migrate article embeddings to support multi-model architecture and enhance data integrity

src/embeddings.js

@@ -117,6 +117,47 @@ try {
   console.error('embedding store backfill failed:', err);
 }
 
+// probe the API to get the real dimension count for the current model, then purge
+// any store entries that don't match — handles the case where old embeddings
+// got stamped with the wrong model name during migration
+async function purgeWrongSizeEmbeddings() {
+  const apiKey = config.openRouter && config.openRouter.apiKey
+    ? String(config.openRouter.apiKey).trim()
+    : '';
+
+  if (!apiKey) return;
+
+  try {
+    const probe = await requestEmbedding('probe');
+    const expectedBytes = probe.length * 4;
+
+    const stale = db.prepare(`
+      SELECT article_id FROM article_embedding_store
+      WHERE model = ? AND LENGTH(embedding) != ?
+    `).all(EMBEDDING_MODEL, expectedBytes);
+
+    if (stale.length === 0) return;
+
+    const deleteStore = db.prepare(`DELETE FROM article_embedding_store WHERE article_id = ? AND model = ?`);
+    const deleteMeta = db.prepare(`DELETE FROM article_embedding_meta WHERE article_id = ?`);
+    const deleteVec = db.prepare(`DELETE FROM article_embeddings WHERE article_id = ?`);
+
+    db.transaction(() => {
+      for (const row of stale) {
+        deleteStore.run(row.article_id, EMBEDDING_MODEL);
+        deleteMeta.run(row.article_id);
+        deleteVec.run(BigInt(row.article_id));
+      }
+    })();
+
+    console.log(`purged ${stale.length} wrong-size embeddings for model ${EMBEDDING_MODEL} (expected ${probe.length} dims)`);
+  } catch (err) {
+    console.error('embedding size validation failed:', err);
+  }
+}
+
+purgeWrongSizeEmbeddings();
+
 // if the config model changed, rebuild the vec0 search index from store.
 // only proceeds if the store actually has embeddings for the new model.
 function rebuildVec0IfModelChanged() {