trace_synthesis/tasks/769.json
yuyr a84d51a101 1. 增加r1生成综合策略代码和输出;
2. 增加tasks;
3. 增加analysis部分,对策略进行归纳分类,然后进行评测。
2025-04-17 17:40:15 +08:00

62 lines
2.0 KiB
JSON

{
"sites": [
"shopping_admin"
],
"task_id": 769,
"require_login": true,
"storage_state": "./.auth/shopping_admin_state.json",
"start_url": "http://localhost:28083/admin",
"geolocation": null,
"intent_template": "We've received {{quantity}} {{product}}, please update the inventory.",
"instantiation_dict": {
"quantity": "378",
"product": "brown Aero daily fitness tee in every size"
},
"intent": "We've received 378 brown Aero daily fitness tee in every size, please update the inventory.",
"require_reset": false,
"eval": {
"eval_types": [
"program_html"
],
"reference_answers": null,
"reference_url": "",
"program_html": [
{
"url": "http://localhost:28083/admin/catalog/product/edit/id/544/",
"locator": "document.querySelector('[name=\"product[quantity_and_stock_status][qty]\"').value",
"required_contents": {
"exact_match": "478"
}
},
{
"url": "http://localhost:28083/admin/catalog/product/edit/id/547/",
"locator": "document.querySelector('[name=\"product[quantity_and_stock_status][qty]\"').value",
"required_contents": {
"exact_match": "478"
}
},
{
"url": "http://localhost:28083/admin/catalog/product/edit/id/550/",
"locator": "document.querySelector('[name=\"product[quantity_and_stock_status][qty]\"').value",
"required_contents": {
"exact_match": "478"
}
},
{
"url": "http://localhost:28083/admin/catalog/product/edit/id/553/",
"locator": "document.querySelector('[name=\"product[quantity_and_stock_status][qty]\"').value",
"required_contents": {
"exact_match": "478"
}
},
{
"url": "http://localhost:28083/admin/catalog/product/edit/id/556/",
"locator": "document.querySelector('[name=\"product[quantity_and_stock_status][qty]\"').value",
"required_contents": {
"exact_match": "478"
}
}
]
},
"intent_template_id": 241
}