fix(py): updated prompt sample to match JS SDK

[MengqinShen]

CHANGELOG:
1.Removed unrelated flows (simplePrompt, threeGreetings, etc.) to focus on the prompt file demonstration.
2. Added new flows to match JS SDK.

[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 refactors the Python prompt samples and their corresponding demo application to achieve feature parity with the JavaScript SDK. It introduces more advanced prompt definitions, including structured input/output schemas, partials, and a new list formatting helper. The accompanying main.py demo has been updated to showcase these new capabilities through flows that generate recipes and stream stories, along with improved prompt lifecycle management to prevent unexpected behavior.

Highlights

• Prompt Sample Overhaul: Replaced several basic prompt files with new, more sophisticated examples (_style.prompt, recipe.prompt, recipe.robot.prompt, story.prompt) that showcase advanced features like structured input/output, partials, and helper functions.
• Structured Output with Pydantic: Introduced Ingredient and Recipe Pydantic models in main.py to define and validate structured outputs from prompts, aligning with modern data handling practices.
• Enhanced Prompt Management: Implemented a get_sticky_prompt helper and a global cache to prevent premature garbage collection of prompt objects, ensuring their stability during flow execution.
• New Demo Flows: Added chef_flow, robot_chef_flow, and tell_story flows in main.py to demonstrate recipe generation (including a variant for 'robot' recipes) and streaming story generation, showcasing dynamic prompt configuration and output processing.
• Helper Function Update: Replaced the generic my_helper with a more specific list_helper to format lists within prompts, used by the new recipe.prompt.

🧠 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 updates the Python prompt samples to align with the JavaScript SDK. It introduces new prompts and flows for generating recipes and stories, replacing the older examples. The changes are a good step towards feature parity. However, I've identified a few issues that should be addressed. These include a potential bug in handling stale weak references in get_sticky_prompt, some duplicated comments, an inconsistent return type in one of the new flows, a minor styling issue, and some dead code. Addressing these points will improve the robustness and clarity of the sample code.