Security
A release page is most useful when its claims can be traced. For v2026.5.19-beta.2, the source points to an access, approval, or trust-boundary change. The notes below separate what the project says from the result you should measure on your own installation.
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.
Channel
Pre-Release
Primary signals
Agents; Dependencies; CLI
Publication date
2026-05-19
Evidence to keep
Agents
Evidence from the release. clarify that fixes should default to clean bounded refactors, lean internals, and explicit plugin SDK/API deprecation paths.
Operator reading. Keep discovery separate from permission for Agents. Review the manifest, source, dependencies, and removal path in a disposable workspace before enabling it.
Dependencies
Evidence from the release. update @openclaw/proxyline to 0.3.3.
Operator reading. 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.
Dependencies
Evidence from the release. update Pi packages to 0.75.1 and raise the minimum supported Node.js 22 line to 22.19.
Operator reading. Test Dependencies with a failure you can explain. Confirm that the prior configuration and data remain readable, then document the cases where an operator must restore manually.
CLI
Evidence from the release. reject explicit port numbers above 65535 before they reach Gateway or Node bind paths. Fixes #83900.
Operator reading. Measure CLI before and after the update with synthetic data, and explain every accepted finding in the release record.
Changes and fixes worth comparing
Codex app-server
preserve plugin tool auth profiles when Codex owns model transport so OpenClaw dynamic tools can resolve their provider credentials.
Read Codex app-server as an authorization checkpoint: prove who may act, what the action can reach, and how the rejected attempt is surfaced to the operator.
Run the smallest useful rehearsal
- Write down the baseline for Agents, including the installed version, host, provider, and workspace.
- Confirm what can be restored, then take a verified backup before applying the candidate package.
- Use a disposable session to compare the new model or provider with the previous route on one fixed input.
- Restore the previous provider setting after the check and retain the measured result beside the release tag.
- Keep the experiment bounded; an unexpected result belongs in the release record before any wider rollout.
openclaw --version
openclaw gateway status
openclaw security auditLeave 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. reject explicit port numbers above 65535 before they reach Gateway or Node bind paths. Fixes #83900. This is the edge case to include in a regression check, especially when the release is pre-release.
Codex app-server. preserve plugin tool auth profiles when Codex owns model transport so OpenClaw dynamic tools can resolve their provider credentials. Treat the fix as a boundary condition and retain the source wording beside your local result.
Keep the full v2026.5.19-beta.2 notes with your test result. Read the official release index for neighboring versions and the Gateway security guide for configuration limits.
Reference Trail
Sources and further reading
- full v2026.5.19-beta.2 notesgithub.com
- official release indexgithub.com
- Gateway security guidedocs.openclaw.ai