2 Commits

Author SHA1 Message Date
Siavash Sameni
073756ed4b fix: auto-switch decoder codec to match incoming packets
The CallDecoder now inspects each incoming packet's codec_id and
automatically switches the audio decoder if it differs from the
current profile. This enables cross-codec interop where one client
sends Opus and the other sends Codec2 — previously the receiver
would try to decode with the wrong codec, producing garbled audio.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 15:25:24 +04:00
Siavash Sameni
2fcc2d77cf feat: add --profile/--codec flag to CLI for forcing codec selection
Enables debugging Codec2 by allowing forced codec selection from CLI.
Supports: good, degraded, catastrophic, codec2-3200, codec2-1200.
Frame size, timing, and jitter buffer are all adjusted dynamically
based on the selected profile.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 15:23:36 +04:00
14 changed files with 45 additions and 715 deletions

View File

@@ -532,9 +532,6 @@ impl CallDecoder {
frames_per_block: 5,
},
CodecId::Opus6k => QualityProfile::DEGRADED,
CodecId::Opus32k => QualityProfile::STUDIO_32K,
CodecId::Opus48k => QualityProfile::STUDIO_48K,
CodecId::Opus64k => QualityProfile::STUDIO_64K,
CodecId::Codec2_3200 => QualityProfile {
codec: CodecId::Codec2_3200,
fec_ratio: 0.5,

View File

@@ -133,12 +133,9 @@ fn resolve_profile(name: &str) -> wzp_proto::QualityProfile {
frame_duration_ms: 20,
frames_per_block: 5,
},
"studio-32k" | "opus32k" | "32k" => QualityProfile::STUDIO_32K,
"studio-48k" | "opus48k" | "48k" | "studio" => QualityProfile::STUDIO_48K,
"studio-64k" | "opus64k" | "64k" | "studio-high" => QualityProfile::STUDIO_64K,
other => {
eprintln!("unknown profile: {other}");
eprintln!("valid: good, degraded, catastrophic, codec2-3200, codec2-1200, studio-32k, studio-48k, studio-64k");
eprintln!("valid: good, degraded, catastrophic, codec2-3200, codec2-1200");
std::process::exit(1);
}
}

View File

@@ -38,9 +38,6 @@ pub async fn perform_handshake(
ephemeral_pub,
signature,
supported_profiles: vec![
QualityProfile::STUDIO_64K,
QualityProfile::STUDIO_48K,
QualityProfile::STUDIO_32K,
QualityProfile::GOOD,
QualityProfile::DEGRADED,
QualityProfile::CATASTROPHIC,

View File

@@ -79,7 +79,7 @@ impl AudioDecoder for OpusDecoder {
fn set_profile(&mut self, profile: QualityProfile) -> Result<(), CodecError> {
match profile.codec {
c if c.is_opus() => {
CodecId::Opus24k | CodecId::Opus16k | CodecId::Opus6k => {
self.codec_id = profile.codec;
self.frame_duration_ms = profile.frame_duration_ms;
Ok(())

View File

@@ -100,7 +100,7 @@ impl AudioEncoder for OpusEncoder {
fn set_profile(&mut self, profile: QualityProfile) -> Result<(), CodecError> {
match profile.codec {
c if c.is_opus() => {
CodecId::Opus24k | CodecId::Opus16k | CodecId::Opus6k => {
self.codec_id = profile.codec;
self.frame_duration_ms = profile.frame_duration_ms;
self.apply_bitrate(profile.codec)?;

View File

@@ -18,12 +18,6 @@ pub enum CodecId {
Codec2_1200 = 4,
/// Comfort noise descriptor (silence suppression)
ComfortNoise = 5,
/// Opus at 32kbps (studio low)
Opus32k = 6,
/// Opus at 48kbps (studio)
Opus48k = 7,
/// Opus at 64kbps (studio high)
Opus64k = 8,
}
impl CodecId {
@@ -33,9 +27,6 @@ impl CodecId {
Self::Opus24k => 24_000,
Self::Opus16k => 16_000,
Self::Opus6k => 6_000,
Self::Opus32k => 32_000,
Self::Opus48k => 48_000,
Self::Opus64k => 64_000,
Self::Codec2_3200 => 3_200,
Self::Codec2_1200 => 1_200,
Self::ComfortNoise => 0,
@@ -45,7 +36,8 @@ impl CodecId {
/// Preferred frame duration in milliseconds.
pub const fn frame_duration_ms(self) -> u8 {
match self {
Self::Opus24k | Self::Opus16k | Self::Opus32k | Self::Opus48k | Self::Opus64k => 20,
Self::Opus24k => 20,
Self::Opus16k => 20,
Self::Opus6k => 40,
Self::Codec2_3200 => 20,
Self::Codec2_1200 => 40,
@@ -56,8 +48,7 @@ impl CodecId {
/// Sample rate expected by this codec.
pub const fn sample_rate_hz(self) -> u32 {
match self {
Self::Opus24k | Self::Opus16k | Self::Opus6k
| Self::Opus32k | Self::Opus48k | Self::Opus64k => 48_000,
Self::Opus24k | Self::Opus16k | Self::Opus6k => 48_000,
Self::Codec2_3200 | Self::Codec2_1200 => 8_000,
Self::ComfortNoise => 48_000,
}
@@ -72,9 +63,6 @@ impl CodecId {
3 => Some(Self::Codec2_3200),
4 => Some(Self::Codec2_1200),
5 => Some(Self::ComfortNoise),
6 => Some(Self::Opus32k),
7 => Some(Self::Opus48k),
8 => Some(Self::Opus64k),
_ => None,
}
}
@@ -83,12 +71,6 @@ impl CodecId {
pub const fn to_wire(self) -> u8 {
self as u8
}
/// Returns true if this is an Opus variant.
pub const fn is_opus(self) -> bool {
matches!(self, Self::Opus6k | Self::Opus16k | Self::Opus24k
| Self::Opus32k | Self::Opus48k | Self::Opus64k)
}
}
/// Describes the complete quality configuration for a call session.
@@ -129,30 +111,6 @@ impl QualityProfile {
frames_per_block: 8,
};
/// Studio low: Opus 32kbps, minimal FEC.
pub const STUDIO_32K: Self = Self {
codec: CodecId::Opus32k,
fec_ratio: 0.1,
frame_duration_ms: 20,
frames_per_block: 5,
};
/// Studio: Opus 48kbps, minimal FEC.
pub const STUDIO_48K: Self = Self {
codec: CodecId::Opus48k,
fec_ratio: 0.1,
frame_duration_ms: 20,
frames_per_block: 5,
};
/// Studio high: Opus 64kbps, minimal FEC.
pub const STUDIO_64K: Self = Self {
codec: CodecId::Opus64k,
fec_ratio: 0.1,
frame_duration_ms: 20,
frames_per_block: 5,
};
/// Estimated total bandwidth in kbps including FEC overhead.
pub fn total_bitrate_kbps(&self) -> f32 {
let base = self.codec.bitrate_bps() as f32 / 1000.0;

