/minesweeper — a wine session streamed to the browser over RFB

a websocket byte relay onto x11vnc's tcp socket, the same shape as the
terminal's relay onto the pty sidecar. this is the piece plugins/desktop
could not have: a plugin cannot claim a websocket provider.

the rfb client is ours rather than vendored novnc — raw and copyrect,
one pixel format we dictate so a rectangle memcpys into ImageData. we
control the server, so the other eight encodings are surface we would
carry and never run.

execution, so owner-only: wine runs as the owner, which makes the game's
menus file dialogs over the owner's home.

two bugs worth keeping. the token key is BEARER_TOKEN, not token, so the
upgrade 401'd before any rfb byte moved. and the /status health check
opened a tcp connection to prove liveness — libvncserver blocks its
accept loop peeking for a websocket handshake, so a polled health check
filled the backlog and locked out the real viewer. a liveness check must
not be indistinguishable from a client; it reads /proc/net/tcp now.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
2026-08-22 21:39:35 +00:00
co-authored by Claude Fable 5
parent ae27478a27
commit af918251d3
15 changed files with 848 additions and 1 deletions
@@ -11,6 +11,7 @@ import { appRegistryMetas as chatHistoryMetas } from '../apps/ChatHistory';
import { appRegistryMetas as widgetMetas } from '../apps/Widgets';
import { appRegistryMetas as monitorMetas } from '../apps/SystemMonitor';
import { appRegistryMetas as qrTransferMetas } from '../apps/QrTransfer';
import { appRegistryMetas as minesweeperMetas } from '../apps/Minesweeper';
import { appRegistryMetas as davMetas } from '../apps/Dav';
import { appRegistryMetas as commandHqMetas } from '../apps/CommandHQ';
import type { QueryClient } from '@tanstack/react-query';
@@ -28,6 +29,7 @@ export const apps = [
...widgetMetas,
...monitorMetas,
...qrTransferMetas,
...minesweeperMetas,
...davMetas,
...commandHqMetas,
...appStoreMetas,
@@ -0,0 +1,227 @@
import { useCallback, useEffect, useRef, useState } from "react";
import { Bomb, Loader2, Play, RefreshCw } from "lucide-react";
import { useClient } from "hooks/useClient";
import { RfbClient } from "./rfb";
type SessionStatus = {
installed: boolean;
running: boolean;
window: { width: number; height: number; x: number; y: number } | null;
};
// The framebuffer is bigger than the board — the board sits at 0,0 and the rest is empty desktop.
// Rendering into an offscreen canvas the size of the framebuffer and showing only the board's corner
// of it is what makes this look like a window rather than a small game adrift in grey.
const VISIBLE = { width: 164, height: 226 };
const BUTTON_MASK: Record<number, number> = { 0: 1, 1: 2, 2: 4 };
export const MinesweeperPanel = () => {
const client = useClient();
const canvasRef = useRef<HTMLCanvasElement | null>(null);
const offscreenRef = useRef<HTMLCanvasElement | null>(null);
const rfbRef = useRef<RfbClient | null>(null);
const buttonsRef = useRef(0);
const geometryRef = useRef(VISIBLE);
const [status, setStatus] = useState<SessionStatus | null>(null);
const [error, setError] = useState<string | null>(null);
const [connected, setConnected] = useState(false);
const [busy, setBusy] = useState(false);
const adopt = useCallback((next: SessionStatus) => {
// The board is 152x214 on beginner and wider on the other difficulties. Taking the size from
// status means the canvas is right on the first paint instead of after the first poll.
if (next.window) geometryRef.current = { width: next.window.width, height: next.window.height };
setStatus(next);
}, []);
const refresh = useCallback(async () => {
try {
adopt(await client.get<SessionStatus>("/minesweeper/status"));
} catch {
setError("Could not reach the server.");
}
}, [client, adopt]);
useEffect(() => {
void refresh();
}, [refresh]);
const start = async () => {
setBusy(true);
setError(null);
try {
adopt(await client.post<SessionStatus>("/minesweeper/start", {}));
} catch {
setError("The session would not start. Is wine-minesweeper installed on the server?");
} finally {
setBusy(false);
}
};
// Paint the visible canvas from the offscreen one. Only the board's rectangle is copied, so the
// surrounding desktop never reaches the screen.
