Files
voice-cat/server/src/session_registry.cpp

254 lines
8.6 KiB
C++
Raw Normal View History

2026-06-15 23:48:44 +02:00
#include "session_registry.h"
#ifdef VOICECAT_HAS_NET
#include <atomic>
2026-06-15 23:48:44 +02:00
#include <mutex>
#include <shared_mutex>
#include "conn_session.h"
namespace voicecat::server {
void SessionRegistry::init_default_channels() {
std::unique_lock lk(mu_);
ChannelEntry lobby;
lobby.proto.set_id(1);
lobby.proto.set_name("Lobby");
lobby.proto.set_type(voicecat::v1::CHANNEL_PERMANENT);
lobby.proto.set_order(0);
feat(M3): multi-stream & per-channel tuning Implements docs/roadmap.md M3: multiple concurrent streams per user (MIC + SCREEN_AUDIO + AUX_DEVICE), independent per-stream receiver gain/mute/noise- reduction, talk indicators, and enforced per-channel Opus configurability (mono/stereo, bitrate, frame size, FEC/DTX, application). Bugs fixed along the way (found while implementing, not pre-existing scope): - Server hard-coded stream_id=1 for every announce, so a second stream from the same user silently overwrote the first in SessionRegistry::set_user_stream. Now a per-session counter (ConnSession::next_stream_id_); handle_stream_stop validates against announced_stream_ids_ before clearing. - Client dropped mode/dtx/complexity/application from effective_audio even for the single M2 stream -- only sample_rate/bitrate_bps/frame_ms/fec were ever applied to OpusParams. Fixed on both the send (handle_stream_announce_result) and receive (sync_remote_streams) paths via a shared opus_params_from_audio_config() helper. - OpusEncoder always used OPUS_APPLICATION_VOIP; added OpusParams::application and wired it through. - on_playback's per-stream decode passed the wrong frame_size to opus_decode (total samples instead of samples-per-channel), which would have overflowed the decode buffer for any stereo stream. - teardown_voice() raced when called concurrently from run_io()'s own cleanup and from disconnect() on a different thread -- both could see udp_thread_/talk_timer_thread_ as joinable() at once and race to join() the same std::thread (intermittent std::system_error under ctest). Fixed with a teardown_mu_ guard instead of carrying the flake forward. New: - Per-channel AudioConfig: SessionRegistry now seeds Lobby (mono/24kbps/VOIP/ FEC+DTX) and a new "Music Room" channel (stereo/128kbps/AUDIO/no DTX); handle_stream_announce enforces the channel's config, clamping (not overriding) bitrate_bps to its ceiling. - core/src/core/client.h/.cpp: local-stream state is now a std::unordered_map<int, LocalStream> keyed by vc_stream_kind, with request_id-correlated announce/result handling (request_id already round-tripped on the wire; just wasn't read before). on_capture_frame is kind-aware and upmixes mono capture to stereo when a stream's config calls for it. set_self_mute's mic_muted now only gates the MIC kind. NS is wired through set_remote_stream. New run_talk_timer() thread emits VC_EVENT_TALK_STATE from both remote and local edge detection. - core/src/audio/audio_engine.h/.cpp: kind-keyed injection taps (inject_capture), stereo-to-mono downmix at the decode/mix boundary, RemoteStream gains recv_ns (lazy ApmProcessor) + noise_reduction_enabled and last_voice_ms/talking; new set_stream_noise_reduction() and poll_talk_transitions(). - core/src/session/session.h/.cpp: Stream now carries the full AudioConfig, not just sample_rate/frame_ms. - New additive C ABI (core/include/voicecat.h): vc_audio_config + vc_get_stream_audio_config (effective Opus config for any stream you own or a peer's); vc_test_inject_capture (test-only synthetic PCM injection, clearly marked, mirrors AudioEngine::inject_capture). - tests/test_m3_multistream.cpp: the M3 exit criterion through the real ABI (mirrors test_voice_client_abi.cpp's approach, not raw sockets) -- two concurrent local streams, independent gain/mute/NS control, per-channel config divergence via vc_get_stream_audio_config, talk indicators. Explicitly out of scope for this pass (tracked in PROGRESS.md, not silently dropped): VAD/PTT input gate + device enumeration; real WASAPI loopback capture for SCREEN_AUDIO (synthetic injection only); true stereo playback output (AudioEngine's mixer/output device stays mono -- Opus itself is fully stereo-correct on the wire). ctest --test-dir build/m1-dev: 11/11 green, verified across 3 consecutive full-suite runs plus 8 standalone runs of the new test. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-16 14:12:37 +02:00
{
// Speech profile: mono, low bitrate, FEC+DTX on for resilience/silence-suppression.
