small real gauntlet
SOLARI LIVEReference Agent · Complete Demo Checkout · run f90af6b · 3d ago
This suite did not finish
Solari is at its concurrent-session limit. Lower GAUNTLET_MAX_CONCURRENCY or upgrade the plan.
Error code: solari_concurrency
Reliability
—0 / 0 runs passed
- Baseline
- —
- Perturbed
- —
Runs
4
0 scored
Failed
0
no infra errors
p95 duration
0ms
p50 0ms
Avg steps
—
avg 0ms
Run-to-run flips
0%
how often identical repetitions disagreed
Reliability by perturbation
Worst first. The whisker is the 95% Wilson interval — small samples are wide on purpose.
No scored runs yet.
Reliability by category
No scored runs yet.
Failure distribution
Only scored failures. Infrastructure errors are excluded.
No failures to categorise.
Run matrix
Every cell is one run. Select one to open its evidence.
| Perturbation | Run 1 | Rate |
|---|---|---|
| Baseline | Baseline, run 1: Cancelled | — |
| Cookie popup | Cookie popup, run 1: Cancelled | — |
| Expired session | Expired session, run 1: Cancelled | — |
| Unexpected modal | Unexpected modal, run 1: Cancelled | — |
Individual failures
Open one to see the assertion that failed and the trace that led there.
No failures in this run.
Every scored run satisfied the task's assertions.