Merge pull request #693 from Calcium-Ion/refactor-auth

refactor: access_token auth
Adjust streaming timeout for OpenAI models in OaiStreamHandler
2025-01-06 17:55:20 +08:00 · 2025-01-06 17:52:33 +08:00 · 2025-01-06 16:37:21 +08:00 · 2025-01-06 15:20:38 +08:00 · 2025-01-05 22:13:04 +08:00 · 2025-01-05 22:12:39 +08:00
27 changed files with 2669 additions and 2978 deletions
@@ -3,4 +3,5 @@
 *.md
 .vscode
 .gitignore
-Makefile
+Makefile
+docs
@@ -12,7 +12,7 @@ on:
 jobs:
  push_to_registries:
    name: Push Docker image to multiple registries
-    runs-on: ubuntu-latest
+    runs-on: self-hosted
    permissions:
      packages: write
      contents: read
@@ -13,7 +13,7 @@ on:
 jobs:
  push_to_registries:
    name: Push Docker image to multiple registries
-    runs-on: ubuntu-latest
+    runs-on: self-hosted
    permissions:
      packages: write
      contents: read
@@ -9,7 +9,7 @@ on:
      - '!*-alpha*'
 jobs:
  release:
-    runs-on: ubuntu-latest
+    runs-on: self-hosted
    steps:
      - name: Checkout
        uses: actions/checkout@v3
@@ -38,7 +38,7 @@ jobs:
      - name: Build Backend (arm64)
        run: |
          sudo apt-get update
-          sudo apt-get install gcc-aarch64-linux-gnu
+          DEBIAN_FRONTEND=noninteractive sudo apt-get install -y gcc-aarch64-linux-gnu
          CC=aarch64-linux-gnu-gcc CGO_ENABLED=1 GOOS=linux GOARCH=arm64 go build -ldflags "-s -w -X 'one-api/common.Version=$(git describe --tags)' -extldflags '-static'" -o one-api-arm64

      - name: Release
@@ -9,7 +9,7 @@ on:
      - '!*-alpha*'
 jobs:
  release:
-    runs-on: macos-latest
+    runs-on: self-hosted
    steps:
      - name: Checkout
        uses: actions/checkout@v3
@@ -9,7 +9,7 @@ on:
      - '!*-alpha*'
 jobs:
  release:
-    runs-on: windows-latest
+    runs-on: self-hosted
    defaults:
      run:
        shell: bash
@@ -1,11 +1,11 @@
-FROM node:16 as builder
+FROM oven/bun:latest as builder

 WORKDIR /build
 COPY web/package.json .
-RUN npm install
+RUN bun install
 COPY ./web .
 COPY ./VERSION .
-RUN DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(cat VERSION) npm run build
+RUN DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(cat VERSION) bun run build

 FROM golang AS builder2

@@ -159,15 +159,14 @@ docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:1234
 [对接文档](Suno.md)

 ## 界面截图
-![796df8d287b7b7bd7853b2497e7df511](https://github.com/user-attachments/assets/255b5e97-2d3a-4434-b4fa-e922ad88ff5a)
+![image](https://github.com/user-attachments/assets/a0dcd349-5df8-4dc8-9acf-ca272b239919)
+
+
+![image](https://github.com/user-attachments/assets/c7d0f7e1-729c-43e2-ac7c-2cb73b0afc8e)

-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/ad0e7aae-0203-471c-9716-2d83768927d4)
 ![image](https://github.com/user-attachments/assets/29f81de5-33fc-4fc5-a5ff-f9b54b653c7c)

-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/3ca0b282-00ff-4c96-bf9d-e29ef615c605)
-夜间模式  
-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/1c66b593-bb9e-4757-9720-ff2759539242)
-![image](https://github.com/Calcium-Ion/new-api/assets/61247483/af9a07ee-5101-4b3d-8bd9-ae21a4fd7e9e)
+![image](https://github.com/user-attachments/assets/4fa53e18-d2c5-477a-9b26-b86e44c71e35)

