Merge pull request #464 from Yan-Zero/main

fix: tool use in claude and add gemini mapping

README.md

@@ -54,6 +54,7 @@
 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
+11. Vertex AI，目前兼容Claude，Gemini，Llama3.1
 
 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。
 
@@ -64,7 +65,8 @@
 - `GET_MEDIA_TOKEN`：是统计图片token，默认为 `true`，关闭后将不再在本地计算图片token，可能会导致和上游计费不同，此项覆盖 `GET_MEDIA_TOKEN_NOT_STREAM` 选项作用。
 - `GET_MEDIA_TOKEN_NOT_STREAM`：是否在非流（`stream=false`）情况下统计图片token，默认为 `true`。
 - `UPDATE_TASK`：是否更新异步任务（Midjourney、Suno），默认为 `true`，关闭后将不会更新任务进度。
-
+- `GEMINI_MODEL_MAP`：Gemini模型指定版本(v1/v1beta)，使用“模型:版本”指定，","分隔，例如：-e GEMINI_MODEL_MAP="gemini-1.5-pro-latest:v1beta,gemini-1.5-pro-001:v1beta"，为空则使用默认配置
+- `COHERE_SAFETY_SETTING`：Cohere模型[安全设置](https://docs.cohere.com/docs/safety-modes#overview)，可选值为 `NONE`, `CONTEXTUAL`，`STRICT`，默认为 `NONE`。
 ## 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）

common/constants.go

@@ -112,6 +112,9 @@ var RelayTimeout = GetEnvOrDefault("RELAY_TIMEOUT", 0) // unit is second
 
 var GeminiSafetySetting = GetEnvOrDefaultString("GEMINI_SAFETY_SETTING", "BLOCK_NONE")
 
+// https://docs.cohere.com/docs/safety-modes Type; NONE/CONTEXTUAL/STRICT
+var CohereSafetySetting = GetEnvOrDefaultString("COHERE_SAFETY_SETTING", "NONE")
+
 const (
 	RequestIdKey = "X-Oneapi-Request-Id"
 )
@@ -213,6 +216,8 @@ const (
 	ChannelTypeDify           = 37
 	ChannelTypeJina           = 38
 	ChannelCloudflare         = 39
+	ChannelTypeSiliconFlow    = 40
+	ChannelTypeVertexAi       = 41
 
 	ChannelTypeDummy // this one is only for count, do not add any channel after this
 
@@ -259,4 +264,6 @@ var ChannelBaseURLs = []string{
 	"",                                          //37
 	"https://api.jina.ai",                       //38
 	"https://api.cloudflare.com",                //39
+	"https://api.siliconflow.cn",                //40
+	"",                                          //41
 }

common/email-outlook-auth.go

@@ -3,6 +3,7 @@ package common
 import (
 	"errors"
 	"net/smtp"
+	"strings"
 )
 
 type outlookAuth struct {
@@ -30,3 +31,10 @@ func (a *outlookAuth) Next(fromServer []byte, more bool) ([]byte, error) {
 	}
 	return nil, nil
 }
+
+func isOutlookServer(server string) bool {
+	// 兼容多地区的outlook邮箱和ofb邮箱
+	// 其实应该加一个Option来区分是否用LOGIN的方式登录
+	// 先临时兼容一下
+	return strings.Contains(server, "outlook") || strings.Contains(server, "onmicrosoft")
+}

common/email.go

@@ -9,17 +9,26 @@ import (
 	"time"
 )
 
+func generateMessageID() string {
+	domain := strings.Split(SMTPAccount, "@")[1]
+	return fmt.Sprintf("<%d.%s@%s>", time.Now().UnixNano(), GetRandomString(12), domain)
+}
+
 func SendEmail(subject string, receiver string, content string) error {
 	if SMTPFrom == "" { // for compatibility
 		SMTPFrom = SMTPAccount
 	}
+	if SMTPServer == "" && SMTPAccount == "" {
+		return fmt.Errorf("SMTP 服务器未配置")
+	}
 	encodedSubject := fmt.Sprintf("=?UTF-8?B?%s?=", base64.StdEncoding.EncodeToString([]byte(subject)))
 	mail := []byte(fmt.Sprintf("To: %s\r\n"+
 		"From: %s<%s>\r\n"+
 		"Subject: %s\r\n"+
 		"Date: %s\r\n"+
+		"Message-ID: %s\r\n"+ // 添加 Message-ID 头
 		"Content-Type: text/html; charset=UTF-8\r\n\r\n%s\r\n",
-		receiver, SystemName, SMTPFrom, encodedSubject, time.Now().Format(time.RFC1123Z), content))
+		receiver, SystemName, SMTPFrom, encodedSubject, time.Now().Format(time.RFC1123Z), generateMessageID(), content))
 	auth := smtp.PlainAuth("", SMTPAccount, SMTPToken, SMTPServer)
 	addr := fmt.Sprintf("%s:%d", SMTPServer, SMTPPort)
 	to := strings.Split(receiver, ";")
@@ -62,7 +71,7 @@ func SendEmail(subject string, receiver string, content string) error {
 		if err != nil {
 			return err
 		}
-	} else if strings.HasSuffix(SMTPAccount, "outlook.com") {
+	} else if isOutlookServer(SMTPAccount) {
 		auth = LoginAuth(SMTPAccount, SMTPToken)
 		err = smtp.SendMail(addr, auth, SMTPAccount, to, mail)
 	} else {

common/model-ratio.go

@@ -23,22 +23,25 @@ const (
 
 var defaultModelRatio = map[string]float64{
 	//"midjourney":                50,
-	"gpt-4-gizmo-*": 15,
-	"gpt-4-all":     15,
-	"gpt-4o-all":    15,
-	"gpt-4":         15,
+	"gpt-4-gizmo-*":  15,
+	"gpt-4o-gizmo-*": 2.5,
+	"gpt-4-all":      15,
+	"gpt-4o-all":     15,
+	"gpt-4":          15,
 	//"gpt-4-0314":                   15, //deprecated
 	"gpt-4-0613": 15,
 	"gpt-4-32k":  30,
 	//"gpt-4-32k-0314":               30, //deprecated
 	"gpt-4-32k-0613":            30,
-	"gpt-4-1106-preview":        5,   // $0.01 / 1K tokens
-	"gpt-4-0125-preview":        5,   // $0.01 / 1K tokens
-	"gpt-4-turbo-preview":       5,   // $0.01 / 1K tokens
-	"gpt-4-vision-preview":      5,   // $0.01 / 1K tokens
-	"gpt-4-1106-vision-preview": 5,   // $0.01 / 1K tokens
-	"gpt-4o":                    2.5, // $0.01 / 1K tokens
-	"gpt-4o-2024-05-13":         2.5, // $0.01 / 1K tokens
+	"gpt-4-1106-preview":        5,    // $0.01 / 1K tokens
+	"gpt-4-0125-preview":        5,    // $0.01 / 1K tokens
+	"gpt-4-turbo-preview":       5,    // $0.01 / 1K tokens
+	"gpt-4-vision-preview":      5,    // $0.01 / 1K tokens
+	"gpt-4-1106-vision-preview": 5,    // $0.01 / 1K tokens
+	"chatgpt-4o-latest":         2.5,  // $0.01 / 1K tokens
+	"gpt-4o":                    2.5,  // $0.01 / 1K tokens
+	"gpt-4o-2024-05-13":         2.5,  // $0.01 / 1K tokens
+	"gpt-4o-2024-08-06":         1.25, // $0.01 / 1K tokens
 	"gpt-4o-mini":               0.075,
 	"gpt-4o-mini-2024-07-18":    0.075,
 	"gpt-4-turbo":               5,    // $0.01 / 1K tokens
@@ -103,8 +106,10 @@ var defaultModelRatio = map[string]float64{
 	"gemini-pro-vision":              1, // $0.00025 / 1k characters -> $0.001 / 1k tokens
 	"gemini-1.0-pro-vision-001":      1,
 	"gemini-1.0-pro-001":             1,
-	"gemini-1.5-pro-latest":          1,
+	"gemini-1.5-pro-latest":          1.75, // $3.5 / 1M tokens
+	"gemini-1.5-pro-exp-0827":        1.75, // $3.5 / 1M tokens
 	"gemini-1.5-flash-latest":        1,
+	"gemini-1.5-flash-exp-0827":      1,
 	"gemini-1.0-pro-latest":          1,
 	"gemini-1.0-pro-vision-latest":   1,
 	"gemini-ultra":                   1,
@@ -116,6 +121,13 @@ var defaultModelRatio = map[string]float64{
 	"glm-4v":                         0.05 * RMB, // ￥0.05 / 1k tokens
 	"glm-4-alltools":                 0.1 * RMB,  // ￥0.1 / 1k tokens
 	"glm-3-turbo":                    0.3572,
+	"glm-4-plus":                     0.05 * RMB,
+	"glm-4-0520":                     0.1 * RMB,
+	"glm-4-air":                      0.001 * RMB,
+	"glm-4-airx":                     0.01 * RMB,
+	"glm-4-long":                     0.001 * RMB,
+	"glm-4-flash":                    0,
+	"glm-4v-plus":                    0.01 * RMB,
 	"qwen-turbo":                     0.8572, // ￥0.012 / 1k tokens
 	"qwen-plus":                      10,     // ￥0.14 / 1k tokens
 	"text-embedding-v1":              0.05,   // ￥0.0007 / 1k tokens
@@ -134,26 +146,28 @@ var defaultModelRatio = map[string]float64{
 	"hunyuan":                        7.143,  // ¥0.1 / 1k tokens  // https://cloud.tencent.com/document/product/1729/97731#e0e6be58-60c8-469f-bdeb-6c264ce3b4d0
 	// https://platform.lingyiwanwu.com/docs#-计费单元
 	// 已经按照 7.2 来换算美元价格
-	"yi-34b-chat-0205":      0.18,
-	"yi-34b-chat-200k":      0.864,
-	"yi-vl-plus":            0.432,
-	"yi-large":              20.0 / 1000 * RMB,
-	"yi-medium":             2.5 / 1000 * RMB,
-	"yi-vision":             6.0 / 1000 * RMB,
-	"yi-medium-200k":        12.0 / 1000 * RMB,
-	"yi-spark":              1.0 / 1000 * RMB,
-	"yi-large-rag":          25.0 / 1000 * RMB,
-	"yi-large-turbo":        12.0 / 1000 * RMB,
-	"yi-large-preview":      20.0 / 1000 * RMB,
-	"yi-large-rag-preview":  25.0 / 1000 * RMB,
-	"command":               0.5,
-	"command-nightly":       0.5,
-	"command-light":         0.5,
-	"command-light-nightly": 0.5,
-	"command-r":             0.25,
-	"command-r-plus	":       1.5,
-	"deepseek-chat":         0.07,
-	"deepseek-coder":        0.07,
+	"yi-34b-chat-0205":       0.18,
+	"yi-34b-chat-200k":       0.864,
+	"yi-vl-plus":             0.432,
+	"yi-large":               20.0 / 1000 * RMB,
+	"yi-medium":              2.5 / 1000 * RMB,
+	"yi-vision":              6.0 / 1000 * RMB,
+	"yi-medium-200k":         12.0 / 1000 * RMB,
+	"yi-spark":               1.0 / 1000 * RMB,
+	"yi-large-rag":           25.0 / 1000 * RMB,
+	"yi-large-turbo":         12.0 / 1000 * RMB,
+	"yi-large-preview":       20.0 / 1000 * RMB,
+	"yi-large-rag-preview":   25.0 / 1000 * RMB,
+	"command":                0.5,
+	"command-nightly":        0.5,
+	"command-light":          0.5,
+	"command-light-nightly":  0.5,
+	"command-r":              0.25,
+	"command-r-plus":         1.5,
+	"command-r-08-2024":      0.075,
+	"command-r-plus-08-2024": 1.25,
+	"deepseek-chat":          0.07,
+	"deepseek-coder":         0.07,
 	// Perplexity online 模型对搜索额外收费，有需要应自行调整，此处不计入搜索费用
 	"llama-3-sonar-small-32k-chat":   0.2 / 1000 * USD,
 	"llama-3-sonar-small-32k-online": 0.2 / 1000 * USD,
@@ -181,11 +195,12 @@ var defaultModelPrice = map[string]float64{
 	"mj_describe":       0.05,
 	"mj_upscale":        0.05,
 	"swap_face":         0.05,
+	"mj_upload":         0.05,
 }
 
 var (
-	modelPriceMap      = make(map[string]float64)
-	modelPriceMapMutex = sync.RWMutex{}
+	modelPriceMap      map[string]float64 = nil
+	modelPriceMapMutex                    = sync.RWMutex{}
 )
 var (
 	modelRatioMap      map[string]float64 = nil
@@ -194,8 +209,9 @@ var (
 
 var CompletionRatio map[string]float64 = nil
 var defaultCompletionRatio = map[string]float64{
-	"gpt-4-gizmo-*": 2,
-	"gpt-4-all":     2,
+	"gpt-4-gizmo-*":  2,
+	"gpt-4o-gizmo-*": 3,
+	"gpt-4-all":      2,
 }
 
 func GetModelPriceMap() map[string]float64 {
@@ -229,6 +245,9 @@ func GetModelPrice(name string, printErr bool) (float64, bool) {
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
 	}
+	if strings.HasPrefix(name, "gpt-4o-gizmo") {
+		name = "gpt-4o-gizmo-*"
+	}
 	price, ok := modelPriceMap[name]
 	if !ok {
 		if printErr {
@@ -309,6 +328,9 @@ func GetCompletionRatio(name string) float64 {
 	if strings.HasPrefix(name, "gpt-4-gizmo") {
 		name = "gpt-4-gizmo-*"
 	}
+	if strings.HasPrefix(name, "gpt-4o-gizmo") {
+		name = "gpt-4o-gizmo-*"
+	}
 	if strings.HasPrefix(name, "gpt-3.5") {
 		if name == "gpt-3.5-turbo" || strings.HasSuffix(name, "0125") {
 			// https://openai.com/blog/new-embedding-models-and-api-updates
@@ -325,13 +347,16 @@ func GetCompletionRatio(name string) float64 {
 			return 3
 		}
 		if strings.HasPrefix(name, "gpt-4o") {
-			if strings.Contains(name, "mini") {
+			if strings.HasPrefix(name, "gpt-4o-mini") || name == "gpt-4o-2024-08-06" {
 				return 4
 			}
 			return 3
 		}
 		return 2
 	}
+	if name == "chatgpt-4o-latest" {
+		return 3
+	}
 	if strings.Contains(name, "claude-instant-1") {
 		return 3
 	} else if strings.Contains(name, "claude-2") {
@@ -351,6 +376,10 @@ func GetCompletionRatio(name string) float64 {
 			return 3
 		case "command-r-plus":
 			return 5
+		case "command-r-08-2024":
+			return 4
+		case "command-r-plus-08-2024":
+			return 4
 		default:
 			return 2
 		}

common/str.go

@@ -31,14 +31,6 @@ func MapToJsonStr(m map[string]interface{}) string {
 	return string(bytes)
 }
 
-func MapToJsonStrFloat(m map[string]float64) string {
-	bytes, err := json.Marshal(m)
-	if err != nil {
-		return ""
-	}
-	return string(bytes)
-}
-
 func StrToMap(str string) map[string]interface{} {
 	m := make(map[string]interface{})
 	err := json.Unmarshal([]byte(str), &m)
@@ -48,6 +40,11 @@ func StrToMap(str string) map[string]interface{} {
 	return m
 }
 
+func IsJsonStr(str string) bool {
+	var js map[string]interface{}
+	return json.Unmarshal([]byte(str), &js) == nil
+}
+
 func String2Int(str string) int {
 	num, err := strconv.Atoi(str)
 	if err != nil {

constant/env.go

@@ -1,7 +1,10 @@
 package constant
 
 import (
+	"fmt"
 	"one-api/common"
+	"os"
+	"strings"
 )
 
 var StreamingTimeout = common.GetEnvOrDefault("STREAMING_TIMEOUT", 30)
@@ -15,3 +18,31 @@ var GetMediaToken = common.GetEnvOrDefaultBool("GET_MEDIA_TOKEN", true)
 var GetMediaTokenNotStream = common.GetEnvOrDefaultBool("GET_MEDIA_TOKEN_NOT_STREAM", true)
 
 var UpdateTask = common.GetEnvOrDefaultBool("UPDATE_TASK", true)
+
+var GeminiModelMap = map[string]string{
+	"gemini-1.5-pro-latest":     "v1beta",
+	"gemini-1.5-pro-001":        "v1beta",
+	"gemini-1.5-pro":            "v1beta",
+	"gemini-1.5-pro-exp-0801":   "v1beta",
+	"gemini-1.5-pro-exp-0827":   "v1beta",
+	"gemini-1.5-flash-latest":   "v1beta",
+	"gemini-1.5-flash-exp-0827": "v1beta",
+	"gemini-1.5-flash-001":      "v1beta",
+	"gemini-1.5-flash":          "v1beta",
+	"gemini-ultra":              "v1beta",
+}
+
+func InitEnv() {
+	modelVersionMapStr := strings.TrimSpace(os.Getenv("GEMINI_MODEL_MAP"))
+	if modelVersionMapStr == "" {
+		return
+	}
+	for _, pair := range strings.Split(modelVersionMapStr, ",") {
+		parts := strings.Split(pair, ":")
+		if len(parts) == 2 {
+			GeminiModelMap[parts[0]] = parts[1]
+		} else {
+			common.SysError(fmt.Sprintf("invalid model version map: %s", pair))
+		}
+	}
+}

constant/midjourney.go

@@ -27,6 +27,7 @@ const (
 	MjActionLowVariation  = "LOW_VARIATION"
 	MjActionPan           = "PAN"
 	MjActionSwapFace      = "SWAP_FACE"
+	MjActionUpload        = "UPLOAD"
 )
 
 var MidjourneyModel2Action = map[string]string{
@@ -45,4 +46,5 @@ var MidjourneyModel2Action = map[string]string{
 	"mj_low_variation":  MjActionLowVariation,
 	"mj_pan":            MjActionPan,
 	"swap_face":         MjActionSwapFace,
+	"mj_upload":         MjActionUpload,
 }

controller/channel-test.go

@@ -240,7 +240,7 @@ func testAllChannels(notify bool) error {
 			}
 
 			// parse *int to bool
-			if channel.AutoBan != nil && *channel.AutoBan == 0 {
+			if !channel.GetAutoBan() {
 				ban = false
 			}
 

controller/channel.go

@@ -198,6 +198,28 @@ func AddChannel(c *gin.Context) {
 	}
 	channel.CreatedTime = common.GetTimestamp()
 	keys := strings.Split(channel.Key, "\n")
+	if channel.Type == common.ChannelTypeVertexAi {
+		if channel.Other == "" {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "部署地区不能为空",
+			})
+			return
+		} else {
+			if common.IsJsonStr(channel.Other) {
+				// must have default
+				regionMap := common.StrToMap(channel.Other)
+				if regionMap["default"] == nil {
+					c.JSON(http.StatusOK, gin.H{
+						"success": false,
+						"message": "部署地区必须包含default字段",
+					})
+					return
+				}
+			}
+		}
+		keys = []string{channel.Key}
+	}
 	channels := make([]model.Channel, 0, len(keys))
 	for _, key := range keys {
 		if key == "" {
@@ -297,6 +319,27 @@ func UpdateChannel(c *gin.Context) {
 		})
 		return
 	}
+	if channel.Type == common.ChannelTypeVertexAi {
+		if channel.Other == "" {
+			c.JSON(http.StatusOK, gin.H{
+				"success": false,
+				"message": "部署地区不能为空",
+			})
+			return
+		} else {
+			if common.IsJsonStr(channel.Other) {
+				// must have default
+				regionMap := common.StrToMap(channel.Other)
+				if regionMap["default"] == nil {
+					c.JSON(http.StatusOK, gin.H{
+						"success": false,
+						"message": "部署地区必须包含default字段",
+					})
+					return
+				}
+			}
+		}
+	}
 	err = channel.Update()
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{

