mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-07 12:30:44 +00:00
da3d17e1ca
End-to-end testing on macOS + BlueBubbles + ElevenLabs walked through three CAF flavors before landing on the format Apple's Messages.app actually emits when a user records a native iMessage voice memo: - PCM int16 @ 44.1 kHz CAF: BlueBubbles' internal `afconvert -f m4af -d aac` conversion fails; the original CAF reaches iMessage but renders with 0 s duration. - AAC @ 22.05 kHz mono CAF: BlueBubbles' conversion succeeds and the server silently downgrades the delivery, sending the converted MP3 as a generic audio attachment. - **Opus @ 24 kHz mono CAF**: byte-identical to the descriptor block Apple's Messages.app produces; BlueBubbles passes it through unchanged and iMessage renders a native voice-memo bubble with proper duration and waveform UI. Adds an opt-in `tts.voice.preferAudioFileFormat` channel capability and a macOS `afconvert`-backed pre-transcode in the speech-core pipeline. BlueBubbles declares `preferAudioFileFormat: "caf"`. Other channels are unaffected. Falls back to the original buffer when the host platform, the source/target pair, or the transcoder process can't produce the preferred container — so non-Darwin hosts and unsupported provider combinations are unchanged. Also adds a `caff` magic-byte sniff in `src/media/mime.ts` so the auto-reply host-local-media validator (which uses `file-type` and didn't recognize CAF natively) accepts the buffer instead of dropping it as "⚠️ Media failed." Fixes #72506. Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
65 lines
2.3 KiB
TypeScript
65 lines
2.3 KiB
TypeScript
import { describe, expect, it } from "vitest";
|
|
import { transcodeAudioBuffer } from "./audio-transcode.js";
|
|
|
|
describe("transcodeAudioBuffer", () => {
|
|
it("returns noop-same-container when source and target containers match", async () => {
|
|
const result = await transcodeAudioBuffer({
|
|
audioBuffer: Buffer.from("payload"),
|
|
sourceExtension: "mp3",
|
|
targetExtension: ".mp3",
|
|
});
|
|
expect(result).toEqual({ ok: false, reason: "noop-same-container" });
|
|
});
|
|
|
|
it("returns no-recipe when no afconvert recipe is defined for the requested pair", async () => {
|
|
const result = await transcodeAudioBuffer({
|
|
audioBuffer: Buffer.from("payload"),
|
|
sourceExtension: "mp3",
|
|
targetExtension: "flac",
|
|
});
|
|
expect(result).toEqual({ ok: false, reason: "no-recipe" });
|
|
});
|
|
|
|
it("returns invalid-extension for an empty source extension", async () => {
|
|
const result = await transcodeAudioBuffer({
|
|
audioBuffer: Buffer.from("payload"),
|
|
sourceExtension: "",
|
|
targetExtension: "caf",
|
|
});
|
|
expect(result).toEqual({ ok: false, reason: "invalid-extension" });
|
|
});
|
|
|
|
it("returns invalid-extension for an empty target extension", async () => {
|
|
const result = await transcodeAudioBuffer({
|
|
audioBuffer: Buffer.from("payload"),
|
|
sourceExtension: "mp3",
|
|
targetExtension: "",
|
|
});
|
|
expect(result).toEqual({ ok: false, reason: "invalid-extension" });
|
|
});
|
|
|
|
it("rejects path-traversal style extensions", async () => {
|
|
const result = await transcodeAudioBuffer({
|
|
audioBuffer: Buffer.from("payload"),
|
|
sourceExtension: "../etc/passwd",
|
|
targetExtension: "caf",
|
|
});
|
|
expect(result).toEqual({ ok: false, reason: "invalid-extension" });
|
|
});
|
|
|
|
it("returns platform-unsupported off-Darwin without invoking afconvert", async () => {
|
|
if (process.platform === "darwin") {
|
|
// macOS: a valid mp3→caf request would proceed to spawn `afconvert`,
|
|
// which we don't want to run from a unit test. The Darwin happy path
|
|
// is exercised end-to-end via the BlueBubbles voice-memo flow.
|
|
return;
|
|
}
|
|
const result = await transcodeAudioBuffer({
|
|
audioBuffer: Buffer.from("payload"),
|
|
sourceExtension: "mp3",
|
|
targetExtension: "caf",
|
|
});
|
|
expect(result).toEqual({ ok: false, reason: "platform-unsupported" });
|
|
});
|
|
});
|