Guide

OpenClaw v2026.6.5-beta.5: Better Matrix and Vertex reliability, provider notes

June 8, 20265 min readUpdated September 11, 2026By OpenClawBlog Team

v2026.6.5-beta.5 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.

Channel
Pre-Release

Primary signals
Safer channel output; MCP results no longer poison sessions; Anthropic extended thinking recovers after

Publication date
2026-06-08

Provider and model consequences

Safer channel output

Evidence from the release. QQBot strips model reasoning and thinking scaffolding before native delivery, so users see the final answer rather than raw internal markup.

Operator reading. For Safer channel output, delivery is only proven when identity survives an interruption. Keep a disposable channel, send one request, and check for a single reply in the intended thread.

MCP results no longer poison sessions

Evidence from the release. resource_link, audio, malformed images, and future non-text blocks are normalized before provider conversion, avoiding Anthropic 400s and broken follow-up history.

Operator reading. The safe reading of MCP results no longer poison sessions is operational: prove the model can answer the intended task, then force a bounded failure and verify that no side effect is repeated.

Anthropic extended thinking recovers after restarts

Evidence from the release. prompt-cache expiry and early-signature failures wait for a real message start, so they reach the existing retry path rather than ending a turn.

Operator reading. For Anthropic extended thinking recovers after restarts, delivery is only proven when identity survives an interruption. Keep a disposable channel, send one request, and check for a single reply in the intended thread.

Parallel web search is bundled

Evidence from the release. API-key discovery, guarded endpoint handling, cache-safe session IDs, onboarding, and documentation make it a first-class search provider.

Operator reading. Parallel web search is bundled changes a capability choice, not automatically a billing or privacy agreement. Record provider, model id, context setting, and fallback behavior before changing a default.

What changes outside the chat box

Better Matrix and Vertex reliability

Matrix voice notes and threaded conversations retain their context, while Google Vertex ADC models regain static catalog and runtime resolution.

The operator question around Better Matrix and Vertex reliability is where the reply lands after a restart. Record the conversation identifiers before testing and compare them after the channel is healthy again.

Search/providers

add the Parallel bundled web-search plugin, registration contracts, onboarding integration, and guarded api.parallel.ai/v1/search support.

Search/providers changes a capability choice, not automatically a billing or privacy agreement. Record provider, model id, context setting, and fallback behavior before changing a default.

Matrix/channels

add voice-message preflight and thread-aware read/reply behavior.

Matrix/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.

A bounded check for this version

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

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. sessions_send now honors an explicit sessionKey when stale label metadata is also present, and denied session-id sends no longer echo the resolved canonical session key. Fixes #64699; refs #74009 and #41199. Record the failure that this correction addresses before declaring the upgrade complete.

Channel content boundaries. QQBot now strips reasoning/thinking tags before sending, preserving final answers while hiding internal model narration from users. This is the edge case to include in a regression check, especially when the release is pre-release.

The authoritative record is the v2026.6.5-beta.5 GitHub release. The release index gives the surrounding sequence, while the model provider reference supplies the operational background.