 ## 交流群
 <img src="https://github.com/user-attachments/assets/9ca0bc82-e057-4230-a28d-9f198fa022e3" width="200">
@@ -32,30 +32,34 @@ var defaultModelRatio = map[string]float64{
 	"gpt-4-0613": 15,
 	"gpt-4-32k":  30,
 	//"gpt-4-32k-0314":               30, //deprecated
-	"gpt-4-32k-0613":                  30,
-	"gpt-4-1106-preview":              5,    // $10 / 1M tokens
-	"gpt-4-0125-preview":              5,    // $10 / 1M tokens
-	"gpt-4-turbo-preview":             5,    // $10 / 1M tokens
-	"gpt-4-vision-preview":            5,    // $10 / 1M tokens
-	"gpt-4-1106-vision-preview":       5,    // $10 / 1M tokens
-	"chatgpt-4o-latest":               2.5,  // $5 / 1M tokens
-	"gpt-4o":                          1.25, // $2.5 / 1M tokens
-	"gpt-4o-audio-preview":            1.25, // $2.5 / 1M tokens
-	"gpt-4o-audio-preview-2024-10-01": 1.25, // $2.5 / 1M tokens
-	"gpt-4o-2024-05-13":               2.5,  // $5 / 1M tokens
-	"gpt-4o-2024-08-06":               1.25, // $2.5 / 1M tokens
-	"gpt-4o-2024-11-20":               1.25, // $2.5 / 1M tokens
-	"gpt-4o-realtime-preview":         2.5,
-	"o1":                              7.5,
-	"o1-2024-12-17":                   7.5,
-	"o1-preview":                      7.5,
-	"o1-preview-2024-09-12":           7.5,
-	"o1-mini":                         1.5,
-	"o1-mini-2024-09-12":              1.5,
-	"gpt-4o-mini":                     0.075,
-	"gpt-4o-mini-2024-07-18":          0.075,
-	"gpt-4-turbo":                     5, // $0.01 / 1K tokens
-	"gpt-4-turbo-2024-04-09":          5, // $0.01 / 1K tokens
+	"gpt-4-32k-0613":                          30,
+	"gpt-4-1106-preview":                      5,    // $10 / 1M tokens
+	"gpt-4-0125-preview":                      5,    // $10 / 1M tokens
+	"gpt-4-turbo-preview":                     5,    // $10 / 1M tokens
+	"gpt-4-vision-preview":                    5,    // $10 / 1M tokens
+	"gpt-4-1106-vision-preview":               5,    // $10 / 1M tokens
+	"chatgpt-4o-latest":                       2.5,  // $5 / 1M tokens
+	"gpt-4o":                                  1.25, // $2.5 / 1M tokens
+	"gpt-4o-audio-preview":                    1.25, // $2.5 / 1M tokens
+	"gpt-4o-audio-preview-2024-10-01":         1.25, // $2.5 / 1M tokens
+	"gpt-4o-2024-05-13":                       2.5,  // $5 / 1M tokens
+	"gpt-4o-2024-08-06":                       1.25, // $2.5 / 1M tokens
+	"gpt-4o-2024-11-20":                       1.25, // $2.5 / 1M tokens
+	"gpt-4o-realtime-preview":                 2.5,
+	"gpt-4o-realtime-preview-2024-10-01":      2.5,
+	"gpt-4o-realtime-preview-2024-12-17":      2.5,
+	"gpt-4o-mini-realtime-preview":            0.3,
+	"gpt-4o-mini-realtime-preview-2024-12-17": 0.3,
+	"o1":                     7.5,
+	"o1-2024-12-17":          7.5,
+	"o1-preview":             7.5,
+	"o1-preview-2024-09-12":  7.5,
+	"o1-mini":                1.5,
+	"o1-mini-2024-09-12":     1.5,
+	"gpt-4o-mini":            0.075,
+	"gpt-4o-mini-2024-07-18": 0.075,
+	"gpt-4-turbo":            5, // $0.01 / 1K tokens
+	"gpt-4-turbo-2024-04-09": 5, // $0.01 / 1K tokens
 	//"gpt-3.5-turbo-0301":           0.75, //deprecated
 	"gpt-3.5-turbo":          0.25,
 	"gpt-3.5-turbo-0613":     0.75,
@@ -427,10 +431,23 @@ func GetCompletionRatio(name string) float64 {
 }

