tkrmagid/javis_bot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 20 Wiki Activity

feat: robust controlBrowser — real xdotool input, tabs/back/forward/popups

Browse Source 
- Install xdotool + wmctrl (late Docker layer, preserves the melo cache) so
  the on-screen Chrome gets real X input (visible cursor, char-by-char typing)
  instead of synthetic events; falls back to the Playwright API if absent.
- Fix active-tab detection (probe document.visibilityState instead of assuming
  tab 0) so sequential ops target the right tab.
- Add back / forward / refresh; new/switch/close tabs via real keyboard
  (Ctrl+T / Ctrl+<n> / Ctrl+W) when xdotool is present.
- Auto-dismiss native JS dialogs; closePopups clears blank/popup tabs.
- Report broadcast (Go-Live) state in status from the turn context.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
javis-bot
2026-06-14 02:33:59 +09:00
parent b18217fcdd
commit 109dbc7e16
3 changed files with 140 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
Dockerfile
View File

@@ -65,6 +65,14 @@ RUN ls -d /opt/venv/lib/python*/site-packages/nvidia/cublas/lib \
COPY docker/setup-melo.sh /app/docker/setup-melo.sh
RUN bash /app/docker/setup-melo.sh
# --- Human input + window management for the on-screen Chrome control tool.
# Placed AFTER the heavy melo layer so it doesn't bust that cache. xdotool
# injects real X pointer/keyboard events (visible cursor, char-by-char
# typing) into the broadcast; wmctrl lists/moves windows. ---
RUN apt-get update && apt-get install -y --no-install-recommends \
xdotool wmctrl \
&& rm -rf /var/lib/apt/lists/*
# --- Discord bot deps (cache layer on lockfile) ---
COPY bot/package.json bot/bun.lock /app/bot/
RUN cd /app/bot && bun install --frozen-lockfile || bun install

