            ),
+        ]);
+        let chunks = CodeTsAstV1Chunker.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-ts-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!("    const x{i} = {i};"))
+            .collect::<Vec<_>>()
+            .join("\n");
+        let code = format!("function big(): void {{\n{body}\n}}");
+        let doc = code_doc(&[("big", 1, 502, &code)]);
+        let chunks = CodeTsAstV1Chunker.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_unstable();
+        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, "function parse(): void {}")]);
+        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 = CodeTsAstV1Chunker.chunk(&doc, &policy()).unwrap_err();
+        assert!(err.to_string().contains("CodeTsAstV1Chunker"));
+    }
+
+    #[test]
+    fn deterministic_chunk_ids_1000() {
+        let doc = code_doc(&[("parse", 1, 2, "function parse(): void {}\n")]);
+        let base: Vec<String> = CodeTsAstV1Chunker
+            .chunk(&doc, &policy())
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        for _ in 0..1000 {
+            let again: Vec<String> = CodeTsAstV1Chunker
+                .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!(
+            CodeTsAstV1Chunker.policy_hash(&p),
+            crate::MdHeadingV1Chunker.policy_hash(&p)
+        );
+    }
+}

crates/kebab-chunk/src/dockerfile_file_v1.rs

@@ -0,0 +1,58 @@
+//! p10-2: dockerfile whole-file chunker (Tier 2).
+//!
+//! Reads entire Dockerfile content and emits a single Chunk with symbol
+//! "<dockerfile>", code_lang "dockerfile", line range 1..EOF.
+//! Oversize >200 lines splits into line-windows sharing the symbol via
+//! tier2_shared::push_chunks_with_oversize.
+
+use crate::tier2_shared::{policy_hash, push_chunks_with_oversize};
+use anyhow::Result;
+use kebab_core::{Block, CanonicalDocument, Chunk, ChunkPolicy, Chunker, ChunkerVersion};
+
+pub const VERSION_LABEL: &str = "dockerfile-file-v1";
+
+#[derive(Clone, Copy, Debug, Default)]
+pub struct DockerfileFileV1Chunker;
+
+impl Chunker for DockerfileFileV1Chunker {
+    fn chunker_version(&self) -> ChunkerVersion {
+        ChunkerVersion(VERSION_LABEL.to_string())
+    }
+
+    fn policy_hash(&self, policy: &ChunkPolicy) -> String {
+        policy_hash(policy)
+    }
+
+    fn chunk(&self, doc: &CanonicalDocument, policy: &ChunkPolicy) -> Result<Vec<Chunk>> {
+        // Expect a single Block::Code carrying the full Dockerfile text.
+        let text = match doc.blocks.first() {
+            Some(Block::Code(cb)) => cb.code.as_str(),
+            _ => return Ok(vec![]),
+        };
+
+        let total_lines = text.lines().count().max(1) as u32;
+        let mut chunks = Vec::new();
+
+        push_chunks_with_oversize(
+            &mut chunks,
+            doc,
+            policy,
+            text,
+            1,
+            total_lines,
+            "<dockerfile>",
+            "dockerfile",
+            VERSION_LABEL,
+            None,
+        )?;
+
+        tracing::debug!(
+            target: "kebab-chunk",
+            doc_id = %doc.doc_id,
+            chunks = chunks.len(),
+            "dockerfile-file-v1 chunked",
+        );
+
+        Ok(chunks)
+    }
+}

crates/kebab-chunk/src/k8s_manifest_resource_v1.rs

@@ -0,0 +1,162 @@
+//! p10-2: k8s manifest resource-aware chunker.
+//!
+//! Splits a multi-document YAML file on `^---\s*$` boundaries, recognises
+//! documents that have both `apiVersion` and `kind` string fields as k8s
+//! resources, and emits one `Chunk` per resource (with oversize >200-line
+//! fallback).  Non-k8s documents are skipped; invalid YAML yields 0 chunks
+//! for the entire file.
+
+use crate::tier2_shared::{policy_hash, push_chunks_with_oversize};
+use anyhow::Result;
+use kebab_core::{Block, CanonicalDocument, Chunk, ChunkPolicy, Chunker, ChunkerVersion};
+
+pub const VERSION_LABEL: &str = "k8s-manifest-resource-v1";
+
+#[derive(Clone, Copy, Debug, Default)]
+pub struct K8sManifestResourceV1Chunker;
+
+impl Chunker for K8sManifestResourceV1Chunker {
+    fn chunker_version(&self) -> ChunkerVersion {
+        ChunkerVersion(VERSION_LABEL.to_string())
+    }
+
+    fn policy_hash(&self, policy: &ChunkPolicy) -> String {
+        policy_hash(policy)
+    }
+
+    fn chunk(&self, doc: &CanonicalDocument, policy: &ChunkPolicy) -> Result<Vec<Chunk>> {
+        // Expect a single Block::Code carrying the full YAML text.
+        let text = match doc.blocks.first() {
+            Some(Block::Code(cb)) => cb.code.as_str(),
+            _ => return Ok(vec![]),
+        };
+
+        let slices = split_yaml_documents(text);
+        let mut chunks: Vec<Chunk> = Vec::new();
+
+        for slice in slices {
+            // Invalid YAML in any document → return 0 chunks for the file.
+            let value: serde_yaml::Value = match serde_yaml::from_str(slice.text) {
+                Ok(v) => v,
+                Err(_) => return Ok(vec![]),
+            };
+
+            let Some(mapping) = value.as_mapping() else {
+                continue;
+            };
+
+            let api = mapping
+                .get("apiVersion")
+                .and_then(|v| v.as_str())
+                .unwrap_or("");
+            let kind = mapping.get("kind").and_then(|v| v.as_str()).unwrap_or("");
+
+            // Skip non-k8s documents.
+            if api.is_empty() || kind.is_empty() {
+                continue;
+            }
+
+            let metadata = mapping.get("metadata").and_then(|v| v.as_mapping());
+            let name = metadata
+                .and_then(|m| m.get("name"))
+                .and_then(|v| v.as_str())
+                .unwrap_or("<unnamed>");
+            let namespace = metadata
+                .and_then(|m| m.get("namespace"))
+                .and_then(|v| v.as_str());
+
+            let symbol = match namespace {
+                Some(ns) if !ns.is_empty() => format!("{kind}/{ns}/{name}"),
+                _ => format!("{kind}/{name}"),
+            };
+
+            push_chunks_with_oversize(
+                &mut chunks,
+                doc,
+                policy,
+                slice.text,
+                slice.line_start,
+                slice.line_end,
+                &symbol,
+                "yaml",
+                VERSION_LABEL,
+                Some(slice.line_start),
+            )?;
+        }
+
+        tracing::debug!(
+            target: "kebab-chunk",
+            doc_id = %doc.doc_id,
+            chunks = chunks.len(),
+            "k8s-manifest-resource-v1 chunked",
+        );
+
+        Ok(chunks)
+    }
+}
+
+struct YamlSlice<'a> {
+    text: &'a str,
+    line_start: u32,
+    line_end: u32,
+}
+
+/// Split raw YAML text into per-document slices on `---` separator lines.
+/// Line numbers are 1-indexed.
+fn split_yaml_documents(text: &str) -> Vec<YamlSlice<'_>> {
+    let lines: Vec<&str> = text.lines().collect();
+
+    // Collect indices of separator lines (0-based), then append a sentinel at
+    // the end so the last slice is always terminated.
+    let mut separators: Vec<usize> = lines
+        .iter()
+        .enumerate()
+        .filter_map(|(i, l)| {
+            let trimmed = l.trim_end();
+            if trimmed == "---" || trimmed.starts_with("--- ") || trimmed.starts_with("---\t") {
+                Some(i)
+            } else {
+                None
+            }
+        })
+        .collect();
+    separators.push(lines.len());
+
+    let mut slices: Vec<YamlSlice<'_>> = Vec::new();
+    let mut doc_start_line: usize = 0; // 0-based index of current doc start
+
+    for sep_line in separators {
+        if sep_line > doc_start_line {
+            let start_byte = byte_offset_of_line(text, doc_start_line);
+            let end_byte = byte_offset_of_line(text, sep_line);
+            let slice_text = &text[start_byte..end_byte];
+            if !slice_text.trim().is_empty() {
+                slices.push(YamlSlice {
+                    text: slice_text,
+                    line_start: (doc_start_line + 1) as u32,
+                    line_end: sep_line as u32,
+                });
+            }
+        }
+        doc_start_line = sep_line + 1;
+    }
+
+    slices
+}
+
+/// Return the byte offset of the start of `line_idx` (0-based line index).
+fn byte_offset_of_line(text: &str, line_idx: usize) -> usize {
+    if line_idx == 0 {
+        return 0;
+    }
+    let mut count = 0usize;
+    for (i, c) in text.char_indices() {
+        if c == '\n' {
+            count += 1;
+            if count == line_idx {
+                return i + 1;
+            }
+        }
+    }
+    text.len()
+}

crates/kebab-chunk/src/lib.rs

@@ -15,8 +15,107 @@
 //! 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;
+mod code_kotlin_ast_v1;
+mod code_python_ast_v1;
+mod code_rust_ast_v1;
+pub mod code_text_paragraph_v1;
+mod code_ts_ast_v1;
+pub mod dockerfile_file_v1;
+pub mod k8s_manifest_resource_v1;
+pub mod manifest_file_v1;
 mod md_heading_v1;
 mod pdf_page_v1;
+mod tier2_shared;
 
+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;
+pub use code_kotlin_ast_v1::CodeKotlinAstV1Chunker;
+pub use code_python_ast_v1::CodePythonAstV1Chunker;
+pub use code_rust_ast_v1::CodeRustAstV1Chunker;
+pub use code_text_paragraph_v1::CodeTextParagraphV1Chunker;
+pub use code_ts_ast_v1::CodeTsAstV1Chunker;
+pub use dockerfile_file_v1::DockerfileFileV1Chunker;
+pub use k8s_manifest_resource_v1::K8sManifestResourceV1Chunker;
+pub use manifest_file_v1::ManifestFileV1Chunker;
 pub use md_heading_v1::MdHeadingV1Chunker;
 pub use pdf_page_v1::PdfPageV1Chunker;
+
+// ── Korean morphological tokenizer ───────────────────────────────────────────
+
+use lindera::dictionary::{DictionaryKind, load_embedded_dictionary};
+use lindera::mode::Mode;
+use lindera::segmenter::Segmenter;
+use lindera::tokenizer::Tokenizer;
+
+static KOREAN_TOKENIZER: std::sync::OnceLock<Option<Tokenizer>> = std::sync::OnceLock::new();
+
+/// 한 codepoint 가 한글 음절 또는 자모인지 판정 — N-gram supplement 의 emit 대상 필터링.
+fn is_hangul(c: char) -> bool {
+    matches!(
+        c,
+        '\u{AC00}'..='\u{D7A3}'  // 한글 음절 (precomposed)
+        | '\u{1100}'..='\u{11FF}' // 한글 자모
+        | '\u{3130}'..='\u{318F}' // 한글 호환 자모
+    )
+}
+
+/// 한국어 chunk text 를 lindera ko-dic 으로 형태소 분해해 공백 join 한 결과를 반환.
+/// chunker 들이 `Chunk.tokenized_korean_text` pre-fill 에 사용.
+/// 분석 실패 시 None — 호출자는 NULL fallback 처리.
+/// Tokenizer 는 OnceLock 으로 1회 초기화; dict load 실패 시 영구 None.
+///
+/// v0.21.0 — N-gram supplement (Option β, post-v0.20.1 enhancement).
+/// ko-dic 가 compound noun (`한국정부`, `서울특별시` 등) 을 단일 token 으로
+/// 저장하는 정책 의 한계 해소 — morpheme 길이 ≥ 3 인 한글 token 에 대해
+/// 2-char sliding window n-gram 도 추가 emit. `'한국정부'` morpheme →
+/// `[한국정부, 한국, 국정, 정부]` 의 4 token 으로 expand. 사용자 의 2-char
+/// query (`'한국'`) 가 compound chunk 에서도 hit. 영어/숫자 token 은 영향
+/// 없음 (is_hangul filter). DB size + ingest latency 의 trade-off 는
+/// HOTFIXES 2026-05-28 의 "N-gram supplement (Option β)" 보강 entry.
+pub fn tokenize_korean_morphological(text: &str) -> Option<String> {
+    if text.trim().is_empty() {
+        return None;
+    }
+    let tokenizer = KOREAN_TOKENIZER.get_or_init(|| {
+        let dict = match load_embedded_dictionary(DictionaryKind::KoDic) {
+            Ok(d) => d,
+            Err(e) => {
+                tracing::warn!(target: "kebab-chunk", "tokenize_korean_morphological: dict load failed: {e}");
+                return None;
+            }
+        };
+        let segmenter = Segmenter::new(Mode::Normal, dict, None);
+        Some(Tokenizer::new(segmenter))
+    });
+    let tokenizer = tokenizer.as_ref()?;
+    let tokens = tokenizer.tokenize(text).ok()?;
+
+    let mut out_tokens: Vec<String> = Vec::with_capacity(tokens.len() * 2);
+    for tok in tokens.iter() {
+        let surface = tok.surface.as_ref();
+        out_tokens.push(surface.to_string());
+
+        // N-gram supplement: 한글 morpheme 의 2-char sliding window.
+        let chars: Vec<char> = surface.chars().collect();
+        if chars.len() >= 3 && chars.iter().all(|c| is_hangul(*c)) {
+            for window in chars.windows(2) {
+                out_tokens.push(window.iter().collect());
+            }
+        }
+    }
+
+    let joined = out_tokens.join(" ");
+    if joined.is_empty() {
+        None
+    } else {
+        Some(joined)
+    }
+}

crates/kebab-chunk/src/manifest_file_v1.rs

@@ -0,0 +1,59 @@
+//! p10-2: manifest whole-file chunker (Tier 2).
+//!
+//! Reads entire manifest file (Cargo.toml / package.json / pom.xml / go.mod /
+//! build.gradle / pyproject.toml / tsconfig.json) and emits a single Chunk
+//! with symbol "<manifest>", code_lang read from Block::Code.lang, line range
+//! 1..EOF. Oversize >200 lines splits into line-windows sharing the symbol via
+//! tier2_shared::push_chunks_with_oversize.
+
+use crate::tier2_shared::{policy_hash, push_chunks_with_oversize};
+use anyhow::Result;
+use kebab_core::{Block, CanonicalDocument, Chunk, ChunkPolicy, Chunker, ChunkerVersion};
+
+pub const VERSION_LABEL: &str = "manifest-file-v1";
+
+#[derive(Clone, Copy, Debug, Default)]
+pub struct ManifestFileV1Chunker;
+
+impl Chunker for ManifestFileV1Chunker {
+    fn chunker_version(&self) -> ChunkerVersion {
+        ChunkerVersion(VERSION_LABEL.to_string())
+    }
+
+    fn policy_hash(&self, policy: &ChunkPolicy) -> String {
+        policy_hash(policy)
+    }
+
+    fn chunk(&self, doc: &CanonicalDocument, policy: &ChunkPolicy) -> Result<Vec<Chunk>> {
+        // Expect a single Block::Code carrying the full manifest text.
+        let (text, lang) = match doc.blocks.first() {
+            Some(Block::Code(cb)) => (cb.code.as_str(), cb.lang.as_deref().unwrap_or("")),
+            _ => return Ok(vec![]),
+        };
+
+        let total_lines = text.lines().count().max(1) as u32;
+        let mut chunks = Vec::new();
+
+        push_chunks_with_oversize(
+            &mut chunks,
+            doc,
+            policy,
+            text,
+            1,
+            total_lines,
+            "<manifest>",
+            lang,
+            VERSION_LABEL,
+            None,
+        )?;
+
+        tracing::debug!(
+            target: "kebab-chunk",
+            doc_id = %doc.doc_id,
+            chunks = chunks.len(),
+            "manifest-file-v1 chunked",
+        );
+
+        Ok(chunks)
+    }
+}

crates/kebab-chunk/src/md_heading_v1.rs

@@ -1,8 +1,8 @@
 //! `md-heading-v1` — heading-aware Markdown chunker.
 
 use kebab_core::{
-    Block, BlockId, CanonicalDocument, Chunk, ChunkPolicy, Chunker,
-    ChunkerVersion, DocumentId, SourceSpan, id_for_chunk,
+    Block, BlockId, CanonicalDocument, Chunk, ChunkPolicy, Chunker, ChunkerVersion, DocumentId,
+    SourceSpan, id_for_chunk,
 };
 
 /// Version label emitted by [`MdHeadingV1Chunker`]. Bumping this label
@@ -99,11 +99,7 @@ impl Chunker for MdHeadingV1Chunker {
         hex[..POLICY_HASH_HEX_LEN].to_string()
     }
 
