dsh-hyperframes 0.2.0 → 0.3.0

package/skills/media-use/audio/scripts/lib/bgm.mjs

@@ -0,0 +1,257 @@
+// bgm.mjs — background music for the media audio engine. Two routes, gated the
+// same way as TTS/SFX:
+//
+//   retrieve (default when HeyGen is configured) — search HeyGen's music library
+//        by mood, download the top track. Synchronous. assets/bgm/track.mp3.
+//   generate (the alternative; the automatic choice when HeyGen is absent) —
+//        Lyria (cloud, $GEMINI_API_KEY/$GOOGLE_API_KEY + google-genai) preferred,
+//        else local MusicGen (facebook/musicgen-small via transformers). Spawned
+//        DETACHED so the engine can return while audio renders; the caller marks
+//        bgm_pending and runs wait-bgm.mjs before assembling. assets/bgm/track.wav.
+//
+// Missing/failed BGM never blocks a render.
+
+import { spawn, spawnSync } from "node:child_process";
+import { existsSync, mkdirSync, openSync, closeSync } from "node:fs";
+import { join } from "node:path";
+import { downloadTo, searchSounds } from "./heygen.mjs";
+import { pythonInvocation } from "./python.mjs";
+
+const r3 = (x) => Number(x.toFixed(3));
+const lyriaKey = () => process.env.GEMINI_API_KEY || process.env.GOOGLE_API_KEY || "";
+
+// Default BGM level. Under narration music is a bed that must stay under the
+// voice — 0.12 linear ≈ -18 dB. A silent film (no voice) has no voice to duck
+// beneath, so BGM sits forward at 0.9. Callers may override per composition.
+export const BGM_BED_VOLUME = 0.12;
+export const BGM_SILENT_VOLUME = 0.9;
+export const bgmDefaultVolume = (hasVoice) => (hasVoice ? BGM_BED_VOLUME : BGM_SILENT_VOLUME);
+
+const BGM_PY_DEPS = ["transformers", "torch", "soundfile", "numpy"];
+const BGM_PY_PROBE =
+  "import transformers, soundfile, torch, numpy; from transformers import MusicgenForConditionalGeneration";
+const LYRIA_PY_DEPS = ["google-genai", "python-dotenv"];
+const LYRIA_PY_PROBE = "import google.genai";
+
+function pyOk(probe) {
+  const { cmd, args } = pythonInvocation(["-c", probe]);
+  return spawnSync(cmd, args, { stdio: "ignore" }).status === 0;
+}
+// `python -m pip`, not a bare `pip` binary: a Homebrew/system Python often
+// exposes only `python3`/`pip3` on PATH, so a plain `pip` spawn silently
+// no-ops (ENOENT) and the documented "auto-installed on demand" path never
+// actually installs. `-m pip` also guarantees the packages land in the SAME
+// interpreter pyOk() probes — a bare `pip`/`pip3` could resolve to a
+// different Python installation than `python3` if more than one is on PATH.
+function pipInstall(deps) {
+  const { cmd, args } = pythonInvocation(["-m", "pip", "install", "-q", ...deps]);
+  return spawnSync(cmd, args, { stdio: "ignore" }).status === 0;
+}
+
+// ── retrieval (HeyGen music library) ──────────────────────────────────────────
+export async function retrieveBgm({ query, headers, hyperframesDir, hasVoice }) {
+  const q = query || "calm cinematic underscore";
+  const results = await searchSounds(q, "music", headers, { limit: 5 });
+  if (!results.length) return null;
+  const top = results[0];
+  const rel = "assets/bgm/track.mp3";
+  await downloadTo(top.audio_url, join(hyperframesDir, rel));
+  return {
+    path: rel,
+    volume: bgmDefaultVolume(hasVoice),
+    query: q,
+    mode: "retrieve",
+    duration_s: typeof top.duration === "number" ? r3(top.duration) : null,
+  };
+}
+
+// ── mood inference (for the generate path's prompt) ──────────────────────────
+// Industry base → archetype shape → emotional-arc tiebreaker. Exported so a
+// workflow adapter can build a rich prompt from its own narrative metadata; the
+// engine also calls it when generate has only a plain mood query.
