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

351 lines
12 KiB
C++
Raw Normal View History

/*
* voicecat.cpp C ABI implementation.
*
* Lifecycle (create/destroy) and trivial accessors are always real. Everything else below
* just delegates to vc_client (core/src/core/client.cpp): under VOICECAT_HAS_NET
* (`dev`/`release`/`server-release` see docs/building.md) that's the real M1M3 implementation;
* under the no-deps `skeleton` preset, client.cpp's `#else` branch returns VC_ERR_NOT_IMPLEMENTED
* for all of it, to keep that skeleton build green.
*/
#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 vc_client (real or stub, per preset above). ───────── */
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);
}
feat(M4): Windows WinForms client, TOFU identity pinning, VAD threshold + always-on mode Core ABI extensions (voicecat.h): - vc_list_channels / vc_list_users / vc_list_user_streams — pull-based snapshot getters for the channel-tree and user-list UI; session_model_mu_ guards cross-thread reads - VC_EVENT_JOIN_RESULT / vc_join_channel — channel join with optional password - VC_EVENT_SERVER_IDENTITY + vc_confirm_server_identity — TOFU gate that blocks io_thread_ until the UI approves or rejects; pins TLS leaf-cert SHA-256 (not declared Ed25519) - vc_get_server_identity_display — Ed25519 fingerprint for human-readable display only - VC_INPUT_ALWAYS_ON = 2 in vc_input_mode — transmit unconditionally, no VAD gate - vc_set_vad_threshold — live RMS threshold update (0.0–1.0); EnergyVadProcessor stores it atomically so the audio RT path reads without a lock C++ implementation: - SessionModel::apply_snapshot / apply_channel_event fixed to populate parent_id, password_protected, and max_users (were permanently zeroed) - TlsContext::peer_cert_fingerprint — SHA-256 of peer leaf cert DER via mbedTLS - TofuStore split into peek (read-only) + pin (write) so first-connect only persists after user approval; tofu_store_path in vc_config for per-user pin file location - TcpAcceptor uses dual-stack IPv6+IPv4 fallback (fixes localhost → ::1 on Windows) - windows-client CMake preset: Release shared DLL, static MinGW runtime, no tools/tests - New C++ tests: test_channel_user_list_abi, test_tofu_flow (14/14 green) Windows client (clients/windows/ — .NET 10 WinForms): - VoiceCat.Interop: LibraryImport P/Invoke surface, UnmanagedCallersOnly callbacks, Channel<VoiceCatEvent> event delivery drained by 30ms WinForms Timer - VoiceCat.App: ConnectDialog (saved servers, DPAPI password storage), ServerIdentity- Dialog (TOFU first-connect / mismatch warning), MainForm (channel TreeView, user ListBox, RichTextBox chat, voice controls, device pickers, VAD/PTT/always-on mode, per-user gain/mute/NR tuning, VAD sensitivity TrackBar, level meter ProgressBar) - PttKeyCaptureDialog — focus-scoped PTT key capture (documented limitation) - PerUserTuningDialog — real-time gain/mute/NR applied to all of a user's streams - Accessibility: explicit AccessibleName/Description on every control, & mnemonics, Activity log ListBox as durable screen-reader record, AutomationNotification for curated live announcements Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-17 00:35:16 +02:00
vc_result vc_set_vad_threshold(vc_client* c, float threshold) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->set_vad_threshold(threshold);
}
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);
}
feat(windows): UI overhaul -- toolbar, unified log, PM windows, channel counts, output volume - Voice actions (Join Voice, Share Screen Audio) moved to a ToolStrip toolbar and a new Voice menu in the menu bar; removed from the bottom voice panel - Activity log and chat log collapsed into a single RichTextBox (rtbLog); activity events appear in gray, chat messages in default color - Private messaging reworked: each conversation opens in its own modeless PrivateMessageForm instead of sharing the main chat log via a scope dropdown; cboScope removed; main compose bar always sends to the current channel - New "Messages -> New Private Message..." menu item (Ctrl+P) opens a UserPickerDialog listing all connected server users (not just the current channel) so you can PM anyone on the server - Channel tree now shows live user counts, e.g. "General (3)" -- counts sourced from the existing _users dictionary which already tracks all server users with channel IDs - Global output volume slider (TrackBar, 0-100, default 80) added to the right panel; wired to new vc_set_output_volume C ABI function that applies a master gain multiplier in the audio engine playback callback after mixing all streams - vc_set_output_volume added end-to-end: voicecat.h, audio_engine.h/.cpp, client.h/.cpp, voicecat.cpp, NativeMethods.cs, VoiceCatClient.cs - Documented Windows PowerShell ctest requirement in AGENTS.md and CLAUDE.md: MinGW binaries exit 0xc0000139 in Git Bash; always run ctest/.exe via PowerShell 22/22 ctest green (PowerShell); dotnet build 0 warnings. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-20 14:24:54 +02:00
vc_result vc_set_output_volume(vc_client* c, float gain) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->set_output_volume(gain);
}
feat(clients): persist input settings, add mic input gain, fix iOS chat + VoiceOver Input mode (VAD/PTT/Always-On), VAD threshold, and the new mic gain were applied to the core + UI but never saved, so every relaunch reset to VAD defaults. Each client now persists them and re-applies on connect: - iOS: UserDefaults (SessionState.loadAndApplyVoiceSettings + setter writes) - macOS: UserDefaults via MainWindowController didSet + loadPersistedAudioSettings (settings window also restores the VAD slider from the stored threshold) - Windows: new Models/VoiceSettings.cs (JSON at %AppData%\VoiceCat\voice.json, mirrors FeedbackSettings) loaded/applied in MainForm Add global send-side mic gain API vc_set_input_gain (applied to MIC PCM in on_capture_frame before the VAD gate, clamped to int16) + Swift/C# bindings, and a 0-300% (default 100%) mic-volume slider on all three clients. Fix iOS chat: ChatView called sendText(scope:.channel) with no targetId (0), so channel messages went nowhere; now passes session.currentChannelId. Fix iOS per-user tuning for VoiceOver: the tuning sheet was long-press .contextMenu only (invisible to VoiceOver); UserRow now also exposes the same buttons via .accessibilityActions (no visual change). Verified: core builds clean; ctest 24/27 (3 pre-existing teardown crashes, reproduced with changes stashed); VoiceCatMac + VoiceCatiOS (arm64 sim) build SUCCEEDED; VoiceCat.Interop dotnet build succeeded. Windows App not built (WinForms can't build on macOS) — follows existing patterns.
2026-06-23 03:35:26 +02:00
vc_result vc_set_input_gain(vc_client* c, float gain) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->set_input_gain(gain);
}
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);
}
vc_result vc_get_remote_stream(vc_client* c, uint32_t user_id, uint32_t stream_id,
vc_remote_stream_state* out) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->get_remote_stream(user_id, stream_id, out);
}
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;
feat: external PCM feed/tap API (vc_stream_feed_pcm + vc_set_pcm_sink) Promotes vc_test_inject_capture (mono-only, TEST-ONLY) to a public, stereo-capable production API and adds a symmetric PCM tap on the receive side. Enables ReplayKit (iOS), ScreenCaptureKit (macOS), bots, soundboards, and custom clients — all without a hardware audio device. Core C++: - voicecat.h: new vc_stream_feed_pcm, vc_pcm_sink_cb typedef, vc_set_pcm_sink; vc_test_inject_capture kept as deprecated alias - audio_engine: stereo-aware inject_capture (channels param + ring reset on channel-count change); atomic pcm_sink_ fired per decoded frame in on_playback; RemoteStream carries user_id/stream_id for RT-safe sink metadata; init_recv_stream takes user_id+stream_id - client.cpp: stream_feed_pcm / set_pcm_sink implementations; sync_remote_streams passes user_id/stream_id to init_recv_stream - voicecat.cpp: trampolines + channels=1/2 validation Tests: test_external_pcm (headless, 3 sub-tests: mono round-trip, stereo feed L≠R, sink metadata+disable). ctest 23/23. Swift: feedPcm / setPcmSink in VoiceCatClient.swift + 4 XCTest smoke tests (ExternalPcmTests.swift). C#: StreamFeedPcm / SetPcmSink in VoiceCatClient.cs + NativeMethods.cs (vc_stream_feed_pcm unsafe P/Invoke, VcPcmSinkCallback delegate, vc_set_pcm_sink via nint) + 4 xUnit smoke tests (ExternalPcmTests.cs). Docs: architecture.md §4 new subsection, voice.md §9 updated (macOS/iOS now reference vc_stream_feed_pcm), protocol.md §8 explicit no-protocol-change note, roadmap.md M5 entry. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-20 17:52:09 +02:00
