@apmantza/greedysearch-pi 1.0.0

package/extractors/bing-copilot.mjs

@@ -0,0 +1,169 @@
+#!/usr/bin/env node
+// extractors/bing-copilot.mjs
+// Navigate copilot.microsoft.com, wait for answer to complete, return clean answer + sources.
+//
+// Usage:
+//   node extractors/bing-copilot.mjs "<query>" [--tab <prefix>]
+//
+// Output (stdout): JSON { answer, sources, query, url }
+// Errors go to stderr only — stdout is always clean JSON for piping.
+
+import { readFileSync, existsSync } from 'fs';
+import { spawn } from 'child_process';
+import { tmpdir, homedir } from 'os';
+import { join, dirname } from 'path';
+import { fileURLToPath } from 'url';
+import { dismissConsent } from './consent.mjs';
+
+const CDP = join(dirname(fileURLToPath(import.meta.url)), '..', 'cdp.mjs');
+const PAGES_CACHE = `${tmpdir().replace(/\\/g, '/')}/cdp-pages.json`;
+
+const STREAM_POLL_INTERVAL = 700;  // ms between checks
+const STREAM_STABLE_ROUNDS = 3;    // consecutive equal-length polls = done
+const STREAM_TIMEOUT = 60000;      // bail out after 60s
+const MIN_ANSWER_LENGTH = 50;      // don't accept trivial answers
+
+// ---------------------------------------------------------------------------
+
+function cdp(args, timeoutMs = 30000) {
+  return new Promise((resolve, reject) => {
+    const proc = spawn('node', [CDP, ...args], { stdio: ['ignore', 'pipe', 'pipe'] });
+    let out = '';
+    let err = '';
+    proc.stdout.on('data', d => out += d);
+    proc.stderr.on('data', d => err += d);
+    const timer = setTimeout(() => { proc.kill(); reject(new Error(`cdp timeout: ${args[0]}`)); }, timeoutMs);
+    proc.on('close', code => {
+      clearTimeout(timer);
+      if (code !== 0) reject(new Error(err.trim() || `cdp exit ${code}`));
+      else resolve(out.trim());
+    });
+  });
+}
+
+async function getOrOpenTab(tabPrefix) {
+  if (tabPrefix) return tabPrefix;
+
+  if (existsSync(PAGES_CACHE)) {
+    const pages = JSON.parse(readFileSync(PAGES_CACHE, 'utf8'));
+    const existing = pages.find(p => p.url.includes('copilot.microsoft.com'));
+    if (existing) return existing.targetId.slice(0, 8);
+  }
+
+  const list = await cdp(['list']);
+  const firstLine = list.split('\n')[0];
+  if (!firstLine) throw new Error('No Chrome tabs found. Is Chrome running with --remote-debugging-port=9222?');
+  return firstLine.slice(0, 8);
+}
+
+async function waitForStreamComplete(tab) {
+  const deadline = Date.now() + STREAM_TIMEOUT;
+  let stableCount = 0;
+  let lastLen = -1;
+
+  while (Date.now() < deadline) {
+    await new Promise(r => setTimeout(r, STREAM_POLL_INTERVAL));
+
+    // Poll the last non-empty ai-message-item (item[1] is always an empty placeholder)
+    const lenStr = await cdp(['eval', tab,
+      `(function(){
+        var items = Array.from(document.querySelectorAll('[class*="ai-message-item"]'));
+        var filled = items.filter(el => (el.innerText?.length || 0) > 0);
+        var last = filled[filled.length - 1];
+        return (last?.innerText?.length || 0) + '';
+      })()`
+    ]).catch(() => '0');
+
+    const len = parseInt(lenStr) || 0;
+
+    if (len >= MIN_ANSWER_LENGTH && len === lastLen) {
+      stableCount++;
+      if (stableCount >= STREAM_STABLE_ROUNDS) return len;
+    } else {
+      stableCount = 0;
+      lastLen = len;
+    }
+  }
+
+  if (lastLen >= MIN_ANSWER_LENGTH) return lastLen;
+  throw new Error(`Copilot answer did not stabilise within ${STREAM_TIMEOUT}ms`);
