agent-harness / tasks /validation /study2 /TASK_S2_R003_019.json
cuber12's picture
Publish agent harness research code and paper artifacts
d61821a verified
Raw
History Blame Contribute Delete
5.05 kB
{
"commit": "c5d0404ac9edfbfd328e7b4f07f554366377df3f",
"parent": "c23e6bd5785205f0f4b4c80321153658fc23fb98",
"repository_id": "R003",
"schema_version": 1,
"task_id": "TASK_S2_R003_019",
"valid_end_to_end": true,
"validation": {
"commands": [
"python -m pytest -q tests/unit/objects"
],
"elapsed_seconds": 1.4226869160775095,
"gold": [
{
"command": "python -m pytest -q tests/unit/objects",
"elapsed_seconds": 0.40396074997261167,
"returncode": 0,
"stderr": "",
"stdout": "...............................................................s..s..... [ 22%]\n........................................................................ [ 45%]\n.......................................................s................ [ 68%]\n........................................................................ [ 90%]\n............................. [100%]\n314 passed, 3 skipped in 0.23s\n",
"timed_out": false
}
],
"hidden": [
{
"command": "python -m pytest -q tests/unit/objects",
"elapsed_seconds": 0.42500008293427527,
"returncode": 1,
"stderr": "",
"stdout": "...............................................................s..s..... [ 22%]\n..............................................F......................... [ 45%]\n.......................................................s................ [ 68%]\n........................................................................ [ 90%]\n............................. [100%]\n=================================== FAILURES ===================================\n____________________________ test_list_project_job _____________________________\n\nproject = <Project id:1>\nresp_list_job = <responses.RequestsMock object at 0x113086610>\n\n def test_list_project_job(project, resp_list_job):\n failed_jobs = project.jobs.list(scope=\"failed\")\n success_jobs = project.jobs.list(scope=\"success\")\n failed_and_success_jobs = project.jobs.list(scope=[\"failed\", \"success\"])\n pipeline_lazy = project.pipelines.get(1, lazy=True)\n pjobs_failed = pipeline_lazy.jobs.list(scope=\"failed\")\n pjobs_success = pipeline_lazy.jobs.list(scope=\"success\")\n pjobs_failed_and_success = pipeline_lazy.jobs.list(scope=[\"failed\", \"success\"])\n \n prepared_urls = [c.request.url for c in resp_list_job.calls]\n \n # Both pipelines and pipelines/jobs should behave the same way\n # When `scope` is scalar, one can use scope=value or scope[]=value\n assert set(failed_and_success_jobs) == set(failed_jobs + success_jobs)\n assert set(pjobs_failed_and_success) == set(pjobs_failed + pjobs_success)\n> assert prepared_urls == [\n \"http://localhost/api/v4/projects/1/jobs?scope%5B%5D=failed\",\n \"http://localhost/api/v4/projects/1/jobs?scope%5B%5D=success\",\n \"http://localhost/api/v4/projects/1/jobs?scope%5B%5D=failed&scope%5B%5D=success\",\n \"http://localhost/api/v4/projects/1/pipelines/1/jobs?scope%5B%5D=failed\",\n \"http://localhost/api/v4/projects/1/pipelines/1/jobs?scope%5B%5D=success\",\n \"http://localhost/api/v4/projects/1/pipelines/1/jobs?scope%5B%5D=failed&scope%5B%5D=success\",\n ]\nE AssertionError: assert ['http://loca...cope=success'] == ['http://loca...B%5D=success']\nE \nE At index 3 diff: 'http://localhost/api/v4/projects/1/pipelines/1/jobs?scope=failed' != 'http://localhost/api/v4/projects/1/pipelines/1/jobs?scope%5B%5D=failed'\nE Use -v to get more diff\n\ntests/unit/objects/test_jobs.py:163: AssertionError\n=========================== short test summary info ============================\nFAILED tests/unit/objects/test_jobs.py::test_list_project_job - AssertionErro...\n1 failed, 313 passed, 3 skipped in 0.25s\n",
"timed_out": false
}
],
"hidden_apply": {
"elapsed_seconds": 0.009690249804407358,
"returncode": 0,
"stderr": "",
"stdout": ""
},
"original": [
{
"command": "python -m pytest -q tests/unit/objects",
"elapsed_seconds": 0.5325255000498146,
"returncode": 0,
"stderr": "",
"stdout": "...............................................................s..s..... [ 22%]\n........................................................................ [ 45%]\n......................................................s................. [ 68%]\n........................................................................ [ 91%]\n............................ [100%]\n313 passed, 3 skipped in 0.35s\n",
"timed_out": false
}
],
"reason": null,
"source_apply": {
"elapsed_seconds": 0.009085542056709528,
"returncode": 0,
"stderr": "",
"stdout": ""
},
"valid": true
}
}