claude-code - 💡(How to fix) Fix [BUG] Regression: Can no longer type/queue messages while agent is running (Desktop App)

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…

Error Message

Error Messages/Logs

RAW_BUFFERClick to expand / collapse

Preflight Checklist

  • I have searched existing issues and this hasn't been reported yet
  • This is a single bug report (please file separate reports for different bugs)
  • I am using the latest version of Claude Code

What's Wrong?

Describe the bug On the Desktop App, you previously could type in the input field while Claude was actively running a task. The message would queue and be picked up after the current turn completed — without interrupting the agent.

This behavior has regressed in the Desktop App. The input field is now blocked/disabled while the agent runs. The only way to send a new message is to hit the Stop button first, which interrupts the current operation.

Environment

  • App: Claude Desktop App (macOS)

To reproduce

  1. Give Claude a long-running agentic task
  2. While it is actively running, attempt to type in the input field

Expected behavior Input field accepts typing during agent run; message queues and processes after the current turn ends. This worked previously.

Actual behavior Input field is disabled. Must stop the agent to enter any input, interrupting the current run.

Impact High — breaks real-time steering of agentic workflows. This is a confirmed regression from prior Desktop App behavior, not a missing feature.

Related issues #1126, #50246

What Should Happen?

While Claude is actively running a task, the input field should remain active and accept typing. Any message typed during a run should be queued and automatically processed once the current turn completes — without requiring the user to stop the agent first. This behavior worked correctly in a previous version of the Desktop App and has since regressed.

Error Messages/Logs

Steps to Reproduce

start a prompt. as it's working. Add new prompt It's not added to the conversation You have to STOP a prompt for it to discover it Then say GO or something typically to get it to move ahead

Claude Model

None

Is this a regression?

Yes, this worked in a previous version

Last Working Version

No response

Claude Code Version

2.1.92

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Other

Additional Information

No response

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