feat(search): heading_path FTS5 text column filter (default text-only matching)

v0.17.0 trigram tokenizer entry 가 미수정으로 남겨둔
heading_path_json JSON 노이즈 (HOTFIXES 2026-05-24) closure.
trigram 이 chunks_fts.heading_path 컬럼 (V002/V007 트리거가
chunks.heading_path_json 그대로 INSERT) 의 JSON 표기 + 안의 path
세그먼트 (app, src) 까지 3-gram 색인해서 query 가 우연히 false
positive hit 하는 문제. column filter 채택 — heading 색인 유지
(V007 verbatim 불변), 매칭 대상만 text 컬럼 한정.

- build_match_string 가 non-raw 분기에서 combined expression 을
  `text : (<expr>)` 로 wrap. FTS5 column filter syntax 가 OR/AND
  sub-expression 허용.
- Raw mode (`'...'`) 는 그대로 — 사용자가 명시 의도로
  `'heading_path : agent'` 같은 explicit opt-in 가능 (escape hatch).
- 8 기존 build_match_string unit test expected string 갱신 +
  `build_match_string_raw_mode_preserves_heading_filter` 신규.
- `lexical_heading_only_token_does_not_hit_default_mode` 신규 회귀 핀
  (heading-only unique token 이 default mode 에서 0 hit).
- `lexical_raw_mode_can_opt_into_heading_path_filter` 신규 — 같은
  fixture 가 raw mode 로 hit 확인 (escape hatch 동작 핀).

사용자 영향: lexical / hybrid 검색의 본문 precision ↑. recall
변화 없음 (text 본문 token 매칭은 동일). re-ingest 불필요 (FTS
query 시점 매칭만 변경). lexical_snapshot_run_1 + hybrid_snapshot
도 fixture regenerate 불필요 (text 본문 매칭 query 라 BM25 동일).

HOTFIXES: 2026-05-24 v0.17.0 entry 의 `heading_path_json` 노이즈
항목 closure 표기 + 새 2026-05-25 post-v0.17.1 dogfood entry 추가.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-25 05:40:51 +00:00
parent f2867540d2
commit 271329efbd
3 changed files with 183 additions and 25 deletions

