feat: 优化rpm查询

feat: ignore npm build dir

.gitignore

@@ -5,4 +5,5 @@ upload
 *.db
 build
 *.db-journal
-logs
+logs
+web/dist

README.md

@@ -58,12 +58,12 @@
 您可以在渠道中添加自定义模型gpt-4-gizmo-*，此模型并非OpenAI官方模型，而是第三方模型，使用官方key无法调用。
 
 ## 比原版One API多出的配置
-- `STREAMING_TIMEOUT`：设置流式一次回复的超时时间，默认为 30 秒
-- `DIFY_DEBUG`：设置 Dify 渠道是否输出工作流和节点信息到客户端，默认为 `true`
-- `FORCE_STREAM_OPTION`：是否覆盖客户端stream_options参数，请求上游返回流模式usage，默认为 `true`
-- `GET_MEDIA_TOKEN`：是统计图片token，默认为 `true`，关闭后将不再在本地计算图片token，可能会导致和上游计费不同，此项覆盖 `GET_MEDIA_TOKEN_NOT_STREAM` 选项作用，
-- `GET_MEDIA_TOKEN_NOT_STREAM`：是否在非流（`stream=false`）情况下统计图片token，默认为 `true`
-- `UPDATE_TASK`：是否更新异步任务（Midjourney、Suno），默认为 `true`，关闭后将不会更新任务进度
+- `STREAMING_TIMEOUT`：设置流式一次回复的超时时间，默认为 30 秒。
+- `DIFY_DEBUG`：设置 Dify 渠道是否输出工作流和节点信息到客户端，默认为 `true`。
+- `FORCE_STREAM_OPTION`：是否覆盖客户端stream_options参数，请求上游返回流模式usage，默认为 `true`，建议开启，不影响客户端传入stream_options参数返回结果。
+- `GET_MEDIA_TOKEN`：是统计图片token，默认为 `true`，关闭后将不再在本地计算图片token，可能会导致和上游计费不同，此项覆盖 `GET_MEDIA_TOKEN_NOT_STREAM` 选项作用。
+- `GET_MEDIA_TOKEN_NOT_STREAM`：是否在非流（`stream=false`）情况下统计图片token，默认为 `true`。
+- `UPDATE_TASK`：是否更新异步任务（Midjourney、Suno），默认为 `true`，关闭后将不会更新任务进度。
 
 ## 部署
 ### 部署要求

common/email-outlook-auth.go

@@ -0,0 +1,32 @@
+package common
+
+import (
+	"errors"
+	"net/smtp"
+)
+
+type outlookAuth struct {
+	username, password string
+}
+
+func LoginAuth(username, password string) smtp.Auth {
+	return &outlookAuth{username, password}
+}
+
+func (a *outlookAuth) Start(_ *smtp.ServerInfo) (string, []byte, error) {
+	return "LOGIN", []byte{}, nil
+}
+
+func (a *outlookAuth) Next(fromServer []byte, more bool) ([]byte, error) {
+	if more {
+		switch string(fromServer) {
+		case "Username:":
+			return []byte(a.username), nil
+		case "Password:":
+			return []byte(a.password), nil
+		default:
+			return nil, errors.New("unknown fromServer")
+		}
+	}
+	return nil, nil
+}

common/email.go

@@ -62,6 +62,9 @@ func SendEmail(subject string, receiver string, content string) error {
 		if err != nil {
 			return err
 		}
+	} else if strings.HasSuffix(SMTPAccount, "outlook.com") {
+		auth = LoginAuth(SMTPAccount, SMTPToken)
+		err = smtp.SendMail(addr, auth, SMTPAccount, to, mail)
 	} else {
 		err = smtp.SendMail(addr, auth, SMTPAccount, to, mail)
 	}

common/model-ratio.go

@@ -3,6 +3,7 @@ package common
 import (
 	"encoding/json"
 	"strings"
+	"sync"
 )
 
 // from songquanpeng/one-api
@@ -182,8 +183,14 @@ var defaultModelPrice = map[string]float64{
 	"swap_face":         0.05,
 }
 
-var modelPrice map[string]float64 = nil
-var modelRatio map[string]float64 = nil
+var (
+	modelPriceMap      = make(map[string]float64)
+	modelPriceMapMutex = sync.RWMutex{}
+)
+var (
+	modelRatioMap      map[string]float64 = nil
+	modelRatioMapMutex                    = sync.RWMutex{}
+)
 
 var CompletionRatio map[string]float64 = nil
 var defaultCompletionRatio = map[string]float64{
@@ -191,11 +198,18 @@ var defaultCompletionRatio = map[string]float64{
 	"gpt-4-all":     2,
 }
 
