Kevin Kaminski (@kkaminsk) reports OpenAI Agents SDK Python v0.22.0 and TypeScript v0.15.0, with the default model switched to GPT-5.6 Luna (claimed ~73% cheaper and ~2.6x larger context). Enterprise safety adds MCP credential redaction without config, guardrail visibility, and human-in-the-loop approval state across handoffs. Built-in checkpointing is still absent; Temporal remains the recommended durable-execution path.

Key Takeaways

  • ✓Versions: Agents SDK Python v0.22.0 and TypeScript v0.15.0.
  • ✓Default model is now GPT-5.6 Luna (~73% cheaper, ~2.6x context per the post).
  • ✓Adds MCP credential redaction, guardrail visibility, and cross-handoff approval state; Temporal still recommended for durable runs.
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
See how it ranks on the leaderboard
Full Leaderboard→
💰 Cost & PlansCompare
GPT-5.6 Luna · in: $0.2 / out: $1.2
Compare Plans↗
🛠️ Ecosystem & IDERules
OpenAI · Agents SDK · GPT-5.6 Luna
Setup IDE Rules↗
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗
Up NextApple Creator Studio adds AI assistants built on Apple models and OpenAI to Logic Pro, Keynote, Pages and Numbers, plus MCP support so external agents can edit iWork documents
Read Now→