refactor: split global BUILT_IN_NAMES into per-language provider fields

gitnexus/src/core/ingestion/call-processor.ts

@@ -11,7 +11,6 @@ import { getLanguageFromFilename } from './utils/language-detection.js';
 import { isVerboseIngestionEnabled } from './utils/verbose.js';
 import { yieldToEventLoop } from './utils/event-loop.js';
 import { FUNCTION_NODE_TYPES, extractFunctionName, findEnclosingClassId } from './utils/ast-helpers.js';
-import { isBuiltInOrNoise } from './utils/noise-filter.js';
 import {
   countCallArguments,
   inferCallForm,
@@ -497,7 +496,7 @@ export const processCalls = async (
         }
       }
 
-      if (isBuiltInOrNoise(calledName)) return;
+      if (provider.isBuiltInName(calledName)) return;
 
       const callNode = captureMap['call'];
       const callForm = inferCallForm(callNode, nameNode);

gitnexus/src/core/ingestion/language-provider.ts

@@ -110,6 +110,11 @@ interface LanguageProviderConfig {
    *  When true, the worker extracts routes via the language's route extraction logic.
    *  Default: undefined (no route files). */
   readonly isRouteFile?: (filePath: string) => boolean;
+
+  // ── Noise filtering ────────────────────────────────────────────────
+  /** Built-in/stdlib names that should be filtered from the call graph for this language.
+   *  Default: undefined (no language-specific filtering). */
+  readonly builtInNames?: ReadonlySet<string>;
 }
 
 /** Runtime type — same as LanguageProviderConfig but with defaults guaranteed present. */
@@ -119,6 +124,8 @@ export interface LanguageProvider extends Omit<LanguageProviderConfig,
   readonly importSemantics: ImportSemantics;
   readonly heritageDefaultEdge: 'EXTENDS' | 'IMPLEMENTS';
   readonly mroStrategy: MroStrategy;
+  /** Check if a name is a built-in/stdlib function that should be filtered from the call graph. */
+  readonly isBuiltInName: (name: string) => boolean;
 }
 
 const DEFAULTS: Pick<LanguageProvider, 'importSemantics' | 'heritageDefaultEdge' | 'mroStrategy'> = {
@@ -129,5 +136,10 @@ const DEFAULTS: Pick<LanguageProvider, 'importSemantics' | 'heritageDefaultEdge'
 
 /** Define a language provider — required fields must be supplied, optional fields get sensible defaults. */
 export function defineLanguage(config: LanguageProviderConfig): LanguageProvider {
-  return { ...DEFAULTS, ...config };
+  const builtIns = config.builtInNames;
+  return {
+    ...DEFAULTS,
+    ...config,
+    isBuiltInName: builtIns ? (name: string) => builtIns.has(name) : () => false,
+  };
 }

gitnexus/src/core/ingestion/languages/c-cpp.ts

@@ -18,6 +18,28 @@ import { C_QUERIES, CPP_QUERIES } from '../tree-sitter-queries.js';
 import { isCppInsideClassOrStruct } from '../utils/ast-helpers.js';
 import type { LanguageProvider } from '../language-provider.js';
 
