dsh-hyperframes 0.2.0 → 0.3.1

package/skills/faceless-explainer/scripts/assemble-index.test.mjs

@@ -0,0 +1,72 @@
+import assert from "node:assert/strict";
+import { existsSync, mkdirSync, mkdtempSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { spawnSync } from "node:child_process";
+import test from "node:test";
+
+const assembleScript = new URL("./assemble-index.mjs", import.meta.url).pathname;
+
+// ── bgm_pending at the assembly boundary ─────────────────────────────────────
+// Regression: the flag survived into audio_meta.json but assemble rebuilt its audio object
+// from three named keys and dropped it, so the step that actually builds the film could not
+// tell "not ready yet" from "silent by design" and would ship the silent one.
+
+function assembleWith({ audioMeta, extraArgs = [] }) {
+  const dir = mkdtempSync(join(tmpdir(), "product-launch-assemble-"));
+  writeFileSync(
+    join(dir, "STORYBOARD.md"),
+    "---\nformat: 1920x1080\nmessage: T\n---\n\n## Frame 1 — A\n- duration: 3s\n- src: compositions/frames/01-a.html\n",
+  );
+  mkdirSync(join(dir, "compositions", "frames"), { recursive: true });
+  writeFileSync(
+    join(dir, "compositions", "frames", "01-a.html"),
+    '<div data-composition-id="01-a" data-width="1920" data-height="1080">' +
+      '<section class="clip" data-start="0" data-duration="3"></section></div>',
+  );
+  if (audioMeta) writeFileSync(join(dir, "audio_meta.json"), JSON.stringify(audioMeta));
+  const r = spawnSync(
+    process.execPath,
+    [
+      assembleScript,
+      "--storyboard",
+      join(dir, "STORYBOARD.md"),
+      "--hyperframes",
+      dir,
+      ...extraArgs,
+    ],
+    { encoding: "utf8" },
+  );
+  return { dir, r };
+}
+
+test("assemble REFUSES while bgm_pending and no bed on disk", () => {
+  const { dir, r } = assembleWith({
+    audioMeta: { bgm: null, bgm_pending: true, voices: [], sfx: [] },
+  });
+
+  assert.notEqual(r.status, 0, "should not assemble a silent film over a pending bed");
+  assert.match(r.stderr, /bgm_pending/);
+  // Refusing means producing nothing, not a half-built index.
+  assert.equal(existsSync(join(dir, "index.html")), false);
+});
+
+test("--allow-pending-bgm assembles anyway, and says so", () => {
+  const { dir, r } = assembleWith({
+    audioMeta: { bgm: null, bgm_pending: true, voices: [], sfx: [] },
+    extraArgs: ["--allow-pending-bgm"],
+  });
+
+  assert.equal(r.status, 0, r.stderr);
+  assert.equal(existsSync(join(dir, "index.html")), true);
+  assert.match(r.stdout + r.stderr, /pending/i);
+});
+
+test("a film that is silent BY DESIGN still assembles untouched", () => {
+  // The whole point of carrying the flag: this case must stay distinguishable from the above.
+  const { dir, r } = assembleWith({ audioMeta: { bgm: null, voices: [], sfx: [] } });
+
+  assert.equal(r.status, 0, r.stderr);
+  assert.equal(existsSync(join(dir, "index.html")), true);
+  assert.doesNotMatch(r.stderr, /bgm_pending/);
+});

package/skills/faceless-explainer/scripts/audio.mjs

@@ -0,0 +1,291 @@
+#!/usr/bin/env node
+// audio.mjs — audio ADAPTER (reuses the product-launch SCRIPT.md / STORYBOARD.md
+// model; this file is intentionally identical across the reusing skills). The
+// TTS / BGM / SFX implementation
+// no longer lives here: it is the shared engine at
+// ../../media-use/audio/scripts/audio.mjs. This file only (a) maps the
+// product-launch model (SCRIPT.md frames + STORYBOARD.md music/sfx) into the
+// engine's neutral audio_request.json, (b) converts the engine's id-keyed
+// audio_meta back into the frame-keyed shape captions.mjs / assemble-index.mjs
+// already consume, and (c) keeps the local `sync-durations` pass (it rewrites
+// STORYBOARD.md, which is product-launch-specific).
