Lang support

AGENTS.md

@@ -20,6 +20,7 @@
 - **Artifacts:** Session data lives in `{repo}/.rgctl/`. Warm caches invalidate wall-time claims.
 - **Features:** Default semantic embedder is compiled **vocab**. Do not require ONNX / Python ML unless behind an explicit feature (e.g. `semantic-onnx` / code-daemon + Git LFS).
 - **OpenSpec language work:** Still cite [openspec/changes/_shared/starting-context.md](openspec/changes/_shared/starting-context.md) (pointer here); follow the sections below.
+- **Grammar bumps:** When you bump a tree-sitter grammar pin, update that language’s `*-ast-coverage.json` (and add the language to `rgctl-ast-coverage::bundled_specs` for new languages). Unit tests hard-fail the same drift; `cargo check -p rgctl-languages` warns (`RGCTL_AST_COVERAGE_STRICT=1` fails). The website `/docs/languages/` pages are generated from those JSON files — do not maintain parallel tables under `docs/languages/`.
 
 ---
 
@@ -28,7 +29,7 @@
 - **Discover** walks the tree, runs language plugins (tree-sitter), builds the graph, writes compact caches to `.rgctl/`.
 - **Query** paths are read-oriented and return versioned JSON (`schema_version` on stdout — never scrape stderr).
 - **Analysis** (`rgctl-analysis`) projects CSR / callgraph / centrality / blast-radius / CFG–PDG; see [docs/analysis-architecture.md](docs/analysis-architecture.md).
-- **Languages:** `crates/rgctl-lang-*` + `rgctl-plugin-api`; register in `languages.toml`.
+- **Languages:** `crates/rgctl-lang-*` + `rgctl-plugin-api`; register in `languages.toml`. See **Grammar bumps** under Must-follow for AST coverage manifests.
 
 ---
 
@@ -80,8 +81,11 @@ Fetch: `./scripts/fetch-profile-repos.sh`
 | **PHP** | Magento 2 | `example/magento2` | `-l php` | `RGCTL_MAGENTO2_REPO` |
 | **Python** | Home Assistant | `example/home-assistant` | `-l python` | `RGCTL_HOME_ASSISTANT_REPO` |
 | **Ruby** | Discourse | `example/discourse` | `-l ruby` | — |
+| **Puppet** | *(deferred)* | `RGCTL_PUPPET_REPO` | `-l puppet` | `RGCTL_PUPPET_REPO` — no default ~10k corpus yet |
 | **Rust** | rustc | `example/rust` | `-l rust` | `RGCTL_RUST_REPO` |
 | **TypeScript** | VS Code | `example/vscode` | `-l typescript` on `src/` | `RGCTL_VSCODE_REPO` |
+| **Kotlin** | JetBrains/kotlin | `example/kotlin` | `-l kotlin` (sparse `libraries` `plugins` `analysis`) | `RGCTL_KOTLIN_REPO` |
+| **Groovy** | Gradle | `example/groovy` | `-l groovy` | `RGCTL_GROOVY_REPO` |
 
 File counts are approximate (goal **O(10⁴)** sources). Exclude `vendor/`, `node_modules/`, `target/`, `third_party/`.
 

CONTRIBUTING.md

@@ -95,7 +95,7 @@ Use the hub checklist for path choice, test matrices, and pre-PR commands:
 
 **[docs/contributor-checklist.md](docs/contributor-checklist.md)**
 
-Tier 1 depth (Layers A–F): [docs/tier-1-language-support.md](docs/tier-1-language-support.md) · language list: [docs/languages/README.md](docs/languages/README.md)
+Tier 1 depth (Layers A–F): [docs/tier-1-language-support.md](docs/tier-1-language-support.md) · language matrix SSOT: `crates/rgctl-lang-*/{id}-ast-coverage.json` ([docs/languages/README.md](docs/languages/README.md))
 
