Retry pre-response transport failures across candidates with an explicit stop policy, and propagate end-to-end timing into usage records and UI diagnostics.
Remove legacy body, import, cookie, PII, and tunnel replay caps while preserving optional operator-configured gateway limits.
Refresh the resolved user role without bypassing owner group and key policies. Resolve Rust 1.95 Clippy failures and make the pending persistence bound test scheduler-independent.
Shard and singleflight hot-path caches, batch and prioritize candidate and usage lifecycle persistence, and extend database and pressure-test instrumentation for 20k concurrent streams.
Add end-to-end terminal admission, bounded database fallback, and observable overload handling. Preserve first-byte lifecycle state across asynchronous runtime and frontend updates.