feat: support stream_options

fix testAllChannels nil pointer panic

Midjourney.md

@@ -2,6 +2,21 @@
 
 **简介**:Midjourney Proxy API文档
 
+## 接口列表
+支持的接口如下：
++ [x] /mj/submit/imagine
++ [x] /mj/submit/change
++ [x] /mj/submit/blend
++ [x] /mj/submit/describe
++ [x] /mj/image/{id} （通过此接口获取图片，**请必须在系统设置中填写服务器地址！！**）
++ [x] /mj/task/{id}/fetch （此接口返回的图片地址为经过One API转发的地址）
++ [x] /task/list-by-condition
++ [x] /mj/submit/action （仅midjourney-proxy-plus支持，下同）
++ [x] /mj/submit/modal
++ [x] /mj/submit/shorten
++ [x] /mj/task/{id}/image-seed
++ [x] /mj/insight-face/swap （InsightFace）
+
 ## 模型列表
 
 ### midjourney-proxy支持

README.md

@@ -5,8 +5,6 @@
 > 本项目为开源项目，在[One API](https://github.com/songquanpeng/one-api)的基础上进行二次开发，感谢原作者的无私奉献。 
 > 使用者必须在遵循 OpenAI 的[使用条款](https://openai.com/policies/terms-of-use)以及**法律法规**的情况下使用，不得用于非法用途。
 
-
-> [!WARNING]
 > 本项目为个人学习使用，不保证稳定性，且不提供任何技术支持，使用者必须在遵循 OpenAI 的使用条款以及法律法规的情况下使用，不得用于非法用途。  
 > 根据[《生成式人工智能服务管理暂行办法》](http://www.cac.gov.cn/2023-07/13/c_1690898327029107.htm)的要求，请勿对中国地区公众提供一切未经备案的生成式人工智能服务。
 
@@ -18,19 +16,7 @@
 此分叉版本的主要变更如下：
 
 1. 全新的UI界面（部分界面还待更新）
-2. 添加[Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口的支持，[对接文档](Midjourney.md)，支持的接口如下：
-   + [x] /mj/submit/imagine
-   + [x] /mj/submit/change
-   + [x] /mj/submit/blend
-   + [x] /mj/submit/describe
-   + [x] /mj/image/{id} （通过此接口获取图片，**请必须在系统设置中填写服务器地址！！**）
-   + [x] /mj/task/{id}/fetch （此接口返回的图片地址为经过One API转发的地址）
-   + [x] /task/list-by-condition
-   + [x] /mj/submit/action （仅midjourney-proxy-plus支持，下同）
-   + [x] /mj/submit/modal
-   + [x] /mj/submit/shorten
-   + [x] /mj/task/{id}/image-seed
-   + [x] /mj/insight-face/swap （InsightFace）
+2. 添加[Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口的支持，[对接文档](Midjourney.md)
 3. 支持在线充值功能，可在系统设置中设置，当前支持的支付接口：
    + [x] 易支付
 4. 支持用key查询使用额度:
@@ -47,16 +33,21 @@
     2. 对[@Botfather](https://t.me/botfather)输入指令/setdomain
     3. 选择你的bot，然后输入http(s)://你的网站地址/login
     4. Telegram Bot 名称是bot username 去掉@后的字符串
+13. 添加 [Suno API](https://github.com/Suno-API/Suno-API)接口的支持，[对接文档](Suno.md)
+14. 支持Rerank模型，目前仅兼容Cohere和Jina，可接入Dify，[对接文档](Rerank.md)
 
 ## 模型支持
 此版本额外支持以下模型：
 1. 第三方模型 **gps** （gpt-4-gizmo-*）
 2. 智谱glm-4v，glm-4v识图
-3. Anthropic Claude 3 (claude-3-opus-20240229, claude-3-sonnet-20240229)
+3. Anthropic Claude 3
 4. [Ollama](https://github.com/ollama/ollama?tab=readme-ov-file)，添加渠道时，密钥可以随便填写，默认的请求地址是[http://localhost:11434](http://localhost:11434)，如果需要修改请在渠道中修改
 5. [Midjourney-Proxy(Plus)](https://github.com/novicezk/midjourney-proxy)接口，[对接文档](Midjourney.md)
 6. [零一万物](https://platform.lingyiwanwu.com/)
 7. 自定义渠道，支持填入完整调用地址
+8. [Suno API](https://github.com/Suno-API/Suno-API) 接口，[对接文档](Suno.md)
+9. Rerank模型，目前支持[Cohere](https://cohere.ai/)和[Jina](https://jina.ai/)，[对接文档](Rerank.md)
+10. Dify
 
 您可以在渠道中添加自定义模型gpt-4-gizmo-*，此模型并非OpenAI官方模型，而是第三方模型，使用官方key无法调用。
 
@@ -79,8 +70,14 @@
 ```
 可以实现400错误转为500错误，从而重试
 
-
+## 比原版One API多出的配置
+- `STREAMING_TIMEOUT`：设置流式一次回复的超时时间，默认为 30 秒
+- `DIFY_DEBUG`：设置 Dify 渠道是否输出工作流和节点信息到客户端，默认为 `true`， 可选值为 `true` 和 `false`
+- `FORCE_STREAM_OPTION`：覆盖客户端stream_options参数，请求上游返回流模式usage，目前仅支持 `OpenAI` 渠道类型
 ## 部署
+### 部署要求
+- 本地数据库（默认）：SQLite（Docker 部署默认使用 SQLite，必须挂载 `/data` 目录到宿主机）
+- 远程数据库：MySQL 版本 >= 5.7.8，PgSQL 版本 >= 9.6
 ### 基于 Docker 进行部署
 ```shell
 # 使用 SQLite 的部署命令：
@@ -105,6 +102,9 @@ docker run --name new-api -d --restart always -p 3000:3000 -e SQL_DSN="root:1234
 ## Midjourney接口设置文档
 [对接文档](Midjourney.md)
 
+## Suno接口设置文档
+[对接文档](Suno.md)
+
 ## 交流群
 <img src="https://github.com/Calcium-Ion/new-api/assets/61247483/de536a8a-0161-47a7-a0a2-66ef6de81266" width="300">
 

Rerank.md

@@ -0,0 +1,62 @@
+# Rerank API文档
+
+**简介**:Rerank API文档
+
+## 接入Dify
+模型供应商选择Jina，按要求填写模型信息即可接入Dify。
+
+## 请求方式
+
+Post: /v1/rerank
+
+Request:
+
+```json
+{
+  "model": "rerank-multilingual-v3.0",
+  "query": "What is the capital of the United States?",
+  "top_n": 3,
+  "documents": [
+    "Carson City is the capital city of the American state of Nevada.",
+    "The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean. Its capital is Saipan.",
+    "Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district.",
+    "Capitalization or capitalisation in English grammar is the use of a capital letter at the start of a word. English usage varies from capitalization in other languages.",
+    "Capital punishment (the death penalty) has existed in the United States since beforethe United States was a country. As of 2017, capital punishment is legal in 30 of the 50 states."
+  ]
+}
+```
+
+Response:
+
+```json
+{
+  "results": [
+    {
+      "document": {
+        "text": "Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district."
+      },
+      "index": 2,
+      "relevance_score": 0.9999702
+    },
+    {
+      "document": {
+        "text": "Carson City is the capital city of the American state of Nevada."
+      },
+      "index": 0,
+      "relevance_score": 0.67800725
+    },
+    {
+      "document": {
+        "text": "Capitalization or capitalisation in English grammar is the use of a capital letter at the start of a word. English usage varies from capitalization in other languages."
+      },
+      "index": 3,
+      "relevance_score": 0.02800752
+    }
+  ],
+  "usage": {
+    "prompt_tokens": 158,
+    "completion_tokens": 0,
+    "total_tokens": 158
+  }
+}
+```

Suno.md

@@ -0,0 +1,44 @@
+# Suno API文档
+
+**简介**:Suno API文档
+
+## 接口列表
+支持的接口如下：
++ [x] /suno/submit/music
++ [x] /suno/submit/lyrics
++ [x] /suno/fetch
++ [x] /suno/fetch/:id
+
+## 模型列表
+
+### Suno API支持
+
+- suno_music (自定义模式、灵感模式、续写)
+- suno_lyrics (生成歌词)
+
+
+## 模型价格设置（在设置-运营设置-模型固定价格设置中设置）
+```json
+{
+  "suno_music": 0.3,
+  "suno_lyrics": 0.01
+}
+```
+
+## 渠道设置
+
+### 对接 Suno API
+
+1.
+部署 Suno API，并配置好suno账号等（强烈建议设置密钥），[项目地址](https://github.com/Suno-API/Suno-API)
+
+2. 在渠道管理中添加渠道，渠道类型选择**Suno API**
+   ，模型请参考上方模型列表
+3. **代理**填写 Suno API 部署的地址，例如：http://localhost:8080
+4. 密钥填写 Suno API 的密钥，如果没有设置密钥，可以随便填
+
+### 对接上游new api
+
+1. 在渠道管理中添加渠道，渠道类型选择**Suno API**，或任意类型，只需模型包含上方模型列表的模型
+2. **代理**填写上游new api的地址，例如：http://localhost:3000
+3. 密钥填写上游new api的密钥

common/constants.go

@@ -21,6 +21,7 @@ var QuotaPerUnit = 500 * 1000.0 // $0.002 / 1K tokens
 var DisplayInCurrencyEnabled = true
 var DisplayTokenStatEnabled = true
 var DrawingEnabled = true
+var TaskEnabled = true
 var DataExportEnabled = true
 var DataExportInterval = 5         // unit: minute
 var DataExportDefaultTime = "hour" // unit: minute
@@ -102,14 +103,14 @@ var IsMasterNode = os.Getenv("NODE_TYPE") != "slave"
 var requestInterval, _ = strconv.Atoi(os.Getenv("POLLING_INTERVAL"))
 var RequestInterval = time.Duration(requestInterval) * time.Second
 
-var SyncFrequency = GetOrDefault("SYNC_FREQUENCY", 60) // unit is second
+var SyncFrequency = GetEnvOrDefault("SYNC_FREQUENCY", 60) // unit is second
 
 var BatchUpdateEnabled = false
-var BatchUpdateInterval = GetOrDefault("BATCH_UPDATE_INTERVAL", 5)
+var BatchUpdateInterval = GetEnvOrDefault("BATCH_UPDATE_INTERVAL", 5)
 
-var RelayTimeout = GetOrDefault("RELAY_TIMEOUT", 0) // unit is second
+var RelayTimeout = GetEnvOrDefault("RELAY_TIMEOUT", 0) // unit is second
 
-var GeminiSafetySetting = GetOrDefaultString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
+var GeminiSafetySetting = GetEnvOrDefaultString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
 
 const (
 	RequestIdKey = "X-Oneapi-Request-Id"
@@ -132,10 +133,10 @@ var (
 // All duration's unit is seconds
 // Shouldn't larger then RateLimitKeyExpirationDuration
 var (
-	GlobalApiRateLimitNum            = GetOrDefault("GLOBAL_API_RATE_LIMIT", 180)
+	GlobalApiRateLimitNum            = GetEnvOrDefault("GLOBAL_API_RATE_LIMIT", 180)
 	GlobalApiRateLimitDuration int64 = 3 * 60
 
-	GlobalWebRateLimitNum            = GetOrDefault("GLOBAL_WEB_RATE_LIMIT", 60)
+	GlobalWebRateLimitNum            = GetEnvOrDefault("GLOBAL_WEB_RATE_LIMIT", 60)
 	GlobalWebRateLimitDuration int64 = 3 * 60
 
 	UploadRateLimitNum            = 10
@@ -208,8 +209,12 @@ const (
 	ChannelTypeAws            = 33
 	ChannelTypeCohere         = 34
 	ChannelTypeMiniMax        = 35
+	ChannelTypeSunoAPI        = 36
+	ChannelTypeDify           = 37
+	ChannelTypeJina           = 38
 
 	ChannelTypeDummy // this one is only for count, do not add any channel after this
+
 )
 
 var ChannelBaseURLs = []string{
@@ -249,4 +254,7 @@ var ChannelBaseURLs = []string{
 	"",                                          //33
 	"https://api.cohere.ai",                     //34
 	"https://api.minimax.chat",                  //35
+	"",                                          //36
+	"",                                          //37
+	"https://api.jina.ai",                       //38
 }

common/env.go

@@ -0,0 +1,38 @@
+package common
+
+import (
+	"fmt"
+	"os"
+	"strconv"
+)
+
+func GetEnvOrDefault(env string, defaultValue int) int {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	num, err := strconv.Atoi(os.Getenv(env))
+	if err != nil {
+		SysError(fmt.Sprintf("failed to parse %s: %s, using default value: %d", env, err.Error(), defaultValue))
+		return defaultValue
+	}
+	return num
+}
+
+func GetEnvOrDefaultString(env string, defaultValue string) string {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	return os.Getenv(env)
+}
+
+func GetEnvOrDefaultBool(env string, defaultValue bool) bool {
+	if env == "" || os.Getenv(env) == "" {
+		return defaultValue
+	}
+	b, err := strconv.ParseBool(os.Getenv(env))
+	if err != nil {
+		SysError(fmt.Sprintf("failed to parse %s: %s, using default value: %t", env, err.Error(), defaultValue))
+		return defaultValue
+	}
+	return b
+}

common/go-channel.go

@@ -3,6 +3,7 @@ package common
 import (
 	"fmt"
 	"runtime/debug"
+	"time"
 )
 
 func SafeGoroutine(f func()) {
@@ -45,3 +46,21 @@ func SafeSendString(ch chan string, value string) (closed bool) {
 	// If the code reaches here, then the channel was not closed.
 	return false
 }
+
+// SafeSendStringTimeout send, return true, else return false
+func SafeSendStringTimeout(ch chan string, value string, timeout int) (closed bool) {
+	defer func() {
+		// Recover from panic if one occured. A panic would mean the channel was closed.
+		if recover() != nil {
+			closed = false
+		}
+	}()
+
+	// This will panic if the channel is closed.
+	select {
+	case ch <- value:
+		return true
+	case <-time.After(time.Duration(timeout) * time.Second):
+		return false
+	}
+}

common/group-ratio.go

@@ -1,6 +1,8 @@
 package common
 
-import "encoding/json"
+import (
+	"encoding/json"
+)
 
 var GroupRatio = map[string]float64{
 	"default": 1,

common/model-ratio.go

@@ -72,24 +72,29 @@ var defaultModelRatio = map[string]float64{
 	"text-search-ada-doc-001":        10,
 	"text-moderation-stable":         0.1,
 	"text-moderation-latest":         0.1,
-	"claude-instant-1":               0.4,    // $0.8 / 1M tokens
-	"claude-2.0":                     4,      // $8 / 1M tokens
-	"claude-2.1":                     4,      // $8 / 1M tokens
-	"claude-3-haiku-20240307":        0.125,  // $0.25 / 1M tokens
-	"claude-3-sonnet-20240229":       1.5,    // $3 / 1M tokens
-	"claude-3-opus-20240229":         7.5,    // $15 / 1M tokens
-	"ERNIE-Bot":                      0.8572, // ￥0.012 / 1k tokens //renamed to ERNIE-3.5-8K
-	"ERNIE-Bot-turbo":                0.5715, // ￥0.008 / 1k tokens //renamed to ERNIE-Lite-8K
-	"ERNIE-Bot-4":                    8.572,  // ￥0.12 / 1k tokens //renamed to ERNIE-4.0-8K
-	"ERNIE-4.0-8K":                   8.572,  // ￥0.12 / 1k tokens
-	"ERNIE-3.5-8K":                   0.8572, // ￥0.012 / 1k tokens
-	"ERNIE-Speed-8K":                 0.2858, // ￥0.004 / 1k tokens
-	"ERNIE-Speed-128K":               0.2858, // ￥0.004 / 1k tokens
-	"ERNIE-Lite-8K":                  0.2143, // ￥0.003 / 1k tokens
-	"ERNIE-Tiny-8K":                  0.0715, // ￥0.001 / 1k tokens
-	"ERNIE-Character-8K":             0.2858, // ￥0.004 / 1k tokens
-	"ERNIE-Functions-8K":             0.2858, // ￥0.004 / 1k tokens
-	"Embedding-V1":                   0.1429, // ￥0.002 / 1k tokens
+	"claude-instant-1":               0.4,   // $0.8 / 1M tokens
+	"claude-2.0":                     4,     // $8 / 1M tokens
+	"claude-2.1":                     4,     // $8 / 1M tokens
+	"claude-3-haiku-20240307":        0.125, // $0.25 / 1M tokens
+	"claude-3-sonnet-20240229":       1.5,   // $3 / 1M tokens
+	"claude-3-5-sonnet-20240620":     1.5,
+	"claude-3-opus-20240229":         7.5, // $15 / 1M tokens
+	"ERNIE-4.0-8K":                   0.120 * RMB,
+	"ERNIE-3.5-8K":                   0.012 * RMB,
+	"ERNIE-3.5-8K-0205":              0.024 * RMB,
+	"ERNIE-3.5-8K-1222":              0.012 * RMB,
+	"ERNIE-Bot-8K":                   0.024 * RMB,
+	"ERNIE-3.5-4K-0205":              0.012 * RMB,
+	"ERNIE-Speed-8K":                 0.004 * RMB,
+	"ERNIE-Speed-128K":               0.004 * RMB,
+	"ERNIE-Lite-8K-0922":             0.008 * RMB,
+	"ERNIE-Lite-8K-0308":             0.003 * RMB,
+	"ERNIE-Tiny-8K":                  0.001 * RMB,
+	"BLOOMZ-7B":                      0.004 * RMB,
+	"Embedding-V1":                   0.002 * RMB,
+	"bge-large-zh":                   0.002 * RMB,
+	"bge-large-en":                   0.002 * RMB,
+	"tao-8k":                         0.002 * RMB,
 	"PaLM-2":                         1,
 	"gemini-pro":                     1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
 	"gemini-pro-vision":              1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
@@ -114,6 +119,7 @@ var defaultModelRatio = map[string]float64{
 	"SparkDesk-v2.1":                 1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v3.1":                 1.2858, // ￥0.018 / 1k tokens
 	"SparkDesk-v3.5":                 1.2858, // ￥0.018 / 1k tokens
+	"SparkDesk-v4.0":                 1.2858,
 	"360GPT_S2_V9":                   0.8572, // ¥0.012 / 1k tokens
 	"360gpt-turbo":                   0.0858, // ¥0.0012 / 1k tokens
 	"360gpt-turbo-responsibility-8k": 0.8572, // ¥0.012 / 1k tokens

common/topup-ratio.go

@@ -1,6 +1,8 @@
 package common
 
-import "encoding/json"
+import (
+	"encoding/json"
+)
 
 var TopupGroupRatio = map[string]float64{
 	"default": 1,

common/utils.go

@@ -8,7 +8,6 @@ import (
 	"log"
 	"math/rand"
 	"net"
-	"os"
 	"os/exec"
 	"runtime"
 	"strconv"
@@ -191,25 +190,6 @@ func Max(a int, b int) int {
 	}
 }
 
-func GetOrDefault(env string, defaultValue int) int {
-	if env == "" || os.Getenv(env) == "" {
-		return defaultValue
-	}
-	num, err := strconv.Atoi(os.Getenv(env))
-	if err != nil {
-		SysError(fmt.Sprintf("failed to parse %s: %s, using default value: %d", env, err.Error(), defaultValue))
-		return defaultValue
-	}
-	return num
-}
-
-func GetOrDefaultString(env string, defaultValue string) string {
-	if env == "" || os.Getenv(env) == "" {
-		return defaultValue
-	}
-	return os.Getenv(env)
-}
-
 func MessageWithRequestId(message string, id string) string {
 	return fmt.Sprintf("%s (request id: %s)", message, id)
 }

constant/env.go

@@ -0,0 +1,11 @@
+package constant
+
+import (
+	"one-api/common"
+)
+
+var StreamingTimeout = common.GetEnvOrDefault("STREAMING_TIMEOUT", 30)
+var DifyDebug = common.GetEnvOrDefaultBool("DIFY_DEBUG", true)
+
+// ForceStreamOption 覆盖请求参数，强制返回usage信息
+var ForceStreamOption = common.GetEnvOrDefaultBool("FORCE_STREAM_OPTION", true)

constant/task.go

@@ -0,0 +1,18 @@
+package constant
+
+type TaskPlatform string
+
+const (
+	TaskPlatformSuno       TaskPlatform = "suno"
+	TaskPlatformMidjourney              = "mj"
+)
+
+const (
+	SunoActionMusic  = "MUSIC"
+	SunoActionLyrics = "LYRICS"
+)
+
+var SunoModel2Action = map[string]string{
+	"suno_music":  SunoActionMusic,
+	"suno_lyrics": SunoActionLyrics,
+}

controller/channel-test.go

@@ -6,6 +6,7 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"math"
 	"net/http"
 	"net/http/httptest"
 	"net/url"
@@ -24,9 +25,13 @@ import (
 )
 
 func testChannel(channel *model.Channel, testModel string) (err error, openaiErr *dto.OpenAIError) {
+	tik := time.Now()
 	if channel.Type == common.ChannelTypeMidjourney {
 		return errors.New("midjourney channel test is not supported"), nil
 	}
+	if channel.Type == common.ChannelTypeSunoAPI {
+		return errors.New("suno channel test is not supported"), nil
+	}
 	w := httptest.NewRecorder()
 	c, _ := gin.CreateTestContext(w)
 	c.Request = &http.Request{
@@ -62,7 +67,11 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
 		if channel.TestModel != nil && *channel.TestModel != "" {
 			testModel = *channel.TestModel
 		} else {
-			testModel = adaptor.GetModelList()[0]
+			if len(adaptor.GetModelList()) > 0 {
+				testModel = adaptor.GetModelList()[0]
+			} else {
+				testModel = "gpt-3.5-turbo"
+			}
 		}
 	} else {
 		modelMapping := *channel.ModelMapping
@@ -117,6 +126,25 @@ func testChannel(channel *model.Channel, testModel string) (err error, openaiErr
 	if err != nil {
 		return err, nil
 	}
+	modelPrice, usePrice := common.GetModelPrice(testModel, false)
+	modelRatio := common.GetModelRatio(testModel)
+	completionRatio := common.GetCompletionRatio(testModel)
+	ratio := modelRatio
+	quota := 0
+	if !usePrice {
+		quota = usage.PromptTokens + int(math.Round(float64(usage.CompletionTokens)*completionRatio))
+		quota = int(math.Round(float64(quota) * ratio))
+		if ratio != 0 && quota <= 0 {
+			quota = 1
+		}
+	} else {
+		quota = int(modelPrice * common.QuotaPerUnit)
+	}
+	tok := time.Now()
+	milliseconds := tok.Sub(tik).Milliseconds()
+	consumedTime := float64(milliseconds) / 1000.0
+	other := service.GenerateTextOtherInfo(c, meta, modelRatio, 1, completionRatio, modelPrice)
+	model.RecordConsumeLog(c, 1, channel.Id, usage.PromptTokens, usage.CompletionTokens, testModel, "模型测试", quota, "模型测试", 0, quota, int(consumedTime), false, other)
 	common.SysLog(fmt.Sprintf("testing channel #%d, response: \n%s", channel.Id, string(respBody)))
 	return nil, nil
 }
@@ -137,7 +165,7 @@ func buildTestRequest() *dto.GeneralOpenAIRequest {
 }
 
