refactor(audio): extract RendererBus (phase 2)

Moves the WebAudio→engine bus — ring, producer-side linear resampler,
prefill gate, fill clamp, metrics — verbatim into
src/audio/engine/RendererBus.h. AudioEngine keeps thin facades
(setRendererBus/pushRendererAudio/pullRendererBus/getRendererBusMetrics) so
the NodeAddon surface is unchanged. JUCE-free: pull() takes raw channel
pointers, which is what lets tests/engine_units drive the resampler
continuity, prime/underflow/clamp, and metrics cases without a device.

The control-thread readIndex write on disable (deep-read §4) is preserved
verbatim and marked; its flush-flag fix lands as the phase-8 commit.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

src/audio/AudioEngine.cpp

@@ -3039,126 +3039,28 @@ void AudioEngine::audioOutputCallback(const float* const* /*inputData*/,
 
 bool AudioEngine::pushRendererAudio(const float* interleavedLR, int frames, double sourceRate)
 {
-    if (!rendererBusEnabled.load(std::memory_order_acquire)) return false;
-    if (interleavedLR == nullptr || frames <= 0) return false;
-    const double deviceRate = getCurrentSampleRate();
-    if (deviceRate <= 0.0) return false;
-    if (!(sourceRate > 0.0)) sourceRate = deviceRate;
-
-    uint64_t w = rendererBusRing.beginWrite();
-
-    // Linear resample source→device rate on this (IPC) thread. `pos` is the
-    // fractional read position into the incoming chunk; index -1 refers to the
-    // carried last frame of the previous chunk so interpolation is continuous
-    // across pushes. Equal rates degenerate to step == 1.0 (still exact:
-    // pos stays integral, frac == 0).
-    const double step = sourceRate / deviceRate;
-    double pos = rendererBusSrcPos;
-    uint64_t written = 0;
-    while (true)
-    {
-        const double ip = std::floor(pos);
-        const int i0 = (int) ip;
-        if (i0 + 1 >= frames) break;                 // next chunk continues from here
-        const float frac = (float) (pos - ip);
-        const float l0 = (i0 < 0) ? rendererBusPrevL : interleavedLR[(size_t) i0 * 2];
-        const float r0 = (i0 < 0) ? rendererBusPrevR : interleavedLR[(size_t) i0 * 2 + 1];
-        const float l1 = interleavedLR[((size_t) i0 + 1) * 2];
-        const float r1 = interleavedLR[((size_t) i0 + 1) * 2 + 1];
-        rendererBusRing.stageFrame(w, l0 + (l1 - l0) * frac, r0 + (r1 - r0) * frac);
-        ++w;
-        ++written;
-        pos += step;
-    }
-    rendererBusSrcPos = pos - (double) frames;       // relative to the next chunk
-    rendererBusPrevL = interleavedLR[((size_t) frames - 1) * 2];
-    rendererBusPrevR = interleavedLR[((size_t) frames - 1) * 2 + 1];
-
-    // Publish. Overflow (producer lapping the consumer) is handled consumer-
-    // side with drop-oldest — same contract as the extra-input rings — so only
-    // the consumer ever moves readIndex.
-    rendererBusRing.publish(w);
-    rendererBusPushedFrames.fetch_add(written, std::memory_order_relaxed);
-    return true;
+    // Producer-side resample + publish live on RendererBus (engine/RendererBus.h).
+    return rendererBus.push(interleavedLR, frames, sourceRate, getCurrentSampleRate());
 }
 
