Releases

LangChain Core version 1.4.3 has been released with improvements to OpenAI integration. The primary feature addition is support for the `apply_patch` built-in tool, enabling more flexible tool usage within OpenAI-powered agents. This incremental release builds on version 1.4.2 with focused enhancements to the core framework's tooling capabilities.

LangChain OpenAI package version 1.3.0 introduces support for the `apply_patch` built-in tool, updates minimum core dependencies, and refreshes model profile data. This release includes bug fixes, test improvements, and maintenance updates to ensure compatibility and stability. The update builds on version 1.2.2 with enhanced tooling capabilities and improved test infrastructure.

langchain-perplexity version 1.4.0 introduces tool binding capabilities and Responses-API tool round-trip functionality, enabling more sophisticated agent interactions. This release builds on version 1.3.2 with enhanced tool integration features. A hotfix for OpenAI's minimum core dependency is also included to ensure compatibility.

crewAI v1.14.7a4 introduces runtime migration for @listen/@router decorators to read from FlowDefinition and adds pluggable default backends for memory, knowledge, RAG, and flow components. This release enhances the framework's flexibility by allowing developers to swap backend implementations without code changes. The update includes documentation updates and contributions from three core team members.

Claude Code v2.1.170 introduces Claude Fable 5, a powerful Mythos-class model now available for general use with capabilities exceeding all previously released models. The release also fixes a critical bug where sessions launched from VS Code's integrated terminal failed to save transcripts and weren't resumable. Users should update to access Fable 5's enhanced capabilities and benefit from the session persistence fix.

OpenClaw v2026.6.5-beta.6 introduces critical fixes for QQBot reasoning stripping, MCP tool result coercion to prevent API errors, improved Anthropic extended-thinking recovery, Parallel web-search provider bundling, and enhanced durability for auth/plugin state via SQLite. The release strengthens security around MCP leases, prompt-cache tool names, and HTTP tools while improving macOS node stability and upgrade safety across multiple platforms.

crewAI v1.14.7a3 is a patch release addressing critical security vulnerabilities and bug fixes. Key improvements include fixing the exposure of `ask_for_human_input` on the experimental AgentExecutor, resolving CVEs in dependencies (aiohttp, docling, docling-core, pip), and refactoring the `@start` decorator to read from FlowDefinition. This release maintains stability while enhancing security posture and internal architecture.

Claude Code v2.1.169 introduces safe mode for troubleshooting, a `/cd` command for directory switching without breaking prompt cache, and a `disableBundledSkills` setting to control skill visibility. The release includes numerous bug fixes for MCP policy enforcement, UI responsiveness, remote session handling, and background agent reliability. Performance improvements reduce CPU usage during streaming and fix stalls on macOS and Windows.

OpenClaw v2026.6.5-beta.3 introduces critical fixes for model reasoning leakage in QQBot, MCP tool result coercion to prevent API errors, improved Anthropic extended-thinking session recovery, and a new bundled Parallel web-search provider. The release strengthens security around tool access, improves provider/model resolution reliability, and enhances durability of auth and plugin state through SQLite persistence. Multiple platform-specific improvements address macOS node reconnection issues, Matrix voice/thread handling, and mobile UI clarity.

OpenClaw v2026.6.5-beta.5 introduces critical stability and safety improvements across multiple channels and providers. Key fixes include QQBot reasoning stripping, MCP tool result coercion to prevent API errors, Anthropic extended-thinking session recovery, and Parallel web-search bundling. The release strengthens auth durability, provider model resolution, and agent/tool/provider loop safety while improving macOS node mode reliability and upgrade path safety.

OpenClaw v2026.6.5-beta.2 introduces critical fixes for model reasoning leakage, MCP tool result handling, Anthropic extended-thinking recovery, and adds Parallel as a bundled web-search provider. The release improves durability of auth/plugin state via SQLite, enhances Matrix voice/thread support, and strengthens upgrade/service paths with safer migration and configuration handling. Multiple provider integrations (Google Vertex, WhatsApp, Mattermost) receive reliability improvements alongside comprehensive test isolation and CI/E2E enhancements.

