Every ticket as the root of its provenance graph — goal, patch, approval, runs and (as the ticket-class build lands) mandate, manifestations, guarantees, journey, artifacts and children. Rendered through the <<<TicketGraphList>>> tag.
Test: standing structured-output reliability harness (Gemma/Qwen tool-calling) in CI
goal
A standing harness measuring local-model structured-output/tool-call reliability on our schemas over N trials, FAILING below the R4 threshold. Rides the dispatch schedule so model/prompt regressions surface as tickets, not silent pair failures. Gated on B1.
patch
none
approval
unapproved
runs
no runs recorded
mandate (clauses)
not yet recorded — lands with the ticket-class build
manifestations
not yet recorded — lands with the ticket-class build
guarantees
not yet recorded — lands with the ticket-class build
journey (blunders & successes)
not yet recorded — lands with the ticket-class build
artifacts (forge)
not yet recorded — lands with the ticket-class build