refactor: Improve channel property update mechanism (fix #761)

feat: add 火山引擎 support stream options

.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 +88,13 @@ 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`
 
 ## 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 +104,58 @@ 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 +89,17 @@
 - `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`
 ## 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 +116,54 @@
 [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

@@ -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/model-ratio.go

@@ -50,18 +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,
-	"o3-mini":                0.55,
-	"o3-mini-2025-01-31":     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
+	"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,
@@ -185,8 +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,
@@ -412,11 +419,9 @@ 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

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

@@ -21,6 +21,8 @@ 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",
 }

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{

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/relay.go

@@ -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

@@ -846,9 +846,10 @@ 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 {

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 {

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/openai_request.go

@@ -86,11 +86,13 @@ 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"`
 }
 
 type MediaContent struct {
@@ -116,6 +118,17 @@ 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

dto/openai_response.go

@@ -81,7 +81,7 @@ func (c *ChatCompletionsStreamResponseChoiceDelta) GetContentString() string {
 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

@@ -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

@@ -239,5 +239,7 @@ 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

@@ -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":
@@ -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)
 	}

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

@@ -56,6 +56,10 @@ 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

@@ -29,7 +29,7 @@ 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
+	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 +49,11 @@ 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

@@ -68,6 +68,12 @@ 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/constant.go

@@ -3,17 +3,19 @@ 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",
 }
 
 var ChannelName = "google gemini"

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

@@ -46,18 +46,17 @@ 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), 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 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/relay-ollama.go

@@ -42,7 +42,7 @@ func requestOpenAI2Ollama(request dto.GeneralOpenAIRequest) *OllamaRequest {
 	}
 }
 
-func requestOpenAI2Embeddings(request dto.GeneralOpenAIRequest) *OllamaEmbeddingRequest {
+func requestOpenAI2Embeddings(request dto.EmbeddingRequest) *OllamaEmbeddingRequest {
 	return &OllamaEmbeddingRequest{
 		Model: request.Model,
 		Input: request.ParseInput(),
@@ -123,9 +123,9 @@ 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:
@@ -114,6 +119,21 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, re
 			request.MaxCompletionTokens = request.MaxTokens
 			request.MaxTokens = 0
 		}
+		if strings.HasPrefix(request.Model, "o3") {
+			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" || strings.HasPrefix(request.Model, "o3") {
 		//修改第一个Message的内容，将system改为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

@@ -14,6 +14,9 @@ var ModelList = []string{
 	"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)

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

@@ -58,6 +58,10 @@ 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:

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/common/relay_info.go

@@ -30,6 +30,7 @@ type RelayInfo struct {
 	RelayMode            int
 	UpstreamModelName    string
 	OriginModelName      string
+	RecodeModelName      string
 	RequestURLPath       string
 	ApiVersion           string
 	PromptTokens         int
@@ -45,6 +46,7 @@ type RelayInfo struct {
 	RealtimeTools        []dto.RealTimeTool
 	IsFirstRequest       bool
 	AudioUsage           bool
+	ReasoningEffort      string
 	ChannelSetting       map[string]interface{}
 }
 
@@ -87,6 +89,7 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
 		FirstResponseTime: startTime.Add(-time.Second),
 		OriginModelName:   c.GetString("original_model"),
 		UpstreamModelName: c.GetString("original_model"),
+		RecodeModelName:   c.GetString("recode_model"),
 		ApiType:           apiType,
 		ApiVersion:        c.GetString("api_version"),
 		ApiKey:            strings.TrimPrefix(c.Request.Header.Get("Authorization"), "Bearer "),
@@ -109,7 +112,8 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
 	}
 	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 {
+		info.ChannelType == common.ChannelCloudflare || info.ChannelType == common.ChannelTypeAzure ||
+	        info.ChannelType == common.ChannelTypeVolcEngine {
 		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/relay-text.go

@@ -93,6 +93,7 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 		}
 	}
 	relayInfo.UpstreamModelName = textRequest.Model
+	relayInfo.RecodeModelName = textRequest.Model
 	modelPrice, getModelPriceSuccess := common.GetModelPrice(textRequest.Model, false)
 	groupRatio := setting.GetGroupRatio(relayInfo.Group)
 
@@ -218,10 +219,10 @@ func TextHelper(c *gin.Context) (openaiErr *dto.OpenAIErrorWithStatusCode) {
 		return openaiErr
 	}
 
-	if strings.HasPrefix(relayInfo.UpstreamModelName, "gpt-4o-audio") {
+	if strings.HasPrefix(relayInfo.RecodeModelName, "gpt-4o-audio") {
 		service.PostAudioConsumeQuota(c, relayInfo, usage.(*dto.Usage), preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
 	} else {
-		postConsumeQuota(c, relayInfo, textRequest.Model, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
+		postConsumeQuota(c, relayInfo, relayInfo.RecodeModelName, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, getModelPriceSuccess, "")
 	}
 	return nil
 }

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 +1,137 @@
+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/service"
+	"one-api/setting"
+)
+
+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)
+	}
+
+	// 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[embeddingRequest.Model] != "" {
+			embeddingRequest.Model = modelMap[embeddingRequest.Model]
+			// set upstream model name
+			//isModelMapped = true
+		}
+	}
+
+	relayInfo.UpstreamModelName = embeddingRequest.Model
+	modelPrice, success := common.GetModelPrice(embeddingRequest.Model, false)
+	groupRatio := setting.GetGroupRatio(relayInfo.Group)
+
+	var preConsumedQuota int
+	var ratio float64
+	var modelRatio float64
+
+	promptToken := getEmbeddingPromptToken(*embeddingRequest)
+	if !success {
+		preConsumedTokens := promptToken
+		modelRatio = common.GetModelRatio(embeddingRequest.Model)
+		ratio = modelRatio * groupRatio
+		preConsumedQuota = int(float64(preConsumedTokens) * ratio)
+	} else {
+		preConsumedQuota = int(modelPrice * common.QuotaPerUnit * groupRatio)
+	}
+	relayInfo.PromptTokens = promptToken
+
+	// pre-consume quota 预消耗配额
+	preConsumedQuota, userQuota, openaiErr := preConsumeQuota(c, preConsumedQuota, 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, embeddingRequest.Model, usage.(*dto.Usage), ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, success, "")
+	return nil
+}

service/channel.go

@@ -6,6 +6,7 @@ import (
 	"one-api/common"
 	relaymodel "one-api/dto"
 	"one-api/model"
+	"one-api/setting"
 	"strings"
 )
 