+//
+// Three modes (unchanged CLI surface):
+//   (default) generate — engine --only tts,bgm. BGM mode is "retrieve" (strict:
+//        no HeyGen credential ⇒ skip, never a detached generate, since this
+//        workflow has no wait-bgm step). Runs in the background during Step 4.
+//   sync-durations — write real voice durations into STORYBOARD.md (local).
+//   fetch-sfx      — engine --only sfx, merged into the existing meta (Step 5,
+//        after the frames' `sfx:` cues exist).
+//
+//   node audio.mjs --script ./SCRIPT.md --storyboard ./STORYBOARD.md --hyperframes . --out ./audio_meta.json
+//   node audio.mjs sync-durations --audio-meta ./audio_meta.json --storyboard ./STORYBOARD.md
+//   node audio.mjs fetch-sfx --storyboard ./STORYBOARD.md --hyperframes .
+
+import { spawnSync } from "node:child_process";
+import { existsSync, readFileSync, rmSync, writeFileSync } from "node:fs";
+import { dirname, join, resolve } from "node:path";
+import { fileURLToPath } from "node:url";
+import { parseStoryboard } from "./lib/storyboard.mjs";
+
+const HERE = dirname(fileURLToPath(import.meta.url));
+const DEFAULT_ENGINE = join(HERE, "..", "..", "media-use", "audio", "scripts", "audio.mjs");
+
+const flag = (argv, name, def) => {
+  const i = argv.indexOf(`--${name}`);
+  return i >= 0 && i + 1 < argv.length ? argv[i + 1] : def;
+};
+const pad2 = (n) => String(n).padStart(2, "0");
+
+// SCRIPT.md → [{ frame, text }]. `## … (Frame N)` opens a line; `**key:**` rows
+// are metadata; the indented block is the spoken text (the only TTS input).
+function parseScript(md) {
+  const out = [];
+  let cur = null;
+  const flush = () => {
+    if (cur && cur.text.trim()) out.push({ frame: cur.frame, text: cur.text.trim() });
+    cur = null;
+  };
+  for (const line of md.split(/\r?\n/)) {
+    const h = line.match(/^#{2,3}\s+.*?\(frame\s+(\d+)\)/i);
+    if (h) {
+      flush();
+      cur = { frame: Number(h[1]), text: "" };
+      continue;
+    }
+    if (!cur) continue;
+    if (/^\s*\*\*/.test(line)) continue;
+    const m = line.match(/^(?: {4,}|\t)(.+)$/);
+    if (m) cur.text += (cur.text ? " " : "") + m[1].trim();
+  }
+  flush();
+  return out;
+}
+
+// Path of the engine's neutral meta — a stable sidecar so `--only` merges
+// (generate then fetch-sfx) accumulate, while audio_meta.json holds the PL shape.
+const neutralPath = (plOutPath) => join(dirname(plOutPath), "audio_engine_meta.json");
+
+// Run the shared engine. Returns nothing; dies on a non-zero exit.
+function runEngine({ request, hyperframesDir, neutral, only, extra = [] }, die) {
+  const reqPath = join(hyperframesDir, "audio_request.json");
+  writeFileSync(reqPath, JSON.stringify(request, null, 2));
+  const engine = process.env.HF_MEDIA_ENGINE || DEFAULT_ENGINE;
+  if (!existsSync(engine)) die(`media audio engine not found at ${engine} (set $HF_MEDIA_ENGINE)`);
+  const args = [
+    engine,
+    "--request",
+    reqPath,
+    "--hyperframes",
+    hyperframesDir,
+    "--out",
+    neutral,
+    "--only",
+    only,
+    ...extra,
+  ];
+  const r = spawnSync("node", args, { stdio: "inherit" });
+  if (r.status !== 0) die(`media audio engine exited ${r.status}`);
+}
+
+// Engine neutral meta (id-keyed) → product-launch meta (frame-keyed) consumed by
+// captions.mjs / assemble-index.mjs. id is the zero-padded frame number.
