openclaw - 💡(How to fix) Fix Session stuck in 'running' state after LLM timeout — abortedLastRun not updated [1 comments, 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#63440Fetched 2026-04-09 07:53:43
View on GitHub
Comments
1
Participants
1
Timeline
3
Reactions
0
Author
Participants
Timeline (top)
closed ×1commented ×1cross-referenced ×1

Fix Action

Fix / Workaround

Workaround: Manually editing sessions.json to set status='idle' and abortedLastRun=true recovers the session.

RAW_BUFFERClick to expand / collapse

Description: When an embedded LLM run times out (e.g. MiniMax idle timeout), the session's status remains 'running' permanently and abortedLastRun is not set to true. The session becomes unresponsive to new messages.

Steps to Reproduce:

  1. Send a message to an agent that causes the LLM to time out
  2. Observe the session status remains 'running'
  3. Subsequent messages fail to generate responses

Expected Behavior: Session should transition back to 'idle' state when a run is aborted due to timeout.

Workaround: Manually editing sessions.json to set status='idle' and abortedLastRun=true recovers the session.

Environment: OpenClaw 2026.4.8, model: MiniMax-M2.7, channel: Telegram

extent analysis

TL;DR

Update the session status to 'idle' and set abortedLastRun to true when an LLM run times out to recover the session.

Guidance

  • Investigate the timeout handling mechanism in the LLM to ensure it correctly updates the session status and abortedLastRun flag.
  • Verify that the session status is being updated correctly in other scenarios, such as successful LLM runs or manual aborts.
  • Consider implementing a periodic cleanup task to identify and recover stuck sessions with a 'running' status.
  • Review the OpenClaw documentation to see if there are any known issues or configuration options related to LLM timeout handling in version 2026.4.8.

Example

No explicit code example is provided, but the workaround involves updating the sessions.json file with the following changes:

{
  "status": "idle",
  "abortedLastRun": true
}

Notes

The provided workaround suggests that manually updating the session status and abortedLastRun flag can recover the session, but a more robust solution would involve fixing the underlying issue with the LLM timeout handling.

Recommendation

Apply a workaround to update the session status and abortedLastRun flag when an LLM run times out, as this is a more immediate solution to recover stuck sessions.

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 Session stuck in 'running' state after LLM timeout — abortedLastRun not updated [1 comments, 1 participants]