4 Commits

22 changed files with 511 additions and 91 deletions

View File

@@ -1,5 +1,20 @@
# Changelog
## 2026-04-10 - 1.17.2 - fix(proxy-engine)
use negotiated SDP payload types when wiring SIP legs and enable default nnnoiseless features for telephony denoising
- Select the negotiated codec payload type from SDP answers instead of always using the first offered codec
- Preserve the device leg's preferred payload type from its own INVITE SDP when attaching it to the mixer
- Enable default nnnoiseless features in codec-lib and proxy-engine dependencies
## 2026-04-10 - 1.17.1 - fix(proxy-engine,codec-lib,sip-proto,ts)
preserve negotiated media details and improve RTP audio handling across call legs
- Use native Opus float encode/decode to avoid unnecessary i16 quantization in the f32 audio path.
- Parse full RTP headers including extensions and sequence numbers, then sort inbound packets before decoding to keep codec state stable for out-of-order audio.
- Capture negotiated codec payload types from SDP offers and answers and include codec, RTP port, remote media, and metadata in leg_added events.
- Emit leg_state_changed and leg_removed events more consistently so the dashboard reflects leg lifecycle updates accurately.
## 2026-04-10 - 1.17.0 - feat(proxy-engine)
upgrade the internal audio bus to 48kHz f32 with per-leg denoising and improve SIP leg routing

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

View File

@@ -1,6 +1,6 @@
{
"name": "siprouter",
"version": "1.17.0",
"version": "1.17.2",
"private": true,
"type": "module",
"scripts": {

