feat: Add reasoning content support in OpenAI response handling

refactor: Simplify model mapping and pricing logic across relay modules

.env.example

@@ -10,9 +10,9 @@
 
 # 数据库相关配置
 # 数据库连接字符串
-# SQL_DSN=mysql://user:password@tcp(127.0.0.1:3306)/dbname?parseTime=true
+# SQL_DSN=user:password@tcp(127.0.0.1:3306)/dbname?parseTime=true
 # 日志数据库连接字符串
-# LOG_SQL_DSN=mysql://user:password@tcp(127.0.0.1:3306)/logdb?parseTime=true
+# LOG_SQL_DSN=user:password@tcp(127.0.0.1:3306)/logdb?parseTime=true
 # SQLite数据库路径
 # SQLITE_PATH=/path/to/sqlite.db
 # 数据库最大空闲连接数

.github/workflows/docker-image-arm64.yml

@@ -13,7 +13,7 @@ on:
 jobs:
   push_to_registries:
     name: Push Docker image to multiple registries
-    runs-on: self-hosted
+    runs-on: ubuntu-latest
     permissions:
       packages: write
       contents: read

.github/workflows/macos-release.yml

@@ -9,7 +9,7 @@ on:
       - '!*-alpha*'
 jobs:
   release:
-    runs-on: ubuntu-latest
+    runs-on: macos-latest
     steps:
       - name: Checkout
         uses: actions/checkout@v3

.github/workflows/windows-release.yml

@@ -9,7 +9,7 @@ on:
       - '!*-alpha*'
 jobs:
   release:
-    runs-on: ubuntu-latest
+    runs-on: windows-latest
     defaults:
       run:
         shell: bash

Dockerfile

@@ -1,4 +1,4 @@
-FROM oven/bun:latest as builder
+FROM oven/bun:latest AS builder
 
 WORKDIR /build
 COPY web/package.json .
@@ -7,18 +7,20 @@ COPY ./web .
 COPY ./VERSION .
 RUN DISABLE_ESLINT_PLUGIN='true' VITE_REACT_APP_VERSION=$(cat VERSION) bun run build
 
-FROM golang AS builder2
+FROM golang:alpine AS builder2
 
 ENV GO111MODULE=on \
-    CGO_ENABLED=1 \
+    CGO_ENABLED=0 \
     GOOS=linux
 
 WORKDIR /build
+
 ADD go.mod go.sum ./
 RUN go mod download
+
 COPY . .
 COPY --from=builder /build/dist ./web/dist
-RUN go build -ldflags "-s -w -X 'one-api/common.Version=$(cat VERSION)' -extldflags '-static'" -o one-api
+RUN go build -ldflags "-s -w -X 'one-api/common.Version=$(cat VERSION)'" -o one-api
 
 FROM alpine
 

README.en.md

@@ -59,6 +59,10 @@
 13. 🎵 Added [Suno API](https://github.com/Suno-API/Suno-API) interface support, [Integration Guide](Suno.md)
 14. 🔄 Support for Rerank models, compatible with Cohere and Jina, can integrate with Dify, [Integration Guide](Rerank.md)
 15. ⚡ **[OpenAI Realtime API](https://platform.openai.com/docs/guides/realtime/integration)** - Support for OpenAI's Realtime API, including Azure channels
+16. 🧠 Support for setting reasoning effort through model name suffix:
+    - Add suffix `-high` to set high reasoning effort (e.g., `o3-mini-high`)
+    - Add suffix `-medium` to set medium reasoning effort
+    - Add suffix `-low` to set low reasoning effort
 
 ## Model Support
 This version additionally supports:
@@ -84,15 +88,15 @@ You can add custom models gpt-4-gizmo-* in channels. These are third-party model
 - `GEMINI_VISION_MAX_IMAGE_NUM`: Gemini model maximum image number, default `16`, set to `-1` to disable
 - `MAX_FILE_DOWNLOAD_MB`: Maximum file download size in MB, default `20`
 - `CRYPTO_SECRET`: Encryption key for encrypting database content
+- `AZURE_DEFAULT_API_VERSION`: Azure channel default API version, if not specified in channel settings, use this version, default `2024-12-01-preview`
+- `NOTIFICATION_LIMIT_DURATION_MINUTE`: Duration of notification limit in minutes, default `10`
+- `NOTIFY_LIMIT_COUNT`: Maximum number of user notifications in the specified duration, default `2`
 
 ## Deployment
+
 > [!TIP]
 > Latest Docker image: `calciumion/new-api:latest`  
-> Default account: root, password: 123456  
-> Update command:
-> ```
-> docker run --rm -v /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower -cR
-> ```
+> Default account: root, password: 123456
 
 ### Multi-Server Deployment
 - Must set `SESSION_SECRET` environment variable, otherwise login state will not be consistent across multiple servers.
@@ -102,26 +106,58 @@ You can add custom models gpt-4-gizmo-* in channels. These are third-party model
 - Local database (default): SQLite (Docker deployment must mount `/data` directory)
 - Remote database: MySQL >= 5.7.8, PgSQL >= 9.6
 
+### Deployment with BT Panel
+Install BT Panel (**version 9.2.0** or above) from [BT Panel Official Website](https://www.bt.cn/new/download.html), choose the stable version script to download and install.  
+After installation, log in to BT Panel and click Docker in the menu bar. First-time access will prompt to install Docker service. Click Install Now and follow the prompts to complete installation.  
+After installation, find **New-API** in the app store, click install, configure basic options to complete installation.  
+[Pictorial Guide](BT.md)
+
 ### Docker Deployment
+
 ### Using Docker Compose (Recommended)
 ```shell
 # Clone project
 git clone https://github.com/Calcium-Ion/new-api.git
 cd new-api
 # Edit docker-compose.yml as needed
+# nano docker-compose.yml
+# vim docker-compose.yml
 # Start
 docker-compose up -d
 ```
 
+#### Update Version
+```shell
+docker-compose pull
+docker-compose up -d
+```
+
 ### Direct Docker Image Usage
 ```shell
 # SQLite deployment:
 docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
+
 # MySQL deployment (add -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi"), modify database connection parameters as needed
 # Example:
 docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
 ```
 
+#### Update Version
+```shell
+# Pull the latest image
+docker pull calciumion/new-api:latest
+# Stop and remove the old container
+docker stop new-api
+docker rm new-api
+# Run the new container with the same parameters as before
+docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
+```
+
+Alternatively, you can use Watchtower for automatic updates (not recommended, may cause database incompatibility):
+```shell
+docker run --rm -v /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower -cR
+```
+
 ## Channel Retry
 Channel retry is implemented, configurable in `Settings->Operation Settings->General Settings`. **Cache recommended**.  
 First retry uses same priority, second retry uses next priority, and so on.

README.md

@@ -65,6 +65,10 @@
 14. 🔄 支持Rerank模型，目前兼容Cohere和Jina，可接入Dify，[对接文档](Rerank.md)
 15. ⚡ **[OpenAI Realtime API](https://platform.openai.com/docs/guides/realtime/integration)** - 支持OpenAI的Realtime API，支持Azure渠道
 16. 支持使用路由/chat2link 进入聊天界面
+17. 🧠 支持通过模型名称后缀设置 reasoning effort：
+    - 添加后缀 `-high` 设置为 high reasoning effort (例如: `o3-mini-high`)
+    - 添加后缀 `-medium` 设置为 medium reasoning effort (例如: `o3-mini-medium`)
+    - 添加后缀 `-low` 设置为 low reasoning effort (例如: `o3-mini-low`)
 
 ## 模型支持
 此版本额外支持以下模型：
@@ -85,19 +89,20 @@
 - `GET_MEDIA_TOKEN`：是否统计图片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。
-- `GEMINI_MODEL_MAP`：Gemini模型指定版本(v1/v1beta)，使用“模型:版本”指定，","分隔，例如：-e GEMINI_MODEL_MAP="gemini-1.5-pro-latest:v1beta,gemini-1.5-pro-001:v1beta"，为空则使用默认配置(v1beta)
-- `COHERE_SAFETY_SETTING`：Cohere模型[安全设置](https://docs.cohere.com/docs/safety-modes#overview)，可选值为 `NONE`, `CONTEXTUAL`，`STRICT`，默认为 `NONE`。
+- `GEMINI_MODEL_MAP`：Gemini模型指定版本(v1/v1beta)，使用"模型:版本"指定，","分隔，例如：-e GEMINI_MODEL_MAP="gemini-1.5-pro-latest:v1beta,gemini-1.5-pro-001:v1beta"，为空则使用默认配置(v1beta)
+- `COHERE_SAFETY_SETTING`：Cohere模型[安全设置](https://docs.cohere.com/docs/safety-modes#overview)，可选值为 `NONE`, `CONTEXTUAL`, `STRICT`，默认为 `NONE`。
 - `GEMINI_VISION_MAX_IMAGE_NUM`：Gemini模型最大图片数量，默认为 `16`，设置为 `-1` 则不限制。
 - `MAX_FILE_DOWNLOAD_MB`: 最大文件下载大小，单位 MB，默认为 `20`。
 - `CRYPTO_SECRET`：加密密钥，用于加密数据库内容。
+- `AZURE_DEFAULT_API_VERSION`：Azure渠道默认API版本，如果渠道设置中未指定API版本，则使用此版本，默认为 `2024-12-01-preview`
+- `NOTIFICATION_LIMIT_DURATION_MINUTE`：通知限制的持续时间（分钟），默认为 `10`。
+- `NOTIFY_LIMIT_COUNT`：用户通知在指定持续时间内的最大数量，默认为 `2`。
+
 ## 部署
+
 > [!TIP]
 > 最新版Docker镜像：`calciumion/new-api:latest`  
-> 默认账号root 密码123456  
-> 更新指令：
-> ```
-> docker run --rm -v /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower -cR
-> ```
+> 默认账号root 密码123456
 
 ### 多机部署
 - 必须设置环境变量 `SESSION_SECRET`，否则会导致多机部署时登录状态不一致。
@@ -114,25 +119,54 @@
 [图文教程](BT.md)
 
 ### 基于 Docker 进行部署
+
+> [!TIP]
+> 默认管理员账号root 密码123456
+
 ### 使用 Docker Compose 部署（推荐）
 ```shell
 # 下载项目
 git clone https://github.com/Calcium-Ion/new-api.git
 cd new-api
 # 按需编辑 docker-compose.yml
+# nano docker-compose.yml
+# vim docker-compose.yml
 # 启动
 docker-compose up -d
 ```
 
+#### 更新版本
+```shell
+docker-compose pull
+docker-compose up -d
+```
+
 ### 直接使用 Docker 镜像
 ```shell
 # 使用 SQLite 的部署命令：
 docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
+
 # 使用 MySQL 的部署命令，在上面的基础上添加 `-e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi"`，请自行修改数据库连接参数。
 # 例如：
 docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
 ```
 
+#### 更新版本
+```shell
+# 拉取最新镜像
+docker pull calciumion/new-api:latest
+# 停止并删除旧容器
+docker stop new-api
+docker rm new-api
+# 使用相同参数运行新容器
+docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/data calciumion/new-api:latest
+```
+
+或者使用 Watchtower 自动更新（不推荐，可能会导致数据库不兼容）：
+```shell
+docker run --rm -v /var/run/docker.sock:/var/run/docker.sock containrrr/watchtower -cR
+```
+
 ## 渠道重试
 渠道重试功能已经实现，可以在`设置->运营设置->通用设置`设置重试次数，**建议开启缓存**功能。  
 如果开启了重试功能，第一次重试使用同优先级，第二次重试使用下一个优先级，以此类推。

common/constants.go

@@ -101,7 +101,7 @@ var PreConsumedQuota = 500
 
 var RetryTimes = 0
 
-var RootUserEmail = ""
+//var RootUserEmail = ""
 
 var IsMasterNode = os.Getenv("NODE_TYPE") != "slave"
 
@@ -231,8 +231,10 @@ const (
 	ChannelTypeVertexAi       = 41
 	ChannelTypeMistral        = 42
 	ChannelTypeDeepSeek       = 43
-
-	ChannelTypeDummy // this one is only for count, do not add any channel after this
+	ChannelTypeMokaAI         = 44
+	ChannelTypeVolcEngine     = 45
+	ChannelTypeBaiduV2        = 46
+	ChannelTypeDummy          // this one is only for count, do not add any channel after this
 
 )
 
@@ -281,4 +283,7 @@ var ChannelBaseURLs = []string{
 	"",                                          //41
 	"https://api.mistral.ai",                    //42
 	"https://api.deepseek.com",                  //43
+	"https://api.moka.ai",                       //44
+	"https://ark.cn-beijing.volces.com",         //45
+	"https://qianfan.baidubce.com",              //46
 }

common/database.go

@@ -3,5 +3,6 @@ package common
 var UsingSQLite = false
 var UsingPostgreSQL = false
 var UsingMySQL = false
+var UsingClickHouse = false
 
 var SQLitePath = "one-api.db?_busy_timeout=5000"

common/go-channel.go

@@ -1,22 +1,9 @@
 package common
 
 import (
-	"fmt"
-	"runtime/debug"
 	"time"
 )
 
-func SafeGoroutine(f func()) {
-	go func() {
-		defer func() {
-			if r := recover(); r != nil {
-				SysError(fmt.Sprintf("child goroutine panic occured: error: %v, stack: %s", r, string(debug.Stack())))
-			}
-		}()
-		f()
-	}()
-}
-
 func SafeSendBool(ch chan bool, value bool) (closed bool) {
 	defer func() {
 		// Recover from panic if one occured. A panic would mean the channel was closed.

common/logger.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+	"github.com/bytedance/gopkg/util/gopool"
 	"github.com/gin-gonic/gin"
 	"io"
 	"log"
@@ -80,9 +81,9 @@ func logHelper(ctx context.Context, level string, msg string) {
 	if logCount > maxLogCount && !setupLogWorking {
 		logCount = 0
 		setupLogWorking = true
-		go func() {
+		gopool.Go(func() {
 			SetupLogger()
-		}()
+		})
 	}
 }
 
@@ -100,6 +101,14 @@ func LogQuota(quota int) string {
 	}
 }
 
+func FormatQuota(quota int) string {
+	if DisplayInCurrencyEnabled {
+		return fmt.Sprintf("＄%.6f", float64(quota)/QuotaPerUnit)
+	} else {
+		return fmt.Sprintf("%d", quota)
+	}
+}
+
 // LogJson 仅供测试使用 only for test
 func LogJson(ctx context.Context, msg string, obj any) {
 	jsonStr, err := json.Marshal(obj)

common/model-ratio.go

@@ -50,16 +50,24 @@ var defaultModelRatio = map[string]float64{
 	"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
+	"o1":                        7.5,
+	"o1-2024-12-17":             7.5,
+	"o1-preview":                7.5,
+	"o1-preview-2024-09-12":     7.5,
+	"o1-mini":                   0.55,
+	"o1-mini-2024-09-12":        0.55,
+	"o3-mini":                   0.55,
+	"o3-mini-2025-01-31":        0.55,
+	"o3-mini-high":              0.55,
+	"o3-mini-2025-01-31-high":   0.55,
+	"o3-mini-low":               0.55,
+	"o3-mini-2025-01-31-low":    0.55,
+	"o3-mini-medium":            0.55,
+	"o3-mini-2025-01-31-medium": 0.55,
+	"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,
@@ -183,8 +191,9 @@ var defaultModelRatio = map[string]float64{
 	"command-r-plus":         1.5,
 	"command-r-08-2024":      0.075,
 	"command-r-plus-08-2024": 1.25,
-	"deepseek-chat":          0.07,
-	"deepseek-coder":         0.07,
+	"deepseek-chat":          0.27 / 2,
+	"deepseek-coder":         0.27 / 2,
+	"deepseek-reasoner":      0.55 / 2, // 0.55 / 1k tokens
 	// Perplexity online 模型对搜索额外收费，有需要应自行调整，此处不计入搜索费用
 	"llama-3-sonar-small-32k-chat":   0.2 / 1000 * USD,
 	"llama-3-sonar-small-32k-online": 0.2 / 1000 * USD,
@@ -224,7 +233,11 @@ var (
 	modelRatioMapMutex                    = sync.RWMutex{}
 )
 
-var CompletionRatio map[string]float64 = nil
+var (
+	CompletionRatio      map[string]float64 = nil
+	CompletionRatioMutex                    = sync.RWMutex{}
+)
+
 var defaultCompletionRatio = map[string]float64{
 	"gpt-4-gizmo-*":  2,
 	"gpt-4o-gizmo-*": 3,
@@ -325,10 +338,17 @@ func GetDefaultModelRatioMap() map[string]float64 {
 	return defaultModelRatio
 }
 
-func CompletionRatio2JSONString() string {
+func GetCompletionRatioMap() map[string]float64 {
+	CompletionRatioMutex.Lock()
+	defer CompletionRatioMutex.Unlock()
 	if CompletionRatio == nil {
 		CompletionRatio = defaultCompletionRatio
 	}
+	return CompletionRatio
+}
+
+func CompletionRatio2JSONString() string {
+	GetCompletionRatioMap()
 	jsonBytes, err := json.Marshal(CompletionRatio)
 	if err != nil {
 		SysError("error marshalling completion ratio: " + err.Error())
@@ -337,11 +357,15 @@ func CompletionRatio2JSONString() string {
 }
 
 func UpdateCompletionRatioByJSONString(jsonStr string) error {
+	CompletionRatioMutex.Lock()
+	defer CompletionRatioMutex.Unlock()
 	CompletionRatio = make(map[string]float64)
 	return json.Unmarshal([]byte(jsonStr), &CompletionRatio)
 }
 
 func GetCompletionRatio(name string) float64 {
+	GetCompletionRatioMap()
+
 	if strings.Contains(name, "/") {
 		if ratio, ok := CompletionRatio[name]; ok {
 			return ratio
@@ -366,7 +390,7 @@ func GetCompletionRatio(name string) float64 {
 		}
 		return 2
 	}
-	if strings.HasPrefix(name, "o1") {
+	if strings.HasPrefix(name, "o1") || strings.HasPrefix(name, "o3") {
 		return 4
 	}
 	if name == "chatgpt-4o-latest" {
@@ -410,11 +434,9 @@ func GetCompletionRatio(name string) float64 {
 			return 4
 		}
 	}
-	if strings.HasPrefix(lowercaseName, "deepseek") {
-		if strings.HasSuffix(lowercaseName, "reasoner") || strings.HasSuffix(lowercaseName, "r1") {
-			return 4
-		}
-		return 2
+	// hint 只给官方上4倍率，由于开源模型供应商自行定价，不对其进行补全倍率进行强制对齐
+	if lowercaseName == "deepseek-chat" || lowercaseName == "deepseek-reasoner" {
+		return 4
 	}
 	if strings.HasPrefix(name, "ERNIE-Speed-") {
 		return 2
@@ -469,24 +491,3 @@ func GetAudioCompletionRatio(name string) float64 {
 	}
 	return 2
 }
-
-//func GetAudioPricePerMinute(name string) float64 {
-//	if strings.HasPrefix(name, "gpt-4o-realtime") {
-//		return 0.06
-//	}
-//	return 0.06
-//}
-//
-//func GetAudioCompletionPricePerMinute(name string) float64 {
-//	if strings.HasPrefix(name, "gpt-4o-realtime") {
-//		return 0.24
-//	}
-//	return 0.24
-//}
-
-func GetCompletionRatioMap() map[string]float64 {
-	if CompletionRatio == nil {
-		CompletionRatio = defaultCompletionRatio
-	}
-	return CompletionRatio
-}

constant/channel_setting.go

@@ -1,5 +1,6 @@
 package constant
 
 var (
-	ForceFormat = "force_format" // ForceFormat 强制格式化为OpenAI格式
+	ForceFormat        = "force_format" // ForceFormat 强制格式化为OpenAI格式
+	ChanelSettingProxy = "proxy"        // Proxy 代理
 )

constant/env.go

@@ -21,12 +21,17 @@ var GetMediaTokenNotStream = common.GetEnvOrDefaultBool("GET_MEDIA_TOKEN_NOT_STR
 
 var UpdateTask = common.GetEnvOrDefaultBool("UPDATE_TASK", true)
 
+var AzureDefaultAPIVersion = common.GetEnvOrDefaultString("AZURE_DEFAULT_API_VERSION", "2024-12-01-preview")
+
 var GeminiModelMap = map[string]string{
 	"gemini-1.0-pro": "v1",
 }
 
 var GeminiVisionMaxImageNum = common.GetEnvOrDefault("GEMINI_VISION_MAX_IMAGE_NUM", 16)
 
+var NotifyLimitCount = common.GetEnvOrDefault("NOTIFY_LIMIT_COUNT", 2)
+var NotificationLimitDurationMinute = common.GetEnvOrDefault("NOTIFICATION_LIMIT_DURATION_MINUTE", 10)
+
 func InitEnv() {
 	modelVersionMapStr := strings.TrimSpace(os.Getenv("GEMINI_MODEL_MAP"))
 	if modelVersionMapStr == "" {
@@ -42,5 +47,5 @@ func InitEnv() {
 	}
 }
 
-// 是否生成初始令牌，默认关闭。
+// GenerateDefaultToken 是否生成初始令牌，默认关闭。
 var GenerateDefaultToken = common.GetEnvOrDefaultBool("GENERATE_DEFAULT_TOKEN", false)

constant/user_setting.go

@@ -0,0 +1,14 @@
+package constant
+
+var (
+	UserSettingNotifyType            = "notify_type"             // QuotaWarningType 额度预警类型
+	UserSettingQuotaWarningThreshold = "quota_warning_threshold" // QuotaWarningThreshold 额度预警阈值
+	UserSettingWebhookUrl            = "webhook_url"             // WebhookUrl webhook地址
+	UserSettingWebhookSecret         = "webhook_secret"          // WebhookSecret webhook密钥
+	UserSettingNotificationEmail     = "notification_email"      // NotificationEmail 通知邮箱地址
+)
+
+var (
+	NotifyTypeEmail   = "email"   // Email 邮件
+	NotifyTypeWebhook = "webhook" // Webhook
+)

controller/channel-test.go

@@ -41,9 +41,21 @@ func testChannel(channel *model.Channel, testModel string) (err error, openAIErr
 	}
 	w := httptest.NewRecorder()
 	c, _ := gin.CreateTestContext(w)
+
+	requestPath := "/v1/chat/completions"
+
+	// 先判断是否为 Embedding 模型
+	if strings.Contains(strings.ToLower(testModel), "embedding") ||
+		strings.HasPrefix(testModel, "m3e") || // m3e 系列模型
+		strings.Contains(testModel, "bge-") || // bge 系列模型
+		testModel == "text-embedding-v1" ||
+		channel.Type == common.ChannelTypeMokaAI { // 其他 embedding 模型
+		requestPath = "/v1/embeddings" // 修改请求路径
+	}
+
 	c.Request = &http.Request{
 		Method: "POST",
-		URL:    &url.URL{Path: "/v1/chat/completions"},
+		URL:    &url.URL{Path: requestPath}, // 使用动态路径
 		Body:   nil,
 		Header: make(http.Header),
 	}
@@ -55,20 +67,20 @@ func testChannel(channel *model.Channel, testModel string) (err error, openAIErr
 			if len(channel.GetModels()) > 0 {
 				testModel = channel.GetModels()[0]
 			} else {
-				testModel = "gpt-3.5-turbo"
+				testModel = "gpt-4o-mini"
 			}
 		}
-	} else {
-		modelMapping := *channel.ModelMapping
-		if modelMapping != "" && modelMapping != "{}" {
-			modelMap := make(map[string]string)
-			err := json.Unmarshal([]byte(modelMapping), &modelMap)
-			if err != nil {
-				return err, service.OpenAIErrorWrapperLocal(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
-			}
-			if modelMap[testModel] != "" {
-				testModel = modelMap[testModel]
-			}
+	}
+
+	modelMapping := *channel.ModelMapping
+	if modelMapping != "" && modelMapping != "{}" {
+		modelMap := make(map[string]string)
+		err := json.Unmarshal([]byte(modelMapping), &modelMap)
+		if err != nil {
+			return err, service.OpenAIErrorWrapperLocal(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
+		}
+		if modelMap[testModel] != "" {
+			testModel = modelMap[testModel]
 		}
 	}
 
