feat: AI 서비스 MLX 듀얼 백엔드 및 모델 최적화

- MLX(맥미니 27B) 우선 → Ollama(조립컴 9B) fallback 구조
- pydantic-settings 기반 config 전환
- health check에 MLX 상태 추가
- 텍스트 모델 qwen3:8b → qwen3.5:9b-q8_0 변경

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

ai-service/routers/daily_report.py

@@ -1,4 +1,4 @@
-from fastapi import APIRouter, Request
+from fastapi import APIRouter, HTTPException, Request
 from pydantic import BaseModel
 from services.report_service import generate_daily_report
 from datetime import date
@@ -19,7 +19,7 @@ async def daily_report(req: DailyReportRequest, request: Request):
         result = await generate_daily_report(report_date, req.project_id, token)
         return {"available": True, **result}
     except Exception as e:
-        return {"available": False, "error": str(e)}
+        raise HTTPException(status_code=500, detail="AI 서비스 처리 중 오류가 발생했습니다")
 
 
 @router.post("/report/preview")
@@ -30,4 +30,4 @@ async def report_preview(req: DailyReportRequest, request: Request):
         result = await generate_daily_report(report_date, req.project_id, token)
         return {"available": True, "preview": True, **result}
     except Exception as e:
-        return {"available": False, "error": str(e)}
+        raise HTTPException(status_code=500, detail="AI 서비스 처리 중 오류가 발생했습니다")