trace_synthesis/tasks/755.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

45 lines
1.5 KiB
JSON

{
"sites": [
"gitlab"
],
"task_id": 755,
"require_login": true,
"storage_state": "./.auth/gitlab_state.json",
"start_url": "http://localhost:28084",
"geolocation": null,
"intent_template": "Create a private {{template}} repository called \"{{project_name}}\" using the right template to speed up development.",
"instantiation_dict": {
"project_name": "web_agent_index",
"template": "HTML"
},
"intent": "Create a private HTML repository called \"web_agent_index\" using the right template to speed up development.",
"require_reset": false,
"eval": {
"eval_types": [
"program_html"
],
"reference_answers": null,
"reference_url": "",
"program_html": [
{
"url": "http://localhost:28084/byteblaze/web_agent_index",
"locator": "document.querySelector('.visibility-icon').getAttribute('title')",
"required_contents": {
"must_include": [
"Private"
]
}
},
{
"url": "http://localhost:28084/byteblaze/web_agent_index",
"locator": "document.querySelector('.home-panel-description-markdown').outerText",
"required_contents": {
"must_include": [
"Example plain HTML site using GitLab Pages: https://pages.gitlab.io/plain-html |OR| A plain HTML site that uses Netlify for CI/CD instead of GitLab, but still with all the other great GitLab features."
]
}
}
]
},
"intent_template_id": 332
}