v2026.4.25-beta.3 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.
Channel
Pre-Release
Primary signals
Voice replies get a full TTS upgrade; Plugin startup and install paths move; OpenTelemetry coverage expands
Publication date
2026-04-26
Failure and recovery path
Voice replies get a full TTS upgrade
What changed. /tts latest, chat-scoped auto-TTS controls, personas, per-agent/per-account overrides, and new Azure Speech, Xiaomi, Local CLI, Inworld, Volcengine, and ElevenLabs v3 provider coverage.
Check it with. Check Voice replies get a full TTS upgrade 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.
Plugin startup and install paths move to the cold
What changed. Plugin startup and install paths move to the cold persisted registry, cutting broad manifest scans while making plugin update, repair, provider discovery, and install metadata more deterministic.
Check it with. Check Plugin startup and install paths move to the cold 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.
OpenTelemetry coverage expands across model calls, token
What changed. OpenTelemetry coverage expands across model calls, token usage, tool loops, harness runs, exec processes, outbound delivery, context assembly, and memory pressure with bounded low-cardinality attributes.
Check it with. OpenTelemetry coverage expands across model calls, token 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.
Browser automation gets safer tab URLs, iframe-aware
What changed. Browser automation gets safer tab URLs, iframe-aware role snapshots, CDP readiness tuning, headless one-shot launch, and deeper browser doctor probes for slow hosts.
Check it with. The visible promise in Browser automation gets safer tab URLs, iframe-aware needs a continuity check. Use non-sensitive data, refresh midway, and confirm that the same work remains attached to the right session.
The limits of the recovery promise
Control UI and setup flows add PWA/Web Push support
Control UI and setup flows add PWA/Web Push support, Crestodian first-run repair, TUI setup, context mode selection, and a shorter startup greeting.
For Control UI and setup flows add PWA/Web Push support, inspect state rather than only the new control. Repeat the flow after reload and reconnect, and note the session, pending action, URL, and visible error.
TTS/WhatsApp
add /tts latest read-aloud support with duplicate suppression and /tts chat on|off|default session-scoped auto-TTS overrides, completing the on-demand voice-note UX for current-chat replies. Fixes #66032.
TTS/WhatsApp 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.
TTS/channels
resolve channel and account TTS overrides generically, enabling Feishu and QQBot accounts to deep-merge channels.<channel>.accounts.<id>.tts over global and per-agent TTS config.
TTS/channels 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.
Run the smallest useful rehearsal
- Write down the baseline for Voice replies get a full TTS upgrade, including the installed version, host, provider, and workspace.
- Confirm what can be restored, then take a verified backup before applying the candidate package.
- Exercise the affected channel with synthetic text and note the thread, sender, reaction, or attachment id that comes back.
- Restart or reconnect the Gateway, then check for one intended reply rather than a duplicate, missing, or misrouted message.
- Keep the experiment bounded; an unexpected result belongs in the release record before any wider rollout.
openclaw --version
openclaw gateway status
openclaw models
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
Plugins/CLI. let flag-driven openclaw channels add install the selected channel plugin from its default source without opening an interactive prompt, fixing published npm Telegram setup in stdin-closed automation. This is the edge case to include in a regression check, especially when the release is pre-release.
Plugins/startup. load the default memory-core slot during Gateway startup when permitted so active-memory recall can call memory_search and memory_get without requiring an explicit plugins.slots.memory entry, while preserving plugins.slots.memory: "none". Treat the fix as a boundary condition and retain the source wording beside your local result.
Keep the full v2026.4.25-beta.3 notes with your test result. Read the official release index for neighboring versions and the model provider reference for configuration limits.
Reference Trail
Sources and further reading
- full v2026.4.25-beta.3 notesgithub.com
- official release indexgithub.com
- model provider referencedocs.openclaw.ai