controller/log.go

@@ -1,18 +1,19 @@
 package controller
 
 import (
-	"github.com/gin-gonic/gin"
 	"net/http"
 	"one-api/common"
 	"one-api/model"
 	"strconv"
+
+	"github.com/gin-gonic/gin"
 )
 
 func GetAllLogs(c *gin.Context) {
 	p, _ := strconv.Atoi(c.Query("p"))
 	pageSize, _ := strconv.Atoi(c.Query("page_size"))
-	if p < 0 {
-		p = 0
+	if p < 1 {
+		p = 1
 	}
 	if pageSize < 0 {
 		pageSize = common.ItemsPerPage
@@ -24,7 +25,7 @@ func GetAllLogs(c *gin.Context) {
 	tokenName := c.Query("token_name")
 	modelName := c.Query("model_name")
 	channel, _ := strconv.Atoi(c.Query("channel"))
-	logs, err := model.GetAllLogs(logType, startTimestamp, endTimestamp, modelName, username, tokenName, p*pageSize, pageSize, channel)
+	logs, total, err := model.GetAllLogs(logType, startTimestamp, endTimestamp, modelName, username, tokenName, (p-1)*pageSize, pageSize, channel)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -35,16 +36,20 @@ func GetAllLogs(c *gin.Context) {
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
-		"data":    logs,
+		"data": map[string]any{
+			"items":     logs,
+			"total":     total,
+			"page":      p,
+			"page_size": pageSize,
+		},
 	})
-	return
 }
 
 func GetUserLogs(c *gin.Context) {
 	p, _ := strconv.Atoi(c.Query("p"))
 	pageSize, _ := strconv.Atoi(c.Query("page_size"))
-	if p < 0 {
-		p = 0
+	if p < 1 {
+		p = 1
 	}
 	if pageSize < 0 {
 		pageSize = common.ItemsPerPage
@@ -58,7 +63,7 @@ func GetUserLogs(c *gin.Context) {
 	endTimestamp, _ := strconv.ParseInt(c.Query("end_timestamp"), 10, 64)
 	tokenName := c.Query("token_name")
 	modelName := c.Query("model_name")
-	logs, err := model.GetUserLogs(userId, logType, startTimestamp, endTimestamp, modelName, tokenName, p*pageSize, pageSize)
+	logs, total, err := model.GetUserLogs(userId, logType, startTimestamp, endTimestamp, modelName, tokenName, (p-1)*pageSize, pageSize)
 	if err != nil {
 		c.JSON(http.StatusOK, gin.H{
 			"success": false,
@@ -69,7 +74,12 @@ func GetUserLogs(c *gin.Context) {
 	c.JSON(http.StatusOK, gin.H{
 		"success": true,
 		"message": "",
-		"data":    logs,
+		"data": map[string]any{
+			"items":     logs,
+			"total":     total,
+			"page":      p,
+			"page_size": pageSize,
+		},
 	})
 	return
 }

controller/relay.go

@@ -2,6 +2,7 @@ package controller
 
 import (
 	"bytes"
+	"errors"
 	"fmt"
 	"github.com/gin-gonic/gin"
 	"io"
@@ -39,44 +40,35 @@ func relayHandler(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 
 func Relay(c *gin.Context) {
 	relayMode := constant.Path2RelayMode(c.Request.URL.Path)
-	retryTimes := common.RetryTimes
 	requestId := c.GetString(common.RequestIdKey)
-	channelId := c.GetInt("channel_id")
-	channelType := c.GetInt("channel_type")
-	channelName := c.GetString("channel_name")
 	group := c.GetString("group")
 	originalModel := c.GetString("original_model")
-	openaiErr := relayHandler(c, relayMode)
-	c.Set("use_channel", []string{fmt.Sprintf("%d", channelId)})
-	if openaiErr != nil {
-		go processChannelError(c, channelId, channelType, channelName, openaiErr)
-	} else {
-		retryTimes = 0
-	}
-	for i := 0; shouldRetry(c, channelId, openaiErr, retryTimes) && i < retryTimes; i++ {
-		channel, err := model.CacheGetRandomSatisfiedChannel(group, originalModel, i)
+	var openaiErr *dto.OpenAIErrorWithStatusCode
+
+	for i := 0; i <= common.RetryTimes; i++ {
+		channel, err := getChannel(c, group, originalModel, i)
 		if err != nil {
-			common.LogError(c.Request.Context(), fmt.Sprintf("CacheGetRandomSatisfiedChannel failed: %s", err.Error()))
+			common.LogError(c, err.Error())
+			openaiErr = service.OpenAIErrorWrapperLocal(err, "get_channel_failed", http.StatusInternalServerError)
 			break
 		}
-		channelId = channel.Id
-		useChannel := c.GetStringSlice("use_channel")
-		useChannel = append(useChannel, fmt.Sprintf("%d", channel.Id))
-		c.Set("use_channel", useChannel)
-		common.LogInfo(c.Request.Context(), fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, i))
-		middleware.SetupContextForSelectedChannel(c, channel, originalModel)
 
-		requestBody, err := common.GetRequestBody(c)
-		c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
-		openaiErr = relayHandler(c, relayMode)
-		if openaiErr != nil {
-			go processChannelError(c, channel.Id, channel.Type, channel.Name, openaiErr)
+		openaiErr = relayRequest(c, relayMode, channel)
+
+		if openaiErr == nil {
+			return // 成功处理请求，直接返回
+		}
+
+		go processChannelError(c, channel.Id, channel.Type, channel.Name, channel.GetAutoBan(), openaiErr)
+
+		if !shouldRetry(c, openaiErr, common.RetryTimes-i) {
+			break
 		}
 	}
 	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)
+		common.LogInfo(c, retryLogStr)
 	}
 
 	if openaiErr != nil {
@@ -90,10 +82,48 @@ func Relay(c *gin.Context) {
 	}
 }
 
-func shouldRetry(c *gin.Context, channelId int, openaiErr *dto.OpenAIErrorWithStatusCode, retryTimes int) bool {
+func relayRequest(c *gin.Context, relayMode int, channel *model.Channel) *dto.OpenAIErrorWithStatusCode {
+	addUsedChannel(c, channel.Id)
+	requestBody, _ := common.GetRequestBody(c)
+	c.Request.Body = io.NopCloser(bytes.NewBuffer(requestBody))
+	return relayHandler(c, relayMode)
+}
+
+func addUsedChannel(c *gin.Context, channelId int) {
+	useChannel := c.GetStringSlice("use_channel")
+	useChannel = append(useChannel, fmt.Sprintf("%d", channelId))
+	c.Set("use_channel", useChannel)
+}
+
+func getChannel(c *gin.Context, group, originalModel string, retryCount int) (*model.Channel, error) {
+	if retryCount == 0 {
+		autoBan := c.GetBool("auto_ban")
+		autoBanInt := 1
+		if !autoBan {
+			autoBanInt = 0
+		}
+		return &model.Channel{
+			Id:      c.GetInt("channel_id"),
+			Type:    c.GetInt("channel_type"),
+			Name:    c.GetString("channel_name"),
+			AutoBan: &autoBanInt,
+		}, nil
+	}
+	channel, err := model.CacheGetRandomSatisfiedChannel(group, originalModel, retryCount)
+	if err != nil {
+		return nil, errors.New(fmt.Sprintf("获取重试渠道失败: %s", err.Error()))
+	}
+	middleware.SetupContextForSelectedChannel(c, channel, originalModel)
+	return channel, nil
+}
+
+func shouldRetry(c *gin.Context, openaiErr *dto.OpenAIErrorWithStatusCode, retryTimes int) bool {
 	if openaiErr == nil {
 		return false
 	}
+	if openaiErr.LocalError {
+		return false
+	}
 	if retryTimes <= 0 {
 		return false
 	}
@@ -114,24 +144,26 @@ func shouldRetry(c *gin.Context, channelId int, openaiErr *dto.OpenAIErrorWithSt
 		return true
 	}
 	if openaiErr.StatusCode == http.StatusBadRequest {
+		channelType := c.GetInt("channel_type")
+		if channelType == common.ChannelTypeAnthropic {
+			return true
+		}
 		return false
 	}
 	if openaiErr.StatusCode == 408 {
 		// azure处理超时不重试
 		return false
 	}
-	if openaiErr.LocalError {
-		return false
-	}
 	if openaiErr.StatusCode/100 == 2 {
 		return false
 	}
 	return true
 }
 
-func processChannelError(c *gin.Context, channelId int, channelType int, channelName string, err *dto.OpenAIErrorWithStatusCode) {
-	autoBan := c.GetBool("auto_ban")
-	common.LogError(c.Request.Context(), fmt.Sprintf("relay error (channel #%d, status code: %d): %s", channelId, err.StatusCode, err.Error.Message))
+func processChannelError(c *gin.Context, channelId int, channelType int, channelName string, autoBan bool, err *dto.OpenAIErrorWithStatusCode) {
+	// 不要使用context获取渠道信息，异步处理时可能会出现渠道信息不一致的情况
+	// do not use context to get channel info, there may be inconsistent channel info when processing asynchronously
+	common.LogError(c, fmt.Sprintf("relay error (channel #%d, status code: %d): %s", channelId, err.StatusCode, err.Error.Message))
 	if service.ShouldDisableChannel(channelType, err) && autoBan {
 		service.DisableChannel(channelId, channelName, err.Error.Message)
 	}
@@ -208,14 +240,14 @@ func RelayTask(c *gin.Context) {
 	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()))
+			common.LogError(c, 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))
+		common.LogInfo(c, fmt.Sprintf("using channel #%d to retry (remain times %d)", channel.Id, i))
 		middleware.SetupContextForSelectedChannel(c, channel, originalModel)
 
 		requestBody, err := common.GetRequestBody(c)
@@ -225,7 +257,7 @@ func RelayTask(c *gin.Context) {
 	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)
+		common.LogInfo(c, retryLogStr)
 	}
 	if taskErr != nil {
 		if taskErr.StatusCode == http.StatusTooManyRequests {

controller/topup.go

@@ -41,12 +41,12 @@ func GetEpayClient() *epay.Client {
 	return withUrl
 }
 
-func getPayMoney(amount float64, user model.User) float64 {
+func getPayMoney(amount float64, group string) float64 {
 	if !common.DisplayInCurrencyEnabled {
 		amount = amount / common.QuotaPerUnit
 	}
 	// 别问为什么用float64，问就是这么点钱没必要
-	topupGroupRatio := common.GetTopupGroupRatio(user.Group)
+	topupGroupRatio := common.GetTopupGroupRatio(group)
 	if topupGroupRatio == 0 {
 		topupGroupRatio = 1
 	}
@@ -75,8 +75,12 @@ func RequestEpay(c *gin.Context) {
 	}
 
 	id := c.GetInt("id")
-	user, _ := model.GetUserById(id, false)
-	payMoney := getPayMoney(float64(req.Amount), *user)
+	group, err := model.CacheGetUserGroup(id)
+	if err != nil {
+		c.JSON(200, gin.H{"message": "error", "data": "获取用户分组失败"})
+		return
+	}
+	payMoney := getPayMoney(float64(req.Amount), group)
 	if payMoney < 0.01 {
 		c.JSON(200, gin.H{"message": "error", "data": "充值金额过低"})
 		return
@@ -94,6 +98,7 @@ func RequestEpay(c *gin.Context) {
 	returnUrl, _ := url.Parse(constant.ServerAddress + "/log")
 	notifyUrl, _ := url.Parse(callBackAddress + "/api/user/epay/notify")
 	tradeNo := fmt.Sprintf("%s%d", common.GetRandomString(6), time.Now().Unix())
+	tradeNo = fmt.Sprintf("USR%dNO%s", id, tradeNo)
 	client := GetEpayClient()
 	if client == nil {
 		c.JSON(200, gin.H{"message": "error", "data": "当前管理员未配置支付信息"})
@@ -101,8 +106,8 @@ func RequestEpay(c *gin.Context) {
 	}
 	uri, params, err := client.Purchase(&epay.PurchaseArgs{
 		Type:           payType,
-		ServiceTradeNo: "A" + tradeNo,
-		Name:           "B" + tradeNo,
+		ServiceTradeNo: tradeNo,
+		Name:           fmt.Sprintf("TUC%d", req.Amount),
 		Money:          strconv.FormatFloat(payMoney, 'f', 2, 64),
 		Device:         epay.PC,
 		NotifyUrl:      notifyUrl,
@@ -120,7 +125,7 @@ func RequestEpay(c *gin.Context) {
 		UserId:     id,
 		Amount:     amount,
 		Money:      payMoney,
-		TradeNo:    "A" + tradeNo,
+		TradeNo:    tradeNo,
 		CreateTime: time.Now().Unix(),
 		Status:     "pending",
 	}
@@ -232,8 +237,12 @@ func RequestAmount(c *gin.Context) {
 		return
 	}
 	id := c.GetInt("id")
-	user, _ := model.GetUserById(id, false)
-	payMoney := getPayMoney(float64(req.Amount), *user)
+	group, err := model.CacheGetUserGroup(id)
+	if err != nil {
+		c.JSON(200, gin.H{"message": "error", "data": "获取用户分组失败"})
+		return
+	}
+	payMoney := getPayMoney(float64(req.Amount), group)
 	if payMoney <= 0.01 {
 		c.JSON(200, gin.H{"message": "error", "data": "充值金额过低"})
 		return

controller/user.go

@@ -791,11 +791,11 @@ type topUpRequest struct {
 	Key string `json:"key"`
 }
 
-var lock = sync.Mutex{}
+var topUpLock = sync.Mutex{}
 
 func TopUp(c *gin.Context) {
-	lock.Lock()
-	defer lock.Unlock()
+	topUpLock.Lock()
+	defer topUpLock.Unlock()
 	req := topUpRequest{}
 	err := c.ShouldBindJSON(&req)
 	if err != nil {

dto/midjourney.go

@@ -33,6 +33,12 @@ type MidjourneyResponse struct {
 	Result      string      `json:"result"`
 }
 
+type MidjourneyUploadResponse struct {
+	Code        int      `json:"code"`
+	Description string   `json:"description"`
+	Result      []string `json:"result"`
+}
+
 type MidjourneyResponseWithStatusCode struct {
 	StatusCode int `json:"statusCode"`
 	Response   MidjourneyResponse

dto/rerank.go

@@ -1,14 +1,17 @@
 package dto
 
 type RerankRequest struct {
-	Documents []any  `json:"documents"`
-	Query     string `json:"query"`
-	Model     string `json:"model"`
-	TopN      int    `json:"top_n"`
+	Documents       []any  `json:"documents"`
+	Query           string `json:"query"`
+	Model           string `json:"model"`
+	TopN            int    `json:"top_n"`
+	ReturnDocuments bool   `json:"return_documents,omitempty"`
+	MaxChunkPerDoc  int    `json:"max_chunk_per_doc,omitempty"`
+	OverLapTokens   int    `json:"overlap_tokens,omitempty"`
 }
 
 type RerankResponseDocument struct {
-	Document       any     `json:"document"`
+	Document       any     `json:"document,omitempty"`
 	Index          int     `json:"index"`
 	RelevanceScore float64 `json:"relevance_score"`
 }

dto/text_request.go

@@ -7,31 +7,31 @@ type ResponseFormat struct {
 }
 
 type GeneralOpenAIRequest struct {
-	Model            string          `json:"model,omitempty"`
-	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"`
-	TopK             int             `json:"top_k,omitempty"`
-	Stop             any             `json:"stop,omitempty"`
-	N                int             `json:"n,omitempty"`
-	Input            any             `json:"input,omitempty"`
-	Instruction      string          `json:"instruction,omitempty"`
-	Size             string          `json:"size,omitempty"`
-	Functions        any             `json:"functions,omitempty"`
-	FrequencyPenalty float64         `json:"frequency_penalty,omitempty"`
-	PresencePenalty  float64         `json:"presence_penalty,omitempty"`
-	ResponseFormat   *ResponseFormat `json:"response_format,omitempty"`
-	Seed             float64         `json:"seed,omitempty"`
-	Tools            []ToolCall      `json:"tools,omitempty"`
-	ToolChoice       any             `json:"tool_choice,omitempty"`
-	User             string          `json:"user,omitempty"`
-	LogProbs         bool            `json:"logprobs,omitempty"`
-	TopLogProbs      int             `json:"top_logprobs,omitempty"`
-	Dimensions       int             `json:"dimensions,omitempty"`
+	Model            string         `json:"model,omitempty"`
+	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"`
+	TopK             int            `json:"top_k,omitempty"`
+	Stop             any            `json:"stop,omitempty"`
+	N                int            `json:"n,omitempty"`
+	Input            any            `json:"input,omitempty"`
+	Instruction      string         `json:"instruction,omitempty"`
+	Size             string         `json:"size,omitempty"`
+	Functions        any            `json:"functions,omitempty"`
+	FrequencyPenalty float64        `json:"frequency_penalty,omitempty"`
+	PresencePenalty  float64        `json:"presence_penalty,omitempty"`
+	ResponseFormat   any            `json:"response_format,omitempty"`
+	Seed             float64        `json:"seed,omitempty"`
+	Tools            []ToolCall     `json:"tools,omitempty"`
+	ToolChoice       any            `json:"tool_choice,omitempty"`
+	User             string         `json:"user,omitempty"`
+	LogProbs         bool           `json:"logprobs,omitempty"`
+	TopLogProbs      int            `json:"top_logprobs,omitempty"`
+	Dimensions       int            `json:"dimensions,omitempty"`
 }
 
 type OpenAITools struct {

dto/text_response.go

@@ -34,6 +34,7 @@ type OpenAITextResponseChoice struct {
 
 type OpenAITextResponse struct {
 	Id      string                     `json:"id"`
+	Model   string                     `json:"model"`
 	Object  string                     `json:"object"`
 	Created int64                      `json:"created"`
 	Choices []OpenAITextResponseChoice `json:"choices"`

go.mod

@@ -1,7 +1,9 @@
 module one-api
 
 // +heroku goVersion go1.18
-go 1.18
+go 1.21
+
+toolchain go1.22.4
 
 require (
 	github.com/Calcium-Ion/go-epay v0.0.2
@@ -9,6 +11,7 @@ require (
 	github.com/aws/aws-sdk-go-v2 v1.26.1
 	github.com/aws/aws-sdk-go-v2/credentials v1.17.11
 	github.com/aws/aws-sdk-go-v2/service/bedrockruntime v1.7.4
+	github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b
 	github.com/gin-contrib/cors v1.4.0
 	github.com/gin-contrib/gzip v0.0.6
 	github.com/gin-contrib/sessions v0.0.5
@@ -24,7 +27,7 @@ require (
 	github.com/pkoukk/tiktoken-go v0.1.7
 	github.com/samber/lo v1.39.0
 	github.com/shirou/gopsutil v3.21.11+incompatible
-	golang.org/x/crypto v0.21.0
+	golang.org/x/crypto v0.26.0
 	golang.org/x/image v0.15.0
 	gorm.io/driver/mysql v1.4.3
 	gorm.io/driver/postgres v1.5.2
@@ -38,9 +41,8 @@ require (
 	github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.5 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.5 // indirect
 	github.com/aws/smithy-go v1.20.2 // indirect
-	github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b // indirect
 	github.com/bytedance/sonic v1.9.1 // indirect
-	github.com/cespare/xxhash/v2 v2.1.2 // indirect
+	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/dlclark/regexp2 v1.11.0 // indirect
@@ -51,6 +53,7 @@ require (
 	github.com/go-playground/universal-translator v0.18.1 // indirect
 	github.com/go-sql-driver/mysql v1.6.0 // indirect
 	github.com/goccy/go-json v0.10.2 // indirect
+	github.com/google/go-cmp v0.6.0 // indirect
 	github.com/gorilla/context v1.1.1 // indirect
 	github.com/gorilla/securecookie v1.1.1 // indirect
 	github.com/gorilla/sessions v1.2.1 // indirect
@@ -69,6 +72,7 @@ require (
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/pelletier/go-toml/v2 v2.0.8 // indirect
+	github.com/stretchr/testify v1.9.0 // indirect
 	github.com/tklauser/go-sysconf v0.3.12 // indirect
 	github.com/tklauser/numcpus v0.6.1 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
@@ -76,10 +80,10 @@ require (
 	github.com/yusufpapurcu/wmi v1.2.3 // indirect
 	golang.org/x/arch v0.3.0 // indirect
 	golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 // indirect
-	golang.org/x/net v0.21.0 // indirect
-	golang.org/x/sync v0.7.0 // indirect
-	golang.org/x/sys v0.18.0 // indirect
-	golang.org/x/text v0.14.0 // indirect
-	google.golang.org/protobuf v1.30.0 // indirect
+	golang.org/x/net v0.28.0 // indirect
+	golang.org/x/sync v0.8.0 // indirect
+	golang.org/x/sys v0.24.0 // indirect
+	golang.org/x/text v0.17.0 // indirect
+	google.golang.org/protobuf v1.34.2 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

