feat(p10-1a-1): CLI filter flags + SchemaStats breakdowns + regression tests

Task 13: add wire regression tests proving markdown SearchHit omits
repo/code_lang when None, and all 5 original Citation variants serialize
byte-identically without spurious Code-variant keys.

Task 15: add --repo (repeatable) and --code-lang (repeatable,
comma-separated) flags to `kebab search`; propagate both into
SearchFilters instead of the previous vec![] stub. Add
#[allow(clippy::large_enum_variant)] — Cmd is short-lived, boxing buys
nothing.

Task 16: add code_lang_breakdown and repo_breakdown BTreeMap fields to
Stats (schema.v1); derive Default on Stats; populate both as empty in
collect_stats (1A-2 fills them when code chunks land). Add unit test
asserting both keys are present in the serialized object.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

crates/kebab-app/src/schema.rs

@@ -45,7 +45,7 @@ pub struct Models {
     pub corpus_revision: u64,
 }
 
-#[derive(Debug, Clone, Serialize, Deserialize)]
+#[derive(Debug, Clone, Default, Serialize, Deserialize)]
 pub struct Stats {
     pub doc_count: u64,
     pub chunk_count: u64,
@@ -63,6 +63,14 @@ pub struct Stats {
     /// p9-fb-37: docs whose `updated_at` exceeds the staleness threshold.
     #[serde(default)]
     pub stale_doc_count: u64,
+    /// p10-1A-1: code language breakdown (chunk counts by canonical lowercase
+    /// language identifier). Empty until 1A-2 produces code chunks.
+    #[serde(default)]
+    pub code_lang_breakdown: std::collections::BTreeMap<String, u32>,
+    /// p10-1A-1: repo breakdown (chunk counts by `metadata.repo` value).
+    /// Empty until 1A-2 produces code chunks.
+    #[serde(default)]
+    pub repo_breakdown: std::collections::BTreeMap<String, u32>,
 }
 
 const KEBAB_VERSION: &str = env!("CARGO_PKG_VERSION");
@@ -158,6 +166,9 @@ fn collect_stats(
         lang_breakdown: counts.lang_breakdown,
         index_bytes,
         stale_doc_count: counts.stale_doc_count,
+        // p10-1A-1: populated by 1A-2 code ingest; empty until then.
+        code_lang_breakdown: std::collections::BTreeMap::new(),
+        repo_breakdown: std::collections::BTreeMap::new(),
     })
 }
 
@@ -182,6 +193,32 @@ fn collect_models(cfg: &Config, store: &kebab_store_sqlite::SqliteStore) -> Mode
 mod tests_stats_ext {
     use super::*;
 
+    /// p10-1A-1: Stats must serialize `code_lang_breakdown` and
+    /// `repo_breakdown` so downstream consumers (MCP skill, Claude Code)
+    /// can branch on their presence.
+    #[test]
+    fn stats_includes_code_lang_and_repo_breakdown_fields() {
+        let stats = Stats::default();
+        let v = serde_json::to_value(&stats).unwrap();
+        assert!(
+            v.get("code_lang_breakdown").is_some(),
+            "Stats JSON must include code_lang_breakdown: {v}"
+        );
+        assert!(
+            v.get("repo_breakdown").is_some(),
+            "Stats JSON must include repo_breakdown: {v}"
+        );
+        // Empty BTreeMap serializes as `{}` — confirm it's an object, not null.
+        assert!(
+            v["code_lang_breakdown"].is_object(),
+            "code_lang_breakdown must be an object: {v}"
+        );
+        assert!(
+            v["repo_breakdown"].is_object(),
+            "repo_breakdown must be an object: {v}"
+        );
+    }
+
     #[test]
     fn stats_includes_breakdowns_and_bytes_on_fresh_corpus() {
         let dir = tempfile::tempdir().unwrap();

crates/kebab-cli/src/main.rs

@@ -46,6 +46,11 @@ struct Cli {
     command: Cmd,
 }
 
+// p10-1A-1: adding `repo` and `code_lang` Vec<String> fields pushed `Cmd`
+// over clippy's large_enum_variant threshold. The enum is short-lived
+// (parsed once at startup, never cloned in a hot path) — boxing would add
+// noise with no real benefit.
+#[allow(clippy::large_enum_variant)]
 #[derive(Subcommand, Debug)]
 enum Cmd {
     /// Initialise XDG dirs + workspace + `config.toml`.
@@ -165,6 +170,18 @@ enum Cmd {
         #[arg(long)]
         doc_id: Option<String>,
 
