Troubleshooting Scenarios

Real-world troubleshooting examples and solutions for common DeepWikiOpen issues

Troubleshooting Scenarios

This guide provides step-by-step solutions for common issues you may encounter when using DeepWikiOpen.

1. API Key Validation Issues

Scenario: “Invalid API key” error when starting the application

Symptoms

Error: Invalid API key provided
Status: 401 Unauthorized

Debugging Steps

1. Verify API key format

   # Check if API key is properly set
   echo $ANTHROPIC_API_KEY
   
   # Should start with "sk-ant-api03-"
   

2. Check environment file

   # Ensure .env file exists
   ls -la .env
   
   # Verify contents
   cat .env | grep ANTHROPIC_API_KEY
   

3. Test API key directly

   curl https://api.anthropic.com/v1/messages \
     -H "x-api-key: $ANTHROPIC_API_KEY" \
     -H "anthropic-version: 2023-06-01" \
     -H "content-type: application/json" \
     -d '{
       "model": "claude-3-5-sonnet-20241022",
       "max_tokens": 10,
       "messages": [{"role": "user", "content": "Hello"}]
     }'
   

Solutions

# Solution 1: Export API key correctly
export ANTHROPIC_API_KEY="sk-ant-api03-your-actual-key"

# Solution 2: Fix .env file formatting
echo 'ANTHROPIC_API_KEY="sk-ant-api03-your-actual-key"' > .env

# Solution 3: Use Docker with proper env passing
docker run -e ANTHROPIC_API_KEY="$ANTHROPIC_API_KEY" \
  deepwikiopen/app:latest

# Solution 4: Check for special characters
# Ensure no trailing spaces or newlines
ANTHROPIC_API_KEY=$(echo "$ANTHROPIC_API_KEY" | tr -d ' \n')

2. Connection Problems (CORS, Network)

Scenario: CORS errors when accessing the API

Symptoms

Access to XMLHttpRequest at 'http://localhost:8000/api' from origin 
'http://localhost:3000' has been blocked by CORS policy

Debugging Steps

1. Check server CORS configuration

   # backend/main.py
   from fastapi.middleware.cors import CORSMiddleware
   
   app.add_middleware(
       CORSMiddleware,
       allow_origins=["http://localhost:3000"],  # Add your frontend URL
       allow_credentials=True,
       allow_methods=["*"],
       allow_headers=["*"],
   )
   

2. Verify network connectivity

   # Test backend is running
   curl http://localhost:8000/health
   
   # Check ports are not blocked
   netstat -an | grep -E "8000|3000"
   

3. Inspect browser network tab

   • Open Developer Tools → Network tab
   • Look for preflight OPTIONS requests
   • Check response headers for CORS headers

Solutions

// Solution 1: Frontend proxy configuration
// frontend/package.json
{
  "proxy": "http://localhost:8000"
}

// Solution 2: Use environment-specific API URLs
const API_BASE = process.env.REACT_APP_API_URL || 'http://localhost:8000';

// Solution 3: nginx reverse proxy
// nginx.conf
server {
    location /api {
        proxy_pass http://backend:8000;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
    }
}

3. Large Repository Handling

Scenario: Application crashes when analyzing large repositories

Symptoms

Error: JavaScript heap out of memory
FATAL ERROR: Reached heap limit Allocation failed

Debugging Steps

1. Monitor memory usage

   # Check current memory usage
   docker stats
   
   # Monitor Node.js memory
   node --max-old-space-size=4096 server.js
   

2. Profile repository size

   # Check repository size
   du -sh /path/to/repo
   
   # Count files
   find /path/to/repo -type f | wc -l
   

Solutions

// Solution 1: Implement streaming file processing
const processLargeRepo = async (repoPath) => {
  const stream = fs.createReadStream(repoPath);
  const chunks = [];
  
  for await (const chunk of stream) {
    // Process in chunks
    await processChunk(chunk);
    
