OpenClaw v2026.6.8: Safer model routing, upgrade notes

v2026.6.8 arrived on 2026-06-16 with a change that matters during maintenance: safer 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 stable, but the direct notes still define its migrations, corrections, and package-specific limits. Support still depends on the provider, channel, platform, and account behind the installation, so check those boundaries before extrapolating from the tag.

Before the package changes

Richer channel delivery

What changed. Telegram and WhatsApp are less brittle: Telegram renders structured text with tables, lists, expandable blockquotes, preserved intentional line breaks, and CLI-backed replies, while WhatsApp now honors configured ACP bindings.

Check it with. For Richer channel delivery, 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 reliable agent runs

What changed. account-scoped DM sends, generated media completions, auto-reply message-tool final replies, reset archive fallback reads, restart shutdown aborts, yielded subagent pauses, and session identity prompts all stay on the correct recovery path.

Check it with. Use More reliable agent runs 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.

Safer model routing

What changed. new GLM-5.2 and Claude Haiku 4.5 catalog support arrives with normalized provider IDs, managed SecretRef auth, bounded model browsing, and safer OpenAI/Anthropic tool-schema recovery.

Check it with. Before widening access for Safer model routing, replay a narrow allow and deny case. A readable denial and a revoked test credential are part of the acceptance record.

Useful usage footers

What changed. /usage and reply payload hooks now have a native full footer renderer, default template, fixed-decimal formatting, credential-aware limits, better partial-count handling, and warnings for broken templates instead of silent bad output.

Check it with. The useful evidence for Useful usage footers is the refusal path as well as the success path. Use synthetic credentials and record the policy that made each decision.

Details behind the headline

Predictable web search defaults

key-free providers such as Parallel Free, DuckDuckGo, Ollama, and Codex Hosted Search remain explicit opt-ins rather than surprising automatic fallbacks.

Predictable web search defaults changes a capability choice, not automatically a billing or privacy agreement. Record provider, model id, context setting, and fallback behavior before changing a default.

Providers/models

add GLM-5.2 support and Claude Haiku 4.5 catalog entries while keeping provider-qualified model IDs normalized across OpenRouter and Google Vertex paths.

Check Providers/models 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.

Web search

keep key-free providers such as Parallel Free, DuckDuckGo, Ollama, and Codex Hosted Search as explicit opt-ins instead of selecting them automatically when no API-backed provider is configured.

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

Test this release without widening the boundary

1. Note the current version, host, provider, and workspace before exercising Richer channel delivery.
2. Keep a tested backup beside the release record if the update can touch configuration, sessions, or a database.
3. Send one harmless message through the named account and save the account, thread, and sender identifiers.
4. Compare the transcript before and after reconnect, including delivery state and any visible error.
5. 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 audit

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

Channels and delivery. preserve account-scoped DM channel send policy, intentional rich-message line breaks in Telegram and status output, rich Telegram final replies, rich Telegram tables and lists, Telegram thread-create CLI remapping, Feishu dynamic-agent routes after persisted binding reuse, Slack outbound message_sent hooks, contributed message-tool schema optionality, same-channel generated media completions, and channel chunking around surrogate pairs and Infinity limits. Keep the reproduction and the post-fix result together in the acceptance record.

Gemini CLI. use the selected OpenClaw OAuth/API-key auth profile in an isolated Gemini CLI runtime home, preventing ambient Google machine credentials from overriding the chosen profile. Record the failure that this correction addresses before declaring the upgrade complete.

Use the complete OpenClaw v2026.6.8 release notes for the exact change list, then cross-check the official release index and the model provider reference before acting.