feat: enable error logging configuration in docker-compose and application

constant/env.go

@@ -16,6 +16,7 @@ var GeminiVisionMaxImageNum int
 var NotifyLimitCount int
 var NotificationLimitDurationMinute int
 var GenerateDefaultToken bool
+var ErrorLogEnabled bool
 
 //var GeminiModelMap = map[string]string{
 //	"gemini-1.0-pro": "v1",
@@ -36,6 +37,8 @@ func InitEnv() {
 	NotificationLimitDurationMinute = common.GetEnvOrDefault("NOTIFICATION_LIMIT_DURATION_MINUTE", 10)
 	// GenerateDefaultToken 是否生成初始令牌，默认关闭。
 	GenerateDefaultToken = common.GetEnvOrDefaultBool("GENERATE_DEFAULT_TOKEN", false)
+	// 是否启用错误日志
+	ErrorLogEnabled = common.GetEnvOrDefaultBool("ERROR_LOG_ENABLED", false)
 
 	//modelVersionMapStr := strings.TrimSpace(os.Getenv("GEMINI_MODEL_MAP"))
 	//if modelVersionMapStr == "" {

controller/relay.go

@@ -10,6 +10,7 @@ import (
 	"log"
 	"net/http"
 	"one-api/common"
+	constant2 "one-api/constant"
 	"one-api/dto"
 	"one-api/middleware"
 	"one-api/model"
@@ -40,7 +41,7 @@ func relayHandler(c *gin.Context, relayMode int) *dto.OpenAIErrorWithStatusCode
 		err = relay.TextHelper(c)
 	}
 
-	if err != nil {
+	if constant2.ErrorLogEnabled && err != nil {
 		// 保存错误日志到mysql中
 		userId := c.GetInt("id")
 		tokenName := c.GetString("token_name")

docker-compose.yml

@@ -15,6 +15,7 @@ services:
       - SQL_DSN=root:123456@tcp(mysql:3306)/new-api  # Point to the mysql service
       - REDIS_CONN_STRING=redis://redis
       - TZ=Asia/Shanghai
+      - ERROR_LOG_ENABLED=true # 是否启用错误日志记录
     #      - TIKTOKEN_CACHE_DIR=./tiktoken_cache  # 如果需要使用tiktoken_cache，请取消注释
     #      - SESSION_SECRET=random_string  # 多机部署时设置，必须修改这个随机字符串！！！！！！！
     #      - NODE_TYPE=slave  # Uncomment for slave node in multi-node deployment

dto/openai_request.go

@@ -51,6 +51,7 @@ type GeneralOpenAIRequest struct {
 	Dimensions       int               `json:"dimensions,omitempty"`
 	Modalities       any               `json:"modalities,omitempty"`
 	Audio            any               `json:"audio,omitempty"`
+	EnableThinking   any               `json:"enable_thinking,omitempty"` // ali
 	ExtraBody        any               `json:"extra_body,omitempty"`
 }
 

model/cache.go

@@ -84,9 +84,11 @@ func CacheGetRandomSatisfiedChannel(group string, model string, retry int) (*Cha
 	if !common.MemoryCacheEnabled {
 		return GetRandomSatisfiedChannel(group, model, retry)
 	}
+	
 	channelSyncLock.RLock()
-	defer channelSyncLock.RUnlock()
 	channels := group2model2channels[group][model]
+	channelSyncLock.RUnlock()
+	
 	if len(channels) == 0 {
 		return nil, errors.New("channel not found")
 	}

relay/channel/ali/constants.go

@@ -1,7 +1,12 @@
 package ali
 
 var ModelList = []string{
-	"qwen-turbo", "qwen-plus", "qwen-max", "qwen-max-longcontext",
+	"qwen-turbo",
+	"qwen-plus",
+	"qwen-max",
+	"qwen-max-longcontext",
+	"qwq-32b",
+	"qwen3-235b-a22b",
 	"text-embedding-v1",
 }
 

relay/channel/gemini/relay-gemini.go

@@ -670,6 +670,7 @@ func GeminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycom
 			usage.PromptTokens = geminiResponse.UsageMetadata.PromptTokenCount
 			usage.CompletionTokens = geminiResponse.UsageMetadata.CandidatesTokenCount
 			usage.CompletionTokenDetails.ReasoningTokens = geminiResponse.UsageMetadata.ThoughtsTokenCount
+			usage.TotalTokens = geminiResponse.UsageMetadata.TotalTokenCount
 		}
 		err = helper.ObjectData(c, response)
 		if err != nil {
@@ -690,9 +691,8 @@ func GeminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycom
 		}
 	}
 
-	usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
 	usage.PromptTokensDetails.TextTokens = usage.PromptTokens
-	//usage.CompletionTokenDetails.TextTokens = usage.CompletionTokens
+	usage.CompletionTokens = usage.TotalTokens - usage.PromptTokens
 
 	if info.ShouldIncludeUsage {
 		response = helper.GenerateFinalUsageResponse(id, createAt, info.UpstreamModelName, *usage)
@@ -740,6 +740,7 @@ func GeminiChatHandler(c *gin.Context, resp *http.Response, info *relaycommon.Re
 	}
 
 	usage.CompletionTokenDetails.ReasoningTokens = geminiResponse.UsageMetadata.ThoughtsTokenCount
+	usage.CompletionTokens = usage.TotalTokens - usage.PromptTokens
 
 	fullTextResponse.Usage = usage
 	jsonResponse, err := json.Marshal(fullTextResponse)

setting/operation_setting/model-ratio.go

@@ -517,18 +517,18 @@ func getHardcodedCompletionModelRatio(name string) (float64, bool) {
 
 func GetAudioRatio(name string) float64 {
 	if strings.Contains(name, "-realtime") {
-		if strings.HasSuffix(name, "gpt-4o-realtime-preview-2024-12-17") {
+		if strings.HasSuffix(name, "gpt-4o-realtime-preview") {
 			return 8
-		} else if strings.Contains(name, "mini") {
+		} else if strings.Contains(name, "gpt-4o-mini-realtime-preview") {
 			return 10 / 0.6
 		} else {
 			return 20
 		}
 	}
 	if strings.Contains(name, "-audio") {
-		if strings.HasSuffix(name, "gpt-4o-audio-preview-2024-12-17") {
-			return 16
-		} else if strings.Contains(name, "mini") {
+		if strings.HasPrefix(name, "gpt-4o-audio-preview") {
+			return 40 / 2.5
+		} else if strings.HasPrefix(name, "gpt-4o-mini-audio-preview") {
 			return 10 / 0.15
 		} else {
 			return 40