Files
sci-gui-agent-benchmark/evaluation_examples/examples/chrome/7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3.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

85 lines
1.9 KiB
JSON

{
"id": "7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3",
"snapshot": "chrome",
"instruction": "Can you help me clean up my computer by getting rid of all the tracking things that Amazon might have saved? I want to make sure my browsing is private and those sites don't remember me.",
"source": "https://support.google.com/chrome/answer/95647?hl=en&ref_topic=7438325&sjid=16867045591165135686-AP#zippy=%2Cdelete-cookies-from-a-site",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.amazon.com",
"https://www.amazon.com/s?k=huggingface+transformers+book"
]
}
}
],
"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": "is_cookie_deleted",
"result": {
"type": "cookie_data",
"dest": "Cookies"
},
"expected": {
"type": "rule",
"rules": {
"type": "domains",
"domains": [
".amazon.com"
]
}
}
},
"proxy": true,
"fixed_ip": false,
"possibility_of_env_change": "low"
}