feat(search): provenance 출처 필터 — [[workspace.sources]] 멀티소스 + --source/--source-type

혼합 출처 KB(위키+jira 등)에서 색인은 전부 하되 질의 시 출처로 좁히는 provenance
레버. 전역 trust 곱셈가중(weighted-RRF)은 A/B 에서 반증(θ=0.85 만으로 incident MRR
0.918→0.340 절벽, 점수 압축) — 필터가 see-saw 없는 올바른 레버.

- config [[workspace.sources]] (각 id/root/exclude/trust_level/source_type);
  단일 root 는 implicit `default` source 로 정규화. validate: id 유일·비어있지 않음.
- config schema v3→v4 (step_3_to_4, root→[[workspace.sources]] id=default 미러, 멱등)
- V014 documents.source_id 컬럼+인덱스 (additive, DEFAULT 'default', 재색인 0)
- Metadata.source_id + BodyHints trust precedence(frontmatter > source 기본값 > Primary)
- ingest: --root 미지정 시 resolved_sources() 순회 + doc 마다 source_id/trust stamp
- 검색 SearchFilters.source_type/source_id → lexical + vector 두 site (IN, OR)
- CLI kebab search --source <id> / --source-type <type> (repeatable/comma-sep)

도그푸딩(620 doc, jira400+wiki220): --source wiki 로 개념 질의 MRR 0.780→0.810,
--source jira 로 incident 0.918→0.975. trust precedence 실측(jira=secondary 기본값).

version bump 0.28.0 → 0.29.0 (신규 CLI flag + config 키 + V014 migration → minor).
follow-up: MCP search 필터 미노출 · kebab list source_id 미표시 · RAG provenance 라벨.

자세한 내용: tasks/HOTFIXES.md (2026-06-21), docs/release-notes/v0.29.0-draft.md.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012Mc6W1fgsrbFKTsqA6P8La
This commit is contained in:
2026-06-21 08:35:19 +00:00
parent 403e162ac0
commit 58ac62d53a
101 changed files with 1201 additions and 111 deletions

View File

@@ -242,6 +242,7 @@ mod tests {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("c".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -244,6 +244,7 @@ mod tests {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("cpp".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -244,6 +244,7 @@ mod tests {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("go".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -244,6 +244,7 @@ mod tests {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("java".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -244,6 +244,7 @@ mod tests {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("javascript".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -244,6 +244,7 @@ mod tests {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("kotlin".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -244,6 +244,7 @@ mod tests {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("python".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -244,6 +244,7 @@ mod tests {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("rust".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -244,6 +244,7 @@ mod tests {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("typescript".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -450,6 +450,7 @@ mod tests {
git_branch: None,
git_commit: None,
code_lang: None,
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: kebab_core::ParserVersion("test-parser-0".into()),

View File

@@ -355,6 +355,7 @@ mod tests {
git_branch: None,
git_commit: None,
code_lang: None,
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version,
@@ -533,6 +534,7 @@ mod tests {
git_branch: None,
git_commit: None,
code_lang: None,
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version,

View File

@@ -111,6 +111,7 @@ fn fixed_doc() -> CanonicalDocument {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("c".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -118,6 +118,7 @@ fn fixed_doc() -> CanonicalDocument {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("cpp".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -136,6 +136,7 @@ fn fixed_doc() -> CanonicalDocument {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("go".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -136,6 +136,7 @@ fn fixed_doc() -> CanonicalDocument {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("java".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -136,6 +136,7 @@ fn fixed_doc() -> CanonicalDocument {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("javascript".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -136,6 +136,7 @@ fn fixed_doc() -> CanonicalDocument {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("kotlin".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -136,6 +136,7 @@ fn fixed_doc() -> CanonicalDocument {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("python".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -136,6 +136,7 @@ fn fixed_doc() -> CanonicalDocument {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("rust".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -68,6 +68,7 @@ fn text_doc(lang: &str, text: &str) -> CanonicalDocument {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some(lang.into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -136,6 +136,7 @@ fn fixed_doc() -> CanonicalDocument {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("typescript".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -67,6 +67,7 @@ fn dockerfile_doc(dockerfile_text: &str) -> CanonicalDocument {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("dockerfile".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -67,6 +67,7 @@ fn yaml_doc(yaml_text: &str) -> CanonicalDocument {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some("yaml".into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,

View File

@@ -58,6 +58,8 @@ fn long_section_chunks_snapshot() {
fs_ctime: asset.discovered_at,
fs_mtime: asset.discovered_at,
fallback_lang: Some("en".into()),
source_id: None,
fallback_trust_level: None,
};
let (metadata, fm_span, _fm_warns) =
parse_frontmatter(&bytes, &hints).expect("frontmatter parses");
@@ -133,6 +135,8 @@ fn long_section_chunks_are_deterministic() {
fs_ctime: asset.discovered_at,
fs_mtime: asset.discovered_at,
fallback_lang: Some("en".into()),
source_id: None,
fallback_trust_level: None,
};
let policy = ChunkPolicy {

View File

@@ -67,6 +67,7 @@ fn manifest_doc(lang: &str, manifest_text: &str) -> CanonicalDocument {
git_branch: Some("main".into()),
git_commit: Some("0".repeat(40)),
code_lang: Some(lang.into()),
source_id: None,
},
provenance: Provenance { events: vec![] },
parser_version: pv,