Agent DailyAgent Daily
releaseintermediate

[Release] openclaw/openclaw v2026.5.31-beta.4: OpenClaw 2026.5.31 beta 4

By steipetegithub
View original on github

OpenClaw v2026.5.31-beta.4 introduces significant stability improvements for agent runtimes, channel delivery across multiple platforms, and a new Skill Workshop feature for governed skill creation. The release enhances recovery mechanisms from interrupted tool calls, strengthens mobile and messaging integrations, and adds SQLite-backed state management for more reliable restarts. Key improvements include better plugin/skill loading error handling, expanded provider support (MiniMax M3, Copilot Claude 1M), and a comprehensive Control UI overhaul with improved chat composition and navigation.

Key Points

  • Agents and CLI runtimes now recover cleanly from interrupted tool calls, stale session bindings, and media delivery retries through improved error handling
  • Skill Workshop feature enables governed skill creation with proposal lists, revision handoff, searchable file previews, and review states with approval workflows
  • Channel stability improved across Telegram, WhatsApp, iMessage, Slack, Discord, Teams, Google Chat/Meet with better session recovery and realtime Talk support
  • SQLite-backed state management for iMessage monitor state, plugin install ledgers, and inbound queues reduces duplicate filesystem scanning on restarts
  • Provider coverage expanded with MiniMax M3, Copilot Claude 1M capabilities, OpenRouter SQLite caching, and improved OAuth/device-code lifetime management
  • Plugin system externalized key components (Tokenjuice, GitHub Copilot) as official npm packages with ClawHub publish metadata
  • Control UI enhancements include calmer composer controls, Dreaming-tab agent selector, Communication Notifications settings, and incremental stream deltas
  • Workboard adds orchestration primitives and agent coordination tools for multi-agent planning with task-backed board runs
  • Gateway now supports Tailscale Serve service-name bindings for safer agent exposure and more reliable progress tracking
  • Improved skill/plugin loading handles stale disabled snapshots and loader failures with clearer recovery guidance for operators

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