+}
+
+async function extractAnswer(tab) {
+  const raw = await cdp(['eval', tab, `
+    (function() {
+      var items = Array.from(document.querySelectorAll('[class*="ai-message-item"]'));
+      var el = items.filter(e => (e.innerText?.length || 0) > 0).pop();
+      if (!el) return JSON.stringify({ answer: '', sources: [] });
+      var answer = el.innerText.trim();
+      var sources = Array.from(document.querySelectorAll('a[href^="http"][target="_blank"]'))
+        .map(a => ({ url: a.href, title: a.innerText?.trim().split('\\n')[0] || a.title || '' }))
+        .filter(s => s.url && !s.url.includes('copilot.microsoft.com'))
+        .filter((v, i, arr) => arr.findIndex(x => x.url === v.url) === i)
+        .slice(0, 10);
+      return JSON.stringify({ answer, sources });
+    })()
+  `]);
+  return JSON.parse(raw);
+}
+
+// ---------------------------------------------------------------------------
+
+async function main() {
+  const args = process.argv.slice(2);
+  if (!args.length || args[0] === '--help') {
+    process.stderr.write('Usage: node extractors/bing-copilot.mjs "<query>" [--tab <prefix>]\n');
+    process.exit(1);
+  }
+
+  const short = args.includes('--short');
+  const rest  = args.filter(a => a !== '--short');
+  const tabFlagIdx = rest.indexOf('--tab');
+  const tabPrefix = tabFlagIdx !== -1 ? rest[tabFlagIdx + 1] : null;
+  const query = tabFlagIdx !== -1
+    ? rest.filter((_, i) => i !== tabFlagIdx && i !== tabFlagIdx + 1).join(' ')
+    : rest.join(' ');
+
+  try {
+    await cdp(['list']);
+    const tab = await getOrOpenTab(tabPrefix);
+
+    // Navigate to Copilot homepage and use the chat input
+    await cdp(['nav', tab, 'https://copilot.microsoft.com/'], 35000);
+    await dismissConsent(tab, cdp);
+
+    // Wait for React app to mount #userInput (up to 8s)
+    const deadline = Date.now() + 8000;
+    while (Date.now() < deadline) {
+      const found = await cdp(['eval', tab, `!!document.querySelector('#userInput')`]).catch(() => 'false');
+      if (found === 'true') break;
+      await new Promise(r => setTimeout(r, 400));
+    }
+    await new Promise(r => setTimeout(r, 300));
+
+    // Find input and type query
+    await cdp(['click', tab, '#userInput']);
+    await new Promise(r => setTimeout(r, 400));
+    await cdp(['type', tab, query]);
+    await new Promise(r => setTimeout(r, 400));
+
+    // Submit with Enter (most reliable across locales and Chrome instances)
+    await cdp(['eval', tab,
+      `document.querySelector('#userInput')?.dispatchEvent(new KeyboardEvent('keydown',{key:'Enter',bubbles:true,keyCode:13})), 'ok'`
+    ]);
+
+    await waitForStreamComplete(tab);
+
+    const { answer, sources } = await extractAnswer(tab);
+    if (!answer) throw new Error('No answer extracted — Copilot may not have responded');
+    const out = short ? answer.slice(0, 300).replace(/\s+\S*$/, '') + '…' : answer;
+
+    const finalUrl = await cdp(['eval', tab, 'document.location.href']).catch(() => '');
+    process.stdout.write(JSON.stringify({ query, url: finalUrl, answer: out, sources }, null, 2) + '\n');
+  } catch (e) {
+    process.stderr.write(`Error: ${e.message}\n`);
+    process.exit(1);
+  }
+}
+
+main();

package/extractors/consent.mjs

@@ -0,0 +1,29 @@
+// consent.mjs — auto-dismiss common cookie/consent banners
+// Call dismissConsent(tab, cdpFn) after navigating to any page.
