fix(extraction): recover heavily-reflected Unreal Engine C++ classes (in-body reflection macros) (#1158)

Heavily-reflected UE C++ classes (`UCharacterMovementComponent`, `AActor`, `UWorld`, …) were dropped from the index: in-body no-semicolon reflection macros (`UPROPERTY`/`UFUNCTION`/`GENERATED_BODY`/`UE_DEPRECATED_*`), member-level `*_API` prefixes, and mid-line `UMETA`/`UPARAM`/`UE_DEPRECATED` accumulate tree-sitter parse errors until the enclosing class_specifier collapses into an ERROR node. Three offset-preserving, C++-only pre-parse passes (`blankCppAnnotationMacroCalls`, `blankCppApiPrefixMacros`, `blankCppInlineAnnotationMacros`) blank the markup before parsing so the class survives.

Validated on the real Epic engine headers (CharacterMovementComponent.h / Actor.h / World.h): each main class + its base clause goes from DROPPED on main to recovered with the fix.

Closes #1160.

Thanks @luoyxy for the report and root-cause analysis.

CHANGELOG.md

@@ -48,6 +48,9 @@ and adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 - A stuck git command can no longer hang CodeGraph indefinitely. The git checks behind worktree detection and git-hook setup, and the installer's optional `npm install -g` step, now time out and fail gracefully instead of blocking forever — this matters most for the background MCP server, where an unbounded git hang (network filesystems, a wedged fsmonitor) could previously freeze it long enough for the safety watchdog to kill it. Thanks @inth3shadows for the report. (#1139)
 - The context hook's new plain-words matching works immediately on projects indexed by an older CodeGraph version. The word lookup it relies on is built at index time, so a project indexed before the upgrade had an empty one, and the hook would silently find nothing until something else happened to refresh the index; the hook now fills it in on first use (a one-time step — normally the background MCP server's startup catch-up gets there first). Thanks @inth3shadows for the report. (#1142)
 - Several accuracy fixes to the plain-words matching: a renamed symbol (for example a NestJS route after its module prefix is applied) stays findable under its new name (#1141); a word that only appears in your code as an import statement's package name is no longer presented as a matched symbol (#1144); plural words no longer generate garbled lookup keys ("services" no longer also looks up "servic") (#1145); and a name matching both the singular and plural of one word can no longer squeeze out a genuine two-word match (#1146). Thanks @inth3shadows for the reports.
+- Heavily-reflected Unreal Engine C++ classes are no longer dropped from the index. Reflection markup that decorates members — `UPROPERTY(...)`, `UFUNCTION(...)`, `UCLASS(...)`, `GENERATED_BODY()`, `UE_DEPRECATED_*(...)`, `DECLARE_DELEGATE_*(...)` — are no-semicolon macro calls that tree-sitter doesn't recognize, so each drops into error recovery; in a big class the errors pile up until the whole `class_specifier` collapses and the class, its base clause, and its members vanish (`UCharacterMovementComponent`, with ~240 such macros, disappeared entirely, breaking every subclass/type-hierarchy and blast-radius query that went through it). These line-leading annotation macros are now blanked (offset-preserving) before parsing so the class survives. Thanks @luoyxy for the report and root-cause analysis. (#1093 follow-up)
+- Unreal Engine members and methods prefixed by an export/visibility macro are no longer lost. The `*_API` macro doesn't only sit on the class header — it prefixes almost every exported member of a large UE class (`ENGINE_API virtual void Tick(...)`, `static ENGINE_API void AddReferencedObjects(...)`); the parser read the macro as an extra type token and each such declaration fell into error recovery, so on headers like `Actor.h` and `World.h` hundreds of return types piled up as orphan errors and could still tip the class into collapse. Member/method-level `*_API` / `*_EXPORT` / `*_ABI` macros (Unreal, Qt/Boost, LLVM) are now blanked before parsing, mirroring the existing class-header recovery. (#1093 follow-up)
+- Unreal Engine annotation macros that appear mid-line — an enum value's `UMETA(DisplayName=...)`, a parameter's `UPARAM(ref)`, or a deprecation tag wedged into a `using` alias (`using FOnNetTick UE_DEPRECATED(5.5, "...") = ...;`, which alone collapsed `UWorld` in `World.h`) — are now stripped too. These sit in positions the line-leading recovery structurally can't reach, and a single one could take down the surrounding enum or class. They are matched by an Unreal-only name list (`UMETA`, `UPARAM`, `UE_DEPRECATED*`) so no standard-C++ or other-library code is affected. Together these three fixes recover the main class of every large Unreal Engine header tested (`Actor`, `ActorComponent`, `SkeletalMeshComponent`, `World`, `LightComponent`, `CharacterMovementComponent`). (#1093 follow-up)
 
