(feat)Add GPT-5.4 and GPT-5.3-Codex model support#157
Merged
lofcz merged 2 commits intolofcz:masterfrom Mar 7, 2026
Merged
Conversation
Add GPT-5.4 and GPT-5.4-pro across the OpenAI model catalog and provider mappings. Add GPT-5.3-Codex through the codex-specific OpenAI path and expose matching OpenRouter and Requesty entries. Remove the placeholder GPT-5.3 non-codex family that was never publicly available and update the README string-model example to use gpt-5-mini.
Adjust the context window summarizer order test to use a token-sized chunk threshold that actually exercises the multi-summary path. Keep the original six-message expectation while updating the comments to reflect token-based chunking.
lofcz
approved these changes
Mar 7, 2026
Owner
|
thanks |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add
gpt-5.4support, addgpt-5.3-codex, and clean up stale OpenAI model referencesThis PR updates the OpenAI model catalog to match what is actually available today.
What changed:
gpt-5.4andgpt-5.4-progpt-5.3-codexGPT-5.3family that was never publicly available as a normal OpenAI modelgpt-4oas a string model name and changed it togpt-5-miniWhy:
gpt-5.4is now the current public GPT-5.4 line and should be available in the SDKgpt-5.3-codexhas been public for a while and was missingGPT-5.3non-codex entry was misleading because that model was never actually publicgpt-4o)Notes:
gpt-5.4was added with the same compatibility handling style already used for other GPT-5.x modelsgpt-5.3-codexwas added through the codex-specific path, not by reintroducing a fake generalGPT-5.3model familyPreservesOrder_WithChunkSplitting_MultipleSummaries:The test intended to verify the multi-summary path, but its
ChunkSizeassumed character-based splitting while the summarizer actually splits on estimated tokens.Lowering the chunk size and updating the comments preserves the original six-message expectation while making the setup match the implementation.