OpenClaw: Gateway Shutdown Hardening and Member Devices
Gateway lifecycle fixes dominate today, stopping expired plugin scopes from crashing shutdown and stranding sessions. OpenClaw ID adds member self-approval for devices, while model picker stability and catalog performance get meaningful trims.
Duration: PT2M34S
Episode overview
This episode is a short developer briefing from OpenClaw.
It explains recent repository work in plain language.
- Show: OpenClaw
- Published: 2026-11-14T06:04:49Z
- Audio duration: PT2M34S
Transcript excerpt
This excerpt keeps the crawler page concise. Listen to the episode or use the RSS feed for the full update.
Good morning, it's November 14th, 2026, and this is OpenClaw.
The throughline today is Gateway survival after restarts — expired plugin scopes were blocking clean shutdown, crashing narration, and leaving parent sessions parked.
First, shutdown and recovery hardening. PR 198645 traces the immediate pain: a retried visibility check threw on a closed plugin scope, crash-looping a Team gateway roughly every half hour with about two minutes dark each time. PR 198653 contains those expired channel callbacks so optional progress work fails…
Second, OpenClaw ID becomes actually usable for multi-device members. PR 198575 lets members approve their own additional browsers and apps from a device they already have, with role inheritance and self-removal, and owners get device provenance on the People page. That builds on commit 4fc7acf, which resolves…
Third, picker polish and performance trims. PR 198623 stops the model picker from closing unexpectedly, losing favorites, or dropping dragged provider order, while PR 198591 cuts catalog refresh memory by 39 percent and speeds warm requests by 16 percent, and PR 198643 defers dictation feedback UI until first use to…
What's next: watch for fewer…
Nearby episodes from OpenClaw
- Unblocking the Gateway Thread
- Unblocking the Gateway and Honoring Stop
- Interface Steadiness and Gateway Efficiency
- Gateway Recovery and UI Responsiveness
- Weekly Recap - Restart Resilience, CI Efficiency, and Text Safety
- Cutting Repeat Work Across Cron, Sandbox, and CI
- Retained Repair Unblocked and Steering Hardened
- Gateway Self-Recovery and Backup Reliability