Files
sci-gui-agent-benchmark/evaluation_examples/examples/os/28cc3b7e-b194-4bc9-8353-d04c0f4d56d2.json
Yuan Mengqi 27319ce1e3 fix password&resolution (#251)
* fix chrome

* fix: fix proxy setup

* feat&fix: add proxy support in setup and remove hardcoded proxy from example

* fix tasks

* fix chrome finished

* fix

* clean chrome_fix code

* clean chrome_fix code

* fix chrome 2888b4e6-5b47-4b57-8bf5-c73827890774

* fix multiapps

* fix chrome 2888b4e6-5b47-4b57-8bf5-c73827890774

* fix some multi_apps tasks

* fix some multi_apps tasks

* fix password&resolution

* fix password&resolution

---------

Co-authored-by: adlsdztony <zzl0712@connect.hku.hk>
2025-07-13 00:25:37 +08:00

37 lines
961 B
JSON

{
"id": "28cc3b7e-b194-4bc9-8353-d04c0f4d56d2",
"snapshot": "os",
"instruction": "The volume of my system is too small. Can you help me turn up to the max volume?",
"source": "https://help.ubuntu.com/lts/ubuntu-help/sound-volume.html.en",
"trajectory": "trajectories/",
"config": [
{
"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": "pulseaudio --start\npactl list sinks | grep '^[[:space:]]Volume:' | head -n 1 | awk '{print $5}' | sed 's/%//g'",
"shell": true
},
"expected": {
"type": "rule",
"rules": {
"expected": "100\n"
}
}
},
"proxy": false
}