import { parseGGUFMetadata } from '@localmode/wllama';

const metadata = await parseGGUFMetadata(
  'bartowski/Llama-3.2-1B-Instruct-GGUF:Llama-3.2-1B-Instruct-Q4_K_M.gguf'
);

console.log(metadata.architecture);   // 'llama'
console.log(metadata.contextLength);  // 131072
console.log(metadata.quantization);   // 'Q4_K_M'
console.log(metadata.parameterCount); // ~1.24 billion
console.log(metadata.vocabSize);      // 32000
console.log(metadata.layerCount);     // 22
console.log(metadata.headCount);      // 32
console.log(metadata.modelName);      // 'Llama 3.2 1B Instruct'

// HuggingFace shorthand (repo:filename)
await parseGGUFMetadata('bartowski/Llama-3.2-1B-Instruct-GGUF:Llama-3.2-1B-Instruct-Q4_K_M.gguf');

// Full HuggingFace URL
await parseGGUFMetadata('https://huggingface.co/bartowski/Llama-3.2-1B-Instruct-GGUF/resolve/main/Llama-3.2-1B-Instruct-Q4_K_M.gguf');

// Any CDN that supports Range requests
await parseGGUFMetadata('https://your-cdn.com/models/custom-model.gguf');

import { checkGGUFBrowserCompatFromURL } from '@localmode/wllama';

const result = await checkGGUFBrowserCompatFromURL(
  'bartowski/Llama-3.2-1B-Instruct-GGUF:Llama-3.2-1B-Instruct-Q4_K_M.gguf'
);

console.log(result.canRun);             // true
console.log(result.estimatedRAMHuman);   // '900 MB'
console.log(result.deviceRAMHuman);      // '8 GB'
console.log(result.estimatedSpeed);      // '~30-50 tok/s multi-thread'
console.log(result.hasCORS);             // true (multi-threading available)
console.log(result.warnings);            // []
console.log(result.recommendations);     // []

// Full metadata is also attached
console.log(result.metadata.architecture); // 'llama'

import { parseGGUFMetadata, checkGGUFBrowserCompat } from '@localmode/wllama';

// Step 1: Parse metadata (light HTTP Range request)
const metadata = await parseGGUFMetadata(modelUrl);

// Step 2: Check compatibility (no network, instant)
const compat = await checkGGUFBrowserCompat(metadata);

import {
  parseGGUFMetadata,
  checkGGUFBrowserCompat,
  wllama,
} from '@localmode/wllama';
import { streamText } from '@localmode/core';

// 1. User selects a model from HuggingFace
const modelUrl = 'bartowski/Llama-3.2-1B-Instruct-GGUF:Llama-3.2-1B-Instruct-Q4_K_M.gguf';

// 2. Inspect metadata (~4KB download)
const metadata = await parseGGUFMetadata(modelUrl);
showModelInfo(metadata); // Display to user

// 3. Check compatibility (instant, no download)
const compat = await checkGGUFBrowserCompat(metadata);

if (!compat.canRun) {
  showWarnings(compat.warnings);
  showRecommendations(compat.recommendations);
  return;
}

// 4. Download and run
const model = wllama.languageModel(modelUrl, {
  onProgress: (p) => updateProgressBar(p.progress ?? 0),
});

const result = await streamText({ model, prompt: 'Hello!' });

import { WLLAMA_MODELS } from '@localmode/wllama';

for (const [id, info] of Object.entries(WLLAMA_MODELS)) {
  console.log(`${info.name}: ${info.size}, ${info.quantization}, ${info.description}`);
}

import { searchGGUFModels, listGGUFFiles, HFApiError } from '@localmode/wllama';

const controller = new AbortController();

try {
  // Search by relevance; an EMPTY query browses the top models for the sort
  // (the 160K+ catalog browse entry point).
  const { results, nextCursor } = await searchGGUFModels({
    query: 'llama 1b',
    sort: 'downloads', // 'downloads' | 'likes' | 'lastModified' (always descending)
    abortSignal: controller.signal,
  });

  // Pick a repo and list its .gguf files
  const repo = results[0];
  const files = await listGGUFFiles(repo.repoId, { abortSignal: controller.signal });

  for (const file of files) {
    console.log(file.filename, file.quantLabel, file.sizeBytes);
    // → 'Llama-3.2-1B-Instruct-Q4_K_M.gguf'  'Q4_K_M'  807694464
  }

  // Pagination: pass nextCursor back as `cursor` for the next page.
  if (nextCursor) {
    const page2 = await searchGGUFModels({ query: 'llama 1b', sort: 'downloads', cursor: nextCursor });
    // nextCursor === null means the last page.
  }
} catch (err) {
  if (err instanceof HFApiError) {
    switch (err.kind) {
      case 'rate-limit': // HTTP 429 — wait and retry
        break;
      case 'not-found': // HTTP 404/401/403 — unknown or private repo
        break;
      case 'network': // fetch failure, non-OK status, or malformed response
        break;
    }
  }
  // Abort rejections propagate untouched (the original AbortError, never wrapped),
  // so a cancelled search is distinguishable from a real failure.
}