Guide
v2026.5.12-beta.1 arrived on 2026-05-12 with a change that matters during maintenance: models/openai cli auth. The page is a researched reading note from the official release record, with a test path for a real Gateway.
The tag is pre-release: keep it isolated from a production Gateway and compare it with the stable line before making it a default. Support still depends on the provider, channel, platform, and account behind the installation, so check those boundaries before extrapolating from the tag.
Channel
Pre-Release
Primary signals
Models/OpenAI CLI auth; Google/Gemini; Memory Wiki fix
Publication date
2026-05-12
Before the package changes
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. Before widening access for Models/OpenAI CLI auth, replay a narrow allow and deny case. A readable denial and a revoked test credential are part of the acceptance record.
Google/Gemini
Evidence from the release. normalize retired Gemini 3 Pro Preview ids inside SDK OAuth auth-result default config patches, so helper-built provider auth flows emit google/gemini-3.1-pro-preview for Gemini 3.1 testing.
Operator reading. Before widening access for Google/Gemini, replay a narrow allow and deny case. A readable denial and a revoked test credential are part of the acceptance record.
Google/Gemini
Evidence from the release. normalize retired Gemini 3 Pro Preview ids returned by direct openclaw models auth login --set-default provider auth flows before writing config, so Gemini testing targets google/gemini-3.1-pro-preview.
Operator reading. Treat Google/Gemini as a boundary change. Exercise one permitted request and one refused request with a test identity, then keep both decisions in the log.
Memory Wiki fix
Evidence from the release. require admin scope for ingest [AI].
Operator reading. For Memory Wiki fix, inspect state rather than only the new control. Repeat the flow after reload and reconnect, and note the session, pending action, URL, and visible error.
Details behind the headline
Memory-wiki
require write scope for Obsidian search [AI].
Test Memory-wiki at the edges of the interface: clean start, reload, reconnect, and a refused or unavailable action. Keep the final screen and error message with the release note.
Test this release without widening the boundary
- Note the current version, host, provider, and workspace before exercising Models/OpenAI CLI auth.
- Keep a tested backup beside the release record if the update can touch configuration, sessions, or a database.
- Run a read-only prompt with a known answer and save provider, model, reasoning, and latency details.
- Change only the candidate route, then confirm that a failed request returns a readable error and leaves the session intact.
- Stop if the observed behavior falls outside the official note, and link the log or screenshot to the version record.
openclaw --version
openclaw gateway status
openclaw security auditRecord what the release actually changed
Keep the version, source URL, test identity, and rollback decision together. If this tag is pre-release, leave it isolated; if it is stable, record the migration and rollback result before reconnecting every channel.
Corrections worth replaying
Memory Wiki fix. require admin scope for ingest [AI]. Keep the reproduction and the post-fix result together in the acceptance record.
Memory-wiki. require write scope for Obsidian search [AI]. Record the failure that this correction addresses before declaring the upgrade complete.
Use the complete OpenClaw v2026.5.12-beta.1 release notes for the exact change list, then cross-check the official release index and the model provider reference before acting.
Reference Trail
Sources and further reading
- complete OpenClaw v2026.5.12-beta.1 release notesgithub.com
- official release indexgithub.com
- model provider referencedocs.openclaw.ai