# Frontend AI Analysis Integration

## Overview
This document describes the complete integration of AI analysis functionality into the frontend, including real-time monitoring, progress tracking, and API gateway communication.

## Architecture

```
Frontend → API Gateway → AI Analysis Service → Git Integration Service
    ↓           ↓              ↓                      ↓
Real-time UI → HTTP API → Repository Info → Local File Access
    ↓           ↓              ↓                      ↓
Progress     → WebSocket → Analysis → Direct File System
Monitoring   → Stream    → Processing → Access
```

## Components Implemented

### 1. API Routes (`/app/api/ai/repository/`)

#### `/analyze/route.ts`
- **Purpose**: Start AI analysis for a repository
- **Method**: POST
- **Input**: `{ repository_id, user_id, output_format, max_files }`
- **Output**: Analysis result with stats and report path

#### `/stream/route.ts`
- **Purpose**: Real-time streaming of analysis progress
- **Method**: GET
- **Input**: `repository_id`, `user_id` as query parameters
- **Output**: Server-Sent Events stream with progress updates

#### `/report/[filename]/route.ts`
- **Purpose**: Download analysis reports
- **Method**: GET
- **Input**: Filename as URL parameter
- **Output**: File download with appropriate headers

### 2. React Hooks (`/hooks/useAIAnalysis.ts`)

#### `useAIAnalysis` Hook
- **State Management**: Analysis progress, results, errors
- **Functions**:
  - `startAnalysis()`: Initiates analysis with options
  - `stopAnalysis()`: Stops ongoing analysis
  - `resetAnalysis()`: Resets all state
- **Real-time Updates**: Uses EventSource for streaming updates

### 3. UI Components (`/components/ai/`)

#### `AnalysisMonitor.tsx`
- **Real-time Progress**: Shows analysis progress with percentage
- **Status Indicators**: Loading, error, and completion states
- **Statistics Display**: File counts, quality scores, languages
- **Download Functionality**: Direct report download

#### `AnalysisModal.tsx`
- **Modal Interface**: Full-screen analysis interface
- **Progress Tracking**: Real-time progress updates
- **Error Handling**: User-friendly error messages
- **Result Display**: Comprehensive analysis results

### 4. Integration Points

#### GitHub Repos Page (`/app/github/repos/page.tsx`)
- **AI Analysis Button**: Triggers analysis modal
- **Repository Context**: Passes repository ID and name
- **User Context**: Handles user authentication
- **Modal Integration**: Seamless modal experience

## Real-time Features

### 1. Progress Monitoring
```typescript
interface AnalysisProgress {
  current_chunk: number
  total_chunks: number
  processed_files: number
  total_files: number
  percentage: number
}
```

### 2. Status Updates
- **Ready**: Analysis not started
- **Analyzing**: In progress with real-time updates
- **Complete**: Analysis finished with results
- **Error**: Analysis failed with error message

### 3. Statistics Display
- **File Metrics**: Total files, lines of code
- **Quality Scores**: Overall code quality rating
- **Language Breakdown**: Programming languages detected
- **Quality Distribution**: High/medium/low quality files

## API Gateway Integration

### 1. Service Communication
All communication flows through the API gateway:
```
Frontend → Next.js API Routes → External Services
```

### 2. Environment Configuration
```env
# Service URLs
GIT_INTEGRATION_SERVICE_URL=http://git-integration:8012
AI_ANALYSIS_SERVICE_URL=http://ai-analysis-service:8022

# Public URLs (for client-side)
NEXT_PUBLIC_GIT_INTEGRATION_SERVICE_URL=http://localhost:8012
NEXT_PUBLIC_AI_ANALYSIS_SERVICE_URL=http://localhost:8022
```

### 3. Error Handling
- **Service Unavailable**: Graceful fallback messages
- **Network Errors**: Retry mechanisms
- **Analysis Failures**: User-friendly error display

## User Experience Flow

### 1. Analysis Initiation
1. User clicks "AI Analysis" button on repository card
2. Modal opens with analysis interface
3. User can start analysis or close modal

### 2. Real-time Progress
1. Analysis starts with progress indicator
2. Real-time updates show:
   - Files processed
   - Chunks processed
   - Percentage complete
3. User can stop analysis if needed

### 3. Results Display
1. Analysis completes with success indicator
2. Statistics displayed:
   - Total files and lines
   - Quality score
   - Language breakdown
   - Quality distribution
3. Download button for report

### 4. Error Handling
1. Error messages displayed clearly
2. Retry options provided
3. User can close and try again

## Technical Implementation

### 1. State Management
```typescript
const {
  isAnalyzing,      // Analysis in progress
  progress,         // Real-time progress
  result,          // Analysis results
  error,           // Error messages
  startAnalysis,   // Start function
  stopAnalysis,    // Stop function
  resetAnalysis    // Reset function
} = useAIAnalysis()
```

### 2. Real-time Updates
```typescript
// EventSource for streaming updates
const eventSource = new EventSource(streamUrl)

eventSource.onmessage = (event) => {
  const data = JSON.parse(event.data)
  // Update progress, handle completion, etc.
}
```

### 3. File Download
```typescript
const handleDownloadReport = async () => {
  const response = await fetch(`/api/ai/repository/report/${filename}`)
  const blob = await response.blob()
  // Create download link and trigger download
}
```

## Security Considerations

### 1. Authentication
- User ID passed through all requests
- JWT tokens for service authentication
- Repository access validation

### 2. Input Validation
- Repository ID validation
- User ID validation
- File size limits
- Content type validation

### 3. Error Handling
- No sensitive information in error messages
- Graceful degradation on service failures
- User-friendly error display

## Performance Optimizations

### 1. Caching
- Analysis results cached for 24 hours
- File content hashing for change detection
- Redis-based caching system

### 2. Rate Limiting
- 90 requests per minute to Claude API
- Request queuing and throttling
- Progress updates to prevent timeouts

### 3. Content Optimization
- Large files truncated intelligently
- Important code sections preserved
- Token limit compliance

## Deployment Considerations

### 1. Environment Variables
```env
# Required for production
GIT_INTEGRATION_SERVICE_URL=https://git-integration.yourdomain.com
AI_ANALYSIS_SERVICE_URL=https://ai-analysis.yourdomain.com
```

### 2. CORS Configuration
```typescript
// API routes handle CORS
app.add_middleware(
  CORSMiddleware,
  allow_origins=["*"],
  allow_credentials=True,
  allow_methods=["*"],
  allow_headers=["*"],
)
```

### 3. Error Monitoring
- Console logging for debugging
- Error tracking for production
- Performance monitoring

## Testing

### 1. Unit Tests
- Hook functionality testing
- Component rendering tests
- API route testing

### 2. Integration Tests
- End-to-end analysis flow
- Real-time update testing
- Error scenario testing

### 3. Performance Tests
- Large repository handling
- Concurrent analysis testing
- Memory usage monitoring

## Future Enhancements

### 1. Advanced Features
- Batch analysis for multiple repositories
- Analysis scheduling
- Custom analysis parameters

### 2. UI Improvements
- Analysis history
- Comparison between repositories
- Advanced filtering and sorting

### 3. Performance
- Background processing
- Queue management
- Resource optimization

This integration provides a complete, production-ready AI analysis system with real-time monitoring, progress tracking, and seamless user experience through the API gateway architecture.