+
+const CONSENT_JS = `
+(function() {
+  // Google consent page (consent.google.com)
+  var g = document.querySelector('#L2AGLb, button[jsname="b3VHJd"], .tHlp8d');
+  if (g) { g.click(); return 'google'; }
+
+  // OneTrust (used by many sites including Stack Overflow)
+  var ot = document.querySelector('#onetrust-accept-btn-handler, .onetrust-accept-btn-handler');
+  if (ot) { ot.click(); return 'onetrust'; }
+
+  // Generic "accept all" / "agree" buttons
+  var btns = Array.from(document.querySelectorAll('button, a[role=button]'));
+  var accept = btns.find(b => /^(accept all|accept cookies|agree|i agree|got it|allow all|allow cookies)$/i.test(b.innerText?.trim()));
+  if (accept) { accept.click(); return 'generic:' + accept.innerText.trim(); }
+
+  return null;
+})()
+`;
+
+export async function dismissConsent(tab, cdp) {
+  const result = await cdp(['eval', tab, CONSENT_JS]).catch(() => null);
+  if (result && result !== 'null') {
+    // Give page a moment to react after dismissal
+    await new Promise(r => setTimeout(r, 1500));
+  }
+}

package/extractors/google-ai.mjs

@@ -0,0 +1,152 @@
+#!/usr/bin/env node
+// extractors/google-ai.mjs
+// Navigate Google AI Mode (udm=50), wait for answer, return clean answer + sources.
+//
+// Usage:
+//   node extractors/google-ai.mjs "<query>" [--tab <prefix>]
+//
+// Output (stdout): JSON { answer, sources, query, url }
+// Errors go to stderr only — stdout is always clean JSON for piping.
+
+import { readFileSync, existsSync } from 'fs';
+import { spawn } from 'child_process';
+import { tmpdir, homedir } from 'os';
+import { join, dirname } from 'path';
+import { fileURLToPath } from 'url';
+import { dismissConsent } from './consent.mjs';
+const __dir = dirname(fileURLToPath(import.meta.url));
+
+const CDP = join(dirname(fileURLToPath(import.meta.url)), '..', 'cdp.mjs');
+const PAGES_CACHE = `${tmpdir().replace(/\\/g, '/')}/cdp-pages.json`;
+
+const STREAM_POLL_INTERVAL = 600;
+const STREAM_STABLE_ROUNDS = 3;
+const STREAM_TIMEOUT = 45000;
+const MIN_ANSWER_LENGTH = 50;
+
+// ---------------------------------------------------------------------------
+
+function cdp(args, timeoutMs = 30000) {
+  return new Promise((resolve, reject) => {
+    const proc = spawn('node', [CDP, ...args], { stdio: ['ignore', 'pipe', 'pipe'] });
+    let out = '';
+    let err = '';
+    proc.stdout.on('data', d => out += d);
+    proc.stderr.on('data', d => err += d);
+    const timer = setTimeout(() => { proc.kill(); reject(new Error(`cdp timeout: ${args[0]}`)); }, timeoutMs);
+    proc.on('close', code => {
+      clearTimeout(timer);
+      if (code !== 0) reject(new Error(err.trim() || `cdp exit ${code}`));
+      else resolve(out.trim());
+    });
+  });
+}
+
+async function getOrOpenTab(tabPrefix) {
+  if (tabPrefix) return tabPrefix;
+
+  if (existsSync(PAGES_CACHE)) {
+    const pages = JSON.parse(readFileSync(PAGES_CACHE, 'utf8'));
+    const existing = pages.find(p => p.url.includes('google.com'));
+    if (existing) return existing.targetId.slice(0, 8);
+  }
+
+  const list = await cdp(['list']);
+  const firstLine = list.split('\n')[0];
+  if (!firstLine) throw new Error('No Chrome tabs found. Is Chrome running with --remote-debugging-port=9222?');
+  return firstLine.slice(0, 8);
+}
+
+async function waitForStreamComplete(tab) {
+  const deadline = Date.now() + STREAM_TIMEOUT;
+  let stableCount = 0;
+  let lastLen = -1;
+
+  while (Date.now() < deadline) {
+    await new Promise(r => setTimeout(r, STREAM_POLL_INTERVAL));