-func ModelPrice2JSONString() string {
-	if modelPrice == nil {
-		modelPrice = defaultModelPrice
+func GetModelPriceMap() map[string]float64 {
+	modelPriceMapMutex.Lock()
+	defer modelPriceMapMutex.Unlock()
+	if modelPriceMap == nil {
+		modelPriceMap = defaultModelPrice
 	}
-	jsonBytes, err := json.Marshal(modelPrice)
+	return modelPriceMap
+}
+
+func ModelPrice2JSONString() string {
+	GetModelPriceMap()
+	jsonBytes, err := json.Marshal(modelPriceMap)
 	if err != nil {
 		SysError("error marshalling model price: " + err.Error())
 	}
@@ -203,19 +217,19 @@ func ModelPrice2JSONString() string {
 }
 
 func UpdateModelPriceByJSONString(jsonStr string) error {
-	modelPrice = make(map[string]float64)
-	return json.Unmarshal([]byte(jsonStr), &modelPrice)
+	modelPriceMapMutex.Lock()
+	defer modelPriceMapMutex.Unlock()
+	modelPriceMap = make(map[string]float64)
+	return json.Unmarshal([]byte(jsonStr), &modelPriceMap)
 }
 
 // GetModelPrice 返回模型的价格，如果模型不存在则返回-1，false
 func GetModelPrice(name string, printErr bool) (float64, bool) {
-	if modelPrice == nil {
-		modelPrice = defaultModelPrice
-	}
+	GetModelPriceMap()
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
 	}
-	price, ok := modelPrice[name]
+	price, ok := modelPriceMap[name]
 	if !ok {
 		if printErr {
 			SysError("model price not found: " + name)
@@ -225,18 +239,18 @@ func GetModelPrice(name string, printErr bool) (float64, bool) {
 	return price, true
 }
 
-func GetModelPriceMap() map[string]float64 {
-	if modelPrice == nil {
-		modelPrice = defaultModelPrice
+func GetModelRatioMap() map[string]float64 {
+	modelRatioMapMutex.Lock()
+	defer modelRatioMapMutex.Unlock()
+	if modelRatioMap == nil {
+		modelRatioMap = defaultModelRatio
 	}
-	return modelPrice
+	return modelRatioMap
 }
 
 func ModelRatio2JSONString() string {
-	if modelRatio == nil {
-		modelRatio = defaultModelRatio
-	}
-	jsonBytes, err := json.Marshal(modelRatio)
+	GetModelRatioMap()
+	jsonBytes, err := json.Marshal(modelRatioMap)
 	if err != nil {
 		SysError("error marshalling model ratio: " + err.Error())
 	}
@@ -244,18 +258,18 @@ func ModelRatio2JSONString() string {
 }
 
 func UpdateModelRatioByJSONString(jsonStr string) error {
-	modelRatio = make(map[string]float64)
-	return json.Unmarshal([]byte(jsonStr), &modelRatio)
+	modelRatioMapMutex.Lock()
+	defer modelRatioMapMutex.Unlock()
+	modelRatioMap = make(map[string]float64)
+	return json.Unmarshal([]byte(jsonStr), &modelRatioMap)
 }
 
 func GetModelRatio(name string) float64 {
-	if modelRatio == nil {
-		modelRatio = defaultModelRatio
-	}
+	GetModelRatioMap()
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
 	}
-	ratio, ok := modelRatio[name]
+	ratio, ok := modelRatioMap[name]
 	if !ok {
 		SysError("model ratio not found: " + name)
 		return 30

controller/relay.go

@@ -43,12 +43,13 @@ func Relay(c *gin.Context) {
 	requestId := c.GetString(common.RequestIdKey)
 	channelId := c.GetInt("channel_id")
 	channelType := c.GetInt("channel_type")
+	channelName := c.GetString("channel_name")
 	group := c.GetString("group")
 	originalModel := c.GetString("original_model")
 	openaiErr := relayHandler(c, relayMode)
 	c.Set("use_channel", []string{fmt.Sprintf("%d", channelId)})
 	if openaiErr != nil {
-		go processChannelError(c, channelId, channelType, openaiErr)
+		go processChannelError(c, channelId, channelType, channelName, openaiErr)
 	} else {
 		retryTimes = 0
 	}
@@ -60,7 +61,7 @@ func Relay(c *gin.Context) {
 		}
 		channelId = channel.Id
 		useChannel := c.GetStringSlice("use_channel")
-		useChannel = append(useChannel, fmt.Sprintf("%d", channelId))
+		useChannel = append(useChannel, fmt.Sprintf("%d", channel.Id))
 		c.Set("use_channel", useChannel)
 		common.LogInfo(c.Request.Context(), fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, i))
 		middleware.SetupContextForSelectedChannel(c, channel, originalModel)
@@ -69,7 +70,7 @@ func Relay(c *gin.Context) {
 		c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
 		openaiErr = relayHandler(c, relayMode)
 		if openaiErr != nil {
-			go processChannelError(c, channelId, channel.Type, openaiErr)
+			go processChannelError(c, channel.Id, channel.Type, channel.Name, openaiErr)
 		}
 	}
 	useChannel := c.GetStringSlice("use_channel")
@@ -128,11 +129,10 @@ func shouldRetry(c *gin.Context, channelId int, openaiErr *dto.OpenAIErrorWithSt
 	return true
 }
 
