Repository navigation
feat: add GPT-5.6/5.5/5.4 model support for current ChatGPT backend - #129
Open
GustavMhaler wants to merge 1 commit into
Open
GustavMhaler wants to merge 1 commit into
GustavMhaler wants to merge 1 commit into
Conversation
- Add model mappings for gpt-5.6-luna/terra/sol, gpt-5.5, gpt-5.4-mini - Fix normalizeModel fallback so new models aren't downgraded to deprecated gpt-5.1 - Extend ModelFamily type and prompt/cache file mappings for new families - Update modern and legacy config presets with new models
PaoloC68
added a commit
to PaoloC68/opencode-openai-codex-auth
that referenced
this pull request
Sep 20, 2026
getModelFamily enumerated 5.2 through 5.5 and fell through to a gpt-5.1 catch-all, so gpt-5.6-sol/terra/luna and gpt-6-astra were each sent gpt_5_1_prompt.md while gpt-5.4 and gpt-5.5 correctly received gpt_5_2_prompt.md. The newest models were getting the oldest instructions. This is the same catch-all-default failure that silently downgraded astra in normalizeModel, one layer further down, so the comment now states the invariant: any family omitted here is served the oldest prompt in the repo. Found while reviewing upstream numman-ali#129, which extends ModelFamily for the 5.6 tiers. No new prompt files exist for 5.6 or 6, so they join the existing gpt-5.2 family rather than adding entries that point at the same file.
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The ChatGPT Codex backend has migrated to the gpt-5.6 family (gpt-5.6-luna/terra/sol), gpt-5.5 and gpt-5.4-mini. The current plugin normalizes these new model names down to the deprecated gpt-5.1, which the backend rejects with:
The gpt-5.1 model is not supported when using Codex with a ChatGPT account.Changes:
Verified working with ChatGPT Plus OAuth: chat requests and the gpt-image-1.5 image generation endpoint both succeed.