9 Commits
Author SHA1 Message Date
hauke 6a14f50e4c chore #14740: release 0.3.0 2026-11-10 13:54:25 +01:00
haukeandClaude Opus 5.5 8c47388eee fix #14740: serve playback only to the main window
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-11-10 13:52:26 +01:00
haukeandClaude Opus 5.5 a74cfa5864 feat #14740: play back calls
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-11-10 13:37:47 +01:00
haukeandClaude Sonnet 5 8d757fd639 feat #14740: transcription model choice, vocabulary and short-word corrections
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-11-10 13:10:50 +01:00
hauke c57eb9511d chore #14740: update feed 0.2.4 2026-11-10 12:54:21 +01:00
hauke 7a45d20f46 chore #14740: release 0.2.4 2026-11-10 12:54:12 +01:00
haukeandClaude Opus 5.5 802a6f81fd fix #14740: compact open-count badge in the sidebar header
Review found two bugs in 0ae6ed3: the " · N offen" suffix lost its
leading space to Svelte's whitespace trimming, and the header wrapped
the record button + gear onto a second line whenever N > 0, at both
the ~288px default and the 260px sidebar floor.

Replaces the text suffix with a small rounded count badge (same blue
as the row dots) right after "Gespräche", with title/aria-label "N
offen", and tightens the header so it fits on one line even at the
260px floor with a two-digit count. Also gives the row dot a thin
white ring so it stays visible on the selected row's tinted
background.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-11-10 12:20:57 +01:00
haukeandClaude Opus 5.5 0ae6ed304f feat #14740: done only once uploaded
A done call only shows "fertig" once its transcript reached this
build's backend (uploaded_here); otherwise it's "bereit zum
Hochladen". The list row gets a blue dot for anything needing action
(ready to upload or not transcribed yet), and the sidebar header shows
"Gespräche · N offen".

Adds ListState/needs_action to CallListItem, computed in
recorder-core so the UI doesn't re-implement the rule.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-11-10 12:09:08 +01:00
hauke 183c135b1d chore #14740: update feed 0.2.3 2026-11-09 15:08:10 +01:00
28 changed files with 2513 additions and 47 deletions
Generated
+8 -1
View File
@@ -445,10 +445,11 @@ dependencies = [
[[package]] [[package]]
name = "call-recorder" name = "call-recorder"
version = "0.2.3" version = "0.3.0"
dependencies = [ dependencies = [
"async-trait", "async-trait",
"chrono", "chrono",
"http-range",
"log", "log",
"recorder-audio", "recorder-audio",
"recorder-core", "recorder-core",
@@ -1803,6 +1804,12 @@ dependencies = [
"pin-project-lite", "pin-project-lite",
] ]
[[package]]
name = "http-range"
version = "0.1.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2149c4b4b83390c71fab669730347d578ec6bdf759f2160c581ad8b8819733b4"
[[package]] [[package]]
name = "httparse" name = "httparse"
version = "1.10.1" version = "1.10.1"
+352
View File
@@ -0,0 +1,352 @@
//! Mixes the two 16 kHz mono tracks of a call into one mono track for
//! playback.
//!
//! The tracks are summed at full level and passed through a soft clipper,
//! so a passage where only one side speaks keeps its original loudness
//! while both sides speaking loudly at once never wraps around or clips
//! hard. [`mix_wavs`] streams both files in chunks, so even a long call
//! never sits in memory.
use std::fs::{self, File};
use std::io::{self, BufReader, ErrorKind};
use std::path::Path;
use hound::{SampleFormat, WavReader, WavSpec, WavWriter};
use super::wav::SAMPLE_RATE;
/// Samples read per track and step in [`mix_wavs`] (about one second).
const CHUNK_SAMPLES: usize = 16_384;
/// Up to this level (half of full scale) the sum passes unchanged; above,
/// the soft clipper compresses it towards full scale.
const KNEE: f32 = 0.5;
/// The format of both tracks and of the mixed file.
fn spec() -> WavSpec {
WavSpec {
channels: 1,
sample_rate: SAMPLE_RATE,
bits_per_sample: 16,
sample_format: SampleFormat::Int,
}
}
/// Mixes `a` and `b` sample by sample and appends the result to `out`.