-func processChannelError(c *gin.Context, channelId int, channelType int, err *dto.OpenAIErrorWithStatusCode) {
+func processChannelError(c *gin.Context, channelId int, channelType int, channelName string, err *dto.OpenAIErrorWithStatusCode) {
 	autoBan := c.GetBool("auto_ban")
 	common.LogError(c.Request.Context(), fmt.Sprintf("relay error (channel #%d, status code: %d): %s", channelId, err.StatusCode, err.Error.Message))
 	if service.ShouldDisableChannel(channelType, err) && autoBan {
-		channelName := c.GetString("channel_name")
 		service.DisableChannel(channelId, channelName, err.Error.Message)
 	}
 }

middleware/auth.go

@@ -6,6 +6,7 @@ import (
 	"net/http"
 	"one-api/common"
 	"one-api/model"
+	"strconv"
 	"strings"
 )
 
@@ -15,6 +16,7 @@ func authHelper(c *gin.Context, minRole int) {
 	role := session.Get("role")
 	id := session.Get("id")
 	status := session.Get("status")
+	useAccessToken := false
 	if username == nil {
 		// Check access token
 		accessToken := c.Request.Header.Get("Authorization")
@@ -33,6 +35,7 @@ func authHelper(c *gin.Context, minRole int) {
 			role = user.Role
 			id = user.Id
 			status = user.Status
+			useAccessToken = true
 		} else {
 			c.JSON(http.StatusOK, gin.H{
 				"success": false,
@@ -42,6 +45,36 @@ func authHelper(c *gin.Context, minRole int) {
 			return
 		}
 	}
+	if !useAccessToken {
+		// get header New-Api-User
+		apiUserIdStr := c.Request.Header.Get("New-Api-User")
+		if apiUserIdStr == "" {
+			c.JSON(http.StatusUnauthorized, gin.H{
+				"success": false,
+				"message": "无权进行此操作，请刷新页面或清空缓存后重试",
+			})
+			c.Abort()
+			return
+		}
+		apiUserId, err := strconv.Atoi(apiUserIdStr)
+		if err != nil {
+			c.JSON(http.StatusUnauthorized, gin.H{
+				"success": false,
+				"message": "无权进行此操作，登录信息无效，请重新登录",
+			})
+			c.Abort()
+			return
+
+		}
+		if id != apiUserId {
+			c.JSON(http.StatusUnauthorized, gin.H{
+				"success": false,
+				"message": "无权进行此操作，与登录用户不匹配，请重新登录",
+			})
+			c.Abort()
+			return
+		}
+	}
 	if status.(int) == common.UserStatusDisabled {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,

middleware/utils.go

@@ -1,11 +1,13 @@
 package middleware
 
 import (
+	"fmt"
 	"github.com/gin-gonic/gin"
 	"one-api/common"
 )
 
 func abortWithOpenAiMessage(c *gin.Context, statusCode int, message string) {
+	userId := c.GetInt("id")
 	c.JSON(statusCode, gin.H{
 		"error": gin.H{
 			"message": common.MessageWithRequestId(message, c.GetString(common.RequestIdKey)),
@@ -13,7 +15,7 @@ func abortWithOpenAiMessage(c *gin.Context, statusCode int, message string) {
 		},
 	})
 	c.Abort()
-	common.LogError(c.Request.Context(), message)
+	common.LogError(c.Request.Context(), fmt.Sprintf("user %d | %s", userId, message))
 }
 
 func abortWithMidjourneyMessage(c *gin.Context, statusCode int, code int, description string) {

model/channel.go

@@ -100,8 +100,8 @@ func SearchChannels(keyword string, group string, model string) ([]*Channel, err
 	var whereClause string
 	var args []interface{}
 	if group != "" {
-		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + groupCol + " LIKE ? AND " + modelsCol + " LIKE ?"
-		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, "%"+group+"%", "%"+model+"%")
+		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + groupCol + " = ? AND " + modelsCol + " LIKE ?"
+		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, group, "%"+model+"%")
 	} else {
 		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + modelsCol + " LIKE ?"
 		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, "%"+model+"%")

model/log.go

@@ -7,6 +7,7 @@ import (
 	"gorm.io/gorm"
 	"one-api/common"
 	"strings"
+	"time"
 )
 
 type Log struct {
@@ -102,7 +103,7 @@ func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName
 		tx = DB.Where("type = ?", logType)
 	}
 	if modelName != "" {
-		tx = tx.Where("model_name = ?", modelName)
+		tx = tx.Where("model_name like ?", modelName)
 	}
 	if username != "" {
 		tx = tx.Where("username = ?", username)
@@ -131,7 +132,7 @@ func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int
 		tx = DB.Where("user_id = ? and type = ?", userId, logType)
 	}
 	if modelName != "" {
-		tx = tx.Where("model_name = ?", modelName)
+		tx = tx.Where("model_name like ?", modelName)
 	}
 	if tokenName != "" {
 		tx = tx.Where("token_name = ?", tokenName)
@@ -172,12 +173,18 @@ type Stat struct {
 }
 