+function toProductLaunchMeta(neutral) {
+  const voices = (neutral.voices ?? []).map((v) => ({
+    frame: Number(v.id),
+    path: v.path,
+    duration_s: v.duration_s,
+    words: (v.words ?? []).map((w) => ({ id: w.id, text: w.text, start: w.start, end: w.end })),
+  }));
+  const bgm = neutral.bgm
+    ? {
+        path: neutral.bgm.path,
+        volume: neutral.bgm.volume,
+        query: neutral.bgm.query ?? null,
+        duration_s: neutral.bgm.duration_s ?? null,
+      }
+    : null;
+  // bgm_pending must survive the neutral → skill translation. A detached generate
+  // (Lyria/MusicGen) leaves `bgm: null, bgm_pending: true` until the track lands; dropping the
+  // flag makes "not ready yet" indistinguishable from "silent by design", so a later
+  // `fetch-sfx` snapshot turns a still-generating bed into no music at all with no signal.
+  const bgmPending = !!neutral.bgm_pending;
+  const sfx = (neutral.sfx ?? []).map((s) => ({
+    frame: Number(s.id),
+    file: s.file,
+    offset_s: s.offset_s ?? 0,
+    duration_s: s.duration_s ?? 1,
+    volume: s.volume ?? 0.35,
+  }));
+  return { bgm, bgm_pending: bgmPending, voices, sfx };
+}
+
+// ── generate (TTS + BGM) ────────────────────────────────────────────────────
+function runGenerate(argv) {
+  const die = (m) => {
+    console.error(`✗ audio generate: ${m}`);
+    process.exit(1);
+  };
+  const hyperframesDir = resolve(flag(argv, "hyperframes", "."));
+  const storyboardPath = resolve(flag(argv, "storyboard", join(hyperframesDir, "STORYBOARD.md")));
+  const scriptPath = resolve(flag(argv, "script", join(hyperframesDir, "SCRIPT.md")));
+  const outPath = resolve(flag(argv, "out", join(hyperframesDir, "audio_meta.json")));
+  const userVoice = flag(argv, "voice", null);
+  const speed = Number(flag(argv, "speed", "1.0")) || 1.0;
+
+  if (!existsSync(storyboardPath)) die(`STORYBOARD.md not found at ${storyboardPath}`);
+  const manifest = parseStoryboard(readFileSync(storyboardPath, "utf8"));
+  const g = manifest.globals;
+
+  const lines = existsSync(scriptPath)
+    ? parseScript(readFileSync(scriptPath, "utf8")).map((l) => ({
+        id: pad2(l.frame),
+        text: l.text,
+      }))
+    : [];
+  // The canonical fully-silent marker (SKILL.md Step 3.1): `music: none` in
+  // the storyboard's top YAML block turns BGM off; combined with no SCRIPT.md
+  // the project is fully silent — generate nothing and remove any stale meta
+  // from a previous run (assemble treats an absent audio_meta.json as silent).
+  const bgmOff =
+    String(g.extra?.music ?? "")
+      .trim()
+      .toLowerCase() === "none";
+  if (bgmOff && !lines.length) {
+    rmSync(outPath, { force: true });
+    rmSync(neutralPath(outPath), { force: true });
+    console.log(
+      "✓ audio generate: project marked silent (music: none, no SCRIPT.md) — nothing to generate",
+    );
+    return;
+  }
+  if (!lines.length) console.error("· no SCRIPT.md — silent film (BGM only)");
+
+  // BGM mood: storyboard `music:` → message → arc → default. `mode: retrieve` is
+  // strict here (no wait-bgm step downstream).
