Files
sci-gui-agent-benchmark/evaluation_examples/examples/multi_apps/c2751594-0cd5-4088-be1b-b5f2f9ec97c4.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

64 lines
1.6 KiB
JSON

{
"id": "c2751594-0cd5-4088-be1b-b5f2f9ec97c4",
"snapshot": "thunderbird",
"instruction": "Help me export the first image from the doc file attached in the most recent email in Notes folder, and set this image as the new desktop background.",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/c2751594-0cd5-4088-be1b-b5f2f9ec97c4/thunderbird-profile.tar.gz",
"path": "/home/user/thunderbird-profile.tar.gz"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"tar",
"--recursive-unlink",
"-xz",
"-f",
"/home/user/thunderbird-profile.tar.gz",
"-C",
"/home/user/"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"/usr/bin/thunderbird"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"thunderbird",
"os"
],
"evaluator": {
"func": "compare_images",
"result": {
"type": "vm_wallpaper",
"dest": "background.png"
},
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/c2751594-0cd5-4088-be1b-b5f2f9ec97c4/background.png",
"dest": "gold_background.png"
},
"options": {
"reference_base_result": 0.54
}
},
"proxy": false,
"fixed_ip": false,
"possibility_of_env_change": "low"
}