View File

@@ -169,12 +169,26 @@ impl Retriever for LexicalRetriever {
/// branch. Korean compounds typically split into 2-char eojeols (e.g.
/// `해시 충돌`), so a naive token AND drops the dominant usage pattern.
///
/// post-v0.17.1 dogfood — `text` column filter (closure of HOTFIXES
/// 2026-05-24 `heading_path_json` 노이즈). The `chunks_fts` virtual
/// table indexes both `heading_path` (the JSON-serialized
/// `chunks.heading_path_json` per V002/V007 triggers) and `text`. Under
/// the trigram tokenizer the JSON punctuation (`[`, `"`, `,`) plus the
/// path segments (`app`, `src`, …) become indexable 3-grams, so a
/// query can hit a chunk purely because its file's heading JSON shares
/// a path segment with the query — false positives that have no body
/// relevance. The default match expression therefore scopes to the
/// `text` column. The `heading_path` column stays indexed (V007 / §5.5
/// verbatim block is preserved) so a user who *wants* heading matching
/// can opt in via raw mode (`'heading_path : foo'`).
///
/// Rules:
///
/// - Raw mode (unchanged): the query is wrapped in a single pair of
/// `'...'` → strip the quotes and pass the inner text through verbatim.
/// The user has explicitly opted into FTS5 syntax (e.g.
/// `'rust AND cargo'`, `'foo*'`).
/// `'rust AND cargo'`, `'foo*'`, `'heading_path : agent'`). No column
/// scoping is applied — the raw expression is honored as-is.
///
/// - Otherwise build up to two MATCH candidates:
/// 1. **whole-phrase**: the entire trimmed input wrapped as one FTS5
@@ -191,6 +205,10 @@ impl Retriever for LexicalRetriever {
///
/// - A single-token long query (`러스트`, `foo`) yields `whole == token_and`
/// → return the bare quoted form so the OR doesn't duplicate.
///
/// - Finally wrap the combined expression in `text : (<expr>)` so the
/// match is scoped to the body column. FTS5's column-filter syntax
/// accepts an arbitrary OR/AND sub-expression inside the parens.
fn build_match_string(text: &str) -> Option<String> {
let trimmed = text.trim();
if trimmed.is_empty() {
@@ -218,13 +236,14 @@ fn build_match_string(text: &str) -> Option<String> {
(!toks.is_empty()).then(|| toks.join(" "))
};
match (whole_candidate, token_and_candidate) {
(None, None) => None,
(Some(w), None) => Some(w),
(None, Some(a)) => Some(a),
(Some(w), Some(a)) if w == a => Some(w),
(Some(w), Some(a)) => Some(format!("({w}) OR ({a})")),
}
let expression = match (whole_candidate, token_and_candidate) {
(None, None) => return None,
(Some(w), None) => w,
(None, Some(a)) => a,
(Some(w), Some(a)) if w == a => w,
(Some(w), Some(a)) => format!("({w}) OR ({a})"),
};
Some(format!("text : ({expression})"))
}
/// Return `Some(inner)` if `s` is wrapped in a matching pair of single
@@ -587,9 +606,11 @@ mod tests {
#[test]
fn build_match_string_default_emits_or_of_phrase_and_and() {
// Two long tokens: both whole-phrase and token-AND candidates
// exist and differ, so the builder combines them with OR.
// exist and differ, so the builder combines them with OR
// inside a `text : (...)` column filter (post-v0.17.1 dogfood:
// text-only scoping to avoid heading_path_json false positives).
let s = build_match_string("rust cargo").unwrap();
assert_eq!(s, r#"("rust cargo") OR ("rust" "cargo")"#);
assert_eq!(s, r#"text : (("rust cargo") OR ("rust" "cargo"))"#);
}
#[test]
@@ -597,28 +618,41 @@ mod tests {
// `*`, `(`, `)`, `:`, `^`, `"` should all be wrapped inside
// FTS5 string-literal quotes so they're treated as literal
// text rather than FTS5 operators. Every token is ≥3 chars,
// so both the whole-phrase and token-AND candidates exist.
// so both the whole-phrase and token-AND candidates exist,
// wrapped in the `text : (...)` column filter.
let s = build_match_string(r#"foo* (bar) baz:qux ^head he"llo"#).unwrap();