+  const query = (g.extra && g.extra.music) || g.message || g.arc || "calm cinematic underscore";
+  const request = {
+    provider: "auto",
+    speed,
+    lines,
+    bgm: bgmOff
+      ? { mode: "none" }
+      : { mode: "retrieve", query, blob: g.message || "", arc: g.arc || "" },
+  };
+  if (userVoice) request.voice = userVoice;
+
+  const neutral = neutralPath(outPath);
+  runEngine({ request, hyperframesDir, neutral, only: "tts,bgm" }, die);
+
+  const meta = toProductLaunchMeta(JSON.parse(readFileSync(neutral, "utf8")));
+  writeFileSync(outPath, JSON.stringify(meta, null, 2));
+  console.log(
+    `✓ audio generate: ${meta.voices.length} voice + ${meta.bgm ? "1 bgm" : "no bgm"} → ${outPath}`,
+  );
+}
+
+// ── fetch-sfx ────────────────────────────────────────────────────────────────
+function runFetchSfx(argv) {
+  const die = (m) => {
+    console.error(`✗ audio fetch-sfx: ${m}`);
+    process.exit(1);
+  };
+  const hyperframesDir = resolve(flag(argv, "hyperframes", "."));
+  const storyboardPath = resolve(flag(argv, "storyboard", join(hyperframesDir, "STORYBOARD.md")));
+  const outPath = resolve(flag(argv, "audio-meta", join(hyperframesDir, "audio_meta.json")));
+
+  if (!existsSync(storyboardPath)) die(`STORYBOARD.md not found at ${storyboardPath}`);
+  const manifest = parseStoryboard(readFileSync(storyboardPath, "utf8"));
+
+  // Per-frame `sfx:` cues (comma-separated) → engine lines carrying only sfx.
+  // `filter(Boolean)` alone is not enough: a storyboard that spells "no SFX here" as
+  // `sfx: none` reaches the engine as a cue literally NAMED "none", which then fails to
+  // resolve. The absence sentinels are part of the storyboard vocabulary, so drop them.
+  const SFX_NONE = new Set(["none", "no", "n/a", "na", "skip", "-", "—", "–"]);
+  const lines = [];
+  for (const f of manifest.frames) {
+    const names = (f.extra?.sfx ?? "")
+      .split(",")
+      .map((s) => s.trim())
+      .filter((s) => s && !SFX_NONE.has(s.toLowerCase()));
+    if (names.length && f.number != null) lines.push({ id: pad2(f.number), sfx: names });
+  }
+
+  const neutral = neutralPath(outPath);
+  const request = { lines, bgm: { mode: "none" } };
+  // --only sfx is a MERGE, not an overwrite: the engine reads the existing neutral
+  // sidecar (audio_engine_meta.json) and recomputes only the sfx section, so the
+  // voices/bgm written by the earlier generate (--only tts,bgm) pass are preserved.
+  runEngine({ request, hyperframesDir, neutral, only: "sfx" }, die);
+
+  const meta = toProductLaunchMeta(JSON.parse(readFileSync(neutral, "utf8")));
+  writeFileSync(outPath, JSON.stringify(meta, null, 2));
+  console.log(`✓ audio fetch-sfx: ${meta.sfx.length} SFX cue(s) → ${outPath}`);
+  // This pass rewrites audio_meta.json from the neutral sidecar. If a detached BGM generate is
+  // still running, the bed it eventually writes is NOT folded back in — the snapshot we just
+  // took has no music. Say so instead of leaving a silent film behind.
