fix: timezone handling and prediction logic

- api/models.py: Fix timezone conversion in stats queries by calculating UTC ranges in Python instead of using SQL CONVERT_TZ. Ensure JSON serializable types.
- api/prediction_service.py:
    - Update ensure_predictions_for_month to check previous day (ET) to cover CST month start.
    - Update _generate_prediction_for_hour to skip saving unclosed candles (current hour).
- trader/auto_trade_polymarket.py: Update to use hourly_model_predictions (V2) table for storing live trading predictions.

api/models.py

@@ -4,7 +4,7 @@
 import pymysql
 import os
 from typing import Optional, List, Dict
-from datetime import datetime
+from datetime import datetime, timedelta
 from contextlib import contextmanager
 from zoneinfo import ZoneInfo
 from dotenv import load_dotenv
@@ -340,7 +340,29 @@ class PredictionModel:
     def get_monthly_stats_v2(month: str) -> Dict:
         """
         获取月度统计 (V2 - 从宽表)
+        修改：不使用 SQL 进行时区转换和格式化，而是查询 UTC 时间范围，然后在 Python 中处理
         """
+        # 计算 UTC 时间范围
+        try:
+            year, mon = map(int, month.split('-'))
+            start_date_cst = datetime(year, mon, 1, tzinfo=TZ_CST)
+            # 下个月第一天
+            if mon == 12:
+                end_date_cst = datetime(year + 1, 1, 1, tzinfo=TZ_CST)
+            else:
+                end_date_cst = datetime(year, mon + 1, 1, tzinfo=TZ_CST)
+            
+            # 转换为 UTC
+            start_dt_utc = start_date_cst.astimezone(TZ_UTC)
+            end_dt_utc = end_date_cst.astimezone(TZ_UTC)
+            
+            start_str = start_dt_utc.strftime('%Y-%m-%d %H:%M:%S')
+            end_str = end_dt_utc.strftime('%Y-%m-%d %H:%M:%S')
+            
+        except Exception as e:
+            print(f"日期解析错误: {e}")
+            return {}
+
         with get_db_connection() as conn:
             cursor = conn.cursor()
             
@@ -352,25 +374,26 @@ class PredictionModel:
                 col_pred = f"{model}_prediction"
                 col_correct = f"{model}_correct"
                 
+                # 查询 UTC 时间范围内的所有数据
                 sql = f"""
                     SELECT 
                         COUNT({col_pred}) as total,
                         SUM(CASE WHEN {col_correct} = 1 THEN 1 ELSE 0 END) as correct,
                         SUM(CASE WHEN {col_correct} = 0 THEN 1 ELSE 0 END) as incorrect
                     FROM hourly_model_predictions 
-                    WHERE DATE_FORMAT(CONVERT_TZ(timestamp, '+00:00', '+08:00'), '%%Y-%%m') = %s
+                    WHERE timestamp >= %s AND timestamp < %s
                       AND actual_result IS NOT NULL
                 """
-                cursor.execute(sql, (month,))
+                cursor.execute(sql, (start_str, end_str))
                 row = cursor.fetchone()
                 
                 if row:
-                    total = row['total']
-                    correct = row['correct'] or 0
-                    incorrect = row['incorrect'] or 0
+                    total = int(row['total'])
+                    correct = int(row['correct'] or 0)
+                    incorrect = int(row['incorrect'] or 0)
                     accuracy = (correct / total * 100) if total > 0 else 0
                     
-                    # 格式化键名以匹配前端 (例如 dlinear -> DLinear)
+                    # 格式化键名以匹配前端
                     model_key = {
                         'dlinear': 'DLinear', 
                         'nbeats': 'N-BEATS', 
@@ -391,55 +414,97 @@ class PredictionModel:
     def get_daily_stats_v2(month: str, page: int = 1, limit: int = 10) -> Dict:
         """
         获取每日统计 (V2 - 从宽表)
+        修改：不使用 SQL 进行时区转换，查询 UTC 范围，然后在 Python 中转换
         """
+        # 计算 UTC 时间范围
+        try:
+            year, mon = map(int, month.split('-'))
+            start_date_cst = datetime(year, mon, 1, tzinfo=TZ_CST)
+            if mon == 12:
+                end_date_cst = datetime(year + 1, 1, 1, tzinfo=TZ_CST)
+            else:
+                end_date_cst = datetime(year, mon + 1, 1, tzinfo=TZ_CST)
+            
+            start_dt_utc = start_date_cst.astimezone(TZ_UTC)
+            end_dt_utc = end_date_cst.astimezone(TZ_UTC)
+            
+            start_str = start_dt_utc.strftime('%Y-%m-%d %H:%M:%S')
+            end_str = end_dt_utc.strftime('%Y-%m-%d %H:%M:%S')
+        except Exception:
+            return {"data": [], "page": page, "limit": limit, "total": 0, "total_pages": 0}
+
         with get_db_connection() as conn:
             cursor = conn.cursor()
             