 int AudioEngine::pullRendererBus(juce::AudioBuffer<float>& dest, int numSamples)
 {
-    if (!rendererBusEnabled.load(std::memory_order_acquire)) return 0;
     // Cold start before about-to-start sized the scratch — skip, never alloc
     // on the RT thread (same rule as the stream scratches).
     if (dest.getNumSamples() < numSamples || dest.getNumChannels() < 2) return 0;
-    const uint64_t w = rendererBusRing.writeIndex.load(std::memory_order_acquire);
-    uint64_t r = rendererBusRing.readIndex.load(std::memory_order_relaxed);
-    if (w - r > (uint64_t) kRendererBusFrames)
-    {
-        // Producer lapped us — drop-oldest to the newest full ring.
-        r = w - (uint64_t) kRendererBusFrames;
-        rendererBusOverflowCount.fetch_add(1, std::memory_order_relaxed);
-    }
-    uint64_t avail = w - r;
-
-    // Fill clamp (spike finding): steady-state drift is near zero, so a fill
-    // beyond kRendererBusMaxFill only ever means a renderer stall dumped a
-    // backlog. Trim to the prime target instead of playing the whole tail at
-    // ~85+ ms behind — a latency reset, not an audible gap.
-    if (avail > (uint64_t) kRendererBusMaxFillFrames)
-    {
-        r = w - (uint64_t) kRendererBusPrimeFrames;
-        avail = (uint64_t) kRendererBusPrimeFrames;
-        rendererBusOverflowCount.fetch_add(1, std::memory_order_relaxed);
-    }
-
-    // Prefill gate (spike finding): the warmup underflow burst is the mix
-    // starting before the ring has a cushion. Consume nothing until the
-    // producer has built ~10 ms; re-arm the same gate after a real underflow
-    // so stall recovery is one clean gap, not a ragged refill.
-    if (!rendererBusPrimed)
-    {
-        if (avail < (uint64_t) kRendererBusPrimeFrames)
-        {
-            rendererBusRing.commitRead(r);
-            return 0;
-        }
-        rendererBusPrimed = true;
-    }
-    if (avail < (uint64_t) numSamples)
-    {
-        // Underflow: emit silence for the whole block (partial blocks blip),
-        // drop what's buffered, and go back to priming.
-        rendererBusPrimed = false;
-        rendererBusUnderflowCount.fetch_add(1, std::memory_order_relaxed);
-        rendererBusRing.commitRead(w);
-        return 0;
-    }
-
-    const int pull = numSamples;
-    const float g = rendererBusGain.load(std::memory_order_relaxed);
-    float* dl = dest.getWritePointer(0);
-    float* dr = dest.getWritePointer(1);
-    for (int i = 0; i < pull; ++i)
-    {
-        float l, rr;
-        rendererBusRing.readFrame(r + (uint64_t) i, l, rr);
-        dl[i] = l * g;
-        dr[i] = rr * g;
-    }
-    rendererBusRing.commitRead(r + (uint64_t) pull);
-    rendererBusConsumedFrames.fetch_add((uint64_t) pull, std::memory_order_relaxed);
-    return pull;
+    return rendererBus.pull(dest.getWritePointer(0), dest.getWritePointer(1), numSamples);
 }
 
 AudioEngine::RendererBusMetrics AudioEngine::getRendererBusMetrics() const
 {
+    const auto bm = rendererBus.metrics();
     RendererBusMetrics m;
-    m.pushedFrames   = rendererBusPushedFrames.load(std::memory_order_relaxed);
-    m.consumedFrames = rendererBusConsumedFrames.load(std::memory_order_relaxed);
-    m.underflowCount = rendererBusUnderflowCount.load(std::memory_order_relaxed);
-    m.overflowCount  = rendererBusOverflowCount.load(std::memory_order_relaxed);
-    const uint64_t w = rendererBusRing.writeIndex.load(std::memory_order_acquire);
-    const uint64_t r = rendererBusRing.readIndex.load(std::memory_order_acquire);
-    m.fillFrames = (int) juce::jmin(w - r, (uint64_t) kRendererBusFrames);
-    m.capacityFrames = kRendererBusFrames;
-    m.enabled = rendererBusEnabled.load(std::memory_order_relaxed);
+    m.pushedFrames   = bm.pushedFrames;
+    m.consumedFrames = bm.consumedFrames;
+    m.underflowCount = bm.underflowCount;
+    m.overflowCount  = bm.overflowCount;
+    m.fillFrames     = bm.fillFrames;
+    m.capacityFrames = bm.capacityFrames;
+    m.enabled        = bm.enabled;
     return m;
 }

