1 files changed, 174 insertions, 0 deletions
diff --git a/packages/meshbay-node/tests/test_stream_audio_transcode.py b/packages/meshbay-node/tests/test_stream_audio_transcode.py
new file mode 100644
index 0000000..5b1fc46
--- /dev/null
+++ b/packages/meshbay-node/tests/test_stream_audio_transcode.py
@@ -0,0 +1,174 @@
+"""
+Audio in a streamed video is always transcoded to AAC, never copied.
+
+Found live against a real 5.1 E-AC-3 WEB-DL (season 2 of a show whose season 1
+was AAC and played fine): "-c copy" on an E-AC-3 track makes ffmpeg itself
+refuse to write the fragmented MP4 header at all — "Cannot write moov atom
+before EAC3 packets parsed" — and even for the codecs that don't make ffmpeg
+outright refuse (plain AC-3, DTS, ...), no mainstream browser's MSE decodes
+them, so the viewer would see a stream that starts and immediately ends with
+no picture and no error. Video is untouched here — it is always copied,
+still H264 in every fixture below, since re-encoding it is the expensive
+thing this pipeline exists to avoid.
+
+These tests spawn real ffmpeg/ffprobe against small synthetic files (lavfi
+test sources, ~1s) rather than asserting against the source text — a source
+match cannot tell a working remux from one ffmpeg silently refuses to write.
+"""
+
+import shutil
+import subprocess
+from pathlib import Path
+
+import pytest
+from cryptography.hazmat.primitives.asymmetric.ed25519 import Ed25519PrivateKey
+
+from meshbay_common.crypto import generate_gek
+from meshbay_common.webcrypto import chunk_key_aes, decrypt_chunk_aes
+from meshbay_node.indexer.group_index import GroupIndex
+from meshbay_node.transport.webrtc_server import WebRTCPeerSession, _probe_video
+
+from conftest import one_root
+
+_HAVE_FFMPEG = shutil.which("ffmpeg") and shutil.which("ffprobe")
+pytestmark = [
+    pytest.mark.asyncio,
+    pytest.mark.skipif(not _HAVE_FFMPEG, reason="ffmpeg/ffprobe not installed"),
+]
+
+
+def _make_clip(path: Path, *, acodec: str, channels: int = 2) -> None:
+    """~1s of H264 video + `acodec` audio, muxed into an .mkv — a minimal
+    stand-in for a real WEB-DL with that audio codec."""
+    subprocess.run(
+        ["ffmpeg", "-hide_banner", "-loglevel", "error", "-y",
+         "-f", "lavfi", "-i", "testsrc=size=320x240:rate=25:duration=1",
+         "-f", "lavfi", "-i", f"sine=frequency=440:duration=1:sample_rate=48000",
+         "-ac", str(channels),
+         "-c:v", "libx264", "-preset", "ultrafast", "-c:a", acodec,
+         str(path)],
+        check=True, capture_output=True,
+    )
+
+
+def _session(tmp_path: Path, video_path: Path, gek: bytes) -> WebRTCPeerSession:
+    import blake3
+    file_bytes = video_path.read_bytes()
+    file_id = blake3.blake3(file_bytes).hexdigest()
+
+    sk_node = Ed25519PrivateKey.generate()
+    index = GroupIndex(group_id="g" * 32, sk_node=sk_node, gek=gek)
+    from meshbay_common.protocol import IndexEntry
+    index.add_entry(IndexEntry(
+        id=file_id, name=video_path.name, path=video_path.parent.name,
+        size=len(file_bytes), type="video", added_at=0))
+
+    session = WebRTCPeerSession.__new__(WebRTCPeerSession)
+    session._ctx = {
+        "roots": one_root(video_path.parent),
+        "index": index,
+        "gek": gek,
+        "sk_node": sk_node,
+        "max_concurrent_streams": 4,
+    }
+    session._group_id = None
+    session._user_id = "tester"
+    session._stream_stopped = False
+    session._stream_keepalives = 0
+    session.sent = []
+    session._send = session.sent.append
+    session._audit = lambda *a, **k: None
+    return session, file_id
+
+
+def _reassemble(sent: list[dict], gek: bytes, file_id: str) -> bytes:
+    file_hash = bytes.fromhex(file_id)
+    segments = sorted(
+        (m for m in sent if m.get("type") == "stream_data"),
+        key=lambda m: m["segment_index"])
+    out = b""
+    for m in segments:
+        key = chunk_key_aes(gek, file_hash, m["segment_index"])
+        out += decrypt_chunk_aes(key, m["nonce"], m["ct"])
+    return out
+
+
+async def test_eac3_audio_is_transcoded_not_copied(tmp_path):
+    """The exact reproduction: ffmpeg refuses "-c copy" on E-AC-3 outright."""
