Repository navigation
Conversation
|
Eagerly waiting for this one to be merged |
This was referenced Sep 8, 2026
5 of 6 tasks
Member
|
This branch has been upgraded to V2. We're no longer taking PRs for V1. If you think this is still relevant, please port it over and open it for V2. — from 𝕺𝖕𝖊𝖓𝕮𝖔𝖉𝖊 |
1 task done
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Issue for this PR
Closes #46527
Type of change
What does this PR do?
This adds opt-in 1M-context variants for the GPT-5.6 Codex OAuth models:
gpt-5.6-sol-1mgpt-5.6-sol-fast-1mgpt-5.6-terra-1mgpt-5.6-terra-fast-1mgpt-5.6-luna-1mgpt-5.6-luna-fast-1mThe existing GPT-5.6 models remain unchanged with their current 400K context and 272K input limits.
The new variants use a 1,000,000-token context limit, with 872,000 input tokens and 128,000 output
tokens.
The new variants resolve to the same underlying Codex model IDs as their standard counterparts while
preserving the existing model options and reasoning variants. Other models, including GPT-5.5 and
unsupported GPT-5.6 variants, are not affected.
How did you verify your code works?
cd packages/opencode && bun test test/plugin/codex.test.tscd packages/opencode && bun typecheckTURBO_CONCURRENCY=4 bun run typecheckThe Codex plugin test suite passed with 24 tests, and the full typecheck passed with 30 tasks.
Screenshots / recordings
Not applicable — this is not a UI change.
Checklist