Fix google-genai response handling #251
Merged
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Outdated suggestions cannot be applied.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.
This pull request adds support for the new google-genai SDK response format and fixes #246 (which uses a
candidatesattribute instead of the old protobuf_pbattribute) to the LLM base classes. It also introduces comprehensive tests to ensure correct handling of both streaming and non-streaming responses in the new format, while maintaining backwards compatibility with the old format.Support for new google-genai SDK response format:
_format_responseandprocess_chunkmethods inmemori/llm/_base.pyto detect and correctly parse responses and streaming chunks using the new google-genai SDK format, which uses acandidatesattribute instead of_pb[1] [2].Testing and backwards compatibility:
tests/llm/test_llm_google_genai.pywith extensive tests for both the new (no_pb) and old (protobuf) google-genai formats, covering both streaming and non-streaming response handling, as well as format detection and role preservation.