Implement Phase 12 feedback, Phase 13 Semantic Chunker, Phase 13-B Reranker, Bug 5 thinking fix

- Phase 12: FeedbackRepository + td_feedback 테이블, Gradio 👍/👎 이벤트, run_id 추적, LangSmith create_feedback() 연동
- Phase 13: 커스텀 _SemanticSplitter 제거 → langchain_experimental.SemanticChunker 교체, buffer_size/threshold_type 환경변수 적용
- Phase 13-B: RerankService (Cross-Encoder), RetrieverService.search()에 reranker 통합, tools.py as_retriever() → search() 전환
- Bug 5: mlx_chat_model enable_thinking 런타임 오버라이드, agent_service stream_mode=["messages","custom"] 이중 스트림, thinking 토큰 custom 이벤트로 emit
- ROADMAP: LLM 모델명 8B 반영, RAG에 Reranker 추가, 추천 진행 순서 갱신

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

services/db/mysql_service.py

@@ -99,6 +99,17 @@ class DatabaseService:
                 UNIQUE KEY uq_user_key (user_id, key_name)
             )
         """)
+        cursor.execute("""
+            CREATE TABLE IF NOT EXISTS td_feedback (
+                id INT AUTO_INCREMENT PRIMARY KEY,
+                user_id VARCHAR(50) NOT NULL DEFAULT 'default',
+                message TEXT,
+                response TEXT,
+                rating TINYINT,
+                langsmith_run_id VARCHAR(100),
+                created_at DATETIME DEFAULT CURRENT_TIMESTAMP
+            )
+        """)
         conn.commit()
         self._migrate_schema(conn)