Tool Use
Patterns for agents using tools effectively
Build a playbook about Tool Use
Save articles from this feed, then generate a personalized implementation guide
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.
★★★★★LangChain Core version 1.4.2 has been released with a focus on deprecating the problematic `dict()` method. This release addresses technical debt and improves API consistency. The update follows version 1.4.1 and includes changes aimed at enhancing the framework's stability and developer experience.
★★★★★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.
★★★★★Claude Code v2.1.166 introduces fallback model configuration for improved reliability, adds glob pattern support for tool access control, and hardens cross-session messaging security. The release includes numerous bug fixes for terminal compatibility, image processing, remote sessions, and managed settings enforcement. Key improvements enhance user experience across JetBrains IDEs, terminal protocols, and background agent sessions.
★★★★★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.
★★★★★crewAI v1.14.7a2 introduces conversational flow traces support with enhanced LLM event transparency, including real finish_reason, sampling parameters, and response IDs. The release refactors the flow DSL into focused decorator modules and implements a chat API for conversational flows. Key improvements include type-aware route decorators, overridable locking backends, and flattened LiteLLM usage tracking, alongside new NVIDIA Nemotron documentation and monorepo deployment guides.
★★★★★langchain-core version 1.4.1 is a maintenance release that includes bug fixes, dependency updates, and documentation improvements. Key fixes address Bedrock prevalidation removal, message serialization handling, and stream assembly for reasoning blocks and tool calls. The release updates several dependencies including langsmith (0.8.0), uuid-utils (0.16.0), and security patches for idna (3.15).
★★★★★Claude Code v2.1.163 introduces version management controls via `requiredMinimumVersion` and `requiredMaximumVersion` settings, adds a `/plugin list` command with filtering, and enhances the `/btw` command with clipboard copying. The release includes significant bug fixes for bash command execution on Windows/Bazel/EDR systems, background session management, terminal responsiveness, and permission rule application. Multiple stability improvements address hook conditions, keyboard input, and background agent updates.
★★★★★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.
★★★★★Claude Code v2.1.162 introduces improved session management with the `waitingFor` field in JSON output, enhanced slash command behavior with confirmation before execution, and a persistent Remote Control footer. The release fixes critical issues including read-only config directory handling, WebFetch permission precedence, Windows path matching in permission rules, and MCP timeout configuration. UI improvements include quieter startup messaging, full terminal-width status display, and better error reporting across agents, LSP tools, and cross-session messaging.
★★★★★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.
★★★★★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.
★★★★★OpenClaw v2026.6.1-beta.3 introduces significant stability improvements for agent runtimes, CLI tools, and multi-channel delivery across Telegram, WhatsApp, iMessage, Slack, Discord, and Teams. The release features a new Skill Workshop with proposal-based skill creation, externalized plugins (Tokenjuice and Copilot), SQLite-backed state management for better recovery, and enhanced Control UI with improved chat composition and latency tracking. Multiple fixes address tool-call recovery, streaming argument parsing, and process lifecycle management to prevent hanging runs and stale session bindings.
★★★★★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 1.3.4 has been released with improvements to Human-in-the-Loop (HITL) rejection guidance. This patch release follows version 1.3.3 and includes bug fixes and enhancements to the HITL workflow, making it easier for users to handle rejection scenarios in agent-based applications.
★★★★★Google ADK Python v1.34.2 is a bug fix release addressing three critical issues: grounding metadata being silently discarded in Gemini 3.1 live, incorrect input/output transcription finished events in Gemini v3.1, and session drops occurring when MCP tools encounter errors. These fixes improve reliability and data integrity for Gemini integrations and tool-based workflows.
★★★★★