Files
sci-gui-agent-benchmark/evaluation_examples/examples/chrome/fc6d8143-9452-4171-9459-7f515143419a.json
yuanmengqi e433f35c1f feat: standardize configuration fields across all evaluation examples
- Add `fixed_ip` field to all 369 JSON files in examples directory
  - Set to `true` for 8 files listed in google_chrome.json multi_apps
  - Set to `false` for remaining 361 files
- Add `possibility_of_env_change` field to 363 JSON files missing this field
  - Set to "low" for newly added fields
  - Preserve existing values (4 medium, 2 high) for 6 files that already had this field

This ensures consistent configuration schema across all evaluation examples
while maintaining backward compatibility with existing settings.
2025-07-16 13:45:34 +00:00

78 lines
1.7 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"id": "fc6d8143-9452-4171-9459-7f515143419a",
"snapshot": "chrome",
"instruction": "Find flights from New YorkKennedy Airport to Chicago O'Hare Airport for tomorrow.",
"source": "test_task_0",
"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.delta.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "check_direct_json_object",
"result": {
"type": "active_tab_html_parse",
"goto_prefix": "https://www.",
"category": "class",
"class_singleObject": {
"mach-flight-context-info__wrapper--date": "time"
},
"class_multiObject_child": {
"mach-flight-context-info__wrapper__info--separator": {
"0": "start",
"1": "end"
}
}
},
"expected": {
"type": "rule_relativeTime",
"rules": {
"relativeTime": {
"from": "tomorrow"
},
"expected": {
"start": "JFK",
"end": "ORD",
"time": "{DoW}, {Month} {Day0D}, {Year}"
}
}
}
},
"proxy": false,
"fixed_ip": false,
"possibility_of_env_change": "low"
}