Merge branch 'main' of https://github.com/songquanpeng/one-api

README.md

@@ -51,15 +51,15 @@ _✨ 通过标准的 OpenAI API 格式访问所有的大模型，开箱即用
   <a href="https://iamazing.cn/page/reward">赞赏支持</a>
 </p>
 
-> **Note**
+> [!NOTE]
 > 本项目为开源项目，使用者必须在遵循 OpenAI 的[使用条款](https://openai.com/policies/terms-of-use)以及**法律法规**的情况下使用，不得用于非法用途。
 > 
 > 根据[《生成式人工智能服务管理暂行办法》](http://www.cac.gov.cn/2023-07/13/c_1690898327029107.htm)的要求，请勿对中国地区公众提供一切未经备案的生成式人工智能服务。
 
-> **Warning**
+> [!WARNING]
 > 使用 Docker 拉取的最新镜像可能是 `alpha` 版本，如果追求稳定性请手动指定版本。
 
-> **Warning**
+> [!WARNING]
 > 使用 root 用户初次登录系统后，务必修改默认密码 `123456`！
 
 ## 功能

common/email.go

@@ -7,6 +7,7 @@ import (
 	"fmt"
 	"net/smtp"
 	"strings"
+	"time"
 )
 
 func SendEmail(subject string, receiver string, content string) error {
@@ -33,9 +34,9 @@ func SendEmail(subject string, receiver string, content string) error {
 		"From: %s<%s>\r\n"+
 		"Subject: %s\r\n"+
 		"Message-ID: %s\r\n"+ // add Message-ID header to avoid being treated as spam, RFC 5322
+		"Date: %s\r\n"+
 		"Content-Type: text/html; charset=UTF-8\r\n\r\n%s\r\n",
-		receiver, SystemName, SMTPFrom, encodedSubject, messageId, content))
+		receiver, SystemName, SMTPFrom, encodedSubject, messageId, time.Now().Format(time.RFC1123Z), content))
-
 	auth := smtp.PlainAuth("", SMTPAccount, SMTPToken, SMTPServer)
 	addr := fmt.Sprintf("%s:%d", SMTPServer, SMTPPort)
 	to := strings.Split(receiver, ";")

common/model-ratio.go

@@ -76,6 +76,8 @@ var ModelRatio = map[string]float64{
 	"dall-e-3":                  20,     // $0.040 - $0.120 / image
 	"claude-instant-1":          0.815,  // $1.63 / 1M tokens
 	"claude-2":                  5.51,   // $11.02 / 1M tokens
+	"claude-2.0":                5.51,   // $11.02 / 1M tokens
+	"claude-2.1":                5.51,   // $11.02 / 1M tokens
 	"ERNIE-Bot":                 0.8572, // ￥0.012 / 1k tokens
 	"ERNIE-Bot-turbo":           0.5715, // ￥0.008 / 1k tokens
 	"ERNIE-Bot-4":               8.572,  // ￥0.12 / 1k tokens

controller/model.go

@@ -360,6 +360,24 @@ func init() {
 			Root:       "claude-2",
 			Parent:     nil,
 		},
+		{
+			Id:         "claude-2.1",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "anthropic",
+			Permission: permission,
+			Root:       "claude-2.1",
+			Parent:     nil,
+		},
+		{
+			Id:         "claude-2.0",
+			Object:     "model",
+			Created:    1677649963,
+			OwnedBy:    "anthropic",
+			Permission: permission,
+			Root:       "claude-2.0",
+			Parent:     nil,
+		},
 		{
 			Id:         "ERNIE-Bot",
 			Object:     "model",

controller/relay-audio.go

@@ -5,11 +5,13 @@ import (
 	"context"
 	"encoding/json"
 	"errors"
+	"fmt"
 	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
+	"strings"
 )
 
 func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
@@ -37,41 +39,40 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 		}
 	}
 
-	preConsumedTokens := common.PreConsumedQuota
 	modelRatio := common.GetModelRatio(audioModel)
 	groupRatio := common.GetGroupRatio(group)
 	ratio := modelRatio * groupRatio
-	preConsumedQuota := int(float64(preConsumedTokens) * ratio)
+	var quota int
+	var preConsumedQuota int
+	switch relayMode {
+	case RelayModeAudioSpeech:
+		preConsumedQuota = int(float64(len(ttsRequest.Input)) * ratio)
+		quota = preConsumedQuota
+	default:
+		preConsumedQuota = int(float64(common.PreConsumedQuota) * ratio)
+	}
 	userQuota, err := model.CacheGetUserQuota(userId)
 	if err != nil {
 		return errorWrapper(err, "get_user_quota_failed", http.StatusInternalServerError)
 	}
 
