gitnexus 1.6.10-rc.16 → 1.6.10-rc.17

package/dist/core/ingestion/workers/parse-worker.js

@@ -814,7 +814,7 @@ const processFileGroup = (files, language, queryString, result, onFileProcessed)
         try {
             tree = parseSourceSafe(parser, parseContent, undefined, {
                 bufferSize: getTreeSitterBufferSize(parseContent),
-            });
+            }, file.path);
         }
         catch (err) {
             reportWarning(`Failed to parse file ${file.path}: ${err instanceof Error ? err.message : String(err)}`);

package/dist/core/tree-sitter/safe-parse.d.ts

@@ -42,7 +42,7 @@ export declare function getParseDiagnostics(tree: Parser.Tree): {
 /**
  * Parse `sourceText` safely on every platform.
  *
- * This is the single "parse safely" entry point and its contract covers three
+ * This is the single "parse safely" entry point and its contract covers four
  * concerns:
  *
  *  1. **Windows crash workaround.** Inputs longer than 32 767 chars are fed
@@ -62,7 +62,12 @@ export declare function getParseDiagnostics(tree: Parser.Tree): {
  *     the tree is **returned anyway** — error recovery is a downgrade, never a
  *     drop. Callers wanting the boolean use {@link parseHadErrors}.
  *
- * @param label optional context (e.g. file path) attached to timeout errors
- *   and degraded-parse logs. Non-breaking trailing param.
+ *  4. **Embedded NUL recovery.** U+0000 is replaced with one ASCII space in
+ *     the parser-only input. The one-for-one substitution keeps tree indices
+ *     aligned with the original source while preventing language lexers from
+ *     swallowing declarations during error recovery.
+ *
+ * @param label optional context (e.g. file path) attached to timeout errors,
+ *   recovery warnings, and degraded-parse logs. Non-breaking trailing param.
  */
 export declare function parseSourceSafe(parser: Parser, sourceText: string, oldTree?: Parser.Tree, options?: Parser.Options, label?: string): Parser.Tree;

package/dist/core/tree-sitter/safe-parse.js

@@ -155,7 +155,7 @@ export function getParseDiagnostics(tree) {
 /**
  * Parse `sourceText` safely on every platform.
  *
- * This is the single "parse safely" entry point and its contract covers three
+ * This is the single "parse safely" entry point and its contract covers four
  * concerns:
  *
  *  1. **Windows crash workaround.** Inputs longer than 32 767 chars are fed
@@ -175,22 +175,36 @@ export function getParseDiagnostics(tree) {
  *     the tree is **returned anyway** — error recovery is a downgrade, never a
  *     drop. Callers wanting the boolean use {@link parseHadErrors}.
  *
- * @param label optional context (e.g. file path) attached to timeout errors
- *   and degraded-parse logs. Non-breaking trailing param.
+ *  4. **Embedded NUL recovery.** U+0000 is replaced with one ASCII space in
+ *     the parser-only input. The one-for-one substitution keeps tree indices
+ *     aligned with the original source while preventing language lexers from
+ *     swallowing declarations during error recovery.
+ *
+ * @param label optional context (e.g. file path) attached to timeout errors,
+ *   recovery warnings, and degraded-parse logs. Non-breaking trailing param.
  */
 export function parseSourceSafe(parser, sourceText, oldTree, options, label) {
+    let parserInput = sourceText;
+    if (sourceText.includes('\0')) {
+        let nullByteCount = 0;
+        parserInput = sourceText.replaceAll('\0', () => {
+            nullByteCount += 1;
+            return ' ';
+        });
+        logger.warn({ ...(label ? { file: label } : {}), nullByteCount }, 'replaced embedded NUL bytes before tree-sitter parsing');
+    }
     const budgetMs = resolveParseTimeoutMs();
     const armed = armParseBudget(parser, budgetMs);
     let tree;
     try {
-        if (sourceText.length <= DIRECT_PARSE_LIMIT_CHARS) {
-            tree = parser.parse(sourceText, oldTree, options);
+        if (parserInput.length <= DIRECT_PARSE_LIMIT_CHARS) {
+            tree = parser.parse(parserInput, oldTree, options);
         }
         else {
             const input = (index) => {
-                if (index >= sourceText.length)
+                if (index >= parserInput.length)
                     return null;
-                return sourceText.slice(index, index + SAFE_PARSE_CHUNK_CHARS);
+                return parserInput.slice(index, index + SAFE_PARSE_CHUNK_CHARS);
             };
             tree = parser.parse(input, oldTree, options);
         }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gitnexus",
-  "version": "1.6.10-rc.16",
+  "version": "1.6.10-rc.17",
   "description": "Graph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.",
   "author": "Abhigyan Patwari",
   "license": "PolyForm-Noncommercial-1.0.0",