226
rust/Cargo.lock generated
View File

@@ -237,6 +237,17 @@ version = "1.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1505bd5d3d116872e7271a6d4e16d81d0c8570876c8de68093a09ac269d8aac0"
[[package]]
name = "atty"
version = "0.2.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d9b39be18770d11421cdb1b9947a45dd3f37e93092cbf377614828a319d5fee8"
dependencies = [
"hermit-abi",
"libc",
"winapi",
]
[[package]]
name = "audiopus"
version = "0.3.0-rc.0"
@@ -487,6 +498,31 @@ dependencies = [
"inout",
]
[[package]]
name = "clap"
version = "3.2.25"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4ea181bf566f71cb9a5d17a59e1871af638180a18fb0035c92ae62b705207123"
dependencies = [
"atty",
"bitflags 1.3.2",
"clap_lex",
"indexmap 1.9.3",
"once_cell",
"strsim",
"termcolor",
"textwrap",
]
[[package]]
name = "clap_lex"
version = "0.2.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2850f2f5a82cbf437dd5af4d49848fbdfc27c157c3d010345776f952765261c5"
dependencies = [
"os_str_bytes",
]
[[package]]
name = "cmake"
version = "0.1.58"
@@ -700,6 +736,125 @@ version = "0.3.8"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "06d2e3287df1c007e74221c49ca10a95d557349e54b3a75dc2fb14712c751f04"
[[package]]
name = "dasp"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7381b67da416b639690ac77c73b86a7b5e64a29e31d1f75fb3b1102301ef355a"
dependencies = [
"dasp_envelope",
"dasp_frame",
"dasp_interpolate",
"dasp_peak",
"dasp_ring_buffer",
"dasp_rms",
"dasp_sample",
"dasp_signal",
"dasp_slice",
"dasp_window",
]
[[package]]
name = "dasp_envelope"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8ec617ce7016f101a87fe85ed44180839744265fae73bb4aa43e7ece1b7668b6"
dependencies = [
"dasp_frame",
"dasp_peak",
"dasp_ring_buffer",
"dasp_rms",
"dasp_sample",
]
[[package]]
name = "dasp_frame"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b2a3937f5fe2135702897535c8d4a5553f8b116f76c1529088797f2eee7c5cd6"
dependencies = [
"dasp_sample",
]
[[package]]
name = "dasp_interpolate"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7fc975a6563bb7ca7ec0a6c784ead49983a21c24835b0bc96eea11ee407c7486"
dependencies = [
"dasp_frame",
"dasp_ring_buffer",
"dasp_sample",
]
[[package]]
name = "dasp_peak"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5cf88559d79c21f3d8523d91250c397f9a15b5fc72fbb3f87fdb0a37b79915bf"
dependencies = [
"dasp_frame",
"dasp_sample",
]
[[package]]
name = "dasp_ring_buffer"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "07d79e19b89618a543c4adec9c5a347fe378a19041699b3278e616e387511ea1"
[[package]]
name = "dasp_rms"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a6c5dcb30b7e5014486e2822537ea2beae50b19722ffe2ed7549ab03774575aa"
dependencies = [
"dasp_frame",
"dasp_ring_buffer",
"dasp_sample",
]
[[package]]
name = "dasp_sample"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0c87e182de0887fd5361989c677c4e8f5000cd9491d6d563161a8f3a5519fc7f"
[[package]]
name = "dasp_signal"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "aa1ab7d01689c6ed4eae3d38fe1cea08cba761573fbd2d592528d55b421077e7"
dependencies = [
"dasp_envelope",
"dasp_frame",
"dasp_interpolate",
"dasp_peak",
"dasp_ring_buffer",
"dasp_rms",
"dasp_sample",
"dasp_window",
]
[[package]]
name = "dasp_slice"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4e1c7335d58e7baedafa516cb361360ff38d6f4d3f9d9d5ee2a2fc8e27178fa1"
dependencies = [
"dasp_frame",
"dasp_sample",
]
[[package]]
name = "dasp_window"
version = "0.11.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "99ded7b88821d2ce4e8b842c9f1c86ac911891ab89443cc1de750cae764c5076"
dependencies = [
"dasp_sample",
]
[[package]]
name = "data-encoding"
version = "2.10.0"
@@ -1214,6 +1369,12 @@ dependencies = [
"subtle",
]
[[package]]
name = "hashbrown"
version = "0.12.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8a9ee70c43aaf417c914396645a0fa852624801b24ebb7ae78fe8272889ac888"
[[package]]
name = "hashbrown"
version = "0.15.5"
@@ -1246,6 +1407,15 @@ version = "0.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
[[package]]
name = "hermit-abi"
version = "0.1.19"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "62b467343b94ba476dcb2500d242dadbb39557df889310ac77c5d99100aaac33"
dependencies = [
"libc",
]
[[package]]
name = "hex"
version = "0.4.3"
@@ -1446,6 +1616,16 @@ dependencies = [
"zstd",
]
[[package]]
name = "indexmap"
version = "1.9.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bd070e393353796e801d209ad339e89596eb4c8d430d18ede6a1cced8fafbd99"
dependencies = [
"autocfg",
"hashbrown 0.12.3",
]
[[package]]
name = "indexmap"
version = "2.14.0"
@@ -1739,7 +1919,13 @@ version = "0.5.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "805d5964d1e7a0006a7fdced7dae75084d66d18b35f1dfe81bd76929b1f8da0c"
dependencies = [
"anyhow",
"clap",
"dasp",
"dasp_interpolate",
"dasp_ring_buffer",
"easyfft",
"hound",
"once_cell",
]
@@ -1905,6 +2091,12 @@ dependencies = [
"ureq",
]
[[package]]
name = "os_str_bytes"
version = "6.6.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e2355d85b9a3786f481747ced0e0ff2ba35213a1f9bd406ed906554d7af805a1"
[[package]]
name = "p256"
version = "0.11.1"
@@ -2883,6 +3075,21 @@ dependencies = [
"windows-sys",
]
[[package]]
name = "termcolor"
version = "1.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "06794f8f6c5c898b3275aebefa6b8a1cb24cd2c6c79397ab15774837a0bc5755"
dependencies = [
"winapi-util",
]
[[package]]
name = "textwrap"
version = "0.16.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c13547615a44dc9c452a8a534638acdf07120d4b6847c8178705da06306a3057"
[[package]]
name = "thiserror"
version = "1.0.69"
@@ -3244,7 +3451,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bb0e353e6a2fbdc176932bbaab493762eb1255a7900fe0fea1a2f96c296cc909"
dependencies = [
"anyhow",
"indexmap",
"indexmap 2.14.0",
"wasm-encoder",
"wasmparser",
]
@@ -3257,7 +3464,7 @@ checksum = "47b807c72e1bac69382b3a6fb3dbe8ea4c0ed87ff5629b8685ae6b9a611028fe"
dependencies = [
"bitflags 2.11.0",
"hashbrown 0.15.5",
"indexmap",
"indexmap 2.14.0",
"semver",
]
@@ -3515,6 +3722,15 @@ version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
[[package]]
name = "winapi-util"
version = "0.1.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
dependencies = [
"windows-sys",
]
[[package]]
name = "winapi-x86_64-pc-windows-gnu"
version = "0.4.0"
@@ -3564,7 +3780,7 @@ checksum = "b7c566e0f4b284dd6561c786d9cb0142da491f46a9fbed79ea69cdad5db17f21"
dependencies = [
"anyhow",
"heck",
"indexmap",
"indexmap 2.14.0",
"prettyplease",
"syn 2.0.117",
"wasm-metadata",
@@ -3595,7 +3811,7 @@ checksum = "9d66ea20e9553b30172b5e831994e35fbde2d165325bec84fc43dbf6f4eb9cb2"
dependencies = [
"anyhow",
"bitflags 2.11.0",
"indexmap",
"indexmap 2.14.0",
"log",
"serde",
"serde_derive",
@@ -3614,7 +3830,7 @@ checksum = "ecc8ac4bc1dc3381b7f59c34f00b67e18f910c2c0f50015669dde7def656a736"
dependencies = [
"anyhow",
"id-arena",
"indexmap",
"indexmap 2.14.0",
"log",
"semver",
"serde",

