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

119
evaluation_examples/examples/chrome/2888b4e6-5b47-4b57-8bf5-c73827890774.json
View File

@@ -1,63 +1,62 @@
{
"id": "2888b4e6-5b47-4b57-8bf5-c73827890774",
"snapshot": "chrome",
"instruction": "Find a men's T-Shirt that is in large size with a stripe pattern, short sleeve and under the Sales&Discount.",
"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.macys.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
"id": "2888b4e6-5b47-4b57-8bf5-c73827890774",
"snapshot": "chrome",
"instruction": "Find a men's T-Shirt that is in large size with a stripe pattern, short sleeve and under the Sales&Discount.",
"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.macys.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"exact_match",
"result": {
"type": "url_dashPart",
"goto_prefix": "https://www.",
"partIndex": -1,
"needDeleteId": true,
"returnType": "string"
},
"expected":{
"type": "rule",
"rules":{
"expected": "Stripe,Men,L,Short%20Sleeve,Sales%20%26%20Discounts"
}
}
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "exact_match",
"result": {
"type": "url_dashPart",
"goto_prefix": "https://www.",
"partIndex": -1,
"needDeleteId": true,
"returnType": "string"
},
"expected": {
"type": "rule",
"rules": {
"expected": "Stripe,Men,L,Short%20Sleeve,Sales%20%26%20Discounts"
}
}
},
"proxy": true
}