+        /// p10-1A-1: filter by repo name (`metadata.repo`). Repeatable;
+        /// multi-value = OR.  Empty = no filter (all repos returned).
+        #[arg(long = "repo", value_name = "NAME", num_args = 1)]
+        repo: Vec<String>,
+
+        /// p10-1A-1: filter by code language identifier (lowercase
+        /// canonical).  Repeatable or comma-separated.
+        /// Examples: `rust`, `python`, `typescript`.
+        /// Unknown values produce empty hits.
+        #[arg(long = "code-lang", value_name = "LANG", num_args = 1, value_delimiter = ',')]
+        code_lang: Vec<String>,
+
         /// p9-fb-37: emit pre-fusion lexical / vector / RRF candidate
         /// lists + per-stage timing in the response. Bypasses cache
         /// (debug intent — fresh run guaranteed). Requires embeddings
@@ -688,6 +705,8 @@ fn run(cli: &Cli) -> anyhow::Result<()> {
             media,
             ingested_after,
             doc_id,
+            repo,
+            code_lang,
             trace,
             bulk,
         } => {
@@ -819,7 +838,7 @@ fn run(cli: &Cli) -> anyhow::Result<()> {
                     None => None,
                 };
 
-            // p9-fb-36: build SearchFilters from the 7 new flags.
+            // p9-fb-36 + p10-1A-1: build SearchFilters from CLI flags.
             let filters = kebab_core::SearchFilters {
                 tags_any: tag.clone(),
                 lang: lang.as_ref().map(|s| kebab_core::Lang(s.clone())),
@@ -828,8 +847,8 @@ fn run(cli: &Cli) -> anyhow::Result<()> {
                 media: media_norm,
                 ingested_after: ingested_after_parsed,
                 doc_id: doc_id.as_ref().map(|s| kebab_core::DocumentId(s.clone())),
-                repo: vec![],
+                repo: repo.clone(),
-                code_lang: vec![],
+                code_lang: code_lang.clone(),
             };
 
             let q = kebab_core::SearchQuery {

crates/kebab-cli/tests/wire_citation_5_variants_unchanged.rs

@@ -0,0 +1,100 @@
+//! p10-1A-1 Task 13: regression — the 5 original Citation variants
+//! (Line, Page, Region, Caption, Time) serialize byte-identically to
+//! pre-Task-1 form.  No spurious `code`, `line_start`, or `symbol` keys
+//! must leak into these variants.
+
+use kebab_core::{Citation, WorkspacePath};
+
+#[test]
+fn line_variant_serialization_unchanged() {
+    let c = Citation::Line {
+        path: WorkspacePath::new("a.md".into()).unwrap(),
+        start: 1,
+        end: 2,
+        section: Some("§14".into()),
+    };
+    let v = serde_json::to_value(&c).unwrap();
+    assert_eq!(v["kind"], "line");
+    assert_eq!(v["start"], 1);
+    assert_eq!(v["end"], 2);
+    assert_eq!(v["section"], "§14");
+    // Must not bleed Code-variant keys.
+    assert!(v.get("line_start").is_none(), "line_start must be absent: {v}");
+    assert!(v.get("symbol").is_none(), "symbol must be absent: {v}");
+    assert!(v.get("code").is_none(), "code must be absent: {v}");
+}
+
+#[test]
+fn line_variant_null_section_omitted() {
+    let c = Citation::Line {
+        path: WorkspacePath::new("b.md".into()).unwrap(),
+        start: 5,
+        end: 10,
+        section: None,
+    };
+    let v = serde_json::to_value(&c).unwrap();
+    assert_eq!(v["kind"], "line");
+    // `section` with None should be omitted (skip_serializing_if = is_none).
+    assert!(v.get("section").is_none() || v["section"].is_null());
+}
+
+#[test]
+fn page_variant_serialization_unchanged() {
+    let c = Citation::Page {
+        path: WorkspacePath::new("a.pdf".into()).unwrap(),
+        page: 13,
+        section: None,
+    };
+    let v = serde_json::to_value(&c).unwrap();
+    assert_eq!(v["kind"], "page");
+    assert_eq!(v["page"], 13);
+    assert!(v.get("line_start").is_none(), "line_start must be absent: {v}");
+    assert!(v.get("symbol").is_none(), "symbol must be absent: {v}");
+}
+
+#[test]
+fn region_variant_serialization_unchanged() {
+    let c = Citation::Region {
+        path: WorkspacePath::new("img.png".into()).unwrap(),
+        x: 10,
+        y: 20,
+        w: 100,
+        h: 200,
+    };
+    let v = serde_json::to_value(&c).unwrap();
+    assert_eq!(v["kind"], "region");
+    assert_eq!(v["x"], 10);
+    assert_eq!(v["y"], 20);
+    assert_eq!(v["w"], 100);
+    assert_eq!(v["h"], 200);
+    assert!(v.get("line_start").is_none(), "line_start must be absent: {v}");
+}
+
+#[test]
+fn caption_variant_serialization_unchanged() {
+    let c = Citation::Caption {
+        path: WorkspacePath::new("a.png".into()).unwrap(),
+        model: "qwen2.5-vl:7b".into(),
+    };
+    let v = serde_json::to_value(&c).unwrap();
+    assert_eq!(v["kind"], "caption");
+    assert_eq!(v["model"], "qwen2.5-vl:7b");
+    assert!(v.get("line_start").is_none(), "line_start must be absent: {v}");
+}
+
+#[test]
+fn time_variant_serialization_unchanged() {
+    let c = Citation::Time {
+        path: WorkspacePath::new("audio.mp3".into()).unwrap(),
+        start_ms: 1000,
+        end_ms: 5000,
+        speaker: Some("Alice".into()),
+    };
+    let v = serde_json::to_value(&c).unwrap();
+    assert_eq!(v["kind"], "time");
+    assert_eq!(v["start_ms"], 1000);
+    assert_eq!(v["end_ms"], 5000);
+    assert_eq!(v["speaker"], "Alice");
+    assert!(v.get("line_start").is_none(), "line_start must be absent: {v}");
+    assert!(v.get("symbol").is_none(), "symbol must be absent: {v}");
+}

