OpenClaw v2026.6.7-beta.1: Durable channel replies, operator field notes

The source record for v2026.6.7-beta.1 names a provider, model, voice, or context change. This is an operator's reading of that record, with the exact source facts kept next to a bounded experiment rather than a generic feature list.

Pre-release status matters here: stage the tag beside the stable package and do not infer support for every account or platform. A release tag describes the project change. Your Gateway's provider, channel, platform, and account support should be recorded separately.

A small field test

Durable channel replies

What changed. Telegram polling and preview failures recover instead of ending a stream, Slack keeps delivered replies in the transcript, and top-level image sends retain their intended media source.

Check it with. For Durable channel replies, 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.

More dependable provider sessions

What changed. SecretRef-backed profiles, configured DeepSeek transports, static model fallback, Anthropic thinking replay, and Codex prompt memory all recover cleanly instead of leaving a turn unusable.

Check it with. Read More dependable provider sessions as an authorization checkpoint: prove who may act, what the action can reach, and how the rejected attempt is surfaced to the operator.

Kimi K2.7 Code support

What changed. the provider catalog now includes the new Kimi coding model, with replay handling that preserves its reasoning content across tool turns.

Check it with. The safe reading of Kimi K2.7 Code support is operational: prove the model can answer the intended task, then force a bounded failure and verify that no side effect is repeated.

Safer operations

What changed. SQLite-backed cron status, disabled heartbeat retries, Linux service updates, and external-plugin diagnosis now expose clearer, actionable state to operators.

Check it with. Exercise Safer operations 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.

The details that affect a runbook

Guarded skill installs

Skill Workshop support-file targets now go through trusted lifecycle writes instead of unbounded filesystem updates, while ClawHub package checks stay on the current release path.

Read Guarded skill installs as an authorization checkpoint: prove who may act, what the action can reach, and how the rejected attempt is surfaced to the operator.

Skills and plugin workflows now permit trusted Skill

Skills and plugin workflows now permit trusted Skill Workshop support-file targets only through guarded lifecycle writes, and package publishing uses the current ClawHub plugin checks.

The useful evidence for Skills and plugin workflows now permit trusted Skill is the refusal path as well as the success path. Use synthetic credentials and record the policy that made each decision.

Providers

add Kimi K2.7 Code support.

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

Operator checklist before rollout

1. Before touching persistent state, capture the version, host, provider, and workspace for Durable channel replies.
2. Read the linked release record and verify a backup whenever the change can alter configuration or session data.
3. Interrupt one delivery after admission, reconnect the transport, and compare the final reply with the original conversation.
4. Force a short transport interruption and verify that retry or recovery preserves the original thread and sender.
5. Close the test with the evidence attached, and do not widen the rollout while a behavior remains unexplained.

openclaw --version
openclaw gateway status
openclaw security audit

Keep the source trail attached

Close the loop with an explicit next action: keep the candidate isolated, proceed with the staged upgrade, or stop and investigate. Do not treat a green install as proof that the runtime path is correct.

Regression cases from the source

Channels and delivery. recover Telegram preview and polling failures, retain Slack final replies in transcripts, preserve top-level outbound image parameters, and make channel-action result pages available to callers. Treat the fix as a boundary condition and retain the source wording beside your local result.

Agent/provider reliability. preserve configured model transport/auth resolution, fail closed for unsupported CLI-backed /btw fallback, continue after source message-tool replies, repair Anthropic thinking replay, and keep Codex memory prompts registered. Keep the reproduction and the post-fix result together in the acceptance record.

This page is a practical reading of the v2026.6.7-beta.1 source record; the release index and model provider reference remain the references to use for migrations and support boundaries.