 func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, channel int) (stat Stat) {
-	tx := DB.Table("logs").Select("sum(quota) quota, count(*) rpm, sum(prompt_tokens) + sum(completion_tokens) tpm")
+	tx := DB.Table("logs").Select("sum(quota) quota")
+
+	// 为rpm和tpm创建单独的查询
+	rpmTpmQuery := DB.Table("logs").Select("count(*) rpm, sum(prompt_tokens) + sum(completion_tokens) tpm")
+
 	if username != "" {
 		tx = tx.Where("username = ?", username)
+		rpmTpmQuery = rpmTpmQuery.Where("username = ?", username)
 	}
 	if tokenName != "" {
 		tx = tx.Where("token_name = ?", tokenName)
+		rpmTpmQuery = rpmTpmQuery.Where("token_name = ?", tokenName)
 	}
 	if startTimestamp != 0 {
 		tx = tx.Where("created_at >= ?", startTimestamp)
@@ -187,11 +194,23 @@ func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelNa
 	}
 	if modelName != "" {
 		tx = tx.Where("model_name = ?", modelName)
+		rpmTpmQuery = rpmTpmQuery.Where("model_name = ?", modelName)
 	}
 	if channel != 0 {
 		tx = tx.Where("channel_id = ?", channel)
+		rpmTpmQuery = rpmTpmQuery.Where("channel_id = ?", channel)
 	}
-	tx.Where("type = ?", LogTypeConsume).Scan(&stat)
+
+	tx = tx.Where("type = ?", LogTypeConsume)
+	rpmTpmQuery = rpmTpmQuery.Where("type = ?", LogTypeConsume)
+
+	// 只统计最近60秒的rpm和tpm
+	rpmTpmQuery = rpmTpmQuery.Where("created_at >= ?", time.Now().Add(-60*time.Second).Unix())
+
+	// 执行查询
+	tx.Scan(&stat)
+	rpmTpmQuery.Scan(&stat)
+
 	return stat
 }
 

relay/channel/aws/relay-aws.go

@@ -222,9 +222,11 @@ func awsStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 		}
 	}
 	service.Done(c)
-	err = resp.Body.Close()
-	if err != nil {
-		return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	if resp != nil {
+		err = resp.Body.Close()
+		if err != nil {
+			return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		}
 	}
 	return nil, &usage
 }

relay/channel/cloudflare/constant.go

@@ -1,6 +1,7 @@
 package cloudflare
 
 var ModelList = []string{
+	"@cf/meta/llama-3.1-8b-instruct",
 	"@cf/meta/llama-2-7b-chat-fp16",
 	"@cf/meta/llama-2-7b-chat-int8",
 	"@cf/mistral/mistral-7b-instruct-v0.1",

relay/channel/dify/relay-dify.go

@@ -53,7 +53,7 @@ func streamResponseDify2OpenAI(difyResponse DifyChunkChatCompletionResponse) *dt
 		choice.Delta.SetContentString("Workflow: " + difyResponse.Data.WorkflowId + "\n")
 	} else if constant.DifyDebug && difyResponse.Event == "node_started" {
 		choice.Delta.SetContentString("Node: " + difyResponse.Data.NodeId + "\n")
-	} else if difyResponse.Event == "message" {
+	} else if difyResponse.Event == "message" || difyResponse.Event == "agent_message" {
 		choice.Delta.SetContentString(difyResponse.Answer)
 	}
 	response.Choices = append(response.Choices, choice)

relay/channel/gemini/relay-gemini.go

@@ -83,13 +83,28 @@ func CovertGemini2OpenAI(textRequest dto.GeneralOpenAIRequest) *GeminiChatReques
 				if imageNum > GeminiVisionMaxImageNum {
 					continue
 				}
-				mimeType, data, _ := service.GetImageFromUrl(part.ImageUrl.(dto.MessageImageUrl).Url)
-				parts = append(parts, GeminiPart{
-					InlineData: &GeminiInlineData{
-						MimeType: mimeType,
-						Data:     data,
-					},
-				})
+				// 判断是否是url
+				if strings.HasPrefix(part.ImageUrl.(dto.MessageImageUrl).Url, "http") {
+					// 是url，获取图片的类型和base64编码的数据
+					mimeType, data, _ := service.GetImageFromUrl(part.ImageUrl.(dto.MessageImageUrl).Url)
+					parts = append(parts, GeminiPart{
+						InlineData: &GeminiInlineData{
+							MimeType: mimeType,
+							Data:     data,
+						},
+					})
+				} else {
+					_, format, base64String, err := service.DecodeBase64ImageData(part.ImageUrl.(dto.MessageImageUrl).Url)
+					if err != nil {
+						continue
+					}
+					parts = append(parts, GeminiPart{
+						InlineData: &GeminiInlineData{
+							MimeType: "image/" + format,
+							Data:     base64String,
+						},
+					})
+				}
 			}
 		}
 		content.Parts = parts
@@ -198,7 +213,6 @@ func streamResponseGeminiChat2OpenAI(geminiResponse *GeminiChatResponse) *dto.Ch
 			choice.Delta.SetContentString(respFirst.Text)
 		}
 	}
-	choice.FinishReason = &relaycommon.StopFinishReason
 	var response dto.ChatCompletionsStreamResponse
 	response.Object = "chat.completion.chunk"
 	response.Model = "gemini"
@@ -247,10 +261,14 @@ func geminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycom
 			common.LogError(c, err.Error())
 		}
 	}
+
+	response := service.GenerateStopResponse(id, createAt, info.UpstreamModelName, relaycommon.StopFinishReason)
+	service.ObjectData(c, response)
+
 	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 
 	if info.ShouldIncludeUsage {
-		response := service.GenerateFinalUsageResponse(id, createAt, info.UpstreamModelName, *usage)
+		response = service.GenerateFinalUsageResponse(id, createAt, info.UpstreamModelName, *usage)
 		err := service.ObjectData(c, response)
 		if err != nil {
 			common.SysError("send final response failed: " + err.Error())

