Windows port Phase 2: cpal device enumeration #4

Open
mollusk wants to merge 15 commits from windows-port-phase2 into windows-port-phase1
11 changed files with 1688 additions and 209 deletions
+1 -1
View File
@@ -49,7 +49,7 @@ tokio-stream = "0.1.18"
# app talks to the `AudioBackend` trait and the `PlatformAudioBackend` alias (see
# `src/audio/mod.rs`), so platform selection is confined to these few lines.
[target.'cfg(unix)'.dependencies]
[target.'cfg(target_os = "linux")'.dependencies]
# Linux audio backend. v0_3_49 exposes `Buffer::requested()` (the graph's per-cycle
# quantum), used by the playback RT callback to fill exactly what the device asks
# for instead of a hard-coded 1024-frame quantum (crackle on non-1024 hardware).
+77
View File
@@ -0,0 +1,77 @@
# PeerSpeak on Windows
Current status: the Windows port cross-compiles to `x86_64-pc-windows-gnu` and the `.exe`
launches under Wine. A real Windows/WASAPI host is still needed for the final audio-device
checks listed below.
## What works today
| Area | Status |
|---|---|
| GUI | Iced/wgpu builds and renders under Wine. |
| Networking | Iroh QUIC transport and gossip compile on Windows. |
| Audio backend | `cpal` drives WASAPI capture/playback behind `AudioBackend`. |
| Codec | Opus remains 48 kHz mono, 20 ms frames. |
| Identity | `ring` identity generation/load is platform-neutral. |
| Chimes | Windows uses PowerShell `System.Media.SoundPlayer` for WAV playback. |
Windows paths are resolved through `dirs`:
- Config: `%APPDATA%\peerspeak\config.json`
- Identity: `%APPDATA%\peerspeak\identity.key`
- Log: `%LOCALAPPDATA%\peerspeak\peerspeak.log`
## Building
### Native Windows
Install MSVC Build Tools and CMake, then build normally:
```powershell
cargo build --release
```
If CMake is 4.x or newer, the vendored `opus`/`libopus` build may need:
```powershell
$env:CMAKE_POLICY_VERSION_MINIMUM = "3.5"
cargo build --release
```
### Cross-compile from Linux
The current dev path cross-compiles from an Arch environment to the GNU Windows target:
```sh
rustup target add x86_64-pc-windows-gnu
sudo pacman -S mingw-w64-gcc cmake
CMAKE_POLICY_VERSION_MINIMUM=3.5 cargo build --release --target x86_64-pc-windows-gnu --bin peerspeak
```
Wine is useful for launch/render smoke tests, but it is not a substitute for a real
Windows audio-device pass. The deeper migration plan (phases, decisions, the opus build
spike) lives in the maintainer's handoff docs, outside the repo.
## First run and networking
Expect a Windows Firewall prompt the first time the app opens network sockets. Allow it:
PeerSpeak uses UDP for QUIC, plus relay traffic when direct NAT traversal is not available.
The default network mode keeps the n0 relay available for NAT traversal without publishing
presence to n0 DNS. Direct peer-to-peer paths may work when both networks allow them; relayed
connections are expected and valid.
## Known gaps
| Item | Status |
|---|---|
| Echo cancellation | Linux-only PipeWire feature. The Windows UI shows it disabled as unavailable. |
| Screen share | Requires a Windows `pixelpass.exe` on `PATH` or a configured override. |
| Chimes | Now routed through Windows `SoundPlayer`; needs a real Windows host to audibly verify. |
| Resampling/device format | Cross-compiled. cpal/WASAPI now chooses native 48 kHz when available and otherwise resamples/remaps at the device boundary; needs real Windows hardware audio verification. |
| Device persistence | Open. WASAPI friendly names may duplicate or change across driver/profile changes. |
| Playback pacing | Cross-compiled. The fixed playback target under WASAPI shared mode still needs real-hardware verification with `audio_probe`. |
Before calling Windows support done, verify a real Windows machine can create/join a room,
capture mic audio, hear remote audio, select devices, restart with selections preserved, and
play notification chimes.
+58 -12
View File
@@ -2,7 +2,7 @@ use crate::core::{CoreController, messages::{CoreCommand, UiEvent}};
use crate::network::PeerState;
use crate::notify::{self, Sound};
use crate::audio::eq::{EqSettings, EQ_GAIN_DB_MAX, EQ_GAIN_DB_MIN};
use crate::audio::pw_cli::{AudioDevice, enumerate_audio_devices};
use crate::audio::{AudioDevice, enumerate_audio_devices};
use crate::config::{AppConfig, NetworkMode, RecordingMode, RoomLayout};
use crate::hotkeys::{format_binding, HotkeyAction, HotkeyContext, KeyBinding};
use crate::presence::PresenceMode;
@@ -553,11 +553,9 @@ pub fn run_gui() -> iced::Result {
// the icon from the .desktop file matched by app_id instead).
