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>
This commit is contained in:
2026-06-20 17:52:09 +02:00
parent 540ec13a63
commit 615d2a8e5f
21 changed files with 891 additions and 39 deletions

View File

@@ -309,6 +309,46 @@ public final class VoiceCatClient {
VoiceCatResult(vc_set_capture_channels(handle, streamId, channels))
}
// MARK: - External PCM feed / tap
/// External PCM feed drives a local stream's encode pipeline with caller-supplied PCM
/// instead of (or in addition to) a hardware capture device. Intended for ReplayKit
/// Broadcast Extension (iOS), ScreenCaptureKit (macOS), bots, and soundboard use cases.
///
/// - Parameters:
/// - streamId: The stream returned by `startStream`. Must be active.
/// - pcm: Raw int16 PCM pointer. Caller must keep the buffer alive for the duration of the call.
/// - samplesPerChannel: Samples per channel (e.g. 960 for 20 ms @ 48 kHz).
/// - channels: 1 (mono) or 2 (stereo interleaved L/R).
@discardableResult
public func feedPcm(streamId: UInt32, pcm: UnsafePointer<Int16>,
samplesPerChannel: Int, channels: UInt32) -> VoiceCatResult {
VoiceCatResult(vc_stream_feed_pcm(handle, streamId, pcm,
UInt(samplesPerChannel), channels))
}
/// Convenience overload for feeding from a Swift `[Int16]` array.
@discardableResult
public func feedPcm(streamId: UInt32, pcm: [Int16],
samplesPerChannel: Int, channels: UInt32) -> VoiceCatResult {
pcm.withUnsafeBufferPointer {
feedPcm(streamId: streamId, pcm: $0.baseAddress!,
samplesPerChannel: samplesPerChannel, channels: channels)
}
}
/// External PCM tap receive decoded per-stream audio as raw int16 PCM before it
/// reaches the hardware mix. Fires once per decoded Opus frame per remote stream.
///
/// The callback is a C function pointer (`@convention(c)`) receiving:
/// `(user, userId, streamId, pcm, samplesPerChannel, channels, sampleRate)`
///
/// Pass `nil` to disable (default). The callback MUST NOT block or allocate.
@discardableResult
public func setPcmSink(_ cb: vc_pcm_sink_cb?, user: UnsafeMutableRawPointer?) -> VoiceCatResult {
VoiceCatResult(vc_set_pcm_sink(handle, cb, user))
}
@discardableResult
public func setInputMode(_ mode: VoiceCatInputMode) -> VoiceCatResult {
VoiceCatResult(vc_set_input_mode(handle, mode.cValue))

View File

@@ -0,0 +1,68 @@
// ExternalPcmTests Swift wrapper smoke tests for vc_stream_feed_pcm / vc_set_pcm_sink.
//
// These tests verify that the Swift API surface compiles, is callable, and returns expected
// results at the C-ABI boundary without requiring a live server or audio hardware.
// Full end-to-end relay / decode verification is covered by tests/test_external_pcm.cpp
// (C++ ctest), which runs headlessly on all platforms.
import XCTest
@testable import VoiceCatCore
final class ExternalPcmTests: XCTestCase {
// MARK: - feedPcm: API surface smoke
/// Calling feedPcm without a connected client or active stream must return .invalidArg
/// (not crash). Proves the SwiftC bridge compiles and handles the error path.
func testFeedPcm_noActiveStream_returnsInvalidArg() {
let client = VoiceCatClient(config: VoiceCatConfig(
clientName: "ext-pcm-test",
clientVersion: "0.1",
logLevel: .off
))
let sine = [Int16](repeating: 0, count: 960)
// Stream 0 doesn't exist the core must return invalidArg, not crash.
let result = client.feedPcm(streamId: 0, pcm: sine, samplesPerChannel: 960, channels: 1)
XCTAssertEqual(result, .invalidArg)
}
/// Calling feedPcm with channels=3 (invalid) must return .invalidArg.
func testFeedPcm_invalidChannels_returnsInvalidArg() {
let client = VoiceCatClient(config: VoiceCatConfig(
clientName: "ext-pcm-test",
clientVersion: "0.1",
logLevel: .off
))
let pcm = [Int16](repeating: 0, count: 960 * 3)
let result = client.feedPcm(streamId: 0, pcm: pcm, samplesPerChannel: 960, channels: 3)
XCTAssertEqual(result, .invalidArg)
}
// MARK: - setPcmSink: API surface smoke
/// setPcmSink(nil) on a freshly-created client must succeed (nil = disable, which is the
/// default state a no-op that must still return .ok).
func testSetPcmSink_nil_returnsOk() {
let client = VoiceCatClient(config: VoiceCatConfig(
clientName: "ext-pcm-test",
clientVersion: "0.1",
logLevel: .off
))
let result = client.setPcmSink(nil, user: nil)
XCTAssertEqual(result, .ok)
}
/// Calling setPcmSink with a @convention(c) function and then immediately disabling it
/// with nil must both succeed. Verifies the C-ABI function-pointer round-trip.
func testSetPcmSink_enableThenDisable_bothSucceed() {
let client = VoiceCatClient(config: VoiceCatConfig(
clientName: "ext-pcm-test",
clientVersion: "0.1",
logLevel: .off
))
let mySink: vc_pcm_sink_cb = { _, _, _, _, _, _, _ in }
XCTAssertEqual(client.setPcmSink(mySink, user: nil), .ok)
XCTAssertEqual(client.setPcmSink(nil, user: nil), .ok)
}
}

