fix(lotto-evolver): previous_base diff + 일요일 cron skip + idempotent evaluate

- weight_evolver.evaluate_weekly: save_base_history 직전에 current_base를
  previous_base로 캡처해 return dict에 포함 → formatter가 진짜 diff 표시 가능
- evaluate_weekly: same effective_from row 이미 존재 시 save skip + idempotent
  return (토 22:00 lotto cron과 agent-office 22:15 재호출 중복 row 방지)
- main._run_weight_evolver_daily: 일요일(weekday=6) 도 skip — 토요일 trial을
  INSERT OR REPLACE로 덮어쓰는 문제 방지
- telegram_lotto._format_evolution_report: eval_result.previous_base 우선
  사용 (없으면 current_base 폴백) → diff 자기 자신 비교 버그 수정
- test_lotto_evolution_format: previous_base 키 추가 + 새 diff 검증 테스트

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

lotto/app/weight_evolver.py

@@ -277,8 +277,24 @@ def evaluate_weekly() -> Dict[str, Any]:
     )
 
     next_monday = today + timedelta(days=(7 - today.weekday()) % 7 or 7)
+    next_monday_iso = next_monday.isoformat()
+
+    # Idempotent guard: 같은 effective_from으로 이미 저장된 row가 있으면 skip
+    existing = db.get_base_history(limit=1)
+    if existing and existing[0]["effective_from"] == next_monday_iso:
+        return {
+            "ok": True,
+            "draw_no": latest["drw_no"],
+            "week_start": week_start,
+            "previous_base": existing[0].get("weight"),
+            "winner": winner,
+            "new_base": existing[0]["weight"],   # 이미 저장된 값
+            "update_reason": existing[0].get("update_reason", "idempotent_skip"),
+            "per_day": per_day,
+        }
+
     db.save_base_history(
-        effective_from=next_monday.isoformat(),
+        effective_from=next_monday_iso,
         weight=new_base,
         source_trial_id=winner["trial_id"],
         update_reason=reason,
@@ -290,6 +306,7 @@ def evaluate_weekly() -> Dict[str, Any]:
         "ok": True,
         "draw_no": latest["drw_no"],
         "week_start": week_start,
+        "previous_base": current_base,   # save 이전에 캡처한 값 — diff 계산용
         "winner": winner,
         "new_base": new_base,
         "update_reason": reason,