/// The output is as long as the longer input; the shorter one counts as
/// silence after its end. Never clips hard: see [`soft_clip`].
pub fn mix_samples(a: &[i16], b: &[i16], out: &mut Vec<i16>) {
let len = a.len().max(b.len());
out.reserve(len);
for i in 0..len {
let sum = to_f32(a.get(i).copied().unwrap_or(0)) + to_f32(b.get(i).copied().unwrap_or(0));
out.push(to_i16(soft_clip(sum)));
}
}
fn to_f32(sample: i16) -> f32 {
sample as f32 / i16::MAX as f32
}
fn to_i16(sample: f32) -> i16 {
(sample.clamp(-1.0, 1.0) * i16::MAX as f32).round() as i16
}
/// Linear up to [`KNEE`]; above, `tanh` bends the level smoothly (same
/// slope at the knee) towards, but never beyond, full scale.
fn soft_clip(x: f32) -> f32 {
let level = x.abs();
if level <= KNEE {
return x;
}
let room = 1.0 - KNEE;
x.signum() * (KNEE + room * ((level - KNEE) / room).tanh())
}
/// One source track; `None` if the file is missing or holds no audio.
type Track = Option<hound::WavIntoSamples<BufReader<File>, i16>>;
/// Whether the WAV at `path` holds audio to play: it is a 16 kHz mono
/// 16-bit PCM track whose header counts at least one sample. The one rule
/// both [`mix_wavs`] and the detail view's "audio available" go by.
pub fn has_audio(path: &Path) -> bool {
open_track(path).is_some()
}
/// Opens a track for [`mix_wavs`]; `None` unless it [has audio](has_audio).
/// Why an existing file is left out is logged.
fn open_track(path: &Path) -> Track {
if path.as_os_str().is_empty() {
return None;
}
let reader = match WavReader::open(path) {
Ok(reader) => reader,
Err(hound::Error::IoError(e)) if e.kind() == ErrorKind::NotFound => return None,
Err(e) => {
log::warn!("left out {}: {e}", path.display());
return None;
}
};
if reader.spec() != spec() {
log::warn!("left out {}: not 16 kHz mono 16-bit PCM", path.display());
return None;
}
if reader.len() == 0 {
return None;
}
Some(reader.into_samples())
}
/// Reads up to [`CHUNK_SAMPLES`] samples of `track` into `buf` (cleared
/// first).
fn read_chunk(track: &mut Track, buf: &mut Vec<i16>) -> io::Result<()> {
buf.clear();
let Some(samples) = track else {
return Ok(());
};
for sample in samples.take(CHUNK_SAMPLES) {
buf.push(sample.map_err(|e| io::Error::new(ErrorKind::InvalidData, e))?);
}
Ok(())
}
/// Mixes the WAV tracks at `a` and `b` (16 kHz mono 16-bit PCM, as written
/// by [`super::TrackWriter`]) into a new WAV at `dest` and returns its
/// length in samples. A track without audio ([`has_audio`]: missing,
/// empty or not in that format) is left out; with neither track holding
/// audio nothing is written and the error is [`ErrorKind::NotFound`].
///
/// Writes `dest` with a `.part` suffix first and renames it at the end, so
/// `dest` is never a half-written file.