auto* a = lobby.proto.mutable_audio();
a->set_codec(0);
a->set_mode(voicecat::v1::MODE_MONO);
a->set_sample_rate(48000);
a->set_bitrate_bps(24000);
a->set_frame_ms(20);
a->set_application(voicecat::v1::OPUS_VOIP);
a->set_fec(true);
a->set_expected_packet_loss(10);
a->set_dtx(true);
a->set_complexity(5);
}
2026-06-15 23:48:44 +02:00
channels_[1] = std::move(lobby);
feat(M3): multi-stream & per-channel tuning Implements docs/roadmap.md M3: multiple concurrent streams per user (MIC + SCREEN_AUDIO + AUX_DEVICE), independent per-stream receiver gain/mute/noise- reduction, talk indicators, and enforced per-channel Opus configurability (mono/stereo, bitrate, frame size, FEC/DTX, application). Bugs fixed along the way (found while implementing, not pre-existing scope): - Server hard-coded stream_id=1 for every announce, so a second stream from the same user silently overwrote the first in SessionRegistry::set_user_stream. Now a per-session counter (ConnSession::next_stream_id_); handle_stream_stop validates against announced_stream_ids_ before clearing. - Client dropped mode/dtx/complexity/application from effective_audio even for the single M2 stream -- only sample_rate/bitrate_bps/frame_ms/fec were ever applied to OpusParams. Fixed on both the send (handle_stream_announce_result) and receive (sync_remote_streams) paths via a shared opus_params_from_audio_config() helper. - OpusEncoder always used OPUS_APPLICATION_VOIP; added OpusParams::application and wired it through. - on_playback's per-stream decode passed the wrong frame_size to opus_decode (total samples instead of samples-per-channel), which would have overflowed the decode buffer for any stereo stream. - teardown_voice() raced when called concurrently from run_io()'s own cleanup and from disconnect() on a different thread -- both could see udp_thread_/talk_timer_thread_ as joinable() at once and race to join() the same std::thread (intermittent std::system_error under ctest). Fixed with a teardown_mu_ guard instead of carrying the flake forward. New: - Per-channel AudioConfig: SessionRegistry now seeds Lobby (mono/24kbps/VOIP/ FEC+DTX) and a new "Music Room" channel (stereo/128kbps/AUDIO/no DTX); handle_stream_announce enforces the channel's config, clamping (not overriding) bitrate_bps to its ceiling. - core/src/core/client.h/.cpp: local-stream state is now a std::unordered_map<int, LocalStream> keyed by vc_stream_kind, with request_id-correlated announce/result handling (request_id already round-tripped on the wire; just wasn't read before). on_capture_frame is kind-aware and upmixes mono capture to stereo when a stream's config calls for it. set_self_mute's mic_muted now only gates the MIC kind. NS is wired through set_remote_stream. New run_talk_timer() thread emits VC_EVENT_TALK_STATE from both remote and local edge detection. - core/src/audio/audio_engine.h/.cpp: kind-keyed injection taps (inject_capture), stereo-to-mono downmix at the decode/mix boundary, RemoteStream gains recv_ns (lazy ApmProcessor) + noise_reduction_enabled and last_voice_ms/talking; new set_stream_noise_reduction() and poll_talk_transitions(). - core/src/session/session.h/.cpp: Stream now carries the full AudioConfig, not just sample_rate/frame_ms. - New additive C ABI (core/include/voicecat.h): vc_audio_config + vc_get_stream_audio_config (effective Opus config for any stream you own or a peer's); vc_test_inject_capture (test-only synthetic PCM injection, clearly marked, mirrors AudioEngine::inject_capture). - tests/test_m3_multistream.cpp: the M3 exit criterion through the real ABI (mirrors test_voice_client_abi.cpp's approach, not raw sockets) -- two concurrent local streams, independent gain/mute/NS control, per-channel config divergence via vc_get_stream_audio_config, talk indicators. Explicitly out of scope for this pass (tracked in PROGRESS.md, not silently dropped): VAD/PTT input gate + device enumeration; real WASAPI loopback capture for SCREEN_AUDIO (synthetic injection only); true stereo playback output (AudioEngine's mixer/output device stays mono -- Opus itself is fully stereo-correct on the wire). ctest --test-dir build/m1-dev: 11/11 green, verified across 3 consecutive full-suite runs plus 8 standalone runs of the new test. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-16 14:12:37 +02:00
ChannelEntry music;
music.proto.set_id(2);
music.proto.set_name("Music Room");
music.proto.set_type(voicecat::v1::CHANNEL_PERMANENT);
music.proto.set_order(1);
{
// Music/screen-audio profile: stereo, high bitrate, FEC/DTX off (continuous signal).