 func GetAudioRatio(name string) float64 {
-	if strings.HasPrefix(name, "gpt-4o-realtime") {
-		return 20
-	} else if strings.HasPrefix(name, "gpt-4o-audio") {
-		return 40
+	if strings.Contains(name, "-realtime") {
+		if strings.HasSuffix(name, "gpt-4o-realtime-preview-2024-12-17") {
+			return 8
+		} else if strings.Contains(name, "mini") {
+			return 10 / 0.6
+		} else {
+			return 20
+		}
+	}
+	if strings.Contains(name, "-audio") {
+		if strings.HasSuffix(name, "gpt-4o-audio-preview-2024-12-17") {
+			return 16
+		} else if strings.Contains(name, "mini") {
+			return 10 / 0.15
+		} else {
+			return 40
+		}
 	}
 	return 20
 }
@@ -438,6 +455,8 @@ func GetAudioRatio(name string) float64 {
 func GetAudioCompletionRatio(name string) float64 {
 	if strings.HasPrefix(name, "gpt-4o-realtime") {
 		return 2
+	} else if strings.HasPrefix(name, "gpt-4o-mini-realtime") {
+		return 2
 	}
 	return 2
 }
@@ -274,6 +274,17 @@ func AddChannel(c *gin.Context) {
 		}
 		localChannel := channel
 		localChannel.Key = key
+		// Validate the length of the model name
+		models := strings.Split(localChannel.Models, ",")
+		for _, model := range models {
+			if len(model) > 255 {
+				c.JSON(http.StatusOK, gin.H{
+					"success": false,
+					"message": fmt.Sprintf("模型名称过长: %s", model),
+				})
+				return
+			}
+		}
 		channels = append(channels, localChannel)
 	}
 	err = model.BatchInsertChannels(channels)
@@ -0,0 +1,53 @@
+# API 鉴权文档
+
+## 认证方式
+
+### Access Token
+
+对于需要鉴权的 API 接口，必须同时提供以下两个请求头来进行 Access Token 认证：
+
+1. **请求头中的 `Authorization` 字段**
+
+    将 Access Token 放置于 HTTP 请求头部的 `Authorization` 字段中，格式如下：
+
+    ```
+    Authorization: <your_access_token>
+    ```
+
+    其中 `<your_access_token>` 需要替换为实际的 Access Token 值。
+
+2. **请求头中的 `New-Api-User` 字段**
+
+    将用户 ID 放置于 HTTP 请求头部的 `New-Api-User` 字段中，格式如下：
+
+    ```
+    New-Api-User: <your_user_id>
+    ```
+
+    其中 `<your_user_id>` 需要替换为实际的用户 ID。
+
+**注意：**
+
+*   **必须同时提供 `Authorization` 和 `New-Api-User` 两个请求头才能通过鉴权。**
+*   如果只提供其中一个请求头，或者两个请求头都未提供，则会返回 `401 Unauthorized` 错误。
+*   如果 `Authorization` 中的 Access Token 无效，则会返回 `401 Unauthorized` 错误，并提示“无权进行此操作，access token 无效”。
+*   如果 `New-Api-User` 中的用户 ID 与 Access Token 不匹配，则会返回 `401 Unauthorized` 错误，并提示“无权进行此操作，与登录用户不匹配，请重新登录”。
+*   如果没有提供 `New-Api-User` 请求头，则会返回 `401 Unauthorized` 错误，并提示“无权进行此操作，未提供 New-Api-User”。
+*   如果 `New-Api-User` 请求头格式错误，则会返回 `401 Unauthorized` 错误，并提示“无权进行此操作，New-Api-User 格式错误”。
+*   如果用户已被禁用，则会返回 `403 Forbidden` 错误，并提示“用户已被封禁”。
+*   如果用户权限不足，则会返回 `403 Forbidden` 错误，并提示“无权进行此操作，权限不足”。
+*   如果用户信息无效，则会返回 `403 Forbidden` 错误，并提示“无权进行此操作，用户信息无效”。
+
+## Curl 示例
+
+假设您的 Access Token 为 `access_token`，用户 ID 为 `123`，要访问的 API 接口为 `/api/user/self`，则可以使用以下 curl 命令：
+
+```bash
+curl -X GET \
+  -H "Authorization: access_token" \
+  -H "New-Api-User: 123" \
+  https://your-domain.com/api/user/self
+```
+
+请将 `access_token`、`123` 和 `https://your-domain.com` 替换为实际的值。
+
@@ -64,35 +64,33 @@ 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
+	// 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，未提供 New-Api-User",
+		})
+		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，New-Api-User 格式错误",
+		})
+		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 id != apiUserId {
+		c.JSON(http.StatusUnauthorized, gin.H{
+			"success": false,
+			"message": "无权进行此操作，New-Api-User 与登录用户不匹配",
+		})
+		c.Abort()
+		return
 	}
 	if status.(int) == common.UserStatusDisabled {
 		c.JSON(http.StatusOK, gin.H{
@@ -12,7 +12,7 @@ import (

 type Ability struct {
 	Group     string  `json:"group" gorm:"type:varchar(64);primaryKey;autoIncrement:false"`
-	Model     string  `json:"model" gorm:"type:varchar(64);primaryKey;autoIncrement:false"`
+	Model     string  `json:"model" gorm:"type:varchar(255);primaryKey;autoIncrement:false"`
 	ChannelId int     `json:"channel_id" gorm:"primaryKey;autoIncrement:false;index"`
 	Enabled   bool    `json:"enabled"`
 	Priority  *int64  `json:"priority" gorm:"bigint;default:0;index"`
@@ -278,7 +278,6 @@ func FixAbility() (int, error) {
 		return 0, err
 	}
 	var channels []Channel
-
 	if len(abilityChannelIds) == 0 {
 		err = DB.Find(&channels).Error
 	} else {
@@ -119,6 +119,7 @@ func SearchChannels(keyword string, group string, model string, idSort bool) ([]
 	// 如果是 PostgreSQL，使用双引号
 	if common.UsingPostgreSQL {
 		keyCol = `"key"`
+		modelsCol = `"models"`
 	}

 	order := "priority desc"
@@ -134,18 +134,23 @@ func SearchUsers(keyword string, group string, startIdx int, num int) ([]*User,
 	// 构建基础查询
 	query := tx.Unscoped().Model(&User{})