View File

@@ -7,4 +7,4 @@ edition = "2021"
audiopus = "0.3.0-rc.0"
ezk-g722 = "0.1"
rubato = "0.14"
nnnoiseless = { version = "0.5", default-features = false }
nnnoiseless = "0.5"

View File

@@ -301,19 +301,59 @@ impl TranscodeState {
/// Decode an encoded audio payload to f32 PCM samples in [-1.0, 1.0].
/// Returns (samples, sample_rate).
///
/// For Opus, uses native float decode (no i16 quantization).
/// For G.722/G.711, decodes to i16 then converts (codec is natively i16).
pub fn decode_to_f32(&mut self, data: &[u8], pt: u8) -> Result<(Vec<f32>, u32), String> {
let (pcm_i16, rate) = self.decode_to_pcm(data, pt)?;
let pcm_f32 = pcm_i16.iter().map(|&s| s as f32 / 32768.0).collect();
Ok((pcm_f32, rate))
match pt {
PT_OPUS => {
let mut pcm = vec![0.0f32; 5760]; // up to 120ms at 48kHz
let packet =
OpusPacket::try_from(data).map_err(|e| format!("opus packet: {e}"))?;
let out =
MutSignals::try_from(&mut pcm[..]).map_err(|e| format!("opus signals: {e}"))?;
let n: usize = self
.opus_dec
.decode_float(Some(packet), out, false)
.map_err(|e| format!("opus decode_float: {e}"))?
.into();
pcm.truncate(n);
Ok((pcm, 48000))
}
_ => {
// G.722, PCMU, PCMA: natively i16 codecs — decode then convert.
let (pcm_i16, rate) = self.decode_to_pcm(data, pt)?;
let pcm_f32 = pcm_i16.iter().map(|&s| s as f32 / 32768.0).collect();
Ok((pcm_f32, rate))
}
}
}
/// Encode f32 PCM samples ([-1.0, 1.0]) to an audio codec.
///
/// For Opus, uses native float encode (no i16 quantization).
/// For G.722/G.711, converts to i16 then encodes (codec is natively i16).
pub fn encode_from_f32(&mut self, pcm: &[f32], pt: u8) -> Result<Vec<u8>, String> {
let pcm_i16: Vec<i16> = pcm
.iter()
.map(|&s| (s * 32767.0).round().clamp(-32768.0, 32767.0) as i16)
.collect();
self.encode_from_pcm(&pcm_i16, pt)
match pt {
PT_OPUS => {
let mut buf = vec![0u8; 4000];
let n: usize = self
.opus_enc
.encode_float(pcm, &mut buf)
.map_err(|e| format!("opus encode_float: {e}"))?
.into();
buf.truncate(n);
Ok(buf)
}
_ => {
// G.722, PCMU, PCMA: natively i16 codecs.
let pcm_i16: Vec<i16> = pcm
.iter()
.map(|&s| (s * 32767.0).round().clamp(-32768.0, 32767.0) as i16)
.collect();
self.encode_from_pcm(&pcm_i16, pt)
}
}
}
/// High-quality sample rate conversion for f32 PCM using rubato FFT resampler.