+  if (meta.bgm_pending && !meta.bgm) {
+    console.warn(
+      "⚠ audio fetch-sfx: a detached BGM generate is still pending, so this snapshot has no bed. " +
+        "Re-run `fetch-sfx` (or re-point audio_meta.json at the track) once it lands, before assembling.",
+    );
+  }
+}
+
+// ── sync-durations (local; rewrites STORYBOARD.md) ────────────────────────────
+function runSyncDurations(argv) {
+  const die = (m) => {
+    console.error(`✗ audio sync-durations: ${m}`);
+    process.exit(1);
+  };
+  const hyperframesDir = resolve(flag(argv, "hyperframes", "."));
+  const audioMetaPath = resolve(flag(argv, "audio-meta", join(hyperframesDir, "audio_meta.json")));
+  const storyboardPath = resolve(flag(argv, "storyboard", join(hyperframesDir, "STORYBOARD.md")));
+  if (!existsSync(audioMetaPath)) die(`audio_meta.json not found at ${audioMetaPath}`);
+
+  const meta = JSON.parse(readFileSync(audioMetaPath, "utf8"));
+  const durByFrame = new Map();
+  for (const v of meta.voices ?? []) {
+    if (v.frame != null && v.duration_s) durByFrame.set(v.frame, v.duration_s);
+  }
+
+  // Read directly and handle ENOENT here, rather than an existsSync precheck —
+  // the check→write pair (write-back below) is a TOCTOU race CodeQL flags.
+  let storyboardRaw = "";
+  try {
+    storyboardRaw = readFileSync(storyboardPath, "utf8");
+  } catch {
+    die(`STORYBOARD.md not found at ${storyboardPath}`);
+  }
+  const lines = storyboardRaw.split(/\r?\n/);
+  const FRAME_RE = /^#{2,3}\s+(?:frame|beat|scene)\b.*?(\d+)/i;
+  let curFrame = null;
+  let updated = 0;
+  for (let i = 0; i < lines.length; i++) {
+    const h = lines[i].match(FRAME_RE);
+    if (h) {
+      curFrame = Number(h[1]);
+      continue;
+    }
+    if (curFrame != null && durByFrame.has(curFrame)) {
+      const m = lines[i].match(/^(\s*[-*]\s+duration\s*:\s*).*/i);
+      if (m) {
+        lines[i] = `${m[1]}${durByFrame.get(curFrame)}s`;
+        durByFrame.delete(curFrame);
+        updated++;
+      }
+    }
+  }
+  writeFileSync(storyboardPath, lines.join("\n"));
+  const missing = [...durByFrame.keys()];
+  console.log(
+    `✓ audio sync-durations: ${updated} frame duration(s) updated` +
+      (missing.length ? ` · no \`- duration:\` line for frame(s) ${missing.join(", ")}` : ""),
+  );
+}
+
+// ── dispatch ──────────────────────────────────────────────────────────────────
+const sub = process.argv[2];
+if (sub === "sync-durations") runSyncDurations(process.argv.slice(3));
+else if (sub === "fetch-sfx") runFetchSfx(process.argv.slice(3));
+else runGenerate(process.argv.slice(2)); // default: generate

package/skills/faceless-explainer/scripts/audio.test.mjs

@@ -0,0 +1,176 @@
+import assert from "node:assert/strict";
+import { existsSync, mkdtempSync, readFileSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { spawnSync } from "node:child_process";
+import test from "node:test";
+
+const script = new URL("./audio.mjs", import.meta.url).pathname;
+
+// The header of this adapter declares it "intentionally identical across the
+// reusing skills" — pin that contract so a fix landing in one copy can't
+// silently miss the other (the fully-silent marker bug did exactly that).
+test("audio.mjs is byte-identical to pr-to-video's copy (the stated contract)", () => {
+  const here = readFileSync(script, "utf8");
+  const sibling = readFileSync(
+    new URL("../../pr-to-video/scripts/audio.mjs", import.meta.url),
+    "utf8",
+  );
+  assert.equal(here, sibling);
+});
+
+// ── the canonical fully-silent marker (SKILL.md Step 3.1) ────────────────────
+// Same contract as product-launch (see its audio.test.mjs): `music: none` in
+// the storyboard's top YAML block + no SCRIPT.md ⇒ generate nothing; with
+// narration ⇒ TTS runs, BGM off.
