OpenClaw v2026.3.24-beta.1: OpenAI compatibility, recovery notes

v2026.3.24-beta.1 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 / Gateway/OpenAI compatibility

Source signal. add /v1/models and /v1/embeddings, and forward explicit model overrides through /v1/chat/completions and /v1/responses for broader client and RAG compatibility.

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

02 / Agents/tools

Source signal. make /tools show the tools the current agent can actually use right now, add a compact default view with an optional detailed mode, and add a live "Available Right Now" section in the Control UI so it is easier to see what will work before you ask.

A successful click does not establish Agents/tools. Compare the state before and after a reload, then verify that a user can tell what happened without reading internal logs.

03 / Microsoft Teams

Source signal. migrate to the official Teams SDK and add AI-agent UX best practices including streaming 1:1 replies, welcome cards with prompt starters, feedback/reflection, informative status updates, typing indicators, and native AI labeling.

The operator question around Microsoft Teams is where the reply lands after a restart. Record the conversation identifiers before testing and compare them after the channel is healthy again.

04 / Security/sandbox media dispatch

Source signal. close the mediaUrl/fileUrl alias bypass so outbound tool and message actions cannot escape media-root restrictions.

The useful evidence for Security/sandbox media dispatch is the refusal path as well as the success path. Use synthetic credentials and record the policy that made each decision.

The limits of the recovery promise

Gateway/restart sentinel

wake the interrupted agent session via heartbeat after restart instead of only sending a best-effort restart note, retry outbound delivery once on transient failure, and preserve explicit thread/topic routing through the wake path so replies land in the correct Telegram topic or Slack thread.

The operator question around Gateway/restart sentinel is where the reply lands after a restart. Record the conversation identifiers before testing and compare them after the channel is healthy again.

Run the smallest useful rehearsal

1. Write down the baseline for Gateway/OpenAI compatibility, 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. Exercise the affected channel with synthetic text and note the thread, sender, reaction, or attachment id that comes back.
4. Restart or reconnect the Gateway, then check for one intended reply rather than a duplicate, missing, or misrouted message.
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

Security/sandbox media dispatch. close the mediaUrl/fileUrl alias bypass so outbound tool and message actions cannot escape media-root restrictions. This is the edge case to include in a regression check, especially when the release is pre-release.

Gateway/restart sentinel. wake the interrupted agent session via heartbeat after restart instead of only sending a best-effort restart note, retry outbound delivery once on transient failure, and preserve explicit thread/topic routing through the wake path so replies land in the correct Telegram topic or Slack thread. Treat the fix as a boundary condition and retain the source wording beside your local result.

Keep the full v2026.3.24-beta.1 notes with your test result. Read the official release index for neighboring versions and the model provider reference for configuration limits.