213
bot/scripts/stream-test/chrome-control.mjs
View File

@@ -4,182 +4,213 @@
//
// 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.
// Python `controlBrowser` tool to wrap.
//
// Input style: when xdotool is available the pointer/keyboard ACTIONS
// (navigate via the omnibox, click, type, scroll, tab keys) are driven as REAL
// X input — the cursor visibly moves and text is typed one character at a time,
// exactly as a person would. If xdotool is missing it falls back to the
// Playwright/CDP API so the action still happens (just without a visible
// cursor). READ actions always use the CDP/DOM API.
//
// 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
// status | listTabs
// navigate {url} | back | forward | refresh
// newTab {url?} | closeTab {index?} | activateTab {index} | closePopups
// click {selector} | type {text, selector?} | scroll {dir, notches?}
// pressKey {key} | screenshot {path}
import { chromium } from 'playwright';
import {
humanClick,
humanType,
pressKey,
humanScroll,
navigateOmnibox,
} from './human.mjs';
import { execFileSync } from 'node:child_process';
import * as human 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));
const HAS_XDOTOOL = (() => {
try { execFileSync('which', ['xdotool'], { stdio: 'ignore' }); return true; }
catch { return false; }
})();
let cmd;
try {
cmd = JSON.parse(process.argv[2] || '{}');
} catch (e) {
out({ ok: false, error: `bad command json: ${e?.message || e}` });
process.exit(1);
}
try { cmd = JSON.parse(process.argv[2] || '{}'); }
catch (e) { out({ ok: false, error: `bad command json: ${e?.message || e}` }); process.exit(1); }
const action = String(cmd.action || '').trim();
if (!action) {
out({ ok: false, error: 'no action' });
process.exit(1);
if (!action) { out({ ok: false, error: 'no action' }); process.exit(1); }
const norm = (u) => (/^https?:\/\//i.test(u) ? u : `https://${u}`);
// The genuinely-active tab is the one whose document is visible. Playwright has
// no "active page" accessor over CDP, so probe visibilityState (fixes treating
// tab 0 as active and breaking sequential ops on a specific tab).
async function pickActive(pages) {
for (const p of pages) {
try { if (await p.evaluate(() => document.visibilityState === 'visible')) return p; }
catch { /* page may be closing */ }
}
return pages.find((p) => p.url() && p.url() !== 'about:blank') || pages[0];
}
const tabInfo = async (pages, active) => {
async function tabInfo(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,
});
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());
let pages = ctx.pages();
if (!pages.length) pages = [await ctx.newPage()];
let page = await pickActive(pages);
page.setDefaultTimeout(20000);
// Auto-dismiss native JS dialogs (alert/confirm/beforeunload) so a popup can
// never wedge the page.
page.on('dialog', (d) => d.dismiss().catch(() => {}));
const front = async (p) => { await p.bringToFront().catch(() => {}); };
const reload = async () => { await page.reload({ waitUntil: 'domcontentloaded' }).catch(() => {}); };
switch (action) {
case 'status': {
out({ ok: true, browserOpen: true, tabCount: pages.length, tabs: await tabInfo(pages, page) });
case 'status':
case 'listTabs':
await front(page);
out({ ok: true, browserOpen: true, xdotool: HAS_XDOTOOL, 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://${url}`;
await page.bringToFront().catch(() => {});
if (cmd.human === false) {
await page.goto(target, { waitUntil: 'domcontentloaded' });
await front(page);
if (HAS_XDOTOOL && cmd.human !== false) {
try { await human.navigateOmnibox(norm(url)); await page.waitForLoadState('domcontentloaded').catch(() => {}); }
catch { await page.goto(norm(url), { waitUntil: 'domcontentloaded' }); }
} else {
// Type the URL into the omnibox char-by-char with a real cursor.
await navigateOmnibox(target);
await page.waitForLoadState('domcontentloaded').catch(() => {});
await page.goto(norm(url), { waitUntil: 'domcontentloaded' });
}
out({ ok: true, url: page.url(), title: await page.title().catch(() => '') });
out({ ok: true, url: page.url(), title: await page.title().catch(() => ''), input: HAS_XDOTOOL ? 'human' : 'api' });
break;
}
case 'back': await front(page); await page.goBack({ waitUntil: 'domcontentloaded' }).catch(() => {}); out({ ok: true, url: page.url() }); break;
case 'forward': await front(page); await page.goForward({ waitUntil: 'domcontentloaded' }).catch(() => {}); out({ ok: true, url: page.url() }); break;
case 'refresh': await front(page); await reload(); out({ ok: true, url: page.url() }); break;
case 'newTab': {
const np = await ctx.newPage();
await np.bringToFront().catch(() => {});
if (cmd.url) {
const target = /^https?:\/\//i.test(cmd.url) ? cmd.url : `https://${cmd.url}`;
await np.goto(target, { waitUntil: 'domcontentloaded' }).catch(() => {});
let np;
if (HAS_XDOTOOL && cmd.human !== false) {
await front(page);
