TDD: red → green cycle confirmed. New `Code(String)` variant serializes
as `{"code":"rust"}` via serde `rename_all = "lowercase"`. All exhaustive
`match` sites updated (`media_label`, `ingest_one_asset` catch-all →
explicit or-pattern). Design §3.5 enum listing synced. Also fix
`/target` symlink gitignore pattern so integration-test binary lookup
via workspace-relative path works with CARGO_TARGET_DIR redirect.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
회차 1 review 의 4 건 actionable 모두 반영:
1. frozen design §2.1 의 code variant 예시에서 존재하지 않는 `repo` 필드 제거 + nested form 에서 actual wire (flat) 형태로 정리. 5 variant 의 nested-form illustrative example 은 그대로 두고, code variant 만 별도 block 으로 분리해서 actual wire 와 1:1 매칭. 또 위쪽 6 variant nested-form group 에서도 'code' 행 삭제 (정확한 contract 는 별도 block 에 있음).
2. §2.2 SearchHit 예시의 `repo: null, code_lang: null` + 'omitted when null' 주석 모순 제거 — 키 자체를 빼고 inline 주석으로 'markdown hit 에는 absent, 코드 hit 에서만 surface' 설명.
3. HANDOFF Phase row 식별자 `**10**` → `**P10**` (다른 row 와 일관성).
4. README synopsis 의 중복 `[--media code]` 제거 (`--media` 는 이미 위쪽에 한 번 있음, code 는 값 중 하나라 prose 에서 설명).
코드 변경 없음 — 모두 markdown 문서.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Task 16's new code_lang_breakdown / repo_breakdown fields broke the existing schema_wrapper_tags_schema_version test in wire.rs which constructs Stats { ... } literally. Use ..Default::default() since Stats now derives Default.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Task 13: add wire regression tests proving markdown SearchHit omits
repo/code_lang when None, and all 5 original Citation variants serialize
byte-identically without spurious Code-variant keys.
Task 15: add --repo (repeatable) and --code-lang (repeatable,
comma-separated) flags to `kebab search`; propagate both into
SearchFilters instead of the previous vec![] stub. Add
#[allow(clippy::large_enum_variant)] — Cmd is short-lived, boxing buys
nothing.
Task 16: add code_lang_breakdown and repo_breakdown BTreeMap fields to
Stats (schema.v1); derive Default on Stats; populate both as empty in
collect_stats (1A-2 fills them when code chunks land). Add unit test
asserting both keys are present in the serialized object.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Wire kebab_parse_code::is_generated_file and is_oversized into
FsSourceConnector::scan_with_skips. Files that pass gitignore/builtin/
kebabignore matching are now checked for generated-file markers
(config-gated via ingest.code.skip_generated_header) and byte/line caps
(ingest.code.max_file_bytes / max_file_lines). FsScanSkips gains
skipped_generated + skipped_size_exceeded counters; kebab-app threads
them into IngestReport. Also fixes a pre-existing clippy::derivable_impls
warning in IngestCfg. Three new connector tests cover all three paths.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add IngestCfg + IngestCodeCfg structs with serde defaults and embed
ingest: IngestCfg into the top-level Config. Existing configs without
an [ingest] section continue to load unchanged.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Refactor walker to expose WalkOverrides (combined + per-source matchers),
add walk_files_with_skips that returns accepted files alongside skip
attribution, wire FsSourceConnector::scan_with_skips into kebab-app so
IngestReport.skipped_gitignore, skipped_kebabignore, skipped_builtin_blacklist,
and skip_examples are populated instead of left at zero. Priority order
per spec §5.2 (builtin > gitignore > kebabignore) enforced in classify_skip,
with a directory-aware builtin matcher so pruned directory entries are
correctly attributed to builtin rather than a coincident gitignore entry.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Prevent double-`!` corruption when a `.gitignore` negation pattern
(e.g. `!keep/`) hits the trailing-slash normalizer in `read_gitignore`.
Also updates module-level and `build_overrides` doc to list all five
filter sources in application order, and adds a regression test.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds read_gitignore() (pub(crate), root-only, nested cascade deferred)
and merges its patterns as a 5th group in build_overrides(). Trailing-
slash patterns (dist/) are normalized to also emit a stem/** glob so
files inside the directory are matched when is_dir=false. Two new tests
cover both the happy path and the missing-file no-op.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Wires `kebab_parse_code::BUILTIN_BLACKLIST` (6 patterns: node_modules,
target, __pycache__, .venv, venv, env) into `build_overrides()` so the
walker automatically excludes these directories even when the user has
no `.kebabignore`. TDD cycle: 2 failing tests added first, then the
pattern-add loop inserted after the existing kbignore block.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Tasks 5-8: new `kebab-parse-code` crate with three infrastructure modules
for the code ingest framework. Ships lang.rs (extension→language identifier
mapping), repo.rs (.git walk-up via gix 0.70 for RepoMeta), and skip.rs
(BUILTIN_BLACKLIST, is_generated_file, is_oversized). 14 integration tests
across three test files, all passing; clippy -D warnings clean.
