Tool Use

OpenClaw v2026.5.3-beta.3 introduces a bundled file-transfer plugin with secure binary file operations, hardens plugin installation workflows, and optimizes Gateway performance through lazy-loading. Major improvements include enhanced channel support (WhatsApp, Discord, Telegram), improved agent runtime reliability, and numerous fixes for edge cases in streaming, transcription, and configuration management. The release emphasizes security (default-deny policies, symlink traversal protection), performance (startup optimization, hot-path trimming), and operational robustness (doctor command enhancements, state recovery).

langchain-anthropic version 1.4.3 has been released with several improvements and fixes. Key changes include refactoring deprecation targets for the classic agent creation, updating documentation references, and fixing httpx finalizer guards in the Anthropic integration. This release maintains compatibility while addressing technical debt and improving the integration's stability.

langchain-classic version 1.0.5 has been released with several maintenance updates and dependency bumps. Key changes include retargeting deprecations to `create_agent`, uncommenting optional dependencies, and updating various type stubs and libraries. The release also includes hotfixes for minimum core versions and improvements to streaming functionality in the core package.

OpenClaw v2026.5.3-beta.2 introduces a bundled file-transfer plugin with secure binary file operations, hardens plugin installation and updates, and improves gateway performance through lazy-loading. The release enhances channel reliability across Discord, WhatsApp, Telegram, and other platforms, while fixing critical issues in agent runtime, memory status reporting, and macOS upgrades. Key improvements focus on security (path policies, symlink traversal), performance (startup optimization), and reliability (streamed replies, session recovery).

OpenAI Agents Python v0.15.1 is a maintenance release focusing on WebSocket keepalive options, PTY terminal signal handling fixes, and improved documentation. Key improvements include exposing Responses WebSocket keepalive configuration, restoring UnixLocal PTY terminal signal defaults, and fixing SIGINT handling for PTY child processes. The release also enhances Windows OS quickstart documentation and strengthens test coverage for guardrail functionality.

LangChain released langchain-fireworks version 1.3.0, introducing a new `service_tier` initialization parameter for the `ChatFireworks` class. This update includes model profile data refresh and represents an incremental feature addition to the Fireworks integration. The release enables users to specify service tier configurations when initializing Fireworks chat models.

langchain-mistralai version 1.1.3 introduces image input support for human messages and updates core streaming capabilities with content-block-centric streaming (v2). The release includes dependency updates, security patches (CVE-2026-4539 via pygments), model profile refreshes, and infrastructure improvements. Key changes involve bumping minimum core versions, updating langsmith to 0.7.31, and standardizing integration test invocation across partner packages.

langchain-openrouter v0.2.2 release introduces new `session_id` and `trace` fields for enhanced tracking and observability. The release includes content-block-centric streaming improvements, dependency updates (langsmith 0.7.22→0.7.31, pytest 9.0.3), security patches (pygments CVE-2026-4539), and multiple model profile refreshes. Key fixes address token extraction in usage metadata and core version compatibility.

langchain-openrouter version 0.2.3 has been released with a critical bug fix for streaming functionality. The main improvement addresses fragmented `reasoning_details` that were being split across multiple streaming chunks. This fix ensures that reasoning details are properly merged during streaming operations, improving the reliability of OpenRouter integration in LangChain.

LangChain v1.3.0a1 is an alpha release featuring stream_events(version='v3') protocol integration into create_agent, HITL middleware enhancements with a 'respond' decision, and performance optimizations including reduced agent state inlining and LRU caching for type resolution. The release includes updates across multiple partner packages (Fireworks, Anthropic, OpenAI), dependency bumps for security (Pygments CVE-2026-4539, cryptography), and improvements to token counting, middleware initialization speed, and agent configuration. Key infrastructure changes include content-block-centric streaming (v2), dynamic tool registration via middleware, and enhanced LangSmith integration metadata.

crewAI v1.14.5a1 introduces the `restore_from_state_id` kickoff parameter for state management and enhances the ExaSearchTool with highlights while renaming it from EXASearchTool. Bug fixes address missing crewai pin sites in the release flow and ensure proper skills loading events for traces. This alpha release includes documentation updates and contributions from five team members.

langchain-core version 1.4.0a1 is an alpha release featuring the new stream_events(version='v3') protocol for improved event streaming. The release includes fixes for structured inputs preservation in tool runs, optional removal parameters in deprecation warnings, and batch size validation to prevent infinite loops. Key improvements focus on streaming capabilities, tracer metadata handling, and various bug fixes across core functionality.

langchain-core version 1.4.0a2 is released with significant improvements to event streaming, tracing, and core functionality. Key updates include unwinding the _AsyncEventsResult hybrid implementation, introducing stream_events(version='v3') protocol, and preserving structured inputs on tool runs in tracers. The release includes numerous bug fixes, performance optimizations, and dependency updates across the LangChain ecosystem.

Google ADK Python v1.32.0 introduces significant enhancements to agent development capabilities, including native OpenTelemetry metrics, Anthropic thinking blocks support, improved authentication mechanisms (2LO/3LO via GcpAuthProvider), and express mode deployment. The release addresses critical security vulnerabilities (RCE via YAML, SSRF), fixes parallel tool execution issues, and improves analytics with BigQuery LLM cache metadata logging and credential isolation to prevent race conditions.

OpenAI Agents Python v0.15.0 introduces explicit model refusal handling through a new `ModelRefusalError` exception, replacing previous behavior where refusals were treated as empty output or caused retry loops. The release includes a `model_refusal` error handler that allows developers to gracefully handle refusals without raising exceptions. For structured-output agents, handlers can return values matching the output schema for validation. Additional updates include documentation improvements and dependency bumps.

Claude Code v2.1.126 introduces gateway model listing, project purge functionality, improved OAuth authentication for WSL/SSH/containers, and numerous bug fixes. Key improvements include permission bypass options, better shell detection on Windows, security fixes for managed settings, and stability enhancements for streaming, image handling, and remote sessions. The release also refines telemetry events, fixes UI issues, and resolves edge cases in tool availability and clipboard handling.

langchain-fireworks v1.2.1 is a patch release that fixes multimodal content block translation for chat completions, updates dependencies (aiohttp and requests), refreshes model profile data, and includes core streaming improvements. The release addresses compatibility issues with minimum core versions and updates documentation references.

LangChain version 1.2.17 has been released with a new feature adding a `respond` decision to the HITL (Human-in-the-Loop) middleware. This update enhances the middleware's decision-making capabilities by allowing systems to respond directly within the human-in-the-loop workflow. The release builds on version 1.2.16 with focused improvements to middleware functionality.

OpenClaw v2026.4.29-beta.4 introduces significant enhancements across messaging, memory, provider coverage, and reliability. Key additions include active-run steering by default, a people-aware wiki with provenance views, NVIDIA provider onboarding, and improved gateway/channel reliability. Security improvements include OpenGrep scanning and sharper GHSA triage policies, while multiple channel fixes address Slack, Telegram, Discord, WhatsApp, and Teams edge cases.

OpenClaw v2026.4.29 is a major release introducing active-run steering for messaging, people-aware memory wiki with provenance tracking, expanded provider coverage (NVIDIA, Bedrock), and enhanced reliability across gateway, channels, and security. Key improvements include opt-in follow-up commitments with heartbeat delivery, per-conversation Active Memory filters, faster model manifest paths, and comprehensive channel fixes for Slack, Telegram, Discord, WhatsApp, and Teams. Security enhancements add OpenGrep scanning and safer exec/pairing handling.