return c->stream_feed_pcm(stream_id, pcm, samples, 1);
}
vc_result vc_stream_feed_pcm(vc_client* c, uint32_t stream_id, const int16_t* pcm,
size_t samples_per_channel, uint32_t channels) {
if (c == nullptr || pcm == nullptr) return VC_ERR_INVALID_ARG;
if (channels != 1 && channels != 2) return VC_ERR_INVALID_ARG;
return c->stream_feed_pcm(stream_id, pcm, samples_per_channel, channels);
}
vc_result vc_set_pcm_sink(vc_client* c, vc_pcm_sink_cb cb, void* user) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->set_pcm_sink(cb, user);
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_set_mixed_output_sink(vc_client* c, vc_mixed_output_cb cb, void* user) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->set_mixed_output_sink(cb, user);
}
vc_result vc_set_external_playback(vc_client* c, int enable) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->set_external_playback(enable != 0);
}
feat(ios): audio overhaul, Join/Leave Voice, channel-id sync fix, stereo mic capture Three iOS client problems fixed plus a new core stereo-mic capture ABI: 1. Channel-id sync bug (mic button permanently dimmed): SessionState never synced currentChannelId from the self user's channelId on connect, so the mic button (gated on currentChannelId == 0) stayed dimmed. Added syncSelfChannel() (mirrors macOS MainWindowController.swift:461,491,522); called from init/.channelList/.userJoined/.userLeft/.userUpdated/.joinResult. Added applyServerMuteState() + serverMuted/serverDeafened to VoiceState. 2. Join/Leave Voice button: replaced icon-only mic toggle with explicit text button (parity with macOS). Mute/deafen disable when not in voice. 3. IOSAudioRouter.swift (new): full AVAudioSession routing layer — input port selection, built-in mic orientation/polar patterns, Bluetooth HFP/A2DP/Off modes, Standard/Raw mic processing, stereo capture, AirPlay, UserDefaults persistence. AudioSessionManager delegates to it. 4. Core stereo-mic capture (append-only ABI): vc_set_capture_channels() lets the core open the mic device in stereo (2-ch interleaved). LocalStream gains capture_channels; ensure_audio_running reads it; audio_engine.cpp capture_accum_ + on_capture updated to channel-aware accumulation. Test test_stereo_mic_capture (headless, L!=R stereo round-trip). Swift wrapper VoiceCatClient.setCaptureChannels. 5. Settings UI rework: AVAudioSession-derived input/output tree replaces miniaudio device picker. 6. iOS deployment target raised to 18.0 (Package.swift + project.pbxproj). swift-tools-version 6.0 with swiftLanguageModes .v5. Docs: tech-stack.md, architecture.md, voice.md, roadmap.md, building.md updated; stale 'vc_audio_suspend/resume deferred' claims corrected. Verified: ctest --preset dev 21/21 green; swift test 6/6 green; xcodebuild -target VoiceCatiOS -sdk iphonesimulator BUILD SUCCEEDED.
2026-06-19 13:17:52 +02:00
vc_result vc_set_capture_channels(vc_client* c, uint32_t stream_id, uint32_t channels) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->set_capture_channels(stream_id, channels);
}
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;
}
feat(M4): Windows WinForms client, TOFU identity pinning, VAD threshold + always-on mode Core ABI extensions (voicecat.h): - vc_list_channels / vc_list_users / vc_list_user_streams — pull-based snapshot getters for the channel-tree and user-list UI; session_model_mu_ guards cross-thread reads - VC_EVENT_JOIN_RESULT / vc_join_channel — channel join with optional password - VC_EVENT_SERVER_IDENTITY + vc_confirm_server_identity — TOFU gate that blocks io_thread_ until the UI approves or rejects; pins TLS leaf-cert SHA-256 (not declared Ed25519) - vc_get_server_identity_display — Ed25519 fingerprint for human-readable display only - VC_INPUT_ALWAYS_ON = 2 in vc_input_mode — transmit unconditionally, no VAD gate - vc_set_vad_threshold — live RMS threshold update (0.0–1.0); EnergyVadProcessor stores it atomically so the audio RT path reads without a lock C++ implementation: - SessionModel::apply_snapshot / apply_channel_event