 func TestChannel(c *gin.Context) {
-	id, err := strconv.Atoi(c.Param("id"))
+	channelId, err := strconv.Atoi(c.Param("id"))
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -145,7 +173,7 @@ func TestChannel(c *gin.Context) {
 		})
 		return
 	}
-	channel, err := model.GetChannelById(id, true)
+	channel, err := model.GetChannelById(channelId, true)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -219,11 +247,18 @@ func testAllChannels(notify bool) error {
 			if channel.AutoBan != nil && *channel.AutoBan == 0 {
 				ban = false
 			}
-			if isChannelEnabled && service.ShouldDisableChannel(openaiErr, -1) && ban {
-				service.DisableChannel(channel.Id, channel.Name, err.Error())
-			}
-			if !isChannelEnabled && service.ShouldEnableChannel(err, openaiErr, channel.Status) {
-				service.EnableChannel(channel.Id, channel.Name)
+			if openaiErr != nil {
+				openAiErrWithStatus := dto.OpenAIErrorWithStatusCode{
+					StatusCode: -1,
+					Error:      *openaiErr,
+					LocalError: false,
+				}
+				if isChannelEnabled && service.ShouldDisableChannel(channel.Type, &openAiErrWithStatus) && ban {
+					service.DisableChannel(channel.Id, channel.Name, err.Error())
+				}
+				if !isChannelEnabled && service.ShouldEnableChannel(err, openaiErr, channel.Status) {
+					service.EnableChannel(channel.Id, channel.Name)
+				}
 			}
 			channel.UpdateResponseTime(milliseconds)
 			time.Sleep(common.RequestInterval)

controller/midjourney.go

@@ -19,9 +19,6 @@ import (
 )
 
 func UpdateMidjourneyTaskBulk() {
-	if !common.IsMasterNode {
-		return
-	}
 	//imageModel := "midjourney"
 	ctx := context.TODO()
 	for {

controller/misc.go

@@ -57,6 +57,7 @@ func GetStatus(c *gin.Context) {
 			"display_in_currency":      common.DisplayInCurrencyEnabled,
 			"enable_batch_update":      common.BatchUpdateEnabled,
 			"enable_drawing":           common.DrawingEnabled,
+			"enable_task":              common.TaskEnabled,
 			"enable_data_export":       common.DataExportEnabled,
 			"data_export_default_time": common.DataExportDefaultTime,
 			"default_collapse_sidebar": common.DefaultCollapseSidebar,

controller/relay.go

@@ -29,6 +29,8 @@ func relayHandler(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 		fallthrough
 	case relayconstant.RelayModeAudioTranscription:
 		err = relay.AudioHelper(c, relayMode)
+	case relayconstant.RelayModeRerank:
+		err = relay.RerankHelper(c, relayMode)
 	default:
 		err = relay.TextHelper(c)
 	}
@@ -40,12 +42,13 @@ func Relay(c *gin.Context) {
 	retryTimes := common.RetryTimes
 	requestId := c.GetString(common.RequestIdKey)
 	channelId := c.GetInt("channel_id")
+	channelType := c.GetInt("channel_type")
 	group := c.GetString("group")
 	originalModel := c.GetString("original_model")
 	openaiErr := relayHandler(c, relayMode)
 	c.Set("use_channel", []string{fmt.Sprintf("%d", channelId)})
 	if openaiErr != nil {
-		go processChannelError(c, channelId, openaiErr)
+		go processChannelError(c, channelId, channelType, openaiErr)
 	} else {
 		retryTimes = 0
 	}
@@ -66,7 +69,7 @@ func Relay(c *gin.Context) {
 		c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
 		openaiErr = relayHandler(c, relayMode)
 		if openaiErr != nil {
-			go processChannelError(c, channelId, openaiErr)
+			go processChannelError(c, channelId, channel.Type, openaiErr)
 		}
 	}
 	useChannel := c.GetStringSlice("use_channel")
@@ -125,10 +128,10 @@ func shouldRetry(c *gin.Context, channelId int, openaiErr *dto.OpenAIErrorWithSt
 	return true
 }
 
-func processChannelError(c *gin.Context, channelId int, err *dto.OpenAIErrorWithStatusCode) {
+func processChannelError(c *gin.Context, channelId int, channelType int, err *dto.OpenAIErrorWithStatusCode) {
 	autoBan := c.GetBool("auto_ban")
 	common.LogError(c.Request.Context(), fmt.Sprintf("relay error (channel #%d, status code: %d): %s", channelId, err.StatusCode, err.Error.Message))
-	if service.ShouldDisableChannel(&err.Error, err.StatusCode) && autoBan {
+	if service.ShouldDisableChannel(channelType, err) && autoBan {
 		channelName := c.GetString("channel_name")
 		service.DisableChannel(channelId, channelName, err.Error.Message)
 	}
@@ -190,3 +193,94 @@ func RelayNotFound(c *gin.Context) {
 		"error": err,
 	})
 }
+
+func RelayTask(c *gin.Context) {
+	retryTimes := common.RetryTimes
+	channelId := c.GetInt("channel_id")
+	relayMode := c.GetInt("relay_mode")
+	group := c.GetString("group")
+	originalModel := c.GetString("original_model")
+	c.Set("use_channel", []string{fmt.Sprintf("%d", channelId)})
+	taskErr := taskRelayHandler(c, relayMode)
+	if taskErr == nil {
+		retryTimes = 0
+	}
+	for i := 0; shouldRetryTaskRelay(c, channelId, taskErr, retryTimes) && i < retryTimes; i++ {
+		channel, err := model.CacheGetRandomSatisfiedChannel(group, originalModel, i)
+		if err != nil {
+			common.LogError(c.Request.Context(), fmt.Sprintf("CacheGetRandomSatisfiedChannel failed: %s", err.Error()))
+			break
+		}
+		channelId = channel.Id
+		useChannel := c.GetStringSlice("use_channel")
+		useChannel = append(useChannel, fmt.Sprintf("%d", channelId))
+		c.Set("use_channel", useChannel)
+		common.LogInfo(c.Request.Context(), fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, i))
+		middleware.SetupContextForSelectedChannel(c, channel, originalModel)
+
+		requestBody, err := common.GetRequestBody(c)
+		c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
+		taskErr = taskRelayHandler(c, relayMode)
+	}
+	useChannel := c.GetStringSlice("use_channel")
+	if len(useChannel) > 1 {
+		retryLogStr := fmt.Sprintf("重试：%s", strings.Trim(strings.Join(strings.Fields(fmt.Sprint(useChannel)), "->"), "[]"))
+		common.LogInfo(c.Request.Context(), retryLogStr)
+	}
+	if taskErr != nil {
+		if taskErr.StatusCode == http.StatusTooManyRequests {
+			taskErr.Message = "当前分组上游负载已饱和，请稍后再试"
+		}
+		c.JSON(taskErr.StatusCode, taskErr)
+	}
+}
+
+func taskRelayHandler(c *gin.Context, relayMode int) *dto.TaskError {
+	var err *dto.TaskError
+	switch relayMode {
+	case relayconstant.RelayModeSunoFetch, relayconstant.RelayModeSunoFetchByID:
+		err = relay.RelayTaskFetch(c, relayMode)
+	default:
+		err = relay.RelayTaskSubmit(c, relayMode)
+	}
+	return err
+}
+
+func shouldRetryTaskRelay(c *gin.Context, channelId int, taskErr *dto.TaskError, retryTimes int) bool {
+	if taskErr == nil {
+		return false
+	}
+	if retryTimes <= 0 {
+		return false
+	}
+	if _, ok := c.Get("specific_channel_id"); ok {
+		return false
+	}
+	if taskErr.StatusCode == http.StatusTooManyRequests {
+		return true
+	}
+	if taskErr.StatusCode == 307 {
+		return true
+	}
+	if taskErr.StatusCode/100 == 5 {
+		// 超时不重试
+		if taskErr.StatusCode == 504 || taskErr.StatusCode == 524 {
+			return false
+		}
+		return true
+	}
+	if taskErr.StatusCode == http.StatusBadRequest {
+		return false
+	}
+	if taskErr.StatusCode == 408 {
+		// azure处理超时不重试
+		return false
+	}
+	if taskErr.LocalError {
+		return false
+	}
+	if taskErr.StatusCode/100 == 2 {
+		return false
+	}
+	return true
+}

controller/task.go

@@ -0,0 +1,284 @@
+package controller
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/samber/lo"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/constant"
+	"one-api/dto"
+	"one-api/model"
+	"one-api/relay"
+	"sort"
+	"strconv"
+	"time"
+)
+
+func UpdateTaskBulk() {
+	//revocer
+	//imageModel := "midjourney"
+	for {
+		time.Sleep(time.Duration(15) * time.Second)
+		common.SysLog("任务进度轮询开始")
+		ctx := context.TODO()
+		allTasks := model.GetAllUnFinishSyncTasks(500)
+		platformTask := make(map[constant.TaskPlatform][]*model.Task)
+		for _, t := range allTasks {
+			platformTask[t.Platform] = append(platformTask[t.Platform], t)
+		}
+		for platform, tasks := range platformTask {
+			if len(tasks) == 0 {
+				continue
+			}
+			taskChannelM := make(map[int][]string)
+			taskM := make(map[string]*model.Task)
+			nullTaskIds := make([]int64, 0)
+			for _, task := range tasks {
+				if task.TaskID == "" {
+					// 统计失败的未完成任务
+					nullTaskIds = append(nullTaskIds, task.ID)
+					continue
+				}
+				taskM[task.TaskID] = task
+				taskChannelM[task.ChannelId] = append(taskChannelM[task.ChannelId], task.TaskID)
+			}
+			if len(nullTaskIds) > 0 {
+				err := model.TaskBulkUpdateByID(nullTaskIds, map[string]any{
+					"status":   "FAILURE",
+					"progress": "100%",
+				})
+				if err != nil {
+					common.LogError(ctx, fmt.Sprintf("Fix null task_id task error: %v", err))
+				} else {
+					common.LogInfo(ctx, fmt.Sprintf("Fix null task_id task success: %v", nullTaskIds))
+				}
+			}
+			if len(taskChannelM) == 0 {
+				continue
+			}
+
+			UpdateTaskByPlatform(platform, taskChannelM, taskM)
+		}
+		common.SysLog("任务进度轮询完成")
+	}
+}
+
+func UpdateTaskByPlatform(platform constant.TaskPlatform, taskChannelM map[int][]string, taskM map[string]*model.Task) {
+	switch platform {
+	case constant.TaskPlatformMidjourney:
+		//_ = UpdateMidjourneyTaskAll(context.Background(), tasks)
+	case constant.TaskPlatformSuno:
+		_ = UpdateSunoTaskAll(context.Background(), taskChannelM, taskM)
+	default:
+		common.SysLog("未知平台")
+	}
+}
+
+func UpdateSunoTaskAll(ctx context.Context, taskChannelM map[int][]string, taskM map[string]*model.Task) error {
+	for channelId, taskIds := range taskChannelM {
+		err := updateSunoTaskAll(ctx, channelId, taskIds, taskM)
+		if err != nil {
+			common.LogError(ctx, fmt.Sprintf("渠道 #%d 更新异步任务失败: %d", channelId, err.Error()))
+		}
+	}
+	return nil
+}
+
+func updateSunoTaskAll(ctx context.Context, channelId int, taskIds []string, taskM map[string]*model.Task) error {
+	common.LogInfo(ctx, fmt.Sprintf("渠道 #%d 未完成的任务有: %d", channelId, len(taskIds)))
+	if len(taskIds) == 0 {
+		return nil
+	}
+	channel, err := model.CacheGetChannel(channelId)
+	if err != nil {
+		common.SysLog(fmt.Sprintf("CacheGetChannel: %v", err))
+		err = model.TaskBulkUpdate(taskIds, map[string]any{
+			"fail_reason": fmt.Sprintf("获取渠道信息失败，请联系管理员，渠道ID：%d", channelId),
+			"status":      "FAILURE",
+			"progress":    "100%",
+		})
+		if err != nil {
+			common.SysError(fmt.Sprintf("UpdateMidjourneyTask error2: %v", err))
+		}
+		return err
+	}
+	adaptor := relay.GetTaskAdaptor(constant.TaskPlatformSuno)
+	if adaptor == nil {
+		return errors.New("adaptor not found")
+	}
+	resp, err := adaptor.FetchTask(*channel.BaseURL, channel.Key, map[string]any{
+		"ids": taskIds,
+	})
+	if err != nil {
+		common.SysError(fmt.Sprintf("Get Task Do req error: %v", err))
+		return err
+	}
+	if resp.StatusCode != http.StatusOK {
+		common.LogError(ctx, fmt.Sprintf("Get Task status code: %d", resp.StatusCode))
+		return errors.New(fmt.Sprintf("Get Task status code: %d", resp.StatusCode))
+	}
+	defer resp.Body.Close()
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		common.SysError(fmt.Sprintf("Get Task parse body error: %v", err))
+		return err
+	}
+	var responseItems dto.TaskResponse[[]dto.SunoDataResponse]
+	err = json.Unmarshal(responseBody, &responseItems)
+	if err != nil {
+		common.LogError(ctx, fmt.Sprintf("Get Task parse body error2: %v, body: %s", err, string(responseBody)))
+		return err
+	}
+	if !responseItems.IsSuccess() {
+		common.SysLog(fmt.Sprintf("渠道 #%d 未完成的任务有: %d, 成功获取到任务数: %d", channelId, len(taskIds), string(responseBody)))
+		return err
+	}
+
+	for _, responseItem := range responseItems.Data {
+		task := taskM[responseItem.TaskID]
+		if !checkTaskNeedUpdate(task, responseItem) {
+			continue
+		}
+
+		task.Status = lo.If(model.TaskStatus(responseItem.Status) != "", model.TaskStatus(responseItem.Status)).Else(task.Status)
+		task.FailReason = lo.If(responseItem.FailReason != "", responseItem.FailReason).Else(task.FailReason)
+		task.SubmitTime = lo.If(responseItem.SubmitTime != 0, responseItem.SubmitTime).Else(task.SubmitTime)
+		task.StartTime = lo.If(responseItem.StartTime != 0, responseItem.StartTime).Else(task.StartTime)
+		task.FinishTime = lo.If(responseItem.FinishTime != 0, responseItem.FinishTime).Else(task.FinishTime)
+		if responseItem.FailReason != "" || task.Status == model.TaskStatusFailure {
+			common.LogInfo(ctx, task.TaskID+" 构建失败，"+task.FailReason)
+			task.Progress = "100%"
+			err = model.CacheUpdateUserQuota(task.UserId)
+			if err != nil {
+				common.LogError(ctx, "error update user quota cache: "+err.Error())
+			} else {
+				quota := task.Quota
+				if quota != 0 {
+					err = model.IncreaseUserQuota(task.UserId, quota)
+					if err != nil {
+						common.LogError(ctx, "fail to increase user quota: "+err.Error())
+					}
+					logContent := fmt.Sprintf("异步任务执行失败 %s，补偿 %s", task.TaskID, common.LogQuota(quota))
+					model.RecordLog(task.UserId, model.LogTypeSystem, logContent)
+				}
+			}
+		}
+		if responseItem.Status == model.TaskStatusSuccess {
+			task.Progress = "100%"
+		}
+		task.Data = responseItem.Data
+
+		err = task.Update()
+		if err != nil {
+			common.SysError("UpdateMidjourneyTask task error: " + err.Error())
+		}
+	}
+	return nil
+}
+
+func checkTaskNeedUpdate(oldTask *model.Task, newTask dto.SunoDataResponse) bool {
+
+	if oldTask.SubmitTime != newTask.SubmitTime {
+		return true
+	}
+	if oldTask.StartTime != newTask.StartTime {
+		return true
+	}
+	if oldTask.FinishTime != newTask.FinishTime {
+		return true
+	}
+	if string(oldTask.Status) != newTask.Status {
+		return true
+	}
+	if oldTask.FailReason != newTask.FailReason {
+		return true
+	}
+	if oldTask.FinishTime != newTask.FinishTime {
+		return true
+	}
+
+	if (oldTask.Status == model.TaskStatusFailure || oldTask.Status == model.TaskStatusSuccess) && oldTask.Progress != "100%" {
+		return true
+	}
+
+	oldData, _ := json.Marshal(oldTask.Data)
+	newData, _ := json.Marshal(newTask.Data)
+
+	sort.Slice(oldData, func(i, j int) bool {
+		return oldData[i] < oldData[j]
+	})
+	sort.Slice(newData, func(i, j int) bool {
+		return newData[i] < newData[j]
+	})
+
+	if string(oldData) != string(newData) {
+		return true
+	}
+	return false
+}
+
+func GetAllTask(c *gin.Context) {
+	p, _ := strconv.Atoi(c.Query("p"))
+	if p < 0 {
+		p = 0
+	}
+	startTimestamp, _ := strconv.ParseInt(c.Query("start_timestamp"), 10, 64)
+	endTimestamp, _ := strconv.ParseInt(c.Query("end_timestamp"), 10, 64)
+	// 解析其他查询参数
+	queryParams := model.SyncTaskQueryParams{
+		Platform:       constant.TaskPlatform(c.Query("platform")),
+		TaskID:         c.Query("task_id"),
+		Status:         c.Query("status"),
+		Action:         c.Query("action"),
+		StartTimestamp: startTimestamp,
+		EndTimestamp:   endTimestamp,
+	}
+
+	logs := model.TaskGetAllTasks(p*common.ItemsPerPage, common.ItemsPerPage, queryParams)
+	if logs == nil {
+		logs = make([]*model.Task, 0)
+	}
+
+	c.JSON(200, gin.H{
+		"success": true,
+		"message": "",
+		"data":    logs,
+	})
+}
+
+func GetUserTask(c *gin.Context) {
+	p, _ := strconv.Atoi(c.Query("p"))
+	if p < 0 {
+		p = 0
+	}
+
+	userId := c.GetInt("id")
+
+	startTimestamp, _ := strconv.ParseInt(c.Query("start_timestamp"), 10, 64)
+	endTimestamp, _ := strconv.ParseInt(c.Query("end_timestamp"), 10, 64)
+
+	queryParams := model.SyncTaskQueryParams{
+		Platform:       constant.TaskPlatform(c.Query("platform")),
+		TaskID:         c.Query("task_id"),
+		Status:         c.Query("status"),
+		Action:         c.Query("action"),
+		StartTimestamp: startTimestamp,
+		EndTimestamp:   endTimestamp,
+	}
+
+	logs := model.TaskGetAllUserTask(userId, p*common.ItemsPerPage, common.ItemsPerPage, queryParams)
+	if logs == nil {
+		logs = make([]*model.Task, 0)
+	}
+
+	c.JSON(200, gin.H{
+		"success": true,
+		"message": "",
+		"data":    logs,
+	})
+}

controller/topup.go

@@ -5,11 +5,10 @@ import (
 	"github.com/Calcium-Ion/go-epay/epay"
 	"github.com/gin-gonic/gin"
 	"github.com/samber/lo"
-	"one-api/constant"
-
 	"log"
 	"net/url"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/model"
 	"one-api/service"
 	"strconv"

dto/pricing.go

@@ -24,14 +24,3 @@ type OpenAIModels struct {
 	Root       string                  `json:"root"`
 	Parent     *string                 `json:"parent"`
 }
-
-type ModelPricing struct {
-	Available       bool     `json:"available"`
-	ModelName       string   `json:"model_name"`
-	QuotaType       int      `json:"quota_type"`
-	ModelRatio      float64  `json:"model_ratio"`
-	ModelPrice      float64  `json:"model_price"`
-	OwnerBy         string   `json:"owner_by"`
-	CompletionRatio float64  `json:"completion_ratio"`
-	EnableGroup     []string `json:"enable_group,omitempty"`
-}

dto/rerank.go

@@ -0,0 +1,19 @@
+package dto
+
+type RerankRequest struct {
+	Documents []any  `json:"documents"`
+	Query     string `json:"query"`
+	Model     string `json:"model"`
+	TopN      int    `json:"top_n"`
+}
+
+type RerankResponseDocument struct {
+	Document       any     `json:"document"`
+	Index          int     `json:"index"`
+	RelevanceScore float64 `json:"relevance_score"`
+}
+
+type RerankResponse struct {
+	Results []RerankResponseDocument `json:"results"`
+	Usage   Usage                    `json:"usage"`
+}