icon: window_icon(),
// app_id must match the .desktop basename so Wayland compositors
// (e.g. KWin) attach our launcher icon to the window.
platform_specific: iced::window::settings::PlatformSpecific {
application_id: "peerspeak".to_string(),
..Default::default()
},
// (e.g. KWin) attach our launcher icon to the window. The field is
// Linux-only in iced (X11/Wayland); see platform_specific_settings().
platform_specific: platform_specific_settings(),
// We save the final size ourselves on CloseRequested, then exit.
exit_on_close_request: false,
..Default::default()
@@ -565,6 +563,22 @@ pub fn run_gui() -> iced::Result {
.run()
}
/// Window `PlatformSpecific` settings. `application_id` (used by X11/Wayland to
/// match our `.desktop` launcher icon) only exists in iced on Linux, so it is
/// set there and left at defaults on Windows.
#[cfg(target_os = "linux")]
fn platform_specific_settings() -> iced::window::settings::PlatformSpecific {
iced::window::settings::PlatformSpecific {
application_id: "peerspeak".to_string(),
..Default::default()
}
}
#[cfg(not(target_os = "linux"))]
fn platform_specific_settings() -> iced::window::settings::PlatformSpecific {
iced::window::settings::PlatformSpecific::default()
}
/// Build the window icon from an embedded 128×128 straight-RGBA blob rendered
/// from `assets/icons/peerspeak.svg`. Using `from_rgba` (always available) keeps
/// us off iced's heavy `image` feature — the blob is raw pixels, no decoder.
@@ -2557,10 +2571,28 @@ fn view(state: &AppState) -> Element<'_, AppMessage> {
mic_meter,
text("Drag the yellow handle to set the gate. While talking, place it just above your quiet-room level so silence is muted but your voice passes through.").size(11).color(color_subtext),
vertical_space(4.0),
{
let control: Element<'_, AppMessage> = {
#[cfg(target_os = "linux")]
{
column![
checkbox(state.config.echo_cancellation_enabled)
.label("Echo cancellation")
.on_toggle(AppMessage::ToggleEchoCancellation),
text("Cancels speaker echo + suppresses noise (PipeWire). Takes effect on your next room join.").size(11).color(color_subtext),
].spacing(8).into()
}
#[cfg(not(target_os = "linux"))]
{
column![
checkbox(false)
.label("Echo cancellation"),
text("Echo cancellation is not available on Windows yet.").size(11).color(color_subtext),
].spacing(8).into()
}
};
control
},
].spacing(8).width(iced::Length::Fill),
]
.spacing(10)
@@ -3263,11 +3295,12 @@ fn view(state: &AppState) -> Element<'_, AppMessage> {
column![]
},
vertical_space(20.0),
// Echo cancellation — same flag + message as the Settings checkbox, so
// toggling here and there stay in sync automatically (single source of
// truth: config.echo_cancellation_enabled). Tooltip is explicit that it
// applies on the NEXT join (the PipeWire-module AEC is wired at join
// time, not hot-swappable mid-call).
{
// Echo cancellation is wired at join time on Linux; other
// targets show an inert status row instead of a dead toggle.
let control: Element<'_, AppMessage> = {
#[cfg(target_os = "linux")]
{
tooltip(
checkbox(state.config.echo_cancellation_enabled)
.label("Echo cancellation")
@@ -3282,7 +3315,20 @@ fn view(state: &AppState) -> Element<'_, AppMessage> {
.style(c_style(color_crust, color_surface, 6.0)),
iced::widget::tooltip::Position::Top,
)
.gap(8),
.gap(8)
.into()
}
#[cfg(not(target_os = "linux"))]
{
column![
checkbox(false)
.label("Echo cancellation"),
text("Not available on Windows yet.").size(11).color(color_subtext),
].spacing(4).into()
}
};
control
},
vertical_space(20.0),
{
let (rec_kind, rec_label, rec_bg, rec_hover, rec_fg) = if state.recording {
+942 -99
View File
File diff suppressed because it is too large Load Diff
+36 -6
View File
@@ -56,19 +56,50 @@ pub trait AudioBackend: Send + Sync {
fn stop(&self) -> Result<(), AudioError>;
}
pub mod echo_cancel;
pub mod eq;
pub mod gate;
pub mod limiter;
pub mod multitrack;
pub mod pan;
#[cfg(unix)]
// Linear resamplers used by the Windows/cpal backend (W4). Platform-neutral and
// pure, so it builds (and its tests run) everywhere even though only the cpal
// backend wires it in.
pub mod resample;
#[cfg(target_os = "linux")]
pub mod echo_cancel;
#[cfg(target_os = "linux")]
pub mod pipewire_impl;
#[cfg(windows)]
pub mod cpal_impl;
#[cfg(target_os = "linux")]
pub mod pw_cli;
pub mod recorder;
/// A selectable audio device for the input/output pickers. `name` is the stable
/// identifier the backend uses to request the device (`target_node`);
/// `description` is the human-facing label shown in the UI. The two may be equal
/// (cpal/WASAPI) or differ (PipeWire node name vs. description).