go.sum

@@ -23,8 +23,8 @@ github.com/bytedance/gopkg v0.0.0-20220118071334-3db87571198b/go.mod h1:2ZlV9BaU
 github.com/bytedance/sonic v1.5.0/go.mod h1:ED5hyg4y6t3/9Ku1R6dU/4KyJ48DZ4jPhfY1O2AihPM=
 github.com/bytedance/sonic v1.9.1 h1:6iJ6NqdoxCDr6mbY8h18oSO+cShGSMRGCEo7F2h0x8s=
 github.com/bytedance/sonic v1.9.1/go.mod h1:i736AoUSYt75HyZLoJW9ERYxcy6eaN6h4BZXU064P/U=
-github.com/cespare/xxhash/v2 v2.1.2 h1:YRXhKfTDauu4ajMg1TPgFO5jnlC2HCbmLXMcTG5cbYE=
-github.com/cespare/xxhash/v2 v2.1.2/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
+github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
+github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
 github.com/chenzhuoyu/base64x v0.0.0-20211019084208-fb5309c8db06/go.mod h1:DH46F32mSOjUmXrMHnKwZdA8wcEefY7UVqBKYGjpdQY=
 github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311 h1:qSGYFH7+jGhDF8vLC+iwCD4WpbV1EBDSzWkJODFLams=
 github.com/chenzhuoyu/base64x v0.0.0-20221115062448-fe3a3abad311/go.mod h1:b583jCggY9gE99b6G5LEC39OIiVsWj+R97kbl5odCEk=
@@ -37,6 +37,7 @@ github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cu
 github.com/dlclark/regexp2 v1.11.0 h1:G/nrcoOa7ZXlpoa/91N3X7mM3r8eIlMBBJZvsz/mxKI=
 github.com/dlclark/regexp2 v1.11.0/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
 github.com/fsnotify/fsnotify v1.4.9 h1:hsms1Qyu0jgnwNXIxa+/V/PDsU6CfLf6CNO8H7IWoS4=
+github.com/fsnotify/fsnotify v1.4.9/go.mod h1:znqG4EE+3YCdAaPaxE2ZRY/06pZUdp0tY4IgpuI1SZQ=
 github.com/gabriel-vasile/mimetype v1.4.3 h1:in2uUcidCuFcDKtdcBxlR0rJ1+fsokWf+uqxgUFjbI0=
 github.com/gabriel-vasile/mimetype v1.4.3/go.mod h1:d8uq/6HKRL6CGdk+aubisF/M5GcPfT7nKyLpA0lbSSk=
 github.com/gin-contrib/cors v1.4.0 h1:oJ6gwtUl3lqV0WEIwM/LxPF1QZ5qe2lGWdY2+bz7y0g=
@@ -57,6 +58,7 @@ github.com/go-ole/go-ole v1.2.6 h1:/Fpf6oFPoeFik9ty7siob0G6Ke8QvQEuVcuChpwXzpY=
 github.com/go-ole/go-ole v1.2.6/go.mod h1:pprOEPIfldk/42T2oK7lQ4v4JSDwmV0As9GaiUsvbm0=
 github.com/go-playground/assert/v2 v2.0.1/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
 github.com/go-playground/assert/v2 v2.2.0 h1:JvknZsQTYeFEAhQwI4qEt9cyV5ONwRHC+lYKSsYSR8s=
+github.com/go-playground/assert/v2 v2.2.0/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
 github.com/go-playground/locales v0.13.0/go.mod h1:taPMhCMXrRLJO55olJkUXHZBHCxTMfnGwq/HNwmWNS8=
 github.com/go-playground/locales v0.14.0/go.mod h1:sawfccIbzZTqEDETgFXqTho0QybSa7l++s0DH+LDiLs=
 github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/oXslEjJA=
@@ -81,7 +83,8 @@ github.com/golang-jwt/jwt v3.2.2+incompatible/go.mod h1:8pz2t5EyA70fFQQSrl6XZXzq
 github.com/golang/protobuf v1.3.3/go.mod h1:vzj43D7+SQXF/4pzW/hwtAqwc6iTitCiVSaWz5lYuqw=
 github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
-github.com/google/go-cmp v0.5.8 h1:e6P7q2lk1O+qJJb4BtCQXlK8vWEO8V1ZeuEdJNOqZyg=
+github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
+github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
@@ -142,8 +145,11 @@ github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lN
 github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
 github.com/nxadm/tail v1.4.8 h1:nPr65rt6Y5JFSKQO7qToXr7pePgD6Gwiw05lkbyAQTE=
+github.com/nxadm/tail v1.4.8/go.mod h1:+ncqLTQzXmGhMZNUePPaPqPvBxHAIsmXswZKocGu+AU=
 github.com/onsi/ginkgo v1.16.5 h1:8xi0RTUf59SOSfEtZMvwTvXYMzG4gV23XVHOZiXNtnE=
+github.com/onsi/ginkgo v1.16.5/go.mod h1:+E8gABHa3K6zRBolWtd+ROzc/U5bkGt0FwiG042wbpU=
 github.com/onsi/gomega v1.18.1 h1:M1GfJqGRrBrrGGsbxzV5dqM2U2ApXefZCQpkukxYRLE=
+github.com/onsi/gomega v1.18.1/go.mod h1:0q+aL8jAiMXy9hbwj2mr5GziHiwhAIQpFmmtT5hitRs=
 github.com/pelletier/go-toml/v2 v2.0.1/go.mod h1:r9LEWfGN8R5k0VXJ+0BkIe7MYkRdwZOjgMj2KwnJFUo=
 github.com/pelletier/go-toml/v2 v2.0.8 h1:0ctb6s9mE31h0/lhu+J6OPmVeDxJn+kYnJc2jZR9tGQ=
 github.com/pelletier/go-toml/v2 v2.0.8/go.mod h1:vuYfssBdrU2XDZ9bYydBu6t+6a6PYNcZljzZR9VXg+4=
@@ -172,7 +178,8 @@ github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
 github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
 github.com/stretchr/testify v1.8.3/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
-github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
+github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
+github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
 github.com/tklauser/go-sysconf v0.3.12 h1:0QaGUFOdQaIVdPgfITYzaTegZvdCjmYO52cSFAEVmqU=
 github.com/tklauser/go-sysconf v0.3.12/go.mod h1:Ho14jnntGE1fpdOqQEEaiKRpvIavV0hSfmBq8nJbHYI=
 github.com/tklauser/numcpus v0.6.1 h1:ng9scYS7az0Bk4OZLvrNXNSAO2Pxr1XXRAPyjhIx+Fk=
@@ -191,18 +198,18 @@ golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUu
 golang.org/x/arch v0.3.0 h1:02VY4/ZcO/gBOH6PUaoiptASxtXU10jazRCP865E97k=
 golang.org/x/arch v0.3.0/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
 golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
-golang.org/x/crypto v0.21.0 h1:X31++rzVUdKhX5sWmSOFZxx8UW/ldWx55cbf08iNAMA=
-golang.org/x/crypto v0.21.0/go.mod h1:0BP7YvVV9gBbVKyeTG0Gyn+gZm94bibOW5BjDEYAOMs=
+golang.org/x/crypto v0.26.0 h1:RrRspgV4mU+YwB4FYnuBoKsUapNIL5cohGAmSH3azsw=
+golang.org/x/crypto v0.26.0/go.mod h1:GY7jblb9wI+FOo5y8/S2oY4zWP07AkOJ4+jxCqdqn54=
 golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0 h1:985EYyeCOxTpcgOTJpflJUwOeEz0CQOdPt73OzpE9F8=
 golang.org/x/exp v0.0.0-20240404231335-c0f41cb1a7a0/go.mod h1:/lliqkxwWAhPjf5oSOIJup2XcqJaw8RGS6k3TGEc7GI=
 golang.org/x/image v0.15.0 h1:kOELfmgrmJlw4Cdb7g/QGuB3CvDrXbqEIww/pNtNBm8=
 golang.org/x/image v0.15.0/go.mod h1:HUYqC05R2ZcZ3ejNQsIHQDQiwWM4JBqmm6MKANTp4LE=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
-golang.org/x/net v0.21.0 h1:AQyQV4dYCvJ7vGmJyKki9+PBdyvhkSd8EIx/qb0AYv4=
-golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
+golang.org/x/net v0.28.0 h1:a9JDOJc5GMUJ0+UDqmLT86WiEy7iWyIhz8gz8E4e5hE=
+golang.org/x/net v0.28.0/go.mod h1:yqtgsTWOOnlGLG9GFRrK3++bGOUEkNBoHZc8MEDWPNg=
 golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.7.0 h1:YsImfSBoP9QPYL0xyKJPq0gcaJdG3rInoqxTWbfQu9M=
-golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
+golang.org/x/sync v0.8.0 h1:3NFvSEYkUoMifnESzZl15y791HH1qU2xm6eCJU5ZPXQ=
+golang.org/x/sync v0.8.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200116001909-b77594299b42/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -214,26 +221,27 @@ golang.org/x/sys v0.0.0-20220704084225-05e143d24a9e/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.18.0 h1:DBdB3niSjOA/O0blCZBqDefyWNYveAYMNF1Wum0DYQ4=
-golang.org/x/sys v0.18.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.24.0 h1:Twjiwq9dn6R1fQcyiK+wQyHWfaz/BJB+YIpzU/Cv3Xg=
+golang.org/x/sys v0.24.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
-golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
-golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/text v0.17.0 h1:XtiM5bkSOt+ewxlOE/aE/AKEHibwj/6gvWMl9Rsh0Qc=
+golang.org/x/text v0.17.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
 google.golang.org/protobuf v1.28.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
-google.golang.org/protobuf v1.30.0 h1:kPPoIgf3TsEvrm0PFe15JQ+570QVxYzEvvHqChK+cng=
-google.golang.org/protobuf v1.30.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
+google.golang.org/protobuf v1.34.2 h1:6xV6lTsCfpGD21XK49h7MhtcApnLqkfYgPcdHftf6hg=
+google.golang.org/protobuf v1.34.2/go.mod h1:qYOHts0dSfpeUzUFpOMr/WGzszTmLH+DiWniOlNbLDw=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
 gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI=
 gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 h1:uRGJdciOHaEIrze2W8Q3AKkepLTh2hOroT7a+7czfdQ=
+gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7/go.mod h1:dt/ZhP58zS4L8KSrWDmTeBkI65Dw0HsyUHuEVlX15mw=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.2.8/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=

main.go

@@ -42,6 +42,11 @@ func main() {
 	if err != nil {
 		common.FatalLog("failed to initialize database: " + err.Error())
 	}
+	// Initialize SQL Database
+	err = model.InitLogDB()
+	if err != nil {
+		common.FatalLog("failed to initialize database: " + err.Error())
+	}
 	defer func() {
 		err := model.CloseDB()
 		if err != nil {
@@ -55,6 +60,8 @@ func main() {
 		common.FatalLog("failed to initialize Redis: " + err.Error())
 	}
 
+	// Initialize constants
+	constant.InitEnv()
 	// Initialize options
 	model.InitOptionMap()
 	if common.RedisEnabled {

middleware/auth.go

@@ -143,6 +143,12 @@ func TokenAuth() func(c *gin.Context) {
 			key = parts[0]
 		}
 		token, err := model.ValidateUserToken(key)
+		if token != nil {
+			id := c.GetInt("id")
+			if id == 0 {
+				c.Set("id", token.UserId)
+			}
+		}
 		if err != nil {
 			abortWithOpenAiMessage(c, http.StatusUnauthorized, err.Error())
 			return

middleware/distributor.go

@@ -184,19 +184,13 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 	if channel == nil {
 		return
 	}
-	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 {
-		ban = false
-	}
 	if nil != channel.OpenAIOrganization && "" != *channel.OpenAIOrganization {
 		c.Set("channel_organization", *channel.OpenAIOrganization)
 	}
-	c.Set("auto_ban", ban)
+	c.Set("auto_ban", channel.GetAutoBan())
 	c.Set("model_mapping", channel.GetModelMapping())
 	c.Set("status_code_mapping", channel.GetStatusCodeMapping())
 	c.Request.Header.Set("Authorization", fmt.Sprintf("Bearer %s", channel.Key))
@@ -205,6 +199,8 @@ func SetupContextForSelectedChannel(c *gin.Context, channel *model.Channel, mode
 	switch channel.Type {
 	case common.ChannelTypeAzure:
 		c.Set("api_version", channel.Other)
+	case common.ChannelTypeVertexAi:
+		c.Set("region", channel.Other)
 	case common.ChannelTypeXunfei:
 		c.Set("api_version", channel.Other)
 	case common.ChannelTypeGemini:

model/cache.go

@@ -270,6 +270,9 @@ func CacheGetRandomSatisfiedChannel(group string, model string, retry int) (*Cha
 	if strings.HasPrefix(model, "gpt-4-gizmo") {
 		model = "gpt-4-gizmo-*"
 	}
+	if strings.HasPrefix(model, "gpt-4o-gizmo") {
+		model = "gpt-4o-gizmo-*"
+	}
 
 	// if memory cache is disabled, get channel directly from database
 	if !common.MemoryCacheEnabled {

model/channel.go

@@ -61,6 +61,13 @@ func (channel *Channel) SetOtherInfo(otherInfo map[string]interface{}) {
 	channel.OtherInfo = string(otherInfoBytes)
 }
 
+func (channel *Channel) GetAutoBan() bool {
+	if channel.AutoBan == nil {
+		return false
+	}
+	return *channel.AutoBan == 1
+}
+
 func (channel *Channel) Save() error {
 	return DB.Save(channel).Error
 }
@@ -99,16 +106,23 @@ func SearchChannels(keyword string, group string, model string) ([]*Channel, err
 	// 构造WHERE子句
 	var whereClause string
 	var args []interface{}
-	if group != "" {
-		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + groupCol + " = ? AND " + modelsCol + " LIKE ?"
-		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, group, "%"+model+"%")
+	if group != "" && group != "null" {
+		var groupCondition string
+		if common.UsingMySQL {
+			groupCondition = `CONCAT(',', ` + groupCol + `, ',') LIKE ?`
+		} else {
+			// sqlite, PostgreSQL
+			groupCondition = `(',' || ` + groupCol + ` || ',') LIKE ?`
+		}
+		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + modelsCol + ` LIKE ? AND ` + groupCondition
+		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, "%"+model+"%", "%,"+group+",%")
 	} else {
 		whereClause = "(id = ? OR name LIKE ? OR " + keyCol + " = ?) AND " + modelsCol + " LIKE ?"
 		args = append(args, common.String2Int(keyword), "%"+keyword+"%", keyword, "%"+model+"%")
 	}
 
 	// 执行查询
-	err := baseQuery.Where(whereClause, args...).Find(&channels).Error
+	err := baseQuery.Where(whereClause, args...).Order("priority desc").Find(&channels).Error
 	if err != nil {
 		return nil, err
 	}

model/log.go

@@ -3,10 +3,12 @@ package model
 import (
 	"context"
 	"fmt"
-	"github.com/bytedance/gopkg/util/gopool"
-	"gorm.io/gorm"
 	"one-api/common"
 	"strings"
+	"time"
+
+	"github.com/bytedance/gopkg/util/gopool"
+	"gorm.io/gorm"
 )
 
 type Log struct {
@@ -37,7 +39,7 @@ const (
 )
 
 func GetLogByKey(key string) (logs []*Log, err error) {
-	err = DB.Joins("left join tokens on tokens.id = logs.token_id").Where("tokens.key = ?", strings.TrimPrefix(key, "sk-")).Find(&logs).Error
+	err = LOG_DB.Joins("left join tokens on tokens.id = logs.token_id").Where("tokens.key = ?", strings.TrimPrefix(key, "sk-")).Find(&logs).Error
 	return logs, err
 }
 
@@ -53,7 +55,7 @@ func RecordLog(userId int, logType int, content string) {
 		Type:      logType,
 		Content:   content,
 	}
-	err := DB.Create(log).Error
+	err := LOG_DB.Create(log).Error
 	if err != nil {
 		common.SysError("failed to record log: " + err.Error())
 	}
@@ -83,7 +85,7 @@ func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptToke
 		IsStream:         isStream,
 		Other:            otherStr,
 	}
-	err := DB.Create(log).Error
+	err := LOG_DB.Create(log).Error
 	if err != nil {
 		common.LogError(ctx, "failed to record log: "+err.Error())
 	}
@@ -94,15 +96,15 @@ func RecordConsumeLog(ctx context.Context, userId int, channelId int, promptToke
 	}
 }
 
-func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, startIdx int, num int, channel int) (logs []*Log, err error) {
+func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, startIdx int, num int, channel int) (logs []*Log, total int64, err error) {
 	var tx *gorm.DB
 	if logType == LogTypeUnknown {
-		tx = DB
+		tx = LOG_DB
 	} else {
-		tx = DB.Where("type = ?", logType)
+		tx = LOG_DB.Where("type = ?", logType)
 	}
 	if modelName != "" {
-		tx = tx.Where("model_name like ?", "%"+modelName+"%")
+		tx = tx.Where("model_name like ?", modelName)
 	}
 	if username != "" {
 		tx = tx.Where("username = ?", username)
@@ -119,19 +121,26 @@ func GetAllLogs(logType int, startTimestamp int64, endTimestamp int64, modelName
 	if channel != 0 {
 		tx = tx.Where("channel_id = ?", channel)
 	}
+	err = tx.Model(&Log{}).Count(&total).Error
+	if err != nil {
+		return nil, 0, err
+	}
 	err = tx.Order("id desc").Limit(num).Offset(startIdx).Find(&logs).Error
-	return logs, err
+	if err != nil {
+		return nil, 0, err
+	}
+	return logs, total, err
 }
 
-func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int64, modelName string, tokenName string, startIdx int, num int) (logs []*Log, err error) {
+func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int64, modelName string, tokenName string, startIdx int, num int) (logs []*Log, total int64, err error) {
 	var tx *gorm.DB
 	if logType == LogTypeUnknown {
-		tx = DB.Where("user_id = ?", userId)
+		tx = LOG_DB.Where("user_id = ?", userId)
 	} else {
-		tx = DB.Where("user_id = ? and type = ?", userId, logType)
+		tx = LOG_DB.Where("user_id = ? and type = ?", userId, logType)
 	}
 	if modelName != "" {
-		tx = tx.Where("model_name = ?", modelName)
+		tx = tx.Where("model_name like ?", modelName)
 	}
 	if tokenName != "" {
 		tx = tx.Where("token_name = ?", tokenName)
@@ -142,6 +151,10 @@ func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int
 	if endTimestamp != 0 {
 		tx = tx.Where("created_at <= ?", endTimestamp)
 	}
+	err = tx.Model(&Log{}).Count(&total).Error
+	if err != nil {
+		return nil, 0, err
+	}
 	err = tx.Order("id desc").Limit(num).Offset(startIdx).Omit("id").Find(&logs).Error
 	for i := range logs {
 		var otherMap map[string]interface{}
@@ -152,16 +165,16 @@ func GetUserLogs(userId int, logType int, startTimestamp int64, endTimestamp int
 		}
 		logs[i].Other = common.MapToJsonStr(otherMap)
 	}
-	return logs, err
+	return logs, total, err
 }
 
 func SearchAllLogs(keyword string) (logs []*Log, err error) {
-	err = DB.Where("type = ? or content LIKE ?", keyword, keyword+"%").Order("id desc").Limit(common.MaxRecentItems).Find(&logs).Error
+	err = LOG_DB.Where("type = ? or content LIKE ?", keyword, keyword+"%").Order("id desc").Limit(common.MaxRecentItems).Find(&logs).Error
 	return logs, err
 }
 
 func SearchUserLogs(userId int, keyword string) (logs []*Log, err error) {
-	err = DB.Where("user_id = ? and type = ?", userId, keyword).Order("id desc").Limit(common.MaxRecentItems).Omit("id").Find(&logs).Error
+	err = LOG_DB.Where("user_id = ? and type = ?", userId, keyword).Order("id desc").Limit(common.MaxRecentItems).Omit("id").Find(&logs).Error
 	return logs, err
 }
 
