OpenClaw v2026.4.27: Reliability fixes cover Telegram startup/sends, Slack, recovery notes

v2026.4.27 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.

Stable status describes the release line, not every local provider or channel. Check the version-specific notes before upgrading. 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

Codex Computer Use setup now ships with status/install

What changed. Codex Computer Use setup now ships with status/install commands, marketplace discovery, and fail-closed MCP checks for Codex-mode desktop control.

Check it with. A catalog label for Codex Computer Use setup now ships with status/install is only the first signal. Confirm the account, endpoint, context limit, and tool policy that the running Gateway actually selected.

DeepInfra joins the bundled provider set with model

What changed. DeepInfra joins the bundled provider set with model discovery, media generation/editing, TTS, embeddings, and provider-owned onboarding policy.

Check it with. A catalog label for DeepInfra joins the bundled provider set with model is only the first signal. Confirm the account, endpoint, context limit, and tool policy that the running Gateway actually selected.

Tencent Yuanbao and QQBot support expand channel

What changed. Tencent Yuanbao and QQBot support expand channel coverage with Yuanbao docs/catalog entries and QQBot group chat, streaming, media upload, and pipeline refactors.

Check it with. Use Tencent Yuanbao and QQBot support expand channel as a routing test: capture the destination before the send, interrupt the transport, and verify that retry logic did not duplicate or redirect the response.

Plugin startup and model catalogs move toward

What changed. Plugin startup and model catalogs move toward manifest-first metadata, reducing Gateway boot work and making provider rows/aliases/suppressions easier to audit.

Check it with. Check Plugin startup and model catalogs move toward 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 limits of the recovery promise

Reliability fixes cover Telegram startup/sends, Slack

Reliability fixes cover Telegram startup/sends, Slack socket/media stalls, gateway startup prewarm, session/history defaults, update sync, and Windows restart handoffs.

Reliability fixes cover Telegram startup/sends, Slack lives at the handoff between the Gateway and a conversation. Send one harmless message, reconnect once, and compare the account, thread, sender, and final transcript.

Sandbox/Docker

add opt-in sandbox.docker.gpus passthrough for Docker sandbox containers so local GPU workloads can run inside sandboxed agents when the host Docker runtime supports --gpus. Fixes #57976; carries forward #58124.

The useful evidence for Sandbox/Docker is the refusal path as well as the success path. Use synthetic credentials and record the policy that made each decision.

iOS/Gateway

add an authenticated node.presence.alive protocol event and node.list last-seen fields so background iOS wakes can mark paired nodes recently alive without treating them as connected. Carries forward #63123.

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

Run the smallest useful rehearsal

1. Write down the baseline for Codex Computer Use setup now ships with status/install, 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

Gateway/sessions. align chat.history and sessions.list thinking defaults with owning-agent and catalog-aware resolution so Control UI session defaults match backend runtime state. This is the edge case to include in a regression check, especially when the release is pre-release.

Devices/pairing. recover array-shaped device and node pairing state files before persisting approvals, so UUID-keyed pending and paired entries no longer disappear after a malformed JSON store write. Fixes #63035. Treat the fix as a boundary condition and retain the source wording beside your local result.

Keep the full v2026.4.27 notes with your test result. Read the official release index for neighboring versions and the model provider reference for configuration limits.