const present = useCallback(() => {
const canvas = canvasRef.current;
const offscreen = offscreenRef.current;
if (!canvas || !offscreen) return;
const context = canvas.getContext("2d");
if (!context) return;
const { width, height } = geometryRef.current;
if (canvas.width !== width || canvas.height !== height) {
canvas.width = width;
canvas.height = height;
}
context.drawImage(offscreen, 0, 0, width, height, 0, 0, width, height);
}, []);
useEffect(() => {
if (!status?.running) return;
const scheme = window.location.protocol === "https:" ? "wss" : "ws";
// 'BEARER_TOKEN' is the key the rest of the app uses (Terminal.tsx, useAudioRecording). Reading
// 'token' here sent an empty string, and upgradeWs answered 401 before any RFB byte was exchanged.
const token = localStorage.getItem("BEARER_TOKEN") ?? sessionStorage.getItem("BEARER_TOKEN") ?? "";
const url = `${scheme}://${window.location.host}/api/minesweeper/ws?token=${encodeURIComponent(token)}`;
const rfb = new RfbClient(url, {
onReady: (width, height) => {
const offscreen = document.createElement("canvas");
offscreen.width = width;
offscreen.height = height;
offscreenRef.current = offscreen;
setConnected(true);
setError(null);
},
onFrame: (image, x, y) => {
offscreenRef.current?.getContext("2d")?.putImageData(image, x, y);
present();
},
onCopyRect: (from, to) => {
const offscreen = offscreenRef.current;
const context = offscreen?.getContext("2d");
if (!offscreen || !context) return;
context.drawImage(offscreen, from.x, from.y, to.w, to.h, to.x, to.y, to.w, to.h);
present();
},
onResize: (width, height) => {
const offscreen = offscreenRef.current;
if (offscreen) {
offscreen.width = width;
offscreen.height = height;
}
rfb.requestUpdate(false);
},
onError: (message) => setError(message),
onClose: () => setConnected(false),
});
rfbRef.current = rfb;
return () => {
rfb.close();
rfbRef.current = null;
setConnected(false);
};
}, [status?.running, present]);
// The board resizes when the difficulty changes, and nothing in RFB announces that — the framebuffer
// stays the same size. Polling the window geometry is what keeps the visible canvas matched to it.
useEffect(() => {
if (!connected) return;
const timer = setInterval(async () => {
try {
const next = await client.get<SessionStatus>("/minesweeper/status");
if (!next.window) return;
const { width, height } = next.window;
if (width !== geometryRef.current.width || height !== geometryRef.current.height) {
geometryRef.current = { width, height };
present();
}
} catch {
/* a failed poll is not worth surfacing; the next one will do */
}
}, 4000);
return () => clearInterval(timer);
}, [connected, client, present]);
const toFramebuffer = (ev: React.MouseEvent<HTMLCanvasElement>) => {
const rect = ev.currentTarget.getBoundingClientRect();
const scaleX = ev.currentTarget.width / rect.width;
const scaleY = ev.currentTarget.height / rect.height;
return { x: (ev.clientX - rect.left) * scaleX, y: (ev.clientY - rect.top) * scaleY };
};
const onPointer = (ev: React.MouseEvent<HTMLCanvasElement>, kind: "down" | "up" | "move") => {
const rfb = rfbRef.current;
if (!rfb) return;
ev.preventDefault();
if (kind !== "move") {
const bit = BUTTON_MASK[ev.button] ?? 0;
buttonsRef.current = kind === "down" ? buttonsRef.current | bit : buttonsRef.current & ~bit;
}
const { x, y } = toFramebuffer(ev);
rfb.pointer(x, y, buttonsRef.current);
};
if (status && !status.installed) {
return (
<Centred>
<Bomb className="size-8 text-muted-foreground" />
<p className="text-sm text-muted-foreground">Minesweeper is not installed on this server.</p>
<p className="max-w-sm text-center text-xs text-muted-foreground">
It needs <code>wine-minesweeper</code> beside the platform, with wine and a 32-bit prefix.
