voice-cat/tests/test_external_playback.cpp

/*
 * test_external_playback — verifies AudioEngine's external-playback mode (iOS VPIO path).
 *
 * When external playback is enabled, the engine opens NO hardware playback device; a mixer-timer
 * thread drives decode+mix on a ~20ms cadence and delivers the FINAL mixed PCM to the
 * mixed-output sink (the Swift AVAudioEngine VPIO renderer consumes this). This test asserts:
 *   1. The mixed sink fires steadily on the timer thread (count grows over time) with the right
 *      format (48kHz, stereo), and carries real energy while a stream is being decoded.
 *   2. The per-stream pcm_sink still fires concurrently (both taps coexist).
 *   3. With no remote streams, the mixed sink KEEPS firing (silent-but-present blocks) so the
 *      renderer has a continuous clock.
 *
 * White-box: constructs AudioEngine directly (no server, no audio hardware needed) — the timer
 * thread drives the mixer with no ma_device, which is the core new behavior under test.
 */
#include <atomic>
#include <chrono>
#include <cmath>
#include <cstdio>
#include <thread>
#include <vector>

#if defined(VOICECAT_HAS_AUDIO) && defined(VOICECAT_HAS_OPUS)

#include "audio/audio_engine.h"
#include "codec/opus_codec.h"

static int g_failures = 0;
#define CHECK(cond)                                                       \
    do {                                                                  \
        if (!(cond)) {                                                    \
            std::printf("FAIL [%s:%d]: %s\n", __FILE__, __LINE__, #cond); \
            ++g_failures;                                                 \
        }                                                                 \
    } while (0)

// Shared state written by the sink callbacks (timer thread) and read by main.
struct MixedSinkState {
    std::atomic<int> calls{0};
    std::atomic<int64_t> max_energy{0};
    std::atomic<uint32_t> last_channels{0};
    std::atomic<uint32_t> last_sample_rate{0};
};
static MixedSinkState g_mixed;
static std::atomic<int> g_pcm_sink_calls{0};

static void mixed_cb(void* user, const int16_t* pcm, size_t spc, uint32_t ch, uint32_t sr) {
    auto* s = static_cast<MixedSinkState*>(user);
    s->calls.fetch_add(1, std::memory_order_relaxed);
    s->last_channels.store(ch, std::memory_order_relaxed);
    s->last_sample_rate.store(sr, std::memory_order_relaxed);
    int64_t e = 0;
    for (size_t i = 0; i < spc * ch; ++i) e += std::abs(static_cast<int>(pcm[i]));
    int64_t prev = s->max_energy.load(std::memory_order_relaxed);
    while (e > prev && !s->max_energy.compare_exchange_weak(prev, e, std::memory_order_relaxed)) {
    }
}

static void pcm_cb(void*, uint32_t, uint32_t, const int16_t*, size_t, uint32_t, uint32_t) {
    g_pcm_sink_calls.fetch_add(1, std::memory_order_relaxed);
}

int main() {
    voicecat::audio::AudioEngine engine;
    engine.set_external_playback(true);
    engine.set_mixed_output_sink(&mixed_cb, &g_mixed);
    engine.set_pcm_sink(&pcm_cb, nullptr);

    voicecat::audio::AudioParams p;
    p.sample_rate = 48000;
    p.capture_channels = 1;
    p.playback_channels = 2;
    p.frame_ms = 20;
    CHECK(engine.start(p));  // no hardware device opened — the timer thread drives the mixer

    voicecat::codec::OpusParams op;
    op.sample_rate = 48000;
    op.frame_ms = 20;
    op.stereo = false;
    int frame_samples = voicecat::codec::opus_frame_samples(op);  // 960

    voicecat::codec::OpusEncoder enc;
    CHECK(enc.init(op));
    std::vector<int16_t> sine(static_cast<size_t>(frame_samples));
    for (int i = 0; i < frame_samples; ++i) {
        float t = static_cast<float>(i) / 48000.0f;
        sine[i] = static_cast<int16_t>(std::sin(2.0f * 3.14159265f * 440.0f * t) * 20000.0f);
    }
    uint8_t opus_buf[1500];
    int opus_len = enc.encode(sine.data(), frame_samples, opus_buf, sizeof(opus_buf));
    CHECK(opus_len > 0);

    const uint32_t ssrc = 1;
    engine.init_recv_stream(ssrc, op, /*user_id=*/7, /*stream_id=*/3);

    // ── Phase 1: feed ~600ms of real frames; the timer must decode + mix them. ──────────
    uint32_t ts = 0;
    for (int i = 0; i < 30; ++i) {  // 30 * 20ms = 600ms of audio
        voicecat::audio::JitterBuffer::Frame f;
        f.seq = static_cast<uint64_t>(i);
        f.timestamp = ts;
        f.fec_present = false;
        f.payload.assign(opus_buf, opus_buf + opus_len);
        engine.push_recv_frame(ssrc, std::move(f));
        ts += static_cast<uint32_t>(frame_samples);
    }
    std::this_thread::sleep_for(std::chrono::milliseconds(500));

    int active_calls = g_mixed.calls.load(std::memory_order_relaxed);
    std::printf("external_playback: phase1 mixed-sink calls=%d max_energy=%lld pcm_sink=%d\n",
                active_calls, static_cast<long long>(g_mixed.max_energy.load()),
                g_pcm_sink_calls.load());
    // ~25 blocks expected at a 20ms cadence over 500ms; allow generous slack for scheduler/debug.
    CHECK(active_calls >= 10);
    CHECK(g_mixed.max_energy.load(std::memory_order_relaxed) > 0);  // real decoded audio in the mix
    CHECK(g_mixed.last_channels.load(std::memory_order_relaxed) == 2);
    CHECK(g_mixed.last_sample_rate.load(std::memory_order_relaxed) == 48000);
    CHECK(g_pcm_sink_calls.load(std::memory_order_relaxed) > 0);  // per-stream tap coexists

    // ── Phase 2: remove the stream; the mixed sink must KEEP firing (silent blocks). ─────
    engine.remove_stream(ssrc);
    int before = g_mixed.calls.load(std::memory_order_relaxed);
    std::this_thread::sleep_for(std::chrono::milliseconds(200));
    int after = g_mixed.calls.load(std::memory_order_relaxed);
    std::printf("external_playback: phase2 silent blocks delivered=%d\n", after - before);
    CHECK(after - before >= 5);  // continuous clock even with nothing to play

    engine.stop();  // joins the mixer-timer thread
    enc.destroy();

    if (g_failures == 0) {
        std::printf("external_playback: all checks passed\n");
        return 0;
    }
    std::printf("external_playback: %d failure(s)\n", g_failures);
    return 1;
}

#else

int main() {
    std::printf("external_playback: SKIP (VOICECAT_HAS_AUDIO or VOICECAT_HAS_OPUS not defined)\n");
    return 0;
}

#endif