Files
sci-gui-agent-benchmark/evaluation_examples/examples/chrome/c1fa57f3-c3db-4596-8f09-020701085416.json
MillanK cbc3b590ff Task fix batch (#383)
* update 873cafdd-a581-47f6-8b33-b9696ddb7b05 task eval

* c1fa57f3-c3db-4596-8f09-020701085416 fix, add tolerance to url matching

* 8df7e444-8e06-4f93-8a1a-c5c974269d82 add more clear instruction to the filename for compress

* add address string normalization for 6f4073b8-d8ea-4ade-8a18-c5d1d5d5aa9a

---------

Co-authored-by: Jiaqi <dengjiaqi@moonshot.cn>
2025-11-19 17:24:25 +08:00

63 lines
1.3 KiB
JSON

{
"id": "c1fa57f3-c3db-4596-8f09-020701085416",
"snapshot": "chrome",
"instruction": "Open the baggage fee calculator in United Airlines website.",
"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.united.com/en/us"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "is_expected_url_pattern_match",
"result": {
"type": "active_tab_info",
"goto_prefix": "https://www."
},
"expected": {
"type": "rule",
"rules": {
"expected": [
"united\\.com/en/us/checked-bag-fee-calculator(/.*)?"
]
}
}
},
"proxy": true,
"possibility_of_env_change": "medium",
"fixed_ip": false
}