feat: gemini video veo3.1 add i2v

relay/channel/task/gemini/adaptor.go

@@ -24,13 +24,9 @@ import (
 	"github.com/pkg/errors"
 )
 
-// ============================
+// VideoGenerationConfig represents the video generation configuration
-// Request / Response structures
-// ============================
-
-// GeminiVideoGenerationConfig represents the video generation configuration
 // Based on: https://ai.google.dev/gemini-api/docs/video
-type GeminiVideoGenerationConfig struct {
+type VideoGenerationConfig struct {
 	AspectRatio      string  `json:"aspectRatio,omitempty"`      // "16:9" or "9:16"
 	DurationSeconds  float64 `json:"durationSeconds,omitempty"`  // 4, 6, or 8 (as number)
 	NegativePrompt   string  `json:"negativePrompt,omitempty"`   // unwanted elements
@@ -38,15 +34,21 @@ type GeminiVideoGenerationConfig struct {
 	Resolution       string  `json:"resolution,omitempty"`       // video resolution
 }
 
-// GeminiVideoRequest represents a single video generation instance
+type Image struct {
-type GeminiVideoRequest struct {
+	BytesBase64Encoded string `json:"bytesBase64Encoded,omitempty"`
-	Prompt string `json:"prompt"`
+	MimeType           string `json:"mimeType,omitempty"`
 }
 
-// GeminiVideoPayload represents the complete video generation request payload
+type VideoRequest struct {
-type GeminiVideoPayload struct {
+	Prompt    string `json:"prompt"`
-	Instances  []GeminiVideoRequest        `json:"instances"`
+	Image     *Image `json:"image,omitempty"`
-	Parameters GeminiVideoGenerationConfig `json:"parameters,omitempty"`
+	LastFrame *Image `json:"lastFrame,omitempty"`
+}
+
+// VideoPayload represents the complete video generation request payload
+type VideoPayload struct {
+	Instances  []VideoRequest        `json:"instances"`
+	Parameters VideoGenerationConfig `json:"parameters,omitempty"`
 }
 
 type submitResponse struct {
@@ -100,8 +102,7 @@ func (a *TaskAdaptor) Init(info *relaycommon.RelayInfo) {
 
 // ValidateRequestAndSetAction parses body, validates fields and sets default action.
 func (a *TaskAdaptor) ValidateRequestAndSetAction(c *gin.Context, info *relaycommon.RelayInfo) (taskErr *dto.TaskError) {
-	// Use the standard validation method for TaskSubmitReq
+	return relaycommon.ValidateBasicTaskRequest(c, info, constant.TaskActionGenerate)
-	return relaycommon.ValidateBasicTaskRequest(c, info, constant.TaskActionTextGenerate)
 }
 
 // BuildRequestURL constructs the upstream URL.
@@ -137,13 +138,21 @@ func (a *TaskAdaptor) BuildRequestBody(c *gin.Context, info *relaycommon.RelayIn
 	}
 
 	// Create structured video generation request
-	body := GeminiVideoPayload{
+	body := VideoPayload{
-		Instances: []GeminiVideoRequest{
+		Instances: []VideoRequest{
 			{Prompt: req.Prompt},
 		},
-		Parameters: GeminiVideoGenerationConfig{},
+		Parameters: VideoGenerationConfig{},
 	}
 
+	if len(req.Images) > 0 {
+		body.Instances[0].Image = a.convertImage(req.Images[0])
+	}
+	if len(req.Images) > 1 {
+		body.Instances[0].LastFrame = a.convertImage(req.Images[1])
+	}
+
+	// Parse metadata for additional configuration
 	metadata := req.Metadata
 	medaBytes, err := json.Marshal(metadata)
 	if err != nil {
@@ -289,6 +298,30 @@ func (a *TaskAdaptor) ConvertToOpenAIVideo(task *model.Task) ([]byte, error) {
 	return common.Marshal(video)
 }
 
+func (a *TaskAdaptor) convertImage(imageStr string) *Image {
+	if strings.TrimSpace(imageStr) == "" {
+		return nil
+	}
+	img := &Image{
+		MimeType:           "image/png",
+		BytesBase64Encoded: imageStr,
+	}
+	if strings.HasPrefix(imageStr, "data:image/") {
+		parts := strings.Split(imageStr, ";base64,")
+		if len(parts) == 2 {
+			img.MimeType = strings.TrimPrefix(parts[0], "data:")
+			img.BytesBase64Encoded = parts[1]
+		}
+	} else if strings.HasPrefix(imageStr, "http") {
+		mimeType, data, err := service.GetImageFromUrl(imageStr)
+		if err == nil {
+			img.MimeType = mimeType
+			img.BytesBase64Encoded = data
+		}
+	}
+	return img
+}
+
 // ============================
 // helpers
 // ============================