@@ -64,21 +65,10 @@ 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
 	}
 

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 +13,9 @@ 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
+	}
 	adminInfo := make(map[string]interface{})
 	adminInfo["use_channel"] = ctx.GetStringSlice("use_channel")
 	other["admin_info"] = adminInfo

service/quota.go

@@ -182,9 +182,9 @@ 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.RecodeModelName)
+	audioRatio := common.GetAudioRatio(relayInfo.RecodeModelName)
+	audioCompletionRatio := common.GetAudioCompletionRatio(relayInfo.RecodeModelName)
 
 	quotaInfo := QuotaInfo{
 		InputDetails: TokenDetails{
@@ -195,7 +195,7 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 			TextTokens:  textOutTokens,
 			AudioTokens: audioOutTokens,
 		},
-		ModelName:  relayInfo.UpstreamModelName,
+		ModelName:  relayInfo.RecodeModelName,
 		UsePrice:   usePrice,
 		ModelRatio: modelRatio,
 		GroupRatio: groupRatio,
@@ -218,7 +218,7 @@ 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.RecodeModelName, preConsumedQuota))
 	} else {
 		quotaDelta := quota - preConsumedQuota
 		if quotaDelta != 0 {
@@ -231,7 +231,7 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 		model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
 	}
 
-	logModel := relayInfo.UpstreamModelName
+	logModel := relayInfo.RecodeModelName
 	if extraContent != "" {
 		logContent += ", " + extraContent
 	}

service/sensitive.go

@@ -60,17 +60,7 @@ func SensitiveWordContains(text string) (bool, []string) {
 		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
-	}
-	return false, nil
+	return AcSearch(checkText, setting.SensitiveWords, false)
 }
 
 // SensitiveWordReplace 敏感词替换，返回是否包含敏感词和替换后的文本
@@ -79,7 +69,7 @@ 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)

service/str.go

@@ -4,7 +4,6 @@ import (
 	"bytes"
 	"fmt"
 	goahocorasick "github.com/anknown/ahocorasick"
-	"one-api/setting"
 	"strings"
 )
 
@@ -57,9 +56,9 @@ func RemoveDuplicate(s []string) []string {
 	return result
 }
 
-func InitAc() *goahocorasick.Machine {
+func InitAc(words []string) *goahocorasick.Machine {
 	m := new(goahocorasick.Machine)
-	dict := readRunes()
+	dict := readRunes(words)
 	if err := m.Build(dict); err != nil {
 		fmt.Println(err)
 		return nil
@@ -67,10 +66,10 @@ func InitAc() *goahocorasick.Machine {
 	return m
 }
 
-func readRunes() [][]rune {
+func readRunes(words []string) [][]rune {
 	var dict [][]rune
 
-	for _, word := range setting.SensitiveWords {
+	for _, word := range words {
 		word = strings.ToLower(word)
 		l := bytes.TrimSpace([]byte(word))
 		dict = append(dict, bytes.Runes(l))
@@ -78,3 +77,25 @@ func readRunes() [][]rune {
 
 	return dict
 }
+
+func AcSearch(findText string, dict []string, stopImmediately bool) (bool, []string) {
+	if len(dict) == 0 {
+		return false, nil
+	}
+	if len(findText) == 0 {
+		return false, nil
+	}
+	m := InitAc(dict)
+	if m == nil {
+		return false, nil
+	}
+	hits := m.MultiPatternSearch([]rune(findText), stopImmediately)
+	if len(hits) > 0 {
+		words := make([]string, 0)
+		for _, hit := range hits {
+			words = append(words, string(hit.Word))
+		}
+		return true, words
+	}
+	return false, nil
+}

service/token_counter.go

@@ -4,7 +4,6 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"github.com/pkoukk/tiktoken-go"
 	"image"
 	"log"
 	"math"
@@ -14,6 +13,8 @@ import (
 	relaycommon "one-api/relay/common"
 	"strings"
 	"unicode/utf8"
+
+	"github.com/pkoukk/tiktoken-go"
 )
 
 // tokenEncoderMap won't grow after initialization
@@ -323,6 +324,12 @@ func CountTokenInput(input any, model string) (int, error) {
 			text += s
 		}
 		return CountTextToken(text, model)
+	case []interface{}:
+		text := ""
+		for _, item := range v {
+			text += fmt.Sprintf("%v", item)
+		}
+		return CountTextToken(text, model)
 	}
 	return CountTokenInput(fmt.Sprintf("%v", input), model)
 }

setting/chat.go

@@ -12,6 +12,9 @@ var Chats = []map[string]string{
 	{
 		"Lobe Chat 官方示例": "https://chat-preview.lobehub.com/?settings={\"keyVaults\":{\"openai\":{\"apiKey\":\"{key}\",\"baseURL\":\"{address}/v1\"}}}",
 	},
+	{
+		"AI as Workspace": "https://aiaw.app/set-provider?provider={\"type\":\"openai\",\"settings\":{\"apiKey\":\"{key}\",\"baseURL\":\"{address}/v1\",\"compatibility\":\"strict\"}}",
+	},
 	{
 		"AMA 问天": "ama://set-api-key?server={address}&key={key}",
 	},

