fix(HEL-718): bound synthetic idle audio and preserve RTP cadence

This commit is contained in:
mobai
2026-10-21 01:18:41 +08:00
parent ae4fd5c49d
commit 415f8372e3
12 changed files with 902 additions and 0 deletions
+72
View File
@@ -45,3 +45,75 @@ if replacement not in s:
assert s.count(needle) >= 1
p.write_text(s.replace(needle, replacement, 1))
print("Installed HEL-714 peer retirement endpoint in private copy:", root)
# HEL-718: all edits remain reproducible on a clean pinned driver copy.
def replace_once(path, before, after):
text = path.read_text()
if after in text:
return
assert text.count(before) == 1, f"Unexpected c726943 source: {path}"
path.write_text(text.replace(before, after, 1))
(root / "server/hel718_audio.py").write_text(
Path(__file__).with_name("driver_audio.py").read_text()
)
p = root / "server/webrtc.py"
replace_once(p, "import queue\n", "import queue\nfrom server.hel718_audio import PendingAudio\n")
replace_once(p, "self._queue = queue.Queue(maxsize=100)",
"self._queue = PendingAudio() if kind == 'audio' else queue.Queue(maxsize=100)")
# Preserve the initial common audio/video origin. Once started, pace BEFORE
# selecting audio, so fresh speech cannot wait behind a dequeued idle block.
s = p.read_text()
start = s.find(" # frame = self.frames[self.counter % 30]")
end = s.index(" frame.pts = pts", max(0, start))
replacement = ''' self._player._start(self)
if self.kind == 'audio' and hasattr(self, '_timestamp'):
pts, time_base = await self.next_timestamp()
try:
frame, eventpoint, _ = self._queue.get_nowait()
except queue.Empty:
frame = AudioFrame.from_ndarray(
np.zeros((1, 320), dtype=np.int16), layout='mono', format='s16')
frame.sample_rate = SAMPLE_RATE
eventpoint = None
else:
while self.readyState == 'live':
try:
frame, eventpoint, *_ = self._queue.get_nowait()
break
except queue.Empty:
await asyncio.sleep(0.005)
else:
raise Exception('Track stopped')
pts, time_base = await self.next_timestamp()
'''
if "np.zeros((1, 320), dtype=np.int16), layout='mono'" not in s:
assert start >= 0, "Unexpected c726943 recv implementation"
p.write_text(s[:start] + replacement + s[end:])
replace_once(p, "def push_audio(self, frame, eventpoint=None):",
"def push_audio(self, frame, eventpoint=None, audio_type=0):")
replace_once(p, "self.__audio._queue.put((new_frame, eventpoint))",
"self.__audio._queue.put((new_frame, eventpoint, audio_type))")
# Wall-clock adjustments must not change packet cadence.
s = p.read_text()
start, end = s.index(" async def next_timestamp"), s.index(" async def recv")
s = s[:start] + s[start:end].replace("time.time()", "time.monotonic()") + s[end:]
p.write_text(s)
p = root / "streamout/webrtc.py"
replace_once(p, " def get_buffer_size(self) -> int:", ''' def push_audio_data(self, frame, eventpoint, audio_type):
if self._player:
self._player.push_audio(frame, eventpoint, audio_type)
def get_buffer_size(self) -> int:''')
p = root / "avatars/base_avatar.py"
replace_once(p, " self.output.push_audio_frame(frame, audio_frame.userdata)",
''' if hasattr(self.output, 'push_audio_data'):
self.output.push_audio_data(frame, audio_frame.userdata, audio_frame.type)
else:
self.output.push_audio_frame(frame, audio_frame.userdata)''')
p = root / "avatars/audio_features/base_asr.py"
replace_once(p, " for _ in range(self.stride_left_size):\n self.output_queue.get()",
" for _ in range(self.stride_left_size + self.stride_right_size):\n self.output_queue.get()")
print("Installed HEL-718 bounded synthetic idle, continuous RTP audio, and warm-up drain")