# TalentScout Agent Guide

## Project Overview
TalentScout is a Next.js application that helps companies find talent and helps talent find jobs. The application uses MongoDB, GraphQL with Apollo, and Next.js with TypeScript and Tailwind CSS.

## Development Environment Setup
- Run `npm install` to install all dependencies
- Copy `.env.example` to `.env.local` and fill in the required variables
- Run `./setup.sh` to configure OpenAI Codex integration
- Run `npm run dev` to start the development server

## Testing Instructions
- Run `npm run lint` to check for linting errors
- Run `npm run build` to ensure the application builds correctly

## Code Structure
- `/src` - Contains all source code
  - `/src/app` - Next.js App Router pages and layouts
  - `/src/components` - React components
  - `/src/utils` - Utility functions including OpenAI integration
  - `/src/graphql` - GraphQL schemas and resolvers
  - `/src/models` - MongoDB models

## OpenAI Codex Integration

### Setup
1. Obtain an OpenAI API key from [OpenAI Platform](https://platform.openai.com/)
2. Run `./setup.sh` and enter your API key when prompted
3. The script will configure both `.env.local` and `.codexrc` files

### Available Codex Features

#### Code Generation
Use the `generateCodeCompletion` function from `src/utils/openai.ts` to generate code based on prompts:

```typescript
import { generateCodeCompletion } from '@/utils/openai';

// Example: Generate a React component
const prompt = 'Create a React component that displays a user profile';
const generatedCode = await generateCodeCompletion(prompt, {
  language: 'typescript',
  maxTokens: 500,
  temperature: 0.7
});
```

#### Code Analysis
Use the `analyzeCode` function to get suggestions for improvements and bug fixes:

```typescript
import { analyzeCode } from '@/utils/openai';

// Example: Analyze a function for improvements
const codeToAnalyze = `function calculateTotal(items) {
  let total = 0;
  for (let i = 0; i < items.length; i++) {
    total += items[i].price;
  }
  return total;
}`;

const analysis = await analyzeCode(codeToAnalyze, 'javascript');
```

#### Unit Test Generation
Use the `generateUnitTests` function to create tests for your code:

```typescript
import { generateUnitTests } from '@/utils/openai';

// Example: Generate Jest tests for a function
const codeToTest = `export function validateEmail(email) {
  const regex = /^[^\s@]+@[^\s@]+\.[^\s@]+$/;
  return regex.test(email);
}`;

const tests = await generateUnitTests(codeToTest, 'javascript', 'jest');
```

### Best Practices for Using Codex

1. **Provide Clear Context**: When generating code, include relevant context about your project structure and requirements.

2. **Review Generated Code**: Always review and test code generated by Codex before integrating it into your project.

3. **Iterative Refinement**: Use Codex iteratively, refining prompts based on initial results to get better output.

4. **Security Considerations**: Never include sensitive information in your prompts to Codex.

5. **Rate Limiting**: Be mindful of OpenAI API rate limits and costs when making frequent requests.

## Contribution Guidelines
- Follow TypeScript best practices
- Use Tailwind CSS for styling
- Write clean, modular code
- Add appropriate comments and documentation
- Leverage Codex for code reviews and suggestions

## PR Instructions
- Provide a clear title and description
- Reference any related issues
- Include screenshots for UI changes
- Ensure all tests pass
- Consider including Codex-generated analysis of your changes