+
+    const lenStr = await cdp(['eval', tab,
+      `(document.querySelector('.pWvJNd')?.innerText?.length || 0) + ''`
+    ]).catch(() => '0');
+
+    const len = parseInt(lenStr) || 0;
+
+    if (len >= MIN_ANSWER_LENGTH && len === lastLen) {
+      stableCount++;
+      if (stableCount >= STREAM_STABLE_ROUNDS) return len;
+    } else {
+      stableCount = 0;
+      lastLen = len;
+    }
+  }
+
+  if (lastLen >= MIN_ANSWER_LENGTH) return lastLen;
+  throw new Error(`Google AI answer did not stabilise within ${STREAM_TIMEOUT}ms`);
+}
+
+async function extractAnswer(tab) {
+  const raw = await cdp(['eval', tab, `
+    (function() {
+      var el = document.querySelector('.pWvJNd');
+      if (!el) return JSON.stringify({ answer: '', sources: [] });
+      var answer = el.innerText.trim();
+      var sources = Array.from(document.querySelectorAll('a[href^="http"]'))
+        .filter(a => !a.href.includes('google.') && !a.href.includes('gstatic') && !a.href.includes('googleapis'))
+        .map(a => ({ url: a.href.split('#')[0], title: (a.closest('[data-snhf]')?.querySelector('h3, [role=heading]')?.innerText || a.innerText?.trim().split('\\n')[0] || '').slice(0, 100) }))
+        .filter(s => s.url && s.url.length > 10)
+        .filter((v, i, arr) => arr.findIndex(x => x.url === v.url) === i)
+        .slice(0, 10);
+      return JSON.stringify({ answer, sources });
+    })()
+  `]);
+  return JSON.parse(raw);
+}
+
+// ---------------------------------------------------------------------------
+
+async function main() {
+  const args = process.argv.slice(2);
+  if (!args.length || args[0] === '--help') {
+    process.stderr.write('Usage: node extractors/google-ai.mjs "<query>" [--tab <prefix>]\n');
+    process.exit(1);
+  }
+
+  const short = args.includes('--short');
+  const rest  = args.filter(a => a !== '--short');
+  const tabFlagIdx = rest.indexOf('--tab');
+  const tabPrefix = tabFlagIdx !== -1 ? rest[tabFlagIdx + 1] : null;
+  const query = tabFlagIdx !== -1
+    ? rest.filter((_, i) => i !== tabFlagIdx && i !== tabFlagIdx + 1).join(' ')
+    : rest.join(' ');
+
+  try {
+    await cdp(['list']);
+    const tab = await getOrOpenTab(tabPrefix);
+
+    const url = `https://www.google.com/search?q=${encodeURIComponent(query)}&udm=50`;
+    await cdp(['nav', tab, url], 35000);
+    await new Promise(r => setTimeout(r, 1500));
+    await dismissConsent(tab, cdp);
+
+    // If consent redirected us away, navigate back
+    const currentUrl = await cdp(['eval', tab, 'document.location.href']).catch(() => '');
+    if (!currentUrl.includes('google.com/search')) {
+      await cdp(['nav', tab, url], 35000);
+      await new Promise(r => setTimeout(r, 1500));
+    }
+
+    await waitForStreamComplete(tab);
+
+    const { answer, sources } = await extractAnswer(tab);
+    if (!answer) throw new Error('No answer extracted — Google AI Mode may not have responded');
+    const out = short ? answer.slice(0, 300).replace(/\s+\S*$/, '') + '…' : answer;
+
+    const finalUrl = await cdp(['eval', tab, 'document.location.href']).catch(() => url);
+    process.stdout.write(JSON.stringify({ query, url: finalUrl, answer: out, sources }, null, 2) + '\n');
+  } catch (e) {
+    process.stderr.write(`Error: ${e.message}\n`);
+    process.exit(1);
+  }
+}
+
+main();

package/extractors/perplexity.mjs

@@ -0,0 +1,170 @@
+#!/usr/bin/env node
+// extractors/perplexity.mjs
+// Navigate Perplexity, wait for streaming to complete, return clean answer + sources.
