feat: add video URL support in MediaContent and update token counting logic

dto/openai_request.go

@@ -114,6 +114,7 @@ type MediaContent struct {
 	ImageUrl   any    `json:"image_url,omitempty"`
 	InputAudio any    `json:"input_audio,omitempty"`
 	File       any    `json:"file,omitempty"`
+	VideoUrl   any    `json:"video_url,omitempty"`
 }
 
 func (m *MediaContent) GetImageMedia() *MessageImageUrl {
@@ -158,11 +159,16 @@ type MessageFile struct {
 	FileId   string `json:"file_id,omitempty"`
 }
 
+type MessageVideoUrl struct {
+	Url string `json:"url"`
+}
+
 const (
 	ContentTypeText       = "text"
 	ContentTypeImageURL   = "image_url"
 	ContentTypeInputAudio = "input_audio"
 	ContentTypeFile       = "file"
+	ContentTypeVideoUrl   = "video_url" // 阿里百炼视频识别
 )
 
 func (m *Message) GetPrefix() bool {
@@ -346,6 +352,15 @@ func (m *Message) ParseContent() []MediaContent {
 						}
 					}
 				}
+			case ContentTypeVideoUrl:
+				if videoUrl, ok := contentItem["video_url"].(string); ok {
+					contentList = append(contentList, MediaContent{
+						Type: ContentTypeVideoUrl,
+						VideoUrl: &MessageVideoUrl{
+							Url: videoUrl,
+						},
+					})
+				}
 			}
 		}
 	}

main.go

@@ -80,6 +80,8 @@ func main() {
 	// Initialize options
 	model.InitOptionMap()
 
+	service.InitTokenEncoders()
+
 	if common.RedisEnabled {
 		// for compatibility with old versions
 		common.MemoryCacheEnabled = true
@@ -133,8 +135,6 @@ func main() {
 		common.SysLog("pprof enabled")
 	}
 
-	service.InitTokenEncoders()
-
 	// Initialize HTTP server
 	server := gin.New()
 	server.Use(gin.CustomRecovery(func(c *gin.Context, err any) {

service/token_counter.go

@@ -400,6 +400,8 @@ func CountTokenMessages(info *relaycommon.RelayInfo, messages []dto.Message, mod
 					tokenNum += 100
 				} else if m.Type == dto.ContentTypeFile {
 					tokenNum += 5000
+				} else if m.Type == dto.ContentTypeVideoUrl {
+					tokenNum += 5000
 				} else {
 					tokenNum += getTokenNum(tokenEncoder, m.Text)
 				}