🏏 Captain Cool (IPL Match Strategist)

An autonomous multi-agent IPL (Indian Premier League) tactical advisor built on top of Google Gemini and the Google ADK framework. This application ingests live match states and orchestrates a debate between AI agents (Strategist, Devil's Advocate, Stats Analyst, Commentator) to provide calculated "captaincy" decisions.

Features

• Multi-Agent Deliberation: Coordinated pipeline where a Strategist proposes a move, a Devil's Advocate challenges it, and the Strategist revises or defends it.
• Robust Error Handling: Strict JSON parsing, Pydantic field validation boundaries, and complete CORS/UI security.
• Accessible UI: A lightweight, vanilla JavaScript frontend with WCAG 2.1 AA accessible forms, ARIA live region announcements, and XSS sanitization.
• Memoized Tools: Backend function endpoints limit redundant external API calls, reducing time complexity and HTTP overhead.

Quickstart

Prerequisites

• Python 3.10+
• A Google Gemini API Key

Setup

1. Clone the repository:

   git clone https://github.com/yourusername/captain-cool.git
   cd captain-cool

2. Create a virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies:

   pip install -r requirements.txt

4. Environment Variables: Copy the example config and add your Gemini API Key:

   cp .env.example .env
   # Edit .env and set GEMINI_API_KEY=your_actual_key

5. Run the API (FastAPI Backend):

   uvicorn orchestrator.adk_pipeline:app --reload --port 8000

6. Open the App: Open ui/index.html directly in your browser or run a simple local web server in the ui folder.