@@ -88,7 +100,7 @@ func testChannel(channel *model.Channel, testModel string) (err error, openAIErr
 
 	request := buildTestRequest(testModel)
 	meta.UpstreamModelName = testModel
-	common.SysLog(fmt.Sprintf("testing channel %d with model %s", channel.Id, testModel))
+	common.SysLog(fmt.Sprintf("testing channel %d with model %s , meta %v ", channel.Id, testModel, meta))
 
 	adaptor.Init(meta)
 
@@ -156,12 +168,21 @@ func buildTestRequest(model string) *dto.GeneralOpenAIRequest {
 		Model:  "", // this will be set later
 		Stream: false,
 	}
-	if strings.HasPrefix(model, "o1") {
+
+	// 先判断是否为 Embedding 模型
+	if strings.Contains(strings.ToLower(model), "embedding") ||
+		strings.HasPrefix(model, "m3e") || // m3e 系列模型
+		strings.Contains(model, "bge-") || // bge 系列模型
+		model == "text-embedding-v1" { // 其他 embedding 模型
+		// Embedding 请求
+		testRequest.Input = []string{"hello world"}
+		return testRequest
+	}
+	// 并非Embedding 模型
+	if strings.HasPrefix(model, "o1") || strings.HasPrefix(model, "o3") {
 		testRequest.MaxCompletionTokens = 10
-	} else if strings.HasPrefix(model, "gemini-2.0-flash-thinking") {
-		testRequest.MaxTokens = 2
 	} else {
-		testRequest.MaxTokens = 1
+		testRequest.MaxTokens = 10
 	}
 	content, _ := json.Marshal("hi")
 	testMessage := dto.Message{
@@ -217,9 +238,7 @@ var testAllChannelsLock sync.Mutex
 var testAllChannelsRunning bool = false
 
 func testAllChannels(notify bool) error {
-	if common.RootUserEmail == "" {
-		common.RootUserEmail = model.GetRootUserEmail()
-	}
+
 	testAllChannelsLock.Lock()
 	if testAllChannelsRunning {
 		testAllChannelsLock.Unlock()
@@ -274,10 +293,7 @@ func testAllChannels(notify bool) error {
 		testAllChannelsRunning = false
 		testAllChannelsLock.Unlock()
 		if notify {
-			err := common.SendEmail("通道测试完成", common.RootUserEmail, "通道测试完成，如果没有收到禁用通知，说明所有通道都正常")
-			if err != nil {
-				common.SysError(fmt.Sprintf("failed to send email: %s", err.Error()))
-			}
+			service.NotifyRootUser(dto.NotifyTypeChannelTest, "通道测试完成", "所有通道测试已完成")
 		}
 	})
 	return nil

controller/misc.go

@@ -66,6 +66,7 @@ func GetStatus(c *gin.Context) {
 			"enable_online_topup":      setting.PayAddress != "" && setting.EpayId != "" && setting.EpayKey != "",
 			"mj_notify_enabled":        setting.MjNotifyEnabled,
 			"chats":                    setting.Chats,
+			"demo_site_enabled":        setting.DemoSiteEnabled,
 		},
 	})
 	return

controller/pricing.go

@@ -17,7 +17,7 @@ func GetPricing(c *gin.Context) {
 	}
 	var group string
 	if exists {
-		user, err := model.GetUserById(userId.(int), false)
+		user, err := model.GetUserCache(userId.(int))
 		if err == nil {
 			group = user.Group
 		}

controller/relay.go

@@ -24,7 +24,7 @@ func relayHandler(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 	var err *dto.OpenAIErrorWithStatusCode
 	switch relayMode {
 	case relayconstant.RelayModeImagesGenerations:
-		err = relay.ImageHelper(c, relayMode)
+		err = relay.ImageHelper(c)
 	case relayconstant.RelayModeAudioSpeech:
 		fallthrough
 	case relayconstant.RelayModeAudioTranslation:
@@ -33,6 +33,8 @@ func relayHandler(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 		err = relay.AudioHelper(c)
 	case relayconstant.RelayModeRerank:
 		err = relay.RerankHelper(c, relayMode)
+	case relayconstant.RelayModeEmbeddings:
+		err = relay.EmbeddingHelper(c)
 	default:
 		err = relay.TextHelper(c)
 	}

controller/user.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"net/http"
+	"net/url"
 	"one-api/common"
 	"one-api/model"
 	"one-api/setting"
@@ -471,7 +472,7 @@ func GetUserModels(c *gin.Context) {
 	if err != nil {
 		id = c.GetInt("id")
 	}
-	user, err := model.GetUserById(id, true)
+	user, err := model.GetUserCache(id)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -846,9 +847,10 @@ func EmailBind(c *gin.Context) {
 		})
 		return
 	}
-	id := c.GetInt("id")
+	session := sessions.Default(c)
+	id := session.Get("id")
 	user := model.User{
-		Id: id,
+		Id: id.(int),
 	}
 	err := user.FillUserById()
 	if err != nil {
@@ -868,9 +870,6 @@ func EmailBind(c *gin.Context) {
 		})
 		return
 	}
-	if user.Role == common.RoleRootUser {
-		common.RootUserEmail = email
-	}
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
@@ -912,3 +911,115 @@ func TopUp(c *gin.Context) {
 	})
 	return
 }
+
+type UpdateUserSettingRequest struct {
+	QuotaWarningType      string `json:"notify_type"`
+	QuotaWarningThreshold int    `json:"quota_warning_threshold"`
+	WebhookUrl            string `json:"webhook_url,omitempty"`
+	WebhookSecret         string `json:"webhook_secret,omitempty"`
+	NotificationEmail     string `json:"notification_email,omitempty"`
+}
+
+func UpdateUserSetting(c *gin.Context) {
+	var req UpdateUserSettingRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "无效的参数",
+		})
+		return
+	}
+
+	// 验证预警类型
+	if req.QuotaWarningType != constant.NotifyTypeEmail && req.QuotaWarningType != constant.NotifyTypeWebhook {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "无效的预警类型",
+		})
+		return
+	}
+
+	// 验证预警阈值
+	if req.QuotaWarningThreshold <= 0 {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "预警阈值必须大于0",
+		})
+		return
+	}
+
+	// 如果是webhook类型,验证webhook地址
+	if req.QuotaWarningType == constant.NotifyTypeWebhook {
+		if req.WebhookUrl == "" {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "Webhook地址不能为空",
+			})
+			return
+		}
+		// 验证URL格式
+		if _, err := url.ParseRequestURI(req.WebhookUrl); err != nil {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "无效的Webhook地址",
+			})
+			return
+		}
+	}
+
+	// 如果是邮件类型，验证邮箱地址
+	if req.QuotaWarningType == constant.NotifyTypeEmail && req.NotificationEmail != "" {
+		// 验证邮箱格式
+		if !strings.Contains(req.NotificationEmail, "@") {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "无效的邮箱地址",
+			})
+			return
+		}
+	}
+
+	userId := c.GetInt("id")
+	user, err := model.GetUserById(userId, true)
+	if err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": err.Error(),
+		})
+		return
+	}
+
+	// 构建设置
+	settings := map[string]interface{}{
+		constant.UserSettingNotifyType:            req.QuotaWarningType,
+		constant.UserSettingQuotaWarningThreshold: req.QuotaWarningThreshold,
+	}
+
+	// 如果是webhook类型,添加webhook相关设置
+	if req.QuotaWarningType == constant.NotifyTypeWebhook {
+		settings[constant.UserSettingWebhookUrl] = req.WebhookUrl
+		if req.WebhookSecret != "" {
+			settings[constant.UserSettingWebhookSecret] = req.WebhookSecret
+		}
+	}
+
+	// 如果提供了通知邮箱，添加到设置中
+	if req.QuotaWarningType == constant.NotifyTypeEmail && req.NotificationEmail != "" {
+		settings[constant.UserSettingNotificationEmail] = req.NotificationEmail
+	}
+
+	// 更新用户设置
+	user.SetSetting(settings)
+	if err := user.Update(false); err != nil {
+		c.JSON(http.StatusOK, gin.H{
+			"success": false,
+			"message": "更新设置失败: " + err.Error(),
+		})
+		return
+	}
+
+	c.JSON(http.StatusOK, gin.H{
+		"success": true,
+		"message": "设置已更新",
+	})
+}

controller/wechat.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"github.com/gin-contrib/sessions"
 	"github.com/gin-gonic/gin"
 	"net/http"
 	"one-api/common"
@@ -142,9 +143,10 @@ func WeChatBind(c *gin.Context) {
 		})
 		return
 	}
-	id := c.GetInt("id")
+	session := sessions.Default(c)
+	id := session.Get("id")
 	user := model.User{
-		Id: id,
+		Id: id.(int),
 	}
 	err = user.FillUserById()
 	if err != nil {

docker-compose.yml

@@ -24,7 +24,7 @@ services:
       - redis
       - mysql
     healthcheck:
-      test: [ "CMD-SHELL", "wget -q -O - http://localhost:3000/api/status | grep -o '\"success\":\\s*true' | awk -F: '{print $2}'" ]
+      test: ["CMD-SHELL", "wget -q -O - http://localhost:3000/api/status | grep -o '\"success\":\\s*true' | awk -F: '{print $$2}'"]
       interval: 30s
       timeout: 10s
       retries: 3

docs/channel/other_setting.md

@@ -0,0 +1,28 @@
+# 渠道而外设置说明
+
+该配置用于设置一些额外的渠道参数，可以通过 JSON 对象进行配置。主要包含以下两个设置项：
+
+1. force_format
+    - 用于标识是否对数据进行强制格式化为 OpenAI 格式
+    - 类型为布尔值，设置为 true 时启用强制格式化
+
+2. proxy
+    - 用于配置网络代理
+    - 类型为字符串，填写代理地址（例如 socks5 协议的代理地址）
+
+--------------------------------------------------------------
+
+## JSON 格式示例
+
+以下是一个示例配置，启用强制格式化并设置了代理地址：
+
+```json
+{
+    "force_format": true,
+    "proxy": "socks5://xxxxxxx"
+}
+```
+
+--------------------------------------------------------------
+
+通过调整上述 JSON 配置中的值，可以灵活控制渠道的额外行为，比如是否进行格式化以及使用特定的网络代理。

dto/embedding.go

@@ -0,0 +1,57 @@
+package dto
+
+type EmbeddingOptions struct {
+	Seed             int      `json:"seed,omitempty"`
+	Temperature      *float64 `json:"temperature,omitempty"`
+	TopK             int      `json:"top_k,omitempty"`
+	TopP             *float64 `json:"top_p,omitempty"`
+	FrequencyPenalty *float64 `json:"frequency_penalty,omitempty"`
+	PresencePenalty  *float64 `json:"presence_penalty,omitempty"`
+	NumPredict       int      `json:"num_predict,omitempty"`
+	NumCtx           int      `json:"num_ctx,omitempty"`
+}
+
+type EmbeddingRequest struct {
+	Model            string   `json:"model"`
+	Input            any      `json:"input"`
+	EncodingFormat   string   `json:"encoding_format,omitempty"`
+	Dimensions       int      `json:"dimensions,omitempty"`
+	User             string   `json:"user,omitempty"`
+	Seed             float64  `json:"seed,omitempty"`
+	Temperature      *float64 `json:"temperature,omitempty"`
+	TopP             float64  `json:"top_p,omitempty"`
+	FrequencyPenalty float64  `json:"frequency_penalty,omitempty"`
+	PresencePenalty  float64  `json:"presence_penalty,omitempty"`
+}
+
+func (r EmbeddingRequest) ParseInput() []string {
+	if r.Input == nil {
+		return nil
+	}
+	var input []string
+	switch r.Input.(type) {
+	case string:
+		input = []string{r.Input.(string)}
+	case []any:
+		input = make([]string, 0, len(r.Input.([]any)))
+		for _, item := range r.Input.([]any) {
+			if str, ok := item.(string); ok {
+				input = append(input, str)
+			}
+		}
+	}
+	return input
+}
+
+type EmbeddingResponseItem struct {
+	Object    string    `json:"object"`
+	Index     int       `json:"index"`
+	Embedding []float64 `json:"embedding"`
+}
+
+type EmbeddingResponse struct {
+	Object string                  `json:"object"`
+	Data   []EmbeddingResponseItem `json:"data"`
+	Model  string                  `json:"model"`
+	Usage  `json:"usage"`
+}

dto/notify.go

@@ -0,0 +1,25 @@
+package dto
+
+type Notify struct {
+	Type    string        `json:"type"`
+	Title   string        `json:"title"`
+	Content string        `json:"content"`
+	Values  []interface{} `json:"values"`
+}
+
+const ContentValueParam = "{{value}}"
+
+const (
+	NotifyTypeQuotaExceed   = "quota_exceed"
+	NotifyTypeChannelUpdate = "channel_update"
+	NotifyTypeChannelTest   = "channel_test"
+)
+
+func NewNotify(t string, title string, content string, values []interface{}) Notify {
+	return Notify{
+		Type:    t,
+		Title:   title,
+		Content: content,
+		Values:  values,
+	}
+}

dto/openai_request.go

@@ -18,6 +18,8 @@ type GeneralOpenAIRequest struct {
 	Model               string          `json:"model,omitempty"`
 	Messages            []Message       `json:"messages,omitempty"`
 	Prompt              any             `json:"prompt,omitempty"`
+	Prefix              any             `json:"prefix,omitempty"`
+	Suffix              any             `json:"suffix,omitempty"`
 	Stream              bool            `json:"stream,omitempty"`
 	StreamOptions       *StreamOptions  `json:"stream_options,omitempty"`
 	MaxTokens           uint            `json:"max_tokens,omitempty"`
@@ -86,11 +88,15 @@ func (r GeneralOpenAIRequest) ParseInput() []string {
 }
 
 type Message struct {
-	Role       string          `json:"role"`
-	Content    json.RawMessage `json:"content"`
-	Name       *string         `json:"name,omitempty"`
-	ToolCalls  json.RawMessage `json:"tool_calls,omitempty"`
-	ToolCallId string          `json:"tool_call_id,omitempty"`
+	Role                string          `json:"role"`
+	Content             json.RawMessage `json:"content"`
+	Name                *string         `json:"name,omitempty"`
+	Prefix              *bool           `json:"prefix,omitempty"`
+	ReasoningContent    string          `json:"reasoning_content,omitempty"`
+	ToolCalls           json.RawMessage `json:"tool_calls,omitempty"`
+	ToolCallId          string          `json:"tool_call_id,omitempty"`
+	parsedContent       []MediaContent
+	parsedStringContent *string
 }
 
 type MediaContent struct {
@@ -116,6 +122,17 @@ const (
 	ContentTypeInputAudio = "input_audio"
 )
 
+func (m *Message) GetPrefix() bool {
+	if m.Prefix == nil {
+		return false
+	}
+	return *m.Prefix
+}
+
+func (m *Message) SetPrefix(prefix bool) {
+	m.Prefix = &prefix
+}
+
 func (m *Message) ParseToolCalls() []ToolCall {
 	if m.ToolCalls == nil {
 		return nil
@@ -133,6 +150,9 @@ func (m *Message) SetToolCalls(toolCalls any) {
 }
 
 func (m *Message) StringContent() string {
+	if m.parsedStringContent != nil {
+		return *m.parsedStringContent
+	}
 	var stringContent string
 	if err := json.Unmarshal(m.Content, &stringContent); err == nil {
 		return stringContent
@@ -143,78 +163,113 @@ func (m *Message) StringContent() string {
 func (m *Message) SetStringContent(content string) {
 	jsonContent, _ := json.Marshal(content)
 	m.Content = jsonContent
+	m.parsedStringContent = &content
+	m.parsedContent = nil
+}
+
+func (m *Message) SetMediaContent(content []MediaContent) {
+	jsonContent, _ := json.Marshal(content)
+	m.Content = jsonContent
+	m.parsedContent = nil
+	m.parsedStringContent = nil
 }
 
 func (m *Message) IsStringContent() bool {
+	if m.parsedStringContent != nil {
+		return true
+	}
 	var stringContent string
 	if err := json.Unmarshal(m.Content, &stringContent); err == nil {
+		m.parsedStringContent = &stringContent
 		return true
 	}
 	return false
 }
 
 func (m *Message) ParseContent() []MediaContent {
+	if m.parsedContent != nil {
+		return m.parsedContent
+	}
+
 	var contentList []MediaContent
+
+	// 先尝试解析为字符串
 	var stringContent string
 	if err := json.Unmarshal(m.Content, &stringContent); err == nil {
-		contentList = append(contentList, MediaContent{
+		contentList = []MediaContent{{
 			Type: ContentTypeText,
 			Text: stringContent,
-		})
+		}}
+		m.parsedContent = contentList
 		return contentList
 	}
-	var arrayContent []json.RawMessage
+
+	// 尝试解析为数组
+	var arrayContent []map[string]interface{}
 	if err := json.Unmarshal(m.Content, &arrayContent); err == nil {
 		for _, contentItem := range arrayContent {
-			var contentMap map[string]any
-			if err := json.Unmarshal(contentItem, &contentMap); err != nil {
+			contentType, ok := contentItem["type"].(string)
+			if !ok {
 				continue
 			}
-			switch contentMap["type"] {
+
+			switch contentType {
 			case ContentTypeText:
-				if subStr, ok := contentMap["text"].(string); ok {
+				if text, ok := contentItem["text"].(string); ok {
 					contentList = append(contentList, MediaContent{
 						Type: ContentTypeText,
-						Text: subStr,
+						Text: text,
 					})
 				}
+
 			case ContentTypeImageURL:
-				if subObj, ok := contentMap["image_url"].(map[string]any); ok {
-					detail, ok := subObj["detail"]
-					if ok {
-						subObj["detail"] = detail.(string)
-					} else {
-						subObj["detail"] = "high"
-					}
+				imageUrl := contentItem["image_url"]
+				switch v := imageUrl.(type) {
+				case string:
 					contentList = append(contentList, MediaContent{
 						Type: ContentTypeImageURL,
 						ImageUrl: MessageImageUrl{
-							Url:    subObj["url"].(string),
-							Detail: subObj["detail"].(string),
-						},
-					})
-				} else if url, ok := contentMap["image_url"].(string); ok {
-					contentList = append(contentList, MediaContent{
-						Type: ContentTypeImageURL,
-						ImageUrl: MessageImageUrl{
-							Url:    url,
+							Url:    v,
 							Detail: "high",
 						},
 					})
+				case map[string]interface{}:
+					url, ok1 := v["url"].(string)
+					detail, ok2 := v["detail"].(string)
+					if !ok2 {
+						detail = "high"
+					}
+					if ok1 {
+						contentList = append(contentList, MediaContent{
+							Type: ContentTypeImageURL,
+							ImageUrl: MessageImageUrl{
+								Url:    url,
+								Detail: detail,
+							},
+						})
+					}
 				}
+
 			case ContentTypeInputAudio:
-				if subObj, ok := contentMap["input_audio"].(map[string]any); ok {
-					contentList = append(contentList, MediaContent{
-						Type: ContentTypeInputAudio,
-						InputAudio: MessageInputAudio{
-							Data:   subObj["data"].(string),
-							Format: subObj["format"].(string),
-						},
-					})
+				if audioData, ok := contentItem["input_audio"].(map[string]interface{}); ok {
+					data, ok1 := audioData["data"].(string)
+					format, ok2 := audioData["format"].(string)
+					if ok1 && ok2 {
+						contentList = append(contentList, MediaContent{
+							Type: ContentTypeInputAudio,
+							InputAudio: MessageInputAudio{
+								Data:   data,
+								Format: format,
+							},
+						})
+					}
 				}
 			}
 		}
-		return contentList
 	}
-	return nil
+
+	if len(contentList) > 0 {
+		m.parsedContent = contentList
+	}
+	return contentList
 }

dto/openai_response.go

@@ -62,9 +62,10 @@ type ChatCompletionsStreamResponseChoice struct {
 }
 
 type ChatCompletionsStreamResponseChoiceDelta struct {
-	Content   *string    `json:"content,omitempty"`
-	Role      string     `json:"role,omitempty"`
-	ToolCalls []ToolCall `json:"tool_calls,omitempty"`
+	Content          *string    `json:"content,omitempty"`
+	ReasoningContent *string    `json:"reasoning_content,omitempty"`
+	Role             string     `json:"role,omitempty"`
+	ToolCalls        []ToolCall `json:"tool_calls,omitempty"`
 }
 
 func (c *ChatCompletionsStreamResponseChoiceDelta) SetContentString(s string) {
@@ -78,10 +79,17 @@ func (c *ChatCompletionsStreamResponseChoiceDelta) GetContentString() string {
 	return *c.Content
 }
 