-    fn chunk(
-        &self,
-        doc: &CanonicalDocument,
-        policy: &ChunkPolicy,
-    ) -> anyhow::Result<Vec<Chunk>> {
+    fn chunk(&self, doc: &CanonicalDocument, policy: &ChunkPolicy) -> anyhow::Result<Vec<Chunk>> {
         let policy_hash = self.policy_hash(policy);
         let chunker_version = self.chunker_version();
         let mut out: Vec<Chunk> = Vec::new();
@@ -152,22 +148,12 @@ impl Chunker for MdHeadingV1Chunker {
                     // `collect_overlap_seed` keeps seed ≤ target/2, so
                     // a flush here never produces a chunk smaller than
                     // the seed budget.
-                    let would_exceed = acc.text_tokens + next_tokens
-                        > policy.target_tokens
+                    let would_exceed = acc.text_tokens + next_tokens > policy.target_tokens
                         && acc.has_non_heading_content();
                     if would_exceed {
-                        let overlap_seed = collect_overlap_seed(
-                            &acc,
-                            policy.overlap_tokens,
-                            policy.target_tokens,
-                        );
-                        flush(
-                            &mut acc,
-                            doc,
-                            &chunker_version,
-                            &policy_hash,
-                            &mut out,
-                        );
+                        let overlap_seed =
+                            collect_overlap_seed(&acc, policy.overlap_tokens, policy.target_tokens);
+                        flush(&mut acc, doc, &chunker_version, &policy_hash, &mut out);
                         // Seed next accumulator with the prior chunk's
                         // tail blocks (paragraph-level overlap). The
                         // heading is *not* re-included here — it lives
@@ -292,10 +278,11 @@ fn build_chunk(
 ) -> Chunk {
     debug_assert!(!blocks.is_empty(), "build_chunk requires ≥1 block");
 
-    let block_ids: Vec<BlockId> =
-        blocks.iter().map(|b| common(b).block_id.clone()).collect();
-    let source_spans: Vec<SourceSpan> =
-        blocks.iter().map(|b| common(b).source_span.clone()).collect();
+    let block_ids: Vec<BlockId> = blocks.iter().map(|b| common(b).block_id.clone()).collect();
+    let source_spans: Vec<SourceSpan> = blocks
+        .iter()
+        .map(|b| common(b).source_span.clone())
+        .collect();
 
     // heading_path: pick the first non-Heading block's heading_path
     // (which already includes every parent heading per kb-normalize).
@@ -339,17 +326,13 @@ fn build_chunk(
         text.len().div_ceil(BYTES_PER_TOKEN)
     };
 
-    let chunk_id = id_for_chunk(
-        &doc.doc_id,
-        chunker_version,
-        &block_ids,
-        policy_hash,
-    );
+    let chunk_id = id_for_chunk(&doc.doc_id, chunker_version, &block_ids, policy_hash);
 
     Chunk {
         chunk_id,
         doc_id: DocumentId(doc.doc_id.0.clone()),
         block_ids,
+        tokenized_korean_text: crate::tokenize_korean_morphological(&text),
         text,
         heading_path,
         source_spans,
@@ -387,9 +370,7 @@ fn render_block_text(b: &Block) -> String {
         // alt keeps lexical search hits on filenames working even when
         // P6-1's filename auto-fill is bypassed.
         Block::ImageRef(i) => {
-            let alt = if !i.alt.is_empty() {
-                i.alt.clone()
-            } else {
+            let alt = if i.alt.is_empty() {
                 // P6-1 falls back to filename so this branch is
                 // defensive — keep it lest a future test fixture or
                 // synthetic block path skip the auto-fill.
@@ -399,17 +380,11 @@ fn render_block_text(b: &Block) -> String {
                     .filter(|s| !s.is_empty())
                     .unwrap_or("[image]")
                     .to_string()
+            } else {
+                i.alt.clone()
             };
-            let ocr = i
-                .ocr
-                .as_ref()
-                .map(|o| o.joined.as_str())
-                .unwrap_or("");
-            let cap = i
-                .caption
-                .as_ref()
-                .map(|c| c.text.as_str())
-                .unwrap_or("");
+            let ocr = i.ocr.as_ref().map_or("", |o| o.joined.as_str());
+            let cap = i.caption.as_ref().map_or("", |c| c.text.as_str());
             [alt.as_str(), ocr, cap]
                 .iter()
                 .filter(|s| !s.is_empty())
@@ -449,9 +424,8 @@ fn common(b: &Block) -> &kebab_core::CommonBlock {
 mod tests {
     use super::*;
     use kebab_core::{
-        AssetId, CodeBlock, CommonBlock, HeadingBlock, ImageRefBlock, Lang,
-        Metadata, Provenance, SourceType, TableBlock, TextBlock, TrustLevel,
-        WorkspacePath, id_for_block,
+        AssetId, CodeBlock, CommonBlock, HeadingBlock, ImageRefBlock, Lang, Metadata, Provenance,
+        SourceType, TableBlock, TextBlock, TrustLevel, WorkspacePath, id_for_block,
     };
     use time::OffsetDateTime;
 
@@ -472,6 +446,10 @@ mod tests {
                 trust_level: TrustLevel::Primary,
                 user_id_alias: None,
                 user: Default::default(),
+                repo: None,
+                git_branch: None,
+                git_commit: None,
+                code_lang: None,
             },
             provenance: Provenance { events: vec![] },
             parser_version: kebab_core::ParserVersion("test-parser-0".into()),
@@ -490,12 +468,7 @@ mod tests {
         SourceSpan::Line { start, end }
     }
 
-    fn common_for(
-        kind: &str,
-        heading_path: &[String],
-        ordinal: u32,
-        s: SourceSpan,
-    ) -> CommonBlock {
+    fn common_for(kind: &str, heading_path: &[String], ordinal: u32, s: SourceSpan) -> CommonBlock {
         CommonBlock {
             block_id: id_for_block(&doc_id(), kind, heading_path, ordinal, &s),
             heading_path: heading_path.to_vec(),
@@ -530,12 +503,7 @@ mod tests {
         })
     }
 
-    fn paragraph(
-        text: &str,
-        heading_path: &[&str],
-        ordinal: u32,
-        line: u32,
-    ) -> Block {
+    fn paragraph(text: &str, heading_path: &[&str], ordinal: u32, line: u32) -> Block {
         let hp: Vec<String> = heading_path.iter().map(|s| (*s).into()).collect();
         Block::Paragraph(TextBlock {
             common: common_for("paragraph", &hp, ordinal, span(line, line)),
@@ -544,12 +512,7 @@ mod tests {
         })
     }
 
-    fn code_block(
-        code: &str,
-        heading_path: &[&str],
-        ordinal: u32,
-        s: SourceSpan,
-    ) -> Block {
+    fn code_block(code: &str, heading_path: &[&str], ordinal: u32, s: SourceSpan) -> Block {
         let hp: Vec<String> = heading_path.iter().map(|s| (*s).into()).collect();
         Block::Code(CodeBlock {
             common: common_for("code", &hp, ordinal, s),
@@ -576,12 +539,7 @@ mod tests {
         })
     }
 
-    fn image_ref(
-        alt: &str,
-        heading_path: &[&str],
-        ordinal: u32,
-        line: u32,
-    ) -> Block {
+    fn image_ref(alt: &str, heading_path: &[&str], ordinal: u32, line: u32) -> Block {
         let hp: Vec<String> = heading_path.iter().map(|s| (*s).into()).collect();
         Block::ImageRef(ImageRefBlock {
             common: common_for("imageref", &hp, ordinal, span(line, line)),

crates/kebab-chunk/src/pdf_page_v1.rs

@@ -53,18 +53,21 @@
 //! one chunk per atomic block. PdfPageV1 cannot.
 //!
 //! Workaround that doesn't change the §4.2 recipe: feed a per-chunk
-//! variant `format!("{base_policy_hash}#c{char_start}")` into the
-//! recipe's `policy_hash` slot (so distinct chunks distinguish via
-//! different policy_hash inputs), while storing the unmodified
-//! `base_policy_hash` in `Chunk.policy_hash` so the field still answers
-//! "what policy was active". Logged in `tasks/HOTFIXES.md`.
+//! variant `format!("{base_policy_hash}#c{segment_start}")` into the
+//! recipe's `policy_hash` slot. `segment_start` is the pre-overlap
+//! segment boundary, strictly increasing across the returned chunks
+//! even when the overlap walk collapses `actual_start` to a previous
+//! chunk's `prev_min`. Unmodified `base_policy_hash` is stored in
+//! `Chunk.policy_hash` so the field still answers "what policy was
+//! active". v1.1 second-iteration patch — logged in
+//! `tasks/HOTFIXES.md` (2026-05-27).
 
 use kebab_core::{
     Block, BlockId, CanonicalDocument, Chunk, ChunkPolicy, Chunker, ChunkerVersion, DocumentId,
     SourceSpan, id_for_chunk,
 };
 
-const VERSION_LABEL: &str = "pdf-page-v1";
+const VERSION_LABEL: &str = "pdf-page-v1.1";
 const BYTES_PER_TOKEN: usize = 3;
 const POLICY_HASH_HEX_LEN: usize = 16;
 
@@ -89,11 +92,7 @@ impl Chunker for PdfPageV1Chunker {
         hex[..POLICY_HASH_HEX_LEN].to_string()
     }
 
-    fn chunk(
-        &self,
-        doc: &CanonicalDocument,
-        policy: &ChunkPolicy,
-    ) -> anyhow::Result<Vec<Chunk>> {
+    fn chunk(&self, doc: &CanonicalDocument, policy: &ChunkPolicy) -> anyhow::Result<Vec<Chunk>> {
         // Validate up front — every block must be a Paragraph carrying
         // SourceSpan::Page. A mixed document signals a routing bug in
         // the caller (e.g. running this chunker on Markdown) and is
@@ -106,18 +105,13 @@ impl Chunker for PdfPageV1Chunker {
                 ),
             };
             if !matches!(common.source_span, SourceSpan::Page { .. }) {
-                anyhow::bail!(
-                    "PdfPageV1Chunker only handles PDF docs (got non-Page source_span)"
-                );
+                anyhow::bail!("PdfPageV1Chunker only handles PDF docs (got non-Page source_span)");
             }
         }
 
         let base_policy_hash = self.policy_hash(policy);
         let chunker_version = self.chunker_version();
-        let target_bytes = policy
-            .target_tokens
-            .saturating_mul(BYTES_PER_TOKEN)
-            .max(1);
+        let target_bytes = policy.target_tokens.saturating_mul(BYTES_PER_TOKEN).max(1);
         // Clamp the overlap to half the target. Without this, a policy
         // with `overlap_tokens >= target_tokens` would make every chunk
         // fully re-emit the previous chunk's text — mirrors
@@ -146,7 +140,7 @@ impl Chunker for PdfPageV1Chunker {
                 continue;
             }
 
-            for (char_start, char_end, slice) in
+            for (segment_start, char_start, char_end, slice) in
                 chunk_page(&p.text, target_bytes, overlap_bytes)
             {
                 // PDF chars-per-page comfortably fits in u32 (a single
@@ -154,20 +148,20 @@ impl Chunker for PdfPageV1Chunker {
                 // typography); silent `as u32` truncation would only
                 // surface on corrupted input, where an explicit panic
                 // is preferable to an off-by-2^32 span.
-                let char_start_u32 = u32::try_from(char_start)
-                    .expect("page chars fit in u32");
-                let char_end_u32 =
-                    u32::try_from(char_end).expect("page chars fit in u32");
+                let char_start_u32 = u32::try_from(char_start).expect("page chars fit in u32");
+                let char_end_u32 = u32::try_from(char_end).expect("page chars fit in u32");
                 let span = SourceSpan::Page {
                     page: page_num,
                     char_start: Some(char_start_u32),
                     char_end: Some(char_end_u32),
                 };
                 let block_ids: Vec<BlockId> = vec![p.common.block_id.clone()];
-                // Per-chunk policy_hash variant prevents chunk_id
-                // collision when a page produces multiple chunks. See
-                // module docs for rationale.
-                let per_chunk_hash = format!("{base_policy_hash}#c{char_start}");
+                // v0.20.0 sub-item 1 bugfix (#3): per-chunk policy_hash
+                // variant uses `segment_start` (pre-overlap boundary,
+                // strictly increasing) instead of `char_start` (post-
+                // overlap, may collapse to prev_min). See module docs +
+                // spec §4.1 root cause + HOTFIXES.md 2026-05-27.
+                let per_chunk_hash = format!("{base_policy_hash}#c{segment_start}");
                 let chunk_id =
                     id_for_chunk(&doc.doc_id, &chunker_version, &block_ids, &per_chunk_hash);
                 let token_estimate = slice.len().div_ceil(BYTES_PER_TOKEN);
@@ -176,6 +170,7 @@ impl Chunker for PdfPageV1Chunker {
                     chunk_id,
                     doc_id: DocumentId(doc.doc_id.0.clone()),
                     block_ids,
+                    tokenized_korean_text: crate::tokenize_korean_morphological(&slice),
                     text: slice,
                     heading_path: Vec::new(),
                     source_spans: vec![span],
@@ -198,18 +193,28 @@ impl Chunker for PdfPageV1Chunker {
 }
 
 /// Split a single page's text into ordered chunks, each represented as
-/// `(char_start, char_end, text_slice)`. Char positions are within the
-/// page text, suitable for `SourceSpan::Page::char_start` / `char_end`.
+/// `(segment_start, actual_start, chunk_end, text_slice)`.
+///
+/// - `segment_start` = pre-overlap segment boundary. Strictly increasing
+///   across the returned vec. Use this for chunk_id uniqueness suffixes.
+/// - `actual_start` = post-overlap start char index. May collapse to a
+///   previous chunk's `actual_start` under aggressive overlap policy.
+///   Use this for `SourceSpan::Page::char_start`.
+/// - `chunk_end` = chunk's end char index (exclusive).
 ///
 /// Returns an empty vector when `text` is empty or whitespace-only.
-fn chunk_page(text: &str, target_bytes: usize, overlap_bytes: usize) -> Vec<(usize, usize, String)> {
+fn chunk_page(
+    text: &str,
+    target_bytes: usize,
+    overlap_bytes: usize,
+) -> Vec<(usize, usize, usize, String)> {
     let chars: Vec<char> = text.chars().collect();
     let n = chars.len();
     if n == 0 {
         return Vec::new();
     }
     if text.len() <= target_bytes {
-        return vec![(0, n, text.to_string())];
+        return vec![(0, 0, n, text.to_string())];
     }
 
     // Build candidate boundary positions (char indices where a chunk
@@ -222,8 +227,7 @@ fn chunk_page(text: &str, target_bytes: usize, overlap_bytes: usize) -> Vec<(usi
         let c = chars[k];
         let nx = chars[k + 1];
         let is_paragraph_break = c == '\n' && nx == '\n';
-        let is_sentence_end =
-            matches!(c, '.' | '?' | '!') && nx.is_whitespace();
+        let is_sentence_end = matches!(c, '.' | '?' | '!') && nx.is_whitespace();
         if (is_paragraph_break || is_sentence_end) && k + 2 <= n {
             bounds.push(k + 2);
         }
@@ -235,11 +239,9 @@ fn chunk_page(text: &str, target_bytes: usize, overlap_bytes: usize) -> Vec<(usi
     bounds.dedup();
 
     // UTF-8 byte length of the slice between two char indices.
-    let byte_len = |a: usize, b: usize| -> usize {
-        chars[a..b].iter().map(|c| c.len_utf8()).sum()
-    };
+    let byte_len = |a: usize, b: usize| -> usize { chars[a..b].iter().map(|c| c.len_utf8()).sum() };
 
-    let mut chunks: Vec<(usize, usize, String)> = Vec::new();
+    let mut chunks: Vec<(usize, usize, usize, String)> = Vec::new();
     let mut seg_idx: usize = 0;
     while seg_idx + 1 < bounds.len() {
         let start = bounds[seg_idx];
@@ -264,7 +266,9 @@ fn chunk_page(text: &str, target_bytes: usize, overlap_bytes: usize) -> Vec<(usi
         // have absorbed up to `overlap_bytes` of bytes, but never past
         // the previous chunk's start (no full re-emission).
         let actual_start = if let Some(prev) = chunks.last() {
-            let prev_min = prev.0;
+            // prev tuple shape = (segment_start, actual_start, chunk_end, slice).
+            // overlap walk floor = previous chunk's actual_start (prev.1).
+            let prev_min = prev.1;
             let mut a = start;
             let mut acc_o: usize = 0;
             while a > prev_min {
@@ -281,7 +285,7 @@ fn chunk_page(text: &str, target_bytes: usize, overlap_bytes: usize) -> Vec<(usi
         };
 
         let slice: String = chars[actual_start..chunk_end].iter().collect();
-        chunks.push((actual_start, chunk_end, slice));
+        chunks.push((start, actual_start, chunk_end, slice));
         seg_idx = end_idx;
     }
 
