删除relay-text中的consumeQuota变量

controller/relay-openai.go

@@ -88,9 +88,8 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
 	return nil, responseText
 	return nil, responseText
 }
 }
 
 
-func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool, promptTokens int, model string) (*OpenAIErrorWithStatusCode, *Usage) {
+func openaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*OpenAIErrorWithStatusCode, *Usage) {
 	var textResponse TextResponse
 	var textResponse TextResponse
-	if consumeQuota {
 	responseBody, err := io.ReadAll(resp.Body)
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
 	if err != nil {
 		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
 		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
@@ -111,7 +110,6 @@ func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool, promp
 	}
 	}
 	// Reset response body
 	// Reset response body
 	resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
 	resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
-	}
 	// We shouldn't set the header before we parse the response body, because the parse part may fail.
 	// We shouldn't set the header before we parse the response body, because the parse part may fail.
 	// And then we will have to send an error response, but in this case, the header has already been set.
 	// And then we will have to send an error response, but in this case, the header has already been set.
 	// So the httpClient will be confused by the response.
 	// So the httpClient will be confused by the response.
@@ -120,7 +118,7 @@ func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool, promp
 		c.Writer.Header().Set(k, v[0])
 		c.Writer.Header().Set(k, v[0])
 	}
 	}
 	c.Writer.WriteHeader(resp.StatusCode)
 	c.Writer.WriteHeader(resp.StatusCode)
-	_, err := io.Copy(c.Writer, resp.Body)
+	_, err = io.Copy(c.Writer, resp.Body)
 	if err != nil {
 	if err != nil {
 		return errorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), nil
 		return errorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), nil
 	}
 	}

controller/relay-text.go

@@ -50,10 +50,9 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 	channelId := c.GetInt("channel_id")
 	channelId := c.GetInt("channel_id")
 	tokenId := c.GetInt("token_id")
 	tokenId := c.GetInt("token_id")
 	userId := c.GetInt("id")
 	userId := c.GetInt("id")
-	consumeQuota := c.GetBool("consume_quota")
 	group := c.GetString("group")
 	group := c.GetString("group")
 	var textRequest GeneralOpenAIRequest
 	var textRequest GeneralOpenAIRequest
-	if consumeQuota || channelType == common.ChannelTypeAzure || channelType == common.ChannelTypePaLM {
+	if channelType == common.ChannelTypeAzure || channelType == common.ChannelTypePaLM {
 		err := common.UnmarshalBodyReusable(c, &textRequest)
 		err := common.UnmarshalBodyReusable(c, &textRequest)
 		if err != nil {
 		if err != nil {
 			return errorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
 			return errorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
@@ -236,7 +235,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 		preConsumedQuota = 0
 		preConsumedQuota = 0
 		//common.LogInfo(c.Request.Context(), fmt.Sprintf("user %d has enough quota %d, trusted and no need to pre-consume", userId, userQuota))
 		//common.LogInfo(c.Request.Context(), fmt.Sprintf("user %d has enough quota %d, trusted and no need to pre-consume", userId, userQuota))
 	}
 	}
-	if consumeQuota && preConsumedQuota > 0 {
+	if preConsumedQuota > 0 {
 		userQuota, err = model.PreConsumeTokenQuota(tokenId, preConsumedQuota)
 		userQuota, err = model.PreConsumeTokenQuota(tokenId, preConsumedQuota)
 		if err != nil {
 		if err != nil {
 			return errorWrapper(err, "pre_consume_token_quota_failed", http.StatusForbidden)
 			return errorWrapper(err, "pre_consume_token_quota_failed", http.StatusForbidden)
@@ -420,7 +419,6 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 	defer func(ctx context.Context) {
 	defer func(ctx context.Context) {
 		// c.Writer.Flush()
 		// c.Writer.Flush()
 		go func() {
 		go func() {
-			if consumeQuota {
 			quota := 0
 			quota := 0
 			completionRatio := common.GetCompletionRatio(textRequest.Model)
 			completionRatio := common.GetCompletionRatio(textRequest.Model)
 			promptTokens = textResponse.Usage.PromptTokens
 			promptTokens = textResponse.Usage.PromptTokens
@@ -454,7 +452,6 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			//if quota != 0 {
 			//if quota != 0 {
 			//
 			//
 			//}
 			//}
-			}
 		}()
 		}()
 	}(c.Request.Context())
 	}(c.Request.Context())
 	switch apiType {
 	switch apiType {
@@ -468,7 +465,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
 			textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
 			return nil
 			return nil
 		} else {
 		} else {
-			err, usage := openaiHandler(c, resp, consumeQuota, promptTokens, textRequest.Model)
+			err, usage := openaiHandler(c, resp, promptTokens, textRequest.Model)
 			if err != nil {
 			if err != nil {
 				return err
 				return err
 			}
 			}