 ## [1.2.0] - 2026-07-02
 

__tests__/extraction.test.ts

@@ -11,7 +11,7 @@ import * as os from 'os';
 import { CodeGraph } from '../src';
 import { extractFromSource, scanDirectory, buildDefaultIgnore, discoverEmbeddedRepoRoots, buildScopeIgnore } from '../src/extraction';
 import { detectLanguage, isLanguageSupported, getSupportedLanguages, initGrammars, loadAllGrammars, isSourceFile } from '../src/extraction/grammars';
-import { stripCppTemplateArgs, blankCppExportMacros, blankCppInlineMacros, blankMetalAttributes, blankCudaConstructs, recoverMangledCppName } from '../src/extraction/languages/c-cpp';
+import { stripCppTemplateArgs, blankCppExportMacros, blankCppInlineMacros, blankMetalAttributes, blankCudaConstructs, blankCppAnnotationMacroCalls, blankCppApiPrefixMacros, blankCppInlineAnnotationMacros, recoverMangledCppName } from '../src/extraction/languages/c-cpp';
 import { normalizePath } from '../src/utils';
 
 beforeAll(async () => {
@@ -3112,6 +3112,179 @@ kernel void computeBlur(texture2d<float, access::read> inTexture [[texture(0)]],
     });
   });
 
