Merge remote-tracking branch 'origin/main' into fix/kotlin-property-initializer-walk

# Conflicts:
#	CHANGELOG.md

CHANGELOG.md

@@ -137,6 +137,10 @@ and adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 #### MCP / indexing
 
+- Indexing now warns when parser errors leave a file with no symbols, including C++ raw strings with 16-character delimiters, so missing code is no longer silent. (#1522)
+
+- `codegraph index <path>` now refuses uninitialized paths and names the nearest initialized parent instead of silently rebuilding it; thanks @danusha2345. (#1524, #1689)
+
 - Sync now recovers the same connections as a clean index after interrupted reference resolution, including inherited calls and callbacks that previously stayed missing. (#1577)
 
 - `codegraph_explore` now re-serves source to fresh subagents and after context compaction, with cross-call dedup available only through an explicit `CODEGRAPH_EXPLORE_DEDUP=1` opt-in; thanks @danusha2345. (#1620, #1624)
@@ -230,6 +234,7 @@ and adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 - Kotlin `init { }` blocks and destructuring declarations no longer swallow their code: `init { val cfg = load() }` and `val (a, b) = makePair()` contributed no call edge at all, and now attribute to the enclosing class or file.
 - A Kotlin property's accessor body now belongs to the property whichever line it is written on, instead of being dropped (same line) or handed to the enclosing class (own line).
 - Kotlin properties that hold a lambda, a SAM callback or an anonymous object — `private val frameListener = CameraFrameListener { … }`, the way Android and MSDK callbacks are almost always declared — now contribute call edges. Previously everything inside such an initializer was dropped, so a function reached only through one of these callbacks looked like it had no callers at all and its blast radius came back far too small. Delegated properties (`by lazy { … }`) and plain initializers (`val x = compute()`) were affected the same way and are fixed too. Re-index with `codegraph index -f` after upgrading to pick up the new edges.
+- Rust unit structs (`struct Unit;`) and their trait implementation relationships now appear in the graph after re-indexing. (#1513, #1514)
 - Imports from Node built-ins or npm packages no longer connect to unrelated type members with matching names; re-index after upgrading to clear existing false dependencies. Thanks @ctype-lab. (#1537)
 
 - Inheritance relationships no longer attach external Rust or npm supertypes to unrelated local symbols with the same name, including in Svelte, Vue and Astro components; re-index after upgrading to clear existing false relationships. Thanks @ctype-lab. (#1536)

__tests__/cli-index-explicit-path.test.ts

@@ -0,0 +1,64 @@
+/**
+ * `codegraph index <path>` rebuilds <path>, never an ancestor (#1524).
+ *
+ * The command used to resolve an uninitialized <path> upward to the nearest
+ * initialized parent and rebuild THAT under a normal "Done" — so
+ * `codegraph index child` from a monorepo re-indexed the whole container and
+ * never said so. An explicit path that is not initialized is now an error that
+ * names the ancestor it would have picked.
+ */
+import { describe, it, expect, beforeAll, afterAll } from 'vitest';
+import { spawnSync } from 'child_process';
+import * as fs from 'fs';
+import * as os from 'os';
+import * as path from 'path';
+import { CodeGraph } from '../src';
+
+const BIN = path.resolve(__dirname, '../dist/bin/codegraph.js');
+
+function run(cwd: string, args: string[]) {
+  const r = spawnSync(process.execPath, [BIN, ...args], {
+    cwd,
+    encoding: 'utf-8',
+    env: { ...process.env, CODEGRAPH_NO_DAEMON: '1', CODEGRAPH_WASM_RELAUNCHED: '1', NO_COLOR: '1' },
+  });
+  return { status: r.status, out: (r.stdout ?? '') + (r.stderr ?? '') };
+}
+
+describe('codegraph index <path> (#1524)', () => {
+  let root: string;
+  let parent: string;
+  let child: string;
+
+  beforeAll(async () => {
+    root = fs.mkdtempSync(path.join(os.tmpdir(), 'codegraph-index-path-'));
+    parent = path.join(root, 'parent');
+    child = path.join(parent, 'child');
+    fs.mkdirSync(child, { recursive: true });
+    fs.writeFileSync(path.join(parent, 'p.py'), 'def parent_only():\n    return 1\n');
+    fs.writeFileSync(path.join(child, 'c.py'), 'def child_only():\n    return 2\n');
+    const cg = CodeGraph.initSync(parent);
+    await cg.indexAll();
+    cg.close();
+  });
+
+  afterAll(() => {
+    fs.rmSync(root, { recursive: true, force: true });
+  });
+
+  it('refuses an explicit path that has no index of its own, naming the ancestor it would have rebuilt', () => {
+    const before = fs.statSync(path.join(parent, '.codegraph', 'codegraph.db')).mtimeMs;
+    const r = run(root, ['index', child, '--quiet']);
+    expect(r.status).toBe(1);
+    expect(r.out).toContain(`not initialized in ${child}`);
+    expect(r.out).toContain(parent);
+    // The parent's index was not touched.
+    expect(fs.statSync(path.join(parent, '.codegraph', 'codegraph.db')).mtimeMs).toBe(before);
+    expect(fs.existsSync(path.join(child, '.codegraph'))).toBe(false);
+  });
+
+  it('rebuilds the explicit path when it is initialized, and a bare `index` still resolves upward from a subdirectory', () => {
+    expect(run(root, ['index', parent, '--quiet']).status).toBe(0);
+    expect(run(child, ['index', '--quiet']).status).toBe(0);
+  });
+});

