gitnexus 1.6.2-rc.1 → 1.6.2-rc.2

package/dist/core/embeddings/embedding-pipeline.js

@@ -67,8 +67,8 @@ const queryEmbeddableNodes = async (executeQuery) => {
  * that occurs when UPDATEing nodes with large content fields
  */
 const batchInsertEmbeddings = async (executeWithReusedStatement, updates) => {
-    // INSERT into separate embedding table - much more memory efficient!
-    const cypher = `CREATE (e:CodeEmbedding {nodeId: $nodeId, embedding: $embedding})`;
+    // MERGE instead of CREATE — idempotent, handles concurrent analyzes and partial prior runs
+    const cypher = `MERGE (e:CodeEmbedding {nodeId: $nodeId}) SET e.embedding = $embedding`;
     const paramsList = updates.map((u) => ({ nodeId: u.id, embedding: u.embedding }));
     await executeWithReusedStatement(cypher, paramsList);
 };

package/dist/core/lbug/csv-generator.js

@@ -246,14 +246,17 @@ export const streamAllCSVsToDisk = async (graph, repoPath, csvDir) => {
         Interface: interfaceWriter,
         CodeElement: codeElemWriter,
     };
-    const seenFileIds = new Set();
+    // Deduplicate all node types — the pipeline can produce duplicate IDs across
+    // all symbol types (Class, Method, Function, etc.), not just File nodes.
+    // A single Set covering every label prevents PK violations on COPY.
+    const seenNodeIds = new Set();
     // --- SINGLE PASS over all nodes ---
     for (const node of graph.iterNodes()) {
+        if (seenNodeIds.has(node.id))
+            continue;
+        seenNodeIds.add(node.id);
         switch (node.label) {
             case 'File': {
-                if (seenFileIds.has(node.id))
-                    break;
-                seenFileIds.add(node.id);
                 const content = await extractContent(node, contentCache);
                 await fileWriter.addRow([
                     escapeCSVField(node.id),

package/dist/core/run-analyze.js

@@ -149,7 +149,7 @@ export async function runFullAnalysis(repoPath, options, callbacks) {
                     const batch = cachedEmbeddings.slice(i, i + EMBED_BATCH);
                     const paramsList = batch.map((e) => ({ nodeId: e.nodeId, embedding: e.embedding }));
                     try {
-                        await executeWithReusedStatement(`CREATE (e:CodeEmbedding {nodeId: $nodeId, embedding: $embedding})`, paramsList);
+                        await executeWithReusedStatement(`MERGE (e:CodeEmbedding {nodeId: $nodeId}) SET e.embedding = $embedding`, paramsList);
                     }
                     catch {
                         /* some may fail if node was removed, that's fine */

package/dist/server/api.js

@@ -1277,6 +1277,26 @@ export const createServer = async (port, host = '127.0.0.1') => {
                     const lbugPath = path.join(entry.storagePath, 'lbug');
                     await withLbugDb(lbugPath, async () => {
                         const { runEmbeddingPipeline } = await import('../core/embeddings/embedding-pipeline.js');
+                        // Skip nodes that already have embeddings — Kuzu forbids SET on vector-indexed properties.
+                        let skipNodeIds;
+                        try {
+                            const rows = await executeQuery('MATCH (e:CodeEmbedding) RETURN e.nodeId AS nodeId');
+                            if (rows && rows.length > 0) {
+                                skipNodeIds = new Set(rows.map((r) => r.nodeId ?? r[0]).filter(Boolean));
+                                console.log(`[embed] ${skipNodeIds.size} nodes already embedded — skipping in incremental run`);
+                            }
+                        }
+                        catch (err) {
+                            // Swallow only "table does not exist" — let real connection errors propagate.
+                            // Log so ops can see this path fire if Kuzu ever changes error wording.
+                            const msg = err?.message ?? '';
+                            if (msg.includes('does not exist') || msg.includes('not found')) {
+                                console.log(`[embed] CodeEmbedding table not yet present — full embedding run (${msg})`);
+                            }
+                            else {
+                                throw err;
+                            }
+                        }
                         await runEmbeddingPipeline(executeQuery, executeWithReusedStatement, (p) => {
                             embedJobManager.updateJob(job.id, {
                                 progress: {
@@ -1293,7 +1313,8 @@ export const createServer = async (port, host = '127.0.0.1') => {
                                                     : `${p.phase} (${p.percent}%)`,
                                 },
                             });
-                        });
+                        }, {}, // config: use defaults (runEmbeddingPipeline signature: executeQuery, executeWithReusedStatement, onProgress, config, skipNodeIds)
+                        skipNodeIds);
                     });
                     clearTimeout(embedTimeout);
                     releaseRepoLock(repoLockPath);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gitnexus",
-  "version": "1.6.2-rc.1",
+  "version": "1.6.2-rc.2",
   "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",