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct AudioDevice {
pub name: String,
pub description: String,
pub is_input: bool,
}
impl std::fmt::Display for AudioDevice {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
write!(f, "{}", self.description)
}
}
// Enumerate audio input/output devices for the pickers (sorted by description),
// returning the same `AudioDevice` shape regardless of platform: PipeWire
// (`pw-cli`) on Linux, cpal/WASAPI on Windows.
#[cfg(target_os = "linux")]
pub use pw_cli::enumerate_audio_devices;
#[cfg(windows)]
pub use cpal_impl::enumerate_audio_devices;
/// The audio backend implementation for the current platform.
///
/// The whole app constructs and threads this alias (via
@@ -76,10 +107,9 @@ pub mod recorder;
/// platform selection lives entirely here. Both implementations satisfy the
/// [`AudioBackend`] trait, which is the only interface the core talks to.
///
/// - Linux/Unix → PipeWire ([`pipewire_impl::PipeWireBackend`]).
/// - Windows → cpal/WASAPI ([`cpal_impl::CpalBackend`]); a no-op stub until the
/// Phase 1 capture/playback implementation lands.
#[cfg(unix)]
/// - Linux → PipeWire ([`pipewire_impl::PipeWireBackend`]).
/// - Windows → cpal/WASAPI ([`cpal_impl::CpalBackend`]).
#[cfg(target_os = "linux")]
pub type PlatformAudioBackend = pipewire_impl::PipeWireBackend;
#[cfg(windows)]
pub type PlatformAudioBackend = cpal_impl::CpalBackend;
+1 -13
View File
@@ -1,18 +1,6 @@
use super::AudioDevice;
use std::process::Command;
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct AudioDevice {
pub name: String,
pub description: String,
pub is_input: bool,
}
impl std::fmt::Display for AudioDevice {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
write!(f, "{}", self.description)
}
}
pub fn enumerate_audio_devices() -> Vec<AudioDevice> {
let output = Command::new("pw-cli")
.arg("list-objects")
+307
View File
@@ -0,0 +1,307 @@
//! Dep-free linear-interpolation resamplers for the Windows/cpal backend (W4).
//!
//! The pipeline runs internally at 48 kHz (Opus + the 20 ms frame), but a WASAPI
//! endpoint may run at a different rate (commonly 44.1 kHz) and/or a non-stereo
//! channel layout. These convert at the device boundary so such a device plays and
//! captures instead of hard-erroring (the W4 limitation in the Windows port).
//!
//! ## Where each is used
//! - [`PushResampler`] (single channel) converts **capture** from the device rate
//! to 48 kHz on the capture drain thread — off the RT callback.
//! - [`StereoPullResampler`] converts **playback** from the internal 48 kHz stereo
//! bus to the device rate inside the output RT callback, pulling internal frames
//! from the ring on demand. It allocates nothing in `next`, so it is RT-safe.
//!
//! ## Quality
//! This is plain linear interpolation with no anti-aliasing filter: correct,
//! allocation-free, and adequate for speech, but it adds some aliasing when
//! downsampling. The seam is intentionally tiny so a higher-quality polyphase/FIR
//! resampler (e.g. the `rubato` crate, pending a supply-chain decision) can later
//! replace the internals without touching the cpal backend. The matching-rate /
//! matching-layout path in the backend bypasses these entirely and stays bit-exact.
/// Linear interpolation between `a` and `b` at fractional position `frac` in `[0, 1)`.
#[inline]
fn lerp(a: f32, b: f32, frac: f32) -> f32 {
a + (b - a) * frac
}
/// Stateful single-channel **push** resampler: feed input samples at `in_rate`,
/// receive output samples at `out_rate` through an `emit` callback. It carries the
/// fractional read position and the previous input sample across calls, so feeding
/// the stream block-by-block joins seamlessly. Neither [`push`](Self::push) nor
/// [`process`](Self::process) allocates.
pub struct PushResampler {
/// Input samples consumed per output sample (`in_rate / out_rate`).
step: f64,
/// Position of the next output sample, in input-sample units, measured from the
/// index of `prev` (the most recent input). Always advanced to stay `< 1.0`
/// after each input is consumed.
next: f64,
/// The previous input sample (left edge of the current interpolation segment).
prev: f32,
/// Whether any input has been seen yet (anchors the first output at input[0]).
started: bool,
}
impl PushResampler {
/// Build a resampler from `in_rate` to `out_rate` (both in Hz). Rates are
/// clamped to `>= 1` so `step` is always finite and non-zero: a zero `step`
/// would make [`push`](Self::push)'s `while self.next < 1.0` loop forever. The
/// cpal backend's `resolve()` also rejects such rates up front, so this is
/// belt-and-suspenders against a future caller (review W7).
