feat: 修复重试后请求结构混乱，修复rerank端点无法使用

dto/audio.go

@@ -26,6 +26,12 @@ func (r *AudioRequest) IsStream(c *gin.Context) bool {
 	return false
 }
 
+func (r *AudioRequest) SetModelName(modelName string) {
+	if modelName != "" {
+		r.Model = modelName
+	}
+}
+
 type AudioResponse struct {
 	Text string `json:"text"`
 }

dto/claude.go

@@ -321,8 +321,14 @@ func (c *ClaudeRequest) GetTokenCountMeta() *types.TokenCountMeta {
 	return &tokenCountMeta
 }
 
-func (claudeRequest *ClaudeRequest) IsStream(c *gin.Context) bool {
-	return claudeRequest.Stream
+func (c *ClaudeRequest) IsStream(ctx *gin.Context) bool {
+	return c.Stream
+}
+
+func (c *ClaudeRequest) SetModelName(modelName string) {
+	if modelName != "" {
+		c.Model = modelName
+	}
 }
 
 func (c *ClaudeRequest) SearchToolNameByToolCallId(toolCallId string) string {

dto/embedding.go

@@ -48,6 +48,12 @@ func (r *EmbeddingRequest) IsStream(c *gin.Context) bool {
 	return false
 }
 
+func (r *EmbeddingRequest) SetModelName(modelName string) {
+	if modelName != "" {
+		r.Model = modelName
+	}
+}
+
 func (r *EmbeddingRequest) ParseInput() []string {
 	if r.Input == nil {
 		return make([]string, 0)

dto/gemini.go

@@ -73,6 +73,10 @@ func (r *GeminiChatRequest) IsStream(c *gin.Context) bool {
 	return false
 }
 
+func (r *GeminiChatRequest) SetModelName(modelName string) {
+	// GeminiChatRequest does not have a model field, so this method does nothing.
+}
+
 func (r *GeminiChatRequest) GetTools() []GeminiChatTool {
 	var tools []GeminiChatTool
 	if strings.HasSuffix(string(r.Tools), "[") {
@@ -312,10 +316,61 @@ type GeminiEmbeddingRequest struct {
 	OutputDimensionality int               `json:"outputDimensionality,omitempty"`
 }
 
+func (r *GeminiEmbeddingRequest) IsStream(c *gin.Context) bool {
+	// Gemini embedding requests are not streamed
+	return false
+}
+
+func (r *GeminiEmbeddingRequest) GetTokenCountMeta() *types.TokenCountMeta {
+	var inputTexts []string
+	for _, part := range r.Content.Parts {
+		if part.Text != "" {
+			inputTexts = append(inputTexts, part.Text)
+		}
+	}
+	inputText := strings.Join(inputTexts, "\n")
+	return &types.TokenCountMeta{
+		CombineText: inputText,
+	}
+}
+
+func (r *GeminiEmbeddingRequest) SetModelName(modelName string) {
+	if modelName != "" {
+		r.Model = modelName
+	}
+}
+
 type GeminiBatchEmbeddingRequest struct {
 	Requests []*GeminiEmbeddingRequest `json:"requests"`
 }
 
+func (r *GeminiBatchEmbeddingRequest) IsStream(c *gin.Context) bool {
+	// Gemini batch embedding requests are not streamed
+	return false
+}
+
+func (r *GeminiBatchEmbeddingRequest) GetTokenCountMeta() *types.TokenCountMeta {
+	var inputTexts []string
+	for _, request := range r.Requests {
+		meta := request.GetTokenCountMeta()
+		if meta != nil && meta.CombineText != "" {
+			inputTexts = append(inputTexts, meta.CombineText)
+		}
+	}
+	inputText := strings.Join(inputTexts, "\n")
+	return &types.TokenCountMeta{
+		CombineText: inputText,
+	}
+}
+
+func (r *GeminiBatchEmbeddingRequest) SetModelName(modelName string) {
+	if modelName != "" {
+		for _, req := range r.Requests {
+			req.SetModelName(modelName)
+		}
+	}
+}
+
 type GeminiEmbeddingResponse struct {
 	Embedding ContentEmbedding `json:"embedding"`
 }

dto/openai_image.go

@@ -12,10 +12,10 @@ type ImageRequest struct {
 	Model             string          `json:"model"`
 	Prompt            string          `json:"prompt" binding:"required"`
 	N                 uint            `json:"n,omitempty"`
-	Size           string          `json:"size,omitempty"`
-	Quality        string          `json:"quality,omitempty"`
-	ResponseFormat string          `json:"response_format,omitempty"`
-	Style          json.RawMessage `json:"style,omitempty"`
+	Size              string          `json:"size,omitempty"`
+	Quality           string          `json:"quality,omitempty"`
+	ResponseFormat    string          `json:"response_format,omitempty"`
+	Style             json.RawMessage `json:"style,omitempty"`
 	User              json.RawMessage `json:"user,omitempty"`
 	ExtraFields       json.RawMessage `json:"extra_fields,omitempty"`
 	Background        json.RawMessage `json:"background,omitempty"`
@@ -63,6 +63,12 @@ func (i *ImageRequest) IsStream(c *gin.Context) bool {
 	return false
 }
 
+func (i *ImageRequest) SetModelName(modelName string) {
+	if modelName != "" {
+		i.Model = modelName
+	}
+}
+
 type ImageResponse struct {
 	Data    []ImageData `json:"data"`
 	Created int64       `json:"created"`

dto/openai_request.go

@@ -183,6 +183,12 @@ func (r *GeneralOpenAIRequest) IsStream(c *gin.Context) bool {
 	return r.Stream
 }
 
+func (r *GeneralOpenAIRequest) SetModelName(modelName string) {
+	if modelName != "" {
+		r.Model = modelName
+	}
+}
+
 func (r *GeneralOpenAIRequest) ToMap() map[string]any {
 	result := make(map[string]any)
 	data, _ := common.Marshal(r)
@@ -841,6 +847,12 @@ func (r *OpenAIResponsesRequest) IsStream(c *gin.Context) bool {
 	return r.Stream
 }
 
+func (r *OpenAIResponsesRequest) SetModelName(modelName string) {
+	if modelName != "" {
+		r.Model = modelName
+	}
+}
+
 type Reasoning struct {
 	Effort  string `json:"effort,omitempty"`
 	Summary string `json:"summary,omitempty"`

dto/request_common.go

@@ -8,6 +8,7 @@ import (
 type Request interface {
 	GetTokenCountMeta() *types.TokenCountMeta
 	IsStream(c *gin.Context) bool
+	SetModelName(modelName string)
 }
 
 type BaseRequest struct {
@@ -18,7 +19,7 @@ func (b *BaseRequest) GetTokenCountMeta() *types.TokenCountMeta {
 		TokenType: types.TokenTypeTokenizer,
 	}
 }
-
 func (b *BaseRequest) IsStream(c *gin.Context) bool {
 	return false
 }
+func (b *BaseRequest) SetModelName(modelName string) {}

dto/rerank.go

@@ -37,6 +37,12 @@ func (r *RerankRequest) GetTokenCountMeta() *types.TokenCountMeta {
 	}
 }
 
+func (r *RerankRequest) SetModelName(modelName string) {
+	if modelName != "" {
+		r.Model = modelName
+	}
+}
+
 func (r *RerankRequest) GetReturnDocuments() bool {
 	if r.ReturnDocuments == nil {
 		return false