setting/operation_setting.go

@@ -0,0 +1,30 @@
+package setting
+
+import "strings"
+
+var DemoSiteEnabled = false
+
+var AutomaticDisableKeywords = []string{
+	"Your credit balance is too low",
+	"This organization has been disabled.",
+	"You exceeded your current quota",
+	"Permission denied",
+	"The security token included in the request is invalid",
+	"Operation not allowed",
+	"Your account is not authorized",
+}
+
+func AutomaticDisableKeywordsToString() string {
+	return strings.Join(AutomaticDisableKeywords, "\n")
+}
+
+func AutomaticDisableKeywordsFromString(s string) {
+	AutomaticDisableKeywords = []string{}
+	ak := strings.Split(s, "\n")
+	for _, k := range ak {
+		k = strings.TrimSpace(k)
+		if k != "" {
+			AutomaticDisableKeywords = append(AutomaticDisableKeywords, k)
+		}
+	}
+}

web/src/components/ChannelsTable.js

@@ -44,7 +44,7 @@ function renderTimestamp(timestamp) {
 
 const ChannelsTable = () => {
   const { t } = useTranslation();
-  
+
   let type2label = undefined;
 
   const renderType = (type) => {
@@ -53,11 +53,11 @@ const ChannelsTable = () => {
       for (let i = 0; i < CHANNEL_OPTIONS.length; i++) {
         type2label[CHANNEL_OPTIONS[i].value] = CHANNEL_OPTIONS[i];
       }
-      type2label[0] = { value: 0, text: t('未知类型'), color: 'grey' };
+      type2label[0] = { value: 0, label: t('未知类型'), color: 'grey' };
     }
     return (
       <Tag size="large" color={type2label[type]?.color}>
-        {type2label[type]?.text}
+        {type2label[type]?.label}
       </Tag>
     );
   };
@@ -559,7 +559,7 @@ const ChannelsTable = () => {
       if (!enableTagMode) {
         channelDates.push(channels[i]);
       } else {
-        let tag = channels[i].tag?channels[i].tag:"";
+        let tag = channels[i].tag ? channels[i].tag : "";
         // find from channelTags
         let tagIndex = channelTags[tag];
         let tagChannelDates = undefined;
@@ -798,18 +798,57 @@ const ChannelsTable = () => {
     setSearching(false);
   };
 
+  const updateChannelProperty = (channelId, updateFn) => {
+    // Create a new copy of channels array
+    const newChannels = [...channels];
+    
+    // Find and update the correct channel
+    newChannels.forEach(channel => {
+      if (channel.children !== undefined) {
+        // If this is a tag group, search in its children
+        channel.children.forEach(child => {
+          if (child.id === channelId) {
+            updateFn(child);
+          }
+        });
+      } else if (channel.id === channelId) {
+        // Direct channel match
+        updateFn(channel);
+      }
+    });
+    
+    // Update state with new array to trigger re-render
+    setChannels(newChannels);
+  };
+
   const testChannel = async (record, model) => {
     const res = await API.get(`/api/channel/test/${record.id}?model=${model}`);
     const { success, message, time } = res.data;
     if (success) {
-      record.response_time = time * 1000;
-      record.test_time = Date.now() / 1000;
+      updateChannelProperty(record.id, (channel) => {
+        channel.response_time = time * 1000;
+        channel.test_time = Date.now() / 1000;
+      });
       showInfo(t('通道 ${name} 测试成功，耗时 ${time.toFixed(2)} 秒。').replace('${name}', record.name).replace('${time.toFixed(2)}', time.toFixed(2)));
     } else {
       showError(message);
     }
   };
 
+  const updateChannelBalance = async (record) => {
+    const res = await API.get(`/api/channel/update_balance/${record.id}/`);
+    const { success, message, balance } = res.data;
+    if (success) {
+      updateChannelProperty(record.id, (channel) => {
+        channel.balance = balance;
+        channel.balance_updated_time = Date.now() / 1000;
+      });
+      showInfo(t('通道 ${name} 余额更新成功！').replace('${name}', record.name));
+    } else {
+      showError(message);
+    }
+  };
+
   const testAllChannels = async () => {
     const res = await API.get(`/api/channel/test`);
     const { success, message } = res.data;
@@ -831,18 +870,6 @@ const ChannelsTable = () => {
     }
   };
 
-  const updateChannelBalance = async (record) => {
-    const res = await API.get(`/api/channel/update_balance/${record.id}/`);
-    const { success, message, balance } = res.data;
-    if (success) {
-      record.balance = balance;
-      record.balance_updated_time = Date.now() / 1000;
-      showInfo(t('通道 ${name} 余额更新成功！').replace('${name}', record.name));
-    } else {
-      showError(message);
-    }
-  };
-
   const updateAllChannelsBalance = async () => {
     setUpdatingBalance(true);
     const res = await API.get(`/api/channel/update_balance`);
@@ -1186,7 +1213,7 @@ const ChannelsTable = () => {
         </Space>
       </div>
       <div style={{ marginTop: 20 }}>
-      <Space>
+        <Space>
           <Typography.Text strong>{t('标签聚合模式')}</Typography.Text>
           <Switch
             checked={enableTagMode}
@@ -1199,14 +1226,14 @@ const ChannelsTable = () => {
             }}
           />
           <Button
-        disabled={!enableBatchDelete}
-        theme="light"
-        type="primary"
-        style={{ marginRight: 8 }}
-        onClick={() => setShowBatchSetTag(true)}
-      >
-        {t('批量设置标签')}
-      </Button>
+            disabled={!enableBatchDelete}
+            theme="light"
+            type="primary"
+            style={{ marginRight: 8 }}
+            onClick={() => setShowBatchSetTag(true)}
+          >
+            {t('批量设置标签')}
+          </Button>
         </Space>
 