@@ -172,12 +185,18 @@ type Stat struct {
 }
 
 func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string, channel int) (stat Stat) {
-	tx := DB.Table("logs").Select("sum(quota) quota, count(*) rpm, sum(prompt_tokens) + sum(completion_tokens) tpm")
+	tx := LOG_DB.Table("logs").Select("sum(quota) quota")
+
+	// 为rpm和tpm创建单独的查询
+	rpmTpmQuery := LOG_DB.Table("logs").Select("count(*) rpm, sum(prompt_tokens) + sum(completion_tokens) tpm")
+
 	if username != "" {
 		tx = tx.Where("username = ?", username)
+		rpmTpmQuery = rpmTpmQuery.Where("username = ?", username)
 	}
 	if tokenName != "" {
 		tx = tx.Where("token_name = ?", tokenName)
+		rpmTpmQuery = rpmTpmQuery.Where("token_name = ?", tokenName)
 	}
 	if startTimestamp != 0 {
 		tx = tx.Where("created_at >= ?", startTimestamp)
@@ -186,17 +205,29 @@ func SumUsedQuota(logType int, startTimestamp int64, endTimestamp int64, modelNa
 		tx = tx.Where("created_at <= ?", endTimestamp)
 	}
 	if modelName != "" {
-		tx = tx.Where("model_name = ?", modelName)
+		tx = tx.Where("model_name like ?", modelName)
+		rpmTpmQuery = rpmTpmQuery.Where("model_name like ?", modelName)
 	}
 	if channel != 0 {
 		tx = tx.Where("channel_id = ?", channel)
+		rpmTpmQuery = rpmTpmQuery.Where("channel_id = ?", channel)
 	}
-	tx.Where("type = ?", LogTypeConsume).Scan(&stat)
+
+	tx = tx.Where("type = ?", LogTypeConsume)
+	rpmTpmQuery = rpmTpmQuery.Where("type = ?", LogTypeConsume)
+
+	// 只统计最近60秒的rpm和tpm
+	rpmTpmQuery = rpmTpmQuery.Where("created_at >= ?", time.Now().Add(-60*time.Second).Unix())
+
+	// 执行查询
+	tx.Scan(&stat)
+	rpmTpmQuery.Scan(&stat)
+
 	return stat
 }
 
 func SumUsedToken(logType int, startTimestamp int64, endTimestamp int64, modelName string, username string, tokenName string) (token int) {
-	tx := DB.Table("logs").Select("ifnull(sum(prompt_tokens),0) + ifnull(sum(completion_tokens),0)")
+	tx := LOG_DB.Table("logs").Select("ifnull(sum(prompt_tokens),0) + ifnull(sum(completion_tokens),0)")
 	if username != "" {
 		tx = tx.Where("username = ?", username)
 	}
@@ -217,6 +248,6 @@ func SumUsedToken(logType int, startTimestamp int64, endTimestamp int64, modelNa
 }
 
 func DeleteOldLog(targetTimestamp int64) (int64, error) {
-	result := DB.Where("created_at < ?", targetTimestamp).Delete(&Log{})
+	result := LOG_DB.Where("created_at < ?", targetTimestamp).Delete(&Log{})
 	return result.RowsAffected, result.Error
 }

model/main.go

@@ -15,6 +15,8 @@ import (
 
 var DB *gorm.DB
 
+var LOG_DB *gorm.DB
+
 func createRootAccountIfNeed() error {
 	var user User
 	//if user.Status != common.UserStatusEnabled {
@@ -38,9 +40,9 @@ func createRootAccountIfNeed() error {
 	return nil
 }
 
-func chooseDB() (*gorm.DB, error) {
-	if os.Getenv("SQL_DSN") != "" {
-		dsn := os.Getenv("SQL_DSN")
+func chooseDB(envName string) (*gorm.DB, error) {
+	dsn := os.Getenv(envName)
+	if dsn != "" {
 		if strings.HasPrefix(dsn, "postgres://") {
 			// Use PostgreSQL
 			common.SysLog("using PostgreSQL as database")
@@ -52,6 +54,13 @@ func chooseDB() (*gorm.DB, error) {
 				PrepareStmt: true, // precompile SQL
 			})
 		}
+		if strings.HasPrefix(dsn, "local") {
+			common.SysLog("SQL_DSN not set, using SQLite as database")
+			common.UsingSQLite = true
+			return gorm.Open(sqlite.Open(common.SQLitePath), &gorm.Config{
+				PrepareStmt: true, // precompile SQL
+			})
+		}
 		// Use MySQL
 		common.SysLog("using MySQL as database")
 		// check parseTime
@@ -76,7 +85,7 @@ func chooseDB() (*gorm.DB, error) {
 }
 
 func InitDB() (err error) {
-	db, err := chooseDB()
+	db, err := chooseDB("SQL_DSN")
 	if err == nil {
 		if common.DebugEnabled {
 			db = db.Debug()
@@ -100,52 +109,7 @@ func InitDB() (err error) {
 		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY status VARCHAR(20);")   // TODO: delete this line when most users have upgraded
 		//}
 		common.SysLog("database migration started")
-		err = db.AutoMigrate(&Channel{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Token{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&User{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Option{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Redemption{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Ability{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Log{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Midjourney{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&TopUp{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&QuotaData{})
-		if err != nil {
-			return err
-		}
-		err = db.AutoMigrate(&Task{})
-		if err != nil {
-			return err
-		}
-		common.SysLog("database migrated")
-		err = createRootAccountIfNeed()
+		err = migrateDB()
 		return err
 	} else {
 		common.FatalLog(err)
@@ -153,8 +117,103 @@ func InitDB() (err error) {
 	return err
 }
 
-func CloseDB() error {
-	sqlDB, err := DB.DB()
+func InitLogDB() (err error) {
+	if os.Getenv("LOG_SQL_DSN") == "" {
+		LOG_DB = DB
+		return
+	}
+	db, err := chooseDB("LOG_SQL_DSN")
+	if err == nil {
+		if common.DebugEnabled {
+			db = db.Debug()
+		}
+		LOG_DB = db
+		sqlDB, err := LOG_DB.DB()
+		if err != nil {
+			return err
+		}
+		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
+		}
+		//if common.UsingMySQL {
+		//	_, _ = sqlDB.Exec("DROP INDEX idx_channels_key ON channels;")             // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY action VARCHAR(40);")   // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY progress VARCHAR(30);") // TODO: delete this line when most users have upgraded
+		//	_, _ = sqlDB.Exec("ALTER TABLE midjourneys MODIFY status VARCHAR(20);")   // TODO: delete this line when most users have upgraded
+		//}
+		common.SysLog("database migration started")
+		err = migrateLOGDB()
+		return err
+	} else {
+		common.FatalLog(err)
+	}
+	return err
+}
+
+func migrateDB() error {
+	err := DB.AutoMigrate(&Channel{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Token{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&User{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Option{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Redemption{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Ability{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Log{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Midjourney{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&TopUp{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&QuotaData{})
+	if err != nil {
+		return err
+	}
+	err = DB.AutoMigrate(&Task{})
+	if err != nil {
+		return err
+	}
+	common.SysLog("database migrated")
+	err = createRootAccountIfNeed()
+	return err
+}
+
+func migrateLOGDB() error {
+	var err error
+	if err = LOG_DB.AutoMigrate(&Log{}); err != nil {
+		return err
+	}
+	return nil
+}
+
+func closeDB(db *gorm.DB) error {
+	sqlDB, err := db.DB()
 	if err != nil {
 		return err
 	}
@@ -162,6 +221,16 @@ func CloseDB() error {
 	return err
 }
 
+func CloseDB() error {
+	if LOG_DB != DB {
+		err := closeDB(LOG_DB)
+		if err != nil {
+			return err
+		}
+	}
+	return closeDB(DB)
+}
+
 var (
 	lastPingTime time.Time
 	pingMutex    sync.Mutex

model/token.go

@@ -51,12 +51,12 @@ func ValidateUserToken(key string) (token *Token, err error) {
 		if token.Status == common.TokenStatusExhausted {
 			keyPrefix := key[:3]
 			keySuffix := key[len(key)-3:]
-			return nil, errors.New("该令牌额度已用尽 TokenStatusExhausted[sk-" + keyPrefix + "***" + keySuffix + "]")
+			return token, errors.New("该令牌额度已用尽 TokenStatusExhausted[sk-" + keyPrefix + "***" + keySuffix + "]")
 		} else if token.Status == common.TokenStatusExpired {
-			return nil, errors.New("该令牌已过期")
+			return token, errors.New("该令牌已过期")
 		}
 		if token.Status != common.TokenStatusEnabled {
-			return nil, errors.New("该令牌状态不可用")
+			return token, errors.New("该令牌状态不可用")
 		}
 		if token.ExpiredTime != -1 && token.ExpiredTime < common.GetTimestamp() {
 			if !common.RedisEnabled {
@@ -66,7 +66,7 @@ func ValidateUserToken(key string) (token *Token, err error) {
 					common.SysError("failed to update token status" + err.Error())
 				}
 			}
-			return nil, errors.New("该令牌已过期")
+			return token, errors.New("该令牌已过期")
 		}
 		if !token.UnlimitedQuota && token.RemainQuota <= 0 {
 			if !common.RedisEnabled {
@@ -79,7 +79,7 @@ func ValidateUserToken(key string) (token *Token, err error) {
 			}
 			keyPrefix := key[:3]
 			keySuffix := key[len(key)-3:]
-			return nil, errors.New(fmt.Sprintf("[sk-%s***%s] 该令牌额度已用尽 !token.UnlimitedQuota && token.RemainQuota = %d", keyPrefix, keySuffix, token.RemainQuota))
+			return token, errors.New(fmt.Sprintf("[sk-%s***%s] 该令牌额度已用尽 !token.UnlimitedQuota && token.RemainQuota = %d", keyPrefix, keySuffix, token.RemainQuota))
 		}
 		return token, nil
 	}

relay/channel/claude/adaptor.go

@@ -79,9 +79,9 @@ 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 {
-		err, usage = claudeStreamHandler(c, resp, info, a.RequestMode)
+		err, usage = ClaudeStreamHandler(c, resp, info, a.RequestMode)
 	} else {
-		err, usage = claudeHandler(a.RequestMode, c, resp, info.PromptTokens, info.UpstreamModelName)
+		err, usage = ClaudeHandler(c, resp, a.RequestMode, info)
 	}
 	return
 }

relay/channel/claude/dto.go

@@ -31,9 +31,9 @@ type ClaudeMessage struct {
 }
 
 type Tool struct {
-	Name        string      `json:"name"`
-	Description string      `json:"description,omitempty"`
-	InputSchema InputSchema `json:"input_schema"`
+	Name        string                 `json:"name"`
+	Description string                 `json:"description,omitempty"`
+	InputSchema map[string]interface{} `json:"input_schema"`
 }
 
 type InputSchema struct {

relay/channel/claude/relay-claude.go

@@ -4,7 +4,6 @@ import (
 	"bufio"
 	"encoding/json"
 	"fmt"
-	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
 	"one-api/common"
@@ -12,6 +11,8 @@ import (
 	relaycommon "one-api/relay/common"
 	"one-api/service"
 	"strings"
+
+	"github.com/gin-gonic/gin"
 )
 
 func stopReasonClaude2OpenAI(reason string) string {
@@ -63,15 +64,21 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 
 	for _, tool := range textRequest.Tools {
 		if params, ok := tool.Function.Parameters.(map[string]any); ok {
-			claudeTools = append(claudeTools, Tool{
+			claudeTool := Tool{
 				Name:        tool.Function.Name,
 				Description: tool.Function.Description,
-				InputSchema: InputSchema{
-					Type:       params["type"].(string),
-					Properties: params["properties"],
-					Required:   params["required"],
-				},
-			})
+			}
+			claudeTool.InputSchema = make(map[string]interface{})
+			claudeTool.InputSchema["type"] = params["type"].(string)
+			claudeTool.InputSchema["properties"] = params["properties"]
+			claudeTool.InputSchema["required"] = params["required"]
+			for s, a := range params {
+				if s == "type" || s == "properties" || s == "required" {
+					continue
+				}
+				claudeTool.InputSchema[s] = a
+			}
+			claudeTools = append(claudeTools, claudeTool)
 		}
 	}
 
@@ -102,13 +109,10 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 		}
 	}
 	formatMessages := make([]dto.Message, 0)
-	var lastMessage *dto.Message
+	lastMessage := dto.Message{
+		Role: "tool",
+	}
 	for i, message := range textRequest.Messages {
-		//if message.Role == "system" {
-		//	if i != 0 {
-		//		message.Role = "user"
-		//	}
-		//}
 		if message.Role == "" {
 			textRequest.Messages[i].Role = "user"
 		}
@@ -116,7 +120,13 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 			Role:    message.Role,
 			Content: message.Content,
 		}
-		if lastMessage != nil && lastMessage.Role == message.Role {
+		if message.Role == "tool" {
+			fmtMessage.ToolCallId = message.ToolCallId
+		}
+		if message.Role == "assistant" && message.ToolCalls != nil {
+			fmtMessage.ToolCalls = message.ToolCalls
+		}
+		if lastMessage.Role == message.Role && lastMessage.Role != "tool" {
 			if lastMessage.IsStringContent() && message.IsStringContent() {
 				content, _ := json.Marshal(strings.Trim(fmt.Sprintf("%s %s", lastMessage.StringContent(), message.StringContent()), "\""))
 				fmtMessage.Content = content
@@ -129,10 +139,11 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 			fmtMessage.Content = content
 		}
 		formatMessages = append(formatMessages, fmtMessage)
-		lastMessage = &textRequest.Messages[i]
+		lastMessage = fmtMessage
 	}
 
 	claudeMessages := make([]ClaudeMessage, 0)
+	isFirstMessage := true
 	for _, message := range formatMessages {
 		if message.Role == "system" {
 			if message.IsStringContent() {
@@ -148,10 +159,54 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 				claudeRequest.System = content
 			}
 		} else {
+			if isFirstMessage {
+				isFirstMessage = false
+				if message.Role != "user" {
+					// fix: first message is assistant, add user message
+					claudeMessage := ClaudeMessage{
+						Role: "user",
+						Content: []ClaudeMediaMessage{
+							{
+								Type: "text",
+								Text: "...",
+							},
+						},
+					}
+					claudeMessages = append(claudeMessages, claudeMessage)
+				}
+			}
 			claudeMessage := ClaudeMessage{
 				Role: message.Role,
 			}
-			if message.IsStringContent() {
+			if message.Role == "tool" {
+				if len(claudeMessages) > 0 && claudeMessages[len(claudeMessages)-1].Role == "user" {
+					lastMessage := claudeMessages[len(claudeMessages)-1]
+					if content, ok := lastMessage.Content.(string); ok {
+						lastMessage.Content = []ClaudeMediaMessage{
+							{
+								Type: "text",
+								Text: content,
+							},
+						}
+					}
+					lastMessage.Content = append(lastMessage.Content.([]ClaudeMediaMessage), ClaudeMediaMessage{
+						Type:      "tool_result",
+						ToolUseId: message.ToolCallId,
+						Content:   message.StringContent(),
+					})
+					claudeMessages[len(claudeMessages)-1] = lastMessage
+					continue
+				} else {
+					claudeMessage.Role = "user"
+					claudeMessage.Content = []ClaudeMediaMessage{
+						{
+							Type:      "tool_result",
+							ToolUseId: message.ToolCallId,
+							Content:   message.StringContent(),
+						},
+					}
+				}
+			} else if message.IsStringContent() && message.ToolCalls == nil {
 				claudeMessage.Content = message.StringContent()
 			} else {
 				claudeMediaMessages := make([]ClaudeMediaMessage, 0)
@@ -184,6 +239,28 @@ func RequestOpenAI2ClaudeMessage(textRequest dto.GeneralOpenAIRequest) (*ClaudeR
 					}
 					claudeMediaMessages = append(claudeMediaMessages, claudeMediaMessage)
 				}
+				if message.ToolCalls != nil {
+					for _, tc := range message.ToolCalls.([]interface{}) {
+						toolCallJSON, _ := json.Marshal(tc)
+						var toolCall dto.ToolCall
+						err := json.Unmarshal(toolCallJSON, &toolCall)
+						if err != nil {
+							common.SysError("tool call is not a dto.ToolCall: " + fmt.Sprintf("%v", tc))
+							continue
+						}
+						inputObj := make(map[string]any)
+						if err := json.Unmarshal([]byte(toolCall.Function.Arguments), &inputObj); err != nil {
+							common.SysError("tool call function arguments is not a map[string]any: " + fmt.Sprintf("%v", toolCall.Function.Arguments))
+							continue
+						}
+						claudeMediaMessages = append(claudeMediaMessages, ClaudeMediaMessage{
+							Type:  "tool_use",
+							Id:    toolCall.ID,
+							Name:  toolCall.Function.Name,
+							Input: inputObj,
+						})
+					}
+				}
 				claudeMessage.Content = claudeMediaMessages
 			}
 			claudeMessages = append(claudeMessages, claudeMessage)
@@ -318,12 +395,13 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *ClaudeResponse) *dto.Ope
 	if len(tools) > 0 {
 		choice.Message.ToolCalls = tools
 	}
+	fullTextResponse.Model = claudeResponse.Model
 	choices = append(choices, choice)
 	fullTextResponse.Choices = choices
 	return &fullTextResponse
 }
 
-func claudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, requestMode int) (*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{}
@@ -405,7 +483,7 @@ func claudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 	return nil, usage
 }
 