View File

@@ -10,7 +10,7 @@ path = "src/main.rs"
[dependencies]
codec-lib = { path = "../codec-lib" }
sip-proto = { path = "../sip-proto" }
nnnoiseless = { version = "0.5", default-features = false }
nnnoiseless = "0.5"
tokio = { version = "1", features = ["full"] }
serde = { version = "1", features = ["derive"] }
serde_json = "1"

View File

@@ -20,6 +20,35 @@ use std::net::SocketAddr;
use std::sync::Arc;
use tokio::net::UdpSocket;
/// Emit a `leg_added` event with full leg information.
/// Free function (not a method) to avoid `&self` borrow conflicts when `self.calls` is borrowed.
fn emit_leg_added_event(tx: &OutTx, call_id: &str, leg: &LegInfo) {
let metadata: serde_json::Value = if leg.metadata.is_empty() {
serde_json::json!({})
} else {
serde_json::Value::Object(
leg.metadata
.iter()
.map(|(k, v)| (k.clone(), v.clone()))
.collect(),
)
};
emit_event(
tx,
"leg_added",
serde_json::json!({
"call_id": call_id,
"leg_id": leg.id,
"kind": leg.kind.as_str(),
"state": leg.state.as_str(),
"codec": sip_proto::helpers::codec_name(leg.codec_pt),
"rtpPort": leg.rtp_port,
"remoteMedia": leg.remote_media.map(|a| format!("{}:{}", a.ip(), a.port())),
"metadata": metadata,
}),
);
}
pub struct CallManager {
/// All active calls, keyed by internal call ID.
pub calls: HashMap<String, Call>,
@@ -167,7 +196,17 @@ impl CallManager {
};
// Mutable borrow on call/leg is now released.
let sip_pt = codecs.first().copied().unwrap_or(9);
let mut sip_pt = codecs.first().copied().unwrap_or(9);
// If the message has SDP (e.g., 200 OK answer), use the negotiated codec
// instead of the offered one.
if msg.has_sdp_body() {
if let Some(ep) = parse_sdp_endpoint(&msg.body) {
if let Some(pt) = ep.codec_pt {
sip_pt = pt;
}
}
}
match action {
SipLegAction::None => {}
@@ -265,14 +304,27 @@ impl CallManager {
dev_leg.state = LegState::Connected;
}
}
emit_event(
&self.out_tx,
"leg_state_changed",
serde_json::json!({ "call_id": call_id, "leg_id": dev_leg_id, "state": "connected" }),
);
// Wire device leg to mixer.
// Use the device's preferred codec from its INVITE SDP,
// not the provider's negotiated codec.
let dev_pt = device_invite
.has_sdp_body()
.then(|| parse_sdp_endpoint(&device_invite.body))
.flatten()
.and_then(|ep| ep.codec_pt)
.unwrap_or(sip_pt);
if let Some(dev_remote_addr) = dev_remote {
let dev_channels = create_leg_channels();
spawn_sip_inbound(dev_rtp_socket.clone(), dev_channels.inbound_tx);
spawn_sip_outbound(dev_rtp_socket, dev_remote_addr, dev_channels.outbound_rx);
if let Some(call) = self.calls.get(call_id) {
call.add_leg_to_mixer(&dev_leg_id, sip_pt, dev_channels.inbound_rx, dev_channels.outbound_tx)
call.add_leg_to_mixer(&dev_leg_id, dev_pt, dev_channels.inbound_rx, dev_channels.outbound_tx)
.await;
}
}
@@ -324,6 +376,8 @@ impl CallManager {
leg.state = LegState::Terminated;
}
}
emit_event(&self.out_tx, "leg_state_changed",
serde_json::json!({ "call_id": call_id, "leg_id": leg_id, "state": "terminated" }));
emit_event(&self.out_tx, "call_ended",
serde_json::json!({ "call_id": call_id, "reason": reason, "duration": duration }));
self.terminate_call(call_id).await;
@@ -529,21 +583,30 @@ impl CallManager {
if let Some(leg) = call.legs.get_mut(this_leg_id) {
leg.state = LegState::Ringing;
}
emit_event(&self.out_tx, "leg_state_changed",
serde_json::json!({ "call_id": call_id, "leg_id": this_leg_id, "state": "ringing" }));
} else if code >= 200 && code < 300 {
let mut needs_wiring = false;
if let Some(leg) = call.legs.get_mut(this_leg_id) {
leg.state = LegState::Connected;
// Learn remote media from SDP.
// Learn remote media and negotiated codec from SDP answer.
if msg.has_sdp_body() {
if let Some(ep) = parse_sdp_endpoint(&msg.body) {
if let Ok(addr) = format!("{}:{}", ep.address, ep.port).parse() {
leg.remote_media = Some(addr);
}
// Use the codec from the SDP answer (what the remote actually selected).
if let Some(pt) = ep.codec_pt {
leg.codec_pt = pt;
}
}
}
needs_wiring = true;
}
emit_event(&self.out_tx, "leg_state_changed",
serde_json::json!({ "call_id": call_id, "leg_id": this_leg_id, "state": "connected" }));
if call.state != CallState::Connected {
call.state = CallState::Connected;
emit_event(&self.out_tx, "call_answered", serde_json::json!({ "call_id": call_id }));
@@ -689,15 +752,19 @@ impl CallManager {