       </div>

web/src/components/LogsTable.js

@@ -608,7 +608,12 @@ const LogsTable = () => {
           key: t('计费过程'),
           value: content,
         });
-
+        if (other?.reasoning_effort) {
+          expandDataLocal.push({
+            key: t('Reasoning Effort'),
+            value: other.reasoning_effort,
+          });
+        }
       }
       expandDatesLocal[logs[i].key] = expandDataLocal;
     }
@@ -841,7 +846,7 @@ const LogsTable = () => {
               t('第 {{start}} - {{end}} 条，共 {{total}} 条', {
                 start: page.currentStart,
                 end: page.currentEnd,
-                total: logs.length
+                total: logCount
               }),
             currentPage: activePage,
             pageSize: pageSize,

web/src/components/OperationSetting.js

@@ -58,6 +58,8 @@ const OperationSetting = () => {
     DefaultCollapseSidebar: false, // 默认折叠侧边栏
     RetryTimes: 0,
     Chats: "[]",
+    DemoSiteEnabled: false,
+    AutomaticDisableKeywords: '',
   });
 
   let [loading, setLoading] = useState(false);

web/src/constants/channel.constants.js

@@ -1,129 +1,112 @@
 export const CHANNEL_OPTIONS = [
-  { key: 1, text: 'OpenAI', value: 1, color: 'green', label: 'OpenAI' },
+  { value: 1, color: 'green', label: 'OpenAI' },
   {
-    key: 2,
-    text: 'Midjourney Proxy',
     value: 2,
     color: 'light-blue',
     label: 'Midjourney Proxy'
   },
   {
-    key: 5,
-    text: 'Midjourney Proxy Plus',
     value: 5,
     color: 'blue',
     label: 'Midjourney Proxy Plus'
   },
   {
-    key: 36,
-    text: 'Suno API',
     value: 36,
     color: 'purple',
     label: 'Suno API'
   },
-  { key: 4, text: 'Ollama', value: 4, color: 'grey', label: 'Ollama' },
+  { value: 4, color: 'grey', label: 'Ollama' },
   {
-    key: 14,
-    text: 'Anthropic Claude',
     value: 14,
     color: 'indigo',
     label: 'Anthropic Claude'
   },
   {
-    key: 33,
-    text: 'AWS Claude',
     value: 33,
     color: 'indigo',
     label: 'AWS Claude'
   },
-  { key: 41, text: 'Vertex AI', value: 41, color: 'blue', label: 'Vertex AI' },
+  { value: 41, color: 'blue', label: 'Vertex AI' },
   {
-    key: 3,
-    text: 'Azure OpenAI',
     value: 3,
     color: 'teal',
     label: 'Azure OpenAI'
   },
   {
-    key: 34,
-    text: 'Cohere',
     value: 34,
     color: 'purple',
     label: 'Cohere'
   },
-  { key: 39, text: 'Cloudflare', value: 39, color: 'grey', label: 'Cloudflare' },
-  { key: 43, text: 'DeepSeek', value: 43, color: 'blue', label: 'DeepSeek' },
+  { value: 39, color: 'grey', label: 'Cloudflare' },
+  { value: 43, color: 'blue', label: 'DeepSeek' },
   {
-    key: 15,
-    text: '百度文心千帆',
     value: 15,
     color: 'blue',
     label: '百度文心千帆'
   },
   {
-    key: 17,
-    text: '阿里通义千问',
+    value: 46,
+    color: 'blue',
+    label: '百度文心千帆V2'
+  },
+  {
     value: 17,
     color: 'orange',
     label: '阿里通义千问'
   },
   {
-    key: 18,
-    text: '讯飞星火认知',
     value: 18,
     color: 'blue',
     label: '讯飞星火认知'
   },
   {
-    key: 16,
-    text: '智谱 ChatGLM',
     value: 16,
     color: 'violet',
     label: '智谱 ChatGLM'
   },
   {
-    key: 26,
-    text: '智谱 GLM-4V',
     value: 26,
     color: 'purple',
     label: '智谱 GLM-4V'
   },
   {
-    key: 24,
-    text: 'Google Gemini',
     value: 24,
     color: 'orange',
     label: 'Google Gemini'
   },
   {
-    key: 11,
-    text: 'Google PaLM2',
     value: 11,
     color: 'orange',
     label: 'Google PaLM2'
   },
-  { key: 25, text: 'Moonshot', value: 25, color: 'green', label: 'Moonshot' },
-  { key: 19, text: '360 智脑', value: 19, color: 'blue', label: '360 智脑' },
-  { key: 23, text: '腾讯混元', value: 23, color: 'teal', label: '腾讯混元' },
-  { key: 31, text: '零一万物', value: 31, color: 'green', label: '零一万物' },
-  { key: 35, text: 'MiniMax', value: 35, color: 'green', label: 'MiniMax' },
-  { key: 37, text: 'Dify', value: 37, color: 'teal', label: 'Dify' },
-  { key: 38, text: 'Jina', value: 38, color: 'blue', label: 'Jina' },
-  { key: 40, text: 'SiliconCloud', value: 40, color: 'purple', label: 'SiliconCloud' },
-  { key: 42, text: 'Mistral AI', value: 42, color: 'blue', label: 'Mistral AI' },
-  { key: 8, text: '自定义渠道', value: 8, color: 'pink', label: '自定义渠道' },
   {
-    key: 22,
-    text: '知识库：FastGPT',
+    value: 45,
+    color: 'blue',
+    label: '火山方舟（豆包）'
+  },
+  { value: 25, color: 'green', label: 'Moonshot' },
+  { value: 19, color: 'blue', label: '360 智脑' },
+  { value: 23, color: 'teal', label: '腾讯混元' },
+  { value: 31, color: 'green', label: '零一万物' },
+  { value: 35, color: 'green', label: 'MiniMax' },
+  { value: 37, color: 'teal', label: 'Dify' },
+  { value: 38, color: 'blue', label: 'Jina' },
+  { value: 40, color: 'purple', label: 'SiliconCloud' },
+  { value: 42, color: 'blue', label: 'Mistral AI' },
+  { value: 8, color: 'pink', label: '自定义渠道' },
+  {
     value: 22,
     color: 'blue',
     label: '知识库：FastGPT'
   },
   {
-    key: 21,
-    text: '知识库：AI Proxy',
     value: 21,
     color: 'purple',
     label: '知识库：AI Proxy'
+  },
+  {
+    value: 44,
+    color: 'purple',
+    label: '嵌入模型：MokaAI M3E'
   }
 ];