-	quota := 0
 	// Check if user quota is enough
-	if relayMode == RelayModeAudioSpeech {
+	if userQuota-preConsumedQuota < 0 {
-		quota = int(float64(len(ttsRequest.Input)) * modelRatio * groupRatio)
+		return errorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
-		if quota > userQuota {
+	}
-			return errorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
+	err = model.CacheDecreaseUserQuota(userId, preConsumedQuota)
-		}
+	if err != nil {
-	} else {
+		return errorWrapper(err, "decrease_user_quota_failed", http.StatusInternalServerError)
-		if userQuota-preConsumedQuota < 0 {
+	}
-			return errorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
+	if userQuota > 100*preConsumedQuota {
-		}
+		// in this case, we do not pre-consume quota
-		err = model.CacheDecreaseUserQuota(userId, preConsumedQuota)
+		// because the user has enough quota
+		preConsumedQuota = 0
+	}
+	if preConsumedQuota > 0 {
+		err := model.PreConsumeTokenQuota(tokenId, preConsumedQuota)
 		if err != nil {
-			return errorWrapper(err, "decrease_user_quota_failed", http.StatusInternalServerError)
+			return errorWrapper(err, "pre_consume_token_quota_failed", http.StatusForbidden)
-		}
-		if userQuota > 100*preConsumedQuota {
-			// in this case, we do not pre-consume quota
-			// because the user has enough quota
-			preConsumedQuota = 0
-		}
-		if preConsumedQuota > 0 {
-			err := model.PreConsumeTokenQuota(tokenId, preConsumedQuota)
-			if err != nil {
-				return errorWrapper(err, "pre_consume_token_quota_failed", http.StatusForbidden)
-			}
 		}
 	}
 
@@ -95,13 +96,33 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 	}
 
 	fullRequestURL := getFullRequestURL(baseURL, requestURL, channelType)
+	if relayMode == RelayModeAudioTranscription && channelType == common.ChannelTypeAzure {
+		// https://learn.microsoft.com/en-us/azure/ai-services/openai/whisper-quickstart?tabs=command-line#rest-api
+		query := c.Request.URL.Query()
+		apiVersion := query.Get("api-version")
+		if apiVersion == "" {
+			apiVersion = c.GetString("api_version")
+		}
+		baseURL = c.GetString("base_url")
+		fullRequestURL = fmt.Sprintf("%s/openai/deployments/%s/audio/transcriptions?api-version=%s", baseURL, audioModel, apiVersion)
+	}
+
 	requestBody := c.Request.Body
 
 	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
 	if err != nil {
 		return errorWrapper(err, "new_request_failed", http.StatusInternalServerError)
 	}
-	req.Header.Set("Authorization", c.Request.Header.Get("Authorization"))
+
+	if relayMode == RelayModeAudioTranscription && channelType == common.ChannelTypeAzure {
+		// https://learn.microsoft.com/en-us/azure/ai-services/openai/whisper-quickstart?tabs=command-line#rest-api
+		apiKey := c.Request.Header.Get("Authorization")
+		apiKey = strings.TrimPrefix(apiKey, "Bearer ")
+		req.Header.Set("api-key", apiKey)
+		req.ContentLength = c.Request.ContentLength
+	} else {
+		req.Header.Set("Authorization", c.Request.Header.Get("Authorization"))
+	}
 	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
 	req.Header.Set("Accept", c.Request.Header.Get("Accept"))
 
@@ -119,11 +140,7 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 		return errorWrapper(err, "close_request_body_failed", http.StatusInternalServerError)
 	}
 