+
+function runAudioRaw({ storyboard, scriptMd = null, preexistingMeta = null }) {
+  const dir = mkdtempSync(join(tmpdir(), "faceless-audio-"));
+  const engine = join(dir, "engine.mjs");
+  writeFileSync(join(dir, "STORYBOARD.md"), storyboard);
+  if (scriptMd != null) writeFileSync(join(dir, "SCRIPT.md"), scriptMd);
+  if (preexistingMeta != null) writeFileSync(join(dir, "audio_meta.json"), preexistingMeta);
+  writeFileSync(
+    engine,
+    `import { readFileSync, writeFileSync } from "node:fs";
+const argv = process.argv.slice(2);
+const flag = (name) => argv[argv.indexOf(name) + 1];
+const request = JSON.parse(readFileSync(flag("--request"), "utf8"));
+writeFileSync(new URL("request.json", import.meta.url), JSON.stringify(request));
+writeFileSync(flag("--out"), JSON.stringify({ voices: [], bgm: null, sfx: [] }));
+`,
+  );
+  const result = spawnSync(
+    process.execPath,
+    [script, "--hyperframes", dir, "--storyboard", join(dir, "STORYBOARD.md")],
+    { encoding: "utf8", env: { ...process.env, HF_MEDIA_ENGINE: engine } },
+  );
+  return { dir, result };
+}
+
+test("music: none + no SCRIPT.md = fully silent: no engine run, no audio_meta.json", () => {
+  const { dir, result } = runAudioRaw({ storyboard: "---\nmessage: Test\nmusic: none\n---\n" });
+
+  assert.equal(result.status, 0, result.stderr);
+  assert.match(result.stdout, /marked silent/);
+  assert.equal(existsSync(join(dir, "request.json")), false);
+  assert.equal(existsSync(join(dir, "audio_meta.json")), false);
+});
+
+test("fully-silent run removes stale audio_meta.json from a previous non-silent run", () => {
+  const { dir, result } = runAudioRaw({
+    storyboard: "---\nmessage: Test\nmusic: none\n---\n",
+    preexistingMeta: JSON.stringify({ bgm: { path: "old.mp3" }, voices: [], sfx: [] }),
+  });
+
+  assert.equal(result.status, 0, result.stderr);
+  assert.equal(existsSync(join(dir, "audio_meta.json")), false);
+});
+
+test("music: none with narration keeps TTS but turns BGM off (not fully silent)", () => {
+  const { dir, result } = runAudioRaw({
+    storyboard: "---\nmessage: Test\nmusic: none\n---\n",
+    scriptMd: "## Hook (Frame 1)\n\n    Spoken line for frame one.\n",
+  });
+
+  assert.equal(result.status, 0, result.stderr);
+  const request = JSON.parse(readFileSync(join(dir, "request.json"), "utf8"));
+  assert.equal(request.bgm.mode, "none");
+  assert.equal(request.lines.length, 1);
+});
+
+test("a storyboard music mood still retrieves BGM (marker is exact, not fuzzy)", () => {
+  const { dir, result } = runAudioRaw({
+    storyboard: "---\nmessage: Test\nmusic: upbeat synthwave with heavy drums\n---\n",
+  });
+
+  assert.equal(result.status, 0, result.stderr);
+  const request = JSON.parse(readFileSync(join(dir, "request.json"), "utf8"));
+  assert.equal(request.bgm.mode, "retrieve");
+  assert.equal(request.bgm.query, "upbeat synthwave with heavy drums");
+});
+
+// ── fetch-sfx ────────────────────────────────────────────────────────────────
+// Regressions found while running the full product-launch workflow end to end
+// (linear.app site showcase, 2026-07-30).
