fix: gracefully skip files when language parser is unavailable (#136)

Instead of crashing the pipeline when a native tree-sitter binding
(e.g. tree-sitter-swift) fails to build, skip those files early and
warn the user with an actionable message.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

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

@@ -286,7 +286,11 @@ const processParsingSequential = async (
     // Skip very large files — they can crash tree-sitter or cause OOM
     if (file.content.length > 512 * 1024) continue;
 
-    await loadLanguage(language, file.path);
+    try {
+      await loadLanguage(language, file.path);
+    } catch {
+      continue;  // parser unavailable — already warned in pipeline
+    }
 
     let tree;
     try {

gitnexus/src/core/ingestion/pipeline.ts

@@ -11,6 +11,7 @@ import { createASTCache } from './ast-cache.js';
 import { PipelineProgress, PipelineResult } from '../../types/pipeline.js';
 import { walkRepositoryPaths, readFileContents } from './filesystem-walker.js';
 import { getLanguageFromFilename } from './utils.js';
+import { isLanguageAvailable } from '../tree-sitter/parser-loader.js';
 import { createWorkerPool, WorkerPool } from './workers/worker-pool.js';
 
 const isDev = process.env.NODE_ENV === 'development';
@@ -88,7 +89,23 @@ export const runPipelineFromRepo = async (
     // Group parseable files into byte-budget chunks so only ~20MB of source
     // is in memory at a time. Each chunk is: read → parse → extract → free.
 
-    const parseableScanned = scannedFiles.filter(f => getLanguageFromFilename(f.path));
+    const parseableScanned = scannedFiles.filter(f => {
+      const lang = getLanguageFromFilename(f.path);
+      return lang && isLanguageAvailable(lang);
+    });
+
+    // Warn about files skipped due to unavailable parsers
+    const skippedByLang = new Map<string, number>();
+    for (const f of scannedFiles) {
+      const lang = getLanguageFromFilename(f.path);
+      if (lang && !isLanguageAvailable(lang)) {
+        skippedByLang.set(lang, (skippedByLang.get(lang) || 0) + 1);
+      }
+    }
+    for (const [lang, count] of skippedByLang) {
+      console.warn(`Skipping ${count} ${lang} file(s) — ${lang} parser not available (native binding may not have built). Try: npm rebuild tree-sitter-${lang}`);
+    }
+
     const totalParseable = parseableScanned.length;
 
     // Build byte-budget chunks

gitnexus/src/core/ingestion/workers/parse-worker.ts

@@ -576,14 +576,22 @@ const processBatch = (files: ParseWorkerInput[], onProgress?: (filesProcessed: n
 
     // Process regular files for this language
     if (regularFiles.length > 0) {
-      setLanguage(language, regularFiles[0].path);
-      processFileGroup(regularFiles, language, queryString, result, onFileProcessed);
+      try {
+        setLanguage(language, regularFiles[0].path);
+        processFileGroup(regularFiles, language, queryString, result, onFileProcessed);
+      } catch {
+        // parser unavailable — skip this language group
+      }
     }
 
     // Process tsx files separately (different grammar)
     if (tsxFiles.length > 0) {
-      setLanguage(language, tsxFiles[0].path);
-      processFileGroup(tsxFiles, language, queryString, result, onFileProcessed);
+      try {
+        setLanguage(language, tsxFiles[0].path);
+        processFileGroup(tsxFiles, language, queryString, result, onFileProcessed);
+      } catch {
+        // parser unavailable — skip this language group
+      }
     }
   }
 

gitnexus/src/core/tree-sitter/parser-loader.ts

@@ -36,6 +36,9 @@ const languageMap: Record<string, any> = {
   ...(Swift ? { [SupportedLanguages.Swift]: Swift } : {}),
 };
 
+export const isLanguageAvailable = (language: SupportedLanguages): boolean =>
+  language in languageMap;
+
 export const loadParser = async (): Promise<Parser> => {
   if (parser) return parser;
   parser = new Parser();