openclaw - 💡(How to fix) Fix Feishu channel: AI gives zero feedback during long tasks (no typing, no intermediate responses) [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#58990Fetched 2026-04-08 02:30:14
View on GitHub
Comments
0
Participants
1
Timeline
0
Reactions
0
RAW_BUFFERClick to expand / collapse

Problem: When using the Feishu channel, the AI gives zero feedback during task execution. The user sees nothing - no typing indicator, no intermediate messages, no progress updates. The user is completely in the dark about whether the AI is working or frozen.

Detailed behavior:

  1. User sends a message via Feishu
  2. AI receives the message and immediately starts running diagnostic/execution commands (SSH, file reads, etc.) in serial - each taking 5-30 seconds
  3. User sees nothing for 10-20 minutes - no typing indicator, no response
  4. After 10-20 minutes, AI finally outputs its complete response

Additional issues:

  • No typing indicator: Unlike webchat which shows 'Assistant is typing...', Feishu shows nothing at all during the entire processing period
  • No intermediate feedback: Even for 2+ minute tasks, AI never says 'received, processing' or provides progress updates
  • New sessions inherit old context: Even new Feishu conversations route to the same session key (dmScope=per-channel-peer), so context accumulates

Expected behavior:

  1. AI should immediately acknowledge: 'Received, processing...' upon receiving a message
  2. For tasks expected to take >30 seconds, AI should provide progress updates at least every 30-60 seconds
  3. A typing indicator should be shown on Feishu during processing
  4. Consider adding dmScope=always-fresh option for per-message fresh sessions

Reproduction: 100% reproducible on Feishu channel. Happens every time AI needs to run external commands (SSH, file operations).

Labels: bug, feishu

extent analysis

TL;DR

Implementing intermediate feedback messages and a typing indicator for the Feishu channel can improve the user experience by providing regular updates during task execution.

Guidance

  • Modify the AI's task execution logic to send an immediate acknowledgement message ("Received, processing...") after receiving a user's message.
  • Implement progress updates for tasks expected to take longer than 30 seconds, sending updates at least every 30-60 seconds.
  • Investigate integrating a typing indicator for the Feishu channel, similar to the "Assistant is typing..." feature in webchat.
  • Consider adding a dmScope=always-fresh option to allow for per-message fresh sessions, preventing context accumulation.

Example

No specific code example can be provided without more context, but the AI's response generation logic could be modified to include intermediate feedback messages, such as:

def execute_task(user_message):
    # Send immediate acknowledgement
    send_message("Received, processing...")
    
    # Execute task with progress updates
    for step in task_steps:
        # Execute step
        execute_step(step)
        
        # Send progress update
        send_message(f"Processing... ({step}/{len(task_steps)})")
        
    # Send final response
    send_message(final_response)

Notes

The provided guidance assumes that the AI's task execution logic can be modified to include intermediate feedback messages and a typing indicator. The implementation details may vary depending on the specific AI framework and Feishu API being used.

Recommendation

Apply a workaround by implementing intermediate feedback messages and a typing indicator for the Feishu channel, as this can improve the user experience without requiring significant changes to the underlying AI logic.

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