Add GPT-5 support (OpenAI API parameters)” #1883
Open
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
dickymoore
had a problem deploying
to
unittest
GitHub Actions
Failure
netcorefactory
approved these changes
Sep 14, 2025
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Outdated suggestions cannot be applied.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.
Responding to issue #1880 GPT-5 not supported max_tokens must be max_completion_tokens.
Add GPT-5 support to token accounting and limits (costs, max context, token counting).
Treat GPT-5 as multimodal in model capability checks.
Expose GPT-5 in SPO app model pickers (optimization/evaluation/execution).
Mention GPT-5 in README and example config comments.
Preserve existing model behavior and defaults.
Feature Docs
README and config2.example.yaml comments updated to include “gpt-5”.
No additional RFC/tutorial required; feature is additive.
Influence
Cost tracking now includes GPT-5 with placeholder pricing (mirrors GPT‑4o); update when official rates are available.
Token counting recognizes GPT-5 to avoid NotImplementedError; falls back to cl100k_base if tiktoken lacks mapping.
GPT-5 assumed multimodal; if that’s inaccurate, remove from MULTI_MODAL_MODELS with no broader impact.
UI gains GPT-5 options; no change to defaults.
Result
No tests were run in this change. Functionality is additive and non-breaking; happy to run tests on request.
Other
Update TOKEN_COSTS and TOKEN_MAX when official GPT‑5 pricing/context limits are announced.
If desired, constrain multimodal to only confirmed GPT‑5 variants or add versioned aliases (e.g., gpt-5-turbo).