fix: fix preConsumeQuota error

relay/relay-text.go

@@ -113,7 +113,7 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 	}
 	}
 
 
 	// pre-consume quota 预消耗配额
 	// pre-consume quota 预消耗配额
-	userQuota, openaiErr := preConsumeQuota(c, preConsumedQuota, relayInfo)
+	preConsumedQuota, userQuota, openaiErr := preConsumeQuota(c, preConsumedQuota, relayInfo)
 	if err != nil {
 	if err != nil {
 		return openaiErr
 		return openaiErr
 	}
 	}
@@ -153,7 +153,6 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 	if openaiErr != nil {
 	if openaiErr != nil {
 		return openaiErr
 		return openaiErr
 	}
 	}
-
 	postConsumeQuota(c, relayInfo, *textRequest, usage, ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice)
 	postConsumeQuota(c, relayInfo, *textRequest, usage, ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice)
 	return nil
 	return nil
 }
 }
@@ -178,17 +177,17 @@ func getPromptTokens(textRequest *dto.GeneralOpenAIRequest, info *relaycommon.Re
 }
 }
 
 
 // 预扣费并返回用户剩余配额
 // 预扣费并返回用户剩余配额
-func preConsumeQuota(c *gin.Context, preConsumedQuota int, relayInfo *relaycommon.RelayInfo) (int, *dto.OpenAIErrorWithStatusCode) {
+func preConsumeQuota(c *gin.Context, preConsumedQuota int, relayInfo *relaycommon.RelayInfo) (int, int, *dto.OpenAIErrorWithStatusCode) {
 	userQuota, err := model.CacheGetUserQuota(relayInfo.UserId)
 	userQuota, err := model.CacheGetUserQuota(relayInfo.UserId)
 	if err != nil {
 	if err != nil {
-		return 0, service.OpenAIErrorWrapper(err, "get_user_quota_failed", http.StatusInternalServerError)
+		return 0, 0, service.OpenAIErrorWrapper(err, "get_user_quota_failed", http.StatusInternalServerError)
 	}
 	}
 	if userQuota < 0 || userQuota-preConsumedQuota < 0 {
 	if userQuota < 0 || userQuota-preConsumedQuota < 0 {
-		return 0, service.OpenAIErrorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
+		return 0, 0, service.OpenAIErrorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
 	}
 	}
 	err = model.CacheDecreaseUserQuota(relayInfo.UserId, preConsumedQuota)
 	err = model.CacheDecreaseUserQuota(relayInfo.UserId, preConsumedQuota)
 	if err != nil {
 	if err != nil {
-		return 0, service.OpenAIErrorWrapper(err, "decrease_user_quota_failed", http.StatusInternalServerError)
+		return 0, 0, service.OpenAIErrorWrapper(err, "decrease_user_quota_failed", http.StatusInternalServerError)
 	}
 	}
 	if userQuota > 100*preConsumedQuota {
 	if userQuota > 100*preConsumedQuota {
 		// 用户额度充足，判断令牌额度是否充足
 		// 用户额度充足，判断令牌额度是否充足
@@ -210,10 +209,10 @@ func preConsumeQuota(c *gin.Context, preConsumedQuota int, relayInfo *relaycommo
 	if preConsumedQuota > 0 {
 	if preConsumedQuota > 0 {
 		userQuota, err = model.PreConsumeTokenQuota(relayInfo.TokenId, preConsumedQuota)
 		userQuota, err = model.PreConsumeTokenQuota(relayInfo.TokenId, preConsumedQuota)
 		if err != nil {
 		if err != nil {
-			return 0, service.OpenAIErrorWrapper(err, "pre_consume_token_quota_failed", http.StatusForbidden)
+			return 0, 0, service.OpenAIErrorWrapper(err, "pre_consume_token_quota_failed", http.StatusForbidden)
 		}
 		}
 	}
 	}
-	return userQuota, nil
+	return preConsumedQuota, userQuota, nil
 }
 }
 
 
 func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, textRequest dto.GeneralOpenAIRequest, usage *dto.Usage, ratio float64, preConsumedQuota int, userQuota int, modelRatio float64, groupRatio float64, modelPrice float64) {
 func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, textRequest dto.GeneralOpenAIRequest, usage *dto.Usage, ratio float64, preConsumedQuota int, userQuota int, modelRatio float64, groupRatio float64, modelPrice float64) {