+func (c *ChatCompletionsStreamResponseChoiceDelta) GetReasoningContent() string {
+	if c.ReasoningContent == nil {
+		return ""
+	}
+	return *c.ReasoningContent
+}
+
 type ToolCall struct {
 	// Index is not nil only in chat completion chunk object
 	Index    *int         `json:"index,omitempty"`
-	ID       string       `json:"id"`
+	ID       string       `json:"id,omitempty"`
 	Type     any          `json:"type"`
 	Function FunctionCall `json:"function"`
 }

go.mod

@@ -16,6 +16,7 @@ require (
 	github.com/gin-contrib/sessions v0.0.5
 	github.com/gin-contrib/static v0.0.1
 	github.com/gin-gonic/gin v1.9.1
+	github.com/glebarez/sqlite v1.9.0
 	github.com/go-playground/validator/v10 v10.20.0
 	github.com/go-redis/redis/v8 v8.11.5
 	github.com/golang-jwt/jwt v3.2.2+incompatible
@@ -29,10 +30,10 @@ require (
 	github.com/shirou/gopsutil v3.21.11+incompatible
 	golang.org/x/crypto v0.27.0
 	golang.org/x/image v0.23.0
+	golang.org/x/net v0.28.0
 	gorm.io/driver/mysql v1.4.3
 	gorm.io/driver/postgres v1.5.2
-	gorm.io/driver/sqlite v1.4.3
-	gorm.io/gorm v1.25.0
+	gorm.io/gorm v1.25.2
 )
 
 require (
@@ -48,12 +49,14 @@ require (
 	github.com/cloudwego/iasm v0.2.0 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/dlclark/regexp2 v1.11.0 // indirect
+	github.com/dustin/go-humanize v1.0.1 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.3 // indirect
 	github.com/gin-contrib/sse v0.1.0 // indirect
+	github.com/glebarez/go-sqlite v1.21.2 // indirect
 	github.com/go-ole/go-ole v1.2.6 // indirect
 	github.com/go-playground/locales v0.14.1 // indirect
 	github.com/go-playground/universal-translator v0.18.1 // indirect
-	github.com/go-sql-driver/mysql v1.6.0 // indirect
+	github.com/go-sql-driver/mysql v1.7.0 // indirect
 	github.com/goccy/go-json v0.10.2 // indirect
 	github.com/google/go-cmp v0.6.0 // indirect
 	github.com/gorilla/context v1.1.1 // indirect
@@ -69,11 +72,11 @@ require (
 	github.com/klauspost/cpuid/v2 v2.2.9 // indirect
 	github.com/leodido/go-urn v1.4.0 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
-	github.com/mattn/go-sqlite3 v2.0.3+incompatible // indirect
 	github.com/mitchellh/mapstructure v1.5.0 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/pelletier/go-toml/v2 v2.2.1 // indirect
+	github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
 	github.com/tklauser/go-sysconf v0.3.12 // indirect
 	github.com/tklauser/numcpus v0.6.1 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
@@ -81,10 +84,13 @@ require (
 	github.com/yusufpapurcu/wmi v1.2.3 // indirect
 	golang.org/x/arch v0.12.0 // indirect
 	golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 // indirect
-	golang.org/x/net v0.28.0 // indirect
 	golang.org/x/sync v0.10.0 // indirect
 	golang.org/x/sys v0.27.0 // indirect
 	golang.org/x/text v0.21.0 // indirect
 	google.golang.org/protobuf v1.34.2 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
+	modernc.org/libc v1.22.5 // indirect
+	modernc.org/mathutil v1.5.0 // indirect
+	modernc.org/memory v1.5.0 // indirect
+	modernc.org/sqlite v1.23.1 // indirect
 )

go.sum

@@ -40,6 +40,8 @@ github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f h1:lO4WD4F/r
 github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cuUVRXasLTGF7a8hSLbxyZXjz+1KgoB3wDUb6vlszIc=
 github.com/dlclark/regexp2 v1.11.0 h1:G/nrcoOa7ZXlpoa/91N3X7mM3r8eIlMBBJZvsz/mxKI=
 github.com/dlclark/regexp2 v1.11.0/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
+github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
+github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
 github.com/fsnotify/fsnotify v1.4.9 h1:hsms1Qyu0jgnwNXIxa+/V/PDsU6CfLf6CNO8H7IWoS4=
 github.com/fsnotify/fsnotify v1.4.9/go.mod h1:znqG4EE+3YCdAaPaxE2ZRY/06pZUdp0tY4IgpuI1SZQ=
 github.com/gabriel-vasile/mimetype v1.4.3 h1:in2uUcidCuFcDKtdcBxlR0rJ1+fsokWf+uqxgUFjbI0=
@@ -58,6 +60,10 @@ github.com/gin-gonic/gin v1.6.3/go.mod h1:75u5sXoLsGZoRN5Sgbi1eraJ4GU3++wFwWzhwv
 github.com/gin-gonic/gin v1.8.1/go.mod h1:ji8BvRH1azfM+SYow9zQ6SZMvR8qOMZHmsCuWR9tTTk=
 github.com/gin-gonic/gin v1.9.1 h1:4idEAncQnU5cB7BeOkPtxjfCSye0AAm1R0RVIqJ+Jmg=
 github.com/gin-gonic/gin v1.9.1/go.mod h1:hPrL7YrpYKXt5YId3A/Tnip5kqbEAP+KLuI3SUcPTeU=
+github.com/glebarez/go-sqlite v1.21.2 h1:3a6LFC4sKahUunAmynQKLZceZCOzUthkRkEAl9gAXWo=
+github.com/glebarez/go-sqlite v1.21.2/go.mod h1:sfxdZyhQjTM2Wry3gVYWaW072Ri1WMdWJi0k6+3382k=
+github.com/glebarez/sqlite v1.9.0 h1:Aj6bPA12ZEx5GbSF6XADmCkYXlljPNUY+Zf1EQxynXs=
+github.com/glebarez/sqlite v1.9.0/go.mod h1:YBYCoyupOao60lzp1MVBLEjZfgkq0tdB1voAQ09K9zw=
 github.com/go-ole/go-ole v1.2.6 h1:/Fpf6oFPoeFik9ty7siob0G6Ke8QvQEuVcuChpwXzpY=
 github.com/go-ole/go-ole v1.2.6/go.mod h1:pprOEPIfldk/42T2oK7lQ4v4JSDwmV0As9GaiUsvbm0=
 github.com/go-playground/assert/v2 v2.0.1/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
@@ -77,8 +83,9 @@ github.com/go-playground/validator/v10 v10.20.0 h1:K9ISHbSaI0lyB2eWMPJo+kOS/FBEx
 github.com/go-playground/validator/v10 v10.20.0/go.mod h1:dbuPbCMFw/DrkbEynArYaCwl3amGuJotoKCe95atGMM=
 github.com/go-redis/redis/v8 v8.11.5 h1:AcZZR7igkdvfVmQTPnu9WE37LRrO/YrBH5zWyjDC0oI=
 github.com/go-redis/redis/v8 v8.11.5/go.mod h1:gREzHqY1hg6oD9ngVRbLStwAWKhA0FEgq8Jd4h5lpwo=
-github.com/go-sql-driver/mysql v1.6.0 h1:BCTh4TKNUYmOmMUcQ3IipzF5prigylS7XXjEkfCHuOE=
 github.com/go-sql-driver/mysql v1.6.0/go.mod h1:DCzpHaOWr8IXmIStZouvnhqoel9Qv2LBy8hT2VhHyBg=
+github.com/go-sql-driver/mysql v1.7.0 h1:ueSltNNllEqE3qcWBTD0iQd3IpL/6U+mJxLkazJ7YPc=
+github.com/go-sql-driver/mysql v1.7.0/go.mod h1:OXbVy3sEdcQ2Doequ6Z5BW6fXNQTmx+9S1MCJN5yJMI=
 github.com/goccy/go-json v0.9.7/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
 github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
 github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
@@ -90,6 +97,8 @@ github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/
 github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
 github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
+github.com/google/pprof v0.0.0-20221118152302-e6195bd50e26 h1:Xim43kblpZXfIBQsbuBVKCudVG457BR2GZFIz3uw3hQ=
+github.com/google/pprof v0.0.0-20221118152302-e6195bd50e26/go.mod h1:dDKJzRmX4S37WGHujM7tX//fmj1uioxKzKxz3lo4HJo=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/gorilla/context v1.1.1 h1:AWwleXJkX/nhcU9bZSnZoi3h/qGYqQAGhq6zZe/aQW8=
@@ -140,9 +149,6 @@ github.com/mattn/go-isatty v0.0.12/go.mod h1:cbi8OIDigv2wuxKPP5vlRcQ1OAZbq2CE4Ky
 github.com/mattn/go-isatty v0.0.14/go.mod h1:7GGIvUiUoEMVVmxf/4nioHXj79iQHKdU27kJ6hsGG94=
 github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
 github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
-github.com/mattn/go-sqlite3 v1.14.15/go.mod h1:2eHXhiwb8IkHr+BDWZGa96P6+rkvnG63S2DGjv9HUNg=
-github.com/mattn/go-sqlite3 v2.0.3+incompatible h1:gXHsfypPkaMZrKbD5209QV9jbUTJKjyR5WD3HYQSd+U=
-github.com/mattn/go-sqlite3 v2.0.3+incompatible/go.mod h1:FPy6KqzDD04eiIsT53CuJW3U88zkxoIYsOqkbpncsNc=
 github.com/mitchellh/mapstructure v1.5.0 h1:jeMsZIYE/09sWLaz43PL7Gy6RuMjD2eJVyuac5Z2hdY=
 github.com/mitchellh/mapstructure v1.5.0/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=
 github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
@@ -167,6 +173,9 @@ github.com/pkoukk/tiktoken-go v0.1.7 h1:qOBHXX4PHtvIvmOtyg1EeKlwFRiMKAcoMp4Q+bLQ
 github.com/pkoukk/tiktoken-go v0.1.7/go.mod h1:9NiV+i9mJKGj1rYOT+njbv+ZwA/zJxYdewGl6qVatpg=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/remyoudompheng/bigfft v0.0.0-20200410134404-eec4a21b6bb0/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
+github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec h1:W09IVJc94icq4NjY3clb7Lk8O1qJ8BdBEF8z0ibU0rE=
+github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
 github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=
 github.com/rogpeppe/go-internal v1.8.0 h1:FCbCCtXNOY3UtUuHUYaghJg4y7Fd14rXifAYUAtL9R8=
 github.com/rogpeppe/go-internal v1.8.0/go.mod h1:WmiCO8CzOY8rg0OYDC4/i/2WRWAB6poM+XZ2dLUbcbE=
@@ -263,11 +272,16 @@ gorm.io/driver/mysql v1.4.3 h1:/JhWJhO2v17d8hjApTltKNADm7K7YI2ogkR7avJUL3k=
 gorm.io/driver/mysql v1.4.3/go.mod h1:sSIebwZAVPiT+27jK9HIwvsqOGKx3YMPmrA3mBJR10c=
 gorm.io/driver/postgres v1.5.2 h1:ytTDxxEv+MplXOfFe3Lzm7SjG09fcdb3Z/c056DTBx0=
 gorm.io/driver/postgres v1.5.2/go.mod h1:fmpX0m2I1PKuR7mKZiEluwrP3hbs+ps7JIGMUBpCgl8=
-gorm.io/driver/sqlite v1.4.3 h1:HBBcZSDnWi5BW3B3rwvVTc510KGkBkexlOg0QrmLUuU=
-gorm.io/driver/sqlite v1.4.3/go.mod h1:0Aq3iPO+v9ZKbcdiz8gLWRw5VOPcBOPUQJFLq5e2ecI=
 gorm.io/gorm v1.23.8/go.mod h1:l2lP/RyAtc1ynaTjFksBde/O8v9oOGIApu2/xRitmZk=
-gorm.io/gorm v1.24.0/go.mod h1:DVrVomtaYTbqs7gB/x2uVvqnXzv0nqjB396B8cG4dBA=
-gorm.io/gorm v1.25.0 h1:+KtYtb2roDz14EQe4bla8CbQlmb9dN3VejSai3lprfU=
-gorm.io/gorm v1.25.0/go.mod h1:L4uxeKpfBml98NYqVqwAdmV1a2nBtAec/cf3fpucW/k=
+gorm.io/gorm v1.25.2 h1:gs1o6Vsa+oVKG/a9ElL3XgyGfghFfkKA2SInQaCyMho=
+gorm.io/gorm v1.25.2/go.mod h1:L4uxeKpfBml98NYqVqwAdmV1a2nBtAec/cf3fpucW/k=
+modernc.org/libc v1.22.5 h1:91BNch/e5B0uPbJFgqbxXuOnxBQjlS//icfQEGmvyjE=
+modernc.org/libc v1.22.5/go.mod h1:jj+Z7dTNX8fBScMVNRAYZ/jF91K8fdT2hYMThc3YjBY=
+modernc.org/mathutil v1.5.0 h1:rV0Ko/6SfM+8G+yKiyI830l3Wuz1zRutdslNoQ0kfiQ=
+modernc.org/mathutil v1.5.0/go.mod h1:mZW8CKdRPY1v87qxC/wUdX5O1qDzXMP5TH3wjfpga6E=
+modernc.org/memory v1.5.0 h1:N+/8c5rE6EqugZwHii4IFsaJ7MUhoWX07J5tC/iI5Ds=
+modernc.org/memory v1.5.0/go.mod h1:PkUhL0Mugw21sHPeskwZW4D6VscE/GQJOnIpCnW6pSU=
+modernc.org/sqlite v1.23.1 h1:nrSBg4aRQQwq59JpvGEQ15tNxoO5pX/kUjcRNwSAGQM=
+modernc.org/sqlite v1.23.1/go.mod h1:OrDj17Mggn6MhE+iPbBNf7RGKODDE9NFT0f3EwDzJqk=
 nullprogram.com/x/optparse v1.0.0/go.mod h1:KdyPE+Igbe0jQUrVfMqDMeJQIJZEuyV7pjYmp6pbG50=
 rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=

main.go

@@ -119,9 +119,9 @@ func main() {
 	}
 
 	if os.Getenv("ENABLE_PPROF") == "true" {
-		go func() {
+		gopool.Go(func() {
 			log.Println(http.ListenAndServe("0.0.0.0:8005", nil))
-		}()
+		})
 		go common.Monitor()
 		common.SysLog("pprof enabled")
 	}
@@ -145,6 +145,13 @@ func main() {
 	middleware.SetUpLogger(server)
 	// Initialize session store
 	store := cookie.NewStore([]byte(common.SessionSecret))
+	store.Options(sessions.Options{
+		Path:     "/",
+		MaxAge:   2592000, // 30 days
+		HttpOnly: true,
+		Secure:   false,
+		SameSite: http.SameSiteStrictMode,
+	})
 	server.Use(sessions.Sessions("session", store))
 
 	router.SetRouter(server, buildFS, indexPage)

middleware/distributor.go

@@ -135,17 +135,14 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 			midjourneyRequest := dto.MidjourneyRequest{}
 			err = common.UnmarshalBodyReusable(c, &midjourneyRequest)
 			if err != nil {
-				abortWithMidjourneyMessage(c, http.StatusBadRequest, constant.MjErrorUnknown, "无效的请求, "+err.Error())
 				return nil, false, err
 			}
 			midjourneyModel, mjErr, success := service.GetMjRequestModel(relayMode, &midjourneyRequest)
 			if mjErr != nil {
-				abortWithMidjourneyMessage(c, http.StatusBadRequest, mjErr.Code, mjErr.Description)
 				return nil, false, fmt.Errorf(mjErr.Description)
 			}
 			if midjourneyModel == "" {
 				if !success {
-					abortWithMidjourneyMessage(c, http.StatusBadRequest, constant.MjErrorUnknown, "无效的请求, 无法解析模型")
 					return nil, false, fmt.Errorf("无效的请求, 无法解析模型")
 				} else {
 					// task fetch, task fetch by condition, notify
@@ -170,7 +167,6 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 		err = common.UnmarshalBodyReusable(c, &modelRequest)
 	}
 	if err != nil {
-		abortWithOpenAiMessage(c, http.StatusBadRequest, "无效的请求, "+err.Error())
 		return nil, false, errors.New("无效的请求, " + err.Error())
 	}
 	if strings.HasPrefix(c.Request.URL.Path, "/v1/realtime") {
@@ -239,5 +235,7 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 		c.Set("plugin", channel.Other)
 	case common.ChannelCloudflare:
 		c.Set("api_version", channel.Other)
+	case common.ChannelTypeMokaAI:
+		c.Set("api_version", channel.Other)
 	}
 }

model/cache.go

@@ -11,106 +11,6 @@ import (
 	"time"
 )
 
-//func CacheGetUserGroup(id int) (group string, err error) {
-//	if !common.RedisEnabled {
-//		return GetUserGroup(id)
-//	}
-//	group, err = common.RedisGet(fmt.Sprintf("user_group:%d", id))
-//	if err != nil {
-//		group, err = GetUserGroup(id)
-//		if err != nil {
-//			return "", err
-//		}
-//		err = common.RedisSet(fmt.Sprintf("user_group:%d", id), group, time.Duration(constant.UserId2GroupCacheSeconds)*time.Second)
-//		if err != nil {
-//			common.SysError("Redis set user group error: " + err.Error())
-//		}
-//	}
-//	return group, err
-//}
-//
-//func CacheGetUsername(id int) (username string, err error) {
-//	if !common.RedisEnabled {
-//		return GetUsernameById(id)
-//	}
-//	username, err = common.RedisGet(fmt.Sprintf("user_name:%d", id))
-//	if err != nil {
-//		username, err = GetUsernameById(id)
-//		if err != nil {
-//			return "", err
-//		}
-//		err = common.RedisSet(fmt.Sprintf("user_name:%d", id), username, time.Duration(constant.UserId2GroupCacheSeconds)*time.Second)
-//		if err != nil {
-//			common.SysError("Redis set user group error: " + err.Error())
-//		}
-//	}
-//	return username, err
-//}
-//
-//func CacheGetUserQuota(id int) (quota int, err error) {
-//	if !common.RedisEnabled {
-//		return GetUserQuota(id)
-//	}
-//	quotaString, err := common.RedisGet(fmt.Sprintf("user_quota:%d", id))
-//	if err != nil {
-//		quota, err = GetUserQuota(id)
-//		if err != nil {
-//			return 0, err
-//		}
-//		return quota, nil
-//	}
-//	quota, err = strconv.Atoi(quotaString)
-//	return quota, nil
-//}
-//
-//func CacheUpdateUserQuota(id int) error {
-//	if !common.RedisEnabled {
-//		return nil
-//	}
-//	quota, err := GetUserQuota(id)
-//	if err != nil {
-//		return err
-//	}
-//	return cacheSetUserQuota(id, quota)
-//}
-//
-//func cacheSetUserQuota(id int, quota int) error {
-//	err := common.RedisSet(fmt.Sprintf("user_quota:%d", id), fmt.Sprintf("%d", quota), time.Duration(constant.UserId2QuotaCacheSeconds)*time.Second)
-//	return err
-//}
-//
-//func CacheDecreaseUserQuota(id int, quota int) error {
-//	if !common.RedisEnabled {
-//		return nil
-//	}
-//	err := common.RedisDecrease(fmt.Sprintf("user_quota:%d", id), int64(quota))
-//	return err
-//}
-//
-//func CacheIsUserEnabled(userId int) (bool, error) {
-//	if !common.RedisEnabled {
-//		return IsUserEnabled(userId)
-//	}
-//	enabled, err := common.RedisGet(fmt.Sprintf("user_enabled:%d", userId))
-//	if err == nil {
-//		return enabled == "1", nil
-//	}
-//
-//	userEnabled, err := IsUserEnabled(userId)
-//	if err != nil {
-//		return false, err
-//	}
-//	enabled = "0"
-//	if userEnabled {
-//		enabled = "1"
-//	}
-//	err = common.RedisSet(fmt.Sprintf("user_enabled:%d", userId), enabled, time.Duration(constant.UserId2StatusCacheSeconds)*time.Second)
-//	if err != nil {
-//		common.SysError("Redis set user enabled error: " + err.Error())
-//	}
-//	return userEnabled, err
-//}
-
 var group2model2channels map[string]map[string][]*Channel
 var channelsIDM map[int]*Channel
 var channelSyncLock sync.RWMutex

model/channel.go

@@ -28,7 +28,7 @@ type Channel struct {
 	Models             string  `json:"models"`
 	Group              string  `json:"group" gorm:"type:varchar(64);default:'default'"`
 	UsedQuota          int64   `json:"used_quota" gorm:"bigint;default:0"`
-	ModelMapping       *string `json:"model_mapping" gorm:"type:varchar(1024);default:''"`
+	ModelMapping       *string `json:"model_mapping" gorm:"type:text"`
 	//MaxInputTokens     *int    `json:"max_input_tokens" gorm:"default:0"`
 	StatusCodeMapping *string `json:"status_code_mapping" gorm:"type:varchar(1024);default:''"`
 	Priority          *int64  `json:"priority" gorm:"bigint;default:0"`

model/log.go

@@ -133,9 +133,6 @@ func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName
 		tx = LOG_DB.Where("logs.type = ?", logType)
 	}
 
-	tx = tx.Joins("LEFT JOIN channels ON logs.channel_id = channels.id")
-	tx = tx.Select("logs.*, channels.name as channel_name")
-
 	if modelName != "" {
 		tx = tx.Where("logs.model_name like ?", modelName)
 	}
@@ -165,6 +162,30 @@ func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName
 	if err != nil {
 		return nil, 0, err
 	}
+
+	channelIds := make([]int, 0)
+	channelMap := make(map[int]string)
+	for _, log := range logs {
+		if log.ChannelId != 0 {
+			channelIds = append(channelIds, log.ChannelId)
+		}
+	}
+	if len(channelIds) > 0 {
+		var channels []struct {
+			Id   int    `gorm:"column:id"`
+			Name string `gorm:"column:name"`
+		}
+		if err = DB.Table("channels").Select("id, name").Where("id IN ?", channelIds).Find(&channels).Error; err != nil {
+			return logs, total, err
+		}
+		for _, channel := range channels {
+			channelMap[channel.Id] = channel.Name
+		}
+		for i := range logs {
+			logs[i].ChannelName = channelMap[logs[i].ChannelId]
+		}
+	}
+
 	return logs, total, err
 }
 
@@ -176,9 +197,6 @@ func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int
 		tx = LOG_DB.Where("logs.user_id = ? and logs.type = ?", userId, logType)
 	}
 
