Files
sci-gui-agent-benchmark/evaluation_examples/examples/libreoffice_writer/88fe4b2d-3040-4c70-9a70-546a47764b48.json
Tianbao Xie 4e11eafd1d Robust Evaluation, Blocking File Open, Grader Sensitivity, and LibreOffice Writer Fixes (#217)
* Refactor evaluator structure in LibreOffice Writer example JSON to support multiple expected and result files, enhancing evaluation flexibility.

* Update instance type to t3.large and add VNC access URL logging for allocated VMs, enhancing remote access capabilities.

* Update instance type to t3.large and add VNC access URL logging for allocated VMs, enhancing remote access capabilities.

* Update time format in get_vm_file function to include hours, minutes, and seconds for more precise file naming with time suffix.

* More delay for 936321ce-5236-426a-9a20-e0e3c5dc536f; support one more potential solutions.

* Enhance SetupController with configurable retry limit and improved error handling for file opening requests. Introduce new function to compare unique training records, and update logging for better debugging. Adjust JSON examples for evaluation to support multiple expected and result files.

* Clean debug code

---------

Co-authored-by: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
2025-06-16 21:37:19 +08:00

108 lines
3.4 KiB
JSON

{
"id": "88fe4b2d-3040-4c70-9a70-546a47764b48",
"snapshot": "libreoffice_writer",
"instruction": "I am making a guideline for students of my course and would like to separate each sentence in the the first paragraph to improve readability. Please separate each sentence by creating one empty line space after each of them, as I am having hard time separating them one by one.",
"source": "https://stackoverflow.com/questions/56554555/libreoffice-writer-how-to-create-empty-line-space-after-every-period-in-a-par",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/88fe4b2d-3040-4c70-9a70-546a47764b48/CCCH9003_Tutorial_guidelines.docx",
"path": "/home/user/Desktop/CCCH9003_Tutorial_guidelines.docx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Desktop/CCCH9003_Tutorial_guidelines.docx"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_writer"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "CCCH9003_Tutorial_guidelines.docx - LibreOffice Writer",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('ctrl', 's'); time.sleep(0.5); "
]
}
}
],
"func": [
"compare_docx_files",
"compare_docx_files",
"compare_docx_files"
],
"conj": "or",
"expected": [
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/88fe4b2d-3040-4c70-9a70-546a47764b48/CCCH9003_Tutorial_guidelines_Gold_1.docx",
"dest": "CCCH9003_Tutorial_guidelines_Gold_1.docx"
},
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/88fe4b2d-3040-4c70-9a70-546a47764b48/CCCH9003_Tutorial_guidelines_Gold_2.docx",
"dest": "CCCH9003_Tutorial_guidelines_Gold_2.docx"
},
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_writer/88fe4b2d-3040-4c70-9a70-546a47764b48/CCCH9003_Tutorial_guidelines_Gold_3.docx",
"dest": "CCCH9003_Tutorial_guidelines_Gold_3.docx"
}
],
"result": [
{
"type": "vm_file",
"path": "/home/user/Desktop/CCCH9003_Tutorial_guidelines.docx",
"dest": "CCCH9003_Tutorial_guidelines.docx"
},
{
"type": "vm_file",
"path": "/home/user/Desktop/CCCH9003_Tutorial_guidelines.docx",
"dest": "CCCH9003_Tutorial_guidelines.docx"
},
{
"type": "vm_file",
"path": "/home/user/Desktop/CCCH9003_Tutorial_guidelines.docx",
"dest": "CCCH9003_Tutorial_guidelines.docx"
}
],
"options": [
{
"ignore_blanks": false
},
{
"ignore_blanks": false
},
{
"ignore_blanks": false
}
]
},
"proxy": false
}