OpenClaw v2026.4.24: DeepSeek V4 Flash and V4 Pro are in the bundled catalog, provider notes

v2026.4.24 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.

This is a stable release line; read the exact record for migrations and fixes before applying it to a live Gateway. 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

Google Meet joins OpenClaw as a bundled participant

What changed. Google Meet joins OpenClaw as a bundled participant plugin, with personal Google auth, Chrome/Twilio realtime sessions, paired-node Chrome support, artifact/attendance exports, and recovery tooling for already-open Meet tabs.

Check it with. Treat Google Meet joins OpenClaw as a bundled participant as a boundary change. Exercise one permitted request and one refused request with a test identity, then keep both decisions in the log.

DeepSeek V4 Flash and V4 Pro are in the bundled catalog

What changed. DeepSeek V4 Flash and V4 Pro are in the bundled catalog, V4 Flash is the onboarding default, and DeepSeek thinking/replay behavior is fixed for follow-up tool-call turns.

Check it with. Check DeepSeek V4 Flash and V4 Pro are in the bundled catalog 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.

Talk, Voice Call, and Google Meet can use realtime voice

What changed. Talk, Voice Call, and Google Meet can use realtime voice loops that consult the full OpenClaw agent for deeper tool-backed answers.

Check it with. A catalog label for Talk, Voice Call, and Google Meet can use realtime voice is only the first signal. Confirm the account, endpoint, context limit, and tool policy that the running Gateway actually selected.

Browser automation gets coordinate clicks, longer

What changed. Browser automation gets coordinate clicks, longer default action budgets, per-profile headless overrides, and steadier tab reuse/recovery.

Check it with. A successful click does not establish Browser automation gets coordinate clicks, longer. Compare the state before and after a reload, then verify that a user can tell what happened without reading internal logs.

What changes outside the chat box

Plugin and model infrastructure is lighter at startup

static model catalogs, manifest-backed model rows, lazy provider dependencies, and external runtime-dependency repair for packaged installs.

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

Control UI/Talk

add browser WebRTC realtime voice sessions backed by OpenAI Realtime, with Gateway-minted ephemeral client secrets and openclaw_agent_consult handoff to the full OpenClaw agent.

Before widening access for Control UI/Talk, replay a narrow allow and deny case. A readable denial and a revoked test credential are part of the acceptance record.

Plugins/Google Meet

add a bundled participant plugin with personal Google auth, explicit meeting URL joins, Chrome and Twilio realtime transports, paired-node chrome-node support for Parallels-style Chrome/BlackHole/SoX hosts, and full-agent consults inside live voice sessions.

Before widening access for Plugins/Google Meet, replay a narrow allow and deny case. A readable denial and a revoked test credential are part of the acceptance record.

A bounded check for this version

1. Start with a disposable checkpoint: record the version, host, provider, and workspace tied to Google Meet joins OpenClaw as a bundled participant.
2. Check the release's migration notes and make a restorable backup before changing persistent state.
3. Ask the same small question through the affected route and record the account, model id, context, and response time.
4. Compare the answer, tool permissions, and fallback behavior with the baseline before changing a default.
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

Packaged installs. preserve package-root runtime dependencies and their exported subpaths when bundled plugin runtime mirrors fall back to copying shared chunks, fixing Windows npm updates that could fail to load copied dist modules. Record the failure that this correction addresses before declaring the upgrade complete.

Heartbeat. clamp oversized scheduler delays through the shared safe timer helper, preventing every values over Node's timeout cap from becoming a 1 ms crash loop. Fixes #71414. This is the edge case to include in a regression check, especially when the release is pre-release.

The authoritative record is the v2026.4.24 GitHub release. The release index gives the surrounding sequence, while the model provider reference supplies the operational background.