S3 의 Chunk struct 갱신 (kebab-core 의 tokenized_korean_text:
Option<String> field 추가) 가 모든 chunk snapshot JSON 의 serde
serialize 결과를 변경시킴. 10 snapshot fixture (9 AST chunker +
markdown long-section) 의 baseline 을 V009 형태로 regenerate.
각 snapshot 의 변경 = chunk JSON 마다 `"tokenized_korean_text":
null` field 추가 (대부분의 fixture 가 영어 코드라 lindera 의 None
fallback). 동작 변경 없음 — serde representation 의 cascade만.
Spec: docs/superpowers/specs/2026-05-28-v0.20.x-korean-morphological-tokenizer-spec.md §6.2
Plan: docs/superpowers/plans/2026-05-28-v0.20.x-korean-morphological-tokenizer-plan.md (S3 follow-up via S11 sanity)
- `mh-s-004` 의 `must_contain: ["i"]` 한 글자 → `["INSERT", "i 입력모드"]`
보강. trigram 0-hit + noise 매칭 위험 해소.
- 3 question 영어 변경 (`mh-c-005` / `mh-i-001` / `mh-s-002`) — fixture
의 lang 다양성 mix (12 ko + 3 en). 영어 dogfood 시 measurement gap
회피.
- plan 의 PR-1 단락이 outdated (kebab-eval crate 미survey 단계 작성 →
실제 PR 와 deviation). actual 변경 명시 + 초안 대비 deviation 명시.
회차 1 의 다른 2 suggestion (mh-c-002 의 `v0.17.2` hard-coded, 15
question / 5-per-bucket 회귀 핀의 frozen size) 은 baseline anchor 의도
적 freeze — 회차 2 reply 에 명시.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
PR-1 of fb-41 multi-hop RAG (spec: docs/superpowers/specs/2026-05-25-
p9-fb-41-multi-hop-rag-design.md, plan: docs/superpowers/plans/2026-
05-25-p9-fb-41-multi-hop-rag.md).
XL 작업의 첫 PR — baseline 측정 anchor 만 추가. RAG pipeline 미변경,
fixture file + parse 회귀 핀.
사용자 결정 4 axis (2026-05-25):
- approach: query decomposition (LLM 서브-질문)
- trigger: explicit `--multi-hop` flag
- MVP scope: dynamic N-hop (LLM 이 depth 결정, decompose seed +
ReAct-style decide loop hybrid)
- eval: multi-hop golden set 먼저 (본 PR)
본 PR:
- `fixtures/multi_hop_golden.yaml` 신규. 15 question (5 cross-doc +
5 intra-doc + 5 single-fact negative). 기존 `GoldenQuery` struct
그대로 사용 — 별 loader / type 변경 없음. `expected_chunk_ids`
비어 있어 curator 가 `kebab ingest` 후 채울 수 있는 template
형태. `must_contain` 으로 baseline 측정 가능 (P5-2 metric).
- `crates/kebab-eval/tests/loader.rs::loads_multi_hop_golden_fixture`
신규 회귀 핀. fixture parse OK + 15 question + 5/5/5 bucket
분포 + 모든 question 에 must_contain 최소 1 개.
baseline 측정 protocol (별 run, commit 에 artifact 안 포함):
1. v0.17.2 binary 로 single-pass `kebab eval run --fixture
multi_hop_golden.yaml` 실행
2. P@5, P@10, must_contain pass rate, citation_coverage 캡처
3. PR-3 (dynamic iter 머지) 후 동일 fixture + `multi_hop=true` 로
재실행 → Δ 비교
PR 분할 6 단계 (plan 참조): PR-1 (본 PR — fixture only), PR-2
(RagPipeline::ask_multi_hop fixed depth=2), PR-3 (dynamic iter),
PR-4 (CLI flag + wire), PR-5 (MCP + SKILL.md), PR-6 (TUI toggle +
trace render). 마지막 PR 후 v0.18.0 cut.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
도그푸딩 실 한국어 위키 문서 (hash-table.md, 4512줄 mediawiki HTML,
CC-BY-SA) 는 크기·라이선스 부담으로 직접 commit 회피. 대신 도그푸딩
query 들 (해시 충돌·충돌은·시 충·해시충·충돌) 을 모두 cover 하는 합성
fixture 작성. trigram tokenizer 의 정확한 매칭 동작 (3자 substring
hit, 2자 0-hit, raw vs quoted phrase) 검증용.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Also fixes snapshot drift in code-and-table.canonical.snapshot.json
introduced by task 2 (CanonicalDocument gains last_chunker_version +
last_embedding_version fields).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The snapshot now includes the policy_hash field on every Chunk per the
preceding kb-core schema change. chunk_ids are unchanged because the
chunk_id recipe (§4.2) already incorporated policy_hash via the chunker —
the field is simply now visible in the wire form.
