OpenClaw v2026.5.18-beta.1: Agents, recovery notes

v2026.5.18-beta.1 is easiest to understand through failure. The official record describes a provider, model, voice, or context 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

01 / Agents

Source signal. clarify that fixes should default to clean bounded refactors, lean internals, and explicit plugin SDK/API deprecation paths.

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

02 / Dependencies

Source signal. update @openclaw/proxyline to 0.3.3.

Treat Dependencies as a recovery contract: identify what is preserved, what is irreversible, and which post-update check decides whether the old package may be activated.

03 / Dependencies

Source signal. update Pi packages to 0.75.1 and raise the minimum supported Node.js 22 line to 22.19.

The promise in Dependencies is only useful if the old state returns. Take a verified backup, interrupt a candidate update, and inspect both the retained package and the service.

04 / Discord/OpenAI

Source signal. keep realtime Discord voice sessions hearing follow-up turns with OpenAI realtime and prebuffer assistant playback to avoid choppy starts.

The operator question around Discord/OpenAI is where the reply lands after a restart. Record the conversation identifiers before testing and compare them after the channel is healthy again.

The limits of the recovery promise

Media

prevent image metadata probing from invoking external decoder delegates on unrecognized image bytes, and stop fallback chaining after real processing errors.

Record the source path, transformed output, and refusal reason when testing Media; a successful preview alone does not prove that the boundary is enforced.

Run the smallest useful rehearsal

1. Write down the baseline for Agents, 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 models

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

Discord/OpenAI. keep realtime Discord voice sessions hearing follow-up turns with OpenAI realtime and prebuffer assistant playback to avoid choppy starts. This is the edge case to include in a regression check, especially when the release is pre-release.

Media. prevent image metadata probing from invoking external decoder delegates on unrecognized image bytes, and stop fallback chaining after real processing errors. Treat the fix as a boundary condition and retain the source wording beside your local result.

Keep the full v2026.5.18-beta.1 notes with your test result. Read the official release index for neighboring versions and the model provider reference for configuration limits.