+const C_BUILT_INS: ReadonlySet<string> = new Set([
+  'printf', 'fprintf', 'sprintf', 'snprintf', 'vprintf', 'vfprintf', 'vsprintf', 'vsnprintf',
+  'scanf', 'fscanf', 'sscanf',
+  'malloc', 'calloc', 'realloc', 'free', 'memcpy', 'memmove', 'memset', 'memcmp',
+  'strlen', 'strcpy', 'strncpy', 'strcat', 'strncat', 'strcmp', 'strncmp', 'strstr', 'strchr', 'strrchr',
+  'atoi', 'atol', 'atof', 'strtol', 'strtoul', 'strtoll', 'strtoull', 'strtod',
+  'sizeof', 'offsetof', 'typeof',
+  'assert', 'abort', 'exit', '_exit',
+  'fopen', 'fclose', 'fread', 'fwrite', 'fseek', 'ftell', 'rewind', 'fflush', 'fgets', 'fputs',
+  'likely', 'unlikely', 'BUG', 'BUG_ON', 'WARN', 'WARN_ON', 'WARN_ONCE',
+  'IS_ERR', 'PTR_ERR', 'ERR_PTR', 'IS_ERR_OR_NULL',
+  'ARRAY_SIZE', 'container_of', 'list_for_each_entry', 'list_for_each_entry_safe',
+  'min', 'max', 'clamp', 'abs', 'swap',
+  'pr_info', 'pr_warn', 'pr_err', 'pr_debug', 'pr_notice', 'pr_crit', 'pr_emerg',
+  'printk', 'dev_info', 'dev_warn', 'dev_err', 'dev_dbg',
+  'GFP_KERNEL', 'GFP_ATOMIC',
+  'spin_lock', 'spin_unlock', 'spin_lock_irqsave', 'spin_unlock_irqrestore',
+  'mutex_lock', 'mutex_unlock', 'mutex_init',
+  'kfree', 'kmalloc', 'kzalloc', 'kcalloc', 'krealloc', 'kvmalloc', 'kvfree',
+  'get', 'put',
+]);
+
 /** Label override shared by C and C++: skip function_definition captures inside class/struct
  *  bodies (they're duplicates of definition.method captures). */
 const cppLabelOverride: NonNullable<LanguageProvider['labelOverride']> = (functionNode, defaultLabel) => {
@@ -34,6 +56,7 @@ export const cProvider = defineLanguage({
   importResolver: resolveCImport,
   importSemantics: 'wildcard',
   labelOverride: cppLabelOverride,
+  builtInNames: C_BUILT_INS,
 });
 
 export const cppProvider = defineLanguage({
@@ -46,4 +69,5 @@ export const cppProvider = defineLanguage({
   importSemantics: 'wildcard',
   mroStrategy: 'leftmost-base',
   labelOverride: cppLabelOverride,
+  builtInNames: C_BUILT_INS,
 });

gitnexus/src/core/ingestion/languages/csharp.ts

@@ -14,6 +14,27 @@ import { resolveCSharpImport } from '../import-resolvers/csharp.js';
 import { extractCSharpNamedBindings } from '../named-bindings/csharp.js';
 import { CSHARP_QUERIES } from '../tree-sitter-queries.js';
 
+const BUILT_INS: ReadonlySet<string> = new Set([
+  'Console', 'WriteLine', 'ReadLine', 'Write',
+  'Task', 'Run', 'Wait', 'WhenAll', 'WhenAny', 'FromResult', 'Delay', 'ContinueWith',
+  'ConfigureAwait', 'GetAwaiter', 'GetResult',
+  'ToString', 'GetType', 'Equals', 'GetHashCode', 'ReferenceEquals',
+  'Add', 'Remove', 'Contains', 'Clear', 'Count', 'Any', 'All',
+  'Where', 'Select', 'SelectMany', 'OrderBy', 'OrderByDescending', 'GroupBy',
+  'First', 'FirstOrDefault', 'Single', 'SingleOrDefault', 'Last', 'LastOrDefault',
+  'ToList', 'ToArray', 'ToDictionary', 'AsEnumerable', 'AsQueryable',
+  'Aggregate', 'Sum', 'Average', 'Min', 'Max', 'Distinct', 'Skip', 'Take',
+  'String', 'Format', 'IsNullOrEmpty', 'IsNullOrWhiteSpace', 'Concat', 'Join',
+  'Trim', 'TrimStart', 'TrimEnd', 'Split', 'Replace', 'StartsWith', 'EndsWith',
+  'Convert', 'ToInt32', 'ToDouble', 'ToBoolean', 'ToByte',
+  'Math', 'Abs', 'Ceiling', 'Floor', 'Round', 'Pow', 'Sqrt',
+  'Dispose', 'Close',
+  'TryParse', 'Parse',
+  'AddRange', 'RemoveAt', 'RemoveAll', 'FindAll', 'Exists', 'TrueForAll',
+  'ContainsKey', 'TryGetValue', 'AddOrUpdate',
+  'Throw', 'ThrowIfNull',
+]);
+
 export const csharpProvider = defineLanguage({
   id: SupportedLanguages.CSharp,
   extensions: ['.cs'],
@@ -24,4 +45,5 @@ export const csharpProvider = defineLanguage({
   namedBindingExtractor: extractCSharpNamedBindings,
   interfaceNamePattern: /^I[A-Z]/,
   mroStrategy: 'implements-split',
+  builtInNames: BUILT_INS,
 });

