fix: harden concurrent quota and status updates

service/billing_session.go

@@ -1,6 +1,7 @@
 package service
 
 import (
+	"errors"
 	"fmt"
 	"net/http"
 	"strings"
@@ -214,6 +215,16 @@ func (s *BillingSession) preConsume(c *gin.Context, quota int) *types.NewAPIErro
 			s.tokenConsumed = 0
 		}
 		// TODO: model 层应定义哨兵错误（如 ErrNoActiveSubscription），用 errors.Is 替代字符串匹配
+		if errors.Is(err, ErrInsufficientWalletQuota) {
+			userQuota, quotaErr := model.GetUserQuota(s.relayInfo.UserId, false)
+			if quotaErr != nil {
+				userQuota = 0
+			}
+			return types.NewErrorWithStatusCode(
+				fmt.Errorf("用户额度不足, 剩余额度: %s", logger.FormatQuota(userQuota)),
+				types.ErrorCodeInsufficientUserQuota, http.StatusForbidden,
+				types.ErrOptionWithSkipRetry(), types.ErrOptionWithNoRecordErrorLog())
+		}
 		errMsg := err.Error()
 		if strings.Contains(errMsg, "no active subscription") || strings.Contains(errMsg, "subscription quota insufficient") {
 			return types.NewErrorWithStatusCode(fmt.Errorf("订阅额度不足或未配置订阅: %s", errMsg), types.ErrorCodeInsufficientUserQuota, http.StatusForbidden, types.ErrOptionWithSkipRetry(), types.ErrOptionWithNoRecordErrorLog())