trace_synthesis/tasks/748.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

57 lines
1.6 KiB
JSON

{
"sites": [
"gitlab"
],
"task_id": 748,
"require_login": true,
"storage_state": "./.auth/gitlab_state.json",
"start_url": "http://localhost:28084",
"geolocation": null,
"intent_template": "Start a private project {{project_name}} with {{template}} template and add {{account_list}} as members",
"instantiation_dict": {
"project_name": "web_agent_android_xl",
"template": "Android",
"account_list": "primer, convexegg, abishek"
},
"intent": "Start a private project web_agent_android_xl with Android template and add primer, convexegg, abishek as members",
"require_reset": false,
"eval": {
"eval_types": [
"program_html"
],
"reference_answers": null,
"reference_url": "",
"program_html": [
{
"url": "http://localhost:28084/byteblaze/web_agent_android_xl",
"locator": "document.querySelector('.visibility-icon').getAttribute('title')",
"required_contents": {
"must_include": [
"Private"
]
}
},
{
"url": "http://localhost:28084/byteblaze/web_agent_android_xl/-/commits",
"locator": "",
"required_contents": {
"must_include": [
"Initialized from 'Android' project template"
]
}
},
{
"url": "http://localhost:28084/byteblaze/web_agent_android_xl/-/project_members",
"locator": "",
"required_contents": {
"must_include": [
"@primer",
"@convexegg",
"@abisubramanya27"
]
}
}
]
},
"intent_template_id": 2100
}