feat(A.2 #19): progressive WAV write during live capture
The Vec<f32> in-memory accumulator on run_live_session had three failure modes: (a) a crash during transcription took the recording with it, (b) RAM grew linearly with session length, (c) OOM killed the capture thread silently. New kon_audio::WavWriter wraps hound::WavWriter<BufWriter<File>> with an append-friendly API and a 500 ms-granularity header flush. On any abort after a flush the on-disk file is a valid, playable WAV. Unit test (brief item #19 acceptance) simulates the abort with std::mem::forget and asserts the pre-flush samples are recoverable. Live capture now: - resolves the destination path at start_live_transcription_session time via a new resolve_recording_path helper extracted from persist_audio_samples, - opens a WavWriter before any samples arrive, sample rate taken from LocalEngine::capabilities() (#13 wiring) with 16 kHz fallback, - feeds the resampler output through WavWriter::append inside append_resampled_audio — drops the writer with a user-visible warning if a write fails mid-session, - calls flush() at stop (after resampler tail), finalise() on clean exit, and drops-to-last-flushed state on abort. LiveSessionSummary.audio_samples → audio_path: the path is already written by the time stop_live_transcription_session runs; no post-session write step remains for live capture. persist_audio_samples is kept for the offline save_audio command.
This commit is contained in:
@@ -12,4 +12,4 @@ pub use decode::decode_audio_file;
|
||||
pub use resample::resample_to_16khz;
|
||||
pub use streaming_resample::StreamingResampler;
|
||||
pub use vad::SpeechDetector;
|
||||
pub use wav::{read_wav, write_wav};
|
||||
pub use wav::{read_wav, write_wav, WavWriter};
|
||||
|
||||
@@ -1,8 +1,101 @@
|
||||
use std::io::BufWriter;
|
||||
use std::path::Path;
|
||||
|
||||
use kon_core::error::{KonError, Result};
|
||||
use kon_core::types::AudioSamples;
|
||||
|
||||
/// Append-friendly WAV writer for long-running captures.
|
||||
///
|
||||
/// The in-memory `Vec<f32>` used by `run_live_session` to persist audio
|
||||
/// on session end (brief item #19) has three failure modes: (a) a crash
|
||||
/// during transcription takes the recording with it; (b) RAM bloat at
|
||||
/// long session lengths; (c) an OOM kills the capture loop. `WavWriter`
|
||||
/// replaces that pattern with an on-disk writer that periodically
|
||||
/// flushes the WAV header so the file on disk is a valid, playable WAV
|
||||
/// at any point the process is interrupted.
|
||||
///
|
||||
/// The writer samples at the rate / channel count supplied at
|
||||
/// construction; callers read those from
|
||||
/// `LocalEngine::capabilities()` (brief item #13 wiring) rather than
|
||||
/// hardcoding 16 kHz / mono.
|
||||
pub struct WavWriter {
|
||||
inner: hound::WavWriter<BufWriter<std::fs::File>>,
|
||||
samples_since_flush: usize,
|
||||
flush_every: usize,
|
||||
}
|
||||
|
||||
impl WavWriter {
|
||||
/// Sample count between automatic header flushes. Flushing costs
|
||||
/// two seeks per call; 8000 samples at 16 kHz = 500 ms, so the
|
||||
/// worst-case "last half second is lost on crash" bound holds.
|
||||
const DEFAULT_FLUSH_EVERY_SAMPLES: usize = 8_000;
|
||||
|
||||
/// Create a new WAV file at `path`, truncating any previous content.
|
||||
/// Header reflects zero samples until the first `flush` or
|
||||
/// `finalize`.
|
||||
pub fn create(path: &Path, sample_rate: u32, channels: u16) -> Result<Self> {
|
||||
let spec = hound::WavSpec {
|
||||
channels,
|
||||
sample_rate,
|
||||
bits_per_sample: 16,
|
||||
sample_format: hound::SampleFormat::Int,
|
||||
};
|
||||
let file = std::fs::File::create(path).map_err(KonError::Io)?;
|
||||
let buffered = BufWriter::new(file);
|
||||
let inner = hound::WavWriter::new(buffered, spec).map_err(|e| {
|
||||
KonError::Io(std::io::Error::other(format!("WAV create failed: {e}")))
|
||||
})?;
|
||||
Ok(Self {
|
||||
inner,
|
||||
samples_since_flush: 0,
|
||||
flush_every: Self::DEFAULT_FLUSH_EVERY_SAMPLES,
|
||||
})
|
||||
}
|
||||
|
||||
/// Append f32 samples in `[-1.0, 1.0]`. Samples outside that range
|
||||
/// are clamped (matching `write_wav`). Automatically flushes the
|
||||
/// header every `flush_every` samples so the on-disk file stays a
|
||||
/// valid WAV even if the process is killed between appends.
