feat(openai): Image generation meta #879
Merged
+31
−0
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Outdated suggestions cannot be applied.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
Closes #583
Surfaces OpenAI-specific image response metadata via
additionalContenton the image response. This includesinput_tokens_details(text_tokens, image_tokens) and resolved parameters (quality, size, output_format, background) returned by gpt-image-1.Uses
Arr::whereNotNull()so older models (DALL-E 2/3) that don't return these fields simply have an emptyadditionalContentarray — no breaking changes.Changes
src/Providers/OpenAI/Handlers/Images.php— PopulateadditionalContenton theResponseBuilderwithinput_tokens_details,quality,size,output_format, andbackgroundfrom the API responsetests/Providers/OpenAI/ImagesTest.php— AssertadditionalContentvalues for gpt-image-1 generation and image edit responses; assert emptyadditionalContentfor DALL-E 3 (no regression)