Fix missing "model" role in Gemini LLM responses

[kaikreuzer]

Problem

Chat history that was sent on subsequent requests was only storing user messages, missing bot responses due to Gemini class creating Content objects without the required "model" role.

Solution

Applied fix to all LlmResponse.create() calls in Gemini class

Result

• Bot responses now properly stored in chat history alongside user messages
• Maintains backward compatibility
• All tests pass

[gemini-code-assist]

Summary of Changes

Hello @kaikreuzer, 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!

I've implemented a fix to ensure that bot responses from the Gemini LLM are correctly stored in chat history. Previously, these responses were not being saved because the Content objects generated by the Gemini class were missing the essential "model" role. This change resolves the problem by explicitly assigning the "model" role during the creation of LlmResponse objects, thereby completing the chat history for subsequent requests. The update maintains backward compatibility and has passed all relevant tests.

Highlights

• Fix Missing "model" Role: I've addressed an issue where Gemini LLM responses were not being properly stored in chat history. This was due to the Content objects lacking the required "model" role when created.
• Solution Implementation: The solution involved applying a fix to all LlmResponse.create() calls within the Gemini class, specifically by adding .role("model") to the Content.builder().

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in issue comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments or fill out our survey to provide feedback.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request correctly addresses the issue of a missing "model" role in Gemini LLM responses by adding it to the manually constructed Content objects. My review feedback focuses on improving maintainability by refactoring duplicated code.

[Poggecci]

Good catch, thank you!