[Release] openclaw/openclaw v2026.4.20: openclaw 2026.4.20

OpenClaw v2026.4.20 is a major release featuring UI/UX improvements to the onboarding wizard, enhanced agent prompts with better completion bias and verification, support for tiered model pricing including Moonshot Kimi models, session maintenance optimizations to prevent memory issues, and numerous fixes across plugins, APIs, and provider integrations. Key improvements include streaming thinking in Mattermost, better group-specific system prompts in BlueBubbles, and refined reasoning model handling across OpenAI GPT-5 and other providers.

Key Points

• •Redesigned onboarding wizard with yellow warning banners, section headings, bulleted checklists, and loading spinners for better UX during model catalog loads
• •Strengthened default system prompts with clearer completion bias, live-state checks, weak-result recovery, and verification-before-final guidance for agents
• •Implemented tiered model pricing support from cached catalogs with cost estimates for Moonshot Kimi K2.6/K2.5 models
• •Enforced session entry caps and age pruning by default, with oversized store pruning at load time to prevent OOM issues in gateway
• •Split cron runtime execution state into separate `jobs-state.json` file to keep `jobs.json` stable for git-tracked job definitions
• •Added opt-in start and completion notices during context compaction for better observability
• •Enabled per-group `systemPrompt` config forwarding in BlueBubbles with wildcard fallback matching for group-specific behavioral instructions
• •Implemented detached runtime registration contract for plugin executors to manage task lifecycle and cancellation independently
• •Optimized terminal logging sanitization with single regex pass instead of iterative control-character stripping
• •Fixed multiple provider-specific issues: OpenAI Codex transport normalization, Anthropic API scoping, Discord thinking autocomplete filtering, and reasoning effort handling

Workflow Diagram

Concepts