fixed to populate parent_id, password_protected, and max_users (were permanently zeroed) - TlsContext::peer_cert_fingerprint — SHA-256 of peer leaf cert DER via mbedTLS - TofuStore split into peek (read-only) + pin (write) so first-connect only persists after user approval; tofu_store_path in vc_config for per-user pin file location - TcpAcceptor uses dual-stack IPv6+IPv4 fallback (fixes localhost → ::1 on Windows) - windows-client CMake preset: Release shared DLL, static MinGW runtime, no tools/tests - New C++ tests: test_channel_user_list_abi, test_tofu_flow (14/14 green) Windows client (clients/windows/ — .NET 10 WinForms): - VoiceCat.Interop: LibraryImport P/Invoke surface, UnmanagedCallersOnly callbacks, Channel<VoiceCatEvent> event delivery drained by 30ms WinForms Timer - VoiceCat.App: ConnectDialog (saved servers, DPAPI password storage), ServerIdentity- Dialog (TOFU first-connect / mismatch warning), MainForm (channel TreeView, user ListBox, RichTextBox chat, voice controls, device pickers, VAD/PTT/always-on mode, per-user gain/mute/NR tuning, VAD sensitivity TrackBar, level meter ProgressBar) - PttKeyCaptureDialog — focus-scoped PTT key capture (documented limitation) - PerUserTuningDialog — real-time gain/mute/NR applied to all of a user's streams - Accessibility: explicit AccessibleName/Description on every control, & mnemonics, Activity log ListBox as durable screen-reader record, AutomationNotification for curated live announcements Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-17 00:35:16 +02:00
vc_result vc_list_channels(vc_client* c, vc_channel_list* out) {
if (c == nullptr || out == nullptr) return VC_ERR_INVALID_ARG;
return c->list_channels(out);
}
void vc_free_channel_list(vc_channel_list* list) {
if (list == nullptr || list->items == nullptr) return;
for (size_t i = 0; i < list->count; ++i) {
delete[] list->items[i].name;
delete[] list->items[i].topic;
}
feat(M4): Windows WinForms client, TOFU identity pinning, VAD threshold + always-on mode Core ABI extensions (voicecat.h): - vc_list_channels / vc_list_users / vc_list_user_streams — pull-based snapshot getters for the channel-tree and user-list UI; session_model_mu_ guards cross-thread reads - VC_EVENT_JOIN_RESULT / vc_join_channel — channel join with optional password - VC_EVENT_SERVER_IDENTITY + vc_confirm_server_identity — TOFU gate that blocks io_thread_ until the UI approves or rejects; pins TLS leaf-cert SHA-256 (not declared Ed25519) - vc_get_server_identity_display — Ed25519 fingerprint for human-readable display only - VC_INPUT_ALWAYS_ON = 2 in vc_input_mode — transmit unconditionally, no VAD gate - vc_set_vad_threshold — live RMS threshold update (0.0–1.0); EnergyVadProcessor stores it atomically so the audio RT path reads without a lock C++ implementation: - SessionModel::apply_snapshot / apply_channel_event fixed to populate parent_id, password_protected, and max_users (were permanently zeroed) - TlsContext::peer_cert_fingerprint — SHA-256 of peer leaf cert DER via mbedTLS - TofuStore split into peek (read-only) + pin (write) so first-connect only persists after user approval; tofu_store_path in vc_config for per-user pin file location - TcpAcceptor uses dual-stack IPv6+IPv4 fallback (fixes localhost → ::1 on Windows) - windows-client CMake preset: Release shared DLL, static MinGW runtime, no tools/tests - New C++ tests: test_channel_user_list_abi, test_tofu_flow (14/14 green) Windows client (clients/windows/ — .NET 10 WinForms): - VoiceCat.Interop: LibraryImport P/Invoke surface, UnmanagedCallersOnly callbacks, Channel<VoiceCatEvent> event delivery drained by 30ms WinForms Timer - VoiceCat.App: ConnectDialog (saved servers, DPAPI password storage), ServerIdentity- Dialog (TOFU first-connect / mismatch warning), MainForm (channel TreeView, user ListBox, RichTextBox chat, voice controls, device pickers, VAD/PTT/always-on mode, per-user gain/mute/NR tuning, VAD sensitivity TrackBar, level meter ProgressBar) - PttKeyCaptureDialog — focus-scoped PTT key capture (documented limitation) - PerUserTuningDialog — real-time gain/mute/NR applied to all of a user's streams - Accessibility: explicit AccessibleName/Description on every control, & mnemonics, Activity log ListBox as durable screen-reader record, AutomationNotification for curated live announcements Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-17 00:35:16 +02:00