View File

@@ -670,10 +670,6 @@ pub struct RoomParticipant {
pub fingerprint: String,
/// Optional display name set by the client.
pub alias: Option<String>,
/// Relay label — identifies which relay this participant is connected to.
/// None for local participants, Some("Relay B") for federated.
#[serde(default)]
pub relay_label: Option<String>,
}
/// Reasons for ending a call.

View File

@@ -91,23 +91,6 @@
</div>
<div class="settings-section">
<h3>Audio</h3>
<div class="quality-control">
<div class="quality-header">
<span class="setting-label">QUALITY</span>
<span id="s-quality-label" class="quality-label">Auto</span>
</div>
<input id="s-quality" type="range" min="0" max="7" step="1" value="3" class="quality-slider" />
<div class="quality-ticks">
<span>64k</span>
<span>48k</span>
<span>32k</span>
<span>Auto</span>
<span>24k</span>
<span>6k</span>
<span>C2</span>
<span>1.2k</span>
</div>
</div>
<label class="checkbox">
<input id="s-os-aec" type="checkbox" />
OS Echo Cancellation (macOS VoiceProcessingIO)
@@ -154,28 +137,6 @@
</div>
</div>
</div>
<!-- Key changed warning dialog -->
<div id="key-warning" class="hidden">
<div class="settings-card key-warning-card">
<div class="key-warning-icon">&#9888;</div>
<h2>Server Key Changed</h2>
<p class="key-warning-text">The relay's identity has changed since you last connected. This usually happens when the server was restarted, but could also indicate a security issue.</p>
<div class="key-warning-fps">
<div class="key-fp-row">
<span class="key-fp-label">Previously known</span>
<code id="kw-old-fp" class="key-fp"></code>
</div>
<div class="key-fp-row">
<span class="key-fp-label">New key</span>
<code id="kw-new-fp" class="key-fp"></code>
</div>
</div>
<div class="key-warning-actions">
<button id="kw-accept" class="primary">Accept New Key</button>
<button id="kw-cancel" class="secondary-btn">Cancel</button>
</div>
</div>
</div>
</div>
<script type="module" src="/src/main.ts"></script>
</body>

