fix: address follow-up review findings

- fix(notifier): capture fire-and-forget Future exceptions via done_callback
- fix(bot): add _close_event.set() in SYNC path to unblock _close_and_reenter
- fix(ml_features): apply z-score to oi_price_spread (oi_z - ret_1_z) matching training
- fix(backtester): clean up import ordering after _calc_trade_stats extraction
- fix(backtester): correct Sharpe annualization for 24/7 crypto (365d × 96 = 35,040)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/backtester.py

@@ -6,14 +6,20 @@
 from __future__ import annotations
 
 import json
+import warnings
 from dataclasses import dataclass, field, asdict
 from datetime import datetime
 from pathlib import Path
 
+import joblib
+import lightgbm as lgb
 import numpy as np
 import pandas as pd
 from loguru import logger
 
+# 크립토 24/7 시장: 15분봉 × 96봉/일 × 365일 = 35,040
+_ANNUALIZE_FACTOR = 35_040
+
 
 def _calc_trade_stats(trades: list[dict], initial_balance: float) -> dict:
     """거래 리스트에서 통계 요약을 계산한다. Backtester와 WalkForward 공통 사용."""
@@ -43,7 +49,7 @@ def _calc_trade_stats(trades: list[dict], initial_balance: float) -> dict:
 
     if len(pnls) > 1:
         pnl_arr = np.array(pnls)
-        sharpe = float(np.mean(pnl_arr) / np.std(pnl_arr) * np.sqrt(24192)) if np.std(pnl_arr) > 0 else 0.0
+        sharpe = float(np.mean(pnl_arr) / np.std(pnl_arr) * np.sqrt(_ANNUALIZE_FACTOR)) if np.std(pnl_arr) > 0 else 0.0
     else:
         sharpe = 0.0
 
@@ -81,11 +87,6 @@ def _calc_trade_stats(trades: list[dict], initial_balance: float) -> dict:
         "close_reasons": reasons,
     }
 
-import warnings
-
-import joblib
-import lightgbm as lgb
-
 from src.dataset_builder import (
     _calc_indicators, _calc_signals, _calc_features_vectorized,
     generate_dataset_vectorized, stratified_undersample,