Guide

OpenClaw v2026.3.28-beta.1: xAI/tools, operator field notes

March 28, 20265 min readUpdated September 11, 2026By OpenClawBlog Team

The source record for v2026.3.28-beta.1 names a provider, model, voice, or context change. This is an operator's reading of that record, with the exact source facts kept next to a bounded experiment rather than a generic feature list.

Pre-release status matters here: stage the tag beside the stable package and do not infer support for every account or platform. A release tag describes the project change. Your Gateway's provider, channel, platform, and account support should be recorded separately.

Channel
Pre-Release

Primary signals
xAI/tools; MiniMax; Plugins/hooks

Publication date
2026-03-28

A small field test

xAI/tools

Evidence from the release. move the bundled xAI provider to the Responses API, add first-class x_search, and auto-enable the xAI plugin from owned web-search and tool config so bundled Grok auth/configured search flows work without manual plugin toggles.

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

MiniMax

Evidence from the release. add image generation provider for image-01 model, supporting generate and image-to-image editing with aspect ratio control.

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

Plugins/hooks

Evidence from the release. add async requireApproval to before_tool_call hooks, letting plugins pause tool execution and prompt the user for approval via the exec approval overlay, Telegram buttons, Discord interactions, or the /approve command on any channel. The /approve command now handles both exec and plugin approvals with automatic fallback.

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

Google/models

Evidence from the release. resolve Gemini 3.1 pro, flash, and flash-lite for all Google provider aliases by passing the actual runtime provider ID and adding a template-provider fallback; fix flash-lite prefix ordering.

Operator reading. Check Google/models 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.

The details that affect a runbook

OpenAI Codex/image tools

register Codex for media understanding and route image prompts through Codex instructions so image analysis no longer fails on missing provider registration or missing instructions.

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

Operator checklist before rollout

Before touching persistent state, capture the version, host, provider, and workspace for xAI/tools.
Read the linked release record and verify a backup whenever the change can alter configuration or session data.
Interrupt one delivery after admission, reconnect the transport, and compare the final reply with the original conversation.
Force a short transport interruption and verify that retry or recovery preserves the original thread and sender.
Close the test with the evidence attached, and do not widen the rollout while a behavior remains unexplained.

openclaw --version
openclaw gateway status
openclaw security audit

Keep the source trail attached

Close the loop with an explicit next action: keep the candidate isolated, proceed with the staged upgrade, or stop and investigate. Do not treat a green install as proof that the runtime path is correct.

Regression cases from the source

Google/models. resolve Gemini 3.1 pro, flash, and flash-lite for all Google provider aliases by passing the actual runtime provider ID and adding a template-provider fallback; fix flash-lite prefix ordering. Treat the fix as a boundary condition and retain the source wording beside your local result.

OpenAI Codex/image tools. register Codex for media understanding and route image prompts through Codex instructions so image analysis no longer fails on missing provider registration or missing instructions. Keep the reproduction and the post-fix result together in the acceptance record.

This page is a practical reading of the v2026.3.28-beta.1 source record; the release index and model provider reference remain the references to use for migrations and support boundaries.