+  describe('C++ in-body reflection-macro annotations do not collapse the class (UE)', () => {
+    // Unreal reflection markup — `UPROPERTY(...)`, `UFUNCTION(...)`,
+    // `GENERATED_BODY()`, `UE_DEPRECATED_*(...)`, `DECLARE_DELEGATE_*(...)` — are
+    // no-semicolon macro CALLS decorating members. tree-sitter doesn't know they
+    // are macros, so each drops into error recovery; in a heavily-reflected class
+    // the errors accumulate until the enclosing class_specifier can't close and
+    // the whole class (its base clause and members) collapses into an ERROR node
+    // and disappears from the graph. blankCppAnnotationMacroCalls strips them,
+    // offset-preserving, so the class parses normally.
+    it('recovers a heavily-reflected class with multiple inheritance + members', () => {
+      const code = `UCLASS(MinimalAPI)
+class UMyMovement : public UPawnMovementComponent, public IRVOAvoidanceInterface, public INetworkPredictionInterface
+{
+\tGENERATED_BODY()
+public:
+\tUE_DEPRECATED_FORGAME(5.0, "Deprecated; note the commas, and (parens) inside the string")
+\tUPROPERTY(Category="Move", EditAnywhere, BlueprintReadWrite, meta=(ClampMin="0", UIMin="0"))
+\tfloat MaxWalkSpeed;
+
+\tUFUNCTION(BlueprintCallable, Category="Move")
+\tfloat ComputeSpeed() const { return MaxWalkSpeed * 2.0f; }
+};
+`;
+      const result = extractFromSource('movement.cpp', code);
+      const cls = result.nodes.find((n) => n.kind === 'class' && n.name === 'UMyMovement');
+      expect(cls).toBeTruthy();
+      // The class body parses, so its inline method definition is extracted too —
+      // proof the class_specifier closed instead of collapsing into an ERROR node.
+      expect(result.nodes.some((n) => n.name === 'ComputeSpeed')).toBe(true);
+      // The base clause survives (inheritance queries keep working).
+      expect(
+        result.unresolvedReferences.find(
+          (r) => r.referenceKind === 'extends' && r.referenceName === 'UPawnMovementComponent'
+        )
+      ).toBeTruthy();
+    });
+
+    it('strips line-leading no-semicolon ALL-CAPS calls, offset-preserving', () => {
+      const inp = `\tUPROPERTY(EditAnywhere, meta=(ClampMin="0"))\n\tfloat X;\n`;
+      const out = blankCppAnnotationMacroCalls(inp);
+      expect(out.length).toBe(inp.length); // every byte offset preserved
+      expect(out).not.toContain('UPROPERTY');
+      expect(out).toContain('float X;');
+      // A macro whose args carry commas/parens inside a string still balances.
+      const inp2 = `UE_DEPRECATED_FORGAME(5.0, "a, b (c)")\nUPROPERTY(Foo)\nfloat Y;\n`;
+      const out2 = blankCppAnnotationMacroCalls(inp2);
+      expect(out2.length).toBe(inp2.length);
+      expect(out2).not.toContain('UE_DEPRECATED_FORGAME');
+      expect(out2).not.toContain('UPROPERTY');
+      expect(out2).toContain('float Y;');
+    });
+
+    it('does NOT blank expression / condition / statement / init-list macro uses', () => {
+      for (const c of [
+        'void f() {\n\tif (CHECK_FLAG(x)) { g(); }\n}',   // condition — not line-leading
+        'void f() {\n\tLOG_MESSAGE("hi");\n}',             // statement call — trailing ;
+        'C::C()\n\t: MEMBER_A(1)\n\t, MEMBER_B(2)\n{}',    // init-list — comma / not line-leading
+        'C::C() :\n\tMEMBER_A(1),\n\tMEMBER_B(2)\n{}',     // init-list wrapped — trailing , / {
+        'auto y =\n\tMAKE_THING(a) + 1;',                  // line-leading but an expression fragment
+      ]) {
+        expect(blankCppAnnotationMacroCalls(c)).toBe(c);
+      }
+    });
+  });
+
+  describe('C++ member/method-level export macros do not orphan declarations (UE)', () => {
+    // The `*_API` visibility macro doesn't only prefix the class header — it
+    // prefixes almost every exported member/method of a big UE class
+    // (`ENGINE_API virtual void Tick(…)`, `static ENGINE_API void Foo(…)`).
+    // blankCppExportMacros only recovers the class-HEADER form; without blanking
+    // the member form, tree-sitter reads `MACRO <ret> <name>(` as an extra type
+    // token and each declaration drops into error recovery.
+    it('recovers a class + base + members when members are *_API-prefixed', () => {
+      const code = `class ENGINE_API AActor : public UObject
+{
+\tGENERATED_BODY()
+public:
+\tENGINE_API virtual void Tick(float DeltaSeconds);
+\tstatic ENGINE_API void AddReferencedObjects(int32 Count);
+\tENGINE_API float GetLifeSpan() const { return LifeSpan; }
+};
+`;
+      const result = extractFromSource('actor.cpp', code);