+export function inferBgmPrompt({ blob = "", archetype = "", arc = "", userPrompt = "" } = {}) {
+  if (userPrompt) return userPrompt;
+  const b = String(blob).toLowerCase();
+  let base;
+  let bpm;
+  if (/\b(crypto|nft|web3|defi|token|blockchain|exchange|wallet|dao)\b/.test(b)) {
+    base = "atmospheric electronic, deep bass, futuristic synths, restrained percussion";
+    bpm = 100;
+  } else if (/\b(finance|fintech|bank|payment|invest|wealth|insurance|treasury)\b/.test(b)) {
+    base = "calm cinematic, soft strings, subtle piano, restrained percussion";
+    bpm = 92;
+  } else if (/\b(creative|agency|design|studio|art|brand|marketing|content)\b/.test(b)) {
+    base = "playful electronic, warm pads, light percussion";
+    bpm = 115;
+  } else {
+    base = "uplifting corporate tech, bright modern piano with synth pads";
+    bpm = 108;
+  }
+  const at = String(archetype).toLowerCase();
+  const ar = String(arc).toLowerCase();
+  if (/\bpas\b|pain.agitate|pain.+solve/.test(at))
+    return `${base}, starts with subtle tension then builds to resolution, BPM ${bpm}, transitions from MINOR to MAJOR`;
+  if (/\bbab\b|before.after|future.pac|vision/.test(at))
+    return `${base}, cinematic and aspirational, steady build with rising energy, BPM ${bpm}, MAJOR`;
+  if (/cascade|feature.benefit/.test(at))
+    return `${base}, energetic and driving, consistent momentum, BPM ${Math.min(bpm + 10, 128)}, MAJOR`;
+  if (/demo.loop|question.+answer/.test(at))
+    return `${base}, clean and focused, minimal arrangement, BPM ${Math.max(bpm - 8, 88)}`;
+  if (/frustrat|anxiety|overwhelm|tension/.test(ar) && /relief|excite|triumph/.test(ar))
+    return `${base}, builds from understated tension to uplifting resolution, BPM ${bpm}, MINOR to MAJOR`;
+  if (/excit|awe|power|triumph/.test(ar))
+    return `${base}, energetic and confident, BPM ${bpm}, MAJOR`;
+  if (/trust|ease|clarity|reassur/.test(ar))
+    return `${base}, warm and reassuring, BPM ${Math.max(bpm - 5, 85)}`;
+  return `${base}, BPM ${bpm}, MAJOR`;
+}
+
+// ── generation (Lyria → MusicGen, detached) ──────────────────────────────────
+// Returns a bgmMeta the caller folds into audio_meta:
+//   { path, mode, volume, provider, pid, log, target_duration_s, seed_duration_s,
+//     loop_count, pending:true }  on success, or  { disabled:true, reason }.
+export function generateBgmDetached({
+  prompt,
+  durationS,
+  hyperframesDir,
+  lyriaRecipe,
+  seedSeconds = 28,
+  hasVoice,
+}) {
+  const rel = "assets/bgm/track.wav";
+  const abs = join(hyperframesDir, rel);
+  mkdirSync(join(hyperframesDir, "assets", "bgm"), { recursive: true });
+  const log = join(hyperframesDir, "assets", "bgm", `bgm-${Date.now()}.log`);
+  const targetS = Math.max(1, durationS);
+  const baseMeta = { path: rel, mode: null, volume: bgmDefaultVolume(hasVoice), pending: true };
+
+  const lyriaConfigured = !!lyriaKey() && !!lyriaRecipe && existsSync(lyriaRecipe);
+
+  // Make a backend runnable: prefer Lyria when configured (install google-genai
+  // on demand), else ensure local MusicGen deps. Installs are synchronous here —
+  // generation itself is detached, so the engine still returns promptly.
