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

195
evaluation_examples/examples/chrome/da46d875-6b82-4681-9284-653b0c7ae241.json
View File

@@ -1,102 +1,109 @@
{
"id": "da46d875-6b82-4681-9284-653b0c7ae241",
"snapshot": "chrome",
"instruction": "Schedule an appointment to apply for transportation access pass in the Charlie Card store on the first Monday four months later, 10:15 am, fill in my details (James Smith, james.smith@gmail.com). And don not click \"book\" directly. Let me review it.",
"source": "test_task_2",
"config": [
"id": "da46d875-6b82-4681-9284-653b0c7ae241",
"snapshot": "chrome",
"instruction": "Schedule an appointment to apply for transportation access pass in the Charlie Card store on the first Monday four months later, 10:15 am, fill in my details (James Smith, james.smith@gmail.com). And don not click \"book\" directly. Let me review it.",
"source": "test_task_2",
"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.mbta.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",
"check_direct_json_object"
],
"conj": "and",
"result": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
"type": "active_tab_info"
},
{
"type": "active_tab_html_parse",
"category": "class",
"class_singleObject": {},
"class_multiObject": {
"breakword": {
"1": "content",
"2": "time"
}
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.mbta.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
"type": "active_tab_html_parse",
"category": "input",
"inputObject": {
"/html/body/div/div/form/div[7]/div/div/div[1]/input[1]": "name",
"/html/body/div/div/form/div[7]/div/div/div[1]/input[2]": "mail"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":["is_expected_url_pattern_match", "check_direct_json_object", "check_direct_json_object"],
"conj": "and",
"result": [
{
"type": "active_tab_info"
},
{
"type": "active_tab_html_parse",
"category": "class",
"class_singleObject":{},
"class_multiObject":{
"breakword":{
"1": "content",
"2": "time"
}
}
},
{
"type": "active_tab_html_parse",
"category": "input",
"inputObject":{
"/html/body/div/div/form/div[7]/div/div/div[1]/input[1]": "name",
"/html/body/div/div/form/div[7]/div/div/div[1]/input[2]": "mail"
}
}
],
"expected":[
{
"type": "rule",
"rules":{
"expected": ["CharlieCardStoreAppointments@mbta.com\/bookings\/"]
}
},
{
"type": "rule_relativeTime",
"rules":{
"relativeTime":{
"from":"first monday four months later"
},
"expected": {
"content": "Apply for Transportation Access Pass (TAP) CharlieCard non-auto approval",
"time": "{MonthFull} {Day0D}, 10:15 am"
}
}
},
{
"type": "rule",
"rules":{
"expected": {
"name": "James Smith",
"mail": "james.smith@gmail.com"
}
}
}
]
}
}
"expected": [
{
"type": "rule",
"rules": {
"expected": [
"CharlieCardStoreAppointments@mbta.com/bookings/"
]
}
},
{
"type": "rule_relativeTime",
"rules": {
"relativeTime": {
"from": "first monday four months later"
},
"expected": {
"content": "Apply for Transportation Access Pass (TAP) CharlieCard non-auto approval",
"time": "{MonthFull} {Day0D}, 10:15 am"
}
}
},
{
"type": "rule",
"rules": {
"expected": {
"name": "James Smith",
"mail": "james.smith@gmail.com"
}
}
}
]
},
"proxy": true
}