fix(streaming): resolve Pydantic validation bypass causing dict attribute crashes - #1861
Open
vjaudir8123-debug wants to merge 1 commit into
Open
Conversation
…bute crashes The snapshot initialization previously used Pydantic's `construct(**event.message.to_dict())`. Because `construct()` skips validation and deep coercion, nested fields like `usage` were left as raw Python dictionaries rather than Pydantic objects. When a subsequent usage delta arrived, `current_snapshot.usage.output_tokens = ...` would crash with `AttributeError: 'dict' object has no attribute 'output_tokens'`. This PR isolates and fixes this type safety bug by using `construct_type(type_=...)`, ensuring correct instantiation of nested models. Co-authored-by: Claude <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
(Extracted from #1797 to isolate the Pydantic type safety bug from the out-of-order index bug).
The snapshot initialization currently uses Pydantic
sconstruct(**event.message.to_dict()). Becauseconstruct()skips validation and deep coercion, nested fields likeusage` are left as raw Python dictionaries rather than Pydantic objects.When a subsequent usage delta arrives,
current_snapshot.usage.output_tokens = ...will crash withAttributeError: 'dict' object has no attribute 'output_tokens'. This PR isolates and fixes this type safety bug by usingconstruct_type(type_=...), ensuring correct instantiation of nested models so they can be safely mutated by subsequent streaming events.