Handle None input_tokens from Anthropic SDK #1674
Closed
+1
−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
|
@DouweM FYI |
|
Thanks so much for this. I didn't see this, until I was reviewing the original PR, this is replaced by #1686 which uprev's the version of anthropic we're using and adds tests. |
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Outdated suggestions cannot be applied.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.
With version 0.51.0 of the Anthropic Python SDK, Anthropic models in Pydantic AI no longer work with streaming due to how we unpack the input_tokens field. Previously we assumed that
getattr(response_usage, 'input_tokens', 0)would always be anint, which is no longer trueI have not added a test case for this, since the current tests already capture the bug and fail when the current version of Anthropic SDK is installed (a win for the awesome test coverage!!)