web/src/i18n/locales/en.json

@@ -201,7 +201,7 @@
   "相关 API 显示令牌额度而非用户额度": "Related APIs show token quota instead of user quota",
   "保存通用设置": "Save General Settings",
   "监控设置": "Monitoring Settings",
-  "最长响应时间": "Maximum Response Time",
+  "测试所有渠道的最长响应时间": "Maximum response time for testing all channels",
   "单位秒": "Unit: seconds",
   "当运行通道全部测试时": "When running all channel tests",
   "超过此时间将自动禁用通道": "Channels exceeding this time will be automatically disabled",
@@ -498,8 +498,7 @@
   "请输入用户名": "Please enter username",
   "请输入显示名称": "Please enter display name",
   "请输入密码": "Please enter password",
-  "模型部署名称必须和模型名称保持一致": "The model deployment name must be consistent with the model name",
-  "，因为 One API 会把请求体中的 model": ", because One API will take the model in the request body",
+  "注意，模型部署名称必须和模型名称保持一致": "Note that the model deployment name must be consistent with the model name",
   "请输入 AZURE_OPENAI_ENDPOINT": "Please enter AZURE_OPENAI_ENDPOINT",
   "请输入自定义渠道的 Base URL": "Please enter the Base URL of the custom channel",
   "Homepage URL 填": "Fill in the Homepage URL",
@@ -1109,7 +1108,7 @@
   "如果你对接的是上游One API或者New API等转发项目，请使用OpenAI类型，不要使用此类型，除非你知道你在做什么。": "If you are connecting to upstream One API or New API forwarding projects, please use OpenAI type. Do not use this type unless you know what you are doing.",
   "完整的 Base URL，支持变量{model}": "Complete Base URL, supports variable {model}",
   "请输入完整的URL，例如：https://api.openai.com/v1/chat/completions": "Please enter complete URL, e.g.: https://api.openai.com/v1/chat/completions",
-  "此项可选，用于通过代理站来进行 API 调用": "Optional, used for API calls through proxy sites",
+  "此项可选，用于通过代理站来进行 API 调用，末尾不要带/v1和/": "Optional for API calls through proxy sites, do not end with /v1 and /",
   "私有部署地址": "Private Deployment Address",
   "请输入私有部署地址，格式为：https://fastgpt.run/api/openapi": "Please enter private deployment address, format: https://fastgpt.run/api/openapi",
   "注意非Chat API，请务必填写正确的API地址，否则可能导致无法使用": "Note: For non-Chat API, please make sure to enter the correct API address, otherwise it may not work",
@@ -1247,5 +1246,8 @@
   "请输入要设置的标签名称": "Please enter the tag name to be set",
   "请输入标签名称": "Please enter the tag name",
   "支持搜索用户的 ID、用户名、显示名称和邮箱地址": "Support searching for user ID, username, display name, and email address",
-  "已注销": "Logged out"
+  "已注销": "Logged out",
+  "自动禁用关键词": "Automatic disable keywords",
+  "一行一个，不区分大小写": "One line per keyword, not case-sensitive",
+  "当上游通道返回错误中包含这些关键词时（不区分大小写），自动禁用通道": "When the upstream channel returns an error containing these keywords (not case-sensitive), automatically disable the channel"
 }