pub fn new(in_rate: u32, out_rate: u32) -> Self {
Self {
step: in_rate.max(1) as f64 / out_rate.max(1) as f64,
next: 0.0,
prev: 0.0,
started: false,
}
}
/// Feed one input sample; `emit` is called for each output sample produced
/// (zero or more, depending on the rate ratio).
pub fn push(&mut self, cur: f32, mut emit: impl FnMut(f32)) {
if !self.started {
// First sample: just establish the left edge. Linear interpolation
// needs the next input as the right edge, so the first output is
// produced on the next push. This gives exact alignment
// (`output[k] == input[k]` at equal rates) with one input-sample of
// latency — negligible (~20 µs at 48 kHz).
self.started = true;
self.prev = cur;
self.next = 0.0;
return;
}
// `prev` sits at position 0 of this segment and `cur` at position 1; emit
// every output whose position falls in [0, 1).
while self.next < 1.0 {
emit(lerp(self.prev, cur, self.next as f32));
self.next += self.step;
}
self.next -= 1.0;
self.prev = cur;
}
/// Convenience for tests / batch callers: push a whole slice.
pub fn process(&mut self, input: &[f32], mut emit: impl FnMut(f32)) {
for &s in input {
self.push(s, &mut emit);
}
}
}
/// Stateful stereo **pull** resampler: produce output frames at `out_rate` by
/// pulling input frames at `in_rate` from a closure on demand. Call
/// [`next`](Self::next) once per output frame; it pulls as many input frames as the
/// ratio requires and returns the interpolated `(left, right)`, or `None` when the
/// puller runs dry (an underrun). Allocates nothing, so it is safe in an RT output
/// callback.
pub struct StereoPullResampler {
/// Input frames consumed per output frame (`in_rate / out_rate`).
step: f64,
/// Position of the next output frame within `[prev, cur)`, in `[0, 1)`.
frac: f64,
/// Left edge of the current interpolation segment.
prev: (f32, f32),
/// Right edge of the current interpolation segment.
cur: (f32, f32),
/// Whether `prev`/`cur` have been primed from the puller yet.
primed: bool,
}
impl StereoPullResampler {
/// Build a resampler from `in_rate` to `out_rate` (both in Hz). Rates are
/// clamped to `>= 1` so `step` is finite and non-zero — otherwise
/// [`next`](Self::next)'s `while self.frac >= 1.0` could spin (review W7).
pub fn new(in_rate: u32, out_rate: u32) -> Self {
Self {
step: in_rate.max(1) as f64 / out_rate.max(1) as f64,
frac: 0.0,
prev: (0.0, 0.0),
cur: (0.0, 0.0),
primed: false,
}
}
/// Produce the next output frame, pulling input frames via `pull` as needed.
/// Returns `None` if `pull` returns `None` before the frame can be formed
/// (underrun); the caller should substitute silence for that frame.
pub fn next(&mut self, mut pull: impl FnMut() -> Option<(f32, f32)>) -> Option<(f32, f32)> {
if !self.primed {
// Prime both edges from two pulls so the first output frame aligns
// exactly with the first input frame (`out[0] == in[0]` at equal
// rates). Needs two frames available to start, which the prefilled
// playback ring always has.
self.prev = pull()?;
self.cur = pull()?;
self.primed = true;
self.frac = 0.0;
}
// Advance the segment until the read position lands inside [prev, cur).
while self.frac >= 1.0 {
self.prev = self.cur;
self.cur = pull()?;
self.frac -= 1.0;
}
let f = self.frac as f32;
let out = (lerp(self.prev.0, self.cur.0, f), lerp(self.prev.1, self.cur.1, f));
self.frac += self.step;
Some(out)
}
}
#[cfg(test)]
mod tests {
use super::*;
/// Equal rates align exactly: `output[k] == input[k]`. The final input lands on
/// the next push (one-sample streaming latency), so we get `n - 1` outputs.
#[test]
fn push_identity_when_rates_match() {
let mut r = PushResampler::new(48_000, 48_000);
let input = [0.0, 0.1, 0.2, 0.3, 0.4];
let mut out = Vec::new();
r.process(&input, |s| out.push(s));
assert_eq!(out.len(), input.len() - 1);
for (a, b) in out.iter().zip(input.iter()) {
assert!((a - b).abs() < 1e-6, "{a} vs {b}");
}
}
/// Upsampling 2x roughly doubles the output count and the midpoints interpolate.