call.callee_number = Some(called_number);
call.state = CallState::Ringing;
let codec_pt = provider_config.codecs.first().copied().unwrap_or(9);
let mut codec_pt = provider_config.codecs.first().copied().unwrap_or(9);
// Provider leg — extract media from SDP.
// Provider leg — extract media and negotiated codec from SDP.
let mut provider_media: Option<SocketAddr> = None;
if invite.has_sdp_body() {
if let Some(ep) = parse_sdp_endpoint(&invite.body) {
if let Ok(addr) = format!("{}:{}", ep.address, ep.port).parse() {
provider_media = Some(addr);
}
// Use the codec from the provider's SDP offer (what they actually want to use).
if let Some(pt) = ep.codec_pt {
codec_pt = pt;
}
}
}
@@ -767,6 +834,16 @@ impl CallManager {
// Store the call.
self.calls.insert(call_id.clone(), call);
// Emit leg_added for both initial legs.
if let Some(call) = self.calls.get(&call_id) {
if let Some(leg) = call.legs.get(&provider_leg_id) {
emit_leg_added_event(&self.out_tx, &call_id, leg);
}
if let Some(leg) = call.legs.get(&device_leg_id) {
emit_leg_added_event(&self.out_tx, &call_id, leg);
}
}
Some(call_id)
}
@@ -854,6 +931,14 @@ impl CallManager {
.insert(sip_call_id, (call_id.clone(), leg_id));
self.calls.insert(call_id.clone(), call);
// Emit leg_added for the provider leg.
if let Some(call) = self.calls.get(&call_id) {
for leg in call.legs.values() {
emit_leg_added_event(&self.out_tx, &call_id, leg);
}
}
Some(call_id)
}
@@ -1002,6 +1087,14 @@ impl CallManager {
.insert(provider_sip_call_id, (call_id.clone(), provider_leg_id));
self.calls.insert(call_id.clone(), call);
// Emit leg_added for both initial legs (device + provider).
if let Some(call) = self.calls.get(&call_id) {
for leg in call.legs.values() {
emit_leg_added_event(&self.out_tx, &call_id, leg);
}
}
Some(call_id)
}
@@ -1069,17 +1162,11 @@ impl CallManager {
let call = self.calls.get_mut(call_id).unwrap();
call.legs.insert(leg_id.clone(), leg_info);
emit_event(
&self.out_tx,
"leg_added",
serde_json::json!({
"call_id": call_id,
"leg_id": leg_id,
"kind": "sip-provider",
"state": "inviting",
"number": number,
}),
);
if let Some(call) = self.calls.get(call_id) {
if let Some(leg) = call.legs.get(&leg_id) {
emit_leg_added_event(&self.out_tx, call_id, leg);
}
}
Some(leg_id)
}
@@ -1145,17 +1232,11 @@ impl CallManager {
let call = self.calls.get_mut(call_id).unwrap();
call.legs.insert(leg_id.clone(), leg_info);
emit_event(
&self.out_tx,
"leg_added",
serde_json::json!({
"call_id": call_id,
"leg_id": leg_id,
"kind": "sip-device",
"state": "inviting",
"device_id": device_id,
}),
);
if let Some(call) = self.calls.get(call_id) {
if let Some(leg) = call.legs.get(&leg_id) {
emit_leg_added_event(&self.out_tx, call_id, leg);
}
}
Some(leg_id)
}
@@ -1242,6 +1323,13 @@ impl CallManager {
None => return false,
};
// Emit leg_removed for source call.
emit_event(
&self.out_tx,
"leg_removed",
serde_json::json!({ "call_id": source_call_id, "leg_id": leg_id }),
);
// Update SIP index to point to the target call.
if let Some(sip_cid) = &leg_info.sip_call_id {
self.sip_index.insert(
@@ -1274,15 +1362,12 @@ impl CallManager {
let target_call = self.calls.get_mut(target_call_id).unwrap();
target_call.legs.insert(leg_id.to_string(), leg_info);
emit_event(
&self.out_tx,
"leg_transferred",
serde_json::json!({
"leg_id": leg_id,
"source_call_id": source_call_id,
"target_call_id": target_call_id,
}),
);
// Emit leg_added for target call.
if let Some(target) = self.calls.get(target_call_id) {
if let Some(leg) = target.legs.get(leg_id) {
emit_leg_added_event(&self.out_tx, target_call_id, leg);
}
}
// Check if source call has too few legs remaining.
let source_call = self.calls.get(source_call_id).unwrap();
@@ -1385,6 +1470,11 @@ impl CallManager {
}
}
leg.state = LegState::Terminated;
emit_event(
&self.out_tx,
"leg_state_changed",
serde_json::json!({ "call_id": call_id, "leg_id": leg.id, "state": "terminated" }),
);
}
emit_event(
@@ -1503,6 +1593,13 @@ impl CallManager {
);
self.calls.insert(call_id.to_string(), call);
// Emit leg_added for the provider leg.
if let Some(call) = self.calls.get(call_id) {
for leg in call.legs.values() {
emit_leg_added_event(&self.out_tx, call_id, leg);
}
}
// Build recording path.
let timestamp = std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)