Regenerated via:
UPDATE_SNAPSHOTS=1 cargo test -p kb-chunk long_section_chunks_snapshot
Bakes the chunker output for fixtures/markdown/long-section.md (3 H1s,
nested H2 under Alpha, a 50-line code block, a 3-col x 4-row table,
and a multi-paragraph Gamma section) into the JSON snapshot baseline.
Confirms the priority rules end-to-end:
- Heading boundaries hold across H1 → H2 → H1 transitions
- The code block emits one chunk at 427 tokens > target=200
- The table stays single-chunk
- Gamma's paragraph stream splits with one block of overlap seed
A second test runs the full parse → normalize → chunk pipeline 5
times and asserts identical chunk_ids each pass.
Drops the unused `kb-config` and `serde` from regular dependencies —
they were declared but no source path imports them; `serde` flows in
transitively via `kb-core` as a public API requirement, and
`ChunkingCfg` lives in `kb-config` but the chunker takes
`ChunkPolicy` directly. Production deps are now exactly the allowed
set actually used: anyhow, blake3, kb-core, serde_json_canonicalizer,
tracing.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
I1: warning_agent maps ExtractFailed → "kb-parse-md" (the panic-recovery
emitter in kb-parse-md/src/blocks.rs). Lift-stage warnings from
build_canonical_document are tracked separately and attributed to
"kb-normalize", so the I1 mapping change does not lie about
kb-normalize-originated drops.
I2: ParsedPayload::AudioRef no longer synthesizes Block::AudioRef with
an invalid empty AssetId (would violate AssetId::from_str's 32-hex
invariant). Block is dropped, Warning surfaces in Provenance with src
mention, attributed to kb-normalize (lift-stage decision). TODO(P8)
comment marks this as a placeholder until the audio extractor lands.
I3: NFC-normalize each heading_path string in lift_block before feeding
into id_for_block AND into CommonBlock.heading_path. pulldown-cmark does
not NFC heading text and serde_json_canonicalizer v0.3 does not either,
so canonically-equivalent NFD/NFC inputs would produce different
block_ids without this normalization. Mirrors the existing doc_id NFC
handling via to_posix.
Minors:
- M4: trim Cargo.toml — drop kb-config, serde_json_canonicalizer,
blake3 (unused); keep tracing (now wired) + unicode-normalization
(now used by I3).
- M5: determinism_1000_iterations_under_1s now uses the same 5-block
fixture as block_ordinals_scoped_per_heading_and_kind (extracted into
fixture_blocks_five helper) so the determinism property is exercised
on a real lift_block path, not just an empty Vec. Still < 1s.
- M6: snapshot integration test now passes BodyHints { first_h1:
Some("Code And Table"), .. } and asserts doc.title == "Code And Table"
end-to-end. Baseline JSON updated.
- M7: title/lang edge-case unit tests pin policy: empty string lifts to
empty string; non-stringy values silently drop. Rustdoc updated.
- M10: provenance_contains_stage_events_in_order asserts events[1].at
== events[2].at to pin the shared-now_utc invariant.
New tests (unit, kb-normalize):
- provenance_with_extract_failed_warning_attributes_to_kb_parse_md (I1)
- audio_ref_block_skipped_with_warning (I2)
- nfc_nfd_korean_heading_path_same_block_id (I3)
- title_empty_string_in_user_map_falls_back_to_default (M7)
- title_non_string_in_user_map_silently_drops (M7)
- lang_invalid_shape_silently_drops (M7)
kb-normalize unit tests: 9 → 14. Integration snapshot: 1 (unchanged).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Add the integration snapshot test pinning the full `CanonicalDocument`
JSON for `fixtures/markdown/code-and-table.md` (run through the real
`kb-parse-md::parse_frontmatter` + `parse_blocks`, dev-dep only).
