redgate evals: key element 1 on the queue-health verifier, not any fa…

d49269c

Select commit

Loading

Failed to load commit list.

Uh oh!

There was an error while loading. Please reload this page.

Socket Security

Socket Security: Project Report

Socket Security: Pull Request Alerts

evals on: pull_request 72

cheap tier (deterministic, offline)

counterfeit tier — detect

install tier — detect plugins

confirm grader model resolves

confirm subject model resolves (advisory)

behavioral tier — detect paid packs

routing tier (roster trigger routing)

paid multi-plugin gate

deep tier — detect safety-path changes

counterfeit tier — run (corpus)

install tier — install-smoke + evals (graveyard)

install tier — install-smoke + evals (orchestrate)

install tier — install-smoke + evals (plugin-factory)

install tier — install-smoke + evals (tailscale-wif)

install tier — install-smoke + evals (fleet-playbook-curator)

install tier — install-smoke + evals (dev-diary)

install tier — install-smoke + evals (voice)

install tier — install-smoke + evals (grill-me)

install tier — install-smoke + evals (tracer-bullets)

install tier — install-smoke + evals (semver-gate)

install tier — install-smoke + evals (verify-before-claim)

install tier — install-smoke + evals (diagnosing-bugs)

install tier — install-smoke + evals (docs-hygiene)

install tier — install-smoke + evals (context-handoff)

install tier — install-smoke + evals (codebase-design)

install tier — install-smoke + evals (wayfinder)

install tier — install-smoke + evals (prove-the-undo)

install tier — install-smoke + evals (scope-fence)

install tier — install-smoke + evals (find-before-build)

install tier — install-smoke + evals (egress-gate)

install tier — install-smoke + evals (stop-rule)

install tier — install-smoke + evals (redgate)

install tier — install-smoke + evals (recurrence-detector)

install tier — install-smoke + evals (agent-compiler)

install tier — install-smoke + evals (eval-ladder)

behavioral tier — promptfoo (${{ matrix.plugin }})

deep tier — pier run (${{ matrix.plugin }})

counterfeit tier

install tier (marketplace install-smoke + per-plugin evals)

behavioral tier (promptfoo)

deep tier (pier)

scale on: pull_request 4

agent-compiler scale (kernel stress)

redgate scale (lifecycle stress)

Select a check to view from the sidebar