lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Add proxy configuration to all 369 evaluation examples - 55 with proxy, 314 without

Browse Source
This commit is contained in:
Timothyxxx
2025-06-05 18:46:53 +08:00
parent 3b1540ed23
commit fb7bafb885
371 changed files with 2901 additions and 2028 deletions
Download Patch File Download Diff File Expand all files Collapse all files

142
evaluation_examples/examples/chrome/6c4c23a1-42a4-43cc-9db1-2f86ff3738cc.json
View File

@@ -1,78 +1,78 @@
{
"id": "6c4c23a1-42a4-43cc-9db1-2f86ff3738cc",
"snapshot": "chrome",
"instruction": "Find flights from Seattle to New York on 5th next month and only show those that can be purchased with miles.",
"source": "test_task_1",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
"id": "6c4c23a1-42a4-43cc-9db1-2f86ff3738cc",
"snapshot": "chrome",
"instruction": "Find flights from Seattle to New York on 5th next month and only show those that can be purchased with miles.",
"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.delta.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "check_direct_json_object",
"result": {
"type": "active_tab_html_parse",
"goto_prefix": "https://www.",
"category": "class",
"class_singleObject": {
"search-date": "time",
"price-in-tabs__nav--selected": "category"
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.delta.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
"class_multiObject": {
"search-segment-cities__city": {
"0": "start",
"1": "end"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"check_direct_json_object",
"result": {
"type": "active_tab_html_parse",
"goto_prefix": "https://www.",
"category": "class",
"class_singleObject":{
"search-date": "time",
"price-in-tabs__nav--selected": "category"
},
"class_multiObject":{
"search-segment-cities__city": {
"0": "start",
"1": "end"
}
}
},
"expected": {
"type": "rule_relativeTime",
"rules": {
"relativeTime": {
"from": "5th next month"
},
"expected":{
"type": "rule_relativeTime",
"rules":{
"relativeTime": {
"from": "5th next month"
},
"expected": {
"start": "SEA",
"end": "NYC",
"time": "{DoW}, {Month} {DayD}, {Year}",
"category": "Miles"
}
}
"expected": {
"start": "SEA",
"end": "NYC",
"time": "{DoW}, {Month} {DayD}, {Year}",
"category": "Miles"
}
}
}
}
},
"proxy": true
}