Documentation
OpenAI Codex
OpenAI's coding agent with GPT-5 and Codex-optimized models for software work.
Setup
To use Codex, you can connect your ChatGPT subscription or provide an API key. We recommend using your ChatGPT account to use Codex as part of your Plus, Pro, Team, Edu, or Enterprise plan.
You can configure this in the settings page.
Available Models
- GPT-5.5
- GPT-5.4
- GPT-5.4 Mini
- Codex Spark
Terragon keeps this list aligned with the models currently available in the task composer and Agent Settings.
Connected ChatGPT accounts
When DevDocs MCP provides more than one Codex account, Agent Settings shows the current plan, status, usage windows, and reset times for each account. You can choose a round-robin or priority rotation policy and reorder accounts without exposing their credentials.
Features
Slash Commands
Codex supports built-in slash commands:
/clear- Clear conversation history/compact- Compact conversation
Custom slash commands (like /init, /pr-comments, /review) are not available with Codex. Learn more in the Slash Commands documentation.
Automatic Rate Limit Handling
When you hit a rate limit associated with your OpenAI subscription, Terragon automatically queues new tasks and messages until your rate limit resets, so that you never lose work. After your rate limit resets, any queued tasks or messages are submitted automatically.
If you upgrade your OpenAI plan after hitting a rate limit, you'll need to disconnect and reconnect your OpenAI subscription for your new limits to take effect in Terragon.
Limitations
Codex only supports command-based MCP servers.