-func claudeHandler(requestMode int, c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+func ClaudeHandler(c *gin.Context, resp *http.Response, requestMode int, 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
@@ -431,15 +509,15 @@ func claudeHandler(requestMode int, c *gin.Context, resp *http.Response, promptT
 		}, nil
 	}
 	fullTextResponse := ResponseClaude2OpenAI(requestMode, &claudeResponse)
-	completionTokens, err := service.CountTokenText(claudeResponse.Completion, model)
+	completionTokens, err := service.CountTokenText(claudeResponse.Completion, info.OriginModelName)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "count_token_text_failed", http.StatusInternalServerError), nil
 	}
 	usage := dto.Usage{}
 	if requestMode == RequestModeCompletion {
-		usage.PromptTokens = promptTokens
+		usage.PromptTokens = info.PromptTokens
 		usage.CompletionTokens = completionTokens
-		usage.TotalTokens = promptTokens + completionTokens
+		usage.TotalTokens = info.PromptTokens + completionTokens
 	} else {
 		usage.PromptTokens = claudeResponse.Usage.InputTokens
 		usage.CompletionTokens = claudeResponse.Usage.OutputTokens

relay/channel/cohere/constant.go

@@ -1,7 +1,10 @@
 package cohere
 
 var ModelList = []string{
-	"command-r", "command-r-plus", "command-light", "command-light-nightly", "command", "command-nightly",
+	"command-r", "command-r-plus",
+	"command-r-08-2024", "command-r-plus-08-2024",
+	"c4ai-aya-23-35b", "c4ai-aya-23-8b",
+	"command-light", "command-light-nightly", "command", "command-nightly",
 	"rerank-english-v3.0", "rerank-multilingual-v3.0", "rerank-english-v2.0", "rerank-multilingual-v2.0",
 }
 

relay/channel/cohere/dto.go

@@ -8,6 +8,7 @@ type CohereRequest struct {
 	Message     string        `json:"message"`
 	Stream      bool          `json:"stream"`
 	MaxTokens   int           `json:"max_tokens"`
+	SafetyMode  string        `json:"safety_mode,omitempty"`
 }
 
 type ChatHistory struct {

relay/channel/cohere/relay-cohere.go

@@ -23,6 +23,9 @@ func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
 		Stream:      textRequest.Stream,
 		MaxTokens:   textRequest.GetMaxTokens(),
 	}
+	if common.CohereSafetySetting != "NONE" {
+		cohereReq.SafetyMode = common.CohereSafetySetting
+	}
 	if cohereReq.MaxTokens == 0 {
 		cohereReq.MaxTokens = 4000
 	}
@@ -44,6 +47,7 @@ func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
 			})
 		}
 	}
+
 	return &cohereReq
 }
 

relay/channel/gemini/adaptor.go

@@ -6,6 +6,7 @@ import (
 	"github.com/gin-gonic/gin"
 	"io"
 	"net/http"
+	"one-api/constant"
 	"one-api/dto"
 	"one-api/relay/channel"
 	relaycommon "one-api/relay/common"
@@ -25,18 +26,12 @@ func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInf
 }
 
 func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
-}
 
-// 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",
 }
 
 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]
+	version, beta := constant.GeminiModelMap[info.UpstreamModelName]
 	if !beta {
 		if info.ApiVersion != "" {
 			version = info.ApiVersion
@@ -75,9 +70,9 @@ 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 {
-		err, usage = geminiChatStreamHandler(c, resp, info)
+		err, usage = GeminiChatStreamHandler(c, resp, info)
 	} else {
-		err, usage = geminiChatHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+		err, usage = GeminiChatHandler(c, resp)
 	}
 	return
 }

relay/channel/gemini/constant.go

@@ -6,7 +6,7 @@ const (
 
 var ModelList = []string{
 	"gemini-1.0-pro-latest", "gemini-1.0-pro-001", "gemini-1.5-pro-latest", "gemini-1.5-flash-latest", "gemini-ultra",
-	"gemini-1.0-pro-vision-latest", "gemini-1.0-pro-vision-001",
+	"gemini-1.0-pro-vision-latest", "gemini-1.0-pro-vision-001", "gemini-1.5-pro-exp-0827", "gemini-1.5-flash-exp-0827",
 }
 
 var ChannelName = "google gemini"

relay/channel/gemini/relay-gemini.go

@@ -220,7 +220,7 @@ func streamResponseGeminiChat2OpenAI(geminiResponse *GeminiChatResponse) *dto.Ch
 	return &response
 }
 
-func geminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+func GeminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseText := ""
 	id := fmt.Sprintf("chatcmpl-%s", common.GetUUID())
 	createAt := common.GetTimestamp()
@@ -279,7 +279,7 @@ func geminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycom
 	return nil, usage
 }
 
-func geminiChatHandler(c *gin.Context, resp *http.Response, promptTokens int, model string) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+func GeminiChatHandler(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

relay/channel/jina/adaptor.go

@@ -32,7 +32,7 @@ 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 fmt.Sprintf("%s/v1/embeddings", info.BaseUrl), nil
 	}
 	return "", errors.New("invalid relay mode")
 }
@@ -58,6 +58,8 @@ func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dt
 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)
+	} else if info.RelayMode == constant.RelayModeEmbeddings {
+		err, usage = jinaEmbeddingHandler(c, resp)
 	}
 	return
 }

relay/channel/jina/relay-jina.go

@@ -33,3 +33,28 @@ func jinaRerankHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWit
 	_, err = c.Writer.Write(jsonResponse)
 	return nil, &jinaResp.Usage
 }
+
+func jinaEmbeddingHandler(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.OpenAIEmbeddingResponse
+	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/dto.go

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

relay/channel/openai/constant.go

@@ -8,7 +8,8 @@ var ModelList = []string{
 	"gpt-4-32k", "gpt-4-32k-0613",
 	"gpt-4-turbo-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
 	"gpt-4-vision-preview",
-	"gpt-4o", "gpt-4o-2024-05-13",
+	"chatgpt-4o-latest",
+	"gpt-4o", "gpt-4o-2024-05-13", "gpt-4o-2024-08-06",
 	"gpt-4o-mini", "gpt-4o-mini-2024-07-18",
 	"text-embedding-ada-002", "text-embedding-3-small", "text-embedding-3-large",
 	"text-curie-001", "text-babbage-001", "text-ada-001",

relay/channel/siliconflow/adaptor.go

@@ -0,0 +1,83 @@
+package siliconflow
+
+import (
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	"one-api/relay/channel/openai"
+	relaycommon "one-api/relay/common"
+	"one-api/relay/constant"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	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
+	} else if info.RelayMode == constant.RelayModeChatCompletions {
+		return fmt.Sprintf("%s/v1/chat/completions", 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, info *relaycommon.RelayInfo, 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) {
+	switch info.RelayMode {
+	case constant.RelayModeRerank:
+		err, usage = siliconflowRerankHandler(c, resp)
+	case constant.RelayModeChatCompletions:
+		if info.IsStream {
+			err, usage = openai.OaiStreamHandler(c, resp, info)
+		} else {
+			err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+		}
+	case constant.RelayModeEmbeddings:
+		err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName)
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/siliconflow/constant.go

@@ -0,0 +1,51 @@
+package siliconflow
+
+var ModelList = []string{
+	"THUDM/glm-4-9b-chat",
+	//"stabilityai/stable-diffusion-xl-base-1.0",
+	//"TencentARC/PhotoMaker",
+	"InstantX/InstantID",
+	//"stabilityai/stable-diffusion-2-1",
+	//"stabilityai/sd-turbo",
+	//"stabilityai/sdxl-turbo",
+	"ByteDance/SDXL-Lightning",
+	"deepseek-ai/deepseek-llm-67b-chat",
+	"Qwen/Qwen1.5-14B-Chat",
+	"Qwen/Qwen1.5-7B-Chat",
+	"Qwen/Qwen1.5-110B-Chat",
+	"Qwen/Qwen1.5-32B-Chat",
+	"01-ai/Yi-1.5-6B-Chat",
+	"01-ai/Yi-1.5-9B-Chat-16K",
+	"01-ai/Yi-1.5-34B-Chat-16K",
+	"THUDM/chatglm3-6b",
+	"deepseek-ai/DeepSeek-V2-Chat",
+	"Qwen/Qwen2-72B-Instruct",
+	"Qwen/Qwen2-7B-Instruct",
+	"Qwen/Qwen2-57B-A14B-Instruct",
+	//"stabilityai/stable-diffusion-3-medium",
+	"deepseek-ai/DeepSeek-Coder-V2-Instruct",
+	"Qwen/Qwen2-1.5B-Instruct",
+	"internlm/internlm2_5-7b-chat",
+	"BAAI/bge-large-en-v1.5",
+	"BAAI/bge-large-zh-v1.5",
+	"Pro/Qwen/Qwen2-7B-Instruct",
+	"Pro/Qwen/Qwen2-1.5B-Instruct",
+	"Pro/Qwen/Qwen1.5-7B-Chat",
+	"Pro/THUDM/glm-4-9b-chat",
+	"Pro/THUDM/chatglm3-6b",
+	"Pro/01-ai/Yi-1.5-9B-Chat-16K",
+	"Pro/01-ai/Yi-1.5-6B-Chat",
+	"Pro/google/gemma-2-9b-it",
+	"Pro/internlm/internlm2_5-7b-chat",
+	"Pro/meta-llama/Meta-Llama-3-8B-Instruct",
+	"Pro/mistralai/Mistral-7B-Instruct-v0.2",
+	"black-forest-labs/FLUX.1-schnell",
+	"iic/SenseVoiceSmall",
+	"netease-youdao/bce-embedding-base_v1",
+	"BAAI/bge-m3",
+	"internlm/internlm2_5-20b-chat",
+	"Qwen/Qwen2-Math-72B-Instruct",
+	"netease-youdao/bce-reranker-base_v1",
+	"BAAI/bge-reranker-v2-m3",
+}
+var ChannelName = "siliconflow"

relay/channel/siliconflow/dto.go

@@ -0,0 +1,17 @@
+package siliconflow
+
+import "one-api/dto"
+
+type SFTokens struct {
+	InputTokens  int `json:"input_tokens"`
+	OutputTokens int `json:"output_tokens"`
+}
+
+type SFMeta struct {
+	Tokens SFTokens `json:"tokens"`
+}
+
+type SFRerankResponse struct {
+	Results []dto.RerankResponseDocument `json:"results"`
+	Meta    SFMeta                       `json:"meta"`
+}

relay/channel/siliconflow/relay-siliconflow.go

@@ -0,0 +1,44 @@
+package siliconflow
+
+import (
+	"encoding/json"
+	"github.com/gin-gonic/gin"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/service"
+)
+
+func siliconflowRerankHandler(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 siliconflowResp SFRerankResponse
+	err = json.Unmarshal(responseBody, &siliconflowResp)
+	if err != nil {
+		return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
+	}
+	usage := &dto.Usage{
+		PromptTokens:     siliconflowResp.Meta.Tokens.InputTokens,
+		CompletionTokens: siliconflowResp.Meta.Tokens.OutputTokens,
+		TotalTokens:      siliconflowResp.Meta.Tokens.InputTokens + siliconflowResp.Meta.Tokens.OutputTokens,
+	}
+	rerankResp := &dto.RerankResponse{
+		Results: siliconflowResp.Results,
+		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/vertex/adaptor.go

@@ -0,0 +1,184 @@
+package vertex
+
+import (
+	"encoding/json"
+	"errors"
+	"fmt"
+	"github.com/gin-gonic/gin"
+	"github.com/jinzhu/copier"
+	"io"
+	"net/http"
+	"one-api/dto"
+	"one-api/relay/channel"
+	"one-api/relay/channel/claude"
+	"one-api/relay/channel/gemini"
+	"one-api/relay/channel/openai"
+	relaycommon "one-api/relay/common"
+	"strings"
+)
+
+const (
+	RequestModeClaude = 1
+	RequestModeGemini = 2
+	RequestModeLlama  = 3
+)
+
+var claudeModelMap = map[string]string{
+	"claude-3-sonnet-20240229":   "claude-3-sonnet@20240229",
+	"claude-3-opus-20240229":     "claude-3-opus@20240229",
+	"claude-3-haiku-20240307":    "claude-3-haiku@20240307",
+	"claude-3-5-sonnet-20240620": "claude-3-5-sonnet@20240620",
+}
+
+const anthropicVersion = "vertex-2023-10-16"
+
+type Adaptor struct {
+	RequestMode        int
+	AccountCredentials Credentials
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	//TODO implement me
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+	if strings.HasPrefix(info.UpstreamModelName, "claude") {
+		a.RequestMode = RequestModeClaude
+	} else if strings.HasPrefix(info.UpstreamModelName, "gemini") {
+		a.RequestMode = RequestModeGemini
+	} else if strings.Contains(info.UpstreamModelName, "llama") {
+		a.RequestMode = RequestModeLlama
+	}
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	adc := &Credentials{}
+	if err := json.Unmarshal([]byte(info.ApiKey), adc); err != nil {
+		return "", fmt.Errorf("failed to decode credentials file: %w", err)
+	}
+	region := GetModelRegion(info.ApiVersion, info.OriginModelName)
+	a.AccountCredentials = *adc
+	suffix := ""
+	if a.RequestMode == RequestModeGemini {
+		if info.IsStream {
+			suffix = "streamGenerateContent?alt=sse"
+		} else {
+			suffix = "generateContent"
+		}
+		return fmt.Sprintf(
+			"https://%s-aiplatform.googleapis.com/v1/projects/%s/locations/%s/publishers/google/models/%s:%s",
+			region,
+			adc.ProjectID,
+			region,
+			info.UpstreamModelName,
+			suffix,
+		), nil
+	} else if a.RequestMode == RequestModeClaude {
+		if info.IsStream {
+			suffix = "streamRawPredict?alt=sse"
+		} else {
+			suffix = "rawPredict"
+		}
+		if v, ok := claudeModelMap[info.UpstreamModelName]; ok {
+			info.UpstreamModelName = v
+		}
+		return fmt.Sprintf(
+			"https://%s-aiplatform.googleapis.com/v1/projects/%s/locations/%s/publishers/anthropic/models/%s:%s",
+			region,
+			adc.ProjectID,
+			region,
+			info.UpstreamModelName,
+			suffix,
+		), nil
+	} else if a.RequestMode == RequestModeLlama {
+		return fmt.Sprintf(
+			"https://%s-aiplatform.googleapis.com/v1beta1/projects/%s/locations/%s/endpoints/openapi/chat/completions",
+			region,
+			adc.ProjectID,
+			region,
+		), nil
+	}
+	return "", errors.New("unsupported request mode")
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+	accessToken, err := getAccessToken(a, info)
+	if err != nil {
+		return err
+	}
+	req.Header.Set("Authorization", "Bearer "+accessToken)
+	return nil
+}
+
+func (a *Adaptor) ConvertRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	if a.RequestMode == RequestModeClaude {
+		claudeReq, err := claude.RequestOpenAI2ClaudeMessage(*request)
+		if err != nil {
+			return nil, err
+		}
+		vertexClaudeReq := &VertexAIClaudeRequest{
+			AnthropicVersion: anthropicVersion,
+		}
+		if err = copier.Copy(vertexClaudeReq, claudeReq); err != nil {
+			return nil, errors.New("failed to copy claude request")
+		}
+		c.Set("request_model", request.Model)
+		return vertexClaudeReq, nil
+	} else if a.RequestMode == RequestModeGemini {
+		geminiRequest := gemini.CovertGemini2OpenAI(*request)
+		c.Set("request_model", request.Model)
+		return geminiRequest, nil
+	} else if a.RequestMode == RequestModeLlama {
+		return request, nil
+	}
+	return nil, errors.New("unsupported request mode")
+}
+
+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 {
+		switch a.RequestMode {
+		case RequestModeClaude:
+			err, usage = claude.ClaudeStreamHandler(c, resp, info, claude.RequestModeMessage)
+		case RequestModeGemini:
+			err, usage = gemini.GeminiChatStreamHandler(c, resp, info)
+		case RequestModeLlama:
+			err, usage = openai.OaiStreamHandler(c, resp, info)
+		}
+	} else {
+		switch a.RequestMode {
+		case RequestModeClaude:
+			err, usage = claude.ClaudeHandler(c, resp, claude.RequestModeMessage, info)
+		case RequestModeGemini:
+			err, usage = gemini.GeminiChatHandler(c, resp)
+		case RequestModeLlama:
+			err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.OriginModelName)
+		}
+	}
+	return
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}

relay/channel/vertex/constants.go

@@ -0,0 +1,15 @@
+package vertex
+
+var ModelList = []string{
+	"claude-3-sonnet-20240229",
+	"claude-3-opus-20240229",
+	"claude-3-haiku-20240307",
+	"claude-3-5-sonnet-20240620",
+
+	//"gemini-1.5-pro-latest", "gemini-1.5-flash-latest",
+	"gemini-1.5-pro-001", "gemini-1.5-flash-001", "gemini-pro", "gemini-pro-vision",
+
+	"meta/llama3-405b-instruct-maas",
+}
+
+var ChannelName = "vertex-ai"

relay/channel/vertex/dto.go

@@ -0,0 +1,17 @@
+package vertex
+
+import "one-api/relay/channel/claude"
+
+type VertexAIClaudeRequest struct {
+	AnthropicVersion string                 `json:"anthropic_version"`
+	Messages         []claude.ClaudeMessage `json:"messages"`
+	System           string                 `json:"system,omitempty"`
+	MaxTokens        int                    `json:"max_tokens,omitempty"`
+	StopSequences    []string               `json:"stop_sequences,omitempty"`
+	Stream           bool                   `json:"stream,omitempty"`
+	Temperature      float64                `json:"temperature,omitempty"`
+	TopP             float64                `json:"top_p,omitempty"`
+	TopK             int                    `json:"top_k,omitempty"`
+	Tools            []claude.Tool          `json:"tools,omitempty"`
+	ToolChoice       any                    `json:"tool_choice,omitempty"`
+}

relay/channel/vertex/relay-vertex.go

@@ -0,0 +1,16 @@
+package vertex
+
+import "one-api/common"
+
+func GetModelRegion(other string, localModelName string) string {
+	// if other is json string
+	if common.IsJsonStr(other) {
+		m := common.StrToMap(other)
+		if m[localModelName] != nil {
+			return m[localModelName].(string)
+		} else {
+			return m["default"].(string)
+		}
+	}
+	return other
+}

relay/channel/vertex/service_account.go

@@ -0,0 +1,122 @@
+package vertex
+
+import (
+	"crypto/rsa"
+	"crypto/x509"
+	"encoding/json"
+	"encoding/pem"
+	"errors"
+	"github.com/bytedance/gopkg/cache/asynccache"
+	"github.com/golang-jwt/jwt"
+	"net/http"
+	"net/url"
+	relaycommon "one-api/relay/common"
+	"strings"
+
+	"fmt"
+	"time"
+)
+
+type Credentials struct {
+	ProjectID    string `json:"project_id"`
+	PrivateKeyID string `json:"private_key_id"`
+	PrivateKey   string `json:"private_key"`
+	ClientEmail  string `json:"client_email"`
+	ClientID     string `json:"client_id"`
+}
+
+var Cache = asynccache.NewAsyncCache(asynccache.Options{
+	RefreshDuration: time.Minute * 35,
+	EnableExpire:    true,
+	ExpireDuration:  time.Minute * 30,
+	Fetcher: func(key string) (interface{}, error) {
+		return nil, errors.New("not found")
+	},
+})
+
+func getAccessToken(a *Adaptor, info *relaycommon.RelayInfo) (string, error) {
+	cacheKey := fmt.Sprintf("access-token-%d", info.ChannelId)
+	val, err := Cache.Get(cacheKey)
+	if err == nil {
+		return val.(string), nil
+	}
+
+	signedJWT, err := createSignedJWT(a.AccountCredentials.ClientEmail, a.AccountCredentials.PrivateKey)
+	if err != nil {
+		return "", fmt.Errorf("failed to create signed JWT: %w", err)
+	}
+	newToken, err := exchangeJwtForAccessToken(signedJWT)
+	if err != nil {
+		return "", fmt.Errorf("failed to exchange JWT for access token: %w", err)
+	}
+	if err := Cache.SetDefault(cacheKey, newToken); err {
+		return newToken, nil
+	}
+	return newToken, nil
+}
+
+func createSignedJWT(email, privateKeyPEM string) (string, error) {
+
+	privateKeyPEM = strings.ReplaceAll(privateKeyPEM, "-----BEGIN PRIVATE KEY-----", "")
+	privateKeyPEM = strings.ReplaceAll(privateKeyPEM, "-----END PRIVATE KEY-----", "")
+	privateKeyPEM = strings.ReplaceAll(privateKeyPEM, "\r", "")
+	privateKeyPEM = strings.ReplaceAll(privateKeyPEM, "\n", "")
+	privateKeyPEM = strings.ReplaceAll(privateKeyPEM, "\\n", "")
+
+	block, _ := pem.Decode([]byte("-----BEGIN PRIVATE KEY-----\n" + privateKeyPEM + "\n-----END PRIVATE KEY-----"))
+	if block == nil {
+		return "", fmt.Errorf("failed to parse PEM block containing the private key")
+	}
+
+	privateKey, err := x509.ParsePKCS8PrivateKey(block.Bytes)
+	if err != nil {
+		return "", err
+	}
+
+	rsaPrivateKey, ok := privateKey.(*rsa.PrivateKey)
+	if !ok {
+		return "", fmt.Errorf("not an RSA private key")
+	}
+
+	now := time.Now()
+	claims := jwt.MapClaims{
+		"iss":   email,
+		"scope": "https://www.googleapis.com/auth/cloud-platform",
+		"aud":   "https://www.googleapis.com/oauth2/v4/token",
+		"exp":   now.Add(time.Minute * 35).Unix(),
+		"iat":   now.Unix(),
+	}
+
+	token := jwt.NewWithClaims(jwt.SigningMethodRS256, claims)
+	signedToken, err := token.SignedString(rsaPrivateKey)
+	if err != nil {
+		return "", err
+	}
+
+	return signedToken, nil
+}
+
+func exchangeJwtForAccessToken(signedJWT string) (string, error) {
+
+	authURL := "https://www.googleapis.com/oauth2/v4/token"
+	data := url.Values{}
+	data.Set("grant_type", "urn:ietf:params:oauth:grant-type:jwt-bearer")
+	data.Set("assertion", signedJWT)
+
+	resp, err := http.PostForm(authURL, data)
+	if err != nil {
+		return "", err
+	}
+	defer resp.Body.Close()
+
+	var result map[string]interface{}
+	if err := json.NewDecoder(resp.Body).Decode(&result); err != nil {
+		return "", err
+	}
+
+	if accessToken, ok := result["access_token"].(string); ok {
+		return accessToken, nil
+	}
+
+	return "", fmt.Errorf("failed to get access token: %v", result)
+}