@@ -347,6 +351,10 @@ mod tests {
                 trust_level: TrustLevel::Primary,
                 user_id_alias: None,
                 user: Default::default(),
+                repo: None,
+                git_branch: None,
+                git_commit: None,
+                code_lang: None,
             },
             provenance: Provenance { events: vec![] },
             parser_version,
@@ -386,7 +394,11 @@ mod tests {
             assert_eq!(c.heading_path, Vec::<String>::new());
             assert_eq!(c.source_spans.len(), 1);
             match c.source_spans[0] {
-                SourceSpan::Page { page, char_start, char_end } => {
+                SourceSpan::Page {
+                    page,
+                    char_start,
+                    char_end,
+                } => {
                     assert_eq!(page, (i as u32) + 1);
                     assert_eq!(char_start, Some(0));
                     assert!(char_end.unwrap() > 0);
@@ -431,11 +443,16 @@ mod tests {
         // N-1's char_end).
         for w in chunks.windows(2) {
             let prev_end = match w[0].source_spans[0] {
-                SourceSpan::Page { char_end: Some(e), .. } => e,
+                SourceSpan::Page {
+                    char_end: Some(e), ..
+                } => e,
                 _ => panic!("missing char_end"),
             };
             let next_start = match w[1].source_spans[0] {
-                SourceSpan::Page { char_start: Some(s), .. } => s,
+                SourceSpan::Page {
+                    char_start: Some(s),
+                    ..
+                } => s,
                 _ => panic!("missing char_start"),
             };
             assert!(
@@ -446,7 +463,7 @@ mod tests {
         // chunk_ids stay distinct despite identical block_ids — the
         // per-chunk policy_hash variant is doing its job.
         let mut ids: Vec<&str> = chunks.iter().map(|c| c.chunk_id.0.as_str()).collect();
-        ids.sort();
+        ids.sort_unstable();
         let total = ids.len();
         ids.dedup();
         assert_eq!(ids.len(), total, "all chunk_ids must be unique");
@@ -512,6 +529,10 @@ mod tests {
                 trust_level: TrustLevel::Primary,
                 user_id_alias: None,
                 user: Default::default(),
+                repo: None,
+                git_branch: None,
+                git_commit: None,
+                code_lang: None,
             },
             provenance: Provenance { events: vec![] },
             parser_version,
@@ -645,11 +666,17 @@ mod tests {
         // overlap) is the failure mode.
         for w in chunks.windows(2) {
             let prev_start = match w[0].source_spans[0] {
-                SourceSpan::Page { char_start: Some(s), .. } => s,
+                SourceSpan::Page {
+                    char_start: Some(s),
+                    ..
+                } => s,
                 _ => panic!("missing char_start"),
             };
             let next_start = match w[1].source_spans[0] {
-                SourceSpan::Page { char_start: Some(s), .. } => s,
+                SourceSpan::Page {
+                    char_start: Some(s),
+                    ..
+                } => s,
                 _ => panic!("missing char_start"),
             };
             assert!(
@@ -660,12 +687,49 @@ mod tests {
         // chunk_ids stay distinct (the per-chunk hash variant keys off
         // char_start which is now strictly increasing).
         let mut ids: Vec<&str> = chunks.iter().map(|c| c.chunk_id.0.as_str()).collect();
-        ids.sort();
+        ids.sort_unstable();
         let total = ids.len();
         ids.dedup();
         assert_eq!(ids.len(), total, "chunk_ids must remain unique");
     }
 
+    #[test]
+    fn multi_chunk_page_with_aggressive_overlap_produces_unique_chunk_ids() {
+        // 한국어 OCR text 의 trigger shape: 10 char "가" + ". " + 500 char "나".
+        // → first segment [0, 12), second segment [12, n).
+        //   page_text byte_len = 10*3 + 2 + 500*3 = 1532 > target_bytes=1500
+        //   → multi-chunk. overlap_bytes = min(240, 750) = 240 chars=80
+        //   → second chunk 의 actual_start 가 prev_min=0 collapse → same `#c0`.
+        //
+        // default_policy(500, 80) — target_tokens=500 → target_bytes=500*3=1500
+        // (한국어 3byte/char 환산), overlap_tokens=80 → overlap_bytes=min(240, 750)=240.
+        // verifier round 1 L-3 보강.
+        let early_seg = "가".repeat(10);
+        let tail = "나".repeat(500);
+        let page_text = format!("{early_seg}. {tail}");
+
+        let doc = make_pdf_doc(&[&page_text]);
+        let policy = default_policy(500, 80); // target=1500 byte, overlap=240 byte
+        let chunks = PdfPageV1Chunker.chunk(&doc, &policy).unwrap();
+
+        assert!(
+            chunks.len() >= 2,
+            "expected ≥2 chunks for {} byte page; got {}",
+            page_text.len(),
+            chunks.len()
+        );
+
+        let mut ids: Vec<&str> = chunks.iter().map(|c| c.chunk_id.0.as_str()).collect();
+        ids.sort_unstable();
+        let total = ids.len();
+        ids.dedup();
+        assert_eq!(
+            ids.len(),
+            total,
+            "all chunk_ids must be unique even when overlap walks actual_start back to prev_min"
+        );
+    }
+
     #[test]
     fn policy_hash_matches_md_heading_v1_for_identical_policy() {
         // Cross-chunker policy fingerprint identity — important so a

crates/kebab-chunk/src/tier2_shared.rs

@@ -0,0 +1,200 @@
+//! p10-2: Tier 2 chunker shared helpers (oversize fallback + Chunk build).
+//!
+//! Mirrors `code_rust_ast_v1`'s Chunk-construction pattern exactly so that
+//! id / hashes / token-count / ChunkPolicy semantics stay identical across
+//! Tier 1 (AST) and Tier 2 (resource-aware) chunkers.
+
+use anyhow::Result;
+use kebab_core::{
+    BlockId, CanonicalDocument, Chunk, ChunkPolicy, ChunkerVersion, DocumentId, SourceSpan,
+    id_for_chunk,
+};
+
+pub(crate) const AST_CHUNK_MAX_LINES: u32 = 200;
+const BYTES_PER_TOKEN: usize = 3;
+const POLICY_HASH_HEX_LEN: usize = 16;
+
+/// Compute the policy hash the same way `code_rust_ast_v1` does.
+pub(crate) fn policy_hash(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()
+}
+
+/// 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>,
+    doc: &CanonicalDocument,
+    policy: &ChunkPolicy,
+    text: &str,
+    line_start: u32,
+    line_end: u32,
+    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());
+    let base_policy_hash = policy_hash(policy);
+
+    if n_lines <= AST_CHUNK_MAX_LINES {
+        out.push(build_chunk(
+            doc,
+            &cv,
+            &base_policy_hash,
+            text,
+            line_start,
+            line_end,
+            symbol,
+            lang,
+            base_split_key,
+        ));
+        return Ok(());
+    }
+
+    let lines: Vec<&str> = text.lines().collect();
+    let total = lines.len();
+    let mut window_start = line_start;
+    let mut i = 0usize;
+    while i < total {
+        let take = (AST_CHUNK_MAX_LINES as usize).min(total - i);
+        let window_text = lines[i..i + take].join("\n");
+        let window_end = window_start + take as u32 - 1;
+        out.push(build_chunk(
+            doc,
+            &cv,
+            &base_policy_hash,
+            &window_text,
+            window_start,
+            window_end,
+            symbol,
+            lang,
+            Some(window_start),
+        ));
+        i += take;
+        window_start = window_end + 1;
+    }
+    Ok(())
+}
+
+/// Build a single `Chunk`, mirroring `make_chunk` in `code_rust_ast_v1.rs`
+/// exactly (same id recipe, same token estimate, same field set).
+///
+/// `split_key` is `Some(line_start_of_window)` for oversize splits, `None`
+/// for normal single-chunk emission.  Mirrors the `Some(part_ls)` / `None`
+/// split_key pattern in 1A-2.
+#[allow(clippy::too_many_arguments)]
+pub(crate) fn build_chunk(
+    doc: &CanonicalDocument,
+    chunker_version: &ChunkerVersion,
+    base_policy_hash: &str,
+    text: &str,
+    line_start: u32,
+    line_end: u32,
+    symbol: &str,
+    lang: &str,
+    split_key: Option<u32>,
+) -> Chunk {
+    let span = SourceSpan::Code {
+        line_start,
+        line_end,
+        symbol: Some(symbol.to_string()),
+        lang: Some(lang.to_string()),
+    };
+    build_chunk_from_span(
+        doc,
+        chunker_version,
+        base_policy_hash,
+        text,
+        span,
+        split_key,
+    )
+}
+
+/// Like `build_chunk` but emits `symbol: None`. Used by Tier 3 (per spec §9.3).
+///
+/// Accepts `policy: &ChunkPolicy` and `chunker_version: &str` (string slice)
+/// so callers don't need to pre-compute the hash and version wrapper.
+/// `split_key` is `Some(window_start)` for oversize line-window splits.
+#[allow(clippy::too_many_arguments)]
+pub(crate) fn build_chunk_no_symbol(
+    doc: &CanonicalDocument,
+    policy: &ChunkPolicy,
+    text: &str,
+    line_start: u32,
+    line_end: u32,
+    lang: &str,
+    chunker_version: &str,
+    split_key: Option<u32>,
+) -> Chunk {
+    let cv = ChunkerVersion(chunker_version.to_string());
+    let base_policy_hash = policy_hash(policy);
+    let span = SourceSpan::Code {
+        line_start,
+        line_end,
+        symbol: None,
+        lang: Some(lang.to_string()),
+    };
+    build_chunk_from_span(doc, &cv, &base_policy_hash, text, span, split_key)
+}
+
+/// Core chunk-building logic shared by `build_chunk` and `build_chunk_no_symbol`.
+///
+/// Takes a pre-built `SourceSpan` so the only difference between the two
+/// public helpers is whether `symbol` is `Some` or `None`.  All id/hash/
+/// token mechanics are identical.
+fn build_chunk_from_span(
+    doc: &CanonicalDocument,
+    chunker_version: &ChunkerVersion,
+    base_policy_hash: &str,
+    text: &str,
+    span: SourceSpan,
+    split_key: Option<u32>,
+) -> Chunk {
+    // id_hash mirrors code_rust_ast_v1's make_chunk logic:
+    //   split_key Some(k) => "{base_policy_hash}#L{k}"
+    //   split_key None    => base_policy_hash
+    let id_hash = match split_key {
+        Some(k) => format!("{base_policy_hash}#L{k}"),
+        None => base_policy_hash.to_string(),
+    };
+
+    // block_ids: Tier 2/3 chunkers have no per-block structure (the whole file
+    // is one Block::Code), so we pass an empty slice — same as using the doc-
+    // level slice without explicit block granularity.
+    let block_ids: Vec<BlockId> = vec![];
+
+    let chunk_id = id_for_chunk(
+        &DocumentId(doc.doc_id.0.clone()),
+        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,
+        tokenized_korean_text: crate::tokenize_korean_morphological(text),
+        text: text.to_string(),
+        heading_path: Vec::new(),
+        source_spans: vec![span],
+        token_estimate,
+        chunker_version: chunker_version.clone(),
+        policy_hash: base_policy_hash.to_string(),
+    }
+}

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 +1,354 @@
+//! 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/code_go_ast_snapshot.rs

@@ -0,0 +1,221 @@
+//! Snapshot test pinning the `Vec<Chunk>` JSON for a
+//! representative Go 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_rust_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::CodeGoAstV1Chunker;
+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("kebab_eval/metrics.go".into());
+    let aid = AssetId("b".repeat(64));
+    // Pin parser_version so doc_id / block_ids are reproducible.
+    let pv = ParserVersion("code-go-v1".into());
+    let doc_id = id_for_doc(&wp, &aid, &pv);
+
+    // Build a >200-line function body to force split_oversize.
+    let big_body: String = {
+        let header = "func BigCompute(data []int) int {\n";
+        let body: String = (0..210u32)
+            .map(|i| format!("\tv{i} := 0\n\tif {i} < len(data) {{\n\t\tv{i} = data[{i}]\n\t}}\n"))
+            .collect();
+        let footer = "\treturn len(data)\n}";
+        format!("{header}{body}{footer}")
+    };
+    let big_line_count = big_body.lines().count() as u32;
+    let big_line_end = 48 + big_line_count - 1;
+
+    // Representative units:
+    //  0. import block                    (lines 1–5,   ≤200)
+    //  1. free fn `ComputeMRR`            (lines 7–12,  ≤200)
+    //  2. struct `MetricsCollector`       (lines 14–20, ≤200)
+    //  3. struct `BaseEvaluator`          (lines 22–30, ≤200)
+    //  4. method `Run`                    (lines 32–38, ≤200)
+    //  5. method `Report`                 (lines 40–46, ≤200)
+    //  6. BigCompute (>200 lines)         to force split_oversize
+    let raw_units: Vec<(&str, u32, u32, String)> = vec![
+        (
+            "imports",
+            1,
+            5,
+            "import (\n\t\"fmt\"\n\t\"os\"\n\t\"strings\"\n)".to_string(),
+        ),
+        (
+            "ComputeMRR",
+            7,
+            12,
+            "func ComputeMRR(scores []float64) float64 {\n\tif len(scores) == 0 {\n\t\treturn 0.0\n\t}\n\t_ = fmt.Sprintf(\"%v\", scores)\n\treturn 1.0 / float64(len(scores))\n}".to_string(),
+        ),
+        (
+            "MetricsCollector",
+            14,
+            20,
+            "type MetricsCollector struct {\n\tScores []float64\n\tLabels []string\n\tCounts map[string]int\n\tTotals map[string]float64\n\tTags   []string\n}".to_string(),
+        ),
+        (
+            "BaseEvaluator",
+            22,
+            30,
+            "type BaseEvaluator struct {\n\tName string\n}\n\nfunc (e *BaseEvaluator) Evaluate(data []string) error {\n\t_ = os.Stderr\n\t_ = strings.Join(data, \",\")\n\treturn nil\n}".to_string(),
+        ),
+        (
+            "MetricsCollector.Run",
+            32,
+            38,
+            "func (m *MetricsCollector) Run(inputs []float64) {\n\tfor _, inp := range inputs {\n\t\tm.Scores = append(\n\t\t\tm.Scores,\n\t\t\tinp,\n\t\t)\n\t}\n}".to_string(),
+        ),
+        (
+            "MetricsCollector.Report",
+            40,
+            46,
+            "func (m *MetricsCollector) Report() map[string]interface{} {\n\treturn map[string]interface{}{\n\t\t\"mean\":  0.0,\n\t\t\"count\": len(m.Scores),\n\t\t\"tags\":  m.Tags,\n\t}\n}".to_string(),
+        ),
+        ("BigCompute", 48, big_line_end, big_body),
+    ];
+
+    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("go".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("go".into()),
+                code: code.clone(),
+            })
+        })
+        .collect();
+
+    CanonicalDocument {
+        doc_id,
+        source_asset_id: aid,
+        workspace_path: wp,
+        title: "metrics.go".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("go".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-go-ast-v1".into()),
+    }
+}
+
+#[test]
+fn code_go_ast_chunks_snapshot() {
+    let doc = fixed_doc();
+    let policy = fixed_policy();
+
+    let chunks = CodeGoAstV1Chunker.chunk(&doc, &policy).expect("chunk");
+    let actual = serde_json::to_value(&chunks).unwrap();
+
+    let dir = fixtures_dir();
+    let baseline_path = dir.join("code-sample.go.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-go-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_go_ast_chunks_are_deterministic() {
+    let policy = fixed_policy();
+    let baseline: Vec<String> = CodeGoAstV1Chunker
+        .chunk(&fixed_doc(), &policy)
+        .unwrap()
+        .into_iter()
+        .map(|c| c.chunk_id.0)
+        .collect();
+    for _ in 0..5 {
+        let again: Vec<String> = CodeGoAstV1Chunker
+            .chunk(&fixed_doc(), &policy)
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        assert_eq!(again, baseline);
+    }
+}

crates/kebab-chunk/tests/code_java_ast_snapshot.rs

@@ -0,0 +1,221 @@
+//! Snapshot test pinning the `Vec<Chunk>` JSON for a
+//! representative Java 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_rust_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::CodeJavaAstV1Chunker;
+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("src/main/java/com/example/Metrics.java".into());
+    let aid = AssetId("b".repeat(64));
+    // Pin parser_version so doc_id / block_ids are reproducible.
+    let pv = ParserVersion("code-java-v1".into());
+    let doc_id = id_for_doc(&wp, &aid, &pv);
+
+    // Build a >200-line method body to force split_oversize.
+    let big_body: String = {
+        let header = "public class BigCompute {\n    public int compute(int[] data) {\n";
+        let body: String = (0..210u32)
+            .map(|i| format!("        int v{i} = {i} < data.length ? data[{i}] : 0;\n"))
+            .collect();
+        let footer = "        return data.length;\n    }\n}";
+        format!("{header}{body}{footer}")
+    };
+    let big_line_count = big_body.lines().count() as u32;
+    let big_line_end = 48 + big_line_count - 1;
+
+    // Representative units:
+    //  0. import block                      (lines 1–5,   ≤200)
+    //  1. free method `computeMRR`          (lines 7–12,  ≤200)
+    //  2. class `MetricsCollector`          (lines 14–20, ≤200)
+    //  3. class `BaseEvaluator`             (lines 22–30, ≤200)
+    //  4. method `MetricsCollector.run`     (lines 32–38, ≤200)
+    //  5. method `MetricsCollector.report`  (lines 40–46, ≤200)
+    //  6. BigCompute (>200 lines)           to force split_oversize
+    let raw_units: Vec<(&str, u32, u32, String)> = vec![
+        (
+            "imports",
+            1,
+            5,
+            "import java.util.List;\nimport java.util.Map;\nimport java.util.ArrayList;\nimport java.util.HashMap;\nimport java.util.stream.Collectors;".to_string(),
+        ),
+        (
+            "computeMRR",
+            7,
+            12,
+            "public static double computeMRR(List<Double> scores) {\n    if (scores.isEmpty()) {\n        return 0.0;\n    }\n    return 1.0 / scores.size();\n}".to_string(),
+        ),
+        (
+            "MetricsCollector",
+            14,
+            20,
+            "public class MetricsCollector {\n    private List<Double> scores;\n    private List<String> labels;\n    private Map<String, Integer> counts;\n    private Map<String, Double> totals;\n    private List<String> tags;\n}".to_string(),
+        ),
+        (
+            "BaseEvaluator",
+            22,
+            30,
+            "public class BaseEvaluator {\n    private String name;\n\n    public BaseEvaluator(String name) {\n        this.name = name;\n    }\n\n    public void evaluate(List<String> data) throws Exception {\n        String joined = String.join(\",\", data);\n    }\n}".to_string(),
+        ),
+        (
+            "MetricsCollector.run",
+            32,
+            38,
+            "public void run(List<Double> inputs) {\n    for (Double inp : inputs) {\n        scores.add(\n            inp\n        );\n    }\n}".to_string(),
+        ),
+        (
+            "MetricsCollector.report",
+            40,
+            46,
+            "public Map<String, Object> report() {\n    Map<String, Object> result = new HashMap<>();\n    result.put(\"mean\", 0.0);\n    result.put(\"count\", scores.size());\n    result.put(\"tags\", tags);\n    return result;\n}".to_string(),
+        ),
+        ("BigCompute", 48, big_line_end, big_body),
+    ];
+
+    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("java".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("java".into()),
+                code: code.clone(),
+            })
+        })
+        .collect();
+
+    CanonicalDocument {
+        doc_id,
+        source_asset_id: aid,
+        workspace_path: wp,
+        title: "Metrics.java".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("java".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-java-ast-v1".into()),
+    }
+}
+
+#[test]
+fn code_java_ast_chunks_snapshot() {
+    let doc = fixed_doc();
+    let policy = fixed_policy();
+
+    let chunks = CodeJavaAstV1Chunker.chunk(&doc, &policy).expect("chunk");
+    let actual = serde_json::to_value(&chunks).unwrap();
+
+    let dir = fixtures_dir();
+    let baseline_path = dir.join("code-sample.java.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-java-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_java_ast_chunks_are_deterministic() {
+    let policy = fixed_policy();
+    let baseline: Vec<String> = CodeJavaAstV1Chunker
+        .chunk(&fixed_doc(), &policy)
+        .unwrap()
+        .into_iter()
+        .map(|c| c.chunk_id.0)
+        .collect();
+    for _ in 0..5 {
+        let again: Vec<String> = CodeJavaAstV1Chunker
+            .chunk(&fixed_doc(), &policy)
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        assert_eq!(again, baseline);
+    }
+}

