mirror of
https://github.com/openclaw/openclaw.git
synced 2026-07-15 04:46:03 +00:00
* chore(i18n): regenerate locale bundles for Devices rename * chore(i18n): regenerate locale bundles for Devices rename * chore(i18n): sync locale metadata for Devices rename * fix(gateway): stop tracking ephemeral control-plane clients in presence * feat(ui): merge Instances into a unified Devices page * docs: point Instances references at the unified Devices page * chore(i18n): reconcile locale metadata after rebase * fix(gateway): keep test-mode clients tracked in presence; refresh docs map
3.0 KiB
3.0 KiB
summary, read_when, title
| summary | read_when | title | |
|---|---|---|---|
| When OpenClaw shows typing indicators and how to tune them |
|
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 (keepalive cadence, default 6 seconds).
Defaults
When agents.defaults.typingMode is unset:
- 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 when the admitted run has user-visible activity, such as harness execution activity or message text.
- Heartbeat runs: typing starts when the heartbeat run begins, if the resolved heartbeat target is a typing-capable chat and typing is not 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, or on active harness execution after the turn is accepted.message- start typing on the first user-visible reply activity, such as active harness execution or a non-silent text delta. Silent reply tokens such asNO_REPLYdo not count as text activity.
Order of "how early it fires": never -> message/thinking -> instant.
Configuration
Set the agent-level default:
{
agents: {
defaults: {
typingMode: "thinking",
typingIntervalSeconds: 6,
},
},
}
Override mode or cadence per session:
{
session: {
typingMode: "message",
typingIntervalSeconds: 4,
},
}
Notes
messagemode does not start from silent reply tokens, but active execution can still show typing before any assistant text is available.thinkingstill reacts to streamed reasoning (reasoningLevel: "stream"), and can also start from active execution before reasoning deltas arrive.- Heartbeat typing is a liveness signal for the resolved delivery target. It starts at heartbeat run start instead of following
messageorthinkingstream timing. SettypingMode: "never"to disable it. - Heartbeats do not show typing when the heartbeat target is
"none", when the target cannot be resolved, when chat delivery is disabled for the heartbeat, or when the channel does not support typing. typingIntervalSecondscontrols the refresh cadence, not the start time. Default: 6 seconds.