web/src/pages/Channel/EditChannel.js

@@ -429,6 +429,7 @@ const EditChannel = (props) => {
       >
         <Spin spinning={loading}>
           <div style={{ marginTop: 10 }}>
+            
             <Typography.Text strong>{t('类型')}：</Typography.Text>
           </div>
           <Select
@@ -438,13 +439,38 @@ const EditChannel = (props) => {
             value={inputs.type}
             onChange={(value) => handleInputChange('type', value)}
             style={{ width: '50%' }}
+            filter
+            searchPosition='dropdown'
+            placeholder={t('请选择渠道类型')}
           />
+          {inputs.type === 40 && (
+            <div style={{ marginTop: 10 }}>
+              <Banner
+                type="info" 
+                description={
+                  <div>
+                    <Typography.Text strong>
+                      {t('邀请链接')}: 
+                    </Typography.Text>
+                    <Typography.Text 
+                      link
+                      underline 
+                      style={{marginLeft: 8}}
+                      onClick={() => window.open('https://cloud.siliconflow.cn/i/hij0YNTZ')}
+                    >
+                      https://cloud.siliconflow.cn/i/hij0YNTZ
+                    </Typography.Text>
+                  </div>
+                }
+              />
+            </div>
+          )}
           {inputs.type === 3 && (
             <>
               <div style={{ marginTop: 10 }}>
                 <Banner
                   type={'warning'}
-                  description={t('注意，模型部署名称必须和模型名称保持一致，因为 One API 会把请求体中的 model 参数替换为你的部署名称（模型名称中的点会被剔除）')}
+                  description={t('注意，模型部署名称必须和模型名称保持一致')}
                 ></Banner>
               </div>
               <div style={{ marginTop: 10 }}>
@@ -501,15 +527,28 @@ const EditChannel = (props) => {
               />
             </>
           )}
+          <div style={{ marginTop: 10 }}>
+            <Typography.Text strong>{t('名称')}：</Typography.Text>
+          </div>
+          <Input
+            required
+            name="name"
+            placeholder={t('请为渠道命名')}
+            onChange={(value) => {
+              handleInputChange('name', value);
+            }}
+            value={inputs.name}
+            autoComplete="new-password"
+          />
           {inputs.type !== 3 && inputs.type !== 8 && inputs.type !== 22 && inputs.type !== 36 && (
             <>
               <div style={{ marginTop: 10 }}>
-                <Typography.Text strong>{t('代理')}：</Typography.Text>
+                <Typography.Text strong>{t('BaseURL')}：</Typography.Text>
               </div>
               <Input
-                label={t('代理')}
+                label={t('BaseURL')}
                 name="base_url"
-                placeholder={t('此项可选，用于通过代理站来进行 API 调用')}
+                placeholder={t('此项可选，用于通过代理站来进行 API 调用，末尾不要带/v1和/')}
                 onChange={(value) => {
                   handleInputChange('base_url', value);
                 }}
@@ -518,6 +557,77 @@ const EditChannel = (props) => {
               />
             </>
           )}
+          <div style={{ marginTop: 10 }}>
+            <Typography.Text strong>{t('密钥')}：</Typography.Text>
+          </div>
+          {batch ? (
+            <TextArea
+              label={t('密钥')}
+              name="key"
+              required
+              placeholder={t('请输入密钥，一行一个')}
+              onChange={(value) => {
+                handleInputChange('key', value);
+              }}
+              value={inputs.key}
+              style={{ minHeight: 150, fontFamily: 'JetBrains Mono, Consolas' }}
+              autoComplete="new-password"
+            />
+          ) : (
+            <>
+              {inputs.type === 41 ? (
+                <TextArea
+                  label={t('鉴权json')}
+                  name="key"
+                  required
+                  placeholder={'{\n' +
+                    '  "type": "service_account",\n' +
+                    '  "project_id": "abc-bcd-123-456",\n' +
+                    '  "private_key_id": "123xxxxx456",\n' +
+                    '  "private_key": "-----BEGIN PRIVATE KEY-----xxxx\n' +
+                    '  "client_email": "xxx@developer.gserviceaccount.com",\n' +
+                    '  "client_id": "111222333",\n' +
+                    '  "auth_uri": "https://accounts.google.com/o/oauth2/auth",\n' +
+                    '  "token_uri": "https://oauth2.googleapis.com/token",\n' +
+                    '  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",\n' +
+                    '  "client_x509_cert_url": "https://xxxxx.gserviceaccount.com",\n' +
+                    '  "universe_domain": "googleapis.com"\n' +
+                    '}'}
+                  onChange={(value) => {
+                    handleInputChange('key', value);
+                  }}
+                  autosize={{ minRows: 10 }}
+                  value={inputs.key}
+                  autoComplete="new-password"
+                />
+              ) : (
+                <Input
+                  label={t('密钥')}
+                  name="key"
+                  required
+                  placeholder={t(type2secretPrompt(inputs.type))}
+                  onChange={(value) => {
+                    handleInputChange('key', value);
+                  }}
+                  value={inputs.key}
+                  autoComplete="new-password"
+                />
+              )}
+            </>
+          )}
+          {!isEdit && (
+            <div style={{ marginTop: 10, display: 'flex' }}>
+              <Space>
+                <Checkbox
+                  checked={batch}
+                  label={t('批量创建')}
+                  name="batch"
+                  onChange={() => setBatch(!batch)}
+                />
+                <Typography.Text strong>{t('批量创建')}</Typography.Text>
+              </Space>
+            </div>
+          )}
           {inputs.type === 22 && (
             <>
               <div style={{ marginTop: 10 }}>
@@ -552,19 +662,6 @@ const EditChannel = (props) => {
               />
             </>
           )}
-          <div style={{ marginTop: 10 }}>
-            <Typography.Text strong>{t('名称')}：</Typography.Text>
-          </div>
-          <Input
-            required
-            name="name"
-            placeholder={t('请为渠道命名')}
-            onChange={(value) => {
-              handleInputChange('name', value);
-            }}
-            value={inputs.name}
-            autoComplete="new-password"
-          />
           <div style={{ marginTop: 10 }}>
             <Typography.Text strong>{t('分组')}：</Typography.Text>
           </div>
@@ -640,7 +737,7 @@ const EditChannel = (props) => {
           {inputs.type === 21 && (
             <>
               <div style={{ marginTop: 10 }}>
-                <Typography.Text strong>��识库 ID：</Typography.Text>
+                <Typography.Text strong>知识库 ID：</Typography.Text>
               </div>
               <Input
                 label="知识库 ID"
@@ -769,76 +866,108 @@ const EditChannel = (props) => {
             {t('填入模板')}
           </Typography.Text>
           <div style={{ marginTop: 10 }}>
-            <Typography.Text strong>{t('密钥')}：</Typography.Text>
+            <Typography.Text strong>
+              {t('渠道标签')}
+            </Typography.Text>
           </div>
-          {batch ? (
+          <Input
+            label={t('渠道标签')}
+            name="tag"
+            placeholder={t('渠道标签')}
+            onChange={(value) => {
+              handleInputChange('tag', value);
+            }}
+            value={inputs.tag}
+            autoComplete="new-password"
+          />
+          <div style={{ marginTop: 10 }}>
+            <Typography.Text strong>
+              {t('渠道优先级')}
+            </Typography.Text>
+          </div>
+          <Input
+            label={t('渠道优先级')}
+            name="priority"
+            placeholder={t('渠道优先级')}
+            onChange={(value) => {
+              const number = parseInt(value);
+              if (isNaN(number)) {
+                handleInputChange('priority', value);
+              } else {
