fix(dogfood): k8s multi-resource YAML chunk_id collision (#158)

PR #158 code-reviewer recommendation. Records the dogfood-discovered
k8s multi-resource chunk_id collision + the deliberate decision NOT to
bump chunker_version (dogfood-only stage, single-resource k8s chunk_id
shift is benign churn). Cross-link added to p10-2 spec Risks/notes.

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

Cargo.lock

@@ -4127,7 +4127,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-app"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "base64 0.22.1",
@@ -4172,12 +4172,13 @@ dependencies = [
 
 [[package]]
 name = "kebab-chunk"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "blake3",
  "kebab-core",
  "kebab-normalize",
+ "kebab-parse-code",
  "kebab-parse-md",
  "serde_json",
  "serde_json_canonicalizer",
@@ -4188,7 +4189,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-cli"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "clap",
@@ -4209,7 +4210,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-config"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "dirs 5.0.1",
@@ -4224,7 +4225,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-core"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4238,7 +4239,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-embed"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4252,7 +4253,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-embed-local"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "fastembed",
@@ -4265,7 +4266,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-eval"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "kebab-app",
@@ -4284,7 +4285,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-llm"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "kebab-core",
@@ -4293,7 +4294,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-llm-local"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "kebab-config",
@@ -4310,7 +4311,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-mcp"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "kebab-app",
@@ -4328,7 +4329,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-normalize"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "kebab-core",
@@ -4343,7 +4344,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-code"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "gix",
@@ -4366,7 +4367,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-image"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "ab_glyph",
  "anyhow",
@@ -4390,7 +4391,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-md"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "kebab-core",
@@ -4407,7 +4408,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-pdf"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4420,7 +4421,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-parse-types"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "kebab-core",
  "serde",
@@ -4428,7 +4429,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-rag"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4449,7 +4450,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-search"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "globset",
@@ -4468,7 +4469,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-source-fs"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4487,7 +4488,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-store-sqlite"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "blake3",
@@ -4508,7 +4509,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-store-vector"
-version = "0.16.0"
+version = "0.16.1"
 dependencies = [
  "anyhow",
  "arrow",
@@ -4532,7 +4533,7 @@ dependencies = [
 
 [[package]]
 name = "kebab-tui"
-version = "0.16.0"
+version = "0.16.1"
 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       = "0.16.0"
+version       = "0.16.1"
 
 [workspace.dependencies]
 anyhow       = "1"

crates/kebab-app/tests/code_ingest_smoke.rs

@@ -1286,6 +1286,64 @@ fn tier1_cpp_ingest_searchable() {
     );
 }
 
+/// P10 dogfood regression: a k8s YAML with 2 documents (Deployment + Service
+/// separated by `---`) must ingest without a UNIQUE constraint violation.
+/// Before the fix, push_chunks_with_oversize emitted split_key=None for each
+/// resource, giving every resource chunk the same id_hash → identical chunk_id
+/// → SQLite UNIQUE constraint failure on the second resource.
+#[test]
+fn tier2_k8s_multi_resource_yaml_ingests_without_collision() {
+    let env = TestEnv::lexical_only();
+
+    let k8s_dir = env.workspace_root.join("k8s");
+    std::fs::create_dir_all(&k8s_dir).unwrap();
+    std::fs::write(
+        k8s_dir.join("k8s-multi.yaml"),
+        "apiVersion: apps/v1\nkind: Deployment\nmetadata:\n  name: api\n  namespace: prod\nspec:\n  replicas: 2\n---\napiVersion: v1\nkind: Service\nmetadata:\n  name: api\n  namespace: prod\nspec:\n  selector:\n    app: api\n",
+    )
+    .unwrap();
+
+    let report = kebab_app::ingest_with_config(env.config.clone(), env.scope(), false)
+        .expect("ingest must succeed");
+
+    // The bug: this would land in report with an error + UNIQUE constraint message.
+    let item = report
+        .items
+        .as_ref()
+        .expect("items present")
+        .iter()
+        .find(|i| i.doc_path.0.ends_with("k8s-multi.yaml"))
+        .expect("k8s-multi.yaml in report");
+    assert!(
+        item.error.is_none(),
+        "multi-resource k8s yaml must ingest without error, got: {:?}",
+        item.error
+    );
+    assert!(
+        matches!(item.kind, IngestItemKind::New),
+        "expected New, got {:?}",
+        item.kind
+    );
+
+    // Both resources must be searchable (≥2 hits: Deployment/prod/api + Service/prod/api).
+    let query = kebab_core::SearchQuery {
+        text: "api".to_string(),
+        mode: kebab_core::SearchMode::Lexical,
+        k: 10,
+        filters: kebab_core::SearchFilters {
+            code_lang: vec!["yaml".to_string()],
+            ..Default::default()
+        },
+    };
+    let hits = kebab_app::search_with_config(env.config.clone(), query)
+        .expect("search must succeed");
+    assert!(
+        hits.len() >= 2,
+        "expected ≥2 hits (Deployment + Service), got {}",
+        hits.len()
+    );
+}
+
 /// p10-3 fix regression: a shell file (direct Tier 3, not a fallback)
 /// must also report Unchanged on re-ingest. Shell goes straight to
 /// CodeTextParagraphV1Chunker so `stored_is_tier3_fallback` is false

