fix: handle BinaryImage and UserContent types as attachments in cast() #1257
+132
−1
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
Previously, when passing a BinaryImage or other attachment types to marvin.cast(), the data was serialized as text in the context dictionary, causing token explosion (e.g., 207k+ tokens for a small image). This fix: - Detects UserContent attachment types (ImageUrl, AudioUrl, DocumentUrl, VideoUrl, BinaryContent) when passed as data to cast() - Passes these as task attachments instead of serializing them in context - Adds a placeholder "(provided as attachment)" in context Fixes PrefectHQ#1246 Signed-off-by: majiayu000 <[email protected]>
majiayu000
force-pushed
the
fix/binary-image-token-explosion
branch
from
ba25a72 to
fea040d
Compare
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Outdated suggestions cannot be applied.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
BinaryImagetomarvin.cast()Problem
When passing a
BinaryImagetomarvin.cast(), the binary data was being serialized into the task context as a string (base64), causing token explosion (207K+ tokens for a ~200KB image).Solution
Added detection for pydantic-ai's
UserContenttypes and pass them as task attachments instead of putting them in the context dictionary.Test Plan
_is_user_content()helper functionFixes #1246