add auto-function-call requests

[davidmotson]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @davidmotson, 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 enhances the existing mock response data by introducing new JSON files that simulate successful auto-function call responses from Vertex AI. These additions are crucial for testing and development workflows that rely on the model's ability to generate and suggest function executions, covering both single and parallel function call scenarios.

Highlights

• New Mock Data for Vertex AI Function Calls: This PR introduces two new JSON mock response files for Vertex AI, specifically designed to simulate successful auto-function calls.
• Unary Function Call Mock: One mock file (unary-success-auto-function-call.json) provides a response for a single function call, demonstrating the fetchWeather function.
• Parallel Function Call Mock: The second mock file (unary-success-parallel-auto-function-call.json) illustrates a response with multiple, parallel function calls, including fetchWeather and completelyDifferentFunction.

🧠 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.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

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. ↩

[github-actions]

Coverage Diff

GenerateContentResponse: 59 -> 60 🔵
| candidates: 54 -> 55 🔵
| | content: 53 -> 54 🔵
| | | parts: 49 -> 50 🔵
| | | | functionCall: 9 -> 10 🔵
| | | | | args: 8 -> 9 🔵
| | | | | name: 9 -> 10 🔵
| | | role: 42 -> 43 🔵
| | finishReason: 48 -> 49 🔵
| | | STOP: 44 -> 45 🔵
| | index: 32 -> 33 🔵

Legend:
✅ : total coverage increase
🔵 : files number increase, total coverage unaffected
🟡 : files number decrease, total coverage unaffected
❌ : total coverage decrease

[gemini-code-assist]

Code Review

This pull request adds two new mock JSON responses for Vertex AI auto-function-call scenarios. The overall structure looks good, but I've noticed an inconsistency in how function arguments are structured compared to existing mock files. The new files wrap arguments within a param object, which seems unnecessary and could lead to incorrect test assumptions. I've left suggestions to flatten the argument structure for consistency.

[gemini-code-assist]

The args object appears to have an unnecessary level of nesting with the param key. Other mock responses in this repository (e.g., unary-success-function-call-with-arguments.json) define arguments directly within the args object. This inconsistency could cause issues in tests that rely on this mock data. I suggest flattening the structure for consistency and to better reflect the likely API contract.

                "state": "MA",
                "city": "Boston",
                "date": "2024-10-17"

[gemini-code-assist]

Similar to the other new mock file, the args for fetchWeather are nested under a param key. For consistency with other mock responses and the likely API behavior, these arguments should be at the top level of the args object.

                "state": "MA",
                "city": "Boston",
                "date": "2024-10-17"

[gemini-code-assist]

The args for completelyDifferentFunction also have the param nesting. It's unlikely that two different functions would share this exact argument structure. The arguments should probably be flattened here as well. Additionally, it's worth verifying if these are the correct arguments for completelyDifferentFunction, as they are identical to those for fetchWeather.

                "state": "MA",
                "city": "Boston",
                "date": "2024-10-17"