+	// 构建搜索条件
+	likeCondition := "username LIKE ? OR email LIKE ? OR display_name LIKE ?"
+
 	// 尝试将关键字转换为整数ID
 	keywordInt, err := strconv.Atoi(keyword)
 	if err == nil {
-		// 如果转换成功，按照ID和可选的组别搜索用户
+		// 如果是数字，同时搜索ID和其他字段
+		likeCondition = "id = ? OR " + likeCondition
 		if group != "" {
-			query = query.Where("id = ? AND "+groupCol+" = ?", keywordInt, group)
+			query = query.Where("("+likeCondition+") AND "+groupCol+" = ?",
+				keywordInt, "%"+keyword+"%", "%"+keyword+"%", "%"+keyword+"%", group)
 		} else {
-			query = query.Where("id = ?", keywordInt)
+			query = query.Where(likeCondition,
+				keywordInt, "%"+keyword+"%", "%"+keyword+"%", "%"+keyword+"%")
 		}
 	} else {
-		// 如果不是ID搜索，则使用模糊匹配
-		likeCondition := "username LIKE ? OR email LIKE ? OR display_name LIKE ?"
+		// 非数字关键字，只搜索字符串字段
 		if group != "" {
 			query = query.Where("("+likeCondition+") AND "+groupCol+" = ?",
 				"%"+keyword+"%", "%"+keyword+"%", "%"+keyword+"%", group)
@@ -15,7 +15,8 @@ var ModelList = []string{
 	"o1-mini", "o1-mini-2024-09-12",
 	"o1", "o1-2024-12-17",
 	"gpt-4o-audio-preview", "gpt-4o-audio-preview-2024-10-01",
-	"gpt-4o-realtime-preview", "gpt-4o-realtime-preview-2024-10-01",
+	"gpt-4o-realtime-preview", "gpt-4o-realtime-preview-2024-10-01", "gpt-4o-realtime-preview-2024-12-17",
+	"gpt-4o-mini-realtime-preview", "gpt-4o-mini-realtime-preview-2024-12-17",
 	"text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large",
 	"text-curie-001", "text-babbage-001", "text-ada-001",
 	"text-moderation-latest", "text-moderation-stable",
@@ -65,8 +65,12 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 	scanner.Split(bufio.ScanLines)

 	service.SetEventStreamHeaders(c)
-
-	ticker := time.NewTicker(time.Duration(constant.StreamingTimeout) * time.Second)
+	streamingTimeout := time.Duration(constant.StreamingTimeout) * time.Second
+	if strings.HasPrefix(info.UpstreamModelName, "o1") || strings.HasPrefix(info.UpstreamModelName, "o3") {
+		// twice timeout for o1 model
+		streamingTimeout *= 2
+	}
+	ticker := time.NewTicker(streamingTimeout)
 	defer ticker.Stop()

 	stopChan := make(chan bool)
@@ -112,6 +112,7 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 	var promptTokens int
 	if value, exists := c.Get("prompt_tokens"); exists {
 		promptTokens = value.(int)
+		relayInfo.PromptTokens = promptTokens
 	} else {
 		promptTokens, err = getPromptTokens(textRequest, relayInfo)
 		// count messages token error 计算promptTokens错误
@@ -218,7 +219,7 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 	}

 	if strings.HasPrefix(relayInfo.UpstreamModelName, "gpt-4o-audio") {
-		service.PostAudioConsumeQuota(c, relayInfo, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
+		service.PostAudioConsumeQuota(c, relayInfo, usage.(*dto.Usage), preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
 	} else {
 		postConsumeQuota(c, relayInfo, textRequest.Model, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
 	}
@@ -13,24 +13,6 @@ import (
 	"one-api/setting"
 )

-//func getAndValidateWssRequest(c *gin.Context, ws *websocket.Conn) (*dto.RealtimeEvent, error) {
-//	_, p, err := ws.ReadMessage()
-//	if err != nil {
-//		return nil, err
-//	}
-//	realtimeEvent := &dto.RealtimeEvent{}
-//	err = json.Unmarshal(p, realtimeEvent)
-//	if err != nil {
-//		return nil, err
-//	}
-//	// save the original request
-//	if realtimeEvent.Session == nil {
-//		return nil, errors.New("session object is nil")
-//	}
-//	c.Set("first_wss_request", p)
-//	return realtimeEvent, nil
-//}
-
 func WssHelper(c *gin.Context, ws *websocket.Conn) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 	relayInfo := relaycommon.GenRelayInfoWs(c, ws)

@@ -129,32 +111,7 @@ func WssHelper(c *gin.Context, ws *websocket.Conn) (openaiErr *dto.OpenAIErrorWi
 		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
 		return openaiErr
 	}
-	service.PostWssConsumeQuota(c, relayInfo, relayInfo.UpstreamModelName, usage.(*dto.RealtimeUsage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
+	service.PostWssConsumeQuota(c, relayInfo, relayInfo.UpstreamModelName, usage.(*dto.RealtimeUsage), preConsumedQuota,
+		userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
 	return nil
 }
-
-//func getWssPromptTokens(textRequest *dto.RealtimeEvent, info *relaycommon.RelayInfo) (int, error) {
-//	var promptTokens int
-//	var err error
-//	switch info.RelayMode {
-//	default:
-//		promptTokens, err = service.CountTokenRealtime(*textRequest, info.UpstreamModelName)
-//	}
-//	info.PromptTokens = promptTokens
-//	return promptTokens, err
-//}
-
-//func checkWssRequestSensitive(textRequest *dto.GeneralOpenAIRequest, info *relaycommon.RelayInfo) error {
-//	var err error
-//	switch info.RelayMode {
-//	case relayconstant.RelayModeChatCompletions:
-//		err = service.CheckSensitiveMessages(textRequest.Messages)
-//	case relayconstant.RelayModeCompletions:
-//		err = service.CheckSensitiveInput(textRequest.Prompt)
-//	case relayconstant.RelayModeModerations:
-//		err = service.CheckSensitiveInput(textRequest.Input)
-//	case relayconstant.RelayModeEmbeddings:
-//		err = service.CheckSensitiveInput(textRequest.Input)
-//	}
-//	return err
-//}
@@ -3,7 +3,6 @@ package service
 import (
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"math"
 	"one-api/common"
 	"one-api/dto"
@@ -12,8 +11,47 @@ import (
 	"one-api/setting"
 	"strings"
 	"time"
+
+	"github.com/gin-gonic/gin"
 )

