chore: bump version 0.8.1 → 0.8.2

dogfood-discovered fixes (PR #145) land in production:
- schema.v1.repo_breakdown 가 실제로 채워짐 (이전: 항상 빈 BTreeMap)
- workspace.include glob 가 walker 에서 enforce 됨 (이전: 완전 무시)

patch bump 사유: 둘 다 advertised surface 의 정상 동작 복원.
새 wire / config / surface 변경 없음.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Cargo.lock

@@ -4127,7 +4127,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-app"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "base64 0.22.1",
@@ -4172,7 +4172,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-chunk"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4187,7 +4187,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-cli"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "clap",
@@ -4208,7 +4208,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-config"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "dirs 5.0.1",
@@ -4223,7 +4223,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-core"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4237,7 +4237,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-embed"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4251,7 +4251,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-embed-local"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "fastembed",
@@ -4264,7 +4264,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-eval"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "kebab-app",
@@ -4283,7 +4283,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-llm"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "kebab-core",
@@ -4292,7 +4292,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-llm-local"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "kebab-config",
@@ -4309,7 +4309,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-mcp"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "kebab-app",
@@ -4327,7 +4327,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-normalize"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "kebab-core",
@@ -4342,7 +4342,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-code"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "gix",
@@ -4360,7 +4360,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-image"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "ab_glyph",
  "anyhow",
@@ -4384,7 +4384,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-md"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "kebab-core",
@@ -4401,7 +4401,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-pdf"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4414,7 +4414,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-types"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "kebab-core",
  "serde",
@@ -4422,7 +4422,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-rag"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4443,7 +4443,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-search"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "globset",
@@ -4462,10 +4462,11 @@ dependencies = [
 
 [[package]]
 name = "kebab-source-fs"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "blake3",
+ "globset",
  "ignore",
  "kebab-config",
  "kebab-core",
@@ -4480,7 +4481,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-store-sqlite"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4501,7 +4502,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-store-vector"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "arrow",
@@ -4525,7 +4526,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-tui"
-version = "0.8.0"
+version = "0.8.2"
 dependencies = [
  "anyhow",
  "crossterm",

Cargo.toml

@@ -31,7 +31,7 @@ edition       = "2024"
 rust-version  = "1.85"
 license       = "MIT OR Apache-2.0"
 repository    = "https://github.com/altair823/kebab"
-version       = "0.8.0"
+version       = "0.8.2"
 
 [workspace.dependencies]
 anyhow       = "1"

crates/kebab-app/src/schema.rs

@@ -168,7 +168,9 @@ fn collect_stats(
         stale_doc_count: counts.stale_doc_count,
         // p10-1A-2: populated by the store query added in this task.
         code_lang_breakdown: store.code_lang_breakdown()?,
-        repo_breakdown: std::collections::BTreeMap::new(),
+        // p10-1A-2 follow-up: dogfooding (2026-05-20) revealed this was a
+        // placeholder — mirror of code_lang_breakdown for the repo field.
+        repo_breakdown: store.repo_breakdown()?,
     })
 }
 

crates/kebab-search/src/lexical.rs

@@ -346,6 +346,34 @@ fn run_query(
         }
     }
 
+    // p10-1A-1 fix (dogfood-discovered 2026-05-20): code_lang filter
+    // (IN-list on metadata_json.$.code_lang). Empty Vec = no filter.
+    if !filters.code_lang.is_empty() {
+        let placeholders = std::iter::repeat_n("?", filters.code_lang.len())
+            .collect::<Vec<_>>()
+            .join(",");
+        sql.push_str(&format!(
+            " AND json_extract(d.metadata_json, '$.code_lang') IN ({placeholders})"
+        ));
+        for lang in &filters.code_lang {
+            params.push(Box::new(lang.clone()));
+        }
+    }
+
+    // p10-1A-1 fix (dogfood-discovered 2026-05-20): repo filter
+    // (IN-list on metadata_json.$.repo). Empty Vec = no filter.
+    if !filters.repo.is_empty() {
+        let placeholders = std::iter::repeat_n("?", filters.repo.len())
+            .collect::<Vec<_>>()
+            .join(",");
+        sql.push_str(&format!(
+            " AND json_extract(d.metadata_json, '$.repo') IN ({placeholders})"
+        ));
+        for repo in &filters.repo {
+            params.push(Box::new(repo.clone()));
+        }
+    }
+
     // p9-fb-36: ingested_after filter.
     // `documents.updated_at` is RFC3339 stored as TEXT (always UTC `Z` per
     // fb-32 ingest path), so lexicographic >= compare is correct — but only