__tests__/cli-parse-warning.test.ts

@@ -0,0 +1,63 @@
+import { afterEach, beforeEach, describe, expect, it } from 'vitest';
+import { spawnSync } from 'child_process';
+import * as fs from 'fs';
+import * as os from 'os';
+import * as path from 'path';
+
+const BIN = path.resolve(__dirname, '../dist/bin/codegraph.js');
+const COLLAPSE_WARNING = 'parse produced no symbols (tree has errors)';
+const SOURCE = `const char* kTemplate = R"FILE_TEMPLATE_V1(
+struct Ignored { int v; };
+)FILE_TEMPLATE_V1";
+
+int after_the_raw_string(int x) {
+  return x + 1;
+}
+`;
+
+describe('CLI parse warnings (#1522)', () => {
+  let root: string;
+
+  beforeEach(() => {
+    root = fs.mkdtempSync(path.join(os.tmpdir(), 'codegraph-parse-warning-'));
+  });
+
+  afterEach(() => {
+    fs.rmSync(root, { recursive: true, force: true });
+  });
+
+  function run(args: string[]) {
+    const result = spawnSync(process.execPath, [BIN, ...args], {
+      cwd: root,
+      encoding: 'utf-8',
+      timeout: 20_000,
+      env: {
+        ...process.env,
+        CODEGRAPH_NO_DAEMON: '1',
+        CODEGRAPH_WASM_RELAUNCHED: '1',
+        CODEGRAPH_TELEMETRY: '0',
+        NO_COLOR: '1',
+      },
+    });
+    return { status: result.status, out: (result.stdout ?? '') + (result.stderr ?? '') };
+  }
+
+  it('shows a collapsed parse without failing, then stays quiet after a healthy re-index', () => {
+    const sourcePath = path.join(root, 'min.cpp');
+    fs.writeFileSync(sourcePath, SOURCE);
+
+    const collapsed = run(['init', '--yes']);
+    expect(collapsed.status, collapsed.out).toBe(0);
+    expect(collapsed.out).toContain('Indexed 1 files');
+    expect(collapsed.out).toContain(`min.cpp: ${COLLAPSE_WARNING}`);
+
+    fs.writeFileSync(sourcePath, SOURCE.replaceAll('FILE_TEMPLATE_V1', 'FILE_TEMPLATE_V'));
+    const healthy = run(['index']);
+    expect(healthy.status, healthy.out).toBe(0);
+    expect(healthy.out).not.toContain(COLLAPSE_WARNING);
+
+    const query = run(['query', 'after_the_raw_string']);
+    expect(query.status, query.out).toBe(0);
+    expect(query.out).toMatch(/function\s+after_the_raw_string/);
+  }, 30_000);
+});

