STSheets/tests/bench/real.test.ts

import { describe, expect, test } from "bun:test";
import { mkdtemp, rm } from "node:fs/promises";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { renderRealReport, runReal, type RealSongResult } from "../../src/bench/real.ts";
import { buildSong, loadSongDir } from "../../src/bench/dataset.ts";
import { writeSmf } from "../../src/align/smf.ts";
import { writeAlignment, type SongEntry } from "../../src/ref/manifest.ts";
import { createPipeline } from "../../src/pipeline/run.ts";
import { scoreSong } from "../../src/eval/score.ts";
import type { Role } from "../../src/core/types.ts";
import type { FitReport, FitWindow } from "../../src/align/fit.ts";

const hasReference = await Bun.file("reference/songs.json").exists();
const mr = (f1: number | null, tp = 8, fp = 2, fn = 2) => ({ tp, fp, fn, precision: f1, recall: f1, f1, octaveErrors: 0, matches: [] as [number, number][] });
const win = (startSec: number, precision: number, reasons: string[]): FitWindow => ({ startSec, recOnsets: 40, precision, lift: 0.6, audibleRate: 0.4, medianResidualMs: 12.3, beatShift: null, flagged: reasons.length > 0, reasons });
const fit = (p: number): FitReport => ({
  precision: p, lift: 0.62, audibleRate: 0.38, medianResidualMs: 12.3,
  windows: [win(0, p, []), win(30, 0.5, ["precision 50%"])], stretches: { total: 41, warned: 4, over15: 2 },
});
const base = { offsetSec: 0.06, precision: 0.88 };
const fixture = (): RealSongResult[] => [
  {
    id: "a", title: "Song A", alignment: { source: "computed", manual: 0, auto: 40, savedAt: null, chosen: "dtw", baseline: base, dtwPrecision: 0.8 }, fit: fit(0.8),
    perRole: { bass: mr(0.5), guitar: mr(0.9), keys: mr(null, 0, 0, 0) }, lenient: { bass: 0.6, guitar: 0.95, keys: null },
    drumsPerClass: null, excludedTracks: ["Click", "Pad"], capo: { Lead: 2 }, seconds: 3,
  },
  {
    id: "b", title: "Song B", alignment: { source: "saved", manual: 0, auto: 1, savedAt: "2026-10-29T10:00:00Z", chosen: "baseline", baseline: base, dtwPrecision: 0.85 }, fit: fit(0.6),
    perRole: { guitar: mr(0.3) }, lenient: { guitar: 0.4 }, drumsPerClass: null, excludedTracks: [], capo: {}, seconds: 4,
  },
];

describe("renderRealReport", () => {
  const md = renderRealReport("fx", fixture(), [{ id: "c", reason: "reference/c/alignment.json: not valid JSON" }, { id: "d", reason: "no alignment.json" }]);
  test("guitar row precedes the other roles; source, method, baseline, fit and stretch warnings shown", () => {
    expect(md).toContain("Song A");
    expect(md).toContain("computed this run");
    expect(md).toContain("saved 2026-10-29T10:00:00Z");
    expect(md).toContain("0 manual / 40 auto");
    expect(md).not.toMatch(/manual \(/);
    expect(md).toContain("chosen: DTW (precision 80.0%)");
    expect(md).toContain("chosen: baseline (DTW precision 85.0% not better");
    expect(md).toContain("constant-offset baseline +0.06 s: precision 88.0%");
    expect(md).toContain("precision 80.0% (lift +0.62)");
    expect(md).toContain("MIDI onsets audible as attacks 38.0%");
    expect(md).toContain("1/2 windows flagged (0:30 precision 50%)");
    expect(md).toContain("stretches: 4/41 warned, 2 > 15%");
    expect(md).toContain("consistency of the alignment");
    expect(md).toContain("c (reference/c/alignment.json: not valid JSON)");
    expect(md).toContain("d (no alignment.json)");
    const a = md.slice(md.indexOf("Song A"), md.indexOf("Song B"));
    expect(a.indexOf("| guitar")).toBeGreaterThan(-1);
    expect(a.indexOf("| guitar")).toBeLessThan(a.indexOf("| bass"));
    expect(a.indexOf("| bass")).toBeLessThan(a.indexOf("| keys"));
    expect(a).toContain("0.90");
    expect(a).toContain("0.95");
    expect(a).toContain("Click, Pad");
    expect(a).toContain("Lead: 2");
  });
});