crates/kebab-search/tests/lexical.rs

@@ -785,6 +785,19 @@ impl TestEnv {
         body: &str,
         media: MediaType,
         updated_at: OffsetDateTime,
+    ) -> DocumentId {
+        self.insert_doc_full_with_metadata(path, body, media, updated_at, "{}")
+    }
+
+    /// Like `insert_doc_full` but accepts an explicit `metadata_json` string
+    /// so p10-1A-1 filter tests can set `metadata.code_lang` / `metadata.repo`.
+    fn insert_doc_full_with_metadata(
+        &self,
+        path: &str,
+        body: &str,
+        media: MediaType,
+        updated_at: OffsetDateTime,
+        metadata_json: &str,
     ) -> DocumentId {
         use time::format_description::well_known::Rfc3339;
         let doc_id = self.next_id("doc");
@@ -810,10 +823,10 @@ impl TestEnv {
                 source_type, trust_level, parser_version,
                 doc_version, schema_version, metadata_json,
                 provenance_json, created_at, updated_at
-            ) VALUES (?, ?, ?, NULL, 'en', 'markdown', 'primary', 'pv1', 1, 1,
-                      '{}', '{\"events\":[]}',
+            ) VALUES (?, ?, ?, NULL, 'en', 'code', 'primary', 'pv1', 1, 1,
+                      ?, '{\"events\":[]}',
                       '2024-01-01T00:00:00Z', ?)",
-            rusqlite::params![doc_id, asset_id, path, updated_at_str],
+            rusqlite::params![doc_id, asset_id, path, metadata_json, updated_at_str],
         )
         .expect("insert document");
 
@@ -834,6 +847,21 @@ impl TestEnv {
         DocumentId(doc_id)
     }
 
+    /// Insert a code doc with explicit `code_lang` and optional `repo` in metadata.
+    fn insert_code_doc(&self, path: &str, body: &str, code_lang: &str, repo: Option<&str>) -> DocumentId {
+        let metadata_json = match repo {
+            Some(r) => format!(r#"{{"code_lang":"{code_lang}","repo":"{r}"}}"#),
+            None => format!(r#"{{"code_lang":"{code_lang}"}}"#),
+        };
+        self.insert_doc_full_with_metadata(
+            path,
+            body,
+            MediaType::Markdown,
+            OffsetDateTime::now_utc(),
+            &metadata_json,
+        )
+    }
+
     fn run_search(&self, query: &str, filters: &SearchFilters) -> Vec<SearchHit> {
         let r = self.inner.retriever();
         let q = SearchQuery {
@@ -934,6 +962,52 @@ fn lexical_empty_filters_match_default_behavior() {
     assert!(!with_default.is_empty());
 }
 
+// ── p10-1A-1 filter tests ────────────────────────────────────────────────
+
+#[test]
+fn lexical_filter_by_code_lang() {
+    // Three docs: python code, rust code, markdown (no code_lang).
+    // Filter code_lang=["python"] → only the python doc should match.
+    let env = TestEnv::new();
+    env.insert_code_doc("src/main.py", "AsyncClient session", "python", None);
+    env.insert_code_doc("src/lib.rs", "AsyncClient session", "rust", None);
+    env.insert_doc("docs/guide.md", "AsyncClient session");
+
+    let filters = SearchFilters {
+        code_lang: vec!["python".to_string()],
+        ..Default::default()
+    };
+    let hits = env.run_search("AsyncClient", &filters);
+    assert_eq!(hits.len(), 1, "only python doc should match code_lang filter");
+    assert!(
+        hits[0].doc_path.0.ends_with(".py"),
+        "expected python path, got: {}",
+        hits[0].doc_path.0
+    );
+}
+
+#[test]
+fn lexical_filter_by_repo() {
+    // Three docs: one in repo "httpx", one in repo "requests", one with no repo.
+    // Filter repo=["httpx"] → only the httpx doc should match.
+    let env = TestEnv::new();
+    env.insert_code_doc("httpx/client.py", "session send request", "python", Some("httpx"));
+    env.insert_code_doc("requests/api.py", "session send request", "python", Some("requests"));
+    env.insert_code_doc("standalone.py", "session send request", "python", None);
+
+    let filters = SearchFilters {
+        repo: vec!["httpx".to_string()],
+        ..Default::default()
+    };
+    let hits = env.run_search("session", &filters);
+    assert_eq!(hits.len(), 1, "only httpx doc should match repo filter");
+    assert!(
+        hits[0].doc_path.0.starts_with("httpx/"),
+        "expected httpx path, got: {}",
+        hits[0].doc_path.0
+    );
+}
+
 #[test]
 fn lexical_snapshot_run_1() {
     // Pinned snapshot. A small, deterministic corpus; the JSON shape of

crates/kebab-source-fs/Cargo.toml

@@ -18,6 +18,7 @@ blake3       = { workspace = true }
 tracing      = { workspace = true }
 walkdir      = "2"
 ignore       = "0.4"
+globset      = "0.4"
 
 [dev-dependencies]
 serde_json   = { workspace = true }

crates/kebab-source-fs/src/connector.rs

@@ -86,7 +86,7 @@ impl FsSourceConnector {
         excludes.extend(scope.exclude.iter().cloned());
         let kbignore = read_kbignore(&root)?;
 
-        let overrides = build_overrides(&root, &excludes, &kbignore)?;
+        let overrides = build_overrides(&root, &excludes, &kbignore, &scope.include)?;
         Ok((root, overrides))
     }
 