View File

@@ -11,29 +11,9 @@ use tracing::{error, info};
use wzp_client::audio_io::{AudioCapture, AudioPlayback};
use wzp_client::call::{CallConfig, CallEncoder};
use wzp_proto::{CodecId, MediaTransport, QualityProfile};
use wzp_proto::MediaTransport;
const FRAME_SAMPLES_40MS: usize = 1920;
/// Resolve a quality string from the UI to a QualityProfile.
/// Returns None for "auto" (use default adaptive behavior).
fn resolve_quality(quality: &str) -> Option<QualityProfile> {
match quality {
"good" | "opus" => Some(QualityProfile::GOOD),
"degraded" | "opus6k" => Some(QualityProfile::DEGRADED),
"catastrophic" | "codec2-1200" => Some(QualityProfile::CATASTROPHIC),
"codec2-3200" => Some(QualityProfile {
codec: CodecId::Codec2_3200,
fec_ratio: 0.5,
frame_duration_ms: 20,
frames_per_block: 5,
}),
"studio-32k" => Some(QualityProfile::STUDIO_32K),
"studio-48k" => Some(QualityProfile::STUDIO_48K),
"studio-64k" => Some(QualityProfile::STUDIO_64K),
_ => None, // "auto" or unknown
}
}
const FRAME_SAMPLES: usize = 960;
/// Wrapper to make non-Sync audio handles safe to store in shared state.
/// The audio handle is only accessed from the thread that created it (drop),
@@ -45,7 +25,6 @@ unsafe impl Sync for SyncWrapper {}
pub struct ParticipantInfo {
pub fingerprint: String,
pub alias: Option<String>,
pub relay_label: Option<String>,
}
pub struct EngineStatus {
@@ -57,8 +36,6 @@ pub struct EngineStatus {
pub audio_level: u32,
pub call_duration_secs: f64,
pub fingerprint: String,
pub tx_codec: String,
pub rx_codec: String,
}
pub struct CallEngine {
@@ -69,8 +46,6 @@ pub struct CallEngine {
frames_sent: Arc<AtomicU64>,
frames_received: Arc<AtomicU64>,
audio_level: Arc<AtomicU32>,
tx_codec: Arc<Mutex<String>>,
rx_codec: Arc<Mutex<String>>,
transport: Arc<wzp_transport::QuinnTransport>,
start_time: Instant,
fingerprint: String,
@@ -85,7 +60,6 @@ impl CallEngine {
room: String,
alias: String,
_os_aec: bool,
quality: String,
event_cb: F,
) -> Result<Self, anyhow::Error>
where
@@ -191,8 +165,6 @@ impl CallEngine {
let frames_sent = Arc::new(AtomicU64::new(0));
let frames_received = Arc::new(AtomicU64::new(0));
let audio_level = Arc::new(AtomicU32::new(0));
let tx_codec = Arc::new(Mutex::new(String::new()));
let rx_codec = Arc::new(Mutex::new(String::new()));
// Send task
let send_t = transport.clone();
@@ -201,34 +173,21 @@ impl CallEngine {
let send_fs = frames_sent.clone();
let send_level = audio_level.clone();
let send_drops = Arc::new(AtomicU64::new(0));
let send_quality = quality.clone();
let send_tx_codec = tx_codec.clone();
tokio::spawn(async move {
let profile = resolve_quality(&send_quality);
let config = match profile {
Some(p) => CallConfig {
noise_suppression: false,
suppression_enabled: false,
..CallConfig::from_profile(p)
},
None => CallConfig {
noise_suppression: false,
suppression_enabled: false,
..CallConfig::default()
},
let config = CallConfig {
noise_suppression: false,
suppression_enabled: false,
..CallConfig::default()
};
let frame_samples = (config.profile.frame_duration_ms as usize) * 48;
info!(codec = ?config.profile.codec, frame_samples, "send task starting");
*send_tx_codec.lock().await = format!("{:?}", config.profile.codec);
let mut encoder = CallEncoder::new(&config);
encoder.set_aec_enabled(false); // OS AEC or none
let mut buf = vec![0i16; frame_samples];
let mut buf = vec![0i16; FRAME_SAMPLES];
loop {
if !send_r.load(Ordering::Relaxed) {
break;
}
if capture_ring.available() < frame_samples {
if capture_ring.available() < FRAME_SAMPLES {
tokio::time::sleep(std::time::Duration::from_millis(5)).await;
continue;
}
@@ -262,18 +221,15 @@ impl CallEngine {
}
});
// Recv task (direct playout with auto codec switch)
// Recv task (direct playout)
let recv_t = transport.clone();
let recv_r = running.clone();
let recv_spk = spk_muted.clone();
let recv_fr = frames_received.clone();
let recv_rx_codec = rx_codec.clone();
tokio::spawn(async move {
let initial_profile = resolve_quality(&quality).unwrap_or(QualityProfile::GOOD);
let mut decoder = wzp_codec::create_decoder(initial_profile);
let mut current_codec = initial_profile.codec;
let mut opus_dec = wzp_codec::create_decoder(wzp_proto::QualityProfile::GOOD);
let mut agc = wzp_codec::AutoGainControl::new();
let mut pcm = vec![0i16; FRAME_SAMPLES_40MS]; // big enough for any codec
let mut pcm = vec![0i16; FRAME_SAMPLES];
loop {
if !recv_r.load(Ordering::Relaxed) {
@@ -286,33 +242,8 @@ impl CallEngine {
.await
{
Ok(Ok(Some(pkt))) => {
if !pkt.header.is_repair && pkt.header.codec_id != CodecId::ComfortNoise {
// Track RX codec
{
let mut rx = recv_rx_codec.lock().await;
let codec_name = format!("{:?}", pkt.header.codec_id);
if *rx != codec_name { *rx = codec_name; }
}
// Auto-switch decoder if incoming codec differs
if pkt.header.codec_id != current_codec {
let new_profile = match pkt.header.codec_id {
CodecId::Opus24k => QualityProfile::GOOD,
CodecId::Opus6k => QualityProfile::DEGRADED,
CodecId::Opus32k => QualityProfile::STUDIO_32K,
CodecId::Opus48k => QualityProfile::STUDIO_48K,
CodecId::Opus64k => QualityProfile::STUDIO_64K,
CodecId::Codec2_1200 => QualityProfile::CATASTROPHIC,
CodecId::Codec2_3200 => QualityProfile {
codec: CodecId::Codec2_3200,
fec_ratio: 0.5, frame_duration_ms: 20, frames_per_block: 5,
},
other => QualityProfile { codec: other, ..QualityProfile::GOOD },
};
info!(from = ?current_codec, to = ?pkt.header.codec_id, "recv: switching decoder");
let _ = decoder.set_profile(new_profile);
current_codec = pkt.header.codec_id;
}
if let Ok(n) = decoder.decode(&pkt.payload, &mut pcm) {
if !pkt.header.is_repair {
if let Ok(n) = opus_dec.decode(&pkt.payload, &mut pcm) {
agc.process_frame(&mut pcm[..n]);
if !recv_spk.load(Ordering::Relaxed) {
playout_ring.write(&pcm[..n]);
@@ -328,6 +259,7 @@ impl CallEngine {
error!("recv fatal: {e}");
break;
}
// Transient error — continue
}
Err(_) => {}
}
@@ -362,7 +294,6 @@ impl CallEngine {
.map(|p| ParticipantInfo {
fingerprint: p.fingerprint,
alias: p.alias,
relay_label: p.relay_label,
})
.collect();
let count = unique.len();
@@ -388,8 +319,6 @@ impl CallEngine {
transport,
start_time: Instant::now(),
fingerprint,
tx_codec,
rx_codec,
_audio_handle: SyncWrapper(audio_handle),
})
}
@@ -414,7 +343,6 @@ impl CallEngine {
.map(|p| ParticipantInfo {
fingerprint: p.fingerprint.clone(),
alias: p.alias.clone(),
relay_label: p.relay_label.clone(),
})
.collect()
}; // lock dropped here
@@ -427,8 +355,6 @@ impl CallEngine {
audio_level: self.audio_level.load(Ordering::Relaxed),
call_duration_secs: self.start_time.elapsed().as_secs_f64(),
fingerprint: self.fingerprint.clone(),
tx_codec: self.tx_codec.lock().await.clone(),
rx_codec: self.rx_codec.lock().await.clone(),
}
}

