Updates & News

OpenAI Agents Python SDK v0.17.7 introduces configurable WebSocket limits, buffered Chat Completions tool-call streaming, and numerous stability improvements. Key fixes address sandbox buffering, message cleanup, database atomicity, guardrail task cancellation, and multi-agent tool dispatch. The release also improves error handling, PTY output collection, and documentation with contributions from 10 new community members.

OpenClaw v2026.6.10 introduces automatic fast mode for conversational turns, improves model routing reliability across Zai and GLM systems, and enhances session/channel state safety. The release includes 12 merged PRs focusing on fallback behavior, trusted policy preservation, and provider plugin metadata consistency. Key fixes address fast-mode state persistence, model catalog accuracy, and stale channel-origin field leakage across sessions.

langchain-openrouter version 0.2.4 release includes dependency updates, new features for tool handling, and continuous model profile refreshes. Key improvements include bumping the openrouter floor to 0.9.2, surfacing parallel_tool_calls on bind_tools, and adding cache_control passthrough support. The release also incorporates package version tracking for tracing metadata and various infrastructure improvements across the LangChain monorepo.

langchain-openai version 1.3.3 is released with several bug fixes and improvements. Key changes include dropping response item IDs when store is disabled, fixing strict schema validation for OpenAI-compatible models, removing stop parameter from Responses API, and updating dependencies. The release also includes test clarifications and model profile refreshes.

OpenClaw v2026.6.10-beta.2 introduces automatic fast mode for conversational turns, improves model routing reliability across Zai and GLM systems, and enhances session/channel state management. Key fixes address fast-mode policy correctness, fallback cutoffs, and prevent stale channel-origin state leakage. The release includes 11 merged PRs with contributions focused on runtime metadata consistency, trusted policy preservation, and native reasoning-level selection.

Claude Code v2.1.185 updates the stream-stall user feedback mechanism with improved messaging and adjusted timing. The hint now displays 'Waiting for API response · will retry in …' instead of 'No response from API · Retrying in …', and the trigger threshold increases from 10 seconds to 20 seconds of silence. This change enhances user experience by providing clearer communication about API response delays.

langchain-core version 1.4.8 was released with performance improvements, bug fixes, and dependency updates. Key changes include memoization of BaseTool.tool_call_schema for better performance, preservation of usage token details in v3 streaming events, and removal of Python < 3.10 support code. The release also includes dependency bumps for jupyter-server, tornado, and bleach, along with code quality improvements and test updates.

LangChain v1.3.10 release includes dependency updates (cryptography, aiohttp, pyjwt), bug fixes for summary format and GPT model provider detection, improved test typing, and coordinated releases across related packages (OpenAI 1.4.0, Core 1.4.7, Anthropic 1.4.6). The release also features documentation updates to the README with installation and resource information.

crewAI v1.14.8a1 is a pre-release update introducing optional if expressions for each.do steps, fixing JSON crew issues, and updating documentation. This release enhances workflow control by allowing conditional execution of steps and resolves compatibility issues with JSON-based crew configurations. Contributors include @joaomdmoura and @vinibrsl.

Claude Code v2.1.179 is a maintenance release focused on stability and user experience improvements. Key fixes address connection handling, input focus management, sandbox configuration issues, and UI glitches. The update resolves regressions from previous versions and improves performance in remote sessions, particularly for plugin loading and WSL2 compatibility.

OpenClaw v2026.6.8 is a major release focusing on improved channel delivery (Telegram/WhatsApp), enhanced agent and gateway recovery mechanisms, expanded provider/model support (GLM-5.2, Claude Haiku 4.5), better usage hooks with native footer rendering, and UI/mobile stability improvements. The release includes fixes for memory management, state handling, diagnostics, and numerous edge cases across channels, agents, and runtime systems.

Claude Code v2.1.178 introduces enhanced permission rules with parameter matching syntax, improved nested `.claude/` directory handling for skills and workflows, and refined auto mode with pre-launch subagent evaluation. The release includes better error messaging for Remote Control, improved `/doctor` output, and numerous bug fixes addressing subagent transcript display, authentication issues, and vim mode undo behavior.

OpenClaw v2026.6.8-beta.1 introduces significant improvements to channel delivery (Telegram rich text, WhatsApp ACP bindings), agent and gateway recovery mechanisms, expanded provider/model support (GLM-5.2, Claude Haiku 4.5), enhanced usage hooks with footer rendering, and UI/mobile stability fixes. The release addresses 50+ issues across messaging, runtime reliability, authentication, memory management, and user interface components, with contributions from 30+ developers.

OpenClaw v2026.6.7-beta.1 delivers significant improvements across channel delivery, provider resilience, security boundaries, and recovery paths. Key enhancements include tighter Slack/Telegram integration, better model handling for Kimi/Mistral/DeepSeek/Anthropic, safer auth contexts, and improved failure recovery for agents and cron jobs. The release also strengthens UI/docs accessibility, Docker bundling, and QA validation with new scorecard taxonomy artifacts.

langchain-core version 1.4.7 is released with several maintenance and bug fixes. Key updates include a tornado dependency bump, fixes for Pydantic v1 support in tools/runnable, corrections to package version trace metadata, and documentation style improvements across docstrings. This is a minor patch release focused on stability and compatibility improvements.

Claude Code v2.1.175 introduces the `enforceAvailableModels` managed setting, which strengthens model access control by constraining the Default model selection to the allowlist. When enabled, any Default model that resolves to a disallowed model automatically falls back to the first allowed model, and users cannot override the managed allowlist with broader settings.

OpenClaw v2026.6.6-beta.2 is a security-focused beta release that substantially tightens security boundaries across transcripts, sandboxing, and MCP integrations while improving Telegram delivery reliability, iMessage recovery, browser/MCP connectivity, and Control UI startup performance. The release expands provider support with OpenRouter OAuth and Claude Fable 5, introduces observability enhancements for diagnostics, and fixes critical issues in agent session recovery, channel delivery, and authentication. Multiple infrastructure improvements address performance bottlenecks, plugin management, and build reliability.

crewAI v1.14.7 introduces pluggable backends for memory, knowledge, RAG, and flow management, along with a native Snowflake Cortex LLM provider and chat API for conversational flows. The release includes significant bug fixes for checkpoint restoration, telemetry, file input handling, and security vulnerabilities. Performance improvements focus on lazy-loading docling imports to speed up crewai imports, while refactoring decouples conversational logic and splits flow.py into modular components.

Claude Code v2.1.173 addresses two key fixes: normalization of Fable 5 model names that include a [1m] suffix (representing 1M context) by automatically stripping it, and elimination of a false "sandbox dependencies missing" warning on Windows systems when sandbox mode is enabled. These updates improve model name handling and reduce unnecessary startup warnings for Windows users.

crewAI releases version 1.14.7rc2, a release candidate that addresses a critical bug in snapshot restoration. The main fix gates the restore functionality on a flag to prevent live snapshots from being replayed during resume operations. This update includes documentation updates to the changelog and version information for the previous rc1 release.