assert_eq!(
s,
r#"("foo* (bar) baz:qux ^head he""llo") OR ("foo*" "(bar)" "baz:qux" "^head" "he""llo")"#
r#"text : (("foo* (bar) baz:qux ^head he""llo") OR ("foo*" "(bar)" "baz:qux" "^head" "he""llo"))"#
);
// The doubled `""` is FTS5's way of embedding a literal quote
// inside a string literal. Appears in both whole-phrase and
// token-AND halves.
assert!(s.contains(r#"he""llo"#));
// Sanity: the combined expression is `(...) OR (...)` so it
// starts with `(` and ends with `)`.
assert!(s.starts_with('(') && s.ends_with(')'));
// Sanity: outermost wrapper is the column filter.
assert!(s.starts_with("text : ("));
assert!(s.ends_with(')'));
}
#[test]
fn build_match_string_passthrough_when_single_quoted() {
// The FTS5 expression is preserved verbatim.
// Raw mode bypasses column scoping — the FTS5 expression is
// preserved verbatim, including any explicit column filter
// (e.g. `'heading_path : foo'`) the user opts into.
let s = build_match_string("'foo OR bar*'").unwrap();
assert_eq!(s, "foo OR bar*");
}
/// Raw mode preserves an explicit `heading_path :` column filter
/// — opt-in path for users who deliberately want heading matching
/// (post-v0.17.1 dogfood default scopes to `text` only).
#[test]
fn build_match_string_raw_mode_preserves_heading_filter() {
let s = build_match_string("'heading_path : agent'").unwrap();
assert_eq!(s, "heading_path : agent");
assert!(!s.starts_with("text : "));
}
// ── v0.17.0 trigram-aware redesign coverage ──────────────────────────
/// 2-char Korean query (`충돌`) yields neither a whole-phrase nor a
@@ -634,38 +668,43 @@ mod tests {
/// `해시 충돌` — both tokens are 2 chars (dropped from the AND), but
/// the whole-phrase candidate (`"해시 충돌"`, 5 chars total) survives.
/// This is the dominant Korean usage pattern targeted by A5.
/// The whole-phrase candidate is then wrapped in the `text : (...)`
/// column filter.
#[test]
fn build_match_string_whole_phrase_only_when_all_tokens_short() {
let s = build_match_string("해시 충돌").unwrap();
assert_eq!(s, r#""해시 충돌""#);
assert_eq!(s, r#"text : ("해시 충돌")"#);
}
/// Single long token: whole-phrase and token-AND candidates collapse
/// to the same string. The builder returns the bare quoted form so
/// the MATCH expression doesn't carry a redundant `(x) OR (x)`.
/// the MATCH expression doesn't carry a redundant `(x) OR (x)`,
/// wrapped in `text : (...)`.
#[test]
fn build_match_string_single_long_token_no_duplicate_or() {
assert_eq!(build_match_string("러스트").unwrap(), r#""러스트""#);
assert_eq!(build_match_string("rust").unwrap(), r#""rust""#);
assert_eq!(build_match_string("러스트").unwrap(), r#"text : ("러스트")"#);
assert_eq!(build_match_string("rust").unwrap(), r#"text : ("rust")"#);
}
/// Mixed Korean+English multi-token query where every token is ≥3
/// chars: both candidates exist and differ, OR-combined.
/// chars: both candidates exist and differ, OR-combined inside
/// `text : (...)`.
#[test]
fn build_match_string_mixed_lang_emits_or_of_phrase_and_and() {
let s = build_match_string("Rust 충돌은").unwrap();
assert_eq!(s, r#"("Rust 충돌은") OR ("Rust" "충돌은")"#);
assert_eq!(s, r#"text : (("Rust 충돌은") OR ("Rust" "충돌은"))"#);
}
/// One ≥3 token + one <3 token: short token is dropped from the
/// AND, leaving a single long token there; whole-phrase exists
/// independently. Both candidates differ → OR-combined.
/// independently. Both candidates differ → OR-combined inside
/// `text : (...)`.
#[test]
fn build_match_string_drops_short_token_in_and_keeps_whole() {
// "키" (1 char) dropped from AND; "해시테이블" (5 chars) kept.
// Whole phrase "키 해시테이블" (7 chars) keeps the short token.
let s = build_match_string("키 해시테이블").unwrap();
assert_eq!(s, r#"("키 해시테이블") OR ("해시테이블")"#);
assert_eq!(s, r#"text : (("키 해시테이블") OR ("해시테이블"))"#);
}
#[test]

