Skills & Tools

OpenClaw v2026.5.16-beta.1 is a maintenance and stability release featuring improved skill caching, multi-language onboarding support, and numerous bug fixes across agents, providers, and integrations. Key improvements include resolved token counting for OpenAI APIs, enhanced Telegram reliability, better config validation, and fixes for critical issues in cron jobs, Discord, LINE, and local agent execution. The release strengthens platform robustness through better error handling, lifecycle management, and provider compatibility.

Claude Code v2.1.143 introduces plugin dependency enforcement, projected context costs in the marketplace, and improved background session management. Key fixes address credential corruption, PowerShell execution policies, stop hook infinite loops, and Windows Terminal compatibility issues. The release enhances session persistence across idle states and adds new configuration options for agent dispatching.

OpenClaw v2026.5.14-beta.2 introduces significant enhancements to agent configuration, channel integrations, and platform stability. Key improvements include per-agent bootstrap profile overrides, WhatsApp status reactions, voice call support via Telnyx, lazy-loading of Canvas modules for faster startup, and comprehensive dependency management. The release also strengthens maintainer tooling, adds Docker-based release validation, and fixes critical issues in provider routing, media handling, and protocol compilation.

Claude Code v2.1.142 introduces enhanced agent configuration flags for background sessions, upgrades fast mode to Opus 4.7, improves plugin skill surfacing and LSP server visibility, and fixes critical issues with daemon stability, background session persistence, and cross-platform compatibility. Key improvements include better MCP tool timeout handling, macOS sleep/wake resilience, Windows network drive support, and numerous UI/UX refinements for plugin management and session handling.

OpenClaw v2026.5.14-beta.1 introduces significant improvements to dependency management, UI/i18n tooling, maintainer workflows, and channel integrations. Key additions include WhatsApp status reactions, voice call support via Telnyx, browser-local text sizing, and enhanced release validation through Docker user-journey lanes. The release also refactors Codex CLI integration, improves gateway startup tracing, and fixes critical issues with UTF-16 surrogates, HTTP/2 session errors, and memory file discovery.

OpenClaw v2026.5.12-beta.5 is a comprehensive bug-fix release addressing gateway protocol improvements, security hardening, plugin dependency management, channel integrations (WhatsApp, Telegram, Discord, WeCom), session transcript redaction, and agent execution reliability. Key fixes include OAuth token exchange for Copilot, device pairing approval requirements, media size enforcement across plugins, and LLM idle watchdog timeout escalation. The release improves stability across multiple integrations while strengthening security controls for trusted proxies, admin scopes, and sensitive data redaction.

Claude Code v2.1.140 releases multiple bug fixes and improvements focused on agent tool matching, background service reliability, settings management, and terminal behavior. Key enhancements include case-insensitive subagent type matching, fixed `/goal` command hanging issues, improved background service startup on enterprise networks, and resolved event-loop stalls on Windows. The release also addresses validation issues with the Read tool and improves plugin diagnostics.

crewAI 1.14.5a5 is a pre-release update that deprecates CrewAgentExecutor in favor of AgentExecutor, improves Daytona sandbox tools, and addresses multiple security vulnerabilities in dependencies. The release includes bug fixes for HITL workflows, logging enhancements, and comprehensive documentation updates including migration guides for state restoration and crew-to-flow transitions.

OpenClaw v2026.5.12-beta.2 releases critical fixes and enhancements across authentication, provider streams, memory management, and UI/UX. Key improvements include auth-profile-backed media tools availability, subagent session visualization, error handling in auto-reply, and provider stream reliability. The release also upgrades to pnpm 11, adds per-agent tool policies, expands Slack/Gemini/Fal provider support, and strengthens TypeScript/linting standards.

OpenClaw v2026.5.12-beta.1 is a maintenance and feature release addressing security, UI/UX, and provider integrations. Key improvements include memory-wiki admin scope requirements, subagent session hierarchy visualization, Gemini 3 model normalization, enhanced tool policies, and expanded Slack/iMessage channel support. The release also upgrades build infrastructure to pnpm 11 and refines plugin SDK public APIs.