-	tx = tx.Joins("LEFT JOIN channels ON logs.channel_id = channels.id")
-	tx = tx.Select("logs.*, channels.name as channel_name")
-
 	if modelName != "" {
 		tx = tx.Where("logs.model_name like ?", modelName)
 	}
@@ -199,6 +217,10 @@ func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int
 		return nil, 0, err
 	}
 	err = tx.Order("logs.id desc").Limit(num).Offset(startIdx).Find(&logs).Error
+	if err != nil {
+		return nil, 0, err
+	}
+
 	formatUserLogs(logs)
 	return logs, total, err
 }

model/main.go

@@ -1,9 +1,9 @@
 package model
 
 import (
+	"github.com/glebarez/sqlite"
 	"gorm.io/driver/mysql"
 	"gorm.io/driver/postgres"
-	"gorm.io/driver/sqlite"
 	"gorm.io/gorm"
 	"log"
 	"one-api/common"
@@ -119,12 +119,9 @@ func InitDB() (err error) {
 		if !common.IsMasterNode {
 			return nil
 		}
-		//if common.UsingMySQL {
-		//	_, _ = sqlDB.Exec("DROP INDEX idx_channels_key ON channels;")             // TODO: delete this line when most users have upgraded
-		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY action VARCHAR(40);")   // TODO: delete this line when most users have upgraded
-		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY progress VARCHAR(30);") // TODO: delete this line when most users have upgraded
-		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY status VARCHAR(20);")   // TODO: delete this line when most users have upgraded
-		//}
+		if common.UsingMySQL {
+			_, _ = sqlDB.Exec("ALTER TABLE channels MODIFY model_mapping TEXT;") // TODO: delete this line when most users have upgraded
+		}
 		common.SysLog("database migration started")
 		err = migrateDB()
 		return err

model/option.go

@@ -84,7 +84,7 @@ func InitOptionMap() {
 	common.OptionMap["QuotaForInviter"] = strconv.Itoa(common.QuotaForInviter)
 	common.OptionMap["QuotaForInvitee"] = strconv.Itoa(common.QuotaForInvitee)
 	common.OptionMap["QuotaRemindThreshold"] = strconv.Itoa(common.QuotaRemindThreshold)
-	common.OptionMap["PreConsumedQuota"] = strconv.Itoa(common.PreConsumedQuota)
+	common.OptionMap["ShouldPreConsumedQuota"] = strconv.Itoa(common.PreConsumedQuota)
 	common.OptionMap["ModelRatio"] = common.ModelRatio2JSONString()
 	common.OptionMap["ModelPrice"] = common.ModelPrice2JSONString()
 	common.OptionMap["GroupRatio"] = setting.GroupRatio2JSONString()
@@ -104,11 +104,13 @@ func InitOptionMap() {
 	common.OptionMap["MjForwardUrlEnabled"] = strconv.FormatBool(setting.MjForwardUrlEnabled)
 	common.OptionMap["MjActionCheckSuccessEnabled"] = strconv.FormatBool(setting.MjActionCheckSuccessEnabled)
 	common.OptionMap["CheckSensitiveEnabled"] = strconv.FormatBool(setting.CheckSensitiveEnabled)
+	common.OptionMap["DemoSiteEnabled"] = strconv.FormatBool(setting.DemoSiteEnabled)
 	common.OptionMap["CheckSensitiveOnPromptEnabled"] = strconv.FormatBool(setting.CheckSensitiveOnPromptEnabled)
 	//common.OptionMap["CheckSensitiveOnCompletionEnabled"] = strconv.FormatBool(constant.CheckSensitiveOnCompletionEnabled)
 	common.OptionMap["StopOnSensitiveEnabled"] = strconv.FormatBool(setting.StopOnSensitiveEnabled)
 	common.OptionMap["SensitiveWords"] = setting.SensitiveWordsToString()
 	common.OptionMap["StreamCacheQueueLength"] = strconv.Itoa(setting.StreamCacheQueueLength)
+	common.OptionMap["AutomaticDisableKeywords"] = setting.AutomaticDisableKeywordsToString()
 
 	common.OptionMapRWMutex.Unlock()
 	loadOptionsFromDatabase()
@@ -220,6 +222,8 @@ func updateOptionMap(key string, value string) (err error) {
 			setting.MjActionCheckSuccessEnabled = boolValue
 		case "CheckSensitiveEnabled":
 			setting.CheckSensitiveEnabled = boolValue
+		case "DemoSiteEnabled":
+			setting.DemoSiteEnabled = boolValue
 		case "CheckSensitiveOnPromptEnabled":
 			setting.CheckSensitiveOnPromptEnabled = boolValue
 		//case "CheckSensitiveOnCompletionEnabled":
@@ -302,7 +306,7 @@ func updateOptionMap(key string, value string) (err error) {
 		common.QuotaForInvitee, _ = strconv.Atoi(value)
 	case "QuotaRemindThreshold":
 		common.QuotaRemindThreshold, _ = strconv.Atoi(value)
-	case "PreConsumedQuota":
+	case "ShouldPreConsumedQuota":
 		common.PreConsumedQuota, _ = strconv.Atoi(value)
 	case "RetryTimes":
 		common.RetryTimes, _ = strconv.Atoi(value)
@@ -332,6 +336,8 @@ func updateOptionMap(key string, value string) (err error) {
 		common.QuotaPerUnit, _ = strconv.ParseFloat(value, 64)
 	case "SensitiveWords":
 		setting.SensitiveWordsFromString(value)
+	case "AutomaticDisableKeywords":
+		setting.AutomaticDisableKeywordsFromString(value)
 	case "StreamCacheQueueLength":
 		setting.StreamCacheQueueLength, _ = strconv.Atoi(value)
 	}

model/token.go

@@ -3,13 +3,11 @@ package model
 import (
 	"errors"
 	"fmt"
+	"one-api/common"
+	"strings"
+
 	"github.com/bytedance/gopkg/util/gopool"
 	"gorm.io/gorm"
-	"one-api/common"
-	relaycommon "one-api/relay/common"
-	"one-api/setting"
-	"strconv"
-	"strings"
 )
 
 type Token struct {
@@ -322,80 +320,3 @@ func decreaseTokenQuota(id int, quota int) (err error) {
 	).Error
 	return err
 }
-
-func PreConsumeTokenQuota(relayInfo *relaycommon.RelayInfo, quota int) error {
-	if quota < 0 {
-		return errors.New("quota 不能为负数！")
-	}
-	if relayInfo.IsPlayground {
-		return nil
-	}
-	//if relayInfo.TokenUnlimited {
-	//	return nil
-	//}
-	token, err := GetTokenById(relayInfo.TokenId)
-	if err != nil {
-		return err
-	}
-	if !relayInfo.TokenUnlimited && token.RemainQuota < quota {
-		return errors.New("令牌额度不足")
-	}
-	err = DecreaseTokenQuota(relayInfo.TokenId, relayInfo.TokenKey, quota)
-	if err != nil {
-		return err
-	}
-	return nil
-}
-
-func PostConsumeQuota(relayInfo *relaycommon.RelayInfo, userQuota int, quota int, preConsumedQuota int, sendEmail bool) (err error) {
-
-	if quota > 0 {
-		err = DecreaseUserQuota(relayInfo.UserId, quota)
-	} else {
-		err = IncreaseUserQuota(relayInfo.UserId, -quota)
-	}
-	if err != nil {
-		return err
-	}
-
-	if !relayInfo.IsPlayground {
-		if quota > 0 {
-			err = DecreaseTokenQuota(relayInfo.TokenId, relayInfo.TokenKey, quota)
-		} else {
-			err = IncreaseTokenQuota(relayInfo.TokenId, relayInfo.TokenKey, -quota)
-		}
-		if err != nil {
-			return err
-		}
-	}
-
-	if sendEmail {
-		if (quota + preConsumedQuota) != 0 {
-			quotaTooLow := userQuota >= common.QuotaRemindThreshold && userQuota-(quota+preConsumedQuota) < common.QuotaRemindThreshold
-			noMoreQuota := userQuota-(quota+preConsumedQuota) <= 0
-			if quotaTooLow || noMoreQuota {
-				go func() {
-					email, err := GetUserEmail(relayInfo.UserId)
-					if err != nil {
-						common.SysError("failed to fetch user email: " + err.Error())
-					}
-					prompt := "您的额度即将用尽"
-					if noMoreQuota {
-						prompt = "您的额度已用尽"
-					}
-					if email != "" {
-						topUpLink := fmt.Sprintf("%s/topup", setting.ServerAddress)
-						err = common.SendEmail(prompt, email,
-							fmt.Sprintf("%s，当前剩余额度为 %d，为了不影响您的使用，请及时充值。<br/>充值链接：<a href='%s'>%s</a>", prompt, userQuota, topUpLink, topUpLink))
-						if err != nil {
-							common.SysError("failed to send email" + err.Error())
-						}
-						common.SysLog("user quota is low, consumed quota: " + strconv.Itoa(quota) + ", user quota: " + strconv.Itoa(userQuota))
-					}
-				}()
-			}
-		}
-	}
-
-	return nil
-}

model/token_cache.go

@@ -52,7 +52,7 @@ func cacheSetTokenField(key string, field string, value string) error {
 func cacheGetTokenByKey(key string) (*Token, error) {
 	hmacKey := common.GenerateHMAC(key)
 	if !common.RedisEnabled {
-		return nil, nil
+		return nil, fmt.Errorf("redis is not enabled")
 	}
 	var token Token
 	err := common.RedisHGetObj(fmt.Sprintf("token:%s", hmacKey), &token)

model/user.go

@@ -1,6 +1,7 @@
 package model
 
 import (
+	"encoding/json"
 	"errors"
 	"fmt"
 	"one-api/common"
@@ -38,6 +39,20 @@ type User struct {
 	InviterId        int            `json:"inviter_id" gorm:"type:int;column:inviter_id;index"`
 	DeletedAt        gorm.DeletedAt `gorm:"index"`
 	LinuxDOId        string         `json:"linux_do_id" gorm:"column:linux_do_id;index"`
+	Setting          string         `json:"setting" gorm:"type:text;column:setting"`
+}
+
+func (user *User) ToBaseUser() *UserBase {
+	cache := &UserBase{
+		Id:       user.Id,
+		Group:    user.Group,
+		Quota:    user.Quota,
+		Status:   user.Status,
+		Username: user.Username,
+		Setting:  user.Setting,
+		Email:    user.Email,
+	}
+	return cache
 }
 
 func (user *User) GetAccessToken() string {
@@ -51,6 +66,22 @@ func (user *User) SetAccessToken(token string) {
 	user.AccessToken = &token
 }
 
+func (user *User) GetSetting() map[string]interface{} {
+	if user.Setting == "" {
+		return nil
+	}
+	return common.StrToMap(user.Setting)
+}
+
+func (user *User) SetSetting(setting map[string]interface{}) {
+	settingBytes, err := json.Marshal(setting)
+	if err != nil {
+		common.SysError("failed to marshal setting: " + err.Error())
+		return
+	}
+	user.Setting = string(settingBytes)
+}
+
 // CheckUserExistOrDeleted check if user exist or deleted, if not exist, return false, nil, if deleted or exist, return true, nil
 func CheckUserExistOrDeleted(username string, email string) (bool, error) {
 	var user User
@@ -315,8 +346,8 @@ func (user *User) Update(updatePassword bool) error {
 		return err
 	}
 
-	// 更新缓存
-	return updateUserCache(user.Id, user.Username, user.Group, user.Quota, user.Status)
+	// Update cache
+	return updateUserCache(*user)
 }
 
 func (user *User) Edit(updatePassword bool) error {
@@ -344,8 +375,8 @@ func (user *User) Edit(updatePassword bool) error {
 		return err
 	}
 
-	// 更新缓存
-	return updateUserCache(user.Id, user.Username, user.Group, user.Quota, user.Status)
+	// Update cache
+	return updateUserCache(*user)
 }
 
 func (user *User) Delete() error {
@@ -371,8 +402,8 @@ func (user *User) HardDelete() error {
 // ValidateAndFill check password & user status
 func (user *User) ValidateAndFill() (err error) {
 	// When querying with struct, GORM will only query with non-zero fields,
-	// that means if your field’s value is 0, '', false or other zero values,
-	// it won’t be used to build query conditions
+	// that means if your field's value is 0, '', false or other zero values,
+	// it won't be used to build query conditions
 	password := user.Password
 	username := strings.TrimSpace(user.Username)
 	if username == "" || password == "" {
@@ -531,7 +562,6 @@ func GetUserQuota(id int, fromDB bool) (quota int, err error) {
 			return quota, nil
 		}
 		// Don't return error - fall through to DB
-		//common.SysError("failed to get user quota from cache: " + err.Error())
 	}
 	fromDB = true
 	err = DB.Model(&User{}).Where("id = ?", id).Select("quota").Find(&quota).Error
@@ -580,6 +610,35 @@ func GetUserGroup(id int, fromDB bool) (group string, err error) {
 	return group, nil
 }
 
+// GetUserSetting gets setting from Redis first, falls back to DB if needed
+func GetUserSetting(id int, fromDB bool) (settingMap map[string]interface{}, err error) {
+	var setting string
+	defer func() {
+		// Update Redis cache asynchronously on successful DB read
+		if shouldUpdateRedis(fromDB, err) {
+			gopool.Go(func() {
+				if err := updateUserSettingCache(id, setting); err != nil {
+					common.SysError("failed to update user setting cache: " + err.Error())
+				}
+			})
+		}
+	}()
+	if !fromDB && common.RedisEnabled {
+		setting, err := getUserSettingCache(id)
+		if err == nil {
+			return setting, nil
+		}
+		// Don't return error - fall through to DB
+	}
+	fromDB = true
+	err = DB.Model(&User{}).Where("id = ?", id).Select("setting").Find(&setting).Error
+	if err != nil {
+		return map[string]interface{}{}, err
+	}
+
+	return common.StrToMap(setting), nil
+}
+
 func IncreaseUserQuota(id int, quota int) (err error) {
 	if quota < 0 {
 		return errors.New("quota 不能为负数！")
@@ -641,9 +700,14 @@ func DeltaUpdateUserQuota(id int, delta int) (err error) {
 	}
 }
 
-func GetRootUserEmail() (email string) {
-	DB.Model(&User{}).Where("role = ?", common.RoleRootUser).Select("email").Find(&email)
-	return email
+//func GetRootUserEmail() (email string) {
+//	DB.Model(&User{}).Where("role = ?", common.RoleRootUser).Select("email").Find(&email)
+//	return email
+//}
+
+func GetRootUser() (user *User) {
+	DB.Where("role = ?", common.RoleRootUser).First(&user)
+	return user
 }
 
 func UpdateUserUsedQuotaAndRequestCount(id int, quota int) {
@@ -725,10 +789,10 @@ func IsLinuxDOIdAlreadyTaken(linuxDOId string) bool {
 	return !errors.Is(err, gorm.ErrRecordNotFound)
 }
 
-func (u *User) FillUserByLinuxDOId() error {
-	if u.LinuxDOId == "" {
+func (user *User) FillUserByLinuxDOId() error {
+	if user.LinuxDOId == "" {
 		return errors.New("linux do id is empty")
 	}
-	err := DB.Where("linux_do_id = ?", u.LinuxDOId).First(u).Error
+	err := DB.Where("linux_do_id = ?", user.LinuxDOId).First(user).Error
 	return err
 }

model/user_cache.go

@@ -1,206 +1,213 @@
 package model
 
 import (
+	"encoding/json"
 	"fmt"
 	"one-api/common"
 	"one-api/constant"
-	"strconv"
 	"time"
+
+	"github.com/bytedance/gopkg/util/gopool"
 )
 
-// Change UserCache struct to userCache
-type userCache struct {
+// UserBase struct remains the same as it represents the cached data structure
+type UserBase struct {
 	Id       int    `json:"id"`
 	Group    string `json:"group"`
+	Email    string `json:"email"`
 	Quota    int    `json:"quota"`
 	Status   int    `json:"status"`
-	Role     int    `json:"role"`
 	Username string `json:"username"`
+	Setting  string `json:"setting"`
 }
 
-// Rename all exported functions to private ones
-// invalidateUserCache clears all user related cache
+func (user *UserBase) GetSetting() map[string]interface{} {
+	if user.Setting == "" {
+		return nil
+	}
+	return common.StrToMap(user.Setting)
+}
+
+func (user *UserBase) SetSetting(setting map[string]interface{}) {
+	settingBytes, err := json.Marshal(setting)
+	if err != nil {
+		common.SysError("failed to marshal setting: " + err.Error())
+		return
+	}
+	user.Setting = string(settingBytes)
+}
+
+// getUserCacheKey returns the key for user cache
+func getUserCacheKey(userId int) string {
+	return fmt.Sprintf("user:%d", userId)
+}
+
+// invalidateUserCache clears user cache
 func invalidateUserCache(userId int) error {
 	if !common.RedisEnabled {
 		return nil
 	}
+	return common.RedisHDelObj(getUserCacheKey(userId))
+}
 
-	keys := []string{
-		fmt.Sprintf(constant.UserGroupKeyFmt, userId),
-		fmt.Sprintf(constant.UserQuotaKeyFmt, userId),
-		fmt.Sprintf(constant.UserEnabledKeyFmt, userId),
-		fmt.Sprintf(constant.UserUsernameKeyFmt, userId),
+// updateUserCache updates all user cache fields using hash
+func updateUserCache(user User) error {
+	if !common.RedisEnabled {
+		return nil
 	}
 
-	for _, key := range keys {
-		if err := common.RedisDel(key); err != nil {
-			return fmt.Errorf("failed to delete cache key %s: %w", key, err)
+	return common.RedisHSetObj(
+		getUserCacheKey(user.Id),
+		user.ToBaseUser(),
+		time.Duration(constant.UserId2QuotaCacheSeconds)*time.Second,
+	)
+}
+
+// GetUserCache gets complete user cache from hash
+func GetUserCache(userId int) (userCache *UserBase, err error) {
+	var user *User
+	var fromDB bool
+	defer func() {
+		// Update Redis cache asynchronously on successful DB read
+		if shouldUpdateRedis(fromDB, err) && user != nil {
+			gopool.Go(func() {
+				if err := updateUserCache(*user); err != nil {
+					common.SysError("failed to update user status cache: " + err.Error())
+				}
+			})
 		}
-	}
-	return nil
-}
+	}()
 
-// updateUserGroupCache updates user group cache
-func updateUserGroupCache(userId int, group string) error {
-	if !common.RedisEnabled {
-		return nil
-	}
-	return common.RedisSet(
-		fmt.Sprintf(constant.UserGroupKeyFmt, userId),
-		group,
-		time.Duration(constant.UserId2QuotaCacheSeconds)*time.Second,
-	)
-}
-
-// updateUserQuotaCache updates user quota cache
-func updateUserQuotaCache(userId int, quota int) error {
-	if !common.RedisEnabled {
-		return nil
-	}
-	return common.RedisSet(
-		fmt.Sprintf(constant.UserQuotaKeyFmt, userId),
-		fmt.Sprintf("%d", quota),
-		time.Duration(constant.UserId2QuotaCacheSeconds)*time.Second,
-	)
-}
-
-// updateUserStatusCache updates user status cache
-func updateUserStatusCache(userId int, userEnabled bool) error {
-	if !common.RedisEnabled {
-		return nil
-	}
-	enabled := "0"
-	if userEnabled {
-		enabled = "1"
-	}
-	return common.RedisSet(
-		fmt.Sprintf(constant.UserEnabledKeyFmt, userId),
-		enabled,
-		time.Duration(constant.UserId2StatusCacheSeconds)*time.Second,
-	)
-}
-
-// updateUserNameCache updates username cache
-func updateUserNameCache(userId int, username string) error {
-	if !common.RedisEnabled {
-		return nil
-	}
-	return common.RedisSet(
-		fmt.Sprintf(constant.UserUsernameKeyFmt, userId),
-		username,
-		time.Duration(constant.UserId2QuotaCacheSeconds)*time.Second,
-	)
-}
-
-// updateUserCache updates all user cache fields
-func updateUserCache(userId int, username string, userGroup string, quota int, status int) error {
-	if !common.RedisEnabled {
-		return nil
+	// Try getting from Redis first
+	userCache, err = cacheGetUserBase(userId)
+	if err == nil {
+		return userCache, nil
 	}
 
-	if err := updateUserGroupCache(userId, userGroup); err != nil {
-		return fmt.Errorf("update group cache: %w", err)
-	}
-
-	if err := updateUserQuotaCache(userId, quota); err != nil {
-		return fmt.Errorf("update quota cache: %w", err)
-	}
-
-	if err := updateUserStatusCache(userId, status == common.UserStatusEnabled); err != nil {
-		return fmt.Errorf("update status cache: %w", err)
-	}
-
-	if err := updateUserNameCache(userId, username); err != nil {
-		return fmt.Errorf("update username cache: %w", err)
-	}
-
-	return nil
-}
-
-// getUserGroupCache gets user group from cache
-func getUserGroupCache(userId int) (string, error) {
-	if !common.RedisEnabled {
-		return "", nil
-	}
-	return common.RedisGet(fmt.Sprintf(constant.UserGroupKeyFmt, userId))
-}
-
-// getUserQuotaCache gets user quota from cache
-func getUserQuotaCache(userId int) (int, error) {
-	if !common.RedisEnabled {
-		return 0, nil
-	}
-	quotaStr, err := common.RedisGet(fmt.Sprintf(constant.UserQuotaKeyFmt, userId))
+	// If Redis fails, get from DB
+	fromDB = true
+	user, err = GetUserById(userId, false)
 	if err != nil {
-		return 0, err
+		return nil, err // Return nil and error if DB lookup fails
 	}
-	return strconv.Atoi(quotaStr)
+
+	// Create cache object from user data
+	userCache = &UserBase{
+		Id:       user.Id,
+		Group:    user.Group,
+		Quota:    user.Quota,
+		Status:   user.Status,
+		Username: user.Username,
+		Setting:  user.Setting,
+		Email:    user.Email,
+	}
+
+	return userCache, nil
 }
 
-// getUserStatusCache gets user status from cache
-func getUserStatusCache(userId int) (int, error) {
+func cacheGetUserBase(userId int) (*UserBase, error) {
 	if !common.RedisEnabled {
-		return 0, nil
+		return nil, fmt.Errorf("redis is not enabled")
 	}
-	statusStr, err := common.RedisGet(fmt.Sprintf(constant.UserEnabledKeyFmt, userId))
+	var userCache UserBase
+	// Try getting from Redis first
+	err := common.RedisHGetObj(getUserCacheKey(userId), &userCache)
 	if err != nil {
-		return 0, err
+		return nil, err
 	}
-	return strconv.Atoi(statusStr)
+	return &userCache, nil
 }
 
-// getUserNameCache gets username from cache
-func getUserNameCache(userId int) (string, error) {
-	if !common.RedisEnabled {
-		return "", nil
-	}
-	return common.RedisGet(fmt.Sprintf(constant.UserUsernameKeyFmt, userId))
-}
-
-// getUserCache gets complete user cache
-func getUserCache(userId int) (*userCache, error) {
-	if !common.RedisEnabled {
-		return nil, nil
-	}
-
-	group, err := getUserGroupCache(userId)
-	if err != nil {
-		return nil, fmt.Errorf("get group cache: %w", err)
-	}
-
-	quota, err := getUserQuotaCache(userId)
-	if err != nil {
-		return nil, fmt.Errorf("get quota cache: %w", err)
-	}
-
-	status, err := getUserStatusCache(userId)
-	if err != nil {
-		return nil, fmt.Errorf("get status cache: %w", err)
-	}
-
-	username, err := getUserNameCache(userId)
-	if err != nil {
-		return nil, fmt.Errorf("get username cache: %w", err)
-	}
-
-	return &userCache{
-		Id:       userId,
-		Group:    group,
-		Quota:    quota,
-		Status:   status,
-		Username: username,
-	}, nil
-}
-
-// Add atomic quota operations
+// Add atomic quota operations using hash fields
 func cacheIncrUserQuota(userId int, delta int64) error {
 	if !common.RedisEnabled {
 		return nil
 	}
-	key := fmt.Sprintf(constant.UserQuotaKeyFmt, userId)
-	return common.RedisIncr(key, delta)
+	return common.RedisHIncrBy(getUserCacheKey(userId), "Quota", delta)
 }
 
 func cacheDecrUserQuota(userId int, delta int64) error {
 	return cacheIncrUserQuota(userId, -delta)
 }
+
+// Helper functions to get individual fields if needed
+func getUserGroupCache(userId int) (string, error) {
+	cache, err := GetUserCache(userId)
+	if err != nil {
+		return "", err
+	}
+	return cache.Group, nil
+}
+
+func getUserQuotaCache(userId int) (int, error) {
+	cache, err := GetUserCache(userId)
+	if err != nil {
+		return 0, err
+	}
+	return cache.Quota, nil
+}
+
+func getUserStatusCache(userId int) (int, error) {
+	cache, err := GetUserCache(userId)
+	if err != nil {
+		return 0, err
+	}
+	return cache.Status, nil
+}
+
+func getUserNameCache(userId int) (string, error) {
+	cache, err := GetUserCache(userId)
+	if err != nil {
+		return "", err
+	}
+	return cache.Username, nil
+}
+
+func getUserSettingCache(userId int) (map[string]interface{}, error) {
+	setting := make(map[string]interface{})
+	cache, err := GetUserCache(userId)
+	if err != nil {
+		return setting, err
+	}
+	return cache.GetSetting(), nil
+}
+
+// New functions for individual field updates
+func updateUserStatusCache(userId int, status bool) error {
+	if !common.RedisEnabled {
+		return nil
+	}
+	statusInt := common.UserStatusEnabled
+	if !status {
+		statusInt = common.UserStatusDisabled
+	}
+	return common.RedisHSetField(getUserCacheKey(userId), "Status", fmt.Sprintf("%d", statusInt))
+}
+
+func updateUserQuotaCache(userId int, quota int) error {
+	if !common.RedisEnabled {
+		return nil
+	}
+	return common.RedisHSetField(getUserCacheKey(userId), "Quota", fmt.Sprintf("%d", quota))
+}
+
+func updateUserGroupCache(userId int, group string) error {
+	if !common.RedisEnabled {
+		return nil
+	}
+	return common.RedisHSetField(getUserCacheKey(userId), "Group", group)
+}
+
+func updateUserNameCache(userId int, username string) error {
+	if !common.RedisEnabled {
+		return nil
+	}
+	return common.RedisHSetField(getUserCacheKey(userId), "Username", username)
+}
+
+func updateUserSettingCache(userId int, setting string) error {
+	if !common.RedisEnabled {
+		return nil
+	}
+	return common.RedisHSetField(getUserCacheKey(userId), "Setting", setting)
+}

relay/channel/adapter.go

@@ -15,6 +15,7 @@ type Adaptor interface {
 	SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error
 	ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error)
 	ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error)
+	ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error)
 	ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error)
 	ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error)
 	DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error)

relay/channel/ali/adaptor.go

@@ -49,9 +49,6 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 		return nil, errors.New("request is nil")
 	}
 	switch info.RelayMode {
-	case constant.RelayModeEmbeddings:
-		baiduEmbeddingRequest := embeddingRequestOpenAI2Ali(*request)
-		return baiduEmbeddingRequest, nil
 	default:
 		aliReq := requestOpenAI2Ali(*request)
 		return aliReq, nil
@@ -67,6 +64,10 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	return embeddingRequestOpenAI2Ali(request), nil
+}
+
 func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
 	//TODO implement me
 	return nil, errors.New("not implemented")

relay/channel/ali/text.go

@@ -25,9 +25,12 @@ func requestOpenAI2Ali(request dto.GeneralOpenAIRequest) *dto.GeneralOpenAIReque
 	return &request
 }
 
