내장 AI API: 권장사항과 주의사항

// ✅ DO: Create the session as early as possible (tip on warming up the model early) and use initialPrompts for system instructions in the create call
const session = await LanguageModel.create({
  initialPrompts: [
    { role: 'system', content: 'You are a helpful assistant specialized in code reviews.' }
  ]
});

// A few moments later, when the user triggers the AI feature
const review = await session.prompt(`Review the following code:\n\n${code}`);

// ❌ DON'T: Send instructions using prompt() after creation
// const slowerSession = await LanguageModel.create();
// await slowerSession.prompt(`You are a helpful assistant specialized in code reviews.\n\nReview the following code:\n\n${code}`); // Higher latency

// ✅ DO: Create a baseline session and clone it for each new task
const baseSession = await LanguageModel.create({
  initialPrompts: [{
    role: 'system',
    content: 'You are a technical editor...',
  }],
});

// Clone the base session once for the first task
const task1 = await baseSession.clone();
const response1 = await task1.prompt("Review this first draft...");
// ... Repeat the cloning pattern for subsequent independent tasks
// Each task starts fresh from the baseline system instructions

// ❌ DON'T:
// Bad performance pattern: repeated create() calls for identical tasks.
// This forces the model to re-parse instructions every time, increasing latency.
// const sessionA = await LanguageModel.create({ initialPrompts: [...] });
// await sessionA.prompt("Task 1...");
// const sessionB = await LanguageModel.create({ initialPrompts: [...] });
// await sessionB.prompt("Task 2...");
// Bad quality pattern: reusing the same session for unrelated tasks.
// const session = await LanguageModel.create();
// await session.prompt("Analyze this financial report...");
// Unrelated task in the same session:
// await session.prompt("Now write a children's story...");

// ✅ DO: Use the clone and destroy it immediately after
const clone = await baseSession.clone();
const response = await clone.prompt("Quick task...");
// Free memory right away: destry the clone, keep the baseSession
clone.destroy();

import * as smd from "streaming-markdown";
// Set up virtual buffer and Sanitizer API
const sanitizer = new Sanitizer({
  allowElements: ['figure', 'figcaption', 'p', 'br', 'strong', 'em', 'img', 'a'],
  allowAttributes: {
    'loading': ['img'], 'decoding': ['img'], 'src': ['img'], 'href': ['a']
  }
});

// Create an off-screen fragment so the parser doesn't cause flicker
// or trigger XSS in the live DOM during the building process.
const buffer = new DocumentFragment();
const parser = smd.parser_new(buffer);

// Use sanitizer as a gatekeeper / cleaner function so we can combine it with the streaming Markdown parser
function syncSanitized(target, sourceFragment) {
  // .sanitize() returns a fresh, clean DocumentFragment
  const cleanFragment = sanitizer.sanitize(sourceFragment);
  // replaceChildren is the modern high-performance way to swap DOM content
  target.replaceChildren(cleanFragment);
}

// Streaming Logic
// `chunks` keeps track of the raw string (useful for logs/debug)
chunks += chunk;
// Let the parser build the DOM incrementally in the buffer.
// This is high-performance because the buffer is not live
smd.parser_write(parser, chunk);
// Use the Sanitizer API to port the content safely to the container.
syncSanitized(container, buffer);

// ✅ DO: Send only relevant text
const cleanText = document.querySelector('#article').innerText;
const summary = await Summarizer.summarize(cleanText);

// ❌ DON'T: Send the entire DOM structure
// const dirtyText = document.querySelector('#article').innerHTML;

// ✅ DO: Use a JSON Schema for predictable results
const schema = {
  type: "object",
  properties: {
    isTopicCats: { type: "boolean" }
  }
};

const result = await session.prompt(`Is this post about cats?\n\n${post}`, {
  responseConstraint: schema,
});
console.log(JSON.parse(result).isTopicCats);

/*  DO: Handle overflow using CSS */
.result {
  overflow: hidden;
  white-space: nowrap;
  text-overflow: ellipsis; /* Displays '…' */
}

// ❌ DON'T: Force length in the prompt
const result = await session.prompt("Write a bio in exactly 50 characters.");

// ✅ DO: Check a local cache before running inference
async function getAiResponse(userInput, forceRefresh = false) {
  // Normalize the query to increase cache hits
  const query = userInput.trim().toLowerCase();
  const cacheKey = `ai_results_${query}`;
  const TTL_MS = 3600000; // 1 hour conservative TTL

  if (!forceRefresh) {
    const itemStr = localStorage.getItem(cacheKey);
    if (itemStr) {
      const item = JSON.parse(itemStr);
      const now = Date.now();

      // Check if the item has expired
      if (now < item.expiry) {
        // Lightweight safety check before rendering
        if (isValid(item.value)) return item.value;
      } else {
        // Delete the stale entry if the TTL has passed
        localStorage.removeItem(cacheKey);
      }
    }
  }

  // Fallback: Run inference if no valid cache exists
  const session = await LanguageModel.create();
  const response = await session.prompt(userInput);

  // Store the result for future use (with an expiration)
  const cacheData = {
    value: response,
    expiry: Date.now() + TTL_MS
  };
  localStorage.setItem(cacheKey, JSON.stringify(cacheData));

  return response;
}