</p>
</Centred>
);
}
if (status && !status.running) {
return (
<Centred>
<Bomb className="size-8 text-muted-foreground" />
<p className="text-sm text-muted-foreground">The Minesweeper session is not running.</p>
{error ? <p className="text-xs text-destructive">{error}</p> : null}
<button
type="button"
onClick={start}
disabled={busy}
className="flex items-center gap-2 rounded-md bg-primary px-3 py-1.5 text-sm text-primary-foreground disabled:opacity-60"
>
{busy ? <Loader2 className="size-4 animate-spin" /> : <Play className="size-4" />}
{busy ? "Starting" : "Start it"}
</button>
</Centred>
);
}
return (
<div className="flex size-full flex-col items-center justify-center gap-3 bg-muted/30 p-4">
<canvas
ref={canvasRef}
width={VISIBLE.width}
height={VISIBLE.height}
onMouseDown={(ev) => onPointer(ev, "down")}
onMouseUp={(ev) => onPointer(ev, "up")}
onMouseMove={(ev) => onPointer(ev, "move")}
onContextMenu={(ev) => ev.preventDefault()}
// Nearest-neighbour: this is a 16px-per-cell bitmap from 1995 and smoothing it looks like a
// photograph of a screen rather than the screen.
className="rounded-sm shadow-lg [image-rendering:pixelated]"
style={{ cursor: connected ? "default" : "progress" }}
/>
<div className="flex items-center gap-3 text-xs text-muted-foreground">
<span>{connected ? "connected" : "connecting…"}</span>
<button type="button" onClick={() => void refresh()} className="flex items-center gap-1 hover:text-foreground">
<RefreshCw className="size-3" /> refresh
</button>
</div>
{error ? <p className="text-xs text-destructive">{error}</p> : null}
</div>
);
};
const Centred = ({ children }: { children: React.ReactNode }) => (
<div className="flex size-full flex-col items-center justify-center gap-3 p-6">{children}</div>
);
@@ -0,0 +1,13 @@
import type { AppRegistryMeta } from '../../AppRegistry';
import { Bomb } from 'lucide-react';
import { MinesweeperPanel } from './MinesweeperPanel';
export { MinesweeperPanel } from './MinesweeperPanel';
export { RfbClient } from './rfb';
// Minesweeper X on a virtual display, streamed over RFB. The client is ./rfb.ts — a few hundred lines
// rather than a vendored noVNC, because we control the server and need two encodings out of ten.
export const appRegistryMetas: AppRegistryMeta[] = [
{ key: 'minesweeper', name: 'Minesweeper', icon: Bomb, component: MinesweeperPanel },
];
@@ -0,0 +1,315 @@
/**
* A minimal RFB 3.8 client — enough to watch a framebuffer and click on it, and no more.
*
* ── Why this rather than noVNC ──
*
* noVNC is the obvious choice and it is a good library. It is also ~200 KB of vendored JavaScript for a
* job this file does in a few hundred lines, and vendoring is this repository's reluctant exception
* (hls.js, committed unminified with provenance hashes) rather than its habit. What we need is one
* server we control, one pixel format we choose, and two encodings. The rest of RFB — the eight other
* encodings, the compression, the authentication schemes, the clipboard, the audio — is surface we would
* carry and never execute.
*
* So: Raw and CopyRect, one pixel format, security type None. If this ever has to face a VNC server we
* do not configure, that is the moment to reach for noVNC instead of growing this.
*
* ── The pixel format ──
*
* The client DICTATES the format via SetPixelFormat rather than accepting the server's, so decoding is
* a memcpy into ImageData instead of a per-pixel shift-and-mask. We ask for 32bpp true colour with
* big-endian byte order, which puts the bytes on the wire as R,G,B,X — exactly the order a canvas
* ImageData buffer wants, so a Raw rectangle copies straight in.
*/
export type RfbEvents = {
onReady: (width: number, height: number) => void;
onFrame: (image: ImageData, x: number, y: number) => void;
onCopyRect: (from: { x: number; y: number }, to: { x: number; y: number; w: number; h: number }) => void;
onResize: (width: number, height: number) => void;
onError: (message: string) => void;
onClose: () => void;
};
const ENCODING_RAW = 0;
const ENCODING_COPY_RECT = 1;
const PSEUDO_ENCODING_DESKTOP_SIZE = -223;
type Phase = 'version' | 'security' | 'security-result' | 'init' | 'running';
export class RfbClient {
private socket: WebSocket;
private buffer = new Uint8Array(0);
private phase: Phase = 'version';
private width = 0;
private height = 0;
private events: RfbEvents;
private closed = false;
constructor(url: string, events: RfbEvents) {
this.events = events;
this.socket = new WebSocket(url);
this.socket.binaryType = 'arraybuffer';
this.socket.onmessage = (ev) => this.receive(new Uint8Array(ev.data as ArrayBuffer));
this.socket.onclose = () => {
this.closed = true;
this.events.onClose();
};
this.socket.onerror = () => this.events.onError('The connection to the Minesweeper session failed.');
}
close(): void {
this.closed = true;
try {
this.socket.close();
} catch {
/* already closed */
}
}
private send(bytes: Uint8Array): void {
if (this.socket.readyState === WebSocket.OPEN) this.socket.send(bytes);
}
private receive(chunk: Uint8Array): void {
const merged = new Uint8Array(this.buffer.length + chunk.length);
merged.set(this.buffer);
merged.set(chunk, this.buffer.length);
this.buffer = merged;
// Each step consumes a whole message or nothing at all, so a message split across TCP chunks simply
// waits for the rest. Returning false means "not enough bytes yet".
