Tutorial

OpenClaw v2026.5.9-beta.1: Chat commands, for maintainers

May 9, 20264 min readUpdated September 11, 2026By OpenClawBlog Team

For maintainers reading v2026.5.9-beta.1, the source is a map of contracts. It describes a skills, plugin, marketplace, or SDK change, then lists implementation changes and fixes that can affect plugins, providers, or downstream tooling.

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
Chat commands; Dependencies; Plugins/install

Publication date
2026-05-09

Compatibility for maintainers

Chat commands

Evidence from the release. add /think default and /fast default to clear session overrides and inherit configured/provider defaults.

Operator reading. The safe reading of Chat commands is operational: prove the model can answer the intended task, then force a bounded failure and verify that no side effect is repeated.

Dependencies

Evidence from the release. refresh workspace dependency pins and lockfile, including @openai/codex 0.130.0, acpx 0.7.0, AWS SDK 3.1044.0, OpenTelemetry 0.217.0, typebox 1.1.38, vite 8.0.11, oxfmt 0.48.0, and oxlint 1.63.0, and update the Codex harness model snapshot for the new bundled app-server catalog.

Operator reading. The safe reading of Dependencies is operational: prove the model can answer the intended task, then force a bounded failure and verify that no side effect is repeated.

Plugins/install

Evidence from the release. add guarded plugin install overrides so onboarding and repair tests can route specific plugins to registry specs or local npm pack artifacts via environment variables.

Operator reading. Keep discovery separate from permission for Plugins/install. Review the manifest, source, dependencies, and removal path in a disposable workspace before enabling it.

Agents/CLI

Evidence from the release. handle resumed CLI JSONL output and bound supervisor output buffering so resumed runs stay readable without letting noisy child output grow unbounded.

Operator reading. A release note about Agents/CLI becomes useful when the same task can be repeated after a restart and still produce an explainable result.

API, package, and test clues

Agents/sandbox

include the container workspace path hint in sandbox-root escape errors while preserving shortened host workspace roots. Fixes #79712.

Treat Agents/sandbox as a boundary change. Exercise one permitted request and one refused request with a test identity, then keep both decisions in the log.

Run the smallest useful rehearsal

  1. Write down the baseline for Chat commands, 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. Use a disposable session to compare the new model or provider with the previous route on one fixed input.
  4. Restore the previous provider setting after the check and retain the measured result beside the release tag.
  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

Agents/CLI. handle resumed CLI JSONL output and bound supervisor output buffering so resumed runs stay readable without letting noisy child output grow unbounded. This is the edge case to include in a regression check, especially when the release is pre-release.

Agents/sandbox. include the container workspace path hint in sandbox-root escape errors while preserving shortened host workspace roots. Fixes #79712. Treat the fix as a boundary condition and retain the source wording beside your local result.

Keep the full v2026.5.9-beta.1 notes with your test result. Read the official release index for neighboring versions and the skills documentation for configuration limits.

Reference Trail

Sources and further reading

  1. full v2026.5.9-beta.1 notesgithub.com
  2. official release indexgithub.com
  3. skills documentationdocs.openclaw.ai
Back to ArchiveMore: TutorialsNext: OpenClaw Webhooks: Verify the Signature Before You Wake an Agent