Complete rebuild of voice input on a server-authoritative streaming architecture, replacing the legacy Web Speech / whole-blob / WASM engines and the dead voice-agent layer (~4k lines removed). Speech-to-text (dictation): - Client streams 16 kHz mono PCM16 chunks over /api/dictation/ws with seq/ack ordering; buffered audio is retained and replayed on reconnect - Server transcribes and streams live partial transcripts back; segments auto-commit every ~15s with silence suppression and adaptive finalization timeouts - Local provider (default, zero config): sherpa-onnx models in a forked worker process — auto-download with progress, staged extraction with verification, corrupt-model auto-recovery, idle shutdown after 5 min - Model catalog with settings picker (accuracy/speed ratings, sizes, download/delete): Parakeet TDT v2 (English) and v3 (25 European languages, auto-detected), Whisper base and tiny (multilingual, light) - OpenAI-compatible provider for any Whisper endpoint - Composer overlay with live transcript, volume meter, timer, and cancel / insert / insert-and-send actions; failed transcriptions keep their audio for retry or accepting the partial text as-is - Configurable keyboard shortcut (default mod+alt+v) toggles dictation; Enter confirms and Escape cancels while recording - Overlay is pixel-aligned with the composer (measured footer height, matching paddings/typography/gaps) — no layout shift when toggling Text-to-speech: - Local Kokoro provider (English, 11 voices) synthesized in the same worker via /api/dictation/tts/speak, managed by the shared model pipeline; sentence-pipelined playback keeps time-to-first-audio at ~1 sentence regardless of message length, and stop cancels in-flight synthesis - Sanitizer keeps inline-code content (strips backticks only), reads interword slashes aloud, and removes only absolute file paths Settings: - Voice page unified: a single read-aloud toggle owns all playback options (the confusing "Enable Voice Mode" is gone); a new "Enable voice input" toggle (default on, persisted to settings.json) hides the composer mic entirely when disabled Mobile and transport: - iOS/Android microphone permissions added (dictation was previously impossible on mobile) - Fixed Android WebSocket upgrades: the Capacitor WebView origin (https://localhost) was missing from the packaged-client allowlist, 403-ing every WS connection — root cause of the old mobile SSE lock, which is now removed for all transports Security and conventions: - All HTTP routes sit behind the global /api auth gate; the WS upgrade explicitly validates the UI session and origin, with oc_url_token narrowly allowlisted and covered by tests; the dictation socket mints a fresh URL token before connecting - Routes register before the generic OpenCode proxy; the client goes through runtimeFetch/getRuntimeUrlResolver, and runtime switches reset the dictation socket - VS Code deliberately reports dictation as unavailable (no server process in that runtime) CI: workflow Node bumped 20 -> 22 to match the repo engines and fix better-sqlite3 installs broken by node-gyp@latest on Node 20. New dependency: sherpa-onnx-node (prebuilt N-API; macOS/Linux x64+arm64, Windows x64 — Windows-on-ARM falls back to the OpenAI-compatible provider)
131 lines
4.1 KiB
JavaScript
131 lines
4.1 KiB
JavaScript
export const createRequestSecurityRuntime = (deps) => {
|
|
const { readSettingsFromDiskMigrated } = deps;
|
|
// Origins of packaged (non-browser) clients whose WebView origin never
|
|
// matches the server host: the desktop shell, the iOS Capacitor WebView
|
|
// (capacitor://localhost), and the Android Capacitor WebView, which uses
|
|
// androidScheme 'https' and therefore reports 'https://localhost'. Missing
|
|
// the Android origin 403'd every WebSocket upgrade from the Android app
|
|
// (message stream, terminal, dictation) while SSE kept working.