gitnexus/src/core/ingestion/languages/dart.ts

@@ -14,6 +14,15 @@ import { dartExportChecker } from '../export-detection.js';
 import { resolveDartImport } from '../import-resolvers/dart.js';
 import { DART_QUERIES } from '../tree-sitter-queries.js';
 
+const BUILT_INS: ReadonlySet<string> = new Set([
+  'setState', 'mounted', 'debugPrint',
+  'runApp', 'showDialog', 'showModalBottomSheet',
+  'Navigator', 'push', 'pushNamed', 'pushReplacement', 'pop', 'maybePop',
+  'ScaffoldMessenger', 'showSnackBar',
+  'deactivate', 'reassemble', 'debugDumpApp', 'debugDumpRenderTree',
+  'then', 'catchError', 'whenComplete', 'listen',
+]);
+
 export const dartProvider = defineLanguage({
   id: SupportedLanguages.Dart,
   extensions: ['.dart'],
@@ -22,4 +31,5 @@ export const dartProvider = defineLanguage({
   exportChecker: dartExportChecker,
   importResolver: resolveDartImport,
   importSemantics: 'wildcard',
+  builtInNames: BUILT_INS,
 });

gitnexus/src/core/ingestion/languages/kotlin.ts

@@ -17,6 +17,21 @@ import { appendKotlinWildcard } from '../import-resolvers/jvm.js';
 import { KOTLIN_QUERIES } from '../tree-sitter-queries.js';
 import { isKotlinClassMethod } from '../utils/ast-helpers.js';
 
+const BUILT_INS: ReadonlySet<string> = new Set([
+  'println', 'print', 'readLine', 'require', 'requireNotNull', 'check', 'assert', 'lazy', 'error',
+  'listOf', 'mapOf', 'setOf', 'mutableListOf', 'mutableMapOf', 'mutableSetOf',
+  'arrayOf', 'sequenceOf', 'also', 'apply', 'run', 'with', 'takeIf', 'takeUnless',
+  'TODO', 'buildString', 'buildList', 'buildMap', 'buildSet',
+  'repeat', 'synchronized',
+  'launch', 'async', 'runBlocking', 'withContext', 'coroutineScope',
+  'supervisorScope', 'delay',
+  'flow', 'flowOf', 'collect', 'emit', 'onEach', 'catch',
+  'buffer', 'conflate', 'distinctUntilChanged',
+  'flatMapLatest', 'flatMapMerge', 'combine',
+  'stateIn', 'shareIn', 'launchIn',
+  'to', 'until', 'downTo', 'step',
+]);
+
 export const kotlinProvider = defineLanguage({
   id: SupportedLanguages.Kotlin,
   extensions: ['.kt', '.kts'],
@@ -27,6 +42,7 @@ export const kotlinProvider = defineLanguage({
   namedBindingExtractor: extractKotlinNamedBindings,
   importPathPreprocessor: appendKotlinWildcard,
   mroStrategy: 'implements-split',
+  builtInNames: BUILT_INS,
   labelOverride: (functionNode, defaultLabel) => {
     if (defaultLabel !== 'Function') return defaultLabel;
     if (isKotlinClassMethod(functionNode)) return 'Method';

gitnexus/src/core/ingestion/languages/php.ts

@@ -16,6 +16,25 @@ import { PHP_QUERIES } from '../tree-sitter-queries.js';
 import { findDescendant, extractStringContent } from '../utils/ast-helpers.js';
 import type { NodeLabel } from '../../graph/types.js';
 