src/audio/AudioEngine.h

@@ -3,6 +3,7 @@
 #include "GainSanitize.h"
 #include "engine/PackedStereoRing.h"
 #include "engine/EngineState.h"
+#include "engine/RendererBus.h"
 #include "BackingLeveler.h"
 #include "signalsmith-stretch.h"
 #include <juce_audio_devices/juce_audio_devices.h>
@@ -270,20 +271,7 @@ public:
     // mixer path is silenced. SPSC: producer is the main-process IPC thread,
     // consumer is whichever output callback is live (duplex or split). Default
     // off → zero behaviour change.
-    void setRendererBus(bool enabled, float gain)
-    {
-        rendererBusGain.store(sanitizeStreamGain(gain), std::memory_order_relaxed);
-        const bool was = rendererBusEnabled.exchange(enabled, std::memory_order_acq_rel);
-        if (was && !enabled)
-        {
-            // Drop buffered audio on disable so a later re-enable starts fresh
-            // instead of playing a stale tail. Consumer tolerates the jump.
-            rendererBusRing.readIndex.store(
-                rendererBusRing.writeIndex.load(std::memory_order_acquire),
-                std::memory_order_release);
-            rendererBusPrimed.store(false, std::memory_order_relaxed);
-        }
-    }
+    void setRendererBus(bool enabled, float gain) { rendererBus.setEnabled(enabled, gain); }
     // Interleaved stereo frames at `sourceRate`; linear-resampled to the device
     // rate on the producer thread (fractional position + previous frame carried
     // across calls). Returns false when the bus is disabled or the engine is
@@ -563,35 +551,8 @@ private:
     static constexpr int kOutputRingFrames = 4096;
     slopsmith::PackedStereoRing<kOutputRingFrames> outputRing;
 
-    // ── Renderer-audio bus ring (see setRendererBus/pushRendererAudio) ───────
-    // Same packed-LR SPSC design as outputRing. Sized generously
-    // (~1.5 s @ 48 kHz — vs outputRing's 85 ms) because the producer is
-    // an IPC thread with scheduling jitter, not another audio callback; the
-    // consumer trims steady-state fill via the drift clamp in the mix step.
-    static constexpr int kRendererBusFrames = 65536;
-    static_assert((kRendererBusFrames & (kRendererBusFrames - 1)) == 0,
-                  "kRendererBusFrames must be a power of two for mask wraparound");
-    // Prefill gate: consume nothing until the producer has built this cushion
-    // (~10.7 ms @ 48 kHz); re-armed after every underflow so stall recovery is
-    // one clean gap. Fill clamp: fill beyond this (~85 ms) means a renderer
-    // stall dumped a backlog — trim to the prime target, don't play the tail.
-    static constexpr int kRendererBusPrimeFrames   = 512;
-    static constexpr int kRendererBusMaxFillFrames = 4096;
-    slopsmith::PackedStereoRing<kRendererBusFrames> rendererBusRing;
-    std::atomic<uint64_t> rendererBusPushedFrames{0};
-    std::atomic<uint64_t> rendererBusConsumedFrames{0};
-    std::atomic<uint64_t> rendererBusUnderflowCount{0};
-    std::atomic<uint64_t> rendererBusOverflowCount{0};
-    std::atomic<bool>  rendererBusEnabled{false};
-    std::atomic<float> rendererBusGain{1.0f};
-    // Consumer-side prefill-gate state. Only the live output callback touches
-    // it, but duplex/split hand-offs cross threads — atomic keeps that safe.
-    std::atomic<bool>  rendererBusPrimed{false};
-    // Producer-thread-only linear-resampler state (fractional read position
-    // into the incoming chunk + the previous chunk's last frame for
-    // interpolation continuity across pushes).
-    double rendererBusSrcPos = 0.0;
-    float  rendererBusPrevL = 0.0f, rendererBusPrevR = 0.0f;
+    // ── Renderer-audio bus (see engine/RendererBus.h — moved in TLC phase 2)
+    slopsmith::RendererBus rendererBus;
     // Shared consumer step for the duplex and split output paths: drain one
     // block from the renderer-bus ring into `dest` (stereo, bus gain applied,
     // dest cleared first). Returns numSamples on success, 0 when gated

