feat(extraction): make MAX_FILE_SIZE configurable via CODEGRAPH_MAX_FILE_SIZE env var

__tests__/extraction.test.ts

@@ -9,7 +9,7 @@ import * as fs from 'fs';
 import * as path from 'path';
 import * as os from 'os';
 import { CodeGraph } from '../src';
-import { extractFromSource, scanDirectory, buildDefaultIgnore, discoverEmbeddedRepoRoots, buildScopeIgnore } from '../src/extraction';
+import { extractFromSource, scanDirectory, buildDefaultIgnore, discoverEmbeddedRepoRoots, buildScopeIgnore, getMaxFileSize } from '../src/extraction';
 import { detectLanguage, isLanguageSupported, getSupportedLanguages, initGrammars, loadAllGrammars, isSourceFile } from '../src/extraction/grammars';
 import { stripCppTemplateArgs, blankCppExportMacros, blankCppInlineMacros, blankMetalAttributes, blankCudaConstructs, blankCppAnnotationMacroCalls, blankCppApiPrefixMacros, blankCppInlineAnnotationMacros, recoverMangledCppName } from '../src/extraction/languages/c-cpp';
 import { normalizePath } from '../src/utils';
@@ -10939,3 +10939,32 @@ import DataStore from '../data/DataStore';
     });
   });
 });
+
+describe('CODEGRAPH_MAX_FILE_SIZE env var (#1016)', () => {
+  const originalEnv = process.env.CODEGRAPH_MAX_FILE_SIZE;
+  afterEach(() => {
+    if (originalEnv === undefined) delete process.env.CODEGRAPH_MAX_FILE_SIZE;
+    else process.env.CODEGRAPH_MAX_FILE_SIZE = originalEnv;
+  });
+
+  it('returns 1 MB default when env var is not set', () => {
+    delete process.env.CODEGRAPH_MAX_FILE_SIZE;
+    expect(getMaxFileSize()).toBe(1024 * 1024);
+  });
+
+  it('returns custom value when env var is a valid positive integer', () => {
+    process.env.CODEGRAPH_MAX_FILE_SIZE = '5242880';
+    expect(getMaxFileSize()).toBe(5242880);
+  });
+
+  it('falls back to default for invalid values', () => {
+    process.env.CODEGRAPH_MAX_FILE_SIZE = 'notanumber';
+    expect(getMaxFileSize()).toBe(1024 * 1024);
+
+    process.env.CODEGRAPH_MAX_FILE_SIZE = '-1';
+    expect(getMaxFileSize()).toBe(1024 * 1024);
+
+    process.env.CODEGRAPH_MAX_FILE_SIZE = '0';
+    expect(getMaxFileSize()).toBe(1024 * 1024);
+  });
+});

src/extraction/index.ts

@@ -120,9 +120,18 @@ export function hashContent(content: string): string {
 /**
  * Skip files larger than this (bytes). Generated bundles, minified JS, and
  * vendored blobs blow the WASM heap and the worker-recycle budget for no useful
- * symbols. 1 MB covers essentially all hand-written source.
+ * symbols. 1 MB covers essentially all hand-written source. Override via
+ * CODEGRAPH_MAX_FILE_SIZE (bytes) for projects with legitimate large source files.
  */
-const MAX_FILE_SIZE = 1024 * 1024;
+export function getMaxFileSize(): number {
+  const envVal = process.env.CODEGRAPH_MAX_FILE_SIZE;
+  if (envVal !== undefined) {
+    const parsed = parseInt(envVal, 10);
+    if (parsed > 0 && !isNaN(parsed)) return parsed;
+  }
+  return 1024 * 1024;
+}
+const MAX_FILE_SIZE = getMaxFileSize();
 
 /**
  * Directory names that are dependency, build, cache, or tooling output across the