Files
sci-gui-agent-benchmark/evaluation_examples/examples/chrome/7f52cab9-535c-4835-ac8c-391ee64dc930.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

96 lines
1.9 KiB
JSON

{
"id": "7f52cab9-535c-4835-ac8c-391ee64dc930",
"snapshot": "chrome",
"instruction": "Create a list of drip coffee makers that are on sale and within $25-60 and have a black finish.",
"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://shopping.google.com/"
]
}
},
{
"type": "activate_window",
"parameters": {
"window_name": "Google Chrome"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": [
"check_direct_json_object",
"check_direct_json_object"
],
"result": [
{
"type": "active_tab_url_parse",
"goto_prefix": "https://www.",
"parse_keys": [
"q"
]
},
{
"type": "active_tab_html_parse",
"goto_prefix": "https://www.",
"category": "class",
"class_multiObject_search_exist": {
"fT28tf":[
"Black",
"$25 - $60",
"On sale",
"is_other_exist"
]
}
}
],
"expected": [
{
"type": "rule",
"rules": {
"expected": {
"q": "drip coffee maker"
},
"expect_in_result": true
}
},
{
"type": "rule",
"rules": {
"expected": {
"Black": true,
"$25 - $60": true,
"On sale": true,
"is_other_exist": false
}
}
}
]
},
"proxy": true
}