Claude Code v2.1.139 introduces significant new features including an agent view for managing multiple sessions, a `/goal` command for multi-turn task completion, and enhanced MCP server support with environment variables. The release includes numerous UX improvements like transcript navigation shortcuts, plugin token cost estimation, and fixes for critical issues such as credential deadlocks, memory leaks in MCP servers, and terminal interaction bugs.

OpenClaw v2026.5.10-beta.4 introduces significant enhancements across CI/CD, runtime detection, provider integrations, and agent capabilities. Key improvements include Fly Machines container environment detection, expanded Fal provider image editing support, stricter build tooling (oxlint, Vitest, TypeScript), and enhanced Slack integration with link/media unfurling controls. The release also upgrades to pnpm 11, adds per-agent message tool overrides, improves Discord voice diagnostics, and deprecates legacy Plugin SDK subpaths while exposing active model metadata.

OpenClaw v2026.5.10-beta.5 introduces significant improvements across CI/CD, runtime detection, provider integrations, and agent capabilities. Key updates include Fly Machines container detection, enhanced Fal provider image editing, stricter build tooling (oxlint, Vitest, TypeScript), pnpm 11 upgrade, and expanded agent-to-agent communication limits. The release also adds Slack thread management improvements, Discord voice diagnostics, plugin SDK deprecations, and QA automation enhancements for Telegram and Mantis.

OpenClaw v2026.5.10-beta.2 introduces significant enhancements across QA automation, voice capabilities, and provider compatibility. Key additions include Telegram live PR evidence automation with Crabbox integration, realtime voice diagnostics for Discord, and improved CLI onboarding. The release includes 30+ dependency updates and numerous bug fixes addressing session management, model compatibility, and gateway stability.

OpenClaw v2026.5.10-beta.1 introduces significant enhancements to QA automation, real-time voice diagnostics, and gateway security. Key additions include Telegram live PR evidence automation with Crabbox integration, Discord voice diagnostics, and private skill archive uploads. The release also includes numerous bug fixes across CLI, agent routing, model compatibility, and chat delivery systems, plus dependency updates for improved performance and security.

Google ADK Python v1.33.0 introduces BufferableSessionService, configurable environment tool truncation limits, and enhanced LlmResponse with function call/response accessors. The release includes 11 bug fixes addressing session state management, video event filtering, authentication error handling, and async event loop blocking. Code refactoring improves workflow metrics computation and removes deprecated input/output type attributes from ADK metrics.

Claude Code v2.1.133 introduces enhanced worktree configuration with `worktree.baseRef` settings, improved sandbox path management for Linux/WSL, and critical fixes for parallel sessions, proxy handling, and effort level synchronization. The release addresses memory efficiency, credential management, and cross-session consistency issues while improving focus mode behavior and MCP OAuth flow support.

This guide teaches how to build a grade-and-revise loop using Outcomes in Claude Managed Agents, where a writer agent drafts a cited research brief and a stateless grader independently verifies every URL, quote, and claim against a detailed rubric. The grader provides structured feedback that drives revisions until the brief passes, eliminating manual review cycles. Key techniques include writing specific, actionable rubrics that force concrete evidence, using span.outcome_evaluation_* events to track the loop, and understanding when Outcomes is the right tool for quality assurance.

This cookbook demonstrates building a multiagent coordinator system using Claude Managed Agents to automate sales-proposal generation. A coordinator agent orchestrates three specialist subagents—a web-search researcher, a case-study librarian, and a rules-based pricing modeler—each with scoped toolsets and specific responsibilities. The pattern shows how to structure heterogeneous teams, use per-role tool scoping, and leverage thread_created/thread_message_received events for agent coordination to assemble tailored sales proposals.

OpenAI Agents Python SDK v0.16.0 introduces significant updates including a default model change from gpt-4.1 to gpt-5.4-mini, new configuration options for disabling max_turns limits, SDK-side tool execution concurrency control, and server-prefixed MCP tool naming to prevent conflicts. The release also includes stability fixes for tool call output indexes and security improvements for symlink handling. These changes enhance performance and provide greater flexibility for agent configuration while maintaining backward compatibility through explicit model specification.