Fix(tools): Prevent VLM tool from returning image in assistant message #717
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
Author
|
|
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Outdated suggestions cannot be applied.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.
What problem does this PR solve?
Currently, when using the
CropResizetool inqwen2vl_assistant_tooluse.py, the agent fails with aModelServiceError: InvalidParameter. The error message indicates that animagemodal cannot be placed in anassistantmessage.This happens because the
CropResize.callmethod returns aContentItem(image=output_path), which the agent framework then incorrectly tries to send as part of theassistant's turn, violating the model's API rules.How does this PR solve the problem?
This PR fixes the issue by commenting out the line that returns the
ContentItemwith an image.[ContentItem(image=...), ContentItem(text=...)].[ContentItem(text=...)], which correctly provides the path to the generated image within the text message.This change aligns the tool's behavior with the API's requirements, allowing the interaction to complete successfully while still providing the user with the necessary information about the generated file.