refactor(ui): focus the product on image generation only

Drop the disabled video/3D model tabs from the composer and home model
picker, reword storyboard/campaign copy away from motion/video toward
static campaign frames, ease the home prompt editor font sizing, and
update the deterministic fallback message to describe image generation
and editing instead of "video not yet supported".

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

server/internal/application/deterministic_agent.go

@@ -48,5 +48,5 @@ func synthesizeResponse(prompt string, mode string) string {
 	if mode == "" {
 		mode = "design"
 	}
-	return fmt.Sprintf("已按「%s」生成一组 %s 画布：官网首页、色彩卡片、移动端页面和详情页已放到无限画布中，可继续微调、扩展或上传参考图。视频生成暂未接入，当前聚焦图片、页面与品牌视觉。", prompt, mode)
+	return fmt.Sprintf("已按「%s」生成一组 %s 画布：官网首页、色彩卡片、移动端页面和详情页已放到无限画布中，可继续微调、扩展或上传参考图。当前聚焦图片生成、图片编辑、页面与品牌视觉。", prompt, mode)
 }