relay/channel/ollama/dto.go

@@ -3,14 +3,18 @@ package ollama
 import "one-api/dto"
 
 type OllamaRequest struct {
-	Model       string        `json:"model,omitempty"`
-	Messages    []dto.Message `json:"messages,omitempty"`
-	Stream      bool          `json:"stream,omitempty"`
-	Temperature float64       `json:"temperature,omitempty"`
-	Seed        float64       `json:"seed,omitempty"`
-	Topp        float64       `json:"top_p,omitempty"`
-	TopK        int           `json:"top_k,omitempty"`
-	Stop        any           `json:"stop,omitempty"`
+	Model            string              `json:"model,omitempty"`
+	Messages         []dto.Message       `json:"messages,omitempty"`
+	Stream           bool                `json:"stream,omitempty"`
+	Temperature      float64             `json:"temperature,omitempty"`
+	Seed             float64             `json:"seed,omitempty"`
+	Topp             float64             `json:"top_p,omitempty"`
+	TopK             int                 `json:"top_k,omitempty"`
+	Stop             any                 `json:"stop,omitempty"`
+	Tools            []dto.ToolCall      `json:"tools,omitempty"`
+	ResponseFormat   *dto.ResponseFormat `json:"response_format,omitempty"`
+	FrequencyPenalty float64             `json:"frequency_penalty,omitempty"`
+	PresencePenalty  float64             `json:"presence_penalty,omitempty"`
 }
 
 type OllamaEmbeddingRequest struct {
@@ -21,6 +25,3 @@ type OllamaEmbeddingRequest struct {
 type OllamaEmbeddingResponse struct {
 	Embedding []float64 `json:"embedding,omitempty"`
 }
-
-//type OllamaOptions struct {
-//}

relay/channel/ollama/relay-ollama.go

@@ -28,14 +28,18 @@ func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) *OllamaRequest {
 		Stop, _ = request.Stop.([]string)
 	}
 	return &OllamaRequest{
-		Model:       request.Model,
-		Messages:    messages,
-		Stream:      request.Stream,
-		Temperature: request.Temperature,
-		Seed:        request.Seed,
-		Topp:        request.TopP,
-		TopK:        request.TopK,
-		Stop:        Stop,
+		Model:            request.Model,
+		Messages:         messages,
+		Stream:           request.Stream,
+		Temperature:      request.Temperature,
+		Seed:             request.Seed,
+		Topp:             request.TopP,
+		TopK:             request.TopK,
+		Stop:             Stop,
+		Tools:            request.Tools,
+		ResponseFormat:   request.ResponseFormat,
+		FrequencyPenalty: request.FrequencyPenalty,
+		PresencePenalty:  request.PresencePenalty,
 	}
 }
 

relay/channel/openai/relay-openai.go

@@ -16,12 +16,13 @@ import (
 	relayconstant "one-api/relay/constant"
 	"one-api/service"
 	"strings"
+	"sync"
 	"time"
 )
 
 func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	containStreamUsage := false
-	responseId := ""
+	var responseId string
 	var createAt int64 = 0
 	var systemFingerprint string
 	model := info.UpstreamModelName
@@ -41,7 +42,10 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 
 	stopChan := make(chan bool)
 	defer close(stopChan)
-
+	var (
+		lastStreamData string
+		mu             sync.Mutex
+	)
 	gopool.Go(func() {
 		for scanner.Scan() {
 			info.SetFirstResponseTime()
@@ -53,14 +57,19 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 			if data[:6] != "data: " && data[:6] != "[DONE]" {
 				continue
 			}
+			mu.Lock()
 			data = data[6:]
 			if !strings.HasPrefix(data, "[DONE]") {
-				err := service.StringData(c, data)
-				if err != nil {
-					common.LogError(c, "streaming error: "+err.Error())
+				if lastStreamData != "" {
+					err := service.StringData(c, lastStreamData)
+					if err != nil {
+						common.LogError(c, "streaming error: "+err.Error())
+					}
 				}
+				lastStreamData = data
 				streamItems = append(streamItems, data)
 			}
+			mu.Unlock()
 		}
 		common.SafeSendBool(stopChan, true)
 	})
@@ -73,6 +82,26 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 		// 正常结束
 	}
 