+
+/** Runs the fetch-sfx subcommand. `neutralOut` is what the stub engine writes to --out. */
+function runFetchSfx({ storyboard, neutralOut = { voices: [], bgm: null, sfx: [] } }) {
+  const dir = mkdtempSync(join(tmpdir(), "product-launch-sfx-"));
+  const engine = join(dir, "engine.mjs");
+  writeFileSync(join(dir, "STORYBOARD.md"), storyboard);
+  writeFileSync(
+    engine,
+    `import { readFileSync, writeFileSync } from "node:fs";
+const argv = process.argv.slice(2);
+const flag = (name) => argv[argv.indexOf(name) + 1];
+const request = JSON.parse(readFileSync(flag("--request"), "utf8"));
+writeFileSync(new URL("request.json", import.meta.url), JSON.stringify(request));
+writeFileSync(flag("--out"), ${JSON.stringify(JSON.stringify(neutralOut))});
+`,
+  );
+  const result = spawnSync(
+    process.execPath,
+    [script, "fetch-sfx", "--hyperframes", dir, "--storyboard", join(dir, "STORYBOARD.md")],
+    { encoding: "utf8", env: { ...process.env, HF_MEDIA_ENGINE: engine } },
+  );
+  return { dir, result };
+}
+
+const FRAME_WITH_SFX = (sfx) =>
+  `---\nmessage: Test\n---\n\n## Frame 1 — Hook\n- duration: 3s\n- sfx: ${sfx}\n`;
+
+test("fetch-sfx: `sfx: none` is an absence marker, not a cue named none", () => {
+  const { dir, result } = runFetchSfx({ storyboard: FRAME_WITH_SFX("none") });
+
+  assert.equal(result.status, 0, result.stderr);
+  const request = JSON.parse(readFileSync(join(dir, "request.json"), "utf8"));
+  // Used to reach the engine as { sfx: ["none"] } — a cue that cannot resolve.
+  assert.deepEqual(request.lines, []);
+});
+
+test("fetch-sfx: the other absence spellings are markers too", () => {
+  for (const spelling of ["None", "n/a", "NA", "skip", "-", "—"]) {
+    const { dir, result } = runFetchSfx({ storyboard: FRAME_WITH_SFX(spelling) });
+    assert.equal(result.status, 0, result.stderr);
+    const request = JSON.parse(readFileSync(join(dir, "request.json"), "utf8"));
+    assert.deepEqual(request.lines, [], `spelling: ${spelling}`);
+  }
+});
+
+test("fetch-sfx: a real cue still reaches the engine, and mixed lists drop only the marker", () => {
+  const { dir, result } = runFetchSfx({ storyboard: FRAME_WITH_SFX("whoosh, none, click") });
+
+  assert.equal(result.status, 0, result.stderr);
+  const request = JSON.parse(readFileSync(join(dir, "request.json"), "utf8"));
+  assert.deepEqual(request.lines, [{ id: "01", sfx: ["whoosh", "click"] }]);
+});
+
+test("fetch-sfx: carries bgm_pending through and warns that the snapshot has no bed", () => {
+  const { dir, result } = runFetchSfx({
+    storyboard: FRAME_WITH_SFX("whoosh"),
+    // A detached Lyria/MusicGen generate that has not landed yet.
+    neutralOut: { voices: [], bgm: null, bgm_pending: true, sfx: [] },
+  });
+
+  assert.equal(result.status, 0, result.stderr);
+  const meta = JSON.parse(readFileSync(join(dir, "audio_meta.json"), "utf8"));
+  // The flag used to be dropped in the neutral → PL translation, making "not ready yet"
+  // indistinguishable from "silent by design".
+  assert.equal(meta.bgm_pending, true);
+  assert.equal(meta.bgm, null);
+  assert.match(result.stderr + result.stdout, /pending/i);
+});
+
+test("fetch-sfx: a resolved bed reports bgm_pending false and no warning", () => {
+  const { dir, result } = runFetchSfx({
+    storyboard: FRAME_WITH_SFX("whoosh"),
+    neutralOut: { voices: [], bgm: { path: "assets/bgm/track.mp3", volume: 0.12 }, sfx: [] },
+  });
+
+  assert.equal(result.status, 0, result.stderr);
+  const meta = JSON.parse(readFileSync(join(dir, "audio_meta.json"), "utf8"));
+  assert.equal(meta.bgm_pending, false);
+  assert.equal(meta.bgm.path, "assets/bgm/track.mp3");
+  assert.doesNotMatch(result.stderr, /pending/i);
+});