openai-node v7.62.0 Adds Live WebRTC Standby Support
Version 7.62.0 of the openai-node SDK introduces support for Live WebRTC standby in the API, allowing developers to better manage real-time connection workflows.
Developer intelligence
New endpoints, SDK releases, parameters, limits, deprecations, and migration guidance.
Your stack
Add your stack to personalize.
Version 7.62.0 of the openai-node SDK introduces support for Live WebRTC standby in the API, allowing developers to better manage real-time connection workflows.
The langchain-anthropic 1.7.12 release standardizes finish reason labeling in message events, updates a core dependency, and delivers bug fixes for tool output handling and async HTTP client management.
Amazon Polly's new voice cloning capability lets developers create custom text-to-speech voices from a few minutes of a consenting speaker's recordings. Available via API and console, cloned voices speak the recorded language, are automatically secured, and support brand, media, and accessibility applications.
The Anthropic TypeScript SDK has been updated to v1.11.0, introducing Claude Code managed settings to the Admin API and enhancing error support for plugin methods.
BerriAI releases LiteLLM version 1.108.12 (LTS) with six targeted fixes to prompt caching, API errors, streaming behavior, and guardrail enforcement on chat, message, and batch endpoints.
The openai-node client v7.60.0 introduces Live MCP server configuration support and standalone CSAM moderation types, and hides Managed Agents session budget controls and events.
The new langchain-openai 1.8.2 release introduces support for GPT-6.2 Astra and Sol models, adds new header support, and fixes client behavior.
The latest release of the openai-python SDK, v3.55.1, documents the response fields related to CSAM moderation in the API. No functional changes or breaking updates are included.
Version 1.10.0 of the Anthropic TypeScript SDK introduces beta support for the billing_policy API parameter, new error codes, webhook events for external key failures, and data model renaming. These changes improve billing granularity and error handling in API integrations.
Anthropic's Python SDK v2.10.0 introduces beta support for the billing_policy parameter, new error codes for billing issues, webhook events for external key changes, and more nuanced content scan status reporting. Developers integrating billing or using error codes in automation will benefit from these updates.
AWS has introduced tabular search for Amazon Bedrock Managed Knowledge Base, enabling agentic retrieval to natively analyze and answer questions over CSV, XLSX, and XLS files. This expands the platform’s retrieval capabilities from just text to structured table data, supporting calculations and multi-source analytical queries.
Anthropic SDK for TypeScript v1.9.0 introduces updates to API endpoints, adds bundle instruction support, and deprecates several beta header values. Developers should review header usage and update workflows for new API capabilities.
The anthropic-sdk-python v2.4.0 release introduces new GA methods for analytics, spend limits, and RBAC, adds new error types, extends filter options, improves key management, and refines API responses.
The openai-node library now supports typed Responses for WebSocket warmup, providing improved type safety for developers working with OpenAI's Node.js SDK.
The openai-python library v3.42.0 introduces new agent context compaction settings, agent session review options, experimental time awareness, image edit markup overlays, external key management, SIP DTMF events, API key scoping, WebSocket improvements, and more. These changes provide more control, better error recovery, and new integration possibilities for developers.
Several previously experimental APIs in @ai-sdk/react are now stable. Developers should update usage to stable names as experimental aliases are deprecated.
The @ai-sdk/provider package streamlines model catalog management for OpenAI and Anthropic and introduces a standardized contract for model entries with improved capability documentation.
The latest patch for Vercel's @ai-sdk/zai library introduces asynchronous and promise-based provider credential resolution and updates the experimental OpenAI Live API configuration to support asynchronous operations.
The @ai-sdk/xai package now supports promises and asynchronous callbacks for API credentials, and its experimental OpenAI Live WebSocket config method can resolve asynchronously. Developers gain more control over authentication in dynamic or distributed environments.
The latest update to the anthropic-sdk-python introduces a speed parameter to messages, expands model capability metadata, and improves organizational spend tracking.
The openai-node SDK now supports specifying regional data processing residency. The release also clarifies Decisions API fields. No breaking changes are reported.
The openai-python SDK v3.30.0 introduces beta session spending limits, support for Oracle Cloud Infrastructure (OCI) as an external storage provider, improved error and moderation feedback for image tools, usage reporting updates, and project API key expiry management.
The openai-python library v3.31.0 introduces new browser and computer toolsets, enabling developers to extend AI agent functionality within Python projects.
The langchain-anthropic 1.7.6 release updates model profiles and now explicitly declares mid-conversation support. No breaking changes have been introduced.
The openai-node library now allows agent environments to be suspended and set to expire. This update provides finer control over agent lifecycle management, which is useful for application state management and resource optimization.
The AI SDK now integrates HeyGen as a provider, introducing text-to-video, image-to-video, and reference-to-video generation using 'heygen-video-1', along with asynchronous operation support and workflow serialization.
The @ai-sdk/mcp 2.0.73 release introduces a breaking change to the experimental event adapter API, requiring a synchronous createAdapter({ transport }) function and modifications to imports and interface names. Applications must adopt the new Experimental_MCPEventAdapter pattern.
langchain-openai version 1.7.0 introduces support for the OpenAI Decisions API, enabling new AI workflow capabilities with LangChain integrations.
The OpenAI Node.js SDK v7.30.1 includes critical fixes for custom voice parameter handling, structured text parsing, and file upload decoding, improving reliability for developers integrating voice and structured outputs.
The @ai-sdk/typesafe-ai 3.0.16 patch adds ordered text, file, and JSON parts to experimental decision state, supports image input in OpenAI Decisions and adapters, and revises JSON and state handling. File input is not yet accepted by the Gateway or TypeSafe AI.
The latest Anthropic Typescript SDK update introduces support for Claude Haiku 5-5, typed tool calls, web search and code execution capabilities, and enhanced model metadata.
The @ai-sdk/provider library introduces the portable 'max' reasoning level for consistent, advanced model selection across providers, with new compatibility considerations and fallback support.
Version 7.29.0 of the OpenAI Node.js SDK brings improved agent observations for local tool failures, the ability to run local tools during session creation streams, and enhances typed function helpers with deferred tool search support.
The latest release of @ai-sdk/xai introduces support for the grok-imagine-image-2.0 image model ID, an auto image quality option, a 1.5k image resolution provider, and expanded transcription model capabilities.
The 2.3.0 release of @modelcontextprotocol/client, server, and related packages mandates one server per request, changes HTTP redirect handling, and adds security and validation options. Developers must update their architecture and configuration to stay compatible and secure.
Cloudflare's AI Gateway now lets developers inject real-time, structured web search results from providers like Ceramic.ai, Exa, and Linkup directly into their applications and model inference pipelines, supporting both REST APIs and Cloudflare Workers.
The openai-node library now allows agents to prepare hosted files and download result artifacts, improving workflow automation and data handling capabilities for developers.
The openai-python library v3.23.0 introduces typed answers in agent session streams, better file staging, turn artifact downloads, and Realtime session traces, along with key bug fixes. These features offer improved development and debugging around OpenAI agents.
GitHub's async merge API is now out of beta and recommended for programmatically merging pull requests, supporting stacked and queued merges for improved automation.