+                handleInputChange('priority', number);
+              }
+            }}
+            value={inputs.priority}
+            autoComplete="new-password"
+          />
+          <div style={{ marginTop: 10 }}>
+            <Typography.Text strong>
+              {t('渠道权重')}
+            </Typography.Text>
+          </div>
+          <Input
+            label={t('渠道权重')}
+            name="weight"
+            placeholder={t('渠道权重')}
+            onChange={(value) => {
+              const number = parseInt(value);
+              if (isNaN(number)) {
+                handleInputChange('weight', value);
+              } else {
+                handleInputChange('weight', number);
+              }
+            }}
+            value={inputs.weight}
+            autoComplete="new-password"
+          />
+          <>
+            <div style={{ marginTop: 10 }}>
+              <Typography.Text strong>
+                {t('渠道额外设置')}：
+              </Typography.Text>
+            </div>
             <TextArea
-              label={t('密钥')}
-              name="key"
-              required
-              placeholder={t('请输入密钥，一行一个')}
+              placeholder={t('此项可选，用于配置渠道特定设置，为一个 JSON 字符串，例如：') + '\n{\n  "force_format": true\n}'}
+              name="setting"
               onChange={(value) => {
-                handleInputChange('key', value);
+                handleInputChange('setting', value);
               }}
-              value={inputs.key}
-              style={{ minHeight: 150, fontFamily: 'JetBrains Mono, Consolas' }}
+              autosize
+              value={inputs.setting}
               autoComplete="new-password"
             />
-          ) : (
-            <>
-              {inputs.type === 41 ? (
-                <TextArea
-                  label={t('鉴权json')}
-                  name="key"
-                  required
-                  placeholder={'{\n' +
-                    '  "type": "service_account",\n' +
-                    '  "project_id": "abc-bcd-123-456",\n' +
-                    '  "private_key_id": "123xxxxx456",\n' +
-                    '  "private_key": "-----BEGIN PRIVATE KEY-----xxxx\n' +
-                    '  "client_email": "xxx@developer.gserviceaccount.com",\n' +
-                    '  "client_id": "111222333",\n' +
-                    '  "auth_uri": "https://accounts.google.com/o/oauth2/auth",\n' +
-                    '  "token_uri": "https://oauth2.googleapis.com/token",\n' +
-                    '  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",\n' +
-                    '  "client_x509_cert_url": "https://xxxxx.gserviceaccount.com",\n' +
-                    '  "universe_domain": "googleapis.com"\n' +
-                    '}'}
-                  onChange={(value) => {
-                    handleInputChange('key', value);
-                  }}
-                  autosize={{ minRows: 10 }}
-                  value={inputs.key}
-                  autoComplete="new-password"
-                />
-              ) : (
-                <Input
-                  label={t('密钥')}
-                  name="key"
-                  required
-                  placeholder={t(type2secretPrompt(inputs.type))}
-                  onChange={(value) => {
-                    handleInputChange('key', value);
-                  }}
-                  value={inputs.key}
-                  autoComplete="new-password"
-                />
-              )}
-            </>
-          )}
-          {!isEdit && (
-            <div style={{ marginTop: 10, display: 'flex' }}>
-              <Space>
-                <Checkbox
-                  checked={batch}
-                  label={t('批量创建')}
-                  name="batch"
-                  onChange={() => setBatch(!batch)}
-                />
-                <Typography.Text strong>{t('批量创建')}</Typography.Text>
-              </Space>
-            </div>
-          )}
+            <Space>
+              <Typography.Text
+                style={{
+                  color: 'rgba(var(--semi-blue-5), 1)',
+                  userSelect: 'none',
+                  cursor: 'pointer'
+                }}
+                onClick={() => {
+                  handleInputChange(
+                    'setting',
+                    JSON.stringify({
+                      force_format: true
+                    }, null, 2)
+                  );
+                }}
+              >
+                {t('填入模板')}
+              </Typography.Text>
+              <Typography.Text
+                style={{
+                  color: 'rgba(var(--semi-blue-5), 1)',
+                  userSelect: 'none',
+                  cursor: 'pointer'
+                }}
+                onClick={() => {
+                  window.open('https://github.com/Calcium-Ion/new-api/blob/main/docs/channel/other_setting.md');
+                }}
+              >
+                {t('设置说明')}
+              </Typography.Text>
+            </Space>
+          </>
           {inputs.type === 1 && (
             <>
               <div style={{ marginTop: 10 }}>
@@ -911,97 +1040,6 @@ const EditChannel = (props) => {
           >
             {t('填入模板')}
           </Typography.Text>
-          <div style={{ marginTop: 10 }}>
-            <Typography.Text strong>
-              {t('渠道标签')}
-            </Typography.Text>
-          </div>
-          <Input
-            label={t('渠道标签')}
-            name="tag"
-            placeholder={t('渠道标签')}
-            onChange={(value) => {
-              handleInputChange('tag', value);
-            }}
-            value={inputs.tag}
-            autoComplete="new-password"
-          />
-          <div style={{ marginTop: 10 }}>
-            <Typography.Text strong>
-              {t('渠道优先级')}
-            </Typography.Text>
-          </div>
-          <Input
-            label={t('渠道优先级')}
-            name="priority"
-            placeholder={t('渠道优先级')}
-            onChange={(value) => {
-              const number = parseInt(value);
-              if (isNaN(number)) {
-                handleInputChange('priority', value);
-              } else {
-                handleInputChange('priority', number);
-              }
-            }}
-            value={inputs.priority}
-            autoComplete="new-password"
-          />
-          <div style={{ marginTop: 10 }}>
-            <Typography.Text strong>
-              {t('渠道权重')}
-            </Typography.Text>
-          </div>
-          <Input
-            label={t('渠道权重')}
-            name="weight"
-            placeholder={t('渠道权重')}
-            onChange={(value) => {
-              const number = parseInt(value);
-              if (isNaN(number)) {
-                handleInputChange('weight', value);
-              } else {
-                handleInputChange('weight', number);
-              }
-            }}
-            value={inputs.weight}
-            autoComplete="new-password"
-          />
-          {inputs.type === 8 && (
-          <>
-            <div style={{ marginTop: 10 }}>
-              <Typography.Text strong>
-                {t('渠道额外设置')}：
-              </Typography.Text>
-            </div>
-            <TextArea
-              placeholder={t('此项可选，用于配置渠道特定设置，为一个 JSON 字符串，例如：') + '\n{\n  "force_format": true\n}'}
-              name="setting"
-              onChange={(value) => {
-                handleInputChange('setting', value);
-              }}
-              autosize
-              value={inputs.setting}
-              autoComplete="new-password"
-            />
-            <Typography.Text
-              style={{
-                color: 'rgba(var(--semi-blue-5), 1)',
-                userSelect: 'none',
-                cursor: 'pointer'
-              }}
-              onClick={() => {
-                handleInputChange(
-                  'setting',
-                  JSON.stringify({
-                    force_format: true
-                  }, null, 2)
-                );
-              }}
-            >
-              {t('填入模板')}
-              </Typography.Text>
-            </>
-          )}
         </Spin>
       </SideSheet>
     </>

