safeintelligence/Run Spec27 Eval

Start a Spec27 eval run, poll until it finishes, and write the final result JSON.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
base_urlBase URL for the Spec27 deployment.nohttps://dashboard.spec27.ai
tokenProject-scoped Spec27 API token.yes
eval_idID of the eval to run.yes
poll_interval_secondsSeconds to wait between status polls.no10
timeout_secondsMaximum seconds to wait for the eval run to reach a terminal status.no1800
results_pathPath to write the detailed eval-run JSON results file. Defaults to a unique file in the runner temp directory so the workspace stays clean.no""
namedescription
eval_run_idID of the created eval run.
statusFinal eval-run status.
clean_accuracyClean accuracy from the final eval-run response, when present.
robust_accuracyRobust accuracy from the final eval-run response, when present.
result_urlURL for the eval-run result in Spec27, when present.
summary_jsonCompact eval-run summary as a JSON string, when present.
results_fileAbsolute path to the detailed eval-run JSON results file written by the action.