**Outcome-gated context bundles:** immutable candidates now move through matched screening, adaptive confirmation, held-out evaluation, false-promotion control, causal attribution, and atomic activation while rejected evidence remains available for scoped retesting.
**Capability-scoped execution:** generated research code can run in a locked-down Docker workspace, remote scenarios ship as verified content-addressed packages, and trusted-local execution remains an explicit operator choice rather than a fallback.
**Durable campaign operations:** restart-safe scheduling, leases, heartbeats, cancellation, bounded reuse, campaign auditing, and a paid-result outbox make long-running local and remote evaluation inspectable, accountable, and recoverable without duplicate provider execution.
**Correctness-first kernel evolution:** protected workers, fresh confirmation, finite-sample promotion gates, autonomous model-backed campaigns, and three-family transfer studies expose regressions, specialists, plateaus, and generalizing champions without averaging failures away.
**Capability-validated accelerators:** Prime requests bind immutable images, accelerator type/count, region, telemetry, idempotency, and resolved hardware identity; unsupported or drifting configurations fail before paid candidate execution.
**Stronger learning evidence across runtimes:** Python and TypeScript share context-bundle, attribution, and negative-result contracts, while Python training adds replayable adaptive confirmation and minimum-effect promotion artifacts.