src/audio/engine/RendererBus.h

@@ -0,0 +1,206 @@
+#pragma once
+
+// RendererBus — the WebAudio→engine audio bus (TLC plan phase 2 / §2.6).
+// Moved verbatim from AudioEngine (see git history for the original inline
+// comments' evolution): the renderer pushes its WebAudio master mix here over
+// IPC so song/stem audio stays audible when the output device is
+// exclusive-style (ASIO / WASAPI exclusive) and the OS mixer path is silent.
+//
+// SPSC: producer is the main-process IPC thread (push — includes the linear
+// resampler), consumer is whichever output callback is live (pull). Sized
+// generously (~1.5 s @ 48 kHz) because the producer has scheduling jitter;
+// the consumer trims steady-state fill via the fill clamp.
+//
+// JUCE-free on purpose: pull() takes raw channel pointers, so
+// tests/engine_units drives the resampler/prime/clamp logic without a device.
+
+#include "PackedStereoRing.h"
+#include "../GainSanitize.h"
+
+#include <atomic>
+#include <cmath>
+#include <cstdint>
+
+namespace slopsmith {
+
+class RendererBus
+{
+public:
+    static constexpr int kFrames = 65536;
+    // Prefill gate: consume nothing until the producer has built this cushion
+    // (~10.7 ms @ 48 kHz); re-armed after every underflow so stall recovery is
+    // one clean gap. Fill clamp: fill beyond kMaxFillFrames (~85 ms) means a
+    // renderer stall dumped a backlog — trim to the prime target, don't play
+    // the tail.
+    static constexpr int kPrimeFrames   = 512;
+    static constexpr int kMaxFillFrames = 4096;
+
+    void setEnabled(bool enabled, float gain)
+    {
+        busGain.store(sanitizeStreamGain(gain), std::memory_order_relaxed);
+        const bool was = busEnabled.exchange(enabled, std::memory_order_acq_rel);
+        if (was && !enabled)
+        {
+            // Drop buffered audio on disable so a later re-enable starts fresh
+            // instead of playing a stale tail. Consumer tolerates the jump.
+            // KNOWN ISSUE (deep-read §4, fixed in the follow-up commit): this
+            // writes readIndex from the control thread while pull() is the
+            // designated consumer-side writer.
+            ring.readIndex.store(ring.writeIndex.load(std::memory_order_acquire),
+                                 std::memory_order_release);
+            primed.store(false, std::memory_order_relaxed);
+        }
+    }
+    bool isEnabled() const { return busEnabled.load(std::memory_order_relaxed); }
+
+    // Interleaved stereo frames at `sourceRate`, linear-resampled to
+    // `deviceRate` on the producer thread (fractional position + previous
+    // frame carried across calls). Returns false when the bus is disabled or
+    // the rates are unusable. Drop-oldest on overflow, counted consumer-side.
+    bool push(const float* interleavedLR, int frames, double sourceRate, double deviceRate)
+    {
+        if (!busEnabled.load(std::memory_order_acquire)) return false;
+        if (interleavedLR == nullptr || frames <= 0) return false;
+        if (deviceRate <= 0.0) return false;
+        if (!(sourceRate > 0.0)) sourceRate = deviceRate;
+
+        uint64_t w = ring.beginWrite();
+
+        // Linear resample source→device rate on this (IPC) thread. `pos` is
+        // the fractional read position into the incoming chunk; index -1
+        // refers to the carried last frame of the previous chunk so
+        // interpolation is continuous across pushes. Equal rates degenerate
+        // to step == 1.0 (still exact: pos stays integral, frac == 0).
+        const double step = sourceRate / deviceRate;
+        double pos = srcPos;
+        uint64_t written = 0;
+        while (true)
+        {
+            const double ip = std::floor(pos);
+            const int i0 = (int) ip;
+            if (i0 + 1 >= frames) break;             // next chunk continues from here
+            const float frac = (float) (pos - ip);
+            const float l0 = (i0 < 0) ? prevL : interleavedLR[(size_t) i0 * 2];
+            const float r0 = (i0 < 0) ? prevR : interleavedLR[(size_t) i0 * 2 + 1];
+            const float l1 = interleavedLR[((size_t) i0 + 1) * 2];
+            const float r1 = interleavedLR[((size_t) i0 + 1) * 2 + 1];
+            ring.stageFrame(w, l0 + (l1 - l0) * frac, r0 + (r1 - r0) * frac);
+            ++w;
+            ++written;
+            pos += step;
+        }
+        srcPos = pos - (double) frames;              // relative to the next chunk
+        prevL = interleavedLR[((size_t) frames - 1) * 2];
+        prevR = interleavedLR[((size_t) frames - 1) * 2 + 1];
+
+        // Publish. Overflow (producer lapping the consumer) is handled
