Guide

OpenClaw v2026.6.5-beta.1: Safer channel output, upgrade notes

June 6, 20265 min readUpdated September 11, 2026By OpenClawBlog Team

v2026.6.5-beta.1 arrived on 2026-06-06 with a change that matters during maintenance: safer channel output. The page is a researched reading note from the official release record, with a test path for a real Gateway.

The tag is pre-release: keep it isolated from a production Gateway and compare it with the stable line before making it a default. Support still depends on the provider, channel, platform, and account behind the installation, so check those boundaries before extrapolating from the tag.

Channel
Pre-Release

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

Publication date
2026-06-06

Before the package changes

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. Use Safer channel output 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.

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. MCP results no longer poison sessions changes a capability choice, not automatically a billing or privacy agreement. Record provider, model id, context setting, and fallback behavior before changing a default.

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. The operator question around Anthropic extended thinking recovers after restarts is where the reply lands after a restart. Record the conversation identifiers before testing and compare them after the channel is healthy again.

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. Check Parallel web search is bundled 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.

Details behind the headline

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.

Better Matrix and Vertex reliability 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.

Search/providers

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

The safe reading of Search/providers is operational: prove the model can answer the intended task, then force a bounded failure and verify that no side effect is repeated.

Matrix/channels

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

For Matrix/channels, 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.

Test this release without widening the boundary

Note the current version, host, provider, and workspace before exercising Safer channel output.
Keep a tested backup beside the release record if the update can touch configuration, sessions, or a database.
Send one harmless message through the named account and save the account, thread, and sender identifiers.
Compare the transcript before and after reconnect, including delivery state and any visible error.
Stop if the observed behavior falls outside the official note, and link the log or screenshot to the version record.

openclaw --version
openclaw gateway status
openclaw models

Record what the release actually changed

Keep the version, source URL, test identity, and rollback decision together. If this tag is pre-release, leave it isolated; if it is stable, record the migration and rollback result before reconnecting every channel.

Corrections worth replaying

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. Keep the reproduction and the post-fix result together in the acceptance record.

Channel content boundaries. QQBot now strips reasoning/thinking tags before sending, preserving final answers while hiding internal model narration from users. Record the failure that this correction addresses before declaring the upgrade complete.

Use the complete OpenClaw v2026.6.5-beta.1 release notes for the exact change list, then cross-check the official release index and the model provider reference before acting.