perf: use a goroutine to handle quota post consumption (#364)

controller/relay-text.go

@@ -305,9 +305,12 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 	}
 	}
 
 
 	var textResponse TextResponse
 	var textResponse TextResponse
+	tokenName := c.GetString("token_name")
+	channelId := c.GetInt("channel_id")
 
 
 	defer func() {
 	defer func() {
-		c.Writer.Flush()
+		// c.Writer.Flush()
+		go func() {
 			if consumeQuota {
 			if consumeQuota {
 				quota := 0
 				quota := 0
 				completionRatio := 1.0
 				completionRatio := 1.0
@@ -342,15 +345,15 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 					common.SysError("error update user quota cache: " + err.Error())
 					common.SysError("error update user quota cache: " + err.Error())
 				}
 				}
 				if quota != 0 {
 				if quota != 0 {
-				tokenName := c.GetString("token_name")
 					logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
 					logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
 					model.RecordConsumeLog(userId, promptTokens, completionTokens, textRequest.Model, tokenName, quota, logContent)
 					model.RecordConsumeLog(userId, promptTokens, completionTokens, textRequest.Model, tokenName, quota, logContent)
 					model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
 					model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
-				channelId := c.GetInt("channel_id")
+
 					model.UpdateChannelUsedQuota(channelId, quota)
 					model.UpdateChannelUsedQuota(channelId, quota)
 				}
 				}
 			}
 			}
 		}()
 		}()
+	}()
 	switch apiType {
 	switch apiType {
 	case APITypeOpenAI:
 	case APITypeOpenAI:
 		if isStream {
 		if isStream {