+        // consumer-side with drop-oldest — only the consumer moves readIndex.
+        ring.publish(w);
+        pushedFrames.fetch_add(written, std::memory_order_relaxed);
+        return true;
+    }
+
+    // Drain one block into dl/dr (bus gain applied). Returns numSamples on
+    // success, 0 when gated (disabled, priming, underflow). Single consumer —
+    // call exactly once per output block.
+    int pull(float* dl, float* dr, int numSamples)
+    {
+        if (!busEnabled.load(std::memory_order_acquire)) return 0;
+        const uint64_t w = ring.writeIndex.load(std::memory_order_acquire);
+        uint64_t r = ring.readIndex.load(std::memory_order_relaxed);
+        if (w - r > (uint64_t) kFrames)
+        {
+            // Producer lapped us — drop-oldest to the newest full ring.
+            r = w - (uint64_t) kFrames;
+            overflowCount.fetch_add(1, std::memory_order_relaxed);
+        }
+        uint64_t avail = w - r;
+
+        // Fill clamp (spike finding): steady-state drift is near zero, so a
+        // fill beyond kMaxFillFrames only ever means a renderer stall dumped a
+        // backlog. Trim to the prime target instead of playing the whole tail
+        // at ~85+ ms behind — a latency reset, not an audible gap.
+        if (avail > (uint64_t) kMaxFillFrames)
+        {
+            r = w - (uint64_t) kPrimeFrames;
+            avail = (uint64_t) kPrimeFrames;
+            overflowCount.fetch_add(1, std::memory_order_relaxed);
+        }
+
+        // Prefill gate (spike finding): the warmup underflow burst is the mix
+        // starting before the ring has a cushion. Consume nothing until the
+        // producer has built ~10 ms; re-arm the same gate after a real
+        // underflow so stall recovery is one clean gap, not a ragged refill.
+        if (!primed)
+        {
+            if (avail < (uint64_t) kPrimeFrames)
+            {
+                ring.commitRead(r);
+                return 0;
+            }
+            primed = true;
+        }
+        if (avail < (uint64_t) numSamples)
+        {
+            // Underflow: emit silence for the whole block (partial blocks
+            // blip), drop what's buffered, and go back to priming.
+            primed = false;
+            underflowCount.fetch_add(1, std::memory_order_relaxed);
+            ring.commitRead(w);
+            return 0;
+        }
+
+        const float g = busGain.load(std::memory_order_relaxed);
+        for (int i = 0; i < numSamples; ++i)
+        {
+            float l, rr;
+            ring.readFrame(r + (uint64_t) i, l, rr);
+            dl[i] = l * g;
+            dr[i] = rr * g;
+        }
+        ring.commitRead(r + (uint64_t) numSamples);
+        consumedFrames.fetch_add((uint64_t) numSamples, std::memory_order_relaxed);
+        return numSamples;
+    }
+
+    struct Metrics
+    {
+        uint64_t pushedFrames = 0, consumedFrames = 0, underflowCount = 0, overflowCount = 0;
+        int fillFrames = 0, capacityFrames = 0;
+        bool enabled = false;
+    };
+    Metrics metrics() const
+    {
+        Metrics m;
+        m.pushedFrames   = pushedFrames.load(std::memory_order_relaxed);
+        m.consumedFrames = consumedFrames.load(std::memory_order_relaxed);
+        m.underflowCount = underflowCount.load(std::memory_order_relaxed);
+        m.overflowCount  = overflowCount.load(std::memory_order_relaxed);
+        const uint64_t w = ring.writeIndex.load(std::memory_order_acquire);
+        const uint64_t r = ring.readIndex.load(std::memory_order_acquire);
+        const uint64_t fill = w - r;
+        m.fillFrames = (int) (fill < (uint64_t) kFrames ? fill : (uint64_t) kFrames);
+        m.capacityFrames = kFrames;
+        m.enabled = busEnabled.load(std::memory_order_relaxed);
+        return m;
+    }
+
+private:
+    PackedStereoRing<kFrames> ring;
+    std::atomic<uint64_t> pushedFrames{0};
+    std::atomic<uint64_t> consumedFrames{0};
+    std::atomic<uint64_t> underflowCount{0};
+    std::atomic<uint64_t> overflowCount{0};
+    std::atomic<bool>  busEnabled{false};
+    std::atomic<float> busGain{1.0f};
+    // Consumer-side prefill-gate state. Only the live output callback touches
+    // it, but duplex/split hand-offs cross threads — atomic keeps that safe.
+    std::atomic<bool> primed{false};
+    // Producer-thread-only linear-resampler state (fractional read position
+    // into the incoming chunk + the previous chunk's last frame for
+    // interpolation continuity across pushes).
+    double srcPos = 0.0;
+    float  prevL = 0.0f, prevR = 0.0f;
+};
+
+} // namespace slopsmith

