// Streaming delivers the first token ASAP — user sees response instantly
// instead of waiting for the full response to generate

const stream = client.messages.stream({
  model: 'claude-sonnet-4-20250514',
  max_tokens: 1024,
  messages,
});

// First token arrives in ~400ms (Sonnet)
// Full response may take 5-10s, but user sees progress immediately
for await (const event of stream) {
  if (event.type === 'content_block_delta') {
    yield event.delta.text;
  }
}

// Cached prompts skip re-processing — dramatically lower TTFT for large system prompts
const message = await client.messages.create({
  model: 'claude-sonnet-4-20250514',
  max_tokens: 1024,
  system: [{
    type: 'text',
    text: largeSystemPrompt, // 10K+ tokens
    cache_control: { type: 'ephemeral' },
  }],
  messages,
}, {
  headers: { 'claude-beta': 'prompt-caching-2024-07-31' },
});
// TTFT drops from ~2s to ~500ms on cache hit with large prompts

// Haiku is 2-4x faster than Sonnet with 80% quality for many tasks
// Use for: classification, extraction, simple Q&A, routing decisions

const route = await client.messages.create({
  model: 'claude-haiku-4-5-20251001', // 200ms TTFT
  max_tokens: 10,
  system: 'Classify the intent. Reply with exactly one word: search, create, update, delete.',
  messages: [{ role: 'user', content: userInput }],
});

// Then use Sonnet/Opus for the actual task

// BAD — creates new connection pool per request
app.get('/api/chat', async (req, res) => {
  const client = new Anthropic(); // DON'T
  // ...
});

// GOOD — single client shared across requests
const client = new Anthropic(); // Module-level singleton

app.get('/api/chat', async (req, res) => {
  const message = await client.messages.create({ ... });
  // ...
});

// When you need multiple independent Claude calls, fire them in parallel
const [summary, sentiment, entities] = await Promise.all([
  client.messages.create({ model: 'claude-haiku-4-5-20251001', max_tokens: 200,
    messages: [{ role: 'user', content: `Summarize: ${text}` }] }),
  client.messages.create({ model: 'claude-haiku-4-5-20251001', max_tokens: 20,
    messages: [{ role: 'user', content: `Sentiment (positive/negative/neutral): ${text}` }] }),
  client.messages.create({ model: 'claude-haiku-4-5-20251001', max_tokens: 200,
    messages: [{ role: 'user', content: `Extract named entities from: ${text}` }] }),
]);

// Fewer output tokens = faster response
system: 'Be extremely concise. Use bullet points, not paragraphs.',

// Set tight max_tokens
max_tokens: 256, // Don't use 4096 for short answers