View File

@@ -1060,3 +1060,99 @@ fn lexical_snapshot_run_1() {
let expected: serde_json::Value = serde_json::from_str(&baseline_text).unwrap();
assert_eq!(actual, expected, "lexical run-1 snapshot drift");
}
// ── post-v0.17.1 dogfood — `text` column filter ──────────────────────────
/// Heading-only token (unique to `chunks.heading_path_json`, absent
/// from `chunks.text`) must NOT hit in default mode after the column
/// filter clamp. Pins HOTFIXES 2026-05-24 closure — the JSON
/// punctuation + path segments in `heading_path_json` are no longer
/// matchable from a plain query.
#[test]
fn lexical_heading_only_token_does_not_hit_default_mode() {
let env = Env::new();
let conn = env.raw_conn();
insert_document(
&conn,
&id32("d"),
"notes/heading-only.md",
"Heading-only fixture",
"en",
"primary",
&[],
);
insert_chunk(
&conn,
&id32("c1"),
&id32("d"),
"bravo charlie delta echo",
&["kubernetes-agent-controller"],
Some("Heading"),
r#"[{"kind":"line","start":1,"end":2}]"#,
"v1",
);
drop(conn);
let r = env.retriever();
let hits = r
.search(&SearchQuery {
// "kubernetes-agent-controller" is in heading_path only.
text: "kubernetes-agent-controller".to_string(),
mode: SearchMode::Lexical,
k: 10,
filters: SearchFilters::default(),
})
.unwrap();
assert!(
hits.is_empty(),
"heading-only token must not hit text column; got {} hits",
hits.len()
);
}
/// Raw mode (`'heading_path : <token>'`) is the opt-in escape hatch
/// for users who deliberately want heading-column matching after the
/// default text-only clamp. The same fixture that 0-hits in default
/// mode must hit when the user explicitly scopes to `heading_path`.
#[test]
fn lexical_raw_mode_can_opt_into_heading_path_filter() {
let env = Env::new();
let conn = env.raw_conn();
insert_document(
&conn,
&id32("d"),
"notes/heading-only.md",
"Heading-only fixture",
"en",
"primary",
&[],
);
insert_chunk(
&conn,
&id32("c1"),
&id32("d"),
"bravo charlie delta echo",
&["kubernetes-agent-controller"],
Some("Heading"),
r#"[{"kind":"line","start":1,"end":2}]"#,
"v1",
);
drop(conn);
let r = env.retriever();
let hits = r
.search(&SearchQuery {
// Raw mode: outer single quotes opt out of column-filter
// wrapping and pass the FTS5 expression through verbatim.
text: "'heading_path : \"kubernetes-agent-controller\"'".to_string(),
mode: SearchMode::Lexical,
k: 10,
filters: SearchFilters::default(),
})
.unwrap();
assert_eq!(
hits.len(),
1,
"raw-mode heading_path filter must hit the seeded chunk"
);
}