#[test]
fn push_upsample_2x_interpolates_midpoints() {
let mut r = PushResampler::new(24_000, 48_000); // step = 0.5
let input = [0.0, 1.0, 2.0, 3.0];
let mut out = Vec::new();
r.process(&input, |s| out.push(s));
// (n - 1) segments at 2 outputs each = 6.
assert_eq!(out.len(), 6, "out {out:?}");
// A half-step between 1.0 and 2.0 must appear near 1.5.
assert!(
out.iter().any(|&s| (s - 1.5).abs() < 1e-3),
"expected a ~1.5 midpoint in {out:?}"
);
}
/// Downsampling drops the rate: fewer outputs than inputs, monotonic ramp preserved.
#[test]
fn push_downsample_reduces_count() {
let mut r = PushResampler::new(48_000, 44_100); // step ~1.088
let input: Vec<f32> = (0..441).map(|i| i as f32).collect();
let mut out = Vec::new();
r.process(&input, |s| out.push(s));
// 441 in @ 48k -> ~405 out @ 44.1k.
assert!(
(390..=410).contains(&out.len()),
"expected ~405 outputs, got {}",
out.len()
);
// Output stays within the input's value range and is non-decreasing.
for w in out.windows(2) {
assert!(w[1] >= w[0] - 1e-3, "ramp should not reverse: {w:?}");
}
assert!(*out.last().unwrap() <= 440.0 + 1e-3);
}
/// Pull resampler at equal rates returns each input frame in order, aligned.
/// Two-pull priming uses one frame of lookahead, so `n` inputs yield `n - 1`
/// outputs (the last frame emits once a successor arrives).
#[test]
fn pull_identity_when_rates_match() {
let mut r = StereoPullResampler::new(48_000, 48_000);
let frames = [(0.0, 9.0), (1.0, 8.0), (2.0, 7.0), (3.0, 6.0)];
let mut idx = 0;
let mut out = Vec::new();
while let Some(f) = r.next(|| {
let v = frames.get(idx).copied();
idx += 1;
v
}) {
out.push(f);
}
assert_eq!(out.len(), frames.len() - 1, "out {out:?}");
for (got, want) in out.iter().zip(frames.iter()) {
assert!((got.0 - want.0).abs() < 1e-6 && (got.1 - want.1).abs() < 1e-6);
}
}
/// Pull resampler reports underrun (`None`) once the source is exhausted.
#[test]
fn pull_returns_none_on_underrun() {
let mut r = StereoPullResampler::new(48_000, 44_100); // step ~1.088 -> pulls >1 per out
let frames = [(0.0, 0.0), (1.0, -1.0)];
let mut idx = 0;
let mut pull = || {
let v = frames.get(idx).copied();
idx += 1;
v
};
// First frame primes + emits; subsequent calls eventually exhaust the source.
let mut produced = 0;
let mut hit_none = false;
for _ in 0..10 {
if r.next(&mut pull).is_some() {
produced += 1;
} else {
hit_none = true;
break;
}
}
assert!(produced >= 1, "should produce at least the primed frame");
assert!(hit_none, "should report underrun once the puller is dry");
}
/// Downsampling via pull consumes more input frames than it emits output frames.
#[test]
fn pull_downsample_consumes_more_than_it_emits() {
let mut r = StereoPullResampler::new(48_000, 24_000); // step = 2.0
let input: Vec<(f32, f32)> = (0..100).map(|i| (i as f32, -(i as f32))).collect();
let mut idx = 0;
let mut emitted = 0;
for _ in 0..40 {
let f = r.next(|| {
let v = input.get(idx).copied();
idx += 1;
v
});
if f.is_some() {
emitted += 1;
} else {
break;
}
}
// At step 2.0 we consume ~2 input frames per output frame.
assert!(idx > emitted, "consumed {idx} input, emitted {emitted} output");
}
/// A zero rate must not produce a zero `step` (which would spin `push`'s inner
/// `while self.next < 1.0` forever). Clamping makes the call terminate (W7).
#[test]
fn push_zero_rate_does_not_spin() {
let mut r = PushResampler::new(0, 48_000);
let mut count = 0usize;
// Feed two samples; with a clamped non-zero step this returns promptly.
r.push(0.0, |_| count += 1);
r.push(1.0, |_| count += 1);
// Reaching here at all is the assertion (no hang); some output is produced.
assert!(count >= 1);
}
/// A zero output rate must not make the pull resampler's segment-advance loop
/// spin. Clamping keeps `step` finite so `next` terminates (W7).
#[test]
fn pull_zero_out_rate_does_not_spin() {
let mut r = StereoPullResampler::new(48_000, 0);
let frames = [(0.0, 0.0), (1.0, 1.0), (2.0, 2.0)];
let mut idx = 0;
let got = r.next(|| {
let v = frames.get(idx).copied();
idx += 1;
v
});
// Terminates and yields the primed frame instead of hanging.
assert!(got.is_some());
}
}
+126 -12
View File
@@ -1,11 +1,11 @@
//! Audio playout diagnostic probe.
//!
