fix(openai): support fine-tuned models in structured output#958
Open
danielsimkus wants to merge 1 commit intoprism-php:mainfrom
Open
fix(openai): support fine-tuned models in structured output#958danielsimkus wants to merge 1 commit intoprism-php:mainfrom
danielsimkus wants to merge 1 commit intoprism-php:mainfrom
Conversation
Allow fine-tuned models (e.g. ft:gpt-4.1-mini-2025-04-14:company:model-name:hash) to use structured output by extracting the base model and using prefix matching for version-dated variants. Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
danielsimkus
force-pushed
the
bug/add-support-for-openai-finetuned-models
branch
from
13c4bae to
979528e
Compare
|
Yes please 🫡 |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Fine-tuned OpenAI models (e.g.
ft:gpt-4.1-mini-2025-04-14:company:model-name:hash) silently fall back to JSON mode instead of using structured output. The resolver now extracts the base model from fine-tuned identifiers and uses prefix matching to correctly resolve structured output support for dated model variants.Changes
ft:prefixed identifiers before checking supportin_arraymatching with prefix matching for structured output support (coversgpt-4o,gpt-4.1,gpt-4.5,gpt-5,chatgpt-4o, ando3-minifamilies)