dto/suno.go

@@ -0,0 +1,129 @@
+package dto
+
+import (
+	"encoding/json"
+)
+
+type TaskData interface {
+	SunoDataResponse | []SunoDataResponse | string | any
+}
+
+type SunoSubmitReq struct {
+	GptDescriptionPrompt string  `json:"gpt_description_prompt,omitempty"`
+	Prompt               string  `json:"prompt,omitempty"`
+	Mv                   string  `json:"mv,omitempty"`
+	Title                string  `json:"title,omitempty"`
+	Tags                 string  `json:"tags,omitempty"`
+	ContinueAt           float64 `json:"continue_at,omitempty"`
+	TaskID               string  `json:"task_id,omitempty"`
+	ContinueClipId       string  `json:"continue_clip_id,omitempty"`
+	MakeInstrumental     bool    `json:"make_instrumental"`
+}
+
+type FetchReq struct {
+	IDs []string `json:"ids"`
+}
+
+type SunoDataResponse struct {
+	TaskID     string          `json:"task_id" gorm:"type:varchar(50);index"`
+	Action     string          `json:"action" gorm:"type:varchar(40);index"` // 任务类型, song, lyrics, description-mode
+	Status     string          `json:"status" gorm:"type:varchar(20);index"` // 任务状态, submitted, queueing, processing, success, failed
+	FailReason string          `json:"fail_reason"`
+	SubmitTime int64           `json:"submit_time" gorm:"index"`
+	StartTime  int64           `json:"start_time" gorm:"index"`
+	FinishTime int64           `json:"finish_time" gorm:"index"`
+	Data       json.RawMessage `json:"data" gorm:"type:json"`
+}
+
+type SunoSong struct {
+	ID                string       `json:"id"`
+	VideoURL          string       `json:"video_url"`
+	AudioURL          string       `json:"audio_url"`
+	ImageURL          string       `json:"image_url"`
+	ImageLargeURL     string       `json:"image_large_url"`
+	MajorModelVersion string       `json:"major_model_version"`
+	ModelName         string       `json:"model_name"`
+	Status            string       `json:"status"`
+	Title             string       `json:"title"`
+	Text              string       `json:"text"`
+	Metadata          SunoMetadata `json:"metadata"`
+}
+
+type SunoMetadata struct {
+	Tags                 string      `json:"tags"`
+	Prompt               string      `json:"prompt"`
+	GPTDescriptionPrompt interface{} `json:"gpt_description_prompt"`
+	AudioPromptID        interface{} `json:"audio_prompt_id"`
+	Duration             interface{} `json:"duration"`
+	ErrorType            interface{} `json:"error_type"`
+	ErrorMessage         interface{} `json:"error_message"`
+}
+
+type SunoLyrics struct {
+	ID     string `json:"id"`
+	Status string `json:"status"`
+	Title  string `json:"title"`
+	Text   string `json:"text"`
+}
+
+const TaskSuccessCode = "success"
+
+type TaskResponse[T TaskData] struct {
+	Code    string `json:"code"`
+	Message string `json:"message"`
+	Data    T      `json:"data"`
+}
+
+func (t *TaskResponse[T]) IsSuccess() bool {
+	return t.Code == TaskSuccessCode
+}
+
+type TaskDto struct {
+	TaskID     string          `json:"task_id"` // 第三方id，不一定有/ song id\ Task id
+	Action     string          `json:"action"`  // 任务类型, song, lyrics, description-mode
+	Status     string          `json:"status"`  // 任务状态, submitted, queueing, processing, success, failed
+	FailReason string          `json:"fail_reason"`
+	SubmitTime int64           `json:"submit_time"`
+	StartTime  int64           `json:"start_time"`
+	FinishTime int64           `json:"finish_time"`
+	Progress   string          `json:"progress"`
+	Data       json.RawMessage `json:"data"`
+}
+
+type SunoGoAPISubmitReq struct {
+	CustomMode bool `json:"custom_mode"`
+
+	Input SunoGoAPISubmitReqInput `json:"input"`
+
+	NotifyHook string `json:"notify_hook,omitempty"`
+}
+
+type SunoGoAPISubmitReqInput struct {
+	GptDescriptionPrompt string  `json:"gpt_description_prompt"`
+	Prompt               string  `json:"prompt"`
+	Mv                   string  `json:"mv"`
+	Title                string  `json:"title"`
+	Tags                 string  `json:"tags"`
+	ContinueAt           float64 `json:"continue_at"`
+	TaskID               string  `json:"task_id"`
+	ContinueClipId       string  `json:"continue_clip_id"`
+	MakeInstrumental     bool    `json:"make_instrumental"`
+}
+
+type GoAPITaskResponse[T any] struct {
+	Code         int    `json:"code"`
+	Message      string `json:"message"`
+	Data         T      `json:"data"`
+	ErrorMessage string `json:"error_message,omitempty"`
+}
+
+type GoAPITaskResponseData struct {
+	TaskID string `json:"task_id"`
+}
+
+type GoAPIFetchResponseData struct {
+	TaskID string              `json:"task_id"`
+	Status string              `json:"status"`
+	Input  string              `json:"input"`
+	Clips  map[string]SunoSong `json:"clips"`
+}

dto/task.go

@@ -0,0 +1,10 @@
+package dto
+
+type TaskError struct {
+	Code       string `json:"code"`
+	Message    string `json:"message"`
+	Data       any    `json:"data"`
+	StatusCode int    `json:"-"`
+	LocalError bool   `json:"-"`
+	Error      error  `json:"-"`
+}

dto/text_request.go

@@ -11,6 +11,7 @@ type GeneralOpenAIRequest struct {
 	Messages         []Message       `json:"messages,omitempty"`
 	Prompt           any             `json:"prompt,omitempty"`
 	Stream           bool            `json:"stream,omitempty"`
+	StreamOptions    *StreamOptions  `json:"stream_options,omitempty"`
 	MaxTokens        uint            `json:"max_tokens,omitempty"`
 	Temperature      float64         `json:"temperature,omitempty"`
 	TopP             float64         `json:"top_p,omitempty"`
@@ -43,6 +44,10 @@ type OpenAIFunction struct {
 	Parameters  any    `json:"parameters,omitempty"`
 }
 
+type StreamOptions struct {
+	IncludeUsage bool `json:"include_usage,omitempty"`
+}
+
 func (r GeneralOpenAIRequest) GetMaxTokens() int64 {
 	return int64(r.MaxTokens)
 }

dto/text_response.go

@@ -106,6 +106,7 @@ type ChatCompletionsStreamResponse struct {
 
 type ChatCompletionsStreamResponseSimple struct {
 	Choices []ChatCompletionsStreamResponseChoice `json:"choices"`
+	Usage   *Usage                                `json:"usage"`
 }
 
 type CompletionsStreamResponse struct {

main.go

@@ -89,9 +89,14 @@ func main() {
 		}
 		go controller.AutomaticallyTestChannels(frequency)
 	}
-	common.SafeGoroutine(func() {
-		controller.UpdateMidjourneyTaskBulk()
-	})
+	if common.IsMasterNode {
+		common.SafeGoroutine(func() {
+			controller.UpdateMidjourneyTaskBulk()
+		})
+		common.SafeGoroutine(func() {
+			controller.UpdateTaskBulk()
+		})
+	}
 	if os.Getenv("BATCH_UPDATE_ENABLED") == "true" {
 		common.BatchUpdateEnabled = true
 		common.SysLog("batch update enabled with interval " + strconv.Itoa(common.BatchUpdateInterval) + "s")

middleware/distributor.go

@@ -125,6 +125,17 @@ func getModelRequest(c *gin.Context) (*ModelRequest, bool, error) {
 			modelRequest.Model = midjourneyModel
 		}
 		c.Set("relay_mode", relayMode)
+	} else if strings.Contains(c.Request.URL.Path, "/suno/") {
+		relayMode := relayconstant.Path2RelaySuno(c.Request.Method, c.Request.URL.Path)
+		if relayMode == relayconstant.RelayModeSunoFetch ||
+			relayMode == relayconstant.RelayModeSunoFetchByID {
+			shouldSelectChannel = false
+		} else {
+			modelName := service.CoverTaskActionToModelName(constant.TaskPlatformSuno, c.Param("action"))
+			modelRequest.Model = modelName
+		}
+		c.Set("platform", string(constant.TaskPlatformSuno))
+		c.Set("relay_mode", relayMode)
 	} else if !strings.HasPrefix(c.Request.URL.Path, "/v1/audio/transcriptions") {
 		err = common.UnmarshalBodyReusable(c, &modelRequest)
 	}
@@ -167,6 +178,7 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 	c.Set("channel", channel.Type)
 	c.Set("channel_id", channel.Id)
 	c.Set("channel_name", channel.Name)
+	c.Set("channel_type", channel.Type)
 	ban := true
 	// parse *int to bool
 	if channel.AutoBan != nil && *channel.AutoBan == 0 {

model/ability.go

@@ -56,6 +56,11 @@ func getPriority(group string, model string, retry int) (int, error) {
 		return 0, err
 	}
 
+	if len(priorities) == 0 {
+		// 如果没有查询到优先级，则返回错误
+		return 0, errors.New("数据库一致性被破坏")
+	}
+
 	// 确定要使用的优先级
 	var priorityToUse int
 	if retry >= len(priorities) {
@@ -199,7 +204,7 @@ func FixAbility() (int, error) {
 
 	// Use channelIds to find channel not in abilities table
 	var abilityChannelIds []int
-	err = DB.Model(&Ability{}).Pluck("channel_id", &abilityChannelIds).Error
+	err = DB.Table("abilities").Distinct("channel_id").Pluck("channel_id", &abilityChannelIds).Error
 	if err != nil {
 		common.SysError(fmt.Sprintf("Get channel ids from abilities table failed: %s", err.Error()))
 		return 0, err

model/channel.go

@@ -255,6 +255,7 @@ func UpdateChannelStatusById(id int, status int, reason string) {
 		// find channel by id success, update status and other info
 		info := channel.GetOtherInfo()
 		info["status_reason"] = reason
+		info["status_time"] = common.GetTimestamp()
 		channel.SetOtherInfo(info)
 		channel.Status = status
 		err = channel.Save()

model/main.go

@@ -86,9 +86,9 @@ func InitDB() (err error) {
 		if err != nil {
 			return err
 		}
-		sqlDB.SetMaxIdleConns(common.GetOrDefault("SQL_MAX_IDLE_CONNS", 100))
-		sqlDB.SetMaxOpenConns(common.GetOrDefault("SQL_MAX_OPEN_CONNS", 1000))
-		sqlDB.SetConnMaxLifetime(time.Second * time.Duration(common.GetOrDefault("SQL_MAX_LIFETIME", 60)))
+		sqlDB.SetMaxIdleConns(common.GetEnvOrDefault("SQL_MAX_IDLE_CONNS", 100))
+		sqlDB.SetMaxOpenConns(common.GetEnvOrDefault("SQL_MAX_OPEN_CONNS", 1000))
+		sqlDB.SetConnMaxLifetime(time.Second * time.Duration(common.GetEnvOrDefault("SQL_MAX_LIFETIME", 60)))
 
 		if !common.IsMasterNode {
 			return nil
@@ -140,6 +140,10 @@ func InitDB() (err error) {
 		if err != nil {
 			return err
 		}
+		err = db.AutoMigrate(&Task{})
+		if err != nil {
+			return err
+		}
 		common.SysLog("database migrated")
 		err = createRootAccountIfNeed()
 		return err

model/option.go

@@ -41,6 +41,7 @@ func InitOptionMap() {
 	common.OptionMap["DisplayInCurrencyEnabled"] = strconv.FormatBool(common.DisplayInCurrencyEnabled)
 	common.OptionMap["DisplayTokenStatEnabled"] = strconv.FormatBool(common.DisplayTokenStatEnabled)
 	common.OptionMap["DrawingEnabled"] = strconv.FormatBool(common.DrawingEnabled)
+	common.OptionMap["TaskEnabled"] = strconv.FormatBool(common.TaskEnabled)
 	common.OptionMap["DataExportEnabled"] = strconv.FormatBool(common.DataExportEnabled)
 	common.OptionMap["ChannelDisableThreshold"] = strconv.FormatFloat(common.ChannelDisableThreshold, 'f', -1, 64)
 	common.OptionMap["EmailDomainRestrictionEnabled"] = strconv.FormatBool(common.EmailDomainRestrictionEnabled)
@@ -195,6 +196,8 @@ func updateOptionMap(key string, value string) (err error) {
 			common.DisplayTokenStatEnabled = boolValue
 		case "DrawingEnabled":
 			common.DrawingEnabled = boolValue
+		case "TaskEnabled":
+			common.TaskEnabled = boolValue
 		case "DataExportEnabled":
 			common.DataExportEnabled = boolValue
 		case "DefaultCollapseSidebar":

model/pricing.go

@@ -2,18 +2,28 @@ package model
 
 import (
 	"one-api/common"
-	"one-api/dto"
 	"sync"
 	"time"
 )
 
+type Pricing struct {
+	Available       bool     `json:"available"`
+	ModelName       string   `json:"model_name"`
+	QuotaType       int      `json:"quota_type"`
+	ModelRatio      float64  `json:"model_ratio"`
+	ModelPrice      float64  `json:"model_price"`
+	OwnerBy         string   `json:"owner_by"`
+	CompletionRatio float64  `json:"completion_ratio"`
+	EnableGroup     []string `json:"enable_group,omitempty"`
+}
+
 var (
-	pricingMap         []dto.ModelPricing
+	pricingMap         []Pricing
 	lastGetPricingTime time.Time
 	updatePricingLock  sync.Mutex
 )
 
-func GetPricing(group string) []dto.ModelPricing {
+func GetPricing(group string) []Pricing {
 	updatePricingLock.Lock()
 	defer updatePricingLock.Unlock()
 
@@ -21,7 +31,7 @@ func GetPricing(group string) []dto.ModelPricing {
 		updatePricing()
 	}
 	if group != "" {
-		userPricingMap := make([]dto.ModelPricing, 0)
+		userPricingMap := make([]Pricing, 0)
 		models := GetGroupModels(group)
 		for _, pricing := range pricingMap {
 			if !common.StringsContains(models, pricing.ModelName) {
@@ -42,9 +52,9 @@ func updatePricing() {
 		allModels[model] = i
 	}
 
-	pricingMap = make([]dto.ModelPricing, 0)
+	pricingMap = make([]Pricing, 0)
 	for model, _ := range allModels {
-		pricing := dto.ModelPricing{
+		pricing := Pricing{
 			Available: true,
 			ModelName: model,
 		}

model/redemption.go

@@ -78,7 +78,7 @@ func Redeem(key string, userId int) (quota int, err error) {
 	if err != nil {
 		return 0, errors.New("兑换失败，" + err.Error())
 	}
-	RecordLog(userId, LogTypeTopup, fmt.Sprintf("通过兑换码充值 %s", common.LogQuota(redemption.Quota)))
+	RecordLog(userId, LogTypeTopup, fmt.Sprintf("通过兑换码充值 %s，兑换码ID %d", common.LogQuota(redemption.Quota), redemption.Id))
 	return redemption.Quota, nil
 }
 

model/task.go

@@ -0,0 +1,304 @@
+package model
+
+import (
+	"database/sql/driver"
+	"encoding/json"
+	"one-api/constant"
+	commonRelay "one-api/relay/common"
+	"time"
+)
+
+type TaskStatus string
+
+const (
+	TaskStatusNotStart   TaskStatus = "NOT_START"
+	TaskStatusSubmitted             = "SUBMITTED"
+	TaskStatusQueued                = "QUEUED"
+	TaskStatusInProgress            = "IN_PROGRESS"
+	TaskStatusFailure               = "FAILURE"
+	TaskStatusSuccess               = "SUCCESS"
+	TaskStatusUnknown               = "UNKNOWN"
+)
+
+type Task struct {
+	ID         int64                 `json:"id" gorm:"primary_key;AUTO_INCREMENT"`
+	CreatedAt  int64                 `json:"created_at" gorm:"index"`
+	UpdatedAt  int64                 `json:"updated_at"`
+	TaskID     string                `json:"task_id" gorm:"type:varchar(50);index"`  // 第三方id，不一定有/ song id\ Task id
+	Platform   constant.TaskPlatform `json:"platform" gorm:"type:varchar(30);index"` // 平台
+	UserId     int                   `json:"user_id" gorm:"index"`
+	ChannelId  int                   `json:"channel_id" gorm:"index"`
+	Quota      int                   `json:"quota"`
+	Action     string                `json:"action" gorm:"type:varchar(40);index"` // 任务类型, song, lyrics, description-mode
+	Status     TaskStatus            `json:"status" gorm:"type:varchar(20);index"` // 任务状态
+	FailReason string                `json:"fail_reason"`
+	SubmitTime int64                 `json:"submit_time" gorm:"index"`
+	StartTime  int64                 `json:"start_time" gorm:"index"`
+	FinishTime int64                 `json:"finish_time" gorm:"index"`
+	Progress   string                `json:"progress" gorm:"type:varchar(20);index"`
+	Properties Properties            `json:"properties" gorm:"type:json"`
+
+	Data json.RawMessage `json:"data" gorm:"type:json"`
+}
+
+func (t *Task) SetData(data any) {
+	b, _ := json.Marshal(data)
+	t.Data = json.RawMessage(b)
+}
+
+func (t *Task) GetData(v any) error {
+	err := json.Unmarshal(t.Data, &v)
+	return err
+}
+
+type Properties struct {
+	Input string `json:"input"`
+}
+
+func (m *Properties) Scan(val interface{}) error {
+	bytesValue, _ := val.([]byte)
+	return json.Unmarshal(bytesValue, m)
+}
+
+func (m Properties) Value() (driver.Value, error) {
+	return json.Marshal(m)
+}
+
+// SyncTaskQueryParams 用于包含所有搜索条件的结构体，可以根据需求添加更多字段
+type SyncTaskQueryParams struct {
+	Platform       constant.TaskPlatform
+	ChannelID      string
+	TaskID         string
+	UserID         string
+	Action         string
+	Status         string
+	StartTimestamp int64
+	EndTimestamp   int64
+	UserIDs        []int
+}
+
+func InitTask(platform constant.TaskPlatform, relayInfo *commonRelay.TaskRelayInfo) *Task {
+	t := &Task{
+		UserId:     relayInfo.UserId,
+		SubmitTime: time.Now().Unix(),
+		Status:     TaskStatusNotStart,
+		Progress:   "0%",
+		ChannelId:  relayInfo.ChannelId,
+		Platform:   platform,
+	}
+	return t
+}
+
+func TaskGetAllUserTask(userId int, startIdx int, num int, queryParams SyncTaskQueryParams) []*Task {
+	var tasks []*Task
+	var err error
+
+	// 初始化查询构建器
+	query := DB.Where("user_id = ?", userId)
+
+	if queryParams.TaskID != "" {
+		query = query.Where("task_id = ?", queryParams.TaskID)
+	}
+	if queryParams.Action != "" {
+		query = query.Where("action = ?", queryParams.Action)
+	}
+	if queryParams.Status != "" {
+		query = query.Where("status = ?", queryParams.Status)
+	}
+	if queryParams.Platform != "" {
+		query = query.Where("platform = ?", queryParams.Platform)
+	}
+	if queryParams.StartTimestamp != 0 {
+		// 假设您已将前端传来的时间戳转换为数据库所需的时间格式，并处理了时间戳的验证和解析
+		query = query.Where("submit_time >= ?", queryParams.StartTimestamp)
+	}
+	if queryParams.EndTimestamp != 0 {
+		query = query.Where("submit_time <= ?", queryParams.EndTimestamp)
+	}
+
+	// 获取数据
+	err = query.Omit("channel_id").Order("id desc").Limit(num).Offset(startIdx).Find(&tasks).Error
+	if err != nil {
+		return nil
+	}
+
+	return tasks
+}
+
+func TaskGetAllTasks(startIdx int, num int, queryParams SyncTaskQueryParams) []*Task {
+	var tasks []*Task
+	var err error
+
+	// 初始化查询构建器
+	query := DB
+
+	// 添加过滤条件
+	if queryParams.ChannelID != "" {
+		query = query.Where("channel_id = ?", queryParams.ChannelID)
+	}
+	if queryParams.Platform != "" {
+		query = query.Where("platform = ?", queryParams.Platform)
+	}
+	if queryParams.UserID != "" {
+		query = query.Where("user_id = ?", queryParams.UserID)
+	}
+	if len(queryParams.UserIDs) != 0 {
+		query = query.Where("user_id in (?)", queryParams.UserIDs)
+	}
+	if queryParams.TaskID != "" {
+		query = query.Where("task_id = ?", queryParams.TaskID)
+	}
+	if queryParams.Action != "" {
+		query = query.Where("action = ?", queryParams.Action)
+	}
+	if queryParams.Status != "" {
+		query = query.Where("status = ?", queryParams.Status)
+	}
+	if queryParams.StartTimestamp != 0 {
+		query = query.Where("submit_time >= ?", queryParams.StartTimestamp)
+	}
+	if queryParams.EndTimestamp != 0 {
+		query = query.Where("submit_time <= ?", queryParams.EndTimestamp)
+	}
+
+	// 获取数据
+	err = query.Order("id desc").Limit(num).Offset(startIdx).Find(&tasks).Error
+	if err != nil {
+		return nil
+	}
+
+	return tasks
+}
+
+func GetAllUnFinishSyncTasks(limit int) []*Task {
+	var tasks []*Task
+	var err error
+	// get all tasks progress is not 100%
+	err = DB.Where("progress != ?", "100%").Limit(limit).Order("id").Find(&tasks).Error
+	if err != nil {
+		return nil
+	}
+	return tasks
+}
+
+func GetByOnlyTaskId(taskId string) (*Task, bool, error) {
+	if taskId == "" {
+		return nil, false, nil
+	}
+	var task *Task
+	var err error
+	err = DB.Where("task_id = ?", taskId).First(&task).Error
+	exist, err := RecordExist(err)
+	if err != nil {
+		return nil, false, err
+	}
+	return task, exist, err
+}
+
+func GetByTaskId(userId int, taskId string) (*Task, bool, error) {
+	if taskId == "" {
+		return nil, false, nil
+	}
+	var task *Task
+	var err error
+	err = DB.Where("user_id = ? and task_id = ?", userId, taskId).
+		First(&task).Error
+	exist, err := RecordExist(err)
+	if err != nil {
+		return nil, false, err
+	}
+	return task, exist, err
+}
+
+func GetByTaskIds(userId int, taskIds []any) ([]*Task, error) {
+	if len(taskIds) == 0 {
+		return nil, nil
+	}
+	var task []*Task
+	var err error
+	err = DB.Where("user_id = ? and task_id in (?)", userId, taskIds).
+		Find(&task).Error
+	if err != nil {
+		return nil, err
+	}
+	return task, nil
+}
+
+func TaskUpdateProgress(id int64, progress string) error {
+	return DB.Model(&Task{}).Where("id = ?", id).Update("progress", progress).Error
+}
+
+func (Task *Task) Insert() error {
+	var err error
+	err = DB.Create(Task).Error
+	return err
+}
+
+func (Task *Task) Update() error {
+	var err error
+	err = DB.Save(Task).Error
+	return err
+}
+
+func TaskBulkUpdate(TaskIds []string, params map[string]any) error {
+	if len(TaskIds) == 0 {
+		return nil
+	}
+	return DB.Model(&Task{}).
+		Where("task_id in (?)", TaskIds).
+		Updates(params).Error
+}
+
+func TaskBulkUpdateByTaskIds(taskIDs []int64, params map[string]any) error {
+	if len(taskIDs) == 0 {
+		return nil
+	}
+	return DB.Model(&Task{}).
+		Where("id in (?)", taskIDs).
+		Updates(params).Error
+}
+
+func TaskBulkUpdateByID(ids []int64, params map[string]any) error {
+	if len(ids) == 0 {
+		return nil
+	}
+	return DB.Model(&Task{}).
+		Where("id in (?)", ids).
+		Updates(params).Error
+}
+
+type TaskQuotaUsage struct {
+	Mode  string  `json:"mode"`
+	Count float64 `json:"count"`
+}
+
+func SumUsedTaskQuota(queryParams SyncTaskQueryParams) (stat []TaskQuotaUsage, err error) {
+	query := DB.Model(Task{})
+	// 添加过滤条件
+	if queryParams.ChannelID != "" {
+		query = query.Where("channel_id = ?", queryParams.ChannelID)
+	}
+	if queryParams.UserID != "" {
+		query = query.Where("user_id = ?", queryParams.UserID)
+	}
+	if len(queryParams.UserIDs) != 0 {
+		query = query.Where("user_id in (?)", queryParams.UserIDs)
+	}
+	if queryParams.TaskID != "" {
+		query = query.Where("task_id = ?", queryParams.TaskID)
+	}
+	if queryParams.Action != "" {
+		query = query.Where("action = ?", queryParams.Action)
+	}
+	if queryParams.Status != "" {
+		query = query.Where("status = ?", queryParams.Status)
+	}
+	if queryParams.StartTimestamp != 0 {
+		query = query.Where("submit_time >= ?", queryParams.StartTimestamp)
+	}
+	if queryParams.EndTimestamp != 0 {
+		query = query.Where("submit_time <= ?", queryParams.EndTimestamp)
+	}
+	err = query.Select("mode, sum(quota) as count").Group("mode").Find(&stat).Error
+	return stat, err
+}

model/token.go

@@ -250,11 +250,9 @@ func PreConsumeTokenQuota(tokenId int, quota int) (userQuota int, err error) {
 	if userQuota < quota {
 		return 0, errors.New(fmt.Sprintf("用户额度不足，剩余额度为 %d", userQuota))
 	}
-	if !token.UnlimitedQuota {
-		err = DecreaseTokenQuota(tokenId, quota)
-		if err != nil {
-			return 0, err
-		}
+	err = DecreaseTokenQuota(tokenId, quota)
+	if err != nil {
+		return 0, err
 	}
 	err = DecreaseUserQuota(token.UserId, quota)
 	return userQuota - quota, err
@@ -272,15 +270,13 @@ func PostConsumeTokenQuota(tokenId int, userQuota int, quota int, preConsumedQuo
 		return err
 	}
 