    // Clear memory periodically
    if (chunks.length > 1000) {
      await flushToDatabase(chunks);
      chunks.length = 0;
    }
  }
};

// Solution 2: Use worker threads
const { Worker } = require('worker_threads');

const analyzeInWorker = (filePath) => {
  return new Promise((resolve, reject) => {
    const worker = new Worker('./analyzer.js', {
      workerData: { filePath }
    });
    
    worker.on('message', resolve);
    worker.on('error', reject);
  });
};

// Solution 3: Docker memory limits
// docker-compose.yml
services:
  app:
    mem_limit: 4g
    memswap_limit: 4g

4. Memory and Performance Issues

Scenario: Slow response times and high memory usage

Debugging Steps

1. Profile application performance

   # Node.js profiling
   node --inspect server.js
   
   # Python profiling
   python -m cProfile -o profile.stats app.py
   

2. Monitor resource usage

   # Real-time monitoring
   htop
   iotop
   
   # Docker resource usage
   docker stats --format "table {{.Container}}\t{{.CPUPerc}}\t{{.MemUsage}}"
   

Solutions

# Solution 1: Implement caching
from functools import lru_cache
import redis

cache = redis.Redis(host='localhost', port=6379)

@lru_cache(maxsize=1000)
def expensive_operation(repo_path):
    # Check cache first
    cached = cache.get(f"analysis:{repo_path}")
    if cached:
        return json.loads(cached)
    
    result = perform_analysis(repo_path)
    cache.set(f"analysis:{repo_path}", json.dumps(result), ex=3600)
    return result

# Solution 2: Batch processing
async def batch_analyze(files, batch_size=100):
    for i in range(0, len(files), batch_size):
        batch = files[i:i + batch_size]
        await asyncio.gather(*[analyze_file(f) for f in batch])
        
        # Allow garbage collection
        gc.collect()

5. Docker Container Problems

Scenario: Container fails to start or crashes immediately

Symptoms

docker: Error response from daemon: OCI runtime create failed
Container exited with code 137 (Out of Memory)

Debugging Steps

1. Check container logs

   docker logs deepwikiopen-app
   docker logs --tail 50 -f deepwikiopen-app
   

2. Inspect container

   docker inspect deepwikiopen-app
   docker exec -it deepwikiopen-app /bin/sh
   

Solutions

# Solution 1: Rebuild with proper base image
FROM node:18-alpine AS build
WORKDIR /app
COPY package*.json ./
RUN npm ci --only=production

# Solution 2: Fix permission issues
RUN addgroup -g 1001 -S nodejs
RUN adduser -S nodejs -u 1001
USER nodejs

# Solution 3: Health check
HEALTHCHECK --interval=30s --timeout=3s --start-period=40s \
  CMD node healthcheck.js || exit 1

6. Model Selection Errors

Scenario: “Model not found” or incorrect model responses

Symptoms

Error: Model 'claude-3-opus' not found
Available models: ['claude-3-5-sonnet-20241022', 'claude-3-5-haiku-20241022']

Debugging Steps

1. List available models

   import anthropic
   
   client = anthropic.Anthropic()
   # Check model availability based on your API tier
   

2. Verify model configuration

   // config/models.js
   export const AVAILABLE_MODELS = {
     'claude-3-5-sonnet-20241022': {
       maxTokens: 8192,
       contextWindow: 200000
     },
     'claude-3-5-haiku-20241022': {
       maxTokens: 8192,
       contextWindow: 200000
     }
   };
   

Solutions

// Solution 1: Implement model fallback
const getModel = (preferred) => {
  const fallbackChain = [
    'claude-3-5-sonnet-20241022',
    'claude-3-5-haiku-20241022',
    'claude-3-haiku-20240307'
  ];
  
  if (AVAILABLE_MODELS[preferred]) {
    return preferred;
  }
  
  return fallbackChain.find(model => AVAILABLE_MODELS[model]);
};