-	if relayMode == RelayModeAudioSpeech {
+	if relayMode != RelayModeAudioSpeech {
-		defer func(ctx context.Context) {
-			go postConsumeQuota(ctx, tokenId, quota, userId, channelId, modelRatio, groupRatio, audioModel, tokenName)
-		}(c.Request.Context())
-	} else {
 		responseBody, err := io.ReadAll(resp.Body)
 		if err != nil {
 			return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
@@ -137,13 +154,29 @@ func relayAudioHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 		if err != nil {
 			return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError)
 		}
-		defer func(ctx context.Context) {
+		quota = countTokenText(whisperResponse.Text, audioModel)
-			quota := countTokenText(whisperResponse.Text, audioModel)
-			quotaDelta := quota - preConsumedQuota
-			go postConsumeQuota(ctx, tokenId, quotaDelta, userId, channelId, modelRatio, groupRatio, audioModel, tokenName)
-		}(c.Request.Context())
 		resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
 	}
+	if resp.StatusCode != http.StatusOK {
+		if preConsumedQuota > 0 {
+			// we need to roll back the pre-consumed quota
+			defer func(ctx context.Context) {
+				go func() {
+					// negative means add quota back for token & user
+					err := model.PostConsumeTokenQuota(tokenId, -preConsumedQuota)
+					if err != nil {
+						common.LogError(ctx, fmt.Sprintf("error rollback pre-consumed quota: %s", err.Error()))
+					}
+				}()
+			}(c.Request.Context())
+		}
+		return relayErrorHandler(resp)
+	}
+	quotaDelta := quota - preConsumedQuota
+	defer func(ctx context.Context) {
+		go postConsumeQuota(ctx, tokenId, quotaDelta, quota, userId, channelId, modelRatio, groupRatio, audioModel, tokenName)
+	}(c.Request.Context())
+
 	for k, v := range resp.Header {
 		c.Writer.Header().Set(k, v[0])
 	}

controller/relay-claude.go

@@ -70,7 +70,9 @@ func requestOpenAI2Claude(textRequest GeneralOpenAIRequest) *ClaudeRequest {
 		} else if message.Role == "assistant" {
 			prompt += fmt.Sprintf("\n\nAssistant: %s", message.Content)
 		} else if message.Role == "system" {
-			prompt += fmt.Sprintf("\n\nSystem: %s", message.Content)
+			if prompt == "" {
+				prompt = message.StringContent()
+			}
 		}
 	}
 	prompt += "\n\nAssistant:"

controller/relay-image.go

@@ -35,15 +35,12 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 	channelId := c.GetInt("channel_id")
 	apiVersion := c.GetString("api_version")
 	userId := c.GetInt("id")
-	consumeQuota := c.GetBool("consume_quota")
 	group := c.GetString("group")
 
 	var imageRequest ImageRequest
-	if consumeQuota {
+	err := common.UnmarshalBodyReusable(c, &imageRequest)
-		err := common.UnmarshalBodyReusable(c, &imageRequest)
+	if err != nil {
-		if err != nil {
+		return errorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
-			return errorWrapper(err, "bind_request_body_failed", http.StatusBadRequest)
-		}
 	}
 
 	// Size validation
@@ -131,7 +128,7 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 
 	quota := int(ratio*imageCostRatio*1000) * imageRequest.N
 
-	if consumeQuota && userQuota-quota < 0 {
+	if userQuota-quota < 0 {
 		return errorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
 	}
 
@@ -166,43 +163,39 @@ func relayImageHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode
 	var textResponse ImageResponse
 
 	defer func(ctx context.Context) {
-		if consumeQuota {
+		err := model.PostConsumeTokenQuota(tokenId, quota)
-			err := model.PostConsumeTokenQuota(tokenId, quota)
+		if err != nil {
-			if err != nil {
+			common.SysError("error consuming token remain quota: " + err.Error())
-				common.SysError("error consuming token remain quota: " + err.Error())
+		}
-			}
+		err = model.CacheUpdateUserQuota(userId)
-			err = model.CacheUpdateUserQuota(userId)
+		if err != nil {
-			if err != nil {
+			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")
-				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(ctx, userId, channelId, 0, 0, imageModel, tokenName, quota, logContent)
-				model.RecordConsumeLog(ctx, userId, channelId, 0, 0, imageModel, tokenName, quota, logContent)
+			model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
-				model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
+			channelId := c.GetInt("channel_id")
-				channelId := c.GetInt("channel_id")
+			model.UpdateChannelUsedQuota(channelId, quota)
-				model.UpdateChannelUsedQuota(channelId, quota)
-			}
 		}
 	}(c.Request.Context())
 
