fix: align codex oauth models and request contract#717
Open
tuanminhhole wants to merge 1 commit intodecolua:masterfrom
Open
fix: align codex oauth models and request contract#717tuanminhhole wants to merge 1 commit intodecolua:masterfrom
tuanminhhole wants to merge 1 commit intodecolua:masterfrom
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
9Router Codex OAuth Fix Draft
Closes #718
Proposed PR Title
Fix Codex OAuth request contract and narrow exposed ChatGPT-account models
Summary
/responsesprobe payload during provider self-testmax_output_tokensbefore dispatching Codex requestscx/*model list to models verified to work with ChatGPT Plus OAuth on 2026-04-21Repro
/api/providers/:id/testor route acx/*model through/v1/responses.unavailablestate or repeated 400 errors for models the account can actually use.Root Cause
inputstream: falseinstructionsmax_output_tokens, which the current Codex backend rejectscx/*models that ChatGPT-account OAuth currently rejects upstreamVerified Working Models
cx/gpt-5.4cx/gpt-5.4-minicx/gpt-5.3-codexcx/gpt-5.2Verified Rejected Models
cx/gpt-5.3-codex-xhighcx/gpt-5.3-codex-highcx/gpt-5.3-codex-lowcx/gpt-5.3-codex-nonecx/gpt-5.3-codex-sparkcx/gpt-5.2-codexcx/gpt-5.1-codex-maxcx/gpt-5.1-codexcx/gpt-5.1-codex-minicx/gpt-5.1-codex-mini-highcx/gpt-5.1cx/gpt-5-codexcx/gpt-5-codex-miniFiles Changed In Upstream Draft
.tmp/9router-upstream/open-sse/executors/codex.js.tmp/9router-upstream/open-sse/config/providerModels.js.tmp/9router-upstream/src/app/api/providers/[id]/test/testUtils.js.tmp/9router-upstream/README.mdSuggested PR Body
This patch fixes a Codex OAuth mismatch against the current ChatGPT-backed Codex
/responsesbackend.Changes:
max_output_tokensbefore forwarding Codex requestscx/*list to models that were verified working with ChatGPT Plus OAuth on 2026-04-21Why:
instructions, list-forminput,stream: true, andstore: false