WebChat (macOS) Integration Guide

The macOS menu bar app presents the WebChat interface as a native SwiftUI view. It links to the Gateway and defaults to the primary session for the chosen agent (main, or global when session.scope is global).

The full chat interface uses a native split view:

Sessions sidebar: a searchable list of sessions organized into pinned, gateway-backed group, and recent sections. Child sessions spawned from a parent appear nested under it within each section. Collapsed parents show counts of running, failed, and unread descendants. Right-click menus provide access to session info, rename, pin, fork, mark read or unread, archive or restore, copy session key, and delete. The main action for creating a new session (or Shift-Cmd-N) builds one immediately through sessions.create. A nearby options popover lets you pick an agent and request a managed worktree with an optional base ref.
Window toolbar: a context usage ring displaying tokens and session cost with a compact action, model controls, and a session actions menu. Models are arranged by provider with the default provider listed first, while pinned and recent models stay at the top. The controls can inherit or override the model's thinking level, adjust tool-call verbosity, and toggle Fast responses. The menu can rename or fork the current session and update its pin, read, or archive state. Sessions… (Shift-Cmd-S) opens the Active/Archived manager for gateway search, group management, session inspection, rename, pin, archive, and restore. Select mode applies pin, unpin, archive, or delete to multiple active sessions while showing individual failures. Separate menu checkmarks control whether assistant reasoning and tool activity are visible; both default to on and persist across launches.
Transcript and composer: assistant messages appear as plain text with an avatar, while user messages show as accent bubbles. Pending agent questions display as native cards with single or multi-select options, free-text Other answers, expiry countdowns, and shared terminal state. Empty chats show desktop starter prompts. Typing / opens slash-command autocomplete powered by commands.list, navigable with arrow, Tab, Return, or Escape keys. Right-click a message to copy its visible Markdown without hidden reasoning. Truncated assistant messages also offer Open Full Message, which loads a selectable Markdown reader. Use Listen for gateway TTS with a local speech fallback.
Voice controls: the composer can start or stop the existing macOS Talk Mode without replacing its menu-bar overlay. When Talk Mode is active, the composer shows its listening, thinking, and speaking states, live audio activity, and an expandable rolling transcript. Right-click the Talk button to choose System Default or a connected microphone, which is the same microphone selection used by Voice Wake and push-to-talk. If a selected microphone disconnects, the active Talk session falls back to the system default and retries the selection the next time Talk Mode starts. A separate microphone action records a voice note when Talk Mode does not own audio capture.

The anchored compact chat panel from the menu bar keeps the compact single-column layout with the same model, thinking, verbosity, and Fast controls inline, plus starter prompts, Talk Mode, voice notes, and Listen. Assistant reasoning and tool activity remain hidden in this compact surface.

Multiple Gateway windows

Open Settings → Gateways to add or remove reusable Gateway profiles. Each profile contains a private-network ws:// or secure wss:// endpoint and its optional token or password. Credentials are stored in the macOS Keychain. Secure profiles maintain their own system-trust-gated first-use certificate pin and do not inherit gateway.remote.tlsFingerprint from the primary Gateway. Removing a profile also closes its open windows and shuts down its secondary connection.

Choose File → New Gateway Window… or press Cmd-N, then select one of those saved profiles. The picker remembers the most recently used profile. Each selection creates a new independent window, so the same Gateway can appear in multiple windows with different active sessions and navigation state.

Each saved profile owns one shared Gateway connection, device-auth scope, transcript cache, offline outbox, and route leases. Windows for that profile reuse those resources while staying independently navigable. Windows for different profiles stay connected and run chats simultaneously.

The menu-bar app's configured Gateway remains the owner of Mac node capabilities and Talk Mode. Additional Gateway windows are operator-only, so a second Gateway cannot silently retarget global microphone or device controls. Listen/TTS and normal chat actions use the window's own Gateway connection.

Quick Chat bar

Press Option-Space (⌥Space) or choose Quick Chat from the menu bar menu to open a floating composer for the main session. Change the global shortcut with the recorder in Settings → General → Quick Chat shortcut.

Quick Chat shows the targeted agent (avatar or emoji, with the agent's name as the placeholder) and sends to that agent's main session. After Return accepts a send, the bar stays open and expands downward with the streamed Markdown reply and recent transcript. The bar input remains the composer. Press Command-Return to send and open the same target in the full chat window, Shift-Return for a newline, or Escape to dismiss the whole bar and reply area. Clicking outside also dismisses it. When relevant macOS permissions are missing, an attached strip offers Grant and Not now actions.

