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>

ingest.py

@@ -0,0 +1,28 @@
+"""문서 수집 CLI.
+
+사용법:
+    python ingest.py <파일경로> [<파일경로> ...]
+
+예시:
+    python ingest.py docs/육아가이드.pdf docs/금융상품안내.txt
+"""
+import sys
+from container import Container
+
+
+def main() -> None:
+    files = sys.argv[1:]
+    if not files:
+        print("사용법: python ingest.py <파일경로> [<파일경로> ...]")
+        sys.exit(1)
+
+    container = Container()
+    service = container.ingestion_service()
+
+    print(f"{len(files)}개 파일 수집 시작...")
+    count = service.ingest(files)
+    print(f"완료: {count}개 청크가 Qdrant({container.config().qdrant_url})에 저장되었습니다.")
+
+
+if __name__ == "__main__":
+    main()