Tool Use

OpenAI Agents Python v0.14.3 is a maintenance release focused on Windows compatibility and stability improvements. Key fixes include normalizing sandbox paths for Windows support, making sandboxes importable on Windows, preparing Daytona workspace roots, and improving manifest handling. The release also adds Datadog as an external tracer option and includes documentation updates.

crewAI v1.14.3a1 introduces checkpoint and fork support for standalone agents, enhancing workflow management capabilities. The release includes critical bug fixes for Gemini streaming tool calls, checkpoint TUI redesign, and dry-run ordering. Documentation has been updated to reflect the new version and changelog entries.

OpenClaw v2026.4.19-beta.1 releases critical fixes addressing cross-agent channel routing, Telegram callback handling, browser CDP connectivity, and Codex token accounting. Key improvements include proper account preservation in multi-agent setups, prevention of stale pagination buttons blocking updates, WSL-to-Windows Chrome endpoint detection, and accurate context usage reporting. Enhanced diagnostics for Windows browser startup failures provide better troubleshooting visibility.

OpenAI Agents Python v0.14.2 release introduces sandbox extra path grants, MongoDB session backend support, and tool origin metadata persistence. The release includes 11 bug fixes addressing sandbox parsing, tool removal, response handling, and session management. Documentation updates and dependency bumps round out the release with contributions from 9 new community members.

Claude Code v2.1.114 is a minor release that addresses a critical bug fix in the permission dialog system. The update resolves a crash that occurred when an agent teams teammate requested tool permission, improving stability and reliability for collaborative agent workflows.

Claude Code v2.1.113 introduces a native binary CLI replacing bundled JavaScript, enhances security with improved sandbox controls and bash rule matching, and fixes numerous UI/UX issues including fullscreen scrolling, multiline input navigation, and markdown rendering. Key improvements include faster /ultrareview with parallelization, better subagent error handling with 10-minute timeouts, and expanded Remote Control client capabilities. The release also addresses critical bugs in session management, MCP tool handling, and cross-platform compatibility.

langchain-anthropic version 1.4.1 is a maintenance and feature release that includes support for Claude Opus 4.7 features and adaptive thinking mode, fixes for null encrypted_content in compaction blocks, dependency updates (langsmith 0.7.31, pytest 9.0.3), and security patches for Pygments CVE-2026-4539. The release also updates model profiles and improves documentation with typo fixes.

langchain-core version 1.3.0 has been released with improvements to streaming metadata, traceable invocation parameters, SSRF security hardening, and garbage collection support. Key changes include adding chat model and LLM invocation params to traceable metadata, restoring cloud metadata IPs in SSRF policy, and implementing reference counting for inherited run trees. The release also includes dependency updates and bug fixes for OpenAI responses API conversion.

crewAI 1.14.2 introduces checkpoint management features including resume, diff, and prune commands with lineage tracking and forking capabilities. The release enhances LLM token tracking with reasoning and cache tokens, improves CLI ergonomics for deploy validation and template management, and fixes multiple security vulnerabilities across dependencies. Key improvements include scoped streaming handlers to prevent data contamination, recursive glob for checkpoint discovery, and better HITL (Human-in-the-Loop) resume event handling.

Google ADK Python v1.31.0 introduces significant enhancements including Vertex AI Agent Engine Sandbox integration for computer use, Firestore support, and improved memory management with VertexAiMemoryBankService. The release adds user agent tracking to Parameter and Secret Manager clients, includes live session tracking in LlmResponse, and resolves multiple bugs related to event callbacks, BigQuery plugin issues, and authentication headers. Several refactoring improvements modernize the live session API and update MCP Toolbox documentation.

langchain-core version 1.3.0a3 is released with improvements to streaming metadata, chat model invocation parameters, SSRF security hardening, and various bug fixes. Key updates include checkpoint namespace behavior preservation for backwards compatibility, enhanced traceable metadata for chat models and LLMs, and fixes for OpenAI responses API conversion. The release includes dependency updates (pytest 9.0.3) and security patches for CVE-2026-4539 related to Pygments.

langchain-huggingface version 1.2.2 is a maintenance release that hardens hostname validation and rejects URLs in repo_id fields. The release includes security updates (CVE-2026-4539 via pygments), dependency bumps for langsmith, pytest, aiohttp, and other packages, and performance improvements like avoiding unnecessary HuggingFace API calls for local endpoints. Key changes focus on stability, security, and dependency management across the HuggingFace partner library.

OpenClaw v2026.4.15 is a major release featuring Claude Opus 4.7 as the default Anthropic model, new Google Gemini text-to-speech support, a Model Auth status card for OAuth health monitoring, cloud storage support for LanceDB memory, and GitHub Copilot embedding provider integration. The release includes numerous stability fixes across gateway tools, agent replay recovery, Docker builds, Matrix E2EE, memory management, and channel integrations, plus packaging improvements to reduce bundle size and plugin runtime dependencies.

OpenClaw v2026.4.15-beta.2 introduces Anthropic model updates with Claude Opus 4.7 as the default and new Gemini text-to-speech support in the Google plugin. The release includes improvements to gateway tool handling with enhanced security for local media tool-result passthrough and stricter validation of client tool definitions. Key enhancements focus on model defaults, TTS capabilities, and tool registration robustness.

Claude Code v2.1.111 introduces Claude Opus 4.7 with a new xhigh effort level for tuned speed/intelligence tradeoffs, Auto mode for Max subscribers, and significant UX improvements including interactive effort sliders, comprehensive code review via /ultrareview, and enhanced permission management. The release includes numerous bug fixes for terminal display, LSP diagnostics, plugin handling, and cross-platform compatibility, particularly for Windows PowerShell integration.

langchain-openai version 1.1.14 was released with a critical security fix for SSRF (Server-Side Request Forgery) vulnerabilities in image token counting. The release includes dependency updates for pytest, langsmith, and pillow libraries. This patch addresses potential security risks when processing images through the OpenAI integration.

langchain-text-splitters version 1.1.2 is released with critical security and stability improvements. Key changes include deprecating unsafe URL transport in favor of SSRF-safe alternatives, fixing silent data loss in RecursiveJsonSplitter for empty dict values, and addressing CVE-2026-4539 through pygments version constraints. The release also includes dependency updates (langsmith, pytest, nltk, requests) and performance optimizations for CI/CD pipelines.

Claude Code v2.1.110 introduces significant UI/UX improvements including a new `/tui` command for flicker-free fullscreen rendering, push notification capabilities, and enhanced plugin management. The release includes numerous bug fixes addressing MCP server reliability, session management, and performance issues, plus improvements to command accessibility from Remote Control clients and better handling of distributed tracing.

crewAI 1.14.2rc1 is a release candidate that addresses critical bug fixes and security vulnerabilities. The release includes fixes for cyclic JSON schema handling in MCP tool resolution and security patches for python-multipart and pypdf dependencies. This maintenance release ensures improved stability and security for the crewAI framework.

OpenAI's openai-agents-python v0.14.0 introduces Sandbox Agents, a beta feature enabling agents to run in persistent, isolated workspaces with file access, command execution, and cross-run continuity. The release includes multiple execution backends (local, Docker, hosted providers), workspace management with snapshots and resume capabilities, sandbox memory for learning across runs, and comprehensive examples. Runtime enhancements provide tracing, session lifecycle management, and seamless integration with the existing Agent and Runner framework.