+	shouldSendLastResp := true
+	var lastStreamResponse dto.ChatCompletionsStreamResponse
+	err := json.Unmarshal(common.StringToByteSlice(lastStreamData), &lastStreamResponse)
+	if err == nil {
+		responseId = lastStreamResponse.Id
+		createAt = lastStreamResponse.Created
+		systemFingerprint = lastStreamResponse.GetSystemFingerprint()
+		model = lastStreamResponse.Model
+		if service.ValidUsage(lastStreamResponse.Usage) {
+			containStreamUsage = true
+			usage = lastStreamResponse.Usage
+			if !info.ShouldIncludeUsage {
+				shouldSendLastResp = false
+			}
+		}
+	}
+	if shouldSendLastResp {
+		service.StringData(c, lastStreamData)
+	}
+
 	// 计算token
 	streamResp := "[" + strings.Join(streamItems, ",") + "]"
 	switch info.RelayMode {
@@ -86,14 +115,9 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 				var streamResponse dto.ChatCompletionsStreamResponse
 				err := json.Unmarshal(common.StringToByteSlice(item), &streamResponse)
 				if err == nil {
-					responseId = streamResponse.Id
-					createAt = streamResponse.Created
-					systemFingerprint = streamResponse.GetSystemFingerprint()
-					model = streamResponse.Model
-					if service.ValidUsage(streamResponse.Usage) {
-						usage = streamResponse.Usage
-						containStreamUsage = true
-					}
+					//if service.ValidUsage(streamResponse.Usage) {
+					//	usage = streamResponse.Usage
+					//}
 					for _, choice := range streamResponse.Choices {
 						responseTextBuilder.WriteString(choice.Delta.GetContentString())
 						if choice.Delta.ToolCalls != nil {
@@ -110,14 +134,10 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 			}
 		} else {
 			for _, streamResponse := range streamResponses {
-				responseId = streamResponse.Id
-				createAt = streamResponse.Created
-				systemFingerprint = streamResponse.GetSystemFingerprint()
-				model = streamResponse.Model
-				if service.ValidUsage(streamResponse.Usage) {
-					usage = streamResponse.Usage
-					containStreamUsage = true
-				}
+				//if service.ValidUsage(streamResponse.Usage) {
+				//	usage = streamResponse.Usage
+				//	containStreamUsage = true
+				//}
 				for _, choice := range streamResponse.Choices {
 					responseTextBuilder.WriteString(choice.Delta.GetContentString())
 					if choice.Delta.ToolCalls != nil {

relay/relay-image.go

@@ -121,7 +121,8 @@ func ImageHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
 		}
 	}
 
-	quota := int(modelPrice*groupRatio*common.QuotaPerUnit*sizeRatio*qualityRatio) * imageRequest.N
+	imageRatio := modelPrice * sizeRatio * qualityRatio * float64(imageRequest.N)
+	quota := int(imageRatio * groupRatio * common.QuotaPerUnit)
 
 	if userQuota-quota < 0 {
 		return service.OpenAIErrorWrapperLocal(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
@@ -180,7 +181,7 @@ func ImageHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
 	}
 
 	logContent := fmt.Sprintf("大小 %s, 品质 %s", imageRequest.Size, quality)
-	postConsumeQuota(c, relayInfo, imageRequest.Model, usage, 0, 0, userQuota, 0, groupRatio, modelPrice, true, logContent)
+	postConsumeQuota(c, relayInfo, imageRequest.Model, usage, 0, 0, userQuota, 0, groupRatio, imageRatio, true, logContent)
 
 	return nil
 }

relay/relay-text.go

@@ -130,6 +130,12 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 		return openaiErr
 	}
 
+	includeUsage := false
+	// 判断用户是否需要返回使用情况
+	if textRequest.StreamOptions != nil && textRequest.StreamOptions.IncludeUsage {
+		includeUsage = true
+	}
+
 	// 如果不支持StreamOptions，将StreamOptions设置为nil
 	if !relayInfo.SupportStreamOptions || !textRequest.Stream {
 		textRequest.StreamOptions = nil
@@ -142,8 +148,8 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 		}
 	}
 
-	if textRequest.StreamOptions != nil && textRequest.StreamOptions.IncludeUsage {
-		relayInfo.ShouldIncludeUsage = textRequest.StreamOptions.IncludeUsage
+	if includeUsage {
+		relayInfo.ShouldIncludeUsage = true
 	}
 
 	adaptor := GetAdaptor(relayInfo.ApiType)
@@ -280,7 +286,14 @@ func returnPreConsumedQuota(c *gin.Context, tokenId int, userQuota int, preConsu
 func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelName string,
 	usage *dto.Usage, ratio float64, preConsumedQuota int, userQuota int, modelRatio float64, groupRatio float64,
 	modelPrice float64, usePrice bool, extraContent string) {
-
+	if usage == nil {
+		usage = &dto.Usage{
+			PromptTokens:     relayInfo.PromptTokens,
+			CompletionTokens: 0,
+			TotalTokens:      relayInfo.PromptTokens,
+		}
+		extraContent += "  ，（可能是请求出错）"
+	}
 	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
 	promptTokens := usage.PromptTokens
 	completionTokens := usage.CompletionTokens

service/relay.go

@@ -7,6 +7,7 @@ import (
 	"github.com/gin-gonic/gin"
 	"net/http"
 	"one-api/common"
+	"one-api/dto"
 )
 