+//
+// Usage:
+//   node extractors/perplexity.mjs "<query>" [--tab <prefix>]
+//
+// Output (stdout): JSON { answer, sources, query, url }
+// Errors go to stderr only — stdout is always clean JSON for piping.
+
+import { readFileSync, existsSync } from 'fs';
+import { spawn } from 'child_process';
+import { tmpdir, homedir } from 'os';
+import { join, dirname } from 'path';
+import { fileURLToPath } from 'url';
+import { dismissConsent } from './consent.mjs';
+
+const CDP = join(dirname(fileURLToPath(import.meta.url)), '..', 'cdp.mjs');
+const PAGES_CACHE = `${tmpdir().replace(/\\/g, '/')}/cdp-pages.json`;
+
+const STREAM_POLL_INTERVAL = 600;  // ms between length checks
+const STREAM_STABLE_ROUNDS = 3;    // consecutive equal-length polls = done
+const STREAM_TIMEOUT = 30000;      // bail out after 30s regardless
+const MIN_ANSWER_LENGTH = 50;      // don't accept trivial answers
+
+// ---------------------------------------------------------------------------
+
+function cdp(args, timeoutMs = 30000) {
+  return new Promise((resolve, reject) => {
+    const proc = spawn('node', [CDP, ...args], { stdio: ['ignore', 'pipe', 'pipe'] });
+    let out = '';
+    let err = '';
+    proc.stdout.on('data', d => out += d);
+    proc.stderr.on('data', d => err += d);
+    const timer = setTimeout(() => { proc.kill(); reject(new Error(`cdp timeout: ${args[0]}`)); }, timeoutMs);
+    proc.on('close', code => {
+      clearTimeout(timer);
+      if (code !== 0) reject(new Error(err.trim() || `cdp exit ${code}`));
+      else resolve(out.trim());
+    });
+  });
+}
+
+async function getOrOpenTab(tabPrefix) {
+  // If caller specified a tab, use it
+  if (tabPrefix) return tabPrefix;
+
+  // Otherwise look for an existing Perplexity tab
+  if (existsSync(PAGES_CACHE)) {
+    const pages = JSON.parse(readFileSync(PAGES_CACHE, 'utf8'));
+    const existing = pages.find(p => p.url.includes('perplexity.ai'));
+    if (existing) return existing.targetId.slice(0, 8);
+  }
+
+  // Fall back to first available tab
+  const list = await cdp(['list']);
+  const firstLine = list.split('\n')[0];
+  if (!firstLine) throw new Error('No Chrome tabs found. Is Chrome running with --remote-debugging-port=9222?');
+  return firstLine.slice(0, 8);
+}
+
+async function waitForStreamComplete(tab) {
+  const deadline = Date.now() + STREAM_TIMEOUT;
+  let stableCount = 0;
+  let lastLen = -1;
+
+  while (Date.now() < deadline) {
+    await new Promise(r => setTimeout(r, STREAM_POLL_INTERVAL));
+
+    const lenStr = await cdp(['eval', tab,
+      `(document.querySelector('.prose')?.innerText?.length || 0) + ''`
+    ]).catch(() => '0');
+
+    const len = parseInt(lenStr) || 0;
+
+    if (len >= MIN_ANSWER_LENGTH && len === lastLen) {
+      stableCount++;
+      if (stableCount >= STREAM_STABLE_ROUNDS) return len;
+    } else {
+      stableCount = 0;
+      lastLen = len;
+    }
+  }
+
+  // Timeout — return whatever we have if it meets minimum length
+  if (lastLen >= MIN_ANSWER_LENGTH) return lastLen;
+  throw new Error(`Perplexity answer did not stabilise within ${STREAM_TIMEOUT}ms`);
+}
+
+async function extractAnswer(tab) {
+  const raw = await cdp(['eval', tab, `
+    (function() {
+      var prose = document.querySelector('.prose');
