Skip to content

Agent mode

Two keys, two modes:

  • ⌘L is ask. A one-shot AI bar over the focused pane. The answer comes back as a result block with Run / Edit / Copy actions; nothing executes until you say so.
  • ⌘⇧L is agent. A full conversation with tools: read files, edit, grep, glob, run commands, call MCP servers, drive the screen.

Every tool call passes an ApprovalPolicy before it touches your system:

Policy Behaviour
auto Runs without asking (reads, greps)
prompt Asks you, with the exact command shown
deny Never runs

Policies are per-tool and per-profile, so “read anything, ask before writing, never touch the network” is one profile away. Approved commands execute in the pane — visible, scrollable, and part of your block history like anything you typed yourself.

Agent edits are checkpointed; ⌘Z on the agent timeline rolls the working tree back step by step. An agent can be wrong; it shouldn’t be irreversibly wrong.

Agents can attach to interactive panes; psql, python, gdb; read the live screen, and type into it under the same approval gate. The terminal detects attachment prompts and routes them to the conversation.

Every agent conversation is persisted: replay it, export it, or resume it. The history pane shows each tool call with its approval verdict; an audit trail, not a chat log.

Anthropic, OpenAI, OpenRouter, and Ollama (local). Keys live in the OS keychain. Pick per-conversation models, or set a default in Settings → Providers.