View File

@@ -18,7 +18,6 @@ struct CallEvent {
struct Participant {
fingerprint: String,
alias: Option<String>,
relay_label: Option<String>,
}
#[derive(Clone, Serialize)]
@@ -32,8 +31,6 @@ struct CallStatus {
audio_level: u32,
call_duration_secs: f64,
fingerprint: String,
tx_codec: String,
rx_codec: String,
}
struct AppState {
@@ -125,7 +122,6 @@ async fn connect(
room: String,
alias: String,
os_aec: bool,
quality: String,
) -> Result<String, String> {
let mut engine_lock = state.engine.lock().await;
if engine_lock.is_some() {
@@ -133,7 +129,7 @@ async fn connect(
}
let app_clone = app.clone();
match CallEngine::start(relay, room, alias, os_aec, quality, move |event_kind, message| {
match CallEngine::start(relay, room, alias, os_aec, move |event_kind, message| {
let _ = app_clone.emit(
"call-event",
CallEvent {
@@ -198,7 +194,6 @@ async fn get_status(state: tauri::State<'_, Arc<AppState>>) -> Result<CallStatus
.map(|p| Participant {
fingerprint: p.fingerprint,
alias: p.alias,
relay_label: p.relay_label,
})
.collect(),
encode_fps: status.frames_sent,
@@ -206,8 +201,6 @@ async fn get_status(state: tauri::State<'_, Arc<AppState>>) -> Result<CallStatus
audio_level: status.audio_level,
call_duration_secs: status.call_duration_secs,
fingerprint: status.fingerprint,
tx_codec: status.tx_codec,
rx_codec: status.rx_codec,
})
} else {
Ok(CallStatus {
@@ -220,8 +213,6 @@ async fn get_status(state: tauri::State<'_, Arc<AppState>>) -> Result<CallStatus
audio_level: 0,
call_duration_secs: 0.0,
fingerprint: String::new(),
tx_codec: String::new(),
rx_codec: String::new(),
})
}
}