web/src/pages/Playground/Playground.js

@@ -157,20 +157,17 @@ const Playground = () => {
       payload: JSON.stringify(payload),
     });
     source.addEventListener("message", (e) => {
-      if (e.data !== "[DONE]") {
-        let payload = JSON.parse(e.data);
-        // console.log("Payload: ", payload);
-        if (payload.choices.length === 0) {
-          source.close();
-          completeMessage();
-        } else {
-          let text = payload.choices[0].delta.content;
-          if (text) {
-            generateMockResponse(text);
-          }
-        }
-      } else {
+      // 只有收到 [DONE] 时才结束
+      if (e.data === "[DONE]") {
+        source.close();
         completeMessage();
+        return;
+      }
+
+      let payload = JSON.parse(e.data);
+      // 检查是否有 delta content
+      if (payload.choices?.[0]?.delta?.content) {
+        generateMockResponse(payload.choices[0].delta.content);
       }
     });
 

web/src/pages/Setting/Operation/SettingsGeneral.js

@@ -21,6 +21,7 @@ export default function GeneralSettings(props) {
     DisplayInCurrencyEnabled: false,
     DisplayTokenStatEnabled: false,
     DefaultCollapseSidebar: false,
+    DemoSiteEnabled: false,
   });
   const refForm = useRef();
   const [inputsRow, setInputsRow] = useState(inputs);
@@ -188,6 +189,23 @@ export default function GeneralSettings(props) {
                 />
               </Col>
             </Row>
+            <Row>
+              <Col span={8}>
+                <Form.Switch
+                  field={'DemoSiteEnabled'}
+                  label={t('演示站点模式')}
+                  size='default'
+                  checkedText='｜'
+                  uncheckedText='〇'
+                  onChange={(value) =>
+                    setInputs({
+                      ...inputs,
+                      DemoSiteEnabled: value
+                    })
+                  }
+                />
+              </Col>
+            </Row>
             <Row>
               <Button size='default' onClick={onSubmit}>
                 {t('保存通用设置')}

web/src/pages/Setting/Operation/SettingsMonitoring.js

@@ -5,7 +5,7 @@ import {
   API,
   showError,
   showSuccess,
-  showWarning,
+  showWarning, verifyJSON
 } from '../../../helpers';
 import { useTranslation } from 'react-i18next';
 
@@ -17,6 +17,7 @@ export default function SettingsMonitoring(props) {
     QuotaRemindThreshold: '',
     AutomaticDisableChannelEnabled: false,
     AutomaticEnableChannelEnabled: false,
+    AutomaticDisableKeywords: '',
   });
   const refForm = useRef();
   const [inputsRow, setInputsRow] = useState(inputs);
@@ -79,7 +80,7 @@ export default function SettingsMonitoring(props) {
             <Row gutter={16}>
               <Col span={8}>
                 <Form.InputNumber
-                  label={t('最长响应时间')}
+                  label={t('测试所有渠道的最长响应时间')}
                   step={1}
                   min={0}
                   suffix={t('秒')}
@@ -144,6 +145,18 @@ export default function SettingsMonitoring(props) {
                 />
               </Col>
             </Row>
+            <Row gutter={16}>
+              <Col span={16}>
+                <Form.TextArea
+                  label={t('自动禁用关键词')}
+                  placeholder={t('一行一个，不区分大小写')}
+                  extraText={t('当上游通道返回错误中包含这些关键词时（不区分大小写），自动禁用通道')}
+                  field={'AutomaticDisableKeywords'}
+                  autosize={{ minRows: 6, maxRows: 12 }}
+                  onChange={(value) => setInputs({ ...inputs, AutomaticDisableKeywords: value })}
+                />
+              </Col>
+            </Row>
             <Row>
               <Button size='default' onClick={onSubmit}>
                 {t('保存监控设置')}