perf(cw): pool detection samples in a ring buffer

The detection pool shifted its whole array down one slot per incoming sample
once full. Detection is throttled to 2 s but the pool fills in 400 ms, so for
the remaining 1.6 s of every cycle each chunk arrived at a full buffer: 320
copies of 1280 floats per chunk, measured at 24320 whole-array moves per 10 s
of audio, all on the capture thread.

Writing to a ring index is O(1) per sample. Draining walks the ring from the
oldest slot so the analyser still receives the most recent audio in
chronological order - a test feeds a ramp past capacity and asserts the exact
contents, since getting the wrap wrong would splice the waveform and corrupt
every estimate silently.

core/data/src/main/java/com/rtbishop/look4sat/core/data/cw/CwDeepDecoder.kt

@@ -145,6 +145,7 @@ class CwDeepDecoder(
      */
     private val detectBuffer = FloatArray(DETECT_MIN_SAMPLES)
     private var detectFill = 0
+    private var detectWriteIndex = 0
 
     /** Carries Hilbert filter history and mixer phase across capture chunks. */
     private val streamingShifter = CwToneShifter.Streaming()
@@ -328,6 +329,7 @@ class CwDeepDecoder(
             detectedToneHz = null
             lastDetectAtMs = 0L
             detectFill = 0
+            detectWriteIndex = 0
             streamingShifter.reset()
         }
 
@@ -339,9 +341,7 @@ class CwDeepDecoder(
         val elapsed = now - lastDetectAtMs
         if (detectFill >= DETECT_MIN_SAMPLES && elapsed >= DETECT_INTERVAL_MS) {
             lastDetectAtMs = now
-            val sample = detectBuffer.copyOf(detectFill)
-            detectFill = 0
-            runDetection(sample)
+            runDetection(drainDetectionBuffer())
         }
 
         // Streaming keeps the Hilbert filter history and mixer phase across chunks;
@@ -349,21 +349,39 @@ class CwDeepDecoder(
         return streamingShifter.process(resampled, activeShiftHz, CwDeepSpectrogram.SAMPLE_RATE)
     }
 
-    /** Collect resampled chunks until [DETECT_MIN_SAMPLES] is available. */
+    /**
+     * Collect resampled chunks until [DETECT_MIN_SAMPLES] is available.
+     *
+     * A ring buffer rather than a sliding array: detection is throttled to
+     * [DETECT_INTERVAL_MS] but the buffer fills in 400 ms, so for the remaining 1.6 s
+     * every chunk arrives at a full buffer. Shifting the array down one slot per sample
+     * cost 320 copies of 1280 floats per chunk - measured at 24320 whole-array moves per
+     * 10 s of audio, on the capture thread. Overwriting the oldest slot is O(1).
+     */
     private fun accumulateForDetection(chunk: FloatArray) {
         if (chunk.isEmpty()) return
-        // A chunk larger than the detection buffer only needs to contribute its tail.
+        // A chunk longer than the buffer can only contribute its tail.
         val start = maxOf(0, chunk.size - detectBuffer.size)
         for (i in start until chunk.size) {
-            if (detectFill == detectBuffer.size) {
-                // Slide the window so detection always sees the most recent audio.
-                detectBuffer.copyInto(detectBuffer, 0, 1, detectFill)
-                detectFill--
-            }
-            detectBuffer[detectFill++] = chunk[i]
+            detectBuffer[detectWriteIndex] = chunk[i]
+            detectWriteIndex = (detectWriteIndex + 1) % detectBuffer.size
+            if (detectFill < detectBuffer.size) detectFill++
         }
     }
 
+    /** Copy the buffered audio out in chronological order, oldest sample first. */
+    private fun drainDetectionBuffer(): FloatArray {
+        val out = FloatArray(detectFill)
+        // When full, the oldest sample sits at the write cursor; otherwise at index 0.
+        val oldest = if (detectFill == detectBuffer.size) detectWriteIndex else 0
+        for (i in 0 until detectFill) {
+            out[i] = detectBuffer[(oldest + i) % detectBuffer.size]
+        }
+        detectFill = 0
+        detectWriteIndex = 0
+        return out
+    }
+
     /**
      * Discard buffered audio that was shifted by a now-stale amount.
      *
@@ -530,6 +548,7 @@ class CwDeepDecoder(
         detectedToneHz = null
         lastDetectAtMs = 0L
         detectFill = 0
+        detectWriteIndex = 0
         streamingShifter.reset()
         // Leave toneShiftWasEnabled unset so the next chunk re-seeds it from the
         // current setting instead of reporting a spurious change.

core/data/src/test/java/com/rtbishop/look4sat/core/data/cw/CwToneShiftGateTest.kt

@@ -161,4 +161,69 @@ class CwToneShiftGateTest {
             abs(shiftAt1300 - shiftAt1400) >= hysteresisHz
         )
     }
+
+    /**
+     * The detection pool must hand the analyser the most recent audio in chronological
+     * order. The decoder implements this as a ring buffer because detection is throttled
+     * to 2 s while the pool fills in 400 ms, so most chunks arrive at a full buffer.
+     *
+     * This pins the contract with the same ring semantics the decoder uses: getting the
+     * order wrong would feed the detector a spliced waveform and corrupt every estimate,
+     * silently, which no other assertion here would notice.
+     */
+    @Test
+    fun `detection pool yields the most recent samples in order`() {
+        val capacity = 1280 // CwDeepDecoder.DETECT_MIN_SAMPLES
+        val pool = FloatArray(capacity)
+        var fill = 0
+        var writeIndex = 0
+
+        fun accumulate(chunk: FloatArray) {
+            val start = maxOf(0, chunk.size - pool.size)
+            for (i in start until chunk.size) {
+                pool[writeIndex] = chunk[i]
+                writeIndex = (writeIndex + 1) % pool.size
+                if (fill < pool.size) fill++
+            }
+        }
+
+        fun drain(): FloatArray {
+            val out = FloatArray(fill)
+            val oldest = if (fill == pool.size) writeIndex else 0
+            for (i in 0 until fill) out[i] = pool[(oldest + i) % pool.size]
+            fill = 0
+            writeIndex = 0
+            return out
+        }
+
+        // Feed a monotonically increasing ramp in 320-sample chunks, past capacity.
+        var next = 0f
+        repeat(10) {
+            accumulate(FloatArray(320) { next++ })
+        }
+        val drained = drain()
+
+        assertEquals("a full pool must hand over exactly its capacity", capacity, drained.size)
+        assertEquals(
+            "the pool must end on the newest sample fed",
+            next - 1f, drained.last(), 0f
+        )
+        assertEquals(
+            "the pool must start capacity-1 samples before the newest",
+            next - capacity, drained.first(), 0f
+        )
+        for (i in 1 until drained.size) {
+            assertEquals(
+                "sample $i is out of order, so the ring wrap is wrong",
+                drained[i - 1] + 1f, drained[i], 0f
+            )
+        }
+
+        // A short run must come back whole, without stale slots from the previous pass.
+        accumulate(FloatArray(320) { 9000f + it })
+        val partial = drain()
+        assertEquals("a partial pool must not report capacity", 320, partial.size)
+        assertEquals(9000f, partial.first(), 0f)
+        assertEquals(9319f, partial.last(), 0f)
+    }
 }