-	if !token.UnlimitedQuota {
-		if quota > 0 {
-			err = DecreaseTokenQuota(tokenId, quota)
-		} else {
-			err = IncreaseTokenQuota(tokenId, -quota)
-		}
-		if err != nil {
-			return err
-		}
+	if quota > 0 {
+		err = DecreaseTokenQuota(tokenId, quota)
+	} else {
+		err = IncreaseTokenQuota(tokenId, -quota)
+	}
+	if err != nil {
+		return err
 	}
 
 	if sendEmail {

model/utils.go

@@ -1,6 +1,8 @@
 package model
 
 import (
+	"errors"
+	"gorm.io/gorm"
 	"one-api/common"
 	"sync"
 	"time"
@@ -75,3 +77,13 @@ func batchUpdate() {
 	}
 	common.SysLog("batch update finished")
 }
+
+func RecordExist(err error) (bool, error) {
+	if err == nil {
+		return true, nil
+	}
+	if errors.Is(err, gorm.ErrRecordNotFound) {
+		return false, nil
+	}
+	return false, err
+}

relay/channel/adapter.go

@@ -11,11 +11,32 @@ import (
 type Adaptor interface {
 	// Init IsStream bool
 	Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest)
+	InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest)
 	GetRequestURL(info *relaycommon.RelayInfo) (string, error)
 	SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error
 	ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error)
+	ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error)
 	DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error)
 	DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode)
 	GetModelList() []string
 	GetChannelName() string
 }
+
+type TaskAdaptor interface {
+	Init(info *relaycommon.TaskRelayInfo)
+
+	ValidateRequestAndSetAction(c *gin.Context, info *relaycommon.TaskRelayInfo) *dto.TaskError
+
+	BuildRequestURL(info *relaycommon.TaskRelayInfo) (string, error)
+	BuildRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.TaskRelayInfo) error
+	BuildRequestBody(c *gin.Context, info *relaycommon.TaskRelayInfo) (io.Reader, error)
+
+	DoRequest(c *gin.Context, info *relaycommon.TaskRelayInfo, requestBody io.Reader) (*http.Response, error)
+	DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.TaskRelayInfo) (taskID string, taskData []byte, err *dto.TaskError)
+
+	GetModelList() []string
+	GetChannelName() string
+
+	// FetchTask
+	FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error)
+}

relay/channel/ali/adaptor.go

@@ -15,6 +15,9 @@ import (
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 
 }
@@ -53,6 +56,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	}
 }
 
+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) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/api_request.go

@@ -50,3 +50,27 @@ func doRequest(c *gin.Context, req *http.Request) (*http.Response, error) {
 	_ = c.Request.Body.Close()
 	return resp, nil
 }
+
+func DoTaskApiRequest(a TaskAdaptor, c *gin.Context, info *common.TaskRelayInfo, requestBody io.Reader) (*http.Response, error) {
+	fullRequestURL, err := a.BuildRequestURL(info)
+	if err != nil {
+		return nil, err
+	}
+	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)
+	if err != nil {
+		return nil, fmt.Errorf("new request failed: %w", err)
+	}
+	req.GetBody = func() (io.ReadCloser, error) {
+		return io.NopCloser(requestBody), nil
+	}
+
+	err = a.BuildRequestHeader(c, req, info)
+	if err != nil {
+		return nil, fmt.Errorf("setup request header failed: %w", err)
+	}
+	resp, err := doRequest(c, req)
+	if err != nil {
+		return nil, fmt.Errorf("do request failed: %w", err)
+	}
+	return resp, nil
+}

relay/channel/aws/adaptor.go

@@ -20,6 +20,11 @@ type Adaptor struct {
 	RequestMode int
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 	if strings.HasPrefix(info.UpstreamModelName, "claude-3") {
 		a.RequestMode = RequestModeMessage
@@ -53,6 +58,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	return claudeReq, err
 }
 
+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) (*http.Response, error) {
 	return nil, nil
 }

relay/channel/aws/constants.go

@@ -7,6 +7,7 @@ var awsModelIDMap = map[string]string{
 	"claude-3-sonnet-20240229": "anthropic.claude-3-sonnet-20240229-v1:0",
 	"claude-3-opus-20240229":   "anthropic.claude-3-opus-20240229-v1:0",
 	"claude-3-haiku-20240307":  "anthropic.claude-3-haiku-20240307-v1:0",
+	"claude-3-5-sonnet-20240620": "anthropic.claude-3-5-sonnet-20240620-v1:0",
 }
 
 var ChannelName = "aws"

relay/channel/aws/relay-aws.go

@@ -14,6 +14,7 @@ import (
 	"one-api/relay/channel/claude"
 	relaycommon "one-api/relay/common"
 	"strings"
+	"time"
 
 	"github.com/aws/aws-sdk-go-v2/aws"
 	"github.com/aws/aws-sdk-go-v2/credentials"
@@ -156,6 +157,7 @@ func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode i
 	var usage relaymodel.Usage
 	var id string
 	var model string
+	isFirst := true
 	createdTime := common.GetTimestamp()
 	c.Stream(func(w io.Writer) bool {
 		event, ok := <-stream.Events()
@@ -166,6 +168,10 @@ func awsStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, requestMode i
 
 		switch v := event.(type) {
 		case *types.ResponseStreamMemberChunk:
+			if isFirst {
+				isFirst = false
+				info.FirstResponseTime = time.Now()
+			}
 			claudeResp := new(claude.ClaudeResponse)
 			err := json.NewDecoder(bytes.NewReader(v.Value.Bytes)).Decode(claudeResp)
 			if err != nil {

relay/channel/baidu/adaptor.go

@@ -2,6 +2,7 @@ package baidu
 
 import (
 	"errors"
+	"fmt"
 	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
@@ -15,44 +16,74 @@ import (
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	var fullRequestURL string
-	switch info.UpstreamModelName {
-	case "ERNIE-Bot-4":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions_pro"
-	case "ERNIE-Bot-8K":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_bot_8k"
-	case "ERNIE-Bot":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions"
-	case "ERNIE-Speed":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_speed"
-	case "ERNIE-Bot-turbo":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant"
-	case "BLOOMZ-7B":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/bloomz_7b1"
-	case "ERNIE-4.0-8K":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions_pro"
-	case "ERNIE-3.5-8K":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions"
-	case "ERNIE-Speed-8K":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_speed"
-	case "ERNIE-Character-8K":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-char-8k"
-	case "ERNIE-Functions-8K":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-func-8k"
-	case "ERNIE-Lite-8K-0922":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant"
-	case "Yi-34B-Chat":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/yi_34b_chat"
-	case "Embedding-V1":
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings/embedding-v1"
-	default:
-		fullRequestURL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/" + strings.ToLower(info.UpstreamModelName)
+	// https://cloud.baidu.com/doc/WENXINWORKSHOP/s/clntwmv7t
+	suffix := "chat/"
+	if strings.HasPrefix(info.UpstreamModelName, "Embedding") {
+		suffix = "embeddings/"
 	}
+	if strings.HasPrefix(info.UpstreamModelName, "bge-large") {
+		suffix = "embeddings/"
+	}
+	if strings.HasPrefix(info.UpstreamModelName, "tao-8k") {
+		suffix = "embeddings/"
+	}
+	switch info.UpstreamModelName {
+	case "ERNIE-4.0":
+		suffix += "completions_pro"
+	case "ERNIE-Bot-4":
+		suffix += "completions_pro"
+	case "ERNIE-Bot":
+		suffix += "completions"
+	case "ERNIE-Bot-turbo":
+		suffix += "eb-instant"
+	case "ERNIE-Speed":
+		suffix += "ernie_speed"
+	case "ERNIE-4.0-8K":
+		suffix += "completions_pro"
+	case "ERNIE-3.5-8K":
+		suffix += "completions"
+	case "ERNIE-3.5-8K-0205":
+		suffix += "ernie-3.5-8k-0205"
+	case "ERNIE-3.5-8K-1222":
+		suffix += "ernie-3.5-8k-1222"
+	case "ERNIE-Bot-8K":
+		suffix += "ernie_bot_8k"
+	case "ERNIE-3.5-4K-0205":
+		suffix += "ernie-3.5-4k-0205"
+	case "ERNIE-Speed-8K":
+		suffix += "ernie_speed"
+	case "ERNIE-Speed-128K":
+		suffix += "ernie-speed-128k"
+	case "ERNIE-Lite-8K-0922":
+		suffix += "eb-instant"
+	case "ERNIE-Lite-8K-0308":
+		suffix += "ernie-lite-8k"
+	case "ERNIE-Tiny-8K":
+		suffix += "ernie-tiny-8k"
+	case "BLOOMZ-7B":
+		suffix += "bloomz_7b1"
+	case "Embedding-V1":
+		suffix += "embedding-v1"
+	case "bge-large-zh":
+		suffix += "bge_large_zh"
+	case "bge-large-en":
+		suffix += "bge_large_en"
+	case "tao-8k":
+		suffix += "tao_8k"
+	default:
+		suffix += strings.ToLower(info.UpstreamModelName)
+	}
+	fullRequestURL := fmt.Sprintf("%s/rpc/2.0/ai_custom/v1/wenxinworkshop/%s", info.BaseUrl, suffix)
 	var accessToken string
 	var err error
 	if accessToken, err = getBaiduAccessToken(info.ApiKey); err != nil {
@@ -82,6 +113,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	}
 }
 
+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) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/baidu/constants.go

@@ -1,20 +1,22 @@
 package baidu
 
 var ModelList = []string{
-	"ERNIE-3.5-8K",
 	"ERNIE-4.0-8K",
+	"ERNIE-3.5-8K",
+	"ERNIE-3.5-8K-0205",
+	"ERNIE-3.5-8K-1222",
+	"ERNIE-Bot-8K",
+	"ERNIE-3.5-4K-0205",
 	"ERNIE-Speed-8K",
 	"ERNIE-Speed-128K",
-	"ERNIE-Lite-8K",
+	"ERNIE-Lite-8K-0922",
+	"ERNIE-Lite-8K-0308",
 	"ERNIE-Tiny-8K",
-	"ERNIE-Character-8K",
-	"ERNIE-Functions-8K",
-	//"ERNIE-Bot-4",
-	//"ERNIE-Bot-8K",
-	//"ERNIE-Bot",
-	//"ERNIE-Speed",
-	//"ERNIE-Bot-turbo",
+	"BLOOMZ-7B",
 	"Embedding-V1",
+	"bge-large-zh",
+	"bge-large-en",
+	"tao-8k",
 }
 
 var ChannelName = "baidu"

relay/channel/baidu/dto.go

@@ -11,9 +11,16 @@ type BaiduMessage struct {
 }
 
 type BaiduChatRequest struct {
-	Messages []BaiduMessage `json:"messages"`
-	Stream   bool           `json:"stream"`
-	UserId   string         `json:"user_id,omitempty"`
+	Messages        []BaiduMessage `json:"messages"`
+	Temperature     float64        `json:"temperature,omitempty"`
+	TopP            float64        `json:"top_p,omitempty"`
+	PenaltyScore    float64        `json:"penalty_score,omitempty"`
+	Stream          bool           `json:"stream,omitempty"`
+	System          string         `json:"system,omitempty"`
+	DisableSearch   bool           `json:"disable_search,omitempty"`
+	EnableCitation  bool           `json:"enable_citation,omitempty"`
+	MaxOutputTokens int            `json:"max_output_tokens,omitempty"`
+	UserId          string         `json:"user_id,omitempty"`
 }
 
 type Error struct {

relay/channel/baidu/relay-baidu.go

@@ -22,17 +22,27 @@ import (
 var baiduTokenStore sync.Map
 
 func requestOpenAI2Baidu(request dto.GeneralOpenAIRequest) *BaiduChatRequest {
-	messages := make([]BaiduMessage, 0, len(request.Messages))
+	baiduRequest := BaiduChatRequest{
+		Temperature:     request.Temperature,
+		TopP:            request.TopP,
+		PenaltyScore:    request.FrequencyPenalty,
+		Stream:          request.Stream,
+		DisableSearch:   false,
+		EnableCitation:  false,
+		MaxOutputTokens: int(request.MaxTokens),
+		UserId:          request.User,
+	}
 	for _, message := range request.Messages {
-		messages = append(messages, BaiduMessage{
-			Role:    message.Role,
-			Content: message.StringContent(),
-		})
-	}
-	return &BaiduChatRequest{
-		Messages: messages,
-		Stream:   request.Stream,
+		if message.Role == "system" {
+			baiduRequest.System = message.StringContent()
+		} else {
+			baiduRequest.Messages = append(baiduRequest.Messages, BaiduMessage{
+				Role:    message.Role,
+				Content: message.StringContent(),
+			})
+		}
 	}
+	return &baiduRequest
 }
 
 func responseBaidu2OpenAI(response *BaiduChatResponse) *dto.OpenAITextResponse {

relay/channel/claude/adaptor.go

@@ -21,6 +21,11 @@ type Adaptor struct {
 	RequestMode int
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 	if strings.HasPrefix(info.UpstreamModelName, "claude-3") {
 		a.RequestMode = RequestModeMessage
@@ -59,13 +64,17 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	}
 }
 
+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) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
-		err, usage = claudeStreamHandler(a.RequestMode, info.UpstreamModelName, info.PromptTokens, c, resp)
+		err, usage = claudeStreamHandler(c, resp, info, a.RequestMode)
 	} else {
 		err, usage = claudeHandler(a.RequestMode, c, resp, info.PromptTokens, info.UpstreamModelName)
 	}

relay/channel/claude/constants.go

@@ -8,6 +8,7 @@ var ModelList = []string{
 	"claude-3-sonnet-20240229",
 	"claude-3-opus-20240229",
 	"claude-3-haiku-20240307",
+	"claude-3-5-sonnet-20240620",
 }
 
 var ChannelName = "claude"

relay/channel/claude/relay-claude.go

@@ -8,9 +8,12 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/dto"
+	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
+	"time"
 )
 
 func stopReasonClaude2OpenAI(reason string) string {
@@ -246,7 +249,7 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
 	return &fullTextResponse
 }
 
-func claudeStreamHandler(requestMode int, modelName string, promptTokens int, c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+func claudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, requestMode int) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseId := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
 	var usage *dto.Usage
 	usage = &dto.Usage{}
@@ -265,8 +268,8 @@ func claudeStreamHandler(requestMode int, modelName string, promptTokens int, c
 		}
 		return 0, nil, nil
 	})
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
+	dataChan := make(chan string, 5)
+	stopChan := make(chan bool, 2)
 	go func() {
 		for scanner.Scan() {
 			data := scanner.Text()
@@ -274,14 +277,23 @@ func claudeStreamHandler(requestMode int, modelName string, promptTokens int, c
 				continue
 			}
 			data = strings.TrimPrefix(data, "data: ")
-			dataChan <- data
+			if !common.SafeSendStringTimeout(dataChan, data, constant.StreamingTimeout) {
+				// send data timeout, stop the stream
+				common.LogError(c, "send data timeout, stop the stream")
+				break
+			}
 		}
 		stopChan <- true
 	}()
+	isFirst := true
 	service.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
+			if isFirst {
+				isFirst = false
+				info.FirstResponseTime = time.Now()
+			}
 			// some implementations may add \r at the end of data
 			data = strings.TrimSuffix(data, "\r")
 			var claudeResponse ClaudeResponse
@@ -302,7 +314,7 @@ func claudeStreamHandler(requestMode int, modelName string, promptTokens int, c
 				if claudeResponse.Type == "message_start" {
 					// message_start, 获取usage
 					responseId = claudeResponse.Message.Id
-					modelName = claudeResponse.Message.Model
+					info.UpstreamModelName = claudeResponse.Message.Model
 					usage.PromptTokens = claudeUsage.InputTokens
 				} else if claudeResponse.Type == "content_block_delta" {
 					responseText += claudeResponse.Delta.Text
@@ -316,7 +328,7 @@ func claudeStreamHandler(requestMode int, modelName string, promptTokens int, c
 			//response.Id = responseId
 			response.Id = responseId
 			response.Created = createdTime
-			response.Model = modelName
+			response.Model = info.UpstreamModelName
 
 			jsonStr, err := json.Marshal(response)
 			if err != nil {
@@ -335,13 +347,13 @@ func claudeStreamHandler(requestMode int, modelName string, promptTokens int, c
 		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 	if requestMode == RequestModeCompletion {
-		usage, _ = service.ResponseText2Usage(responseText, modelName, promptTokens)
+		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
 	} else {
 		if usage.PromptTokens == 0 {
-			usage.PromptTokens = promptTokens
+			usage.PromptTokens = info.PromptTokens
 		}
 		if usage.CompletionTokens == 0 {
-			usage, _ = service.ResponseText2Usage(responseText, modelName, usage.PromptTokens)
+			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, usage.PromptTokens)
 		}
 	}
 	return nil, usage

relay/channel/cohere/adaptor.go

@@ -8,16 +8,24 @@ import (
 	"one-api/dto"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
 )
 
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-	return fmt.Sprintf("%s/v1/chat", info.BaseUrl), nil
+	if info.RelayMode == constant.RelayModeRerank {
+		return fmt.Sprintf("%s/v1/rerank", info.BaseUrl), nil
+	} else {
+		return fmt.Sprintf("%s/v1/chat", info.BaseUrl), nil
+	}
 }
 
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
@@ -34,11 +42,19 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
 
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return requestConvertRerank2Cohere(request), nil
+}
+
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
-	if info.IsStream {
-		err, usage = cohereStreamHandler(c, resp, info.UpstreamModelName, info.PromptTokens)
+	if info.RelayMode == constant.RelayModeRerank {
+		err, usage = cohereRerankHandler(c, resp, info)
 	} else {
-		err, usage = cohereHandler(c, resp, info.UpstreamModelName, info.PromptTokens)
+		if info.IsStream {
+			err, usage = cohereStreamHandler(c, resp, info)
+		} else {
+			err, usage = cohereHandler(c, resp, info.UpstreamModelName, info.PromptTokens)
+		}
 	}
 	return
 }

relay/channel/cohere/constant.go

@@ -2,6 +2,7 @@ package cohere
 
 var ModelList = []string{
 	"command-r", "command-r-plus", "command-light", "command-light-nightly", "command", "command-nightly",
+	"rerank-english-v3.0", "rerank-multilingual-v3.0", "rerank-english-v2.0", "rerank-multilingual-v2.0",
 }
 
 var ChannelName = "cohere"

relay/channel/cohere/dto.go

@@ -1,5 +1,7 @@
 package cohere
 
+import "one-api/dto"
+
 type CohereRequest struct {
 	Model       string        `json:"model"`
 	ChatHistory []ChatHistory `json:"chat_history"`
@@ -28,6 +30,19 @@ type CohereResponseResult struct {
 	Meta         CohereMeta `json:"meta"`
 }
 
+type CohereRerankRequest struct {
+	Documents       []any  `json:"documents"`
+	Query           string `json:"query"`
+	Model           string `json:"model"`
+	TopN            int    `json:"top_n"`
+	ReturnDocuments bool   `json:"return_documents"`
+}
+
+type CohereRerankResponseResult struct {
+	Results []dto.RerankResponseDocument `json:"results"`
+	Meta    CohereMeta                   `json:"meta"`
+}
+
 type CohereMeta struct {
 	//Tokens CohereTokens `json:"tokens"`
 	BilledUnits CohereBilledUnits `json:"billed_units"`

relay/channel/cohere/relay-cohere.go

@@ -9,8 +9,10 @@ import (
 	"net/http"
 	"one-api/common"
 	"one-api/dto"
+	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
+	"time"
 )
 
 func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
@@ -45,6 +47,20 @@ func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
 	return &cohereReq
 }
 
+func requestConvertRerank2Cohere(rerankRequest dto.RerankRequest) *CohereRerankRequest {
+	if rerankRequest.TopN == 0 {
+		rerankRequest.TopN = 1
+	}
+	cohereReq := CohereRerankRequest{
+		Query:           rerankRequest.Query,
+		Documents:       rerankRequest.Documents,
+		Model:           rerankRequest.Model,
+		TopN:            rerankRequest.TopN,
+		ReturnDocuments: true,
+	}
+	return &cohereReq
+}
+
 func stopReasonCohere2OpenAI(reason string) string {
 	switch reason {
 	case "COMPLETE":
@@ -56,7 +72,7 @@ func stopReasonCohere2OpenAI(reason string) string {
 	}
 }
 