+type TokenDetails struct {
+	TextTokens  int
+	AudioTokens int
+}
+
+type QuotaInfo struct {
+	InputDetails  TokenDetails
+	OutputDetails TokenDetails
+	ModelName     string
+	UsePrice      bool
+	ModelPrice    float64
+	ModelRatio    float64
+	GroupRatio    float64
+}
+
+func calculateAudioQuota(info QuotaInfo) int {
+	if info.UsePrice {
+		return int(info.ModelPrice * common.QuotaPerUnit * info.GroupRatio)
+	}
+
+	completionRatio := common.GetCompletionRatio(info.ModelName)
+	audioRatio := common.GetAudioRatio(info.ModelName)
+	audioCompletionRatio := common.GetAudioCompletionRatio(info.ModelName)
+	ratio := info.GroupRatio * info.ModelRatio
+
+	quota := info.InputDetails.TextTokens + int(math.Round(float64(info.OutputDetails.TextTokens)*completionRatio))
+	quota += int(math.Round(float64(info.InputDetails.AudioTokens)*audioRatio)) +
+		int(math.Round(float64(info.OutputDetails.AudioTokens)*audioRatio*audioCompletionRatio))
+
+	quota = int(math.Round(float64(quota) * ratio))
+	if ratio != 0 && quota <= 0 {
+		quota = 1
+	}
+
+	return quota
+}
+
 func PreWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.RealtimeUsage) error {
 	if relayInfo.UsePrice {
 		return nil
@@ -33,23 +71,26 @@ func PreWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usag
 	textOutTokens := usage.OutputTokenDetails.TextTokens
 	audioInputTokens := usage.InputTokenDetails.AudioTokens
 	audioOutTokens := usage.OutputTokenDetails.AudioTokens
-
-	completionRatio := common.GetCompletionRatio(modelName)
-	audioRatio := common.GetAudioRatio(relayInfo.UpstreamModelName)
-	audioCompletionRatio := common.GetAudioCompletionRatio(modelName)
 	groupRatio := setting.GetGroupRatio(relayInfo.Group)
 	modelRatio := common.GetModelRatio(modelName)

-	ratio := groupRatio * modelRatio
-
-	quota := textInputTokens + int(math.Round(float64(textOutTokens)*completionRatio))
-	quota += int(math.Round(float64(audioInputTokens)*audioRatio)) + int(math.Round(float64(audioOutTokens)*audioRatio*audioCompletionRatio))
-
-	quota = int(math.Round(float64(quota) * ratio))
-	if ratio != 0 && quota <= 0 {
-		quota = 1
+	quotaInfo := QuotaInfo{
+		InputDetails: TokenDetails{
+			TextTokens:  textInputTokens,
+			AudioTokens: audioInputTokens,
+		},
+		OutputDetails: TokenDetails{
+			TextTokens:  textOutTokens,
+			AudioTokens: audioOutTokens,
+		},
+		ModelName:  modelName,
+		UsePrice:   relayInfo.UsePrice,
+		ModelRatio: modelRatio,
+		GroupRatio: groupRatio,
 	}

+	quota := calculateAudioQuota(quotaInfo)
+
 	if userQuota < quota {
 		return errors.New(fmt.Sprintf("用户额度不足，剩余额度为 %d", userQuota))
 	}
@@ -67,8 +108,7 @@ func PreWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usag
 }

 func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelName string,
-	usage *dto.RealtimeUsage, ratio float64, preConsumedQuota int, userQuota int, modelRatio float64,
-	groupRatio float64,
+	usage *dto.RealtimeUsage, preConsumedQuota int, userQuota int, modelRatio float64, groupRatio float64,
 	modelPrice float64, usePrice bool, extraContent string) {

 	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
@@ -83,17 +123,23 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 	audioRatio := common.GetAudioRatio(relayInfo.UpstreamModelName)
 	audioCompletionRatio := common.GetAudioCompletionRatio(modelName)

