e433f35c1f
- Add `fixed_ip` field to all 369 JSON files in examples directory - Set to `true` for 8 files listed in google_chrome.json multi_apps - Set to `false` for remaining 361 files - Add `possibility_of_env_change` field to 363 JSON files missing this field - Set to "low" for newly added fields - Preserve existing values (4 medium, 2 high) for 6 files that already had this field This ensures consistent configuration schema across all evaluation examples while maintaining backward compatibility with existing settings.
82 lines
2.3 KiB
JSON
82 lines
2.3 KiB
JSON
{
|
|
"id": "68a25bd4-59c7-4f4d-975e-da0c8509c848",
|
|
"snapshot": "libreoffice_calc",
|
|
"instruction": "I've compiled papers and books with links in this spreadsheet. Help me download the PDF of the first paper, save it as \"paper01.pdf\" in the /home/user directory. Additionally, I would like to know which paper in my list cites the initial one. Please determine and document the title saved as \"ans.docx\" in the same directory.",
|
|
"source": "",
|
|
"config": [
|
|
{
|
|
"type": "download",
|
|
"parameters": {
|
|
"files": [
|
|
{
|
|
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/68a25bd4-59c7-4f4d-975e-da0c8509c848/rsc-ebook-collection-2023.xlsx",
|
|
"path": "/home/user/Desktop/rsc-ebook-collection-2023.xlsx"
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"type": "launch",
|
|
"parameters": {
|
|
"command": [
|
|
"google-chrome",
|
|
"--remote-debugging-port=1337"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"type": "launch",
|
|
"parameters": {
|
|
"command": [
|
|
"socat",
|
|
"tcp-listen:9222,fork",
|
|
"tcp:localhost:1337"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"type": "open",
|
|
"parameters": {
|
|
"path": "/home/user/Desktop/rsc-ebook-collection-2023.xlsx"
|
|
}
|
|
}
|
|
],
|
|
"trajectory": "trajectories/68a25bd4-59c7-4f4d-975e-da0c8509c848",
|
|
"related_apps": [
|
|
"libreoffice_calc",
|
|
"chrome"
|
|
],
|
|
"evaluator": {
|
|
"func": [
|
|
"compare_pdfs",
|
|
"compare_docx_files"
|
|
],
|
|
"expected": [
|
|
{
|
|
"type": "cloud_file",
|
|
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/68a25bd4-59c7-4f4d-975e-da0c8509c848/paper01.pdf",
|
|
"dest": "paper01_Gold.pdf"
|
|
},
|
|
{
|
|
"type": "cloud_file",
|
|
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/68a25bd4-59c7-4f4d-975e-da0c8509c848/ans.docx",
|
|
"dest": "ans_Gold.docx"
|
|
}
|
|
],
|
|
"result": [
|
|
{
|
|
"type": "vm_file",
|
|
"path": "/home/user/paper01.pdf",
|
|
"dest": "paper01.pdf"
|
|
},
|
|
{
|
|
"type": "vm_file",
|
|
"path": "/home/user/ans.docx",
|
|
"dest": "ans.docx"
|
|
}
|
|
]
|
|
},
|
|
"proxy": false,
|
|
"fixed_ip": false,
|
|
"possibility_of_env_change": "low"
|
|
} |