relay/channel/zhipu_4v/constants.go

@@ -1,7 +1,7 @@
 package zhipu_4v
 
 var ModelList = []string{
-	"glm-4", "glm-4v", "glm-3-turbo", "glm-4-alltools",
+	"glm-4", "glm-4v", "glm-3-turbo", "glm-4-alltools", "glm-4-plus", "glm-4-0520", "glm-4-air", "glm-4-airx", "glm-4-long", "glm-4-flash", "glm-4v-plus",
 }
 
 var ChannelName = "zhipu_4v"

relay/common/relay_info.go

@@ -22,6 +22,7 @@ type RelayInfo struct {
 	IsStream             bool
 	RelayMode            int
 	UpstreamModelName    string
+	OriginModelName      string
 	RequestURLPath       string
 	ApiVersion           string
 	PromptTokens         int
@@ -33,7 +34,7 @@ type RelayInfo struct {
 }
 
 func GenRelayInfo(c *gin.Context) *RelayInfo {
-	channelType := c.GetInt("channel")
+	channelType := c.GetInt("channel_type")
 	channelId := c.GetInt("channel_id")
 
 	tokenId := c.GetInt("token_id")
@@ -57,6 +58,8 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
 		TokenUnlimited:    tokenUnlimited,
 		StartTime:         startTime,
 		FirstResponseTime: startTime.Add(-time.Second),
+		OriginModelName:   c.GetString("original_model"),
+		UpstreamModelName: c.GetString("original_model"),
 		ApiType:           apiType,
 		ApiVersion:        c.GetString("api_version"),
 		ApiKey:            strings.TrimPrefix(c.Request.Header.Get("Authorization"), "Bearer "),
@@ -68,6 +71,9 @@ func GenRelayInfo(c *gin.Context) *RelayInfo {
 	if info.ChannelType == common.ChannelTypeAzure {
 		info.ApiVersion = GetAPIVersion(c)
 	}
+	if info.ChannelType == common.ChannelTypeVertexAi {
+		info.ApiVersion = c.GetString("region")
+	}
 	if info.ChannelType == common.ChannelTypeOpenAI || info.ChannelType == common.ChannelTypeAnthropic ||
 		info.ChannelType == common.ChannelTypeAws || info.ChannelType == common.ChannelTypeGemini ||
 		info.ChannelType == common.ChannelCloudflare {
@@ -112,7 +118,7 @@ type TaskRelayInfo struct {
 }
 
 func GenTaskRelayInfo(c *gin.Context) *TaskRelayInfo {
-	channelType := c.GetInt("channel")
+	channelType := c.GetInt("channel_type")
 	channelId := c.GetInt("channel_id")
 
 	tokenId := c.GetInt("token_id")

relay/constant/api_type.go

@@ -23,6 +23,8 @@ const (
 	APITypeDify
 	APITypeJina
 	APITypeCloudflare
+	APITypeSiliconFlow
+	APITypeVertexAi
 
 	APITypeDummy // this one is only for count, do not add any channel after this
 )
@@ -66,6 +68,10 @@ func ChannelType2APIType(channelType int) (int, bool) {
 		apiType = APITypeJina
 	case common.ChannelCloudflare:
 		apiType = APITypeCloudflare
+	case common.ChannelTypeSiliconFlow:
+		apiType = APITypeSiliconFlow
+	case common.ChannelTypeVertexAi:
+		apiType = APITypeVertexAi
 	}
 	if apiType == -1 {
 		return APITypeOpenAI, false

relay/constant/relay_mode.go

@@ -27,6 +27,7 @@ const (
 	RelayModeMidjourneyModal
 	RelayModeMidjourneyShorten
 	RelayModeSwapFace
+	RelayModeMidjourneyUpload
 
 	RelayModeAudioSpeech        // tts
 	RelayModeAudioTranscription // whisper
@@ -81,6 +82,9 @@ func Path2RelayModeMidjourney(path string) int {
 	} else if strings.HasSuffix(path, "/mj/insight-face/swap") {
 		// midjourney plus
 		relayMode = RelayModeSwapFace
+	} else if strings.HasSuffix(path, "/submit/upload-discord-images") {
+		// midjourney plus
+		relayMode = RelayModeMidjourneyUpload
 	} else if strings.HasSuffix(path, "/mj/submit/imagine") {
 		relayMode = RelayModeMidjourneyImagine
 	} else if strings.HasSuffix(path, "/mj/submit/blend") {

relay/relay-audio.go

@@ -75,7 +75,7 @@ func AudioHelper(c *gin.Context) *dto.OpenAIErrorWithStatusCode {
 		return service.OpenAIErrorWrapperLocal(err, "get_user_quota_failed", http.StatusInternalServerError)
 	}
 	if userQuota-preConsumedQuota < 0 {
-		return service.OpenAIErrorWrapperLocal(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
+		return service.OpenAIErrorWrapperLocal(errors.New(fmt.Sprintf("audio pre-consumed quota failed, user quota: %d, need quota: %d", userQuota, preConsumedQuota)), "insufficient_user_quota", http.StatusBadRequest)
 	}
 	err = model.CacheDecreaseUserQuota(relayInfo.UserId, preConsumedQuota)
 	if err != nil {

relay/relay-image.go

@@ -38,9 +38,7 @@ func getAndValidImageRequest(c *gin.Context, info *relaycommon.RelayInfo) (*dto.
 	if imageRequest.Model == "" {
 		imageRequest.Model = "dall-e-2"
 	}
-	if imageRequest.Quality == "" {
-		imageRequest.Quality = "standard"
-	}
+
 	// Not "256x256", "512x512", or "1024x1024"
 	if imageRequest.Model == "dall-e-2" || imageRequest.Model == "dall-e" {
 		if imageRequest.Size != "" && imageRequest.Size != "256x256" && imageRequest.Size != "512x512" && imageRequest.Size != "1024x1024" {
@@ -50,6 +48,9 @@ func getAndValidImageRequest(c *gin.Context, info *relaycommon.RelayInfo) (*dto.
 		if imageRequest.Size != "" && imageRequest.Size != "1024x1024" && imageRequest.Size != "1024x1792" && imageRequest.Size != "1792x1024" {
 			return nil, errors.New("size must be one of 256x256, 512x512, or 1024x1024, dall-e-3 1024x1792 or 1792x1024")
 		}
+		if imageRequest.Quality == "" {
+			imageRequest.Quality = "standard"
+		}
 		//if imageRequest.N != 1 {
 		//	return nil, errors.New("n must be 1")
 		//}
@@ -125,7 +126,7 @@ func ImageHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode {
 	quota := int(imageRatio * groupRatio * common.QuotaPerUnit)
 
 	if userQuota-quota < 0 {
-		return service.OpenAIErrorWrapperLocal(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
+		return service.OpenAIErrorWrapperLocal(errors.New(fmt.Sprintf("image pre-consumed quota failed, user quota: %d, need quota: %d", userQuota, quota)), "insufficient_user_quota", http.StatusBadRequest)
 	}
 
 	adaptor := GetAdaptor(relayInfo.ApiType)

relay/relay-mj.go

@@ -382,6 +382,8 @@ func RelayMidjourneySubmit(c *gin.Context, relayMode int) *dto.MidjourneyRespons
 		midjRequest.Action = constant.MjActionShorten
 	} else if relayMode == relayconstant.RelayModeMidjourneyBlend { //绘画任务，此类任务可重复
 		midjRequest.Action = constant.MjActionBlend
+	} else if relayMode == relayconstant.RelayModeMidjourneyUpload { //绘画任务，此类任务可重复
+		midjRequest.Action = constant.MjActionUpload
 	} else if midjRequest.TaskId != "" { //放大、变换任务，此类任务，如果重复且已有结果，远端api会直接返回最终结果
 		mjId := ""
 		if relayMode == relayconstant.RelayModeMidjourneyChange {
@@ -547,7 +549,7 @@ func RelayMidjourneySubmit(c *gin.Context, relayMode int) *dto.MidjourneyRespons
 		if err != nil {
 			common.SysError("get_channel_null: " + err.Error())
 		}
-		if channel.AutoBan != nil && *channel.AutoBan == 1 && common.AutomaticDisableChannelEnabled {
+		if channel.GetAutoBan() && common.AutomaticDisableChannelEnabled {
 			model.UpdateChannelStatusById(midjourneyTask.ChannelId, 2, "No available account instance")
 		}
 	}
@@ -580,7 +582,10 @@ func RelayMidjourneySubmit(c *gin.Context, relayMode int) *dto.MidjourneyRespons
 			responseBody = []byte(newBody)
 		}
 	}
-
+	if midjResponse.Code == 1 && midjRequest.Action == "UPLOAD" {
+		midjourneyTask.Progress = "100%"
+		midjourneyTask.Status = "SUCCESS"
+	}
 	err = midjourneyTask.Insert()
 	if err != nil {
 		return &dto.MidjourneyResponse{
@@ -594,7 +599,6 @@ func RelayMidjourneySubmit(c *gin.Context, relayMode int) *dto.MidjourneyRespons
 		newBody := strings.Replace(string(responseBody), `"code":22`, `"code":1`, -1)
 		responseBody = []byte(newBody)
 	}
-
 	//resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
 	bodyReader := io.NopCloser(bytes.NewBuffer(responseBody))
 

relay/relay-text.go

@@ -52,7 +52,7 @@ func getAndValidateTextRequest(c *gin.Context, relayInfo *relaycommon.RelayInfo)
 		}
 	case relayconstant.RelayModeEmbeddings:
 	case relayconstant.RelayModeModerations:
-		if textRequest.Input == "" {
+		if textRequest.Input == "" || textRequest.Input == nil {
 			return nil, errors.New("field input is required")
 		}
 	case relayconstant.RelayModeEdits:
@@ -238,9 +238,12 @@ func preConsumeQuota(c *gin.Context, preConsumedQuota int, relayInfo *relaycommo
 	if err != nil {
 		return 0, 0, service.OpenAIErrorWrapperLocal(err, "get_user_quota_failed", http.StatusInternalServerError)
 	}
-	if userQuota <= 0 || userQuota-preConsumedQuota < 0 {
+	if userQuota <= 0 {
 		return 0, 0, service.OpenAIErrorWrapperLocal(errors.New("user quota is not enough"), "insufficient_user_quota", http.StatusForbidden)
 	}
+	if userQuota-preConsumedQuota < 0 {
+		return 0, 0, service.OpenAIErrorWrapperLocal(errors.New(fmt.Sprintf("chat pre-consumed quota failed, user quota: %d, need quota: %d", userQuota, preConsumedQuota)), "insufficient_user_quota", http.StatusBadRequest)
+	}
 	err = model.CacheDecreaseUserQuota(relayInfo.UserId, preConsumedQuota)
 	if err != nil {
 		return 0, 0, service.OpenAIErrorWrapperLocal(err, "decrease_user_quota_failed", http.StatusInternalServerError)
@@ -253,13 +256,13 @@ func preConsumeQuota(c *gin.Context, preConsumedQuota int, relayInfo *relaycommo
 			if tokenQuota > 100*preConsumedQuota {
 				// 令牌额度充足，信任令牌
 				preConsumedQuota = 0
-				common.LogInfo(c.Request.Context(), fmt.Sprintf("user %d quota %d and token %d quota %d are enough, trusted and no need to pre-consume", relayInfo.UserId, userQuota, relayInfo.TokenId, tokenQuota))
+				common.LogInfo(c, fmt.Sprintf("user %d quota %d and token %d quota %d are enough, trusted and no need to pre-consume", relayInfo.UserId, userQuota, relayInfo.TokenId, tokenQuota))
 			}
 		} else {
 			// in this case, we do not pre-consume quota
 			// because the user has enough quota
 			preConsumedQuota = 0
-			common.LogInfo(c.Request.Context(), fmt.Sprintf("user %d with unlimited token has enough quota %d, trusted and no need to pre-consume", relayInfo.UserId, userQuota))
+			common.LogInfo(c, fmt.Sprintf("user %d with unlimited token has enough quota %d, trusted and no need to pre-consume", relayInfo.UserId, userQuota))
 		}
 	}
 	if preConsumedQuota > 0 {
@@ -286,7 +289,14 @@ func returnPreConsumedQuota(c *gin.Context, tokenId int, userQuota int, preConsu
 func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelName string,
 	usage *dto.Usage, ratio float64, preConsumedQuota int, userQuota int, modelRatio float64, groupRatio float64,
 	modelPrice float64, usePrice bool, extraContent string) {
-
+	if usage == nil {
+		usage = &dto.Usage{
+			PromptTokens:     relayInfo.PromptTokens,
+			CompletionTokens: 0,
+			TotalTokens:      relayInfo.PromptTokens,
+		}
+		extraContent += "  ，（可能是请求出错）"
+	}
 	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
 	promptTokens := usage.PromptTokens
 	completionTokens := usage.CompletionTokens
@@ -307,7 +317,7 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelN
 	totalTokens := promptTokens + completionTokens
 	var logContent string
 	if !usePrice {
-		logContent = fmt.Sprintf("模型倍率 %.2f，分组倍率 %.2f，补全倍率 %.2f", modelRatio, groupRatio, completionRatio)
+		logContent = fmt.Sprintf("模型倍率 %.2f，补全倍率 %.2f，分组倍率 %.2f", modelRatio, completionRatio, groupRatio)
 	} else {
 		logContent = fmt.Sprintf("模型价格 %.2f，分组倍率 %.2f", modelPrice, groupRatio)
 	}
@@ -344,6 +354,10 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelN
 		logModel = "gpt-4-gizmo-*"
 		logContent += fmt.Sprintf("，模型 %s", modelName)
 	}
+	if strings.HasPrefix(logModel, "gpt-4o-gizmo") {
+		logModel = "gpt-4o-gizmo-*"
+		logContent += fmt.Sprintf("，模型 %s", modelName)
+	}
 	if extraContent != "" {
 		logContent += ", " + extraContent
 	}

relay/relay_adaptor.go

@@ -16,8 +16,10 @@ import (
 	"one-api/relay/channel/openai"
 	"one-api/relay/channel/palm"
 	"one-api/relay/channel/perplexity"
+	"one-api/relay/channel/siliconflow"
 	"one-api/relay/channel/task/suno"
 	"one-api/relay/channel/tencent"
+	"one-api/relay/channel/vertex"
 	"one-api/relay/channel/xunfei"
 	"one-api/relay/channel/zhipu"
 	"one-api/relay/channel/zhipu_4v"
@@ -62,6 +64,10 @@ func GetAdaptor(apiType int) channel.Adaptor {
 		return &jina.Adaptor{}
 	case constant.APITypeCloudflare:
 		return &cloudflare.Adaptor{}
+	case constant.APITypeSiliconFlow:
+		return &siliconflow.Adaptor{}
+	case constant.APITypeVertexAi:
+		return &vertex.Adaptor{}
 	}
 	return nil
 }

relay/relay_rerank.go

@@ -38,6 +38,23 @@ func RerankHelper(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 	if len(rerankRequest.Documents) == 0 {
 		return service.OpenAIErrorWrapperLocal(fmt.Errorf("documents is empty"), "invalid_documents", http.StatusBadRequest)
 	}
+
+	// map model name
+	modelMapping := c.GetString("model_mapping")
+	//isModelMapped := false
+	if modelMapping != "" && modelMapping != "{}" {
+		modelMap := make(map[string]string)
+		err := json.Unmarshal([]byte(modelMapping), &modelMap)
+		if err != nil {
+			return service.OpenAIErrorWrapperLocal(err, "unmarshal_model_mapping_failed", http.StatusInternalServerError)
+		}
+		if modelMap[rerankRequest.Model] != "" {
+			rerankRequest.Model = modelMap[rerankRequest.Model]
+			// set upstream model name
+			//isModelMapped = true
+		}
+	}
+
 	relayInfo.UpstreamModelName = rerankRequest.Model
 	modelPrice, success := common.GetModelPrice(rerankRequest.Model, false)
 	groupRatio := common.GetGroupRatio(relayInfo.Group)

router/relay-router.go

@@ -79,5 +79,6 @@ func registerMjRouterGroup(relayMjRouter *gin.RouterGroup) {
 		relayMjRouter.GET("/task/:id/image-seed", controller.RelayMidjourney)
 		relayMjRouter.POST("/task/list-by-condition", controller.RelayMidjourney)
 		relayMjRouter.POST("/insight-face/swap", controller.RelayMidjourney)
+		relayMjRouter.POST("/submit/upload-discord-images", controller.RelayMidjourney)
 	}
 }

service/channel.go

@@ -54,6 +54,8 @@ func ShouldDisableChannel(channelType int, err *relaymodel.OpenAIErrorWithStatus
 	switch err.Error.Type {
 	case "insufficient_quota":
 		return true
+	case "insufficient_user_quota":
+		return true
 	// https://docs.anthropic.com/claude/reference/errors
 	case "authentication_error":
 		return true

service/error.go

@@ -28,13 +28,11 @@ func MidjourneyErrorWithStatusCodeWrapper(code int, desc string, statusCode int)
 // OpenAIErrorWrapper wraps an error into an OpenAIErrorWithStatusCode
 func OpenAIErrorWrapper(err error, code string, statusCode int) *dto.OpenAIErrorWithStatusCode {
 	text := err.Error()
-	// 定义一个正则表达式匹配URL
-	if strings.Contains(text, "Post") || strings.Contains(text, "dial") {
+	lowerText := strings.ToLower(text)
+	if strings.Contains(lowerText, "post") || strings.Contains(lowerText, "dial") || strings.Contains(lowerText, "http") {
 		common.SysLog(fmt.Sprintf("error: %s", text))
 		text = "请求上游地址失败"
 	}
-	//避免暴露内部错误
-
 	openAIError := dto.OpenAIError{
 		Message: text,
 		Type:    "new_api_error",
@@ -113,14 +111,12 @@ func TaskErrorWrapperLocal(err error, code string, statusCode int) *dto.TaskErro
 