-	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)
+		return errorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
-		}
-		err = resp.Body.Close()
-		if err != nil {
-			return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
-		}
-		err = json.Unmarshal(responseBody, &textResponse)
-		if err != nil {
-			return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError)
-		}
-
-		resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
 	}
+	err = resp.Body.Close()
+	if err != nil {
+		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError)
+	}
+	err = json.Unmarshal(responseBody, &textResponse)
+	if err != nil {
+		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError)
+	}
+
+	resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
 
 	for k, v := range resp.Header {
 		c.Writer.Header().Set(k, v[0])

controller/relay-openai.go

@@ -88,30 +88,29 @@ func openaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*O
 	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
-	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
-		}
-		err = resp.Body.Close()
-		if err != nil {
-			return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
-		}
-		err = json.Unmarshal(responseBody, &textResponse)
-		if err != nil {
-			return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
-		}
-		if textResponse.Error.Type != "" {
-			return &OpenAIErrorWithStatusCode{
-				OpenAIError: textResponse.Error,
-				StatusCode:  resp.StatusCode,
-			}, nil
-		}
-		// Reset response body
-		resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
 	}
+	err = resp.Body.Close()
+	if err != nil {
+		return errorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = json.Unmarshal(responseBody, &textResponse)
+	if err != nil {
+		return errorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	if textResponse.Error.Type != "" {
+		return &OpenAIErrorWithStatusCode{
+			OpenAIError: textResponse.Error,
+			StatusCode:  resp.StatusCode,
+		}, nil
+	}
+	// Reset response body
+	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.
 	// 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.
@@ -120,7 +119,7 @@ func openaiHandler(c *gin.Context, resp *http.Response, consumeQuota bool, promp
 		c.Writer.Header().Set(k, v[0])
 	}
 	c.Writer.WriteHeader(resp.StatusCode)
-	_, err := io.Copy(c.Writer, resp.Body)
+	_, err = io.Copy(c.Writer, resp.Body)
 	if err != nil {
 		return errorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError), nil
 	}

controller/relay-text.go

@@ -51,14 +51,11 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 	channelId := c.GetInt("channel_id")
 	tokenId := c.GetInt("token_id")
 	userId := c.GetInt("id")
-	consumeQuota := c.GetBool("consume_quota")
 	group := c.GetString("group")
 	var textRequest GeneralOpenAIRequest
-	if consumeQuota || 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)
-		}
 	}
 	if relayMode == RelayModeModerations && textRequest.Model == "" {
 		textRequest.Model = "text-moderation-latest"
@@ -235,7 +232,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 		preConsumedQuota = 0
 		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 {
 		err := model.PreConsumeTokenQuota(tokenId, preConsumedQuota)
 		if err != nil {
 			return errorWrapper(err, "pre_consume_token_quota_failed", http.StatusForbidden)
@@ -414,37 +411,36 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 	defer func(ctx context.Context) {
 		// c.Writer.Flush()
 		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
+			completionTokens = textResponse.Usage.CompletionTokens
-				completionTokens = textResponse.Usage.CompletionTokens
+			quota = int(math.Ceil((float64(promptTokens) + float64(completionTokens)*completionRatio) * ratio))
-				quota = int(math.Ceil((float64(promptTokens) + float64(completionTokens)*completionRatio) * ratio))
+			if ratio != 0 && quota <= 0 {
-				if ratio != 0 && quota <= 0 {
+				quota = 1
-					quota = 1
-				}
-				totalTokens := promptTokens + completionTokens
-				if totalTokens == 0 {
-					// in this case, must be some error happened
-					// we cannot just return, because we may have to return the pre-consumed quota
-					quota = 0
-				}
-				quotaDelta := quota - preConsumedQuota
-				err := model.PostConsumeTokenQuota(tokenId, quotaDelta)
-				if err != nil {
-					common.LogError(ctx, "error consuming token remain quota: "+err.Error())
-				}
-				err = model.CacheUpdateUserQuota(userId)
-				if err != nil {
-					common.LogError(ctx, "error update user quota cache: "+err.Error())
-				}
-				if quota != 0 {
-					logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
-					model.RecordConsumeLog(ctx, userId, channelId, promptTokens, completionTokens, textRequest.Model, tokenName, quota, logContent)
-					model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
-					model.UpdateChannelUsedQuota(channelId, quota)
-				}
 			}
+			totalTokens := promptTokens + completionTokens
+			if totalTokens == 0 {
+				// in this case, must be some error happened
+				// we cannot just return, because we may have to return the pre-consumed quota
+				quota = 0
+			}
+			quotaDelta := quota - preConsumedQuota
+			err := model.PostConsumeTokenQuota(tokenId, quotaDelta)
+			if err != nil {
+				common.LogError(ctx, "error consuming token remain quota: "+err.Error())
+			}
+			err = model.CacheUpdateUserQuota(userId)
+			if err != nil {
+				common.LogError(ctx, "error update user quota cache: "+err.Error())
+			}
+			if quota != 0 {
+				logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
+				model.RecordConsumeLog(ctx, userId, channelId, promptTokens, completionTokens, textRequest.Model, tokenName, quota, logContent)
+				model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
+				model.UpdateChannelUsedQuota(channelId, quota)
+			}
+
 		}()
 	}(c.Request.Context())
 	switch apiType {
@@ -458,7 +454,7 @@ func relayTextHelper(c *gin.Context, relayMode int) *OpenAIErrorWithStatusCode {
 			textResponse.Usage.CompletionTokens = countTokenText(responseText, textRequest.Model)
 			return nil
 		} else {
-			err, usage := openaiHandler(c, resp, consumeQuota, promptTokens, textRequest.Model)
+			err, usage := openaiHandler(c, resp, promptTokens, textRequest.Model)
 			if err != nil {
 				return err
 			}