|
||||
pub fn append(&mut self, samples: &[f32]) -> Result<()> {
|
||||
for &sample in samples {
|
||||
let clamped = sample.clamp(-1.0, 1.0);
|
||||
let int_sample = (clamped * i16::MAX as f32) as i16;
|
||||
self.inner.write_sample(int_sample).map_err(|e| {
|
||||
KonError::Io(std::io::Error::other(format!("WAV write failed: {e}")))
|
||||
})?;
|
||||
}
|
||||
self.samples_since_flush += samples.len();
|
||||
if self.samples_since_flush >= self.flush_every {
|
||||
self.flush()?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Force an immediate header flush. Leaves the file in a valid-WAV
|
||||
/// state up to the current sample count. Callers do not need to
|
||||
/// call this explicitly — `append` flushes every
|
||||
/// `Self::DEFAULT_FLUSH_EVERY_SAMPLES` — but may do so at natural
|
||||
/// boundaries (end-of-utterance, UI events) for tighter recovery.
|
||||
pub fn flush(&mut self) -> Result<()> {
|
||||
self.inner.flush().map_err(|e| {
|
||||
KonError::Io(std::io::Error::other(format!("WAV flush failed: {e}")))
|
||||
})?;
|
||||
self.samples_since_flush = 0;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Finalise the WAV: writes the terminal header state and closes
|
||||
/// the file. Call on clean session end. A dropped-without-finalize
|
||||
/// writer leaves a playable file up to the last flush; callers
|
||||
/// that care about the unflushed tail should always finalise.
|
||||
pub fn finalize(self) -> Result<()> {
|
||||
self.inner.finalize().map_err(|e| {
|
||||
KonError::Io(std::io::Error::other(format!("WAV finalize failed: {e}")))
|
||||
})?;
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
/// Write f32 PCM samples to a 16-bit WAV file.
|
||||
pub fn write_wav(path: &Path, audio: &AudioSamples) -> Result<()> {
|
||||
let spec = hound::WavSpec {
|
||||
@@ -58,6 +151,72 @@ pub fn read_wav(path: &Path) -> Result<AudioSamples> {
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn wav_writer_survives_crash() {
|
||||
// Property under test: a `WavWriter` that has been flushed but
|
||||
// never finalised leaves a valid, readable WAV on disk. This
|
||||
// is the crash-safety guarantee — if the kon process aborts
|
||||
// mid-session, the on-disk file up to the last flush is
|
||||
// recoverable.
|
||||
//
|
||||
// `std::mem::forget` is the canonical way to simulate an
|
||||
// abort inside a unit test: it skips the Drop impl (which
|
||||
// would otherwise finalise the hound writer for us) and
|
||||
// mirrors what happens when the OS reaps the process without
|
||||
// giving Rust a chance to run destructors.
|
||||
let temp_dir = std::env::temp_dir();
|
||||
let path = temp_dir.join("kon_test_wav_writer_survives_crash.wav");
|
||||
let _ = std::fs::remove_file(&path);
|
||||
|
||||
let mut writer = WavWriter::create(&path, 16_000, 1).unwrap();
|
||||
let flushed_samples = vec![0.1_f32; 16_000]; // 1s
|
||||
writer.append(&flushed_samples).unwrap();
|
||||
writer.flush().unwrap();
|
||||
|
||||
// Post-flush, append another second that will NOT be reflected
|
||||
// in the header if the writer dies before the next flush.
|
||||
let unflushed_tail = vec![0.2_f32; 16_000];
|
||||
writer.append(&unflushed_tail).unwrap();
|
||||
|
||||
// Abort — Drop does not run, the hound finaliser is skipped.
|
||||
std::mem::forget(writer);
|
||||
|
||||
let loaded = read_wav(&path).unwrap();
|
||||
assert_eq!(loaded.sample_rate(), 16_000);
|
||||
assert!(
|
||||
loaded.samples().len() >= 16_000,
|
||||
"expected at least the flushed 16000 samples, got {}",
|
||||
loaded.samples().len()
|
||||
);
|
||||
// The flushed portion is readable and approximately correct.
|
||||
for s in &loaded.samples()[..16_000] {
|
||||
assert!(
|
||||
(s - 0.1).abs() < 0.01,
|
||||
"flushed sample {s} deviates from 0.1 beyond 16-bit quantisation slack",
|
||||
);
|
||||
}
|
||||
|
||||
let _ = std::fs::remove_file(&path);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn wav_writer_append_then_finalize_roundtrips() {
|
||||
let temp_dir = std::env::temp_dir();
|
||||
let path = temp_dir.join("kon_test_wav_writer_finalize.wav");
|
||||
let _ = std::fs::remove_file(&path);
|
||||
|
||||
let mut writer = WavWriter::create(&path, 16_000, 1).unwrap();
|
||||
writer.append(&vec![0.0_f32; 8_000]).unwrap();
|
||||
writer.append(&vec![0.5_f32; 8_000]).unwrap();
|
||||
writer.finalize().unwrap();
|
||||
|
||||
let loaded = read_wav(&path).unwrap();
|
||||
assert_eq!(loaded.sample_rate(), 16_000);
|
||||
assert_eq!(loaded.samples().len(), 16_000);
|
||||
|
||||
let _ = std::fs::remove_file(&path);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn wav_roundtrip() {
|
||||
let temp_dir = std::env::temp_dir();
|
||||
|
||||
Reference in New Issue
Block a user