Chat UI (native chat)

Open supported agents in structured chat and continue conversations in chat or the terminal.

Chat UI is a conversation view with a transcript, composer, and agent controls. Supported agents you choose to open as chats start new sessions in structured chat, which communicates directly with the agent rather than displaying a terminal session. Other agents and unsupported execution environments open in the terminal.

Existing terminal-backed chats use a transcript view over an agent running in a terminal. These keep their original form; changing an agent's Chat or CLI choice does not convert existing sessions.

Choose chat or terminal

Chat UI is available to everyone. Supported agents inherit your global Chat or Terminal default unless you choose differently for an agent. Fresh installs default to Terminal:

You can also choose whether each supported agent opens as a chat in Settings → Agents: each agent's row in the Installed list has a Chat | CLI choice. Choosing CLI makes its new sessions open in the terminal. Agents whose chat runs on a program Orca downloads, such as Antigravity, show that download and their chat sign-in when you expand their row.

Continue a conversation in chat or the terminal

To open a saved conversation in another form:

  1. Open Agent Session History in the right sidebar.
  2. Open the conversation's menu.
  3. Choose Resume in New Chat for a supported CLI conversation, or Resume in New Terminal for a supported chat conversation.

Both actions open a new tab with a copy of the conversation; the original stays unchanged. For example, Resume in New Terminal copies a Claude or Codex chat into a new CLI session. These actions depend on the agent, saved conversation, and execution host; they are not available for every session. Older Orca versions label them Resume in New Native Chat and Resume in New CLI.

You can also right-click an open agent tab:

  • On a structured chat tab, Continue in terminal starts a new terminal agent with a copy of the conversation.
  • On a supported terminal agent tab, Continue in chat opens the conversation in a new structured chat. The terminal pane header shows the same action as a chat button.

These continuation actions also work for conversations on a paired Remote Orca Server that supports conversation-history resume. The chat and its history stay on that server. Direct SSH workspaces without an Orca runtime do not support this action. If the action is unavailable on an older server, update that server as well as the client.

If the terminal agent still owns the conversation, Orca asks you to stop or exit it before continuing from Agent Session History. Continuing in Chat does not forcibly terminate the terminal agent.

Switch an existing terminal-backed chat

Structured chat tabs have no in-place terminal view; use Continue in terminal above instead.

A terminal-backed chat is a view over a running terminal agent, so switching it does not create a new session. Use the pane header's Show terminal button, or Continue in terminal in its tab menu, to return to the terminal. Right-clicking inside a supported terminal pane offers Continue in chat, which shows that same terminal session as a transcript instead of creating a structured chat.

You can also switch the same terminal-backed session with Switch between Chat UI and terminal in Settings → Shortcuts (Cmd+Shift+J by default on macOS, Ctrl+Shift+F11 on Windows/Linux). On Windows/Linux, Ctrl+Shift+J also switches when Search everything doesn't use it, or from terminal input under the terminal-first shortcut policy.

Composer

  • Type a message and send (or stop a working turn). Attach files/images when the host supports it. Unsent draft text and attachments stay with the pane across disconnect/reconnect when the host can restore them. A settled transcript also stays on screen while the same session reconnects, instead of blanking until the fresh load finishes (desktop and mobile share that retention).
  • Type / for slash commands and discovered skills (filtered per agent when possible). The slash catalog is agent-aware (Claude vs Codex command sets) and shared with mobile Chat UI.
  • Use the model and options pills (thought level, mode, agent-specific session options) when the agent exposes them. Claude model choices come from the installed Claude CLI on that host (not a hardcoded list), so new models show up after you update the CLI. Codex supports direct model selection from the pill (sends /model <id>), with bare /model still opening the agent picker. Grok exposes model (-m at launch, /model mid-session) and reasoning effort (--reasoning-effort at launch, /effort mid-session); the model list is probed from the signed-in Grok CLI (grok models) so retired ids drop out of the picker. Effort choices follow the selected model: Grok 4.6 includes Extra high, while Grok 4.5 stops at High. Before the agent process starts, the composer can show draft launch options that apply on first start; after the session is live, pills that only affect a running turn stay disabled or labeled until the session is ready. In a structured chat, live values go to the agent session; in a terminal-backed chat, they go to the CLI in that tab.

Questions from the agent

When Claude shows an AskUserQuestion (or similar structured permission/question card), Chat UI should render the question card in the transcript so you can answer from the composer path instead of treating it as a collapsed tool call. Confirm with Submit on the card. That includes agents running on a paired Remote Orca Server / headless host — not only local panes.

Availability

Chat UI ships on desktop for supported local and remote (paired server) agent sessions. The available agents and actions depend on the execution host and client capabilities; an older paired host or an unsupported launch can still open in the terminal. The mobile companion reuses chat-style transcript patterns for paired sessions; the desktop menu steps above describe the desktop app.