Files
voice-cat/core/src/voicecat.cpp

154 lines
5.4 KiB
C++
Raw Normal View History

/*
* voicecat.cpp C ABI implementation (M0 skeleton).
*
* Lifecycle (create/destroy) and trivial accessors are real. Everything that needs a
* subsystem (net/crypto/codec/protocol/session/audio) returns VC_ERR_NOT_IMPLEMENTED for
* now and is the work of M1+ (see AGENTS.md / docs/roadmap.md).
*/
#include "voicecat.h"
#include <new>
#include "core/client.h"
#define VC_STR2(x) #x
#define VC_STR(x) VC_STR2(x)
extern "C" {
const char* vc_version_string(void) {
static const char* kVersion = VC_STR(VOICECAT_VERSION_MAJOR) "." VC_STR(
VOICECAT_VERSION_MINOR) "." VC_STR(VOICECAT_VERSION_PATCH);
return kVersion;
}
const char* vc_result_string(vc_result code) {
switch (code) {
case VC_OK: return "ok";
case VC_ERR_NOT_IMPLEMENTED: return "not implemented";
case VC_ERR_INVALID_ARG: return "invalid argument";
case VC_ERR_NOT_CONNECTED: return "not connected";
case VC_ERR_ALREADY: return "already in requested state";
case VC_ERR_AUTH_FAILED: return "authentication failed";
case VC_ERR_PERMISSION_DENIED: return "permission denied";
case VC_ERR_TIMEOUT: return "timeout";
case VC_ERR_IO: return "i/o error";
case VC_ERR_PROTOCOL: return "protocol error";
case VC_ERR_CRYPTO: return "crypto error";
case VC_ERR_AUDIO: return "audio error";
case VC_ERR_INTERNAL: return "internal error";
}
return "unknown";
}
vc_client* vc_client_create(const vc_config* cfg, vc_callbacks cb) {
if (cfg == nullptr) return nullptr;
return new (std::nothrow) vc_client(*cfg, cb);
}
void vc_client_destroy(vc_client* c) { delete c; }
/* ── Everything below delegates to the (stub) client. ─────────────────────── */
vc_result vc_connect(vc_client* c, const char* host, uint16_t port) {
if (c == nullptr || host == nullptr) return VC_ERR_INVALID_ARG;
return c->connect(host, port);
}
vc_result vc_disconnect(vc_client* c) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->disconnect();
}
vc_result vc_authenticate_guest(vc_client* c, const char* nickname) {
if (c == nullptr || nickname == nullptr) return VC_ERR_INVALID_ARG;
return c->authenticate_guest(nickname);
}
vc_result vc_authenticate_user(vc_client* c, const char* username, const char* password) {
if (c == nullptr || username == nullptr || password == nullptr) return VC_ERR_INVALID_ARG;
return c->authenticate_user(username, password);
}
vc_result vc_join_channel(vc_client* c, uint32_t channel_id, const char* password) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->join_channel(channel_id, password);
}
vc_result vc_leave_channel(vc_client* c) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->leave_channel();
}
vc_result vc_stream_start(vc_client* c, const vc_stream_desc* desc, uint32_t* out_stream_id) {
if (c == nullptr || desc == nullptr) return VC_ERR_INVALID_ARG;
return c->stream_start(*desc, out_stream_id);
}
vc_result vc_stream_stop(vc_client* c, uint32_t stream_id) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->stream_stop(stream_id);
}
vc_result vc_set_input_device(vc_client* c, uint32_t stream_id, const char* device_id) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->set_input_device(stream_id, device_id);
}
vc_result vc_set_input_mode(vc_client* c, vc_input_mode mode) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->set_input_mode(mode);
}
vc_result vc_set_push_to_talk(vc_client* c, int active) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->set_push_to_talk(active != 0);
}
vc_result vc_set_self_mute(vc_client* c, int mic_muted, int deafened) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->set_self_mute(mic_muted != 0, deafened != 0);
}
vc_result vc_set_remote_stream(vc_client* c, uint32_t user_id, uint32_t stream_id, float gain,
