[BUG] Desktop (Windows): "Add to prompt" quote cards grow without limit and cover the conversation

Status Open
Reported on v2.1.280
Maintainer reply None cached
Activity 0 comments · opened Sep 25, 2026

Preflight Checklist

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

What's Wrong?

When replying to several text selections with "Add to prompt" in the Claude desktop app (Code tab), each quote becomes a card above the message box. The cards wrap into a grid that keeps growing, with no scrolling, collapsing, or height limit. With about 15 cards, the grid covers most of the window and hides the conversation being replied to. Long, multi-quote replies are a core workflow, so this makes the feature hard to use.

What Should Happen?

The quote-card area should not push the conversation out of view. Suggested fix: cap the card area's height with internal scrolling, or collapse the cards into a compact chip (e.g. "16 quotes ▾") that expands on click, so the conversation stays visible.

Error Messages/Logs

Steps to Reproduce

  1. Open a Code-tab session in the Claude desktop app on Windows with a conversation containing several long assistant responses.
  2. Select a passage of text, open the Reply popup, type a short note, and choose "Add to prompt".
  3. Repeat for about 15 different passages.
  4. Observe that the quote cards form a grid above the message box that grows until it covers most of the window, hiding the conversation.

Claude Model

Opus

Is this a regression?

I don't know

Last Working Version

_No response_

Claude Code Version

Claude desktop for Windows 2.7032.0.0 (bundled Claude Code 2.1.280)

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

Other

Additional Information

Environment: Claude desktop for Windows 2.7032.0.0, Code tab. This is desktop-app UI rather than the terminal CLI. No screenshot attached because it would contain private conversation content.

View original on GitHub ↗