+  if (lyriaConfigured && !pyOk(LYRIA_PY_PROBE)) pipInstall(LYRIA_PY_DEPS);
+  const useLyria = lyriaConfigured && pyOk(LYRIA_PY_PROBE);
+  if (!useLyria && !pyOk(BGM_PY_PROBE)) pipInstall(BGM_PY_DEPS);
+
+  const fd = openSync(log, "w");
+  if (useLyria) {
+    const { cmd, args } = pythonInvocation([
+      lyriaRecipe,
+      "--output",
+      abs,
+      "--duration",
+      String(targetS),
+      "--prompt",
+      prompt,
+    ]);
+    const proc = spawn(cmd, args, { detached: true, stdio: ["ignore", fd, fd] });
+    proc.unref();
+    closeSync(fd);
+    return {
+      ...baseMeta,
+      mode: "detached-single",
+      provider: "lyria",
+      pid: proc.pid,
+      log,
+      target_duration_s: r3(targetS),
+    };
+  }
+
+  if (pyOk(BGM_PY_PROBE)) {
+    const seedS = Math.min(Math.max(seedSeconds, 10), 30);
+    const loops = targetS > seedS ? Math.ceil(targetS / seedS) : 1;
+    const script = musicgenScript({ prompt, abs, targetS, seedS });
+    const { cmd, args } = pythonInvocation(["-c", script]);
+    const proc = spawn(cmd, args, { detached: true, stdio: ["ignore", fd, fd] });
+    proc.unref();
+    closeSync(fd);
+    return {
+      ...baseMeta,
+      mode: targetS > seedS ? "detached-seed-loop" : "detached-seed-trim",
+      provider: "musicgen",
+      pid: proc.pid,
+      log,
+      target_duration_s: r3(targetS),
+      seed_duration_s: seedS,
+      loop_count: loops,
+    };
+  }
+
+  closeSync(fd);
+  return {
+    disabled: true,
+    reason: lyriaConfigured
+      ? `Lyria configured but google-genai uninstallable, and local MusicGen unavailable (pip install ${BGM_PY_DEPS.join(" ")})`
+      : `no Lyria key/recipe and local MusicGen deps unavailable (pip install ${BGM_PY_DEPS.join(" ")})`,
+  };
+}
+
+// Inline MusicGen: generate ONE seed clip (≤30s to stay under the decoder's
+// positional limit), then trim it down or crossfade-loop it up to the target.
+function musicgenScript({ prompt, abs, targetS, seedS }) {
+  return `
+import math, os, sys, traceback
+from pathlib import Path
+import numpy as np
+import soundfile as sf
+from transformers import MusicgenForConditionalGeneration, AutoProcessor
+
+prompt = ${JSON.stringify(prompt)}
+out_path = ${JSON.stringify(abs)}
+target_s = float(${targetS.toFixed(3)})
+seed_s = float(${seedS.toFixed(3)})
+token_rate = 50
+crossfade_s = 0.3
+
+def apply_fade(arr, sr, fade_in_s=0.08, fade_out_s=0.5):
+    n_in = min(int(round(fade_in_s * sr)), arr.shape[0] // 2)
+    n_out = min(int(round(fade_out_s * sr)), arr.shape[0] // 2)
+    if n_in > 1: arr[:n_in] *= np.linspace(0.0, 1.0, n_in, dtype="float32")
+    if n_out > 1: arr[-n_out:] *= np.linspace(1.0, 0.0, n_out, dtype="float32")
+    return arr
+
+def loop_crossfade(seed, target_len, xf):
+    if seed.shape[0] >= target_len: return seed[:target_len]
+    xf = min(xf, seed.shape[0] // 2)
+    if xf < 1:
+        reps = int(math.ceil(target_len / seed.shape[0]))
+        return np.tile(seed, reps)[:target_len]
+    t = np.linspace(0.0, 1.0, xf, dtype="float32")
+    fade_out = np.cos(t * (math.pi / 2)); fade_in = np.sin(t * (math.pi / 2))
+    out = seed.copy()
+    while out.shape[0] < target_len:
+        tail = out[-xf:] * fade_out; head = seed[:xf] * fade_in
+        out = np.concatenate([out[:-xf], tail + head, seed[xf:]])
+    return out[:target_len]
+
+try:
+    Path(os.path.dirname(out_path)).mkdir(parents=True, exist_ok=True)
+    processor = AutoProcessor.from_pretrained("facebook/musicgen-small")
+    model = MusicgenForConditionalGeneration.from_pretrained("facebook/musicgen-small")