while (!this.closed && this.step()) {
/* keep draining */
}
}
private take(n: number): Uint8Array | null {
if (this.buffer.length < n) return null;
const head = this.buffer.subarray(0, n);
this.buffer = this.buffer.subarray(n);
return head;
}
private step(): boolean {
switch (this.phase) {
case 'version':
return this.stepVersion();
case 'security':
return this.stepSecurity();
case 'security-result':
return this.stepSecurityResult();
case 'init':
return this.stepInit();
case 'running':
return this.stepMessage();
}
}
private stepVersion(): boolean {
const head = this.take(12);
if (!head) return false;
// Answer 3.8 regardless of what the server offered; x11vnc speaks it and anything older is a server
// we are not configuring.
this.send(new TextEncoder().encode('RFB 003.008\n'));
this.phase = 'security';
return true;
}
private stepSecurity(): boolean {
if (this.buffer.length < 1) return false;
const count = this.buffer[0] as number;
if (count === 0) {
// A zero count means the server is refusing us, and the reason follows as a string.
const body = this.take(1 + 4);
if (!body) return false;
this.events.onError('The VNC server refused the connection.');
this.close();
return false;
}
const head = this.take(1 + count);
if (!head) return false;
const types = Array.from(head.subarray(1));
if (!types.includes(1)) {
this.events.onError('The VNC server wants authentication, which this client does not implement.');
this.close();
return false;
}
this.send(new Uint8Array([1])); // None — the relay is loopback-only and Officer is the authenticator
this.phase = 'security-result';
return true;
}
private stepSecurityResult(): boolean {
const head = this.take(4);
if (!head) return false;
if (new DataView(head.buffer, head.byteOffset, 4).getUint32(0) !== 0) {
this.events.onError('The VNC server rejected the handshake.');
this.close();
return false;
}
this.send(new Uint8Array([1])); // shared: do not disconnect other viewers
this.phase = 'init';
return true;
}
private stepInit(): boolean {
if (this.buffer.length < 24) return false;
const nameLength = new DataView(this.buffer.buffer, this.buffer.byteOffset + 20, 4).getUint32(0);
const head = this.take(24 + nameLength);
if (!head) return false;
const view = new DataView(head.buffer, head.byteOffset, head.byteLength);
this.width = view.getUint16(0);
this.height = view.getUint16(2);
this.setPixelFormat();
this.setEncodings();
this.phase = 'running';
this.events.onReady(this.width, this.height);
this.requestUpdate(false);
return true;
}
/** 32bpp true colour, big-endian, shifts 16/8/0 — i.e. R,G,B,X on the wire, which is ImageData order. */
private setPixelFormat(): void {
const message = new Uint8Array(20);
const view = new DataView(message.buffer);
message[0] = 0; // SetPixelFormat
message[4] = 32; // bits per pixel
message[5] = 24; // depth
message[6] = 1; // big-endian
message[7] = 1; // true colour
view.setUint16(8, 255); // red max
view.setUint16(10, 255); // green max
view.setUint16(12, 255); // blue max
message[14] = 16; // red shift
message[15] = 8; // green shift
message[16] = 0; // blue shift
this.send(message);
}
private setEncodings(): void {
const encodings = [ENCODING_COPY_RECT, ENCODING_RAW, PSEUDO_ENCODING_DESKTOP_SIZE];
const message = new Uint8Array(4 + encodings.length * 4);
const view = new DataView(message.buffer);
message[0] = 2; // SetEncodings
view.setUint16(2, encodings.length);
encodings.forEach((encoding, i) => view.setInt32(4 + i * 4, encoding));
this.send(message);
}
requestUpdate(incremental = true): void {
const message = new Uint8Array(10);
const view = new DataView(message.buffer);
message[0] = 3; // FramebufferUpdateRequest
message[1] = incremental ? 1 : 0;
view.setUint16(6, this.width);
view.setUint16(8, this.height);
this.send(message);
}
private stepMessage(): boolean {
if (this.buffer.length < 1) return false;
const type = this.buffer[0] as number;
// 0 FramebufferUpdate, 1 SetColourMapEntries, 2 Bell, 3 ServerCutText. Only the first matters here;
// the others still have to be CONSUMED or the stream desynchronises and every later frame is garbage.
