Files
sci-gui-agent-benchmark/evaluation_examples/examples/os/bedcedc4-4d72-425e-ad62-21960b11fe0d.json
MillanK 983283a86a patch: minor bug fixes for evaluator and task configurations, documentation update (#121)
* fix: /cursor_position api return format fix

* chore: update README.md to remove deprecated command

* fix: add base score for evaluators and minor bug fixes

* fix: add base score for setup configurations

---------

Co-authored-by: Jiaqi Deng <jiaqideng@Jiaqis-MacBook-Pro.local>
2025-01-18 22:25:18 +08:00

52 lines
1.0 KiB
JSON

{
"id": "bedcedc4-4d72-425e-ad62-21960b11fe0d",
"snapshot": "os",
"instruction": "Could you set the 'Dim screen when inactive' to off in setting?",
"source": "https://www.youtube.com/watch?v=D4WyNjt_hbQ&t=2s",
"trajectory": "trajectories/",
"config": [
{
"type": "execute",
"parameters": {
"command": [
"gsettings",
"set",
"org.gnome.desktop.session",
"idle-delay",
"1"
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.click(960, 540); time.sleep(0.5);"
]
}
}
],
"related_apps": [
"os"
],
"evaluator": {
"func": "exact_match",
"result": {
"type": "vm_command_line",
"command": [
"gsettings",
"get",
"org.gnome.desktop.session",
"idle-delay"
]
},
"expected": {
"type": "rule",
"rules": {
"expected": "uint32 0\n"
}
}
}
}