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

212
evaluation_examples/examples/chrome/47543840-672a-467d-80df-8f7c3b9788c9.json
View File

@@ -1,111 +1,117 @@
{
"id": "47543840-672a-467d-80df-8f7c3b9788c9",
"snapshot": "chrome",
"instruction": "Find and select the car with the most number of seats to pick up in Boston Logan Intl Airport from 10th next month to 11th next month.",
"source": "test_task_1",
"config": [
"id": "47543840-672a-467d-80df-8f7c3b9788c9",
"snapshot": "chrome",
"instruction": "Find and select the car with the most number of seats to pick up in Boston Logan Intl Airport from 10th next month to 11th next 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.budget.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_url_from_accessTree",
"goto_prefix": "https://www."
},
{
"type": "active_tab_html_parse",
"goto_prefix": "https://www.",
"category": "class",
"class_singleObject": {},
"class_multiObject": {
"location-info": {
"0": "start_location",
"1": "end_location"
},
"day-time-info": {
"0": "from",
"1": "to"
}
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"https://www.budget.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
"type": "active_tab_html_parse",
"goto_prefix": "https://www.",
"category": "xpath",
"xpathObject": {
"/html/body/div[6]/div[2]/div[1]/div/div/div[2]/div[1]/section[1]/div/form/div[1]/div[2]/div/a": "rank"
}
}
],
"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_url_from_accessTree",
"goto_prefix": "https://www."
},
{
"type": "active_tab_html_parse",
"goto_prefix": "https://www.",
"category": "class",
"class_singleObject":{},
"class_multiObject":{
"location-info":{
"0": "start_location",
"1": "end_location"
},
"day-time-info":{
"0": "from",
"1": "to"
}
}
},
{
"type": "active_tab_html_parse",
"goto_prefix": "https://www.",
"category": "xpath",
"xpathObject":{
"/html/body/div[6]/div[2]/div[1]/div/div/div[2]/div[1]/section[1]/div/form/div[1]/div[2]/div/a": "rank"
}
}
],
"expected":[
{
"type": "rule",
"rules":{
"expected": ["reservation#\/vehicles"]
}
},
{
"type": "rule_relativeTime",
"rules":{
"relativeTime":{
"from":"10th next month",
"to": "11th next month"
},
"expected": {
"start_location": "Boston Logan Intl Airport,\n\t\t\t\t\t\t\t\tBOS \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t Pick-Up",
"end_location": "Boston Logan Intl Airport,\n\t\t\t\t\t\t\t\tBOS",
"from": "{DoW}, {Month} {Day0D}, 12:00 PM",
"to": "{DoW}, {Month} {Day0D}, 12:00 PM"
}
}
},
{
"type": "rule",
"rules":{
"expected": {
"rank": "Number of Seats (High to Low)"
}
}
}
]
}
}
"expected": [
{
"type": "rule",
"rules": {
"expected": [
"reservation#/vehicles"
]
}
},
{
"type": "rule_relativeTime",
"rules": {
"relativeTime": {
"from": "10th next month",
"to": "11th next month"
},
"expected": {
"start_location": "Boston Logan Intl Airport,\n\t\t\t\t\t\t\t\tBOS \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t \n\t\t\t\t\t\t\t Pick-Up",
"end_location": "Boston Logan Intl Airport,\n\t\t\t\t\t\t\t\tBOS",
"from": "{DoW}, {Month} {Day0D}, 12:00 PM",
"to": "{DoW}, {Month} {Day0D}, 12:00 PM"
}
}
},
{
"type": "rule",
"rules": {
"expected": {
"rank": "Number of Seats (High to Low)"
}
}
}
]
},
"proxy": true
}