pub fn mix_wavs(a: &Path, b: &Path, dest: &Path) -> io::Result<u64> {
let mut track_a = open_track(a);
let mut track_b = open_track(b);
if track_a.is_none() && track_b.is_none() {
return Err(io::Error::new(
ErrorKind::NotFound,
"no audio in either track",
));
}
let mut part = dest.as_os_str().to_owned();
part.push(".part");
let part = Path::new(&part);
let result = write_mix(&mut track_a, &mut track_b, part);
match result {
Ok(samples) => {
fs::rename(part, dest)?;
Ok(samples)
}
Err(e) => {
let _ = fs::remove_file(part);
Err(e)
}
}
}
fn write_mix(a: &mut Track, b: &mut Track, path: &Path) -> io::Result<u64> {
let mut writer = WavWriter::create(path, spec()).map_err(hound_to_io)?;
let (mut buf_a, mut buf_b, mut mixed) = (Vec::new(), Vec::new(), Vec::new());
let mut written = 0u64;
loop {
read_chunk(a, &mut buf_a)?;
read_chunk(b, &mut buf_b)?;
if buf_a.is_empty() && buf_b.is_empty() {
break;
}
mixed.clear();
mix_samples(&buf_a, &buf_b, &mut mixed);
for &sample in &mixed {
writer.write_sample(sample).map_err(hound_to_io)?;
}
written += mixed.len() as u64;
}
writer.finalize().map_err(hound_to_io)?;
Ok(written)
}
fn hound_to_io(e: hound::Error) -> io::Error {
match e {
hound::Error::IoError(e) => e,
other => io::Error::other(other),
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::audio::TrackWriter;
fn mix(a: &[i16], b: &[i16]) -> Vec<i16> {
let mut out = Vec::new();
mix_samples(a, b, &mut out);
out
}
#[test]
fn quiet_samples_of_equal_length_are_summed() {
assert_eq!(mix(&[100, -200, 0], &[50, 300, -7]), vec![150, 100, -7]);
}
#[test]
fn the_longer_track_continues_alone() {
assert_eq!(mix(&[1, 2], &[10, 20, 30, 40]), vec![11, 22, 30, 40]);
assert_eq!(mix(&[10, 20, 30], &[1]), vec![11, 20, 30]);
}
#[test]
fn an_empty_track_leaves_the_other_unchanged_up_to_the_knee() {
let half = (KNEE * i16::MAX as f32) as i16;
let track = [0, 1234, -1234, half, -half, i16::MIN + 1];
let mut expected = track.to_vec();
// Beyond the knee even a single track is compressed (but stays
// loud and keeps its sign).
let last = mix(&[], &track)[5];
expected[5] = last;
assert!(last < -28_000, "{last}");
assert_eq!(mix(&[], &track), expected);
assert_eq!(mix(&track, &[]), expected);
assert_eq!(mix(&[], &[]), Vec::<i16>::new());
}
#[test]
fn full_scale_on_both_sides_stays_within_full_scale() {
let out = mix(
&[i16::MAX, i16::MIN, i16::MAX],
&[i16::MAX, i16::MIN, i16::MIN],
);
// Loud, with the right sign, and softly short of full scale.
assert!(out[0] > 30_000 && out[0] < i16::MAX, "{}", out[0]);
assert!(out[1] < -30_000 && out[1] > -i16::MAX, "{}", out[1]);
// Opposite full-scale samples cancel instead of wrapping around.
assert!(out[2].abs() <= 1, "{}", out[2]);
}
#[test]
fn the_soft_clip_is_monotonic_and_bounded() {
let mut last = -1.0f32;
for step in -400..=400 {
let x = step as f32 / 200.0; // -2.0 ..= 2.0
let y = soft_clip(x);
assert!(y >= last, "not monotonic at {x}");
assert!(y.abs() < 1.0, "{x} -> {y}");
last = y;
}
}
fn write_track(path: &Path, samples: &[f32]) {
let mut writer = TrackWriter::create(path).unwrap();
writer.write(samples).unwrap();
writer.finalize().unwrap();
}
fn read(path: &Path) -> Vec<i16> {
WavReader::open(path)
.unwrap()
.into_samples::<i16>()
.map(Result::unwrap)
.collect()
}
#[test]
fn two_files_are_mixed_across_several_chunks() {
let dir = tempfile::tempdir().unwrap();
let (a, b, dest) = (
dir.path().join("a.wav"),
dir.path().join("b.wav"),
dir.path().join("m.wav"),
);
let long = CHUNK_SAMPLES * 2 + 100;
write_track(&a, &vec![0.1; long]);
write_track(&b, &vec![0.2; CHUNK_SAMPLES + 7]);
assert_eq!(mix_wavs(&a, &b, &dest).unwrap(), long as u64);
let mixed = read(&dest);
assert_eq!(mixed.len(), long);
let both = to_i16(0.1) + to_i16(0.2);
assert!((mixed[0] - both).abs() <= 1);
assert!((mixed[CHUNK_SAMPLES + 6] - both).abs() <= 1);
