You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
GPT 5.2 Codex - Compaction happens way too early and context limit is wrong #11086
Activity
github-actions commentedon Jan 29, 2026
This issue might be a duplicate of existing issues. Please check:
Feel free to ignore if none of these address your specific case.
Deftera186 commentedon Jan 29, 2026
This is probably related to a problem in models.dev that was fixed 2 weeks ago:
anomalyco/models.dev@b0e5b91
maybe you still have the old cache for some reason? try to remove your
~/.cache/opencode/models.jsonand update if it helpsWaishnav commentedon Jan 29, 2026
Yup, they have fixed this issue. It is working all fine
dlukt commentedon Feb 5, 2026
Nope. Deleting
~/.cache/opencode/models.jsondoes not fix it.50k tokens and already 39% context used.
No results.
The search for
github-copilotin this repo reveals no results either.How can you greatly announce your partnership when you don't even do the basics?
dlukt commentedon Feb 5, 2026
The issue is most likely because you source https://models.dev/api.json
which incorrectly states the limits for context and output to 128k and 64k
I'm letting OpenAI/gpt-5.2 now fix this issue and will send a PR
dlukt commentedon Feb 5, 2026
test(compaction): add failing tests for missing headroom when limit.i…
github-actions commentedon Apr 7, 2026
To stay organized issues are automatically closed after 90 days of no activity. If the issue is still relevant please open a new one.