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

134
evaluation_examples/examples/chrome/c1fa57f3-c3db-4596-8f09-020701085416.json
View File

@@ -1,69 +1,71 @@
{
"id": "c1fa57f3-c3db-4596-8f09-020701085416",
"snapshot": "chrome",
"instruction": "Open the baggage fee calculator.",
"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"
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('alt', 'f10'); time.sleep(0.5);"
]
}
"id": "c1fa57f3-c3db-4596-8f09-020701085416",
"snapshot": "chrome",
"instruction": "Open the baggage fee calculator.",
"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"
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('alt', 'f10'); time.sleep(0.5);"
]
}
],
"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": ["checked-bag-fee-calculator"]
}
}
}
}
],
"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": [
"checked-bag-fee-calculator"
]
}
}
},
"proxy": true
}