+      expect(result.nodes.some((n) => n.kind === 'class' && n.name === 'AActor')).toBe(true);
+      // The inline definition (its body prefixed by ENGINE_API) is extracted —
+      // proof the class_specifier closed instead of collapsing into an ERROR.
+      expect(result.nodes.some((n) => n.name === 'GetLifeSpan')).toBe(true);
+      // The base clause survives (inheritance queries keep working).
+      expect(
+        result.unresolvedReferences.find(
+          (r) => r.referenceKind === 'extends' && r.referenceName === 'UObject'
+        )
+      ).toBeTruthy();
+    });
+
+    it('blanks only the suffix macro before a declaration, offset-preserving', () => {
+      const inp = `ENGINE_API void Tick();\nstatic MYMOD_EXPORT int32 X;\nLLVM_ABI bool Y();\n`;
+      const out = blankCppApiPrefixMacros(inp);
+      expect(out.length).toBe(inp.length); // every byte offset preserved
+      expect(out).not.toContain('ENGINE_API');
+      expect(out).not.toContain('MYMOD_EXPORT');
+      expect(out).not.toContain('LLVM_ABI');
+      expect(out).toContain('void Tick();');
+      expect(out).toContain('int32 X;');
+      expect(out).toContain('bool Y();');
+      expect(out).toMatch(/static\s+int32 X;/); // `static` kept, only the macro blanked
+    });
+
+    it('does NOT blank an *_API token used as a value or in non-declaration position', () => {
+      for (const c of [
+        'int x = SOME_API;',              // rvalue — trailing ;
+        'if (mode == FOO_API) { g(); }',  // comparison — trailing )
+        'return DEFAULT_API, other;',     // comma operand
+        'auto v = NS_API::Make();',       // qualified name — trailing ::
+        'x = A_API + B_API;',             // operands of + / trailing ;
+      ]) {
+        expect(blankCppApiPrefixMacros(c)).toBe(c);
+      }
+    });
+
+    it('leaves a genuine _API-suffixed word alone when it is itself the name', () => {
+      // A longer word merely CONTAINING _API (not ending in it) must not match.
+      const inp = 'FOO_APIENTRY handler;';
+      expect(blankCppApiPrefixMacros(inp)).toBe(inp);
+    });
+  });
+
+  describe('C++ mid-line UE annotation macros do not collapse the enum/class (UE)', () => {
+    // UMETA / UPARAM / UE_DEPRECATED can sit MID-LINE (not line-leading), where
+    // blankCppAnnotationMacroCalls structurally can't reach them: an enum value's
+    // `UMETA(...)`, or a deprecation tag wedged into a class-scope `using`
+    // (`using X UE_DEPRECATED(5.5, "…") = …;`) — which alone collapsed UWorld in
+    // World.h. blankCppInlineAnnotationMacros strips them, offset-preserving.
+    it('recovers a class whose in-body using-alias carries a mid-line UE_DEPRECATED', () => {
+      const code = `class ENGINE_API UWorld : public UObject
+{
+\tGENERATED_BODY()
+public:
+\tusing FOnNetTickEvent UE_DEPRECATED(5.5, "use TMulticastDelegate<void(float)>") = TMulticastDelegate<void(float)>;
+\tENGINE_API float GetTimeSeconds() const { return TimeSeconds; }
+};
+`;
+      const result = extractFromSource('world.cpp', code);
+      expect(result.nodes.some((n) => n.kind === 'class' && n.name === 'UWorld')).toBe(true);
+      // The member after the poison using-alias is reached — the class closed.
+      expect(result.nodes.some((n) => n.name === 'GetTimeSeconds')).toBe(true);
+      expect(
+        result.unresolvedReferences.find(
+          (r) => r.referenceKind === 'extends' && r.referenceName === 'UObject'
+        )
+      ).toBeTruthy();
+    });
+
+    it('blanks mid-line UMETA/UPARAM/UE_DEPRECATED with balanced parens, offset-preserving', () => {
+      const inp = `enum class EMode : uint8 {\n\tWalk UMETA(DisplayName="Walk (fast), safe"),\n\tRun\n};\n`;
+      const out = blankCppInlineAnnotationMacros(inp);
+      expect(out.length).toBe(inp.length);
+      expect(out).not.toContain('UMETA');
+      expect(out).toContain('Walk');
+      expect(out).toContain('Run');
+      const inp2 = `void F(UPARAM(ref) int& x) {}\n`;
+      const out2 = blankCppInlineAnnotationMacros(inp2);
+      expect(out2.length).toBe(inp2.length);
+      expect(out2).not.toContain('UPARAM');
+      expect(out2).toContain('int& x');
+    });
+
+    it('does NOT touch source without those UE-only macro names', () => {
+      const c = 'enum class E { A, B };\nvoid metadata(int meta) { return; }\n';
+      expect(blankCppInlineAnnotationMacros(c)).toBe(c);
+    });
+  });
+
   describe('CUDA extraction (#387)', () => {
     // CUDA parses with the C++ grammar. Three CUDA-only shapes misparse:
     // execution-space specifiers (`__global__ void f(…)`) shunt the real return

