altair823-org/kebab
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 40 Wiki Activity

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

Browse Source 
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:
altair823
2026-06-21 08:35:19 +00:00
parent 403e162ac0
commit 58ac62d53a
101 changed files with 1201 additions and 111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
crates/kebab-app/tests/common/mod.rs
View File

@@ -51,7 +51,7 @@ impl TestEnv {
std::fs::create_dir_all(&model_dir).unwrap();
let mut config = Config::defaults();
config.workspace.root = workspace_root.to_string_lossy().into_owned();
config.workspace.root = Some(workspace_root.to_string_lossy().into_owned());
// Drop the ".obsidian" / "node_modules" excludes — they bring
// in nothing useful for fixtures and just hide debugging.
config.workspace.exclude.clear();

8
crates/kebab-app/tests/ingest_file.rs
View File

@@ -14,7 +14,7 @@ fn ingest_file_copies_external_md_and_reports_new() {
fs::create_dir_all(&data).unwrap();
let mut cfg = Config::defaults();
cfg.workspace.root = workspace.to_string_lossy().into_owned();
cfg.workspace.root = Some(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;
@@ -53,7 +53,7 @@ fn ingest_file_idempotent_on_second_call() {
fs::create_dir_all(&data).unwrap();
let mut cfg = Config::defaults();
cfg.workspace.root = workspace.to_string_lossy().into_owned();
cfg.workspace.root = Some(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;
@@ -78,7 +78,7 @@ fn ingest_file_errors_on_missing_path() {
fs::create_dir_all(&data).unwrap();
let mut cfg = Config::defaults();
cfg.workspace.root = workspace.to_string_lossy().into_owned();
cfg.workspace.root = Some(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;
@@ -97,7 +97,7 @@ fn ingest_file_errors_on_unsupported_extension() {
fs::create_dir_all(&data).unwrap();
let mut cfg = Config::defaults();
cfg.workspace.root = workspace.to_string_lossy().into_owned();
cfg.workspace.root = Some(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;

4
crates/kebab-app/tests/ingest_log_smoke.rs
View File

@@ -17,7 +17,7 @@ fn minimal_config(workspace: &std::path::Path, log_dir: &std::path::Path) -> Con
std::fs::create_dir_all(&model_dir).unwrap();
let mut cfg = Config::defaults();
cfg.workspace.root = workspace.to_string_lossy().into_owned();
cfg.workspace.root = Some(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();
@@ -130,7 +130,7 @@ fn ingest_log_disabled_emits_no_file() {
std::fs::create_dir_all(&model_dir).unwrap();
let mut cfg = Config::defaults();
cfg.workspace.root = workspace.to_string_lossy().into_owned();
cfg.workspace.root = Some(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();

2
crates/kebab-app/tests/ingest_progress.rs
View File

@@ -192,7 +192,7 @@ fn pdf_ocr_progress_emits_started_finished_events() {
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.workspace.root = Some(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;

6
crates/kebab-app/tests/ingest_stdin.rs
View File

@@ -12,7 +12,7 @@ fn fresh_cfg(dir: &std::path::Path) -> Config {
fs::create_dir_all(&data).unwrap();
let mut cfg = Config::defaults();
cfg.workspace.root = workspace.to_string_lossy().into_owned();
cfg.workspace.root = Some(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;
@@ -34,7 +34,7 @@ fn ingest_stdin_writes_frontmatter_and_reports_new() {
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 ext_dir = cfg.resolve_workspace_root().join("_external");
let entries: Vec<_> = fs::read_dir(&ext_dir)
.unwrap()
.filter_map(std::result::Result::ok)
@@ -56,7 +56,7 @@ fn ingest_stdin_without_source_uri() {
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 ext_dir = cfg.resolve_workspace_root().join("_external");
let entries: Vec<_> = fs::read_dir(&ext_dir)
.unwrap()
.filter_map(std::result::Result::ok)

2
crates/kebab-app/tests/schema_active_versions.rs
View File

@@ -6,7 +6,7 @@ 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.root = Some(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();

2
crates/kebab-app/tests/schema_report.rs
View File

@@ -8,7 +8,7 @@ use kebab_core::SourceScope;
fn minimal_config(data_dir: &std::path::Path, workspace_root: &std::path::Path) -> Config {
let mut config = Config::defaults();
config.workspace.root = workspace_root.to_string_lossy().into_owned();
config.workspace.root = Some(workspace_root.to_string_lossy().into_owned());
config.workspace.exclude.clear();
config.storage.data_dir = data_dir.to_string_lossy().into_owned();
config.storage.model_dir = data_dir.join("models").to_string_lossy().into_owned();

2
crates/kebab-app/tests/skip_reason.rs
View File

@@ -9,7 +9,7 @@ use common::TestEnv;
#[test]
fn unsupported_extension_skip_carries_warning_and_is_aggregated() {
let env = TestEnv::lexical_only();
let workspace_root = std::path::PathBuf::from(&env.config.workspace.root);
let workspace_root = env.config.resolve_workspace_root();
std::fs::write(workspace_root.join("legacy.docx"), b"unsupported").unwrap();
std::fs::write(workspace_root.join("Makefile"), b"unsupported").unwrap();