Skip to main content

Typing indicators

Typing indicators are sent to the chat channel while a run is active. Use agents.defaults.typingMode to control when typing starts and typingIntervalSeconds to control how often it refreshes.

Defaults

When agents.defaults.typingMode is unset, OpenClaw keeps the legacy behavior:
  • Direct chats: typing starts immediately once the model loop begins.
  • Group chats with a mention: typing starts immediately.
  • Group chats without a mention: typing starts only when message text begins streaming.
  • Heartbeat runs: typing is disabled.

Modes

Set agents.defaults.typingMode to one of:
  • never — no typing indicator, ever.
  • instant — start typing as soon as the model loop begins, even if the run later returns only the silent reply token.
  • thinking — start typing on the first reasoning delta (requires reasoningLevel: "stream" for the run).
  • message — start typing on the first non-silent text delta (ignores the NO_REPLY silent token).
Order of “how early it fires”: nevermessagethinkinginstant

Configuration

You can override mode or cadence per session:

Notes

  • message mode won’t show typing for silent-only replies (e.g. the NO_REPLY token used to suppress output).
  • thinking only fires if the run streams reasoning (reasoningLevel: "stream"). If the model doesn’t emit reasoning deltas, typing won’t start.
  • Heartbeats never show typing, regardless of mode.
  • typingIntervalSeconds controls the refresh cadence, not the start time. The default is 6 seconds.

Troubleshooting

Typing indicator never appears Verify agents.defaults.typingMode is not "off". Typing indicators require the channel to support them — WhatsApp, Telegram, Discord, Slack, and iMessage all do; some extension channels may not. Typing fires during reasoning but not during the reply Only "thinking" mode triggers a typing indicator for the reasoning phase. If typingMode is "message", the indicator only fires when text content starts streaming. Switch to "thinking" if you want early feedback during extended reasoning. Typing persists after the reply is sent This is a channel-side issue — the gateway always sends a stop event. Try restarting the channel connection via openclaw channels status --probe. Related: Streaming · Agent Loop · Configuration Reference