__tests__/cpp-raw-string-delimiter-haserror.test.ts

@@ -0,0 +1,77 @@
+import { beforeAll, describe, expect, it } from 'vitest';
+import { extractFromSource } from '../src/extraction';
+import { getParser, initGrammars, loadGrammarsForLanguages } from '../src/extraction/grammars';
+
+function rawStringSource(delimiter: string): string {
+  return `const char* kTemplate = R"${delimiter}(
+struct Ignored { int v; };
+)${delimiter}";
+
+int after_the_raw_string(int x) {
+  return x + 1;
+}
+`;
+}
+
+describe('C++ raw-string delimiter parse collapse (#1522)', () => {
+  beforeAll(async () => {
+    await initGrammars();
+    await loadGrammarsForLanguages(['cpp', 'c']);
+  });
+
+  it('warns when a legal 16-character delimiter swallows every symbol', () => {
+    const result = extractFromSource('min.cpp', rawStringSource('FILE_TEMPLATE_V1'));
+
+    // The vendored tree-sitter-cpp scanner currently rejects the standard's
+    // maximum delimiter length, consuming the following function as ERROR.
+    expect(result.nodes.filter((n) => n.kind === 'function')).toEqual([]);
+    expect(result.nodes.map((n) => n.kind)).toEqual(['file']);
+    expect(result.errors).toEqual([
+      {
+        message:
+          'min.cpp: parse produced no symbols (tree has errors) — ' +
+          'the file is indexed but contributes nothing to the graph',
+        severity: 'warning',
+        code: 'parse_error',
+      },
+    ]);
+  });
+
+  it('extracts the function after a 15-character delimiter without warning', () => {
+    const result = extractFromSource('min.cpp', rawStringSource('FILE_TEMPLATE_V'));
+
+    expect(result.nodes.filter((n) => n.kind === 'function').map((n) => n.name))
+      .toEqual(['after_the_raw_string']);
+    expect(result.errors).toEqual([]);
+  });
+
+  it.each(['min.cpp', 'min.c', 'min.h'])('does not warn on a healthy include-only %s', (filePath) => {
+    const result = extractFromSource(filePath, '#include <stdio.h>\n#include <stdlib.h>\n');
+
+    expect(result.nodes.filter((n) => n.kind !== 'file' && n.kind !== 'import')).toEqual([]);
+    expect(result.errors).toEqual([]);
+  });
+
+  it('does not warn on a healthy empty file with zero symbols', () => {
+    const result = extractFromSource('empty.cpp', '');
+
+    expect(result.nodes.map((n) => n.kind)).toEqual(['file']);
+    expect(result.errors).toEqual([]);
+  });
+
+  it('does not warn on parse errors when a function survives', () => {
+    const source = 'int before_the_raw_string() { return 0; }\n' + rawStringSource('FILE_TEMPLATE_V1');
+    const tree = getParser('cpp')!.parse(source)!;
+    try {
+      expect(tree.rootNode.hasError).toBe(true);
+    } finally {
+      tree.delete();
+    }
+
+    const result = extractFromSource('min.cpp', source);
+
+    expect(result.nodes.filter((n) => n.kind === 'function').map((n) => n.name))
+      .toEqual(['before_the_raw_string']);
+    expect(result.errors).toEqual([]);
+  });
+});

__tests__/extraction.test.ts

@@ -1324,6 +1324,35 @@ pub struct User {
     expect(structNode?.name).toBe('User');
   });
 
+  it('should extract unit and tuple structs, not just brace structs', () => {
+    // A unit struct has no body field, but it IS a complete definition —
+    // Rust has no forward declarations. Skipping it dropped the type and
+    // every `impl Trait for UnitStruct` edge with it.
+    const code = `
+pub struct Unit;
+pub struct Tuple(pub u32);
+pub struct Brace { pub x: u32 }
+`;
+    const result = extractFromSource('shapes.rs', code);
+
+    const structs = result.nodes.filter((n) => n.kind === 'struct').map((n) => n.name).sort();
+    expect(structs).toEqual(['Brace', 'Tuple', 'Unit']);
+  });
+
+  it('should link impl Trait for a unit struct', () => {
+    const code = `
+pub struct Unit;
+pub trait Greet { fn hi(&self) -> String; }
+impl Greet for Unit { fn hi(&self) -> String { "unit".into() } }
+`;
+    const result = extractFromSource('greet.rs', code);
+
+    const unit = result.nodes.find((n) => n.kind === 'struct' && n.name === 'Unit');
+    expect(unit).toBeDefined();
+    const trait = result.nodes.find((n) => n.kind === 'trait' && n.name === 'Greet');
+    expect(trait).toBeDefined();
+  });
+
   it('should extract trait declarations', () => {
     const code = `
 pub trait Repository {