+    model.eval()
+    sr = int(model.config.audio_encoder.sampling_rate)
+    gen_s = min(seed_s, target_s)
+    tokens = max(1, int(math.ceil(gen_s * token_rate)))
+    print(f"[musicgen] seed dur={gen_s:.2f}s tokens={tokens}", flush=True)
+    inputs = processor(text=[prompt], padding=True, return_tensors="pt")
+    audio = model.generate(**inputs, max_new_tokens=tokens)
+    seed = audio[0, 0].detach().cpu().numpy().astype("float32")
+    peak = float(np.max(np.abs(seed)))
+    if peak > 1e-6: seed = seed * (0.89 / peak)
+    want = max(1, int(round(target_s * sr)))
+    if seed.shape[0] >= want:
+        final = seed[:want].copy()
+    else:
+        final = loop_crossfade(seed, want, int(round(crossfade_s * sr)))
+    if final.shape[0] < want: final = np.pad(final, (0, want - final.shape[0]))
+    else: final = final[:want]
+    final = apply_fade(final, sr)
+    peak = float(np.max(np.abs(final)))
+    if peak > 1.0: final = final / peak
+    sf.write(out_path, final, sr)
+    print(f"[musicgen] wrote {out_path} samples={final.shape[0]} sr={sr}", flush=True)
+except Exception:
+    traceback.print_exc(); sys.exit(1)
+`;
+}

package/skills/media-use/audio/scripts/lib/bgm.test.mjs

@@ -0,0 +1,30 @@
+import { test } from "node:test";
+import assert from "node:assert/strict";
+import { BGM_BED_VOLUME, BGM_SILENT_VOLUME, bgmDefaultVolume } from "./bgm.mjs";
+
+// Regression: narrated pipelines used to ship BGM at 0.8 (≈ -2 dB), ~16 dB
+// hotter than a music bed under a voice should be. The default under narration
+// must be a proper bed (≈ -18 dB); a silent film keeps the louder default.
+
+const dbfs = (linear) => 20 * Math.log10(linear);
+
+test("BGM under narration is a bed near -18 dB", () => {
+  assert.equal(bgmDefaultVolume(true), BGM_BED_VOLUME);
+  assert.equal(BGM_BED_VOLUME, 0.12);
+  const db = dbfs(BGM_BED_VOLUME);
+  assert.ok(db < -17 && db > -19, `bed should be ≈ -18 dB, got ${db.toFixed(1)} dB`);
+});
+
+test("a silent film (no voice) keeps BGM forward", () => {
+  assert.equal(bgmDefaultVolume(false), BGM_SILENT_VOLUME);
+  assert.equal(BGM_SILENT_VOLUME, 0.9);
+});
+
+test("the narrated default is well below the voice (≈ 0 dBFS)", () => {
+  // Voice sits at data-volume="1" (0 dBFS); the bed must be ~16+ dB under it.
+  const separation = dbfs(1) - dbfs(bgmDefaultVolume(true));
+  assert.ok(
+    separation >= 16,
+    `bed should sit ≥16 dB under the voice, got ${separation.toFixed(1)} dB`,
+  );
+});

package/skills/media-use/audio/scripts/lib/concurrency.mjs

@@ -0,0 +1,14 @@
+// mapWithConcurrency — run `fn` over `items` with at most `limit` in flight at
+// once. Preserves input order in the result array regardless of completion order.
+export async function mapWithConcurrency(items, limit, fn) {
+  const results = new Array(items.length);
+  let next = 0;
+  async function worker() {
+    while (next < items.length) {
+      const i = next++;
+      results[i] = await fn(items[i], i);
+    }
+  }
+  await Promise.all(Array.from({ length: Math.min(limit, items.length) }, worker));
+  return results;
+}

package/skills/media-use/audio/scripts/lib/concurrency.test.mjs

@@ -0,0 +1,41 @@
+import { test } from "node:test";
+import assert from "node:assert/strict";
+import { mapWithConcurrency } from "./concurrency.mjs";
+
+// Regression: audio.mjs used a bare Promise.all(lines.map(synthLine)) to
+// synthesize every TTS line at once, spawning one Kokoro/whisper model load
+// per line concurrently. Two independent reports of this overwhelming a
+// machine (OOM, and cold-start contention causing spurious failures).
