3 files changed, 90 insertions, 25 deletions

diff --git a/src/audio/audio.cc b/src/audio/audio.cc
index 2d667bc..2f485a6 100644
--- a/src/audio/audio.cc
+++ b/src/audio/audio.cc
@@ -125,44 +125,73 @@ void audio_render_ahead(float music_time, float dt) {
       break;
     }
 
-    // Determine how much we can actually render
-    // Render the smaller of: desired chunk size OR available space
-    const int actual_samples =
-        (available_space < chunk_samples) ? available_space : chunk_samples;
-    const int actual_frames = actual_samples / RING_BUFFER_CHANNELS;
+    // Get direct write pointer from ring buffer
+    int available_for_write = 0;
+    float* write_ptr = g_ring_buffer.get_write_region(&available_for_write);
 
-    // Allocate temporary buffer (stereo)
-    float* temp_buffer = new float[actual_samples];
+    if (available_for_write == 0) {
+      break; // Buffer full, wait for consumption
+    }
 
-    // Render audio from synth (advances synth state incrementally)
-    synth_render(temp_buffer, actual_frames);
+    // Clamp to desired chunk size
+    const int actual_samples = (available_for_write < chunk_samples)
+                                   ? available_for_write
+                                   : chunk_samples;
+    const int actual_frames = actual_samples / RING_BUFFER_CHANNELS;
 
-    // Write to ring buffer
-    const int written = g_ring_buffer.write(temp_buffer, actual_samples);
+    // Render directly to ring buffer (NO COPY, NO ALLOCATION)
+    synth_render(write_ptr, actual_frames);
 
-    // If partial write, save remaining samples to pending buffer
-    if (written < actual_samples) {
-      const int remaining = actual_samples - written;
-      if (remaining <= MAX_PENDING_SAMPLES) {
-        for (int i = 0; i < remaining; ++i) {
-          g_pending_buffer[i] = temp_buffer[written + i];
-        }
-        g_pending_samples = remaining;
-      }
+    // Apply clipping in-place (Phase 2: ensure samples stay in [-1.0, 1.0])
+    for (int i = 0; i < actual_samples; ++i) {
+      if (write_ptr[i] > 1.0f)
+        write_ptr[i] = 1.0f;
+      if (write_ptr[i] < -1.0f)
+        write_ptr[i] = -1.0f;
     }
 
-    // Notify backend of frames rendered (count frames sent to synth)
+    // Commit written data atomically
+    g_ring_buffer.commit_write(actual_samples);
+
+    // Notify backend of frames rendered
 #if !defined(STRIP_ALL)
     if (g_audio_backend != nullptr) {
       g_audio_backend->on_frames_rendered(actual_frames);
     }
 #endif
 
-    delete[] temp_buffer;
+    // Handle wrap-around: if we wanted more samples but ring wrapped,
+    // get a second region and render remaining chunk
+    if (actual_samples < chunk_samples) {
+      int second_avail = 0;
+      float* second_ptr = g_ring_buffer.get_write_region(&second_avail);
+      if (second_avail > 0) {
+        const int remaining_samples = chunk_samples - actual_samples;
+        const int second_samples = (second_avail < remaining_samples)
+                                       ? second_avail
+                                       : remaining_samples;
+        const int second_frames = second_samples / RING_BUFFER_CHANNELS;
 
-    // If we couldn't write everything, stop and retry next frame
-    if (written < actual_samples)
-      break;
+        synth_render(second_ptr, second_frames);
+
+        // Apply clipping to wrap-around region
+        for (int i = 0; i < second_samples; ++i) {
+          if (second_ptr[i] > 1.0f)
+            second_ptr[i] = 1.0f;
+          if (second_ptr[i] < -1.0f)
+            second_ptr[i] = -1.0f;
+        }
+
+        g_ring_buffer.commit_write(second_samples);
+
+        // Notify backend of additional frames
+#if !defined(STRIP_ALL)
+        if (g_audio_backend != nullptr) {
+          g_audio_backend->on_frames_rendered(second_frames);
+        }
+#endif
+      }
+    }
   }
 }
 
diff --git a/src/audio/ring_buffer.cc b/src/audio/ring_buffer.cc
index 7cedb56..30566c9 100644
--- a/src/audio/ring_buffer.cc
+++ b/src/audio/ring_buffer.cc
@@ -152,3 +152,29 @@ void AudioRingBuffer::clear() {
   // Note: Don't reset total_read_ - it tracks absolute playback time
   memset(buffer_, 0, sizeof(buffer_));
 }
+
+float* AudioRingBuffer::get_write_region(int* out_available_samples) {
+  const int write = write_pos_.load(std::memory_order_acquire);
+  const int avail = available_write();
+
+  // Return linear region (less than available if wraps around)
+  const int space_to_end = capacity_ - write;
+  *out_available_samples = std::min(avail, space_to_end);
+
+  return &buffer_[write];
+}
+
+void AudioRingBuffer::commit_write(int num_samples) {
+  const int write = write_pos_.load(std::memory_order_acquire);
+
+  // BOUNDS CHECK
+  FATAL_CHECK(write < 0 || write + num_samples > capacity_,
+              "commit_write out of bounds: write=%d, num_samples=%d, "
+              "capacity=%d\n",
+              write, num_samples, capacity_);
+
+  // Advance write position atomically
+  write_pos_.store((write + num_samples) % capacity_,
+                   std::memory_order_release);
+  total_written_.fetch_add(num_samples, std::memory_order_release);
+}
diff --git a/src/audio/ring_buffer.h b/src/audio/ring_buffer.h
index 80b375f..524cb29 100644
--- a/src/audio/ring_buffer.h
+++ b/src/audio/ring_buffer.h
@@ -50,6 +50,16 @@ class AudioRingBuffer {
   // Clear buffer (for seeking)
   void clear();
 
+  // Two-phase write API (for zero-copy direct writes)
+  // Get direct pointer to writable region in ring buffer
+  // Returns pointer to linear region and sets out_available_samples
+  // NOTE: May return less than total available space if wrap-around occurs
+  float* get_write_region(int* out_available_samples);
+
+  // Commit written samples (advances write_pos atomically)
+  // FATAL ERROR if num_samples exceeds region from get_write_region()
+  void commit_write(int num_samples);
+
  private:
   float buffer_[RING_BUFFER_CAPACITY_SAMPLES];
   int capacity_; // Total capacity in samples