 ---
 

Cargo.toml

@@ -36,6 +36,10 @@ members = [
     "crates/rgctl-lang-markdown",
     "crates/rgctl-lang-php",
     "crates/rgctl-lang-ruby",
+    "crates/rgctl-lang-puppet",
+    "crates/rgctl-lang-kotlin",
+    "crates/rgctl-lang-groovy",
+    "crates/rgctl-ast-coverage",
     "crates/rgctl-languages",
     "crates/rgctl-agent-pack-codegen",
 ]
@@ -83,6 +87,10 @@ rgctl-lang-cpp = { path = "crates/rgctl-lang-cpp", version = "0.4.16" }
 rgctl-lang-markdown = { path = "crates/rgctl-lang-markdown", version = "0.4.16" }
 rgctl-lang-php = { path = "crates/rgctl-lang-php", version = "0.4.16" }
 rgctl-lang-ruby = { path = "crates/rgctl-lang-ruby", version = "0.4.16" }
+rgctl-lang-puppet = { path = "crates/rgctl-lang-puppet", version = "0.4.16" }
+rgctl-lang-kotlin = { path = "crates/rgctl-lang-kotlin", version = "0.4.16" }
+rgctl-lang-groovy = { path = "crates/rgctl-lang-groovy", version = "0.4.16" }
+rgctl-ast-coverage = { path = "crates/rgctl-ast-coverage", version = "0.4.16" }
 rgctl-languages = { path = "crates/rgctl-languages", version = "0.4.16" }
 tree-sitter = "0.25"
 

crates/rgctl-analysis/Cargo.toml

@@ -28,6 +28,9 @@ tree-sitter-javascript = "0.25"
 tree-sitter-typescript = "0.23"
 tree-sitter-php = "0.24.2"
 tree-sitter-ruby = "0.23.1"
+tree-sitter-puppet = "1.3.0"
+tree-sitter-kotlin-ng = "1.1.0"
+tree-sitter-groovy = "0.1.2"
 uuid = { version = "1", features = ["v4", "serde"] }
 bit-set = "0.8"
 tracing = "0.1"

crates/rgctl-analysis/src/ast_skeleton.rs

@@ -178,6 +178,7 @@ fn find_function<'a>(
             "javascript" | "js" | "typescript" | "ts" => {
                 ecmascript_function_symbol_name(node, source)
             }
+            "puppet" => puppet_callable_name(node, source),
             _ => extract_name_from_node(node, source).ok().flatten(),
         };
         if resolved.as_deref() == Some(name) {
@@ -193,6 +194,26 @@ fn find_function<'a>(
     None
 }
 
+/// Match CFG / Function symbol naming for Puppet class/define/node/function hosts.
+fn puppet_callable_name(node: Node<'_>, source: &[u8]) -> Option<String> {
+    let mut cursor = node.walk();
+    for child in node.children(&mut cursor) {
+        if matches!(
+            child.kind(),
+            "class_identifier" | "identifier" | "node_name" | "string"
+        ) {
+            if let Ok(t) = child.utf8_text(source) {
+                let name = t.trim_matches('\'').trim_matches('"');
+                if node.kind() == "node_definition" {
+                    return Some(format!("node:{name}"));
+                }
+                return Some(name.to_string());
+            }
+        }
+    }
+    extract_name_from_node(node, source).ok().flatten()
+}
+
 fn walk_skeleton(
     node: Node,
     source: &[u8],
@@ -236,9 +257,11 @@ fn walk_skeleton(
 fn classify(kind: &str) -> Option<AstSkeletonKind> {
     Some(match kind {
         "block" | "compound_statement" | "statement_block" | "body" => AstSkeletonKind::Block,
-        "if_statement" | "if_expression" | "if" | "unless" => AstSkeletonKind::If,
+        "if_statement" | "if_expression" | "if" | "unless" | "unless_statement"
+        | "when_expression" => AstSkeletonKind::If,
         "while_statement" | "while_expression" | "for_statement" | "for_expression"
-        | "loop_expression" | "do_statement" | "foreach_statement" | "while" | "until" | "for" => {
+        | "loop_expression" | "do_statement" | "do_while_statement" | "foreach_statement"
+        | "while" | "until" | "for" | "iterator_statement" | "case_statement" => {
             AstSkeletonKind::Loop
         }
         "call_expression" | "method_invocation" | "invocation_expression" | "function_call"
@@ -255,6 +278,7 @@ fn classify(kind: &str) -> Option<AstSkeletonKind> {
         | "local_variable_declaration"
         | "variable_declaration"
         | "short_var_declaration"
+        | "property_declaration"
         | "declaration" => AstSkeletonKind::Decl,
         _ => return None,
     })