auto* a = music.proto.mutable_audio();
a->set_codec(0);
a->set_mode(voicecat::v1::MODE_STEREO);
a->set_sample_rate(48000);
a->set_bitrate_bps(128000);
a->set_frame_ms(20);
a->set_application(voicecat::v1::OPUS_AUDIO);
a->set_fec(false);
a->set_expected_packet_loss(0);
a->set_dtx(false);
a->set_complexity(8);
}
channels_[2] = std::move(music);
next_channel_id_ = 3; // 1 and 2 are now reserved (Lobby, Music Room)
2026-06-15 23:48:44 +02:00
}
uint64_t SessionRegistry::register_session(std::weak_ptr<ConnSession> session) {
std::unique_lock lk(mu_);
uint64_t id = next_session_id_++;
sessions_[id] = std::move(session);
return id;
}
void SessionRegistry::unregister_session(uint64_t session_id) {
std::unique_lock lk(mu_);
sessions_.erase(session_id);
}
uint32_t SessionRegistry::add_user(uint64_t session_id, const voicecat::v1::User& user) {
std::unique_lock lk(mu_);
uint32_t uid = next_user_id_++;
UserEntry entry;
entry.proto = user;
entry.proto.set_id(uid);
entry.proto.set_channel_id(1); // start in Lobby
entry.session_id = session_id;
users_[uid] = std::move(entry);
return uid;
}
void SessionRegistry::remove_user(uint32_t user_id) {
std::unique_lock lk(mu_);
users_.erase(user_id);
}
bool SessionRegistry::set_user_channel(uint32_t user_id, uint32_t channel_id) {
std::unique_lock lk(mu_);
auto ch_it = channels_.find(channel_id);
if (ch_it == channels_.end()) return false;
auto user_it = users_.find(user_id);
if (user_it == users_.end()) return false;
user_it->second.proto.set_channel_id(channel_id);
return true;
}
std::vector<voicecat::v1::Channel> SessionRegistry::channel_snapshot() const {
std::shared_lock lk(mu_);
std::vector<voicecat::v1::Channel> result;
result.reserve(channels_.size());
for (auto& [id, entry] : channels_) result.push_back(entry.proto);
return result;
}
std::vector<voicecat::v1::User> SessionRegistry::user_snapshot() const {
std::shared_lock lk(mu_);
std::vector<voicecat::v1::User> result;
result.reserve(users_.size());
for (auto& [id, entry] : users_) result.push_back(entry.proto);
return result;
}
std::vector<std::shared_ptr<ConnSession>> SessionRegistry::resolve_text_targets(
uint64_t sender_session_id, voicecat::v1::TextScope scope, uint32_t target_id) const {
std::shared_lock lk(mu_);
std::vector<std::shared_ptr<ConnSession>> targets;
if (scope == voicecat::v1::TEXT_CHANNEL) {
// Find channel_id of the target, then all users in that channel
for (auto& [uid, entry] : users_) {
if (entry.proto.channel_id() != target_id) continue;
if (entry.session_id == sender_session_id) continue;
auto sit = sessions_.find(entry.session_id);
if (sit == sessions_.end()) continue;
if (auto sess = sit->second.lock()) targets.push_back(sess);
}
} else if (scope == voicecat::v1::TEXT_PRIVATE) {
// target_id is user_id
auto user_it = users_.find(target_id);
if (user_it != users_.end()) {
auto sit = sessions_.find(user_it->second.session_id);
if (sit != sessions_.end()) {
if (auto sess = sit->second.lock()) targets.push_back(sess);
}
}
}
return targets;
}
void SessionRegistry::broadcast(const voicecat::v1::Envelope& env,
uint64_t exclude_session_id) const {
std::shared_lock lk(mu_);
for (auto& [sid, weak] : sessions_) {
if (sid == exclude_session_id) continue;
if (auto sess = weak.lock()) sess->send_envelope(env);
}
}
// ── M2: UDP / media ──────────────────────────────────────────────────────────
void SessionRegistry::register_udp_token(const std::array<uint8_t, 16>& token,
uint64_t session_id) {
std::unique_lock lk(mu_);
