Chat

The Chat tab is where you talk to an agent and watch it work. It streams every step of a turn — tool calls, subagent delegations, reasoning, and approval prompts — against either your local dev server or the deployed agent.

Local vs Deployed

A Target toggle at the top picks what you're talking to:

Local — the agent's local dev server (eve dev). This is what you use while building; it reflects your unsaved-to-production changes.
Deployed — the production deployment on Vercel. Use it to smoke-test what your users actually reach.

For Local, the dev server must be running: hit Start in the per-agent header (see The workspace) and wait for the status pill to read running. The Deployed target needs a deployment to exist — see Deploy to Vercel.

What streams

As the agent runs a turn, Chat renders each event live, in order:

Turns — the assistant's messages as they're produced.
Tool calls — each call is a collapsible row; expand it to see the tool's input and output.
Subagent delegations — when the agent hands work to a specialist child agent, its run appears nested so you can follow the delegation.
Reasoning — a "thinking…" stream showing the model's reasoning before it acts.
Approval prompts — when a tool is gated for human-in-the-loop, the turn pauses and asks you to approve or reject before it proceeds.

The composer and usage bar

A composer at the bottom sends your message. Directly under it, a usage bar reports the cost and token count for the conversation, so you can see what a turn is spending as you go.

Threads and archiving

Each conversation is a thread (a durable session). Threads live under the active agent in the left rail; start a new one with ＋ New chat. Archive a thread to move it out of the sidebar without losing it, and reopen it later from the Archived modal — see The workspace for the rail controls.

If the agent won't reply

If you see a Connect to Vercel banner instead of a response, the agent has no model credential yet. The model routes through the Vercel AI Gateway, so it needs one before it can run — follow Connect to Vercel, then send your message again.