View File

@@ -35,7 +35,8 @@ pub fn create_leg_channels() -> LegChannels {
}
/// Spawn the inbound I/O task for a SIP leg.
/// Reads RTP from the socket, strips the 12-byte header, sends payload to the mixer.
/// Reads RTP from the socket, parses the variable-length header (RFC 3550),
/// and sends the payload to the mixer.
/// Returns the JoinHandle (exits when the inbound_tx channel is dropped).
pub fn spawn_sip_inbound(
rtp_socket: Arc<UdpSocket>,
@@ -51,12 +52,29 @@ pub fn spawn_sip_inbound(
}
let pt = buf[1] & 0x7F;
let marker = (buf[1] & 0x80) != 0;
let seq = u16::from_be_bytes([buf[2], buf[3]]);
let timestamp = u32::from_be_bytes([buf[4], buf[5], buf[6], buf[7]]);
let payload = buf[12..n].to_vec();
// RFC 3550: header length = 12 + (CC * 4) + optional extension.
let cc = (buf[0] & 0x0F) as usize;
let has_extension = (buf[0] & 0x10) != 0;
let mut offset = 12 + cc * 4;
if has_extension {
if offset + 4 > n {
continue; // Malformed: extension header truncated.
}
let ext_len = u16::from_be_bytes([buf[offset + 2], buf[offset + 3]]) as usize;
offset += 4 + ext_len * 4;
}
if offset >= n {
continue; // No payload after header.
}
let payload = buf[offset..n].to_vec();
if payload.is_empty() {
continue;
}
if inbound_tx.send(RtpPacket { payload, payload_type: pt, marker, timestamp }).await.is_err() {
if inbound_tx.send(RtpPacket { payload, payload_type: pt, marker, seq, timestamp }).await.is_err() {
break; // Channel closed — leg removed.
}
}

