Releases

langchain-openai version 1.5.0 has been released with support for OpenAI 3.0 SDK. This update includes compatibility improvements and dependency updates for langgraph in the openai and huggingface partner packages. The release represents a significant upgrade from version 1.4.3 with enhanced OpenAI integration capabilities.

Claude Code v2.1.231 is a patch release that fixes a critical MCP OAuth sign-in issue where redirect URI mismatches were causing authentication failures for servers using pre-registered OAuth clients like Slack. This update ensures proper OAuth flow handling for integrated services.

langchain-anthropic version 1.5.6 was released with three key fixes: normalization of `tool_search_tool_result` blocks, correction of model profile data for Fable 5, Sonnet 5, and Opus 4.1 models, and general release updates. This patch release addresses tool handling and model configuration issues in the Anthropic integration for LangChain.

Claude Code v2.1.229 introduces server-supplied hook support for self-hosted runners, adds SSE keepalive pings to prevent streaming timeouts, and implements plugin marketplace command sources for dynamic plugin resolution. The release fixes 25+ bugs spanning streaming issues, file path handling, MCP OAuth, workflow execution, and UI stability. Key improvements include staggered workflow fan-outs for prompt caching efficiency, better error messaging for prompt length issues, and VSCode enhancements like resizable side panels and session grouping.

crewAI v1.15.15 introduces enhanced flow reporting capabilities with outcome, duration, and human-in-the-loop signal tracking. The release includes critical security updates for torch and gitpython dependencies, fixes for event emission during boundary hook aborts, and standardization of CLI flags to kebab-case. Bug fixes also address span export scoping to prevent tracer provider conflicts.

Claude Code v2.1.228 is a maintenance release fixing critical bugs in interactive sessions, Git integration on Windows, model switching, cross-session messaging, and self-hosted runners. Key improvements include hardened skill syncing from claude.ai, better Vertex AI credential handling, improved UI feedback during compaction, and updated file-writing permissions for newer models. The release addresses 17 distinct issues spanning session stability, remote control functionality, plugin caching, and settings management.

OpenAI Agents Python v0.20.0 is a minor release introducing GPT-5.6-Luna as the default model, adding support for MCP Python SDK v1 and v2, and enhancing RunState with durable pending input staging. The release includes significant improvements to sandbox mount validation, realtime transcription settings, and numerous bug fixes across tool guardrails, serialization, and session management. Applications with custom MCP HTTP transports must migrate to httpx2 or pin mcp<2 to avoid breaking changes.

Claude Code v2.1.227 addresses critical bugs in feature flag evaluation for subscription tiers, Bash command execution on GitHub runners, and TUI conversation rewinding. The release also enhances the slash-command menu UI with better visual feedback and improves overall performance by reducing event-loop stalls during file operations and mention checks.

langchain-openai version 1.4.3 release includes a critical fix for filtering invalid tool calls from content, updated guidance for the responses API to support OpenAI-compatible providers, and improved documentation for the `include_response_headers` parameter. This patch release addresses tool call validation issues and enhances compatibility with third-party OpenAI-compatible API providers.

Google ADK Python v1.38.0 release introduces safety settings forwarding to the Live API and addresses critical security and stability issues. Key improvements include preventing shell execution vulnerabilities in ReadFileTool, excluding problematic nltk dependency versions, fixing Live API agent transfers, and enhancing evaluation error handling. This release focuses on security hardening and reliability improvements for agent development.

crewAI version 1.15.13 is a maintenance release focusing on bug fixes and documentation improvements. Key fixes include preserving LiteLLM provider routing, hardening LLM event-bus mocks, correcting Anthropic cache token usage reporting, and addressing a security vulnerability in the h2 dependency. Documentation enhancements include a new locale synchronization workflow and corrections to README links and contribution guidance.

langchain-openai version 1.4.2 is a patch release that addresses several critical issues with OpenAI integration. Key fixes include proper handling of context window exceeded errors, filtering of langchain-generated content block IDs, preservation of response text options, and redaction of MCP authorization headers. The release also includes dependency updates and refreshed model profile data.

Claude Code v2.1.223 introduces owner wildcard marketplace controls, improves security by fixing permission bypass vulnerabilities and sandbox escapes, and enhances model discovery and session management. Key updates include stricter command obfuscation prevention, workflow sandbox isolation fixes, and better handling of context windows across Claude models. The release also refines the code review workflow and improves managed settings merging for enterprise deployments.

langchain-anthropic version 1.5.4 release includes bug fixes for tool schema handling with unsupported top-level composition and tool_choice preservation, a new user_profile_id convenience attribute, and dependency bumps across 3 directories. This patch release improves compatibility with Anthropic's API and enhances developer convenience when working with tool configurations.

crewAI 1.15.12 introduces URLReadTool for arbitrary URL reading, unifies resource scaffolding under a single `crewai create` command, and adds app metadata to platform action tools. Bug fixes clarify conversational route/handler name collision errors, with updated documentation for the new unified CLI. No breaking changes are included in this release.

crewAI v1.15.11 introduces enhanced telemetry tracking for interception-hook dispatches and project_id linking for enterprise accounts, adds IBM Db2 search tool support, and surfaces AMP (Agent Management Platform) in documentation. The release includes critical security updates for aiohttp and cryptography dependencies, fixes CodeQL alerts, and improves CI/CD pipeline efficiency by skipping code checks for documentation-only PRs.

Claude Code v2.1.222 is a maintenance release focused on security hardening, bug fixes, and stability improvements. Key fixes address worktree isolation for destructive git commands, tool restriction bypasses in background tasks, proxy connectivity issues, and usage attribution accuracy. The release also improves auto mode safety, refines model selection precedence, and removes the ultraplan feature.

OpenClaw v2026.7.1-2 is a patch release that fixes npm plugin compatibility issues. The update enables the npm plugin to accept singleton-array metadata from newer npm clients, allowing tracked official plugins to properly install and update to correction releases. This resolves a blocking issue (#108336) that prevented plugin updates.

crewAI v1.15.10 introduces skill usage event collection capabilities, enabling better tracking and monitoring of agent skill utilization. The release includes documentation updates removing migrated AMP content and refreshing security reporting guidelines. This minor version update maintains stability while adding observability features for skill performance analysis.

Google ADK Python v2.6.0 introduces significant enhancements for agent development, including per-invocation auth headers for A2A, new evaluation samples, OAuth2 improvements, and telemetry capabilities. Key additions include the ReflectAndRetryModelPlugin for self-healing, OCI Generative AI provider integration, Eventarc Advanced toolset, and ManagedAgent instruction field support. The release also improves CLI functionality with telemetry consent checks, command logging, and enhanced error handling across multiple agent frameworks.