serve.zone/siprouter
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(proxy-engine,codec-lib,sip-proto,ts): preserve negotiated media details and improve RTP audio handling across call legs

Browse Source
This commit is contained in:
Jürgen Kunz
2026-04-10 16:57:07 +00:00
parent 2aca5f1510
commit f78639dd19
15 changed files with 260 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

66
rust/crates/proxy-engine/src/mixer.rs
View File

@@ -35,6 +35,8 @@ pub struct RtpPacket {
pub payload_type: u8,
/// RTP marker bit (first packet of a DTMF event, etc.).
pub marker: bool,
/// RTP sequence number for reordering.
pub seq: u16,
/// RTP timestamp from the original packet header.
pub timestamp: u32,
}
@@ -319,16 +321,18 @@ async fn mixer_loop(
continue;
}
// ── 2. Drain inbound packets, decode to 16kHz PCM. ─────────
// ── 2. Drain inbound packets, decode to 48kHz f32 PCM. ────
// DTMF (PT 101) packets are collected separately.
// Audio packets are sorted by sequence number and decoded
// in order to maintain codec state (critical for G.722 ADPCM).
let leg_ids: Vec<String> = legs.keys().cloned().collect();
let mut dtmf_forward: Vec<(String, RtpPacket)> = Vec::new();
for lid in &leg_ids {
let slot = legs.get_mut(lid).unwrap();
// Drain channel — collect DTMF packets separately, keep latest audio.
let mut latest_audio: Option<RtpPacket> = None;
// Drain channel — collect DTMF separately, collect ALL audio packets.
let mut audio_packets: Vec<RtpPacket> = Vec::new();
loop {
match slot.inbound_rx.try_recv() {
Ok(pkt) => {
@@ -336,35 +340,47 @@ async fn mixer_loop(
// DTMF telephone-event: collect for processing.
dtmf_forward.push((lid.clone(), pkt));
} else {
latest_audio = Some(pkt);
audio_packets.push(pkt);
}
}
Err(_) => break,
}
}
if let Some(pkt) = latest_audio {
if !audio_packets.is_empty() {
slot.silent_ticks = 0;
match slot.transcoder.decode_to_f32(&pkt.payload, pkt.payload_type) {
Ok((pcm, rate)) => {
// Resample to 48kHz mixing rate if needed.
let pcm_48k = if rate == MIX_RATE {
pcm
} else {
slot.transcoder
.resample_f32(&pcm, rate, MIX_RATE)
.unwrap_or_else(|_| vec![0.0f32; MIX_FRAME_SIZE])
};
// Per-leg inbound denoising at 48kHz.
let denoised = TranscodeState::denoise_f32(&mut slot.denoiser, &pcm_48k);
// Pad or truncate to exactly MIX_FRAME_SIZE.
let mut frame = denoised;
frame.resize(MIX_FRAME_SIZE, 0.0);
slot.last_pcm_frame = frame;
}
Err(_) => {
// Decode failed — use silence.
slot.last_pcm_frame = vec![0.0f32; MIX_FRAME_SIZE];
// Sort by sequence number for correct codec state progression.
// This prevents G.722 ADPCM state corruption from out-of-order packets.
audio_packets.sort_by_key(|p| p.seq);
// Decode ALL packets in order (maintains codec state),
// but only keep the last decoded frame for mixing.
for pkt in &audio_packets {
match slot.transcoder.decode_to_f32(&pkt.payload, pkt.payload_type) {
Ok((pcm, rate)) => {
// Resample to 48kHz mixing rate if needed.
let pcm_48k = if rate == MIX_RATE {
pcm
} else {
slot.transcoder
.resample_f32(&pcm, rate, MIX_RATE)
.unwrap_or_else(|_| vec![0.0f32; MIX_FRAME_SIZE])
};
// Per-leg inbound denoising at 48kHz.
// Skip for Opus/WebRTC legs — browsers already apply
// their own noise suppression via getUserMedia.
let processed = if slot.codec_pt != codec_lib::PT_OPUS {
TranscodeState::denoise_f32(&mut slot.denoiser, &pcm_48k)
} else {
pcm_48k
};
// Pad or truncate to exactly MIX_FRAME_SIZE.
let mut frame = processed;
frame.resize(MIX_FRAME_SIZE, 0.0);
slot.last_pcm_frame = frame;
}
Err(_) => {}
}
}
} else if dtmf_forward.iter().any(|(src, _)| src == lid) {