-	quota := 0
-	if !usePrice {
-		quota = int(math.Round(float64(textInputTokens) + float64(textOutTokens)*completionRatio))
-		quota += int(math.Round(float64(audioInputTokens)*audioRatio + float64(audioOutTokens)*audioRatio*audioCompletionRatio))
-		quota = int(math.Round(float64(quota) * ratio))
-		if ratio != 0 && quota <= 0 {
-			quota = 1
-		}
-	} else {
-		quota = int(modelPrice * common.QuotaPerUnit * groupRatio)
+	quotaInfo := QuotaInfo{
+		InputDetails: TokenDetails{
+			TextTokens:  textInputTokens,
+			AudioTokens: audioInputTokens,
+		},
+		OutputDetails: TokenDetails{
+			TextTokens:  textOutTokens,
+			AudioTokens: audioOutTokens,
+		},
+		ModelName:  modelName,
+		UsePrice:   usePrice,
+		ModelRatio: modelRatio,
+		GroupRatio: groupRatio,
 	}
+
+	quota := calculateAudioQuota(quotaInfo)
+
 	totalTokens := usage.TotalTokens
 	var logContent string
 	if !usePrice {
@@ -111,21 +157,6 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 		common.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, "+
 			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, modelName, preConsumedQuota))
 	} else {
-		//if sensitiveResp != nil {
-		//	logContent += fmt.Sprintf("，敏感词：%s", strings.Join(sensitiveResp.SensitiveWords, ", "))
-		//}
-		//quotaDelta := quota - preConsumedQuota
-		//if quotaDelta != 0 {
-		//	err := model.PostConsumeQuota(relayInfo, userQuota, quotaDelta, preConsumedQuota, true)
-		//	if err != nil {
-		//		common.LogError(ctx, "error consuming token remain quota: "+err.Error())
-		//	}
-		//}
-
-		//err := model.CacheUpdateUserQuota(relayInfo.UserId)
-		//if err != nil {
-		//	common.LogError(ctx, "error update user quota cache: "+err.Error())
-		//}
 		model.UpdateUserUsedQuotaAndRequestCount(relayInfo.UserId, quota)
 		model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
 	}
@@ -140,8 +171,7 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 }

 func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
-	usage *dto.Usage, ratio float64, preConsumedQuota int, userQuota int, modelRatio float64,
-	groupRatio float64,
+	usage *dto.Usage, preConsumedQuota int, userQuota int, modelRatio float64, groupRatio float64,
 	modelPrice float64, usePrice bool, extraContent string) {

 	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
@@ -156,17 +186,23 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 	audioRatio := common.GetAudioRatio(relayInfo.UpstreamModelName)
 	audioCompletionRatio := common.GetAudioCompletionRatio(relayInfo.UpstreamModelName)

-	quota := 0
-	if !usePrice {
-		quota = int(math.Round(float64(textInputTokens) + float64(textOutTokens)*completionRatio))
-		quota += int(math.Round(float64(audioInputTokens)*audioRatio + float64(audioOutTokens)*audioRatio*audioCompletionRatio))
-		quota = int(math.Round(float64(quota) * ratio))
-		if ratio != 0 && quota <= 0 {
-			quota = 1
-		}
-	} else {
-		quota = int(modelPrice * common.QuotaPerUnit * groupRatio)
+	quotaInfo := QuotaInfo{
+		InputDetails: TokenDetails{
+			TextTokens:  textInputTokens,
+			AudioTokens: audioInputTokens,
+		},
+		OutputDetails: TokenDetails{
+			TextTokens:  textOutTokens,
+			AudioTokens: audioOutTokens,
+		},
+		ModelName:  relayInfo.UpstreamModelName,
+		UsePrice:   usePrice,
+		ModelRatio: modelRatio,
+		GroupRatio: groupRatio,
 	}
+
+	quota := calculateAudioQuota(quotaInfo)
+
 	totalTokens := usage.TotalTokens
 	var logContent string
 	if !usePrice {
@@ -92,13 +92,6 @@ func getImageToken(info *relaycommon.RelayInfo, imageUrl *dto.MessageImageUrl, m
 	if !constant.GetMediaTokenNotStream && !stream {
 		return 256, nil
 	}
-	// 是否统计图片token
-	if !constant.GetMediaToken {
-		return 256, nil
-	}
-	if info.ChannelType == common.ChannelTypeGemini || info.ChannelType == common.ChannelTypeVertexAi || info.ChannelType == common.ChannelTypeAnthropic {
-		return 256, nil
-	}
 	// 同步One API的图片计费逻辑
 	if imageUrl.Detail == "auto" || imageUrl.Detail == "" {
 		imageUrl.Detail = "high"
@@ -109,6 +102,13 @@ func getImageToken(info *relaycommon.RelayInfo, imageUrl *dto.MessageImageUrl, m