delete[] list->items;
list->items = nullptr;
list->count = 0;
}
vc_result vc_list_users(vc_client* c, vc_user_list* out) {
if (c == nullptr || out == nullptr) return VC_ERR_INVALID_ARG;
return c->list_users(out);
}
void vc_free_user_list(vc_user_list* list) {
if (list == nullptr || list->items == nullptr) return;
for (size_t i = 0; i < list->count; ++i) delete[] list->items[i].nickname;
delete[] list->items;
list->items = nullptr;
list->count = 0;
}
vc_result vc_list_user_streams(vc_client* c, uint32_t user_id, vc_stream_summary_list* out) {
if (c == nullptr || out == nullptr) return VC_ERR_INVALID_ARG;
return c->list_user_streams(user_id, out);
}
void vc_free_stream_summary_list(vc_stream_summary_list* list) {
if (list == nullptr || list->items == nullptr) return;
for (size_t i = 0; i < list->count; ++i) delete[] list->items[i].label;
delete[] list->items;
list->items = nullptr;
list->count = 0;
}
vc_result vc_confirm_server_identity(vc_client* c, int accept) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->confirm_server_identity(accept != 0);
}
vc_result vc_get_server_identity_display(vc_client* c, char* out_buf, size_t buf_cap,
size_t* out_len) {
feat(M4): Windows WinForms client, TOFU identity pinning, VAD threshold + always-on mode Core ABI extensions (voicecat.h): - vc_list_channels / vc_list_users / vc_list_user_streams — pull-based snapshot getters for the channel-tree and user-list UI; session_model_mu_ guards cross-thread reads - VC_EVENT_JOIN_RESULT / vc_join_channel — channel join with optional password - VC_EVENT_SERVER_IDENTITY + vc_confirm_server_identity — TOFU gate that blocks io_thread_ until the UI approves or rejects; pins TLS leaf-cert SHA-256 (not declared Ed25519) - vc_get_server_identity_display — Ed25519 fingerprint for human-readable display only - VC_INPUT_ALWAYS_ON = 2 in vc_input_mode — transmit unconditionally, no VAD gate - vc_set_vad_threshold — live RMS threshold update (0.0–1.0); EnergyVadProcessor stores it atomically so the audio RT path reads without a lock C++ implementation: - SessionModel::apply_snapshot / apply_channel_event fixed to populate parent_id, password_protected, and max_users (were permanently zeroed) - TlsContext::peer_cert_fingerprint — SHA-256 of peer leaf cert DER via mbedTLS - TofuStore split into peek (read-only) + pin (write) so first-connect only persists after user approval; tofu_store_path in vc_config for per-user pin file location - TcpAcceptor uses dual-stack IPv6+IPv4 fallback (fixes localhost → ::1 on Windows) - windows-client CMake preset: Release shared DLL, static MinGW runtime, no tools/tests - New C++ tests: test_channel_user_list_abi, test_tofu_flow (14/14 green) Windows client (clients/windows/ — .NET 10 WinForms): - VoiceCat.Interop: LibraryImport P/Invoke surface, UnmanagedCallersOnly callbacks, Channel<VoiceCatEvent> event delivery drained by 30ms WinForms Timer - VoiceCat.App: ConnectDialog (saved servers, DPAPI password storage), ServerIdentity- Dialog (TOFU first-connect / mismatch warning), MainForm (channel TreeView, user ListBox, RichTextBox chat, voice controls, device pickers, VAD/PTT/always-on mode, per-user gain/mute/NR tuning, VAD sensitivity TrackBar, level meter ProgressBar) - PttKeyCaptureDialog — focus-scoped PTT key capture (documented limitation) - PerUserTuningDialog — real-time gain/mute/NR applied to all of a user's streams - Accessibility: explicit AccessibleName/Description on every control, & mnemonics, Activity log ListBox as durable screen-reader record, AutomationNotification for curated live announcements Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-17 00:35:16 +02:00
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->get_server_identity_display(out_buf, buf_cap, out_len);
}
vc_result vc_kick_user(vc_client* c, uint32_t user_id, const char* reason) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->kick_user(user_id, reason);
}
vc_result vc_ban_user(vc_client* c, uint32_t user_id, const char* reason,
uint64_t expires_unix_ms) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->ban_user(user_id, reason, expires_unix_ms);
}