crates/kebab-chunk/tests/code_js_ast_snapshot.rs

@@ -0,0 +1,221 @@
+//! Snapshot test pinning the `Vec<Chunk>` JSON for a
+//! representative JavaScript 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_rust_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::CodeJsAstV1Chunker;
+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("src/bar.js".into());
+    let aid = AssetId("b".repeat(64));
+    // Pin parser_version so doc_id / block_ids are reproducible.
+    let pv = ParserVersion("code-js-v1".into());
+    let doc_id = id_for_doc(&wp, &aid, &pv);
+
+    // Build a >200-line function body to force split_oversize.
+    let big_body: String = {
+        let header = "function bigTransform(items) {\n";
+        let body: String = (0..210u32)
+            .map(|i| format!("  const v{i} = items[{i}] !== undefined ? items[{i}] : null;\n"))
+            .collect();
+        let footer = "  return items;\n}";
+        format!("{header}{body}{footer}")
+    };
+    let big_line_count = big_body.lines().count() as u32;
+    let big_line_end = 48 + big_line_count - 1;
+
+    // Representative units:
+    //  0. require/import block       (lines 1–5,   ≤200)
+    //  1. free fn `add`              (lines 7–12,  ≤200)
+    //  2. class `EventBus`           (lines 14–20, ≤200)
+    //  3. class `BaseHandler`        (lines 22–30, ≤200)
+    //  4. method `EventBus.emit`     (lines 32–38, ≤200)
+    //  5. method `EventBus.on`       (lines 40–46, ≤200)
+    //  6. bigTransform (>200 lines)  to force split_oversize
+    let raw_units: Vec<(&str, u32, u32, String)> = vec![
+        (
+            "requires",
+            1,
+            5,
+            "const fs = require('fs');\nconst path = require('path');\nconst { EventEmitter } = require('events');\nconst assert = require('assert');\nconst crypto = require('crypto');".to_string(),
+        ),
+        (
+            "add",
+            7,
+            12,
+            "export function add(a, b) {\n  if (typeof a !== 'number') throw new TypeError('a');\n  if (typeof b !== 'number') throw new TypeError('b');\n  const result = a + b;\n  assert(isFinite(result));\n  return result;\n}".to_string(),
+        ),
+        (
+            "EventBus",
+            14,
+            20,
+            "class EventBus {\n  constructor() {\n    this._handlers = new Map();\n    this._history = [];\n    this._maxHistory = 100;\n    this._seq = 0;\n  }\n}".to_string(),
+        ),
+        (
+            "BaseHandler",
+            22,
+            30,
+            "class BaseHandler {\n  handle(event) {\n    throw new Error('not implemented');\n  }\n  batchHandle(events) {\n    const results = [];\n    for (const ev of events) {\n      results.push(this.handle(ev));\n    }\n    return results;\n  }\n}".to_string(),
+        ),
+        (
+            "EventBus.emit",
+            32,
+            38,
+            "class EventBus {\n  emit(name, payload) {\n    const handlers = this._handlers.get(name) ?? [];\n    for (const h of handlers) {\n      h(payload);\n    }\n    return this;\n  }\n}".to_string(),
+        ),
+        (
+            "EventBus.on",
+            40,
+            46,
+            "class EventBus {\n  on(name, handler) {\n    if (!this._handlers.has(name)) {\n      this._handlers.set(name, []);\n    }\n    this._handlers.get(name).push(handler);\n    return this;\n  }\n}".to_string(),
+        ),
+        ("bigTransform", 48, big_line_end, big_body),
+    ];
+
+    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("javascript".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("javascript".into()),
+                code: code.clone(),
+            })
+        })
+        .collect();
+
+    CanonicalDocument {
+        doc_id,
+        source_asset_id: aid,
+        workspace_path: wp,
+        title: "bar.js".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("javascript".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-js-ast-v1".into()),
+    }
+}
+
+#[test]
+fn code_js_ast_chunks_snapshot() {
+    let doc = fixed_doc();
+    let policy = fixed_policy();
+
+    let chunks = CodeJsAstV1Chunker.chunk(&doc, &policy).expect("chunk");
+    let actual = serde_json::to_value(&chunks).unwrap();
+
+    let dir = fixtures_dir();
+    let baseline_path = dir.join("code-sample.js.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-js-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_js_ast_chunks_are_deterministic() {
+    let policy = fixed_policy();
+    let baseline: Vec<String> = CodeJsAstV1Chunker
+        .chunk(&fixed_doc(), &policy)
+        .unwrap()
+        .into_iter()
+        .map(|c| c.chunk_id.0)
+        .collect();
+    for _ in 0..5 {
+        let again: Vec<String> = CodeJsAstV1Chunker
+            .chunk(&fixed_doc(), &policy)
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        assert_eq!(again, baseline);
+    }
+}

crates/kebab-chunk/tests/code_kotlin_ast_snapshot.rs

@@ -0,0 +1,221 @@
+//! Snapshot test pinning the `Vec<Chunk>` JSON for a
+//! representative Kotlin 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_rust_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::CodeKotlinAstV1Chunker;
+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("src/main/kotlin/com/example/Metrics.kt".into());
+    let aid = AssetId("b".repeat(64));
+    // Pin parser_version so doc_id / block_ids are reproducible.
+    let pv = ParserVersion("code-kotlin-v1".into());
+    let doc_id = id_for_doc(&wp, &aid, &pv);
+
+    // Build a >200-line function body to force split_oversize.
+    let big_body: String = {
+        let header = "class BigCompute {\n    fun compute(data: IntArray): Int {\n";
+        let body: String = (0..210u32)
+            .map(|i| format!("        val v{i} = if ({i} < data.size) data[{i}] else 0\n"))
+            .collect();
+        let footer = "        return data.size\n    }\n}";
+        format!("{header}{body}{footer}")
+    };
+    let big_line_count = big_body.lines().count() as u32;
+    let big_line_end = 48 + big_line_count - 1;
+
+    // Representative units:
+    //  0. import block                      (lines 1–5,   ≤200)
+    //  1. top-level fn `computeMRR`         (lines 7–12,  ≤200)
+    //  2. data class `MetricsCollector`     (lines 14–20, ≤200)
+    //  3. class `BaseEvaluator`             (lines 22–30, ≤200)
+    //  4. method `MetricsCollector.run`     (lines 32–38, ≤200)
+    //  5. method `MetricsCollector.report`  (lines 40–46, ≤200)
+    //  6. BigCompute (>200 lines)           to force split_oversize
+    let raw_units: Vec<(&str, u32, u32, String)> = vec![
+        (
+            "imports",
+            1,
+            5,
+            "import kotlin.collections.List\nimport kotlin.collections.Map\nimport kotlin.collections.MutableList\nimport kotlin.collections.MutableMap\nimport kotlin.collections.mutableListOf".to_string(),
+        ),
+        (
+            "computeMRR",
+            7,
+            12,
+            "fun computeMRR(scores: List<Double>): Double {\n    if (scores.isEmpty()) {\n        return 0.0\n    }\n    return 1.0 / scores.size\n}".to_string(),
+        ),
+        (
+            "MetricsCollector",
+            14,
+            20,
+            "data class MetricsCollector(\n    val scores: MutableList<Double> = mutableListOf(),\n    val labels: MutableList<String> = mutableListOf(),\n    val counts: MutableMap<String, Int> = mutableMapOf(),\n    val totals: MutableMap<String, Double> = mutableMapOf(),\n    val tags: MutableList<String> = mutableListOf(),\n)".to_string(),
+        ),
+        (
+            "BaseEvaluator",
+            22,
+            30,
+            "open class BaseEvaluator(val name: String) {\n\n    fun evaluate(data: List<String>) {\n        val joined = data.joinToString(\",\")\n        println(joined)\n    }\n\n    open fun describe(): String = name\n}".to_string(),
+        ),
+        (
+            "MetricsCollector.run",
+            32,
+            38,
+            "fun MetricsCollector.run(inputs: List<Double>) {\n    for (inp in inputs) {\n        scores.add(\n            inp\n        )\n    }\n}".to_string(),
+        ),
+        (
+            "MetricsCollector.report",
+            40,
+            46,
+            "fun MetricsCollector.report(): Map<String, Any> {\n    return mapOf(\n        \"mean\" to 0.0,\n        \"count\" to scores.size,\n        \"tags\" to tags,\n    )\n}".to_string(),
+        ),
+        ("BigCompute", 48, big_line_end, big_body),
+    ];
+
+    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("kotlin".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("kotlin".into()),
+                code: code.clone(),
+            })
+        })
+        .collect();
+
+    CanonicalDocument {
+        doc_id,
+        source_asset_id: aid,
+        workspace_path: wp,
+        title: "Metrics.kt".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("kotlin".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-kotlin-ast-v1".into()),
+    }
+}
+
+#[test]
+fn code_kotlin_ast_chunks_snapshot() {
+    let doc = fixed_doc();
+    let policy = fixed_policy();
+
+    let chunks = CodeKotlinAstV1Chunker.chunk(&doc, &policy).expect("chunk");
+    let actual = serde_json::to_value(&chunks).unwrap();
+
+    let dir = fixtures_dir();
+    let baseline_path = dir.join("code-sample.kt.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-kotlin-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_kotlin_ast_chunks_are_deterministic() {
+    let policy = fixed_policy();
+    let baseline: Vec<String> = CodeKotlinAstV1Chunker
+        .chunk(&fixed_doc(), &policy)
+        .unwrap()
+        .into_iter()
+        .map(|c| c.chunk_id.0)
+        .collect();
+    for _ in 0..5 {
+        let again: Vec<String> = CodeKotlinAstV1Chunker
+            .chunk(&fixed_doc(), &policy)
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        assert_eq!(again, baseline);
+    }
+}

crates/kebab-chunk/tests/code_python_ast_snapshot.rs

@@ -0,0 +1,221 @@
+//! Snapshot test pinning the `Vec<Chunk>` JSON for a
+//! representative Python 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_rust_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::CodePythonAstV1Chunker;
+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("kebab_eval/metrics.py".into());
+    let aid = AssetId("b".repeat(64));
+    // Pin parser_version so doc_id / block_ids are reproducible.
+    let pv = ParserVersion("code-python-v1".into());
+    let doc_id = id_for_doc(&wp, &aid, &pv);
+
+    // Build a >200-line function body to force split_oversize.
+    let big_body: String = {
+        let header = "def big_compute(data):\n";
+        let body: String = (0..210u32)
+            .map(|i| format!("    v{i} = data[{i}] if {i} < len(data) else 0\n"))
+            .collect();
+        let footer = "    return sum(data)";
+        format!("{header}{body}{footer}")
+    };
+    let big_line_count = big_body.lines().count() as u32;
+    let big_line_end = 48 + big_line_count - 1;
+
+    // Representative units:
+    //  0. import block               (lines 1–5,   ≤200)
+    //  1. free fn `compute_mrr`      (lines 7–12,  ≤200)
+    //  2. class `MetricsCollector`   (lines 14–20, ≤200)
+    //  3. class `BaseEvaluator`      (lines 22–30, ≤200)
+    //  4. method `run`               (lines 32–38, ≤200)
+    //  5. method `report`            (lines 40–46, ≤200)
+    //  6. big_compute (>200 lines)   to force split_oversize
+    let raw_units: Vec<(&str, u32, u32, String)> = vec![
+        (
+            "imports",
+            1,
+            5,
+            "import os\nimport sys\nfrom typing import List\nfrom pathlib import Path\nfrom collections import defaultdict".to_string(),
+        ),
+        (
+            "compute_mrr",
+            7,
+            12,
+            "def compute_mrr(scores):\n    if not scores:\n        return 0.0\n    return sum(\n        1.0 / r for r in scores\n    ) / len(scores)".to_string(),
+        ),
+        (
+            "MetricsCollector",
+            14,
+            20,
+            "class MetricsCollector:\n    def __init__(self):\n        self.scores = []\n        self.labels = []\n        self.counts = defaultdict(int)\n        self.totals = defaultdict(float)\n        self.tags = []".to_string(),
+        ),
+        (
+            "BaseEvaluator",
+            22,
+            30,
+            "class BaseEvaluator:\n    def evaluate(self, data):\n        raise NotImplementedError\n    def batch_evaluate(self, items):\n        results = []\n        for item in items:\n            results.append(self.evaluate(item))\n        return results\n    def name(self):\n        return type(self).__name__".to_string(),
+        ),
+        (
+            "MetricsCollector.run",
+            32,
+            38,
+            "class MetricsCollector:\n    def run(self, inputs):\n        for inp in inputs:\n            score = self._score(inp)\n            self.scores.append(\n                score\n            )".to_string(),
+        ),
+        (
+            "MetricsCollector.report",
+            40,
+            46,
+            "class MetricsCollector:\n    def report(self):\n        return {\n            'mean': sum(self.scores) / max(len(self.scores), 1),\n            'count': len(self.scores),\n            'tags': self.tags,\n        }".to_string(),
+        ),
+        ("big_compute", 48, big_line_end, big_body),
+    ];
+
+    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("python".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("python".into()),
+                code: code.clone(),
+            })
+        })
+        .collect();
+
+    CanonicalDocument {
+        doc_id,
+        source_asset_id: aid,
+        workspace_path: wp,
+        title: "metrics.py".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("python".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-python-ast-v1".into()),
+    }
+}
+
+#[test]
+fn code_python_ast_chunks_snapshot() {
+    let doc = fixed_doc();
+    let policy = fixed_policy();
+
+    let chunks = CodePythonAstV1Chunker.chunk(&doc, &policy).expect("chunk");
+    let actual = serde_json::to_value(&chunks).unwrap();
+
+    let dir = fixtures_dir();
+    let baseline_path = dir.join("code-sample.py.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-python-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_python_ast_chunks_are_deterministic() {
+    let policy = fixed_policy();
+    let baseline: Vec<String> = CodePythonAstV1Chunker
+        .chunk(&fixed_doc(), &policy)
+        .unwrap()
+        .into_iter()
+        .map(|c| c.chunk_id.0)
+        .collect();
+    for _ in 0..5 {
+        let again: Vec<String> = CodePythonAstV1Chunker
+            .chunk(&fixed_doc(), &policy)
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        assert_eq!(again, baseline);
+    }
+}

