[Firebase AI] Add CodeExecution tool support
#15280
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request adds support for the CodeExecution tool, enabling the model to generate and run Python code. The changes are well-implemented across the SDK, including updates to data models (Part, ModelContent, Tool), addition of new log codes, and comprehensive unit and integration tests. The refactoring of the Tool initializer is a nice improvement for future extensibility. I have one minor suggestion to improve consistency in parameter naming.
# Conflicts: # FirebaseAI/CHANGELOG.md # FirebaseAI/Sources/AILog.swift # FirebaseAI/Sources/ModelContent.swift
Generated by 🚫 Danger |
There was a problem hiding this comment.
Code Review
This pull request adds support for the Code Execution tool, enabling the model to generate and run Python code. The changes are well-structured, introducing new types for executable code and its results, updating the Tool configuration, and adding comprehensive unit and integration tests. The refactoring of the Tool initializer is a good improvement. The implementation is robust, using safe unwrapping for optional values from the backend. Overall, this is a solid contribution.
Added support for the Code Execution tool that enables the model to generate and run Python code.