Agent DailyAgent Daily
releaseintermediate

[Release] openclaw/openclaw v2026.5.31-beta.3: openclaw 2026.5.31-beta.3

By steipetegithub
View original on github

OpenClaw v2026.5.31-beta.3 introduces significant stability improvements for agent runtimes, channel delivery, and plugin management. Key enhancements include better recovery from interrupted tool calls, steadier multi-channel support (Telegram, WhatsApp, Slack, Discord, Teams, etc.), and a new Skill Workshop for governed skill creation. The release also externalizes Tokenjuice and GitHub Copilot as official plugins, adds Tailscale Serve bindings, and implements bounded timers and retries across providers to prevent hangs.

Key Points

  • Agents and CLI runtimes now recover cleanly from interrupted tool calls, stale sessions, compaction handoffs, and media delivery retries with improved session lock management
  • Multi-channel delivery stabilized across 9+ platforms (Telegram, WhatsApp, iMessage, Slack, Discord, Teams, Google Chat/Meet, iOS) with better progress draft handling and notification settings
  • New Skill Workshop feature enables governed skill creation with CLI/Gateway review actions, versioned proposals, rollback safeguards, and the `skill_workshop` agent tool
  • Provider and plugin requests now have bounded timers, retries, OAuth/device-code lifetimes, and media downloads to prevent hangs and improve reliability
  • Skills and plugin loading handle stale disabled snapshots and loader failures more clearly, preventing disabled SecretRefs from aborting channel turns
  • Externalized Tokenjuice and GitHub Copilot as official npm/ClawHub plugins with improved orchestration and integration surfaces
  • Gateway setup adds Tailscale Serve service-name binding, Communication notification settings, and safer `agents add` command without provider catalog dependency
  • iOS realtime Talk improved with hosted push relay defaults, WebSocket ping paths, and better mobile session reliability
  • Workboard adds multi-agent orchestration primitives and coordination tools for planning and run tracking
  • CI/diagnostics lanes now cap logs, response bodies, and artifact checks to report bounded proof instead of stalling on failures

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