@o-lang/semantic-doc-search 1.0.30 → 1.0.31

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@o-lang/semantic-doc-search",
-  "version": "1.0.30",
+  "version": "1.0.31",
   "description": "O-lang Semantic Document Search Resolver with hybrid search, embeddings, rerank, and streaming.",
   "main": "src/index.js",
   "type": "commonjs",

package/src/embeddings/local.js

@@ -6,7 +6,7 @@
  * - No silent failures
  * - No zero vectors
  * - Deterministic behavior
- * - DEFENSIVE against method detaching
+ * - DEFENSIVE against method detaching & invalid vectors
  */
 
 class LocalEmbedding {
@@ -15,7 +15,7 @@ class LocalEmbedding {
     this.model = null;
     this.loading = null;
 
-    // 🔒 CRITICAL: bind methods to prevent resolver breakage
+    // 🔒 Bind methods to prevent resolver breakage
     this.loadModel = this.loadModel.bind(this);
     this.embed = this.embed.bind(this);
     this.embedBatch = this.embedBatch.bind(this);
@@ -73,18 +73,19 @@ class LocalEmbedding {
         normalize: true,
       });
 
-      const vector = Array.from(output.data);
+      // ✅ Defensive: ensure vector is a valid array
+      const vector = Array.isArray(output?.data) ? Array.from(output.data) : null;
 
-      if (vector.length !== this.dim) {
-        throw new Error(
-          `Invalid embedding dimension: ${vector.length} (expected ${this.dim})`
-        );
+      if (!Array.isArray(vector) || vector.length !== this.dim) {
+        console.error("❌ Invalid embedding vector returned:", vector);
+        throw new Error(`Invalid embedding dimension: ${vector?.length || 0} (expected ${this.dim})`);
       }
 
       return vector;
     } catch (err) {
       console.error(
-        `❌ Embedding failed for text: "${text.slice(0, 60)}..."`
+        `❌ Embedding failed for text: "${text.slice(0, 60)}..."`,
+        err
       );
       throw err;
     }
@@ -115,7 +116,5 @@ class LocalEmbedding {
 
 /* ---------------- SINGLETON EXPORT ---------------- */
 
-// One embedder per process (CRITICAL)
 const embedder = new LocalEmbedding();
-
 module.exports = embedder;

package/src/resolver.js

@@ -1,5 +1,5 @@
 const VectorRouter = require("./adapters/vectorRouter");
-const { embed } = require("./embeddings/local");
+const embedder = require("./embeddings/local"); // ✅ singleton embedder
 const { extractQuery } = require("./utils/extractQuery");
 const { formatResults } = require("./utils/formatResults");
 const fs = require("fs");
@@ -17,11 +17,13 @@ function loadCache() {
   } catch {}
   return {};
 }
+
 function saveCache(cache) {
   try {
     fs.writeFileSync(CACHE_PATH, JSON.stringify(cache, null, 2));
   } catch {}
 }
+
 function hashContent(str) {
   return crypto.createHash("sha256").update(str).digest("hex");
 }
@@ -64,8 +66,13 @@ async function resolver(action, context = {}) {
         const hash = hashContent(text);
         if (cache[hash]) continue; // Skip already ingested
 
-        const vector = await embed(text);
-        if (!vector || vector.every(v => v === 0)) continue;
+        const vector = await embedder.embed(text);
+
+        // ✅ Defensive: skip invalid vectors
+        if (!Array.isArray(vector) || vector.length !== embedder.getDimension() || vector.every(v => v === 0)) {
+          console.warn(`⚠️ Skipping invalid vector for doc ${doc.id}:${i}`);
+          continue;
+        }
 
         await vectorStore.upsert({
           id: `${doc.id}:${i}`,
@@ -81,9 +88,15 @@ async function resolver(action, context = {}) {
   }
 
   // Embed query & search
-  const vector = await embed(query);
+  const queryVector = await embedder.embed(query);
+
+  // ✅ Defensive: validate query vector
+  if (!Array.isArray(queryVector) || queryVector.length !== embedder.getDimension()) {
+    throw new Error("Query embedding invalid or not a proper array");
+  }
+
   const results = await vectorStore.query({
-    vector,
+    vector: queryVector,
     topK: context.topK || 5,
     minScore: context.minScore || 0,
   });