crates/kebab-chunk/tests/code_rust_ast_snapshot.rs

@@ -0,0 +1,221 @@
+//! Snapshot test pinning the `Vec<Chunk>` JSON for a
+//! representative Rust 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_rust_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::CodeRustAstV1Chunker;
+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("crates/kebab-chunk/src/code_rust_ast_v1.rs".into());
+    let aid = AssetId("b".repeat(64));
+    // Pin parser_version so doc_id / block_ids are reproducible.
+    let pv = ParserVersion("code-rust-v1".into());
+    let doc_id = id_for_doc(&wp, &aid, &pv);
+
+    // Build a >200-line function body to force split_oversize.
+    let big_body: String = {
+        let header = "pub fn big_fn(input: &[u8]) -> Vec<u8> {\n";
+        let body: String = (0..210u32)
+            .map(|i| format!("    let v{i} = input.get({i} as usize).copied().unwrap_or(0);\n"))
+            .collect();
+        let footer = "    vec![0u8]\n}";
+        format!("{header}{body}{footer}")
+    };
+    let big_line_count = big_body.lines().count() as u32;
+    let big_line_end = 48 + big_line_count - 1;
+
+    // Representative units:
+    //  0. top-level use+const block  (lines 1–5,   ≤200)
+    //  1. free fn `parse`            (lines 7–12,  ≤200)
+    //  2. struct `Foo`               (lines 14–20, ≤200)
+    //  3. trait `Frobable`           (lines 22–30, ≤200)
+    //  4. impl Foo::double           (lines 32–38, ≤200)
+    //  5. impl Foo::triple           (lines 40–46, ≤200)
+    //  6. big_fn (>200 lines)        to force split_oversize
+    let raw_units: Vec<(&str, u32, u32, String)> = vec![
+        (
+            "use+const",
+            1,
+            5,
+            "use std::collections::HashMap;\nuse std::fmt;\n\nconst MAX: usize = 1024;\nconst MIN: usize = 0;".to_string(),
+        ),
+        (
+            "parse",
+            7,
+            12,
+            "pub fn parse(input: &str) -> Option<u32> {\n    input\n        .trim()\n        .parse()\n        .ok()\n}".to_string(),
+        ),
+        (
+            "Foo",
+            14,
+            20,
+            "pub struct Foo {\n    pub name: String,\n    pub value: u32,\n    pub tags: Vec<String>,\n    pub meta: Option<String>,\n    pub count: usize,\n}".to_string(),
+        ),
+        (
+            "Frobable",
+            22,
+            30,
+            "pub trait Frobable {\n    fn frob(&self) -> String;\n    fn frob_twice(&self) -> String {\n        let a = self.frob();\n        let b = self.frob();\n        format!(\"{a}{b}\")\n    }\n    fn name(&self) -> &str;\n}".to_string(),
+        ),
+        (
+            "Foo::double",
+            32,
+            38,
+            "impl Foo {\n    pub fn double(&self) -> u32 {\n        self.value\n            .checked_mul(2)\n            .unwrap_or(u32::MAX)\n    }\n}".to_string(),
+        ),
+        (
+            "Foo::triple",
+            40,
+            46,
+            "impl Foo {\n    pub fn triple(&self) -> u32 {\n        self.value\n            .checked_mul(3)\n            .unwrap_or(u32::MAX)\n    }\n}".to_string(),
+        ),
+        ("big_fn", 48, big_line_end, big_body),
+    ];
+
+    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("rust".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("rust".into()),
+                code: code.clone(),
+            })
+        })
+        .collect();
+
+    CanonicalDocument {
+        doc_id,
+        source_asset_id: aid,
+        workspace_path: wp,
+        title: "code_rust_ast_v1.rs".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("rust".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-rust-ast-v1".into()),
+    }
+}
+
+#[test]
+fn code_rust_ast_chunks_snapshot() {
+    let doc = fixed_doc();
+    let policy = fixed_policy();
+
+    let chunks = CodeRustAstV1Chunker.chunk(&doc, &policy).expect("chunk");
+    let actual = serde_json::to_value(&chunks).unwrap();
+
+    let dir = fixtures_dir();
+    let baseline_path = dir.join("code-sample.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-rust-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_rust_ast_chunks_are_deterministic() {
+    let policy = fixed_policy();
+    let baseline: Vec<String> = CodeRustAstV1Chunker
+        .chunk(&fixed_doc(), &policy)
+        .unwrap()
+        .into_iter()
+        .map(|c| c.chunk_id.0)
+        .collect();
+    for _ in 0..5 {
+        let again: Vec<String> = CodeRustAstV1Chunker
+            .chunk(&fixed_doc(), &policy)
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        assert_eq!(again, baseline);
+    }
+}

crates/kebab-chunk/tests/code_text_paragraph_v1.rs

@@ -0,0 +1,270 @@
+//! Behavioural tests for `CodeTextParagraphV1Chunker`.
+//!
+//! Documents are constructed manually (no kebab-parse-code dependency) by
+//! placing raw text into a single `Block::Code`, mirroring the pattern used
+//! in `k8s_manifest_resource_v1.rs`.
+
+use std::path::PathBuf;
+
+use kebab_chunk::CodeTextParagraphV1Chunker;
+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 time::OffsetDateTime;
+
+// ── helpers ──────────────────────────────────────────────────────────────────
+
+fn fixtures_dir() -> PathBuf {
+    PathBuf::from(env!("CARGO_MANIFEST_DIR"))
+        .join("tests")
+        .join("fixtures")
+}
+
+/// Build a `CanonicalDocument` with a single `Block::Code` containing `text`
+/// and the supplied `lang` label.
+fn text_doc(lang: &str, text: &str) -> CanonicalDocument {
+    let wp = WorkspacePath("scripts/sample.sh".into());
+    let aid = AssetId("d".repeat(64));
+    let pv = ParserVersion("code-text-paragraph-v1".into());
+    let doc_id = id_for_doc(&wp, &aid, &pv);
+
+    let line_count = text.lines().count() as u32;
+    let span = SourceSpan::Code {
+        line_start: 1,
+        line_end: line_count.max(1),
+        symbol: None,
+        lang: Some(lang.into()),
+    };
+    let bid = id_for_block(&doc_id, "code", &[], 0, &span);
+    let block = Block::Code(CodeBlock {
+        common: CommonBlock {
+            block_id: bid,
+            heading_path: vec![],
+            source_span: span,
+        },
+        lang: Some(lang.into()),
+        code: text.to_string(),
+    });
+
+    CanonicalDocument {
+        doc_id,
+        source_asset_id: aid,
+        workspace_path: wp,
+        title: "sample.sh".into(),
+        lang: Lang("und".into()),
+        blocks: vec![block],
+        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(lang.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("code-text-paragraph-v1".into()),
+    }
+}
+
+// ── tests ─────────────────────────────────────────────────────────────────────
+
+/// `sample_shell.sh` has 4 paragraphs separated by 3 blank lines:
+///   - paragraph 1: lines 1-2  (shebang + set -euo pipefail)
+///   - paragraph 2: lines 4-7  (env setup block)
+///   - paragraph 3: lines 9-11 (ingest block)
+///   - paragraph 4: lines 13-15 (report block)
+///
+/// We assert:
+///   - exactly 4 chunks (one per paragraph)
+///   - all symbols are None (Tier 3 spec §9.3)
+///   - all langs are "shell"
+///   - line ranges are strictly ascending and do NOT include the blank lines
+///     (lines 3, 8, 12 must not appear in any range)
+#[test]
+fn shell_multi_paragraph_splits_on_blank_lines() {
+    let fixture_path = fixtures_dir().join("sample_shell.sh");
+    let text = std::fs::read_to_string(&fixture_path)
+        .unwrap_or_else(|e| panic!("cannot read fixture {}: {e}", fixture_path.display()));
+
+    let doc = text_doc("shell", &text);
+    let chunks = CodeTextParagraphV1Chunker
+        .chunk(&doc, &policy())
+        .expect("chunk");
+
+    assert_eq!(
+        chunks.len(),
+        4,
+        "expected 4 chunks (one per paragraph), got {}: {chunks:#?}",
+        chunks.len()
+    );
+
+    // All symbols must be None (Tier 3 requirement).
+    for (i, chunk) in chunks.iter().enumerate() {
+        match &chunk.source_spans[0] {
+            SourceSpan::Code { symbol, .. } => {
+                assert!(
+                    symbol.is_none(),
+                    "chunk[{i}] symbol must be None for Tier 3 chunker, got {symbol:?}"
+                );
+            }
+            other => panic!("chunk[{i}]: expected Code span, got {other:?}"),
+        }
+    }
+
+    // All langs must be "shell".
+    for (i, chunk) in chunks.iter().enumerate() {
+        match &chunk.source_spans[0] {
+            SourceSpan::Code { lang, .. } => {
+                assert_eq!(
+                    lang.as_deref(),
+                    Some("shell"),
+                    "chunk[{i}] lang must be 'shell', got {lang:?}"
+                );
+            }
+            other => panic!("chunk[{i}]: expected Code span, got {other:?}"),
+        }
+    }
+
+    // Line ranges must be strictly ascending with no overlap,
+    // and blank lines (3, 8, 12) must not be included in any range.
+    let expected_ranges: &[(u32, u32)] = &[(1, 2), (4, 7), (9, 11), (13, 15)];
+    let actual_ranges: Vec<(u32, u32)> = chunks
+        .iter()
+        .map(|c| match &c.source_spans[0] {
+            SourceSpan::Code {
+                line_start,
+                line_end,
+                ..
+            } => (*line_start, *line_end),
+            other => panic!("expected Code span, got {other:?}"),
+        })
+        .collect();
+
+    assert_eq!(
+        actual_ranges, expected_ranges,
+        "line ranges mismatch: got {actual_ranges:?}, expected {expected_ranges:?}"
+    );
+}
+
+/// `sample_long_paragraph.txt` has exactly 200 non-blank lines and no blank
+/// lines, so the entire file is one paragraph.  200 > 80 (FALLBACK_LINES_PER_CHUNK),
+/// so the oversize window split fires with stride 60:
+///   - window 1: lines 1-80
+///   - window 2: lines 61-140
+///   - window 3: lines 121-200
+///
+/// All chunk_ids must be distinct (the #L{window_start} split_key suffix).
+#[test]
+fn single_long_paragraph_line_window_split() {
+    let fixture_path = fixtures_dir().join("sample_long_paragraph.txt");
+    let text = std::fs::read_to_string(&fixture_path)
+        .unwrap_or_else(|e| panic!("cannot read fixture {}: {e}", fixture_path.display()));
+
+    assert_eq!(
+        text.lines().count(),
+        200,
+        "fixture must have exactly 200 lines"
+    );
+
+    let doc = text_doc("shell", &text);
+    let chunks = CodeTextParagraphV1Chunker
+        .chunk(&doc, &policy())
+        .expect("chunk");
+
+    assert_eq!(
+        chunks.len(),
+        3,
+        "expected 3 window chunks for 200-line paragraph, got {}: {chunks:#?}",
+        chunks.len()
+    );
+
+    let expected_ranges: &[(u32, u32)] = &[(1, 80), (61, 140), (121, 200)];
+    let actual_ranges: Vec<(u32, u32)> = chunks
+        .iter()
+        .map(|c| match &c.source_spans[0] {
+            SourceSpan::Code {
+                line_start,
+                line_end,
+                ..
+            } => (*line_start, *line_end),
+            other => panic!("expected Code span, got {other:?}"),
+        })
+        .collect();
+
+    assert_eq!(
+        actual_ranges, expected_ranges,
+        "window ranges mismatch: got {actual_ranges:?}, expected {expected_ranges:?}"
+    );
+
+    // All chunk_ids must be distinct (#L{window_start} suffix differentiates them).
+    let ids: std::collections::HashSet<_> = chunks.iter().map(|c| c.chunk_id.clone()).collect();
+    assert_eq!(
+        ids.len(),
+        chunks.len(),
+        "oversize window chunks must have distinct chunk_ids"
+    );
+}
+
+/// An empty source file (no non-blank lines) must yield zero chunks.
+#[test]
+fn empty_file_emits_zero_chunks() {
+    let doc = text_doc("shell", "");
+    let chunks = CodeTextParagraphV1Chunker
+        .chunk(&doc, &policy())
+        .expect("chunk");
+
+    assert_eq!(
+        chunks.len(),
+        0,
+        "empty file must yield 0 chunks, got {}: {chunks:#?}",
+        chunks.len()
+    );
+}
+
+/// The `lang` field on each emitted chunk must match the `lang` passed to
+/// `text_doc`, regardless of content.  `symbol` must be `None` (Tier 3 spec).
+#[test]
+fn lang_field_preserved_from_input_doc() {
+    let doc = text_doc("yaml", "key1: value1\nkey2: value2\n");
+    let chunks = CodeTextParagraphV1Chunker
+        .chunk(&doc, &policy())
+        .expect("chunk");
+
+    assert!(!chunks.is_empty(), "expected at least one chunk");
+
+    match &chunks[0].source_spans[0] {
+        SourceSpan::Code { lang, symbol, .. } => {
+            assert_eq!(
+                lang.as_deref(),
+                Some("yaml"),
+                "lang must be 'yaml', got {lang:?}"
+            );
+            assert!(
+                symbol.is_none(),
+                "symbol must be None for Tier 3 chunker, got {symbol:?}"
+            );
+        }
+        other => panic!("expected Code span, got {other:?}"),
+    }
+}

crates/kebab-chunk/tests/code_ts_ast_snapshot.rs

@@ -0,0 +1,221 @@
+//! Snapshot test pinning the `Vec<Chunk>` JSON for a
+//! representative TypeScript 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_rust_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::CodeTsAstV1Chunker;
+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("src/Foo.ts".into());
+    let aid = AssetId("b".repeat(64));
+    // Pin parser_version so doc_id / block_ids are reproducible.
+    let pv = ParserVersion("code-ts-v1".into());
+    let doc_id = id_for_doc(&wp, &aid, &pv);
+
+    // Build a >200-line method body to force split_oversize.
+    let big_body: String = {
+        let header = "export class BigProcessor {\n  process(items: string[]): string[] {\n";
+        let body: String = (0..210u32)
+            .map(|i| format!("    const v{i} = items[{i}] ?? '';\n"))
+            .collect();
+        let footer = "    return items;\n  }\n}";
+        format!("{header}{body}{footer}")
+    };
+    let big_line_count = big_body.lines().count() as u32;
+    let big_line_end = 48 + big_line_count - 1;
+
+    // Representative units:
+    //  0. import block               (lines 1–5,   ≤200)
+    //  1. free fn `parseInput`       (lines 7–12,  ≤200)
+    //  2. interface `Frobable`       (lines 14–20, ≤200)
+    //  3. class `Foo`                (lines 22–30, ≤200)
+    //  4. method `Foo.double`        (lines 32–38, ≤200)
+    //  5. method `Foo.triple`        (lines 40–46, ≤200)
+    //  6. BigProcessor (>200 lines)  to force split_oversize
+    let raw_units: Vec<(&str, u32, u32, String)> = vec![
+        (
+            "imports",
+            1,
+            5,
+            "import { readFileSync } from 'fs';\nimport { join } from 'path';\nimport type { Config } from './config';\nimport { Logger } from './logger';\nimport { EventEmitter } from 'events';".to_string(),
+        ),
+        (
+            "parseInput",
+            7,
+            12,
+            "export function parseInput(raw: string): number | null {\n  const trimmed = raw.trim();\n  const n = Number(trimmed);\n  if (isNaN(n)) return null;\n  return n;\n}".to_string(),
+        ),
+        (
+            "Frobable",
+            14,
+            20,
+            "export interface Frobable {\n  frob(): string;\n  frobTwice(): string;\n  readonly name: string;\n  readonly tags: string[];\n  count: number;\n  reset(): void;\n}".to_string(),
+        ),
+        (
+            "Foo",
+            22,
+            30,
+            "export class Foo implements Frobable {\n  constructor(\n    public readonly name: string,\n    public value: number,\n    public tags: string[] = [],\n  ) {}\n  frob(): string { return this.name; }\n  frobTwice(): string { return this.name.repeat(2); }\n  reset(): void { this.value = 0; }\n}".to_string(),
+        ),
+        (
+            "Foo.double",
+            32,
+            38,
+            "export class Foo {\n  double(): number {\n    const result = this.value * 2;\n    if (result > Number.MAX_SAFE_INTEGER) {\n      return Number.MAX_SAFE_INTEGER;\n    }\n    return result;\n  }\n}".to_string(),
+        ),
+        (
+            "Foo.triple",
+            40,
+            46,
+            "export class Foo {\n  triple(): number {\n    const result = this.value * 3;\n    if (result > Number.MAX_SAFE_INTEGER) {\n      return Number.MAX_SAFE_INTEGER;\n    }\n    return result;\n  }\n}".to_string(),
+        ),
+        ("BigProcessor", 48, big_line_end, big_body),
+    ];
+
+    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("typescript".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("typescript".into()),
+                code: code.clone(),
+            })
+        })
+        .collect();
+
+    CanonicalDocument {
+        doc_id,
+        source_asset_id: aid,
+        workspace_path: wp,
+        title: "Foo.ts".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("typescript".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-ts-ast-v1".into()),
+    }
+}
+
+#[test]
+fn code_ts_ast_chunks_snapshot() {
+    let doc = fixed_doc();
+    let policy = fixed_policy();
+
+    let chunks = CodeTsAstV1Chunker.chunk(&doc, &policy).expect("chunk");
+    let actual = serde_json::to_value(&chunks).unwrap();
+
+    let dir = fixtures_dir();
+    let baseline_path = dir.join("code-sample.ts.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-ts-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_ts_ast_chunks_are_deterministic() {
+    let policy = fixed_policy();
+    let baseline: Vec<String> = CodeTsAstV1Chunker
+        .chunk(&fixed_doc(), &policy)
+        .unwrap()
+        .into_iter()
+        .map(|c| c.chunk_id.0)
+        .collect();
+    for _ in 0..5 {
+        let again: Vec<String> = CodeTsAstV1Chunker
+            .chunk(&fixed_doc(), &policy)
+            .unwrap()
+            .into_iter()
+            .map(|c| c.chunk_id.0)
+            .collect();
+        assert_eq!(again, baseline);
+    }
+}

crates/kebab-chunk/tests/dockerfile_file_v1.rs

@@ -0,0 +1,138 @@
+//! Behavioural tests for `DockerfileFileV1Chunker`.
+//!
+//! Documents are constructed manually (no kebab-parse-code dependency) by
+//! placing the raw Dockerfile text into a single `Block::Code`, mirroring the
+//! pattern used in `k8s_manifest_resource_v1.rs`.
+
+use std::path::PathBuf;
+
+use kebab_chunk::DockerfileFileV1Chunker;
+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 time::OffsetDateTime;
+
+// ── helpers ──────────────────────────────────────────────────────────────────
+
+fn fixtures_dir() -> PathBuf {
+    PathBuf::from(env!("CARGO_MANIFEST_DIR"))
+        .join("tests")
+        .join("fixtures")
+}
+
+/// Build a `CanonicalDocument` with a single `Block::Code` containing `dockerfile_text`.
+fn dockerfile_doc(dockerfile_text: &str) -> CanonicalDocument {
+    let wp = WorkspacePath("build/Dockerfile".into());
+    let aid = AssetId("d".repeat(64));
+    let pv = ParserVersion("code-dockerfile-v1".into());
+    let doc_id = id_for_doc(&wp, &aid, &pv);
+
+    let line_count = dockerfile_text.lines().count() as u32;
+    let span = SourceSpan::Code {
+        line_start: 1,
+        line_end: line_count.max(1),
+        symbol: None,
+        lang: Some("dockerfile".into()),
+    };
+    let bid = id_for_block(&doc_id, "code", &[], 0, &span);
+    let block = Block::Code(CodeBlock {
+        common: CommonBlock {
+            block_id: bid,
+            heading_path: vec![],
+            source_span: span,
+        },
+        lang: Some("dockerfile".into()),
+        code: dockerfile_text.to_string(),
+    });
+
+    CanonicalDocument {
+        doc_id,
+        source_asset_id: aid,
+        workspace_path: wp,
+        title: "Dockerfile".into(),
+        lang: Lang("und".into()),
+        blocks: vec![block],
+        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("dockerfile".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("dockerfile-file-v1".into()),
+    }
+}
+
+// ── tests ─────────────────────────────────────────────────────────────────────
+
+/// A simple 5-line Dockerfile fixture must emit exactly 1 chunk with the
+/// correct symbol, lang, and line range.
+#[test]
+fn dockerfile_emits_single_chunk() {
+    let fixture_path = fixtures_dir().join("sample.dockerfile");
+    let text = std::fs::read_to_string(&fixture_path)
+        .unwrap_or_else(|e| panic!("cannot read fixture {}: {e}", fixture_path.display()));
+
+    let doc = dockerfile_doc(&text);
+    let chunks = DockerfileFileV1Chunker
+        .chunk(&doc, &policy())
+        .expect("chunk");
+
+    assert_eq!(
+        chunks.len(),
+        1,
+        "expected 1 chunk, got {}: {chunks:#?}",
+        chunks.len()
+    );
+
+    // Inspect the Chunk's source_spans for symbol / lang / line range.
+    let span = chunks[0].source_spans.first().expect("at least one span");
+    match span {
+        SourceSpan::Code {
+            line_start,
+            line_end,
+            symbol,
+            lang,
+        } => {
+            assert_eq!(*line_start, 1, "line_start must be 1");
+            assert_eq!(*line_end, 5, "line_end must be 5 (5-line fixture)");
+            assert_eq!(
+                symbol.as_deref(),
+                Some("<dockerfile>"),
+                "symbol must be '<dockerfile>'"
+            );
+            assert_eq!(
+                lang.as_deref(),
+                Some("dockerfile"),
+                "lang must be 'dockerfile'"
+            );
+        }
+        other => panic!("expected SourceSpan::Code, got {other:?}"),
+    }
+
+    // Verify chunker_version label.
+    assert_eq!(chunks[0].chunker_version.0, "dockerfile-file-v1");
+}