@@ -103,8 +103,6 @@ impl FsSourceConnector {
     ) -> Result<(Vec<RawAsset>, FsScanSkips)> {
         let (root, overrides) = self.resolve_scan_params(scope)?;
 
-        log_scope_include_warning(scope);
-
         let (files, skipped_entries) = walk_files_with_skips(&root, &overrides)?;
 
         // Accumulate per-category skip counts and sample paths.
@@ -284,14 +282,6 @@ fn build_assets(
     Ok(assets)
 }
 
-fn log_scope_include_warning(scope: &SourceScope) {
-    if !scope.include.is_empty() {
-        tracing::debug!(
-            count = scope.include.len(),
-            "FsSourceConnector ignores scope.include — handled by extractor router"
-        );
-    }
-}
 
 impl SourceConnector for FsSourceConnector {
     fn scan(&self, scope: &SourceScope) -> Result<Vec<RawAsset>> {

crates/kebab-source-fs/src/walker.rs

@@ -44,6 +44,7 @@ use std::collections::HashSet;
 use std::path::{Path, PathBuf};
 
 use anyhow::{Context, Result};
+use globset::{GlobBuilder, GlobSet, GlobSetBuilder};
 use ignore::overrides::{Override, OverrideBuilder};
 use walkdir::WalkDir;
 
@@ -69,6 +70,11 @@ const DEFAULT_EXCLUDES: &[&str] = &[
 ///
 /// `default_and_config` covers DEFAULT_EXCLUDES + `config.workspace.exclude`
 /// — these do NOT map to any of the three named `IngestReport` counters.
+///
+/// `include` is the compiled `scope.include` allow-list. When the set is
+/// empty (no patterns) every file passes; when non-empty a file must match
+/// at least one pattern to be accepted (directories always pass, so the
+/// walker can still descend into them).
 pub(crate) struct WalkOverrides {
     /// Merged matcher — same as today's `Override`; used for the walk decision.
     pub combined: Override,
@@ -78,6 +84,8 @@ pub(crate) struct WalkOverrides {
     pub kebabignore: Override,
     /// Matcher built from `kebab_parse_code::BUILTIN_BLACKLIST` only.
     pub builtin: Override,
+    /// Compiled allow-list from `scope.include`. Empty set = pass all.
+    pub include: GlobSet,
 }
 
 /// Skip attribution category. Used by the connector when counting per-source
@@ -161,10 +169,15 @@ fn build_single_matcher_owned(root: &Path, patterns: &[String]) -> Result<Overri
 /// The three per-source matchers (`gitignore`, `kebabignore`, `builtin`) are
 /// built in addition to the combined one so the connector can attribute skips
 /// to the correct `IngestReport` counter without a second walker pass.
+///
+/// `include_patterns` (from `scope.include`) are compiled into an allow-list
+/// `GlobSet`. Empty slice → pass-all (backward-compat); non-empty → file
+/// must match at least one pattern to be accepted.
 pub(crate) fn build_overrides(
     root: &Path,
     config_exclude: &[String],
     kbignore_patterns: &[String],
+    include_patterns: &[String],
 ) -> Result<WalkOverrides> {
     let gitignore_patterns = read_gitignore(root)?;
 
@@ -209,14 +222,41 @@ pub(crate) fn build_overrides(
         .build()
         .context("failed to compile combined override set")?;
 
+    // Allow-list GlobSet: empty Vec → matches nothing (= pass all); non-empty
+    // → file must match at least one glob to be accepted. We compile with
+    // `case_insensitive=false` to keep the semantics consistent with the
+    // OverrideBuilder exclude patterns above.
+    let include = build_include_globset(include_patterns)?;
+
     Ok(WalkOverrides {
         combined,
         gitignore,
         kebabignore,
         builtin,
+        include,
     })
 }
 
+/// Compile `scope.include` patterns into a `GlobSet` allow-list.
+///
+/// Each pattern uses `GlobBuilder` with `literal_separator = true` so that
+/// `**` can cross directory boundaries while `*` stops at `/`, matching the
+/// gitignore convention used throughout the rest of the walker.
+///
+/// An empty slice produces an empty `GlobSet` — callers interpret that as
+/// "pass all files" (no allow-list constraint).
+fn build_include_globset(patterns: &[String]) -> Result<GlobSet> {
+    let mut builder = GlobSetBuilder::new();
+    for pat in patterns {
+        let glob = GlobBuilder::new(pat)
+            .literal_separator(true)
+            .build()
+            .with_context(|| format!("invalid include pattern: {pat}"))?;
+        builder.add(glob);
+    }
+    builder.build().context("failed to compile include globset")
+}
+
 /// Classify why a path was excluded, using per-source matchers in spec §5.2
 /// priority order: built-in > gitignore > kebabignore > other.
 ///
@@ -391,6 +431,13 @@ pub(crate) fn walk_files_with_skips(
         }
 