 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") {
+	lowerText := strings.ToLower(text)
+	if strings.Contains(lowerText, "post") || strings.Contains(lowerText, "dial") || strings.Contains(lowerText, "http") {
 		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,

service/midjourney.go

@@ -49,6 +49,8 @@ func GetMjRequestModel(relayMode int, midjRequest *dto.MidjourneyRequest) (strin
 			action = constant.MjActionModal
 		case relayconstant.RelayModeSwapFace:
 			action = constant.MjActionSwapFace
+		case relayconstant.RelayModeMidjourneyUpload:
+			action = constant.MjActionUpload
 		case relayconstant.RelayModeMidjourneySimpleChange:
 			params := ConvertSimpleChangeParams(midjRequest.Content)
 			if params == nil {
@@ -220,7 +222,7 @@ func DoMidjourneyHttpRequest(c *gin.Context, timeout time.Duration, fullRequestU
 		return MidjourneyErrorWithStatusCodeWrapper(constant.MjErrorUnknown, "close_request_body_failed", statusCode), nullBytes, err
 	}
 	var midjResponse dto.MidjourneyResponse
-
+	var midjourneyUploadsResponse dto.MidjourneyUploadResponse
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
 		return MidjourneyErrorWithStatusCodeWrapper(constant.MjErrorUnknown, "read_response_body_failed", statusCode), nullBytes, err
@@ -230,13 +232,16 @@ func DoMidjourneyHttpRequest(c *gin.Context, timeout time.Duration, fullRequestU
 		return MidjourneyErrorWithStatusCodeWrapper(constant.MjErrorUnknown, "close_response_body_failed", statusCode), responseBody, err
 	}
 	respStr := string(responseBody)
-	log.Printf("responseBody: %s", respStr)
+	log.Printf("respStr: %s", respStr)
 	if respStr == "" {
 		return MidjourneyErrorWithStatusCodeWrapper(constant.MjErrorUnknown, "empty_response_body", statusCode), responseBody, nil
 	} else {
 		err = json.Unmarshal(responseBody, &midjResponse)
 		if err != nil {
-			return MidjourneyErrorWithStatusCodeWrapper(constant.MjErrorUnknown, "unmarshal_response_body_failed", statusCode), responseBody, err
+			err2 := json.Unmarshal(responseBody, &midjourneyUploadsResponse)
+			if err2 != nil {
+				return MidjourneyErrorWithStatusCodeWrapper(constant.MjErrorUnknown, "unmarshal_response_body_failed", statusCode), responseBody, err
+			}
 		}
 	}
 	//log.Printf("midjResponse: %v", midjResponse)

service/token_counter.go

@@ -52,7 +52,7 @@ func InitTokenEncoders() {
 }
 
 func getModelDefaultTokenEncoder(model string) *tiktoken.Tiktoken {
-	if strings.HasPrefix(model, "gpt-4o") {
+	if strings.HasPrefix(model, "gpt-4o") || strings.HasPrefix(model, "chatgpt-4o") {
 		return cl200kTokenEncoder
 	}
 	return defaultTokenEncoder

web/package.json

@@ -50,7 +50,7 @@
     ]
   },
   "devDependencies": {
-    "@so1ve/prettier-config": "^2.0.0",
+    "@so1ve/prettier-config": "^3.1.0",
     "@vitejs/plugin-react": "^4.2.1",
     "prettier": "^3.0.0",
     "typescript": "4.4.2",

web/pnpm-lock.yaml

@@ -13,10 +13,10 @@ importers:
         version: 2.53.2(react@18.2.0)
       '@douyinfe/semi-ui':
         specifier: ^2.55.3
-        version: 2.55.3(react-dom@18.2.0)(react@18.2.0)
+        version: 2.55.3(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
       '@visactor/react-vchart':
         specifier: ~1.8.8
-        version: 1.8.11(react-dom@18.2.0)(react@18.2.0)
+        version: 1.8.11(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
       '@visactor/vchart':
         specifier: ~1.8.8
         version: 1.8.11
@@ -49,26 +49,26 @@ importers:
         version: 1.0.4
       react-router-dom:
         specifier: ^6.3.0
-        version: 6.22.2(react-dom@18.2.0)(react@18.2.0)
+        version: 6.22.2(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
       react-telegram-login:
         specifier: ^1.1.2
         version: 1.1.2(react@18.2.0)
       react-toastify:
         specifier: ^9.0.8
-        version: 9.1.3(react-dom@18.2.0)(react@18.2.0)
+        version: 9.1.3(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
       react-turnstile:
         specifier: ^1.0.5
-        version: 1.1.3(react-dom@18.2.0)(react@18.2.0)
+        version: 1.1.3(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
       semantic-ui-offline:
         specifier: ^2.5.0
         version: 2.5.0
       semantic-ui-react:
         specifier: ^2.1.3
-        version: 2.1.5(react-dom@18.2.0)(react@18.2.0)
+        version: 2.1.5(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
     devDependencies:
       '@so1ve/prettier-config':
-        specifier: ^2.0.0
-        version: 2.0.0(prettier@3.2.5)
+        specifier: ^3.1.0
+        version: 3.1.0(prettier@3.2.5)
       '@vitejs/plugin-react':
         specifier: ^4.2.1
         version: 4.2.1(vite@5.2.5)
@@ -88,8 +88,8 @@ packages:
     resolution: {integrity: sha512-30iZtAPgz+LTIYoeivqYo853f02jBYSd5uGnGpkFV0M3xOt9aN73erkgYAmZU43x4VfqcnLxW9Kpg3R5LC4YYw==}
     engines: {node: '>=6.0.0'}
 
-  '@astrojs/compiler@1.8.2':
-    resolution: {integrity: sha512-o/ObKgtMzl8SlpIdzaxFnt7SATKPxu4oIP/1NL+HDJRzxfJcAkOTAb/ZKMRyULbz4q+1t2/DAebs2Z1QairkZw==}
+  '@astrojs/compiler@2.10.2':
+    resolution: {integrity: sha512-bvH+v8AirwpRWCkYJEyWYdc5Cs/BjG2ZTxIJzttHilXgfKJAdW2496KsUQKzf5j2tOHtaHXKKn9hb9WZiBGpEg==}
 
   '@babel/code-frame@7.23.5':
     resolution: {integrity: sha512-CgH3s1a96LipHCmSUmYFPwY7MNx8C3avkq7i4Wl3cfa662ldtUe4VM1TPXX70pfmrlWTb6jLqTYrZyT2ZTJBgA==}
@@ -578,13 +578,13 @@ packages:
       react: ^16.0.0 || ^17.0.0 || ^18.0.0
       react-dom: ^16.0.0 || ^17.0.0 || ^18.0.0
 
-  '@so1ve/prettier-config@2.0.0':
-    resolution: {integrity: sha512-s6qsH5Rf4Bl+J0LU9rKmSWe/rYRdsYw0ELyXhDDDqEaTWtah4NpHKJuVWARuKqj0TWLBeWmyWUoIH/Bkp/DHaw==}
+  '@so1ve/prettier-config@3.1.0':
+    resolution: {integrity: sha512-9GJ1yXKBC4DzqCTTaZoBf8zw7WWkVuXcccZt1Aqk4lj6ab/GiNUnjPGajUVYLjaqAEOKqM7jUSUfTjk2JTjCAg==}
     peerDependencies:
       prettier: ^3.0.0
 
-  '@so1ve/prettier-plugin-toml@2.0.0':
-    resolution: {integrity: sha512-GvuFdTqhs3qxbhKTiCXWMXITmNLSdndUp7ql1yJbzzWaGqAdb3UH+R+0ZhtAEctBSx90MWAWW3kkW/Iba02tCg==}
+  '@so1ve/prettier-plugin-toml@3.1.0':
+    resolution: {integrity: sha512-8WZAGjAVNIJlkfWL6wHKxlUuEBY45fdd5qY5bR/Z6r/txgzKXk/r9qi1DTwc17gi/WcNuRrcRugecRT+mWbIYg==}
     peerDependencies:
       prettier: ^3.0.0
 
@@ -1127,12 +1127,12 @@ packages:
     resolution: {integrity: sha512-WxtodH/wWavfw3MR7yK/GrS4pASEQ+iSTkdtSxPJWvqzG55ir5nvbLt9rw5AOiEcqqPCRM92WCtR1rk3TG3JSQ==}
     hasBin: true
 
-  prettier-plugin-astro@0.13.0:
-    resolution: {integrity: sha512-5HrJNnPmZqTUNoA97zn4gNQv9BgVhv+et03314WpQ9H9N8m2L9OSV798olwmG2YLXPl1iSstlJCR1zB3x5xG4g==}
+  prettier-plugin-astro@0.14.1:
+    resolution: {integrity: sha512-RiBETaaP9veVstE4vUwSIcdATj6dKmXljouXc/DDNwBSPTp8FRkLGDSGFClKsAFeeg+13SB0Z1JZvbD76bigJw==}
     engines: {node: ^14.15.0 || >=16.0.0}
 
-  prettier-plugin-curly-and-jsdoc@2.0.0:
-    resolution: {integrity: sha512-uSjWOWmX8+yrCrfhJSI58ODqtX7lXx07M8JYeOC1hfRv+vCttfiDlZoM27mNChGitJNKI+pCBvMMBYh8JiV0HQ==}
+  prettier-plugin-curly-and-jsdoc@3.1.0:
+    resolution: {integrity: sha512-4QMOHnLlkP2jTRWS0MFH6j+cuOiXLvXOqCLKbtwwVd8PPyq8NenW5AAwfwqiTNHBQG/DmzViPphRrwgN0XkUVQ==}
     peerDependencies:
       prettier: ^3.0.0
 
@@ -1442,7 +1442,7 @@ snapshots:
       '@jridgewell/gen-mapping': 0.3.5
       '@jridgewell/trace-mapping': 0.3.24
 
-  '@astrojs/compiler@1.8.2': {}
+  '@astrojs/compiler@2.10.2': {}
 
   '@babel/code-frame@7.23.5':
     dependencies:
@@ -1590,7 +1590,7 @@ snapshots:
       react: 18.2.0
       tslib: 2.6.2
 
-  '@dnd-kit/core@6.1.0(react-dom@18.2.0)(react@18.2.0)':
+  '@dnd-kit/core@6.1.0(react-dom@18.2.0(react@18.2.0))(react@18.2.0)':
     dependencies:
       '@dnd-kit/accessibility': 3.1.0(react@18.2.0)
       '@dnd-kit/utilities': 3.2.2(react@18.2.0)
@@ -1598,9 +1598,9 @@ snapshots:
       react-dom: 18.2.0(react@18.2.0)
       tslib: 2.6.2
 
-  '@dnd-kit/sortable@7.0.2(@dnd-kit/core@6.1.0)(react@18.2.0)':
+  '@dnd-kit/sortable@7.0.2(@dnd-kit/core@6.1.0(react-dom@18.2.0(react@18.2.0))(react@18.2.0))(react@18.2.0)':
     dependencies:
-      '@dnd-kit/core': 6.1.0(react-dom@18.2.0)(react@18.2.0)
+      '@dnd-kit/core': 6.1.0(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
       '@dnd-kit/utilities': 3.2.2(react@18.2.0)
       react: 18.2.0
       tslib: 2.6.2
@@ -1652,10 +1652,10 @@ snapshots:
     dependencies:
       glob: 7.2.3
 
-  '@douyinfe/semi-ui@2.55.3(react-dom@18.2.0)(react@18.2.0)':
+  '@douyinfe/semi-ui@2.55.3(react-dom@18.2.0(react@18.2.0))(react@18.2.0)':
     dependencies:
-      '@dnd-kit/core': 6.1.0(react-dom@18.2.0)(react@18.2.0)
-      '@dnd-kit/sortable': 7.0.2(@dnd-kit/core@6.1.0)(react@18.2.0)
+      '@dnd-kit/core': 6.1.0(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
+      '@dnd-kit/sortable': 7.0.2(@dnd-kit/core@6.1.0(react-dom@18.2.0(react@18.2.0))(react@18.2.0))(react@18.2.0)
       '@dnd-kit/utilities': 3.2.2(react@18.2.0)
       '@douyinfe/semi-animation': 2.55.3
       '@douyinfe/semi-animation-react': 2.55.3
@@ -1673,8 +1673,8 @@ snapshots:
       prop-types: 15.8.1
       react: 18.2.0
       react-dom: 18.2.0(react@18.2.0)
-      react-resizable: 3.0.5(react-dom@18.2.0)(react@18.2.0)
-      react-window: 1.8.10(react-dom@18.2.0)(react@18.2.0)
+      react-resizable: 3.0.5(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
+      react-window: 1.8.10(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
       scroll-into-view-if-needed: 2.2.31
       utility-types: 3.11.0
 
@@ -1747,13 +1747,13 @@ snapshots:
   '@esbuild/win32-x64@0.20.2':
     optional: true
 
-  '@fluentui/react-component-event-listener@0.63.1(react-dom@18.2.0)(react@18.2.0)':
+  '@fluentui/react-component-event-listener@0.63.1(react-dom@18.2.0(react@18.2.0))(react@18.2.0)':
     dependencies:
       '@babel/runtime': 7.24.0
       react: 18.2.0
       react-dom: 18.2.0(react@18.2.0)
 
-  '@fluentui/react-component-ref@0.63.1(react-dom@18.2.0)(react@18.2.0)':
+  '@fluentui/react-component-ref@0.63.1(react-dom@18.2.0(react@18.2.0))(react@18.2.0)':
     dependencies:
       '@babel/runtime': 7.24.0
       react: 18.2.0
@@ -1871,22 +1871,22 @@ snapshots:
   '@rollup/rollup-win32-x64-msvc@4.13.0':
     optional: true
 
-  '@semantic-ui-react/event-stack@3.1.3(react-dom@18.2.0)(react@18.2.0)':
+  '@semantic-ui-react/event-stack@3.1.3(react-dom@18.2.0(react@18.2.0))(react@18.2.0)':
     dependencies:
       exenv: 1.2.2
       prop-types: 15.8.1
       react: 18.2.0
       react-dom: 18.2.0(react@18.2.0)
 
-  '@so1ve/prettier-config@2.0.0(prettier@3.2.5)':
+  '@so1ve/prettier-config@3.1.0(prettier@3.2.5)':
     dependencies:
-      '@so1ve/prettier-plugin-toml': 2.0.0(prettier@3.2.5)
+      '@so1ve/prettier-plugin-toml': 3.1.0(prettier@3.2.5)
       prettier: 3.2.5
-      prettier-plugin-astro: 0.13.0
-      prettier-plugin-curly-and-jsdoc: 2.0.0(prettier@3.2.5)
+      prettier-plugin-astro: 0.14.1
+      prettier-plugin-curly-and-jsdoc: 3.1.0(prettier@3.2.5)
       prettier-plugin-pkgsort: 0.2.1(prettier@3.2.5)
 
-  '@so1ve/prettier-plugin-toml@2.0.0(prettier@3.2.5)':
+  '@so1ve/prettier-plugin-toml@3.1.0(prettier@3.2.5)':
     dependencies:
       prettier: 3.2.5
 
@@ -1951,7 +1951,7 @@ snapshots:
 
   '@types/parse-json@4.0.2': {}
 
-  '@visactor/react-vchart@1.8.11(react-dom@18.2.0)(react@18.2.0)':
+  '@visactor/react-vchart@1.8.11(react-dom@18.2.0(react@18.2.0))(react@18.2.0)':
     dependencies:
       '@visactor/vchart': 1.8.11
       '@visactor/vgrammar-core': 0.10.11
@@ -2528,13 +2528,13 @@ snapshots:
       sort-object-keys: 1.1.3
       sort-order: 1.1.2
 
-  prettier-plugin-astro@0.13.0:
+  prettier-plugin-astro@0.14.1:
     dependencies:
-      '@astrojs/compiler': 1.8.2
+      '@astrojs/compiler': 2.10.2
       prettier: 3.2.5
       sass-formatter: 0.7.9
 
-  prettier-plugin-curly-and-jsdoc@2.0.0(prettier@3.2.5):
+  prettier-plugin-curly-and-jsdoc@3.1.0(prettier@3.2.5):
     dependencies:
       prettier: 3.2.5
 
@@ -2559,7 +2559,7 @@ snapshots:
       react: 18.2.0
       scheduler: 0.23.0
 
-  react-draggable@4.4.6(react-dom@18.2.0)(react@18.2.0):
+  react-draggable@4.4.6(react-dom@18.2.0(react@18.2.0))(react@18.2.0):
     dependencies:
       clsx: 1.2.1
       prop-types: 15.8.1
@@ -2581,7 +2581,7 @@ snapshots:
 
   react-is@18.2.0: {}
 
-  react-popper@2.3.0(@popperjs/core@2.11.8)(react-dom@18.2.0)(react@18.2.0):
+  react-popper@2.3.0(@popperjs/core@2.11.8)(react-dom@18.2.0(react@18.2.0))(react@18.2.0):
     dependencies:
       '@popperjs/core': 2.11.8
       react: 18.2.0
@@ -2591,15 +2591,15 @@ snapshots:
 
   react-refresh@0.14.0: {}
 
-  react-resizable@3.0.5(react-dom@18.2.0)(react@18.2.0):
+  react-resizable@3.0.5(react-dom@18.2.0(react@18.2.0))(react@18.2.0):
     dependencies:
       prop-types: 15.8.1
       react: 18.2.0
-      react-draggable: 4.4.6(react-dom@18.2.0)(react@18.2.0)
+      react-draggable: 4.4.6(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
     transitivePeerDependencies:
       - react-dom
 
-  react-router-dom@6.22.2(react-dom@18.2.0)(react@18.2.0):
+  react-router-dom@6.22.2(react-dom@18.2.0(react@18.2.0))(react@18.2.0):
     dependencies:
       '@remix-run/router': 1.15.2
       react: 18.2.0
@@ -2615,18 +2615,18 @@ snapshots:
     dependencies:
       react: 18.2.0
 
-  react-toastify@9.1.3(react-dom@18.2.0)(react@18.2.0):
+  react-toastify@9.1.3(react-dom@18.2.0(react@18.2.0))(react@18.2.0):
     dependencies:
       clsx: 1.2.1
       react: 18.2.0
       react-dom: 18.2.0(react@18.2.0)
 
-  react-turnstile@1.1.3(react-dom@18.2.0)(react@18.2.0):
+  react-turnstile@1.1.3(react-dom@18.2.0(react@18.2.0))(react@18.2.0):
     dependencies:
       react: 18.2.0
       react-dom: 18.2.0(react@18.2.0)
 
-  react-window@1.8.10(react-dom@18.2.0)(react@18.2.0):
+  react-window@1.8.10(react-dom@18.2.0(react@18.2.0))(react@18.2.0):
     dependencies:
       '@babel/runtime': 7.24.0
       memoize-one: 5.2.1
@@ -2708,13 +2708,13 @@ snapshots:
       fs-extra: 4.0.3
       jquery: 3.7.1
 
-  semantic-ui-react@2.1.5(react-dom@18.2.0)(react@18.2.0):
+  semantic-ui-react@2.1.5(react-dom@18.2.0(react@18.2.0))(react@18.2.0):
     dependencies:
       '@babel/runtime': 7.24.0
-      '@fluentui/react-component-event-listener': 0.63.1(react-dom@18.2.0)(react@18.2.0)
-      '@fluentui/react-component-ref': 0.63.1(react-dom@18.2.0)(react@18.2.0)
+      '@fluentui/react-component-event-listener': 0.63.1(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
+      '@fluentui/react-component-ref': 0.63.1(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
       '@popperjs/core': 2.11.8
-      '@semantic-ui-react/event-stack': 3.1.3(react-dom@18.2.0)(react@18.2.0)
+      '@semantic-ui-react/event-stack': 3.1.3(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
       clsx: 1.2.1
       keyboard-key: 1.1.0
       lodash: 4.17.21
@@ -2723,7 +2723,7 @@ snapshots:
       react: 18.2.0
       react-dom: 18.2.0(react@18.2.0)
       react-is: 18.2.0
-      react-popper: 2.3.0(@popperjs/core@2.11.8)(react-dom@18.2.0)(react@18.2.0)
+      react-popper: 2.3.0(@popperjs/core@2.11.8)(react-dom@18.2.0(react@18.2.0))(react@18.2.0)
       shallowequal: 1.1.0
 
   semver@6.3.1: {}

web/src/components/ChannelsTable.js

@@ -745,7 +745,8 @@ const ChannelsTable = () => {
             <Form.Select
               field='group'
               label='分组'
-              optionList={groupOptions}
+              optionList={[{ label: '选择分组', value: null}, ...groupOptions]}
+              initValue={null}
               onChange={(v) => {
                 setSearchGroup(v);
                 searchChannels(searchKeyword, v, searchModel);

web/src/components/LogsTable.js

@@ -2,6 +2,7 @@ import React, { useEffect, useState } from 'react';
 import {
   API,
   copy,
+  getTodayStartTimestamp,
   isAdmin,
   showError,
   showSuccess,
@@ -29,7 +30,7 @@ import {
   stringToColor,
 } from '../helpers/render';
 import Paragraph from '@douyinfe/semi-ui/lib/es/typography/paragraph';
-import {getLogOther} from "../helpers/other.js";
+import { getLogOther } from '../helpers/other.js';
 
 const { Header } = Layout;
 