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

@@ -0,0 +1,90 @@
+[
+  {
+    "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,
+    "tokenized_korean_text": "# 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 ;"
+  },
+  {
+    "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,
+    "tokenized_korean_text": "int parse _ record ( const char * line , record _ t * out ) { if ( line == NULL || out == NULL ) return ERR _ PARSE ; return OK ; }"
+  },
+  {
+    "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,
+    "tokenized_korean_text": "void print _ record ( const record _ t * r ) { printf (\"[% d ] % s ( status =% d )\\ n \", r -> id , r -> name , r -> status ); }"
+  },
+  {
+    "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,
+    "tokenized_korean_text": "int main ( void ) { record _ t r = { . id = 1 , . name = \" foo \", . status = OK }; print _ record (& r ); return 0 ; }"
+  }
+]

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

@@ -0,0 +1,112 @@
+[
+  {
+    "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,
+    "tokenized_korean_text": "# include < string > # include < vector > namespace kebab {"
+  },
+  {
+    "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,
+    "tokenized_korean_text": "class MdHeadingV 1 Chunker { public : MdHeadingV 1 Chunker ( ) = default ; ~ MdHeadingV 1 Chunker ( ) = default ; std : : string chunk _ doc ( const std : : string & doc ) { return doc ; } int operator ( ) ( int x ) const { return x * 2 ; } private : int counter _ = 0 ; };"
+  },
+  {
+    "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,
+    "tokenized_korean_text": "template < typename T > T identity ( T value ) { return value ; }"
+  },
+  {
+    "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,
+    "tokenized_korean_text": "void global _ helper ( ) { / / free function in kebab namespace }"
+  },
+  {
+    "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,
+    "tokenized_korean_text": "int main ( ) { kebab : : chunk : : MdHeadingV 1 Chunker c ; return 0 ; }"
+  }
+]

