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/cli/args.rs

@@ -40,6 +40,11 @@ pub enum Commands {
         /// UUID
         uuid: String,
     },
+    /// Store ASRX chunks into pre_chunks table
+    StoreAsrx {
+        /// File UUID
+        uuid: String,
+    },
     /// Generate story for cut scenes
     Story {
         /// UUID
@@ -50,6 +55,16 @@ pub enum Commands {
         /// UUID (or 'all' for all)
         uuid: String,
     },
+    /// Run Phase 1 release packaging
+    Phase1 {
+        /// File UUID
+        uuid: String,
+    },
+    /// Mark video as completed
+    Complete {
+        /// File UUID
+        uuid: String,
+    },
     /// Play video with overlays
     Play {
         /// Video path or UUID