Where does the bug appear (feature/product)?
Cursor IDE
Describe the Bug
My prompts are increasingly automated with slash commands. E.g. /go is a slash command that fetches the next unblocked issue from the tracker and works on it.
The agent chat seems to only use the initial prompt when setting the title of the chat. Since /go says nothing on its own, the chat remains named “New chat”. Now my history is filled with "New chat"s and I cannot find anything.
Steps to Reproduce
cat "Say hi!" >> .claude/commands/go.md
New chat: /go
It will say hi, but the chat name remains “New chat”.
Expected Behavior
Chat name should end up descriptive of what the agent actually did. In my case, it would only know this after following some steps in the slash command to get an issue from the tracker and start working on it.
Perhaps for slash commands the name should be set after the first complete response by the agent.
An interim hack would be to include the first 10 lines of the slash command definition in the text used to derive the chat name. In my case it would probably always say “Start work on an issue” since the command definition doesn’t change, but it at least suggests which command I ran as opposed to “New chat”.
Operating System
MacOS
Current Cursor Version (Menu → About Cursor → Copy)
Version: 2.3.41
VSCode Version: 1.105.1
Commit: 2ca326e0d1ce10956aea33d54c0e2d8c13c58a30
Date: 2026-01-16T19:14:00.150Z (2 days ago)
Electron: 37.7.0
Chromium: 138.0.7204.251
Node.js: 22.20.0
V8: 13.8.258.32-electron.0
OS: Darwin arm64 25.2.0
For AI issues: which model did you use?
Opus 4.5
Does this stop you from using Cursor
No - Cursor works, but with this issue