perf(mcp): Batch semantic code search embeddings to resolve CPU bottleneck and fix linting warnings

server/src/embedding.rs

@@ -40,3 +40,14 @@ pub fn cosine_similarity(a: &[f32], b: &[f32]) -> f32 {
         dot_product / (norm_a * norm_b)
     }
 }
+pub async fn generate_embeddings_async(texts: Vec<String>) -> Result<Vec<Vec<f32>>, String> {
+    if texts.is_empty() {
+        return Ok(Vec::new());
+    }
+    tokio::task::spawn_blocking(move || {
+        let model_mutex = get_embedding_model()?;
+        let mut model = model_mutex.lock().map_err(|e| e.to_string())?;
+        let embeddings = model.embed(texts, None).map_err(|e| e.to_string())?;
+        Ok(embeddings)
+    }).await.map_err(|e| e.to_string())?
+}