+const BUILT_INS: ReadonlySet<string> = new Set([
+  'echo', 'isset', 'empty', 'unset', 'list', 'array', 'compact', 'extract',
+  'count', 'strlen', 'strpos', 'strrpos', 'substr', 'strtolower', 'strtoupper', 'trim',
+  'ltrim', 'rtrim', 'str_replace', 'str_contains', 'str_starts_with', 'str_ends_with',
+  'sprintf', 'vsprintf', 'printf', 'number_format',
+  'array_map', 'array_filter', 'array_reduce', 'array_push', 'array_pop', 'array_shift',
+  'array_unshift', 'array_slice', 'array_splice', 'array_merge', 'array_keys', 'array_values',
+  'array_key_exists', 'in_array', 'array_search', 'array_unique', 'usort', 'rsort',
+  'json_encode', 'json_decode', 'serialize', 'unserialize',
+  'intval', 'floatval', 'strval', 'boolval', 'is_null', 'is_string', 'is_int', 'is_array',
+  'is_object', 'is_numeric', 'is_bool', 'is_float',
+  'var_dump', 'print_r', 'var_export',
+  'date', 'time', 'strtotime', 'mktime', 'microtime',
+  'file_exists', 'file_get_contents', 'file_put_contents', 'is_file', 'is_dir',
+  'preg_match', 'preg_match_all', 'preg_replace', 'preg_split',
+  'header', 'session_start', 'session_destroy', 'ob_start', 'ob_end_clean', 'ob_get_clean',
+  'dd', 'dump',
+]);
+
 /** Eloquent model properties whose array values are worth indexing. */
 const ELOQUENT_ARRAY_PROPS = new Set(['fillable', 'casts', 'hidden', 'guarded', 'with', 'appends']);
 
@@ -130,4 +149,5 @@ export const phpProvider = defineLanguage({
   namedBindingExtractor: extractPhpNamedBindings,
   descriptionExtractor: phpDescriptionExtractor,
   isRouteFile: isPhpRouteFile,
+  builtInNames: BUILT_INS,
 });

gitnexus/src/core/ingestion/languages/python.ts

@@ -18,6 +18,13 @@ import { resolvePythonImport } from '../import-resolvers/python.js';
 import { extractPythonNamedBindings } from '../named-bindings/python.js';
 import { PYTHON_QUERIES } from '../tree-sitter-queries.js';
 
+const BUILT_INS: ReadonlySet<string> = new Set([
+  'print', 'len', 'range', 'str', 'int', 'float', 'list', 'dict', 'set', 'tuple',
+  'append', 'extend', 'update',
+  'type', 'isinstance', 'issubclass', 'getattr', 'setattr', 'hasattr',
+  'enumerate', 'zip', 'sorted', 'reversed', 'min', 'max', 'sum', 'abs',
+]);
+
 export const pythonProvider = defineLanguage({
   id: SupportedLanguages.Python,
   extensions: ['.py'],
@@ -28,4 +35,5 @@ export const pythonProvider = defineLanguage({
   namedBindingExtractor: extractPythonNamedBindings,
   importSemantics: 'namespace',
   mroStrategy: 'c3',
+  builtInNames: BUILT_INS,
 });

gitnexus/src/core/ingestion/languages/ruby.ts

@@ -15,6 +15,22 @@ import { rubyExportChecker } from '../export-detection.js';
 import { resolveRubyImport } from '../import-resolvers/ruby.js';
 import { RUBY_QUERIES } from '../tree-sitter-queries.js';
 
+const BUILT_INS: ReadonlySet<string> = new Set([
+  'puts', 'p', 'pp', 'raise', 'fail',
+  'require', 'require_relative', 'load', 'autoload',
+  'include', 'extend', 'prepend',
+  'attr_accessor', 'attr_reader', 'attr_writer',
+  'public', 'private', 'protected', 'module_function',
+  'lambda', 'proc', 'block_given?',
+  'nil?', 'is_a?', 'kind_of?', 'instance_of?', 'respond_to?',
+  'freeze', 'frozen?', 'dup', 'tap', 'yield_self',
+  'each', 'select', 'reject', 'detect', 'collect',
+  'inject', 'flat_map', 'each_with_object', 'each_with_index',
+  'any?', 'all?', 'none?', 'count', 'first', 'last',
+  'sort_by', 'min_by', 'max_by',
+  'group_by', 'partition', 'compact', 'flatten', 'uniq',
+]);
+
 export const rubyProvider = defineLanguage({
   id: SupportedLanguages.Ruby,
   extensions: ['.rb', '.rake', '.gemspec'],
@@ -24,4 +40,5 @@ export const rubyProvider = defineLanguage({
   importResolver: resolveRubyImport,
   callRouter: routeRubyCall,
   importSemantics: 'wildcard',
+  builtInNames: BUILT_INS,
 });

