feat: rehydrate image context in multi-turn conversations for vision models#334
Open
nap-liu wants to merge 1 commit intodataelement:mainfrom
Open
feat: rehydrate image context in multi-turn conversations for vision models#334nap-liu wants to merge 1 commit intodataelement:mainfrom
nap-liu wants to merge 1 commit intodataelement:mainfrom
Conversation
…models Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Author
|
Now that #392 (DingTalk media support) is merged without image context rehydration, this PR is the remaining piece needed for multi-turn conversations with vision models — images sent in earlier turns are re-attached to subsequent LLM calls so the model retains visual context. Verified clean-merge against current |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
image_context.py: scans history for[file:xxx.jpg]markers, reads from disk, injects base64supports_visionTest plan