udp_tokens_[token] = session_id;
}
std::shared_ptr<ConnSession> SessionRegistry::find_by_udp_token(
const std::array<uint8_t, 16>& token) const {
std::shared_lock lk(mu_);
auto it = udp_tokens_.find(token);
if (it == udp_tokens_.end()) return nullptr;
auto sit = sessions_.find(it->second);
if (sit == sessions_.end()) return nullptr;
return sit->second.lock();
}
void SessionRegistry::register_udp_endpoint(asio::ip::udp::endpoint ep,
uint64_t session_id) {
std::unique_lock lk(mu_);
udp_endpoints_[ep] = session_id;
}
std::shared_ptr<ConnSession> SessionRegistry::find_by_udp_endpoint(
const asio::ip::udp::endpoint& ep) const {
std::shared_lock lk(mu_);
auto it = udp_endpoints_.find(ep);
if (it == udp_endpoints_.end()) return nullptr;
auto sit = sessions_.find(it->second);
if (sit == sessions_.end()) return nullptr;
return sit->second.lock();
}
uint32_t SessionRegistry::assign_ssrc(uint64_t session_id) {
uint32_t ssrc = next_ssrc_.fetch_add(1, std::memory_order_relaxed);
std::unique_lock lk(mu_);
ssrc_to_session_[ssrc] = session_id;
return ssrc;
}
std::vector<std::shared_ptr<ConnSession>> SessionRegistry::find_channel_sessions(
uint32_t channel_id, uint64_t exclude_session_id) const {
std::shared_lock lk(mu_);
std::vector<std::shared_ptr<ConnSession>> result;
for (auto& [uid, entry] : users_) {
if (entry.proto.channel_id() != channel_id) continue;
if (entry.session_id == exclude_session_id) continue;
auto sit = sessions_.find(entry.session_id);
if (sit == sessions_.end()) continue;
if (auto sess = sit->second.lock()) result.push_back(sess);
}
return result;
}
std::optional<voicecat::v1::User> SessionRegistry::set_user_stream(
uint32_t user_id, const voicecat::v1::StreamInfo& info) {
std::unique_lock lk(mu_);
auto it = users_.find(user_id);
if (it == users_.end()) return std::nullopt;
auto* streams = it->second.proto.mutable_streams();
for (int i = 0; i < streams->size(); ++i) {
if (streams->Get(i).stream_id() == info.stream_id()) {
*streams->Mutable(i) = info;
return it->second.proto;
}
}
*streams->Add() = info;
return it->second.proto;
}
std::optional<voicecat::v1::User> SessionRegistry::clear_user_stream(uint32_t user_id,
uint32_t stream_id) {
std::unique_lock lk(mu_);
auto it = users_.find(user_id);
if (it == users_.end()) return std::nullopt;
auto* streams = it->second.proto.mutable_streams();
for (int i = 0; i < streams->size(); ++i) {
if (streams->Get(i).stream_id() == stream_id) {
streams->erase(streams->begin() + i);
break;
}
}
return it->second.proto;
}
uint32_t SessionRegistry::user_channel(uint32_t user_id) const {
std::shared_lock lk(mu_);
auto it = users_.find(user_id);
return (it == users_.end()) ? 0 : it->second.proto.channel_id();
}
feat(M3): multi-stream & per-channel tuning Implements docs/roadmap.md M3: multiple concurrent streams per user (MIC + SCREEN_AUDIO + AUX_DEVICE), independent per-stream receiver gain/mute/noise- reduction, talk indicators, and enforced per-channel Opus configurability (mono/stereo, bitrate, frame size, FEC/DTX, application). Bugs fixed along the way (found while implementing, not pre-existing scope): - Server hard-coded stream_id=1 for every announce, so a second stream from the same user silently overwrote the first in SessionRegistry::set_user_stream. Now a per-session counter (ConnSession::next_stream_id_); handle_stream_stop validates against announced_stream_ids_ before clearing. - Client dropped mode/dtx/complexity/application from effective_audio even for the single M2 stream -- only