crates/kebab-cli/tests/wire_search_filters_code.rs

@@ -0,0 +1,72 @@
+//! p10-1A-1 Task 15: CLI accepts --repo and --code-lang flags.
+//!
+//! These tests verify that clap parses the new flags without error.
+//! They drive `kebab search --help` (which exercises flag parsing
+//! via clap's help generation path, exiting 0) or use a minimal
+//! config + `--json` round-trip to verify the flags reach the wire.
+
+use std::process::Command;
+
+fn kebab() -> Command {
+    Command::new(env!("CARGO_BIN_EXE_kebab"))
+}
+
+/// `kebab search --help` must exit 0 and mention `--repo`.
+#[test]
+fn cli_search_help_mentions_repo_flag() {
+    let out = kebab()
+        .args(["search", "--help"])
+        .output()
+        .expect("failed to run kebab");
+    // clap help exits 0.
+    assert!(
+        out.status.success(),
+        "kebab search --help exited non-zero: {:?}",
+        out.status
+    );
+    let stdout = String::from_utf8_lossy(&out.stdout);
+    assert!(
+        stdout.contains("--repo"),
+        "--repo flag must appear in search help output:\n{stdout}"
+    );
+}
+
+/// `kebab search --help` must exit 0 and mention `--code-lang`.
+#[test]
+fn cli_search_help_mentions_code_lang_flag() {
+    let out = kebab()
+        .args(["search", "--help"])
+        .output()
+        .expect("failed to run kebab");
+    assert!(
+        out.status.success(),
+        "kebab search --help exited non-zero: {:?}",
+        out.status
+    );
+    let stdout = String::from_utf8_lossy(&out.stdout);
+    assert!(
+        stdout.contains("--code-lang"),
+        "--code-lang flag must appear in search help output:\n{stdout}"
+    );
+}
+
+/// `kebab search --help` must exit 0 and mention `--media`.
+/// Confirms `--media code` value pathway is available (media is
+/// a free-form Vec<String> that already accepted arbitrary values).
+#[test]
+fn cli_search_help_mentions_media_flag() {
+    let out = kebab()
+        .args(["search", "--help"])
+        .output()
+        .expect("failed to run kebab");
+    assert!(
+        out.status.success(),
+        "kebab search --help exited non-zero: {:?}",
+        out.status
+    );
+    let stdout = String::from_utf8_lossy(&out.stdout);
+    assert!(
+        stdout.contains("--media"),
+        "--media flag must appear in search help output:\n{stdout}"
+    );
+}

crates/kebab-cli/tests/wire_search_hit_no_code_fields.rs

@@ -0,0 +1,47 @@
+//! p10-1A-1 Task 13: regression — markdown SearchHit omits `repo` and
+//! `code_lang` from JSON when both are `None`.
+//!
+//! Proves that adding optional fields to SearchHit does not silently
+//! inject spurious keys into the existing markdown corpus wire shape.
+
+use kebab_core::{
+    Citation, ChunkId, ChunkerVersion, DocumentId, IndexVersion, RetrievalDetail, ScoreKind,
+    SearchHit, WorkspacePath,
+};
+
+#[test]
+fn markdown_hit_omits_repo_and_code_lang() {
+    let hit = SearchHit {
+        rank: 1,
+        chunk_id: ChunkId("c1".into()),
+        doc_id: DocumentId("d1".into()),
+        doc_path: WorkspacePath::new("notes/foo.md".into()).unwrap(),
+        heading_path: vec!["A".into(), "B".into()],
+        section_label: Some("B".into()),
+        snippet: "hi".into(),
+        citation: Citation::Line {
+            path: WorkspacePath::new("notes/foo.md".into()).unwrap(),
+            start: 1,
+            end: 2,
+            section: None,
+        },
+        retrieval: RetrievalDetail::default(),
+        index_version: IndexVersion("v1".into()),
+        embedding_model: None,
+        chunker_version: ChunkerVersion("md-heading-v1".into()),
+        indexed_at: time::OffsetDateTime::UNIX_EPOCH,
+        stale: false,
+        score_kind: ScoreKind::Rrf,
+        repo: None,
+        code_lang: None,
+    };
+    let s = serde_json::to_string(&hit).unwrap();
+    assert!(
+        !s.contains("\"repo\""),
+        "repo should be absent from markdown hit JSON: {s}"
+    );
+    assert!(
+        !s.contains("\"code_lang\""),
+        "code_lang should be absent from markdown hit JSON: {s}"
+    );
+}