         if entry.file_type().is_file() {
+            // Apply include allow-list: if non-empty, the file's path
+            // relative to root must match at least one pattern.
+            if !overrides.include.is_empty() && !overrides.include.is_match(rel) {
+                // Not in the allow-list — silently drop (no skip counter;
+                // the include filter is not a "skip" source in IngestReport).
+                continue;
+            }
             accepted.push(path.to_path_buf());
         }
     }
@@ -406,7 +453,7 @@ mod tests {
     #[test]
     fn empty_inputs_compile_into_an_override() {
         let dir = tempfile::tempdir().unwrap();
-        let ov = build_overrides(dir.path(), &[], &[]).unwrap();
+        let ov = build_overrides(dir.path(), &[], &[], &[]).unwrap();
         // Default-excludes only; non-special files should not match.
         let m = ov.combined.matched(Path::new("notes/alpha.md"), false);
         assert!(!m.is_ignore());
@@ -415,7 +462,7 @@ mod tests {
     #[test]
     fn default_excludes_ds_store_and_resource_forks() {
         let dir = tempfile::tempdir().unwrap();
-        let ov = build_overrides(dir.path(), &[], &[]).unwrap();
+        let ov = build_overrides(dir.path(), &[], &[], &[]).unwrap();
         assert!(ov.combined.matched(Path::new(".DS_Store"), false).is_ignore());
         assert!(
             ov.combined.matched(Path::new("notes/.DS_Store"), false).is_ignore()
@@ -433,6 +480,7 @@ mod tests {
             dir.path(),
             &["*.tmp".to_string(), "node_modules/**".to_string()],
             &[],
+            &[],
         )
         .unwrap();
         assert!(ov.combined.matched(Path::new("a.tmp"), false).is_ignore());
@@ -452,6 +500,7 @@ mod tests {
             dir.path(),
             &["*.tmp".to_string()],
             &["secret/**".to_string()],
+            &[],
         )
         .unwrap();
         assert!(ov.combined.matched(Path::new("a.tmp"), false).is_ignore());
@@ -491,7 +540,7 @@ mod tests {
         fs::write(root.join("src/main.rs"), "x").unwrap();
         fs::write(root.join("node_modules/foo/bar.js"), "x").unwrap();
 
-        let overrides = build_overrides(root, &[], &[]).unwrap();
+        let overrides = build_overrides(root, &[], &[], &[]).unwrap();
         // Override::matched expects paths relative to the builder's root.
         let m_in = overrides.combined.matched(Path::new("src/main.rs"), false);
         let m_out = overrides.combined.matched(Path::new("node_modules/foo/bar.js"), false);
@@ -514,7 +563,7 @@ mod tests {
         fs::create_dir_all(root.join("ok")).unwrap();
         fs::write(root.join("ok/z.txt"), "z").unwrap();
 
-        let overrides = build_overrides(root, &[], &[]).unwrap();
+        let overrides = build_overrides(root, &[], &[], &[]).unwrap();
         // Override::matched expects paths relative to the builder's root.
         for blacklisted in [
             "target/x/y.txt",
@@ -544,7 +593,7 @@ mod tests {
         fs::create_dir_all(root.join("dist")).unwrap();
         fs::write(root.join("dist/bundle.js"), "x").unwrap();
 
-        let overrides = build_overrides(root, &[], &[]).unwrap();
+        let overrides = build_overrides(root, &[], &[], &[]).unwrap();
         assert!(overrides.combined.matched(Path::new("a.log"), false).is_ignore());
         assert!(overrides.combined.matched(Path::new("dist/bundle.js"), false).is_ignore());
         assert!(!overrides.combined.matched(Path::new("src/main.rs"), false).is_ignore());
@@ -562,7 +611,7 @@ mod tests {
         fs::write(root.join("src/main.rs"), "x").unwrap();
 
         // No .gitignore present — patterns from .gitignore should not affect overrides.
-        let overrides = build_overrides(root, &[], &[]).unwrap();
+        let overrides = build_overrides(root, &[], &[], &[]).unwrap();
         assert!(!overrides.combined.matched(Path::new("a.log"), false).is_ignore());
         assert!(!overrides.combined.matched(Path::new("src/main.rs"), false).is_ignore());
     }
@@ -577,7 +626,7 @@ mod tests {
         // semantics, but at minimum it must not produce double-`!` corruption.
         fs::write(root.join(".gitignore"), "!keep/\n").unwrap();
         // Just verify build_overrides doesn't error.
-        let result = build_overrides(root, &[], &[]);
+        let result = build_overrides(root, &[], &[], &[]);
         assert!(result.is_ok(), "should not error on negation pattern: {:?}", result.err());
     }
 
@@ -594,7 +643,7 @@ mod tests {
         // .gitignore entry. Builtin must win (priority order §5.2).
         fs::write(root.join(".gitignore"), "node_modules/\n").unwrap();
 