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

@@ -0,0 +1,244 @@
+[
+  {
+    "block_ids": [
+      "c182bf37e32c7fc1b868bd617f8eaf66"
+    ],
+    "chunk_id": "43de518d946dc18ec040ae20d74e0cff",
+    "chunker_version": "code-go-ast-v1",
+    "doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
+    "heading_path": [],
+    "policy_hash": "6cfe77abe2b0e5c3",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "go",
+        "line_end": 5,
+        "line_start": 1,
+        "symbol": "imports"
+      }
+    ],
+    "text": "import (\n\t\"fmt\"\n\t\"os\"\n\t\"strings\"\n)",
+    "token_estimate": 12,
+    "tokenized_korean_text": "import ( \" fmt \" \" os \" \" strings \" )"
+  },
+  {
+    "block_ids": [
+      "c9992cdcfdf3c2a7700a4abc4782a8a4"
+    ],
+    "chunk_id": "af4c382a83f1e8cdea495d8b33c11abc",
+    "chunker_version": "code-go-ast-v1",
+    "doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
+    "heading_path": [],
+    "policy_hash": "6cfe77abe2b0e5c3",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "go",
+        "line_end": 12,
+        "line_start": 7,
+        "symbol": "ComputeMRR"
+      }
+    ],
+    "text": "func ComputeMRR(scores []float64) float64 {\n\tif len(scores) == 0 {\n\t\treturn 0.0\n\t}\n\t_ = fmt.Sprintf(\"%v\", scores)\n\treturn 1.0 / float64(len(scores))\n}",
+    "token_estimate": 50,
+    "tokenized_korean_text": "func ComputeMRR ( scores [ ] float 64 ) float 64 { if len ( scores ) == 0 { return 0 . 0 } _ = fmt . Sprintf (\"% v \", scores ) return 1 . 0 / float 64 ( len ( scores ) ) }"
+  },
+  {
+    "block_ids": [
+      "5f18dc3e79fe946ba05d32c3bfc00684"
+    ],
+    "chunk_id": "4be6d8f180bc19b8651877e5264852ac",
+    "chunker_version": "code-go-ast-v1",
+    "doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
+    "heading_path": [],
+    "policy_hash": "6cfe77abe2b0e5c3",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "go",
+        "line_end": 20,
+        "line_start": 14,
+        "symbol": "MetricsCollector"
+      }
+    ],
+    "text": "type MetricsCollector struct {\n\tScores []float64\n\tLabels []string\n\tCounts map[string]int\n\tTotals map[string]float64\n\tTags   []string\n}",
+    "token_estimate": 45,
+    "tokenized_korean_text": "type MetricsCollector struct { Scores [ ] float 64 Labels [ ] string Counts map [ string ] int Totals map [ string ] float 64 Tags [ ] string }"
+  },
+  {
+    "block_ids": [
+      "3009cc022ca832c323393e4f9bcdb388"
+    ],
+    "chunk_id": "3ae182f4c6d304ee7f0aaf447142f948",
+    "chunker_version": "code-go-ast-v1",
+    "doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
+    "heading_path": [],
+    "policy_hash": "6cfe77abe2b0e5c3",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "go",
+        "line_end": 30,
+        "line_start": 22,
+        "symbol": "BaseEvaluator"
+      }
+    ],
+    "text": "type BaseEvaluator struct {\n\tName string\n}\n\nfunc (e *BaseEvaluator) Evaluate(data []string) error {\n\t_ = os.Stderr\n\t_ = strings.Join(data, \",\")\n\treturn nil\n}",
+    "token_estimate": 53,
+    "tokenized_korean_text": "type BaseEvaluator struct { Name string } func ( e * BaseEvaluator ) Evaluate ( data [ ] string ) error { _ = os . Stderr _ = strings . Join ( data , \",\") return nil }"
+  },
+  {
+    "block_ids": [
+      "e0e83d1d7f9327a1902ae9a8f67c1f1c"
+    ],
+    "chunk_id": "b962f14980e756bb8ba514e2282756cd",
+    "chunker_version": "code-go-ast-v1",
+    "doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
+    "heading_path": [],
+    "policy_hash": "6cfe77abe2b0e5c3",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "go",
+        "line_end": 38,
+        "line_start": 32,
+        "symbol": "MetricsCollector.Run"
+      }
+    ],
+    "text": "func (m *MetricsCollector) Run(inputs []float64) {\n\tfor _, inp := range inputs {\n\t\tm.Scores = append(\n\t\t\tm.Scores,\n\t\t\tinp,\n\t\t)\n\t}\n}",
+    "token_estimate": 44,
+    "tokenized_korean_text": "func ( m * MetricsCollector ) Run ( inputs [ ] float 64 ) { for _, inp := range inputs { m . Scores = append ( m . Scores , inp , ) } }"
+  },
+  {
+    "block_ids": [
+      "0e6a572bc3fe2bd6d173fe614bd1b763"
+    ],
+    "chunk_id": "441c695e990e7f49188068433e313e87",
+    "chunker_version": "code-go-ast-v1",
+    "doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
+    "heading_path": [],
+    "policy_hash": "6cfe77abe2b0e5c3",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "go",
+        "line_end": 46,
+        "line_start": 40,
+        "symbol": "MetricsCollector.Report"
+      }
+    ],
+    "text": "func (m *MetricsCollector) Report() map[string]interface{} {\n\treturn map[string]interface{}{\n\t\t\"mean\":  0.0,\n\t\t\"count\": len(m.Scores),\n\t\t\"tags\":  m.Tags,\n\t}\n}",
+    "token_estimate": 53,
+    "tokenized_korean_text": "func ( m * MetricsCollector ) Report ( ) map [ string ] interface {} { return map [ string ] interface {}{ \" mean \": 0 . 0 , \" count \": len ( m . Scores ) , \" tags \": m . Tags , } }"
+  },
+  {
+    "block_ids": [
+      "5d269745b2e5dbdcbef0c09ba54b0bd6"
+    ],
+    "chunk_id": "7a942d871c588ec69426290561f05179",
+    "chunker_version": "code-go-ast-v1",
+    "doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
+    "heading_path": [],
+    "policy_hash": "6cfe77abe2b0e5c3",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "go",
+        "line_end": 247,
+        "line_start": 48,
+        "symbol": "BigCompute [part 1/5]"
+      }
+    ],
+    "text": "func BigCompute(data []int) int {\n\tv0 := 0\n\tif 0 < len(data) {\n\t\tv0 = data[0]\n\t}\n\tv1 := 0\n\tif 1 < len(data) {\n\t\tv1 = data[1]\n\t}\n\tv2 := 0\n\tif 2 < len(data) {\n\t\tv2 = data[2]\n\t}\n\tv3 := 0\n\tif 3 < len(data) {\n\t\tv3 = data[3]\n\t}\n\tv4 := 0\n\tif 4 < len(data) {\n\t\tv4 = data[4]\n\t}\n\tv5 := 0\n\tif 5 < len(data) {\n\t\tv5 = data[5]\n\t}\n\tv6 := 0\n\tif 6 < len(data) {\n\t\tv6 = data[6]\n\t}\n\tv7 := 0\n\tif 7 < len(data) {\n\t\tv7 = data[7]\n\t}\n\tv8 := 0\n\tif 8 < len(data) {\n\t\tv8 = data[8]\n\t}\n\tv9 := 0\n\tif 9 < len(data) {\n\t\tv9 = data[9]\n\t}\n\tv10 := 0\n\tif 10 < len(data) {\n\t\tv10 = data[10]\n\t}\n\tv11 := 0\n\tif 11 < len(data) {\n\t\tv11 = data[11]\n\t}\n\tv12 := 0\n\tif 12 < len(data) {\n\t\tv12 = data[12]\n\t}\n\tv13 := 0\n\tif 13 < len(data) {\n\t\tv13 = data[13]\n\t}\n\tv14 := 0\n\tif 14 < len(data) {\n\t\tv14 = data[14]\n\t}\n\tv15 := 0\n\tif 15 < len(data) {\n\t\tv15 = data[15]\n\t}\n\tv16 := 0\n\tif 16 < len(data) {\n\t\tv16 = data[16]\n\t}\n\tv17 := 0\n\tif 17 < len(data) {\n\t\tv17 = data[17]\n\t}\n\tv18 := 0\n\tif 18 < len(data) {\n\t\tv18 = data[18]\n\t}\n\tv19 := 0\n\tif 19 < len(data) {\n\t\tv19 = data[19]\n\t}\n\tv20 := 0\n\tif 20 < len(data) {\n\t\tv20 = data[20]\n\t}\n\tv21 := 0\n\tif 21 < len(data) {\n\t\tv21 = data[21]\n\t}\n\tv22 := 0\n\tif 22 < len(data) {\n\t\tv22 = data[22]\n\t}\n\tv23 := 0\n\tif 23 < len(data) {\n\t\tv23 = data[23]\n\t}\n\tv24 := 0\n\tif 24 < len(data) {\n\t\tv24 = data[24]\n\t}\n\tv25 := 0\n\tif 25 < len(data) {\n\t\tv25 = data[25]\n\t}\n\tv26 := 0\n\tif 26 < len(data) {\n\t\tv26 = data[26]\n\t}\n\tv27 := 0\n\tif 27 < len(data) {\n\t\tv27 = data[27]\n\t}\n\tv28 := 0\n\tif 28 < len(data) {\n\t\tv28 = data[28]\n\t}\n\tv29 := 0\n\tif 29 < len(data) {\n\t\tv29 = data[29]\n\t}\n\tv30 := 0\n\tif 30 < len(data) {\n\t\tv30 = data[30]\n\t}\n\tv31 := 0\n\tif 31 < len(data) {\n\t\tv31 = data[31]\n\t}\n\tv32 := 0\n\tif 32 < len(data) {\n\t\tv32 = data[32]\n\t}\n\tv33 := 0\n\tif 33 < len(data) {\n\t\tv33 = data[33]\n\t}\n\tv34 := 0\n\tif 34 < len(data) {\n\t\tv34 = data[34]\n\t}\n\tv35 := 0\n\tif 35 < len(data) {\n\t\tv35 = data[35]\n\t}\n\tv36 := 0\n\tif 36 < len(data) {\n\t\tv36 = data[36]\n\t}\n\tv37 := 0\n\tif 37 < len(data) {\n\t\tv37 = data[37]\n\t}\n\tv38 := 0\n\tif 38 < len(data) {\n\t\tv38 = data[38]\n\t}\n\tv39 := 0\n\tif 39 < len(data) {\n\t\tv39 = data[39]\n\t}\n\tv40 := 0\n\tif 40 < len(data) {\n\t\tv40 = data[40]\n\t}\n\tv41 := 0\n\tif 41 < len(data) {\n\t\tv41 = data[41]\n\t}\n\tv42 := 0\n\tif 42 < len(data) {\n\t\tv42 = data[42]\n\t}\n\tv43 := 0\n\tif 43 < len(data) {\n\t\tv43 = data[43]\n\t}\n\tv44 := 0\n\tif 44 < len(data) {\n\t\tv44 = data[44]\n\t}\n\tv45 := 0\n\tif 45 < len(data) {\n\t\tv45 = data[45]\n\t}\n\tv46 := 0\n\tif 46 < len(data) {\n\t\tv46 = data[46]\n\t}\n\tv47 := 0\n\tif 47 < len(data) {\n\t\tv47 = data[47]\n\t}\n\tv48 := 0\n\tif 48 < len(data) {\n\t\tv48 = data[48]\n\t}\n\tv49 := 0\n\tif 49 < len(data) {\n\t\tv49 = data[49]",
+    "token_estimate": 847,
+    "tokenized_korean_text": "func BigCompute ( data [ ] int ) int { v 0 := 0 if 0 < len ( data ) { v 0 = data [ 0 ] } v 1 := 0 if 1 < len ( data ) { v 1 = data [ 1 ] } v 2 := 0 if 2 < len ( data ) { v 2 = data [ 2 ] } v 3 := 0 if 3 < len ( data ) { v 3 = data [ 3 ] } v 4 := 0 if 4 < len ( data ) { v 4 = data [ 4 ] } v 5 := 0 if 5 < len ( data ) { v 5 = data [ 5 ] } v 6 := 0 if 6 < len ( data ) { v 6 = data [ 6 ] } v 7 := 0 if 7 < len ( data ) { v 7 = data [ 7 ] } v 8 := 0 if 8 < len ( data ) { v 8 = data [ 8 ] } v 9 := 0 if 9 < len ( data ) { v 9 = data [ 9 ] } v 10 := 0 if 10 < len ( data ) { v 10 = data [ 10 ] } v 11 := 0 if 11 < len ( data ) { v 11 = data [ 11 ] } v 12 := 0 if 12 < len ( data ) { v 12 = data [ 12 ] } v 13 := 0 if 13 < len ( data ) { v 13 = data [ 13 ] } v 14 := 0 if 14 < len ( data ) { v 14 = data [ 14 ] } v 15 := 0 if 15 < len ( data ) { v 15 = data [ 15 ] } v 16 := 0 if 16 < len ( data ) { v 16 = data [ 16 ] } v 17 := 0 if 17 < len ( data ) { v 17 = data [ 17 ] } v 18 := 0 if 18 < len ( data ) { v 18 = data [ 18 ] } v 19 := 0 if 19 < len ( data ) { v 19 = data [ 19 ] } v 20 := 0 if 20 < len ( data ) { v 20 = data [ 20 ] } v 21 := 0 if 21 < len ( data ) { v 21 = data [ 21 ] } v 22 := 0 if 22 < len ( data ) { v 22 = data [ 22 ] } v 23 := 0 if 23 < len ( data ) { v 23 = data [ 23 ] } v 24 := 0 if 24 < len ( data ) { v 24 = data [ 24 ] } v 25 := 0 if 25 < len ( data ) { v 25 = data [ 25 ] } v 26 := 0 if 26 < len ( data ) { v 26 = data [ 26 ] } v 27 := 0 if 27 < len ( data ) { v 27 = data [ 27 ] } v 28 := 0 if 28 < len ( data ) { v 28 = data [ 28 ] } v 29 := 0 if 29 < len ( data ) { v 29 = data [ 29 ] } v 30 := 0 if 30 < len ( data ) { v 30 = data [ 30 ] } v 31 := 0 if 31 < len ( data ) { v 31 = data [ 31 ] } v 32 := 0 if 32 < len ( data ) { v 32 = data [ 32 ] } v 33 := 0 if 33 < len ( data ) { v 33 = data [ 33 ] } v 34 := 0 if 34 < len ( data ) { v 34 = data [ 34 ] } v 35 := 0 if 35 < len ( data ) { v 35 = data [ 35 ] } v 36 := 0 if 36 < len ( data ) { v 36 = data [ 36 ] } v 37 := 0 if 37 < len ( data ) { v 37 = data [ 37 ] } v 38 := 0 if 38 < len ( data ) { v 38 = data [ 38 ] } v 39 := 0 if 39 < len ( data ) { v 39 = data [ 39 ] } v 40 := 0 if 40 < len ( data ) { v 40 = data [ 40 ] } v 41 := 0 if 41 < len ( data ) { v 41 = data [ 41 ] } v 42 := 0 if 42 < len ( data ) { v 42 = data [ 42 ] } v 43 := 0 if 43 < len ( data ) { v 43 = data [ 43 ] } v 44 := 0 if 44 < len ( data ) { v 44 = data [ 44 ] } v 45 := 0 if 45 < len ( data ) { v 45 = data [ 45 ] } v 46 := 0 if 46 < len ( data ) { v 46 = data [ 46 ] } v 47 := 0 if 47 < len ( data ) { v 47 = data [ 47 ] } v 48 := 0 if 48 < len ( data ) { v 48 = data [ 48 ] } v 49 := 0 if 49 < len ( data ) { v 49 = data [ 49 ]"
+  },
+  {
+    "block_ids": [
+      "5d269745b2e5dbdcbef0c09ba54b0bd6"
+    ],
+    "chunk_id": "3f44ba43c9415652e2705bb667776e76",
+    "chunker_version": "code-go-ast-v1",
+    "doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
+    "heading_path": [],
+    "policy_hash": "6cfe77abe2b0e5c3",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "go",
+        "line_end": 447,
+        "line_start": 248,
+        "symbol": "BigCompute [part 2/5]"
+      }
+    ],
+    "text": "\t}\n\tv50 := 0\n\tif 50 < len(data) {\n\t\tv50 = data[50]\n\t}\n\tv51 := 0\n\tif 51 < len(data) {\n\t\tv51 = data[51]\n\t}\n\tv52 := 0\n\tif 52 < len(data) {\n\t\tv52 = data[52]\n\t}\n\tv53 := 0\n\tif 53 < len(data) {\n\t\tv53 = data[53]\n\t}\n\tv54 := 0\n\tif 54 < len(data) {\n\t\tv54 = data[54]\n\t}\n\tv55 := 0\n\tif 55 < len(data) {\n\t\tv55 = data[55]\n\t}\n\tv56 := 0\n\tif 56 < len(data) {\n\t\tv56 = data[56]\n\t}\n\tv57 := 0\n\tif 57 < len(data) {\n\t\tv57 = data[57]\n\t}\n\tv58 := 0\n\tif 58 < len(data) {\n\t\tv58 = data[58]\n\t}\n\tv59 := 0\n\tif 59 < len(data) {\n\t\tv59 = data[59]\n\t}\n\tv60 := 0\n\tif 60 < len(data) {\n\t\tv60 = data[60]\n\t}\n\tv61 := 0\n\tif 61 < len(data) {\n\t\tv61 = data[61]\n\t}\n\tv62 := 0\n\tif 62 < len(data) {\n\t\tv62 = data[62]\n\t}\n\tv63 := 0\n\tif 63 < len(data) {\n\t\tv63 = data[63]\n\t}\n\tv64 := 0\n\tif 64 < len(data) {\n\t\tv64 = data[64]\n\t}\n\tv65 := 0\n\tif 65 < len(data) {\n\t\tv65 = data[65]\n\t}\n\tv66 := 0\n\tif 66 < len(data) {\n\t\tv66 = data[66]\n\t}\n\tv67 := 0\n\tif 67 < len(data) {\n\t\tv67 = data[67]\n\t}\n\tv68 := 0\n\tif 68 < len(data) {\n\t\tv68 = data[68]\n\t}\n\tv69 := 0\n\tif 69 < len(data) {\n\t\tv69 = data[69]\n\t}\n\tv70 := 0\n\tif 70 < len(data) {\n\t\tv70 = data[70]\n\t}\n\tv71 := 0\n\tif 71 < len(data) {\n\t\tv71 = data[71]\n\t}\n\tv72 := 0\n\tif 72 < len(data) {\n\t\tv72 = data[72]\n\t}\n\tv73 := 0\n\tif 73 < len(data) {\n\t\tv73 = data[73]\n\t}\n\tv74 := 0\n\tif 74 < len(data) {\n\t\tv74 = data[74]\n\t}\n\tv75 := 0\n\tif 75 < len(data) {\n\t\tv75 = data[75]\n\t}\n\tv76 := 0\n\tif 76 < len(data) {\n\t\tv76 = data[76]\n\t}\n\tv77 := 0\n\tif 77 < len(data) {\n\t\tv77 = data[77]\n\t}\n\tv78 := 0\n\tif 78 < len(data) {\n\t\tv78 = data[78]\n\t}\n\tv79 := 0\n\tif 79 < len(data) {\n\t\tv79 = data[79]\n\t}\n\tv80 := 0\n\tif 80 < len(data) {\n\t\tv80 = data[80]\n\t}\n\tv81 := 0\n\tif 81 < len(data) {\n\t\tv81 = data[81]\n\t}\n\tv82 := 0\n\tif 82 < len(data) {\n\t\tv82 = data[82]\n\t}\n\tv83 := 0\n\tif 83 < len(data) {\n\t\tv83 = data[83]\n\t}\n\tv84 := 0\n\tif 84 < len(data) {\n\t\tv84 = data[84]\n\t}\n\tv85 := 0\n\tif 85 < len(data) {\n\t\tv85 = data[85]\n\t}\n\tv86 := 0\n\tif 86 < len(data) {\n\t\tv86 = data[86]\n\t}\n\tv87 := 0\n\tif 87 < len(data) {\n\t\tv87 = data[87]\n\t}\n\tv88 := 0\n\tif 88 < len(data) {\n\t\tv88 = data[88]\n\t}\n\tv89 := 0\n\tif 89 < len(data) {\n\t\tv89 = data[89]\n\t}\n\tv90 := 0\n\tif 90 < len(data) {\n\t\tv90 = data[90]\n\t}\n\tv91 := 0\n\tif 91 < len(data) {\n\t\tv91 = data[91]\n\t}\n\tv92 := 0\n\tif 92 < len(data) {\n\t\tv92 = data[92]\n\t}\n\tv93 := 0\n\tif 93 < len(data) {\n\t\tv93 = data[93]\n\t}\n\tv94 := 0\n\tif 94 < len(data) {\n\t\tv94 = data[94]\n\t}\n\tv95 := 0\n\tif 95 < len(data) {\n\t\tv95 = data[95]\n\t}\n\tv96 := 0\n\tif 96 < len(data) {\n\t\tv96 = data[96]\n\t}\n\tv97 := 0\n\tif 97 < len(data) {\n\t\tv97 = data[97]\n\t}\n\tv98 := 0\n\tif 98 < len(data) {\n\t\tv98 = data[98]\n\t}\n\tv99 := 0\n\tif 99 < len(data) {\n\t\tv99 = data[99]",
+    "token_estimate": 850,
+    "tokenized_korean_text": "} v 50 := 0 if 50 < len ( data ) { v 50 = data [ 50 ] } v 51 := 0 if 51 < len ( data ) { v 51 = data [ 51 ] } v 52 := 0 if 52 < len ( data ) { v 52 = data [ 52 ] } v 53 := 0 if 53 < len ( data ) { v 53 = data [ 53 ] } v 54 := 0 if 54 < len ( data ) { v 54 = data [ 54 ] } v 55 := 0 if 55 < len ( data ) { v 55 = data [ 55 ] } v 56 := 0 if 56 < len ( data ) { v 56 = data [ 56 ] } v 57 := 0 if 57 < len ( data ) { v 57 = data [ 57 ] } v 58 := 0 if 58 < len ( data ) { v 58 = data [ 58 ] } v 59 := 0 if 59 < len ( data ) { v 59 = data [ 59 ] } v 60 := 0 if 60 < len ( data ) { v 60 = data [ 60 ] } v 61 := 0 if 61 < len ( data ) { v 61 = data [ 61 ] } v 62 := 0 if 62 < len ( data ) { v 62 = data [ 62 ] } v 63 := 0 if 63 < len ( data ) { v 63 = data [ 63 ] } v 64 := 0 if 64 < len ( data ) { v 64 = data [ 64 ] } v 65 := 0 if 65 < len ( data ) { v 65 = data [ 65 ] } v 66 := 0 if 66 < len ( data ) { v 66 = data [ 66 ] } v 67 := 0 if 67 < len ( data ) { v 67 = data [ 67 ] } v 68 := 0 if 68 < len ( data ) { v 68 = data [ 68 ] } v 69 := 0 if 69 < len ( data ) { v 69 = data [ 69 ] } v 70 := 0 if 70 < len ( data ) { v 70 = data [ 70 ] } v 71 := 0 if 71 < len ( data ) { v 71 = data [ 71 ] } v 72 := 0 if 72 < len ( data ) { v 72 = data [ 72 ] } v 73 := 0 if 73 < len ( data ) { v 73 = data [ 73 ] } v 74 := 0 if 74 < len ( data ) { v 74 = data [ 74 ] } v 75 := 0 if 75 < len ( data ) { v 75 = data [ 75 ] } v 76 := 0 if 76 < len ( data ) { v 76 = data [ 76 ] } v 77 := 0 if 77 < len ( data ) { v 77 = data [ 77 ] } v 78 := 0 if 78 < len ( data ) { v 78 = data [ 78 ] } v 79 := 0 if 79 < len ( data ) { v 79 = data [ 79 ] } v 80 := 0 if 80 < len ( data ) { v 80 = data [ 80 ] } v 81 := 0 if 81 < len ( data ) { v 81 = data [ 81 ] } v 82 := 0 if 82 < len ( data ) { v 82 = data [ 82 ] } v 83 := 0 if 83 < len ( data ) { v 83 = data [ 83 ] } v 84 := 0 if 84 < len ( data ) { v 84 = data [ 84 ] } v 85 := 0 if 85 < len ( data ) { v 85 = data [ 85 ] } v 86 := 0 if 86 < len ( data ) { v 86 = data [ 86 ] } v 87 := 0 if 87 < len ( data ) { v 87 = data [ 87 ] } v 88 := 0 if 88 < len ( data ) { v 88 = data [ 88 ] } v 89 := 0 if 89 < len ( data ) { v 89 = data [ 89 ] } v 90 := 0 if 90 < len ( data ) { v 90 = data [ 90 ] } v 91 := 0 if 91 < len ( data ) { v 91 = data [ 91 ] } v 92 := 0 if 92 < len ( data ) { v 92 = data [ 92 ] } v 93 := 0 if 93 < len ( data ) { v 93 = data [ 93 ] } v 94 := 0 if 94 < len ( data ) { v 94 = data [ 94 ] } v 95 := 0 if 95 < len ( data ) { v 95 = data [ 95 ] } v 96 := 0 if 96 < len ( data ) { v 96 = data [ 96 ] } v 97 := 0 if 97 < len ( data ) { v 97 = data [ 97 ] } v 98 := 0 if 98 < len ( data ) { v 98 = data [ 98 ] } v 99 := 0 if 99 < len ( data ) { v 99 = data [ 99 ]"
