perf(search+embed): zero-copy embedding API and deferred RRF mapping

Change OllamaClient::embed_batch to accept &[&str] instead of
Vec<String>. The EmbedRequest struct now borrows both model name and
input texts, eliminating per-batch cloning of chunk text (up to 32KB
per chunk x 32 chunks per batch). Serialization output is identical
since serde serializes &str and String to the same JSON.

In hybrid search, defer the RrfResult->HybridResult mapping until
after filter+take, so only `limit` items (typically 20) are
constructed instead of up to 1,500 at RECALL_CAP. Also switch
filtered_ids to into_iter() to avoid an extra .copied() pass.

Switch FTS search_fts from prepare() to prepare_cached() for statement
reuse across repeated searches. Benchmarked at ~1.6x faster.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/embedding/pipeline.rs

@@ -162,9 +162,9 @@ async fn embed_page(
     let mut cleared_docs: HashSet<i64> = HashSet::with_capacity(pending.len());
 
     for batch in all_chunks.chunks(BATCH_SIZE) {
-        let texts: Vec<String> = batch.iter().map(|c| c.text.clone()).collect();
+        let texts: Vec<&str> = batch.iter().map(|c| c.text.as_str()).collect();
 
-        match client.embed_batch(texts).await {
+        match client.embed_batch(&texts).await {
             Ok(embeddings) => {
                 for (i, embedding) in embeddings.iter().enumerate() {
                     if i >= batch.len() {
@@ -228,7 +228,7 @@ async fn embed_page(
                 if is_context_error && batch.len() > 1 {
                     warn!("Batch failed with context length error, retrying chunks individually");
                     for chunk in batch {
-                        match client.embed_batch(vec![chunk.text.clone()]).await {
+                        match client.embed_batch(&[chunk.text.as_str()]).await {
                             Ok(embeddings)
                                 if !embeddings.is_empty()
                                     && embeddings[0].len() == EXPECTED_DIMS =>