-        let ov = build_overrides(root, &[], &[]).unwrap();
+        let ov = build_overrides(root, &[], &[], &[]).unwrap();
         // node_modules/ dir itself
         let cat = classify_skip(Path::new("node_modules"), true, &ov);
         assert_eq!(cat, SkipCategory::BuiltinBlacklist, "builtin must have priority");
@@ -609,7 +658,7 @@ mod tests {
         let root = tmp.path();
         fs::write(root.join(".gitignore"), "*.log\n").unwrap();
 
-        let ov = build_overrides(root, &[], &[]).unwrap();
+        let ov = build_overrides(root, &[], &[], &[]).unwrap();
         let cat = classify_skip(Path::new("app.log"), false, &ov);
         assert_eq!(cat, SkipCategory::Gitignore);
     }
@@ -621,7 +670,7 @@ mod tests {
         let tmp = TempDir::new().unwrap();
         let root = tmp.path();
 
-        let ov = build_overrides(root, &[], &["*.secret".to_string()]).unwrap();
+        let ov = build_overrides(root, &[], &["*.secret".to_string()], &[]).unwrap();
         let cat = classify_skip(Path::new("creds.secret"), false, &ov);
         assert_eq!(cat, SkipCategory::Kebabignore);
     }
@@ -637,7 +686,7 @@ mod tests {
         fs::write(root.join("ok.md"), "# ok").unwrap();
         fs::write(root.join("skipme.log"), "x").unwrap();
 
-        let ov = build_overrides(root, &[], &[]).unwrap();
+        let ov = build_overrides(root, &[], &[], &[]).unwrap();
         let (accepted, skipped_entries) = walk_files_with_skips(root, &ov).unwrap();
 
         let accepted_names: Vec<_> = accepted
@@ -677,7 +726,7 @@ mod tests {
         fs::write(root.join("node_modules/foo/bar.js"), "x").unwrap();
         fs::write(root.join("ok.md"), "# ok").unwrap();
 
-        let ov = build_overrides(root, &[], &[]).unwrap();
+        let ov = build_overrides(root, &[], &[], &[]).unwrap();
         let (accepted, skipped_entries) = walk_files_with_skips(root, &ov).unwrap();
 
         let accepted_names: Vec<_> = accepted

crates/kebab-source-fs/tests/include_allowlist.rs

@@ -0,0 +1,111 @@
+//! Integration test: `scope.include` enforces an allow-list.
+//!
+//! Semantics (gitignore convention):
+//!   - `include` is empty Vec → all files pass through (backward-compat).
+//!   - `include` is non-empty → only files matching at least one pattern
+//!     are accepted. `exclude` rules still apply after include.
+//!
+//! Layout (built per-test in a TempDir):
+//!   root/
+//!   ├── a.md
+//!   ├── b.py
+//!   ├── c.png
+//!   └── d.pdf
+
+use std::fs;
+
+use kebab_config::Config;
+use kebab_core::{SourceConnector, SourceScope};
+use kebab_source_fs::FsSourceConnector;
+
+fn cfg_with_root(root: &str) -> Config {
+    let mut c = Config::defaults();
+    c.workspace.root = root.to_string();
+    c.workspace.exclude.clear();
+    // Disable size / generated caps so small test files always pass.
+    c.ingest.code.max_file_bytes = u64::MAX;
+    c.ingest.code.max_file_lines = u32::MAX;
+    c.ingest.code.skip_generated_header = false;
+    c
+}
+
+fn setup_mixed_dir() -> tempfile::TempDir {
+    let dir = tempfile::tempdir().unwrap();
+    let root = dir.path();
+    fs::write(root.join("a.md"), b"md").unwrap();
+    fs::write(root.join("b.py"), b"py").unwrap();
+    fs::write(root.join("c.png"), b"\x89PNG").unwrap();
+    fs::write(root.join("d.pdf"), b"%PDF").unwrap();
+    dir
+}
+
+/// Empty include → all 4 files pass (backward-compat).
+#[test]
+fn include_empty_accepts_all_files() {
+    let dir = setup_mixed_dir();
+    let conn = FsSourceConnector::new(&cfg_with_root(dir.path().to_str().unwrap())).unwrap();
+    let scope = SourceScope {
+        include: vec![],
+        ..SourceScope::default()
+    };
+    let assets = conn.scan(&scope).unwrap();
+    let names: Vec<_> = assets.iter().map(|a| a.workspace_path.0.clone()).collect();
+    assert!(names.contains(&"a.md".to_string()), "a.md missing; got: {names:?}");
+    assert!(names.contains(&"b.py".to_string()), "b.py missing; got: {names:?}");
+    assert!(names.contains(&"c.png".to_string()), "c.png missing; got: {names:?}");
+    assert!(names.contains(&"d.pdf".to_string()), "d.pdf missing; got: {names:?}");
+    assert_eq!(names.len(), 4, "expected exactly 4 files; got: {names:?}");
+}
+
+/// Non-empty include → only md + py come back; png + pdf are excluded.
+#[test]
+fn include_nonempty_is_allowlist() {
+    let dir = setup_mixed_dir();
+    let conn = FsSourceConnector::new(&cfg_with_root(dir.path().to_str().unwrap())).unwrap();
+    let scope = SourceScope {
+        include: vec!["**/*.md".to_string(), "**/*.py".to_string()],
+        ..SourceScope::default()
+    };
+    let assets = conn.scan(&scope).unwrap();
+    let names: Vec<_> = assets.iter().map(|a| a.workspace_path.0.clone()).collect();
+    assert!(names.contains(&"a.md".to_string()), "a.md should be accepted; got: {names:?}");
+    assert!(names.contains(&"b.py".to_string()), "b.py should be accepted; got: {names:?}");
+    assert!(
+        !names.contains(&"c.png".to_string()),
+        "c.png must be rejected by include allowlist; got: {names:?}"
+    );
+    assert!(
+        !names.contains(&"d.pdf".to_string()),
+        "d.pdf must be rejected by include allowlist; got: {names:?}"
+    );
+    assert_eq!(names.len(), 2, "expected exactly 2 files; got: {names:?}");
+}
+
+/// include + exclude are ANDed: a file matching include but also matching
+/// exclude must be rejected.
+#[test]
+fn include_and_exclude_are_anded() {
+    let dir = tempfile::tempdir().unwrap();
+    let root = dir.path();
+    fs::write(root.join("keep.md"), b"keep").unwrap();
+    fs::write(root.join("drop.md"), b"drop").unwrap();
+    fs::write(root.join("other.py"), b"py").unwrap();
+
+    let conn = FsSourceConnector::new(&cfg_with_root(root.to_str().unwrap())).unwrap();
+    let scope = SourceScope {
+        include: vec!["**/*.md".to_string()],
+        exclude: vec!["drop.md".to_string()],
+        ..SourceScope::default()
+    };
+    let assets = conn.scan(&scope).unwrap();
+    let names: Vec<_> = assets.iter().map(|a| a.workspace_path.0.clone()).collect();
+    assert!(names.contains(&"keep.md".to_string()), "keep.md should be accepted; got: {names:?}");
+    assert!(
+        !names.contains(&"drop.md".to_string()),
+        "drop.md should be excluded (matched exclude); got: {names:?}"
+    );
+    assert!(
+        !names.contains(&"other.py".to_string()),
+        "other.py should be excluded (not in include); got: {names:?}"
+    );
+}