assert_eq!(mixed[CHUNK_SAMPLES + 7], to_i16(0.1));
assert_eq!(mixed[long - 1], to_i16(0.1));
assert!(!dir.path().join("m.wav.part").exists());
}
#[test]
fn a_missing_or_empty_file_is_left_out() {
let dir = tempfile::tempdir().unwrap();
let (a, empty, dest) = (
dir.path().join("a.wav"),
dir.path().join("e.wav"),
dir.path().join("m.wav"),
);
write_track(&a, &[0.25; 10]);
write_track(&empty, &[]);
assert_eq!(
mix_wavs(&dir.path().join("gone.wav"), &a, &dest).unwrap(),
10
);
assert_eq!(read(&dest), vec![to_i16(0.25); 10]);
assert_eq!(mix_wavs(&a, &empty, &dest).unwrap(), 10);
assert_eq!(read(&dest), vec![to_i16(0.25); 10]);
}
#[test]
fn without_audio_in_either_file_nothing_is_written() {
let dir = tempfile::tempdir().unwrap();
let (empty, dest) = (dir.path().join("e.wav"), dir.path().join("m.wav"));
write_track(&empty, &[]);
let err = mix_wavs(&empty, &dir.path().join("gone.wav"), &dest).unwrap_err();
assert_eq!(err.kind(), ErrorKind::NotFound);
assert!(!dest.exists());
}
#[test]
fn a_file_that_is_not_a_track_is_left_out() {
let dir = tempfile::tempdir().unwrap();
let (a, junk, other, dest) = (
dir.path().join("a.wav"),
dir.path().join("j.wav"),
dir.path().join("o.wav"),
dir.path().join("m.wav"),
);
write_track(&a, &[0.25; 10]);
fs::write(&junk, b"not a wav file at all").unwrap();
let stereo = WavSpec {
channels: 2,
..spec()
};
let mut writer = WavWriter::create(&other, stereo).unwrap();
writer.write_sample(1i16).unwrap();
writer.write_sample(1i16).unwrap();
writer.finalize().unwrap();
assert_eq!(mix_wavs(&a, &junk, &dest).unwrap(), 10);
assert_eq!(mix_wavs(&other, &a, &dest).unwrap(), 10);
let err = mix_wavs(&junk, &other, &dest).unwrap_err();
assert_eq!(err.kind(), ErrorKind::NotFound);
}
#[test]
fn a_track_has_audio_only_with_samples_in_the_track_format() {
let dir = tempfile::tempdir().unwrap();
let path = |name: &str| dir.path().join(name);
assert!(!has_audio(&path("gone.wav")), "missing");
assert!(!has_audio(Path::new("")), "no path");
write_track(&path("empty.wav"), &[]);
assert!(!has_audio(&path("empty.wav")), "header only");
// Larger than a header, but its header says it holds nothing.
let mut bytes = fs::read(path("empty.wav")).unwrap();
bytes.extend([0u8; 100]);
fs::write(path("unrepaired.wav"), bytes).unwrap();
assert!(
!has_audio(&path("unrepaired.wav")),
"data not in the header"
);
fs::write(path("junk.wav"), vec![7u8; 100]).unwrap();
assert!(!has_audio(&path("junk.wav")), "not a wav");
write_track(&path("one.wav"), &[0.1]);
assert!(has_audio(&path("one.wav")));
}
}
+3 -1
View File
@@ -11,10 +11,12 @@ mod conditioner;
mod flac; mod flac;
mod gap; mod gap;
mod level; mod level;
mod mix;
mod wav; mod wav;
pub use conditioner::Conditioner; pub use conditioner::Conditioner;
pub use flac::encode_flac; pub use flac::encode_flac;
pub use gap::GapFiller; pub use gap::GapFiller;
pub use level::rms_level; pub use level::rms_level;
pub use wav::{repair_wav, TrackWriter}; pub use mix::{has_audio, mix_samples, mix_wavs};
pub use wav::{repair_wav, TrackWriter, SAMPLE_RATE};
+188 -5
View File
@@ -6,6 +6,7 @@ use std::collections::BTreeMap;
use chrono::{DateTime, Local}; use chrono::{DateTime, Local};
use serde::Serialize; use serde::Serialize;
use crate::corrections::correct_segment_text;
use crate::merge; use crate::merge;
use crate::model::{Call, CallId, CallStatus, Segment, Speaker}; use crate::model::{Call, CallId, CallStatus, Segment, Speaker};
@@ -18,6 +19,15 @@ pub struct CallListItem {
/// Whole seconds from start to end; 0 while recording. /// Whole seconds from start to end; 0 while recording.
pub duration_secs: i64, pub duration_secs: i64,
pub status: CallStatus, pub status: CallStatus,
/// What the status pill shows and whether the row needs the user's
/// attention — see [`ListState`]. Computed from `status` and
/// [`uploaded_here`] so the UI does not re-implement the rule.
