Agent DailyAgent Daily
releaseintermediate

[Release] openclaw/openclaw v2026.7.1: openclaw 2026.7.1

By github-actions[bot]github
View original on github

OpenClaw v2026.7.1 introduces major platform enhancements including new AI models (Claude Sonnet 5, Mythos 5, Meta Muse Spark 1.1), a redesigned Control UI with sessions-first navigation, conversational onboarding via Crestodian agent-loop, offline/spoken mobile chat capabilities, and improved session organization with auto-generated titles. The release also strengthens Telegram/Codex continuity, adds startup/upgrade recovery mechanisms, and expands provider support with ClawRouter for dynamic model discovery and budget management.

Key Points

  • Add support for new models: Claude Sonnet 5, Mythos 5, Meta Muse Spark 1.1, Featherless, and GPT-5.6 as new default with `/think ultra` for Sol/Terra and `max` for Luna
  • Redesign Control UI with sessions-primary sidebar, compact context ring, reasoning-effort slider, and native macOS session browser with model/thinking pickers and transcript export
  • Implement Crestodian conversational onboarding with real agent-loop setup, AI-guided provider configuration, model-judged approvals, and masked credential prompts across CLI, web, and macOS
  • Enable offline mobile chat with pre-painted per-gateway session/transcript caches on iOS/Android; add Apple Watch voice turns and iOS TTS reply capability with on-device fallback
  • Auto-generate concise session titles via utility-model routing; add Gateway-backed groups with unread state, rename, fork, archive, delete controls across all platforms
  • Enhance Telegram/Codex integration with private `/login`, `/steer`, `/tell` commands, durable turn adoption, and recovery from formatting/flood-wait failures
  • Improve startup/upgrade resilience: run container migrations before Gateway readiness, prevent legacy state from blocking startup, enter control-plane-safe mode after repeated unclean boots
  • Launch ClawRouter bundled provider plugin with credential-scoped dynamic model discovery, OpenAI-compatible/native Anthropic/Gemini transports, and managed budget reporting
  • Add Gateway host status visibility (network address, OS, runtime, uptime, CPU, memory, disk) in Control UI Settings and implement crash-loop recovery with `EX_CONFIG` exit codes
  • Expand Control UI features: GitHub issue/PR previews with state/activity, per-message token/context/model details on hover, customizable pinned sidebar destinations, and Logbook work journal plugin

Found this useful? Add it to a playbook for a step-by-step implementation guide.

Workflow Diagram

Start Process
Step A
Step B
Step C
Complete
Quality

Concepts