feat: implement multi-agent orchestration backend #61

[motalib-code]

This PR implements the backend infrastructure for the Multi-Agent Orchestration System (Issue #61). It introduces a new engine capable of managing dynamic runtimes where multiple AI agents (planner, executor, researcher, etc.) collaborate sequentially to complete complex tasks.

The system handles agent definition, execution sequencing, logic state management, and detailed step-by-step logging, paving the way for autonomous multi-agent workflows.

✨ Key Features Implemented
Dynamic Agent Configuration: Created schemas to define agents with specific roles (planner, researcher, executor), inputs, and priorities.
Orchestration Engine: Implemented a service that executes agents in a defined sequence, passing the output of one agent as the context/input for the next.
State Management: Tracks the lifecycle of a run (pending → running → completed or failed) using MongoDB.
Audit Logging: capturing detailed execution logs (input, output, execution time) for every step in a run.
Safety: Added validation (Zod) for maximum agents per run (limit: 7) and data integrity.

[gemini-code-assist]

Summary of Changes

Hello @motalib-code, 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 establishes the foundational backend for a multi-agent orchestration system. It provides the necessary components to define, manage, and execute sequences of AI agents, facilitating complex task completion through collaborative workflows. The system includes robust state tracking, comprehensive logging, and input validation to ensure reliable and observable agent operations.

Highlights

• Multi-Agent Orchestration Backend: Introduces the core backend infrastructure for a Multi-Agent Orchestration System, enabling dynamic runtime management for collaborative AI agents.
• Dynamic Agent Configuration: New schemas are implemented to define agents with specific roles (planner, researcher, executor), inputs, and priorities, allowing flexible agent setup.
• Orchestration Engine & State Management: A service is added to execute agents in a defined sequence, passing context between them, and MongoDB is used to track the lifecycle of each run (pending, running, completed, failed).
• Audit Logging & Safety: Detailed step-by-step execution logs are captured for every agent interaction, and Zod validation ensures data integrity, including a limit of 7 agents per run.

🧠 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 PR introduces a robust backend for multi-agent orchestration. The code is well-structured, with clear separation of concerns into controllers, services, models, and validators. The use of Zod for validation and constants for statuses and roles is excellent. My review focuses on improving type safety, error handling, and performance. Key suggestions include removing any types to leverage TypeScript's full potential, enhancing error handling to provide more accurate HTTP status codes, addressing a critical issue with potential unhandled promise rejections that could crash the service, and making minor improvements in Mongoose schema definitions and array handling to align with best practices. Overall, this is a great addition, and addressing these points will make the implementation more resilient and maintainable.

[motalib-code]

pls