__tests__/kernel-rustlang-parity.test.ts

@@ -5,7 +5,8 @@
  * SAME ExtractionResult as the wasm TreeSitterExtractor — nodes, edges, and
  * unresolved refs compared as canonicalized multisets — over the checked-in
  * torture fixture (torture.rs: impl/trait quirks incl. generic / lifetime /
- * reference / scoped / generic-trait impl receivers (#1588), unit-struct skip, phantom
+ * reference / scoped / generic-trait impl receivers (#1588), unit structs
+ * (a bodiless struct IS a definition — both walkers mint a node), phantom
  * const identifiers, use-binding refs incl. nested groups + wildcard-emits-
  * nothing, chained-call re-encode, turbofish, Rocket route macros body-only,
  * fn-ref shapes, value-ref shadowing, attribute-broken docstrings, dead-code

codegraph-kernel/src/rustlang.rs

@@ -20,8 +20,7 @@
 //!   kind is always `variable`, no signature, and EVERY direct `identifier`
 //!   child mints a node (`const MAX: u32 = OTHER;` → two nodes, `MAX` + the
 //!   phantom `OTHER`). Top-level initializer values are never body-walked.
-//! - Unit structs (`struct Unit;`, no body field) mint NO node; `mod_item`
-//!   mints no module node and adds no QN prefix.
+//! - `mod_item` mints no module node and adds no QN prefix.
 //! - Chained-call re-encode is scoped_identifier-gated (`Foo::new().bar()` →
 //!   `Foo::new().bar`); a call through a field of the enclosing type keeps
 //!   the owner-field shape (`self.inner.run()` → `self.inner.run`, #1585);
@@ -590,10 +589,12 @@ impl<'t> Walker<'t> {
         self.stack.pop();
     }
 
-    /// Extract a Rust struct or union with a body; unit structs remain skipped.
+    /// Extract a Rust struct or union — the body field is OPTIONAL. A unit
+    /// struct (`struct U;`) has no body and is still a complete definition,
+    /// so it mints a node with no members; tuple structs' ordered_field_declaration_list
+    /// is a body. Mirrors the TS reference's `allowBodilessStruct`.
     fn extract_aggregate(&mut self, node: Node<'t>, kind: &'static str) {
         stack_guard!();
-        let Some(body) = node.child_by_field_name("body") else { return };
         let name = self.extract_name(node);
         let extra = Extra {
             docstring: preceding_docstring(node, self.src),
@@ -603,6 +604,10 @@ impl<'t> Walker<'t> {
         let Some(row) = self.create_node(kind, &name, node, extra) else { return };
         self.extract_inheritance(node, row);
 
+        // Unit structs have no body to walk — the node itself is the whole
+        // definition.
+        let Some(body) = node.child_by_field_name("body") else { return };
+
         self.stack.push(Scope { row, kind, name });
         for i in 0..body.named_child_count() {
             if let Some(c) = body.named_child(i) {

