feat(M2): UDP voice/media plane -- SFU relay, Opus, AEAD, jitter buffer

Adds the full voice pipeline: 14-byte binary frame header, ChaCha20-Poly1305
AEAD keyed from the TLS exporter, libopus encode/decode with FEC/PLC/DTX,
an adaptive per-ssrc jitter buffer, a miniaudio capture/playback engine, an
APM passthrough stub, and the UdpBinding/StreamAnnounce signaling chain
wired through ConnSession/SessionRegistry into a new server-side SFU
(MediaRelay) that decrypts and re-encrypts frames per channel member.

Exit criterion verified: test_m2_voice — two headless clients relay 50
encrypted Opus frames through the server; ctest --preset m1-dev is 9/9
green. Also corrects protocol.md's UdpBinding diagram, which described the
UDP-side binding packet as AEAD-sealed when it is in fact a plaintext
bootstrap frame (separate from the TCP/TLS UdpBinding ack).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-06-16 01:31:14 +02:00
parent 63f457fc54
commit 694494a5be
29 changed files with 2548 additions and 86 deletions

View File

@@ -175,6 +175,8 @@ void TcpServerConn::start() {
return;
}
self->connected_.store(true, std::memory_order_release);
// Export media keying material before the read loop starts.
if (self->cbs_.on_tls_ready) self->cbs_.on_tls_ready(*self->tls_);
// 50 ms timeout so tls_read_loop can drain the send queue between reads.
self->tls_->set_read_timeout(50);
self->tls_thread_ = std::thread([self] { self->tls_read_loop(); });
@@ -351,6 +353,67 @@ void TcpAcceptor::do_accept() {
});
}
// ── UdpMediaChannel ──────────────────────────────────────────────────────────
bool UdpMediaChannel::bind(asio::io_context& io, uint16_t port) {
if (bound_.load()) return false;
try {
socket_ = std::make_unique<asio::ip::udp::socket>(io);
socket_->open(asio::ip::udp::v4());
socket_->set_option(asio::socket_base::reuse_address(true));
socket_->bind(asio::ip::udp::endpoint(asio::ip::udp::v4(), port));
bound_.store(true, std::memory_order_release);
return true;
} catch (...) {
socket_.reset();
return false;
}
}
void UdpMediaChannel::start_recv(FrameCallback cb) {
frame_cb_ = std::move(cb);
do_recv();
}
void UdpMediaChannel::do_recv() {
if (!socket_ || closed_.load()) return;
socket_->async_receive_from(
asio::buffer(recv_buf_), sender_ep_,
[this](std::error_code ec, std::size_t n) {
if (ec || closed_.load()) return;
if (frame_cb_ && n > 0)
frame_cb_(recv_buf_.data(), n, sender_ep_);
do_recv();
});
}
void UdpMediaChannel::send_to(const uint8_t* data, size_t len,
asio::ip::udp::endpoint dst) {
if (!socket_ || closed_.load() || len == 0) return;
auto buf = std::make_shared<std::vector<uint8_t>>(data, data + len);
asio::post(socket_->get_executor(), [this, buf, dst]() mutable {
if (closed_.load()) return;
socket_->async_send_to(
asio::buffer(*buf), dst,
[buf](std::error_code, std::size_t) {});
});
}
void UdpMediaChannel::close() {
if (closed_.exchange(true)) return;
if (socket_) {
std::error_code ec;
socket_->cancel(ec);
socket_->close(ec);
}
}
asio::ip::udp::endpoint UdpMediaChannel::local_endpoint() const {
if (!socket_) return {};
std::error_code ec;
return socket_->local_endpoint(ec);
}
} // namespace voicecat::net
#endif // VOICECAT_HAS_NET