describe("runReal", () => {
  test("t1a fixture with identity alignment matches the synthetic full-mode score", async () => {
    const root = await mkdtemp(join(tmpdir(), "stsheets-real-"));
    try {
      const dir = await buildSong("t1a", 1, join(root, "data"));
      const { truth } = await loadSongDir(dir);
      const prog: Record<Role, number> = { guitar: 25, bass: 33, keys: 0, vocals: 53, drums: 0 };
      const tracks = truth.tracks.map((t) => ({ name: t.name, program: prog[t.role], isDrums: t.role === "drums", notes: t.notes }));
      const ref = join(root, "ref");
      await Bun.write(join(ref, "t1a-1", "song.mid"), writeSmf(tracks, truth.bpm));
      const entry: SongEntry = {
        id: "t1a-1", title: "Synthetic t1a/1", audio: join(dir, "mix.wav"), midi: join(ref, "t1a-1", "song.mid"),
        roles: Object.fromEntries(truth.tracks.map((t) => [t.name, t.role])), capo: {},
      };
      await Bun.write(join(ref, "songs.json"), JSON.stringify([entry, { ...entry, id: "noalign", title: "No alignment" }, { ...entry, id: "corrupt", title: "Corrupt alignment" }]));
      await Bun.write(join(ref, "corrupt", "alignment.json"), "{ not json");
      const dur = 600;
      await writeAlignment("t1a-1", { anchors: [{ midiSec: 0, audioSec: 0, kind: "manual" }, { midiSec: dur, audioSec: dur, kind: "manual" }], savedAt: "2026-10-30T00:00:00Z", fit: null }, ref);

      const results = await runReal({ runId: "t", auto: false, root: ref, out: join(root, "runs"), resultsDir: join(root, "results") });
      expect(results.map((r) => r.id)).toEqual(["t1a-1"]);
      const r = results[0]!;
      expect(r.alignment).toEqual({ source: "saved", manual: 2, auto: 0, savedAt: "2026-10-30T00:00:00Z", chosen: null, baseline: expect.any(Object), dtwPrecision: null });
      expect(Math.abs(r.alignment.baseline.offsetSec)).toBeLessThan(0.05); // identity alignment
      expect(r.fit.precision).not.toBeNull();
      expect(r.fit.stretches).toBeDefined();

      const pipe = await createPipeline({
        demucs: new Uint8Array(await Bun.file("models/demucs/htdemucs_6s.onnx").arrayBuffer()),
        basicPitch: new Uint8Array(await Bun.file("models/basic-pitch/nmp.onnx").arrayBuffer()),
      });
      const flags = { oracleStems: false, oracleTempo: false, oracleNotes: false };
      const loaded = await loadSongDir(dir);
      const synth = scoreSong(truth, (await pipe({ mix: loaded.mix }, flags)).output, flags);
      expect(Math.abs((r.perRole.guitar!.f1 ?? 0) - (synth.guitarMerged.f1 ?? 0))).toBeLessThan(0.02);

      for (const f of ["notes.json", "out.gp", "score.json"]) expect(await Bun.file(join(root, "runs", "real-t", "t1a-1", f)).exists()).toBe(true);
      const json = await Bun.file(join(root, "results", "real-t.json")).text();
      expect(json).not.toContain('"matches"');
      const md = await Bun.file(join(root, "results", "real-t.md")).text();
      expect(md).toContain("Synthetic t1a/1");
      expect(md).toMatch(/corrupt \(.*alignment\.json.*not valid JSON/);
      expect(md).toContain("noalign (no alignment.json; pass --auto to compute one)");
    } finally { await rm(root, { recursive: true, force: true }); }
  }, 600_000);

  test.skipIf(!hasReference)("real reference manifest loads", async () => {
    const { readManifest } = await import("../../src/ref/manifest.ts");
    expect((await readManifest()).length).toBeGreaterThan(0);
  });
});