Support strict mode in NativeOutput #2084
Merged
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
severinh
commented
Jun 26, 2025
severinh
commented
Jun 26, 2025
|
@severinh Thank you, I'll review this tomorrow! |
DouweM
requested changes
Jun 27, 2025
Co-authored-by: Douwe Maan <me@douwe.me>
DouweM
changed the title
|
@severinh Thanks Severin! |
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Outdated suggestions cannot be applied.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.
This PR adds the boolean parameter
strictto the newly introducedNativeOutput, analogous to the parameter that already existed onToolOutput. This enables strict mode in supported models. For OpenAI, this turns on constrained grammar sampling, which guarantees at the LLM-level that the output conforms to the JSON schema (at least the subset of supported features).closes #2080