crates/kebab-chunk/Cargo.toml

@@ -16,12 +16,13 @@ tracing                    = { workspace = true }
 serde_yaml                 = { workspace = true }
 
 [dev-dependencies]
-# kb-parse-md / kb-normalize are dev-only — used by the snapshot integration
-# test to build a CanonicalDocument from a fixture Markdown file. Forbidden as
-# regular deps per design §8 (chunker consumes CanonicalDocument from kb-core
-# only); `cargo tree -p kb-chunk --depth 1` (default scope, excludes dev-deps)
-# confirms this.
-kebab-parse-md = { path = "../kebab-parse-md" }
-kebab-normalize = { path = "../kebab-normalize" }
-serde_json      = { workspace = true }
-time            = { workspace = true }
+# kb-parse-md / kb-normalize / kb-parse-code are dev-only — used by the
+# snapshot integration tests to build a CanonicalDocument from fixture files.
+# Forbidden as regular deps per design §8 (chunker consumes CanonicalDocument
+# from kb-core only); `cargo tree -p kb-chunk --depth 1` (default scope,
+# excludes dev-deps) confirms this.
+kebab-parse-md   = { path = "../kebab-parse-md" }
+kebab-parse-code = { path = "../kebab-parse-code" }
+kebab-normalize  = { path = "../kebab-normalize" }
+serde_json       = { workspace = true }
+time             = { workspace = true }

crates/kebab-chunk/src/dockerfile_file_v1.rs

@@ -43,6 +43,7 @@ impl Chunker for DockerfileFileV1Chunker {
             "<dockerfile>",
             "dockerfile",
             VERSION_LABEL,
+            None,
         )?;
 
         tracing::debug!(

crates/kebab-chunk/src/k8s_manifest_resource_v1.rs

@@ -85,6 +85,7 @@ impl Chunker for K8sManifestResourceV1Chunker {
                 &symbol,
                 "yaml",
                 VERSION_LABEL,
+                Some(slice.line_start),
             )?;
         }
 

crates/kebab-chunk/src/manifest_file_v1.rs

@@ -44,6 +44,7 @@ impl Chunker for ManifestFileV1Chunker {
             "<manifest>",
             lang,
             VERSION_LABEL,
+            None,
         )?;
 
         tracing::debug!(

crates/kebab-chunk/src/tier2_shared.rs

@@ -25,6 +25,13 @@ pub(crate) fn policy_hash(policy: &ChunkPolicy) -> String {
 /// Emit one chunk for `(text, line_start..=line_end, symbol, lang)`, splitting
 /// into line-windows of at most `AST_CHUNK_MAX_LINES` if the slice is oversize.
 /// Mirrors the oversize path in `code_rust_ast_v1`'s `chunk` impl.
+///
+/// `base_split_key` is used as the `split_key` for the non-oversize single-chunk
+/// case. Callers that emit multiple chunks from the same document (e.g.
+/// `K8sManifestResourceV1Chunker` — one call per k8s resource) MUST pass
+/// `Some(line_start)` so that each call produces a distinct `chunk_id`.
+/// Single-chunk callers (dockerfile-file-v1, manifest-file-v1) pass `None` to
+/// keep chunk_ids stable (no sibling can collide when there's only one chunk).
 #[allow(clippy::too_many_arguments)]
 pub(crate) fn push_chunks_with_oversize(
     out: &mut Vec<Chunk>,
@@ -36,6 +43,7 @@ pub(crate) fn push_chunks_with_oversize(
     symbol: &str,
     lang: &str,
     chunker_version: &str,
+    base_split_key: Option<u32>,
 ) -> Result<()> {
     let n_lines = (line_end - line_start + 1).max(1);
     let cv = ChunkerVersion(chunker_version.to_string());
@@ -51,7 +59,7 @@ pub(crate) fn push_chunks_with_oversize(
             line_end,
             symbol,
             lang,
-            None,
+            base_split_key,
         ));
         return Ok(());
     }

