Files
hyperframes/skills/media-use/scripts/lib/heygen-video-provider.mjs
T
Miguel Ángel 0a66671fc5 feat(media-use): add video generation (HeyGen avatar-video + local LTX fallback) (#2614)
* fix(media-use): tag HeyGen TTS generation with attribution header

Centralizes the X-HeyGen-Client-Source header into HEYGEN_CLIENT_SOURCE_ARGV
in heygen-cli.mjs and reuses it in heygen-search.mjs (dropping the duplicated
inline literal) so voice-provider's `voice speech create` call carries it too.
The generation call was previously untagged, making media-use TTS usage
invisible in HeyGen's billing/analytics warehouse; the read-only `voice list`
discovery call intentionally stays untagged.

* feat(media-use): add local LTX video generate provider

* feat(media-use): add HeyGen avatar-video generate provider

* feat(media-use): register video as a real provider type

* docs(media-use): document the wired video type and full HeyGen tagging coverage

resolve --type video is now the default path (HeyGen avatar video first,
local LTX fallback, sign-in nudge on auth failure) instead of a manual
recipe; correct the claim that only search requests are tagged now that
TTS and avatar-video generation carry the attribution header too.

* fix(media-use): wire --avatar-id/--voice-id CLI flags and close video-provider auth/cache gaps

- resolve.mjs never implemented the --avatar-id/--voice-id override that
  operations.md documented, so following the docs crashed with
  ERR_PARSE_ARGS_UNKNOWN_OPTION; wire the flags through to ctx.
- defaultAvatarId/defaultStarfishVoiceId cached a failed discovery lookup
  as a permanent null, disabling heygen.video after one transient miss;
  cache only a truthy id, matching the same fix in voice-provider.mjs's
  defaultVoiceId.
- the avatar-video onboarding nudge only fired on a video-create failure,
  never when avatar/voice discovery itself was unauthenticated (the
  common unauthenticated case) -- propagate the discovery failure reason
  so onboarding fires either way.
- dedupe the CLI-shelling JSON helper (heygen-cli.mjs's new runHeygenJson)
  and the local-model argv-template builder (local-models.mjs's new
  buildArgv) instead of leaving byte-identical copies in each provider.

* fix(media-use): address avatar-video PR review feedback

- heygenVideoGenerate short-circuits after the first discovery-call
  failure instead of always attempting both avatar list and voice list,
  so an unauthenticated caller gets one onboarding message and one
  provider-error telemetry ping instead of a double-fire.
- runHeygenJson logs a diagnostic when a CLI call succeeds but returns
  unparseable JSON, instead of silently returning null.
- dedupe the "avatar video is free" onboarding string into one constant
  (was duplicated across three call sites).

* fix(media-use): match review-requested naming and message conventions

- export AVATAR_VIDEO_SIGNIN_MESSAGE from heygen-video-provider.mjs so
  the test imports the canonical string instead of redeclaring it.
- runHeygenJson's non-JSON diagnostic now matches heygen-search.mjs's
  existing wording ("returned non-JSON output").
2026-07-17 03:56:57 -04:00

128 lines
3.6 KiB
JavaScript

import { execFileSync } from "node:child_process";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { freezeUrl } from "./freeze.mjs";
import {
classifyHeygenErrorCode,
HEYGEN_AUTH_COMMAND,
HEYGEN_CLIENT_SOURCE_ARGV,
reportHeygenFailure,
runHeygenJson,
} from "./heygen-cli.mjs";
export const AVATAR_VIDEO_SIGNIN_MESSAGE = `media-use: avatar video is free for new API users — sign in: ${HEYGEN_AUTH_COMMAND}`;
// Cache only a truthy id -- a transient discovery failure must not poison the
// cache with `null` and permanently disable heygen.video for the rest of the
// process. `onError` lets the caller distinguish not_authenticated (and nudge
// onboarding) from any other discovery failure.
let cachedAvatarId;
function defaultAvatarId(onError) {
if (cachedAvatarId) return cachedAvatarId;
const j = runHeygenJson(
"heygen",
["avatar", "list", "--ownership", "public", "--limit", "1"],
"avatar list",
onError,
);
cachedAvatarId = j?.data?.[0]?.avatar_id || null;
return cachedAvatarId;
}
let cachedStarfishVoiceId;
function defaultStarfishVoiceId(onError) {
if (cachedStarfishVoiceId) return cachedStarfishVoiceId;
const j = runHeygenJson(
"heygen",
["voice", "list", "--engine", "starfish", "--limit", "1"],
"voice list",
onError,
);
cachedStarfishVoiceId = j?.data?.[0]?.voice_id || null;
return cachedStarfishVoiceId;
}
export async function heygenVideoGenerate(intent, ctx) {
let discoveryFailureReason = null;
const captureReason = (reason) => {
discoveryFailureReason ??= reason;
};
// Short-circuit: once one discovery call fails, the result is null either
// way, so don't attempt the second -- that would double-fire the onboarding
// message and the provider-error telemetry ping for what's really one failure.
const avatarId = ctx?.avatarId || defaultAvatarId(captureReason);
if (!avatarId) {
if (discoveryFailureReason === "not_authenticated") console.error(AVATAR_VIDEO_SIGNIN_MESSAGE);
return null;
}
const voiceId = ctx?.voiceId || defaultStarfishVoiceId(captureReason);
if (!voiceId) {
if (discoveryFailureReason === "not_authenticated") console.error(AVATAR_VIDEO_SIGNIN_MESSAGE);
return null;
}
let out;
try {
out = execFileSync(
"heygen",
[
...HEYGEN_CLIENT_SOURCE_ARGV,
"video",
"create",
"--wait",
"-d",
JSON.stringify({
type: "avatar",
avatar_id: avatarId,
script: intent,
voice_id: voiceId,
}),
],
{
encoding: "utf8",
timeout: 300000,
stdio: ["pipe", "pipe", "pipe"],
},
);
} catch (err) {
if (classifyHeygenErrorCode(err) === "not_authenticated") {
console.error(AVATAR_VIDEO_SIGNIN_MESSAGE);
}
reportHeygenFailure(err, "heygen video create");
return null;
}
let parsed;
try {
parsed = JSON.parse(out);
} catch {
console.error("media-use: `heygen video create` returned invalid JSON");
return null;
}
const videoUrl = parsed?.data?.video_url;
if (typeof videoUrl !== "string" || !videoUrl) {
console.error("media-use: `heygen video create` returned no video URL");
return null;
}
const tmpPath = join(tmpdir(), `media-use-heygen-video-${process.pid}-${Date.now()}.mp4`);
try {
await freezeUrl(videoUrl, tmpPath);
} catch (err) {
console.error(`media-use: heygen video download failed: ${err.message}`);
return null;
}
return {
localPath: tmpPath,
ext: ".mp4",
source: "generated",
metadata: {
description: intent,
provider: "heygen.video",
provenance: { prompt: intent },
},
};
}