feat(piagent): bypass planner for direct image generation modes

For image / pure-image / image-generator / image-action modes, skip the task-planning round trip and hand the prompt straight to the image model, deriving the requested image count from the composer settings. Also normalize completed image-generator nodes back into regular image nodes (clearing the image-generator layer role and defaulting Tone to "visual") when merging generated results and when restoring finished nodes, so a finished generator node is not re-appended as a duplicate. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-09 01:09:59 +08:00
parent a39e18950c
commit ffd8d78df7
5 changed files with 573 additions and 60 deletions
@@ -46,6 +46,10 @@ func NewDesignAgent(base design.AgentRunner, imageAgent ImageGenerator, textAgen
 }

 func (a *DesignAgent) Plan(ctx context.Context, req design.AgentRequest) (design.AgentPlan, error) {
+	if shouldUseDirectImageGeneration(req) {
+		return a.planDirectImageGeneration(ctx, req)
+	}
+
 	plan, err := a.base.Plan(ctx, req)
 	if err != nil {
 		return design.AgentPlan{}, err
@@ -76,6 +80,10 @@ func (a *DesignAgent) Plan(ctx context.Context, req design.AgentRequest) (design
 }

 func (a *DesignAgent) PlanIncremental(ctx context.Context, req design.AgentRequest, onResult func(design.AgentImageGenerationResult) error) (design.AgentPlan, error) {
+	if shouldUseDirectImageGeneration(req) {
+		return a.planDirectImageGenerationIncremental(ctx, req, onResult)
+	}
+
 	plan, err := a.base.Plan(ctx, req)
 	if err != nil {
 		return design.AgentPlan{}, err
@@ -115,6 +123,92 @@ func (a *DesignAgent) PlanIncremental(ctx context.Context, req design.AgentReque
 	return plan, nil
 }