gitnexus/src/core/ingestion/languages/rust.ts

@@ -18,6 +18,19 @@ import { resolveRustImport } from '../import-resolvers/rust.js';
 import { extractRustNamedBindings } from '../named-bindings/rust.js';
 import { RUST_QUERIES } from '../tree-sitter-queries.js';
 
+const BUILT_INS: ReadonlySet<string> = new Set([
+  'unwrap', 'expect', 'unwrap_or', 'unwrap_or_else', 'unwrap_or_default',
+  'ok', 'err', 'is_ok', 'is_err', 'map', 'map_err', 'and_then', 'or_else',
+  'clone', 'to_string', 'to_owned', 'into', 'from', 'as_ref', 'as_mut',
+  'iter', 'into_iter', 'collect', 'filter', 'fold', 'for_each',
+  'len', 'is_empty', 'push', 'pop', 'insert', 'remove', 'contains',
+  'format', 'write', 'writeln', 'panic', 'unreachable', 'todo', 'unimplemented',
+  'vec', 'println', 'eprintln', 'dbg',
+  'lock', 'read', 'try_lock',
+  'spawn', 'join', 'sleep',
+  'Some', 'None', 'Ok', 'Err',
+]);
+
 export const rustProvider = defineLanguage({
   id: SupportedLanguages.Rust,
   extensions: ['.rs'],
@@ -27,4 +40,5 @@ export const rustProvider = defineLanguage({
   importResolver: resolveRustImport,
   namedBindingExtractor: extractRustNamedBindings,
   mroStrategy: 'qualified-syntax',
+  builtInNames: BUILT_INS,
 });

gitnexus/src/core/ingestion/languages/swift.ts

@@ -101,6 +101,34 @@ function wireSwiftImplicitImports(
   }
 }
 
+const BUILT_INS: ReadonlySet<string> = new Set([
+  'print', 'debugPrint', 'dump', 'fatalError', 'precondition', 'preconditionFailure',
+  'assert', 'assertionFailure', 'NSLog',
+  'abs', 'min', 'max', 'zip', 'stride', 'sequence', 'repeatElement',
+  'swap', 'withUnsafePointer', 'withUnsafeMutablePointer', 'withUnsafeBytes',
+  'autoreleasepool', 'unsafeBitCast', 'unsafeDowncast', 'numericCast',
+  'type', 'MemoryLayout',
+  'map', 'flatMap', 'compactMap', 'filter', 'reduce', 'forEach', 'contains',
+  'first', 'last', 'prefix', 'suffix', 'dropFirst', 'dropLast',
+  'sorted', 'reversed', 'enumerated', 'joined', 'split',
+  'append', 'insert', 'remove', 'removeAll', 'removeFirst', 'removeLast',
+  'isEmpty', 'count', 'index', 'startIndex', 'endIndex',
+  'addSubview', 'removeFromSuperview', 'layoutSubviews', 'setNeedsLayout',
+  'layoutIfNeeded', 'setNeedsDisplay', 'invalidateIntrinsicContentSize',
+  'addTarget', 'removeTarget', 'addGestureRecognizer',
+  'addConstraint', 'addConstraints', 'removeConstraint', 'removeConstraints',
+  'NSLocalizedString', 'Bundle',
+  'reloadData', 'reloadSections', 'reloadRows', 'performBatchUpdates',
+  'register', 'dequeueReusableCell', 'dequeueReusableSupplementaryView',
+  'beginUpdates', 'endUpdates', 'insertRows', 'deleteRows', 'insertSections', 'deleteSections',
+  'present', 'dismiss', 'pushViewController', 'popViewController', 'popToRootViewController',
+  'performSegue', 'prepare',
+  'DispatchQueue', 'async', 'sync', 'asyncAfter',
+  'Task', 'withCheckedContinuation', 'withCheckedThrowingContinuation',
+  'sink', 'store', 'assign', 'receive', 'subscribe',
+  'addObserver', 'removeObserver', 'post', 'NotificationCenter',
+]);
+
 export const swiftProvider = defineLanguage({
   id: SupportedLanguages.Swift,
   extensions: ['.swift'],
@@ -111,4 +139,5 @@ export const swiftProvider = defineLanguage({
   importSemantics: 'wildcard',
   heritageDefaultEdge: 'IMPLEMENTS',
   implicitImportWirer: wireSwiftImplicitImports,
+  builtInNames: BUILT_INS,
 });