tests/engine_units/CMakeLists.txt

@@ -16,3 +16,7 @@ add_test(NAME packed_stereo_ring COMMAND packed_stereo_ring_test)
 add_executable(engine_state_test engine_state_test.cpp)
 target_compile_features(engine_state_test PRIVATE cxx_std_17)
 add_test(NAME engine_state COMMAND engine_state_test)
+
+add_executable(renderer_bus_test renderer_bus_test.cpp)
+target_compile_features(renderer_bus_test PRIVATE cxx_std_20)
+add_test(NAME renderer_bus COMMAND renderer_bus_test)

tests/engine_units/renderer_bus_test.cpp

@@ -0,0 +1,155 @@
+// Phase 2 unit tests for RendererBus (docs/audio-engine-tlc.md §5):
+// resampler continuity across pushes, equal-rate bit-exactness, the prime
+// gate, underflow → silence + re-prime, fill clamp, and metrics arithmetic.
+// The flush-on-disable test flips once the phase-8 flush-flag fix lands.
+
+#include "../../src/audio/engine/RendererBus.h"
+
+#include <cassert>
+#include <cmath>
+#include <cstdio>
+#include <vector>
+
+using slopsmith::RendererBus;
+
+static std::vector<float> rampChunk(int frames, float start, float step)
+{
+    std::vector<float> v((size_t) frames * 2);
+    for (int i = 0; i < frames; ++i)
+    {
+        v[(size_t) i * 2]     = start + step * (float) i;
+        v[(size_t) i * 2 + 1] = -(start + step * (float) i);
+    }
+    return v;
+}
+
+// Equal rates degenerate to step == 1.0 — frames must come out bit-exact
+// (minus the one-frame interpolation carry at each chunk boundary).
+static void testEqualRateBitExact()
+{
+    RendererBus bus;
+    bus.setEnabled(true, 1.0f);
+    const auto c1 = rampChunk(512, 0.0f, 1.0f);
+    const auto c2 = rampChunk(512, 512.0f, 1.0f);
+    assert(bus.push(c1.data(), 512, 48000.0, 48000.0));
+    assert(bus.push(c2.data(), 512, 48000.0, 48000.0));
+
+    std::vector<float> dl(512), dr(512);
+    assert(bus.pull(dl.data(), dr.data(), 512) == 512);
+    for (int i = 0; i < 512; ++i)
+    {
+        // First chunk's frame 0 is consumed as interpolation carry (pos
+        // starts at 0 with prev=0 carry → exact frame i lands at output i).
+        assert(dl[(size_t) i] == (float) i && dr[(size_t) i] == -(float) i);
+    }
+}
+
+// Downsampling 2:1 across a chunk seam must be continuous: the interpolated
+// ramp has no discontinuity where one push ends and the next begins.
+static void testResampleContinuityAcrossPushes()
+{
+    RendererBus bus;
+    bus.setEnabled(true, 1.0f);
+    const double src = 96000.0, dev = 48000.0;
+    // Two chunks big enough that the 2:1 output (~1023 frames) clears the
+    // prime gate; the seam sits at output frame ~512.
+    const auto c1 = rampChunk(1024, 0.0f, 1.0f);
+    const auto c2 = rampChunk(1024, 1024.0f, 1.0f);
+    bus.push(c1.data(), 1024, src, dev);
+    bus.push(c2.data(), 1024, src, dev);
+
+    std::vector<float> dl(768), dr(768);
+    assert(bus.pull(dl.data(), dr.data(), 768) == 768);
+    for (int i = 1; i < 768; ++i)
+    {
+        const float d = dl[(size_t) i] - dl[(size_t) i - 1];
+        // A linear ramp resampled 2:1 must step by ~2 everywhere, including
+        // across the seam at output frame ~128.
+        assert(std::fabs(d - 2.0f) < 1e-3f && "discontinuity at chunk seam");
+    }
+}
+
+// Prime gate: nothing comes out until ~kPrimeFrames are buffered.
+static void testPrimeGate()