-func embeddingRequestOpenAI2Ali(request dto.GeneralOpenAIRequest) *AliEmbeddingRequest {
+func embeddingRequestOpenAI2Ali(request dto.EmbeddingRequest) *AliEmbeddingRequest {
+	if request.Model == "" {
+		request.Model = "text-embedding-v1"
+	}
 	return &AliEmbeddingRequest{
-		Model: "text-embedding-v1",
+		Model: request.Model,
 		Input: struct {
 			Texts []string `json:"texts"`
 		}{

relay/channel/api_request.go

@@ -39,7 +39,7 @@ func DoApiRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody
 	if err != nil {
 		return nil, fmt.Errorf("setup request header failed: %w", err)
 	}
-	resp, err := doRequest(c, req)
+	resp, err := doRequest(c, req, info)
 	if err != nil {
 		return nil, fmt.Errorf("do request failed: %w", err)
 	}
@@ -62,7 +62,7 @@ func DoFormRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBod
 	if err != nil {
 		return nil, fmt.Errorf("setup request header failed: %w", err)
 	}
-	resp, err := doRequest(c, req)
+	resp, err := doRequest(c, req, info)
 	if err != nil {
 		return nil, fmt.Errorf("do request failed: %w", err)
 	}
@@ -90,8 +90,18 @@ func DoWssRequest(a Adaptor, c *gin.Context, info *common.RelayInfo, requestBody
 	return targetConn, nil
 }
 
-func doRequest(c *gin.Context, req *http.Request) (*http.Response, error) {
-	resp, err := service.GetHttpClient().Do(req)
+func doRequest(c *gin.Context, req *http.Request, info *common.RelayInfo) (*http.Response, error) {
+	var client *http.Client
+	var err error
+	if proxyURL, ok := info.ChannelSetting["proxy"]; ok {
+		client, err = service.NewProxyHttpClient(proxyURL.(string))
+		if err != nil {
+			return nil, fmt.Errorf("new proxy http client failed: %w", err)
+		}
+	} else {
+		client = service.GetHttpClient()
+	}
+	resp, err := client.Do(req)
 	if err != nil {
 		return nil, err
 	}
@@ -120,7 +130,7 @@ func DoTaskApiRequest(a TaskAdaptor, c *gin.Context, info *common.TaskRelayInfo,
 	if err != nil {
 		return nil, fmt.Errorf("setup request header failed: %w", err)
 	}
-	resp, err := doRequest(c, req)
+	resp, err := doRequest(c, req, info.ToRelayInfo())
 	if err != nil {
 		return nil, fmt.Errorf("do request failed: %w", err)
 	}

relay/channel/aws/adaptor.go

@@ -59,6 +59,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return nil, nil
 }

relay/channel/baidu/adaptor.go

@@ -109,9 +109,6 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 		return nil, errors.New("request is nil")
 	}
 	switch info.RelayMode {
-	case constant.RelayModeEmbeddings:
-		baiduEmbeddingRequest := embeddingRequestOpenAI2Baidu(*request)
-		return baiduEmbeddingRequest, nil
 	default:
 		baiduRequest := requestOpenAI2Baidu(*request)
 		return baiduRequest, nil
@@ -122,6 +119,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	baiduEmbeddingRequest := embeddingRequestOpenAI2Baidu(request)
+	return baiduEmbeddingRequest, nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/baidu/relay-baidu.go

@@ -87,7 +87,7 @@ func streamResponseBaidu2OpenAI(baiduResponse *BaiduChatStreamResponse) *dto.Cha
 	return &response
 }
 
-func embeddingRequestOpenAI2Baidu(request dto.GeneralOpenAIRequest) *BaiduEmbeddingRequest {
+func embeddingRequestOpenAI2Baidu(request dto.EmbeddingRequest) *BaiduEmbeddingRequest {
 	return &BaiduEmbeddingRequest{
 		Input: request.ParseInput(),
 	}

relay/channel/baidu_v2/adaptor.go

@@ -0,0 +1,76 @@
+package baidu_v2
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	"one-api/relay/channel/openai"
+	relaycommon "one-api/relay/common"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return fmt.Sprintf("%s/v2/chat/completions", info.BaseUrl), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Set("Authorization", "Bearer "+info.ApiKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return request, nil
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		err, usage = openai.OaiStreamHandler(c, resp, info)
+	} else {
+		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/baidu_v2/constants.go

@@ -0,0 +1,29 @@
+package baidu_v2
+
+var ModelList = []string{
+	"ernie-4.0-8k-latest",
+	"ernie-4.0-8k-preview",
+	"ernie-4.0-8k",
+	"ernie-4.0-turbo-8k-latest",
+	"ernie-4.0-turbo-8k-preview",
+	"ernie-4.0-turbo-8k",
+	"ernie-4.0-turbo-128k",
+	"ernie-3.5-8k-preview",
+	"ernie-3.5-8k",
+	"ernie-3.5-128k",
+	"ernie-speed-8k",
+	"ernie-speed-128k",
+	"ernie-speed-pro-128k",
+	"ernie-lite-8k",
+	"ernie-lite-pro-128k",
+	"ernie-tiny-8k",
+	"ernie-char-8k",
+	"ernie-char-fiction-8k",
+	"ernie-novel-8k",
+	"deepseek-v3",
+	"deepseek-r1",
+	"deepseek-r1-distill-qwen-32b",
+	"deepseek-r1-distill-qwen-14b",
+}
+
+var ChannelName = "volcengine"

relay/channel/claude/adaptor.go

@@ -73,6 +73,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/cloudflare/adaptor.go

@@ -4,13 +4,14 @@ import (
 	"bytes"
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/dto"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
 	"one-api/relay/constant"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -56,6 +57,10 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return request, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	return request, nil
+}
+
 func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
 	// 添加文件字段
 	file, _, err := c.Request.FormFile("file")

relay/channel/cohere/adaptor.go

@@ -54,6 +54,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return requestConvertRerank2Cohere(request), nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.RelayMode == constant.RelayModeRerank {
 		err, usage = cohereRerankHandler(c, resp, info)

relay/channel/deepseek/adaptor.go

@@ -10,6 +10,7 @@ import (
 	"one-api/relay/channel"
 	"one-api/relay/channel/openai"
 	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
 )
 
 type Adaptor struct {
@@ -29,7 +30,12 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	return fmt.Sprintf("%s/chat/completions", info.BaseUrl), nil
+	switch info.RelayMode {
+	case constant.RelayModeCompletions:
+		return fmt.Sprintf("%s/beta/completions", info.BaseUrl), nil
+	default:
+		return fmt.Sprintf("%s/v1/chat/completions", info.BaseUrl), nil
+	}
 }
 
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
@@ -49,6 +55,11 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/dify/adaptor.go

@@ -48,6 +48,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/gemini/adaptor.go

@@ -1,15 +1,21 @@
 package gemini
 
 import (
+	"encoding/json"
 	"errors"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
+	"one-api/common"
 	"one-api/constant"
 	"one-api/dto"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
+	"one-api/service"
+
+	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 type Adaptor struct {
@@ -21,8 +27,36 @@ func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInf
 }
 
 func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
-	//TODO implement me
-	return nil, errors.New("not implemented")
+	if !strings.HasPrefix(info.UpstreamModelName, "imagen") {
+		return nil, errors.New("not supported model for image generation")
+	}
+
+	// convert size to aspect ratio
+	aspectRatio := "1:1" // default aspect ratio
+	switch request.Size {
+	case "1024x1024":
+		aspectRatio = "1:1"
+	case "1024x1792":
+		aspectRatio = "9:16"
+	case "1792x1024":
+		aspectRatio = "16:9"
+	}
+
+	// build gemini imagen request
+	geminiRequest := GeminiImageRequest{
+		Instances: []GeminiImageInstance{
+			{
+				Prompt: request.Prompt,
+			},
+		},
+		Parameters: GeminiImageParameters{
+			SampleCount:      request.N,
+			AspectRatio:      aspectRatio,
+			PersonGeneration: "allow_adult", // default allow adult
+		},
+	}
+
+	return geminiRequest, nil
 }
 
 func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
@@ -40,6 +74,10 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 		}
 	}
 
+	if strings.HasPrefix(info.UpstreamModelName, "imagen") {
+		return fmt.Sprintf("%s/%s/models/%s:predict", info.BaseUrl, version, info.UpstreamModelName), nil
+	}
+
 	action := "generateContent"
 	if info.IsStream {
 		action = "streamGenerateContent?alt=sse"
@@ -68,11 +106,20 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
+	if strings.HasPrefix(info.UpstreamModelName, "imagen") {
+		return GeminiImageHandler(c, resp, info)
+	}
+
 	if info.IsStream {
 		err, usage = GeminiChatStreamHandler(c, resp, info)
 	} else {
@@ -81,6 +128,60 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
 	return
 }
 
+func GeminiImageHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
+	responseBody, readErr := io.ReadAll(resp.Body)
+	if readErr != nil {
+		return nil, service.OpenAIErrorWrapper(readErr, "read_response_body_failed", http.StatusInternalServerError)
+	}
+	_ = resp.Body.Close()
+
+	var geminiResponse GeminiImageResponse
+	if jsonErr := json.Unmarshal(responseBody, &geminiResponse); jsonErr != nil {
+		return nil, service.OpenAIErrorWrapper(jsonErr, "unmarshal_response_body_failed", http.StatusInternalServerError)
+	}
+
+	if len(geminiResponse.Predictions) == 0 {
+		return nil, service.OpenAIErrorWrapper(errors.New("no images generated"), "no_images", http.StatusBadRequest)
+	}
+
+	// convert to openai format response
+	openAIResponse := dto.ImageResponse{
+		Created: common.GetTimestamp(),
+		Data:    make([]dto.ImageData, 0, len(geminiResponse.Predictions)),
+	}
+
+	for _, prediction := range geminiResponse.Predictions {
+		if prediction.RaiFilteredReason != "" {
+			continue // skip filtered image
+		}
+		openAIResponse.Data = append(openAIResponse.Data, dto.ImageData{
+			B64Json: prediction.BytesBase64Encoded,
+		})
+	}
+
+	jsonResponse, jsonErr := json.Marshal(openAIResponse)
+	if jsonErr != nil {
+		return nil, service.OpenAIErrorWrapper(jsonErr, "marshal_response_failed", http.StatusInternalServerError)
+	}
+
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, _ = c.Writer.Write(jsonResponse)
+
+	// https://github.com/google-gemini/cookbook/blob/719a27d752aac33f39de18a8d3cb42a70874917e/quickstarts/Counting_Tokens.ipynb
+	// each image has fixed 258 tokens
+	const imageTokens = 258
+	generatedImages := len(openAIResponse.Data)
+
+	usage = &dto.Usage{
+		PromptTokens:     imageTokens * generatedImages, // each generated image has fixed 258 tokens
+		CompletionTokens: 0,                             // image generation does not calculate completion tokens
+		TotalTokens:      imageTokens * generatedImages,
+	}
+
+	return usage, nil
+}
+
 func (a *Adaptor) GetModelList() []string {
 	return ModelList
 }

relay/channel/gemini/constant.go

@@ -3,17 +3,21 @@ package gemini
 var ModelList = []string{
 	// stable version
 	"gemini-1.5-pro", "gemini-1.5-flash", "gemini-1.5-flash-8b",
+	"gemini-2.0-flash",
 	// latest version
 	"gemini-1.5-pro-latest", "gemini-1.5-flash-latest",
-	// legacy version
-	"gemini-1.5-pro-exp-0827", "gemini-1.5-flash-exp-0827",
-	// exp
-	"gemini-exp-1114", "gemini-exp-1121", "gemini-exp-1206",
+	// preview version
+	"gemini-2.0-flash-lite-preview",
+	// gemini exp
+	"gemini-exp-1206",
 	// flash exp
 	"gemini-2.0-flash-exp",
+	// pro exp
+	"gemini-2.0-pro-exp",
 	// thinking exp
 	"gemini-2.0-flash-thinking-exp",
-	"gemini-2.0-flash-thinking-exp-1219",
+	// imagen models
+	"imagen-3.0-generate-002",
 }
 
 var ChannelName = "google gemini"

relay/channel/gemini/dto.go

@@ -109,3 +109,30 @@ type GeminiUsageMetadata struct {
 	CandidatesTokenCount int `json:"candidatesTokenCount"`
 	TotalTokenCount      int `json:"totalTokenCount"`
 }
+
+// Imagen related structs
+type GeminiImageRequest struct {
+	Instances  []GeminiImageInstance `json:"instances"`
+	Parameters GeminiImageParameters `json:"parameters"`
+}
+
+type GeminiImageInstance struct {
+	Prompt string `json:"prompt"`
+}
+
+type GeminiImageParameters struct {
+	SampleCount      int    `json:"sampleCount,omitempty"`
+	AspectRatio      string `json:"aspectRatio,omitempty"`
+	PersonGeneration string `json:"personGeneration,omitempty"`
+}
+
+type GeminiImageResponse struct {
+	Predictions []GeminiImagePrediction `json:"predictions"`
+}
+
+type GeminiImagePrediction struct {
+	MimeType           string `json:"mimeType"`
+	BytesBase64Encoded string `json:"bytesBase64Encoded"`
+	RaiFilteredReason  string `json:"raiFilteredReason,omitempty"`
+	SafetyAttributes   any    `json:"safetyAttributes,omitempty"`
+}

relay/channel/jina/adaptor.go

@@ -55,6 +55,10 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return request, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	return request, nil
+}
+
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	if info.RelayMode == constant.RelayModeRerank {
 		err, usage = jinaRerankHandler(c, resp)

relay/channel/mistral/adaptor.go

@@ -50,6 +50,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/mokaai/adaptor.go

@@ -0,0 +1,93 @@
+package mokaai
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
+	"strings"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return request, nil
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/clntwmv7t
+	suffix := "chat/"
+	if strings.HasPrefix(info.UpstreamModelName, "m3e") {
+		suffix = "embeddings"
+	}
+	fullRequestURL := fmt.Sprintf("%s/%s", info.BaseUrl, suffix)
+	return fullRequestURL, nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	switch info.RelayMode {
+	case constant.RelayModeEmbeddings:
+		baiduEmbeddingRequest := embeddingRequestOpenAI2Moka(*request)
+		return baiduEmbeddingRequest, nil
+	default:
+		return nil, errors.New("not implemented")
+	}
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
+		
+	switch info.RelayMode {
+	case constant.RelayModeEmbeddings:
+		err, usage = mokaEmbeddingHandler(c, resp)
+	default:
+		// err, usage = mokaHandler(c, resp)
+		
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/mokaai/constants.go

@@ -0,0 +1,9 @@
+package mokaai
+
+var ModelList = []string{
+	"m3e-large",
+	"m3e-base",
+	"m3e-small",
+}
+
+var ChannelName = "mokaai"

relay/channel/mokaai/relay-mokaai.go

@@ -0,0 +1,83 @@
+package mokaai
+
+import (
+	"encoding/json"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/service"
+)
+
+func embeddingRequestOpenAI2Moka(request dto.GeneralOpenAIRequest) *dto.EmbeddingRequest {
+	var input []string // Change input to []string
+
+	switch v := request.Input.(type) {
+	case string:
+		input = []string{v} // Convert string to []string
+	case []string:
+		input = v // Already a []string, no conversion needed
+	case []interface{}:
+		for _, part := range v {
+			if str, ok := part.(string); ok {
+				input = append(input, str) // Append each string to the slice
+			}
+		}
+	}
+	return &dto.EmbeddingRequest{
+		Input: input,
+		Model:  request.Model,
+	}
+}
+
+func embeddingResponseMoka2OpenAI(response *dto.EmbeddingResponse) *dto.OpenAIEmbeddingResponse {
+	openAIEmbeddingResponse := dto.OpenAIEmbeddingResponse{
+		Object: "list",
+		Data:   make([]dto.OpenAIEmbeddingResponseItem, 0, len(response.Data)),
+		Model:  "baidu-embedding",
+		Usage:  response.Usage,
+	}
+	for _, item := range response.Data {
+		openAIEmbeddingResponse.Data = append(openAIEmbeddingResponse.Data, dto.OpenAIEmbeddingResponseItem{
+			Object:    item.Object,
+			Index:     item.Index,
+			Embedding: item.Embedding,
+		})
+	}
+	return &openAIEmbeddingResponse
+}
+
+func mokaEmbeddingHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var baiduResponse dto.EmbeddingResponse
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = resp.Body.Close()
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+	}
+	err = json.Unmarshal(responseBody, &baiduResponse)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	// if baiduResponse.ErrorMsg != "" {
+	// 	return &dto.OpenAIErrorWithStatusCode{
+	// 		Error: dto.OpenAIError{
+	// 			Type:    "baidu_error",
+	// 			Param:   "",
+	// 		},
+	// 		StatusCode: resp.StatusCode,
+	// 	}, nil
+	// }
+	fullTextResponse := embeddingResponseMoka2OpenAI(&baiduResponse)
+	jsonResponse, err := json.Marshal(fullTextResponse)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "marshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+	_, err = c.Writer.Write(jsonResponse)
+	return nil, &fullTextResponse.Usage
+}
+

relay/channel/ollama/adaptor.go

@@ -39,6 +39,7 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
+	req.Set("Authorization", "Bearer "+info.ApiKey)
 	return nil
 }
 
@@ -46,18 +47,17 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
-	switch info.RelayMode {
-	case relayconstant.RelayModeEmbeddings:
-		return requestOpenAI2Embeddings(*request), nil
-	default:
-		return requestOpenAI2Ollama(*request), nil
-	}
+	return requestOpenAI2Ollama(*request)
 }
 
 func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	return requestOpenAI2Embeddings(request), nil
+}
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/ollama/dto.go

@@ -3,18 +3,21 @@ 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"`
-	Tools            []dto.ToolCall `json:"tools,omitempty"`
-	ResponseFormat   any            `json:"response_format,omitempty"`
-	FrequencyPenalty float64        `json:"frequency_penalty,omitempty"`
-	PresencePenalty  float64        `json:"presence_penalty,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   any                `json:"response_format,omitempty"`
+	FrequencyPenalty float64            `json:"frequency_penalty,omitempty"`
+	PresencePenalty  float64            `json:"presence_penalty,omitempty"`
+	Suffix           any                `json:"suffix,omitempty"`
+	StreamOptions    *dto.StreamOptions `json:"stream_options,omitempty"`
+	Prompt           any                `json:"prompt,omitempty"`
 }
 
 type Options struct {
@@ -35,7 +38,7 @@ type OllamaEmbeddingRequest struct {
 }
 
 type OllamaEmbeddingResponse struct {
-	Error     string    `json:"error,omitempty"`
-	Model     string    `json:"model"`
+	Error     string      `json:"error,omitempty"`
+	Model     string      `json:"model"`
 	Embedding [][]float64 `json:"embeddings,omitempty"`
 }

relay/channel/ollama/relay-ollama.go

@@ -9,14 +9,36 @@ import (
 	"net/http"
 	"one-api/dto"
 	"one-api/service"
+	"strings"
 )
 
-func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) *OllamaRequest {
+func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) (*OllamaRequest, error) {
 	messages := make([]dto.Message, 0, len(request.Messages))
 	for _, message := range request.Messages {
+		if !message.IsStringContent() {
+			mediaMessages := message.ParseContent()
+			for j, mediaMessage := range mediaMessages {
+				if mediaMessage.Type == dto.ContentTypeImageURL {
+					imageUrl := mediaMessage.ImageUrl.(dto.MessageImageUrl)
+					// check if not base64
+					if strings.HasPrefix(imageUrl.Url, "http") {
+						fileData, err := service.GetFileBase64FromUrl(imageUrl.Url)
+						if err != nil {
+							return nil, err
+						}
+						imageUrl.Url = fmt.Sprintf("data:%s;base64,%s", fileData.MimeType, fileData.Base64Data)
+					}
+					mediaMessage.ImageUrl = imageUrl
+					mediaMessages[j] = mediaMessage
+				}
+			}
+			message.SetMediaContent(mediaMessages)
+		}
 		messages = append(messages, dto.Message{
-			Role:    message.Role,
-			Content: message.Content,
+			Role:       message.Role,
+			Content:    message.Content,
+			ToolCalls:  message.ToolCalls,
+			ToolCallId: message.ToolCallId,
 		})
 	}
 	str, ok := request.Stop.(string)
@@ -39,10 +61,13 @@ func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) *OllamaRequest {
 		ResponseFormat:   request.ResponseFormat,
 		FrequencyPenalty: request.FrequencyPenalty,
 		PresencePenalty:  request.PresencePenalty,
-	}
+		Prompt:           request.Prompt,
+		StreamOptions:    request.StreamOptions,
+		Suffix:           request.Suffix,
+	}, nil
 }
 
