openai-responses

Build stateful agentic applications with the OpenAI Responses API.

52|6|Updated Nov 24, 2025

Search Tags:#mcp #web-search #code-interpreter #file-search #tool-calls #stateful-conversations #responses-api

Ready to run

npx skills add https://github.com/ovachiever/droid-tings --skill openai-responses-ovachiever

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: openai-responses
Source: https://github.com/ovachiever/droid-tings/tree/main/skills/openai-responses
Command: npx skills add https://github.com/ovachiever/droid-tings --skill openai-responses-ovachiever

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a comprehensive guide and implementation for OpenAI's Responses API, enabling stateful, long-running agentic workflows with automatic reasoning preservation, built-in tools (Code Interpreter, File Search, Web Search, Image Generation), MCP integration, and background processing.

Core Features & Use Cases

Stateful conversations via automatic conversation IDs
Polymorphic outputs including reasoning summaries, tool calls, and messages
Server-side built-in tools: Code Interpreter, File Search, Web Search, Image Generation
MCP integration for external tools and services
Background processing for long-running tasks and batch workflows
Seamless integration with ML workflows and analytics pipelines

Quick Start

Get an API key and install the SDK
Create a Conversations-based workflow and experiment with built-in tools
Explore MCP tool integration and background processing

Frequently Asked Questions about openai-responses

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build stateful conversations with the OpenAI Responses API?▼

The Responses API enables stateful conversations by automatically managing conversation IDs and preserving multi-turn reasoning across requests. Create conversations, send messages, and the API maintains state server-side, eliminating manual session tracking and enabling long-running agentic workflows without Chat Completions' limitations.

What built-in tools does the OpenAI Responses API provide for agent applications?▼

Built-in tools include Code Interpreter for executing code, File Search for document retrieval, Web Search for real-time information, and Image Generation. The API handles tool orchestration server-side, and you can extend capabilities with MCP server integrations for custom tools and external services.

Can I integrate MCP servers with the Responses API for custom tools?▼

Yes, the Responses API supports MCP integration to connect external tools and services. Define MCP tool configurations in your request, and the API manages server-side orchestration, enabling polymorphic outputs that combine reasoning, tool calls, and message streams.

How do I migrate from Chat Completions to the Responses API?▼

Responses API migration requires adopting conversation-based workflows, conversation identifiers, and server-side tool definitions instead of client-side tool handling. The API provides automatic state management and background processing, streamlining multi-turn reasoning and long-task execution compared to Chat Completions' stateless model.

Does the Responses API support background processing for long-running tasks?▼

Yes, background processing is built in for long-running tasks and batch workflows. The API handles asynchronous execution while maintaining conversation state, enabling seamless integration with ML workflows and analytics pipelines without blocking request-response cycles.

What Node.js version and SDK requirements does the Responses API need?▼

Use Node.js with [email protected] or later, or edge-runtime equivalents. The API requires /v1/responses endpoints and conversation identifiers for stateful operations. Ensure your environment supports the specified SDK version for full feature compatibility including tool definitions and MCP integration.