crates/kebab-store-sqlite/src/filters.rs

@@ -153,6 +153,34 @@ impl SqliteStore {
             }
         }
 
+        // p10-1A-1 fix (dogfood-discovered 2026-05-20): code_lang filter
+        // (IN-list on metadata_json.$.code_lang). Empty Vec = no filter.
+        if !filters.code_lang.is_empty() {
+            let placeholders = std::iter::repeat_n("?", filters.code_lang.len())
+                .collect::<Vec<_>>()
+                .join(",");
+            sql.push_str(&format!(
+                " AND json_extract(d.metadata_json, '$.code_lang') IN ({placeholders})"
+            ));
+            for lang in &filters.code_lang {
+                bind.push(Box::new(lang.clone()));
+            }
+        }
+
+        // p10-1A-1 fix (dogfood-discovered 2026-05-20): repo filter
+        // (IN-list on metadata_json.$.repo). Empty Vec = no filter.
+        if !filters.repo.is_empty() {
+            let placeholders = std::iter::repeat_n("?", filters.repo.len())
+                .collect::<Vec<_>>()
+                .join(",");
+            sql.push_str(&format!(
+                " AND json_extract(d.metadata_json, '$.repo') IN ({placeholders})"
+            ));
+            for repo in &filters.repo {
+                bind.push(Box::new(repo.clone()));
+            }
+        }
+
         // p9-fb-36: ingested_after filter.
         // `documents.updated_at` is RFC3339 TEXT (UTC `Z` per fb-32);
         // lexicographic >= compare is correct — but only when the filter
@@ -408,6 +436,78 @@ mod tests {
             .unwrap();
     }
 