src/extraction/languages/c-cpp.ts

@@ -433,6 +433,172 @@ export function blankMetalAttributes(source: string): string {
   return source.replace(METAL_ATTRIBUTE_RE, (m) => ' '.repeat(m.length));
 }
 
+/**
+ * Blank annotation-style macro invocations that decorate a declaration but carry
+ * NO terminating semicolon — the pervasive Unreal-Engine reflection markup
+ * (`UPROPERTY(...)`, `UFUNCTION(...)`, `UCLASS(...)`, `GENERATED_BODY()`,
+ * `UE_DEPRECATED_FORGAME(...)`, `DECLARE_DELEGATE_*(...)`, …) that sits on its
+ * own line right before a member/type. tree-sitter's C++ grammar doesn't know
+ * these are macros, so each one drops into error recovery; in a big reflected
+ * class (`CharacterMovementComponent.h` has ~240 of them) the errors accumulate
+ * until the enclosing `class_specifier` can't close and collapses into an ERROR
+ * node — the whole class definition, its members, and its `extends` edges vanish
+ * from the graph. Neither `blankCppExportMacros` (class-header export macros) nor
+ * `blankCppInlineMacros` (return-type inline specifiers) touches these in-body
+ * markup macros. Replacing each with equal-length spaces preserves every byte
+ * offset (so line/column stay exact) and the class then parses normally.
+ *
+ * Deliberately name-list-FREE — UE alone has hundreds of such macros and projects
+ * add their own — so it keys on structure, not a curated list, matched tightly to
+ * avoid touching legitimate C++:
+ *  - the macro must be the FIRST non-whitespace token on its line (`^[ \t]*`),
+ *    which is where declaration markup lives — so a macro used inside an
+ *    expression or condition (`if (CHECK(x))`, `x = MACRO(a) + b`) is never
+ *    matched (it isn't line-leading);
+ *  - the name must be ALL-CAPS (`[A-Z][A-Z0-9_]{2,}`), since ordinary
+ *    function/type names called at line start are lower/mixed case;
+ *  - the char after the balanced `(...)` must START A DECLARATION — a letter,
+ *    `_`, `~` (destructor), or `#` (a following directive). Declaration markup is
+ *    always followed by the thing it decorates (`UPROPERTY(...)\n float X;`,
+ *    `UE_DEPRECATED(...) UPROPERTY(...)`), whereas a statement call is followed by
+ *    `;` (`FOO(x);`), an init-list item by `,`/`{`, and an expression fragment by
+ *    an operator (`MAKE(a) + 1`) — all rejected. String/char literals inside the
+ *    args are skipped so an embedded `)` can't mis-close the balance.
+ *
+ * C++-only (wired into cppExtractor). A blanked macro inside a block comment is
+ * harmless (comments don't parse), and the rare line-leading no-semicolon
+ * ALL-CAPS call that isn't markup only loses that one annotation, never a whole
+ * class.
+ */
+export function blankCppAnnotationMacroCalls(source: string): string {
+  if (!/^[ \t]*[A-Z][A-Z0-9_]{2,}\s*\(/m.test(source)) return source;
+  const chars = source.split('');
+  const re = /^([ \t]*)([A-Z][A-Z0-9_]{2,})(\s*)\(/gm;
+  let m: RegExpExecArray | null;
+  while ((m = re.exec(source)) !== null) {
+    const macroStart = m.index + (m[1] ?? '').length; // skip leading indent
+    let i = m.index + m[0].length - 1; // index of the opening '('
+    let depth = 0;
+    let end = -1;
+    for (; i < source.length; i++) {
+      const c = source[i];
+      if (c === '"' || c === "'") {
+        const quote = c;
+        i++;
+        while (i < source.length && source[i] !== quote) {
+          if (source[i] === '\\') i++;
+          i++;
+        }
+        continue;
+      }
+      if (c === '(') depth++;
+      else if (c === ')') {
+        depth--;
+        if (depth === 0) { end = i + 1; break; }
+      }
+    }
+    if (end < 0) continue;
+    let j = end;
+    while (j < source.length && /\s/.test(source[j] as string)) j++;
+    const after = source[j];
+    // Only markup is followed by the declaration it decorates; a statement call
+    // (`;`), init-list item (`,`/`{`), or expression fragment (operator) is not.
+    if (!after || !/[A-Za-z_~#]/.test(after)) continue;
+    for (let k = macroStart; k < end; k++) {
+      if (chars[k] !== '\n' && chars[k] !== '\r') chars[k] = ' ';
+    }
+    re.lastIndex = end;
+  }
+  return chars.join('');
+}
+
+/**
+ * Blank an export/visibility macro sitting in front of a *member* or *method*
+ * declaration inside a class/namespace (`ENGINE_API virtual void Tick(…)`,
+ * `static ENGINE_API void AddReferencedObjects(…)`, `UE_API FVector GetVel()