-func cohereStreamHandler(c *gin.Context, resp *http.Response, modelName string, promptTokens int) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+func cohereStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseId := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
 	createdTime := common.GetTimestamp()
 	usage := &dto.Usage{}
@@ -84,9 +100,14 @@ func cohereStreamHandler(c *gin.Context, resp *http.Response, modelName string,
 		stopChan <- true
 	}()
 	service.SetEventStreamHeaders(c)
+	isFirst := true
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
+			if isFirst {
+				isFirst = false
+				info.FirstResponseTime = time.Now()
+			}
 			data = strings.TrimSuffix(data, "\r")
 			var cohereResp CohereResponse
 			err := json.Unmarshal([]byte(data), &cohereResp)
@@ -98,7 +119,7 @@ func cohereStreamHandler(c *gin.Context, resp *http.Response, modelName string,
 			openaiResp.Id = responseId
 			openaiResp.Created = createdTime
 			openaiResp.Object = "chat.completion.chunk"
-			openaiResp.Model = modelName
+			openaiResp.Model = info.UpstreamModelName
 			if cohereResp.IsFinished {
 				finishReason := stopReasonCohere2OpenAI(cohereResp.FinishReason)
 				openaiResp.Choices = []dto.ChatCompletionsStreamResponseChoice{
@@ -137,7 +158,7 @@ func cohereStreamHandler(c *gin.Context, resp *http.Response, modelName string,
 		}
 	})
 	if usage.PromptTokens == 0 {
-		usage, _ = service.ResponseText2Usage(responseText, modelName, promptTokens)
+		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
 	}
 	return nil, usage
 }
@@ -187,3 +208,42 @@ func cohereHandler(c *gin.Context, resp *http.Response, modelName string, prompt
 	_, err = c.Writer.Write(jsonResponse)
 	return nil, &usage
 }
+
+func cohereRerankHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	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
+	}
+	var cohereResp CohereRerankResponseResult
+	err = json.Unmarshal(responseBody, &cohereResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	usage := dto.Usage{}
+	if cohereResp.Meta.BilledUnits.InputTokens == 0 {
+		usage.PromptTokens = info.PromptTokens
+		usage.CompletionTokens = 0
+		usage.TotalTokens = info.PromptTokens
+	} else {
+		usage.PromptTokens = cohereResp.Meta.BilledUnits.InputTokens
+		usage.CompletionTokens = cohereResp.Meta.BilledUnits.OutputTokens
+		usage.TotalTokens = cohereResp.Meta.BilledUnits.InputTokens + cohereResp.Meta.BilledUnits.OutputTokens
+	}
+
+	var rerankResp dto.RerankResponse
+	rerankResp.Results = cohereResp.Results
+	rerankResp.Usage = usage
+
+	jsonResponse, err := json.Marshal(rerankResp)
+	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, &usage
+}

relay/channel/dify/adaptor.go

@@ -0,0 +1,65 @@
+package dify
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return fmt.Sprintf("%s/v1/chat-messages", info.BaseUrl), nil
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return requestOpenAI2Dify(*request), nil
+}
+
+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) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.IsStream {
+		err, usage = difyStreamHandler(c, resp, info)
+	} else {
+		err, usage = difyHandler(c, resp, info)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/dify/constants.go

@@ -0,0 +1,5 @@
+package dify
+
+var ModelList []string
+
+var ChannelName = "dify"

relay/channel/dify/dto.go

@@ -0,0 +1,35 @@
+package dify
+
+import "one-api/dto"
+
+type DifyChatRequest struct {
+	Inputs           map[string]interface{} `json:"inputs"`
+	Query            string                 `json:"query"`
+	ResponseMode     string                 `json:"response_mode"`
+	User             string                 `json:"user"`
+	AutoGenerateName bool                   `json:"auto_generate_name"`
+}
+
+type DifyMetaData struct {
+	Usage dto.Usage `json:"usage"`
+}
+
+type DifyData struct {
+	WorkflowId string `json:"workflow_id"`
+	NodeId     string `json:"node_id"`
+}
+
+type DifyChatCompletionResponse struct {
+	ConversationId string       `json:"conversation_id"`
+	Answers        string       `json:"answers"`
+	CreateAt       int64        `json:"create_at"`
+	MetaData       DifyMetaData `json:"metadata"`
+}
+
+type DifyChunkChatCompletionResponse struct {
+	Event          string       `json:"event"`
+	ConversationId string       `json:"conversation_id"`
+	Answer         string       `json:"answer"`
+	Data           DifyData     `json:"data"`
+	MetaData       DifyMetaData `json:"metadata"`
+}

relay/channel/dify/relay-dify.go

@@ -0,0 +1,155 @@
+package dify
+
+import (
+	"bufio"
+	"encoding/json"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/constant"
+	"one-api/dto"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+	"strings"
+)
+
+func requestOpenAI2Dify(request dto.GeneralOpenAIRequest) *DifyChatRequest {
+	content := ""
+	for _, message := range request.Messages {
+		if message.Role == "system" {
+			content += "SYSTEM: \n" + message.StringContent() + "\n"
+		} else if message.Role == "assistant" {
+			content += "ASSISTANT: \n" + message.StringContent() + "\n"
+		} else {
+			content += "USER: \n" + message.StringContent() + "\n"
+		}
+	}
+	mode := "blocking"
+	if request.Stream {
+		mode = "streaming"
+	}
+	user := request.User
+	if user == "" {
+		user = "api-user"
+	}
+	return &DifyChatRequest{
+		Inputs:           make(map[string]interface{}),
+		Query:            content,
+		ResponseMode:     mode,
+		User:             user,
+		AutoGenerateName: false,
+	}
+}
+
+func streamResponseDify2OpenAI(difyResponse DifyChunkChatCompletionResponse) *dto.ChatCompletionsStreamResponse {
+	response := dto.ChatCompletionsStreamResponse{
+		Object:  "chat.completion.chunk",
+		Created: common.GetTimestamp(),
+		Model:   "dify",
+	}
+	var choice dto.ChatCompletionsStreamResponseChoice
+	if constant.DifyDebug && difyResponse.Event == "workflow_started" {
+		choice.Delta.SetContentString("Workflow: " + difyResponse.Data.WorkflowId + "\n")
+	} else if constant.DifyDebug && difyResponse.Event == "node_started" {
+		choice.Delta.SetContentString("Node: " + difyResponse.Data.NodeId + "\n")
+	} else if difyResponse.Event == "message" {
+		choice.Delta.SetContentString(difyResponse.Answer)
+	}
+	response.Choices = append(response.Choices, choice)
+	return &response
+}
+
+func difyStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var responseText string
+	usage := &dto.Usage{}
+	scanner := bufio.NewScanner(resp.Body)
+	scanner.Split(bufio.ScanLines)
+
+	service.SetEventStreamHeaders(c)
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < 5 || !strings.HasPrefix(data, "data:") {
+			continue
+		}
+		data = strings.TrimPrefix(data, "data:")
+		var difyResponse DifyChunkChatCompletionResponse
+		err := json.Unmarshal([]byte(data), &difyResponse)
+		if err != nil {
+			common.SysError("error unmarshalling stream response: " + err.Error())
+			continue
+		}
+		var openaiResponse dto.ChatCompletionsStreamResponse
+		if difyResponse.Event == "message_end" {
+			usage = &difyResponse.MetaData.Usage
+			break
+		} else if difyResponse.Event == "error" {
+			break
+		} else {
+			openaiResponse = *streamResponseDify2OpenAI(difyResponse)
+			if len(openaiResponse.Choices) != 0 {
+				responseText += openaiResponse.Choices[0].Delta.GetContentString()
+			}
+		}
+		err = service.ObjectData(c, openaiResponse)
+		if err != nil {
+			common.SysError(err.Error())
+		}
+	}
+	if err := scanner.Err(); err != nil {
+		common.SysError("error reading stream: " + err.Error())
+	}
+	service.Done(c)
+	err := resp.Body.Close()
+	if err != nil {
+		//return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
+		common.SysError("close_response_body_failed: " + err.Error())
+	}
+	if usage.TotalTokens == 0 {
+		usage.PromptTokens = info.PromptTokens
+		usage.CompletionTokens, _ = service.CountTokenText("gpt-3.5-turbo", responseText)
+		usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
+	}
+	return nil, usage
+}
+
+func difyHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	var difyResponse DifyChatCompletionResponse
+	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, &difyResponse)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	fullTextResponse := dto.OpenAITextResponse{
+		Id:      difyResponse.ConversationId,
+		Object:  "chat.completion",
+		Created: common.GetTimestamp(),
+		Usage:   difyResponse.MetaData.Usage,
+	}
+	content, _ := json.Marshal(difyResponse.Answers)
+	choice := dto.OpenAITextResponseChoice{
+		Index: 0,
+		Message: dto.Message{
+			Role:    "assistant",
+			Content: content,
+		},
+		FinishReason: "stop",
+	}
+	fullTextResponse.Choices = append(fullTextResponse.Choices, choice)
+	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, &difyResponse.MetaData.Usage
+}

relay/channel/gemini/adaptor.go

@@ -15,32 +15,35 @@ import (
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 }
 
 // 定义一个映射，存储模型名称和对应的版本
 var modelVersionMap = map[string]string{
-    "gemini-1.5-pro-latest": "v1beta",
-    "gemini-1.5-flash-latest": "v1beta",
-    "gemini-ultra":   "v1beta",
+	"gemini-1.5-pro-latest":   "v1beta",
+	"gemini-1.5-flash-latest": "v1beta",
+	"gemini-ultra":            "v1beta",
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
-    // 从映射中获取模型名称对应的版本，如果找不到就使用 info.ApiVersion 或默认的版本 "v1"
-    version, beta := modelVersionMap[info.UpstreamModelName]
-    if !beta {
-        if info.ApiVersion != "" {
-            version = info.ApiVersion
-        } else {
-            version = "v1"
-        }
-    }
+	// 从映射中获取模型名称对应的版本，如果找不到就使用 info.ApiVersion 或默认的版本 "v1"
+	version, beta := modelVersionMap[info.UpstreamModelName]
+	if !beta {
+		if info.ApiVersion != "" {
+			version = info.ApiVersion
+		} else {
+			version = "v1"
+		}
+	}
 
-    action := "generateContent"
-    if info.IsStream {
-        action = "streamGenerateContent"
-    }
-    return fmt.Sprintf("%s/%s/models/%s:%s", info.BaseUrl, version, info.UpstreamModelName, action), nil
+	action := "generateContent"
+	if info.IsStream {
+		action = "streamGenerateContent"
+	}
+	return fmt.Sprintf("%s/%s/models/%s:%s", info.BaseUrl, version, info.UpstreamModelName, action), nil
 }
 
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
@@ -56,6 +59,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	return CovertGemini2OpenAI(*request), nil
 }
 
+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) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
@@ -63,7 +70,7 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		var responseText string
-		err, responseText = geminiChatStreamHandler(c, resp)
+		err, responseText = geminiChatStreamHandler(c, resp, info)
 		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
 	} else {
 		err, usage = geminiChatHandler(c, resp, info.PromptTokens, info.UpstreamModelName)

relay/channel/gemini/relay-gemini.go

@@ -7,10 +7,12 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/dto"
 	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
+	"time"
 
 	"github.com/gin-gonic/gin"
 )
@@ -160,10 +162,10 @@ func streamResponseGeminiChat2OpenAI(geminiResponse *GeminiChatResponse) *dto.Ch
 	return &response
 }
 
-func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, string) {
+func geminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, string) {
 	responseText := ""
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
+	dataChan := make(chan string, 5)
+	stopChan := make(chan bool, 2)
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
 		if atEOF && len(data) == 0 {
@@ -186,14 +188,23 @@ func geminiChatStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIEr
 			}
 			data = strings.TrimPrefix(data, "\"text\": \"")
 			data = strings.TrimSuffix(data, "\"")
-			dataChan <- data
+			if !common.SafeSendStringTimeout(dataChan, data, constant.StreamingTimeout) {
+				// send data timeout, stop the stream
+				common.LogError(c, "send data timeout, stop the stream")
+				break
+			}
 		}
 		stopChan <- true
 	}()
+	isFirst := true
 	service.SetEventStreamHeaders(c)
 	c.Stream(func(w io.Writer) bool {
 		select {
 		case data := <-dataChan:
+			if isFirst {
+				isFirst = false
+				info.FirstResponseTime = time.Now()
+			}
 			// this is used to prevent annoying \ related format bug
 			data = fmt.Sprintf("{\"content\": \"%s\"}", data)
 			type dummyStruct struct {

relay/channel/jina/adaptor.go

@@ -0,0 +1,64 @@
+package jina
+
+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"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	if info.RelayMode == constant.RelayModeRerank {
+		return fmt.Sprintf("%s/v1/rerank", info.BaseUrl), nil
+	} else if info.RelayMode == constant.RelayModeEmbeddings {
+		return fmt.Sprintf("%s/v1/embeddings ", info.BaseUrl), nil
+	}
+	return "", errors.New("invalid relay mode")
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.GeneralOpenAIRequest) (any, error) {
+	return request, nil
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return request, nil
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
+	if info.RelayMode == constant.RelayModeRerank {
+		err, usage = jinaRerankHandler(c, resp)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/jina/constant.go

@@ -0,0 +1,8 @@
+package jina
+
+var ModelList = []string{
+	"jina-clip-v1",
+	"jina-reranker-v2-base-multilingual",
+}
+
+var ChannelName = "jina"

relay/channel/jina/relay-jina.go

@@ -0,0 +1,35 @@
+package jina
+
+import (
+	"encoding/json"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/service"
+)
+
+func jinaRerankHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+	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
+	}
+	var jinaResp dto.RerankResponse
+	err = json.Unmarshal(responseBody, &jinaResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+
+	jsonResponse, err := json.Marshal(jinaResp)
+	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, &jinaResp.Usage
+}

relay/channel/ollama/adaptor.go

@@ -16,6 +16,9 @@ import (
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 }
 
@@ -45,6 +48,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	}
 }
 
+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) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
@@ -52,8 +59,10 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		var responseText string
-		err, responseText, _ = openai.OpenaiStreamHandler(c, resp, info.RelayMode)
-		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+		err, usage, responseText, _ = openai.OpenaiStreamHandler(c, resp, info)
+		if usage == nil || usage.TotalTokens == 0 || (usage.PromptTokens+usage.CompletionTokens) == 0 {
+			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+		}
 	} else {
 		if info.RelayMode == relayconstant.RelayModeEmbeddings {
 			err, usage = ollamaEmbeddingHandler(c, resp, info.PromptTokens, info.UpstreamModelName, info.RelayMode)

relay/channel/openai/adaptor.go

@@ -7,6 +7,7 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/dto"
 	"one-api/relay/channel"
 	"one-api/relay/channel/ai360"
@@ -19,11 +20,20 @@ import (
 )
 
 type Adaptor struct {
-	ChannelType int
+	ChannelType          int
+	SupportStreamOptions bool
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
 }
 
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 	a.ChannelType = info.ChannelType
+	a.SupportStreamOptions = info.SupportStreamOptions
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
@@ -71,6 +81,17 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	if request == nil {
 		return nil, errors.New("request is nil")
 	}
+	// 如果不支持StreamOptions，将StreamOptions设置为nil
+	if !a.SupportStreamOptions {
+		request.StreamOptions = nil
+	} else {
+		// 如果支持StreamOptions，且请求中没有设置StreamOptions，根据配置文件设置StreamOptions
+		if constant.ForceStreamOption {
+			request.StreamOptions = &dto.StreamOptions{
+				IncludeUsage: true,
+			}
+		}
+	}
 	return request, nil
 }
 
@@ -82,9 +103,11 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
 	if info.IsStream {
 		var responseText string
 		var toolCount int
-		err, responseText, toolCount = OpenaiStreamHandler(c, resp, info.RelayMode)
-		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
-		usage.CompletionTokens += toolCount * 7
+		err, usage, responseText, toolCount = OpenaiStreamHandler(c, resp, info)
+		if usage == nil || usage.TotalTokens == 0 || (usage.PromptTokens+usage.CompletionTokens) == 0 {
+			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+			usage.CompletionTokens += toolCount * 7
+		}
 	} else {
 		err, usage = OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 	}

relay/channel/openai/relay-openai.go

@@ -8,7 +8,9 @@ import (
 	"io"
 	"net/http"
 	"one-api/common"
+	"one-api/constant"
 	"one-api/dto"
+	relaycommon "one-api/relay/common"
 	relayconstant "one-api/relay/constant"
 	"one-api/service"
 	"strings"
@@ -16,9 +18,10 @@ import (
 	"time"
 )
 
-func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*dto.OpenAIErrorWithStatusCode, string, int) {
+func OpenaiStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage, string, int) {
 	//checkSensitive := constant.ShouldCheckCompletionSensitive()
 	var responseTextBuilder strings.Builder
+	var usage dto.Usage
 	toolCount := 0
 	scanner := bufio.NewScanner(resp.Body)
 	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
@@ -50,23 +53,36 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*d
 			if data[:6] != "data: " && data[:6] != "[DONE]" {
 				continue
 			}
-			common.SafeSendString(dataChan, data)
+			if !common.SafeSendStringTimeout(dataChan, data, constant.StreamingTimeout) {
+				// send data timeout, stop the stream
+				common.LogError(c, "send data timeout, stop the stream")
+				break
+			}
 			data = data[6:]
 			if !strings.HasPrefix(data, "[DONE]") {
 				streamItems = append(streamItems, data)
 			}
 		}
+		// 计算token
 		streamResp := "[" + strings.Join(streamItems, ",") + "]"
-		switch relayMode {
+		switch info.RelayMode {
 		case relayconstant.RelayModeChatCompletions:
 			var streamResponses []dto.ChatCompletionsStreamResponseSimple
 			err := json.Unmarshal(common.StringToByteSlice(streamResp), &streamResponses)
 			if err != nil {
+				// 一次性解析失败，逐个解析
 				common.SysError("error unmarshalling stream response: " + err.Error())
 				for _, item := range streamItems {
 					var streamResponse dto.ChatCompletionsStreamResponseSimple
 					err := json.Unmarshal(common.StringToByteSlice(item), &streamResponse)
 					if err == nil {
+						if streamResponse.Usage != nil {
+							if streamResponse.Usage.TotalTokens != 0 {
+								usage.PromptTokens += streamResponse.Usage.PromptTokens
+								usage.CompletionTokens += streamResponse.Usage.CompletionTokens
+								usage.TotalTokens += streamResponse.Usage.TotalTokens
+							}
+						}
 						for _, choice := range streamResponse.Choices {
 							responseTextBuilder.WriteString(choice.Delta.GetContentString())
 							if choice.Delta.ToolCalls != nil {
@@ -83,6 +99,13 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*d
 				}
 			} else {
 				for _, streamResponse := range streamResponses {
+					if streamResponse.Usage != nil {
+						if streamResponse.Usage.TotalTokens != 0 {
+							usage.PromptTokens += streamResponse.Usage.PromptTokens
+							usage.CompletionTokens += streamResponse.Usage.CompletionTokens
+							usage.TotalTokens += streamResponse.Usage.TotalTokens
+						}
+					}
 					for _, choice := range streamResponse.Choices {
 						responseTextBuilder.WriteString(choice.Delta.GetContentString())
 						if choice.Delta.ToolCalls != nil {
@@ -101,6 +124,7 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*d
 			var streamResponses []dto.CompletionsStreamResponse
 			err := json.Unmarshal(common.StringToByteSlice(streamResp), &streamResponses)
 			if err != nil {
+				// 一次性解析失败，逐个解析
 				common.SysError("error unmarshalling stream response: " + err.Error())
 				for _, item := range streamItems {
 					var streamResponse dto.CompletionsStreamResponse
@@ -126,9 +150,20 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*d
 		common.SafeSendBool(stopChan, true)
 	}()
 	service.SetEventStreamHeaders(c)
+	isFirst := true
+	ticker := time.NewTicker(time.Duration(constant.StreamingTimeout) * time.Second)
+	defer ticker.Stop()
 	c.Stream(func(w io.Writer) bool {
 		select {
+		case <-ticker.C:
+			common.LogError(c, "reading data from upstream timeout")
+			return false
 		case data := <-dataChan:
+			if isFirst {
+				isFirst = false
+				info.FirstResponseTime = time.Now()
+			}
+			ticker.Reset(time.Duration(constant.StreamingTimeout) * time.Second)
 			if strings.HasPrefix(data, "data: [DONE]") {
 				data = data[:12]
 			}
@@ -142,10 +177,10 @@ func OpenaiStreamHandler(c *gin.Context, resp *http.Response, relayMode int) (*d
 	})
 	err := resp.Body.Close()
 	if err != nil {
-		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), "", toolCount
+		return service.OpenAIErrorWrapperLocal(err, "close_response_body_failed", http.StatusInternalServerError), nil, "", toolCount
 	}
 	wg.Wait()
-	return nil, responseTextBuilder.String(), toolCount
+	return nil, &usage, responseTextBuilder.String(), toolCount
 }
 
 func OpenaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
@@ -187,7 +222,7 @@ func OpenaiHandler(c *gin.Context, resp *http.Response, promptTokens int, model
 		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
 	}
 
-	if simpleResponse.Usage.TotalTokens == 0 {
+	if simpleResponse.Usage.TotalTokens == 0 || (simpleResponse.Usage.PromptTokens == 0 && simpleResponse.Usage.CompletionTokens == 0) {
 		completionTokens := 0
 		for _, choice := range simpleResponse.Choices {
 			ctkm, _ := service.CountTokenText(string(choice.Message.Content), model)

relay/channel/palm/adaptor.go

@@ -15,6 +15,11 @@ import (
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 }
 
@@ -35,6 +40,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	return request, nil
 }
 
+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) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/perplexity/adaptor.go

@@ -16,6 +16,11 @@ import (
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 }
 
@@ -39,6 +44,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	return requestOpenAI2Perplexity(*request), nil
 }
 
