OpenClaw: Restart Survival and Interface Reliability

Nearly 60 merged changes center on Gateway restart resilience and Control UI correctness. Interrupted tasks, cron runs, and conversations now recover cleanly instead of stalling or disappearing.

Duration: PT2M30S

Episode overview

This episode is a short developer briefing from OpenClaw.

It explains recent repository work in plain language.

  • Show: OpenClaw
  • Published: 2026-09-20T06:05:12Z
  • Audio duration: PT2M30S

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 September 20th, 2026. You're listening to OpenClaw.

The lead story is survival. A cluster of Gateway fixes ensures restarts, crashes, and version recoveries no longer silently drop active work.

First, restart durability. Pull request 153435 preserves admitted work when startup recovers from an unsupported Node version on Unix Gateways, respecting the existing shutdown budget instead of killing work after two seconds. Related work in 153360 gives every acknowledged manual cron run a durable receipt linked…

Second, task continuity. Pull request 153243 lets interrupted parent tasks continue with a restart notice when their last turn came from a subagent, while 153386 fixes a Gateway hang when agents inherit a model without a runtime pin. Together with stricter child follow-up admission in 153358, unpinned turns no…

Third, interface correctness. Async questions now stay docked above the composer in 153418 instead of disappearing into collapsed history. Chat history in 153245 windows its position rail to settle long transcripts faster, while Systems gains filter and sort plus interactive resource graphs in 153224 and 153268. On…

What's next: watch startup burst behavior…

Nearby episodes from OpenClaw

  1. Auth Races and the Great Refactor Wave
  2. The Great Cancellation Sweep
  3. Taming Fleet-Scale Overhead
  4. Clearing the Gateway Event Loop
  5. Getting the Gateway Thread Out of the Way
  6. Weekly Recap - Gateway Responsiveness & Startup Performance
  7. The Update and Repair Reliability Push
  8. Session Reliability and the Great Test Cleanup