Entering & exiting

Agent conversations are designed to be cheap to enter and cheap to leave. You can drop into one mid-command, pop back to the shell, and pick the thread up later — nothing is lost in between.

Starting a conversation

There are two front doors:

• Ctrl+Enter (⌘Enter on macOS) from the terminal prompt. Whatever you've already typed comes along as the first message — so you can start writing a shell command, realize it's really a question, and press ctrl+enter instead of enter.
• /mel from the slash menu: type / at the prompt, pick /mel, and the conversation opens on its landing view. (Typing /agent still finds it — the row matches on its description.)

Either way the pane switches into the conversation view, and the tab title becomes the conversation title once one is set — so a sidebar full of tabs reads like a list of what each agent is working on.

The slash menu also offers /orchestrate-agent and /orchestrate-cli for multi-agent runs (Orchestration) and /plan to ask for research and a plan before any code is written.

Leaving with esc

Press esc and the conversation collapses out of the way (while a turn is still running, esc instead hides the conversation and the agent keeps working; an open menu, an expanded diagram, the compose box and the plan editor take the first esc):

• The pane returns to the normal terminal.
• The conversation shrinks to a mini block in your scrollback — a compact row with a checkmark, the conversation title, and a chevron — sitting just above the prompt.
• The conversation is saved and appears in Recent Activity on the agent landing page and in the Tools panel's conversations list.

Clicking the mini block reopens the conversation with its full transcript and model selection intact. You can accumulate several mini blocks in one pane and hop between conversations and shell work freely.

Resuming

• Ctrl+Shift+Y (⌃⇧Y on a Mac) opens your conversations in a panel docked along the bottom of the pane, with All and Current Directory tabs and a search field. Continue Last Conversation in the command palette reopens the most recent one.
• /conversations opens a searchable picker over your whole conversation history. See Conversation management.
• The agent landing page lists Recent Activity — click any entry to resume it.

Resuming restores both the visible transcript and the underlying context, so the agent remembers what it was doing.

Starting another while one works

Starting a new conversation while another one is still working opens it in a new tab, with your text sent there; the running one carries on.

Split panes are independent

Each pane hosts its own agent. Split with Ctrl+Shift+D or Ctrl+Shift+E (⌃D or ⌃⇧D on a Mac; Split panes) and you can run two conversations side by side; esc and Ctrl+Shift+Y (⌃⇧Y on a Mac) act only on the active pane.