+      if (!prose) return JSON.stringify({ answer: '', sources: [] });
+      var answer = prose.innerText.trim();
+      var sources = Array.from(document.querySelectorAll('[data-pplx-citation-url]'))
+        .map(el => ({ url: el.getAttribute('data-pplx-citation-url'), title: el.querySelector('a')?.innerText?.trim() || '' }))
+        .filter(s => s.url)
+        .filter((v, i, arr) => arr.findIndex(x => x.url === v.url) === i)
+        .slice(0, 10);
+      return JSON.stringify({ answer, sources });
+    })()
+  `]);
+  return JSON.parse(raw);
+}
+
+// ---------------------------------------------------------------------------
+
+async function main() {
+  const args = process.argv.slice(2);
+  if (!args.length || args[0] === '--help') {
+    process.stderr.write('Usage: node extractors/perplexity.mjs "<query>" [--tab <prefix>]\n');
+    process.exit(1);
+  }
+
+  const short = args.includes('--short');
+  const rest  = args.filter(a => a !== '--short');
+  const tabFlagIdx = rest.indexOf('--tab');
+  const tabPrefix = tabFlagIdx !== -1 ? rest[tabFlagIdx + 1] : null;
+  const query = tabFlagIdx !== -1
+    ? rest.filter((_, i) => i !== tabFlagIdx && i !== tabFlagIdx + 1).join(' ')
+    : rest.join(' ');
+
+
+  try {
+    // Refresh page list so cache is current
+    await cdp(['list']);
+
+    const tab = await getOrOpenTab(tabPrefix);
+
+    // Navigate to homepage and use the search box (direct ?q= URLs trigger bot redirect)
+    await cdp(['nav', tab, 'https://www.perplexity.ai/'], 35000);
+    await dismissConsent(tab, cdp);
+
+    // Wait for React app to mount #ask-input (up to 8s)
+    const deadline = Date.now() + 8000;
+    while (Date.now() < deadline) {
+      const found = await cdp(['eval', tab, `!!document.querySelector('#ask-input')`]).catch(() => 'false');
+      if (found === 'true') break;
+      await new Promise(r => setTimeout(r, 400));
+    }
+    await new Promise(r => setTimeout(r, 300));
+
+    await cdp(['click', tab, '#ask-input']);
+    await new Promise(r => setTimeout(r, 400));
+    await cdp(['type', tab, query]);
+    await new Promise(r => setTimeout(r, 400));
+    // Submit with Enter (most reliable across Chrome instances)
+    await cdp(['eval', tab,
+      `document.querySelector('#ask-input')?.dispatchEvent(new KeyboardEvent('keydown',{key:'Enter',bubbles:true,keyCode:13})), 'ok'`
+    ]);
+
+    // Wait for streaming answer to complete
+    await waitForStreamComplete(tab);
+
+    // Extract
+    const { answer, sources } = await extractAnswer(tab);
+
+    if (!answer) throw new Error('No answer extracted — Perplexity may not have responded');
+    const out = short ? answer.slice(0, 300).replace(/\s+\S*$/, '') + '…' : answer;
+
+    const finalUrl = await cdp(['eval', tab, 'document.location.href']).catch(() => '');
+    process.stdout.write(JSON.stringify({ query, url: finalUrl, answer: out, sources }, null, 2) + '\n');
+  } catch (e) {
+    process.stderr.write(`Error: ${e.message}\n`);
+    process.exit(1);
+  }
+}
+
+main();

package/extractors/stackoverflow-ai.mjs

@@ -0,0 +1,169 @@
+#!/usr/bin/env node
+// extractors/stackoverflow-ai.mjs
+// Navigate Stack Overflow AI Assist, wait for answer, return clean answer + sources.