View File

@@ -48,39 +48,10 @@ const sRoom = document.getElementById("s-room") as HTMLInputElement;
const sAlias = document.getElementById("s-alias") as HTMLInputElement;
const sOsAec = document.getElementById("s-os-aec") as HTMLInputElement;
const sAgc = document.getElementById("s-agc") as HTMLInputElement;
const sQuality = document.getElementById("s-quality") as HTMLInputElement;
const sQualityLabel = document.getElementById("s-quality-label")!;
// Quality slider config — best (left/green) to worst (right/red)
const QUALITY_STEPS = ["studio-64k", "studio-48k", "studio-32k", "auto", "good", "degraded", "codec2-3200", "catastrophic"];
const QUALITY_LABELS = ["Studio 64k", "Studio 48k", "Studio 32k", "Auto", "Opus 24k", "Opus 6k", "Codec2 3.2k", "Codec2 1.2k"];
const QUALITY_COLORS = ["#22c55e", "#4ade80", "#86efac", "#a3e635", "#facc15", "#f59e0b", "#e97320", "#991b1b"];
function qualityToIndex(q: string): number {
const idx = QUALITY_STEPS.indexOf(q);
return idx >= 0 ? idx : 3; // default to "auto" (index 3)
}
function updateQualityUI(index: number) {
sQualityLabel.textContent = QUALITY_LABELS[index];
sQualityLabel.style.color = QUALITY_COLORS[index];
sQuality.style.background = `linear-gradient(90deg, #22c55e 0%, #86efac 25%, #facc15 50%, #e97320 75%, #991b1b 100%)`;
}
sQuality.addEventListener("input", () => {
updateQualityUI(parseInt(sQuality.value));
});
const sFingerprint = document.getElementById("s-fingerprint")!;
const sRecentRooms = document.getElementById("s-recent-rooms")!;
const sClearRecent = document.getElementById("s-clear-recent")!;
// Key warning dialog
const keyWarning = document.getElementById("key-warning")!;
const kwOldFp = document.getElementById("kw-old-fp")!;
const kwNewFp = document.getElementById("kw-new-fp")!;
const kwAccept = document.getElementById("kw-accept")!;
const kwCancel = document.getElementById("kw-cancel")!;
let statusInterval: number | null = null;
let myFingerprint = "";
let userDisconnected = false;
@@ -103,7 +74,6 @@ interface Settings {
alias: string;
osAec: boolean;
agc: boolean;
quality: string;
recentRooms: RecentRoom[];
}
@@ -111,7 +81,7 @@ function loadSettings(): Settings {
const defaults: Settings = {
relays: [{ name: "Default", address: "193.180.213.68:4433" }],
selectedRelay: 0, room: "android", alias: "",
osAec: true, agc: true, quality: "auto", recentRooms: [],
osAec: true, agc: true, recentRooms: [],
};
try {
const raw = localStorage.getItem("wzp-settings");
@@ -382,28 +352,6 @@ connectBtn.addEventListener("click", doConnect);
el.addEventListener("keydown", (e) => { if (e.key === "Enter") doConnect(); })
);
function showKeyWarning(oldFp: string, newFp: string): Promise<boolean> {
return new Promise((resolve) => {
kwOldFp.textContent = oldFp;
kwNewFp.textContent = newFp;
keyWarning.classList.remove("hidden");
const cleanup = () => {
keyWarning.classList.add("hidden");
kwAccept.removeEventListener("click", onAccept);
kwCancel.removeEventListener("click", onCancel);
keyWarning.removeEventListener("click", onBackdrop);
};
const onAccept = () => { cleanup(); resolve(true); };
const onCancel = () => { cleanup(); resolve(false); };
const onBackdrop = (e: Event) => { if (e.target === keyWarning) { cleanup(); resolve(false); } };
kwAccept.addEventListener("click", onAccept);
kwCancel.addEventListener("click", onCancel);
keyWarning.addEventListener("click", onBackdrop);
});
}
async function doConnect() {
const relay = getSelectedRelay();
if (!relay) { connectError.textContent = "No relay selected"; return; }
@@ -411,13 +359,13 @@ async function doConnect() {
// Warn on fingerprint mismatch
const ls = lockStatus(relay);
if (ls === "changed") {
const accepted = await showKeyWarning(relay.knownFingerprint || "", relay.serverFingerprint || "");
if (!accepted) return;
if (!confirm(`Server fingerprint has changed!\n\nKnown: ${relay.knownFingerprint}\nNew: ${relay.serverFingerprint}\n\nThis could indicate a man-in-the-middle attack. Continue?`)) {
return;
}
// User accepted — update known fingerprint
const s = loadSettings();
s.relays[s.selectedRelay].knownFingerprint = relay.serverFingerprint;
saveSettingsObj(s);
renderRelayButton();
}
// Don't block connect on offline — ping may have failed transiently
@@ -440,7 +388,6 @@ async function doConnect() {
await invoke("connect", {
relay: relay.address, room: roomInput.value,
alias: aliasInput.value, osAec: osAecCheckbox.checked,
quality: s.quality || "auto",
});
showCallScreen();
} catch (e: any) {
@@ -540,56 +487,36 @@ async function pollStatus() {
const pct = rms > 0 ? Math.min(100, (Math.log(rms) / Math.log(32767)) * 100) : 0;
levelBar.style.width = `${pct}%`;
// Participants grouped by relay
// Participants with identicons
if (st.participants.length === 0) {
participantsDiv.innerHTML = '<div class="participants-empty">Waiting for participants...</div>';
} else {
participantsDiv.innerHTML = "";
// Group by relay_label (null = this relay)
const groups: Record<string, typeof st.participants> = {};
st.participants.forEach((p: any) => {
const relay = p.relay_label || "This Relay";
if (!groups[relay]) groups[relay] = [];
groups[relay].push(p);
});
st.participants.forEach((p) => {
const name = p.alias || "Anonymous";
const fp = p.fingerprint || "";
const isMe = fp && myFingerprint.includes(fp);
Object.entries(groups).forEach(([relay, members]) => {
// Relay header
const header = document.createElement("div");
header.className = "relay-group-header";
const isLocal = relay === "This Relay";
header.innerHTML = `<span class="relay-dot-small ${isLocal ? "green" : "blue"}"></span> ${escapeHtml(relay)}`;
participantsDiv.appendChild(header);
const row = document.createElement("div");
row.className = "participant";
// Participants under this relay
(members as any[]).forEach((p) => {
const name = p.alias || "Anonymous";
const fp = p.fingerprint || "";
const isMe = fp && myFingerprint.includes(fp);
// Identicon avatar
const icon = createIdenticonEl(fp || name, 36, true);
if (isMe) icon.style.outline = "2px solid var(--accent)";
row.appendChild(icon);
const row = document.createElement("div");
row.className = "participant";
const icon = createIdenticonEl(fp || name, 36, true);
if (isMe) icon.style.outline = "2px solid var(--accent)";
row.appendChild(icon);
const info = document.createElement("div");
info.className = "info";
info.innerHTML = `
<div class="name">${escapeHtml(name)} ${isMe ? '<span class="you-badge">you</span>' : ""}</div>
<div class="fp">${escapeHtml(fp ? fp.substring(0, 16) : "")}</div>
`;
row.appendChild(info);
participantsDiv.appendChild(row);
});
const info = document.createElement("div");
info.className = "info";
info.innerHTML = `
<div class="name">${escapeHtml(name)} ${isMe ? '<span class="you-badge">you</span>' : ""}</div>
<div class="fp">${escapeHtml(fp ? fp.substring(0, 16) : "")}</div>
`;
row.appendChild(info);
participantsDiv.appendChild(row);
});
}
// Stats line with codec badges
const txBadge = (st as any).tx_codec ? `<span class="codec-badge tx">${escapeHtml((st as any).tx_codec)}</span>` : "";
const rxBadge = (st as any).rx_codec ? `<span class="codec-badge rx">${escapeHtml((st as any).rx_codec)}</span>` : "";
statsDiv.innerHTML = `${txBadge} ${rxBadge} TX: ${st.encode_fps} | RX: ${st.recv_fps}`;
statsDiv.textContent = `TX: ${st.encode_fps} | RX: ${st.recv_fps}`;
} catch {}
}
@@ -603,9 +530,6 @@ listen("call-event", (event: any) => {
function openSettings() {
const s = loadSettings();
sRoom.value = s.room; sAlias.value = s.alias; sOsAec.checked = s.osAec;
const qi = qualityToIndex(s.quality || "auto");
sQuality.value = String(qi);
updateQualityUI(qi);
sFingerprint.textContent = myFingerprint || "(loading...)";
renderSettingsRecentRooms(s.recentRooms);
settingsPanel.classList.remove("hidden");
@@ -641,7 +565,6 @@ settingsPanel.addEventListener("click", (e) => { if (e.target === settingsPanel)
settingsSave.addEventListener("click", () => {
const s = loadSettings();
s.room = sRoom.value; s.alias = sAlias.value; s.osAec = sOsAec.checked;
s.quality = QUALITY_STEPS[parseInt(sQuality.value)] || "auto";
saveSettingsObj(s);
roomInput.value = s.room; aliasInput.value = s.alias; osAecCheckbox.checked = s.osAec;
renderRecentRooms(s.recentRooms);