-func requestOpenAI2Embeddings(request dto.GeneralOpenAIRequest) *OllamaEmbeddingRequest {
+func requestOpenAI2Embeddings(request dto.EmbeddingRequest) *OllamaEmbeddingRequest {
 	return &OllamaEmbeddingRequest{
 		Model: request.Model,
 		Input: request.ParseInput(),
@@ -123,9 +148,9 @@ func ollamaEmbeddingHandler(c *gin.Context, resp *http.Response, promptTokens in
 }
 
 func flattenEmbeddings(embeddings [][]float64) []float64 {
-flattened := []float64{}
-for _, row := range embeddings {
-	flattened = append(flattened, row...)
+	flattened := []float64{}
+	for _, row := range embeddings {
+		flattened = append(flattened, row...)
+	}
+	return flattened
 }
-return flattened
-}

relay/channel/openai/adaptor.go

@@ -10,6 +10,7 @@ import (
 	"mime/multipart"
 	"net/http"
 	"one-api/common"
+	constant2 "one-api/constant"
 	"one-api/dto"
 	"one-api/relay/channel"
 	"one-api/relay/channel/ai360"
@@ -44,16 +45,20 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 	}
 	switch info.ChannelType {
 	case common.ChannelTypeAzure:
+		apiVersion := info.ApiVersion
+		if apiVersion == "" {
+			apiVersion = constant2.AzureDefaultAPIVersion
+		}
 		// https://learn.microsoft.com/en-us/azure/cognitive-services/openai/chatgpt-quickstart?pivots=rest-api&tabs=command-line#rest-api
 		requestURL := strings.Split(info.RequestURLPath, "?")[0]
-		requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, info.ApiVersion)
+		requestURL = fmt.Sprintf("%s?api-version=%s", requestURL, apiVersion)
 		task := strings.TrimPrefix(requestURL, "/v1/")
 		model_ := info.UpstreamModelName
 		model_ = strings.Replace(model_, ".", "", -1)
 		// https://github.com/songquanpeng/one-api/issues/67
 		requestURL = fmt.Sprintf("/openai/deployments/%s/%s", model_, task)
 		if info.RelayMode == constant.RelayModeRealtime {
-			requestURL = fmt.Sprintf("/openai/realtime?deployment=%s&api-version=%s", model_, info.ApiVersion)
+			requestURL = fmt.Sprintf("/openai/realtime?deployment=%s&api-version=%s", model_, apiVersion)
 		}
 		return relaycommon.GetFullRequestURL(info.BaseUrl, requestURL, info.ChannelType), nil
 	case common.ChannelTypeMiniMax:
@@ -109,13 +114,28 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 	if info.ChannelType != common.ChannelTypeOpenAI && info.ChannelType != common.ChannelTypeAzure {
 		request.StreamOptions = nil
 	}
-	if strings.HasPrefix(request.Model, "o1") {
+	if strings.HasPrefix(request.Model, "o1") || strings.HasPrefix(request.Model, "o3") {
 		if request.MaxCompletionTokens == 0 && request.MaxTokens != 0 {
 			request.MaxCompletionTokens = request.MaxTokens
 			request.MaxTokens = 0
 		}
+		if strings.HasPrefix(request.Model, "o3") || strings.HasPrefix(request.Model, "o1") {
+			request.Temperature = nil
+		}
+		if strings.HasSuffix(request.Model, "-high") {
+			request.ReasoningEffort = "high"
+			request.Model = strings.TrimSuffix(request.Model, "-high")
+		} else if strings.HasSuffix(request.Model, "-low") {
+			request.ReasoningEffort = "low"
+			request.Model = strings.TrimSuffix(request.Model, "-low")
+		} else if strings.HasSuffix(request.Model, "-medium") {
+			request.ReasoningEffort = "medium"
+			request.Model = strings.TrimSuffix(request.Model, "-medium")
+		}
+		info.ReasoningEffort = request.ReasoningEffort
+		info.UpstreamModelName = request.Model
 	}
-	if request.Model == "o1" || request.Model == "o1-2024-12-17" {
+	if request.Model == "o1" || request.Model == "o1-2024-12-17" || strings.HasPrefix(request.Model, "o3") {
 		//修改第一个Message的内容，将system改为developer
 		if len(request.Messages) > 0 && request.Messages[0].Role == "system" {
 			request.Messages[0].Role = "developer"
@@ -129,6 +149,10 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, errors.New("not implemented")
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	return request, nil
+}
+
 func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
 	a.ResponseFormat = request.ResponseFormat
 	if info.RelayMode == constant.RelayModeAudioSpeech {

relay/channel/openai/constant.go

@@ -13,6 +13,10 @@ var ModelList = []string{
 	"gpt-4o-mini", "gpt-4o-mini-2024-07-18",
 	"o1-preview", "o1-preview-2024-09-12",
 	"o1-mini", "o1-mini-2024-09-12",
+	"o3-mini", "o3-mini-2025-01-31",
+	"o3-mini-high", "o3-mini-2025-01-31-high",
+	"o3-mini-low", "o3-mini-2025-01-31-low",
+	"o3-mini-medium", "o3-mini-2025-01-31-medium",
 	"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-2024-12-17",

relay/channel/openai/relay-openai.go

@@ -5,6 +5,9 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
+	"github.com/bytedance/gopkg/util/gopool"
+	"github.com/gin-gonic/gin"
+	"github.com/gorilla/websocket"
 	"github.com/pkg/errors"
 	"io"
 	"math"
@@ -20,10 +23,6 @@ import (
 	"strings"
 	"sync"
 	"time"
-
-	"github.com/bytedance/gopkg/util/gopool"
-	"github.com/gin-gonic/gin"
-	"github.com/gorilla/websocket"
 )
 
 func sendStreamData(c *gin.Context, data string, forceFormat bool) error {
@@ -91,11 +90,12 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 			if len(data) < 6 { // ignore blank line or wrong format
 				continue
 			}
-			if data[:6] != "data: " && data[:6] != "[DONE]" {
+			if data[:5] != "data:" && data[:6] != "[DONE]" {
 				continue
 			}
 			mu.Lock()
-			data = data[6:]
+			data = data[5:]
+			data = strings.TrimSpace(data)
 			if !strings.HasPrefix(data, "[DONE]") {
 				if lastStreamData != "" {
 					err := sendStreamData(c, lastStreamData, forceFormat)
@@ -162,6 +162,7 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 					//}
 					for _, choice := range streamResponse.Choices {
 						responseTextBuilder.WriteString(choice.Delta.GetContentString())
+						responseTextBuilder.WriteString(choice.Delta.GetReasoningContent())
 						if choice.Delta.ToolCalls != nil {
 							if len(choice.Delta.ToolCalls) > toolCount {
 								toolCount = len(choice.Delta.ToolCalls)
@@ -182,6 +183,7 @@ func OaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Rel
 				//}
 				for _, choice := range streamResponse.Choices {
 					responseTextBuilder.WriteString(choice.Delta.GetContentString())
+					responseTextBuilder.WriteString(choice.Delta.GetReasoningContent())
 					if choice.Delta.ToolCalls != nil {
 						if len(choice.Delta.ToolCalls) > toolCount {
 							toolCount = len(choice.Delta.ToolCalls)
@@ -273,7 +275,7 @@ func OpenaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model
 	if simpleResponse.Usage.TotalTokens == 0 || (simpleResponse.Usage.PromptTokens == 0 && simpleResponse.Usage.CompletionTokens == 0) {
 		completionTokens := 0
 		for _, choice := range simpleResponse.Choices {
-			ctkm, _ := service.CountTextToken(string(choice.Message.Content), model)
+			ctkm, _ := service.CountTextToken(choice.Message.StringContent()+choice.Message.ReasoningContent, model)
 			completionTokens += ctkm
 		}
 		simpleResponse.Usage = dto.Usage{

relay/channel/palm/adaptor.go

@@ -49,6 +49,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/perplexity/adaptor.go

@@ -52,6 +52,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/siliconflow/adaptor.go

@@ -36,6 +36,8 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 		return fmt.Sprintf("%s/v1/embeddings", info.BaseUrl), nil
 	} else if info.RelayMode == constant.RelayModeChatCompletions {
 		return fmt.Sprintf("%s/v1/chat/completions", info.BaseUrl), nil
+	} else if info.RelayMode == constant.RelayModeCompletions {
+		return fmt.Sprintf("%s/v1/completions", info.BaseUrl), nil
 	}
 	return "", errors.New("invalid relay mode")
 }
@@ -58,6 +60,10 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return request, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	return request, nil
+}
+
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
 	switch info.RelayMode {
 	case constant.RelayModeRerank:
@@ -68,6 +74,12 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
 		} else {
 			err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 		}
+	case constant.RelayModeCompletions:
+		if info.IsStream {
+			err, usage = openai.OaiStreamHandler(c, resp, info)
+		} else {
+			err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+		}
 	case constant.RelayModeEmbeddings:
 		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 	}

relay/channel/siliconflow/constant.go

@@ -40,7 +40,7 @@ var ModelList = []string{
 	"Pro/meta-llama/Meta-Llama-3-8B-Instruct",
 	"Pro/mistralai/Mistral-7B-Instruct-v0.2",
 	"black-forest-labs/FLUX.1-schnell",
-	"iic/SenseVoiceSmall",
+	"FunAudioLLM/SenseVoiceSmall",
 	"netease-youdao/bce-embedding-base_v1",
 	"BAAI/bge-m3",
 	"internlm/internlm2_5-20b-chat",

relay/channel/tencent/adaptor.go

@@ -73,6 +73,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/vertex/adaptor.go

@@ -151,6 +151,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/volcengine/adaptor.go

@@ -0,0 +1,92 @@
+package volcengine
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	"one-api/relay/channel/openai"
+	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
+	"strings"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	switch info.RelayMode {
+	case constant.RelayModeChatCompletions:
+		if strings.HasPrefix(info.UpstreamModelName, "bot") {
+			return fmt.Sprintf("%s/api/v3/bots/chat/completions", info.BaseUrl), nil
+		}
+		return fmt.Sprintf("%s/api/v3/chat/completions", info.BaseUrl), nil
+	case constant.RelayModeEmbeddings:
+		return fmt.Sprintf("%s/api/v3/embeddings", info.BaseUrl), nil
+	default:
+	}
+	return "", fmt.Errorf("unsupported relay mode: %d", info.RelayMode)
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Set("Authorization", "Bearer "+info.ApiKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return request, nil
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	return request, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *dto.OpenAIErrorWithStatusCode) {
+	switch info.RelayMode {
+	case constant.RelayModeChatCompletions:
+		if info.IsStream {
+			err, usage = openai.OaiStreamHandler(c, resp, info)
+		} else {
+			err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+		}
+	case constant.RelayModeEmbeddings:
+		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/volcengine/constants.go

@@ -0,0 +1,13 @@
+package volcengine
+
+var ModelList = []string{
+	"Doubao-pro-128k",
+	"Doubao-pro-32k",
+	"Doubao-pro-4k",
+	"Doubao-lite-128k",
+	"Doubao-lite-32k",
+	"Doubao-lite-4k",
+	"Doubao-embedding",
+}
+
+var ChannelName = "volcengine"

relay/channel/xunfei/adaptor.go

@@ -50,6 +50,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	// xunfei's request is not http request, so we don't need to do anything here
 	dummyResp := &http.Response{}

relay/channel/zhipu/adaptor.go

@@ -56,6 +56,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/zhipu_4v/adaptor.go

@@ -53,6 +53,12 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 	return nil, nil
 }
 
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+
 func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/zhipu_4v/relay-zhipu_v4.go

@@ -90,8 +90,7 @@ func requestOpenAI2Zhipu(request dto.GeneralOpenAIRequest) *dto.GeneralOpenAIReq
 					mediaMessages[j] = mediaMessage
 				}
 			}
-			messageRaw, _ := json.Marshal(mediaMessages)
-			message.Content = messageRaw
+			message.SetMediaContent(mediaMessages)
 		}
 		messages = append(messages, dto.Message{
 			Role:       message.Role,

relay/common/relay_info.go

@@ -13,23 +13,24 @@ import (
 )
 
 type RelayInfo struct {
-	ChannelType          int
-	ChannelId            int
-	TokenId              int
-	TokenKey             string
-	UserId               int
-	Group                string
-	TokenUnlimited       bool
-	StartTime            time.Time
-	FirstResponseTime    time.Time
-	setFirstResponse     bool
-	ApiType              int
-	IsStream             bool
-	IsPlayground         bool
-	UsePrice             bool
-	RelayMode            int
-	UpstreamModelName    string
-	OriginModelName      string
+	ChannelType       int
+	ChannelId         int
+	TokenId           int
+	TokenKey          string
+	UserId            int
+	Group             string
+	TokenUnlimited    bool
+	StartTime         time.Time
+	FirstResponseTime time.Time
+	setFirstResponse  bool
+	ApiType           int
+	IsStream          bool
+	IsPlayground      bool
+	UsePrice          bool
+	RelayMode         int
+	UpstreamModelName string
+	OriginModelName   string
+	//RecodeModelName      string
 	RequestURLPath       string
 	ApiVersion           string
 	PromptTokens         int
@@ -38,6 +39,7 @@ type RelayInfo struct {
 	BaseUrl              string
 	SupportStreamOptions bool
 	ShouldIncludeUsage   bool
+	IsModelMapped        bool
 	ClientWs             *websocket.Conn
 	TargetWs             *websocket.Conn
 	InputAudioFormat     string
@@ -45,9 +47,22 @@ type RelayInfo struct {
 	RealtimeTools        []dto.RealTimeTool
 	IsFirstRequest       bool
 	AudioUsage           bool
+	ReasoningEffort      string
 	ChannelSetting       map[string]interface{}
 }
 
+// 定义支持流式选项的通道类型
+var streamSupportedChannels = map[int]bool{
+	common.ChannelTypeOpenAI:     true,
+	common.ChannelTypeAnthropic:  true,
+	common.ChannelTypeAws:        true,
+	common.ChannelTypeGemini:     true,
+	common.ChannelCloudflare:     true,
+	common.ChannelTypeAzure:      true,
+	common.ChannelTypeVolcEngine: true,
+	common.ChannelTypeOllama:     true,
+}
+
 func GenRelayInfoWs(c *gin.Context, ws *websocket.Conn) *RelayInfo {
 	info := GenRelayInfo(c)
 	info.ClientWs = ws
@@ -87,11 +102,13 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
 		FirstResponseTime: startTime.Add(-time.Second),
 		OriginModelName:   c.GetString("original_model"),
 		UpstreamModelName: c.GetString("original_model"),
-		ApiType:           apiType,
-		ApiVersion:        c.GetString("api_version"),
-		ApiKey:            strings.TrimPrefix(c.Request.Header.Get("Authorization"), "Bearer "),
-		Organization:      c.GetString("channel_organization"),
-		ChannelSetting:    channelSetting,
+		//RecodeModelName:   c.GetString("original_model"),
+		IsModelMapped:  false,
+		ApiType:        apiType,
+		ApiVersion:     c.GetString("api_version"),
+		ApiKey:         strings.TrimPrefix(c.Request.Header.Get("Authorization"), "Bearer "),
+		Organization:   c.GetString("channel_organization"),
+		ChannelSetting: channelSetting,
 	}
 	if strings.HasPrefix(c.Request.URL.Path, "/pg") {
 		info.IsPlayground = true
@@ -107,9 +124,7 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
 	if info.ChannelType == common.ChannelTypeVertexAi {
 		info.ApiVersion = c.GetString("region")
 	}
-	if info.ChannelType == common.ChannelTypeOpenAI || info.ChannelType == common.ChannelTypeAnthropic ||
-		info.ChannelType == common.ChannelTypeAws || info.ChannelType == common.ChannelTypeGemini ||
-		info.ChannelType == common.ChannelCloudflare || info.ChannelType == common.ChannelTypeAzure {
+	if streamSupportedChannels[info.ChannelType] {
 		info.SupportStreamOptions = true
 	}
 	return info

relay/constant/api_type.go

@@ -27,7 +27,9 @@ const (
 	APITypeVertexAi
 	APITypeMistral
 	APITypeDeepSeek
-
+	APITypeMokaAI
+	APITypeVolcEngine
+	APITypeBaiduV2
 	APITypeDummy // this one is only for count, do not add any channel after this
 )
 
@@ -78,6 +80,12 @@ func ChannelType2APIType(channelType int) (int, bool) {
 		apiType = APITypeMistral
 	case common.ChannelTypeDeepSeek:
 		apiType = APITypeDeepSeek
+	case common.ChannelTypeMokaAI:
+		apiType = APITypeMokaAI
+	case common.ChannelTypeVolcEngine:
+		apiType = APITypeVolcEngine
+	case common.ChannelTypeBaiduV2:
+		apiType = APITypeBaiduV2
 	}
 	if apiType == -1 {
 		return APITypeOpenAI, false

relay/helper/model_mapped.go

@@ -0,0 +1,25 @@
+package helper
+
+import (
+	"encoding/json"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"one-api/relay/common"
+)
+
+func ModelMappedHelper(c *gin.Context, info *common.RelayInfo) error {
+	// map model name
+	modelMapping := c.GetString("model_mapping")
+	if modelMapping != "" && modelMapping != "{}" {
+		modelMap := make(map[string]string)
+		err := json.Unmarshal([]byte(modelMapping), &modelMap)
+		if err != nil {
+			return fmt.Errorf("unmarshal_model_mapping_failed")
+		}
+		if modelMap[info.OriginModelName] != "" {
+			info.UpstreamModelName = modelMap[info.OriginModelName]
+			info.IsModelMapped = true
+		}
+	}
+	return nil
+}

relay/helper/price.go

@@ -0,0 +1,41 @@
+package helper
+
+import (
+	"github.com/gin-gonic/gin"
+	"one-api/common"
+	relaycommon "one-api/relay/common"
+	"one-api/setting"
+)
+
+type PriceData struct {
+	ModelPrice             float64
+	ModelRatio             float64
+	GroupRatio             float64
+	UsePrice               bool
+	ShouldPreConsumedQuota int
+}
+
+func ModelPriceHelper(c *gin.Context, info *relaycommon.RelayInfo, promptTokens int, maxTokens int) PriceData {
+	modelPrice, usePrice := common.GetModelPrice(info.OriginModelName, false)
+	groupRatio := setting.GetGroupRatio(info.Group)
+	var preConsumedQuota int
+	var modelRatio float64
+	if !usePrice {
+		preConsumedTokens := common.PreConsumedQuota
+		if maxTokens != 0 {
+			preConsumedTokens = promptTokens + maxTokens
+		}
+		modelRatio = common.GetModelRatio(info.OriginModelName)
+		ratio := modelRatio * groupRatio
+		preConsumedQuota = int(float64(preConsumedTokens) * ratio)
+	} else {
+		preConsumedQuota = int(modelPrice * common.QuotaPerUnit * groupRatio)
+	}
+	return PriceData{
+		ModelPrice:             modelPrice,
+		ModelRatio:             modelRatio,
+		GroupRatio:             groupRatio,
+		UsePrice:               usePrice,
+		ShouldPreConsumedQuota: preConsumedQuota,
+	}
+}

relay/relay-audio.go

@@ -1,7 +1,6 @@
 package relay
 
 import (
-	"encoding/json"
 	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
@@ -11,8 +10,10 @@ import (
 	"one-api/model"
 	relaycommon "one-api/relay/common"
 	relayconstant "one-api/relay/constant"
+	"one-api/relay/helper"
 	"one-api/service"
 	"one-api/setting"
+	"strings"
 )
 
 func getAndValidAudioRequest(c *gin.Context, info *relaycommon.RelayInfo) (*dto.AudioRequest, error) {
@@ -27,8 +28,9 @@ func getAndValidAudioRequest(c *gin.Context, info *relaycommon.RelayInfo) (*dto.
 			return nil, errors.New("model is required")
 		}
 		if setting.ShouldCheckPromptSensitive() {
-			err := service.CheckSensitiveInput(audioRequest.Input)
+			words, err := service.CheckSensitiveInput(audioRequest.Input)
 			if err != nil {
+				common.LogWarn(c, fmt.Sprintf("user sensitive words detected: %s", strings.Join(words, ",")))
 				return nil, err
 			}
 		}
@@ -73,15 +75,13 @@ func AudioHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 		relayInfo.PromptTokens = promptTokens
 	}
 
-	modelRatio := common.GetModelRatio(audioRequest.Model)
-	groupRatio := setting.GetGroupRatio(relayInfo.Group)
-	ratio := modelRatio * groupRatio
-	preConsumedQuota := int(float64(preConsumedTokens) * ratio)
+	priceData := helper.ModelPriceHelper(c, relayInfo, preConsumedTokens, 0)
+
 	userQuota, err := model.GetUserQuota(relayInfo.UserId, false)
 	if err != nil {
 		return service.OpenAIErrorWrapperLocal(err, "get_user_quota_failed", http.StatusInternalServerError)
 	}
-	preConsumedQuota, userQuota, openaiErr = preConsumeQuota(c, preConsumedQuota, relayInfo)
+	preConsumedQuota, userQuota, openaiErr := preConsumeQuota(c, priceData.ShouldPreConsumedQuota, relayInfo)
 	if openaiErr != nil {
 		return openaiErr
 	}
@@ -91,19 +91,12 @@ func AudioHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 		}
 	}()
 
-	// map model name
-	modelMapping := c.GetString("model_mapping")
-	if modelMapping != "" {
-		modelMap := make(map[string]string)
-		err := json.Unmarshal([]byte(modelMapping), &modelMap)
-		if err != nil {
-			return service.OpenAIErrorWrapper(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
-		}
-		if modelMap[audioRequest.Model] != "" {
-			audioRequest.Model = modelMap[audioRequest.Model]
-		}
+	err = helper.ModelMappedHelper(c, relayInfo)
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "model_mapped_error", http.StatusInternalServerError)
 	}
-	relayInfo.UpstreamModelName = audioRequest.Model
+
+	audioRequest.Model = relayInfo.UpstreamModelName
 
 	adaptor := GetAdaptor(relayInfo.ApiType)
 	if adaptor == nil {
@@ -140,7 +133,7 @@ func AudioHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 		return openaiErr
 	}
 
-	postConsumeQuota(c, relayInfo, audioRequest.Model, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, 0, false, "")
+	postConsumeQuota(c, relayInfo, usage.(*dto.Usage), preConsumedQuota, userQuota, priceData, "")
 
 	return nil
 }

relay/relay-image.go

@@ -12,6 +12,7 @@ import (
 	"one-api/dto"
 	"one-api/model"
 	relaycommon "one-api/relay/common"
+	"one-api/relay/helper"
 	"one-api/service"
 	"one-api/setting"
 	"strings"
@@ -60,15 +61,16 @@ func getAndValidImageRequest(c *gin.Context, info *relaycommon.RelayInfo) (*dto.
 	//	return service.OpenAIErrorWrapper(errors.New("n must be between 1 and 10"), "invalid_field_value", http.StatusBadRequest)
 	//}
 	if setting.ShouldCheckPromptSensitive() {
-		err := service.CheckSensitiveInput(imageRequest.Prompt)
+		words, err := service.CheckSensitiveInput(imageRequest.Prompt)
 		if err != nil {
+			common.LogWarn(c, fmt.Sprintf("user sensitive words detected: %s", strings.Join(words, ",")))
 			return nil, err
 		}
 	}
 	return imageRequest, nil
 }
 
-func ImageHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
+func ImageHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 	relayInfo := relaycommon.GenRelayInfo(c)
 
 	imageRequest, err := getAndValidImageRequest(c, relayInfo)
@@ -77,29 +79,20 @@ func ImageHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
 		return service.OpenAIErrorWrapper(err, "invalid_image_request", http.StatusBadRequest)
 	}
 
-	// map model name
-	modelMapping := c.GetString("model_mapping")
-	if modelMapping != "" {
-		modelMap := make(map[string]string)
-		err := json.Unmarshal([]byte(modelMapping), &modelMap)
-		if err != nil {
-			return service.OpenAIErrorWrapper(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
-		}
-		if modelMap[imageRequest.Model] != "" {
-			imageRequest.Model = modelMap[imageRequest.Model]
-		}
+	err = helper.ModelMappedHelper(c, relayInfo)
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "model_mapped_error", http.StatusInternalServerError)
 	}
-	relayInfo.UpstreamModelName = imageRequest.Model
 
-	modelPrice, success := common.GetModelPrice(imageRequest.Model, true)
-	if !success {
-		modelRatio := common.GetModelRatio(imageRequest.Model)
+	imageRequest.Model = relayInfo.UpstreamModelName
+
+	priceData := helper.ModelPriceHelper(c, relayInfo, 0, 0)
+	if !priceData.UsePrice {
 		// modelRatio 16 = modelPrice $0.04
 		// per 1 modelRatio = $0.04 / 16
-		modelPrice = 0.0025 * modelRatio
+		priceData.ModelPrice = 0.0025 * priceData.ModelRatio
 	}
 