+//
+// Usage:
+//   node extractors/stackoverflow-ai.mjs "<query>" [--tab <prefix>]
+//
+// Output (stdout): JSON { answer, sources, query, url }
+// Errors go to stderr only — stdout is always clean JSON for piping.
+
+import { readFileSync, existsSync } from 'fs';
+import { spawn } from 'child_process';
+import { tmpdir, homedir } from 'os';
+import { join, dirname } from 'path';
+import { fileURLToPath } from 'url';
+import { dismissConsent } from './consent.mjs';
+
+const CDP = join(dirname(fileURLToPath(import.meta.url)), '..', 'cdp.mjs');
+const PAGES_CACHE = `${tmpdir().replace(/\\/g, '/')}/cdp-pages.json`;
+
+const STREAM_POLL_INTERVAL = 700;
+const STREAM_STABLE_ROUNDS = 3;
+const STREAM_TIMEOUT = 60000;
+const MIN_ANSWER_LENGTH = 50;
+
+// ---------------------------------------------------------------------------
+
+function cdp(args, timeoutMs = 30000) {
+  return new Promise((resolve, reject) => {
+    const proc = spawn('node', [CDP, ...args], { stdio: ['ignore', 'pipe', 'pipe'] });
+    let out = '';
+    let err = '';
+    proc.stdout.on('data', d => out += d);
+    proc.stderr.on('data', d => err += d);
+    const timer = setTimeout(() => { proc.kill(); reject(new Error(`cdp timeout: ${args[0]}`)); }, timeoutMs);
+    proc.on('close', code => {
+      clearTimeout(timer);
+      if (code !== 0) reject(new Error(err.trim() || `cdp exit ${code}`));
+      else resolve(out.trim());
+    });
+  });
+}
+
+async function getOrOpenTab(tabPrefix) {
+  if (tabPrefix) return tabPrefix;
+
+  if (existsSync(PAGES_CACHE)) {
+    const pages = JSON.parse(readFileSync(PAGES_CACHE, 'utf8'));
+    const existing = pages.find(p => p.url.includes('stackoverflow.com'));
+    if (existing) return existing.targetId.slice(0, 8);
+  }
+
+  const list = await cdp(['list']);
+  const firstLine = list.split('\n')[0];
+  if (!firstLine) throw new Error('No Chrome tabs found. Is Chrome running with --remote-debugging-port=9222?');
+  return firstLine.slice(0, 8);
+}
+
+async function waitForStreamComplete(tab) {
+  const deadline = Date.now() + STREAM_TIMEOUT;
+  let stableCount = 0;
+  let lastLen = -1;
+
+  while (Date.now() < deadline) {
+    await new Promise(r => setTimeout(r, STREAM_POLL_INTERVAL));
+
+    const lenStr = await cdp(['eval', tab, `
+      (function(){
+        var msgs = Array.from(document.querySelectorAll('.s-prose.assistantMessage'));
+        var last = msgs[msgs.length - 1];
+        return (last?.innerText?.length || 0) + '';
+      })()
+    `]).catch(() => '0');
+
+    const len = parseInt(lenStr) || 0;
+
+    if (len >= MIN_ANSWER_LENGTH && len === lastLen) {
+      stableCount++;
+      if (stableCount >= STREAM_STABLE_ROUNDS) return len;
+    } else {
+      stableCount = 0;
+      lastLen = len;
+    }
+  }
+
+  if (lastLen >= MIN_ANSWER_LENGTH) return lastLen;
+  throw new Error(`Stack Overflow AI answer did not stabilise within ${STREAM_TIMEOUT}ms`);
+}
+
+async function extractAnswer(tab) {
+  const raw = await cdp(['eval', tab, `
+    (function() {
+      var msgs = Array.from(document.querySelectorAll('.s-prose.assistantMessage'));
+      var el = msgs[msgs.length - 1];
+      if (!el) return JSON.stringify({ answer: '', sources: [] });
