Implement Phase 4~14: LangGraph Agent, RAG pipeline, Gradio Web UI, voice interface

- Upgrade LLM to Qwen3-14B-4bit with Thinking mode (MlxChatModel as LangChain BaseChatModel)
- Add LangGraph ReAct agent with tool calling loop (search_documents, web_search, get_current_date, remember/recall_user_info)
- Add RAG pipeline: BAAI/bge-m3 embeddings + Qdrant vector store + semantic chunking (SemanticSplitter via cosine similarity)
- Replace fixed-size RecursiveCharacterTextSplitter with meaning-based SemanticSplitter (numpy only, no extra deps)
- Add Gradio Web UI (app.py): chat, document ingestion, document management tabs
- Add multi-user support (user_id isolation in DB + per-user agent cache + dropdown selector)
- Add conversation history restore from MySQL on agent init (Phase 11)
- Add UserProfileRepository for persistent user profile (remember/recall tools)
- Add thread-local DB connections to fix pymysql thread-safety with LangGraph ToolNode
- Add Phase 14 voice interface: Whisper STT (microphone → text) + macOS TTS (say -v Yuna)
- Enforce search_documents-first policy in system prompt and tool descriptions
- Update ROADMAP2.md: Phase 14 완료, Phase 13 청킹 부분 완료

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

main.py

@@ -1,25 +1,23 @@
+import asyncio
+
+from dotenv import load_dotenv
+load_dotenv()
+
 from container import Container
-from services.chat.chat_service import ChatService
 
 
-def main() -> None:
+async def main_async() -> None:
     container = Container()
-
     ui = container.ui_service()
-    model = container.model_service()
-    bus = container.event_bus()
+
     db = container.db_service()
-    repo = container.conversation_repository()
-
-    bus.subscribe(ChatService.EVENT_TOKEN, container.stream_token_handler())
-    bus.subscribe(ChatService.EVENT_END, container.stream_end_handler())
-
-    ui.show_banner(container.config().model_id)
-    model.load()
     db.connect()
     db.init_schema()
 
-    chat = container.chat_service()
+    ui.show_banner(container.config().model_id)
+
+    # AgentService 초기화 — MlxChatModel 모델 로딩 + LangGraph 그래프 구성 포함
+    agent = container.agent_service()
 
     while True:
         try:
@@ -36,15 +34,18 @@ def main() -> None:
             break
 
         if ui.is_reset_command(user_input):
-            repo.create_conversation()
-            chat = container.chat_service()
+            agent.reset()
             print("\n[대화가 초기화되었습니다.]\n")
             continue
 
         ui.show_assistant_prefix()
-        chat.respond(user_input)
+        async for token in agent.stream_response(user_input):
+            print(token, end="", flush=True)
+        print("\n")
 
-    db.close()
+
+def main() -> None:
+    asyncio.run(main_async())
 
 
 if __name__ == "__main__":