 func SetEventStreamHeaders(c *gin.Context) {
@@ -45,3 +46,30 @@ func GetResponseID(c *gin.Context) string {
 	logID := c.GetString("X-Oneapi-Request-Id")
 	return fmt.Sprintf("chatcmpl-%s", logID)
 }
+
+func GenerateStopResponse(id string, createAt int64, model string, finishReason string) *dto.ChatCompletionsStreamResponse {
+	return &dto.ChatCompletionsStreamResponse{
+		Id:                id,
+		Object:            "chat.completion.chunk",
+		Created:           createAt,
+		Model:             model,
+		SystemFingerprint: nil,
+		Choices: []dto.ChatCompletionsStreamResponseChoice{
+			{
+				FinishReason: &finishReason,
+			},
+		},
+	}
+}
+
+func GenerateFinalUsageResponse(id string, createAt int64, model string, usage dto.Usage) *dto.ChatCompletionsStreamResponse {
+	return &dto.ChatCompletionsStreamResponse{
+		Id:                id,
+		Object:            "chat.completion.chunk",
+		Created:           createAt,
+		Model:             model,
+		SystemFingerprint: nil,
+		Choices:           make([]dto.ChatCompletionsStreamResponseChoice, 0),
+		Usage:             &usage,
+	}
+}

service/token_counter.go

@@ -82,11 +82,12 @@ func getTokenNum(tokenEncoder *tiktoken.Tiktoken, text string) int {
 }
 
 func getImageToken(imageUrl *dto.MessageImageUrl, model string, stream bool) (int, error) {
+	baseTokens := 85
 	if model == "glm-4v" {
 		return 1047, nil
 	}
 	if imageUrl.Detail == "low" {
-		return 85, nil
+		return baseTokens, nil
 	}
 	// TODO: 非流模式下不计算图片token数量
 	if !constant.GetMediaTokenNotStream && !stream {
@@ -100,6 +101,12 @@ func getImageToken(imageUrl *dto.MessageImageUrl, model string, stream bool) (in
 	if imageUrl.Detail == "auto" || imageUrl.Detail == "" {
 		imageUrl.Detail = "high"
 	}
+
+	tileTokens := 170
+	if strings.HasPrefix(model, "gpt-4o-mini") {
+		tileTokens = 5667
+		baseTokens = 2833
+	}
 	var config image.Config
 	var err error
 	var format string
@@ -146,7 +153,7 @@ func getImageToken(imageUrl *dto.MessageImageUrl, model string, stream bool) (in
 	// 计算图片的token数量(边的长度除以512，向上取整)
 	tiles := (shortSide + 511) / 512 * ((otherSide + 511) / 512)
 	log.Printf("tiles: %d", tiles)
-	return tiles*170 + 85, nil
+	return tiles*tileTokens + baseTokens, nil
 }
 
 func CountTokenChatRequest(request dto.GeneralOpenAIRequest, model string) (int, error) {

service/usage_helpr.go

@@ -25,18 +25,6 @@ func ResponseText2Usage(responseText string, modeName string, promptTokens int)
 	return usage, err
 }
 
-func GenerateFinalUsageResponse(id string, createAt int64, model string, usage dto.Usage) *dto.ChatCompletionsStreamResponse {
-	return &dto.ChatCompletionsStreamResponse{
-		Id:                id,
-		Object:            "chat.completion.chunk",
-		Created:           createAt,
-		Model:             model,
-		SystemFingerprint: nil,
-		Choices:           make([]dto.ChatCompletionsStreamResponseChoice, 0),
-		Usage:             &usage,
-	}
-}
-
 func ValidUsage(usage *dto.Usage) bool {
 	return usage != nil && (usage.PromptTokens != 0 || usage.CompletionTokens != 0)
 }

web/src/components/LoginForm.js

@@ -1,7 +1,7 @@
 import React, { useContext, useEffect, useState } from 'react';
 import { Link, useNavigate, useSearchParams } from 'react-router-dom';
 import { UserContext } from '../context/User';
-import { API, getLogo, showError, showInfo, showSuccess } from '../helpers';
+import { API, getLogo, showError, showInfo, showSuccess, updateAPI } from '../helpers';
 import { onGitHubOAuthClicked } from './utils';
 import Turnstile from 'react-turnstile';
 import {
@@ -101,6 +101,7 @@ const LoginForm = () => {
       if (success) {
         userDispatch({ type: 'login', payload: data });
         setUserData(data);
+        updateAPI()
         showSuccess('登录成功！');
         if (username === 'root' && password === '123456') {
           Modal.error({

web/src/components/LogsTable.js

@@ -1,11 +1,11 @@
 import React, { useEffect, useState } from 'react';
 import {
   API,
-  copy,
+  copy, getTodayStartTimestamp,
   isAdmin,
   showError,
   showSuccess,
-  timestamp2string,
+  timestamp2string
 } from '../helpers';
 
