openai-responses

Status : Production Ready Last Updated : 2026-01-21 API Launch : March 2025 Dependencies : openai@6.16.0 (Node.js) or fetch API (Cloudflare Workers) OpenAI's unified interface for agentic applications, launched March 2025 . Provides stateful conversations with preserved reasoning state across turns. Key Innovation: Unlike Chat Completions (reasoning discarded between turns), Responses preserves the model's reasoning notebook , improving performance by 5% on TAUBench and enabling better multi-turn interactions. vs Chat Completions: Key differences from Chat Completions: Use Responses: Use Chat Completions: Automatic State Management using conversation IDs: Benefits: No manual history tracking, reasoning preserved, 40-80% better cache utilization Conversation Limits: 90-day expiration Server-side hosted tools eliminate backend round trips: Usage: TypeScript Limitation : The web_search tool's external_web_access option is missing from SDK types (as of v6.16.0). Workaround : Source : GitHub Issue #1716 Built-in support for Model Context Protocol (MCP) servers to connect external tools (Stripe, databases, custom APIs). By default, explicit user approval is required before any data is shared with a remote MCP server (security feature). Handling Approval : Alternative : Pre-approve MCP servers in OpenAI dashboard (users configure trusted servers via settings) Source : Official MCP...