OpenClaw v2026.5.30-beta.1: Agents and CLI-backed runtimes recover more cleanly, recovery notes

v2026.5.30-beta.1 is easiest to understand through failure. The official record describes a health, liveness, or runtime-observability change; the sections below spell out what to save, what to interrupt, and what must remain available afterward.

This candidate is still pre-release. Treat provider, channel, and migration behavior as unconfirmed until your own bounded test passes. Treat the version as one input to the decision. Local credentials, enabled plugins, channels, and host support still need their own evidence.

Failure and recovery path

Agents and CLI-backed runtimes recover more cleanly

What changed. Agents and CLI-backed runtimes recover more cleanly from interrupted tool calls, stale session bindings, compaction handoffs, and media delivery retries.

Check it with. Use Agents and CLI-backed runtimes recover more cleanly as a routing test: capture the destination before the send, interrupt the transport, and verify that retry logic did not duplicate or redirect the response.

Channels and mobile delivery are steadier

What changed. Channels and mobile delivery are steadier across Telegram, WhatsApp, iMessage, Slack, Discord, Microsoft Teams, Google Chat, Google Meet, and iOS realtime Talk.

Check it with. Channels and mobile delivery are steadier lives at the handoff between the Gateway and a conversation. Send one harmless message, reconnect once, and compare the account, thread, sender, and final transcript.

Provider and plugin requests now bound more timers

What changed. Provider and plugin requests now bound more timers, retries, OAuth/device-code lifetimes, media downloads, local service probes, and generated-content polling paths before they can hang a run.

Check it with. Treat Provider and plugin requests now bound more timers as a boundary change. Exercise one permitted request and one refused request with a test identity, then keep both decisions in the log.

Skills, session metadata, gateway runtime state, plugin

What changed. Skills, session metadata, gateway runtime state, plugin metadata, and store writes do less repeated work on hot paths while keeping config and dispatch behavior stable.

Check it with. The visible promise in Skills, session metadata, gateway runtime state, plugin needs a continuity check. Use non-sensitive data, refresh midway, and confirm that the same work remains attached to the right session.

The limits of the recovery promise

Workboard, SecretRef plugin manifests, hosted iOS push

Workboard, SecretRef plugin manifests, hosted iOS push relay, and external Copilot/Tokenjuice packaging add broader orchestration, integration, and plugin delivery surfaces.

The useful evidence for Workboard, SecretRef plugin manifests, hosted iOS push is the refusal path as well as the success path. Use synthetic credentials and record the policy that made each decision.

Skills

let the skill_research agent tool apply, reject, and quarantine explicit Skill Workshop proposals through the guarded proposal lifecycle.

A visible plugin card is not approval for Skills. Inspect the source and run one allowed and one refused operation before changing a shared Gateway.

Skills

let Skill Workshop proposals carry approved support files under standard skill folders, with scanner, hash, and rollback safeguards.

Keep discovery separate from permission for Skills. Review the manifest, source, dependencies, and removal path in a disposable workspace before enabling it.

Run the smallest useful rehearsal

1. Write down the baseline for Agents and CLI-backed runtimes recover more cleanly, including the installed version, host, provider, and workspace.
2. Confirm what can be restored, then take a verified backup before applying the candidate package.
3. Exercise the affected channel with synthetic text and note the thread, sender, reaction, or attachment id that comes back.
4. Restart or reconnect the Gateway, then check for one intended reply rather than a duplicate, missing, or misrouted message.
5. Keep the experiment bounded; an unexpected result belongs in the release record before any wider rollout.

openclaw --version
openclaw gateway status
openclaw security audit

Leave a usable maintenance note

Save the command, output, source link, and environment used for this check. Future operators should be able to tell whether a difference belongs to the release or to local provider, channel, or platform state.

Fix details to carry forward

CLI. keep plugins list --json on the snapshot-only path so plugin sweeps avoid loading the full runtime status graph. This is the edge case to include in a regression check, especially when the release is pre-release.

Plugins. make PixVerse external-plugin ClawHub metadata explicit and keep it out of bundled dist builds. Treat the fix as a boundary condition and retain the source wording beside your local result.

Keep the full v2026.5.30-beta.1 notes with your test result. Read the official release index for neighboring versions and the Gateway health guide for configuration limits.