- **Bootstrap IoC-based architecture with modular services.**

- **Implement `MlxModelService` for local LLM backend.**
- **Introduce `DatabaseService` for MySQL integration.**
- **Add `HistoryService` to manage conversation context.**
- **Set up CLI interface via `CliUiService`.**
- **Establish EventBus for token streaming.**
- **Include conversation repository for data persistence.**
- **Add environment-based configuration management.**
- **Draft IoC architectural plan.**

services/ui/cli_service.py

@@ -0,0 +1,23 @@
+class CliUiService:
+    """CLI 입출력 서비스."""
+
+    def show_banner(self, model_id: str) -> None:
+        print(f"모델 로딩 중: {model_id}")
+        print("(첫 실행 시 HuggingFace에서 자동 다운로드됩니다. 약 4.5GB)\n")
+        print("=" * 50)
+        print("육아 & 금융 상담 챗봇 시작!")
+        print("종료: '종료' / 'quit' / 'exit' 입력")
+        print("초기화: 'reset' 또는 'clear' 입력")
+        print("=" * 50 + "\n")
+
+    def prompt_user(self) -> str:
+        return input("나: ").strip()
+
+    def show_assistant_prefix(self) -> None:
+        print("\n도우미: ", end="", flush=True)
+
+    def is_exit_command(self, text: str) -> bool:
+        return text.lower() in ("종료", "quit", "exit")
+
+    def is_reset_command(self, text: str) -> bool:
+        return text.lower() in ("reset", "clear", "초기화")