+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) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
@@ -46,8 +55,10 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage *dto.Usage, err *dto.OpenAIErrorWithStatusCode) {
 	if info.IsStream {
 		var responseText string
-		err, responseText, _ = openai.OpenaiStreamHandler(c, resp, info.RelayMode)
-		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+		err, usage, responseText, _ = openai.OpenaiStreamHandler(c, resp, info)
+		if usage == nil || usage.TotalTokens == 0 || (usage.PromptTokens+usage.CompletionTokens) == 0 {
+			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+		}
 	} else {
 		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 	}

relay/channel/task/suno/adaptor.go

@@ -0,0 +1,172 @@
+package suno
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/constant"
+	"one-api/dto"
+	"one-api/relay/channel"
+	relaycommon "one-api/relay/common"
+	"one-api/service"
+	"strings"
+	"time"
+)
+
+type TaskAdaptor struct {
+	ChannelType int
+}
+
+func (a *TaskAdaptor) Init(info *relaycommon.TaskRelayInfo) {
+	a.ChannelType = info.ChannelType
+}
+
+func (a *TaskAdaptor) ValidateRequestAndSetAction(c *gin.Context, info *relaycommon.TaskRelayInfo) (taskErr *dto.TaskError) {
+	action := strings.ToUpper(c.Param("action"))
+
+	var sunoRequest *dto.SunoSubmitReq
+	err := common.UnmarshalBodyReusable(c, &sunoRequest)
+	if err != nil {
+		taskErr = service.TaskErrorWrapperLocal(err, "invalid_request", http.StatusBadRequest)
+		return
+	}
+	err = actionValidate(c, sunoRequest, action)
+	if err != nil {
+		taskErr = service.TaskErrorWrapperLocal(err, "invalid_request", http.StatusBadRequest)
+		return
+	}
+
+	if sunoRequest.ContinueClipId != "" {
+		if sunoRequest.TaskID == "" {
+			taskErr = service.TaskErrorWrapperLocal(fmt.Errorf("task id is empty"), "invalid_request", http.StatusBadRequest)
+			return
+		}
+		info.OriginTaskID = sunoRequest.TaskID
+	}
+
+	info.Action = action
+	c.Set("task_request", sunoRequest)
+	return nil
+}
+
+func (a *TaskAdaptor) BuildRequestURL(info *relaycommon.TaskRelayInfo) (string, error) {
+	baseURL := info.BaseUrl
+	fullRequestURL := fmt.Sprintf("%s%s", baseURL, "/suno/submit/"+info.Action)
+	return fullRequestURL, nil
+}
+
+func (a *TaskAdaptor) BuildRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.TaskRelayInfo) error {
+	req.Header.Set("Content-Type", c.Request.Header.Get("Content-Type"))
+	req.Header.Set("Accept", c.Request.Header.Get("Accept"))
+	req.Header.Set("Authorization", "Bearer "+info.ApiKey)
+	return nil
+}
+
+func (a *TaskAdaptor) BuildRequestBody(c *gin.Context, info *relaycommon.TaskRelayInfo) (io.Reader, error) {
+	sunoRequest, ok := c.Get("task_request")
+	if !ok {
+		err := common.UnmarshalBodyReusable(c, &sunoRequest)
+		if err != nil {
+			return nil, err
+		}
+	}
+	data, err := json.Marshal(sunoRequest)
+	if err != nil {
+		return nil, err
+	}
+	return bytes.NewReader(data), nil
+}
+
+func (a *TaskAdaptor) DoRequest(c *gin.Context, info *relaycommon.TaskRelayInfo, requestBody io.Reader) (*http.Response, error) {
+	return channel.DoTaskApiRequest(a, c, info, requestBody)
+}
+
+func (a *TaskAdaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.TaskRelayInfo) (taskID string, taskData []byte, taskErr *dto.TaskError) {
+	responseBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		taskErr = service.TaskErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError)
+		return
+	}
+	var sunoResponse dto.TaskResponse[string]
+	err = json.Unmarshal(responseBody, &sunoResponse)
+	if err != nil {
+		taskErr = service.TaskErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError)
+		return
+	}
+	if !sunoResponse.IsSuccess() {
+		taskErr = service.TaskErrorWrapper(fmt.Errorf(sunoResponse.Message), sunoResponse.Code, http.StatusInternalServerError)
+		return
+	}
+
+	for k, v := range resp.Header {
+		c.Writer.Header().Set(k, v[0])
+	}
+	c.Writer.Header().Set("Content-Type", "application/json")
+	c.Writer.WriteHeader(resp.StatusCode)
+
+	_, err = io.Copy(c.Writer, bytes.NewBuffer(responseBody))
+	if err != nil {
+		taskErr = service.TaskErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError)
+		return
+	}
+
+	return sunoResponse.Data, nil, nil
+}
+
+func (a *TaskAdaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *TaskAdaptor) GetChannelName() string {
+	return ChannelName
+}
+
+func (a *TaskAdaptor) FetchTask(baseUrl, key string, body map[string]any) (*http.Response, error) {
+	requestUrl := fmt.Sprintf("%s/suno/fetch", baseUrl)
+	byteBody, err := json.Marshal(body)
+	if err != nil {
+		return nil, err
+	}
+
+	req, err := http.NewRequest("POST", requestUrl, bytes.NewBuffer(byteBody))
+	if err != nil {
+		common.SysError(fmt.Sprintf("Get Task error: %v", err))
+		return nil, err
+	}
+	defer req.Body.Close()
+	// 设置超时时间
+	timeout := time.Second * 15
+	ctx, cancel := context.WithTimeout(context.Background(), timeout)
+	defer cancel()
+	// 使用带有超时的 context 创建新的请求
+	req = req.WithContext(ctx)
+	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Authorization", "Bearer "+key)
+	resp, err := service.GetHttpClient().Do(req)
+	if err != nil {
+		return nil, err
+	}
+	return resp, nil
+}
+
+func actionValidate(c *gin.Context, sunoRequest *dto.SunoSubmitReq, action string) (err error) {
+	switch action {
+	case constant.SunoActionMusic:
+		if sunoRequest.Mv == "" {
+			sunoRequest.Mv = "chirp-v3-0"
+		}
+	case constant.SunoActionLyrics:
+		if sunoRequest.Prompt == "" {
+			err = fmt.Errorf("prompt_empty")
+			return
+		}
+	default:
+		err = fmt.Errorf("invalid_action")
+	}
+	return
+}

relay/channel/task/suno/models.go

@@ -0,0 +1,7 @@
+package suno
+
+var ModelList = []string{
+	"suno_music", "suno_lyrics",
+}
+
+var ChannelName = "suno"

relay/channel/tencent/adaptor.go

@@ -6,18 +6,31 @@ import (
 	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
+	"one-api/common"
 	"one-api/dto"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
 	"one-api/service"
+	"strconv"
 	"strings"
 )
 
 type Adaptor struct {
-	Sign string
+	Sign      string
+	Action    string
+	Version   string
+	Timestamp int64
+}
+
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
 }
 
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
+	a.Action = "ChatCompletions"
+	a.Version = "2023-09-01"
+	a.Timestamp = common.GetTimestamp()
 }
 
 func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
@@ -27,7 +40,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
 func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
 	channel.SetupApiRequestHeader(info, c, req)
 	req.Header.Set("Authorization", a.Sign)
-	req.Header.Set("X-TC-Action", info.UpstreamModelName)
+	req.Header.Set("X-TC-Action", a.Action)
+	req.Header.Set("X-TC-Version", a.Version)
+	req.Header.Set("X-TC-Timestamp", strconv.FormatInt(a.Timestamp, 10))
 	return nil
 }
 
@@ -37,18 +52,20 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	}
 	apiKey := c.Request.Header.Get("Authorization")
 	apiKey = strings.TrimPrefix(apiKey, "Bearer ")
-	appId, secretId, secretKey, err := parseTencentConfig(apiKey)
+	_, secretId, secretKey, err := parseTencentConfig(apiKey)
 	if err != nil {
 		return nil, err
 	}
 	tencentRequest := requestOpenAI2Tencent(*request)
-	tencentRequest.AppId = appId
-	tencentRequest.SecretId = secretId
 	// we have to calculate the sign here
-	a.Sign = getTencentSign(*tencentRequest, secretKey)
+	a.Sign = getTencentSign(*tencentRequest, a, secretId, secretKey)
 	return tencentRequest, nil
 }
 
+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) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/tencent/constants.go

@@ -1,9 +1,10 @@
 package tencent
 
 var ModelList = []string{
-	"ChatPro",
-	"ChatStd",
-	"hunyuan",
+	"hunyuan-lite",
+	"hunyuan-standard",
+	"hunyuan-standard-256K",
+	"hunyuan-pro",
 }
 
 var ChannelName = "tencent"

relay/channel/tencent/dto.go

@@ -1,61 +1,71 @@
 package tencent
 
-import "one-api/dto"
-
 type TencentMessage struct {
-	Role    string `json:"role"`
-	Content string `json:"content"`
+	Role    string `json:"Role"`
+	Content string `json:"Content"`
 }
 
 type TencentChatRequest struct {
-	AppId    int64  `json:"app_id"`    // 腾讯云账号的 APPID
-	SecretId string `json:"secret_id"` // 官网 SecretId
-	// Timestamp当前 UNIX 时间戳，单位为秒，可记录发起 API 请求的时间。
-	// 例如1529223702，如果与当前时间相差过大，会引起签名过期错误
-	Timestamp int64 `json:"timestamp"`
-	// Expired 签名的有效期，是一个符合 UNIX Epoch 时间戳规范的数值，
-	// 单位为秒；Expired 必须大于 Timestamp 且 Expired-Timestamp 小于90天
-	Expired int64  `json:"expired"`
-	QueryID string `json:"query_id"` //请求 Id，用于问题排查
-	// Temperature 较高的数值会使输出更加随机，而较低的数值会使其更加集中和确定
-	// 默认 1.0，取值区间为[0.0,2.0]，非必要不建议使用,不合理的取值会影响效果
-	// 建议该参数和 top_p 只设置1个，不要同时更改 top_p
-	Temperature float64 `json:"temperature"`
-	// TopP 影响输出文本的多样性，取值越大，生成文本的多样性越强
-	// 默认1.0，取值区间为[0.0, 1.0]，非必要不建议使用, 不合理的取值会影响效果
-	// 建议该参数和 temperature 只设置1个，不要同时更改
-	TopP float64 `json:"top_p"`
-	// Stream 0：同步，1：流式 （默认，协议：SSE)
-	// 同步请求超时：60s，如果内容较长建议使用流式
-	Stream int `json:"stream"`
-	// Messages 会话内容, 长度最多为40, 按对话时间从旧到新在数组中排列
-	// 输入 content 总数最大支持 3000 token。
-	Messages []TencentMessage `json:"messages"`
+	// 模型名称，可选值包括 hunyuan-lite、hunyuan-standard、hunyuan-standard-256K、hunyuan-pro。
+	// 各模型介绍请阅读 [产品概述](https://cloud.tencent.com/document/product/1729/104753) 中的说明。
+	//
+	// 注意：
+	// 不同的模型计费不同，请根据 [购买指南](https://cloud.tencent.com/document/product/1729/97731) 按需调用。
+	Model *string `json:"Model"`
+	// 聊天上下文信息。
+	// 说明：
+	// 1. 长度最多为 40，按对话时间从旧到新在数组中排列。
+	// 2. Message.Role 可选值：system、user、assistant。
+	// 其中，system 角色可选，如存在则必须位于列表的最开始。user 和 assistant 需交替出现（一问一答），以 user 提问开始和结束，且 Content 不能为空。Role 的顺序示例：[system（可选） user assistant user assistant user ...]。
+	// 3. Messages 中 Content 总长度不能超过模型输入长度上限（可参考 [产品概述](https://cloud.tencent.com/document/product/1729/104753) 文档），超过则会截断最前面的内容，只保留尾部内容。
+	Messages []*TencentMessage `json:"Messages"`
+	// 流式调用开关。
+	// 说明：
+	// 1. 未传值时默认为非流式调用（false）。
+	// 2. 流式调用时以 SSE 协议增量返回结果（返回值取 Choices[n].Delta 中的值，需要拼接增量数据才能获得完整结果）。
+	// 3. 非流式调用时：
+	// 调用方式与普通 HTTP 请求无异。
+	// 接口响应耗时较长，**如需更低时延建议设置为 true**。
+	// 只返回一次最终结果（返回值取 Choices[n].Message 中的值）。
+	//
+	// 注意：
+	// 通过 SDK 调用时，流式和非流式调用需用**不同的方式**获取返回值，具体参考 SDK 中的注释或示例（在各语言 SDK 代码仓库的 examples/hunyuan/v20230901/ 目录中）。
+	Stream *bool `json:"Stream"`
+	// 说明：
+	// 1. 影响输出文本的多样性，取值越大，生成文本的多样性越强。
+	// 2. 取值区间为 [0.0, 1.0]，未传值时使用各模型推荐值。
+	// 3. 非必要不建议使用，不合理的取值会影响效果。
+	TopP *float64 `json:"TopP"`
+	// 说明：
+	// 1. 较高的数值会使输出更加随机，而较低的数值会使其更加集中和确定。
+	// 2. 取值区间为 [0.0, 2.0]，未传值时使用各模型推荐值。
+	// 3. 非必要不建议使用，不合理的取值会影响效果。
+	Temperature *float64 `json:"Temperature"`
 }
 
 type TencentError struct {
-	Code    int    `json:"code"`
-	Message string `json:"message"`
+	Code    int    `json:"Code"`
+	Message string `json:"Message"`
 }
 
 type TencentUsage struct {
-	InputTokens  int `json:"input_tokens"`
-	OutputTokens int `json:"output_tokens"`
-	TotalTokens  int `json:"total_tokens"`
+	PromptTokens     int `json:"PromptTokens"`
+	CompletionTokens int `json:"CompletionTokens"`
+	TotalTokens      int `json:"TotalTokens"`
 }
 
 type TencentResponseChoices struct {
-	FinishReason string         `json:"finish_reason,omitempty"` // 流式结束标志位，为 stop 则表示尾包
-	Messages     TencentMessage `json:"messages,omitempty"`      // 内容，同步模式返回内容，流模式为 null 输出 content 内容总数最多支持 1024token。
-	Delta        TencentMessage `json:"delta,omitempty"`         // 内容，流模式返回内容，同步模式为 null 输出 content 内容总数最多支持 1024token。
+	FinishReason string         `json:"FinishReason,omitempty"` // 流式结束标志位，为 stop 则表示尾包
+	Messages     TencentMessage `json:"Message,omitempty"`      // 内容，同步模式返回内容，流模式为 null 输出 content 内容总数最多支持 1024token。
+	Delta        TencentMessage `json:"Delta,omitempty"`        // 内容，流模式返回内容，同步模式为 null 输出 content 内容总数最多支持 1024token。
 }
 
 type TencentChatResponse struct {
-	Choices []TencentResponseChoices `json:"choices,omitempty"` // 结果
-	Created string                   `json:"created,omitempty"` // unix 时间戳的字符串
-	Id      string                   `json:"id,omitempty"`      // 会话 id
-	Usage   dto.Usage                `json:"usage,omitempty"`   // token 数量
-	Error   TencentError             `json:"error,omitempty"`   // 错误信息 注意：此字段可能返回 null，表示取不到有效值
-	Note    string                   `json:"note,omitempty"`    // 注释
-	ReqID   string                   `json:"req_id,omitempty"`  // 唯一请求 Id，每次请求都会返回。用于反馈接口入参
+	Choices []TencentResponseChoices `json:"Choices,omitempty"` // 结果
+	Created int64                    `json:"Created,omitempty"` // unix 时间戳的字符串
+	Id      string                   `json:"Id,omitempty"`      // 会话 id
+	Usage   TencentUsage             `json:"Usage,omitempty"`   // token 数量
+	Error   TencentError             `json:"Error,omitempty"`   // 错误信息 注意：此字段可能返回 null，表示取不到有效值
+	Note    string                   `json:"Note,omitempty"`    // 注释
+	ReqID   string                   `json:"Req_id,omitempty"`  // 唯一请求 Id，每次请求都会返回。用于反馈接口入参
 }

relay/channel/tencent/relay-tencent.go

@@ -3,8 +3,8 @@ package tencent
 import (
 	"bufio"
 	"crypto/hmac"
-	"crypto/sha1"
-	"encoding/base64"
+	"crypto/sha256"
+	"encoding/hex"
 	"encoding/json"
 	"errors"
 	"fmt"
@@ -15,45 +15,28 @@ import (
 	"one-api/dto"
 	relaycommon "one-api/relay/common"
 	"one-api/service"
-	"sort"
 	"strconv"
 	"strings"
+	"time"
 )
 
 // https://cloud.tencent.com/document/product/1729/97732
 
 func requestOpenAI2Tencent(request dto.GeneralOpenAIRequest) *TencentChatRequest {
-	messages := make([]TencentMessage, 0, len(request.Messages))
+	messages := make([]*TencentMessage, 0, len(request.Messages))
 	for i := 0; i < len(request.Messages); i++ {
 		message := request.Messages[i]
-		if message.Role == "system" {
-			messages = append(messages, TencentMessage{
-				Role:    "user",
-				Content: message.StringContent(),
-			})
-			messages = append(messages, TencentMessage{
-				Role:    "assistant",
-				Content: "Okay",
-			})
-			continue
-		}
-		messages = append(messages, TencentMessage{
+		messages = append(messages, &TencentMessage{
 			Content: message.StringContent(),
 			Role:    message.Role,
 		})
 	}
-	stream := 0
-	if request.Stream {
-		stream = 1
-	}
 	return &TencentChatRequest{
-		Timestamp:   common.GetTimestamp(),
-		Expired:     common.GetTimestamp() + 24*60*60,
-		QueryID:     common.GetUUID(),
-		Temperature: request.Temperature,
-		TopP:        request.TopP,
-		Stream:      stream,
+		Temperature: &request.Temperature,
+		TopP:        &request.TopP,
+		Stream:      &request.Stream,
 		Messages:    messages,
+		Model:       &request.Model,
 	}
 }
 
@@ -61,7 +44,11 @@ func responseTencent2OpenAI(response *TencentChatResponse) *dto.OpenAITextRespon
 	fullTextResponse := dto.OpenAITextResponse{
 		Object:  "chat.completion",
 		Created: common.GetTimestamp(),
-		Usage:   response.Usage,
+		Usage: dto.Usage{
+			PromptTokens:     response.Usage.PromptTokens,
+			CompletionTokens: response.Usage.CompletionTokens,
+			TotalTokens:      response.Usage.TotalTokens,
+		},
 	}
 	if len(response.Choices) > 0 {
 		content, _ := json.Marshal(response.Choices[0].Messages.Content)
@@ -98,64 +85,46 @@ func streamResponseTencent2OpenAI(TencentResponse *TencentChatResponse) *dto.Cha
 func tencentStreamHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, string) {
 	var responseText string
 	scanner := bufio.NewScanner(resp.Body)
-	scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
-		if atEOF && len(data) == 0 {
-			return 0, nil, nil
-		}
-		if i := strings.Index(string(data), "\n"); i >= 0 {
-			return i + 1, data[0:i], nil
-		}
-		if atEOF {
-			return len(data), data, nil
-		}
-		return 0, nil, nil
-	})
-	dataChan := make(chan string)
-	stopChan := make(chan bool)
-	go func() {
-		for scanner.Scan() {
-			data := scanner.Text()
-			if len(data) < 5 { // ignore blank line or wrong format
-				continue
-			}
-			if data[:5] != "data:" {
-				continue
-			}
-			data = data[5:]
-			dataChan <- data
-		}
-		stopChan <- true
-	}()
+	scanner.Split(bufio.ScanLines)
+
 	service.SetEventStreamHeaders(c)
-	c.Stream(func(w io.Writer) bool {
-		select {
-		case data := <-dataChan:
-			var TencentResponse TencentChatResponse
-			err := json.Unmarshal([]byte(data), &TencentResponse)
-			if err != nil {
-				common.SysError("error unmarshalling stream response: " + err.Error())
-				return true
-			}
-			response := streamResponseTencent2OpenAI(&TencentResponse)
-			if len(response.Choices) != 0 {
-				responseText += response.Choices[0].Delta.GetContentString()
-			}
-			jsonResponse, err := json.Marshal(response)
-			if err != nil {
-				common.SysError("error marshalling stream response: " + err.Error())
-				return true
-			}
-			c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
-			return true
-		case <-stopChan:
-			c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
-			return false
+
+	for scanner.Scan() {
+		data := scanner.Text()
+		if len(data) < 5 || !strings.HasPrefix(data, "data:") {
+			continue
 		}
-	})
+		data = strings.TrimPrefix(data, "data:")
+
+		var tencentResponse TencentChatResponse
+		err := json.Unmarshal([]byte(data), &tencentResponse)
+		if err != nil {
+			common.SysError("error unmarshalling stream response: " + err.Error())
+			continue
+		}
+
+		response := streamResponseTencent2OpenAI(&tencentResponse)
+		if len(response.Choices) != 0 {
+			responseText += response.Choices[0].Delta.GetContentString()
+		}
+
+		err = service.ObjectData(c, response)
+		if err != nil {
+			common.SysError(err.Error())
+		}
+	}
+
+	if err := scanner.Err(); err != nil {
+		common.SysError("error reading stream: " + err.Error())
+	}
+
+	service.Done(c)
+
 	err := resp.Body.Close()
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), ""
 	}
+
 	return nil, responseText
 }
 
@@ -205,29 +174,62 @@ func parseTencentConfig(config string) (appId int64, secretId string, secretKey
 	return
 }
 