OpenClaw v2026.6.5-beta.1 is a major release focusing on content safety, provider reliability, and platform stability. Key improvements include QQBot reasoning stripping to prevent model thinking leakage, MCP tool result coercion to prevent API errors, Anthropic extended-thinking session recovery, Parallel web search bundling, and enhanced durability for auth/plugin state. The release addresses 50+ bug fixes across channels, providers, agents, and infrastructure with improved test isolation and CI/CD reliability.

LangChain released langchain-perplexity version 1.3.2, a patch update that fixes serialization issues for ToolMessage and AIMessage.tool_calls. This release addresses a critical bug in message handling that affects tool integration workflows. The fix ensures proper serialization of tool-related messages in the Perplexity integration, improving compatibility with LangChain's message processing pipeline.

ADK Python v2.2.0 introduces breaking changes including a default model migration from gemini-2.5-flash to gemini-3-flash-preview and terminology updates from "turns" to "steps" for GenAI SDK v2.0.0 compatibility. The release adds significant features like AutoTracingPlugin for OpenTelemetry, RubricBasedMultiTurnTrajectoryEvaluator, improved agent analytics, and enhanced tool capabilities. Multiple bug fixes address security vulnerabilities (CVE-2026-48710, path traversal), session management, Live protocol support for Gemini 3.1, and MCP initialization issues.

langchain-deepseek version 1.1.0 is a maintenance and feature release that includes dependency updates, infrastructure improvements, and bug fixes. Key changes involve bumping core dependencies (langchain-core, langsmith), security patches (Pygments CVE fix), and enhancements to model profile handling and streaming capabilities. The release standardizes integration testing, improves Azure endpoint detection, and adds content-block-centric streaming support from langchain-core.

OpenClaw v2026.6.2-beta.1 introduces a safer plugin/skill installation system using operator install policies instead of dangerous-code scanners, with enhanced security across messaging channels (Telegram, Discord, Feishu, WhatsApp). Major improvements include better chat UI streaming preservation, session management fixes, and comprehensive security hardening for config recovery and gateway operations. The release also strengthens CI/E2E validation with bounded network calls and improved error handling across Docker, packaging, and release processes.

crewAI 1.14.7a1 introduces native Snowflake Cortex LLM provider support and crew trained agents file functionality. The release includes integration guides for Databricks and Snowflake, fixes critical CLI and file input issues, and improves import performance through lazy-loading. Key refactoring splits flow.py into modular components while addressing tool result handling and multi-source listener reliability.

OpenClaw v2026.6.1 is a stability and reliability release focusing on improved recovery from interruptions, enhanced multi-channel support across messaging platforms, better resource management with bounded timers and retries, and new Skill Workshop features for governed skill creation and review. The release includes SQLite-backed state persistence for iMessage and plugin metadata, expanded provider coverage (MiniMax M3, Copilot Claude 1M), and significant UI/UX improvements in Chat and Control interfaces with streaming optimizations and draft management.

Claude Code v2.1.161 introduces enhanced observability through OTEL metric labels, improves parallel tool execution by allowing independent failures, and fixes critical issues with clipboard handling, authentication policies, and background session management. The release includes UI/UX improvements for agent progress display, MCP connector management, and accessibility features like motion reduction support. Multiple regressions and edge cases are resolved, particularly around git worktrees, file editing in isolated workflows, and telemetry initialization.

LangChain version 1.3.3 introduces improvements to subagent run projection onto typed channels and enhances the HumanInTheLoopMiddleware with interrupt_mode and conditional predicate support. The release includes a dependency bump for langgraph to 1.2.4 and loosens the langgraph version constraint for better compatibility. These changes improve agent orchestration capabilities and middleware flexibility for human-in-the-loop workflows.