feat: score-based search, LLM re-ranking endpoint, video title search, pipeline module

Core search changes:
- Replace RRF with score-based merge (max of semantic/keyword/identity)
- Add video title ILIKE search for brand/name queries (score 0.9)
- Add /api/v1/search/llm-smart endpoint with Gemma 4 re-ranking
- Fix LLM JSON parsing (markdown fences, empty responses)

Infrastructure:
- Rebuild Qdrant collection (clear 347K contaminated points)
- Add dotenv loading to main.rs for config parity
- Implement store_pre_chunk in postgres_db.rs

Pipeline module (WordPress):
- store-asrx, rule1, vectorize, phase1, complete endpoints
- CLI commands for pipeline operations

Docs:
- SEARCH_SCORE_IMPROVEMENT.md (score-based merge proposal)

src/api/server.rs

@@ -19,6 +19,8 @@ use super::identities;
 use super::identity_agent_api;
 use super::identity_api;
 use super::identity_binding;
+use super::llm_search;
+use super::pipeline;
 use super::media_api;
 use super::middleware::unified_auth;
 use super::processing;
@@ -117,7 +119,9 @@ pub async fn start_server(host: &str, port: u16) -> anyhow::Result<()> {
         .merge(media_api::bbox_routes())
         .merge(trace_agent_api::trace_agent_routes())
         .merge(search_routes())
+        .merge(llm_search::llm_smart_routes())
         .merge(universal_search_routes())
+        .merge(pipeline::pipeline_routes())
         .layer(axum::middleware::from_fn_with_state(
             state.api_state.clone(),
             unified_auth,