Repository navigation
fix: preserve images in tool results - #4661
Merged
Merged
Conversation
Keep typed Chat Completions attachments after the complete tool-result group, including the explicit-cache path. Use native multimodal function outputs for Responses. Signed-off-by: Topabomb <hualei.hb@gmail.com>
dgageot
approved these changes
Oct 20, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #4629. Follow-up to #4608, #4609 and #4610.
#4610 keeps parallel tool replies together, but turns images into text. This restores typed image attachments after all tool replies, with their originating call IDs. It also handles the explicit-cache path and preserves following user text when messages are merged.
Responses now keeps images and files inside their
function_call_outputinstead of adding separate user messages.Checked with
task build,task testandtask linton Linux, plus built-CLI loopback tests for Chat Completions and Responses. Regression tests also cover the existing Anthropic and Gemini 3 converters and text-only model filtering.Gemini integration fixtures were left disabled per the contributing guide. No live-provider vision test was run for this candidate.