Use the microphone button to dictate into the composer. Partial speech results replace the dictated span live while preserving text that was already in the composer. Press the button again, Return, or Escape to stop. Sending, hiding, or unfocusing Quick Chat also releases the microphone. The first use asks for macOS Microphone and Speech Recognition access. Quick Chat uses Apple Speech and may use its network services. Only passive Voice Wake requires on-device recognition.

The compact model control shows the target session's current model and reasoning level. A model choice updates that session and therefore persists there, while a reasoning choice applies only to each message sent from the current Quick Chat presentation. Local choices reset when the bar hides. Switching agents or choosing a recent session keeps explicit choices but reloads the newly targeted session's underlying model state.

Click the history button to choose from the five most recently updated sessions or return to New message to <agent>. A recent selection sends to that exact session and changes the placeholder to Reply in <session>. Hiding Quick Chat resets this temporary target to the selected agent's main session. Switching agents from the avatar menu also clears it.

Command-Return opens the conversation of the agent that received the send, including when session scope is global.

The camera button opens a menu for Capture Window… or Capture Area…. Window capture labels every visible window. Area capture dims each display while you drag a region and shows its live size. The selected screenshot is sent to the chosen agent with any typed text as its caption. The first use asks for macOS Screen Recording access. Escape, clicking empty space, or clicking without a meaningful area drag cancels.

Use the document-text button to attach text from the focused app's focused window. Quick Chat shows the result as a removable context chip rather than placing the captured text in the composer. Sending appends the chip's text to the outgoing message and then clears it. This requires macOS Accessibility permission. Attached text also clears whenever Quick Chat closes, so context from one presentation cannot leak into a later send.

After a reply finishes, choose Paste to <app> to copy its visible assistant text, excluding hidden reasoning, to the general pasteboard and paste it into the app that was frontmost. This requires macOS Accessibility permission. The action replaces the current pasteboard contents and then hides Quick Chat.

Turn off the whole feature using Settings → General → Quick Chat; the shortcut recorder is also found in that same pane.

Local mode: establishes a direct connection to the local Gateway WebSocket.
Remote mode: sends data through either the configured direct ws:///wss:// path or the SSH tunnel managed by the app.

Launch and debugging

Manual: open from the Lobster menu by selecting "Open Chat".
Auto-open for testing:
```
dist/OpenClaw.app/Contents/MacOS/OpenClaw --chat
```
(--webchat is treated as a legacy alias.)
Logs: ./scripts/clawlog.sh (subsystem ai.openclaw, category WebChatSwiftUI).

How it is wired

Data plane: Gateway WS methods chat.history, chat.message.get, chat.send, chat.abort, chat.inject, along with question.list and question.resolve, and events chat, agent, presence, tick, health; question cards rely on question.requested and question.resolved events and reload from question.list after reconnections.
chat.history provides a display-normalized transcript: inline directive tags are removed from visible text, plain-text tool-call XML payloads (<tool_call>, <function_call>, <tool_calls>, <function_calls>, including truncated blocks) and leaked model control tokens are stripped, pure silent-token assistant rows like exact NO_REPLY/no_reply are excluded, and oversized rows may be replaced with a truncated placeholder.
Session: defaults to the primary session as described above; the UI supports switching between sessions.
Session groups: sessions.groups.list, sessions.groups.put, sessions.groups.rename, and sessions.groups.delete manage the group catalog. Membership is determined by the session category updated via sessions.patch.
Unread state: once a session activates and its live history loads successfully, the app clears that session's unread marker. A failed history load does not clear it; a transient patch failure will retry on the next activation.
Onboarding uses a dedicated session to keep first-run setup isolated.
Offline cache: the app maintains a small read-only cache of recent chat sessions and transcripts per gateway (~/Library/Application Support/OpenClaw/chat-cache.sqlite): cold opens display the last known transcript immediately and refresh once the Gateway responds, and recent chats remain browsable while offline (sending is disabled until the connection is restored).

Security surface

Remote mode only forwards the Gateway WebSocket control port over SSH.

Known limitations

The UI is designed for chat sessions, not a full browser sandbox.