+// mapWithConcurrency is the extracted cap; test it in isolation since
+// audio.mjs itself is a script (runs CLI/exit side effects on import).
+test("processes every item and preserves input order regardless of completion order", async () => {
+  const order = [5, 1, 3, 2, 4];
+  const results = await mapWithConcurrency(order, 2, async (n) => {
+    await new Promise((r) => setTimeout(r, n));
+    return n * 10;
+  });
+  assert.deepEqual(results, [50, 10, 30, 20, 40]);
+});
+
+test("never runs more than `limit` at once", async () => {
+  let inFlight = 0;
+  let maxInFlight = 0;
+  const items = Array.from({ length: 10 }, (_, i) => i);
+  await mapWithConcurrency(items, 3, async () => {
+    inFlight++;
+    maxInFlight = Math.max(maxInFlight, inFlight);
+    await new Promise((r) => setTimeout(r, 5));
+    inFlight--;
+  });
+  assert.equal(maxInFlight, 3);
+});
+
+test("limit larger than the item count runs everything without hanging", async () => {
+  const results = await mapWithConcurrency([1, 2], 10, async (n) => n * 2);
+  assert.deepEqual(results, [2, 4]);
+});
+
+test("empty input resolves to an empty array", async () => {
+  const results = await mapWithConcurrency([], 4, async (n) => n);
+  assert.deepEqual(results, []);
+});

package/skills/media-use/audio/scripts/lib/heygen.mjs

@@ -0,0 +1,155 @@
+// heygen.mjs — vendored HeyGen REST helpers (auth + transport) for the audio
+// pipeline. The credential resolver matches the hyperframes CLI auth: first
+// usable source wins — $HEYGEN_API_KEY / $HYPERFRAMES_API_KEY → a nearby .env → ~/.heygen/
+// credentials (oauth → Bearer, else api_key → X-Api-Key; $HEYGEN_CONFIG_DIR
+// overrides the dir). Vendored so the skill ships standalone. Pure node.
+
+import { existsSync, mkdirSync, readFileSync, writeFileSync } from "node:fs";
+import { homedir } from "node:os";
+import { dirname, join, resolve } from "node:path";
+
+export const HEYGEN_BASE = "https://api.heygen.com/v3";
+export const HEYGEN_CLI_SOURCE_HEADERS = { "X-HeyGen-Source": "cli" };
+// Tool-attribution sent on EVERY media-use HeyGen call regardless of auth type, so
+// the backend can isolate media-use consumption from other free TTS / avatar video.
+// Unconditional — a paying user's media-use call is still media-use — unlike the
+// OAuth-only cli-source header above, which also gates the free allowance.
+export const HEYGEN_CLIENT_SOURCE_HEADERS = { "X-HeyGen-Client-Source": "media-use" };
+
+// Walk up ≤5 dirs from startDir; load the first .env (shell env always wins).
+export function loadEnvFromDir(startDir) {
+  let dir = resolve(startDir);
+  for (let i = 0; i < 5; i++) {
+    const envPath = join(dir, ".env");
+    if (existsSync(envPath)) {
+      for (const raw of readFileSync(envPath, "utf8").split("\n")) {
+        let line = raw.trim();
+        if (!line || line.startsWith("#")) continue;
+        if (line.startsWith("export ")) line = line.slice(7).trim();
+        const eq = line.indexOf("=");
+        if (eq < 1) continue;
+        const key = line.slice(0, eq).trim();
+        let val = line.slice(eq + 1).trim();
+        if (val.startsWith('"') || val.startsWith("'")) {
+          const q = val[0];
+          const end = val.indexOf(q, 1);
+          val = end > 0 ? val.slice(1, end) : val.slice(1);
+        }
+        if (!(key in process.env)) process.env[key] = val;
+      }
+      return;
+    }
+    const parent = dirname(dir);
+    if (parent === dir) break;
+    dir = parent;
+  }
+}
+
+// → { headers } | { expired: true } | null. Never throws.