pub list_state: ListState,
/// Whether this row needs the user to act on it (the dot in
/// `CallList.svelte` and the sidebar header's "N offen" count). Equal
/// to `list_state.needs_action()`, kept as its own field so the UI
/// does not need to know `ListState`'s variants to filter by it.
pub needs_action: bool,
pub interrupted: bool, pub interrupted: bool,
/// The name the user gave the call, if any. /// The name the user gave the call, if any.
pub title: Option<String>, pub title: Option<String>,
@@ -35,12 +45,15 @@ impl CallListItem {
/// row. Nothing is deleted; the fields are just not shown as set. /// row. Nothing is deleted; the fields are just not shown as set.
pub fn of(call: &Call, backend_url: &str) -> Self { pub fn of(call: &Call, backend_url: &str) -> Self {
let uploaded = uploaded_here(call, backend_url); let uploaded = uploaded_here(call, backend_url);
let list_state = ListState::of(call.status, uploaded);
Self { Self {
id: call.id, id: call.id,
app: call.app.clone(), app: call.app.clone(),
started_at: call.started_at, started_at: call.started_at,
duration_secs: duration_secs(call), duration_secs: duration_secs(call),
status: call.status, status: call.status,
list_state,
needs_action: list_state.needs_action(),
interrupted: call.interrupted, interrupted: call.interrupted,
title: call.title.clone(), title: call.title.clone(),
crm_transcript_id: if uploaded { crm_transcript_id: if uploaded {
@@ -53,6 +66,45 @@ impl CallListItem {
} }
} }
/// What the call list row (and the detail header's pill) shows about a
/// call's status. Mirrors [`CallStatus`] one-to-one, except that `Done`
/// splits in two: a call is only ever shown as done ("fertig") once its
/// transcript has actually reached *this build's* backend ([`uploaded_here`]);
/// otherwise — never uploaded, or uploaded to a different backend — it is
/// `ReadyToUpload` ("bereit zum Hochladen"), because from this build's
/// point of view the CRM has not seen it yet.
#[derive(Serialize, Clone, Copy, Debug, PartialEq, Eq)]
#[serde(rename_all = "snake_case")]
pub enum ListState {
Recording,
AwaitingDecision,
Processing,
Failed,
Done,
ReadyToUpload,
}
impl ListState {
fn of(status: CallStatus, uploaded_here: bool) -> Self {
match status {
CallStatus::Recording => ListState::Recording,
CallStatus::AwaitingDecision => ListState::AwaitingDecision,
CallStatus::Processing => ListState::Processing,
CallStatus::Failed => ListState::Failed,
CallStatus::Done if uploaded_here => ListState::Done,
CallStatus::Done => ListState::ReadyToUpload,
}
}
/// Whether a row in this state needs the user to act on it: not yet
/// transcribed, or transcribed but not uploaded here. Excludes
/// `Failed` (already shown in red) and the transient
/// `Recording`/`Processing` states.
pub fn needs_action(self) -> bool {
matches!(self, ListState::AwaitingDecision | ListState::ReadyToUpload)
}
}
/// Whole seconds from `started_at` to `ended_at`; 0 while the call has not /// Whole seconds from `started_at` to `ended_at`; 0 while the call has not
/// ended (and never negative). /// ended (and never negative).
pub fn duration_secs(call: &Call) -> i64 { pub fn duration_secs(call: &Call) -> i64 {
@@ -120,18 +172,30 @@ pub struct CallDetail {
/// Whether the transcript is being uploaded right now. Set by the app, /// Whether the transcript is being uploaded right now. Set by the app,
/// which tracks its uploads; `false` from [`CallDetail::of`]. /// which tracks its uploads; `false` from [`CallDetail::of`].
pub uploading: bool, pub uploading: bool,
/// Whether the call's audio is still on disk to be played
/// ([`crate::playback::audio_available`]). Set by the app; `false` from
/// [`CallDetail::of`], which does not look at the files.
pub audio_available: bool,
/// Whether retention deleted the call's audio (as opposed to the files
/// being missing for another reason).
pub audio_deleted: bool,
} }
impl CallDetail { impl CallDetail {
/// `segments` are the stored ones; `merges` the stored speaker merges /// `segments` are the stored ones; `merges` the stored speaker merges
/// (source key → target key); `backend_url` is this build's backend /// (source key → target key); `backend_url` is this build's backend
/// (see [`CallListItem::of`]). /// (see [`CallListItem::of`]); `language` is the call-language setting
/// in effect now (not necessarily what the call was transcribed with),
/// used to apply [`correct_segment_text`] to each segment's text —
/// non-destructively, so it also corrects transcripts from before the
/// correction existed.