+  },
+  {
+    "block_ids": [
+      "5d269745b2e5dbdcbef0c09ba54b0bd6"
+    ],
+    "chunk_id": "e4763e10f059d97f40c2932761b56c3e",
+    "chunker_version": "code-go-ast-v1",
+    "doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
+    "heading_path": [],
+    "policy_hash": "6cfe77abe2b0e5c3",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "go",
+        "line_end": 647,
+        "line_start": 448,
+        "symbol": "BigCompute [part 3/5]"
+      }
+    ],
+    "text": "\t}\n\tv100 := 0\n\tif 100 < len(data) {\n\t\tv100 = data[100]\n\t}\n\tv101 := 0\n\tif 101 < len(data) {\n\t\tv101 = data[101]\n\t}\n\tv102 := 0\n\tif 102 < len(data) {\n\t\tv102 = data[102]\n\t}\n\tv103 := 0\n\tif 103 < len(data) {\n\t\tv103 = data[103]\n\t}\n\tv104 := 0\n\tif 104 < len(data) {\n\t\tv104 = data[104]\n\t}\n\tv105 := 0\n\tif 105 < len(data) {\n\t\tv105 = data[105]\n\t}\n\tv106 := 0\n\tif 106 < len(data) {\n\t\tv106 = data[106]\n\t}\n\tv107 := 0\n\tif 107 < len(data) {\n\t\tv107 = data[107]\n\t}\n\tv108 := 0\n\tif 108 < len(data) {\n\t\tv108 = data[108]\n\t}\n\tv109 := 0\n\tif 109 < len(data) {\n\t\tv109 = data[109]\n\t}\n\tv110 := 0\n\tif 110 < len(data) {\n\t\tv110 = data[110]\n\t}\n\tv111 := 0\n\tif 111 < len(data) {\n\t\tv111 = data[111]\n\t}\n\tv112 := 0\n\tif 112 < len(data) {\n\t\tv112 = data[112]\n\t}\n\tv113 := 0\n\tif 113 < len(data) {\n\t\tv113 = data[113]\n\t}\n\tv114 := 0\n\tif 114 < len(data) {\n\t\tv114 = data[114]\n\t}\n\tv115 := 0\n\tif 115 < len(data) {\n\t\tv115 = data[115]\n\t}\n\tv116 := 0\n\tif 116 < len(data) {\n\t\tv116 = data[116]\n\t}\n\tv117 := 0\n\tif 117 < len(data) {\n\t\tv117 = data[117]\n\t}\n\tv118 := 0\n\tif 118 < len(data) {\n\t\tv118 = data[118]\n\t}\n\tv119 := 0\n\tif 119 < len(data) {\n\t\tv119 = data[119]\n\t}\n\tv120 := 0\n\tif 120 < len(data) {\n\t\tv120 = data[120]\n\t}\n\tv121 := 0\n\tif 121 < len(data) {\n\t\tv121 = data[121]\n\t}\n\tv122 := 0\n\tif 122 < len(data) {\n\t\tv122 = data[122]\n\t}\n\tv123 := 0\n\tif 123 < len(data) {\n\t\tv123 = data[123]\n\t}\n\tv124 := 0\n\tif 124 < len(data) {\n\t\tv124 = data[124]\n\t}\n\tv125 := 0\n\tif 125 < len(data) {\n\t\tv125 = data[125]\n\t}\n\tv126 := 0\n\tif 126 < len(data) {\n\t\tv126 = data[126]\n\t}\n\tv127 := 0\n\tif 127 < len(data) {\n\t\tv127 = data[127]\n\t}\n\tv128 := 0\n\tif 128 < len(data) {\n\t\tv128 = data[128]\n\t}\n\tv129 := 0\n\tif 129 < len(data) {\n\t\tv129 = data[129]\n\t}\n\tv130 := 0\n\tif 130 < len(data) {\n\t\tv130 = data[130]\n\t}\n\tv131 := 0\n\tif 131 < len(data) {\n\t\tv131 = data[131]\n\t}\n\tv132 := 0\n\tif 132 < len(data) {\n\t\tv132 = data[132]\n\t}\n\tv133 := 0\n\tif 133 < len(data) {\n\t\tv133 = data[133]\n\t}\n\tv134 := 0\n\tif 134 < len(data) {\n\t\tv134 = data[134]\n\t}\n\tv135 := 0\n\tif 135 < len(data) {\n\t\tv135 = data[135]\n\t}\n\tv136 := 0\n\tif 136 < len(data) {\n\t\tv136 = data[136]\n\t}\n\tv137 := 0\n\tif 137 < len(data) {\n\t\tv137 = data[137]\n\t}\n\tv138 := 0\n\tif 138 < len(data) {\n\t\tv138 = data[138]\n\t}\n\tv139 := 0\n\tif 139 < len(data) {\n\t\tv139 = data[139]\n\t}\n\tv140 := 0\n\tif 140 < len(data) {\n\t\tv140 = data[140]\n\t}\n\tv141 := 0\n\tif 141 < len(data) {\n\t\tv141 = data[141]\n\t}\n\tv142 := 0\n\tif 142 < len(data) {\n\t\tv142 = data[142]\n\t}\n\tv143 := 0\n\tif 143 < len(data) {\n\t\tv143 = data[143]\n\t}\n\tv144 := 0\n\tif 144 < len(data) {\n\t\tv144 = data[144]\n\t}\n\tv145 := 0\n\tif 145 < len(data) {\n\t\tv145 = data[145]\n\t}\n\tv146 := 0\n\tif 146 < len(data) {\n\t\tv146 = data[146]\n\t}\n\tv147 := 0\n\tif 147 < len(data) {\n\t\tv147 = data[147]\n\t}\n\tv148 := 0\n\tif 148 < len(data) {\n\t\tv148 = data[148]\n\t}\n\tv149 := 0\n\tif 149 < len(data) {\n\t\tv149 = data[149]",
+    "token_estimate": 917,
+    "tokenized_korean_text": "} v 100 := 0 if 100 < len ( data ) { v 100 = data [ 100 ] } v 101 := 0 if 101 < len ( data ) { v 101 = data [ 101 ] } v 102 := 0 if 102 < len ( data ) { v 102 = data [ 102 ] } v 103 := 0 if 103 < len ( data ) { v 103 = data [ 103 ] } v 104 := 0 if 104 < len ( data ) { v 104 = data [ 104 ] } v 105 := 0 if 105 < len ( data ) { v 105 = data [ 105 ] } v 106 := 0 if 106 < len ( data ) { v 106 = data [ 106 ] } v 107 := 0 if 107 < len ( data ) { v 107 = data [ 107 ] } v 108 := 0 if 108 < len ( data ) { v 108 = data [ 108 ] } v 109 := 0 if 109 < len ( data ) { v 109 = data [ 109 ] } v 110 := 0 if 110 < len ( data ) { v 110 = data [ 110 ] } v 111 := 0 if 111 < len ( data ) { v 111 = data [ 111 ] } v 112 := 0 if 112 < len ( data ) { v 112 = data [ 112 ] } v 113 := 0 if 113 < len ( data ) { v 113 = data [ 113 ] } v 114 := 0 if 114 < len ( data ) { v 114 = data [ 114 ] } v 115 := 0 if 115 < len ( data ) { v 115 = data [ 115 ] } v 116 := 0 if 116 < len ( data ) { v 116 = data [ 116 ] } v 117 := 0 if 117 < len ( data ) { v 117 = data [ 117 ] } v 118 := 0 if 118 < len ( data ) { v 118 = data [ 118 ] } v 119 := 0 if 119 < len ( data ) { v 119 = data [ 119 ] } v 120 := 0 if 120 < len ( data ) { v 120 = data [ 120 ] } v 121 := 0 if 121 < len ( data ) { v 121 = data [ 121 ] } v 122 := 0 if 122 < len ( data ) { v 122 = data [ 122 ] } v 123 := 0 if 123 < len ( data ) { v 123 = data [ 123 ] } v 124 := 0 if 124 < len ( data ) { v 124 = data [ 124 ] } v 125 := 0 if 125 < len ( data ) { v 125 = data [ 125 ] } v 126 := 0 if 126 < len ( data ) { v 126 = data [ 126 ] } v 127 := 0 if 127 < len ( data ) { v 127 = data [ 127 ] } v 128 := 0 if 128 < len ( data ) { v 128 = data [ 128 ] } v 129 := 0 if 129 < len ( data ) { v 129 = data [ 129 ] } v 130 := 0 if 130 < len ( data ) { v 130 = data [ 130 ] } v 131 := 0 if 131 < len ( data ) { v 131 = data [ 131 ] } v 132 := 0 if 132 < len ( data ) { v 132 = data [ 132 ] } v 133 := 0 if 133 < len ( data ) { v 133 = data [ 133 ] } v 134 := 0 if 134 < len ( data ) { v 134 = data [ 134 ] } v 135 := 0 if 135 < len ( data ) { v 135 = data [ 135 ] } v 136 := 0 if 136 < len ( data ) { v 136 = data [ 136 ] } v 137 := 0 if 137 < len ( data ) { v 137 = data [ 137 ] } v 138 := 0 if 138 < len ( data ) { v 138 = data [ 138 ] } v 139 := 0 if 139 < len ( data ) { v 139 = data [ 139 ] } v 140 := 0 if 140 < len ( data ) { v 140 = data [ 140 ] } v 141 := 0 if 141 < len ( data ) { v 141 = data [ 141 ] } v 142 := 0 if 142 < len ( data ) { v 142 = data [ 142 ] } v 143 := 0 if 143 < len ( data ) { v 143 = data [ 143 ] } v 144 := 0 if 144 < len ( data ) { v 144 = data [ 144 ] } v 145 := 0 if 145 < len ( data ) { v 145 = data [ 145 ] } v 146 := 0 if 146 < len ( data ) { v 146 = data [ 146 ] } v 147 := 0 if 147 < len ( data ) { v 147 = data [ 147 ] } v 148 := 0 if 148 < len ( data ) { v 148 = data [ 148 ] } v 149 := 0 if 149 < len ( data ) { v 149 = data [ 149 ]"
+  },
+  {
+    "block_ids": [
+      "5d269745b2e5dbdcbef0c09ba54b0bd6"
+    ],
+    "chunk_id": "24176c911d0bacf9a29fa7f8251f5036",
+    "chunker_version": "code-go-ast-v1",
+    "doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
+    "heading_path": [],
+    "policy_hash": "6cfe77abe2b0e5c3",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "go",
+        "line_end": 847,
+        "line_start": 648,
+        "symbol": "BigCompute [part 4/5]"
+      }
+    ],
+    "text": "\t}\n\tv150 := 0\n\tif 150 < len(data) {\n\t\tv150 = data[150]\n\t}\n\tv151 := 0\n\tif 151 < len(data) {\n\t\tv151 = data[151]\n\t}\n\tv152 := 0\n\tif 152 < len(data) {\n\t\tv152 = data[152]\n\t}\n\tv153 := 0\n\tif 153 < len(data) {\n\t\tv153 = data[153]\n\t}\n\tv154 := 0\n\tif 154 < len(data) {\n\t\tv154 = data[154]\n\t}\n\tv155 := 0\n\tif 155 < len(data) {\n\t\tv155 = data[155]\n\t}\n\tv156 := 0\n\tif 156 < len(data) {\n\t\tv156 = data[156]\n\t}\n\tv157 := 0\n\tif 157 < len(data) {\n\t\tv157 = data[157]\n\t}\n\tv158 := 0\n\tif 158 < len(data) {\n\t\tv158 = data[158]\n\t}\n\tv159 := 0\n\tif 159 < len(data) {\n\t\tv159 = data[159]\n\t}\n\tv160 := 0\n\tif 160 < len(data) {\n\t\tv160 = data[160]\n\t}\n\tv161 := 0\n\tif 161 < len(data) {\n\t\tv161 = data[161]\n\t}\n\tv162 := 0\n\tif 162 < len(data) {\n\t\tv162 = data[162]\n\t}\n\tv163 := 0\n\tif 163 < len(data) {\n\t\tv163 = data[163]\n\t}\n\tv164 := 0\n\tif 164 < len(data) {\n\t\tv164 = data[164]\n\t}\n\tv165 := 0\n\tif 165 < len(data) {\n\t\tv165 = data[165]\n\t}\n\tv166 := 0\n\tif 166 < len(data) {\n\t\tv166 = data[166]\n\t}\n\tv167 := 0\n\tif 167 < len(data) {\n\t\tv167 = data[167]\n\t}\n\tv168 := 0\n\tif 168 < len(data) {\n\t\tv168 = data[168]\n\t}\n\tv169 := 0\n\tif 169 < len(data) {\n\t\tv169 = data[169]\n\t}\n\tv170 := 0\n\tif 170 < len(data) {\n\t\tv170 = data[170]\n\t}\n\tv171 := 0\n\tif 171 < len(data) {\n\t\tv171 = data[171]\n\t}\n\tv172 := 0\n\tif 172 < len(data) {\n\t\tv172 = data[172]\n\t}\n\tv173 := 0\n\tif 173 < len(data) {\n\t\tv173 = data[173]\n\t}\n\tv174 := 0\n\tif 174 < len(data) {\n\t\tv174 = data[174]\n\t}\n\tv175 := 0\n\tif 175 < len(data) {\n\t\tv175 = data[175]\n\t}\n\tv176 := 0\n\tif 176 < len(data) {\n\t\tv176 = data[176]\n\t}\n\tv177 := 0\n\tif 177 < len(data) {\n\t\tv177 = data[177]\n\t}\n\tv178 := 0\n\tif 178 < len(data) {\n\t\tv178 = data[178]\n\t}\n\tv179 := 0\n\tif 179 < len(data) {\n\t\tv179 = data[179]\n\t}\n\tv180 := 0\n\tif 180 < len(data) {\n\t\tv180 = data[180]\n\t}\n\tv181 := 0\n\tif 181 < len(data) {\n\t\tv181 = data[181]\n\t}\n\tv182 := 0\n\tif 182 < len(data) {\n\t\tv182 = data[182]\n\t}\n\tv183 := 0\n\tif 183 < len(data) {\n\t\tv183 = data[183]\n\t}\n\tv184 := 0\n\tif 184 < len(data) {\n\t\tv184 = data[184]\n\t}\n\tv185 := 0\n\tif 185 < len(data) {\n\t\tv185 = data[185]\n\t}\n\tv186 := 0\n\tif 186 < len(data) {\n\t\tv186 = data[186]\n\t}\n\tv187 := 0\n\tif 187 < len(data) {\n\t\tv187 = data[187]\n\t}\n\tv188 := 0\n\tif 188 < len(data) {\n\t\tv188 = data[188]\n\t}\n\tv189 := 0\n\tif 189 < len(data) {\n\t\tv189 = data[189]\n\t}\n\tv190 := 0\n\tif 190 < len(data) {\n\t\tv190 = data[190]\n\t}\n\tv191 := 0\n\tif 191 < len(data) {\n\t\tv191 = data[191]\n\t}\n\tv192 := 0\n\tif 192 < len(data) {\n\t\tv192 = data[192]\n\t}\n\tv193 := 0\n\tif 193 < len(data) {\n\t\tv193 = data[193]\n\t}\n\tv194 := 0\n\tif 194 < len(data) {\n\t\tv194 = data[194]\n\t}\n\tv195 := 0\n\tif 195 < len(data) {\n\t\tv195 = data[195]\n\t}\n\tv196 := 0\n\tif 196 < len(data) {\n\t\tv196 = data[196]\n\t}\n\tv197 := 0\n\tif 197 < len(data) {\n\t\tv197 = data[197]\n\t}\n\tv198 := 0\n\tif 198 < len(data) {\n\t\tv198 = data[198]\n\t}\n\tv199 := 0\n\tif 199 < len(data) {\n\t\tv199 = data[199]",
+    "token_estimate": 917,
+    "tokenized_korean_text": "} v 150 := 0 if 150 < len ( data ) { v 150 = data [ 150 ] } v 151 := 0 if 151 < len ( data ) { v 151 = data [ 151 ] } v 152 := 0 if 152 < len ( data ) { v 152 = data [ 152 ] } v 153 := 0 if 153 < len ( data ) { v 153 = data [ 153 ] } v 154 := 0 if 154 < len ( data ) { v 154 = data [ 154 ] } v 155 := 0 if 155 < len ( data ) { v 155 = data [ 155 ] } v 156 := 0 if 156 < len ( data ) { v 156 = data [ 156 ] } v 157 := 0 if 157 < len ( data ) { v 157 = data [ 157 ] } v 158 := 0 if 158 < len ( data ) { v 158 = data [ 158 ] } v 159 := 0 if 159 < len ( data ) { v 159 = data [ 159 ] } v 160 := 0 if 160 < len ( data ) { v 160 = data [ 160 ] } v 161 := 0 if 161 < len ( data ) { v 161 = data [ 161 ] } v 162 := 0 if 162 < len ( data ) { v 162 = data [ 162 ] } v 163 := 0 if 163 < len ( data ) { v 163 = data [ 163 ] } v 164 := 0 if 164 < len ( data ) { v 164 = data [ 164 ] } v 165 := 0 if 165 < len ( data ) { v 165 = data [ 165 ] } v 166 := 0 if 166 < len ( data ) { v 166 = data [ 166 ] } v 167 := 0 if 167 < len ( data ) { v 167 = data [ 167 ] } v 168 := 0 if 168 < len ( data ) { v 168 = data [ 168 ] } v 169 := 0 if 169 < len ( data ) { v 169 = data [ 169 ] } v 170 := 0 if 170 < len ( data ) { v 170 = data [ 170 ] } v 171 := 0 if 171 < len ( data ) { v 171 = data [ 171 ] } v 172 := 0 if 172 < len ( data ) { v 172 = data [ 172 ] } v 173 := 0 if 173 < len ( data ) { v 173 = data [ 173 ] } v 174 := 0 if 174 < len ( data ) { v 174 = data [ 174 ] } v 175 := 0 if 175 < len ( data ) { v 175 = data [ 175 ] } v 176 := 0 if 176 < len ( data ) { v 176 = data [ 176 ] } v 177 := 0 if 177 < len ( data ) { v 177 = data [ 177 ] } v 178 := 0 if 178 < len ( data ) { v 178 = data [ 178 ] } v 179 := 0 if 179 < len ( data ) { v 179 = data [ 179 ] } v 180 := 0 if 180 < len ( data ) { v 180 = data [ 180 ] } v 181 := 0 if 181 < len ( data ) { v 181 = data [ 181 ] } v 182 := 0 if 182 < len ( data ) { v 182 = data [ 182 ] } v 183 := 0 if 183 < len ( data ) { v 183 = data [ 183 ] } v 184 := 0 if 184 < len ( data ) { v 184 = data [ 184 ] } v 185 := 0 if 185 < len ( data ) { v 185 = data [ 185 ] } v 186 := 0 if 186 < len ( data ) { v 186 = data [ 186 ] } v 187 := 0 if 187 < len ( data ) { v 187 = data [ 187 ] } v 188 := 0 if 188 < len ( data ) { v 188 = data [ 188 ] } v 189 := 0 if 189 < len ( data ) { v 189 = data [ 189 ] } v 190 := 0 if 190 < len ( data ) { v 190 = data [ 190 ] } v 191 := 0 if 191 < len ( data ) { v 191 = data [ 191 ] } v 192 := 0 if 192 < len ( data ) { v 192 = data [ 192 ] } v 193 := 0 if 193 < len ( data ) { v 193 = data [ 193 ] } v 194 := 0 if 194 < len ( data ) { v 194 = data [ 194 ] } v 195 := 0 if 195 < len ( data ) { v 195 = data [ 195 ] } v 196 := 0 if 196 < len ( data ) { v 196 = data [ 196 ] } v 197 := 0 if 197 < len ( data ) { v 197 = data [ 197 ] } v 198 := 0 if 198 < len ( data ) { v 198 = data [ 198 ] } v 199 := 0 if 199 < len ( data ) { v 199 = data [ 199 ]"
+  },
+  {
+    "block_ids": [
+      "5d269745b2e5dbdcbef0c09ba54b0bd6"
+    ],
+    "chunk_id": "438127626378632c03780d10603de32c",
+    "chunker_version": "code-go-ast-v1",
+    "doc_id": "83daba5fbb026e7a400d68a1c4bd36db",
+    "heading_path": [],
+    "policy_hash": "6cfe77abe2b0e5c3",
+    "source_spans": [
+      {
+        "kind": "code",
+        "lang": "go",
+        "line_end": 890,
+        "line_start": 848,
+        "symbol": "BigCompute [part 5/5]"
+      }
+    ],
+    "text": "\t}\n\tv200 := 0\n\tif 200 < len(data) {\n\t\tv200 = data[200]\n\t}\n\tv201 := 0\n\tif 201 < len(data) {\n\t\tv201 = data[201]\n\t}\n\tv202 := 0\n\tif 202 < len(data) {\n\t\tv202 = data[202]\n\t}\n\tv203 := 0\n\tif 203 < len(data) {\n\t\tv203 = data[203]\n\t}\n\tv204 := 0\n\tif 204 < len(data) {\n\t\tv204 = data[204]\n\t}\n\tv205 := 0\n\tif 205 < len(data) {\n\t\tv205 = data[205]\n\t}\n\tv206 := 0\n\tif 206 < len(data) {\n\t\tv206 = data[206]\n\t}\n\tv207 := 0\n\tif 207 < len(data) {\n\t\tv207 = data[207]\n\t}\n\tv208 := 0\n\tif 208 < len(data) {\n\t\tv208 = data[208]\n\t}\n\tv209 := 0\n\tif 209 < len(data) {\n\t\tv209 = data[209]\n\t}\n\treturn len(data)\n}",
+    "token_estimate": 191,
+    "tokenized_korean_text": "} v 200 := 0 if 200 < len ( data ) { v 200 = data [ 200 ] } v 201 := 0 if 201 < len ( data ) { v 201 = data [ 201 ] } v 202 := 0 if 202 < len ( data ) { v 202 = data [ 202 ] } v 203 := 0 if 203 < len ( data ) { v 203 = data [ 203 ] } v 204 := 0 if 204 < len ( data ) { v 204 = data [ 204 ] } v 205 := 0 if 205 < len ( data ) { v 205 = data [ 205 ] } v 206 := 0 if 206 < len ( data ) { v 206 = data [ 206 ] } v 207 := 0 if 207 < len ( data ) { v 207 = data [ 207 ] } v 208 := 0 if 208 < len ( data ) { v 208 = data [ 208 ] } v 209 := 0 if 209 < len ( data ) { v 209 = data [ 209 ] } return len ( data ) }"
+  }
+]

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;
+}