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

148
evaluation_examples/examples/chrome/f79439ad-3ee8-4f99-a518-0eb60e5652b0.json
View File

@@ -1,74 +1,82 @@
{
"id": "f79439ad-3ee8-4f99-a518-0eb60e5652b0",
"snapshot": "chrome",
"instruction": "Search for a one way flight from Dublin to Vienna on 10th next month for 2 adults.",
"source": "test_task_2",
"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.ryanair.com/gb/en"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
"id": "f79439ad-3ee8-4f99-a518-0eb60e5652b0",
"snapshot": "chrome",
"instruction": "Search for a one way flight from Dublin to Vienna on 10th next month for 2 adults.",
"source": "test_task_2",
"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.ryanair.com/gb/en"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "check_direct_json_object",
"result": {
"type": "active_tab_url_parse",
"goto_prefix": "https://www.",
"parse_keys": [
"originIata",
"destinationIata",
"tpAdults",
"tpTeens",
"tpChildren",
"tpStartDate",
"isReturn"
],
"replace": {
"tpStartDate": "time"
}
},
"expected": {
"type": "rule_relativeTime",
"rules": {
"relativeTime": {
"from": "10th next month"
},
"expected": {
"originIata": "DUB",
"destinationIata": "VIE",
"tpAdults": "2",
"tpTeens": "0",
"tpChildren": "0",
"time": "{Year}-{Month0D}-{DayD}",
"isReturn": "false"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"check_direct_json_object",
"result": {
"type": "active_tab_url_parse",
"goto_prefix": "https://www.",
"parse_keys":["originIata", "destinationIata", "tpAdults", "tpTeens", "tpChildren", "tpStartDate", "isReturn"],
"replace":{
"tpStartDate": "time"
}
},
"expected":{
"type": "rule_relativeTime",
"rules":{
"relativeTime": {
"from": "10th next month"
},
"expected": {
"originIata": "DUB",
"destinationIata": "VIE",
"tpAdults": "2",
"tpTeens": "0",
"tpChildren": "0",
"time": "{Year}-{Month0D}-{DayD}",
"isReturn":"false"
}
}
}
}
}
},
"proxy": true
}