crates/kebab-chunk/tests/code_cpp_ast_snapshot.rs

@@ -1,11 +1,13 @@
 //! Snapshot test pinning the `Vec<Chunk>` JSON for a
 //! representative C++ code `CanonicalDocument`.
 //!
-//! This is an integration test. `kebab-parse-code` is intentionally NOT
-//! a dev-dep (design §6.3 / §8 boundary: AST extraction is parser-side).
-//! The `CanonicalDocument` is built inline from hand-crafted `Block::Code`
-//! units, which is the same pattern used in `code_c_ast_v1.rs`'s
-//! internal `code_doc` test helper.
+//! Two complementary tests:
+//! 1. `code_cpp_ast_chunks_snapshot` — hand-built `fixed_doc()` validates the
+//!    chunker's 1:1 mapping (design §6.3 / §8 boundary: no parse-code dep needed).
+//! 2. `code_cpp_ast_extractor_snapshot` — invokes `CppAstExtractor` against the
+//!    real `tests/fixtures/sample.cpp` fixture, validating the extractor → chunker
+//!    end-to-end pipeline. `kebab-parse-code` is a dev-dep (same pattern as
+//!    `kebab-parse-md` in Markdown snapshot tests).
 //!
 //! Set `UPDATE_SNAPSHOTS=1` to re-bake the baseline.
 
@@ -17,6 +19,7 @@ use kebab_core::{
     Lang, Metadata, ParserVersion, Provenance, SourceSpan, SourceType, TrustLevel, WorkspacePath,
     id_for_block, id_for_doc,
 };
+use kebab_parse_code::CppAstExtractor;
 use serde_json::Value;
 use time::OffsetDateTime;
 
