Codex subscriptions default to GPT-5.6 Sol, and free tasks run on it

Until 15 September an unconfigured Codex subscription ran opencode with gpt-5.5, and for the four days after that it ran GPT-5.6 Terra at high effort, the model free tasks had used since July. Medium is a lower reasoning effort than the high those runs had. On your own subscription, an agent.effort you set is kept when we pick the model, so setting high gets it back; setting an engine or model turns the automatic pick off entirely. Free tasks on our key always run this fixed model and effort, whatever your configuration says.