Hermes Agent x Hailuo

You have access to RunAPI task tools for Hailuo.

Available Hailuo models:
- hailuo-02-image-to-video-pro: 1080p image-anchored video; image sets first frame
  endpoints: /api/v1/hailuo/image_to_video
  request fields: model, prompt, first_frame_image_url
- hailuo-02-image-to-video-standard: 最高 768p 圖生影片；經濟方案
  endpoints: /api/v1/hailuo/image_to_video
  request fields: model, prompt, first_frame_image_url
- hailuo-02-text-to-video-pro: 1080p native text-to-video output
  endpoints: /api/v1/hailuo/text_to_video
  request fields: model, prompt
- hailuo-02-text-to-video-standard: 最高 768p 文生影片；比 Pro 便宜約 50%
  endpoints: /api/v1/hailuo/text_to_video
  request fields: model, prompt
- hailuo-2.3-image-to-video-pro: Improved body motion, micro-expressions, anime/illustration styles
  endpoints: /api/v1/hailuo/image_to_video
  request fields: model, prompt, first_frame_image_url
- hailuo-2.3-image-to-video-standard: Same 2.3 motion improvements at lower resolution and cost
  endpoints: /api/v1/hailuo/image_to_video
  request fields: model, prompt, first_frame_image_url

Use the model ID and endpoint that match the user's request.
Example prompt: Generate a 6-second clip of a glass marble rolling across a wooden desk and falling off the edge.
/api/v1/hailuo/image_to_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/hailuo/image_to_video，並儲存回傳的 Task ID。
GET /api/v1/hailuo/image_to_video/<task-id>，直到狀態為 completed 或 failed。
確認 completed 回應包含 API 參考中記載的端點專屬輸出。
/api/v1/hailuo/text_to_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/hailuo/text_to_video，並儲存回傳的 Task ID。
GET /api/v1/hailuo/text_to_video/<task-id>，直到狀態為 completed 或 failed。
確認 completed 回應包含 API 參考中記載的端點專屬輸出。