fix(py): add test flow in prompt_demo to match JS SDK

[MengqinShen]

This change aims to mirror the prompt and flow definitions from the JS js-prompts sample into the Python prompt_demo sample.

[gemini-code-assist]

Summary of Changes

Hello @MengqinShen, 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 a refactoring in the Genkit Python SDK's core to standardize how action inputs are handled, moving from direct payload['input'] access to a dedicated action_input variable. Concurrently, it enriches the prompt_demo sample by adding new prompt and flow definitions, including examples using Pydantic models for structured data, thereby mirroring the capabilities and examples present in the JavaScript SDK. This ensures feature parity and provides more comprehensive demonstrations for Python users.

Highlights

• Refactored Action Input Handling: The core reflection.py module now explicitly extracts and passes action_input to action execution functions, improving clarity and consistency in how prompt inputs are managed within the Genkit Python SDK.
• Expanded Python Prompt Demo: The prompt_demo.py sample has been significantly updated to include various new Genkit flows and prompt definitions, aligning its functionality and examples with the JavaScript SDK's js-prompts sample for feature parity.
• Pydantic Integration in Prompts: The prompt_demo now demonstrates the use of Pydantic BaseModel for defining structured input and output schemas for Genkit prompts and flows, enhancing type safety and data validation for AI interactions.

🧠 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. ↩

[gemini-code-assist]

Code Review

This pull request aligns the Python prompt_demo sample with the JS SDK by adding several new test flows and prompts. The changes also include a necessary fix in the core reflection API to handle flows that are called without an input.

My review focuses on improving the new sample code in prompt_demo.py. I've pointed out a few areas for improvement regarding Python conventions (PEP 8), type hint correctness, and a critical bug that would cause a runtime error when logging flow results. The changes in reflection.py look good and correctly enable the new functionality.