@@ -134,6 +137,47 @@ fn fixed_policy() -> ChunkPolicy {
     }
 }
 
+// ---------------------------------------------------------------------------
+// Helper: run the real CppAstExtractor against tests/fixtures/sample.cpp
+// ---------------------------------------------------------------------------
+
+fn extract_cpp_fixture() -> CanonicalDocument {
+    use kebab_core::{
+        AssetId, AssetStorage, Checksum, ExtractConfig, ExtractContext, Extractor, RawAsset,
+        SourceUri, WorkspacePath,
+    };
+    use std::path::PathBuf;
+
+    let bytes = std::fs::read(fixtures_dir().join("sample.cpp")).expect("read sample.cpp fixture");
+    let src = String::from_utf8(bytes).expect("fixture is valid UTF-8");
+    let wp = WorkspacePath("tests/fixtures/sample.cpp".to_string());
+    let asset = RawAsset {
+        asset_id: AssetId("e".repeat(64)),
+        source_uri: SourceUri::File(PathBuf::from("tests/fixtures/sample.cpp")),
+        workspace_path: wp,
+        media_type: kebab_core::MediaType::Code("cpp".to_string()),
+        byte_len: src.len() as u64,
+        checksum: Checksum("f".repeat(64)),
+        discovered_at: time::OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
+        stored: AssetStorage::Reference {
+            path: PathBuf::from("tests/fixtures/sample.cpp"),
+            sha: Checksum("f".repeat(64)),
+        },
+    };
+    let cfg = ExtractConfig::default();
+    let root = PathBuf::from("/tmp");
+    let ctx = ExtractContext {
+        asset: &asset,
+        workspace_root: &root,
+        config: &cfg,
+    };
+    CppAstExtractor::new().extract(&ctx, src.as_bytes()).unwrap()
+}
+
+// ---------------------------------------------------------------------------
+// Test 1 (hand-built): chunker-only 1:1 mapping validation
+// ---------------------------------------------------------------------------
+
 #[test]
 fn code_cpp_ast_chunks_snapshot() {
     let doc = fixed_doc();
@@ -198,3 +242,84 @@ fn code_cpp_ast_chunks_are_deterministic() {
         assert_eq!(again, baseline);
     }
 }
+
+// ---------------------------------------------------------------------------
+// Test 2 (real extractor): end-to-end extractor → chunker pipeline
+// ---------------------------------------------------------------------------
+
+/// Validates that the real `CppAstExtractor` processes `sample.cpp` and
+/// emits the expected set of symbols through the full chunker pipeline.
+///
+/// `sample.cpp` contains:
+/// - `#include` directives + nested namespace `kebab::chunk` → glue + struct unit
+/// - `class MdHeadingV1Chunker` with methods (ctor, dtor, chunk_doc, operator())
+/// - `template <typename T> T identity(T value)` (template fn)
+/// - `void kebab::global_helper()` (free fn in namespace)
+/// - `int main()` (global free fn)
+#[test]
+fn code_cpp_ast_extractor_snapshot() {
+    let doc = extract_cpp_fixture();
+
+    // Verify the extractor emits all expected named units.
+    let block_syms: Vec<Option<String>> = doc.blocks.iter().filter_map(|b| match b {
+        Block::Code(c) => match &c.common.source_span {
+            SourceSpan::Code { symbol, .. } => Some(symbol.clone()),
+            _ => None,
+        },
+        _ => None,
+    }).collect();
+
+    // Must include namespace-qualified class and its methods
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("kebab::chunk::MdHeadingV1Chunker")),
+        "class unit missing: {block_syms:?}"
+    );
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("kebab::chunk::MdHeadingV1Chunker::MdHeadingV1Chunker")),
+        "ctor unit missing: {block_syms:?}"
+    );
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("kebab::chunk::MdHeadingV1Chunker::~MdHeadingV1Chunker")),
+        "dtor unit missing: {block_syms:?}"
+    );
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("kebab::chunk::MdHeadingV1Chunker::chunk_doc")),
+        "chunk_doc unit missing: {block_syms:?}"
+    );
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("kebab::chunk::MdHeadingV1Chunker::operator()")),
+        "operator() unit missing: {block_syms:?}"
+    );
+    // Template function (inside kebab::chunk namespace in the fixture)
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("kebab::chunk::identity")),
+        "identity template fn unit missing: {block_syms:?}"
+    );
+    // Free function in outer namespace
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("kebab::global_helper")),
+        "global_helper unit missing: {block_syms:?}"
+    );
+    // Global main
+    assert!(
+        block_syms.iter().any(|s| s.as_deref() == Some("main")),
+        "main unit missing: {block_syms:?}"
+    );
+}
+
+/// End-to-end chunker output from real extractor is deterministic.
+#[test]
+fn code_cpp_ast_extractor_chunks_deterministic() {
+    let doc1 = extract_cpp_fixture();
+    let doc2 = extract_cpp_fixture();
+    assert_eq!(doc1.blocks, doc2.blocks, "extractor output non-deterministic");
+
+    let policy = fixed_policy();
+    let chunks1 = CodeCppAstV1Chunker.chunk(&doc1, &policy).unwrap();
+    let chunks2 = CodeCppAstV1Chunker.chunk(&doc2, &policy).unwrap();
+    assert_eq!(
+        chunks1.iter().map(|c| c.chunk_id.0.clone()).collect::<Vec<_>>(),
+        chunks2.iter().map(|c| c.chunk_id.0.clone()).collect::<Vec<_>>(),
+        "chunker output non-deterministic"
+    );
+}

crates/kebab-chunk/tests/k8s_manifest_resource_v1.rs

@@ -140,6 +140,17 @@ fn k8s_multi_doc_emits_one_chunk_per_resource() {
     for chunk in &chunks {
         assert_eq!(chunk.chunker_version.0, "k8s-manifest-resource-v1");
     }
+
+    // Every chunk from a multi-resource file must have a distinct chunk_id.
+    // Without the fix, all non-oversize resources get split_key=None which
+    // collapses to the same id_hash (= base_policy_hash) → UNIQUE constraint
+    // violation on the second resource.
+    let ids: std::collections::HashSet<_> = chunks.iter().map(|c| c.chunk_id.clone()).collect();
+    assert_eq!(
+        ids.len(),
+        chunks.len(),
+        "every k8s resource chunk must have a distinct chunk_id (multi-resource collision regression)"
+    );
 }
 
