Files
sci-gui-agent-benchmark/evaluation_examples/examples/chrome/f5d96daf-83a8-4c86-9686-bada31fc66ab.json
yuanmengqi 9be6fcd688 Check and fix on Chrome tasks
- Added `pytz` dependency to `requirements.txt` for timezone handling.
- Introduced `get_macys_product_url_parse` function to replace the old `get_url_path_parse` for better clarity and maintain backward compatibility.
- Enhanced logging throughout the `get_active_tab_html_parse` and `get_rule_relativeTime` functions for improved debugging and traceability.
- Updated JSON examples to reflect changes in expected keys and added new fields for better evaluation context.
- Removed deprecated execution commands from JSON examples to streamline the evaluation process.
2025-07-06 07:52:37 +00:00

71 lines
1.4 KiB
JSON

{
"id": "f5d96daf-83a8-4c86-9686-bada31fc66ab",
"snapshot": "chrome",
"instruction": "Compare iPhone 15 Pro Max with iPhone 14 Pro Max and iPhone 13 Pro Max",
"source": "Mind2Web",
"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.apple.com/"
]
}
},
{
"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": [
"modelList"
],
"split_list": true
},
"expected": {
"type": "rule",
"rules": {
"expected": {
"modelList": [
"iphone-15-pro-max",
"iphone-14-pro-max",
"iphone-13-pro-max"
]
},
"ignore_list_order": true
}
}
},
"proxy": true,
"possibility_of_env_change": "medium"
}