Files
openchamber/packages/web/server/lib/dev-servers/routes.js
T
Bohdan Triapitsyn a5aa32446d feat(browser): replace the preview proxy with a real browser panel and an agent web tool (#2883)
The preview panel worked by proxying a dev server through OpenChamber's own
origin and rewriting the HTML that came back. Anything the rewriter did not
anticipate broke, and pages that refuse to be embedded never loaded at all.
This deletes the proxy (-1604 lines and its tests) and merges the preview and
browser panels into one surface backed by a real Chromium view.

What the panel is now

- A `<webview>` in its own session partition: logins and cookies persist, hot
  reload works because nothing is rewritten, DevTools are one click away.
- Annotation: pick one element, drag a region, or draw freehand, write a note,
  and it reaches chat with a screenshot of the visible page with the marks on it.
- Toolbar: hard reload, page zoom, device sizes, a light/dark switch that
  applies to the page rather than the app, and cookie/cache clearing scoped to
  the panel alone.
- Several pages at once, each tab showing the page's own favicon, and an address
  bar that suggests pages already visited in this project.
- Dev servers are listed from what is actually listening on the machine, checked
  against what a project announced, so a server is offered no matter how it was
  started. One that is still starting is waited for instead of failing.

Remote dev servers

The desktop app binds a local port and pipes raw bytes to the OpenChamber host
over the existing authenticated connection, so the page keeps its own origin at
the root of its own host. The reachable set is exactly what discovery reports
and is re-checked per connection, so an authenticated client cannot dial
arbitrary local services on the host. Links and redirects to another loopback
port stay on the machine that served the page. A tunnel that cannot be opened is
reported; it is never replaced by the plain loopback URL, which would answer
from the user's own machine under a remote address.

Agent control

Browser actions are a separate `openchamber_web` tool: open, snapshot, click,
type, scroll, inspect computed styles, resize between mobile/tablet/desktop, and
capture a screenshot into `.openchamber/screenshots/` in the project. The
existing `openchamber` tool keeps sessions, worktrees and scheduled tasks. Each
has its own setting in the new Settings -> General -> OpenChamber Tools section,
and the plugin is not injected at all when both are off.

Capability belongs to the connected client, not to configuration: a client
declares on its event stream that it can drive a page, which only a Chromium
host does. Exactly one client performs each request — it claims the request
before acting, and the first claim wins — because deciding by whose result
arrives first would be too late for a click that already happened. No client
listening is answered immediately with an explanation rather than a timeout.

Runtime boundaries

Web tabs get a plain iframe that can display a page but not inspect one. The
VS Code extension no longer offers the surface at all, since nothing that makes
the panel worth having works there. Mobile is unaffected.

Native boundary

Camera, microphone, location and device-picker requests from panel pages are
denied — Electron grants them by default when no handler is set, and the panel
loads whatever address the user types. Page capture, appearance emulation and
storage clearing verify that their target belongs to the panel's own session
instead of trusting a web-contents id from the renderer.

Persisted state

Stored `preview` tabs migrate to `browser` (v13 -> v14). Context panel tab
limits are now per surface, so filling one surface no longer evicts another's
tabs. Address history is stored per project and per runtime.

Documentation

`preview.mdx` and `desktop-browser.mdx` rewritten across all locales, the agent
tool settings path corrected, new `DOCUMENTATION.md` for the browser-control
broker and the dev tunnel, and the `ui-api-decoupling` skill updated where it
still described the deleted proxy.
2026-08-13 22:44:13 +03:00

