Files
sci-gui-agent-benchmark/evaluation_examples/examples/chrome/47543840-672a-467d-80df-8f7c3b9788c9.json
Yuan Mengqi b2fb8b4222 fix chrome tasks (#230)
* 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

---------

Co-authored-by: adlsdztony <zzl0712@connect.hku.hk>
2025-07-03 21:32:41 +08:00

117 lines
3.0 KiB
JSON

{
"id": "47543840-672a-467d-80df-8f7c3b9788c9",
"snapshot": "chrome",
"instruction": "Show me the cars available for pickup at Boston Logan Intl Airport from the 10th to the 11th of next month, sorted by the number of seats to find the largest capacity.",
"source": "test_task_1",
"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.budget.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": [
"is_expected_url_pattern_match",
"check_direct_json_object",
"check_direct_json_object"
],
"conj": "and",
"result": [
{
"type": "active_url_from_accessTree",
"goto_prefix": "https://www."
},
{
"type": "active_tab_html_parse",
"goto_prefix": "https://www.",
"category": "class",
"class_singleObject": {},
"class_multiObject": {
"location-info": {
"0": "start_location",
"1": "end_location"
},
"day-time-info": {
"0": "from",
"1": "to"
}
}
},
{
"type": "active_tab_html_parse",
"goto_prefix": "https://www.",
"category": "xpath",
"xpathObject": {
"/html/body/div[6]/div[2]/div[1]/div/div/div[2]/section[1]/div[1]/form/div[1]/div[1]/div[2]/div/a": "rank"
}
}
],
"expected": [
{
"type": "rule",
"rules": {
"expected": [
"reservation#/vehicles"
]
}
},
{
"type": "rule_relativeTime",
"rules": {
"relativeTime": {
"from": "10th next month",
"to": "11th next month"
},
"expected": {
"start_location": "Boston Logan Intl Airport,\n\t\t\t\t\t\t\t\tBOS \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t Pick-Up",
"end_location": "Boston Logan Intl Airport,\n\t\t\t\t\t\t\t\tBOS",
"from": "{DoW}, {Month} {Day0D}, 12:00 PM",
"to": "{DoW}, {Month} {Day0D}, 12:00 PM"
}
}
},
{
"type": "rule",
"rules": {
"expected": {
"rank": "Number of Seats (High to Low)"
}
}
}
]
},
"proxy": true
}