+ * const`), before parsing. `blankCppExportMacros` only recovers the macro in a
+ * `class MACRO Name` *header*; the very same macro also prefixes almost every
+ * exported member of a big Unreal-Engine class, and tree-sitter — not knowing
+ * it's a macro — reads `MACRO <return-type> <name>(` as an extra type token and
+ * drops each such declaration into error recovery. In a heavily-exported header
+ * (`Actor.h`, `World.h`, …) hundreds of these accumulate: the return types pile
+ * up as orphan ERROR tokens and, combined with other markup, can still tip the
+ * enclosing class into collapse. Replacing the macro with equal-length spaces
+ * preserves every byte offset (line/column stay exact) and each member parses
+ * as an ordinary declaration.
+ *
+ * Matched tightly so it can't touch the same token used as a value
+ * (`int x = SOME_API;`, `if (mode == FOO_API)`): the token must be ALL-CAPS AND
+ * end in the conventional visibility-macro suffix `_API` / `_EXPORT` / `_ABI`
+ * (Unreal `*_API`, Qt/Boost `*_EXPORT`, LLVM `*_ABI`) — ordinary identifiers
+ * effectively never carry these suffixes — and must be immediately followed by
+ * whitespace then a declaration token (`\s+[A-Za-z_]`: a type, `virtual`,
+ * `static`, or the name). A value use is instead followed by `;`, `)`, `,`,
+ * `=`, `::`, or an operator, all of which fail the look-ahead. C++-only (wired
+ * into cppExtractor).
+ */
+const CPP_API_PREFIX_RE = /\b[A-Z][A-Z0-9_]*(?:_API|_EXPORT|_ABI)\b(?=\s+[A-Za-z_])/g;
+export function blankCppApiPrefixMacros(source: string): string {
+  if (!/_(?:API|EXPORT|ABI)\b/.test(source)) return source;
+  return source.replace(CPP_API_PREFIX_RE, (m) => ' '.repeat(m.length));
+}
+
+/**
+ * Blank an Unreal-Engine annotation macro that appears MID-LINE (not
+ * line-leading, so `blankCppAnnotationMacroCalls` never sees it) inside a
+ * declaration: an enum value's `UMETA(DisplayName="…")`, a parameter's
+ * `UPARAM(ref)`, or a deprecation tag wedged into a `using`/member declaration
+ * (`using FOnNetTick UE_DEPRECATED(5.5, "…") = TMulticastDelegate<void(float)>;`
+ * in `World.h`, which otherwise collapses `UWorld`). tree-sitter can't reconcile
+ * these embedded macro calls and drops into error recovery, and a mid-line one
+ * inside a big enum or a class-scope `using` can cascade into the whole enum /
+ * class being lost. Replacing the entire `MACRO(...)` (balanced parens, string
+ * literals skipped so an embedded `)` can't mis-close) with equal-length spaces
+ * preserves every byte offset and the declaration parses normally.
+ *
+ * Keyed on an explicit UE-only name list (`UMETA`, `UPARAM`, and the
+ * `UE_DEPRECATED*` family) — these identifiers are exclusive to Unreal's
+ * reflection layer and appear in no standard-C++ or other-library code, so
+ * blanking them is zero-risk to non-UE sources. (The line-LEADING forms of
+ * `UE_DEPRECATED(...)` are already handled by `blankCppAnnotationMacroCalls`;
+ * this covers the mid-line forms it structurally can't.) C++-only.
+ */
+const CPP_INLINE_ANNOTATION_RE = /\b(?:UMETA|UPARAM|UE_DEPRECATED\w*)\s*\(/g;
+export function blankCppInlineAnnotationMacros(source: string): string {
+  if (!/\b(?:UMETA|UPARAM|UE_DEPRECATED)/.test(source)) return source;
+  const chars = source.split('');
+  const re = new RegExp(CPP_INLINE_ANNOTATION_RE.source, 'g');
+  let m: RegExpExecArray | null;
+  while ((m = re.exec(source)) !== null) {
+    let i = m.index + m[0].length - 1; // index of the opening '('
+    let depth = 0;
+    let end = -1;
+    for (; i < source.length; i++) {
+      const c = source[i];
+      if (c === '"' || c === "'") {
+        const quote = c;
+        i++;
+        while (i < source.length && source[i] !== quote) {
+          if (source[i] === '\\') i++;
+          i++;
+        }
+        continue;
+      }
+      if (c === '(') depth++;
+      else if (c === ')') {
+        depth--;
+        if (depth === 0) { end = i + 1; break; }
+      }
+    }
+    if (end < 0) continue;
+    for (let k = m.index; k < end; k++) {
+      if (chars[k] !== '\n' && chars[k] !== '\r') chars[k] = ' ';
+    }
+    re.lastIndex = end;
+  }
+  return chars.join('');
+}
+
 /**
  * Blank CUDA-specific constructs before parsing `.cu`/`.cuh` files (parsed with
  * the C++ grammar). Three shapes tree-sitter-cpp can't reconcile, each replaced
@@ -515,13 +681,18 @@ function looksLikeCudaSource(source: string): boolean {
   );
 }
 