-            # 分页查询日期
-            offset = (page - 1) * limit
-            date_sql = """
-                SELECT DISTINCT DATE(CONVERT_TZ(timestamp, '+00:00', '+08:00')) as date_cst
+            # 获取范围内的所有原始数据
+            # 我们需要 timestamp, actual_result, 和各模型的 prediction/correct
+            # 为了按 CST 日期分组，我们需要取出每一行，然后在 Python 中转换时间
+            
+            sql = """
+                SELECT 
+                    timestamp,
+                    actual_result,
+                    dlinear_prediction, dlinear_correct,
+                    nbeats_prediction, nbeats_correct,
+                    ttm_prediction, ttm_correct,
+                    ensemble_prediction, ensemble_correct
                 FROM hourly_model_predictions
-                WHERE DATE_FORMAT(CONVERT_TZ(timestamp, '+00:00', '+08:00'), '%%Y-%%m') = %s
-                ORDER BY date_cst DESC
-                LIMIT %s OFFSET %s
+                WHERE timestamp >= %s AND timestamp < %s
+                  AND actual_result IS NOT NULL
+                ORDER BY timestamp DESC
             """
-            cursor.execute(date_sql, (month, limit, offset))
-            dates = [row['date_cst'] for row in cursor.fetchall()]
+            cursor.execute(sql, (start_str, end_str))
+            rows = cursor.fetchall()
             
-            # 总天数
-            count_sql = """
-                SELECT COUNT(DISTINCT DATE(CONVERT_TZ(timestamp, '+00:00', '+08:00'))) as cnt
-                FROM hourly_model_predictions
-                WHERE DATE_FORMAT(CONVERT_TZ(timestamp, '+00:00', '+08:00'), '%%Y-%%m') = %s
-            """
-            cursor.execute(count_sql, (month,))
-            total_count = cursor.fetchone()['cnt']
+            # 在 Python 中处理分组
+            daily_stats = {} # { "YYYY-MM-DD": { "date": "...", "dlinear": {...}, ... } }
             
-            daily_data = []
-            models = ['dlinear', 'nbeats', 'ttm', 'ensemble']
-            
-            for date_obj in dates:
-                date_str = str(date_obj)
-                day_stats = {"date": date_str}
+            for row in rows:
+                # 转换 timestamp 到 CST
+                ts_utc = row['timestamp']
+                # 确保是带时区的 datetime
+                if isinstance(ts_utc, str):
+                    ts_utc = datetime.fromisoformat(str(ts_utc).replace('Z', '+00:00'))
+                if ts_utc.tzinfo is None:
+                    ts_utc = ts_utc.replace(tzinfo=TZ_UTC)
                 
+                ts_cst = ts_utc.astimezone(TZ_CST)
+                date_str = ts_cst.strftime('%Y-%m-%d')
+                
+                if date_str not in daily_stats:
+                    daily_stats[date_str] = {
+                        "date": date_str,
+                        "raw_data": {m: {"total": 0, "correct": 0} for m in ['dlinear', 'nbeats', 'ttm', 'ensemble']}
+                    }
+                
+                # 累加统计
+                models = ['dlinear', 'nbeats', 'ttm', 'ensemble']
                 for model in models:
-                    col_pred = f"{model}_prediction"
-                    col_correct = f"{model}_correct"
+                    pred = row[f"{model}_prediction"]
+                    correct_flag = row[f"{model}_correct"]
                     