sample_rate/bitrate_bps/frame_ms/fec were ever applied to OpusParams. Fixed on both the send (handle_stream_announce_result) and receive (sync_remote_streams) paths via a shared opus_params_from_audio_config() helper. - OpusEncoder always used OPUS_APPLICATION_VOIP; added OpusParams::application and wired it through. - on_playback's per-stream decode passed the wrong frame_size to opus_decode (total samples instead of samples-per-channel), which would have overflowed the decode buffer for any stereo stream. - teardown_voice() raced when called concurrently from run_io()'s own cleanup and from disconnect() on a different thread -- both could see udp_thread_/talk_timer_thread_ as joinable() at once and race to join() the same std::thread (intermittent std::system_error under ctest). Fixed with a teardown_mu_ guard instead of carrying the flake forward. New: - Per-channel AudioConfig: SessionRegistry now seeds Lobby (mono/24kbps/VOIP/ FEC+DTX) and a new "Music Room" channel (stereo/128kbps/AUDIO/no DTX); handle_stream_announce enforces the channel's config, clamping (not overriding) bitrate_bps to its ceiling. - core/src/core/client.h/.cpp: local-stream state is now a std::unordered_map<int, LocalStream> keyed by vc_stream_kind, with request_id-correlated announce/result handling (request_id already round-tripped on the wire; just wasn't read before). on_capture_frame is kind-aware and upmixes mono capture to stereo when a stream's config calls for it. set_self_mute's mic_muted now only gates the MIC kind. NS is wired through set_remote_stream. New run_talk_timer() thread emits VC_EVENT_TALK_STATE from both remote and local edge detection. - core/src/audio/audio_engine.h/.cpp: kind-keyed injection taps (inject_capture), stereo-to-mono downmix at the decode/mix boundary, RemoteStream gains recv_ns (lazy ApmProcessor) + noise_reduction_enabled and last_voice_ms/talking; new set_stream_noise_reduction() and poll_talk_transitions(). - core/src/session/session.h/.cpp: Stream now carries the full AudioConfig, not just sample_rate/frame_ms. - New additive C ABI (core/include/voicecat.h): vc_audio_config + vc_get_stream_audio_config (effective Opus config for any stream you own or a peer's); vc_test_inject_capture (test-only synthetic PCM injection, clearly marked, mirrors AudioEngine::inject_capture). - tests/test_m3_multistream.cpp: the M3 exit criterion through the real ABI (mirrors test_voice_client_abi.cpp's approach, not raw sockets) -- two concurrent local streams, independent gain/mute/NS control, per-channel config divergence via vc_get_stream_audio_config, talk indicators. Explicitly out of scope for this pass (tracked in PROGRESS.md, not silently dropped): VAD/PTT input gate + device enumeration; real WASAPI loopback capture for SCREEN_AUDIO (synthetic injection only); true stereo playback output (AudioEngine's mixer/output device stays mono -- Opus itself is fully stereo-correct on the wire). ctest --test-dir build/m1-dev: 11/11 green, verified across 3 consecutive full-suite runs plus 8 standalone runs of the new test. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-16 14:12:37 +02:00
std::optional<voicecat::v1::AudioConfig> SessionRegistry::channel_audio_config(
uint32_t channel_id) const {
std::shared_lock lk(mu_);
auto it = channels_.find(channel_id);
if (it == channels_.end()) return std::nullopt;
return it->second.proto.audio();
}
2026-06-15 23:48:44 +02:00
} // namespace voicecat::server
#endif // VOICECAT_HAS_NET