docs/design/rust-lang-kernel-port-checklist.md

@@ -140,7 +140,7 @@ undefined; **no isConst means `const_item`/`static_item` extract as kind
 |---|---|---|
 | `function_item` (top level) | functionTypes, tree-sitter.ts:994 → extractFunction:1517 | not inside class-like at file scope → extractFunction; **first line of extractFunction (1522): if getReceiverType returns a value → extractMethod instead** (this is how impl-block fns become methods — impl_item does NOT push a scope) |
 | `function_signature_item` | same | in a trait body (trait pushed, class-like) → extractMethod; no `body` field → no body walk |
-| `struct_item` | structTypes:1059 → extractStruct:1869 | `body` field required: **unit structs `struct Unit;` have no body → NO node minted** (1876, `record_declaration` exemption is C#-only). Tuple structs have body `ordered_field_declaration_list` → extracted. `field_declaration` children make NO nodes (rust has no fieldTypes) — visitNode recurses into them and finds nothing |
+| `struct_item` | structTypes:1059 → extractStruct:1869 | ~~`body` field required: unit structs `struct Unit;` have no body → NO node minted~~ — **superseded: Rust now sets `allowBodilessStruct`, so `struct Unit;` mints a node with no members.** Rust has no forward declarations, so the bodiless skip (meant for C/C++) never applied here; the `record_declaration` exemption is the C# form of the same carve-out. Tuple structs have body `ordered_field_declaration_list` → extracted. `field_declaration` children make NO nodes (rust has no fieldTypes) — visitNode recurses into them and finds nothing |
 | `enum_item` | enumTypes:1064 → extractEnum:1914 | body `enum_variant_list`; `enum_variant` children → extractEnumMembers:1958 — **`name` field path: one `enum_member` node from `getChildByField(node,'name')`, then return** (variant payload bodies `B(u32)` / `C { x }` are never walked). Non-variant children (e.g. `attribute_item`) → visitNode (no-op) |
 | `trait_item` | interfaceTypes:1054 → extractInterface:1834 | kind `'trait'` (interfaceKind); extractInheritance sees the `trait_bounds` child (see below); body `declaration_list` children visited with the trait pushed → fn items become methods with QN `Trait::name` via nodeStack |
 | `impl_item` | dedicated branch:1273-1276 → extractRustImplItem:5690 | emits the implements back-reference (below); **skipChildren stays false** → the `declaration_list` is then visited normally by the loop at 1295 (that's how impl members are reached; impl pushes NOTHING on the nodeStack) |
@@ -490,7 +490,7 @@ inner `array_expression`, but `const CB: fn() = handler;` captures nothing
 ## Gates (per plan §5, no exceptions)
 
 - **Torture fixture `torture.rs`** (+ CRLF variant, derived in-memory), pinning
-  at minimum: unit struct (NO node) / tuple struct / field struct; enum with
+  at minimum: unit struct (node, no members) / tuple struct / field struct; enum with
   unit+tuple+struct variants; trait with supertraits incl. a SCOPED one
   (`fmt::Debug` — dropped) + `function_signature_item` + default method +
   associated type/const (no node; const value call attributes to trait);

src/bin/codegraph.ts

@@ -378,6 +378,7 @@ type IndexResult = {
  */
 function printIndexResult(clack: typeof import('@clack/prompts'), result: IndexResult, projectPath?: string): void {
   const hasErrors = result.filesErrored > 0;
+  const parseWarnings = result.errors.filter((e) => e.code === 'parse_error' && e.severity === 'warning');
 
   // Surface non-file-level failures (e.g. lock-acquisition failure
   // when another indexer is running) before the file-count branches.
@@ -403,6 +404,10 @@ function printIndexResult(clack: typeof import('@clack/prompts'), result: IndexR
       clack.log.success(`Indexed ${formatNumber(result.filesIndexed)} files`);
     }
     clack.log.info(`${formatNumber(result.nodesCreated)} nodes, ${formatNumber(result.edgesCreated)} edges in ${formatDuration(result.durationMs)}`);
+    // Warning-only parse failures keep indexing successful, but must be visible.
+    for (const warning of parseWarnings) {
+      clack.log.warn(warning.message);
+    }
     // A PARTIAL index (files silently dropped mid-pipeline) must not pass
     // as a clean run — it's the difference between "indexed the repo" and
     // "indexed most of the repo, quietly". Only the completeness
@@ -791,7 +796,13 @@ program
   .option('-q, --quiet', 'Suppress progress output')
   .option('-v, --verbose', 'Show detailed worker lifecycle and memory info')
   .action(async (pathArg: string | undefined, options: { force?: boolean; quiet?: boolean; verbose?: boolean }) => {
-    const projectPath = resolveProjectPath(pathArg);
+    // An EXPLICIT path names the project to rebuild — it is never a hint to go
+    // looking for one. resolveProjectPath walks up to the nearest initialized
+    // ancestor, which is right for `codegraph query` run from a subdirectory,
+    // but for a full re-index it silently rebuilt the parent's graph under a
+    // normal "Done" when <path> had no index of its own (#1524). Only a bare
+    // `codegraph index` (cwd) may resolve upward.
+    const projectPath = pathArg ? path.resolve(pathArg) : resolveProjectPath();
 