-                    sql = f"""
-                        SELECT 
-                            COUNT({col_pred}) as total,
-                            SUM(CASE WHEN {col_correct} = 1 THEN 1 ELSE 0 END) as correct
-                        FROM hourly_model_predictions
-                        WHERE DATE(CONVERT_TZ(timestamp, '+00:00', '+08:00')) = %s
-                          AND actual_result IS NOT NULL
-                    """
-                    cursor.execute(sql, (date_str,))
-                    row = cursor.fetchone()
-                    
-                    total = row['total']
-                    correct = row['correct'] or 0
+                    if pred is not None:
+                        daily_stats[date_str]['raw_data'][model]['total'] += 1
+                        if correct_flag == 1:
+                            daily_stats[date_str]['raw_data'][model]['correct'] += 1
+
+            # 整理为最终格式
+            sorted_dates = sorted(daily_stats.keys(), reverse=True)
+            total_count = len(sorted_dates)
+            
+            # 分页
+            offset = (page - 1) * limit
+            paginated_dates = sorted_dates[offset:offset + limit]
+            
+            result_data = []
+            for date_key in paginated_dates:
+                day_item = daily_stats[date_key]
+                formatted_item = {"date": day_item["date"]}
+                
+                for model in ['dlinear', 'nbeats', 'ttm', 'ensemble']:
+                    raw = day_item['raw_data'][model]
+                    total = int(raw['total'])
+                    correct = int(raw['correct'])
                     accuracy = (correct / total * 100) if total > 0 else 0
                     
                     model_key = {
@@ -449,16 +514,15 @@ class PredictionModel:
                         'ensemble': 'Ensemble'
                     }.get(model, model)
                     
-                    day_stats[model_key] = {
+                    formatted_item[model_key] = {
                         "total": total,
                         "correct": correct,
                         "accuracy": round(accuracy, 2)
                     }
-                
-                daily_data.append(day_stats)
+                result_data.append(formatted_item)
             
             return {
-                "data": daily_data,
+                "data": result_data,
                 "page": page,
                 "limit": limit,
                 "total": total_count,
@@ -469,25 +533,46 @@ class PredictionModel:
     def get_hourly_details_v2(date: str) -> List[Dict]:
         """
         获取指定日期的每小时详情 (V2)
+        修改：根据传入的 CST 日期计算 UTC 范围，查询该范围内的数据
         """
+        try:
+            # date 是 'YYYY-MM-DD' (CST)
+            date_cst_start = datetime.strptime(date, '%Y-%m-%d').replace(tzinfo=TZ_CST)
+            date_cst_end = date_cst_start + timedelta(days=1)
+            
+            start_dt_utc = date_cst_start.astimezone(TZ_UTC)
+            end_dt_utc = date_cst_end.astimezone(TZ_UTC)
+            
+            start_str = start_dt_utc.strftime('%Y-%m-%d %H:%M:%S')
+            end_str = end_dt_utc.strftime('%Y-%m-%d %H:%M:%S')
+        except Exception as e:
+            print(f"日期处理错误: {e}")
+            return []
+
         with get_db_connection() as conn:
             cursor = conn.cursor()
             cursor.execute("""
-                SELECT 
-                    *,
-                    HOUR(CONVERT_TZ(timestamp, '+00:00', '+08:00')) as hour_cst,
-                    CONVERT_TZ(timestamp, '+00:00', '+08:00') as timestamp_cst_dt
+                SELECT *
                 FROM hourly_model_predictions 
-                WHERE DATE(CONVERT_TZ(timestamp, '+00:00', '+08:00')) = %s
-                ORDER BY hour_cst
-            """, (date,))
+                WHERE timestamp >= %s AND timestamp < %s
+                ORDER BY timestamp ASC
+            """, (start_str, end_str))
             
             rows = cursor.fetchall()
             result = []
             
             for row in rows:
+                # 计算 CST 小时用于显示排序 (虽然 SQL 已经按 timestamp 排序了，但为了确保前端显示 hour 字段正确)
+                ts_utc = row['timestamp']
+                if isinstance(ts_utc, str):
+                    ts_utc = datetime.fromisoformat(str(ts_utc).replace('Z', '+00:00'))
+                if ts_utc.tzinfo is None:
+                    ts_utc = ts_utc.replace(tzinfo=TZ_UTC)
+                ts_cst = ts_utc.astimezone(TZ_CST)
+                hour_cst = ts_cst.hour
+                
                 hour_data = {
-                    "hour": row['hour_cst'],
+                    "hour": hour_cst,
                     "timestamp_et": row['timestamp_et'],
                     "timestamp_cst": convert_to_cst(row.get('timestamp', '')),
                     "open_price": row['open_price'],