 /// A YAML document with an indentation error (tab in a space-indented context)

crates/kebab-parse-code/src/c.rs

@@ -333,5 +333,260 @@ fn flush_glue(glue: &mut Vec<(u32, u32)>, units: &mut Vec<(String, u32, u32, boo
     glue.clear();
 }
 
-// Tests for CAstExtractor (snapshot + unit assertions) are added in Task D
-// alongside the C fixture file. This module is intentionally empty until then.
+// ---------------------------------------------------------------------------
+// Tests
+// ---------------------------------------------------------------------------
+
+#[cfg(test)]
+pub(crate) mod tests_support {
+    use kebab_core::*;
+    use std::path::PathBuf;
+    use time::OffsetDateTime;
+
+    pub fn fixed_code_asset(workspace_path: &str, lang: &str) -> RawAsset {
+        RawAsset {
+            asset_id: AssetId("a".repeat(64)),
+            source_uri: SourceUri::File(PathBuf::from(workspace_path)),
+            workspace_path: WorkspacePath(workspace_path.to_string()),
+            media_type: MediaType::Code(lang.to_string()),
+            byte_len: 0,
+            checksum: Checksum("b".repeat(64)),
+            discovered_at: OffsetDateTime::from_unix_timestamp(1_700_000_000).unwrap(),
+            stored: AssetStorage::Reference {
+                path: PathBuf::from(workspace_path),
+                sha: Checksum("b".repeat(64)),
+            },
+        }
+    }
+
+    pub fn extract_c(src: &str, path: &str) -> kebab_core::CanonicalDocument {
+        use super::CAstExtractor;
+        use kebab_core::Extractor;
+        let asset = fixed_code_asset(path, "c");
+        let cfg = ExtractConfig::default();
+        let root = PathBuf::from("/tmp");
+        let ctx = ExtractContext {
+            asset: &asset,
+            workspace_root: &root,
+            config: &cfg,
+        };
+        CAstExtractor::new().extract(&ctx, src.as_bytes()).unwrap()
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use kebab_core::{Block, MediaType, SourceSpan};
+
+    fn syms(doc: &kebab_core::CanonicalDocument) -> Vec<String> {
+        doc.blocks
+            .iter()
+            .filter_map(|b| match b {
+                Block::Code(c) => match &c.common.source_span {
+                    SourceSpan::Code { symbol, .. } => symbol.clone(),
+                    _ => None,
+                },
+                _ => None,
+            })
+            .collect()
+    }
+
+    #[test]
+    fn extractor_supports_only_media_code_c() {
+        let e = CAstExtractor::new();
+        assert!(e.supports(&MediaType::Code("c".into())));
+        assert!(!e.supports(&MediaType::Code("cpp".into())));
+        assert!(!e.supports(&MediaType::Code("rust".into())));
+        assert!(!e.supports(&MediaType::Markdown));
+    }
+
+    #[test]
+    fn c_extractor_simple_function() {
+        let src = "int add(int a, int b) { return a + b; }\n";
+        let doc = tests_support::extract_c(src, "x/math.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "add"), "got {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_pointer_return_function() {
+        let src = "int *find(int *arr, int n) { return arr; }\n";
+        let doc = tests_support::extract_c(src, "x/find.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "find"), "ptr-return fn missing: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_static_function() {
+        let src = "static void helper(void) {}\n";
+        let doc = tests_support::extract_c(src, "x/helper.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "helper"), "static fn missing: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_extern_function() {
+        let src = "extern int compute(int x);\n";
+        // extern prototype is a declaration → glue
+        let doc = tests_support::extract_c(src, "x/compute.c");
+        let s = syms(&doc);
+        // declaration (prototype) falls into glue → "<module>"
+        assert!(
+            s.iter().any(|x| x == "<module>"),
+            "expected <module> for extern proto: {s:?}"
+        );
+    }
+
+    #[test]
+    fn c_extractor_inline_function() {
+        let src = "inline int square(int x) { return x * x; }\n";
+        let doc = tests_support::extract_c(src, "x/square.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "square"), "inline fn missing: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_named_struct() {
+        let src = "struct Point { int x; int y; };\n";
+        let doc = tests_support::extract_c(src, "x/point.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "Point"), "struct missing: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_named_enum() {
+        let src = "enum Color { RED, GREEN, BLUE };\n";
