Guide
v2026.6.10-beta.2 arrived on 2026-06-22 with a change that matters during maintenance: more reliable model routing. 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
Automatic fast mode for talks; More reliable model routing; Safer session and channel state
Publication date
2026-06-22
Before the package changes
Automatic fast mode for talks
Evidence from the release. OpenClaw can enable fast mode for short conversational turns, then return to normal mode for longer runs with bounded fallback and delivery behavior.
Operator reading. The operator question around Automatic fast mode for talks is where the reply lands after a restart. Record the conversation identifiers before testing and compare them after the channel is healthy again.
More reliable model routing
Evidence from the release. Zai model synthesis, GLM overload failover, and native reasoning-level selection now follow the active model catalog more consistently.
Operator reading. The operator question around More reliable model routing is where the reply lands after a restart. Record the conversation identifiers before testing and compare them after the channel is healthy again.
Safer session and channel state
Evidence from the release. channel switches reset stale origin fields, and cron delivery awareness stays attached to the target session.
Operator reading. Use Safer session and channel state 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.
Trusted policies survive hook composition
Evidence from the release. composed hook registries keep the trusted tool policies required by approval-sensitive flows.
Operator reading. Treat Trusted policies survive hook composition as a boundary change. Exercise one permitted request and one refused request with a test identity, then keep both decisions in the log.
Details behind the headline
Agent and channel runtime
fast-mode state now survives retries, fallback transitions, progress events, and embedded/CLI/ACP normalization; session and channel routing retain the current target and delivery context.
The operator question around Agent and channel runtime is where the reply lands after a restart. Record the conversation identifiers before testing and compare them after the channel is healthy again.
Provider behavior
model catalogs now supply the correct Zai base URL, overload classification, and native reasoning controls for live-discovered models.
A catalog label for Provider behavior is only the first signal. Confirm the account, endpoint, context limit, and tool policy that the running Gateway actually selected.
Fast-mode and policy correctness
fallback cutoffs and reset notices are bounded, repeated progress events remain visible, Codex service-tier state is normalized, and trusted policies are not lost when hook registries are composed.
Read Fast-mode and policy correctness as an authorization checkpoint: prove who may act, what the action can reach, and how the rejected attempt is surfaced to the operator.
Test this release without widening the boundary
- Note the current version, host, provider, and workspace before exercising Automatic fast mode for talks.
- 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 security auditRecord 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
Fast-mode and policy correctness. fallback cutoffs and reset notices are bounded, repeated progress events remain visible, Codex service-tier state is normalized, and trusted policies are not lost when hook registries are composed. Keep the reproduction and the post-fix result together in the acceptance record.
Model and delivery edge cases. Zai and GLM failover paths use the right runtime metadata, while stale channel-origin state no longer leaks across session changes. Record the failure that this correction addresses before declaring the upgrade complete.
Use the complete OpenClaw v2026.6.10-beta.2 release notes for the exact change list, then cross-check the official release index and the model provider reference before acting.
Reference Trail
Sources and further reading
- complete OpenClaw v2026.6.10-beta.2 release notesgithub.com
- official release indexgithub.com
- model provider referencedocs.openclaw.ai