-func getTencentSign(req TencentChatRequest, secretKey string) string {
-	params := make([]string, 0)
-	params = append(params, "app_id="+strconv.FormatInt(req.AppId, 10))
-	params = append(params, "secret_id="+req.SecretId)
-	params = append(params, "timestamp="+strconv.FormatInt(req.Timestamp, 10))
-	params = append(params, "query_id="+req.QueryID)
-	params = append(params, "temperature="+strconv.FormatFloat(req.Temperature, 'f', -1, 64))
-	params = append(params, "top_p="+strconv.FormatFloat(req.TopP, 'f', -1, 64))
-	params = append(params, "stream="+strconv.Itoa(req.Stream))
-	params = append(params, "expired="+strconv.FormatInt(req.Expired, 10))
-
-	var messageStr string
-	for _, msg := range req.Messages {
-		messageStr += fmt.Sprintf(`{"role":"%s","content":"%s"},`, msg.Role, msg.Content)
-	}
-	messageStr = strings.TrimSuffix(messageStr, ",")
-	params = append(params, "messages=["+messageStr+"]")
-
-	sort.Sort(sort.StringSlice(params))
-	url := "hunyuan.cloud.tencent.com/hyllm/v1/chat/completions?" + strings.Join(params, "&")
-	mac := hmac.New(sha1.New, []byte(secretKey))
-	signURL := url
-	mac.Write([]byte(signURL))
-	sign := mac.Sum([]byte(nil))
-	return base64.StdEncoding.EncodeToString(sign)
+func sha256hex(s string) string {
+	b := sha256.Sum256([]byte(s))
+	return hex.EncodeToString(b[:])
+}
+
+func hmacSha256(s, key string) string {
+	hashed := hmac.New(sha256.New, []byte(key))
+	hashed.Write([]byte(s))
+	return string(hashed.Sum(nil))
+}
+
+func getTencentSign(req TencentChatRequest, adaptor *Adaptor, secId, secKey string) string {
+	// build canonical request string
+	host := "hunyuan.tencentcloudapi.com"
+	httpRequestMethod := "POST"
+	canonicalURI := "/"
+	canonicalQueryString := ""
+	canonicalHeaders := fmt.Sprintf("content-type:%s\nhost:%s\nx-tc-action:%s\n",
+		"application/json", host, strings.ToLower(adaptor.Action))
+	signedHeaders := "content-type;host;x-tc-action"
+	payload, _ := json.Marshal(req)
+	hashedRequestPayload := sha256hex(string(payload))
+	canonicalRequest := fmt.Sprintf("%s\n%s\n%s\n%s\n%s\n%s",
+		httpRequestMethod,
+		canonicalURI,
+		canonicalQueryString,
+		canonicalHeaders,
+		signedHeaders,
+		hashedRequestPayload)
+	// build string to sign
+	algorithm := "TC3-HMAC-SHA256"
+	requestTimestamp := strconv.FormatInt(adaptor.Timestamp, 10)
+	timestamp, _ := strconv.ParseInt(requestTimestamp, 10, 64)
+	t := time.Unix(timestamp, 0).UTC()
+	// must be the format 2006-01-02, ref to package time for more info
+	date := t.Format("2006-01-02")
+	credentialScope := fmt.Sprintf("%s/%s/tc3_request", date, "hunyuan")
+	hashedCanonicalRequest := sha256hex(canonicalRequest)
+	string2sign := fmt.Sprintf("%s\n%s\n%s\n%s",
+		algorithm,
+		requestTimestamp,
+		credentialScope,
+		hashedCanonicalRequest)
+
+	// sign string
+	secretDate := hmacSha256(date, "TC3"+secKey)
+	secretService := hmacSha256("hunyuan", secretDate)
+	secretKey := hmacSha256("tc3_request", secretService)
+	signature := hex.EncodeToString([]byte(hmacSha256(string2sign, secretKey)))
+
+	// build authorization
+	authorization := fmt.Sprintf("%s Credential=%s/%s, SignedHeaders=%s, Signature=%s",
+		algorithm,
+		secId,
+		credentialScope,
+		signedHeaders,
+		signature)
+	return authorization
 }

relay/channel/xunfei/adaptor.go

@@ -16,6 +16,11 @@ type Adaptor struct {
 	request *dto.GeneralOpenAIRequest
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 }
 
@@ -36,6 +41,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	return request, nil
 }
 
+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) (*http.Response, error) {
 	// xunfei's request is not http request, so we don't need to do anything here
 	dummyResp := &http.Response{}

relay/channel/xunfei/constants.go

@@ -6,6 +6,7 @@ var ModelList = []string{
 	"SparkDesk-v2.1",
 	"SparkDesk-v3.1",
 	"SparkDesk-v3.5",
+	"SparkDesk-v4.0",
 }
 
 var ChannelName = "xunfei"

relay/channel/xunfei/relay-xunfei.go

@@ -252,6 +252,8 @@ func apiVersion2domain(apiVersion string) string {
 		return "generalv3"
 	case "v3.5":
 		return "generalv3.5"
+	case "v4.0":
+		return "4.0Ultra"
 	}
 	return "general" + apiVersion
 }

relay/channel/zhipu/adaptor.go

@@ -14,6 +14,11 @@ import (
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 }
 
@@ -42,6 +47,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	return requestOpenAI2Zhipu(*request), nil
 }
 
+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) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }

relay/channel/zhipu_4v/adaptor.go

@@ -16,6 +16,11 @@ import (
 type Adaptor struct {
 }
 
+func (a *Adaptor) InitRerank(info *relaycommon.RelayInfo, request dto.RerankRequest) {
+	//TODO implement me
+
+}
+
 func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) {
 }
 
@@ -40,6 +45,10 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
 	return requestOpenAI2Zhipu(*request), nil
 }
 
+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) (*http.Response, error) {
 	return channel.DoApiRequest(a, c, info, requestBody)
 }
@@ -48,9 +57,11 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
 	if info.IsStream {
 		var responseText string
 		var toolCount int
-		err, responseText, toolCount = openai.OpenaiStreamHandler(c, resp, info.RelayMode)
-		usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
-		usage.CompletionTokens += toolCount * 7
+		err, usage, responseText, toolCount = openai.OpenaiStreamHandler(c, resp, info)
+		if usage == nil || usage.TotalTokens == 0 || (usage.PromptTokens+usage.CompletionTokens) == 0 {
+			usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
+			usage.CompletionTokens += toolCount * 7
+		}
 	} else {
 		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
 	}

relay/common/relay_info.go

@@ -9,23 +9,25 @@ import (
 )
 
 type RelayInfo struct {
-	ChannelType       int
-	ChannelId         int
-	TokenId           int
-	UserId            int
-	Group             string
-	TokenUnlimited    bool
-	StartTime         time.Time
-	ApiType           int
-	IsStream          bool
-	RelayMode         int
-	UpstreamModelName string
-	RequestURLPath    string
-	ApiVersion        string
-	PromptTokens      int
-	ApiKey            string
-	Organization      string
-	BaseUrl           string
+	ChannelType          int
+	ChannelId            int
+	TokenId              int
+	UserId               int
+	Group                string
+	TokenUnlimited       bool
+	StartTime            time.Time
+	FirstResponseTime    time.Time
+	ApiType              int
+	IsStream             bool
+	RelayMode            int
+	UpstreamModelName    string
+	RequestURLPath       string
+	ApiVersion           string
+	PromptTokens         int
+	ApiKey               string
+	Organization         string
+	BaseUrl              string
+	SupportStreamOptions bool
 }
 
 func GenRelayInfo(c *gin.Context) *RelayInfo {
@@ -37,24 +39,26 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
 	group := c.GetString("group")
 	tokenUnlimited := c.GetBool("token_unlimited_quota")
 	startTime := time.Now()
+	// firstResponseTime = time.Now() - 1 second
 
 	apiType, _ := constant.ChannelType2APIType(channelType)
 
 	info := &RelayInfo{
-		RelayMode:      constant.Path2RelayMode(c.Request.URL.Path),
-		BaseUrl:        c.GetString("base_url"),
-		RequestURLPath: c.Request.URL.String(),
-		ChannelType:    channelType,
-		ChannelId:      channelId,
-		TokenId:        tokenId,
-		UserId:         userId,
-		Group:          group,
-		TokenUnlimited: tokenUnlimited,
-		StartTime:      startTime,
-		ApiType:        apiType,
-		ApiVersion:     c.GetString("api_version"),
-		ApiKey:         strings.TrimPrefix(c.Request.Header.Get("Authorization"), "Bearer "),
-		Organization:   c.GetString("channel_organization"),
+		RelayMode:         constant.Path2RelayMode(c.Request.URL.Path),
+		BaseUrl:           c.GetString("base_url"),
+		RequestURLPath:    c.Request.URL.String(),
+		ChannelType:       channelType,
+		ChannelId:         channelId,
+		TokenId:           tokenId,
+		UserId:            userId,
+		Group:             group,
+		TokenUnlimited:    tokenUnlimited,
+		StartTime:         startTime,
+		FirstResponseTime: startTime.Add(-time.Second),
+		ApiType:           apiType,
+		ApiVersion:        c.GetString("api_version"),
+		ApiKey:            strings.TrimPrefix(c.Request.Header.Get("Authorization"), "Bearer "),
+		Organization:      c.GetString("channel_organization"),
 	}
 	if info.BaseUrl == "" {
 		info.BaseUrl = common.ChannelBaseURLs[channelType]
@@ -62,6 +66,9 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
 	if info.ChannelType == common.ChannelTypeAzure {
 		info.ApiVersion = GetAPIVersion(c)
 	}
+	if info.ChannelType == common.ChannelTypeOpenAI {
+		info.SupportStreamOptions = true
+	}
 	return info
 }
 
@@ -72,3 +79,53 @@ func (info *RelayInfo) SetPromptTokens(promptTokens int) {
 func (info *RelayInfo) SetIsStream(isStream bool) {
 	info.IsStream = isStream
 }
+
+type TaskRelayInfo struct {
+	ChannelType       int
+	ChannelId         int
+	TokenId           int
+	UserId            int
+	Group             string
+	StartTime         time.Time
+	ApiType           int
+	RelayMode         int
+	UpstreamModelName string
+	RequestURLPath    string
+	ApiKey            string
+	BaseUrl           string
+
+	Action       string
+	OriginTaskID string
+
+	ConsumeQuota bool
+}
+
+func GenTaskRelayInfo(c *gin.Context) *TaskRelayInfo {
+	channelType := c.GetInt("channel")
+	channelId := c.GetInt("channel_id")
+
+	tokenId := c.GetInt("token_id")
+	userId := c.GetInt("id")
+	group := c.GetString("group")
+	startTime := time.Now()
+
+	apiType, _ := constant.ChannelType2APIType(channelType)
+
+	info := &TaskRelayInfo{
+		RelayMode:      constant.Path2RelayMode(c.Request.URL.Path),
+		BaseUrl:        c.GetString("base_url"),
+		RequestURLPath: c.Request.URL.String(),
+		ChannelType:    channelType,
+		ChannelId:      channelId,
+		TokenId:        tokenId,
+		UserId:         userId,
+		Group:          group,
+		StartTime:      startTime,
+		ApiType:        apiType,
+		ApiKey:         strings.TrimPrefix(c.Request.Header.Get("Authorization"), "Bearer "),
+	}
+	if info.BaseUrl == "" {
+		info.BaseUrl = common.ChannelBaseURLs[channelType]
+	}
+	return info
+}

relay/constant/api_type.go

@@ -20,6 +20,8 @@ const (
 	APITypePerplexity
 	APITypeAws
 	APITypeCohere
+	APITypeDify
+	APITypeJina
 
 	APITypeDummy // this one is only for count, do not add any channel after this
 )
@@ -57,6 +59,10 @@ func ChannelType2APIType(channelType int) (int, bool) {
 		apiType = APITypeAws
 	case common.ChannelTypeCohere:
 		apiType = APITypeCohere
+	case common.ChannelTypeDify:
+		apiType = APITypeDify
+	case common.ChannelTypeJina:
+		apiType = APITypeJina
 	}
 	if apiType == -1 {
 		return APITypeOpenAI, false

relay/constant/relay_mode.go

@@ -1,6 +1,9 @@
 package constant
 
-import "strings"
+import (
+	"net/http"
+	"strings"
+)
 
 const (
 	RelayModeUnknown = iota
@@ -26,6 +29,10 @@ const (
 	RelayModeMidjourneyModal
 	RelayModeMidjourneyShorten
 	RelayModeSwapFace
+	RelayModeSunoFetch
+	RelayModeSunoFetchByID
+	RelayModeSunoSubmit
+	RelayModeRerank
 )
 
 func Path2RelayMode(path string) int {
@@ -50,6 +57,8 @@ func Path2RelayMode(path string) int {
 		relayMode = RelayModeAudioTranscription
 	} else if strings.HasPrefix(path, "/v1/audio/translations") {
 		relayMode = RelayModeAudioTranslation
+	} else if strings.HasPrefix(path, "/v1/rerank") {
+		relayMode = RelayModeRerank
 	}
 	return relayMode
 }
@@ -89,3 +98,15 @@ func Path2RelayModeMidjourney(path string) int {
 	}
 	return relayMode
 }
+
+func Path2RelaySuno(method, path string) int {
+	relayMode := RelayModeUnknown
+	if method == http.MethodPost && strings.HasSuffix(path, "/fetch") {
+		relayMode = RelayModeSunoFetch
+	} else if method == http.MethodGet && strings.Contains(path, "/fetch/") {
+		relayMode = RelayModeSunoFetchByID
+	} else if strings.Contains(path, "/submit/") {
+		relayMode = RelayModeSunoSubmit
+	}
+	return relayMode
+}

relay/relay-audio.go

@@ -73,14 +73,14 @@ func AudioHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
 	preConsumedQuota := int(float64(preConsumedTokens) * ratio)
 	userQuota, err := model.CacheGetUserQuota(userId)
 	if err != nil {
-		return service.OpenAIErrorWrapper(err, "get_user_quota_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapperLocal(err, "get_user_quota_failed", http.StatusInternalServerError)
 	}
 	if userQuota-preConsumedQuota < 0 {
-		return service.OpenAIErrorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
+		return service.OpenAIErrorWrapperLocal(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
 	}
 	err = model.CacheDecreaseUserQuota(userId, preConsumedQuota)
 	if err != nil {
-		return service.OpenAIErrorWrapper(err, "decrease_user_quota_failed", http.StatusInternalServerError)
+		return service.OpenAIErrorWrapperLocal(err, "decrease_user_quota_failed", http.StatusInternalServerError)
 	}
 	if userQuota > 100*preConsumedQuota {
 		// in this case, we do not pre-consume quota
@@ -90,7 +90,7 @@ func AudioHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
 	if preConsumedQuota > 0 {
 		userQuota, err = model.PreConsumeTokenQuota(tokenId, preConsumedQuota)
 		if err != nil {
-			return service.OpenAIErrorWrapper(err, "pre_consume_token_quota_failed", http.StatusForbidden)
+			return service.OpenAIErrorWrapperLocal(err, "pre_consume_token_quota_failed", http.StatusForbidden)
 		}
 	}
 

relay/relay-image.go

@@ -147,7 +147,7 @@ func RelayImageHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusC
 	quota := int(modelPrice*groupRatio*common.QuotaPerUnit*sizeRatio*qualityRatio) * imageRequest.N
 
 	if userQuota-quota < 0 {
-		return service.OpenAIErrorWrapper(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
+		return service.OpenAIErrorWrapperLocal(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
 	}
 
 	req, err := http.NewRequest(c.Request.Method, fullRequestURL, requestBody)

relay/relay-mj.go

@@ -500,7 +500,7 @@ func RelayMidjourneySubmit(c *gin.Context, relayMode int) *dto.MidjourneyRespons
 			}
 			if quota != 0 {
 				tokenName := c.GetString("token_name")
-				logContent := fmt.Sprintf("模型固定价格 %.2f，分组倍率 %.2f，操作 %s", modelPrice, groupRatio, midjRequest.Action)
+				logContent := fmt.Sprintf("模型固定价格 %.2f，分组倍率 %.2f，操作 %s，ID %s", modelPrice, groupRatio, midjRequest.Action, midjResponse.Result)
 				other := make(map[string]interface{})
 				other["model_price"] = modelPrice
 				other["group_ratio"] = groupRatio
@@ -538,7 +538,16 @@ func RelayMidjourneySubmit(c *gin.Context, relayMode int) *dto.MidjourneyRespons
 		ChannelId:   c.GetInt("channel_id"),
 		Quota:       quota,
 	}
-
+	if midjResponse.Code == 3 {
+		//无实例账号自动禁用渠道（No available account instance）
+		channel, err := model.GetChannelById(midjourneyTask.ChannelId, true)
+		if err != nil {
+			common.SysError("get_channel_null: " + err.Error())
+		}
+		if channel.AutoBan != nil && *channel.AutoBan == 1 && common.AutomaticDisableChannelEnabled {
+			model.UpdateChannelStatusById(midjourneyTask.ChannelId, 2, "No available account instance")
+		}
+	}
 	if midjResponse.Code != 1 && midjResponse.Code != 21 && midjResponse.Code != 22 {
 		//非1-提交成功,21-任务已存在和22-排队中，则记录错误原因
 		midjourneyTask.FailReason = midjResponse.Description

relay/relay-text.go

@@ -77,7 +77,7 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 
 	// map model name
 	modelMapping := c.GetString("model_mapping")
-	isModelMapped := false
+	//isModelMapped := false
 	if modelMapping != "" && modelMapping != "{}" {
 		modelMap := make(map[string]string)
 		err := json.Unmarshal([]byte(modelMapping), &modelMap)
@@ -87,7 +87,7 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 		if modelMap[textRequest.Model] != "" {
 			textRequest.Model = modelMap[textRequest.Model]
 			// set upstream model name
-			isModelMapped = true
+			//isModelMapped = true
 		}
 	}
 	relayInfo.UpstreamModelName = textRequest.Model
@@ -136,27 +136,16 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 	}
 	adaptor.Init(relayInfo, *textRequest)
 	var requestBody io.Reader
-	if relayInfo.ApiType == relayconstant.APITypeOpenAI {
-		if isModelMapped {
-			jsonStr, err := json.Marshal(textRequest)
-			if err != nil {
-				return service.OpenAIErrorWrapperLocal(err, "marshal_text_request_failed", http.StatusInternalServerError)
-			}
-			requestBody = bytes.NewBuffer(jsonStr)
-		} else {
-			requestBody = c.Request.Body
-		}
-	} else {
-		convertedRequest, err := adaptor.ConvertRequest(c, relayInfo.RelayMode, textRequest)
-		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)
+
+	convertedRequest, err := adaptor.ConvertRequest(c, relayInfo.RelayMode, textRequest)
+	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)
@@ -182,7 +171,7 @@ func TextHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
 		return openaiErr
 	}
-	postConsumeQuota(c, relayInfo, *textRequest, usage, ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, success)
+	postConsumeQuota(c, relayInfo, textRequest.Model, usage, ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, success)
 	return nil
 }
 
@@ -272,7 +261,7 @@ func returnPreConsumedQuota(c *gin.Context, tokenId int, userQuota int, preConsu
 	}
 }
 
-func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, textRequest dto.GeneralOpenAIRequest,
+func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelName string,
 	usage *dto.Usage, ratio float64, preConsumedQuota int, userQuota int, modelRatio float64, groupRatio float64,
 	modelPrice float64, usePrice bool) {
 
@@ -281,7 +270,7 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, textRe
 	completionTokens := usage.CompletionTokens
 
 	tokenName := ctx.GetString("token_name")
-	completionRatio := common.GetCompletionRatio(textRequest.Model)
+	completionRatio := common.GetCompletionRatio(modelName)
 
 	quota := 0
 	if !usePrice {
@@ -307,7 +296,8 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, textRe
 		// we cannot just return, because we may have to return the pre-consumed quota
 		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, textRequest.Model, preConsumedQuota))
+		common.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, "+
+			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, modelName, preConsumedQuota))
 	} else {
 		//if sensitiveResp != nil {
 		//	logContent += fmt.Sprintf("，敏感词：%s", strings.Join(sensitiveResp.SensitiveWords, ", "))
@@ -327,20 +317,14 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, textRe
 		model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
 	}
 
-	logModel := textRequest.Model
+	logModel := modelName
 	if strings.HasPrefix(logModel, "gpt-4-gizmo") {
 		logModel = "gpt-4-gizmo-*"
-		logContent += fmt.Sprintf("，模型 %s", textRequest.Model)
+		logContent += fmt.Sprintf("，模型 %s", modelName)
 	}
-	other := make(map[string]interface{})
-	other["model_ratio"] = modelRatio
-	other["group_ratio"] = groupRatio
-	other["completion_ratio"] = completionRatio
-	other["model_price"] = modelPrice
-	adminInfo := make(map[string]interface{})
-	adminInfo["use_channel"] = ctx.GetStringSlice("use_channel")
-	other["admin_info"] = adminInfo
-	model.RecordConsumeLog(ctx, relayInfo.UserId, relayInfo.ChannelId, promptTokens, completionTokens, logModel, tokenName, quota, logContent, relayInfo.TokenId, userQuota, int(useTimeSeconds), relayInfo.IsStream, other)
+	other := service.GenerateTextOtherInfo(ctx, relayInfo, modelRatio, groupRatio, completionRatio, modelPrice)
+	model.RecordConsumeLog(ctx, relayInfo.UserId, relayInfo.ChannelId, promptTokens, completionTokens, logModel,
+		tokenName, quota, logContent, relayInfo.TokenId, userQuota, int(useTimeSeconds), relayInfo.IsStream, other)
 