controller/relay-utils.go

@@ -200,8 +200,9 @@ func getFullRequestURL(baseURL string, requestURL string, channelType int) strin
 	return fullRequestURL
 }
 
-func postConsumeQuota(ctx context.Context, tokenId int, quota int, userId int, channelId int, modelRatio float64, groupRatio float64, modelName string, tokenName string) {
+func postConsumeQuota(ctx context.Context, tokenId int, quotaDelta int, totalQuota int, userId int, channelId int, modelRatio float64, groupRatio float64, modelName string, tokenName string) {
-	err := model.PostConsumeTokenQuota(tokenId, quota)
+	// quotaDelta is remaining quota to be consumed
+	err := model.PostConsumeTokenQuota(tokenId, quotaDelta)
 	if err != nil {
 		common.SysError("error consuming token remain quota: " + err.Error())
 	}
@@ -209,10 +210,14 @@ func postConsumeQuota(ctx context.Context, tokenId int, quota int, userId int, c
 	if err != nil {
 		common.SysError("error update user quota cache: " + err.Error())
 	}
-	if quota != 0 {
+	// totalQuota is total quota consumed
+	if totalQuota != 0 {
 		logContent := fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f", modelRatio, groupRatio)
-		model.RecordConsumeLog(ctx, userId, channelId, 0, 0, modelName, tokenName, quota, logContent)
+		model.RecordConsumeLog(ctx, userId, channelId, totalQuota, 0, modelName, tokenName, totalQuota, logContent)
-		model.UpdateUserUsedQuotaAndRequestCount(userId, quota)
+		model.UpdateUserUsedQuotaAndRequestCount(userId, totalQuota)
-		model.UpdateChannelUsedQuota(channelId, quota)
+		model.UpdateChannelUsedQuota(channelId, totalQuota)
+	}
+	if totalQuota <= 0 {
+		common.LogError(ctx, fmt.Sprintf("totalQuota consumed is %d, something is wrong", totalQuota))
 	}
 }

middleware/auth.go

@@ -106,12 +106,6 @@ func TokenAuth() func(c *gin.Context) {
 		c.Set("id", token.UserId)
 		c.Set("token_id", token.Id)
 		c.Set("token_name", token.Name)
-		requestURL := c.Request.URL.String()
-		consumeQuota := true
-		if strings.HasPrefix(requestURL, "/v1/models") {
-			consumeQuota = false
-		}
-		c.Set("consume_quota", consumeQuota)
 		if len(parts) > 1 {
 			if model.IsAdmin(token.UserId) {
 				c.Set("channelId", parts[1])

pull_request_template.md

@@ -0,0 +1,3 @@
+close #issue_number
+
+我已确认该 PR 已自测通过，相关截图如下：

web/src/pages/Channel/EditChannel.js

@@ -60,7 +60,7 @@ const EditChannel = () => {
       let localModels = [];
       switch (value) {
         case 14:
-          localModels = ['claude-instant-1', 'claude-2'];
+          localModels = ['claude-instant-1', 'claude-2', 'claude-2.0', 'claude-2.1'];
           break;
         case 11:
           localModels = ['PaLM-2'];