Note: gix pinned to 0.70 (not 0.83 as originally suggested) because 0.83
fails to compile against Rust 1.94.1 due to non-exhaustive match patterns
in gix-hash. 0.70 resolves cleanly and has identical head_name/head_id API.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Four optional, serde-skipped-when-None fields added to `Metadata` for
code ingest context. All 11 downstream construction sites patched with
`repo: None, git_branch: None, git_commit: None, code_lang: None`.
Full workspace check (`--tests`) and per-crate test suite pass clean.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds five new u32 counters (skipped_gitignore, skipped_kebabignore,
skipped_builtin_blacklist, skipped_generated, skipped_size_exceeded)
and a SkipExamples struct (≤5 sample paths per category) to
IngestReport. All new fields are #[serde(default)] for backward-compat
deserialization. Downstream literal construction sites patched with
zeros/empty; snapshot re-baked.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Wire two new optional fields onto SearchHit (skip_serializing_if = None)
and two Vec<String> filter fields onto SearchFilters (serde default).
Add RetrievalDetail::Default impl (manual, uses SearchMode::Hybrid as
sentinel). Patch all downstream SearchHit / SearchFilters literal
constructors with repo: None / code_lang: None / vec![] as appropriate.
Also covers Citation::Code arm in kebab-eval metrics match.
1A 가 들고 들어가는 *프레임워크 surface* (Citation `code` variant, SearchHit repo/code_lang, --media code / --code-lang / --repo filter, skip 정책, IngestReport 세분화, config 절, kebab-parse-code crate skeleton) 가 *언어 chunker 자체* 와 독립 검증 가능 — 1A-1 머지 후 기존 markdown corpus 의 wire 출력이 byte-level identical 한지 regression test 로 검증한 다음 1A-2 에서 Rust AST chunker 자체에 집중. binary version bump 트리거도 1A-2 로 미룸 (1A-1 은 wire additive minor + 사용자 surface 변경 없음).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
수십 개 git repo (한 부모 dir 아래) 를 corpus 로 확장. Tier 1 (Rust/Python/TS-JS/Go/Java/Kotlin/C/C++) 은 tree-sitter AST per-language chunker, Tier 2 (k8s manifest / Dockerfile / Cargo.toml 류) 는 resource-aware chunker, Tier 3 (shell / fallback) 는 paragraph + line-window. embedding 은 multilingual-e5-large 유지 — cross-corpus 검색 위해. Phase 1A (Rust) 부터 1D (C/C++) + Phase 2 (Tier 2) + Phase 3 (Tier 3) 순으로 진행. ignore 통합 (.gitignore honor + .kebabignore 추가 + 최소 built-in safety net), generated header sniff, size cap 으로 첫 도그푸딩 비용 차단. 새 Citation variant `code`, SearchHit 의 repo/code_lang 필드, --media code / --code-lang / --repo filter — 모두 additive minor.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Task 1: Add multilingual-e5-large arm to kebab-embed-local::resolve_model with tests for 1024-dim variants and error cases.
Task 2: Flip kebab-config defaults from e5-small (384-dim) to e5-large (1024-dim) across defaults(), test assertions, and TOML template.
All tests pass; clippy clean.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
kebab eval compare now surfaces precision_at_k_chunk delta in both
human-readable table + deltas JSON. Snapshot fixture regenerated
additively.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
4 tasks: AggregateMetrics.precision_at_k_chunk field + serde
backwards-compat, compute aggregation in loop with 5 unit tests,
golden YAML header doc strengthening, design §11 + INDEX + status
flip.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- AggregateMetrics 에 precision_at_k_chunk: BTreeMap<u32, f32>
(P@5, P@10) 추가, binary relevance via expected_chunk_ids
- Denominator = k 고정 (hits.len() < k 도 precision 손실 간주)
- Empty expected_chunk_ids query 는 skip (hit_at_k 동일 정책)
- Lever 적용 (chunk policy / RRF / cross-encoder / embedding) 은
본 spec 범위 외 — fb-39b 이후 별도 task
- Golden set schema 무변경, shipped fixtures 헤더 주석만 강화
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
target/ balloons to 90+ GB after a few task cycles (fb-* batches
accumulate). User reported disk full mid-session twice — strengthen
guidance from "if pressure shows up" to "routinely after each merged
PR".
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
