openai_blog · Apr 22, 2026 · news
Speeding up agentic workflows with WebSockets in the Responses API
A deep dive into the Codex agent loop, showing how WebSockets and connection-scoped caching reduced API overhead and improved model latency.
openai_blog · Apr 22, 2026 · news
A deep dive into the Codex agent loop, showing how WebSockets and connection-scoped caching reduced API overhead and improved model latency.