Skip to main content
A run’s execution status and its eval verdict answer different questions. Succeeded means the session finished successfully; it does not necessarily mean it passed every criterion. Judging and analytics can finish after execution.

​
Read the status

Failed or timed-out runs receive a run-credit refund. A successfully executed session that fails an eval criterion does not count as an execution failure. See Billing and credits for how charges are calculated.

​
Inspect a run

Replace <run-id> with the ID from the run list:
logs returns events available so far. A research task may make no repository changes, so an empty diff alone is not a failure. If a run has finished but its insight or verdict is pending, allow the analysis to complete. Pending or failed judging does not enter the eval pass-rate denominator. Check the judged-run count as well as the percentage.

​
When no runs are created

  1. Check the organization with gauge status.
  2. Inspect the eval with gauge evals get <eval-id> and its attached scenarios with gauge evals scenarios list <eval-id>.
  3. Check gauge billing status for balance and workload eligibility.
  4. If a provider key is required, resolve that connection before trying again. See Configure a scenario.
An eval without scenarios will not produce recurring runs. A one-off scenario can be supplied for a manual run, as shown in the quickstart.

​
Retry deliberately

Read the original run’s status before launching a replacement, especially after a network timeout. A new launch can create additional billable work. Fix the cause first, then rerun the same task and criteria to make the comparison useful. For persistent failures, contact [email protected] with the organization, run/eval link, status, and visible error. Do not include provider keys or credentials.