 		tileTokens = 5667
 		baseTokens = 2833
 	}
+	// 是否统计图片token
+	if !constant.GetMediaToken {
+		return 3 * baseTokens, nil
+	}
+	if info.ChannelType == common.ChannelTypeGemini || info.ChannelType == common.ChannelTypeVertexAi || info.ChannelType == common.ChannelTypeAnthropic {
+		return 3 * baseTokens, nil
+	}
 	var config image.Config
 	var err error
 	var format string
@@ -315,6 +315,9 @@ export function renderAudioModelPrice(
    if (completionRatio === undefined) {
      completionRatio = 0;
    }
+
+    // try toFixed audioRatio
+    audioRatio = parseFloat(audioRatio).toFixed(6);
    // 这里的 *2 是因为 1倍率=0.002刀，请勿删除
    let inputRatioPrice = modelRatio * 2.0;
    let completionRatioPrice = modelRatio * 2.0 * completionRatio;
@@ -326,13 +329,31 @@ export function renderAudioModelPrice(
    return (
      <>
        <article>
-          <p>提示：${inputRatioPrice} * {groupRatio} = ${inputRatioPrice * groupRatio} / 1M tokens</p>
-          <p>补全：${completionRatioPrice} * {groupRatio} = ${completionRatioPrice * groupRatio} / 1M tokens</p>
-          <p>音频提示：${inputRatioPrice} * {groupRatio} * {audioRatio} = ${inputRatioPrice * audioRatio * groupRatio} / 1M tokens</p>
-          <p>音频补全：${inputRatioPrice} * {groupRatio} * {audioRatio} * {audioCompletionRatio} = ${inputRatioPrice * audioRatio * audioCompletionRatio * groupRatio} / 1M tokens</p>
-          <p></p>
+          <p>{i18next.t('提示：${{price}} * {{ratio}} = ${{total}} / 1M tokens', {
+            price: inputRatioPrice,
+            ratio: groupRatio,
+            total: inputRatioPrice * groupRatio
+          })}</p>
+          <p>{i18next.t('补全：${{price}} * {{ratio}} = ${{total}} / 1M tokens', {
+            price: completionRatioPrice,
+            ratio: groupRatio,
+            total: completionRatioPrice * groupRatio
+          })}</p>
+          <p>{i18next.t('音频提示：${{price}} * {{ratio}} * {{audioRatio}} = ${{total}} / 1M tokens', {
+            price: inputRatioPrice,
+            ratio: groupRatio,
+            audioRatio,
+            total: inputRatioPrice * audioRatio * groupRatio
+          })}</p>
+          <p>{i18next.t('音频补全：${{price}} * {{ratio}} * {{audioRatio}} * {{audioCompRatio}} = ${{total}} / 1M tokens', {
+            price: inputRatioPrice,
+            ratio: groupRatio,
+            audioRatio,
+            audioCompRatio: audioCompletionRatio,
+            total: inputRatioPrice * audioRatio * audioCompletionRatio * groupRatio
+          })}</p>
          <p>
-            {i18next.t('提示 {{input}} tokens / 1M tokens * ${{price}} + 补全 {{completion}} tokens / 1M tokens * ${{compPrice}} +', {
+            {i18next.t('文字提示 {{input}} tokens / 1M tokens * ${{price}} + 文字补全 {{completion}} tokens / 1M tokens * ${{compPrice}} +', {
              input: inputTokens,
              price: inputRatioPrice,
              completion: completionTokens,
@@ -340,13 +361,21 @@ export function renderAudioModelPrice(
            })}
          </p>
          <p>
-            音频提示 {audioInputTokens} tokens / 1M tokens * ${inputRatioPrice} * {audioRatio} + 音频补全 {audioCompletionTokens} tokens / 1M tokens * ${inputRatioPrice} * {audioRatio} * {audioCompletionRatio}
+            {i18next.t('音频提示 {{input}} tokens / 1M tokens * ${{price}} * {{audioRatio}} + 音频补全 {{completion}} tokens / 1M tokens * ${{price}} * {{audioRatio}} * {{audioCompRatio}}', {
+              input: audioInputTokens,
+              completion: audioCompletionTokens,
+              price: inputRatioPrice,
+              audioRatio,
+              audioCompRatio: audioCompletionRatio
+            })}
          </p>
          <p>
-            （文字 + 音频） * 分组 {groupRatio} =
-            ${price.toFixed(6)}
+            {i18next.t('（文字 + 音频）* 分组倍率 {{ratio}} = ${{total}}', {
+              ratio: groupRatio,
+              total: price.toFixed(6)
+            })}
          </p>
-          <p>仅供参考，以实际扣费为准</p>
+          <p>{i18next.t('仅供参考，以实际扣费为准')}</p>
        </article>
      </>
    );
@@ -377,13 +406,13 @@ const colors = [
  'red',
  'teal',
  'violet',
-  'yellow',
+  'yellow'
 ];

