OpenClaw v2026.4.24-beta.5: Plugin and model infrastructure is lighter at startup, recovery notes

v2026.4.24-beta.5 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

The limits of the recovery promise

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.

Plugin and model infrastructure is lighter at startup changes a capability choice, not automatically a billing or privacy agreement. Record provider, model id, context setting, and fallback behavior before changing a default.

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.

A visible plugin card is not approval for Packaged installs. Inspect the source and run one allowed and one refused operation before changing a shared Gateway.

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.

Exercise Heartbeat twice with a disposable trigger. The expected result is one side effect, a readable terminal state, and a cancellation path while work is still pending.

Run the smallest useful rehearsal

1. Write down the baseline for Google Meet joins OpenClaw as a bundled participant, 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. Use a disposable session to compare the new model or provider with the previous route on one fixed input.
4. Restore the previous provider setting after the check and retain the measured result beside the release tag.
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

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. This is the edge case to include in a regression check, especially when the release is pre-release.

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. Treat the fix as a boundary condition and retain the source wording beside your local result.

Keep the full v2026.4.24-beta.5 notes with your test result. Read the official release index for neighboring versions and the model provider reference for configuration limits.