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

153
evaluation_examples/examples/chrome/368d9ba4-203c-40c1-9fa3-da2f1430ce63.json
View File

@@ -1,78 +1,87 @@
{
"id": "368d9ba4-203c-40c1-9fa3-da2f1430ce63",
"snapshot": "chrome",
"instruction": "find the Monthly forecast for Manchester, GB for this month",
"source": "test_task_1",
"config": [
"id": "368d9ba4-203c-40c1-9fa3-da2f1430ce63",
"snapshot": "chrome",
"instruction": "find the Monthly forecast for Manchester, GB for this month",
"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.accuweather.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": [
"check_direct_json_object",
"is_expected_url_pattern_match"
],
"result": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
"type": "url_dashPart",
"goto_prefix": "https://www.",
"partIndex": -2,
"needDeleteId": false,
"returnType": "json",
"key": "time"
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.accuweather.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
"type": "active_url_from_accessTree",
"goto_prefix": "https://www."
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":["check_direct_json_object", "is_expected_url_pattern_match"],
"result": [{
"type": "url_dashPart",
"goto_prefix": "https://www.",
"partIndex": -2,
"needDeleteId": false,
"returnType": "json",
"key":"time"
},
{
"type": "active_url_from_accessTree",
"goto_prefix": "https://www."
}],
"expected":[
{
"type": "rule_relativeTime",
"rules":{
"relativeTime": {
"from": "this month"
},
"expected": {
"time": "{month}-weather"
}
}
},
{
"type": "rule",
"rules":{
"expected": ["\/manchester\/"]
}
}]
}
}
"expected": [
{
"type": "rule_relativeTime",
"rules": {
"relativeTime": {
"from": "this month"
},
"expected": {
"time": "{month}-weather"
}
}
},
{
"type": "rule",
"rules": {
"expected": [
"/manchester/"
]
}
}
]
},
"proxy": true
}