 import {
@@ -419,12 +419,12 @@ const LogsTable = () => {
   const [logType, setLogType] = useState(0);
   const isAdminUser = isAdmin();
   let now = new Date();
-  // 初始化start_timestamp为前一天
+  // 初始化start_timestamp为今天0点
   const [inputs, setInputs] = useState({
     username: '',
     token_name: '',
     model_name: '',
-    start_timestamp: timestamp2string(now.getTime() / 1000 - 86400),
+    start_timestamp: timestamp2string(getTodayStartTimestamp()),
     end_timestamp: timestamp2string(now.getTime() / 1000 + 3600),
     channel: '',
   });
@@ -475,6 +475,9 @@ const LogsTable = () => {
   };
 
   const handleEyeClick = async () => {
+    if (loadingStat) {
+      return;
+    }
     setLoadingStat(true);
     if (isAdminUser) {
       await getLogStat();
@@ -574,6 +577,7 @@ const LogsTable = () => {
   const refresh = async () => {
     // setLoading(true);
     setActivePage(1);
+    handleEyeClick();
     await loadLogs(0, pageSize, logType);
   };
 
@@ -596,6 +600,7 @@ const LogsTable = () => {
       .catch((reason) => {
         showError(reason);
       });
+    handleEyeClick();
   }, []);
 
   const searchLogs = async () => {
@@ -622,19 +627,17 @@ const LogsTable = () => {
       <Layout>
         <Header>
           <Spin spinning={loadingStat}>
-            <h3>
-              使用明细（总消耗额度：
-              <span
-                onClick={handleEyeClick}
-                style={{
-                  cursor: 'pointer',
-                  color: 'gray',
-                }}
-              >
-                {showStat ? renderQuota(stat.quota) : '点击查看'}
-              </span>
-              ）
-            </h3>
+            <Space>
+              <Tag color='green' size='large' style={{ padding: 15 }}>
+                总消耗额度: {renderQuota(stat.quota)}
+              </Tag>
+              <Tag color='blue' size='large' style={{ padding: 15 }}>
+                RPM: {stat.rpm}
+              </Tag>
+              <Tag color='purple' size='large' style={{ padding: 15 }}>
+                TPM: {stat.tpm}
+              </Tag>
+            </Space>
           </Spin>
         </Header>
         <Form layout='horizontal' style={{ marginTop: 10 }}>
@@ -700,17 +703,19 @@ const LogsTable = () => {
                 />
               </>
             )}
+            <Button
+              label='查询'
+              type='primary'
+              htmlType='submit'
+              className='btn-margin-right'
+              onClick={refresh}
+              loading={loading}
+              style={{ marginTop: 24 }}
+            >
+              查询
+            </Button>
             <Form.Section>
-              <Button
-                label='查询'
-                type='primary'
-                htmlType='submit'
-                className='btn-margin-right'
-                onClick={refresh}
-                loading={loading}
-              >
-                查询
-              </Button>
+
             </Form.Section>
           </>
         </Form>

web/src/helpers/api.js

@@ -1,12 +1,26 @@
-import { showError } from './utils';
+import { getUserIdFromLocalStorage, showError } from './utils';
 import axios from 'axios';
 
-export const API = axios.create({
+export let API = axios.create({
   baseURL: import.meta.env.VITE_REACT_APP_SERVER_URL
     ? import.meta.env.VITE_REACT_APP_SERVER_URL
     : '',
+  headers: {
+    'New-API-User': getUserIdFromLocalStorage()
+  }
 });
 
+export function updateAPI() {
+  API = axios.create({
+    baseURL: import.meta.env.VITE_REACT_APP_SERVER_URL
+      ? import.meta.env.VITE_REACT_APP_SERVER_URL
+      : '',
+    headers: {
+      'New-API-User': getUserIdFromLocalStorage()
+    }
+  });
+}
+
 API.interceptors.response.use(
   (response) => response,
   (error) => {

web/src/helpers/utils.js

@@ -33,6 +33,13 @@ export function getLogo() {
   return logo;
 }
 
+export function getUserIdFromLocalStorage() {
+  let user = localStorage.getItem('user');
+  if (!user) return -1;
+  user = JSON.parse(user);
+  return user.id;
+}
+
 export function getFooterHTML() {
   return localStorage.getItem('footer_html');
 }
@@ -133,6 +140,12 @@ export function removeTrailingSlash(url) {
   }
 }
 
+export function getTodayStartTimestamp() {
+  var now = new Date();
+  now.setHours(0, 0, 0, 0);
+  return Math.floor(now.getTime() / 1000);
+}
+
 export function timestamp2string(timestamp) {
   let date = new Date(timestamp * 1000);
   let year = date.getFullYear().toString();

web/src/pages/Token/index.js

@@ -1,11 +1,14 @@
 import React from 'react';
 import TokensTable from '../../components/TokensTable';
-import { Layout } from '@douyinfe/semi-ui';
+import { Banner, Layout } from '@douyinfe/semi-ui';
 const Token = () => (
   <>
     <Layout>
       <Layout.Header>
-        <h3>我的令牌</h3>
+        <Banner
+          type='warning'
+          description='令牌无法精确控制使用额度，请勿直接将令牌分发给用户。'
+        />
       </Layout.Header>
       <Layout.Content>
         <TokensTable />