+{
+    RendererBus bus;
+    bus.setEnabled(true, 1.0f);
+    std::vector<float> dl(64), dr(64);
+    const auto tiny = rampChunk(RendererBus::kPrimeFrames / 2, 1.0f, 0.0f);
+    bus.push(tiny.data(), RendererBus::kPrimeFrames / 2, 48000.0, 48000.0);
+    assert(bus.pull(dl.data(), dr.data(), 64) == 0 && "must gate until primed");
+    bus.push(tiny.data(), RendererBus::kPrimeFrames / 2, 48000.0, 48000.0);
+    // Cushion built (minus the 1-frame carry per push) — next pull flows.
+    bus.push(tiny.data(), RendererBus::kPrimeFrames / 2, 48000.0, 48000.0);
+    assert(bus.pull(dl.data(), dr.data(), 64) == 64);
+}
+
+// Underflow: whole-block silence, buffered tail dropped, back to priming.
+static void testUnderflowReprimes()
+{
+    RendererBus bus;
+    bus.setEnabled(true, 1.0f);
+    const auto chunk = rampChunk(RendererBus::kPrimeFrames + 64, 1.0f, 0.0f);
+    bus.push(chunk.data(), RendererBus::kPrimeFrames + 64, 48000.0, 48000.0);
+    std::vector<float> dl(512), dr(512);
+    assert(bus.pull(dl.data(), dr.data(), 512) == 512);
+    // Ring now nearly empty → this pull underflows.
+    assert(bus.pull(dl.data(), dr.data(), 512) == 0);
+    assert(bus.metrics().underflowCount == 1);
+    // And the gate re-armed: a sub-prime refill still gates.
+    const auto tiny = rampChunk(64, 1.0f, 0.0f);
+    bus.push(tiny.data(), 64, 48000.0, 48000.0);
+    assert(bus.pull(dl.data(), dr.data(), 32) == 0 && "must re-prime after underflow");
+}
+
+// Fill clamp: a dumped backlog beyond kMaxFillFrames is trimmed to the prime
+// target instead of being played ~85 ms late.
+static void testFillClampTrimsBacklog()
+{
+    RendererBus bus;
+    bus.setEnabled(true, 1.0f);
+    const int backlog = RendererBus::kMaxFillFrames + 2048;
+    const auto chunk = rampChunk(backlog + 1, 1.0f, 0.0f);
+    bus.push(chunk.data(), backlog + 1, 48000.0, 48000.0);
+    std::vector<float> dl(256), dr(256);
+    assert(bus.pull(dl.data(), dr.data(), 256) == 256);
+    const auto m = bus.metrics();
+    assert(m.overflowCount == 1 && "fill clamp must count as overflow");
+    assert(m.fillFrames <= RendererBus::kPrimeFrames && "backlog must be trimmed to prime target");
+}
+
+// Disabled bus: push and pull are inert.
+static void testDisabledIsInert()
+{
+    RendererBus bus;
+    const auto chunk = rampChunk(128, 1.0f, 0.0f);
+    assert(!bus.push(chunk.data(), 128, 48000.0, 48000.0));
+    std::vector<float> dl(64), dr(64);
+    assert(bus.pull(dl.data(), dr.data(), 64) == 0);
+    assert(!bus.metrics().enabled);
+}
+
+// Gain is applied consumer-side and sanitized (0..8, non-finite → 0).
+static void testGainApplied()
+{
+    RendererBus bus;
+    bus.setEnabled(true, 2.0f);
+    const auto chunk = rampChunk(RendererBus::kPrimeFrames + 65, 1.0f, 0.0f);
+    bus.push(chunk.data(), RendererBus::kPrimeFrames + 65, 48000.0, 48000.0);
+    std::vector<float> dl(64), dr(64);
+    assert(bus.pull(dl.data(), dr.data(), 64) == 64);
+    assert(dl[0] == 2.0f && dr[0] == -2.0f);
+}
+
+int main()
+{
+    testEqualRateBitExact();
+    testResampleContinuityAcrossPushes();
+    testPrimeGate();
+    testUnderflowReprimes();
+    testFillClampTrimsBacklog();
+    testDisabledIsInert();
+    testGainApplied();
+    std::puts("renderer_bus: all cases passed");
+    return 0;
+}