+        let doc = tests_support::extract_c(src, "x/color.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "Color"), "enum missing: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_named_union() {
+        let src = "union Data { int i; float f; };\n";
+        let doc = tests_support::extract_c(src, "x/data.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "Data"), "union missing: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_anonymous_struct_falls_into_glue() {
+        // Anonymous struct (no name field) → glue → "<module>" (only glue, no real unit)
+        let src = "struct { int x; int y; } origin;\n";
+        let doc = tests_support::extract_c(src, "x/anon.c");
+        let s = syms(&doc);
+        // anonymous struct is a declaration containing anonymous struct_specifier → glue
+        assert!(
+            s.iter().any(|x| x == "<module>"),
+            "expected <module> for anon struct: {s:?}"
+        );
+        // Must NOT emit a unit named after anything else
+        assert!(
+            !s.iter().any(|x| x == "origin"),
+            "unexpected 'origin' unit: {s:?}"
+        );
+    }
+
+    #[test]
+    fn c_extractor_typedef_struct_falls_into_glue() {
+        // typedef struct { ... } Foo; — inner struct_specifier is anonymous,
+        // outer node is type_definition → glue. See HOTFIXES.md 2026-05-21.
+        let src = "typedef struct { int x; int y; } Point;\n";
+        let doc = tests_support::extract_c(src, "x/typedef.c");
+        let s = syms(&doc);
+        assert!(
+            s.iter().any(|x| x == "<module>"),
+            "expected <module> for typedef struct: {s:?}"
+        );
+        // The typedef alias should NOT surface as a Code symbol
+        assert!(
+            !s.iter().any(|x| x == "Point"),
+            "unexpected 'Point' unit for typedef struct: {s:?}"
+        );
+    }
+
+    #[test]
+    fn c_extractor_preprocessor_directives_are_glue() {
+        let src = "#include <stdio.h>\n#define MAX 100\n#ifdef DEBUG\n#endif\n";
+        let doc = tests_support::extract_c(src, "x/macros.c");
+        let s = syms(&doc);
+        // Only preprocessor → no real unit → "<module>"
+        assert!(
+            s.iter().any(|x| x == "<module>"),
+            "expected <module> for preproc-only file: {s:?}"
+        );
+        assert_eq!(s.len(), 1, "expected exactly 1 block: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_multiple_functions_correct_count() {
+        let src = "int foo(void) { return 1; }\nint bar(void) { return 2; }\nint baz(void) { return 3; }\n";
+        let doc = tests_support::extract_c(src, "x/multi.c");
+        let s = syms(&doc);
+        assert!(s.iter().any(|x| x == "foo"), "foo missing: {s:?}");
+        assert!(s.iter().any(|x| x == "bar"), "bar missing: {s:?}");
+        assert!(s.iter().any(|x| x == "baz"), "baz missing: {s:?}");
+        assert_eq!(s.len(), 3, "expected 3 units: {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_empty_file_produces_module() {
+        let src = "";
+        let doc = tests_support::extract_c(src, "x/empty.c");
+        let s = syms(&doc);
+        assert_eq!(s, vec!["<module>"], "expected <module>: got {s:?}");
+    }
+
+    #[test]
+    fn c_extractor_preprocessor_only_produces_module() {
+        let src = "#include <stdlib.h>\n#define VERSION \"1.0\"\n";
+        let doc = tests_support::extract_c(src, "x/header.c");
+        let s = syms(&doc);
+        assert!(
+            s.iter().any(|x| x == "<module>"),
+            "expected <module> for preproc-only file: {s:?}"
+        );
+    }
+
+    #[test]
+    fn c_extractor_mixed_functions_and_glue() {
+        let src = r#"#include <stdio.h>
+
+int compute(int x) {
+    return x * 2;
+}
+
+extern int lookup(int key);
+
+void print_result(int v) {
+    printf("%d\n", v);
+}
+"#;
+        let doc = tests_support::extract_c(src, "x/mixed.c");
+        let s = syms(&doc);
+        // Two real functions + one glue block
+        assert!(s.iter().any(|x| x == "compute"), "compute missing: {s:?}");
+        assert!(s.iter().any(|x| x == "print_result"), "print_result missing: {s:?}");
+        assert!(
+            s.iter().any(|x| x == "<top-level>"),
+            "<top-level> glue missing: {s:?}"
+        );
+    }
+
+    #[test]
+    fn c_extractor_deterministic_across_runs() {
+        let src = r#"
+struct Node { int val; };
+int sum(int a, int b) { return a + b; }
+void noop(void) {}
+"#;
+        let a = tests_support::extract_c(src, "x/det.c");
+        for _ in 0..20 {
+            assert_eq!(
+                tests_support::extract_c(src, "x/det.c").blocks,
+                a.blocks
+            );
+        }
+    }
+}