+    /// Variant of `seed_committed_full` that additionally accepts a
+    /// `metadata_json` string so p10-1A-1 filter tests can set
+    /// `metadata.code_lang` / `metadata.repo` without going through the
+    /// full ingest pipeline.
+    #[allow(clippy::too_many_arguments)]
+    fn seed_committed_with_metadata(
+        store: &SqliteStore,
+        chunk_id: &str,
+        doc_id: &str,
+        workspace_path: &str,
+        media_type_json: &str,
+        metadata_json: &str,
+    ) {
+        let asset_id = format!("a{}", &doc_id[..31]);
+        {
+            let conn = store.lock_conn();
+            conn.execute(
+                "INSERT INTO assets (
+                    asset_id, source_uri, workspace_path, media_type, byte_len,
+                    checksum, storage_kind, storage_path, discovered_at
+                 ) VALUES (?, ?, ?, ?, 0, 'deadbeefdeadbeefdeadbeefdeadbeef',
+                           'reference', ?, '1970-01-01T00:00:00Z')",
+                params![
+                    asset_id,
+                    format!("file://{workspace_path}"),
+                    workspace_path,
+                    media_type_json,
+                    workspace_path,
+                ],
+            )
+            .unwrap();
+            conn.execute(
+                "INSERT INTO documents (
+                    doc_id, asset_id, workspace_path, title, lang, source_type,
+                    trust_level, parser_version, doc_version, schema_version,
+                    metadata_json, provenance_json, created_at, updated_at
+                 ) VALUES (?, ?, ?, NULL, 'en', 'code', 'primary', 'v1', 1, 1,
+                           ?, '{}', '1970-01-01T00:00:00Z', '1970-01-01T00:00:00Z')",
+                params![doc_id, asset_id, workspace_path, metadata_json],
+            )
+            .unwrap();
+            conn.execute(
+                "INSERT INTO chunks (
+                    chunk_id, doc_id, text, heading_path_json, section_label,
+                    source_spans_json, token_estimate, chunker_version,
+                    policy_hash, block_ids_json, created_at
+                 ) VALUES (?, ?, 'code snippet', '[]', NULL, '[]', 1, 'v1', 'h', '[]',
+                           '1970-01-01T00:00:00Z')",
+                params![chunk_id, doc_id],
+            )
+            .unwrap();
+        }
+
+        let embed_row = EmbeddingRecordRow {
+            embedding_id: format!("e{}", &chunk_id[..31]),
+            chunk_id: chunk_id.to_string(),
+            model_id: "m".to_string(),
+            model_version: "v1".to_string(),
+            dimensions: 4,
+            lance_table: "t".to_string(),
+            created_at: OffsetDateTime::UNIX_EPOCH,
+        };
+        store
+            .put_embedding_records_pending(std::slice::from_ref(&embed_row))
+            .unwrap();
+        store
+            .mark_embedding_records_committed(std::slice::from_ref(
+                &embed_row.embedding_id,
+            ))
+            .unwrap();
+    }
+
     fn cid(s: &str) -> ChunkId {
         ChunkId(s.to_string())
     }
@@ -671,6 +771,78 @@ mod tests {
         assert_eq!(out, vec![cid(c1)], "doc_id filter must scope to the target doc only");
     }
 
+    // ── p10-1A-1 new filter arms ─────────────────────────────────────────
+
+    #[test]
+    fn filter_chunks_code_lang_keeps_matching_lang() {
+        // c1 = python, c2 = rust, c3 = markdown (no code_lang).
+        // Filter code_lang=["python"] → only c1 survives.
+        let tmp = TempDir::new().unwrap();
+        let store = open_store(&tmp);
+        let c1 = "11111111111111111111111111111111";
+        let c2 = "22222222222222222222222222222222";
+        let c3 = "33333333333333333333333333333333";
+        seed_committed_with_metadata(
+            &store, c1, "d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1",
+            "src/main.py", r#""code""#,
+            r#"{"code_lang":"python"}"#,
+        );
+        seed_committed_with_metadata(
+            &store, c2, "d2d2d2d2d2d2d2d2d2d2d2d2d2d2d2d2",
+            "src/lib.rs", r#""code""#,
+            r#"{"code_lang":"rust"}"#,
+        );
+        seed_committed_with_metadata(
+            &store, c3, "d3d3d3d3d3d3d3d3d3d3d3d3d3d3d3d3",
+            "README.md", r#""markdown""#,
+            r#"{}"#,
+        );
+
+        let f = SearchFilters {
+            code_lang: vec!["python".to_string()],
+            ..Default::default()
+        };
+        let out = store
+            .filter_chunks(&[cid(c1), cid(c2), cid(c3)], &f)
+            .unwrap();
+        assert_eq!(out, vec![cid(c1)], "only python chunk should survive code_lang filter");
+    }
+
+    #[test]
+    fn filter_chunks_repo_keeps_matching_repo() {
+        // c1 = repo "httpx", c2 = repo "requests", c3 = no repo.
+        // Filter repo=["httpx"] → only c1 survives.
+        let tmp = TempDir::new().unwrap();
+        let store = open_store(&tmp);
+        let c1 = "11111111111111111111111111111111";
+        let c2 = "22222222222222222222222222222222";
+        let c3 = "33333333333333333333333333333333";
+        seed_committed_with_metadata(
+            &store, c1, "d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1d1",
+            "httpx/client.py", r#""code""#,
+            r#"{"repo":"httpx","code_lang":"python"}"#,
+        );
+        seed_committed_with_metadata(
+            &store, c2, "d2d2d2d2d2d2d2d2d2d2d2d2d2d2d2d2",
+            "requests/api.py", r#""code""#,
+            r#"{"repo":"requests","code_lang":"python"}"#,
+        );
+        seed_committed_with_metadata(
+            &store, c3, "d3d3d3d3d3d3d3d3d3d3d3d3d3d3d3d3",
+            "standalone.py", r#""code""#,
+            r#"{"code_lang":"python"}"#,
+        );
+
+        let f = SearchFilters {
+            repo: vec!["httpx".to_string()],
+            ..Default::default()
+        };
+        let out = store
+            .filter_chunks(&[cid(c1), cid(c2), cid(c3)], &f)
+            .unwrap();
+        assert_eq!(out, vec![cid(c1)], "only httpx chunk should survive repo filter");
+    }
+
     #[test]
     fn filter_chunks_ingested_after_non_utc_offset_compares_as_instant() {
         // Regression test for the non-UTC offset lex-compare bug.

