Guide

OpenClaw v2026.5.12-beta.4: Codex runtime, provider notes

May 13, 20264 min readUpdated September 11, 2026By OpenClawBlog Team

v2026.5.12-beta.4 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.

Because this is a pre-release, use a disposable Gateway first and leave the stable version available for comparison. 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.

Channel
Pre-Release

Primary signals
Gateway/OpenAI HTTP; Models/OpenAI CLI auth; Google/Gemini

Publication date
2026-05-13

Provider and model consequences

Gateway/OpenAI HTTP

Evidence from the release. honor max_completion_tokens and max_tokens on inbound /v1/chat/completions requests so client-provided token caps reach the upstream provider via streamParams.maxTokens, with max_completion_tokens taking precedence when both are sent.

Operator reading. Check Gateway/OpenAI HTTP 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.

Models/OpenAI CLI auth

Evidence from the release. make openclaw models auth login --provider openai start the ChatGPT/Codex account login by default, while --method api-key remains the explicit OpenAI API-key setup path.

Operator reading. Treat Models/OpenAI CLI auth as a boundary change. Exercise one permitted request and one refused request with a test identity, then keep both decisions in the log.

Google/Gemini

Evidence from the release. normalize retired Gemini 3 Pro Preview ids inside explicit SDK OAuth auth-result config patches, so provider helpers emit google/gemini-3.1-pro-preview for Gemini 3.1 testing.

Operator reading. The useful evidence for Google/Gemini is the refusal path as well as the success path. Use synthetic credentials and record the policy that made each decision.

Codex runtime

Evidence from the release. allow the official installed @openclaw/codex package to use its private task-runtime SDK helper, fixing MODULE_NOT_FOUND during migrated OpenAI/Codex beta runs.

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

What changes outside the chat box

Codex migration

make Enter activate the highlighted checkbox row before continuing, so Skip for now and bulk-selection rows work even when planned items start preselected.

Check Codex migration 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.

A bounded check for this version

Start with a disposable checkpoint: record the version, host, provider, and workspace tied to Gateway/OpenAI HTTP.
Check the release's migration notes and make a restorable backup before changing persistent state.
Ask the same small question through the affected route and record the account, model id, context, and response time.
Compare the answer, tool permissions, and fallback behavior with the baseline before changing a default.
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

Codex runtime. allow the official installed @openclaw/codex package to use its private task-runtime SDK helper, fixing MODULE_NOT_FOUND during migrated OpenAI/Codex beta runs. Record the failure that this correction addresses before declaring the upgrade complete.

Codex migration. make Enter activate the highlighted checkbox row before continuing, so Skip for now and bulk-selection rows work even when planned items start preselected. This is the edge case to include in a regression check, especially when the release is pre-release.

The authoritative record is the v2026.5.12-beta.4 GitHub release. The release index gives the surrounding sequence, while the model provider reference supplies the operational background.