//! Drives a phase-continuous sine tone through the *real* PipeWire playback path
//! (`PipeWireBackend::start_playback`), using the *same* fill-paced production
//! the production mixer uses (`core/mod.rs`): generate a frame only while the
//! Drives a phase-continuous sine tone through the *real* playback path
//! (PipeWire on Linux, cpal/WASAPI on Windows), using the *same* fill-paced
//! production the production mixer uses (`core/mod.rs`): generate a frame only while the
//! playback ring is below `PLAYBACK_TARGET_SAMPLES`, so production tracks the
//! PipeWire hardware clock. No network, no microphone — this isolates the local
//! output path so we can confirm the clock-paced playout is glitch-free.
//! hardware clock. No network, no microphone — this isolates the local output
//! path so we can confirm the clock-paced playout is glitch-free.
//!
//! Use your ears on the tone (any click/pop is a glitch) together with the
//! `playout-health:` lines tailed to stdout:
@@ -18,20 +18,27 @@
//! Run: cargo run --bin audio_probe -- [freq_hz] [seconds] [target_node]
//! e.g. cargo run --release --bin audio_probe -- 440 30
//!
//! This probe exercises the PipeWire backend directly, so it is a Unix-only tool.
//! On non-Unix targets `main` is a stub that explains the limitation.
//! This probe exercises the platform playback backend directly: PipeWire on Linux
//! and cpal/WASAPI on Windows. Other targets use a stub that explains the limitation.
#[cfg(unix)]
#[cfg(target_os = "linux")]
fn main() {
unix_probe::run();
}
#[cfg(not(unix))]
#[cfg(windows)]
fn main() {
eprintln!("audio_probe is only supported on Unix builds (it drives the PipeWire backend directly).");
win_probe::run();
}
#[cfg(unix)]
#[cfg(not(any(target_os = "linux", windows)))]
fn main() {
eprintln!(
"audio_probe is only supported on Linux and Windows builds (it drives the platform playback backend directly)."
);
}
#[cfg(target_os = "linux")]
mod unix_probe {
use std::io::{BufRead, BufReader, Seek, SeekFrom};
use std::sync::Arc;
@@ -88,7 +95,114 @@ mod unix_probe {
for _ in 0..FRAME_SAMPLES {
let t = n as f32 / SAMPLE_RATE;
// 0.25 amplitude: clearly audible but not harsh.
let sample = (0.25 * i16::MAX as f32 * (2.0 * std::f32::consts::PI * freq * t).sin()) as i16;
let sample =
(0.25 * i16::MAX as f32 * (2.0 * std::f32::consts::PI * freq * t).sin()) as i16;
// Stereo playback bus: duplicate the probe tone to L/R.
frame.push(sample);
frame.push(sample);
n += 1;
}
if tx.send(frame).is_err() {
eprintln!("playback channel closed early");
break;
}
}
// Let the ring drain, then stop.
tokio::time::sleep(Duration::from_millis(300)).await;
let _ = backend.stop();
println!("\naudio_probe: done.");
}
/// Open the app log, seek to the end, and echo new lines (the `playout-health:`
/// reports) to stdout once they appear.
fn spawn_log_tailer() {
let path = peerspeak::log_file_path();
std::thread::spawn(move || {
// Wait for the file to exist (first log_msg creates it).
let file = loop {
if let Ok(f) = std::fs::File::open(&path) {
break f;
}
std::thread::sleep(Duration::from_millis(100));
};
let mut reader = BufReader::new(file);
let _ = reader.seek(SeekFrom::End(0));
loop {
let mut line = String::new();
match reader.read_line(&mut line) {
Ok(0) => std::thread::sleep(Duration::from_millis(150)),
Ok(_) => {
if line.contains("playout-health:") {
print!("{line}");
}
}
Err(_) => std::thread::sleep(Duration::from_millis(150)),
}
}
});
}
}
#[cfg(windows)]
mod win_probe {
use std::io::{BufRead, BufReader, Seek, SeekFrom};
use std::sync::Arc;
use std::sync::atomic::AtomicUsize;
use std::sync::mpsc;
use std::time::Duration;
use peerspeak::audio::AudioBackend;
use peerspeak::audio::cpal_impl::CpalBackend;
use peerspeak::core::jitter::FRAME_SAMPLES; // 960 mono frames = 20ms @ 48kHz
const SAMPLE_RATE: f32 = 48_000.0;
#[tokio::main]
pub async fn run() {
let mut args = std::env::args().skip(1);
let freq: f32 = args.next().and_then(|s| s.parse().ok()).unwrap_or(440.0);
let secs: u64 = args.next().and_then(|s| s.parse().ok()).unwrap_or(30);
let target_node: Option<String> = args.next();
// The playout-health logger is quiet in normal operation (it only logs
// glitches); ask it for the full once-per-second heartbeat so the probe can
// show the steady-state numbers.
