Files
sci-gui-agent-benchmark/evaluation_examples/examples/chrome/f79439ad-3ee8-4f99-a518-0eb60e5652b0.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

84 lines
1.8 KiB
JSON

{
"id": "f79439ad-3ee8-4f99-a518-0eb60e5652b0",
"snapshot": "chrome",
"instruction": "Search for a one way flight from Dublin to Vienna on 10th next month for 2 adults.",
"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.ryanair.com/gb/en"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "check_direct_json_object",
"result": {
"type": "active_tab_url_parse",
"goto_prefix": "https://www.",
"parse_keys": [
"originIata",
"destinationIata",
"tpAdults",
"tpTeens",
"tpChildren",
"tpStartDate",
"isReturn"
],
"replace": {
"tpStartDate": "time"
}
},
"expected": {
"type": "rule_relativeTime",
"rules": {
"relativeTime": {
"from": "10th next month"
},
"expected": {
"originIata": "DUB",
"destinationIata": "VIE",
"tpAdults": "2",
"tpTeens": "0",
"tpChildren": "0",
"time": "{Year}-{Month0D}-{DayD}",
"isReturn": "false"
}
}
}
},
"proxy": true,
"fixed_ip": false,
"possibility_of_env_change": "low"
}