fix(hyperframes-media): cap TTS synthesis concurrency instead of firing every line at once (#1862)

Two independent post-release feedback reports of the same mechanism from
two different skills (both delegate to this one shared engine): audio.mjs
fired every line's Kokoro TTS + whisper-transcribe subprocess concurrently
via a bare Promise.all with no cap.

- One OOM'd 12/13 lines on a resource-constrained laptop (32GB total, ~7GB
  free), requiring a manual patch to a sequential for-loop.
- The other saw 7/8 lines fail on first run, then pass on retry once the
  model was cached — concurrent cold-start model loads overwhelming the
  machine, not a real synthesis failure.

Kokoro/Whisper each load their own local model per subprocess, so firing
every line at once multiplies that cost by the line count. Extracted the
concurrency cap into lib/concurrency.mjs (audio.mjs is a script — it runs
CLI/exit side effects on import, so it can't be unit-tested directly;
the cap is small enough to pull out and test in isolation). Default 4,
overridable via HYPERFRAMES_TTS_CONCURRENCY, floored at 1 (matching one
report's own manual workaround).

hyperframes-media/scripts/audio.mjs is the single canonical engine per its
own header comment; product-launch-video, faceless-explainer, and
pr-to-video each carry a thin wrapper that spawns this file as a
subprocess (confirmed via their DEFAULT_ENGINE path), so this one fix
covers all four skills without touching the other three.

Tests: 4 new cases for mapWithConcurrency (order preserved regardless of
completion order, cap actually enforced, limit > item count doesn't hang,
empty input). Full skills test suite (514 tests) shows no new failures —
the 444 pre-existing failures are environment-dependent and reproduce
identically on unmodified main.

skills/hyperframes-media/scripts/audio.mjs

@@ -53,6 +53,7 @@ import {
 } from "./lib/tts.mjs";
 import { generateBgmDetached, inferBgmPrompt, retrieveBgm } from "./lib/bgm.mjs";
 import { resolveSfx } from "./lib/sfx.mjs";
+import { mapWithConcurrency } from "./lib/concurrency.mjs";
 
 const HERE = dirname(fileURLToPath(import.meta.url));
 const argv = process.argv.slice(2);
@@ -67,6 +68,16 @@ const die = (m) => {
 };
 const r3 = (x) => Number(x.toFixed(3));
 
+// Two independent reports of an unbounded Promise.all over TTS lines
+// overwhelming a machine: one OOM'd 12/13 concurrent Kokoro TTS +
+// whisper-transcribe lines on a resource-constrained laptop, the other saw
+// 7/8 lines fail on first run (concurrent cold-start model loads) and pass on
+// retry once the model was cached. Kokoro/Whisper each load their own local
+// model per subprocess, so firing every line at once multiplies that cost by
+// the line count. mapWithConcurrency caps how many run at once — still
+// parallel, just bounded.
+const ttsConcurrency = Math.max(1, Number(process.env.HYPERFRAMES_TTS_CONCURRENCY) || 4);
+
 const hyperframesDir = resolve(flag("hyperframes", "."));
 const requestPath = resolve(flag("request", join(hyperframesDir, "audio_request.json")));
 const outPath = resolve(flag("out", join(hyperframesDir, "audio_meta.json")));
@@ -156,7 +167,7 @@ if (only.has("tts") && lines.length) {
     }
     return { id, path: rel, duration_s: r3(dur), words: withWordIds(wordArr) };
   };
-  const results = await Promise.all(lines.map(synthLine));
+  const results = await mapWithConcurrency(lines, ttsConcurrency, synthLine);
   voices = results.filter(Boolean);
   for (const v of voices)
     console.error(`  voice ${v.id}: ${v.path} (${v.duration_s}s, ${v.words.length} words)`);

skills/hyperframes-media/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;
+}

skills/hyperframes-media/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, []);
+});