feat: customer support agent

[KunalJavelin]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @KunalJavelin, 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 delivers a new, fully-featured customer support agent built as an example application. It demonstrates a robust architecture using LangGraph for conversational AI, a Model Context Protocol (MCP) server for efficient and scalable database operations, and Highflame for flexible LLM integration. The agent is designed for practical use, offering multiple interaction points and comprehensive management of customer service workflows.

Highlights

• New Customer Support Agent: Introduces a comprehensive AI-powered customer support agent example, designed to handle various customer service scenarios including order inquiries, technical support, and billing issues.
• LangGraph Integration: The agent leverages LangGraph to manage complex conversation states and routing, ensuring intelligent and context-aware interactions.
• Model Context Protocol (MCP) for Database Operations: Database interactions are isolated within a dedicated MCP server, providing 11 specialized tools for managing customers, orders, tickets, and a knowledge base, enhancing scalability and separation of concerns.
• Unified LLM Provider via Highflame: The agent uses Highflame as a unified LLM provider, supporting both OpenAI and Google Gemini models through a single configuration.
• Multi-Interface Access: The agent is accessible via a FastAPI REST API (supporting stateful and stateless queries), an interactive Streamlit UI, and a command-line interface (CLI).
• Comprehensive Toolset: Beyond database tools, the agent includes direct tools for web searching (DuckDuckGo) and sending emails via SMTP.

🧠 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. ↩

[KunalJavelin]

This agent is intended for testing purposes and was intentionally made vulnerable.

[gemini-code-assist]

Code Review

This pull request introduces a comprehensive customer support agent, which is a significant and well-structured feature. The architecture, separating concerns with an MCP server for database operations, a FastAPI backend, and a Streamlit UI, is excellent. The code is generally clean, well-documented, and includes extensive testing and utility scripts. My review focuses on a few critical issues, including a syntax error and a broken test, as well as opportunities to improve maintainability by refactoring duplicated logic and simplifying complex control flows. Addressing these points will enhance the robustness and clarity of this impressive new feature.