View File

@@ -441,56 +441,6 @@ button.primary:disabled { opacity: 0.5; cursor: not-allowed; }
border-radius: 8px;
}
/* ── Relay group headers ── */
.relay-group-header {
display: flex;
align-items: center;
gap: 6px;
font-size: 11px;
text-transform: uppercase;
letter-spacing: 0.5px;
color: var(--text-dim);
padding: 6px 0 2px;
border-top: 1px solid #ffffff08;
margin-top: 4px;
}
.relay-group-header:first-child {
border-top: none;
margin-top: 0;
}
.relay-dot-small {
width: 6px;
height: 6px;
border-radius: 50%;
display: inline-block;
}
.relay-dot-small.green { background: var(--green); }
.relay-dot-small.blue { background: #60a5fa; }
/* ── Codec badges ── */
.codec-badge {
display: inline-block;
font-size: 10px;
font-weight: 600;
padding: 1px 6px;
border-radius: 4px;
font-family: monospace;
margin: 0 2px;
}
.codec-badge.tx {
background: #22c55e30;
color: #4ade80;
}
.codec-badge.rx {
background: #3b82f630;
color: #60a5fa;
}
/* ── Controls ── */
.controls {
display: flex;
@@ -701,172 +651,3 @@ button.primary:disabled { opacity: 0.5; cursor: not-allowed; }
}
.secondary-btn:hover { border-color: var(--accent); color: var(--text); }
/* ── Key warning dialog ── */
#key-warning {
position: fixed;
inset: 0;
background: rgba(0, 0, 0, 0.7);
backdrop-filter: blur(6px);
display: flex;
align-items: center;
justify-content: center;
z-index: 300;
padding: 20px;
}
.key-warning-card {
max-width: 360px;
text-align: center;
gap: 16px;
}
.key-warning-icon {
font-size: 48px;
color: var(--yellow);
line-height: 1;
}
.key-warning-card h2 {
font-size: 18px;
font-weight: 600;
}
.key-warning-text {
font-size: 13px;
color: var(--text-dim);
line-height: 1.5;
}
.key-warning-fps {
display: flex;
flex-direction: column;
gap: 8px;
background: var(--surface);
border-radius: 8px;
padding: 12px;
}
.key-fp-row {
display: flex;
flex-direction: column;
gap: 2px;
text-align: left;
}
.key-fp-label {
font-size: 10px;
text-transform: uppercase;
letter-spacing: 0.5px;
color: var(--text-dim);
}
.key-fp {
font-family: monospace;
font-size: 11px;
word-break: break-all;
color: var(--text);
}
.key-warning-actions {
display: flex;
gap: 10px;
}
.key-warning-actions .primary {
flex: 1;
background: var(--yellow);
color: #000;
font-weight: 600;
}
.key-warning-actions .secondary-btn {
flex: 1;
}
/* ── Quality slider ── */
.quality-control {
display: flex;
flex-direction: column;
gap: 6px;
padding: 4px 0;
}
.quality-header {
display: flex;
justify-content: space-between;
align-items: center;
}
.quality-label {
font-size: 13px;
font-weight: 600;
padding: 2px 8px;
border-radius: 6px;
transition: all 0.2s;
}
.quality-slider {
-webkit-appearance: none;
appearance: none;
width: 100%;
height: 6px;
border-radius: 3px;
outline: none;
cursor: pointer;
transition: background 0.2s;
}
.quality-slider::-webkit-slider-thumb {
-webkit-appearance: none;
appearance: none;
width: 18px;
height: 18px;
border-radius: 50%;
background: var(--text);
border: 2px solid var(--bg);
box-shadow: 0 1px 4px rgba(0,0,0,0.4);
cursor: pointer;
transition: transform 0.1s;
}
.quality-slider::-webkit-slider-thumb:hover {
transform: scale(1.15);
}
.quality-ticks {
display: flex;
justify-content: space-between;
font-size: 9px;
color: var(--text-dim);
padding: 0 2px;
}
.form select {
background: var(--surface);
border: 1px solid #333;
border-radius: 8px;
padding: 10px 12px;
color: var(--text);
font-size: 15px;
outline: none;
transition: border-color 0.2s;
}
.form select:focus {
border-color: var(--accent);
}
.settings-section select {
background: var(--surface);
border: 1px solid #333;
border-radius: 8px;
padding: 8px 10px;
color: var(--text);
font-size: 14px;
outline: none;
}
.settings-section select:focus {
border-color: var(--accent);
}

