OpenClaw v2026.7.1-beta.5: Session organization and generated titles, provider notes

v2026.7.1-beta.5 changes how an agent selects, calls, or remembers a provider. The official record describes a provider, model, voice, or context change; the useful test is a small request with the provider boundary recorded.

Because this is a pre-release, use a disposable Gateway first and leave the stable version available for comparison. The release body cannot certify every local combination of provider, channel, platform, and account; use the bounded test below for the path you actually run.

Provider and model consequences

New models and providers

What changed. 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.

Check it with. 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.

Control UI and native macOS chat

What changed. 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.

Check it with. Check Control UI and native macOS chat 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.

Conversational onboarding

What changed. 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.

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

Offline and spoken mobile chat

What changed. 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.

Check it with. A catalog label for Offline and spoken mobile chat is only the first signal. Confirm the account, endpoint, context limit, and tool policy that the running Gateway actually selected.

What changes outside the chat box

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.

Use Session organization and generated titles 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.

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.

Check Meta provider 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.

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.

Test Android chat agent selector at the edges of the interface: clean start, reload, reconnect, and a refused or unavailable action. Keep the final screen and error message with the release note.

A bounded check for this version

1. Start with a disposable checkpoint: record the version, host, provider, and workspace tied to New models and providers.
2. Check the release's migration notes and make a restorable backup before changing persistent state.
3. Ask the same small question through the affected route and record the account, model id, context, and response time.
4. Compare the answer, tool permissions, and fallback behavior with the baseline before changing a default.
5. If the result differs from the release body, stop the rollout and attach the log, screenshot, or transcript to the version record.

openclaw --version
openclaw gateway status
openclaw security audit

Close the loop with evidence

A useful maintenance record names the changed behavior, the behavior that stayed stable, the identity that approved the test, and the step that would undo it. Preserve that record beside the release tag.

Edge cases in this tag

Codex runtime switching. accept the bundled Codex runtime for both codex/* and openai/* model routes while keeping unsupported provider/runtime pairs rejected. Record the failure that this correction addresses before declaring the upgrade complete.

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. This is the edge case to include in a regression check, especially when the release is pre-release.

The authoritative record is the v2026.7.1-beta.5 GitHub release. The release index gives the surrounding sequence, while the model provider reference supplies the operational background.