+export function heygenCredential() {
+  const envKey = process.env.HEYGEN_API_KEY || process.env.HYPERFRAMES_API_KEY;
+  if (envKey) return { headers: { "X-Api-Key": envKey } };
+
+  const file = join(process.env.HEYGEN_CONFIG_DIR || join(homedir(), ".heygen"), "credentials");
+  if (!existsSync(file)) return null;
+  const raw = readFileSync(file, "utf8").trim();
+  if (!raw) return null;
+  if (!raw.startsWith("{")) return { headers: { "X-Api-Key": raw } };
+
+  // A malformed credentials file (partial write / wrong shape) must degrade to
+  // "no credential", not crash the engine at startup — this function never throws.
+  let cred;
+  try {
+    cred = JSON.parse(raw);
+  } catch {
+    return null;
+  }
+  const oauth = cred.oauth;
+  if (oauth?.access_token) {
+    const expired = oauth.expires_at && new Date(oauth.expires_at).getTime() - 60_000 < Date.now();
+    if (!expired) return { headers: { Authorization: `Bearer ${oauth.access_token}` } };
+    if (!cred.api_key) return { expired: true };
+  }
+  if (cred.api_key) return { headers: { "X-Api-Key": cred.api_key } };
+  return null;
+}
+
+// → "oauth" | "api_key" | null. Same oauth-vs-api-key check heygenAuthHeaders()
+// makes internally, exposed on its own so callers that only need to *tag* the
+// auth path (telemetry) don't have to parse headers back apart. Never throws:
+// no credential (or an expired one) is just `null`, same as a fresh resolve
+// with nothing to tag.
+export function heygenAuthMethod() {
+  const cred = heygenCredential();
+  if (!cred?.headers) return null;
+  return "Authorization" in cred.headers ? "oauth" : "api_key";
+}
+
+// → auth headers object, or throw with a fix hint.
+export function heygenAuthHeaders() {
+  const cred = heygenCredential();
+  if (cred?.headers) {
+    // Only tag OAuth (Bearer) traffic as cli-source — the backend uses it to
+    // grant the free allowance for OAuth requests and ignores it for API-key
+    // (X-Api-Key) traffic, where it's dead metadata.
+    const isOauth = "Authorization" in cred.headers;
+    return isOauth
+      ? { ...cred.headers, ...HEYGEN_CLI_SOURCE_HEADERS, ...HEYGEN_CLIENT_SOURCE_HEADERS }
+      : { ...cred.headers, ...HEYGEN_CLIENT_SOURCE_HEADERS };
+  }
+  if (cred?.expired)
+    throw new Error(
+      "HeyGen OAuth token expired — run `npx hyperframes auth refresh` (or `npx hyperframes auth login`)",
+    );
+  throw new Error(
+    "no HeyGen credentials — set $HEYGEN_API_KEY, or run `npx hyperframes auth login` (writes ~/.heygen/credentials)",
+  );
+}
+
+// Authed JSON request against the v3 API; throws on a non-OK status.
+export async function heygenJSON(path, { method = "GET", headers = {}, body } = {}) {
+  const opts = { method, headers: { ...HEYGEN_CLIENT_SOURCE_HEADERS, ...headers } };
+  if (body !== undefined) {
+    opts.headers["Content-Type"] = "application/json";
+    opts.body = JSON.stringify(body);
+  }
+  const res = await fetch(`${HEYGEN_BASE}${path}`, opts);
+  if (!res.ok) {
+    const detail = await res.text().catch(() => "");
+    throw new Error(
+      `HeyGen ${method} ${path} → HTTP ${res.status}${detail ? `\n${detail.slice(0, 300)}` : ""}`,
+    );
+  }
+  return res.json();
+}
+
+// Download a (presigned) URL to destPath; returns byte length.
+export async function downloadTo(url, destPath) {
+  const res = await fetch(url);
+  if (!res.ok) throw new Error(`download HTTP ${res.status}: ${String(url).slice(0, 80)}`);
+  const bytes = Buffer.from(await res.arrayBuffer());
+  mkdirSync(dirname(destPath), { recursive: true });
+  writeFileSync(destPath, bytes);
+  return bytes.length;
+}
+
+// Retrieval search over HeyGen's audio catalog (NOT generation). type =
+// "music" | "sound_effects". Returns the ranked results array (best first); each
+// item has a presigned `audio_url` (+ `duration`, `description`, `name`, `score`).