View File

@@ -1,141 +0,0 @@
# PRD: Local Recording + Cloud Mixer for Podcast-Quality Interviews
## Problem
WarzonePhone delivers real-time encrypted voice, but the audio quality is limited by network conditions (codec compression, packet loss, jitter). Podcasters and interviewers need pristine, studio-grade recordings of each participant — independent of what the network delivers.
## Solution
**Dual-path architecture**: each client simultaneously (1) participates in the live call at whatever codec quality the network supports, and (2) records their own microphone locally as lossless PCM. After the session, all local recordings are uploaded to a self-hosted mixer service that aligns, normalizes, and outputs a final multi-track or mixed file.
## Architecture
```
┌──────────────────┐
Mic ──┬── Opus/Codec2 ──► Network (live) │ ← real-time call
│ └──────────────────┘
└── WAV 48kHz ────► Local File │ ← pristine recording
(timestamped)
▼ (after hangup)
┌──────────────────┐
│ Mixer Service │ ← self-hosted
│ (align + mix) │
└──────────────────┘
Final MP3/WAV/FLAC
```
## Requirements
### Phase 1: Local Recording (MVP)
**All clients (Desktop, Android, Web):**
1. **Record toggle**: User can enable "Record this call" before or during a call
2. **Recording pipeline**: Tap raw PCM from the microphone capture path *before* it enters the codec encoder
3. **File format**: WAV (48kHz, 16-bit, mono) — simple, universally supported, lossless
4. **Sync markers**: Embed a monotonic timestamp (ms since call start) at the beginning of the recording, and periodically (every 10s) write a sync marker packet into a sidecar JSON file:
```json
{"ts_ms": 30000, "seq": 1500, "wall_clock_utc": "2026-04-07T12:00:30Z"}
```
This allows the mixer to align recordings from different participants even if they join at different times.
5. **Storage**:
- Desktop: `~/.wzp/recordings/{room}_{timestamp}.wav`
- Android: `Documents/WarzonePhone/{room}_{timestamp}.wav`
- Web: IndexedDB blob or File System Access API
6. **File size estimate**: 48kHz * 16-bit * mono = 96 KB/s = ~5.6 MB/min = ~345 MB/hour
7. **UI indicator**: Red dot + timer showing recording is active and file size growing
8. **On hangup**: Close the WAV file, show "Recording saved" with file path/size
### Phase 2: Upload to Mixer
1. **Upload endpoint**: Self-hosted HTTP service (Rust or Go) that accepts WAV uploads with metadata
2. **Chunked/resumable upload**: Large files need resumable uploads (tus protocol or simple chunked POST)
3. **Upload metadata**:
```json
{
"session_id": "uuid",
"participant_fingerprint": "xxxx:xxxx:...",
"alias": "Alice",
"room": "podcast-ep-42",
"duration_secs": 3600,
"sync_markers": [...],
"sample_rate": 48000,
"channels": 1,
"bit_depth": 16
}
```
4. **Upload UI**: Progress bar after hangup, option to upload now or later
5. **Retry on failure**: Queue uploads for retry if network is unavailable
### Phase 3: Mixer Service
1. **Alignment**: Use sync markers (wall clock + sequence numbers) to align recordings from all participants to a common timeline
2. **Silence trimming**: Detect and optionally trim leading/trailing silence
3. **Normalization**: Per-track loudness normalization (LUFS-based)
4. **Noise reduction**: Optional per-track noise gate or RNNoise pass
5. **Output formats**:
- Multi-track: ZIP of individual WAVs (aligned, normalized)
- Mixed: Single stereo or mono WAV/MP3/FLAC with all participants
- Podcast-ready: Loudness-normalized to -16 LUFS (podcast standard)
6. **Web UI**: Simple dashboard to see sessions, download outputs, preview waveforms
7. **Self-hosted**: Docker image, single binary, SQLite for metadata
## Implementation Notes
### Recording tap point
The recording must tap *after* AGC (so levels are normalized) but *before* the codec encoder (to avoid compression artifacts). In the current architecture:
```
Mic → Ring Buffer → AGC → [TAP HERE for recording] → Opus/Codec2 → Network
```
**Desktop** (`engine.rs`): After `capture_agc.process_frame()`, before `encoder.encode()`
**Android** (`engine.rs`): Same location — after AGC, before encode
**CLI** (`call.rs`): After `self.agc.process_frame()` in `CallEncoder::encode_frame()`
### WAV writer
Use a simple streaming WAV writer that:
- Writes the WAV header with placeholder data length
- Appends PCM samples as they come
- On close, seeks back to update the data length in the header
### Sync mechanism
Wall-clock UTC alone is insufficient (clocks drift). The sync strategy:
1. Each participant records their local monotonic time + wall clock at call start
2. Periodically (every 10s), each participant writes: `{local_mono_ms, seq_number, utc_iso}`
3. The mixer uses sequence numbers (which are shared via the wire protocol) as ground truth for alignment, with wall clock as a fallback
### Privacy
- Local recordings never leave the device without explicit user action
- Upload is manual, not automatic
- The mixer service processes files and can delete originals after mixing
- No recording data flows through the relay — only the user's own mic
## Non-Goals (v1)
- Live transcription (future)
- Video recording (audio only)
- Automatic upload without user consent
- Recording other participants' audio (only your own mic)
- Real-time mixing (post-session only)
## Milestones
| Phase | Scope | Effort |
|-------|-------|--------|
| 1a | Local WAV recording on Desktop | 1-2 days |
| 1b | Local WAV recording on Android | 1-2 days |
| 1c | Sync markers + metadata sidecar | 1 day |
| 2a | Upload service (HTTP + storage) | 2-3 days |
| 2b | Upload UI in clients | 1-2 days |
| 3a | Mixer: alignment + normalization | 2-3 days |
| 3b | Mixer: web dashboard | 2-3 days |
| 3c | Docker packaging | 1 day |

