[Release] openclaw/openclaw v2026.5.30-beta.1: openclaw 2026.5.30-beta.1
OpenClaw v2026.5.30-beta.1 introduces significant stability improvements for agent runtimes, CLI tools, and multi-channel delivery across Telegram, WhatsApp, Slack, Discord, and other platforms. Key enhancements include better recovery from interrupted tool calls, bounded timers and retries to prevent hangs, and new orchestration primitives through Workboard and SecretRef integrations. The release externalizes Tokenjuice and GitHub Copilot as official plugins, adds Skill Workshop proposal lifecycle management, and improves iOS push relay reliability. Extensive fixes address cron migrations, provider media downloads, session cleanup, and CI/E2E test coverage routing.
Key Points
- •Agents and CLI runtimes now recover cleanly from interrupted tool calls, stale sessions, and media delivery retries with improved session lock management and orphan state cleanup
- •All provider and plugin requests now have bounded timers, retries, OAuth lifetimes, and media download limits to prevent runs from hanging
- •Multi-channel delivery (Telegram, WhatsApp, iMessage, Slack, Discord, Teams, Google Chat, iOS) improved with steadier connections and guarded WebSocket ping paths
- •Skill Workshop proposals now support full lifecycle: creation, revision with versioned frontmatter, approval/rejection through skill_research agent tool, and rollback safeguards
- •Workboard adds multi-agent orchestration primitives and run tracking; Code mode adds internal namespaces for scoped agent/global sessions
- •Tokenjuice and GitHub Copilot externalized as official npm plugins (@openclaw/tokenjuice, @openclaw/copilot) with ClawHub publish metadata
- •SecretRef provider integration manifest contract and shared LLM core packages enable better provider/plugin reuse and security
- •Release/CI/E2E lanes now cap logs, response bodies, readiness probes, and artifact checks with bounded proof instead of stalling on failures
- •SQLite cron migrations maintain compatibility with legacy run-log tables and archived job stores; recurring jobs retry after transient rate limits
- •Performance optimizations: prebuild QA probes with plugin assets, skip declaration bundling for CLI startup, reuse prepared provider handles and gateway metadata
Found this useful? Add it to a playbook for a step-by-step implementation guide.