feat(kernel): R7a C/C++ walker — dual-lang ccpp module, preParse hoist, 7 new blanks, c/cpp default-routed (#1346)

Parity: 0 diffs on redis/git/fmt/protobuf/ALS sweeps; full-init dumps
byte-identical on all five + linux at kernel scale (10.4M dump lines,
same sha256 both arms). Linux 2c/6GB envelope: kernel-arm 19.1min vs
wasm-arm 22.9min (parse 356s vs 435s) on a much richer graph (the new
blanks recover error-swallowed code: git 2x nodes, linux kernel/+mm/ 3x).
Deferral guard corrected by measurement (C/C++ error incidence 9-42%;
--max-deferral flag); defer-reuse memo kills the 3x re-blank/re-parse
cost deferred files paid.

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

codegraph-kernel/.gitignore

@@ -1,3 +1,5 @@
 target/
+# Cross-compile scratch dirs (e.g. target-linux for the cg1212 envelope runs)
+target-*/
 prebuilds/
 *.node

codegraph-kernel/Cargo.lock

@@ -52,6 +52,8 @@ dependencies = [
  "regex",
  "sha2",
  "tree-sitter",
+ "tree-sitter-c",
+ "tree-sitter-cpp",
  "tree-sitter-go",
  "tree-sitter-java",
  "tree-sitter-javascript",
@@ -482,6 +484,26 @@ dependencies = [
  "tree-sitter-language",
 ]
 
+[[package]]
+name = "tree-sitter-c"
+version = "0.24.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a9b2eb57a55fed6b00812912e730b7a275cf4fe98bfd6a5d76263d4438371728"
+dependencies = [
+ "cc",
+ "tree-sitter-language",
+]
+
+[[package]]
+name = "tree-sitter-cpp"
+version = "0.23.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "df2196ea9d47b4ab4a31b9297eaa5a5d19a0b121dceb9f118f6790ad0ab94743"
+dependencies = [
+ "cc",
+ "tree-sitter-language",
+]
+
 [[package]]
 name = "tree-sitter-go"
 version = "0.23.4"

codegraph-kernel/Cargo.toml

@@ -25,6 +25,11 @@ tree-sitter-javascript = "0.25"
 tree-sitter-java = "0.23"
 tree-sitter-python = "0.23"
 tree-sitter-go = "0.23"
+# Pinned exact: the vendored wasm (src/extraction/wasm/) was built from these
+# tags' checked-in parser.c, sha-matched against these registry tarballs
+# (R7a prep, #1345). A patch bump here without re-vendoring breaks the match.
+tree-sitter-c = "=0.24.2"
+tree-sitter-cpp = "=0.23.4"
 
 [build-dependencies]
 napi-build = "2"

codegraph-kernel/src/langs.rs

@@ -15,8 +15,8 @@ use tree_sitter::Language;
 
 /// Languages this kernel binary can extract (reported by contractInfo;
 /// TS-side routing policy decides what actually routes).
-pub const LANGUAGES: [&str; 7] =
-    ["typescript", "tsx", "javascript", "jsx", "java", "python", "go"];
+pub const LANGUAGES: [&str; 9] =
+    ["typescript", "tsx", "javascript", "jsx", "java", "python", "go", "c", "cpp"];
 
 pub fn grammar_for(language: &str) -> Option<Language> {
     match language {
@@ -26,6 +26,11 @@ pub fn grammar_for(language: &str) -> Option<Language> {
         "java" => Some(tree_sitter_java::LANGUAGE.into()),
         "python" => Some(tree_sitter_python::LANGUAGE.into()),
         "go" => Some(tree_sitter_go::LANGUAGE.into()),
+        // `.metal`/`.cu`/`.cuh` map to language 'cpp' at detectLanguage, so the
+        // dialects ride this grammar too (their blanking pre-passes stay
+        // TS-side — the route point applies preParse before the kernel call).
+        "c" => Some(tree_sitter_c::LANGUAGE.into()),
+        "cpp" => Some(tree_sitter_cpp::LANGUAGE.into()),
         _ => None,
     }
 }

codegraph-kernel/src/lib.rs

@@ -17,6 +17,7 @@
 #![deny(clippy::all)]
 
 mod buffers;
+mod ccpp;
 mod docstring;
 mod ids;
 mod go;
@@ -103,6 +104,7 @@ pub fn extract_file(file_path: String, content: String, language: String) -> Res
         "java" => java::extract(&file_path, &content).map_err(Error::from_reason)?,
         "python" => python::extract(&file_path, &content).map_err(Error::from_reason)?,
         "go" => go::extract(&file_path, &content).map_err(Error::from_reason)?,
+        "c" | "cpp" => ccpp::extract(&file_path, &content, &language).map_err(Error::from_reason)?,
         _ => tsjs::extract(&file_path, &content, &language).map_err(Error::from_reason)?,
     };
     Ok(ExtractBuffers {