View File

@@ -0,0 +1,55 @@
using System.Runtime.InteropServices;
using VoiceCat.Interop;
namespace VoiceCat.Interop.Tests;
/// <summary>
/// API-surface smoke tests for StreamFeedPcm / SetPcmSink through the P/Invoke layer.
/// These tests need voicecat.dll but NOT a running server — they verify the C# wrapper
/// compiles, is callable, and the error paths work at the C-ABI boundary. Full E2E relay
/// verification is handled by tests/test_external_pcm.cpp (C++ ctest).
/// </summary>
public sealed class ExternalPcmTests
{
[Fact]
public void StreamFeedPcm_NoActiveStream_ReturnsInvalidArg()
{
using var client = new VoiceCatClient("ext-pcm-test", "0.1", VcLogLevel.Off);
var pcm = new short[960];
// Stream 0 doesn't exist — core must return InvalidArg, not crash.
var result = client.StreamFeedPcm(0, pcm, 960, channels: 1);
Assert.Equal(VcResult.InvalidArg, result);
}
[Fact]
public void StreamFeedPcm_InvalidChannels_ReturnsInvalidArg()
{
using var client = new VoiceCatClient("ext-pcm-test", "0.1", VcLogLevel.Off);
var pcm = new short[960 * 3];
// channels=3 is not supported — trampoline rejects before touching audio state.
var result = client.StreamFeedPcm(0, pcm, 960, channels: 3);
Assert.Equal(VcResult.InvalidArg, result);
}
[Fact]
public void SetPcmSink_Zero_ReturnsOk()
{
using var client = new VoiceCatClient("ext-pcm-test", "0.1", VcLogLevel.Off);
// IntPtr.Zero = disable — default state, must be a no-op that returns Ok.
var result = client.SetPcmSink(IntPtr.Zero, IntPtr.Zero);
Assert.Equal(VcResult.Ok, result);
}
[Fact]
public void SetPcmSink_EnableThenDisable_BothSucceed()
{
using var client = new VoiceCatClient("ext-pcm-test", "0.1", VcLogLevel.Off);
// Keep the delegate alive until after we unregister it (not just until the P/Invoke call).
NativeMethods.VcPcmSinkCallback sink = static (_, _, _, _, _, _, _) => { };
nint fp = Marshal.GetFunctionPointerForDelegate(sink);
Assert.Equal(VcResult.Ok, client.SetPcmSink(fp, IntPtr.Zero));
Assert.Equal(VcResult.Ok, client.SetPcmSink(IntPtr.Zero, IntPtr.Zero));
GC.KeepAlive(sink);
}
}

View File

@@ -98,6 +98,25 @@ internal static partial class NativeMethods
internal static unsafe partial VcResult vc_test_inject_capture(nint c, uint streamId,
short* pcm, nuint samples);
// ── External PCM feed / tap ──────────────────────────────────────────────────────────
[LibraryImport(LibName)]
internal static unsafe partial VcResult vc_stream_feed_pcm(nint c, uint streamId,
short* pcm, nuint samplesPerChannel, uint channels);
// Delegate type for the PCM sink callback — callers convert to a native function
// pointer via Marshal.GetFunctionPointerForDelegate (for instance members) or by casting
// a static lambda to delegate* unmanaged<> (for [UnmanagedCallersOnly] statics).
// Keep the delegate alive for the lifetime of the sink registration.
[UnmanagedFunctionPointer(CallingConvention.Cdecl)]
public delegate void VcPcmSinkCallback(IntPtr user, uint userId, uint streamId,
IntPtr pcm, nuint samplesPerChannel, uint channels, uint sampleRate);
// cb is a raw function pointer (IntPtr.Zero = disable). Use
// Marshal.GetFunctionPointerForDelegate(sinkDelegate) to convert from VcPcmSinkCallback.
[LibraryImport(LibName)]
internal static partial VcResult vc_set_pcm_sink(nint c, nint cb, IntPtr user);
// ── Text ─────────────────────────────────────────────────────────────────────────────
[LibraryImport(LibName, StringMarshalling = StringMarshalling.Utf8)]
internal static partial VcResult vc_send_text(nint c, VcTextScope scope, uint targetId,

View File

@@ -225,6 +225,20 @@ public sealed class VoiceCatClient : IDisposable
return (r, r == VcResult.Ok ? Marshaling.ToManaged(in native) : null);
}
// ── External PCM feed / tap ─────────────────────────────────────────────────────────
public unsafe VcResult StreamFeedPcm(uint streamId, ReadOnlySpan<short> pcm,
int samplesPerChannel, uint channels)
{
fixed (short* p = pcm)
return NativeMethods.vc_stream_feed_pcm(_handle.DangerousGetHandle(),
streamId, p, (nuint)samplesPerChannel, channels);
}
// Pass Marshal.GetFunctionPointerForDelegate(cb) for a managed delegate, or
// IntPtr.Zero to disable. Keep the delegate alive for the lifetime of the registration.
public VcResult SetPcmSink(nint cb, IntPtr user) =>
NativeMethods.vc_set_pcm_sink(_handle.DangerousGetHandle(), cb, user);
// ── M5: Moderation & admin ───────────────────────────────────────────────────────────
public VcResult KickUser(uint userId, string? reason = null) =>
NativeMethods.vc_kick_user(_handle.DangerousGetHandle(), userId, reason);