-	groupRatio := setting.GetGroupRatio(relayInfo.Group)
 	userQuota, err := model.GetUserQuota(relayInfo.UserId, false)
 
 	sizeRatio := 1.0
@@ -122,11 +115,11 @@ func ImageHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
 		}
 	}
 
-	imageRatio := modelPrice * sizeRatio * qualityRatio * float64(imageRequest.N)
-	quota := int(imageRatio * groupRatio * common.QuotaPerUnit)
+	imageRatio := priceData.ModelPrice * sizeRatio * qualityRatio * float64(imageRequest.N)
+	quota := int(imageRatio * priceData.GroupRatio * common.QuotaPerUnit)
 
 	if userQuota-quota < 0 {
-		return service.OpenAIErrorWrapperLocal(errors.New(fmt.Sprintf("image pre-consumed quota failed, user quota: %d, need quota: %d", userQuota, quota)), "insufficient_user_quota", http.StatusBadRequest)
+		return service.OpenAIErrorWrapperLocal(fmt.Errorf("image pre-consumed quota failed, user quota: %s, need quota: %s", common.FormatQuota(userQuota), common.FormatQuota(quota)), "insufficient_user_quota", http.StatusForbidden)
 	}
 
 	adaptor := GetAdaptor(relayInfo.ApiType)
@@ -184,7 +177,6 @@ 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, imageRatio, true, logContent)
-
+	postConsumeQuota(c, relayInfo, usage, 0, userQuota, priceData, logContent)
 	return nil
 }

relay/relay-mj.go

@@ -194,7 +194,7 @@ func RelaySwapFace(c *gin.Context) *dto.MidjourneyResponse {
 	}
 	defer func(ctx context.Context) {
 		if mjResp.StatusCode == 200 && mjResp.Response.Code == 1 {
-			err := model.PostConsumeQuota(relayInfo, userQuota, quota, 0, true)
+			err := service.PostConsumeQuota(relayInfo, quota, 0, true)
 			if err != nil {
 				common.SysError("error consuming token remain quota: " + err.Error())
 			}
@@ -500,7 +500,7 @@ func RelayMidjourneySubmit(c *gin.Context, relayMode int) *dto.MidjourneyRespons
 
 	defer func(ctx context.Context) {
 		if consumeQuota && midjResponseWithStatus.StatusCode == 200 {
-			err := model.PostConsumeQuota(relayInfo, userQuota, quota, 0, true)
+			err := service.PostConsumeQuota(relayInfo, quota, 0, true)
 			if err != nil {
 				common.SysError("error consuming token remain quota: " + err.Error())
 			}

relay/relay-text.go

@@ -5,6 +5,7 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"github.com/bytedance/gopkg/util/gopool"
 	"io"
 	"math"
 	"net/http"
@@ -14,6 +15,7 @@ import (
 	"one-api/model"
 	relaycommon "one-api/relay/common"
 	relayconstant "one-api/relay/constant"
+	"one-api/relay/helper"
 	"one-api/service"
 	"one-api/setting"
 	"strings"
@@ -75,39 +77,21 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 		return service.OpenAIErrorWrapperLocal(err, "invalid_text_request", http.StatusBadRequest)
 	}
 
-	// map model name
-	//isModelMapped := false
-	modelMapping := c.GetString("model_mapping")
-	//isModelMapped := false
-	if modelMapping != "" && modelMapping != "{}" {
-		modelMap := make(map[string]string)
-		err := json.Unmarshal([]byte(modelMapping), &modelMap)
-		if err != nil {
-			return service.OpenAIErrorWrapperLocal(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
-		}
-		if modelMap[textRequest.Model] != "" {
-			//isModelMapped = true
-			textRequest.Model = modelMap[textRequest.Model]
-			// set upstream model name
-			//isModelMapped = true
-		}
-	}
-	relayInfo.UpstreamModelName = textRequest.Model
-	modelPrice, getModelPriceSuccess := common.GetModelPrice(textRequest.Model, false)
-	groupRatio := setting.GetGroupRatio(relayInfo.Group)
-
-	var preConsumedQuota int
-	var ratio float64
-	var modelRatio float64
-	//err := service.SensitiveWordsCheck(textRequest)
-
 	if setting.ShouldCheckPromptSensitive() {
-		err = checkRequestSensitive(textRequest, relayInfo)
+		words, err := checkRequestSensitive(textRequest, relayInfo)
 		if err != nil {
+			common.LogWarn(c, fmt.Sprintf("user sensitive words detected: %s", strings.Join(words, ", ")))
 			return service.OpenAIErrorWrapperLocal(err, "sensitive_words_detected", http.StatusBadRequest)
 		}
 	}
 
+	err = helper.ModelMappedHelper(c, relayInfo)
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "model_mapped_error", http.StatusInternalServerError)
+	}
+
+	textRequest.Model = relayInfo.UpstreamModelName
+
 	// 获取 promptTokens，如果上下文中已经存在，则直接使用
 	var promptTokens int
 	if value, exists := c.Get("prompt_tokens"); exists {
@@ -122,20 +106,10 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 		c.Set("prompt_tokens", promptTokens)
 	}
 
-	if !getModelPriceSuccess {
-		preConsumedTokens := common.PreConsumedQuota
-		if textRequest.MaxTokens != 0 {
-			preConsumedTokens = promptTokens + int(textRequest.MaxTokens)
-		}
-		modelRatio = common.GetModelRatio(textRequest.Model)
-		ratio = modelRatio * groupRatio
-		preConsumedQuota = int(float64(preConsumedTokens) * ratio)
-	} else {
-		preConsumedQuota = int(modelPrice * common.QuotaPerUnit * groupRatio)
-	}
+	priceData := helper.ModelPriceHelper(c, relayInfo, promptTokens, int(textRequest.MaxTokens))
 
 	// pre-consume quota 预消耗配额
-	preConsumedQuota, userQuota, openaiErr := preConsumeQuota(c, preConsumedQuota, relayInfo)
+	preConsumedQuota, userQuota, openaiErr := preConsumeQuota(c, priceData.ShouldPreConsumedQuota, relayInfo)
 	if openaiErr != nil {
 		return openaiErr
 	}
@@ -218,10 +192,10 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 		return openaiErr
 	}
 
-	if strings.HasPrefix(relayInfo.UpstreamModelName, "gpt-4o-audio") {
-		service.PostAudioConsumeQuota(c, relayInfo, usage.(*dto.Usage), preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
+	if strings.HasPrefix(relayInfo.OriginModelName, "gpt-4o-audio") {
+		service.PostAudioConsumeQuota(c, relayInfo, usage.(*dto.Usage), preConsumedQuota, userQuota, priceData, "")
 	} else {
-		postConsumeQuota(c, relayInfo, textRequest.Model, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
+		postConsumeQuota(c, relayInfo, usage.(*dto.Usage), preConsumedQuota, userQuota, priceData, "")
 	}
 	return nil
 }
@@ -246,19 +220,20 @@ func getPromptTokens(textRequest *dto.GeneralOpenAIRequest, info *relaycommon.Re
 	return promptTokens, err
 }
 
-func checkRequestSensitive(textRequest *dto.GeneralOpenAIRequest, info *relaycommon.RelayInfo) error {
+func checkRequestSensitive(textRequest *dto.GeneralOpenAIRequest, info *relaycommon.RelayInfo) ([]string, error) {
 	var err error
+	var words []string
 	switch info.RelayMode {
 	case relayconstant.RelayModeChatCompletions:
-		err = service.CheckSensitiveMessages(textRequest.Messages)
+		words, err = service.CheckSensitiveMessages(textRequest.Messages)
 	case relayconstant.RelayModeCompletions:
-		err = service.CheckSensitiveInput(textRequest.Prompt)
+		words, err = service.CheckSensitiveInput(textRequest.Prompt)
 	case relayconstant.RelayModeModerations:
-		err = service.CheckSensitiveInput(textRequest.Input)
+		words, err = service.CheckSensitiveInput(textRequest.Input)
 	case relayconstant.RelayModeEmbeddings:
-		err = service.CheckSensitiveInput(textRequest.Input)
+		words, err = service.CheckSensitiveInput(textRequest.Input)
 	}
-	return err
+	return words, err
 }
 
 // 预扣费并返回用户剩余配额
@@ -271,7 +246,7 @@ func preConsumeQuota(c *gin.Context, preConsumedQuota int, relayInfo *relaycommo
 		return 0, 0, service.OpenAIErrorWrapperLocal(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
 	}
 	if userQuota-preConsumedQuota < 0 {
-		return 0, 0, service.OpenAIErrorWrapperLocal(fmt.Errorf("chat pre-consumed quota failed, user quota: %d, need quota: %d", userQuota, preConsumedQuota), "insufficient_user_quota", http.StatusBadRequest)
+		return 0, 0, service.OpenAIErrorWrapperLocal(fmt.Errorf("chat pre-consumed quota failed, user quota: %s, need quota: %s", common.FormatQuota(userQuota), common.FormatQuota(preConsumedQuota)), "insufficient_user_quota", http.StatusForbidden)
 	}
 	if userQuota > 100*preConsumedQuota {
 		// 用户额度充足，判断令牌额度是否充足
@@ -281,18 +256,18 @@ func preConsumeQuota(c *gin.Context, preConsumedQuota int, relayInfo *relaycommo
 			if tokenQuota > 100*preConsumedQuota {
 				// 令牌额度充足，信任令牌
 				preConsumedQuota = 0
-				common.LogInfo(c, fmt.Sprintf("user %d quota %d and token %d quota %d are enough, trusted and no need to pre-consume", relayInfo.UserId, userQuota, relayInfo.TokenId, tokenQuota))
+				common.LogInfo(c, fmt.Sprintf("user %d quota %s and token %d quota %d are enough, trusted and no need to pre-consume", relayInfo.UserId, common.FormatQuota(userQuota), relayInfo.TokenId, tokenQuota))
 			}
 		} else {
 			// in this case, we do not pre-consume quota
 			// because the user has enough quota
 			preConsumedQuota = 0
-			common.LogInfo(c, fmt.Sprintf("user %d with unlimited token has enough quota %d, trusted and no need to pre-consume", relayInfo.UserId, userQuota))
+			common.LogInfo(c, fmt.Sprintf("user %d with unlimited token has enough quota %s, trusted and no need to pre-consume", relayInfo.UserId, common.FormatQuota(userQuota)))
 		}
 	}
 
 	if preConsumedQuota > 0 {
-		err = model.PreConsumeTokenQuota(relayInfo, preConsumedQuota)
+		err = service.PreConsumeTokenQuota(relayInfo, preConsumedQuota)
 		if err != nil {
 			return 0, 0, service.OpenAIErrorWrapperLocal(err, "pre_consume_token_quota_failed", http.StatusForbidden)
 		}
@@ -306,20 +281,19 @@ func preConsumeQuota(c *gin.Context, preConsumedQuota int, relayInfo *relaycommo
 
 func returnPreConsumedQuota(c *gin.Context, relayInfo *relaycommon.RelayInfo, userQuota int, preConsumedQuota int) {
 	if preConsumedQuota != 0 {
-		go func() {
+		gopool.Go(func() {
 			relayInfoCopy := *relayInfo
 
-			err := model.PostConsumeQuota(&relayInfoCopy, userQuota, -preConsumedQuota, 0, false)
+			err := service.PostConsumeQuota(&relayInfoCopy, -preConsumedQuota, 0, false)
 			if err != nil {
 				common.SysError("error return pre-consumed quota: " + err.Error())
 			}
-		}()
+		})
 	}
 }
 
-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) {
+func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
+	usage *dto.Usage, preConsumedQuota int, userQuota int, priceData helper.PriceData, extraContent string) {
 	if usage == nil {
 		usage = &dto.Usage{
 			PromptTokens:     relayInfo.PromptTokens,
@@ -331,12 +305,18 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelN
 	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
 	promptTokens := usage.PromptTokens
 	completionTokens := usage.CompletionTokens
+	modelName := relayInfo.OriginModelName
 
 	tokenName := ctx.GetString("token_name")
 	completionRatio := common.GetCompletionRatio(modelName)
+	ratio := priceData.ModelRatio * priceData.GroupRatio
+	modelRatio := priceData.ModelRatio
+	groupRatio := priceData.GroupRatio
+	modelPrice := priceData.ModelPrice
+	usePrice := priceData.UsePrice
 
 	quota := 0
-	if !usePrice {
+	if !priceData.UsePrice {
 		quota = promptTokens + int(math.Round(float64(completionTokens)*completionRatio))
 		quota = int(math.Round(float64(quota) * ratio))
 		if ratio != 0 && quota <= 0 {
@@ -367,7 +347,7 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelN
 		//}
 		quotaDelta := quota - preConsumedQuota
 		if quotaDelta != 0 {
-			err := model.PostConsumeQuota(relayInfo, userQuota, quotaDelta, preConsumedQuota, true)
+			err := service.PostConsumeQuota(relayInfo, quotaDelta, preConsumedQuota, true)
 			if err != nil {
 				common.LogError(ctx, "error consuming token remain quota: "+err.Error())
 			}

relay/relay_adaptor.go

@@ -6,6 +6,7 @@ import (
 	"one-api/relay/channel/ali"
 	"one-api/relay/channel/aws"
 	"one-api/relay/channel/baidu"
+	"one-api/relay/channel/baidu_v2"
 	"one-api/relay/channel/claude"
 	"one-api/relay/channel/cloudflare"
 	"one-api/relay/channel/cohere"
@@ -14,6 +15,7 @@ import (
 	"one-api/relay/channel/gemini"
 	"one-api/relay/channel/jina"
 	"one-api/relay/channel/mistral"
+	"one-api/relay/channel/mokaai"
 	"one-api/relay/channel/ollama"
 	"one-api/relay/channel/openai"
 	"one-api/relay/channel/palm"
@@ -22,6 +24,7 @@ import (
 	"one-api/relay/channel/task/suno"
 	"one-api/relay/channel/tencent"
 	"one-api/relay/channel/vertex"
+	"one-api/relay/channel/volcengine"
 	"one-api/relay/channel/xunfei"
 	"one-api/relay/channel/zhipu"
 	"one-api/relay/channel/zhipu_4v"
@@ -74,6 +77,12 @@ func GetAdaptor(apiType int) channel.Adaptor {
 		return &mistral.Adaptor{}
 	case constant.APITypeDeepSeek:
 		return &deepseek.Adaptor{}
+	case constant.APITypeMokaAI:
+		return &mokaai.Adaptor{}
+	case constant.APITypeVolcEngine:
+		return &volcengine.Adaptor{}
+	case constant.APITypeBaiduV2:
+		return &baidu_v2.Adaptor{}
 	}
 	return nil
 }

relay/relay_embedding.go

@@ -0,0 +1,114 @@
+package relay
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"net/http"
+	"one-api/common"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	relayconstant "one-api/relay/constant"
+	"one-api/relay/helper"
+	"one-api/service"
+)
+
+func getEmbeddingPromptToken(embeddingRequest dto.EmbeddingRequest) int {
+	token, _ := service.CountTokenInput(embeddingRequest.Input, embeddingRequest.Model)
+	return token
+}
+
+func validateEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, embeddingRequest dto.EmbeddingRequest) error {
+	if embeddingRequest.Input == nil {
+		return fmt.Errorf("input is empty")
+	}
+	if info.RelayMode == relayconstant.RelayModeModerations && embeddingRequest.Model == "" {
+		embeddingRequest.Model = "omni-moderation-latest"
+	}
+	if info.RelayMode == relayconstant.RelayModeEmbeddings && embeddingRequest.Model == "" {
+		embeddingRequest.Model = c.Param("model")
+	}
+	return nil
+}
+
+func EmbeddingHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
+	relayInfo := relaycommon.GenRelayInfo(c)
+
+	var embeddingRequest *dto.EmbeddingRequest
+	err := common.UnmarshalBodyReusable(c, &embeddingRequest)
+	if err != nil {
+		common.LogError(c, fmt.Sprintf("getAndValidateTextRequest failed: %s", err.Error()))
+		return service.OpenAIErrorWrapperLocal(err, "invalid_text_request", http.StatusBadRequest)
+	}
+
+	err = validateEmbeddingRequest(c, relayInfo, *embeddingRequest)
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "invalid_embedding_request", http.StatusBadRequest)
+	}
+
+	err = helper.ModelMappedHelper(c, relayInfo)
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "model_mapped_error", http.StatusInternalServerError)
+	}
+
+	embeddingRequest.Model = relayInfo.UpstreamModelName
+
+	promptToken := getEmbeddingPromptToken(*embeddingRequest)
+	relayInfo.PromptTokens = promptToken
+
+	priceData := helper.ModelPriceHelper(c, relayInfo, promptToken, 0)
+
+	// pre-consume quota 预消耗配额
+	preConsumedQuota, userQuota, openaiErr := preConsumeQuota(c, priceData.ShouldPreConsumedQuota, relayInfo)
+	if openaiErr != nil {
+		return openaiErr
+	}
+	defer func() {
+		if openaiErr != nil {
+			returnPreConsumedQuota(c, relayInfo, userQuota, preConsumedQuota)
+		}
+	}()
+
+	adaptor := GetAdaptor(relayInfo.ApiType)
+	if adaptor == nil {
+		return service.OpenAIErrorWrapperLocal(fmt.Errorf("invalid api type: %d", relayInfo.ApiType), "invalid_api_type", http.StatusBadRequest)
+	}
+	adaptor.Init(relayInfo)
+
+	convertedRequest, err := adaptor.ConvertEmbeddingRequest(c, relayInfo, *embeddingRequest)
+
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "convert_request_failed", http.StatusInternalServerError)
+	}
+	jsonData, err := json.Marshal(convertedRequest)
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "json_marshal_failed", http.StatusInternalServerError)
+	}
+	requestBody := bytes.NewBuffer(jsonData)
+	statusCodeMappingStr := c.GetString("status_code_mapping")
+	resp, err := adaptor.DoRequest(c, relayInfo, requestBody)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
+	}
+
+	var httpResp *http.Response
+	if resp != nil {
+		httpResp = resp.(*http.Response)
+		if httpResp.StatusCode != http.StatusOK {
+			openaiErr = service.RelayErrorHandler(httpResp)
+			// reset status code 重置状态码
+			service.ResetStatusCode(openaiErr, statusCodeMappingStr)
+			return openaiErr
+		}
+	}
+
+	usage, openaiErr := adaptor.DoResponse(c, httpResp, relayInfo)
+	if openaiErr != nil {
+		// reset status code 重置状态码
+		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
+		return openaiErr
+	}
+	postConsumeQuota(c, relayInfo, usage.(*dto.Usage), preConsumedQuota, userQuota, priceData, "")
+	return nil
+}

relay/relay_rerank.go

@@ -9,8 +9,8 @@ import (
 	"one-api/common"
 	"one-api/dto"
 	relaycommon "one-api/relay/common"
+	"one-api/relay/helper"
 	"one-api/service"
-	"one-api/setting"
 )
 
 func getRerankPromptToken(rerankRequest dto.RerankRequest) int {
@@ -40,43 +40,20 @@ func RerankHelper(c *gin.Context, relayMode int) (openaiErr *dto.OpenAIErrorWith
 		return service.OpenAIErrorWrapperLocal(fmt.Errorf("documents is empty"), "invalid_documents", http.StatusBadRequest)
 	}
 
-	// map model name
-	modelMapping := c.GetString("model_mapping")
-	//isModelMapped := false
-	if modelMapping != "" && modelMapping != "{}" {
-		modelMap := make(map[string]string)
-		err := json.Unmarshal([]byte(modelMapping), &modelMap)
-		if err != nil {
-			return service.OpenAIErrorWrapperLocal(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
-		}
-		if modelMap[rerankRequest.Model] != "" {
-			rerankRequest.Model = modelMap[rerankRequest.Model]
-			// set upstream model name
-			//isModelMapped = true
-		}
+	err = helper.ModelMappedHelper(c, relayInfo)
+	if err != nil {
+		return service.OpenAIErrorWrapperLocal(err, "model_mapped_error", http.StatusInternalServerError)
 	}
 
-	relayInfo.UpstreamModelName = rerankRequest.Model
-	modelPrice, success := common.GetModelPrice(rerankRequest.Model, false)
-	groupRatio := setting.GetGroupRatio(relayInfo.Group)
-
-	var preConsumedQuota int
-	var ratio float64
-	var modelRatio float64
+	rerankRequest.Model = relayInfo.UpstreamModelName
 
 	promptToken := getRerankPromptToken(*rerankRequest)
-	if !success {
-		preConsumedTokens := promptToken
-		modelRatio = common.GetModelRatio(rerankRequest.Model)
-		ratio = modelRatio * groupRatio
-		preConsumedQuota = int(float64(preConsumedTokens) * ratio)
-	} else {
-		preConsumedQuota = int(modelPrice * common.QuotaPerUnit * groupRatio)
-	}
 	relayInfo.PromptTokens = promptToken
 
+	priceData := helper.ModelPriceHelper(c, relayInfo, promptToken, 0)
+
 	// pre-consume quota 预消耗配额
-	preConsumedQuota, userQuota, openaiErr := preConsumeQuota(c, preConsumedQuota, relayInfo)
+	preConsumedQuota, userQuota, openaiErr := preConsumeQuota(c, priceData.ShouldPreConsumedQuota, relayInfo)
 	if openaiErr != nil {
 		return openaiErr
 	}
@@ -124,6 +101,6 @@ func RerankHelper(c *gin.Context, relayMode int) (openaiErr *dto.OpenAIErrorWith
 		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
 		return openaiErr
 	}
-	postConsumeQuota(c, relayInfo, rerankRequest.Model, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, success, "")
+	postConsumeQuota(c, relayInfo, usage.(*dto.Usage), preConsumedQuota, userQuota, priceData, "")
 	return nil
 }

relay/relay_task.go

@@ -113,7 +113,7 @@ func RelayTaskSubmit(c *gin.Context, relayMode int) (taskErr *dto.TaskError) {
 		// release quota
 		if relayInfo.ConsumeQuota && taskErr == nil {
 
-			err := model.PostConsumeQuota(relayInfo.ToRelayInfo(), userQuota, quota, 0, true)
+			err := service.PostConsumeQuota(relayInfo.ToRelayInfo(), quota, 0, true)
 			if err != nil {
 				common.SysError("error consuming token remain quota: " + err.Error())
 			}

router/api-router.go

@@ -56,6 +56,7 @@ func SetApiRouter(router *gin.Engine) {
 				selfRoute.POST("/pay", controller.RequestEpay)
 				selfRoute.POST("/amount", controller.RequestAmount)
 				selfRoute.POST("/aff_transfer", controller.TransferAffQuota)
+				selfRoute.PUT("/setting", controller.UpdateUserSetting)
 			}
 
 			adminRoute := userRoute.Group("/")

service/cf_worker.go

@@ -2,6 +2,7 @@ package service
 
 import (
 	"bytes"
+	"encoding/json"
 	"fmt"
 	"net/http"
 	"one-api/common"
@@ -9,19 +10,46 @@ import (
 	"strings"
 )
 
