OpenClaw v2026.4.20-beta.2: Prompts, recovery notes

v2026.4.20-beta.2 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 / Onboard/wizard

Source signal. restyle the setup security disclaimer with a single yellow warning banner, section headings and bulleted checklists, and un-dim the note body so key guidance is easy to scan; add a loading spinner during the initial model catalog load so the wizard no longer goes blank while it runs; add an "API key" placeholder to provider API key prompts.

Read Onboard/wizard as an authorization checkpoint: prove who may act, what the action can reach, and how the rejected attempt is surfaced to the operator.

02 / Agents/prompts

Source signal. strengthen the default system prompt and OpenAI GPT-5 overlay with clearer completion bias, live-state checks, weak-result recovery, and verification-before-final guidance.

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

03 / Models/costs

Source signal. support tiered model pricing from cached catalogs and configured models, and include bundled Moonshot Kimi K2.6/K2.5 cost estimates for token-usage reports.

Models/costs changes a capability choice, not automatically a billing or privacy agreement. Record provider, model id, context setting, and fallback behavior before changing a default.

04 / Exec/YOLO

Source signal. stop rejecting gateway-host exec in security=full plus ask=off mode via the Python/Node script preflight hardening path, so promptless YOLO exec once again runs direct interpreter stdin and heredoc forms such as node <<'NODE' ... NODE.

Before widening access for Exec/YOLO, replay a narrow allow and deny case. A readable denial and a revoked test credential are part of the acceptance record.

The limits of the recovery promise

OpenAI Codex

normalize legacy openai-completions transport overrides on default OpenAI/Codex and GitHub Copilot-compatible hosts back to the native Codex Responses transport while leaving custom proxies untouched.

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

Run the smallest useful rehearsal

1. Write down the baseline for Onboard/wizard, 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

Exec/YOLO. stop rejecting gateway-host exec in security=full plus ask=off mode via the Python/Node script preflight hardening path, so promptless YOLO exec once again runs direct interpreter stdin and heredoc forms such as node <<'NODE' ... NODE. This is the edge case to include in a regression check, especially when the release is pre-release.

OpenAI Codex. normalize legacy openai-completions transport overrides on default OpenAI/Codex and GitHub Copilot-compatible hosts back to the native Codex Responses transport while leaving custom proxies untouched. Treat the fix as a boundary condition and retain the source wording beside your local result.

Keep the full v2026.4.20-beta.2 notes with your test result. Read the official release index for neighboring versions and the model provider reference for configuration limits.