tasks/HOTFIXES.md

@@ -14,6 +14,34 @@ historical contract that was implemented; this file accumulates the
 deltas so phase 5+ readers can find the live behavior without diffing
 git history.
 
+## 2026-05-21 — p10-2: k8s multi-resource YAML chunk_id collision
+
+**Origin**: P10 종합 도그푸딩 (`/tmp/kebab-p10-dogfood/`, 16 파일). 한 파일에 2+ k8s document (Deployment + Service, `---` 구분) 인 YAML 이 ingest 실패.
+
+**Symptom**: `DocumentStore::put_chunks (code): UNIQUE constraint failed: chunks.chunk_id`. document row 는 생성되나 chunk 0개 → 검색 불가. p10-2 의 통합 테스트 `tier2_k8s_yaml_ingest_searchable` 가 single-Deployment fixture 만 써서 미발견.
+
+**원인**: `tier2_shared::push_chunks_with_oversize` 의 non-oversize 분기가 `split_key = None` 하드코딩. `K8sManifestResourceV1Chunker` 가 resource 마다 호출 — 같은 document 의 모든 resource 가 `doc_id` + `chunker_version` + `base_policy_hash` 공유 + `split_key = None` → 동일 `id_hash` → 동일 `chunk_id`. p10-3 의 `code_text_paragraph_v1` 가 같은 버그였고 `df3c5b8` 에서 fix 됐지만 그건 `build_chunk_no_symbol` 직접 호출 경로, `push_chunks_with_oversize` 경로는 미수정.
+
+**Fix** (PR #158, v0.16.1): `push_chunks_with_oversize` 에 `base_split_key: Option<u32>` 추가. k8s chunker 가 `Some(resource.line_start)` 전달 → resource 별 distinct chunk_id. dockerfile / manifest 는 `None` (파일당 1 chunk, 충돌 없음, chunk_id 불변).
+
+**Deviation note**: single-resource k8s YAML 의 chunk_id 도 `None → Some(1)` 으로 바뀜 (`id_hash` 가 `base_policy_hash` → `base_policy_hash#L1`). `chunker_version` (`k8s-manifest-resource-v1`) 은 의도적으로 bump 안 함 — p10-2 가 v0.14.0 (~1주 전) 머지된 dogfood 단계라 prod KB 없음. v0.14.0~v0.16.0 사이 single-resource k8s 를 색인한 KB 는 re-ingest 시 old chunk 가 orphan 될 수 있으나 (UNIQUE 충돌 아님 — 다른 id), `kebab reset` 또는 re-ingest sweep 으로 정리됨. dogfood-only 단계라 chunker_version bump (전체 re-process) 보다 가벼운 선택.
+
+Cross-link: `tasks/p10/p10-2-tier2-resource-aware.md` Risks/notes section.
+
+## 2026-05-21 — p10-1D: typedef-wrapped struct/enum in C falls into glue
+
+**Origin**: PR #156 (p10-1d) code-reviewer review. Verified during dogfood.
+
+**Symptom**: `typedef struct { ... } Foo;` in a `.c` file does NOT emit a struct-level unit. tree-sitter-c classifies the construct as a top-level `type_definition` with an *anonymous* inner `struct_specifier` (no `name` field), so the extractor's `struct_specifier` arm doesn't fire — the whole declaration falls into `<top-level>` glue. The named typedef alias `Foo` is therefore not searchable as a symbol.
+
+**Status**: Consistent with spec p10-1d-c-cpp-ast-chunker.md's Risks/notes ("Anonymous union / struct … anonymous → glue"), but the spec's main body line 22 ("struct_specifier (named, top-level) → 1 unit") suggests this idiom WOULD emit. Tension noted, not yet fixed.
+
+**Workaround**: search the struct by its field/function names, or use `--code-lang c` to broaden scope. Typedef-aliased struct names won't surface as `Citation::Code.symbol`.
+
+**Next step**: dogfood real C code for a week+; if this turns out to be a frequent pain point (kernel-style code, libuv, etc.), revisit the extractor to detect `type_definition` → inner `struct_specifier` and emit a synthetic unit named after the typedef alias.
+
+Cross-link: `tasks/p10/p10-1d-c-cpp-ast-chunker.md` Risks/notes section.
+
 ## 2026-05-20 — p10-1B: Rust 1A-2 symbol path is file-scope-only; 1B+ uses workspace path → module prefix
 