+// WorkerRequest Worker请求的数据结构
+type WorkerRequest struct {
+	URL     string            `json:"url"`
+	Key     string            `json:"key"`
+	Method  string            `json:"method,omitempty"`
+	Headers map[string]string `json:"headers,omitempty"`
+	Body    json.RawMessage   `json:"body,omitempty"`
+}
+
+// DoWorkerRequest 通过Worker发送请求
+func DoWorkerRequest(req *WorkerRequest) (*http.Response, error) {
+	if !setting.EnableWorker() {
+		return nil, fmt.Errorf("worker not enabled")
+	}
+	if !strings.HasPrefix(req.URL, "https") {
+		return nil, fmt.Errorf("only support https url")
+	}
+
+	workerUrl := setting.WorkerUrl
+	if !strings.HasSuffix(workerUrl, "/") {
+		workerUrl += "/"
+	}
+
+	// 序列化worker请求数据
+	workerPayload, err := json.Marshal(req)
+	if err != nil {
+		return nil, fmt.Errorf("failed to marshal worker payload: %v", err)
+	}
+
+	return http.Post(workerUrl, "application/json", bytes.NewBuffer(workerPayload))
+}
+
 func DoDownloadRequest(originUrl string) (resp *http.Response, err error) {
 	if setting.EnableWorker() {
 		common.SysLog(fmt.Sprintf("downloading file from worker: %s", originUrl))
-		if !strings.HasPrefix(originUrl, "https") {
-			return nil, fmt.Errorf("only support https url")
+		req := &WorkerRequest{
+			URL: originUrl,
+			Key: setting.WorkerValidKey,
 		}
-		workerUrl := setting.WorkerUrl
-		if !strings.HasSuffix(workerUrl, "/") {
-			workerUrl += "/"
-		}
-		// post request to worker
-		data := []byte(`{"url":"` + originUrl + `","key":"` + setting.WorkerValidKey + `"}`)
-		return http.Post(setting.WorkerUrl, "application/json", bytes.NewBuffer(data))
+		return DoWorkerRequest(req)
 	} else {
 		common.SysLog(fmt.Sprintf("downloading from origin: %s", originUrl))
 		return http.Get(originUrl)

service/channel.go

@@ -4,8 +4,9 @@ import (
 	"fmt"
 	"net/http"
 	"one-api/common"
-	relaymodel "one-api/dto"
+	"one-api/dto"
 	"one-api/model"
+	"one-api/setting"
 	"strings"
 )
 
@@ -14,17 +15,17 @@ func DisableChannel(channelId int, channelName string, reason string) {
 	model.UpdateChannelStatusById(channelId, common.ChannelStatusAutoDisabled, reason)
 	subject := fmt.Sprintf("通道「%s」（#%d）已被禁用", channelName, channelId)
 	content := fmt.Sprintf("通道「%s」（#%d）已被禁用，原因：%s", channelName, channelId, reason)
-	notifyRootUser(subject, content)
+	NotifyRootUser(subject, content, dto.NotifyTypeChannelUpdate)
 }
 
 func EnableChannel(channelId int, channelName string) {
 	model.UpdateChannelStatusById(channelId, common.ChannelStatusEnabled, "")
 	subject := fmt.Sprintf("通道「%s」（#%d）已被启用", channelName, channelId)
 	content := fmt.Sprintf("通道「%s」（#%d）已被启用", channelName, channelId)
-	notifyRootUser(subject, content)
+	NotifyRootUser(subject, content, dto.NotifyTypeChannelUpdate)
 }
 
-func ShouldDisableChannel(channelType int, err *relaymodel.OpenAIErrorWithStatusCode) bool {
+func ShouldDisableChannel(channelType int, err *dto.OpenAIErrorWithStatusCode) bool {
 	if !common.AutomaticDisableChannelEnabled {
 		return false
 	}
@@ -64,28 +65,17 @@ func ShouldDisableChannel(channelType int, err *relaymodel.OpenAIErrorWithStatus
 	case "forbidden":
 		return true
 	}
-	if strings.HasPrefix(err.Error.Message, "Your credit balance is too low") { // anthropic
-		return true
-	} else if strings.HasPrefix(err.Error.Message, "This organization has been disabled.") {
-		return true
-	} else if strings.HasPrefix(err.Error.Message, "You exceeded your current quota") {
-		return true
-	} else if strings.HasPrefix(err.Error.Message, "Permission denied") {
-		return true
-	}
 
-	if strings.Contains(err.Error.Message, "The security token included in the request is invalid") { // anthropic
-		return true
-	} else if strings.Contains(err.Error.Message, "Operation not allowed") {
-		return true
-	} else if strings.Contains(err.Error.Message, "Your account is not authorized") {
+	lowerMessage := strings.ToLower(err.Error.Message)
+	search, _ := AcSearch(lowerMessage, setting.AutomaticDisableKeywords, true)
+	if search {
 		return true
 	}
 
 	return false
 }
 
-func ShouldEnableChannel(err error, openaiWithStatusErr *relaymodel.OpenAIErrorWithStatusCode, status int) bool {
+func ShouldEnableChannel(err error, openaiWithStatusErr *dto.OpenAIErrorWithStatusCode, status int) bool {
 	if !common.AutomaticEnableChannelEnabled {
 		return false
 	}

service/http_client.go

@@ -1,7 +1,12 @@
 package service
 
 import (
+	"context"
+	"fmt"
+	"golang.org/x/net/proxy"
+	"net"
 	"net/http"
+	"net/url"
 	"one-api/common"
 	"time"
 )
@@ -30,3 +35,54 @@ func GetHttpClient() *http.Client {
 func GetImpatientHttpClient() *http.Client {
 	return impatientHTTPClient
 }
+
+// NewProxyHttpClient 创建支持代理的 HTTP 客户端
+func NewProxyHttpClient(proxyURL string) (*http.Client, error) {
+	if proxyURL == "" {
+		return http.DefaultClient, nil
+	}
+
+	parsedURL, err := url.Parse(proxyURL)
+	if err != nil {
+		return nil, err
+	}
+
+	switch parsedURL.Scheme {
+	case "http", "https":
+		return &http.Client{
+			Transport: &http.Transport{
+				Proxy: http.ProxyURL(parsedURL),
+			},
+		}, nil
+
+	case "socks5":
+		// 获取认证信息
+		var auth *proxy.Auth
+		if parsedURL.User != nil {
+			auth = &proxy.Auth{
+				User:     parsedURL.User.Username(),
+				Password: "",
+			}
+			if password, ok := parsedURL.User.Password(); ok {
+				auth.Password = password
+			}
+		}
+
+		// 创建 SOCKS5 代理拨号器
+		dialer, err := proxy.SOCKS5("tcp", parsedURL.Host, auth, proxy.Direct)
+		if err != nil {
+			return nil, err
+		}
+
+		return &http.Client{
+			Transport: &http.Transport{
+				DialContext: func(ctx context.Context, network, addr string) (net.Conn, error) {
+					return dialer.Dial(network, addr)
+				},
+			},
+		}, nil
+
+	default:
+		return nil, fmt.Errorf("unsupported proxy scheme: %s", parsedURL.Scheme)
+	}
+}

service/log_info_generate.go

@@ -13,6 +13,13 @@ func GenerateTextOtherInfo(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, m
 	other["completion_ratio"] = completionRatio
 	other["model_price"] = modelPrice
 	other["frt"] = float64(relayInfo.FirstResponseTime.UnixMilli() - relayInfo.StartTime.UnixMilli())
+	if relayInfo.ReasoningEffort != "" {
+		other["reasoning_effort"] = relayInfo.ReasoningEffort
+	}
+	if relayInfo.IsModelMapped {
+		other["is_model_mapped"] = true
+		other["upstream_model_name"] = relayInfo.UpstreamModelName
+	}
 	adminInfo := make(map[string]interface{})
 	adminInfo["use_channel"] = ctx.GetStringSlice("use_channel")
 	other["admin_info"] = adminInfo

service/notify-limit.go

@@ -0,0 +1,117 @@
+package service
+
+import (
+	"fmt"
+	"github.com/bytedance/gopkg/util/gopool"
+	"one-api/common"
+	"one-api/constant"
+	"strconv"
+	"sync"
+	"time"
+)
+
+// notifyLimitStore is used for in-memory rate limiting when Redis is disabled
+var (
+	notifyLimitStore sync.Map
+	cleanupOnce      sync.Once
+)
+
+type limitCount struct {
+	Count     int
+	Timestamp time.Time
+}
+
+func getDuration() time.Duration {
+	minute := constant.NotificationLimitDurationMinute
+	return time.Duration(minute) * time.Minute
+}
+
+// startCleanupTask starts a background task to clean up expired entries
+func startCleanupTask() {
+	gopool.Go(func() {
+		for {
+			time.Sleep(time.Hour)
+			now := time.Now()
+			notifyLimitStore.Range(func(key, value interface{}) bool {
+				if limit, ok := value.(limitCount); ok {
+					if now.Sub(limit.Timestamp) >= getDuration() {
+						notifyLimitStore.Delete(key)
+					}
+				}
+				return true
+			})
+		}
+	})
+}
+
+// CheckNotificationLimit checks if the user has exceeded their notification limit
+// Returns true if the user can send notification, false if limit exceeded
+func CheckNotificationLimit(userId int, notifyType string) (bool, error) {
+	if common.RedisEnabled {
+		return checkRedisLimit(userId, notifyType)
+	}
+	return checkMemoryLimit(userId, notifyType)
+}
+
+func checkRedisLimit(userId int, notifyType string) (bool, error) {
+	key := fmt.Sprintf("notify_limit:%d:%s:%s", userId, notifyType, time.Now().Format("2006010215"))
+
+	// Get current count
+	count, err := common.RedisGet(key)
+	if err != nil && err.Error() != "redis: nil" {
+		return false, fmt.Errorf("failed to get notification count: %w", err)
+	}
+
+	// If key doesn't exist, initialize it
+	if count == "" {
+		err = common.RedisSet(key, "1", getDuration())
+		return true, err
+	}
+
+	currentCount, _ := strconv.Atoi(count)
+	limit := constant.NotifyLimitCount
+
+	// Check if limit is already reached
+	if currentCount >= limit {
+		return false, nil
+	}
+
+	// Only increment if under limit
+	err = common.RedisIncr(key, 1)
+	if err != nil {
+		return false, fmt.Errorf("failed to increment notification count: %w", err)
+	}
+
+	return true, nil
+}
+
+func checkMemoryLimit(userId int, notifyType string) (bool, error) {
+	// Ensure cleanup task is started
+	cleanupOnce.Do(startCleanupTask)
+
+	key := fmt.Sprintf("%d:%s:%s", userId, notifyType, time.Now().Format("2006010215"))
+	now := time.Now()
+
+	// Get current limit count or initialize new one
+	var currentLimit limitCount
+	if value, ok := notifyLimitStore.Load(key); ok {
+		currentLimit = value.(limitCount)
+		// Check if the entry has expired
+		if now.Sub(currentLimit.Timestamp) >= getDuration() {
+			currentLimit = limitCount{Count: 0, Timestamp: now}
+		}
+	} else {
+		currentLimit = limitCount{Count: 0, Timestamp: now}
+	}
+
+	// Increment count
+	currentLimit.Count++
+
+	// Check against limits
+	limit := constant.NotifyLimitCount
+
+	// Store updated count
+	notifyLimitStore.Store(key, currentLimit)
+
+	return currentLimit.Count <= limit, nil
+}

service/quota.go

@@ -3,11 +3,14 @@ package service
 import (
 	"errors"
 	"fmt"
+	"github.com/bytedance/gopkg/util/gopool"
 	"math"
 	"one-api/common"
+	constant2 "one-api/constant"
 	"one-api/dto"
 	"one-api/model"
 	relaycommon "one-api/relay/common"
+	"one-api/relay/helper"
 	"one-api/setting"
 	"strings"
 	"time"
@@ -66,7 +69,7 @@ func PreWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usag
 		return err
 	}
 
-	modelName := relayInfo.UpstreamModelName
+	modelName := relayInfo.OriginModelName
 	textInputTokens := usage.InputTokenDetails.TextTokens
 	textOutTokens := usage.OutputTokenDetails.TextTokens
 	audioInputTokens := usage.InputTokenDetails.AudioTokens
@@ -92,14 +95,14 @@ func PreWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usag
 	quota := calculateAudioQuota(quotaInfo)
 
 	if userQuota < quota {
-		return errors.New(fmt.Sprintf("用户额度不足，剩余额度为 %d", userQuota))
+		return fmt.Errorf("user quota is not enough, user quota: %s, need quota: %s", common.FormatQuota(userQuota), common.FormatQuota(quota))
 	}
 
 	if !token.UnlimitedQuota && token.RemainQuota < quota {
-		return errors.New(fmt.Sprintf("令牌额度不足，剩余额度为 %d", token.RemainQuota))
+		return fmt.Errorf("token quota is not enough, token remain quota: %s, need quota: %s", common.FormatQuota(token.RemainQuota), common.FormatQuota(quota))
 	}
 
-	err = model.PostConsumeQuota(relayInfo, 0, quota, 0, false)
+	err = PostConsumeQuota(relayInfo, quota, 0, false)
 	if err != nil {
 		return err
 	}
@@ -120,7 +123,7 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 
 	tokenName := ctx.GetString("token_name")
 	completionRatio := common.GetCompletionRatio(modelName)
-	audioRatio := common.GetAudioRatio(relayInfo.UpstreamModelName)
+	audioRatio := common.GetAudioRatio(relayInfo.OriginModelName)
 	audioCompletionRatio := common.GetAudioCompletionRatio(modelName)
 
 	quotaInfo := QuotaInfo{
@@ -171,8 +174,7 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 }
 
 func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
-	usage *dto.Usage, preConsumedQuota int, userQuota int, modelRatio float64, groupRatio float64,
-	modelPrice float64, usePrice bool, extraContent string) {
+	usage *dto.Usage, preConsumedQuota int, userQuota int, priceData helper.PriceData, extraContent string) {
 
 	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
 	textInputTokens := usage.PromptTokensDetails.TextTokens
@@ -182,9 +184,14 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 	audioOutTokens := usage.CompletionTokenDetails.AudioTokens
 
 	tokenName := ctx.GetString("token_name")
-	completionRatio := common.GetCompletionRatio(relayInfo.UpstreamModelName)
-	audioRatio := common.GetAudioRatio(relayInfo.UpstreamModelName)
-	audioCompletionRatio := common.GetAudioCompletionRatio(relayInfo.UpstreamModelName)
+	completionRatio := common.GetCompletionRatio(relayInfo.OriginModelName)
+	audioRatio := common.GetAudioRatio(relayInfo.OriginModelName)
+	audioCompletionRatio := common.GetAudioCompletionRatio(relayInfo.OriginModelName)
+
+	modelRatio := priceData.ModelRatio
+	groupRatio := priceData.GroupRatio
+	modelPrice := priceData.ModelPrice
+	usePrice := priceData.UsePrice
 
 	quotaInfo := QuotaInfo{
 		InputDetails: TokenDetails{
@@ -195,7 +202,7 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 			TextTokens:  textOutTokens,
 			AudioTokens: audioOutTokens,
 		},
-		ModelName:  relayInfo.UpstreamModelName,
+		ModelName:  relayInfo.OriginModelName,
 		UsePrice:   usePrice,
 		ModelRatio: modelRatio,
 		GroupRatio: groupRatio,
@@ -218,11 +225,11 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 		quota = 0
 		logContent += fmt.Sprintf("（可能是上游超时）")
 		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, relayInfo.UpstreamModelName, preConsumedQuota))
+			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, relayInfo.OriginModelName, preConsumedQuota))
 	} else {
 		quotaDelta := quota - preConsumedQuota
 		if quotaDelta != 0 {
-			err := model.PostConsumeQuota(relayInfo, userQuota, quotaDelta, preConsumedQuota, true)
+			err := PostConsumeQuota(relayInfo, quotaDelta, preConsumedQuota, true)
 			if err != nil {
 				common.LogError(ctx, "error consuming token remain quota: "+err.Error())
 			}
@@ -231,7 +238,7 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 		model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
 	}
 
-	logModel := relayInfo.UpstreamModelName
+	logModel := relayInfo.OriginModelName
 	if extraContent != "" {
 		logContent += ", " + extraContent
 	}
@@ -239,3 +246,88 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 	model.RecordConsumeLog(ctx, relayInfo.UserId, relayInfo.ChannelId, usage.PromptTokens, usage.CompletionTokens, logModel,
 		tokenName, quota, logContent, relayInfo.TokenId, userQuota, int(useTimeSeconds), relayInfo.IsStream, relayInfo.Group, other)
 }
+
+func PreConsumeTokenQuota(relayInfo *relaycommon.RelayInfo, quota int) error {
+	if quota < 0 {
+		return errors.New("quota 不能为负数！")
+	}
+	if relayInfo.IsPlayground {
+		return nil
+	}
+	//if relayInfo.TokenUnlimited {
+	//	return nil
+	//}
+	token, err := model.GetTokenByKey(relayInfo.TokenKey, false)
+	if err != nil {
+		return err
+	}
+	if !relayInfo.TokenUnlimited && token.RemainQuota < quota {
+		return fmt.Errorf("token quota is not enough, token remain quota: %s, need quota: %s", common.FormatQuota(token.RemainQuota), common.FormatQuota(quota))
+	}
+	err = model.DecreaseTokenQuota(relayInfo.TokenId, relayInfo.TokenKey, quota)
+	if err != nil {
+		return err
+	}
+	return nil
+}
+
+func PostConsumeQuota(relayInfo *relaycommon.RelayInfo, quota int, preConsumedQuota int, sendEmail bool) (err error) {
+
+	if quota > 0 {
+		err = model.DecreaseUserQuota(relayInfo.UserId, quota)
+	} else {
+		err = model.IncreaseUserQuota(relayInfo.UserId, -quota)
+	}
+	if err != nil {
+		return err
+	}
+
+	if !relayInfo.IsPlayground {
+		if quota > 0 {
+			err = model.DecreaseTokenQuota(relayInfo.TokenId, relayInfo.TokenKey, quota)
+		} else {
+			err = model.IncreaseTokenQuota(relayInfo.TokenId, relayInfo.TokenKey, -quota)
+		}
+		if err != nil {
+			return err
+		}
+	}
+
+	if sendEmail {
+		if (quota + preConsumedQuota) != 0 {
+			checkAndSendQuotaNotify(relayInfo.UserId, quota, preConsumedQuota)
+		}
+	}
+
+	return nil
+}
+
+func checkAndSendQuotaNotify(userId int, quota int, preConsumedQuota int) {
+	gopool.Go(func() {
+		userCache, err := model.GetUserCache(userId)
+		if err != nil {
+			common.SysError("failed to get user cache: " + err.Error())
+		}
+		userSetting := userCache.GetSetting()
+		threshold := common.QuotaRemindThreshold
+		if userCustomThreshold, ok := userSetting[constant2.UserSettingQuotaWarningThreshold]; ok {
+			threshold = int(userCustomThreshold.(float64))
+		}
+
+		//noMoreQuota := userCache.Quota-(quota+preConsumedQuota) <= 0
+		quotaTooLow := false
+		consumeQuota := quota + preConsumedQuota
+		if userCache.Quota-consumeQuota < threshold {
+			quotaTooLow = true
+		}
+		if quotaTooLow {
+			prompt := "您的额度即将用尽"
+			topUpLink := fmt.Sprintf("%s/topup", setting.ServerAddress)
+			content := "{{value}}，当前剩余额度为 {{value}}，为了不影响您的使用，请及时充值。<br/>充值链接：<a href='{{value}}'>{{value}}</a>"
+			err = NotifyUser(userCache, dto.NewNotify(dto.NotifyTypeQuotaExceed, prompt, content, []interface{}{prompt, common.FormatQuota(userCache.Quota), topUpLink, topUpLink}))
+			if err != nil {
+				common.SysError(fmt.Sprintf("failed to send quota notify to user %d: %s", userId, err.Error()))
+			}
+		}
+	})
+}

service/sensitive.go

@@ -8,48 +8,47 @@ import (
 	"strings"
 )
 
-func CheckSensitiveMessages(messages []dto.Message) error {
+func CheckSensitiveMessages(messages []dto.Message) ([]string, error) {
+	if len(messages) == 0 {
+		return nil, nil
+	}
+
 	for _, message := range messages {
-		if len(message.Content) > 0 {
-			if message.IsStringContent() {
-				stringContent := message.StringContent()
-				if ok, words := SensitiveWordContains(stringContent); ok {
-					return errors.New("sensitive words: " + strings.Join(words, ","))
-				}
+		arrayContent := message.ParseContent()
+		for _, m := range arrayContent {
+			if m.Type == "image_url" {
+				// TODO: check image url
+				continue
 			}
-		} else {
-			arrayContent := message.ParseContent()
-			for _, m := range arrayContent {
-				if m.Type == "image_url" {
-					// TODO: check image url
-				} else {
-					if ok, words := SensitiveWordContains(m.Text); ok {
-						return errors.New("sensitive words: " + strings.Join(words, ","))
-					}
-				}
+			// 检查 text 是否为空
+			if m.Text == "" {
+				continue
+			}
+			if ok, words := SensitiveWordContains(m.Text); ok {
+				return words, errors.New("sensitive words detected")
 			}
 		}
 	}
-	return nil
+	return nil, nil
 }
 
-func CheckSensitiveText(text string) error {
+func CheckSensitiveText(text string) ([]string, error) {
 	if ok, words := SensitiveWordContains(text); ok {
-		return errors.New("sensitive words: " + strings.Join(words, ","))
+		return words, errors.New("sensitive words detected")
 	}
-	return nil
+	return nil, nil
 }
 
-func CheckSensitiveInput(input any) error {
+func CheckSensitiveInput(input any) ([]string, error) {
 	switch v := input.(type) {
 	case string:
 		return CheckSensitiveText(v)
 	case []string:
-		text := ""
+		var builder strings.Builder
 		for _, s := range v {
-			text += s
+			builder.WriteString(s)
 		}
-		return CheckSensitiveText(text)
+		return CheckSensitiveText(builder.String())
 	}
 	return CheckSensitiveText(fmt.Sprintf("%v", input))
 }
@@ -59,18 +58,11 @@ func SensitiveWordContains(text string) (bool, []string) {
 	if len(setting.SensitiveWords) == 0 {
 		return false, nil
 	}
-	checkText := strings.ToLower(text)
-	// 构建一个AC自动机
-	m := InitAc()
-	hits := m.MultiPatternSearch([]rune(checkText), false)
-	if len(hits) > 0 {
-		words := make([]string, 0)
-		for _, hit := range hits {
-			words = append(words, string(hit.Word))
-		}
-		return true, words
+	if len(text) == 0 {
+		return false, nil
 	}
-	return false, nil
+	checkText := strings.ToLower(text)
+	return AcSearch(checkText, setting.SensitiveWords, true)
 }
 
 // SensitiveWordReplace 敏感词替换，返回是否包含敏感词和替换后的文本
@@ -79,17 +71,24 @@ func SensitiveWordReplace(text string, returnImmediately bool) (bool, []string,
 		return false, nil, text
 	}
 	checkText := strings.ToLower(text)
-	m := InitAc()
+	m := InitAc(setting.SensitiveWords)
 	hits := m.MultiPatternSearch([]rune(checkText), returnImmediately)
 	if len(hits) > 0 {
-		words := make([]string, 0)
+		words := make([]string, 0, len(hits))
+		var builder strings.Builder
+		builder.Grow(len(text))
+		lastPos := 0
+
 		for _, hit := range hits {
 			pos := hit.Pos
 			word := string(hit.Word)
-			text = text[:pos] + "**###**" + text[pos+len(word):]
+			builder.WriteString(text[lastPos:pos])
+			builder.WriteString("**###**")
+			lastPos = pos + len(word)
 			words = append(words, word)
 		}
-		return true, words, text
+		builder.WriteString(text[lastPos:])
+		return true, words, builder.String()
 	}
 	return false, nil, text
 }