add support for extra_content in chat response tool calls returned by Gemini models#718
Open
ezequiel-safirsztein-momentum wants to merge 2 commits intoopenai-php:mainfrom
Conversation
ezequiel-safirsztein-momentum
changed the title
Collaborator
|
Could we keep the error changes and this change split? Tackling a unified Gemini error thing is a bit more difficult and I wouldn't want it caught up with this extra content. You can see outstanding questions for Gemini errors in this PR: #693 |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What:
Description:
This PR introduces support for the extra_content field, which is returned by certain Gemini models (specifically those utilizing the reasoning signature) during tool calls.
When interacting with these models, the API provides extra_content alongside tool calls. To maintain the integrity of the conversation and satisfy the model's reasoning signature requirements, this content must be preserved and passed back to the API when submitting tool outputs.
Changes:
• Updated the response handling to parse and expose extra_content from tool call responses.
• Updated the payload builder to include extra_content when submitting tool outputs back to the model.