From 32d96cadcc7c2e6f163dbac7154483d39bed64e7 Mon Sep 17 00:00:00 2001
From: Lucas Winther <lucwin@ece.au.dk>
Date: Fri, 30 Oct 2026 02:52:50 +0100
Subject: [PATCH] fix: dataset layout data/<tier>/<seed>, mix tests, cli
 hardening

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
---
 src/bench/cli.ts            |  7 +++++--
 src/bench/dataset.ts        |  6 +++---
 tests/audio/mix.test.ts     | 25 +++++++++++++++++++++++++
 tests/bench/dataset.test.ts | 20 ++++++++++++++++++++
 4 files changed, 53 insertions(+), 5 deletions(-)
 create mode 100644 tests/audio/mix.test.ts

diff --git a/src/bench/cli.ts b/src/bench/cli.ts
index 826d013..7b55adf 100644
--- a/src/bench/cli.ts
+++ b/src/bench/cli.ts
@@ -15,7 +15,10 @@ function parseSeeds(s: string): number[] {
 
 function arg(args: string[], name: string, def: string): string {
   const i = args.indexOf(`--${name}`);
-  return i >= 0 && args[i + 1] ? args[i + 1]! : def;
+  if (i < 0) return def;
+  const v = args[i + 1];
+  if (v === undefined || v.startsWith("--")) throw new Error(`missing value for --${name}`);
+  return v;
 }
 
 async function main() {
@@ -23,7 +26,7 @@ async function main() {
   switch (cmd) {
     case "gen": {
       const tiers = arg(rest, "tiers", "t1a,t1b,t1c,t1d").split(",") as TierId[];
-      for (const t of tiers) if (!(t in TIERS)) throw new Error(`unknown tier: ${t}`);
+      for (const t of tiers) if (!Object.hasOwn(TIERS, t)) throw new Error(`unknown tier: ${t}`);
       const seeds = parseSeeds(arg(rest, "seeds", "1-5"));
       const root = arg(rest, "root", "data");
       for (const t of tiers) for (const s of seeds) {
diff --git a/src/bench/dataset.ts b/src/bench/dataset.ts
index 4fe6244..9f1579d 100644
--- a/src/bench/dataset.ts
+++ b/src/bench/dataset.ts
@@ -10,16 +10,16 @@ import { mixStemsScaled } from "../audio/mix.ts";
 import { readWav, writeWav } from "../audio/wav.ts";
 import { encodeMp3 } from "../audio/mp3.ts";
 
-const SF2_PATH = "node_modules/@coderline/alphatab/dist/soundfont/sonivox.sf2";
+const SF2_PATH = join(import.meta.dir, "../../node_modules/@coderline/alphatab/dist/soundfont/sonivox.sf2");
 const SR = 44100;
 
 /**
- * Build one song into `<root>/<tier>-<seed>/`. Idempotent: skipped when mix.mp3 exists and song.json matches.
+ * Build one song into `<root>/<tier>/<seed>/`. Idempotent: skipped when mix.mp3 exists and song.json matches.
  * stems/<track>.wav are exactly each track's contribution to mix.wav (post-fx, post-pan, gain, normalisation),
  * so the stems sum to the mix up to PCM16 rounding.
  */
 export async function buildSong(tier: TierId, seed: number, root = "data"): Promise<string> {
-  const dir = join(root, `${tier}-${seed}`);
+  const dir = join(root, tier, String(seed));
   const song = generateSong(tier, seed);
   const songJson = JSON.stringify(song, null, 1);
   const jsonFile = Bun.file(join(dir, "song.json"));
diff --git a/tests/audio/mix.test.ts b/tests/audio/mix.test.ts
new file mode 100644
index 0000000..8d5c889
--- /dev/null
+++ b/tests/audio/mix.test.ts
@@ -0,0 +1,25 @@
+import { test, expect } from "bun:test";
+import { mixStemsScaled } from "../../src/audio/mix.ts";
+import type { Audio } from "../../src/core/types.ts";
+
+test("mixStemsScaled: scaled stems sum to mix; scale is the normalisation factor", () => {
+  const mk = (n: number, amp: number): Audio => {
+    const x = Float32Array.from({ length: n }, (_, i) => amp * Math.sin(i / 7));
+    return { sampleRate: 44100, channels: [x, x.slice()] };
+  };
+  const a = mk(1000, 0.9), b = mk(700, 0.8);
+  const { mix, scaled, scale } = mixStemsScaled([{ audio: a, gainDb: 0 }, { audio: b, gainDb: -3 }]);
+  // unnormalised peak
+  const gb = Math.pow(10, -3 / 20);
+  let peak = 0;
+  for (let i = 0; i < 1000; i++) peak = Math.max(peak, Math.abs(a.channels[0]![i]! + (i < 700 ? b.channels[0]![i]! * gb : 0)));
+  expect(peak).toBeGreaterThan(1);
+  expect(Math.abs(scale - Math.pow(10, -1 / 20) / peak)).toBeLessThan(1e-6);
+  expect(scaled.length).toBe(2);
+  let maxDiff = 0;
+  for (let c = 0; c < 2; c++) for (let i = 0; i < 1000; i++) {
+    const s = scaled[0]!.channels[c]![i]! + scaled[1]!.channels[c]![i]!;
+    maxDiff = Math.max(maxDiff, Math.abs(s - mix.channels[c]![i]!));
+  }
+  expect(maxDiff).toBeLessThan(1e-6);
+});
diff --git a/tests/bench/dataset.test.ts b/tests/bench/dataset.test.ts
index 4f388c1..ff76f8c 100644
--- a/tests/bench/dataset.test.ts
+++ b/tests/bench/dataset.test.ts
@@ -35,3 +35,23 @@ test("buildSong writes all artefacts; loadSongDir reads them; stems sum to mix;
     await rm(root, { recursive: true, force: true });
   }
 }, 120_000);
+
+test("multi-track t1b: stems on disk sum to mix.wav", async () => {
+  const root = await mkdtemp(join(tmpdir(), "stsheets-ds-"));
+  try {
+    const dir = await buildSong("t1b", 1, root);
+    expect(dir).toBe(join(root, "t1b", "1"));
+    const { song, mix, stems } = await loadSongDir(dir);
+    expect(song.tracks.length).toBeGreaterThan(1);
+    expect(stems.size).toBe(song.tracks.length);
+    let maxDiff = 0;
+    for (let c = 0; c < mix.channels.length; c++) for (let i = 0; i < mix.channels[c]!.length; i++) {
+      let s = 0;
+      for (const a of stems.values()) s += a.channels[c]![i] ?? 0;
+      maxDiff = Math.max(maxDiff, Math.abs(s - mix.channels[c]![i]!));
+    }
+    expect(maxDiff).toBeLessThan(2e-3);
+  } finally {
+    await rm(root, { recursive: true, force: true });
+  }
+}, 120_000);