+      var answer = el.innerText.trim();
+      // Source cards appear as sibling elements with links to SO questions/docs
+      var sources = Array.from(document.querySelectorAll('.d-flex.g16.px2 a[href], .s-card a[href]'))
+        .map(a => ({ url: a.href, title: a.innerText?.trim().split('\\n')[0]?.slice(0, 100) || '' }))
+        .filter(s => s.url && s.url.startsWith('http'))
+        .filter(s => !s.url.includes('/users/') && !s.url.includes('/questions/ask'))
+        .filter((v, i, arr) => arr.findIndex(x => x.url === v.url) === i)
+        .slice(0, 10);
+      return JSON.stringify({ answer, sources });
+    })()
+  `]);
+  return JSON.parse(raw);
+}
+
+// ---------------------------------------------------------------------------
+
+async function main() {
+  const args = process.argv.slice(2);
+  if (!args.length || args[0] === '--help') {
+    process.stderr.write('Usage: node extractors/stackoverflow-ai.mjs "<query>" [--tab <prefix>]\n');
+    process.exit(1);
+  }
+
+  const tabFlagIdx = args.indexOf('--tab');
+  const tabPrefix = tabFlagIdx !== -1 ? args[tabFlagIdx + 1] : null;
+  const query = tabFlagIdx !== -1
+    ? args.filter((_, i) => i !== tabFlagIdx && i !== tabFlagIdx + 1).join(' ')
+    : args.join(' ');
+
+  try {
+    await cdp(['list']);
+    const tab = await getOrOpenTab(tabPrefix);
+
+    await cdp(['nav', tab, 'https://stackoverflow.com/ai-assist'], 35000);
+    await dismissConsent(tab, cdp);
+
+    // Wait for React app to mount the textarea (up to 8s)
+    const deadline = Date.now() + 8000;
+    while (Date.now() < deadline) {
+      const found = await cdp(['eval', tab, `!!document.querySelector('textarea.s-textarea')`]).catch(() => 'false');
+      if (found === 'true') break;
+      await new Promise(r => setTimeout(r, 400));
+    }
+    await new Promise(r => setTimeout(r, 800)); // extra settle time for SO's React app
+
+    // Set value and submit in one eval — prevents React re-render clearing the value between calls
+    await cdp(['eval', tab, `
+      (function(){
+        var ta = document.querySelector('textarea.s-textarea');
+        if (!ta) return;
+        ta.focus();
+        var setter = Object.getOwnPropertyDescriptor(window.HTMLTextAreaElement.prototype, 'value').set;
+        setter.call(ta, ${JSON.stringify(query)});
+        ta.dispatchEvent(new Event('input', { bubbles: true }));
+        ta.dispatchEvent(new Event('change', { bubbles: true }));
+        // Submit immediately before React can re-render and clear the field
+        ta.dispatchEvent(new KeyboardEvent('keydown', { key: 'Enter', bubbles: true, keyCode: 13 }));
+      })()
+    `]);
+
+    await waitForStreamComplete(tab);
+
+    const { answer, sources } = await extractAnswer(tab);
+    if (!answer) throw new Error('No answer extracted — Stack Overflow AI may not have responded');
+
+    const finalUrl = await cdp(['eval', tab, 'document.location.href']).catch(() => '');
+    process.stdout.write(JSON.stringify({ query, url: finalUrl, answer, sources }, null, 2) + '\n');
+  } catch (e) {
+    process.stderr.write(`Error: ${e.message}\n`);
+    process.exit(1);
+  }
+}
+
+main();