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>

agent-office/app/notifiers/telegram_lotto.py

@@ -199,7 +199,8 @@ def _format_evolution_report(eval_result: Dict[str, Any], current_base: List[flo
         "",
         f"📊 다음주 base 변경 ({reason}):",
     ]
-    base_now = current_base or [0.2] * 5
+    # 우선순위: eval_result.previous_base > current_base (eval 직후 stale) > 균등 fallback
+    base_now = eval_result.get("previous_base") or current_base or [0.2] * 5
     for i, (cur, new) in enumerate(zip(base_now, new_base)):
         diff = new - cur
         if abs(diff) < 0.005:

agent-office/tests/test_lotto_evolution_format.py

@@ -17,6 +17,7 @@ def test_evolution_report_winner_4plus():
             "n_picks": 5,
         },
         "new_base": [0.18, 0.32, 0.20, 0.22, 0.08],
+        "previous_base": [0.20, 0.20, 0.20, 0.20, 0.20],
         "update_reason": "winner_4plus",
         "per_day": [
             {"day_of_week": 0, "avg_score": 0.20, "max_correct": 2},
@@ -58,3 +59,29 @@ def test_evolution_report_empty_returns_empty():
     """evaluate가 ok=False면 빈 문자열 (발송 skip)."""
     text = _format_evolution_report({"ok": False, "reason": "no_trials"}, [0.2]*5)
     assert text == ""
+
+
+def test_evolution_report_uses_previous_base_for_diff():
+    """previous_base와 new_base 차이가 메시지 diff에 정확히 반영됨."""
+    eval_result = {
+        "ok": True,
+        "draw_no": 1227,
+        "winner": {
+            "day_of_week": 0,
+            "weight": [0.30, 0.20, 0.20, 0.20, 0.10],
+            "avg_score": 0.50,
+            "max_correct": 4,
+            "n_picks": 5,
+        },
+        "new_base": [0.30, 0.20, 0.20, 0.20, 0.10],
+        "previous_base": [0.20, 0.20, 0.20, 0.20, 0.20],
+        "update_reason": "winner_4plus",
+    }
+    # current_base는 stale (post-update 값) — previous_base가 우선 적용되어야 함
+    text = _format_evolution_report(eval_result, [0.30, 0.20, 0.20, 0.20, 0.10])
+    # freq: 0.20 → 0.30 (+0.10 = "++")
+    # divers: 0.20 → 0.10 (-0.10 = "--")
+    assert "0.20 → 0.30" in text   # freq 증가
+    assert "0.20 → 0.10" in text   # divers 감소
+    assert "(++)" in text or "(+)" in text   # freq marker
+    assert "(--)" in text or "(-)" in text   # divers marker