LLM Streaming Response Handler

// ✅ Cleanup with useEffect
useEffect(() => {
  let reader: ReadableStreamDefaultReader | null = null;

  const streamResponse = async () => {
    const response = await fetch('/api/chat', { ... });
    reader = response.body.getReader();

    // Streaming...
  };

  streamResponse();

  // Cleanup on unmount
  return () => {
    reader?.cancel();
  };
}, [prompt]);

// ✅ Animated cursor during generation
<div className="message">
  {content}
  {isStreaming && <span className="typing-cursor">▊</span>}
</div>

.typing-cursor {
  animation: blink 1s step-end infinite;
}

@keyframes blink {
  50% { opacity: 0; }
}

async function* streamCompletion(prompt: string) {
  const response = await fetch('/api/chat', {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({ prompt })
  });

  const reader = response.body!.getReader();
  const decoder = new TextDecoder();

  while (true) {
    const { done, value } = await reader.read();
    if (done) break;

    const chunk = decoder.decode(value);
    const lines = chunk.split('\n');

    for (const line of lines) {
      if (line.startsWith('data: ')) {
        const data = JSON.parse(line.slice(6));

        if (data.content) {
          yield data.content;
        }

        if (data.done) {
          return;
        }
      }
    }
  }
}

// Usage
for await (const token of streamCompletion('Hello')) {
  console.log(token);
}

import { useState, useCallback } from 'react';

interface UseStreamingOptions {
  onToken?: (token: string) => void;
  onComplete?: (fullText: string) => void;
  onError?: (error: Error) => void;
}

export function useStreaming(options: UseStreamingOptions = {}) {
  const [content, setContent] = useState('');
  const [isStreaming, setIsStreaming] = useState(false);
  const [error, setError] = useState<Error | null>(null);
  const [abortController, setAbortController] = useState<AbortController | null>(null);

  const stream = useCallback(async (prompt: string) => {
    const controller = new AbortController();
    setAbortController(controller);
    setIsStreaming(true);
    setError(null);
    setContent('');

    try {
      const response = await fetch('/api/chat', {
        method: 'POST',
        signal: controller.signal,
        headers: { 'Content-Type': 'application/json' },
        body: JSON.stringify({ prompt })
      });

      const reader = response.body!.getReader();
      const decoder = new TextDecoder();

      let accumulated = '';

      while (true) {
        const { done, value } = await reader.read();
        if (done) break;

        const chunk = decoder.decode(value);
        const lines = chunk.split('\n').filter(line => line.trim());

        for (const line of lines) {
          if (line.startsWith('data: ')) {
            const data = JSON.parse(line.slice(6));

            if (data.content) {
              accumulated += data.content;
              setContent(accumulated);
              options.onToken?.(data.content);
            }
          }
        }
      }

      options.onComplete?.(accumulated);
    } catch (err) {
      if (err.name !== 'AbortError') {
        setError(err as Error);
        options.onError?.(err as Error);
      }
    } finally {
      setIsStreaming(false);
      setAbortController(null);
    }
  }, [options]);

  const cancel = useCallback(() => {
    abortController?.abort();
  }, [abortController]);

  return { content, isStreaming, error, stream, cancel };
}

// Usage in component
function ChatInterface() {
  const { content, isStreaming, stream, cancel } = useStreaming({
    onToken: (token) => console.log('New token:', token),
    onComplete: (text) => console.log('Done:', text)
  });

  return (
    <div>
      <div className="message">
        {content}
        {isStreaming && <span className="cursor">▊</span>}
      </div>

      <button onClick={() => stream('Tell me a story')} disabled={isStreaming}>
        Generate
      </button>

      {isStreaming && <button onClick={cancel}>Stop</button>}
    </div>
  );
}

// app/api/chat/route.ts
import { OpenAI } from 'openai';

export const runtime = 'edge'; // Required for streaming

export async function POST(req: Request) {
  const { prompt } = await req.json();

  const openai = new OpenAI({
    apiKey: process.env.OPENAI_API_KEY
  });

  const stream = await openai.chat.completions.create({
    model: 'gpt-4',
    messages: [{ role: 'user', content: prompt }],
    stream: true
  });

  // Convert OpenAI stream to SSE format
  const encoder = new TextEncoder();

  const readable = new ReadableStream({
    async start(controller) {
      try {
        for await (const chunk of stream) {
          const content = chunk.choices[0]?.delta?.content;

          if (content) {
            const sseMessage = `data: ${JSON.stringify({ content })}\n\n`;
            controller.enqueue(encoder.encode(sseMessage));
          }
        }

        // Send completion signal
        controller.enqueue(encoder.encode('data: {"done":true}\n\n'));
        controller.close();
      } catch (error) {
        controller.error(error);
      }
    }
  });

  return new Response(readable, {
    headers: {
      'Content-Type': 'text/event-stream',
      'Cache-Control': 'no-cache',
      'Connection': 'keep-alive'
    }
  });
}

□ AbortController for cancellation
□ Error states with retry capability
□ Typing indicator during generation
□ Cleanup on component unmount
□ Rate limiting on API route
□ Token usage tracking
□ Streaming fallback (if API fails)
□ Accessibility (screen reader announces updates)
□ Mobile-friendly (touch targets for stop button)
□ Network error recovery (auto-retry on disconnect)
□ Max response length enforcement
□ Cost estimation before generation