-
-
Notifications
You must be signed in to change notification settings - Fork 80.7k
[Bug]: User interface stuck in infinite loop #87999
Copy link
Copy link
Closed as not planned
Labels
P1High-priority user-facing bug, regression, or broken workflow.High-priority user-facing bug, regression, or broken workflow.bugSomething isn't workingSomething isn't workingclawsweeper:needs-infoClawSweeper needs more reporter information before it can verify this issue.ClawSweeper needs more reporter information before it can verify this issue.clawsweeper:needs-maintainer-reviewClawSweeper marked this issue as needing maintainer review before automation.ClawSweeper marked this issue as needing maintainer review before automation.clawsweeper:no-new-fix-prClawSweeper does not recommend queueing a new automated fix PR for this issue.ClawSweeper does not recommend queueing a new automated fix PR for this issue.impact:session-stateSession, memory, transcript, context, or agent state can drift or corrupt.Session, memory, transcript, context, or agent state can drift or corrupt.issue-rating: 🦪 silver shellfishThin issue quality; more reproduction proof or environment detail is needed.Thin issue quality; more reproduction proof or environment detail is needed.regressionBehavior that previously worked and now failsBehavior that previously worked and now failsstaleMarked as stale due to inactivityMarked as stale due to inactivity
Description
Metadata
Metadata
Assignees
Labels
P1High-priority user-facing bug, regression, or broken workflow.High-priority user-facing bug, regression, or broken workflow.bugSomething isn't workingSomething isn't workingclawsweeper:needs-infoClawSweeper needs more reporter information before it can verify this issue.ClawSweeper needs more reporter information before it can verify this issue.clawsweeper:needs-maintainer-reviewClawSweeper marked this issue as needing maintainer review before automation.ClawSweeper marked this issue as needing maintainer review before automation.clawsweeper:no-new-fix-prClawSweeper does not recommend queueing a new automated fix PR for this issue.ClawSweeper does not recommend queueing a new automated fix PR for this issue.impact:session-stateSession, memory, transcript, context, or agent state can drift or corrupt.Session, memory, transcript, context, or agent state can drift or corrupt.issue-rating: 🦪 silver shellfishThin issue quality; more reproduction proof or environment detail is needed.Thin issue quality; more reproduction proof or environment detail is needed.regressionBehavior that previously worked and now failsBehavior that previously worked and now failsstaleMarked as stale due to inactivityMarked as stale due to inactivity
Type
Fields
Priority
None yet
Bug type
Regression (worked before, now fails)
Beta release blocker
No
Summary
UI gets stuck in infinite “responding” state after every message
I am experiencing a repeatable issue where the UI becomes stuck after sending any message.
Steps to reproduce
Start the application/user interface.
Open a new session.
Send a simple message, for example: “hello”.
The assistant responds normally.
After the response is completed, the UI still shows the message as in progress / still responding.
The in-progress indicator never stops.
The Stop button does not stop the execution.
I cannot continue using the session normally.
Expected behavior
After the assistant finishes responding, the UI should mark the message as completed, stop the in-progress indicator, and allow the next message to be sent normally.
Deleting the session removes the stuck in-progress indicator, but the issue immediately comes back as soon as I create/send another message in a new session.
Actual behavior
UI gets stuck in infinite “responding” state after every message
I am experiencing a repeatable issue where the UI becomes stuck after sending any message.
OpenClaw version
2026.05.27
Operating system
windows 11
Install method
npm
Model
chatgpt 5.5
Provider / routing chain
openclaw - codex - gpt 5.5
Additional provider/model setup details
Logs, screenshots, and evidence
Impact and severity
Severity: High
Additional information
first known bad version 2026.5.20