Agents & Models

The agent is the AI coding system that runs inside your workspace. Aether supports three selectable agent providers — Codex, Claude Code, and OpenCode — each wrapping a real coding-agent CLI with its own curated model catalog and authentication. You choose the agent type, model, interaction mode, and reasoning effort per task — and as project or account defaults. The platform defaults are agent type codex, interaction mode default, and the gpt-6.1-sol model.

Agent Providers

Codex (default)

OpenAI Codex. The default agent type. Runs on Aether inference, a ChatGPT plan connected by device login, or an OpenAI API key.

Model slug	Name
`gpt-6-astra`	GPT-6 Astra
`gpt-6.1-sol` (default)	GPT-6.1 Sol
`gpt-6-sol`	GPT-6 Sol
`gpt-6-luna`	GPT-6 Luna

Claude Code

Anthropic Claude Code. Runs on Aether inference, a Claude plan connected by setup token, or an Anthropic API key.

Model slug	Name
`claude-opus-5-5` (default)	Claude Opus 5.5
`claude-fable-5-1`	Claude Fable 5.1
`claude-sonnet-5-5`	Claude Sonnet 5.5
`claude-haiku-5-5`	Claude Haiku 5.5

OpenCode

The OpenCode agent, with a curated catalog of around 30 models routed through OpenRouter, OpenCode Zen, and Anthropic — including Claude, GPT, Gemini, DeepSeek, Mimo, Kimi, Qwen, and GLM variants. The default model is opencode-claude-sonnet-4-6. Runs on an OpenCode auth file or an OpenRouter API key, not Aether inference. Runtime model availability depends on the connection’s provider entitlements. For each option’s sign-in and the default connection rules, see Agent connections.

Reasoning Effort

Reasoning effort controls how much the model thinks before acting. The available options depend on the agent provider:

Provider	Default	Options
Codex	`xhigh`	`low`, `medium`, `high`, `xhigh`, `max`, `ultra` (model-dependent)
Claude Code	`xhigh`	`low`, `medium`, `high`, `xhigh`, `max`, `ultrathink`, `ultracode`
OpenCode	`high`	`low`, `medium`, `high`, `max`

For Codex, GPT-6 Sol supports low, medium, high, xhigh, max, and ultra; GPT-6.1 Sol and GPT-6 Luna support the same set up to max. For Claude Code, the full option set above applies to every model: Fable 5.1, Opus 5.5, Sonnet 5.5, and Haiku 5.5.

Interaction Modes

A task runs in one of two interaction modes:

default — the agent works the task end to end.
plan — the agent drafts a plan and halts for your approval before making changes. You review the plan and approve or send feedback before the agent proceeds.

Selecting Per Task

Pick the harness, model, mode, and effort when creating a task. The harness stays fixed for that task; you can change its model, mode, and effort:

aether task create --project <project-id> --prompt "..." \
  --agent-type claude-code \
  --model claude-opus-5-5 \
  --interaction-mode plan \
  --reasoning-effort high

aether task update <task-id> --model claude-sonnet-5-5

You can also set these as project or account defaults so new tasks inherit them. See the tasks guide and the agents and models guide.

​Agent Providers

​Codex (default)

​Claude Code

​OpenCode

​Reasoning Effort

​Interaction Modes

​Selecting Per Task