OpenClaw v2026.4.20: Models/costs, provider notes

v2026.4.20 changes how an agent selects, calls, or remembers a provider. The official record describes a provider, model, voice, or context change; the useful test is a small request with the provider boundary recorded.

This is a stable release line; read the exact record for migrations and fixes before applying it to a live Gateway. The release body cannot certify every local combination of provider, channel, platform, and account; use the bounded test below for the path you actually run.

Provider and model consequences

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.

Check Agents/prompts with a known prompt and a disposable account. Save the selected route, reasoning setting, latency, and refusal or fallback result so another operator can reproduce it.

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.

What changes outside the chat box

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.

A bounded check for this version

1. Start with a disposable checkpoint: record the version, host, provider, and workspace tied to Onboard/wizard.
2. Check the release's migration notes and make a restorable backup before changing persistent state.
3. Ask the same small question through the affected route and record the account, model id, context, and response time.
4. Compare the answer, tool permissions, and fallback behavior with the baseline before changing a default.
5. If the result differs from the release body, stop the rollout and attach the log, screenshot, or transcript to the version record.

openclaw --version
openclaw gateway status
openclaw security audit

Close the loop with evidence

A useful maintenance record names the changed behavior, the behavior that stayed stable, the identity that approved the test, and the step that would undo it. Preserve that record beside the release tag.

Edge cases in this tag

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. Record the failure that this correction addresses before declaring the upgrade complete.

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. This is the edge case to include in a regression check, especially when the release is pre-release.

The authoritative record is the v2026.4.20 GitHub release. The release index gives the surrounding sequence, while the model provider reference supplies the operational background.