Skip to main content
radius chat starts and follows agent turns in a running Radius. Combined with --on, the turn runs on another Mac: the agent works in that Mac’s files and uses that Mac’s browser and signed-in sites.

Start a turn

This opens a chat for that project in a background tab, sends the prompt, and prints the conversation ID. The chat is an ordinary Radius chat: it appears in the project’s group and in chat history. The chat uses that Radius’s default agent and model. To choose, pass both --provider and --model:
Add --watch to stay attached until the turn ends:
With --watch, the command prints JSON Lines. The first line identifies the conversation; each following line is one agent event with a cursor:
The command exits 0 when the conversation is idle, and non-zero with CHAT_TURN_FAILED when the turn failed. A turn that was still running when Radius quit or crashed is reported as failed, so reconnecting to it ends with CHAT_TURN_FAILED, not success. To send another message to the same conversation, pass --conversation. If a turn is running there, the message waits its turn and --watch waits with it:

Reconnect to a running turn

The turn belongs to the Radius it runs in. Stopping radius chat, closing your laptop, or losing the ssh connection does not stop it. To pick up where you left off, pass the last cursor you saw:
Without --watch, chat events prints what is available now and exits.

Permission prompts

When the agent needs permission, the event stream shows a permission.requested event, and the turn waits.
approve allows that one request. When several prompts are waiting, name the one to answer: radius chat approve <conversation-id> <permission-id>. Agents cannot answer permission prompts, or use any other radius chat command: in a terminal that Radius opened for an agent, they are refused.

Stop a turn