vc_result vc_set_permission(vc_client* c, uint32_t user_id, const vc_permissions* perms) {
if (c == nullptr || perms == nullptr) return VC_ERR_INVALID_ARG;
return c->set_permission(user_id, perms);
}
vc_result vc_set_server_mute(vc_client* c, uint32_t user_id, int muted, int deafened) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->set_server_mute(user_id, muted != 0, deafened != 0);
}
vc_result vc_move_user(vc_client* c, uint32_t user_id, uint32_t channel_id) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->move_user(user_id, channel_id);
}
vc_result vc_create_channel(vc_client* c, const vc_channel_info* info) {
if (c == nullptr || info == nullptr) return VC_ERR_INVALID_ARG;
return c->create_channel(info);
}
vc_result vc_edit_channel(vc_client* c, const vc_channel_info* info) {
if (c == nullptr || info == nullptr) return VC_ERR_INVALID_ARG;
return c->edit_channel(info);
}
vc_result vc_delete_channel(vc_client* c, uint32_t channel_id) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->delete_channel(channel_id);
}
vc_result vc_create_account(vc_client* c, const char* username, const char* password) {
if (c == nullptr || username == nullptr || password == nullptr) return VC_ERR_INVALID_ARG;
return c->create_account(username, password);
}
vc_result vc_reset_password(vc_client* c, const char* username, const char* new_password) {
if (c == nullptr || username == nullptr || new_password == nullptr) return VC_ERR_INVALID_ARG;
return c->reset_password(username, new_password);
}
vc_result vc_delete_account(vc_client* c, const char* username) {
if (c == nullptr || username == nullptr) return VC_ERR_INVALID_ARG;
return c->delete_account(username);
}
vc_result vc_list_accounts(vc_client* c) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->list_accounts();
}
vc_result vc_get_account_list(vc_client* c, vc_account_list* out) {
if (c == nullptr || out == nullptr) return VC_ERR_INVALID_ARG;
return c->get_account_list(out);
}
void vc_free_account_list(vc_account_list* list) {
if (list == nullptr || list->items == nullptr) return;
for (size_t i = 0; i < list->count; ++i) delete[] list->items[i].username;
delete[] list->items;
list->items = nullptr;
list->count = 0;
}
vc_result vc_get_permissions(vc_client* c, vc_permissions* out) {
if (c == nullptr || out == nullptr) return VC_ERR_INVALID_ARG;
return c->get_permissions(out);
}
vc_result vc_audio_suspend(vc_client* c) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->audio_suspend();
}
vc_result vc_audio_resume(vc_client* c) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->audio_resume();
}
fix(ios): stereo mic + A2DP output, add vc_audio_restart ABI Diagnosed by comparing against TeamTalk5 (Client/iTeamTalk), which achieves stereo mic + A2DP output. Five fixes: 1. configureStereoCapture now calls setPreferredInput + setInputDataSource (mirroring TeamTalk5's SoundDevicesModel). Previously omitted based on incorrect diagnosis that setPreferredInput collapsed A2DP — the real culprit was setPreferredInputNumberOfChannels(2), which neither project uses. 2. New C ABI: vc_audio_restart (full stop + re-init, unlike suspend/resume which only stop/start). Swift wrapper added. The withAudioSuspend wrapper that used it was removed after on-device testing showed it killed all audio (including VoiceOver) when switching presets — the core's set_capture_channels handles engine restart internally. 3. Bluetooth options: Voice Chat preset now includes BOTH .allowBluetoothHFP AND .allowBluetoothA2DP (matching TeamTalk5's UtilSound.swift:228). Previously HFP-only blocked A2DP headphones. 4. Capture channels now reset when switching stereo→mono via selectCaptureChannels/applyPreset. AudioSessionManager tracks activeMicStreamId (set by SessionState on join/leave voice). 5. Docs synced: voice.md, tech-stack.md, architecture.md, PROGRESS.md. Removed stale setPreferredInputNumberOfChannels(2) references. Verified: ctest --preset dev 21/21 green, iOS client builds. Stereo mic + A2DP output still needs on-device debugging — the core recipe is correct but iOS 26 route behavior requires hands-on testing with a debugger.
2026-06-19 16:58:21 +02:00
vc_result vc_audio_restart(vc_client* c) {
if (c == nullptr) return VC_ERR_INVALID_ARG;
return c->audio_restart();
}
} // extern "C"