@@ -144,27 +145,27 @@ function renderUseTime(type) {
 
 function renderFirstUseTime(type) {
   let time = parseFloat(type) / 1000.0;
-  time = time.toFixed(1)
+  time = time.toFixed(1);
   if (time < 3) {
     return (
-        <Tag color='green' size='large'>
-          {' '}
-          {time} s{' '}
-        </Tag>
+      <Tag color='green' size='large'>
+        {' '}
+        {time} s{' '}
+      </Tag>
     );
   } else if (time < 10) {
     return (
-        <Tag color='orange' size='large'>
-          {' '}
-          {time} s{' '}
-        </Tag>
+      <Tag color='orange' size='large'>
+        {' '}
+        {time} s{' '}
+      </Tag>
     );
   } else {
     return (
-        <Tag color='red' size='large'>
-          {' '}
-          {time} s{' '}
-        </Tag>
+      <Tag color='red' size='large'>
+        {' '}
+        {time} s{' '}
+      </Tag>
     );
   }
 }
@@ -281,22 +282,22 @@ const LogsTable = () => {
         if (record.is_stream) {
           let other = getLogOther(record.other);
           return (
-              <div>
-                <Space>
-                  {renderUseTime(text)}
-                  {renderFirstUseTime(other.frt)}
-                  {renderIsStream(record.is_stream)}
-                </Space>
-              </div>
+            <div>
+              <Space>
+                {renderUseTime(text)}
+                {renderFirstUseTime(other.frt)}
+                {renderIsStream(record.is_stream)}
+              </Space>
+            </div>
           );
         } else {
           return (
-              <div>
-                <Space>
-                  {renderUseTime(text)}
-                  {renderIsStream(record.is_stream)}
-                </Space>
-              </div>
+            <div>
+              <Space>
+                {renderUseTime(text)}
+                {renderIsStream(record.is_stream)}
+              </Space>
+            </div>
           );
         }
       },
@@ -344,7 +345,7 @@ const LogsTable = () => {
         if (record.other !== '') {
           let other = JSON.parse(record.other);
           if (other === null) {
-            return <></>
+            return <></>;
           }
           if (other.admin_info !== undefined) {
             if (
@@ -414,17 +415,15 @@ const LogsTable = () => {
   const [activePage, setActivePage] = useState(1);
   const [logCount, setLogCount] = useState(ITEMS_PER_PAGE);
   const [pageSize, setPageSize] = useState(ITEMS_PER_PAGE);
-  const [searchKeyword, setSearchKeyword] = useState('');
-  const [searching, setSearching] = useState(false);
   const [logType, setLogType] = useState(0);
   const isAdminUser = isAdmin();
   let now = new Date();
-  // 初始化start_timestamp为前一天
+  // 初始化start_timestamp为今天0点
   const [inputs, setInputs] = useState({
     username: '',
     token_name: '',
     model_name: '',
-    start_timestamp: timestamp2string(now.getTime() / 1000 - 86400),
+    start_timestamp: timestamp2string(getTodayStartTimestamp()),
     end_timestamp: timestamp2string(now.getTime() / 1000 + 3600),
     channel: '',
   });
@@ -449,9 +448,9 @@ const LogsTable = () => {
   const getLogSelfStat = async () => {
     let localStartTimestamp = Date.parse(start_timestamp) / 1000;
     let localEndTimestamp = Date.parse(end_timestamp) / 1000;
-    let res = await API.get(
-      `/api/log/self/stat?type=${logType}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`,
-    );
+    let url = `/api/log/self/stat?type=${logType}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`;
+    url = encodeURI(url);
+    let res = await API.get(url);
     const { success, message, data } = res.data;
     if (success) {
       setStat(data);
@@ -463,9 +462,9 @@ const LogsTable = () => {
   const getLogStat = async () => {
     let localStartTimestamp = Date.parse(start_timestamp) / 1000;
     let localEndTimestamp = Date.parse(end_timestamp) / 1000;
-    let res = await API.get(
-      `/api/log/stat?type=${logType}&username=${username}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}&channel=${channel}`,
-    );
+    let url = `/api/log/stat?type=${logType}&username=${username}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}&channel=${channel}`;
+    url = encodeURI(url);
+    let res = await API.get(url);
     const { success, message, data } = res.data;
     if (success) {
       setStat(data);
@@ -475,6 +474,9 @@ const LogsTable = () => {
   };
 
   const handleEyeClick = async () => {
+    if (loadingStat) {
+      return;
+    }
     setLoadingStat(true);
     if (isAdminUser) {
       await getLogStat();
@@ -514,10 +516,7 @@ const LogsTable = () => {
       logs[i].timestamp2string = timestamp2string(logs[i].created_at);
       logs[i].key = '' + logs[i].id;
     }
-    // data.key = '' + data.id
     setLogs(logs);
-    setLogCount(logs.length + ITEMS_PER_PAGE);
-    // console.log(logCount);
   };
 
   const loadLogs = async (startIdx, pageSize, logType = 0) => {
@@ -531,40 +530,32 @@ const LogsTable = () => {
     } else {
       url = `/api/log/self/?p=${startIdx}&page_size=${pageSize}&type=${logType}&token_name=${token_name}&model_name=${model_name}&start_timestamp=${localStartTimestamp}&end_timestamp=${localEndTimestamp}`;
     }
+    url = encodeURI(url);
     const res = await API.get(url);
     const { success, message, data } = res.data;
     if (success) {
-      if (startIdx === 0) {
-        setLogsFormat(data);
-      } else {
-        let newLogs = [...logs];
-        newLogs.splice(startIdx * pageSize, data.length, ...data);
-        setLogsFormat(newLogs);
-      }
+      const newPageData = data.items;
+      setActivePage(data.page);
+      setPageSize(data.page_size);
+      setLogCount(data.total);
+
+      setLogsFormat(newPageData);
     } else {
       showError(message);
     }
     setLoading(false);
   };
 
-  const pageData = logs.slice(
-    (activePage - 1) * pageSize,
-    activePage * pageSize,
-  );
-
   const handlePageChange = (page) => {
     setActivePage(page);
-    if (page === Math.ceil(logs.length / pageSize) + 1) {
-      // In this case we have to load more data and then append them.
-      loadLogs(page - 1, pageSize, logType).then((r) => {});
-    }
+    loadLogs(page, pageSize, logType).then((r) => {});
   };
 
   const handlePageSizeChange = async (size) => {
     localStorage.setItem('page-size', size + '');
     setPageSize(size);
     setActivePage(1);
-    loadLogs(0, size)
+    loadLogs(activePage, size)
       .then()
       .catch((reason) => {
         showError(reason);
@@ -572,69 +563,47 @@ const LogsTable = () => {
   };
 
   const refresh = async () => {
-    // setLoading(true);
     setActivePage(1);
-    await loadLogs(0, pageSize, logType);
+    handleEyeClick();
+    await loadLogs(activePage, pageSize, logType);
   };
 
   const copyText = async (text) => {
     if (await copy(text)) {
       showSuccess('已复制：' + text);
     } else {
-      // setSearchKeyword(text);
       Modal.error({ title: '无法复制到剪贴板，请手动复制', content: text });
     }
   };
 
   useEffect(() => {
-    // console.log('default effect')
     const localPageSize =
       parseInt(localStorage.getItem('page-size')) || ITEMS_PER_PAGE;
     setPageSize(localPageSize);
-    loadLogs(0, localPageSize)
+    loadLogs(activePage, localPageSize)
       .then()
       .catch((reason) => {
         showError(reason);
       });
+    handleEyeClick();
   }, []);
 
-  const searchLogs = async () => {
-    if (searchKeyword === '') {
-      // if keyword is blank, load files instead.
-      await loadLogs(0, pageSize);
-      setActivePage(1);
-      return;
-    }
-    setSearching(true);
-    const res = await API.get(`/api/log/self/search?keyword=${searchKeyword}`);
-    const { success, message, data } = res.data;
-    if (success) {
-      setLogs(data);
-      setActivePage(1);
-    } else {
-      showError(message);
-    }
-    setSearching(false);
-  };
-
   return (
     <>
       <Layout>
         <Header>
           <Spin spinning={loadingStat}>
-            <h3>
-              使用明细（总消耗额度：
-              <span
-                onClick={handleEyeClick}
-                style={{
-                  cursor: 'pointer',
-                  color: 'gray',
-                }}
-              >
-                {showStat ? renderQuota(stat.quota) : '点击查看'}
-              </span>
-              ）
-            </h3>
+            <Space>
+              <Tag color='green' size='large' style={{ padding: 15 }}>
+                总消耗额度: {renderQuota(stat.quota)}
+              </Tag>
+              <Tag color='blue' size='large' style={{ padding: 15 }}>
+                RPM: {stat.rpm}
+              </Tag>
+              <Tag color='purple' size='large' style={{ padding: 15 }}>
+                TPM: {stat.tpm}
+              </Tag>
+            </Space>
           </Spin>
         </Header>
         <Form layout='horizontal' style={{ marginTop: 10 }}>
@@ -700,24 +669,24 @@ const LogsTable = () => {
                 />
               </>
             )}
-            <Form.Section>
-              <Button
-                label='查询'
-                type='primary'
-                htmlType='submit'
-                className='btn-margin-right'
-                onClick={refresh}
-                loading={loading}
-              >
-                查询
-              </Button>
-            </Form.Section>
+            <Button
+              label='查询'
+              type='primary'
+              htmlType='submit'
+              className='btn-margin-right'
+              onClick={refresh}
+              loading={loading}
+              style={{ marginTop: 24 }}
+            >
+              查询
+            </Button>
+            <Form.Section></Form.Section>
           </>
         </Form>
         <Table
           style={{ marginTop: 5 }}
           columns={columns}
-          dataSource={pageData}
+          dataSource={logs}
           pagination={{
             currentPage: activePage,
             pageSize: pageSize,
@@ -725,7 +694,7 @@ const LogsTable = () => {
             pageSizeOpts: [10, 20, 50, 100],
             showSizeChanger: true,
             onPageSizeChange: (size) => {
-              handlePageSizeChange(size).then();
+              handlePageSizeChange(size);
             },
             onPageChange: handlePageChange,
           }}

web/src/components/MjLogsTable.js

@@ -90,6 +90,12 @@ function renderType(type) {
           图混合
         </Tag>
       );
+    case 'UPLOAD':
+      return (
+          <Tag color='blue' size='large'>
+            上传文件
+          </Tag>
+      );
     case 'SHORTEN':
       return (
         <Tag color='pink' size='large'>
@@ -239,7 +245,7 @@ const renderTimestamp = (timestampInSeconds) => {
 // 修改renderDuration函数以包含颜色逻辑
 function renderDuration(submit_time, finishTime) {
   // 确保startTime和finishTime都是有效的时间戳
-  if (!submit_time || !finishTime) return 'N/A'; 
+  if (!submit_time || !finishTime) return 'N/A';
 
   // 将时间戳转换为Date对象
   const start = new Date(submit_time);

web/src/components/TokensTable.js

@@ -225,14 +225,14 @@ const TokensTable = () => {
                     onOpenLink('next-mj', record.key);
                   },
                 },
-                {
-                  node: 'item',
-                  key: 'lobe',
-                  name: 'Lobe Chat',
-                  onClick: () => {
-                    onOpenLink('lobe', record.key);
-                  },
-                },
+                // {
+                //   node: 'item',
+                //   key: 'lobe',
+                //   name: 'Lobe Chat',
+                //   onClick: () => {
+                //     onOpenLink('lobe', record.key);
+                //   },
+                // },
                 {
                   node: 'item',
                   key: 'ama',
@@ -425,7 +425,7 @@ const TokensTable = () => {
         url = `opencat://team/join?domain=${encodedServerAddress}&token=sk-${key}`;
         break;
       case 'lobe':
-        url = `https://chat-preview.lobehub.com/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${encodedServerAddress}"}}}`;
+        url = `https://chat-preview.lobehub.com/?settings={"keyVaults":{"openai":{"apiKey":"sk-${key}","baseURL":"${encodedServerAddress}/v1"}}}`;
         break;
       case 'next-mj':
         url =

web/src/constants/channel.constants.js

@@ -5,21 +5,21 @@ export const CHANNEL_OPTIONS = [
     text: 'Midjourney Proxy',
     value: 2,
     color: 'light-blue',
-    label: 'Midjourney Proxy',
+    label: 'Midjourney Proxy'
   },
   {
     key: 5,
     text: 'Midjourney Proxy Plus',
     value: 5,
     color: 'blue',
-    label: 'Midjourney Proxy Plus',
+    label: 'Midjourney Proxy Plus'
   },
   {
     key: 36,
     text: 'Suno API',
     value: 36,
     color: 'purple',
-    label: 'Suno API',
+    label: 'Suno API'
   },
   { key: 4, text: 'Ollama', value: 4, color: 'grey', label: 'Ollama' },
   {
@@ -27,77 +27,78 @@ export const CHANNEL_OPTIONS = [
     text: 'Anthropic Claude',
     value: 14,
     color: 'indigo',
-    label: 'Anthropic Claude',
+    label: 'Anthropic Claude'
   },
   {
     key: 33,
     text: 'AWS Claude',
     value: 33,
     color: 'indigo',
-    label: 'AWS Claude',
+    label: 'AWS Claude'
   },
+  { key: 41, text: 'Vertex AI', value: 41, color: 'blue', label: 'Vertex AI' },
   {
     key: 3,
     text: 'Azure OpenAI',
     value: 3,
     color: 'teal',
-    label: 'Azure OpenAI',
+    label: 'Azure OpenAI'
   },
   {
     key: 24,
     text: 'Google Gemini',
     value: 24,
     color: 'orange',
-    label: 'Google Gemini',
+    label: 'Google Gemini'
   },
   {
     key: 34,
     text: 'Cohere',
     value: 34,
     color: 'purple',
-    label: 'Cohere',
+    label: 'Cohere'
   },
   {
     key: 15,
     text: '百度文心千帆',
     value: 15,
     color: 'blue',
-    label: '百度文心千帆',
+    label: '百度文心千帆'
   },
   {
     key: 17,
     text: '阿里通义千问',
     value: 17,
     color: 'orange',
-    label: '阿里通义千问',
+    label: '阿里通义千问'
   },
   {
     key: 18,
     text: '讯飞星火认知',
     value: 18,
     color: 'blue',
-    label: '讯飞星火认知',
+    label: '讯飞星火认知'
   },
   {
     key: 16,
     text: '智谱 ChatGLM',
     value: 16,
     color: 'violet',
-    label: '智谱 ChatGLM',
+    label: '智谱 ChatGLM'
   },
   {
     key: 26,
     text: '智谱 GLM-4V',
     value: 26,
     color: 'purple',
-    label: '智谱 GLM-4V',
+    label: '智谱 GLM-4V'
   },
   {
     key: 11,
     text: 'Google PaLM2',
     value: 11,
     color: 'orange',
-    label: 'Google PaLM2',
+    label: 'Google PaLM2'
   },
   { key: 39, text: 'Cloudflare', value: 39, color: 'grey', label: 'Cloudflare' },
   { key: 25, text: 'Moonshot', value: 25, color: 'green', label: 'Moonshot' },
@@ -107,19 +108,20 @@ export const CHANNEL_OPTIONS = [
   { key: 35, text: 'MiniMax', value: 35, color: 'green', label: 'MiniMax' },
   { key: 37, text: 'Dify', value: 37, color: 'teal', label: 'Dify' },
   { key: 38, text: 'Jina', value: 38, color: 'blue', label: 'Jina' },
+  { key: 40, text: 'SiliconCloud', value: 40, color: 'purple', label: 'SiliconCloud' },
   { key: 8, text: '自定义渠道', value: 8, color: 'pink', label: '自定义渠道' },
   {
     key: 22,
     text: '知识库：FastGPT',
     value: 22,
     color: 'blue',
-    label: '知识库：FastGPT',
+    label: '知识库：FastGPT'
   },
   {
     key: 21,
     text: '知识库：AI Proxy',
     value: 21,
     color: 'purple',
-    label: '知识库：AI Proxy',
-  },
+    label: '知识库：AI Proxy'
+  }
 ];

web/src/helpers/utils.js

@@ -140,6 +140,12 @@ export function removeTrailingSlash(url) {
   }
 }
 
+export function getTodayStartTimestamp() {
+  var now = new Date();
+  now.setHours(0, 0, 0, 0);
+  return Math.floor(now.getTime() / 1000);
+}
+
 export function timestamp2string(timestamp) {
   let date = new Date(timestamp * 1000);
   let year = date.getFullYear().toString();

web/src/pages/Channel/EditChannel.js

@@ -37,6 +37,11 @@ const STATUS_CODE_MAPPING_EXAMPLE = {
   400: '500',
 };
 
+const REGION_EXAMPLE = {
+  "default": "us-central1",
+  "claude-3-5-sonnet-20240620": "europe-west1"
+}
+
 const fetchButtonTips = "1. 新建渠道时，请求通过当前浏览器发出；2. 编辑已有渠道，请求通过后端服务器发出"
 
 function type2secretPrompt(type) {
@@ -588,6 +593,44 @@ const EditChannel = (props) => {
               />
             </>
           )}
+          {inputs.type === 41 && (
+            <>
+              <div style={{ marginTop: 10 }}>
+                <Typography.Text strong>部署地区：</Typography.Text>
+              </div>
+              <TextArea
+                name='other'
+                placeholder={
+                  '请输入部署地区，例如：us-central1\n支持使用模型映射格式\n' +
+                  '{\n' +
+                  '    "default": "us-central1",\n' +
+                  '    "claude-3-5-sonnet-20240620": "europe-west1"\n' +
+                  '}'
+                }
+                autosize={{ minRows: 2 }}
+                onChange={(value) => {
+                  handleInputChange('other', value);
+                }}
+                value={inputs.other}
+                autoComplete='new-password'
+              />
+              <Typography.Text
+                style={{
+                  color: 'rgba(var(--semi-blue-5), 1)',
+                  userSelect: 'none',
+                  cursor: 'pointer',
+                }}
+                onClick={() => {
+                  handleInputChange(
+                    'other',
+                    JSON.stringify(REGION_EXAMPLE, null, 2),
+                  );
+                }}
+              >
+                填入模板
+              </Typography.Text>
+            </>
+          )}
           {inputs.type === 21 && (
             <>
               <div style={{ marginTop: 10 }}>
@@ -734,17 +777,47 @@ const EditChannel = (props) => {
               autoComplete='new-password'
             />
           ) : (
-            <Input
-              label='密钥'
-              name='key'
-              required
-              placeholder={type2secretPrompt(inputs.type)}
-              onChange={(value) => {
-                handleInputChange('key', value);
-              }}
-              value={inputs.key}
-              autoComplete='new-password'
-            />
+            <>
+              {inputs.type === 41 ? (
+                <TextArea
+                  label='鉴权json'
+                  name='key'
+                  required
+                  placeholder={'{\n' +
+                    '  "type": "service_account",\n' +
+                    '  "project_id": "abc-bcd-123-456",\n' +
+                    '  "private_key_id": "123xxxxx456",\n' +
+                    '  "private_key": "-----BEGIN PRIVATE KEY-----xxxx\n' +
+                    '  "client_email": "xxx@developer.gserviceaccount.com",\n' +
+                    '  "client_id": "111222333",\n' +
+                    '  "auth_uri": "https://accounts.google.com/o/oauth2/auth",\n' +
+                    '  "token_uri": "https://oauth2.googleapis.com/token",\n' +
+                    '  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",\n' +
+                    '  "client_x509_cert_url": "https://xxxxx.gserviceaccount.com",\n' +
+                    '  "universe_domain": "googleapis.com"\n' +
+                    '}'}
+                  onChange={(value) => {
+                    handleInputChange('key', value);
+                  }}
+                  autosize={{ minRows: 10 }}
+                  value={inputs.key}
+                  autoComplete='new-password'
+                />
+              ) : (
+                <Input
+                  label='密钥'
+                  name='key'
+                  required
+                  placeholder={type2secretPrompt(inputs.type)}
+                  onChange={(value) => {
+                    handleInputChange('key', value);
+                  }}
+                  value={inputs.key}
+                  autoComplete='new-password'
+                />
+              )
+              }
+              </>
           )}
           {inputs.type === 1 && (
             <>