-/** C/C++ source pre-processing before tree-sitter: recover both macro-annotated
- * class definitions and macro-prefixed function definitions — plus the non-C++
+/** C/C++ source pre-processing before tree-sitter: recover macro-annotated class
+ * definitions, macro-prefixed function definitions, macro-prefixed members, and
+ * macro-decorated members (Unreal-Engine reflection markup) — plus the non-C++
  * surface of the dialects parsed with the C++ grammar: `.metal` MSL attribute
  * annotations, and CUDA specifiers + launch syntax (by `.cu`/`.cuh` extension
  * or by content, for CUDA living in `.h`/`.hpp` headers). Offset-preserving. */
 function preParseCppSource(source: string, filePath?: string): string {
-  const blanked = blankCppInlineMacros(blankCppExportMacros(source));
+  const blanked = blankCppAnnotationMacroCalls(
+    blankCppInlineAnnotationMacros(
+      blankCppApiPrefixMacros(blankCppInlineMacros(blankCppExportMacros(source)))
+    )
+  );
   const lower = filePath ? filePath.toLowerCase() : '';
   if (lower.endsWith('.metal')) return blankMetalAttributes(blanked);
   if (lower.endsWith('.cu') || lower.endsWith('.cuh') || looksLikeCudaSource(source)) {