if (type === 0) return this.stepFramebufferUpdate();
if (type === 2) return this.take(1) !== null;
if (type === 1) {
if (this.buffer.length < 6) return false;
const count = new DataView(this.buffer.buffer, this.buffer.byteOffset + 4, 2).getUint16(0);
return this.take(6 + count * 6) !== null;
}
if (type === 3) {
if (this.buffer.length < 8) return false;
const length = new DataView(this.buffer.buffer, this.buffer.byteOffset + 4, 4).getUint32(0);
return this.take(8 + length) !== null;
}
this.events.onError(`The VNC server sent an unknown message type (${type}).`);
this.close();
return false;
}
/**
* Parsed without consuming anything until the WHOLE update is present. A partial rectangle cannot be
* drawn and cannot be put back, so the alternative is a second parser for resumed state.
*/
private stepFramebufferUpdate(): boolean {
if (this.buffer.length < 4) return false;
const rectangles = new DataView(this.buffer.buffer, this.buffer.byteOffset + 2, 2).getUint16(0);
let offset = 4;
type Rect = { x: number; y: number; w: number; h: number; encoding: number; at: number };
const rects: Rect[] = [];
for (let i = 0; i < rectangles; i++) {
if (this.buffer.length < offset + 12) return false;
const view = new DataView(this.buffer.buffer, this.buffer.byteOffset + offset, 12);
const rect = { x: view.getUint16(0), y: view.getUint16(2), w: view.getUint16(4), h: view.getUint16(6), encoding: view.getInt32(8), at: offset + 12 };
offset += 12;
if (rect.encoding === ENCODING_RAW) offset += rect.w * rect.h * 4;
else if (rect.encoding === ENCODING_COPY_RECT) offset += 4;
else if (rect.encoding === PSEUDO_ENCODING_DESKTOP_SIZE) {
/* no payload — the rect's w/h ARE the new size */
} else {
this.events.onError(`The VNC server used encoding ${rect.encoding}, which this client did not ask for.`);
this.close();
return false;
}
if (this.buffer.length < offset) return false;
rects.push(rect);
}
for (const rect of rects) {
if (rect.encoding === PSEUDO_ENCODING_DESKTOP_SIZE) {
this.width = rect.w;
this.height = rect.h;
this.events.onResize(rect.w, rect.h);
continue;
}
if (rect.encoding === ENCODING_COPY_RECT) {
const src = new DataView(this.buffer.buffer, this.buffer.byteOffset + rect.at, 4);
this.events.onCopyRect({ x: src.getUint16(0), y: src.getUint16(2) }, rect);
continue;
}
// Raw: the wire bytes are already R,G,B,X, so this is a copy rather than a conversion. The alpha
// byte is whatever the server sent, so force it opaque.
const pixels = new Uint8ClampedArray(this.buffer.subarray(rect.at, rect.at + rect.w * rect.h * 4));
for (let i = 3; i < pixels.length; i += 4) pixels[i] = 255;
this.events.onFrame(new ImageData(pixels, rect.w, rect.h), rect.x, rect.y);
}
this.take(offset);
// One request per update message, issued once the whole message is drawn. Requesting per
// rectangle would send several for one update, and requesting on a timer would queue updates the
// client has not consumed yet — the classic way a VNC view ends up lagging behind the pointer.
this.requestUpdate(true);
return true;
}
/** buttons is an RFB button mask: bit 0 left, bit 1 middle, bit 2 right. */
pointer(x: number, y: number, buttons: number): void {
const message = new Uint8Array(6);
const view = new DataView(message.buffer);
message[0] = 5; // PointerEvent
message[1] = buttons;
view.setUint16(2, Math.max(0, Math.min(this.width - 1, Math.round(x))));
view.setUint16(4, Math.max(0, Math.min(this.height - 1, Math.round(y))));
this.send(message);
}
key(keysym: number, down: boolean): void {
const message = new Uint8Array(8);
const view = new DataView(message.buffer);
message[0] = 4; // KeyEvent
message[1] = down ? 1 : 0;
view.setUint32(4, keysym);
this.send(message);
}
}