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/feedback_repository.py

@@ -0,0 +1,19 @@
+class FeedbackRepository:
+    def __init__(self, db):
+        self._db = db
+
+    def save_feedback(
+        self,
+        user_id: str,
+        message: str,
+        response: str,
+        rating: int,
+        langsmith_run_id: str | None = None,
+    ) -> None:
+        self._db.execute_write(
+            """
+            INSERT INTO td_feedback (user_id, message, response, rating, langsmith_run_id)
+            VALUES (%s, %s, %s, %s, %s)
+            """,
+            (user_id, message, response, rating, langsmith_run_id),
+        )