int muted, int noise_reduction) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->set_remote_stream(user_id, stream_id, gain, muted != 0, noise_reduction != 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
vc_result vc_get_stream_audio_config(vc_client* c, uint32_t user_id, uint32_t stream_id,
vc_audio_config* out) {
if (c == nullptr || out == nullptr) return VC_ERR_INVALID_ARG;
return c->get_stream_audio_config(user_id, stream_id, out);
}
vc_result vc_test_inject_capture(vc_client* c, uint32_t stream_id, const int16_t* pcm,
size_t samples) {
if (c == nullptr || pcm == nullptr) return VC_ERR_INVALID_ARG;
return c->test_inject_capture(stream_id, pcm, samples);
}
vc_result vc_send_text(vc_client* c, vc_text_scope scope, uint32_t target_id,
const char* utf8) {
if (c == nullptr || utf8 == nullptr) return VC_ERR_INVALID_ARG;
return c->send_text(scope, target_id, utf8);
}
vc_result vc_list_devices(vc_client* c, vc_device_kind kind, vc_device_list* out) {
if (c == nullptr || out == nullptr) return VC_ERR_INVALID_ARG;
return c->list_devices(kind, out);
}
void vc_free_device_list(vc_device_list* list) {
feat: device enumeration, VAD/PTT input gate, stereo playback, WASAPI loopback Closes the three items PROGRESS.md's M3 section explicitly carried forward as out of scope: - Device enumeration (vc_list_devices) + input device selection (vc_set_input_device), backed by AudioEngine::enumerate_devices() via miniaudio's ma_context_get_devices. Device ids are opaque hex-encoded ma_device_id strings. - VAD/PTT send-side input gate (vc_set_input_mode, vc_set_push_to_talk). webrtc-audio-processing (the originally-planned APM) has no working Windows/MSVC build upstream (GCC-only Meson, unfinished MinGW support, hard abseil-cpp dependency), so VAD is a new lightweight, dependency-free energy/RMS processor (EnergyVadProcessor) behind the existing ApmProcessor interface. Gating is MIC-only; SCREEN_AUDIO/AUX_DEVICE always bypass it. - True stereo playback: AudioEngine's mixer and output device now carry stereo end-to-end (mono streams upmix L=R) instead of downmixing decoded stereo streams to mono before mixing. - Real WASAPI loopback capture for SCREEN_AUDIO (Windows-only, via miniaudio's loopback device type), replacing test-only injection as the production capture path. Also: vccli gains --list-devices, --input-device, --input-mode, and --share-screen-audio flags, plus a stdin command loop (ptt on/off, mode vad/ptt) for manual verification. New test_vad_ptt_devices.cpp covers all four items (ABI-level + a white-box AudioEngine stereo-mix check). Docs updated to match: voice.md, roadmap.md (decision-log entry superseding the original webrtc-audio-processing choice), tech-stack.md, README.md, architecture.md, CLAUDE.md, PROGRESS.md. Still explicitly out of scope, documented not silently dropped: real webrtc-audio-processing/AEC (no AEC/NS/AGC exists at all yet), macOS/iOS SCREEN_AUDIO capture, process-specific loopback, and a pre-existing RT-thread rule violation in the capture path that predates this work. Verified: ctest 12/12 green across 3 consecutive full-suite runs (both dev and m1-dev presets build clean); test_vad_ptt_devices passed 5 consecutive standalone runs; manually verified live (vccli --list-devices against real hardware, vccli --voice --input-mode vad streaming without incident). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-16 16:11:52 +02:00
if (list == nullptr || list->items == nullptr) return;
for (size_t i = 0; i < list->count; ++i) {
delete[] list->items[i].id;
delete[] list->items[i].name;
}
delete[] list->items;
list->items = nullptr;
list->count = 0;
}
} // extern "C"