Codex Config: GPT-6 Astra Orchestrator + GPT-5.6 Luna Subagents at Medium

Melvin Vivas · X post · 2026-09-08 · Open on X

Topics: AI Dev Tools & Productivity, AI Agents, Tool Use & MCP · Level: intermediate

Summary

Melvin Vivas shares the .codex/config.toml he uses in OpenAI Codex. The orchestrator is GPT-6 Astra and the subagents are GPT-5.6 Luna. He found Astra at low reasoning effort handed the app back before it was finished, so he raised the reasoning effort to medium, and it now works well.

Key points

• The Codex config file lives at .codex/config.toml.
• The root/orchestrator uses model = "gpt-6-astra" with model_reasoning_effort = "medium".
• Subagents use model = "gpt-5.6-luna" with model_reasoning_effort = "medium".
• At low reasoning effort, Astra declared the task done too early and handed over an unfinished app.
• Raising the orchestrator's reasoning effort from low to medium fixed the early handoffs.
• Caution: the snippet repeats the model key at the top level, which is invalid TOML. In a real config, subagent settings must go in their own section or profile, so check the Codex docs.

Resources mentioned

• OpenAI Codex · tool · openai.com · paid
  OpenAI's coding agent. In the diagram it writes code, fixes review findings and drives the build loop. The creator also used it to make this video.
  Also in: An agent bot that installs and drives Codex on its own (Melvin Vivas on X · notes), Asking a Coder bot to install Codex (Melvin Vivas on X · notes), Sign in with ChatGPT: Setting Usage Limits for Each App (Melvin Vivas on X · notes), Codex Cloud Environments Must Be Saved & Published Before Use (Melvin Vivas on X · notes) and 240 more
• GPT-6 Astra · tool · openai.com · paid
  The model announced in the quoted launch post, pitched as the developer's most capable model for work, coding, science and cybersecurity, and able to operate a computer.
  Also in: Customizing Your Coding Setup with Pi Coding Agent Extensions (Melvin Vivas on X · notes), Pi Agent Council: Ask Multiple LLMs in Parallel and Compare Their Advice (Melvin Vivas on X · notes), Use GPT-6.1 Sol by Default, Save Astra for Emergencies (Melvin Vivas on X · notes), Dots in ChatGPT: always-on AI agents that you hand responsibilities to (Melvin Vivas on X · notes) and 49 more
• GPT 5.6 Luna · tool · openai.com · paid
  The OpenAI model used inside Codex for the demo. The transcript gives the variant name as 'Soul', which is unclear.
  Also in: Set Codex subagent model and reasoning to save usage limits (Melvin Vivas on X · notes), Use GPT-5.6 Luna in Codex for Terminal Tasks (Melvin Vivas on X · notes), Match Reasoning Effort to Task Length in Codex (Astra/Sol) (Melvin Vivas on X · notes), Run Coworker desktop agents cheaply with GPT-5.6 Luna on OpenRouter (Melvin Vivas on X · notes) and 24 more

Try this

• If the orchestrator hands work back before it is finished, raise its model_reasoning_effort from low to medium.