OpenClaw v2026.5.28-beta.3: Mobile and chat surfaces got a broader refresh, provider notes

v2026.5.28-beta.3 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.

Provider and model consequences

Agent and Codex runtime recovery is steadier

What changed. subagents keep cwd/workspace separation, hook context stays prompt-local, session locks release on timeout abort, stale restart continuations are avoided, and Codex app-server/helper failures no longer tear down shared runtime state.

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

Channel delivery and session identity got safer

What changed. Channel delivery and session identity got safer across outbound plugin hooks, Matrix room ids, iMessage reactions/approvals, Slack final replies, Discord recovered tool warnings, WhatsApp profile auth roots, Telegram polling, and Microsoft Teams service URL trust checks.

Check it with. Before widening access for Channel delivery and session identity got safer, replay a narrow allow and deny case. A readable denial and a revoked test credential are part of the acceptance record.

Mobile and chat surfaces got a broader refresh

What changed. the iOS Pro UI, Gateway chat transport, onboarding, Talk permissions, WebChat reconnect delivery, and session picker behavior now preserve more state across reconnects and empty searches.

Check it with. Read Mobile and chat surfaces got a broader refresh as an authorization checkpoint: prove who may act, what the action can reach, and how the rejected attempt is surfaced to the operator.

Browser, channel, and automation inputs are stricter

What changed. Browser tool timeouts, viewport/tab indices, Gateway ports, cron retry handling, Discord component ids, schema array refs, Telegram callback pages, and channel progress callbacks now reject malformed values earlier and preserve the intended delivery context.

Check it with. Use Browser, channel, and automation inputs are stricter 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.

What changes outside the chat box

Provider, media, and document coverage expands

Provider, media, and document coverage expands with Claude Opus 4.8, Fal Krea image schemas, NVIDIA featured models, MiniMax streaming music responses, encrypted PDF extraction, voice model catalogs, GitHub Copilot agent runtime support, and a Codex Supervisor plugin path for delegated Codex workflows.

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

Status

show active subagent details in status output.

Use Status for a small reproducible task: save the input, visible result, useful failure, and version context another operator would need.

Diffs

split the default language pack and expand default Diffs language coverage while keeping the host floor aligned.

Use Diffs for a small reproducible task: save the input, visible result, useful failure, and version context another operator would need.

A bounded check for this version

1. Start with a disposable checkpoint: record the version, host, provider, and workspace tied to Agent and Codex runtime recovery is steadier.
2. Check the release's migration notes and make a restorable backup before changing persistent state.
3. Use a disposable conversation for one send, one reconnect, and one retry; keep the destination identifiers with the result.
4. Leave the channel disabled after the test if its credentials or pairing were created only for this rehearsal.
5. 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

Agents. fall back to local config pruning when the optional agents delete Gateway probe cannot authenticate, so offline installs can still delete agents without removing shared workspaces. Record the failure that this correction addresses before declaring the upgrade complete.

Tighten phone-control mutation authorization [AI]. The release records a focused fix in tighten phone-control mutation authorization [ai]. This is the edge case to include in a regression check, especially when the release is pre-release.

The authoritative record is the v2026.5.28-beta.3 GitHub release. The release index gives the surrounding sequence, while the model provider reference supplies the operational background.