 **무엇이 바뀌었나**: P10-1A-2 의 Rust `code-rust-ast-v1` chunker 가 생성하는 symbol 은 file-scope mod-path nesting 만 사용한다 (예: `Foo::double`). P10-1B 이후 Python / TypeScript / JavaScript 의 symbol 은 workspace 경로 → module path prefix 를 포함한다 (예: `kebab_eval.metrics.compute_mrr`, `src/Foo.Foo.search`).

tasks/p10/p10-1d-c-cpp-ast-chunker.md

@@ -113,6 +113,7 @@ crates/kebab-parse-code/Cargo.toml  [edit] — 위 2 dep 신규 entry.
 - **Template specialization** (`template<> class Foo<int>`): tree-sitter-cpp 의 `template_declaration` 안의 `class_specifier` name 만 추출 — `Foo` 만 symbol 에 들어가고 `<int>` 미포함. design 의 generic 무시 룰 일관.
 - **`extern "C"` block 안의 fn**: 일반 fn 처리. 외부 wrapping block 은 glue.
 - **Anonymous union / struct** (`struct { int x; }` 변수 안에): 흔치 않음 + named 만 unit. anonymous 는 glue.
+- **typedef-wrapped struct/enum idiom** (`typedef struct { ... } Foo;`) — anonymous inner struct → glue. Named typedef alias 미캡처. dogfood 후 HOTFIXES 검토. See [HOTFIXES.md 2026-05-21 entry](../HOTFIXES.md).
 - **Macro-heavy code** (Linux kernel 등): `#define FOO(x) ...` 매크로가 function-like 라도 parser 가 fn 으로 인식 안 함. preprocessor glue 로 처리 — symbol 안 잡힘. 의도된 동작 (parser 의 macro expansion 안 함).
 - **`__attribute__((...))`** annotations: tree-sitter-c 의 attribute 노드는 declarator 옆 sibling. 무시 가능. function name 추출에 영향 없음.
 - **fixture 크기**: sample.c 는 ~30 line (top-level fn + struct + enum + preprocessor), sample.cpp 는 ~50 line (nested namespace + class + method + template + free fn). oversize fallback 의 별도 검증은 1A-2 의 long_section_snapshot 패턴이 이미 cover (필요 시 별도 fixture).

tasks/p10/p10-2-tier2-resource-aware.md

@@ -118,3 +118,4 @@ _                                 → skip (p10-3 fallback 의 자리)
 - **`pom.xml` aggregate parent POM** — 매우 큼 (수백~수천 줄). oversize fallback 으로 split. 거대 fixture 로 한 번 검증.
 - **`media.rs` 정리** — 1A-1 부터 누적된 inline `match extension` duplication 을 `code_lang_for_path` 호출로 교체. 기존 단위 테스트 동작 보존 (테스트는 결과 값만 보므로 통과해야 함).
 - **머지 후 deviation** 은 `tasks/HOTFIXES.md` dated 로그 + 본 spec `Risks / notes` 에 one-line cross-link.
+- **[HOTFIXES 2026-05-21]** multi-resource k8s YAML (2+ document) 이 `chunk_id` 충돌로 ingest 실패 — `push_chunks_with_oversize` 의 non-oversize 분기가 `split_key = None` 하드코딩. PR #158 (v0.16.1) 에서 `base_split_key` 파라미터로 fix. See `tasks/HOTFIXES.md` 2026-05-21 entry.