Repository navigation
Conversation
Names newer than the hardcoded gpt-5.1/5.2 families fell through to the pattern-based fallback and were rewritten to an older model, which the Codex backend rejects with HTTP 400 (e.g. gpt-5.5). Return gpt-5.3+ and gpt-6+ names unchanged (lowercased) before the fallback so new models work without a code change. Existing mappings are untouched. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Mindrocket42
added a commit
to Mindrocket42/fork-opencode-codex-auth
that referenced
this pull request
Sep 27, 2026
Adapt AmanKRoy's PR numman-ali#131 so unknown GPT-5.3+ and GPT-6+ model IDs pass through without overriding the fork's existing GPT-5.4/5.5 family normalization. Co-authored-by: AmanKRoy <139571185+AmanKRoy@users.noreply.github.com>
|
Thanks @AmanKRoy. This is the right shape. I’ve pulled the future-model passthrough into my fork’s |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
normalizeModel()only knows the gpt-5.1/5.2 families. Any newer name (e.g.gpt-5.5) falls through to the pattern-based fallback and is rewritten to an older model, which the Codex backend rejects with HTTP 400.Change
Return
gpt-5.3+andgpt-6+names unchanged (lowercased) before the fallback. Existing mappings and the legacy fallback are untouched.AGENTS.mdnotes the new rule.Tests
Added cases for
gpt-5.5,GPT-5.5,gpt-5.6-luna,gpt-6-astra,gpt-10andGPT-10-Astra(passthrough, lowercased), plusgpt-5.2,gpt-5.1-codex-maxandgpt-5-codex(mapped as before).npm run typecheck,npm test(232 passing) andnpm run buildpass locally.Related
#126, #129 and #130 also add newer-model support by listing each model explicitly. This is a smaller alternative that avoids a code change per release, and it can sit alongside them.
🤖 Generated with Claude Code