136 lines
4.6 KiB
JavaScript

/**
* Dev-server discovery.
*
* Answers "what is listening on this machine that I could preview". The old
* approach guessed from `package.json` scripts, which told us what *could* be
* started, never what was actually running — so it was wrong exactly when the
* user needed it. Enumerating listening sockets reports the truth.
*
* Discovery is advisory. A failed scan reports failure; it never reports an
* empty list, because a caller cannot tell "nothing is running" from "the scan
* broke" and would render the wrong empty state.
*/
import fsPromises from 'node:fs/promises';
import {
parseLsofListeners,
parseNetstatListeners,
parseProcNetTcpListeners,
selectDevServerCandidates,
} from './parse.js';
const SCAN_TIMEOUT_MS = 2_500;
/** Enumeration is cheap but not free; a short cache absorbs panel re-renders. */
const CACHE_TTL_MS = 3_000;
const runCommand = (spawn, command, args, timeoutMs) => new Promise((resolve) => {
let child;
try {
child = spawn(command, args, { windowsHide: true, stdio: ['ignore', 'pipe', 'ignore'] });
} catch {
resolve(null);
return;
}
let stdout = '';
let settled = false;
const finish = (value) => {
if (settled) return;
settled = true;
clearTimeout(timer);
try { child.kill(); } catch { /* already exited */ }
resolve(value);
};
const timer = setTimeout(() => finish(null), timeoutMs);
child.stdout?.on('data', (chunk) => { stdout += String(chunk); });
child.on('error', () => finish(null));
child.on('close', (code) => finish(code === 0 || stdout ? stdout : null));
});
/**
* Reads the kernel's socket tables. Containers routinely ship without `lsof`,
* and a deployed OpenChamber is precisely where discovery has to work, so this
* is tried whenever the command is unavailable.
*/
const readProcListeners = async (readFile) => {
const tables = await Promise.all(['/proc/net/tcp', '/proc/net/tcp6'].map(
(path) => readFile(path, 'utf8').catch(() => null),
));
if (tables.every((table) => table === null)) return null;
const byPort = new Map();
for (const table of tables) {
if (table === null) continue;
for (const entry of parseProcNetTcpListeners(table)) {
if (!byPort.has(entry.port)) byPort.set(entry.port, entry);
}
}
return [...byPort.values()].sort((left, right) => left.port - right.port);
};
export const createDevServerScanner = ({ spawn, platform, readFile = fsPromises.readFile }) => {
let cache = null;
const scan = async () => {
const isWindows = platform === 'win32';
if (isWindows) {
const output = await runCommand(spawn, 'netstat', ['-ano', '-p', 'TCP'], SCAN_TIMEOUT_MS);
if (output === null) return { ok: false, reason: 'netstat-unavailable' };
return { ok: true, listeners: parseNetstatListeners(output) };
}
const output = await runCommand(spawn, 'lsof', ['-iTCP', '-sTCP:LISTEN', '-P', '-n', '-F', 'pcn'], SCAN_TIMEOUT_MS);
if (output !== null) return { ok: true, listeners: parseLsofListeners(output) };
const procListeners = await readProcListeners(readFile);
if (procListeners !== null) return { ok: true, listeners: procListeners };
return { ok: false, reason: 'no-listener-source' };
};
return {
/**
* @param {{ ownPorts?: number[] }} options
* @returns {Promise<{ ok: true, servers: Array<{ port: number, pid: number|null, command: string, url: string }> } | { ok: false, reason: string }>}
*/
async discover({ ownPorts = [] } = {}) {
const now = Date.now();
if (cache && now - cache.at < CACHE_TTL_MS) return cache.value;
const result = await scan();
if (!result.ok) {
// Not cached: a transient failure should not suppress the next attempt.
return result;
}
const servers = selectDevServerCandidates(result.listeners, {
ownPorts,
ownPids: [process.pid],
}).map((entry) => ({
...entry,
url: `http://localhost:${entry.port}/`,
}));
const value = { ok: true, servers };
cache = { at: now, value };
return value;
},
};
};
export function registerDevServerRoutes(app, { scanner, getOwnPorts }) {
app.get('/api/dev-servers', async (req, res) => {
try {
const ownPorts = typeof getOwnPorts === 'function' ? getOwnPorts() : [];
const result = await scanner.discover({ ownPorts: Array.isArray(ownPorts) ? ownPorts : [] });
if (!result.ok) {
res.status(503).json({ error: 'Port discovery is unavailable', reason: result.reason });
return;
}
res.json({ servers: result.servers });
} catch (error) {
res.status(500).json({ error: error?.message || 'Port discovery failed' });
}
});
}