View File

@@ -677,6 +677,10 @@ async fn handle_webrtc_link(
"leg_id": session_id,
"kind": "webrtc",
"state": "connected",
"codec": "Opus",
"rtpPort": 0,
"remoteMedia": null,
"metadata": {},
}));
respond_ok(out_tx, &cmd.id, serde_json::json!({
@@ -1125,8 +1129,11 @@ async fn handle_add_tool_leg(
"call_id": call_id,
"leg_id": tool_leg_id,
"kind": "tool",
"tool_type": tool_type_str,
"state": "connected",
"codec": null,
"rtpPort": 0,
"remoteMedia": null,
"metadata": { "tool_type": tool_type_str },
}),
);

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.
// Only for SIP telephony legs — WebRTC browsers
// already apply 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) {

View File

@@ -290,8 +290,9 @@ async fn browser_to_mixer_loop(
.send(RtpPacket {
payload: payload.to_vec(),
payload_type: PT_OPUS,
marker: false,
timestamp: 0,
marker: rtp_packet.header.marker,
seq: rtp_packet.header.sequence_number,
timestamp: rtp_packet.header.timestamp,
})
.await;
}

View File

@@ -197,10 +197,11 @@ pub fn compute_digest_auth(
use crate::Endpoint;
/// Parse the audio media port and connection address from an SDP body.
/// Parse the audio media port, connection address, and preferred codec from an SDP body.
pub fn parse_sdp_endpoint(sdp: &str) -> Option<Endpoint> {
let mut addr: Option<&str> = None;
let mut port: Option<u16> = None;
let mut codec_pt: Option<u8> = None;
let normalized = sdp.replace("\r\n", "\n");
for raw in normalized.split('\n') {
@@ -208,10 +209,16 @@ pub fn parse_sdp_endpoint(sdp: &str) -> Option<Endpoint> {
if let Some(rest) = line.strip_prefix("c=IN IP4 ") {
addr = Some(rest.trim());
} else if let Some(rest) = line.strip_prefix("m=audio ") {
// m=audio <port> RTP/AVP <pt1> [<pt2> ...]
let parts: Vec<&str> = rest.split_whitespace().collect();
if !parts.is_empty() {
port = parts[0].parse().ok();
}
// parts[1] is "RTP/AVP" or similar, parts[2..] are payload types.
// The first PT is the preferred codec.
if parts.len() > 2 {
codec_pt = parts[2].parse::<u8>().ok();
}
}
}
@@ -219,6 +226,7 @@ pub fn parse_sdp_endpoint(sdp: &str) -> Option<Endpoint> {
(Some(a), Some(p)) => Some(Endpoint {
address: a.to_string(),
port: p,
codec_pt,
}),
_ => None,
}

View File

@@ -9,9 +9,11 @@ pub mod dialog;
pub mod helpers;
pub mod rewrite;
/// Network endpoint (address + port).
/// Network endpoint (address + port + optional negotiated codec).
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct Endpoint {
pub address: String,
pub port: u16,
/// First payload type from the SDP `m=audio` line (the preferred codec).
pub codec_pt: Option<u8>,
}

View File

@@ -92,7 +92,7 @@ pub fn rewrite_sdp(body: &str, ip: &str, port: u16) -> (String, Option<Endpoint>
.collect();
let original = match (orig_addr, orig_port) {
(Some(a), Some(p)) => Some(Endpoint { address: a, port: p }),
(Some(a), Some(p)) => Some(Endpoint { address: a, port: p, codec_pt: None }),
_ => None,
};

View File

@@ -3,6 +3,6 @@
*/
export const commitinfo = {
name: 'siprouter',
version: '1.17.0',
version: '1.17.2',
description: 'undefined'
}

View File

@@ -425,9 +425,9 @@ async function startProxyEngine(): Promise<void> {
id: data.leg_id,
type: data.kind,
state: data.state,
codec: null,
rtpPort: null,
remoteMedia: null,
codec: data.codec ?? null,
rtpPort: data.rtpPort ?? null,
remoteMedia: data.remoteMedia ?? null,
metadata: data.metadata || {},
});
}

View File

@@ -3,6 +3,6 @@
*/
export const commitinfo = {
name: 'siprouter',
version: '1.17.0',
version: '1.17.2',
description: 'undefined'
}