OpenClaw v2026.7.1-beta.6: Meta provider, upgrade notes

v2026.7.1-beta.6 arrived on 2026-07-13 with a change that matters during maintenance: meta provider. 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.

Before the package changes

01 / New models and providers

Source signal. add Featherless, Claude Sonnet 5 and Mythos 5, Meta Muse Spark 1.1, and ClawRouter; make GPT-5.6 the new-setup default with /think ultra for Sol and Terra plus max for Luna, honor Z.AI max, and refresh model availability after OAuth renewal.

Treat New models and providers as a boundary change. Exercise one permitted request and one refused request with a test identity, then keep both decisions in the log.

02 / Control UI and native macOS chat

Source signal. make sessions primary with a minimal searchable sidebar, compact context ring, reasoning-effort slider, cleaner dashboard chrome, and a native macOS session browser with model and thinking pickers, slash commands, transcript export, and context usage.

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

03 / Conversational onboarding

Source signal. Crestodian now runs a real agent-loop setup across the CLI, web install, and macOS app, with AI-guided provider setup, model-judged approvals bound to exact operations, masked credential prompts, and deterministic fallback when no model is available.

The useful evidence for Conversational onboarding is the refusal path as well as the success path. Use synthetic credentials and record the policy that made each decision.

04 / Offline and spoken mobile chat

Source signal. iOS and Android now pre-paint bounded per-gateway session and transcript caches offline; Apple Watch gains full voice turns, and iOS can speak replies through configured Gateway TTS with on-device fallback.

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

Details behind the headline

Session organization and generated titles

generate concise session titles through utility-model routing and add Gateway-backed groups, unread state, rename, fork, archive, and delete controls, plus group management across web, iOS, and Android.

Session organization and generated titles 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.

Meta provider

add bundled muse-spark-1.1 Responses API support with streaming, tool calls, encrypted reasoning replay, onboarding, exact-model live validation, and standalone npm/ClawHub distribution as @openclaw/meta-provider.

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

Android chat agent selector

switch the active agent directly from the live chat screen while keeping chat, Talk mode, and home canvas on the same canonical session.

For Android chat agent selector, inspect state rather than only the new control. Repeat the flow after reload and reconnect, and note the session, pending action, URL, and visible error.

Test this release without widening the boundary

1. Note the current version, host, provider, and workspace before exercising New models and providers.
2. Keep a tested backup beside the release record if the update can touch configuration, sessions, or a database.
3. Run a read-only prompt with a known answer and save provider, model, reasoning, and latency details.
4. Change only the candidate route, then confirm that a failed request returns a readable error and leaves the session intact.
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

Codex runtime switching. accept the bundled Codex runtime for both codex/* and openai/* model routes while keeping unsupported provider/runtime pairs rejected. Keep the reproduction and the post-fix result together in the acceptance record.

LM Studio and xAI repaired tool calls. emit the terminal tool-call event before completion when promoting serialized plain-text tool calls, preserving the complete streaming lifecycle for consumers. Record the failure that this correction addresses before declaring the upgrade complete.

Use the complete OpenClaw v2026.7.1-beta.6 release notes for the exact change list, then cross-check the official release index and the model provider reference before acting.