     try {
       // Don't (re)index your home directory / a filesystem root (#845). --force
@@ -804,7 +815,12 @@ program
 
       if (!isInitialized(projectPath)) {
         error(`CodeGraph not initialized in ${projectPath}`);
-        info('Run "codegraph init" first');
+        const ancestor = pathArg ? resolveProjectPath(pathArg) : projectPath;
+        if (ancestor !== projectPath) {
+          info(`The nearest initialized project is ${ancestor} — pass that path to rebuild it, or run "codegraph init" in ${projectPath} to index it on its own.`);
+        } else {
+          info('Run "codegraph init" first');
+        }
         process.exit(1);
       }
 

src/extraction/languages/rust.ts

@@ -81,6 +81,9 @@ export const rustExtractor: LanguageExtractor = {
   methodTypes: ['function_item', 'function_signature_item'],
   interfaceTypes: ['trait_item'],
   structTypes: ['struct_item'],
+  // `struct Unit;` is a unit struct — a complete definition with no body
+  // field, not a forward declaration. Rust has no forward declarations.
+  allowBodilessStruct: true,
   // Unions share struct member syntax and impl attachment, but retain their
   // distinct semantic kind in the graph.
   unionTypes: ['union_item'],

src/extraction/tree-sitter-types.ts

@@ -187,6 +187,19 @@ export interface LanguageExtractor {
    * bodiless class IS complete (Kotlin `class Empty`, Scala `case object`). (#1093)
    */
   skipBodilessClass?: boolean;
+  /**
+   * Keep a bodiless struct node — it IS a complete definition, not a forward
+   * declaration. Set only for languages where a bodiless `struct` is complete:
+   * Rust's unit struct (`struct Unit;`). Leave unset for C/C++, where
+   * `struct Foo;` is a forward declaration.
+   *
+   * Opposite polarity from `skipBodilessClass` (#1093) because the defaults
+   * differ: a bodiless CLASS is kept unless a language opts into skipping,
+   * a bodiless STRUCT is skipped unless a language opts into keeping. The
+   * hardcoded C# `record_declaration` carve-out (#831) is the same situation
+   * predating this flag.
+   */
+  allowBodilessStruct?: boolean;
   /** NodeKind to use for interface-like declarations (Rust: 'trait'). Default: 'interface' */
   interfaceKind?: NodeKind;
 

src/extraction/tree-sitter.ts

@@ -584,6 +584,18 @@ export class TreeSitterExtractor {
 
       if (packageNodeId) this.nodeStack.pop();
       this.nodeStack.pop();
+
+      // hasError is routine for several grammars; warn only when no symbols survived.
+      const symbolCount = this.nodes.filter((n) => n.kind !== 'file').length;
+      if (this.tree?.rootNode.hasError && symbolCount === 0) {
+        this.errors.push({
+          message:
+            `${this.filePath}: parse produced no symbols (tree has errors) — ` +
+            `the file is indexed but contributes nothing to the graph`,
+          severity: 'warning',
+          code: 'parse_error',
+        });
+      }
     } catch (error) {
       const msg = error instanceof Error ? error.message : String(error);
 
@@ -1962,8 +1974,16 @@ export class TreeSitterExtractor {
     // Skip forward declarations and type references (no body = not a definition)
     // — EXCEPT C# positional records (`record struct M(decimal Amount);`),
     // complete definitions with no body block. (#831)
+    //
+    // `allowBodilessStruct` is the per-language escape hatch for the same
+    // situation: a bodiless struct that IS a complete definition (Rust's unit
+    // struct `struct Unit;`). Opposite polarity from `skipBodilessClass`
+    // (#1093) because the two defaults differ — a bodiless CLASS is kept
+    // unless a language opts into skipping, a bodiless STRUCT is skipped
+    // unless a language opts into keeping.
     const body = getChildByField(node, this.extractor.bodyField);
-    if (!body && node.type !== 'record_declaration') return;
+    if (!body && node.type !== 'record_declaration' && !this.extractor.allowBodilessStruct)
+      return;
 
     const name = extractName(node, this.source, this.extractor);
     const docstring = getPrecedingDocstring(node, this.source);