 // 基础10色色板 (N ≤ 10)
 const baseColors = [
  '#1664FF', // 主色
-  '#1AC6FF', 
+  '#1AC6FF',
  '#FF8A00',
  '#3CC780',
  '#7442D4',
@@ -1053,6 +1053,11 @@
  "模型价格：${{price}} * 分组倍率：{{ratio}} = ${{total}}": "Model price: ${{price}} * Group ratio: {{ratio}} = ${{total}}",
  "提示：${{price}} * {{ratio}} = ${{total}} / 1M tokens": "Prompt: ${{price}} * {{ratio}} = ${{total}} / 1M tokens",
  "补全：${{price}} * {{ratio}} = ${{total}} / 1M tokens": "Completion: ${{price}} * {{ratio}} = ${{total}} / 1M tokens",
+  "音频提示：${{price}} * {{ratio}} * {{audioRatio}} = ${{total}} / 1M tokens": "Audio prompt: ${{price}} * {{ratio}} * {{audioRatio}} = ${{total}} / 1M tokens",
+  "音频提示 {{input}} tokens / 1M tokens * ${{price}} * {{audioRatio}} + 音频补全 {{completion}} tokens / 1M tokens * ${{price}} * {{audioRatio}} * {{audioCompRatio}}": "Audio prompt {{input}} tokens / 1M tokens * ${{price}} * {{audioRatio}} + Audio completion {{completion}} tokens / 1M tokens * ${{price}} * {{audioRatio}} * {{audioCompRatio}}",
+  "音频补全：${{price}} * {{ratio}} * {{audioRatio}} * {{audioCompRatio}} = ${{total}} / 1M tokens": "Audio completion: ${{price}} * {{ratio}} * {{audioRatio}} * {{audioCompRatio}} = ${{total}} / 1M tokens",
+  "（文字 + 音频）* 分组倍率 {{ratio}} = ${{total}}": "(Text + Audio) * Group ratio {{ratio}} = ${{total}}",
+  "文字提示 {{input}} tokens / 1M tokens * ${{price}} + 文字补全 {{completion}} tokens / 1M tokens * ${{compPrice}} +": "Text prompt {{input}} tokens / 1M tokens * ${{price}} + Text completion {{completion}} tokens / 1M tokens * ${{compPrice}} +",
  "提示 {{input}} tokens / 1M tokens * ${{price}} + 补全 {{completion}} tokens / 1M tokens * ${{compPrice}} * 分组 {{ratio}} = ${{total}}": "Prompt {{input}} tokens / 1M tokens * ${{price}} + Completion {{completion}} tokens / 1M tokens * ${{compPrice}} * Group {{ratio}} = ${{total}}",
  "价格：${{price}} * 分组：{{ratio}}": "Price: ${{price}} * Group: {{ratio}}",
  "模型: {{ratio}} * 分组: {{groupRatio}}": "Model: {{ratio}} * Group: {{groupRatio}}",
@@ -34,8 +34,9 @@ const ChatPage = () => {
  return !isLoading && iframeSrc ? (
    <iframe
      src={iframeSrc}
-      style={{ width: '100%', height: '85vh', border: 'none' }}
+      style={{ width: '100%', height: '100%', border: 'none' }}
      title="Token Frame"
+      allow="camera;microphone"
    />
  ) : (
    <div>
Author	SHA1	Message	Date
Calcium-Ion	6f47c4d47f	Merge pull request #693 from Calcium-Ion/refactor-auth refactor: access_token auth	2025-01-06 17:55:20 +08:00
1808837298@qq.com	a3fe6c03b8	Adjust streaming timeout for OpenAI models in OaiStreamHandler - Implemented conditional logic to double the streaming timeout for models starting with "o1" or "o3". - Improved handling of streaming timeout configuration to enhance performance based on model type.	2025-01-06 17:52:33 +08:00
1808837298@qq.com	e10531670e	Update Dockerfile to use Bun for package management and build process - Changed base image from Node.js to Bun for improved performance. - Replaced npm install with bun install for dependency management. - Updated build command to use Bun for building the application. - Added new bun.lockb file to track Bun dependencies.	2025-01-06 16:37:21 +08:00
1808837298@qq.com	aa2ac4766e	Enhance user search functionality to support ID and keyword searches. Updated query conditions to allow searching by user ID alongside username, email, and display name. Improved handling of numeric and string keywords in search queries.	2025-01-06 15:20:38 +08:00
Calcium-Ion	f599aede05	Merge pull request #692 from Calcium-Ion/fix-channel-model-length Fix channel model length issue	2025-01-05 22:13:04 +08:00
1808837298@qq.com	f11148bccf	revert cache.go	2025-01-05 22:12:39 +08:00
1808837298@qq.com	530e846ac1	refactor: access_token auth	2025-01-05 22:08:23 +08:00
Calcium-Ion	7baa204e9c	Fix model name length validation limit	2025-01-05 22:02:46 +08:00
Calcium-Ion	3dff0d498f		2025-01-05 22:01:36 +08:00
Calcium-Ion	e275229597	Fix channel model length issue Fixes #691 --- For more details, open the [Copilot Workspace session](https://copilot-workspace.githubnext.com/Calcium-Ion/new-api/issues/691?shareId=XXXX-XXXX-XXXX-XXXX).	2025-01-05 21:55:25 +08:00
1808837298@qq.com	cb5a13920f	fix: update linux-release workflow to install gcc-aarch64-linux-gnu non-interactively	2025-01-05 17:59:29 +08:00
1808837298@qq.com	4aaa99a3d4	chore: change workflow runners to self-hosted for Docker and release jobs	2025-01-05 17:17:57 +08:00
1808837298@qq.com	aea201ca77	fix: update iframe styling and permissions in ChatPage component	2025-01-04 22:24:47 +08:00
1808837298@qq.com	e954913f19	refactor: realtime log render	2025-01-04 17:54:02 +08:00
1808837298@qq.com	44a097243e	refactor: realtime i18n	2025-01-04 17:46:06 +08:00
1808837298@qq.com	1798595afc	refactor: realtime quota	2025-01-04 15:46:35 +08:00
Calcium-Ion	c073debcf5	Merge pull request #689 from iszcz/new512	2025-01-03 20:47:56 +08:00
iszcz	4fc2e49518	Update model-ratio.go	2025-01-03 20:42:46 +08:00
1808837298@qq.com	d953b98417	feat: support gpt-4o-mini-realtime-preview	2025-01-03 18:51:09 +08:00
1808837298@qq.com	16afc5b3d6	fix: retry prompt tokens	2025-01-02 16:33:00 +08:00
Calcium-Ion	a835920f83	Merge pull request #686 from delph1s/main fix: try to fix pgsql #685	2025-01-02 00:17:02 +08:00
delph1s	7244adada5	fix: try to fix pgsql #685	2025-01-02 00:14:16 +08:00
Calcium-Ion	eec3aa3bbd	Update README.md	2024-12-31 22:19:37 +08:00