dsh-hyperframes 0.10.2 → 0.11.0

package/skills/media-use/scripts/lib/tts-local-provider.test.mjs

@@ -0,0 +1,72 @@
+import { test } from "node:test";
+import assert from "node:assert/strict";
+import { localTtsGenerate } from "./tts-local-provider.mjs";
+
+// Regression: on Windows, a bare "npx" is npx.cmd, which execFileSync cannot
+// exec — the Kokoro delegation failed with `spawnSync npx ENOENT` instead of
+// synthesizing (or cleanly falling through to the next provider). The spawn
+// must route through node + npx-cli.js on win32, same as the audio engine's
+// TTS spawns (see ../../audio/scripts/lib/tts.spawn.test.mjs).
+
+const envWithNpxCli = {
+  npm_execpath: "C:/Program Files/nodejs/node_modules/npm/bin/npm-cli.js",
+  npm_node_execpath: "C:/Program Files/nodejs/node.exe",
+};
+const npxCliPath = "C:/Program Files/nodejs/node_modules/npm/bin/npx-cli.js";
+const pathExists = (path) => path === npxCliPath;
+
+test("win32: routes the hyperframes tts call through node + npx-cli, never bare npx", async () => {
+  const captured = [];
+  const fakeExec = (cmd, args, opts) => {
+    captured.push({ cmd, args, opts });
+    // Synthesize nothing — the provider then returns null via the
+    // missing-output check, which is fine: we only assert the spawn shape.
+  };
+
+  await localTtsGenerate(
+    "hello there",
+    { voice: "am_michael" },
+    "win32",
+    fakeExec,
+    envWithNpxCli,
+    pathExists,
+  );
+
+  assert.equal(captured.length, 1);
+  assert.equal(captured[0].cmd, envWithNpxCli.npm_node_execpath);
+  assert.equal(captured[0].args[0], npxCliPath);
+  assert.deepEqual(captured[0].args.slice(1, 4), ["hyperframes", "tts", "hello there"]);
+  assert.ok(captured[0].args.includes("--voice"));
+  // execFileSync options survive the rerouting (pipes are what let the caller
+  // read the "kokoro-onnx not installed" hint back out).
+  assert.deepEqual(captured[0].opts.stdio, ["ignore", "pipe", "pipe"]);
+});
+
+test("win32 without a resolvable npx-cli: falls through to the next provider (null), no spawn", async () => {
+  const captured = [];
+  const fakeExec = (...call) => captured.push(call);
+
+  const result = await localTtsGenerate(
+    "hello",
+    {},
+    "win32",
+    fakeExec,
+    {}, // no npm_execpath, and pathExists finds nothing
+    () => false,
+  );
+
+  assert.equal(result, null);
+  assert.equal(captured.length, 0);
+});
+
+test("non-win32: spawns plain npx unchanged", async () => {
+  const captured = [];
+  const fakeExec = (cmd, args) => captured.push({ cmd, args });
+
+  await localTtsGenerate("hola", { lang: "es" }, "darwin", fakeExec, {}, () => false);
+
+  assert.equal(captured.length, 1);
+  assert.equal(captured[0].cmd, "npx");
+  assert.deepEqual(captured[0].args.slice(0, 3), ["hyperframes", "tts", "hola"]);
+  assert.ok(captured[0].args.includes("--lang"));
+});