// Solution 2: Dynamic model selection
const selectOptimalModel = (contextLength, speed = 'balanced') => {
  if (speed === 'fast' || contextLength < 10000) {
    return 'claude-3-5-haiku-20241022';
  }
  return 'claude-3-5-sonnet-20241022';
};

7. Private Repository Access Issues

Scenario: Cannot access private GitHub repositories

Symptoms

Error: Repository not found or you don't have access
Status: 404

Debugging Steps

1. Verify GitHub token

   # Test token permissions
   curl -H "Authorization: token $GITHUB_TOKEN" \
     https://api.github.com/user/repos
   

2. Check token scopes

   curl -H "Authorization: token $GITHUB_TOKEN" \
     -I https://api.github.com/user
   # Look for X-OAuth-Scopes header
   

Solutions

# Solution 1: Create token with correct scopes
# Go to GitHub Settings → Developer settings → Personal access tokens
# Required scopes: repo, read:org (for private repos)

# Solution 2: Use GitHub App authentication
# github-app-auth.js
const { createAppAuth } = require("@octokit/auth-app");

const auth = createAppAuth({
  appId: process.env.GITHUB_APP_ID,
  privateKey: process.env.GITHUB_PRIVATE_KEY,
  installationId: process.env.GITHUB_INSTALLATION_ID,
});

# Solution 3: SSH key authentication for cloning
ssh-keygen -t ed25519 -C "[e-mail]"
# Add to GitHub account settings

8. WebSocket Connection Failures

Scenario: Real-time updates not working, WebSocket disconnects

Symptoms

WebSocket connection to 'ws://localhost:8000/ws' failed
Error: Connection closed before established

Debugging Steps

1. Test WebSocket endpoint

   // Test WebSocket connection
   const ws = new WebSocket('ws://localhost:8000/ws');
   ws.onopen = () => console.log('Connected');
   ws.onerror = (error) => console.error('Error:', error);
   ws.onclose = (event) => console.log('Closed:', event.code, event.reason);
   

2. Check server WebSocket implementation

   # Ensure WebSocket endpoint exists
   @app.websocket("/ws")
   async def websocket_endpoint(websocket: WebSocket):
       await websocket.accept()
       # Handle connection
   

Solutions

// Solution 1: Implement reconnection logic
class ReconnectingWebSocket {
  constructor(url, options = {}) {
    this.url = url;
    this.reconnectInterval = options.reconnectInterval || 1000;
    this.maxReconnectInterval = options.maxReconnectInterval || 30000;
    this.reconnectDecay = options.reconnectDecay || 1.5;
    this.reconnectAttempts = 0;
    this.connect();
  }
  
  connect() {
    this.ws = new WebSocket(this.url);
    
    this.ws.onclose = () => {
      this.reconnect();
    };
    
    this.ws.onerror = (error) => {
      console.error('WebSocket error:', error);
      this.ws.close();
    };
  }
  
  reconnect() {
    this.reconnectAttempts++;
    const timeout = Math.min(
      this.reconnectInterval * Math.pow(this.reconnectDecay, this.reconnectAttempts),
      this.maxReconnectInterval
    );
    
    setTimeout(() => this.connect(), timeout);
  }
}

// Solution 2: Use Socket.IO for better reliability
const io = require('socket.io')(server, {
  cors: {
    origin: "http://localhost:3000",
    methods: ["GET", "POST"]
  },
  reconnection: true,
  reconnectionAttempts: 5,
  reconnectionDelay: 1000,
});

9. Rate Limiting Scenarios

Scenario: API rate limit exceeded errors

Symptoms

Error: Rate limit exceeded. Please retry after 30 seconds.
Status: 429 Too Many Requests

Debugging Steps

1. Monitor rate limit headers
   // Check response headers
   response.headers.get('X-RateLimit-Limit')
   response.headers.get('X-RateLimit-Remaining')
   response.headers.get('X-RateLimit-Reset')
   