+// `query` is required (≥1 char, empty → HTTP 400) and `limit` is capped at 50.
+// `minScore`: omit to use the server default (0.7). That default is TOO HIGH for
+// sound_effects — good SFX hits score ~0.5–0.67, so callers wanting SFX should
+// pass a lower floor (~0.4); music scores high and is fine at the default.
+export async function searchSounds(query, type, headers, { limit = 5, minScore } = {}) {
+  const params = new URLSearchParams({ query, type, limit: String(limit) });
+  if (minScore != null) params.set("min_score", String(minScore));
+  const payload = await heygenJSON(`/audio/sounds?${params.toString()}`, { headers });
+  // `data` comes back as a ranked array (best first). Older responses keyed it by
+  // numeric index ("0","1",…); normalize both shapes to an array (empty → []).
+  const data = payload?.data ?? payload;
+  if (Array.isArray(data)) return data;
+  if (data && typeof data === "object") return Object.values(data);
+  throw new Error(
+    `unexpected /audio/sounds shape — top keys: ${Object.keys(payload ?? {}).join(", ")}`,
+  );
+}

package/skills/media-use/audio/scripts/lib/heygen.test.mjs

@@ -0,0 +1,103 @@
+import { test } from "node:test";
+import assert from "node:assert/strict";
+import { mkdtempSync, rmSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { heygenAuthHeaders, heygenAuthMethod } from "./heygen.mjs";
+
+function withCleanHeygenEnv(fn) {
+  const previousApiKey = process.env.HEYGEN_API_KEY;
+  const previousHyperframesApiKey = process.env.HYPERFRAMES_API_KEY;
+  const previousConfigDir = process.env.HEYGEN_CONFIG_DIR;
+  try {
+    delete process.env.HEYGEN_API_KEY;
+    delete process.env.HYPERFRAMES_API_KEY;
+    delete process.env.HEYGEN_CONFIG_DIR;
+    return fn();
+  } finally {
+    if (previousApiKey === undefined) delete process.env.HEYGEN_API_KEY;
+    else process.env.HEYGEN_API_KEY = previousApiKey;
+    if (previousHyperframesApiKey === undefined) delete process.env.HYPERFRAMES_API_KEY;
+    else process.env.HYPERFRAMES_API_KEY = previousHyperframesApiKey;
+    if (previousConfigDir === undefined) delete process.env.HEYGEN_CONFIG_DIR;
+    else process.env.HEYGEN_CONFIG_DIR = previousConfigDir;
+  }
+}
+
+test("heygenAuthHeaders does not tag API-key requests as CLI traffic, but still carries the media-use tool tag", () => {
+  withCleanHeygenEnv(() => {
+    process.env.HEYGEN_API_KEY = "hg_test";
+    // API-key requests use normal billing; the backend ignores the cli-source
+    // header for them, so it's not sent. The tool-attribution header IS sent on
+    // every media-use call (any auth type) so the backend can isolate media-use.