+func (a *DesignAgent) planDirectImageGeneration(ctx context.Context, req design.AgentRequest) (design.AgentPlan, error) {
+	if a.imageAgent == nil {
+		return design.AgentPlan{}, fmt.Errorf("gpt image 2 is not configured")
+	}
+	generationReq := req
+	generationReq.ImageSize = resolveImageSizeForGeneration(req.ImageSize, req.Prompt)
+	prompts := directImagePrompts(generationReq)
+	imageURLs, err := a.generatePlannedImages(ctx, prompts, generationReq)
+	if err != nil {
+		return design.AgentPlan{}, fmt.Errorf("gpt image 2 generation failed: %w", err)
+	}
+	plan := directImagePlan(generationReq)
+	applyPlannedGeneratedImages(&plan, generationReq, imageURLs, prompts)
+	title := ""
+	if len(prompts) > 0 {
+		title = prompts[0].Title
+	}
+	plan.Message.Title = generatedMessageTitle(title, req.Prompt)
+	return plan, nil
+}
+
+func (a *DesignAgent) planDirectImageGenerationIncremental(ctx context.Context, req design.AgentRequest, onResult func(design.AgentImageGenerationResult) error) (design.AgentPlan, error) {
+	if a.imageAgent == nil {
+		return design.AgentPlan{}, fmt.Errorf("gpt image 2 is not configured")
+	}
+	generationReq := req
+	generationReq.ImageSize = resolveImageSizeForGeneration(req.ImageSize, req.Prompt)
+	prompts := directImagePrompts(generationReq)
+	plan := directImagePlan(generationReq)
+	nodes, err := a.generatePlannedImagesIncremental(ctx, prompts, generationReq, plan.GeneratedNodes, onResult)
+	if err != nil {
+		if len(nodes) > 0 {
+			plan.GeneratedNodes = nodes
+			plan.Connections = nil
+		}
+		return plan, fmt.Errorf("gpt image 2 generation failed: %w", err)
+	}
+	plan.GeneratedNodes = nodes
+	plan.Connections = nil
+	title := ""
+	if len(prompts) > 0 {
+		title = prompts[0].Title
+	}
+	plan.Message.Title = generatedMessageTitle(title, req.Prompt)
+	return plan, nil
+}
+
+func directImagePlan(req design.AgentRequest) design.AgentPlan {
+	return design.AgentPlan{
+		Message: design.Message{
+			ID:      uuid.NewString(),
+			Role:    "assistant",
+			Type:    "assistant",
+			Title:   generatedMessageTitle("", req.Prompt),
+			Content: "",
+		},
+	}
+}
+
+func directImagePrompts(req design.AgentRequest) []design.AgentImagePrompt {
+	count := plannedGenerationCount(req)
+	prompt := strings.TrimSpace(req.Prompt)
+	if prompt == "" {
+		prompt = fallbackDirectImagePrompt(req)
+	}
+	prompts := make([]design.AgentImagePrompt, 0, count)
+	for index := 0; index < count; index++ {
+		title := normalizeGeneratedTitle("", req.Prompt)
+		if index < len(req.TaskPlan.ImageTasks) {
+			if taskTitle := strings.TrimSpace(req.TaskPlan.ImageTasks[index].Title); taskTitle != "" {
+				title = normalizeGeneratedTitle(taskTitle, req.Prompt)
+			}
+		}
+		prompts = append(prompts, design.AgentImagePrompt{
+			Title:  title,
+			Prompt: prepareGPTImagePrompt(variantImagePrompt(prompt, index+1, count), imageGenerationPromptMaxRunes),
+		})
+	}
+	return prompts
+}
+
+func shouldUseDirectImageGeneration(req design.AgentRequest) bool {
+	mode := strings.ToLower(strings.TrimSpace(req.Mode))
+	return mode == "image" || mode == "pure-image" || mode == "image-generator" || strings.Contains(mode, "image-action")
+}
+
 func (a *DesignAgent) buildImagePrompts(ctx context.Context, req design.AgentRequest) []design.AgentImagePrompt {
 	count := plannedGenerationCount(req)
 	prompts := make([]design.AgentImagePrompt, 0, count)
@@ -667,28 +761,7 @@ func applyGeneratedImages(plan *design.AgentPlan, req design.AgentRequest, image
 	slots := generatedImageSlots(req, plan.GeneratedNodes, requestedCount)
 	nodes := make([]design.Node, 0, requestedCount)
 	for index := 0; index < requestedCount; index++ {
-		node := slots[index]
-		node.Type = design.NodeTypeImage
-		node.Title = generatedNodeTitle(title, req.Prompt, index, requestedCount)
-		node.Content = imageURLs[index]
-		node.Status = "success"
-		if node.ID == "" {
-			node.ID = uuid.NewString()
-		}
-		if width, height, ok := imageSizeDimensions(req.ImageSize); ok {
-			node.Width = width
-			node.Height = height
-		}
-		if node.Width <= 0 {
-			node.Width = design.DefaultGeneratedImageWidth
-		}
-		if node.Height <= 0 {
-			node.Height = design.DefaultGeneratedImageHeight
-		}
-		if node.Tone == "" {
-			node.Tone = "visual"
-		}
-		nodes = append(nodes, node)
+		nodes = append(nodes, generatedImageNodeFromSlot(slots[index], req, imageURLs[index], title, index, requestedCount))
 	}
 	plan.GeneratedNodes = nodes
 	plan.Connections = nil
@@ -731,7 +804,10 @@ func generatedImageNodeFromSlot(slot design.Node, req design.AgentRequest, image
 	if node.Height <= 0 {
 		node.Height = design.DefaultGeneratedImageHeight
 	}
-	if node.Tone == "" {
+	if node.LayerRole == "image-generator" {
+		node.LayerRole = ""
+	}
+	if node.Tone == "" || node.Tone == "image-generator" {
 		node.Tone = "visual"
 	}
 	return node