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

127
evaluation_examples/examples/chrome/82279c77-8fc6-46f6-9622-3ba96f61b477.json
View File

@@ -1,65 +1,70 @@
{
"id": "82279c77-8fc6-46f6-9622-3ba96f61b477",
"snapshot": "chrome",
"instruction": "Find electric cars with a maximum price of $50,000 within 50 miles of 10001.",
"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.cars.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
"id": "82279c77-8fc6-46f6-9622-3ba96f61b477",
"snapshot": "chrome",
"instruction": "Find electric cars with a maximum price of $50,000 within 50 miles of 10001.",
"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.cars.com/"
]
}
},
{
"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": [
"list_price_max",
"maximum_distance",
"zip",
"fuel_slugs[]"
]
},
"expected": {
"type": "rule",
"rules": {
"expected": {
"list_price_max": "50000",
"maximum_distance": "50",
"zip": "10001",
"fuel_slugs[]": "electric"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"check_direct_json_object",
"result": {
"type": "active_tab_url_parse",
"goto_prefix": "https://www.",
"parse_keys": ["list_price_max", "maximum_distance", "zip","fuel_slugs[]"]
},
"expected":{
"type": "rule",
"rules":{
"expected": {
"list_price_max": "50000",
"maximum_distance": "50",
"zip":"10001",
"fuel_slugs[]":"electric"
}
}
}
}
}
},
"proxy": true
}