Files
voice-cat/core/CMakeLists.txt

101 lines
4.7 KiB
CMake
Raw Normal View History

# libvoicecat — the shared C++ core (docs/architecture.md).
# Sources are globbed so adding a stub under src/<subsystem>/ needs no CMake edit.
file(GLOB_RECURSE VOICECAT_SOURCES CONFIGURE_DEPENDS
"${CMAKE_CURRENT_SOURCE_DIR}/src/*.cpp")
if(VOICECAT_BUILD_SHARED)
add_library(voicecat SHARED ${VOICECAT_SOURCES})
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(WIN32 AND MINGW)
# M4: the C# client only ships voicecat.dll itself — no MinGW runtime DLLs alongside
# it. x64-mingw-static only statically links vcpkg's OWN library deps (protobuf,
# sodium, mbedTLS, ...); the GCC/MinGW runtime stays dynamic by default
# (libgcc_s_seh-1.dll/libwinpthread-1.dll/libstdc++-6.dll — confirmed via `objdump -p`
# on the existing vccli.exe). These flags are the standard fully-static-MinGW
# recipe. Verify after building (see clients/windows/README.md):
# objdump -p build/windows-client/bin/voicecat.dll | grep "DLL Name"
# should show only Windows system DLLs.
target_link_options(voicecat PRIVATE
-static-libgcc -static-libstdc++ -static -lwinpthread)
endif()
if(WIN32)
# CMake's default SHARED naming on MinGW adds a "lib" prefix (libvoicecat.dll) —
# drop it so the output is exactly voicecat.dll, matching the C ABI/library name the
# C# [LibraryImport] surface and docs use everywhere else.
set_target_properties(voicecat PROPERTIES PREFIX "")
endif()
else()
add_library(voicecat STATIC ${VOICECAT_SOURCES})
# Static consumers must see VC_API as empty (no dllimport).
target_compile_definitions(voicecat PUBLIC VOICECAT_STATIC)
endif()
add_library(voicecat::voicecat ALIAS voicecat)
target_include_directories(voicecat
PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/include
PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/src)
target_compile_definitions(voicecat PRIVATE VOICECAT_BUILDING)
target_compile_features(voicecat PUBLIC cxx_std_20)
set_target_properties(voicecat PROPERTIES
C_VISIBILITY_PRESET hidden
CXX_VISIBILITY_PRESET hidden
VISIBILITY_INLINES_HIDDEN ON)
if(VOICECAT_USE_VCPKG_DEPS)
2026-06-15 23:48:44 +02:00
find_package(protobuf CONFIG REQUIRED)
find_package(unofficial-sodium CONFIG REQUIRED)
find_package(MbedTLS CONFIG REQUIRED)
find_package(asio CONFIG REQUIRED)
find_package(unofficial-sqlite3 CONFIG REQUIRED)
find_package(spdlog CONFIG REQUIRED)
find_package(Opus CONFIG REQUIRED)
# miniaudio is header-only; vcpkg does not install a CMake config for it.
find_path(MINIAUDIO_INCLUDE_DIR "miniaudio.h" REQUIRED)
2026-06-15 23:48:44 +02:00
# Generate C++ from voicecat.proto into the build tree.
protobuf_generate(
TARGET voicecat
PROTOS proto/voicecat.proto
LANGUAGE cpp
IMPORT_DIRS ${CMAKE_CURRENT_SOURCE_DIR}/proto
PROTOC_OUT_DIR ${CMAKE_CURRENT_BINARY_DIR}/generated/proto)
# Generated .pb.h files are included by protocol/envelope.h (consumed by tests and server),
# so the generated dir and protobuf itself must be PUBLIC.
target_include_directories(voicecat PUBLIC ${CMAKE_CURRENT_BINARY_DIR}/generated)
target_link_libraries(voicecat
PUBLIC protobuf::libprotobuf
PRIVATE unofficial-sodium::sodium
MbedTLS::mbedtls MbedTLS::mbedcrypto MbedTLS::mbedx509
asio::asio unofficial::sqlite3::sqlite3 spdlog::spdlog
Opus::opus)
target_include_directories(voicecat PRIVATE ${MINIAUDIO_INCLUDE_DIR})
target_compile_definitions(voicecat PUBLIC VOICECAT_HAS_OPUS VOICECAT_HAS_AUDIO)
2026-06-15 23:48:44 +02:00
# On iOS, miniaudio's AVFoundation backend includes Objective-C headers (AVFoundation.h →
# Foundation.h). Compiling those as plain C++ fails; setting LANGUAGE OBJCXX for
# audio_engine.cpp (the only file that includes miniaudio.h directly) fixes this.
if(CMAKE_SYSTEM_NAME STREQUAL "iOS")
set_source_files_properties(
${CMAKE_CURRENT_SOURCE_DIR}/src/audio/audio_engine.cpp
PROPERTIES LANGUAGE OBJCXX
)
endif()
2026-06-15 23:48:44 +02:00
if(WIN32)
# AcceptEx / GetAcceptExSockaddrs live in mswsock; ws2_32 covers the base Winsock API.
target_link_libraries(voicecat PRIVATE ws2_32 mswsock)
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
# Real desktop-audio loopback capture for SCREEN_AUDIO (miniaudio's ma_device_type_loopback
# is WASAPI-only). Other platforms keep vc_test_inject_capture as the only way to feed
# SCREEN_AUDIO until a per-platform loopback path is built (macOS: ScreenCaptureKit, per
# docs/voice.md §9 — not in scope yet).
target_compile_definitions(voicecat PUBLIC VOICECAT_HAS_LOOPBACK)
2026-06-15 23:48:44 +02:00
endif()
# Signal to C++ code that the real networking/crypto stack is available.
target_compile_definitions(voicecat PUBLIC VOICECAT_HAS_NET)
endif()