Files
sci-gui-agent-benchmark/evaluation_examples/examples/chrome/af630914-714e-4a24-a7bb-f9af687d3b91.json
yuanmengqi 2c51950e73 feat: enhance evaluator configuration for Chrome with post-execution commands
- Added postconfig commands to multiple JSON files for Chrome evaluation examples.
- Included commands to terminate existing Chrome processes, launch Chrome with remote debugging, and introduce sleep intervals for timing.
- Updated logging messages in the AWS manager to improve clarity and user experience.

These changes enhance the automation and usability of the evaluation examples while preserving existing logic.
2025-07-17 10:50:10 +00:00

74 lines
1.5 KiB
JSON

{
"id": "af630914-714e-4a24-a7bb-f9af687d3b91",
"snapshot": "chrome",
"instruction": "My grandmother has been using the Chrome lately and told me that the font size is way too small for her poor eyesight. Could you set the default font size to the largest for her?",
"source": "https://www.howtogeek.com/680260/how-to-change-chromes-default-text-size/",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"postconfig": [
{
"type": "launch",
"parameters": {
"command": [
"pkill",
"chrome"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3
}
}
],
"func": "check_font_size",
"result": {
"type": "chrome_font_size"
},
"expected": {
"type": "rule",
"rules": {
"type": "range",
"min": 16,
"max": 99999
}
}
},
"proxy": false,
"fixed_ip": false,
"possibility_of_env_change": "low"
}