pub fn of( pub fn of(
call: &Call, call: &Call,
segments: &[Segment], segments: &[Segment],
speaker_names: BTreeMap<String, String>, speaker_names: BTreeMap<String, String>,
merges: &BTreeMap<String, String>, merges: &BTreeMap<String, String>,
backend_url: &str, backend_url: &str,
language: &str,
) -> Self { ) -> Self {
let segments = merge::apply_merges(segments, merges) let segments = merge::apply_merges(segments, merges)
.iter() .iter()
@@ -140,7 +204,7 @@ impl CallDetail {
label: merge::label(&segment.speaker, &speaker_names), label: merge::label(&segment.speaker, &speaker_names),
start: segment.start, start: segment.start,
end: segment.end, end: segment.end,
text: segment.text.clone(), text: correct_segment_text(&segment.text, language),
}) })
.collect(); .collect();
Self { Self {
@@ -152,6 +216,8 @@ impl CallDetail {
segments, segments,
merges: merge_views(merges, &speaker_names), merges: merge_views(merges, &speaker_names),
uploading: false, uploading: false,
audio_available: false,
audio_deleted: call.audio_deleted,
speaker_names, speaker_names,
} }
} }
@@ -318,6 +384,8 @@ mod tests {
started_at: at(10, 14, 0), started_at: at(10, 14, 0),
duration_secs: 60, duration_secs: 60,
status: CallStatus::AwaitingDecision, status: CallStatus::AwaitingDecision,
list_state: ListState::AwaitingDecision,
needs_action: true,
interrupted: true, interrupted: true,
title: None, title: None,
crm_transcript_id: None, crm_transcript_id: None,
@@ -351,6 +419,64 @@ mod tests {
assert!(uploaded_here(&c, BACKEND)); assert!(uploaded_here(&c, BACKEND));
} }
#[test]
fn done_is_fertig_only_once_uploaded_to_this_backend() {
let mut c = call(Some(at(10, 15, 0)));
c.status = CallStatus::Done;
// Never uploaded.
assert_eq!(
CallListItem::of(&c, BACKEND).list_state,
ListState::ReadyToUpload
);
// Uploaded, but to a different backend.
c.crm_transcript_id = Some("4711".into());
c.crm_base_url = Some(OTHER_BACKEND.into());
assert_eq!(
CallListItem::of(&c, BACKEND).list_state,
ListState::ReadyToUpload
);
// Uploaded to this build's backend.
c.crm_base_url = Some(BACKEND.into());
assert_eq!(CallListItem::of(&c, BACKEND).list_state, ListState::Done);
}
#[test]
fn needs_action_marks_awaiting_and_ready_to_upload_only() {
let mut c = call(Some(at(10, 15, 0)));
c.status = CallStatus::AwaitingDecision;
assert!(CallListItem::of(&c, BACKEND).needs_action, "awaiting");
c.status = CallStatus::Done;
assert!(
CallListItem::of(&c, BACKEND).needs_action,
"done, never uploaded"
);
for status in [
CallStatus::Processing,
CallStatus::Failed,
CallStatus::Recording,
] {
c.status = status;
assert!(
!CallListItem::of(&c, BACKEND).needs_action,
"{status:?} must not show the dot"
);
}
c.status = CallStatus::Done;
c.crm_transcript_id = Some("4711".into());
c.crm_base_url = Some(BACKEND.into());
assert!(
!CallListItem::of(&c, BACKEND).needs_action,
"done and uploaded here"
);
}
#[test] #[test]
fn an_upload_to_another_backend_is_hidden_from_the_list_item() { fn an_upload_to_another_backend_is_hidden_from_the_list_item() {
// Uploaded to OTHER_BACKEND; this build's backend is BACKEND: the // Uploaded to OTHER_BACKEND; this build's backend is BACKEND: the
@@ -389,6 +515,7 @@ mod tests {
names.clone(), names.clone(),
&BTreeMap::new(), &BTreeMap::new(),
BACKEND, BACKEND,
"de",
); );
let lines: Vec<_> = detail let lines: Vec<_> = detail
@@ -439,6 +566,7 @@ mod tests {
names, names,
&merges, &merges,