View File

@@ -1,56 +0,0 @@
# PRD: Studio Quality Tiers (Opus 32k/48k/64k)
## Status: Implemented
Studio quality tiers have been added to the wire protocol and all clients.
## What Was Added
### Wire Protocol (codec_id.rs)
Three new `CodecId` variants using the 4-bit header space (values 6-8):
| CodecId | Wire Value | Bitrate | Frame | Use Case |
|---------|-----------|---------|-------|----------|
| Opus32k | 6 | 32 kbps | 20ms | Studio low — noticeable improvement over 24k for voice |
| Opus48k | 7 | 48 kbps | 20ms | Studio — excellent voice, captures nuance |
| Opus64k | 8 | 64 kbps | 20ms | Studio high — near-transparent quality |
### Quality Profiles
| Profile | Codec | FEC | Bandwidth (with FEC) |
|---------|-------|-----|---------------------|
| STUDIO_32K | Opus 32k | 10% | ~35 kbps |
| STUDIO_48K | Opus 48k | 10% | ~53 kbps |
| STUDIO_64K | Opus 64k | 10% | ~70 kbps |
FEC is set to 10% (vs 20% for GOOD) — studio assumes a good network.
### Client Support
| Client | Selection | Status |
|--------|-----------|--------|
| Desktop (Tauri) | Quality slider in Settings (8 levels) | Done |
| CLI | `--profile studio-64k` / `studio-48k` / `studio-32k` | Done |
| Android | Needs codec picker update in SettingsScreen.kt | TODO |
| Web | Needs UI | TODO |
### Cross-Codec Interop
All decoder auto-switch paths (call.rs, desktop engine.rs) handle the new codec IDs. A studio-64k client can talk to a codec2-1200 client — the receiver auto-switches.
## When to Use Studio Tiers
- **Podcast recording sessions**: Use studio-64k for best quality (combined with local WAV recording for pristine output)
- **Music collaboration**: Opus at 48-64k captures instrument harmonics much better than 24k
- **Good network conditions**: Only useful when bandwidth isn't constrained; the extra bits are wasted on lossy networks
## When NOT to Use
- **Mobile data**: Stick with Auto/GOOD — studio tiers use 2-3x the bandwidth
- **High packet loss**: Studio profiles use minimal FEC (10%); degraded networks need DEGRADED or CATASTROPHIC profiles with 50-100% FEC
- **Large group calls**: Each participant's stream multiplies bandwidth; 64k * 10 participants = 640 kbps incoming
## Backward Compatibility
Old clients (before this change) will receive packets with CodecId 6/7/8 which they don't recognize. The `from_wire()` returns `None` for unknown values, causing the packet to be dropped. Old clients can still *send* to new clients fine (they use CodecId 0-5). This is acceptable for a pre-release protocol.