Developer shares Codex multi-model orchestration config
A Codex configuration assigns models by task, with Astra used for low-effort steps like proposal, design, verification and review.
Esta es mi actual config usando los modelos de OpenAi que me funciona muy bien: Orquestador: model=openai-codex/gpt-5.6-sol, effort=medium sdd-init: model=openai-codex/gpt-5.6-sol, effort=medium sdd-onboard: model=openai-codex/gpt-5.6-sol, effort=medium sdd-explore: model=openai-codex/gpt-5.6-terra, effort=high sdd-research: model=inherit, effort=inherit sdd-proposal: model=openai-codex/gpt-6-astra, effort=low sdd-spec: model=openai-codex/gpt-5.6-terra, effort=high sdd-design: model=openai-codex/gpt-6-astra, effort=low sdd-tasks: model=openai-codex/gpt-5.6-terra, effort=high sdd-status: model=openai-codex/gpt-5.6-sol, effort=medium sdd-apply: model=openai-codex/gpt-5.6-terra, effort=high sdd-verify: model=openai-codex/gpt-6-astra, effort=low sdd-sync: model=openai-codex/gpt-5.6-sol, effort=medium sdd-archive: model=openai-codex/gpt-5.6-luna, effort=high jd-judge-a: model=openai-codex/gpt-6-astra, effort=low jd-judge-b: model=openai-codex/gpt-6-astra, effort=low jd-fix-agent: model=openai-codex/gpt-5.6-terra, effort=high gentle-ai-explore: model=openai-codex/gpt-5.6-terra, effort=high gentle-ai-verify: model=openai-codex/gpt-6-astra, effort=low gentle-ai-worker: model=openai-codex/gpt-5.6-terra, effort=high review-readability: model=openai-codex/gpt-6-astra, effort=low review-refuter: model=openai-codex/gpt-6-astra, effort=low review-reliability: model=openai-codex/gpt-6-astra, effort=low review-resilience: model=openai-codex/gpt-6-astra, effort=low review-risk: model=openai-codex/gpt-6-astra, effort=low review-validator: model=openai-codex/gpt-6-astra, effort=low