Files
sci-gui-agent-benchmark/evaluation_examples/examples/multi_apps/716a6079-22da-47f1-ba73-c9d58f986a38.json
yuanmengqi e433f35c1f feat: standardize configuration fields across all evaluation examples
- 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.
2025-07-16 13:45:34 +00:00

55 lines
1.6 KiB
JSON

{
"id": "716a6079-22da-47f1-ba73-c9d58f986a38",
"snapshot": "multiapps",
"instruction": "I remember there is a file named \"secret.docx\" on this computer, but I can't remember where it is. Please find the path where this file is stored and copy it to the clipboard.",
"source": "",
"config": [
{
"type": "command",
"parameters": {
"command": "mkdir -p /home/user/Data1/List1 && mkdir -p /home/user/Data2/List2 && mkdir -p /home/user/Data3/List3 && mkdir -p /home/user/Data4/List4 && mkdir -p /home/user/Data5/List5",
"shell": "true"
}
},
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/716a6079-22da-47f1-ba73-c9d58f986a38/Secret%20document.docx",
"path": "/home/user/Data3/List3/secret.docx"
}
]
}
},
{
"type": "command",
"parameters": {
"command": "echo {CLIENT_PASSWORD} | sudo -S apt install xsel && xsel -bc",
"shell": "true"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"os",
"terminal"
],
"evaluator": {
"func": "is_in_vm_clickboard",
"expected": {
"type": "vm_command_line",
"command": "xsel --clipboard --output",
"shell": "true"
},
"result": {
"type": "rule",
"rules": {
"expected": "/home/user/Data3/List3/secret.docx"
}
}
},
"proxy": false,
"fixed_ip": false,
"possibility_of_env_change": "low"
}