Files
sci-gui-agent-benchmark/evaluation_examples/examples/os/e0df059f-28a6-4169-924f-b9623e7184cc.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

46 lines
1.2 KiB
JSON

{
"id": "e0df059f-28a6-4169-924f-b9623e7184cc",
"snapshot": "os",
"instruction": "I have a directory named \"todo_list_Jan_1\". Can you help me change its name into \"todo_list_Jan_2\"?",
"source": "https://help.ubuntu.com/lts/ubuntu-help/files-rename.html.en",
"trajectory": "trajectories/",
"config": [
{
"type": "execute",
"parameters": {
"command": "echo {CLIENT_PASSWORD} | sudo -S mkdir ~/Desktop/todo_list_Jan_1",
"shell": true
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.click({SCREEN_WIDTH_HALF}, {SCREEN_HEIGHT_HALF}); time.sleep(0.5);"
]
}
}
],
"related_apps": [
"os"
],
"evaluator": {
"func": "exact_match",
"result": {
"type": "vm_command_line",
"command": "[ -d ~/Desktop/todo_list_Jan_2 ] && echo 'Directory exists.' || echo 'Directory does not exist.'",
"shell": true
},
"expected": {
"type": "rule",
"rules": {
"expected": "Directory exists.\n"
}
}
},
"proxy": false,
"fixed_ip": false,
"possibility_of_env_change": "low"
}