+    clip = tmp_path / "clip.mkv"
+    _make_clip(clip, acodec="eac3", channels=6)
+    gek = generate_gek()
+    session, file_id = _session(tmp_path, clip, gek)
+
+    await session._stream_video_inner({"file_id": file_id, "start": 0, "credits": 0})
+
+    errors = [m for m in session.sent if m.get("type") == "error"]
+    assert not errors, f"streaming must not fail: {errors}"
+
+    init = next(m for m in session.sent if m.get("type") == "stream_init")
+    assert "mp4a.40.2" in init["codec"], \
+        "the reported codec must be AAC, never the source's eac3"
+
+    data_segments = [m for m in session.sent if m.get("type") == "stream_data"]
+    assert data_segments, "no video data was ever sent"
+    assert any(m.get("type") == "stream_end" for m in session.sent)
+
+    remuxed = _reassemble(session.sent, gek, file_id)
+    out_path = tmp_path / "out.mp4"
+    out_path.write_bytes(remuxed)
+    probe = subprocess.run(
+        ["ffprobe", "-v", "error", "-show_entries", "stream=codec_name,codec_type,channels",
+         "-of", "csv=p=0", str(out_path)],
+        check=True, capture_output=True, text=True)
+    rows = [line.split(",") for line in probe.stdout.strip().splitlines()]
+    codecs = {r[1]: r[0] for r in rows}
+    channels = {r[1]: r[2] for r in rows if len(r) > 2}
+    assert codecs.get("audio") == "aac", f"audio must be AAC on the wire: {codecs}"
+    assert codecs.get("video") == "h264", f"video must still be H264: {codecs}"
+    assert channels.get("audio") == "2", (
+        "audio must be downmixed to stereo: some browsers' MSE decoder "
+        f"silently rejects multichannel AAC once real fragments are "
+        f"appended, even though ffprobe/VLC accept it fine: {channels}")
+
+
+async def test_already_aac_audio_still_streams(tmp_path):
+    """Season-1-shaped file (already AAC): must keep working exactly as before."""
+    clip = tmp_path / "clip.mkv"
+    _make_clip(clip, acodec="aac", channels=2)
+    gek = generate_gek()
+    session, file_id = _session(tmp_path, clip, gek)
+
+    await session._stream_video_inner({"file_id": file_id, "start": 0, "credits": 0})
+
+    assert not [m for m in session.sent if m.get("type") == "error"]
+    assert any(m.get("type") == "stream_data" for m in session.sent)
+    assert any(m.get("type") == "stream_end" for m in session.sent)
+
+
+async def test_probe_video_reports_aac_regardless_of_source_audio_codec(tmp_path):
+    clip = tmp_path / "clip.mkv"
+    _make_clip(clip, acodec="eac3", channels=6)
+
+    codec, duration, has_audio = await _probe_video(str(clip))
+
+    assert has_audio is True
+    assert duration > 0
+    assert codec is not None
+    assert "eac3" not in codec and "ec-3" not in codec
+    assert "mp4a.40.2" in codec
+
+
+async def test_probe_video_handles_no_audio_track(tmp_path):
+    clip = tmp_path / "silent.mkv"
+    subprocess.run(
+        ["ffmpeg", "-hide_banner", "-loglevel", "error", "-y",
+         "-f", "lavfi", "-i", "testsrc=size=320x240:rate=25:duration=1",
+         "-c:v", "libx264", "-preset", "ultrafast", "-an", str(clip)],
+        check=True, capture_output=True,
+    )
+
+    codec, duration, has_audio = await _probe_video(str(clip))
+
+    assert has_audio is False
+    assert codec is not None and "," not in codec, \
+        "no audio track must not produce a dangling ',' or a fake audio codec"