 	//if quota != 0 {
 	//

relay/relay_adaptor.go

@@ -1,17 +1,21 @@
 package relay
 
 import (
+	commonconstant "one-api/constant"
 	"one-api/relay/channel"
 	"one-api/relay/channel/ali"
 	"one-api/relay/channel/aws"
 	"one-api/relay/channel/baidu"
 	"one-api/relay/channel/claude"
 	"one-api/relay/channel/cohere"
+	"one-api/relay/channel/dify"
 	"one-api/relay/channel/gemini"
+	"one-api/relay/channel/jina"
 	"one-api/relay/channel/ollama"
 	"one-api/relay/channel/openai"
 	"one-api/relay/channel/palm"
 	"one-api/relay/channel/perplexity"
+	"one-api/relay/channel/task/suno"
 	"one-api/relay/channel/tencent"
 	"one-api/relay/channel/xunfei"
 	"one-api/relay/channel/zhipu"
@@ -51,6 +55,20 @@ func GetAdaptor(apiType int) channel.Adaptor {
 		return &aws.Adaptor{}
 	case constant.APITypeCohere:
 		return &cohere.Adaptor{}
+	case constant.APITypeDify:
+		return &dify.Adaptor{}
+	case constant.APITypeJina:
+		return &jina.Adaptor{}
+	}
+	return nil
+}
+
+func GetTaskAdaptor(platform commonconstant.TaskPlatform) channel.TaskAdaptor {
+	switch platform {
+	//case constant.APITypeAIProxyLibrary:
+	//	return &aiproxy.Adaptor{}
+	case commonconstant.TaskPlatformSuno:
+		return &suno.TaskAdaptor{}
 	}
 	return nil
 }

relay/relay_rerank.go

@@ -0,0 +1,104 @@
+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"
+	"one-api/service"
+)
+
+func getRerankPromptToken(rerankRequest dto.RerankRequest) int {
+	token, _ := service.CountTokenInput(rerankRequest.Query, rerankRequest.Model)
+	for _, document := range rerankRequest.Documents {
+		tkm, err := service.CountTokenInput(document, rerankRequest.Model)
+		if err == nil {
+			token += tkm
+		}
+	}
+	return token
+}
+
+func RerankHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
+	relayInfo := relaycommon.GenRelayInfo(c)
+
+	var rerankRequest *dto.RerankRequest
+	err := common.UnmarshalBodyReusable(c, &rerankRequest)
+	if err != nil {
+		common.LogError(c, fmt.Sprintf("getAndValidateTextRequest failed: %s", err.Error()))
+		return service.OpenAIErrorWrapperLocal(err, "invalid_text_request", http.StatusBadRequest)
+	}
+	if rerankRequest.Query == "" {
+		return service.OpenAIErrorWrapperLocal(fmt.Errorf("query is empty"), "invalid_query", http.StatusBadRequest)
+	}
+	if len(rerankRequest.Documents) == 0 {
+		return service.OpenAIErrorWrapperLocal(fmt.Errorf("documents is empty"), "invalid_documents", http.StatusBadRequest)
+	}
+	relayInfo.UpstreamModelName = rerankRequest.Model
+	modelPrice, success := common.GetModelPrice(rerankRequest.Model, false)
+	groupRatio := common.GetGroupRatio(relayInfo.Group)
+
+	var preConsumedQuota int
+	var ratio float64
+	var modelRatio float64
+
+	promptToken := getRerankPromptToken(*rerankRequest)
+	if !success {
+		preConsumedTokens := promptToken
+		modelRatio = common.GetModelRatio(rerankRequest.Model)
+		ratio = modelRatio * groupRatio
+		preConsumedQuota = int(float64(preConsumedTokens) * ratio)
+	} else {
+		preConsumedQuota = int(modelPrice * common.QuotaPerUnit * groupRatio)
+	}
+	relayInfo.PromptTokens = promptToken
+
+	// pre-consume quota 预消耗配额
+	preConsumedQuota, userQuota, openaiErr := preConsumeQuota(c, preConsumedQuota, relayInfo)
+	if openaiErr != nil {
+		return openaiErr
+	}
+	adaptor := GetAdaptor(relayInfo.ApiType)
+	if adaptor == nil {
+		return service.OpenAIErrorWrapperLocal(fmt.Errorf("invalid api type: %d", relayInfo.ApiType), "invalid_api_type", http.StatusBadRequest)
+	}
+	adaptor.InitRerank(relayInfo, *rerankRequest)
+
+	convertedRequest, err := adaptor.ConvertRerankRequest(c, relayInfo.RelayMode, *rerankRequest)
+	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)
+	}
+	if resp != nil {
+		if resp.StatusCode != http.StatusOK {
+			returnPreConsumedQuota(c, relayInfo.TokenId, userQuota, preConsumedQuota)
+			openaiErr := service.RelayErrorHandler(resp)
+			// reset status code 重置状态码
+			service.ResetStatusCode(openaiErr, statusCodeMappingStr)
+			return openaiErr
+		}
+	}
+
+	usage, openaiErr := adaptor.DoResponse(c, resp, relayInfo)
+	if openaiErr != nil {
+		returnPreConsumedQuota(c, relayInfo.TokenId, userQuota, preConsumedQuota)
+		// reset status code 重置状态码
+		service.ResetStatusCode(openaiErr, statusCodeMappingStr)
+		return openaiErr
+	}
+	postConsumeQuota(c, relayInfo, rerankRequest.Model, usage, ratio, preConsumedQuota, userQuota, modelRatio, groupRatio, modelPrice, success)
+	return nil
+}

relay/relay_task.go

@@ -0,0 +1,242 @@
+package relay
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/common"
+	"one-api/constant"
+	"one-api/dto"
+	"one-api/model"
+	relaycommon "one-api/relay/common"
+	relayconstant "one-api/relay/constant"
+	"one-api/service"
+)
+
+/*
+Task 任务通过平台、Action 区分任务
+*/
+func RelayTaskSubmit(c *gin.Context, relayMode int) (taskErr *dto.TaskError) {
+	platform := constant.TaskPlatform(c.GetString("platform"))
+	relayInfo := relaycommon.GenTaskRelayInfo(c)
+
+	adaptor := GetTaskAdaptor(platform)
+	if adaptor == nil {
+		return service.TaskErrorWrapperLocal(fmt.Errorf("invalid api platform: %s", platform), "invalid_api_platform", http.StatusBadRequest)
+	}
+	adaptor.Init(relayInfo)
+	// get & validate taskRequest 获取并验证文本请求
+	taskErr = adaptor.ValidateRequestAndSetAction(c, relayInfo)
+	if taskErr != nil {
+		return
+	}
+
+	modelName := service.CoverTaskActionToModelName(platform, relayInfo.Action)
+	modelPrice, success := common.GetModelPrice(modelName, true)
+	if !success {
+		defaultPrice, ok := common.GetDefaultModelRatioMap()[modelName]
+		if !ok {
+			modelPrice = 0.1
+		} else {
+			modelPrice = defaultPrice
+		}
+	}
+
+	// 预扣
+	groupRatio := common.GetGroupRatio(relayInfo.Group)
+	ratio := modelPrice * groupRatio
+	userQuota, err := model.CacheGetUserQuota(relayInfo.UserId)
+	if err != nil {
+		taskErr = service.TaskErrorWrapper(err, "get_user_quota_failed", http.StatusInternalServerError)
+		return
+	}
+	quota := int(ratio * common.QuotaPerUnit)
+	if userQuota-quota < 0 {
+		taskErr = service.TaskErrorWrapperLocal(errors.New("user quota is not enough"), "quota_not_enough", http.StatusForbidden)
+		return
+	}
+
+	if relayInfo.OriginTaskID != "" {
+		originTask, exist, err := model.GetByTaskId(relayInfo.UserId, relayInfo.OriginTaskID)
+		if err != nil {
+			taskErr = service.TaskErrorWrapper(err, "get_origin_task_failed", http.StatusInternalServerError)
+			return
+		}
+		if !exist {
+			taskErr = service.TaskErrorWrapperLocal(errors.New("task_origin_not_exist"), "task_not_exist", http.StatusBadRequest)
+			return
+		}
+		if originTask.ChannelId != relayInfo.ChannelId {
+			channel, err := model.GetChannelById(originTask.ChannelId, true)
+			if err != nil {
+				taskErr = service.TaskErrorWrapperLocal(err, "channel_not_found", http.StatusBadRequest)
+				return
+			}
+			if channel.Status != common.ChannelStatusEnabled {
+				return service.TaskErrorWrapperLocal(errors.New("该任务所属渠道已被禁用"), "task_channel_disable", http.StatusBadRequest)
+			}
+			c.Set("base_url", channel.GetBaseURL())
+			c.Set("channel_id", originTask.ChannelId)
+			c.Request.Header.Set("Authorization", fmt.Sprintf("Bearer %s", channel.Key))
+
+			relayInfo.BaseUrl = channel.GetBaseURL()
+			relayInfo.ChannelId = originTask.ChannelId
+		}
+	}
+
+	// build body
+	requestBody, err := adaptor.BuildRequestBody(c, relayInfo)
+	if err != nil {
+		taskErr = service.TaskErrorWrapper(err, "build_request_failed", http.StatusInternalServerError)
+		return
+	}
+	// do request
+	resp, err := adaptor.DoRequest(c, relayInfo, requestBody)
+	if err != nil {
+		taskErr = service.TaskErrorWrapper(err, "do_request_failed", http.StatusInternalServerError)
+		return
+	}
+	// handle response
+	if resp != nil && resp.StatusCode != http.StatusOK {
+		responseBody, _ := io.ReadAll(resp.Body)
+		taskErr = service.TaskErrorWrapper(fmt.Errorf(string(responseBody)), "fail_to_fetch_task", resp.StatusCode)
+		return
+	}
+
+	defer func(ctx context.Context) {
+		// release quota
+		if relayInfo.ConsumeQuota && taskErr == nil {
+			err := model.PostConsumeTokenQuota(relayInfo.TokenId, userQuota, quota, 0, true)
+			if err != nil {
+				common.SysError("error consuming token remain quota: " + err.Error())
+			}
+			err = model.CacheUpdateUserQuota(relayInfo.UserId)
+			if err != nil {
+				common.SysError("error update user quota cache: " + err.Error())
+			}
+			if quota != 0 {
+				tokenName := c.GetString("token_name")
+				logContent := fmt.Sprintf("模型固定价格 %.2f，分组倍率 %.2f，操作 %s", modelPrice, groupRatio, relayInfo.Action)
+				other := make(map[string]interface{})
+				other["model_price"] = modelPrice
+				other["group_ratio"] = groupRatio
+				model.RecordConsumeLog(ctx, relayInfo.UserId, relayInfo.ChannelId, 0, 0, modelName, tokenName, quota, logContent, relayInfo.TokenId, userQuota, 0, false, other)
+				model.UpdateUserUsedQuotaAndRequestCount(relayInfo.UserId, quota)
+				model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
+			}
+		}
+	}(c.Request.Context())
+
+	taskID, taskData, taskErr := adaptor.DoResponse(c, resp, relayInfo)
+	if taskErr != nil {
+		return
+	}
+	relayInfo.ConsumeQuota = true
+	// insert task
+	task := model.InitTask(constant.TaskPlatformSuno, relayInfo)
+	task.TaskID = taskID
+	task.Quota = quota
+	task.Data = taskData
+	err = task.Insert()
+	if err != nil {
+		taskErr = service.TaskErrorWrapper(err, "insert_task_failed", http.StatusInternalServerError)
+		return
+	}
+	return nil
+}
+
+var fetchRespBuilders = map[int]func(c *gin.Context) (respBody []byte, taskResp *dto.TaskError){
+	relayconstant.RelayModeSunoFetchByID: sunoFetchByIDRespBodyBuilder,
+	relayconstant.RelayModeSunoFetch:     sunoFetchRespBodyBuilder,
+}
+
+func RelayTaskFetch(c *gin.Context, relayMode int) (taskResp *dto.TaskError) {
+	respBuilder, ok := fetchRespBuilders[relayMode]
+	if !ok {
+		taskResp = service.TaskErrorWrapperLocal(errors.New("invalid_relay_mode"), "invalid_relay_mode", http.StatusBadRequest)
+	}
+
+	respBody, taskErr := respBuilder(c)
+	if taskErr != nil {
+		return taskErr
+	}
+
+	c.Writer.Header().Set("Content-Type", "application/json")
+	_, err := io.Copy(c.Writer, bytes.NewBuffer(respBody))
+	if err != nil {
+		taskResp = service.TaskErrorWrapper(err, "copy_response_body_failed", http.StatusInternalServerError)
+		return
+	}
+	return
+}
+
+func sunoFetchRespBodyBuilder(c *gin.Context) (respBody []byte, taskResp *dto.TaskError) {
+	userId := c.GetInt("id")
+	var condition = struct {
+		IDs    []any  `json:"ids"`
+		Action string `json:"action"`
+	}{}
+	err := c.BindJSON(&condition)
+	if err != nil {
+		taskResp = service.TaskErrorWrapper(err, "invalid_request", http.StatusBadRequest)
+		return
+	}
+	var tasks []any
+	if len(condition.IDs) > 0 {
+		taskModels, err := model.GetByTaskIds(userId, condition.IDs)
+		if err != nil {
+			taskResp = service.TaskErrorWrapper(err, "get_tasks_failed", http.StatusInternalServerError)
+			return
+		}
+		for _, task := range taskModels {
+			tasks = append(tasks, TaskModel2Dto(task))
+		}
+	} else {
+		tasks = make([]any, 0)
+	}
+	respBody, err = json.Marshal(dto.TaskResponse[[]any]{
+		Code: "success",
+		Data: tasks,
+	})
+	return
+}
+
+func sunoFetchByIDRespBodyBuilder(c *gin.Context) (respBody []byte, taskResp *dto.TaskError) {
+	taskId := c.Param("id")
+	userId := c.GetInt("id")
+
+	originTask, exist, err := model.GetByTaskId(userId, taskId)
+	if err != nil {
+		taskResp = service.TaskErrorWrapper(err, "get_task_failed", http.StatusInternalServerError)
+		return
+	}
+	if !exist {
+		taskResp = service.TaskErrorWrapperLocal(errors.New("task_not_exist"), "task_not_exist", http.StatusBadRequest)
+		return
+	}
+
+	respBody, err = json.Marshal(dto.TaskResponse[any]{
+		Code: "success",
+		Data: TaskModel2Dto(originTask),
+	})
+	return
+}
+
+func TaskModel2Dto(task *model.Task) *dto.TaskDto {
+	return &dto.TaskDto{
+		TaskID:     task.TaskID,
+		Action:     task.Action,
+		Status:     string(task.Status),
+		FailReason: task.FailReason,
+		SubmitTime: task.SubmitTime,
+		StartTime:  task.StartTime,
+		FinishTime: task.FinishTime,
+		Progress:   task.Progress,
+		Data:       task.Data,
+	}
+}

router/api-router.go

@@ -140,5 +140,11 @@ func SetApiRouter(router *gin.Engine) {
 		mjRoute := apiRouter.Group("/mj")
 		mjRoute.GET("/self", middleware.UserAuth(), controller.GetUserMidjourney)
 		mjRoute.GET("/", middleware.AdminAuth(), controller.GetAllMidjourney)
+
+		taskRoute := apiRouter.Group("/task")
+		{
+			taskRoute.GET("/self", middleware.UserAuth(), controller.GetUserTask)
+			taskRoute.GET("/", middleware.AdminAuth(), controller.GetAllTask)
+		}
 	}
 }

router/relay-router.go

@@ -42,6 +42,7 @@ func SetRelayRouter(router *gin.Engine) {
 		relayV1Router.GET("/fine-tunes/:id/events", controller.RelayNotImplemented)
 		relayV1Router.DELETE("/models/:model", controller.RelayNotImplemented)
 		relayV1Router.POST("/moderations", controller.Relay)
+		relayV1Router.POST("/rerank", controller.Relay)
 	}
 
 	relayMjRouter := router.Group("/mj")
@@ -50,6 +51,15 @@ func SetRelayRouter(router *gin.Engine) {
 	relayMjModeRouter := router.Group("/:mode/mj")
 	registerMjRouterGroup(relayMjModeRouter)
 	//relayMjRouter.Use()
+
+	relaySunoRouter := router.Group("/suno")
+	relaySunoRouter.Use(middleware.TokenAuth(), middleware.Distribute())
+	{
+		relaySunoRouter.POST("/submit/:action", controller.RelayTask)
+		relaySunoRouter.POST("/fetch", controller.RelayTask)
+		relaySunoRouter.GET("/fetch/:id", controller.RelayTask)
+	}
+
 }
 
 func registerMjRouterGroup(relayMjRouter *gin.RouterGroup) {

service/channel.go

@@ -24,17 +24,26 @@ func EnableChannel(channelId int, channelName string) {
 	notifyRootUser(subject, content)
 }
 
-func ShouldDisableChannel(err *relaymodel.OpenAIError, statusCode int) bool {
+func ShouldDisableChannel(channelType int, err *relaymodel.OpenAIErrorWithStatusCode) bool {
 	if !common.AutomaticDisableChannelEnabled {
 		return false
 	}
 	if err == nil {
 		return false
 	}
-	if statusCode == http.StatusUnauthorized {
+	if err.LocalError {
+		return false
+	}
+	if err.StatusCode == http.StatusUnauthorized {
 		return true
 	}
-	switch err.Code {
+	if err.StatusCode == http.StatusForbidden {
+		switch channelType {
+		case common.ChannelTypeGemini:
+			return true
+		}
+	}
+	switch err.Error.Code {
 	case "invalid_api_key":
 		return true
 	case "account_deactivated":
@@ -42,7 +51,7 @@ func ShouldDisableChannel(err *relaymodel.OpenAIError, statusCode int) bool {
 	case "billing_not_active":
 		return true
 	}
-	switch err.Type {
+	switch err.Error.Type {
 	case "insufficient_quota":
 		return true
 	// https://docs.anthropic.com/claude/reference/errors
@@ -53,11 +62,13 @@ func ShouldDisableChannel(err *relaymodel.OpenAIError, statusCode int) bool {
 	case "forbidden":
 		return true
 	}
-	if strings.HasPrefix(err.Message, "Your credit balance is too low") { // anthropic
+	if strings.HasPrefix(err.Error.Message, "Your credit balance is too low") { // anthropic
 		return true
-	} else if strings.HasPrefix(err.Message, "This organization has been disabled.") {
+	} else if strings.HasPrefix(err.Error.Message, "This organization has been disabled.") {
 		return true
-	} else if strings.HasPrefix(err.Message, "You exceeded your current quota") {
+	} 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
 	}
 	return false

service/error.go

@@ -105,3 +105,29 @@ func ResetStatusCode(openaiErr *dto.OpenAIErrorWithStatusCode, statusCodeMapping
 		openaiErr.StatusCode = intCode
 	}
 }
+
+func TaskErrorWrapperLocal(err error, code string, statusCode int) *dto.TaskError {
+	openaiErr := TaskErrorWrapper(err, code, statusCode)
+	openaiErr.LocalError = true
+	return openaiErr
+}
+
+func TaskErrorWrapper(err error, code string, statusCode int) *dto.TaskError {
+	text := err.Error()
+
+	// 定义一个正则表达式匹配URL
+	if strings.Contains(text, "Post") || strings.Contains(text, "dial") {
+		common.SysLog(fmt.Sprintf("error: %s", text))
+		text = "请求上游地址失败"
+	}
+	//避免暴露内部错误
+
+	taskError := &dto.TaskError{
+		Code:       code,
+		Message:    text,
+		StatusCode: statusCode,
+		Error:      err,
+	}
+
+	return taskError
+}

service/log.go

@@ -0,0 +1,19 @@
+package service
+
+import (
+	"github.com/gin-gonic/gin"
+	relaycommon "one-api/relay/common"
+)
+
+func GenerateTextOtherInfo(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelRatio, groupRatio, completionRatio, modelPrice float64) map[string]interface{} {
+	other := make(map[string]interface{})
+	other["model_ratio"] = modelRatio
+	other["group_ratio"] = groupRatio
+	other["completion_ratio"] = completionRatio
+	other["model_price"] = modelPrice
+	other["frt"] = float64(relayInfo.FirstResponseTime.UnixMilli() - relayInfo.StartTime.UnixMilli())
+	adminInfo := make(map[string]interface{})
+	adminInfo["use_channel"] = ctx.GetStringSlice("use_channel")
+	other["admin_info"] = adminInfo
+	return other
+}

service/sensitive.go

@@ -3,7 +3,6 @@ package service
 import (
 	"errors"
 	"fmt"
-	"one-api/common"
 	"one-api/constant"
 	"one-api/dto"
 	"strings"
@@ -62,7 +61,7 @@ func SensitiveWordContains(text string) (bool, []string) {
 	}
 	checkText := strings.ToLower(text)
 	// 构建一个AC自动机
-	m := common.InitAc()
+	m := InitAc()
 	hits := m.MultiPatternSearch([]rune(checkText), false)
 	if len(hits) > 0 {
 		words := make([]string, 0)
@@ -80,7 +79,7 @@ func SensitiveWordReplace(text string, returnImmediately bool) (bool, []string,
 		return false, nil, text
 	}
 	checkText := strings.ToLower(text)
-	m := common.InitAc()
+	m := InitAc()
 	hits := m.MultiPatternSearch([]rune(checkText), returnImmediately)
 	if len(hits) > 0 {
 		words := make([]string, 0)

service/sse.go

@@ -1,6 +1,12 @@
 package service
 
-import "github.com/gin-gonic/gin"
+import (
+	"encoding/json"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"one-api/common"
+	"strings"
+)
 
 func SetEventStreamHeaders(c *gin.Context) {
 	c.Writer.Header().Set("Content-Type", "text/event-stream")
@@ -9,3 +15,23 @@ func SetEventStreamHeaders(c *gin.Context) {
 	c.Writer.Header().Set("Transfer-Encoding", "chunked")
 	c.Writer.Header().Set("X-Accel-Buffering", "no")
 }
+
+func StringData(c *gin.Context, str string) {
+	str = strings.TrimPrefix(str, "data: ")
+	str = strings.TrimSuffix(str, "\r")
+	c.Render(-1, common.CustomEvent{Data: "data: " + str})
+	c.Writer.Flush()
+}
+
+func ObjectData(c *gin.Context, object interface{}) error {
+	jsonData, err := json.Marshal(object)
+	if err != nil {
+		return fmt.Errorf("error marshalling object: %w", err)
+	}
+	StringData(c, string(jsonData))
+	return nil
+}
+
+func Done(c *gin.Context) {
+	StringData(c, "[DONE]")
+}

service/str.go

@@ -1,4 +1,4 @@
-package common
+package service
 
 import (
 	"bytes"

service/task.go

@@ -0,0 +1,10 @@
+package service
+
+import (
+	"one-api/constant"
+	"strings"
+)
+
+func CoverTaskActionToModelName(platform constant.TaskPlatform, action string) string {
+	return strings.ToLower(string(platform)) + "_" + strings.ToLower(action)
+}

web/src/App.js

@@ -23,6 +23,7 @@ import Chat from './pages/Chat';
 import { Layout } from '@douyinfe/semi-ui';
 import Midjourney from './pages/Midjourney';
 import Pricing from './pages/Pricing/index.js';
+import Task from "./pages/Task/index.js";
 // import Detail from './pages/Detail';
 
 const Home = lazy(() => import('./pages/Home'));
@@ -220,6 +221,16 @@ function App() {
               </PrivateRoute>
             }
           />
+          <Route
+            path='/task'
+            element={
+                <PrivateRoute>
+                    <Suspense fallback={<Loading></Loading>}>
+                        <Task />
+                    </Suspense>
+                </PrivateRoute>
+            }
+          />
           <Route
             path='/pricing'
             element={

web/src/components/ChannelsTable.js

@@ -96,7 +96,23 @@ const ChannelsTable = () => {
       title: '状态',
       dataIndex: 'status',
       render: (text, record, index) => {
-        return <div>{renderStatus(text)}</div>;
+        if (text === 3) {
+          if (record.other_info === '') {
+            record.other_info = '{}'
+          }
+          let otherInfo = JSON.parse(record.other_info);
+          let reason = otherInfo['status_reason'];
+          let time = otherInfo['status_time'];
+          return (
+            <div>
+              <Tooltip content={'原因：' + reason + '，时间：' + timestamp2string(time)}>
+                {renderStatus(text)}
+              </Tooltip>
+            </div>
+          );
+        } else {
+          return renderStatus(text);
+        }
       },
     },
     {