BACKEND, BACKEND,
"de",
); );
let lines: Vec<_> = detail let lines: Vec<_> = detail
@@ -490,9 +618,15 @@ mod tests {
c.transcribed_at = Some(at(10, 20, 0)); c.transcribed_at = Some(at(10, 20, 0));
let merges = keys(&[("remote:2", "remote:1")]); let merges = keys(&[("remote:2", "remote:1")]);
let value = let value = serde_json::to_value(CallDetail::of(
serde_json::to_value(CallDetail::of(&c, &[], BTreeMap::new(), &merges, BACKEND)) &c,
.unwrap(); &[],
BTreeMap::new(),
&merges,
BACKEND,
"de",
))
.unwrap();
assert_eq!( assert_eq!(
value, value,
@@ -503,6 +637,8 @@ mod tests {
"started_at": serde_json::to_value(at(10, 14, 0)).unwrap(), "started_at": serde_json::to_value(at(10, 14, 0)).unwrap(),
"duration_secs": 60, "duration_secs": 60,
"status": "failed", "status": "failed",
"list_state": "failed",
"needs_action": false,
"interrupted": false, "interrupted": false,
"title": "Reklamation", "title": "Reklamation",
"crm_transcript_id": null, "crm_transcript_id": null,
@@ -519,17 +655,29 @@ mod tests {
"into_label": "Sprecher 1", "into_label": "Sprecher 1",
}], }],
"uploading": false, "uploading": false,
"audio_available": false,
"audio_deleted": false,
}) })
); );
} }
fn detail_with(c: &Call, segments: &[Segment], names: &[(&str, &str)]) -> CallDetail { fn detail_with(c: &Call, segments: &[Segment], names: &[(&str, &str)]) -> CallDetail {
detail_with_language(c, segments, names, "de")
}
fn detail_with_language(
c: &Call,
segments: &[Segment],
names: &[(&str, &str)],
language: &str,
) -> CallDetail {
CallDetail::of( CallDetail::of(
c, c,
segments, segments,
keys(names), keys(names),
&keys(&[("remote:2", "remote:1")]), &keys(&[("remote:2", "remote:1")]),
BACKEND, BACKEND,
language,
) )
} }
@@ -591,4 +739,39 @@ mod tests {
} }
assert_eq!(NO_TRANSCRIPT, "Kein Transkript zum Hochladen"); assert_eq!(NO_TRANSCRIPT, "Kein Transkript zum Hochladen");
} }
#[test]
fn a_whole_segment_mistranscribed_as_english_is_corrected_in_the_detail_view() {
let c = call(Some(at(10, 15, 0)));
let segments = [
segment(Speaker::Me, 0.0, "Cheers!"),
segment(Speaker::Remote(3), 3.0, "Perfect."),
segment(Speaker::Remote(1), 6.0, "Cheers, see you later."),
];
let detail = detail_with(&c, &segments, &[]);
let texts: Vec<_> = detail.segments.iter().map(|s| s.text.as_str()).collect();
assert_eq!(texts, ["Tschüss!", "Perfekt.", "Cheers, see you later."]);
}
#[test]
fn corrections_are_not_applied_outside_german_calls() {
let c = call(Some(at(10, 15, 0)));
let segments = [segment(Speaker::Me, 0.0, "Cheers!")];
let detail = detail_with_language(&c, &segments, &[], "en");
assert_eq!(detail.segments[0].text, "Cheers!");
}
#[test]
fn the_upload_text_uses_the_corrected_segment_text() {
let c = call(Some(at(10, 46, 0)));
let segments = [segment(Speaker::Me, 0.0, "Cheers!")];
let text = detail_with(&c, &segments, &[]).upload_text().unwrap();
assert!(text.ends_with("Ich: Tschüss!"), "upload text was: {text}");
}
} }
+81
View File
@@ -0,0 +1,81 @@
//! A short, hard-coded list of German short utterances that the
//! transcription service sometimes mistranscribes as English when they
//! stand alone in an otherwise German call ("Tschüss" → "Cheers!",
//! "Perfekt" → "Perfect."). Applied non-destructively wherever a segment's
//! text is shown or uploaded (see [`crate::call_view::CallDetail::of`]),
//! never to the stored segments themselves — fixing the list later fixes
//! already-transcribed calls too.
//!