Solutions

// Solution 1: Implement rate limit handling
class RateLimiter {
  constructor(maxRequests = 50, windowMs = 60000) {
    this.maxRequests = maxRequests;
    this.windowMs = windowMs;
    this.requests = [];
  }
  
  async acquire() {
    const now = Date.now();
    this.requests = this.requests.filter(time => now - time < this.windowMs);
    
    if (this.requests.length >= this.maxRequests) {
      const oldestRequest = this.requests[0];
      const waitTime = this.windowMs - (now - oldestRequest);
      await new Promise(resolve => setTimeout(resolve, waitTime));
      return this.acquire();
    }
    
    this.requests.push(now);
  }
}

// Solution 2: Implement exponential backoff
async function makeRequestWithRetry(fn, maxRetries = 3) {
  for (let i = 0; i < maxRetries; i++) {
    try {
      return await fn();
    } catch (error) {
      if (error.status === 429 && i < maxRetries - 1) {
        const delay = Math.pow(2, i) * 1000;
        await new Promise(resolve => setTimeout(resolve, delay));
        continue;
      }
      throw error;
    }
  }
}

// Solution 3: Queue requests
const pQueue = require('p-queue').default;
const queue = new pQueue({ 
  concurrency: 2, 
  interval: 1000, 
  intervalCap: 10 
});

10. Common Error Messages and Solutions

Error: “Context length exceeded”

Solution

// Implement context window management
const truncateContext = (messages, maxTokens = 150000) => {
  let totalTokens = 0;
  const truncated = [];
  
  for (let i = messages.length - 1; i >= 0; i--) {
    const tokens = estimateTokens(messages[i].content);
    if (totalTokens + tokens > maxTokens) break;
    totalTokens += tokens;
    truncated.unshift(messages[i]);
  }
  
  return truncated;
};

Error: “WebContainer initialization failed”

Solution

// Ensure proper WebContainer setup
import { WebContainer } from '@webcontainer/api';

let webcontainerInstance;

async function initWebContainer() {
  try {
    webcontainerInstance = await WebContainer.boot();
    console.log('WebContainer initialized');
  } catch (error) {
    console.error('Failed to initialize WebContainer:', error);
    // Fallback to server-side execution
    return initServerSideContainer();
  }
}

Error: “Database connection timeout”

Solution

# Implement connection pooling and retry logic
from sqlalchemy import create_engine
from sqlalchemy.pool import QueuePool
import time

def create_db_engine(retry_count=3, retry_delay=5):
    for attempt in range(retry_count):
        try:
            engine = create_engine(
                DATABASE_URL,
                poolclass=QueuePool,
                pool_size=10,
                max_overflow=20,
                pool_timeout=30,
                pool_recycle=3600
            )
            # Test connection
            with engine.connect() as conn:
                conn.execute("SELECT 1")
            return engine
        except Exception as e:
            if attempt < retry_count - 1:
                time.sleep(retry_delay)
                continue
            raise e

Best Practices for Troubleshooting

1. Enable verbose logging

   export DEBUG=deepwikiopen:*
   export LOG_LEVEL=debug
   

2. Use health check endpoints

   curl http://localhost:8000/health
   curl http://localhost:8000/api/status
   

3. Monitor system resources

   # Create monitoring script
   #!/bin/bash
   while true; do
     echo "=== $(date) ==="
     docker stats --no-stream
     sleep 5
   done
   

4. Implement comprehensive error handling

   app.use((err, req, res, next) => {
     console.error('Error details:', {
       message: err.message,
       stack: err.stack,
       timestamp: new Date().toISOString(),
       request: {
         method: req.method,
         url: req.url,
         headers: req.headers
       }
     });
     
     res.status(err.status || 500).json({
       error: err.message,
       timestamp: new Date().toISOString(),
       requestId: req.id
     });
   });
   

Getting Help

If you encounter issues not covered here:

1. Check the GitHub Issues
2. Enable debug logging and collect logs
3. Provide system information:
   node --version
   npm --version
   docker --version
   uname -a
   
4. Include minimal reproduction steps
5. Join our Discord community for real-time support