openclaw - 💡(How to fix) Fix Feature: Typing indicator during agent active processing [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openclaw/openclaw#72447Fetched 2026-04-27 05:30:05
View on GitHub
Comments
0
Participants
1
Timeline
0
Reactions
0
Author
Participants
RAW_BUFFERClick to expand / collapse

Problem

Currently OpenClaw sends a typing indicator only during heartbeats (~30 min interval), not during active agent processing. Users see no feedback while the agent is thinking or working.

Expected Behavior

When the agent receives a message and is actively processing (model inference, tool execution, etc.), Telegram should show the typing indicator so the user knows the agent is working.

Current State

  • channels.telegram.heartbeat.useIndicator: true sends typing during heartbeat polls
  • No typing indicator during actual agent turns
  • Users see empty chat while agent is processing complex requests

Proposed Solution

Add an option (e.g., channels.telegram.typingDuringProcessing: true) that sends sendChatAction: typing before model calls and tool executions, and stops when the response is ready.

References

  • Telegram API: sendChatAction with action: typing
  • OpenClaw already has sendTypingTelegram() implemented in the Telegram plugin

extent analysis

TL;DR

Enable the proposed channels.telegram.typingDuringProcessing option to send typing indicators during agent processing.

Guidance

  • Review the Telegram API documentation for sendChatAction to understand the requirements for sending typing indicators.
  • Implement the proposed solution by adding the channels.telegram.typingDuringProcessing option and calling sendTypingTelegram() before model calls and tool executions.
  • Verify that the typing indicator is displayed correctly during agent processing by testing with a complex request.
  • Consider adding error handling to ensure that the typing indicator is stopped when the response is ready or an error occurs.

Example

if (channels.telegram.typingDuringProcessing) {
  sendTypingTelegram();
  // Model calls and tool executions
  // ...
  stopTypingTelegram();
}

Notes

The proposed solution assumes that the sendTypingTelegram() function is correctly implemented in the Telegram plugin. Additional testing may be required to ensure that the typing indicator is displayed correctly in all scenarios.

Recommendation

Apply the proposed workaround by implementing the channels.telegram.typingDuringProcessing option, as it provides a clear solution to the problem and is well-supported by the provided references.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

openclaw - 💡(How to fix) Fix Feature: Typing indicator during agent active processing [1 participants]