Fix OpenAI OAuth context window detection#499
Open
thanosapollo wants to merge 1 commit into
Open
Conversation
OpenAI OAuth requests use the ChatGPT Codex backend, whose model context windows differ from the direct OpenAI API catalog. Resolve OAuth model limits from Codex /models first and fall back to known Codex OAuth caps so gpt-5.5 reports 272k instead of the direct API's 1.05M window. Assisted by: eca-agent <git@eca.dev>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
OpenAI OAuth uses the ChatGPT Codex backend, whose context
windows differ from the direct OpenAI API catalog.
ECA was resolving OAuth model limits like direct API-key auth, so
openai/gpt-5.5reported the direct API's 1.05M context windowinstead of the Codex OAuth 272k limit.
This resolves OAuth limits from Codex
/modelsfirst, with knownCodex OAuth caps as fallback. API-key OpenAI behavior is unchanged.