+    assert.deepEqual(heygenAuthHeaders(), {
+      "X-Api-Key": "hg_test",
+      "X-HeyGen-Client-Source": "media-use",
+    });
+  });
+});
+
+test("heygenAuthHeaders tags OAuth requests as CLI traffic and with the media-use tool tag", () => {
+  withCleanHeygenEnv(() => {
+    const dir = mkdtempSync(join(tmpdir(), "heygen-cred-"));
+    try {
+      process.env.HEYGEN_CONFIG_DIR = dir;
+      writeFileSync(
+        join(dir, "credentials"),
+        JSON.stringify({
+          oauth: {
+            access_token: "at_test",
+            expires_at: "2099-01-01T00:00:00Z",
+          },
+        }),
+      );
+      assert.deepEqual(heygenAuthHeaders(), {
+        Authorization: "Bearer at_test",
+        "X-HeyGen-Source": "cli",
+        "X-HeyGen-Client-Source": "media-use",
+      });
+    } finally {
+      rmSync(dir, { recursive: true, force: true });
+    }
+  });
+});
+
+test("heygenAuthMethod returns api_key for an env API key, without tagging headers", () => {
+  withCleanHeygenEnv(() => {
+    process.env.HEYGEN_API_KEY = "hg_test";
+    assert.equal(heygenAuthMethod(), "api_key");
+  });
+});
+
+test("heygenAuthMethod returns oauth for a live OAuth credential", () => {
+  withCleanHeygenEnv(() => {
+    const dir = mkdtempSync(join(tmpdir(), "heygen-cred-"));
+    try {
+      process.env.HEYGEN_CONFIG_DIR = dir;
+      writeFileSync(
+        join(dir, "credentials"),
+        JSON.stringify({
+          oauth: {
+            access_token: "at_test",
+            expires_at: "2099-01-01T00:00:00Z",
+          },
+        }),
+      );
+      assert.equal(heygenAuthMethod(), "oauth");
+    } finally {
+      rmSync(dir, { recursive: true, force: true });
+    }
+  });
+});
+
+test("heygenAuthMethod returns null with no credential at all", () => {
+  withCleanHeygenEnv(() => {
+    const dir = mkdtempSync(join(tmpdir(), "heygen-cred-"));
+    try {
+      process.env.HEYGEN_CONFIG_DIR = dir; // no credentials file written
+      assert.equal(heygenAuthMethod(), null);
+    } finally {
+      rmSync(dir, { recursive: true, force: true });
+    }
+  });
+});

package/skills/media-use/audio/scripts/lib/python.mjs

@@ -0,0 +1,63 @@
+// python.mjs — resolve which Python 3 executable to spawn, per platform.
+//
+// The audio engine (tts.mjs, bgm.mjs) shells out to `python3` for ElevenLabs
+// TTS and the local Lyria/MusicGen BGM paths. `python3` is the right name on
+// macOS/Linux, but on Windows the python.org installer only creates
+// `python.exe` plus the `py` launcher — there is no `python3.exe` (only the
+// Microsoft Store build adds one). So a bare `spawn("python3", …)` ENOENTs on a
+// standard Windows Python install, silently disabling every Python-backed audio
+// feature until the user hand-creates a `python3.exe` shim (reported twice).
+//
+// Resolve once, per process: probe the platform's candidates in order and take
+// the first that actually runs. `py` is the launcher, so it needs a `-3` arg to
+// select Python 3 — hence candidates are argv PREFIXES, not bare names.
+
+import { spawnSync } from "node:child_process";
+
+function defaultProbe(cmd, args) {
+  try {
+    return spawnSync(cmd, args, { stdio: "ignore" }).status === 0;
+  } catch {
+    return false;
+  }
+}
+
+/**
+ * Pick the argv prefix that launches Python 3 on this platform.
+ * Returns e.g. `["python3"]`, `["python"]`, or `["py", "-3"]`.
+ *
+ * Pure except for `probe` (which runs `<cmd> … --version`); both `platform`
+ * and `probe` are injectable so every branch is unit-testable without spawning.
+ * If nothing probes OK, falls back to the canonical name for the platform so
+ * the eventual spawn fails loudly exactly as it did before — never worse.
+ */
+export function resolvePythonCommand(platform = process.platform, probe = defaultProbe) {
+  const candidates =
+    platform === "win32" ? [["python3"], ["python"], ["py", "-3"]] : [["python3"], ["python"]];
+  for (const prefix of candidates) {
+    if (probe(prefix[0], [...prefix.slice(1), "--version"])) return prefix;
+  }
+  return candidates[0];
+}
+
+let cached = null;
+
+/** Cached `resolvePythonCommand()` — probing spawns, so resolve at most once. */
+export function pythonCommand() {
+  if (!cached) cached = resolvePythonCommand();
+  return cached;
+}
+
+/**
+ * Build a `{ cmd, args }` for running Python 3 with `extraArgs`, using the
+ * resolved (or supplied) prefix. Keeps the launcher's `-3` (and any future
+ * prefix args) ahead of the caller's own arguments.
+ */
+export function pythonInvocation(extraArgs, prefix = pythonCommand()) {
+  return { cmd: prefix[0], args: [...prefix.slice(1), ...extraArgs] };
+}
+
+/** Test-only: clear the cached resolution so a test can re-probe. */
+export function _resetPythonCommandCacheForTests() {
+  cached = null;
+}