package/skills/media-use/scripts/lib/usage.mjs

@@ -0,0 +1,57 @@
+import { readFileSync, readdirSync, existsSync } from "node:fs";
+import { join } from "node:path";
+
+// Asset in-use detection: which manifest assets are actually referenced by the
+// project's compositions. Answers "is this safe to prune?" from the CLI. (The
+// Studio Asset tab computes its in-use filter separately from the live timeline;
+// this is the skill-side equivalent for headless use.)
+//
+// ponytail: substring match of each asset's filename against the .html text
+// (covers src= / href= / url() / data-* without parsing HTML). False positives
+// only if a filename literally appears in prose; fine for a filter. Upgrade to
+// attribute parsing if that ever bites.
+
+function compositionHtml(projectDir) {
+  let files = [];
+  try {
+    files = readdirSync(projectDir).filter((f) => f.endsWith(".html"));
+  } catch {
+    return "";
+  }
+  const sub = join(projectDir, "compositions");
+  if (existsSync(sub)) {
+    try {
+      for (const f of readdirSync(sub))
+        if (f.endsWith(".html")) files.push(join("compositions", f));
+    } catch {
+      // ignore unreadable subdir
+    }
+  }
+  return files
+    .map((f) => {
+      try {
+        return readFileSync(join(projectDir, f), "utf8");
+      } catch {
+        return "";
+      }
+    })
+    .join("\n");
+}
+
+/** Tag each record with `inUse` (referenced by some composition). */
+export function tagUsage(records, projectDir) {
+  const html = compositionHtml(projectDir);
+  return records.map((r) => {
+    const file = r.path ? r.path.split("/").pop() : r.id;
+    return { ...r, inUse: Boolean(file) && html.includes(file) };
+  });
+}
+
+/** Split records into { used, unused } for the filter. */
+export function partitionUsage(records, projectDir) {
+  const tagged = tagUsage(records, projectDir);
+  return {
+    used: tagged.filter((r) => r.inUse),
+    unused: tagged.filter((r) => !r.inUse),
+  };
+}

package/skills/media-use/scripts/lib/usage.test.mjs

@@ -0,0 +1,54 @@
+import { strict as assert } from "node:assert";
+import { test } from "node:test";
+import { mkdtempSync, writeFileSync, rmSync } from "node:fs";
+import { join } from "node:path";
+import { tmpdir } from "node:os";
+import { tagUsage, partitionUsage } from "./usage.mjs";
+
+function project(html) {
+  const dir = mkdtempSync(join(tmpdir(), "mu-usage-"));
+  writeFileSync(join(dir, "index.html"), html);
+  return dir;
+}
+
+const records = [
+  { id: "bgm_001", path: ".media/audio/bgm/bgm_001.wav", description: "used track" },
+  { id: "bgm_002", path: ".media/audio/bgm/bgm_002.wav", description: "orphan track" },
+];
+
+test("an asset referenced by a composition is marked in-use", () => {
+  const dir = project(`<audio src="assets/bgm_001.wav"></audio>`);
+  try {
+    const tagged = tagUsage(records, dir);
+    assert.equal(tagged.find((r) => r.id === "bgm_001").inUse, true);
+    assert.equal(tagged.find((r) => r.id === "bgm_002").inUse, false);
+  } finally {
+    rmSync(dir, { recursive: true, force: true });
+  }
+});
+
+test("partitionUsage splits used vs unused for the filter", () => {
+  const dir = project(`<img src="bgm_001.wav">`);
+  try {
+    const { used, unused } = partitionUsage(records, dir);
+    assert.deepEqual(
+      used.map((r) => r.id),
+      ["bgm_001"],
+    );
+    assert.deepEqual(
+      unused.map((r) => r.id),
+      ["bgm_002"],
+    );
+  } finally {
+    rmSync(dir, { recursive: true, force: true });
+  }
+});
+
+test("no compositions -> everything reads as unused (safe default)", () => {
+  const dir = mkdtempSync(join(tmpdir(), "mu-usage-"));
+  try {
+    assert.equal(partitionUsage(records, dir).used.length, 0);
+  } finally {
+    rmSync(dir, { recursive: true, force: true });
+  }
+});

