Summary of Changes

Hello @jc200808, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces several enhancements and fixes to the base and OpenAI chat model modules. It focuses on improving the robustness of tool choice validation, refining audio data formatting for Qwen-omni models to ensure correct base64 prefixing and immutability, and enhancing the management of structured output requests for Qwen models by providing warnings and defaulting to a compatible JSON object format. These updates aim to improve the reliability and compatibility of the chat model integrations.

Highlights

• Enhanced Tool Choice Validation: The _validate_tool_choice function has been significantly improved for robustness. This includes converting TOOL_CHOICE_MODES from a list to a set for optimized lookups, adding checks for empty tool_choice strings, and implementing detailed validation of the tools structure to ensure correct dictionary and string types for function names.
• Qwen-Omni Audio Data Formatting Refinement: The _format_audio_data_for_qwen_omni function now returns a new list of formatted messages instead of modifying the input in-place. It also incorporates a try-except block for error handling during formatting and ensures the 'data:;base64,' prefix is only added to audio data if it's not already an HTTP link.
• Structured Output Handling for Qwen Models: The achat method now provides specific handling for Qwen models when attempting Pydantic structured output. It logs a warning indicating that Qwen models do not support this via response_format and defaults to an unstructured JSON object format, while correctly applying structured models for other non-Qwen models.
• Altered Tool Choice Validation Trigger: The condition for invoking _validate_tool_choice within the achat method was inverted from if tool_choice: to if not tool_choice:. This means validation will now only occur if tool_choice is a falsy value (e.g., None or an empty string), potentially bypassing validation for explicitly provided tool names.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.