crates/kebab-store-sqlite/src/store.rs

@@ -701,6 +701,39 @@ impl SqliteStore {
         }
         Ok(out)
     }
+
+    /// p10-1A-2 follow-up (dogfooding 2026-05-20): per-repo doc count for
+    /// `schema.v1`.
+    ///
+    /// Reads `metadata_json->'$.repo'`, groups by the value, and skips rows
+    /// where `repo` is NULL (documents without an explicit repo tag).
+    /// Returns `BTreeMap<String, u32>` — key is the repo name as stored in
+    /// frontmatter, value is the doc count.
+    pub fn repo_breakdown(
+        &self,
+    ) -> anyhow::Result<std::collections::BTreeMap<String, u32>> {
+        use anyhow::Context;
+        let conn = self.read_conn();
+        let mut stmt = conn
+            .prepare(
+                "SELECT json_extract(metadata_json, '$.repo') AS rp, COUNT(*) \
+                 FROM documents \
+                 WHERE rp IS NOT NULL \
+                 GROUP BY rp",
+            )
+            .context("prepare repo_breakdown")?;
+        let rows = stmt
+            .query_map([], |r| {
+                Ok((r.get::<_, String>(0)?, r.get::<_, i64>(1)? as u32))
+            })
+            .context("query repo_breakdown")?;
+        let mut out = std::collections::BTreeMap::new();
+        for row in rows {
+            let (k, v) = row.context("read repo_breakdown row")?;
+            out.insert(k, v);
+        }
+        Ok(out)
+    }
 }
 
 /// Apply the design §5 / task-spec pragmas. Called once per connection.
@@ -817,5 +850,79 @@ mod tests {
         // only one key total
         assert_eq!(bd.len(), 1, "expected exactly 1 entry, got: {bd:?}");
     }
+
+    /// p10-1A-2 follow-up: `repo_breakdown` counts docs by
+    /// `metadata_json.repo`.
+    ///
+    /// Inserts:
+    /// - one doc with `repo = "my-repo"` → must appear with count 1
+    /// - one doc with `repo = null`       → must NOT appear (NULL skipped)
+    ///
+    /// Uses a side rusqlite connection that bypasses the `assets` FK via
+    /// `PRAGMA foreign_keys = OFF` so the test is self-contained.
+    #[test]
+    fn repo_breakdown_counts_by_repo() {
+        let (dir, store) = open_fresh_store();
+
+        let db_path = dir.path().join("kebab.sqlite");
+        let conn = rusqlite::Connection::open(&db_path).unwrap();
+        conn.pragma_update(None, "foreign_keys", "OFF").unwrap();
+
+        // Doc 1: doc with repo = "my-repo"
+        conn.execute(
+            "INSERT INTO documents (
+                doc_id, asset_id, workspace_path,
+                source_type, trust_level, parser_version,
+                doc_version, schema_version,
+                metadata_json, provenance_json,
+                created_at, updated_at
+            ) VALUES (
+                'doc-repo-1', 'asset-r1', 'my-repo/README.md',
+                'markdown', 'primary', 'test-v1',
+                1, 1,
+                '{\"repo\":\"my-repo\"}', '{}',
+                '2024-01-01T00:00:00Z', '2024-01-01T00:00:00Z'
+            )",
+            [],
+        )
+        .unwrap();
+
+        // Doc 2: doc with repo absent (null in JSON)
+        conn.execute(
+            "INSERT INTO documents (
+                doc_id, asset_id, workspace_path,
+                source_type, trust_level, parser_version,
+                doc_version, schema_version,
+                metadata_json, provenance_json,
+                created_at, updated_at
+            ) VALUES (
+                'doc-norepo-1', 'asset-r2', 'standalone/notes.md',
+                'markdown', 'primary', 'test-v1',
+                1, 1,
+                '{\"repo\":null}', '{}',
+                '2024-01-01T00:00:00Z', '2024-01-01T00:00:00Z'
+            )",
+            [],
+        )
+        .unwrap();
+
+        drop(conn); // release side connection before querying via store
+
+        let bd = store.repo_breakdown().unwrap();
+
+        // "my-repo" must appear with count 1
+        assert_eq!(
+            bd.get("my-repo"),
+            Some(&1u32),
+            "expected my-repo=1 in repo_breakdown, got: {bd:?}"
+        );
+        // null repo must NOT appear as any key
+        assert!(
+            !bd.contains_key("null"),
+            "null repo must not appear in breakdown, got: {bd:?}"
+        );
+        // only one key total
+        assert_eq!(bd.len(), 1, "expected exactly 1 entry, got: {bd:?}");
+    }
 }