gitnexus/src/core/ingestion/languages/typescript.ts

@@ -15,6 +15,27 @@ import { resolveTypescriptImport, resolveJavascriptImport } from '../import-reso
 import { extractTsNamedBindings } from '../named-bindings/typescript.js';
 import { TYPESCRIPT_QUERIES, JAVASCRIPT_QUERIES } from '../tree-sitter-queries.js';
 
+const BUILT_INS: ReadonlySet<string> = new Set([
+  'console', 'log', 'warn', 'error', 'info', 'debug',
+  'setTimeout', 'setInterval', 'clearTimeout', 'clearInterval',
+  'parseInt', 'parseFloat', 'isNaN', 'isFinite',
+  'encodeURI', 'decodeURI', 'encodeURIComponent', 'decodeURIComponent',
+  'JSON', 'parse', 'stringify',
+  'Object', 'Array', 'String', 'Number', 'Boolean', 'Symbol', 'BigInt',
+  'Map', 'Set', 'WeakMap', 'WeakSet',
+  'Promise', 'resolve', 'reject', 'then', 'catch', 'finally',
+  'Math', 'Date', 'RegExp', 'Error',
+  'require', 'import', 'export', 'fetch', 'Response', 'Request',
+  'useState', 'useEffect', 'useCallback', 'useMemo', 'useRef', 'useContext',
+  'useReducer', 'useLayoutEffect', 'useImperativeHandle', 'useDebugValue',
+  'createElement', 'createContext', 'createRef', 'forwardRef', 'memo', 'lazy',
+  'map', 'filter', 'reduce', 'forEach', 'find', 'findIndex', 'some', 'every',
+  'includes', 'indexOf', 'slice', 'splice', 'concat', 'join', 'split',
+  'push', 'pop', 'shift', 'unshift', 'sort', 'reverse',
+  'keys', 'values', 'entries', 'assign', 'freeze', 'seal',
+  'hasOwnProperty', 'toString', 'valueOf',
+]);
+
 export const typescriptProvider = defineLanguage({
   id: SupportedLanguages.TypeScript,
   extensions: ['.ts', '.tsx'],
@@ -23,6 +44,7 @@ export const typescriptProvider = defineLanguage({
   exportChecker: tsExportChecker,
   importResolver: resolveTypescriptImport,
   namedBindingExtractor: extractTsNamedBindings,
+  builtInNames: BUILT_INS,
 });
 
 export const javascriptProvider = defineLanguage({
@@ -33,4 +55,5 @@ export const javascriptProvider = defineLanguage({
   exportChecker: tsExportChecker,
   importResolver: resolveJavascriptImport,
   namedBindingExtractor: extractTsNamedBindings,
+  builtInNames: BUILT_INS,
 });

gitnexus/src/core/ingestion/tree-sitter-queries.ts

@@ -808,7 +808,7 @@ export const RUBY_QUERIES = `
 ; NOTE: This may over-capture variable reads as calls (e.g. 'result' at
 ; statement level). Ruby's grammar makes bare identifiers ambiguous — they
 ; could be local variables or zero-arity method calls. Post-processing via
-; isBuiltInOrNoise and symbol resolution filtering suppresses most false
+; provider.isBuiltInName and symbol resolution filtering suppresses most false
 ; positives, but a variable name that coincidentally matches a method name
 ; elsewhere may produce a false CALLS edge.
 (body_statement