javis_bot/bot/scripts/stream-test/chrome-control.mjs

// Human-operable Chrome control for the on-screen (Go-Live) browser.
//
//   node chrome-control.mjs '<json-command>'
//
// Connects to the on-screen Chrome over CDP (so every action is visible on the
// broadcast) and performs ONE command, printing a JSON result on stdout for the
// Python `controlBrowser` tool to wrap. READ actions use the CDP/DOM API;
// ACTION actions (navigate/click/type/scroll) drive real input via xdotool
// (human.mjs) so the cursor visibly moves and text is typed one char at a time,
// exactly as a person would — never synthetic DOM events.
//
// Commands (json): { "action": "<name>", ...params }
//   status                              -> broadcast/browser readiness + tab list
//   listTabs                            -> [{index,url,title,active}]
//   navigate   {url, human?}            -> open url in the active tab
//   newTab     {url?}                   -> open a new tab (optionally to url)
//   closeTab   {index}                  -> close tab by index
//   activateTab{index}                  -> bring tab to front
//   closePopups                         -> close blank/popup tabs, keep the active one
//   click      {selector, human?}       -> click an element (human cursor by default)
//   type       {text, selector?, human?}-> type text char-by-char (human by default)
//   scroll     {dir, notches?}          -> wheel scroll (dir: "down"|"up")
//   pressKey   {key}                    -> press a single key (xdotool keysym)
//   screenshot {path}                   -> save a PNG of the active tab
import { chromium } from 'playwright';
import {
  humanClick,
  humanType,
  pressKey,
  humanScroll,
  navigateOmnibox,
} from './human.mjs';

const CDP = process.env.CDP_PORT || '9222';
const CDP_HOST = process.env.CDP_HOST || '127.0.0.1';
const out = (o) => process.stdout.write(JSON.stringify(o));

let cmd;
try {
  cmd = JSON.parse(process.argv[2] || '{}');
} catch (e) {
  out({ ok: false, error: `bad command json: ${e?.message || e}` });
  process.exit(1);
}
const action = String(cmd.action || '').trim();
if (!action) {
  out({ ok: false, error: 'no action' });
  process.exit(1);
}

const tabInfo = async (pages, active) => {
  const list = [];
  for (let i = 0; i < pages.length; i++) {
    const p = pages[i];
    list.push({
      index: i,
      url: p.url(),
      title: await p.title().catch(() => ''),
      active: p === active,
    });
  }
  return list;
};

let b;
try {
  b = await chromium.connectOverCDP(`http://${CDP_HOST}:${CDP}`);
  const ctx = b.contexts()[0];
  if (!ctx) throw new Error('no browser context (is Chrome running?)');
  const pages = ctx.pages();
  // The "active" tab: the most recently fronted page. Playwright has no direct
  // accessor, so we treat the first visible page as active and let activateTab
  // change focus explicitly.
  let page = pages.find((p) => p.url() && p.url() !== 'about:blank') || pages[0] || (await ctx.newPage());
  page.setDefaultTimeout(20000);

  switch (action) {
    case 'status': {
      out({ ok: true, browserOpen: true, tabCount: pages.length, tabs: await tabInfo(pages, page) });
      break;
    }
    case 'listTabs': {
      out({ ok: true, tabs: await tabInfo(pages, page) });
      break;
    }
    case 'navigate': {
      const url = String(cmd.url || '').trim();
      if (!url) throw new Error('navigate: no url');
      const target = /^https?:\/\//i.test(url) ? url : `https://${url}`;
      await page.bringToFront().catch(() => {});
      if (cmd.human === false) {
        await page.goto(target, { waitUntil: 'domcontentloaded' });
      } else {
        // Type the URL into the omnibox char-by-char with a real cursor.
        await navigateOmnibox(target);
        await page.waitForLoadState('domcontentloaded').catch(() => {});
      }
      out({ ok: true, url: page.url(), title: await page.title().catch(() => '') });
      break;
    }
    case 'newTab': {
      const np = await ctx.newPage();
      await np.bringToFront().catch(() => {});
      if (cmd.url) {
        const target = /^https?:\/\//i.test(cmd.url) ? cmd.url : `https://${cmd.url}`;
        await np.goto(target, { waitUntil: 'domcontentloaded' }).catch(() => {});
      }
      out({ ok: true, index: ctx.pages().length - 1, url: np.url() });
      break;
    }
    case 'closeTab': {
      const idx = Number(cmd.index);
      if (!Number.isInteger(idx) || idx < 0 || idx >= pages.length) throw new Error('closeTab: bad index');
      await pages[idx].close();
      out({ ok: true, closed: idx, remaining: ctx.pages().length });
      break;
    }
    case 'activateTab': {
      const idx = Number(cmd.index);
      if (!Number.isInteger(idx) || idx < 0 || idx >= pages.length) throw new Error('activateTab: bad index');
      await pages[idx].bringToFront();
      out({ ok: true, active: idx, url: pages[idx].url() });
      break;
    }
    case 'closePopups': {
      // Close throwaway/popup tabs (about:blank or anything that isn't the
      // active content tab), keeping the active one.
      let closed = 0;
      for (const p of pages) {
        if (p === page) continue;
        const u = p.url();
        if (!u || u === 'about:blank' || cmd.all) {
          await p.close().catch(() => {});
          closed++;
        }
      }
      out({ ok: true, closed, remaining: ctx.pages().length });
      break;
    }
    case 'click': {
      const selector = String(cmd.selector || '').trim();
      if (!selector) throw new Error('click: no selector');
      await page.bringToFront().catch(() => {});
      const locator = page.locator(selector).first();
      if (cmd.human === false) await locator.click();
      else await humanClick(page, locator);
      out({ ok: true });
      break;
    }
    case 'type': {
      const text = String(cmd.text ?? '');
      await page.bringToFront().catch(() => {});
      if (cmd.selector) {
        const locator = page.locator(String(cmd.selector)).first();
        if (cmd.human === false) { await locator.fill(text); out({ ok: true }); break; }
        await humanClick(page, locator); // focus the field with a real click first
      }
      await humanType(text);
      out({ ok: true });
      break;
    }
    case 'scroll': {
      const dir = String(cmd.dir || 'down').toLowerCase() === 'up' ? -1 : 1;
      await humanScroll(page, dir, Number(cmd.notches) || 5);
      out({ ok: true });
      break;
    }
    case 'pressKey': {
      const key = String(cmd.key || '').trim();
      if (!key) throw new Error('pressKey: no key');
      await pressKey(key);
      out({ ok: true });
      break;
    }
    case 'screenshot': {
      const path = String(cmd.path || '').trim();
      if (!path) throw new Error('screenshot: no path');
      await page.bringToFront().catch(() => {});
      await page.screenshot({ path });
      out({ ok: true, path });
      break;
    }
    default:
      out({ ok: false, error: `unknown action: ${action}` });
      await b.close();
      process.exit(1);
  }
  await b.close();
} catch (e) {
  try { await b?.close(); } catch { /* ignore */ }
  out({ ok: false, error: String(e?.message || e) });
  process.exit(1);
}