voice-cat/tests/test_plc_cap.cpp

/*
 * test_plc_cap — verifies the PLC cap in AudioEngine::on_playback.
 *
 * After ~2s of pure packet-loss concealment (no real packets decoded), the mixer stops
 * calling opus_decode(nullptr,0,...) and emits digital silence instead. This bounds the
 * Opus comfort-noise hiss so a stale stream left in the mixer can never hiss forever —
 * defense-in-depth for the server's UserEvent::LEFT broadcast (the primary fix that
 * triggers remove_stream on disconnect). Also verifies that a fresh real packet resets
 * the PLC streak and audio resumes.
 *
 * White-box: drives AudioEngine::mix_for_test directly (no audio hardware needed).
 */
#include <cmath>
#include <cstdio>
#include <cstring>
#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)

static double rms(const int16_t* pcm, int n) {
    double sum = 0.0;
    for (int i = 0; i < n; ++i) sum += static_cast<double>(pcm[i]) * pcm[i];
    return std::sqrt(sum / n);
}

static int64_t abs_energy(const int16_t* pcm, int n) {
    int64_t e = 0;
    for (int i = 0; i < n; ++i) e += static_cast<int64_t>(std::abs(static_cast<int>(pcm[i])));
    return e;
}

int main() {
    voicecat::audio::AudioEngine engine;
    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 capture_cb — headless safe (devices may fail to init; ok)

    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

    // Encode a loud sine wave to seed the decoder's PLC state.
    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=*/0, /*stream_id=*/0);

    // Push one real frame to seed the decoder.
    voicecat::audio::JitterBuffer::Frame f;
    f.seq         = 0;
    f.timestamp   = 0;
    f.fec_present = false;
    f.payload.assign(opus_buf, opus_buf + opus_len);
    engine.push_recv_frame(ssrc, std::move(f));

    // mix_for_test period — 480 frames @ 48kHz = 10ms (typical WASAPI shared period).
    const uint32_t pb_frames = 480;
    const int out_n = static_cast<int>(pb_frames) * 2;  // stereo interleaved
    std::vector<int16_t> out(static_cast<size_t>(out_n), 0);

    // 1) Decode the real frame (first mix call) — seeds PLC state.
    engine.mix_for_test(out.data(), pb_frames);

    // 2) Drive ~50ms of pure PLC — should produce comfort noise (non-zero).
    double early_rms = 0.0;
    for (int i = 0; i < 5; ++i) {
        engine.mix_for_test(out.data(), pb_frames);
        early_rms = std::max(early_rms, rms(out.data(), out_n));
    }
    CHECK(early_rms > 1.0);  // PLC of a loud sine is audible, not digital silence

    // 3) Drive well past the 2s PLC cap (250 callbacks = 2.5s of output).
    //    After the cap, on_playback emits silence (memset 0) instead of PLC noise.
    for (int i = 0; i < 250; ++i) {
        engine.mix_for_test(out.data(), pb_frames);
    }

    // 4) The output must now be digital silence (all zeros), not comfort noise.
    //    Drain a couple more callbacks to flush any ring residue, then assert.
    int64_t energy = 0;
    for (int i = 0; i < 3; ++i) {
        engine.mix_for_test(out.data(), pb_frames);
        energy = std::max(energy, abs_energy(out.data(), out_n));
    }
    CHECK(energy == 0);  // capped PLC = silence

    // 5) Resumption: push a fresh real frame — PLC streak resets, audio returns. marker=true is
    //    what the real sender stamps on the first frame after a silence (talkspurt restart); it
    //    makes the playout clock reseed to this leading edge immediately (no prebuffer delay).
    voicecat::audio::JitterBuffer::Frame f2;
    f2.seq         = 1;
    f2.timestamp   = 200000;  // far ahead — playout-clock reseeds to it
    f2.fec_present = false;
    f2.marker      = true;
    f2.payload.assign(opus_buf, opus_buf + opus_len);
    engine.push_recv_frame(ssrc, std::move(f2));

    double resume_rms = 0.0;
    for (int i = 0; i < 5; ++i) {  // a few calls to flush silence residue + decode real
        engine.mix_for_test(out.data(), pb_frames);
        resume_rms = std::max(resume_rms, rms(out.data(), out_n));
    }
    CHECK(resume_rms > 1.0);  // real audio is back

    engine.remove_stream(ssrc);
    engine.stop();
    enc.destroy();

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

#else

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

#endif