package/skills/media-use/scripts/lib/voice-provider.mjs

@@ -0,0 +1,57 @@
+import { HEYGEN_CLIENT_SOURCE_ARGV, runHeygenJson } from "./heygen-cli.mjs";
+
+// Voice / TTS generation via the HeyGen CLI — the only external CLI media-use
+// shells (CLI-only invariant: media-use holds no keys; the CLI owns auth).
+// Flags verified against `heygen voice speech create --help` (v0.3.0).
+
+function result(url, duration, provider, intent) {
+  if (!url) return null;
+  return {
+    url,
+    source: "generated",
+    metadata: {
+      description: intent,
+      provider,
+      ...(duration != null && { duration }),
+      provenance: { prompt: intent },
+    },
+  };
+}
+
+// HeyGen TTS requires a starfish-engine voice. Default to the first one the
+// catalog returns (deterministic order); pass ctx.voiceId to override.
+// ponytail: listed once per process; the resolved asset is frozen + cached after
+// first use, so the network list only happens on a cache miss. Cache only a
+// truthy id -- a transient list failure must not poison the cache with `null`
+// and permanently disable TTS for the rest of the process.
+let cachedVoiceId;
+function defaultVoiceId() {
+  if (cachedVoiceId) return cachedVoiceId;
+  const j = runHeygenJson(
+    "heygen",
+    ["voice", "list", "--engine", "starfish", "--limit", "1"],
+    "voice list",
+  );
+  cachedVoiceId = j?.data?.[0]?.voice_id || null;
+  return cachedVoiceId;
+}
+
+export async function heygenTtsGenerate(intent, ctx) {
+  const voiceId = ctx?.voiceId || defaultVoiceId();
+  if (!voiceId) return null;
+  const p = runHeygenJson(
+    "heygen",
+    [
+      ...HEYGEN_CLIENT_SOURCE_ARGV,
+      "voice",
+      "speech",
+      "create",
+      "--text",
+      intent,
+      "--voice-id",
+      voiceId,
+    ],
+    "tts",
+  );
+  return result(p?.data?.audio_url, p?.data?.duration, "heygen.tts", intent);
+}

package/skills/media-use/scripts/lib/voice-provider.test.mjs

@@ -0,0 +1,46 @@
+import { strict as assert } from "node:assert";
+import { chmodSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { test } from "node:test";
+import { heygenTtsGenerate } from "./voice-provider.mjs";
+
+test("tags TTS generation but not voice discovery with the media-use client source", async () => {
+  const dir = mkdtempSync(join(tmpdir(), "media-use-voice-provider-"));
+  const capturePath = join(dir, "argv.log");
+  const heygenPath = join(dir, "heygen");
+  const previousPath = process.env.PATH;
+  const previousCapturePath = process.env.HEYGEN_CAPTURE_PATH;
+
+  writeFileSync(
+    heygenPath,
+    `#!/bin/sh
+printf '%s\\n' "$*" >> "$HEYGEN_CAPTURE_PATH"
+case "$*" in
+  *"voice list"*) printf '%s\\n' '{"data":[{"voice_id":"voice-123"}]}' ;;
+  *"voice speech create"*) printf '%s\\n' '{"data":{"audio_url":"https://example.com/voice.mp3","duration":1.5}}' ;;
+esac
+`,
+  );
+  chmodSync(heygenPath, 0o755);
+  process.env.PATH = `${dir}:${previousPath ?? ""}`;
+  process.env.HEYGEN_CAPTURE_PATH = capturePath;
+
+  try {
+    const result = await heygenTtsGenerate("Hello from media-use", {});
+    const invocations = readFileSync(capturePath, "utf8").trim().split("\n");
+
+    assert.equal(invocations.length, 2);
+    assert.match(invocations[0], /^voice list /);
+    assert.doesNotMatch(invocations[0], /X-HeyGen-Client-Source/);
+    assert.match(invocations[1], /voice speech create/);
+    assert.match(invocations[1], /X-HeyGen-Client-Source: media-use/);
+    assert.equal(result?.url, "https://example.com/voice.mp3");
+  } finally {
+    if (previousPath === undefined) delete process.env.PATH;
+    else process.env.PATH = previousPath;
+    if (previousCapturePath === undefined) delete process.env.HEYGEN_CAPTURE_PATH;
+    else process.env.HEYGEN_CAPTURE_PATH = previousCapturePath;
+    rmSync(dir, { recursive: true, force: true });
+  }
+});