Where does the bug appear (feature/product)?
Cursor IDE
Describe the Bug
When picking a 1M Model / Version the Context doesnt get updated to 1M it stays with the normal context limit of the Base Model.
Only Opus 4.6 seems to work, Opus 4.7 and GPT 5.5 dont work.
when changing the model while the context is already above the base models limit it will be set to the maximum context of the model = 100% context is being used. Chat summarization happens after that…
Steps to Reproduce
Create a new chat, choose Opus 4.7 or GPT 5.5 and select the 1M option. Send a message and hover over the context bar. It shows 272k / 300k Tokens as the limit tho it should have 1M or 929k or smth in that range. Change the model while in a current chat also shrinks the max context to the 272 / 300k limit…
Expected Behavior
When picking the 1M model it should get that context limit.
Screenshots / Screen Recordings
Operating System
MacOS
Version Information
Version: 3.2.16
VSCode Version: 1.105.1
Commit: 3e548838cf824b70851dd3ef27d0c6aae371b3f0
Date: 2026-04-28T21:07:47.682Z
Layout: editor
Build Type: Stable
Release Track: Default
Electron: 39.8.1
Chromium: 142.0.7444.265
Node.js: 22.22.1
V8: 14.2.231.22-electron.0
OS: Darwin arm64 25.4.0
For AI issues: which model did you use?
GPT 5.5 Extra High, Opus 4.7 high, Opus 4.6 high
Does this stop you from using Cursor
Sometimes - I can sometimes use Cursor
