(已支持 arm 架构)写了一个跑在闲置小鸡上的开源项目：bilive - 7 x 24 小时无人监守录制、渲染弹幕、识别字幕、自动切片上传、综合多种模态模型、兼容超低配机器

[INFO] - [2025-03-22 04:57:57,272 bilive scan] - Begin processing /root/bilive/Videos/21852/21852_20250322-04-32-57.mp4...

[INFO] - [2025-03-22 04:57:57,454 bilive scan] - The video resolution is 1280x720

[INFO] - [2025-03-22 04:57:57,546 bilive scan] - The emojis of /root/bilive/Videos/21852/21852_20250322-04-32-57.ass has been removed.

[INFO] - [2025-03-22 04:57:57,546 bilive scan] - Current Mode: CPU with danmaku

[INFO] - [2025-03-22 05:06:58,485 bilive scan] - Complete danamku burning and wait for uploading!

[INFO] - [2025-03-22 05:06:58,996 bilive scan] - The 30-second window with the highest density starts at 00:00:45.50 seconds with 32 danmakus.

Traceback (most recent call last):

  File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main

    return _run_code(code, main_globals, None,

  File "/usr/lib/python3.10/runpy.py", line 86, in _run_code

    exec(code, run_globals)

  File "/root/bilive/src/burn/scan.py", line 64, in <module>

    process_folder_append(room_folder)

  File "/root/bilive/src/burn/scan.py", line 51, in process_folder_append

    render_video(file)

  File "/root/bilive/src/burn/render_video.py", line 70, in render_video

    glm_title = zhipu_glm_4v_plus_generate_title(slice_video_path, artist)

  File "/root/bilive/src/autoslice/slice_video.py", line 15, in zhipu_glm_4v_plus_generate_title

    response = client.chat.completions.create(

  File "/usr/local/lib/python3.10/dist-packages/zhipuai/api_resource/chat/completions.py", line 96, in create

    return self._post(

  File "/usr/local/lib/python3.10/dist-packages/zhipuai/core/_http_client.py", line 809, in post

    return cast(ResponseT, self.request(cast_type, opts, stream=stream, stream_cls=stream_cls))

  File "/usr/local/lib/python3.10/dist-packages/zhipuai/core/_http_client.py", line 495, in request

    return self._request(

  File "/usr/local/lib/python3.10/dist-packages/zhipuai/core/_http_client.py", line 582, in _request

    raise self._make_status_error(err.response) from None

zhipuai.core._errors.APIRequestFailedError: Error code: 400, with error text {"error":{"code":"1261","message":"Prompt 超长"}}

AI告诉我是 这个错误信息 Prompt 超长表明您在使用智谱 GLM-4V-PLUS 模型生成切片标题时，发送给模型的提示（Prompt）内容过长，超出了模型允许的最大长度。

我的切片的默认配置没有动过，只是改成了True，应该怎么解决 xhj024