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

147
evaluation_examples/examples/chrome/9f3f70fc-5afc-4958-a7b7-3bb4fcb01805.json
View File

@@ -1,78 +1,83 @@
{
"id": "9f3f70fc-5afc-4958-a7b7-3bb4fcb01805",
"snapshot": "chrome",
"instruction": "Browse the list of women's Nike jerseys over $60.",
"source": "test_task_1",
"config": [
"id": "9f3f70fc-5afc-4958-a7b7-3bb4fcb01805",
"snapshot": "chrome",
"instruction": "Browse the list of women's Nike jerseys over $60.",
"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.nba.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": [
"is_expected_url_pattern_match",
"check_direct_json_object"
],
"conj": "and",
"result": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
"type": "active_tab_info"
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.nba.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
"type": "active_tab_html_parse",
"category": "xpath",
"xpathObject": {
"/html/body/div[2]/div/div[6]/div[2]/div[2]/div/div[1]/div[4]/ul/li[2]": "money"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":["is_expected_url_pattern_match", "check_direct_json_object"],
"conj": "and",
"result": [
{
"type": "active_tab_info"
},
{
"type": "active_tab_html_parse",
"category": "xpath",
"xpathObject":{
"/html/body/div[2]/div/div[6]/div[2]/div[2]/div/div[1]/div[4]/ul/li[2]": "money"
}
}
],
"expected":[
{
"type": "rule",
"rules":{
"expected": ["\/women-jerseys\/"]
}
},
{
"type": "rule",
"rules":{
"expected": {
"money": "over $60"
}
}
}
]
}
}
"expected": [
{
"type": "rule",
"rules": {
"expected": [
"/women-jerseys/"
]
}
},
{
"type": "rule",
"rules": {
"expected": {
"money": "over $60"
}
}
}
]
},
"proxy": true
}