try { await human.pressKey('ctrl+t'); } catch { /* fall through */ }
await page.waitForTimeout(500);
const after = ctx.pages();
np = after[after.length - 1];
}
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 });
if (!np) np = await ctx.newPage(); // API fallback / no xdotool
await front(np);
if (cmd.url) {
if (HAS_XDOTOOL && cmd.human !== false) { try { await human.navigateOmnibox(norm(cmd.url)); } catch { await np.goto(norm(cmd.url)).catch(() => {}); } }
else await np.goto(norm(cmd.url), { waitUntil: 'domcontentloaded' }).catch(() => {});
}
out({ ok: true, index: ctx.pages().indexOf(np), url: np.url(), input: HAS_XDOTOOL ? 'human' : 'api' });
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();
// Real keyboard: Ctrl+<1..8> selects that tab, Ctrl+9 the last.
if (HAS_XDOTOOL && cmd.human !== false && idx < 8) {
await front(pages[0]);
try { await human.pressKey(`ctrl+${idx + 1}`); } catch { await pages[idx].bringToFront(); }
} else {
await pages[idx].bringToFront();
}
out({ ok: true, active: idx, url: pages[idx].url() });
break;
}
case 'closeTab': {
const idx = Number.isInteger(Number(cmd.index)) ? Number(cmd.index) : pages.indexOf(page);
if (idx < 0 || idx >= pages.length) throw new Error('closeTab: bad index');
if (HAS_XDOTOOL && cmd.human !== false && idx < 8) {
await front(pages[0]);
try { await human.pressKey(`ctrl+${idx + 1}`); await human.pressKey('ctrl+w'); }
catch { await pages[idx].close(); }
} else {
await pages[idx].close();
}
out({ ok: true, closed: idx, remaining: ctx.pages().length });
break;
}
case 'closePopups': {
// Close throwaway/popup tabs (about:blank or anything that isn't the
// active content tab), keeping the active one.
// Close popup / blank / extra tabs, keeping the active content tab.
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++;
}
if (cmd.all || !u || u === 'about:blank') { 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(() => {});
await front(page);
const locator = page.locator(selector).first();
if (cmd.human === false) await locator.click();
else await humanClick(page, locator);
if (HAS_XDOTOOL && cmd.human !== false) { try { await human.humanClick(page, locator); } catch { await locator.click(); } }
else await locator.click();
out({ ok: true });
break;
}
case 'type': {
const text = String(cmd.text ?? '');
await page.bringToFront().catch(() => {});
await front(page);
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
if (HAS_XDOTOOL && cmd.human !== false) { try { await human.humanClick(page, locator); } catch { await locator.click().catch(() => {}); } }
else { await locator.fill(text); out({ ok: true, input: 'api' }); break; }
}
await humanType(text);
out({ ok: true });
if (HAS_XDOTOOL && cmd.human !== false) { try { await human.humanType(text); } catch { await page.keyboard.type(text, { delay: 80 }); } }
else await page.keyboard.type(text, { delay: 80 });
out({ ok: true, input: HAS_XDOTOOL ? 'human' : 'api' });
break;
}
case 'scroll': {
const dir = String(cmd.dir || 'down').toLowerCase() === 'up' ? -1 : 1;
await humanScroll(page, dir, Number(cmd.notches) || 5);
if (HAS_XDOTOOL && cmd.human !== false) { try { await human.humanScroll(page, dir, Number(cmd.notches) || 5); } catch { await page.mouse.wheel(0, dir * 600); } }
else await page.mouse.wheel(0, dir * (Number(cmd.notches) || 5) * 120);
out({ ok: true });
break;
}
case 'pressKey': {
const key = String(cmd.key || '').trim();
if (!key) throw new Error('pressKey: no key');
await pressKey(key);
if (HAS_XDOTOOL) { try { await human.pressKey(key); } catch { await page.keyboard.press(key); } }
else await page.keyboard.press(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 front(page);
await page.screenshot({ path });
out({ ok: true, path });
break;
}
default:
out({ ok: false, error: `unknown action: ${action}` });
await b.close();

13
src/jarvis/tools/builtin/control_browser.py
View File

@@ -57,9 +57,10 @@ class ControlBrowserTool(Tool):
"action": {
"type": "string",
"enum": [
"status", "listTabs", "navigate", "newTab", "closeTab",
"activateTab", "closePopups", "click", "type", "scroll",
"pressKey", "screenshot",
"status", "listTabs", "navigate", "back", "forward",
"refresh", "newTab", "closeTab", "activateTab",
"closePopups", "click", "type", "scroll", "pressKey",
"screenshot",
],
"description": "What to do in the browser.",
},
@@ -116,6 +117,12 @@ class ControlBrowserTool(Tool):
# Return a factual summary of what ACTUALLY happened so the reply engine
# describes the real outcome and doesn't confabulate.
summary = self._summarise(action, args, data)
if action == "status":
# The broadcast (Go-Live) state lives in the bot runtime, surfaced
# to the tool via the turn context — report it alongside the tabs.
bc = getattr(context, "broadcasting", None)
state = "켜짐" if bc else ("꺼짐" if bc is not None else "알 수 없음")
summary = f"📡 방송: {state}\n{summary}"
return ToolExecutionResult(success=True, reply_text=summary)
@staticmethod