Tool Use

crewAI 1.14.2a3 is a patch release introducing a deploy validation CLI and improved LLM initialization ergonomics. The release addresses critical security vulnerabilities in pypdf, uv, and requests libraries, plus fixes for Bedrock tool arguments, strict mode schema sanitization, and test flakiness. Documentation updates include enterprise A2A feature clarifications and OSS A2A improvements.

OpenClaw v2026.4.11 introduces major enhancements to memory/dreaming features with ChatGPT import ingestion, improved media rendering in chat UIs, expanded video generation capabilities, and better integration with platforms like Feishu and Microsoft Teams. The release includes plugin manifest improvements for declarative setup flows, performance optimizations for model discovery caching, and numerous bug fixes across OAuth, transcription, timeouts, and platform-specific issues to improve stability and user experience.

OpenClaw v2026.4.11-beta.1 introduces significant enhancements to memory/dreaming features with ChatGPT import ingestion, improved media rendering in chat UIs, expanded video generation capabilities, and better integration with Feishu and Microsoft Teams. The release includes numerous fixes for OAuth flows, audio transcription, TTS persistence, and configuration handling, plus improved plugin manifest descriptors and model provider diagnostics.

OpenClaw v2026.4.10 introduces major features including Codex provider integration for GPT models, an Active Memory plugin for context-aware conversations, experimental local MLX speech support for macOS, and expanded QA testing capabilities with Matrix and Telegram lanes. The release includes extensive security hardening across browser navigation, tool execution, and WebSocket handling, plus numerous fixes for Microsoft Teams integration, WhatsApp media delivery, gateway startup stability, and agent-based tool use.

langchain-core version 1.3.0a1 is an alpha release featuring performance improvements, security hardening, and bug fixes. Key updates include reduced streaming metadata overhead, enhanced anti-SSRF protections, improved token counting with multimodal support, and numerous stability fixes across serialization, tool handling, and model integrations. The release represents incremental improvements building on the 1.2.x series with focus on reliability and developer experience.

Claude Code v2.1.101 introduces significant improvements to team collaboration, enterprise security, and user experience. Key additions include a `/team-onboarding` command for generating ramp-up guides, OS CA certificate store trust for enterprise TLS proxies, and auto-creation of cloud environments for remote sessions. The release focuses on enhancing error messaging, fixing critical bugs in session management, and improving plugin/MCP tool reliability across various authentication providers and platforms.

crewAI 1.14.2a2 introduces a checkpoint TUI with tree view and fork support, enhances LLM token tracking with reasoning and cache tokens, and adds checkpoint forking with lineage tracking. The release includes bug fixes for strict mode forwarding to Anthropic and Bedrock providers, and hardens the NL2SQLTool with read-only defaults and query validation. Key additions include the `from_checkpoint` parameter for kickoff methods and embedding `crewai_version` in checkpoints with a migration framework.

Google ADK Python v1.29.0 introduces significant enhancements to authentication, security, and tooling capabilities. Key additions include auth scheme/credential support for MCP toolsets, configurable resource limits and shell metacharacter blocking in BashTool, new EnvironmentToolset for file I/O and command execution, and improved BigQuery logging with configurable view prefixes. The release also adds support for model endpoints in Agent Registry, regional endpoints for SecretManager, and enhanced session management with custom session IDs and shallow-copy options.

Claude Code v2.1.98 introduces significant security enhancements, including subprocess sandboxing with PID namespace isolation, Perforce mode for read-only file protection, and fixes for multiple Bash permission bypass vulnerabilities. The release adds interactive Google Vertex AI setup, improved monitoring capabilities, and numerous UI/UX improvements including better `/resume` picker functionality and Vim mode navigation. Critical fixes address permission rule evaluation, MCP OAuth token refresh, and cross-user prompt caching.

OpenAI Agents Python v0.13.6 release includes three critical bug fixes: lazy-loading SQLiteSession exports to improve performance, stopping recursive trace preview truncation for better debugging, and hardening SQLAlchemySession against transient SQLite locks for improved reliability. Documentation updates include new HoneyHive tracing integration and translated page updates. This patch release focuses on stability and developer experience improvements.

This tutorial demonstrates building a webhook-triggered SRE incident response agent using Claude Managed Agents that automatically investigates production alerts, consults runbooks, proposes infrastructure fixes via pull requests, and gates merging behind human approval. The agent combines built-in sandbox tools (bash, read, edit) with custom tools for PR management and human-in-the-loop approval, providing complete audit trails in the Anthropic Console. The example uses mocked PagerDuty, GitHub, and Datadog integrations to focus on agent patterns, with guidance for swapping in real services.

This tutorial introduces the Claude Managed Agents API by walking through a practical debugging workflow where an agent iteratively fixes failing tests in a Python package. It covers the three core resources (Agent, Environment, Session), file mounting, and the streaming event loop pattern. The example demonstrates how agents autonomously discover the iterate-observe-fix loop by running tests, reading failures, editing code, and repeating until all assertions pass.

This cookbook demonstrates building a Slack data analyst bot using Claude Managed Agents and Bolt for Python. Users mention the bot with a CSV file to receive narrative analysis reports in-thread, with support for multi-turn follow-ups within the same session. The implementation handles file uploads, streams agent progress updates, and manages session persistence across Slack threads.

Claude Code v2.1.97 introduces a focus view toggle for better prompt visibility, enhanced status line customization with git worktree support, improved permissions handling with stricter Bash tool checks, and numerous bug fixes across MCP connections, resume functionality, NO_FLICKER mode rendering, and authentication. The release also improves auto-approval logic for safe commands, image compression consistency, and CJK text input handling.

LangChain Core version 0.3.84 has been released with improvements to prompt sanitization. This patch release follows version 0.3.83 and includes a fix that enhances how prompts are processed and cleaned within the core library. The changes focus on improving data handling and security in prompt processing.

LangChain Core version 1.2.28 has been released with improvements to template sanitization. This patch release follows version 1.2.27 and includes a fix that adds enhanced sanitization logic to templates, improving security and robustness. The release is part of the ongoing LangChain framework maintenance and development cycle.

crewAI 1.14.1rc1 introduces async checkpoint TUI browser and streaming output enhancements, along with critical security updates and architectural improvements. Key changes include CVE-2026-1839 resolution via transformers bump, dynamic tool field exclusion, and refactored provider architecture using BaseModel discriminators. The release focuses on async/streaming capabilities, security hardening, and code quality improvements across the framework.

crewAI 1.14.1 introduces async checkpoint TUI browser functionality and improves streaming output handling with async context managers. The release includes critical security updates (CVE-2026-1839 fix via transformers bump), bug fixes for checkpoint registration and tool name sanitization, and architectural refactoring to use dynamic field exclusion and shared singleton patterns. Key improvements enhance developer experience through better CLI tooling and provider type discrimination.

langchain-tests version 1.1.6 is a maintenance release that includes updates to standard tests for sandbox backends, security patches for Pygments (CVE-2026-4539), and dependency bumps across multiple packages including requests, orjson, and other utilities. The release also includes CI/CD improvements such as pytest streaming output suppression and optimized dependency installation in lint targets.

Claude Code v2.1.96 is a patch release that fixes a critical Bedrock authentication regression introduced in v2.1.94. The fix addresses 403 authorization errors when using AWS_BEARER_TOKEN_BEDROCK or CLAUDE_CODE_SKIP_BEDROCK_AUTH environment variables. This release restores proper header handling for Bedrock API requests.