// SAFETY: set before any playback thread starts, so no concurrent env read.
unsafe { std::env::set_var("PEERSPEAK_AUDIO_VERBOSE", "1") };
println!("audio_probe: {freq} Hz tone for {secs}s through the real playback path.");
println!("Listen for clicks/pops; watch the playout-health lines below.\n");
// Tail the app log (where playout-health lines land) to stdout in the
// background so it's all in one terminal.
spawn_log_tailer();
let backend = CpalBackend::new();
let (tx, rx) = mpsc::channel::<Vec<i16>>();
let ring_fill = Arc::new(AtomicUsize::new(0));
if let Err(e) = backend.start_playback(rx, target_node, ring_fill.clone()) {
eprintln!("failed to start playback: {e}");
return;
}
// Phase-continuous sine, generated one 20ms frame at a time, fill-paced
// exactly like the production mixer: only produce while the ring is below
// target, so production tracks the cpal/WASAPI hardware clock.
use std::sync::atomic::Ordering;
let deadline = tokio::time::Instant::now() + Duration::from_secs(secs);
let mut n: u64 = 0; // running sample index keeps phase continuous across frames
while tokio::time::Instant::now() < deadline {
if ring_fill.load(Ordering::Relaxed) >= peerspeak::audio::PLAYBACK_TARGET_SAMPLES {
tokio::time::sleep(Duration::from_millis(2)).await;
continue;
}
let mut frame = Vec::with_capacity(FRAME_SAMPLES * peerspeak::audio::PLAYBACK_CHANNELS);
for _ in 0..FRAME_SAMPLES {
let t = n as f32 / SAMPLE_RATE;
// 0.25 amplitude: clearly audible but not harsh.
let sample =
(0.25 * i16::MAX as f32 * (2.0 * std::f32::consts::PI * freq * t).sin()) as i16;
// Stereo playback bus: duplicate the probe tone to L/R.
frame.push(sample);
frame.push(sample);
+18
View File
@@ -390,6 +390,7 @@ struct ActiveSession {
grace_timers: GraceTimers,
transport: Arc<IrohTransport>,
/// Loaded PipeWire echo-cancel module (if enabled); unloads on drop.
#[cfg(target_os = "linux")]
echo_cancel: Option<crate::audio::echo_cancel::EchoCancelGuard>,
/// Our pixelpass screen-share host child while sharing (`kill_on_drop`, so it
/// also dies if the session is dropped without an explicit stop).
@@ -431,6 +432,7 @@ impl ActiveSession {
// Unload the echo-cancel module now that the audio streams releasing its
// virtual nodes have stopped. (Dropping the guard runs `pactl unload`.)
#[cfg(target_os = "linux")]
drop(self.echo_cancel);
crate::log_msg("Leaving room...");
@@ -1095,7 +1097,9 @@ async fn run_core_loop(
// The guard unloads the module on drop — including the early-return
// paths below, since it's a local until moved into the session. On
// any failure, warn and fall back to the direct devices.
#[cfg(target_os = "linux")]
let mut echo_cancel_guard = None;
#[cfg(target_os = "linux")]
let (capture_target, playback_target) = if echo_cancellation {
match crate::audio::echo_cancel::enable(
input_device.as_deref(),
@@ -1122,6 +1126,10 @@ async fn run_core_loop(
} else {
(input_device.clone(), output_device.clone())
};
#[cfg(not(target_os = "linux"))]
let _ = echo_cancellation;
#[cfg(not(target_os = "linux"))]
let (capture_target, playback_target) = (input_device.clone(), output_device.clone());
if let Err(e) = audio_backend.start_capture(capture_tx, capture_target) {
let _ = ui_tx.send(UiEvent::Error(format!("Failed to start capture: {}", e))).await;
@@ -1632,6 +1640,7 @@ async fn run_core_loop(
conn_event_task,
grace_timers,
transport: transport.clone(),
#[cfg(target_os = "linux")]
echo_cancel: echo_cancel_guard,
screenshare_host: None,
screenshare_viewers: Vec::new(),
@@ -1807,6 +1816,14 @@ async fn run_core_loop(
}
CoreCommand::SetNetworkMode(mode) => {
// Skip when the posture is unchanged. The GUI re-sends the saved
// network mode as part of its startup config-sync, and that mode
// usually already matches the freshly-built stack — rebuilding the
// iroh endpoint for an identical posture just churns the network
// and adds a needless ~1s teardown+rebuild bounce at every launch
// (seen on both Linux and Windows/Wine). A real change still
// rebuilds exactly as before.
if mode != network_mode {
network_mode = mode;
// Rebuild the persistent stack to the new posture immediately if
// idle; if a call is active, defer to the next Leave/Join so the
@@ -1820,6 +1837,7 @@ async fn run_core_loop(
net_rebuild_pending = true;
}
}
}
CoreCommand::RegenerateIdentity => {
// Mint + persist a fresh identity, discarding the old one. The
+41 -5
View File
@@ -3,11 +3,12 @@
//!