Non-deterministic `provenance.events[*].at` for the Parsed and
Normalized events is stripped before comparison; the Discovered
event's `at` is pinned by constructing the test `RawAsset` with a
fixed `discovered_at`. Run with `UPDATE_SNAPSHOTS=1` to regenerate.
Add the 1000-iteration determinism property: same inputs ⇒ byte-
identical JSON (modulo the same stripped timestamps), in under one
second of wall-clock time. A regression in canonical JSON, BLAKE3
hashing, ordinal counting, or any other deterministic field would
surface here immediately.
The integration test depends on `kb-parse-md` only as a dev-dep, so
`cargo tree -p kb-normalize --depth 1 --edges normal` confirms no
parser implementation appears in the production dep tree per design
§8.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Mechanical sweep over `Inline::Text(_)` / `Code(_)` / `Strong(_)` / `Emph(_)`
construction and match sites under the new struct-variant shape introduced
in the previous commit. `Inline::Link { text, href }` is unchanged.
The snapshot test in `tests/blocks_snapshots.rs` previously projected
`ParsedBlock` into a `BlockView`/`PayloadView` shim because the old
`Inline` could not serialize. With the schema fix in place we now
serialize `ParsedBlock` directly through serde — the shim and its
`flatten_inline` helper are removed. Inlines surface as structured
objects (`{"kind":"text","text":"…"}` etc.). Regenerated
`nested-headings.blocks.snapshot.json` to reflect the new shape via
the existing `--ignored` emitter; `code-and-table.blocks.snapshot.json`
has no inlines and is unchanged.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds two snapshot tests (`nested-headings.md`, `code-and-table.md`) under
crates/kb-parse-md/tests/blocks_snapshots.rs, with matching baseline JSON
next to each fixture. The snapshot view projects `kb_core::Inline` to
flat strings — `Inline` carries `serde(tag = "kind")` which is
incompatible with newtype variants holding a primitive (`Text(String)`),
so direct serialization of `ParsedBlock` would fail today. The view
preserves the contract that matters for P1-3 (heading paths, source
spans, payload kinds, payload text/code/table content) and will keep
working once kb-core fixes the Inline schema in a later task.
Also tightens `level_to_use >= 1 && <= 6` into `(1..=6).contains(&_)` to
satisfy `clippy::manual_range_contains`.
Spec §"Behavior contract" line 74 says `id:` is captured into
`metadata.user_id_alias` only. Remove the redundant `user.insert`
that was also writing it into the user map, and update the snapshot
baseline accordingly.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Two markdown fixtures with hand-authored JSON baselines that pin the
§0 Q9 derive output across runs:
- frontmatter-only.md exercises the YAML happy path with most fields,
unknown keys, an `id:` field, and a non-UTC created_at (so the
baseline shows original_timestamps preservation).
- mixed-lang.md is body-only with no `lang:` field; baseline pins the
lingua autodetect result for our enabled language set.
A separate `emit_snapshots` test (marked `#[ignore]`) regenerates the
baselines from the current parser output. A determinism test parses
the fixture twice and asserts equality so any non-determinism (e.g.
key ordering, lingua nondeterminism) fails fast.
fixtures/source-fs/tree-1/:
README.md
notes/alpha.md
notes/beta.md
ignored/skip.tmp (excluded by .kbignore *.tmp)
.kbignore ("*.tmp")
.DS_Store (implicitly excluded by FsSourceConnector)
The committed baseline (tree-1.snapshot.json) has discovered_at,
source_uri.value, and stored.path replaced with "<stripped>" so the
JSON is portable across checkout locations and CI runs. The test
applies the same stripping to scan output before comparing.
The determinism test runs scan twice and asserts byte-identical
serialized JSON (post-strip) — same filesystem state must yield the
same Vec<RawAsset>.
Regenerate baseline with `KB_REGEN_SNAPSHOT=1 cargo test -p kb-source-fs
--test snapshot_tree1 -- tree_1_snapshot_matches_baseline`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
