Text
117case executions across 13 routes
Track ledger →Live run / evidence state
The provider work finished on 3 August 2026. Two operators reviewed all retained artifacts. 161 cases approved, 2 technical failures quarantined. Raw evidence is public.
v03-live-2026-08-03T14-30-26-901Zcase executions across 13 routes
Track ledger →case executions across 3 routes
Track ledger →case executions across 1 route
Track ledger →case executions across 1 route
Track ledger →Run timeline
The catalog is frozen per version — a new suite release becomes the next run, never an edit in place. Older versions stay comparable in the archive.
Next run: the v0.4 catalog is a data drop-in — new rows appear here when a run registers, no page rewrite.
Route ledger
Outcomes published. Raw artifacts available.
Failure ledger
UT6Upstream shared-pool rate limit. Isolated retry reproduced the failure; publication gate rejects the evidence.
UV4Provider retrieval error. Isolated retry reproduced the failure; publication gate rejects the evidence.
Reproduce this run
Run v03-live-2026-08-03T14-30-26-901Z completed 2026-08-03T15:23:56.836Z. Cap $30.00. Catalog 0.3.0 / 33 frozen cases / 163 executions across 18 models, 2 quarantined failures kept as failures.