//! The WAVs are embedded in the binary (`include_bytes!`) so a deployed single
//! binary is self-contained — no asset directory to ship alongside it. On first
//! use each sound is written once to a temp file, then played fire-and-forget
//! via `pw-play` (PipeWire-native; falls back to `paplay`/`aplay`). Playback runs
//! on a detached thread that waits on the child, so it never blocks the UI and
//! never leaves a zombie. Any failure (no player, no audio) is silent by design —
//! a missing chime should never disrupt a call.
//! use each sound is written once to a temp file, then played fire-and-forget.
//! Linux uses `pw-play` (PipeWire-native; falls back to `paplay`/`aplay`);
//! Windows uses PowerShell's `System.Media.SoundPlayer`. Playback runs on a
//! detached thread that waits on the child, so it never blocks the UI and never
//! leaves a zombie. Any failure (no player, no audio) is silent by design — a
//! missing chime should never disrupt a call.
use std::collections::HashMap;
use std::path::{Path, PathBuf};
@@ -202,8 +203,14 @@ fn cached_path(sound: Sound) -> Option<PathBuf> {
Some(path)
}
#[cfg(any(windows, test))]
fn escape_powershell_single_quoted(s: &str) -> String {
s.replace('\'', "''")
}
/// Try each available player in turn, waiting on the first that starts (which
/// reaps the child). Runs on a detached thread, so the wait is harmless.
#[cfg(not(windows))]
fn spawn_player(path: &Path) {
for player in ["pw-play", "paplay", "aplay"] {
let started = Command::new(player)
@@ -221,6 +228,23 @@ fn spawn_player(path: &Path) {
}
}
/// Play through Windows' built-in WAV player. Runs on a detached thread, so
/// `PlaySync()` blocking for the sound duration is fine.
#[cfg(windows)]
fn spawn_player(path: &Path) {
let path = escape_powershell_single_quoted(&path.display().to_string());
let command = format!("(New-Object System.Media.SoundPlayer '{path}').PlaySync()");
let _ = Command::new("powershell")
.arg("-NoProfile")
.arg("-NonInteractive")
.arg("-Command")
.arg(command)
.stdin(Stdio::null())
.stdout(Stdio::null())
.stderr(Stdio::null())
.status();
}
#[cfg(test)]
mod tests {
use super::*;
@@ -234,6 +258,18 @@ mod tests {
assert!(!should_play(false, false));
}
#[test]
fn test_powershell_single_quote_escape() {
assert_eq!(
escape_powershell_single_quoted(r"C:\Users\O'Brien\chime.wav"),
r"C:\Users\O''Brien\chime.wav"
);
assert_eq!(
escape_powershell_single_quoted("a'b'c"),
"a''b''c"
);
}
#[test]
fn test_sound_indices_unique_and_match_all() {
// `index()` must be a 0..COUNT bijection in `ALL` order, or the flag
+21 -1
View File
@@ -25,6 +25,16 @@ use tokio::process::{Child, Command};
/// points elsewhere.
const PIXELPASS_BIN: &str = "pixelpass";
#[cfg(windows)]
fn pixelpass_path_candidates(dir: &Path) -> [PathBuf; 2] {
[dir.join(PIXELPASS_BIN), dir.join("pixelpass.exe")]
}
#[cfg(not(windows))]
fn pixelpass_path_candidates(dir: &Path) -> [PathBuf; 1] {
[dir.join(PIXELPASS_BIN)]
}
/// Pixelpass endpoint tickets are normally ~140 chars. Leave headroom for format
/// growth, but reject unbounded gossip payloads before the UI offers "Watch".
const MAX_TICKET_LEN: usize = 512;
@@ -143,7 +153,7 @@ pub fn pixelpass_path(config_override: Option<&str>) -> Option<PathBuf> {
}
let path_var = std::env::var_os("PATH")?;
std::env::split_paths(&path_var)
.map(|dir| dir.join(PIXELPASS_BIN))
.flat_map(|dir| pixelpass_path_candidates(&dir))
.find(|c| c.is_file())
}
@@ -513,4 +523,14 @@ mod tests {
// only assert it doesn't return the empty path as a match.
assert_ne!(pixelpass_path(Some(" ")).as_deref(), Some(Path::new("")));
}
#[test]
fn pixelpass_path_candidates_are_platform_specific() {
let dir = Path::new("bin");
let candidates: Vec<PathBuf> = pixelpass_path_candidates(dir).into_iter().collect();
#[cfg(windows)]
assert_eq!(candidates, vec![dir.join("pixelpass"), dir.join("pixelpass.exe")]);
#[cfg(not(windows))]
assert_eq!(candidates, vec![dir.join("pixelpass")]);
}
}