|
|
const packagedClientOrigins = new Set([
|
|
'openchamber-ui://app',
|
|
'capacitor://localhost',
|
|
'https://localhost',
|
|
]);
|
|
|
|
const getUiSessionTokenFromRequest = (req) => {
|
|
const cookieHeader = req?.headers?.cookie;
|
|
if (!cookieHeader || typeof cookieHeader !== 'string') {
|
|
return null;
|
|
}
|
|
const segments = cookieHeader.split(';');
|
|
for (const segment of segments) {
|
|
const [rawName, ...rest] = segment.split('=');
|
|
const name = rawName?.trim();
|
|
if (!name) continue;
|
|
if (name !== 'oc_ui_session') continue;
|
|
const value = rest.join('=').trim();
|
|
try {
|
|
return decodeURIComponent(value || '');
|
|
} catch {
|
|
return value || null;
|
|
}
|
|
}
|
|
return null;
|
|
};
|
|
|
|
const rejectWebSocketUpgrade = (socket, statusCode, reason) => {
|
|
if (!socket || socket.destroyed) {
|
|
return;
|
|
}
|
|
|
|
const message = typeof reason === 'string' && reason.trim().length > 0 ? reason.trim() : 'Bad Request';
|
|
const body = Buffer.from(message, 'utf8');
|
|
const statusText = {
|
|
400: 'Bad Request',
|
|
401: 'Unauthorized',
|
|
403: 'Forbidden',
|
|
404: 'Not Found',
|
|
500: 'Internal Server Error',
|
|
}[statusCode] || 'Bad Request';
|
|
|
|
try {
|
|
socket.write(
|
|
`HTTP/1.1 ${statusCode} ${statusText}\r\n` +
|
|
'Connection: close\r\n' +
|
|
'Content-Type: text/plain; charset=utf-8\r\n' +
|
|
`Content-Length: ${body.length}\r\n\r\n`
|
|
);
|
|
socket.write(body);
|
|
} catch {
|
|
}
|
|
|
|
try {
|
|
socket.destroy();
|
|
} catch {
|
|
}
|
|
};
|
|
|
|
const getRequestOriginCandidates = async (req) => {
|
|
const origins = new Set();
|
|
const forwardedProto = typeof req.headers['x-forwarded-proto'] === 'string'
|
|
? req.headers['x-forwarded-proto'].split(',')[0].trim().toLowerCase()
|
|
: '';
|
|
const protocol = forwardedProto || (req.socket?.encrypted ? 'https' : 'http');
|
|
|
|
const forwardedHost = typeof req.headers['x-forwarded-host'] === 'string'
|
|
? req.headers['x-forwarded-host'].split(',')[0].trim()
|
|
: '';
|
|
const host = forwardedHost || (typeof req.headers.host === 'string' ? req.headers.host.trim() : '');
|
|
|
|
if (host) {
|
|
origins.add(`${protocol}://${host}`);
|
|
const [hostname, port] = host.split(':');
|
|
const normalizedHost = typeof hostname === 'string' ? hostname.toLowerCase() : '';
|
|
const portSuffix = typeof port === 'string' && port.length > 0 ? `:${port}` : '';
|
|
if (normalizedHost === 'localhost') {
|
|
origins.add(`${protocol}://127.0.0.1${portSuffix}`);
|
|
origins.add(`${protocol}://[::1]${portSuffix}`);
|
|
} else if (normalizedHost === '127.0.0.1' || normalizedHost === '[::1]') {
|
|
origins.add(`${protocol}://localhost${portSuffix}`);
|
|
}
|
|
}
|
|
|
|
try {
|
|
const settings = await readSettingsFromDiskMigrated();
|
|
if (typeof settings?.publicOrigin === 'string' && settings.publicOrigin.trim().length > 0) {
|
|
origins.add(new URL(settings.publicOrigin.trim()).origin);
|
|
}
|
|
} catch {
|
|
}
|
|
|
|
return origins;
|
|
};
|
|
|
|
const isRequestOriginAllowed = async (req) => {
|
|
const originHeader = typeof req.headers.origin === 'string' ? req.headers.origin.trim() : '';
|
|
if (!originHeader) {
|
|
return false;
|
|
}
|
|
|
|
if (packagedClientOrigins.has(originHeader)) {
|
|
return true;
|
|
}
|
|
|
|
let normalizedOrigin = '';
|
|
try {
|
|
normalizedOrigin = new URL(originHeader).origin;
|
|
} catch {
|
|
return false;
|
|
}
|
|
|
|
const allowedOrigins = await getRequestOriginCandidates(req);
|
|
return allowedOrigins.has(normalizedOrigin);
|
|
};
|
|
|
|
return {
|
|
getUiSessionTokenFromRequest,
|
|
rejectWebSocketUpgrade,
|
|
isRequestOriginAllowed,
|
|
};
|
|
};
|