View File

@@ -49,6 +49,29 @@ v0.17.1 entry 의 첫 번째 미진행 항목 closure. LLM 쪽이 v0.17.1 에서
Cross-link: `crates/kebab-config/src/lib.rs::OcrCfg::request_timeout_secs`, `crates/kebab-parse-image/src/ocr.rs::OllamaVisionOcr::build`.
## 2026-05-25 — post-v0.17.1 dogfood: `heading_path` FTS5 column filter (text-only matching, closure of 2026-05-24 `heading_path_json` 노이즈)
v0.17.0 의 한국어 trigram tokenizer 채택 entry (2026-05-24 위) 가 미수정으로 남겨둔 `heading_path_json` JSON 노이즈 closure. trigram 이 `chunks_fts.heading_path` 컬럼 (V002/V007 트리거가 `chunks.heading_path_json` 을 그대로 INSERT) 의 JSON 표기 (`[`, `"`, `,`) + 안의 path 세그먼트 (`app`, `src`) 까지 3-gram 색인해서 query 가 우연히 false positive hit 하는 문제. 사용자 결정 (column filter vs 평문 heading 변환): **column filter**`heading_path` 색인은 V007 verbatim 그대로 유지, 매칭 대상만 `text` 컬럼으로 한정. V008 migration / design §5.5 verbatim 블록 변경 불필요.
**변경**:
- `crates/kebab-search/src/lexical.rs::build_match_string` 가 non-raw 분기에서 combined expression 을 `text : (<expr>)` 로 wrap. FTS5 column filter syntax (`column:expr`) 가 OR/AND sub-expression 허용 — 한국어 trigram 빌더의 `(whole) OR (token_and)` 형태가 그대로 들어감.
- Raw mode (`'...'`) 는 변경 없음 — 사용자가 명시 의도로 `'heading_path : agent'` 같은 explicit column filter opt-in 가능 (escape hatch).
- 9 신규 / 갱신 unit test:
- `build_match_string_*` 8 expected string 갱신 (column filter prefix 추가)
- `build_match_string_raw_mode_preserves_heading_filter` 신규 — raw mode 가 `heading_path : ...` 보존
- `lexical_heading_only_token_does_not_hit_default_mode` 신규 (`crates/kebab-search/tests/lexical.rs`) — heading-only unique token 이 default mode 에서 0 hit
- `lexical_raw_mode_can_opt_into_heading_path_filter` 신규 — 같은 fixture 가 raw mode 로 hit 확인
**사용자 영향**:
- 기본 lexical / hybrid 검색에서 heading 만 매칭되던 false positive 차단. 한국어 / 영어 substring 매칭의 recall 은 그대로 (text 본문에 있는 token 은 변함없이 hit). 본문 검색의 precision 가 올라감.
- heading 으로 일부러 검색하던 사용자는 `'heading_path : <token>'` 형태로 raw mode 진입. CLI / TUI / MCP 모든 surface 동일.
- `kebab.sqlite` 크기 변화 없음 (색인 column 그대로 유지). re-ingest 불필요 (FTS query 시점의 매칭 범위만 변경).
- BM25 score 영향: `lexical_snapshot_run_1` + `hybrid_snapshot_run_1` 둘 다 column filter 적용 후에도 점수 동일 (text 본문에만 매칭되던 query 라 column filter 가 점수 분포에 영향 안 줌). fixture regenerate 불필요.
**MCP / agent 가시성**: `search_response.v1` 의 wire shape 변경 없음. 사용자가 heading 검색을 명시 의도하던 케이스는 raw mode 안내 — `integrations/claude-code/kebab/SKILL.md` 의 search 절은 v0.17.0 의 raw mode 안내 (`'foo OR bar*'`) 가 그대로 적용. 별도 SKILL.md 갱신 불필요 (raw mode 가 이미 documented escape hatch).
Cross-link: `crates/kebab-search/src/lexical.rs::build_match_string`, `migrations/V007__fts_trigram.sql` (verbatim 유지), design §5.5 (verbatim 유지, query-time 동작만 변경).
## 2026-05-24 — v0.17.0: 한국어 trigram FTS5 tokenizer 채택 (closure of 2026-05-22 한국어 lexical)
V007 migration 으로 `chunks_fts` 의 tokenizer 를 `unicode61``trigram` 으로 교체. `chunks` 원본 + embedding + vector index 는 그대로, FTS shadow 만 재구축 + 자동 backfill — 사용자는 `kebab ingest` 재실행 불필요 (binary 만 교체하면 다음 open 시 V007 가 즉시 적용). 같은 라운드의 다른 두 follow-up (`code_lang_chunk_breakdown`, C typedef) 은 별 PR (PR-C / PR-B).
@@ -61,7 +84,7 @@ V007 migration 으로 `chunks_fts` 의 tokenizer 를 `unicode61` → `trigram`
**디스크 용량**: trigram 인덱스는 unicode61 대비 통상 2-10배. V007 자동 backfill 후 `kebab.sqlite` 파일 크기 증가 (도그푸딩 KB 기준 ~2-5배 또는 수백 MB). release notes 명시.
**`heading_path_json` JSON 노이즈 (관찰, 미수정)**: trigram 이 JSON 표기 (`[`, `"`, `,`) 와 그 안의 단어 (`app`, `src`) 까지 3-gram 색인 → query 가 우연히 JSON 구문 / 흔한 경로 단어와 겹쳐 false positive 가능. v0.17.0 에서는 컬럼 구성 유지, 도그푸딩 후 column filter (`{text} : <q>` 한정) 또는 평문 heading 변환 결정. 후속 도그푸딩 entry 로 등재 예정.
**`heading_path_json` JSON 노이즈 (관찰, 미수정)**: trigram 이 JSON 표기 (`[`, `"`, `,`) 와 그 안의 단어 (`app`, `src`) 까지 3-gram 색인 → query 가 우연히 JSON 구문 / 흔한 경로 단어와 겹쳐 false positive 가능. v0.17.0 에서는 컬럼 구성 유지, 도그푸딩 후 column filter (`{text} : <q>` 한정) 또는 평문 heading 변환 결정. 후속 도그푸딩 entry 로 등재 예정.**closure**: 아래 2026-05-25 v0.17.1 post-dogfood heading text column filter entry 참조 (column filter 방식 채택, V008 migration 불필요).
**MCP / agent 가시성**: `search_response.v1``hint: Option<String>` additive 필드. 결과가 비어 있고 query trimmed.chars().count() < 3 + raw mode 아닐 때만 set (helper `kebab_app::short_query_hint`). `integrations/claude-code/kebab/SKILL.md` 의 search 절에 "한국어 lexical 은 3자 이상 권장, `hint` 필드 확인" 안내 추가.