//! Not user-editable (yet): a fixed code constant, checked only against a
//! segment's *entire* text, so it never touches a short mistranscription
//! embedded in a longer sentence.
/// (mistranscribed English word, correct German word) pairs.
const CORRECTIONS: &[(&str, &str)] = &[("Cheers", "Tschüss"), ("Perfect", "Perfekt")];
/// Returns `text`'s correction if the call's `language` is German (`"de"`)
/// and `text` — ignoring surrounding whitespace and one run of trailing
/// `. ! ? ,` — case-insensitively equals one of [`CORRECTIONS`]'s source
/// words in full; the original trailing punctuation, if any, is kept (e.g.
/// "Cheers!" → "Tschüss!"). Otherwise `text` is returned unchanged,
/// including when it merely *contains* a source word ("Cheers, see you").
pub fn correct_segment_text(text: &str, language: &str) -> String {
if language != "de" {
return text.to_string();
}
let trimmed = text.trim();
let core = trimmed.trim_end_matches(['.', '!', '?', ',']);
let punctuation = &trimmed[core.len()..];
match CORRECTIONS
.iter()
.find(|(wrong, _)| core.eq_ignore_ascii_case(wrong))
{
Some((_, right)) => format!("{right}{punctuation}"),
None => text.to_string(),
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn a_whole_mistranscribed_utterance_is_corrected_case_insensitively() {
assert_eq!(correct_segment_text("Cheers!", "de"), "Tschüss!");
assert_eq!(correct_segment_text("cheers", "de"), "Tschüss");
assert_eq!(correct_segment_text("CHEERS!", "de"), "Tschüss!");
assert_eq!(correct_segment_text("Perfect.", "de"), "Perfekt.");
assert_eq!(correct_segment_text("perfect?", "de"), "Perfekt?");
}
#[test]
fn surrounding_whitespace_is_ignored_for_matching() {
assert_eq!(correct_segment_text(" Cheers! ", "de"), "Tschüss!");
}
#[test]
fn a_mistranscription_inside_a_longer_sentence_is_untouched() {
assert_eq!(
correct_segment_text("Cheers, see you", "de"),
"Cheers, see you"
);
assert_eq!(
correct_segment_text("That was perfect.", "de"),
"That was perfect."
);
}
#[test]
fn not_applied_outside_german_calls() {
assert_eq!(correct_segment_text("Cheers!", "en"), "Cheers!");
assert_eq!(correct_segment_text("Cheers!", "auto"), "Cheers!");
}
#[test]
fn text_without_a_match_is_returned_unchanged() {
assert_eq!(
correct_segment_text("Hallo zusammen.", "de"),
"Hallo zusammen."
);
}
}
+2
View File
@@ -8,11 +8,13 @@ pub mod audio;
pub mod backend; pub mod backend;
pub mod call_view; pub mod call_view;
pub mod capture; pub mod capture;
pub mod corrections;
pub mod detect; pub mod detect;
pub mod http; pub mod http;
pub mod merge; pub mod merge;
pub mod model; pub mod model;
pub mod pipeline; pub mod pipeline;
pub mod playback;
pub mod recorder; pub mod recorder;
pub mod retention; pub mod retention;
pub mod secrets; pub mod secrets;
+27
View File
@@ -25,6 +25,9 @@ pub struct PipelineOptions {
/// ISO 639-1 code, or `"auto"`. /// ISO 639-1 code, or `"auto"`.
pub language: String, pub language: String,
pub deepscript_model: String, pub deepscript_model: String,
/// Custom words/names submitted with both tracks (DeepScript's
/// `vocabulary` field).
pub vocabulary: Vec<String>,
} }
/// Everything a pipeline run can fail with. /// Everything a pipeline run can fail with.
@@ -140,6 +143,7 @@ async fn transcribe(
language: opts.language.clone(), language: opts.language.clone(),
model: opts.deepscript_model.clone(), model: opts.deepscript_model.clone(),
single_speaker, single_speaker,
vocabulary: opts.vocabulary.clone(),
}; };
let (mic_opts, out_opts) = (track_opts(true), track_opts(false)); let (mic_opts, out_opts) = (track_opts(true), track_opts(false));
let (mic_job, out_job) = tokio::join!( let (mic_job, out_job) = tokio::join!(
@@ -431,6 +435,7 @@ mod tests {
PipelineOptions { PipelineOptions {
language: "de".to_string(), language: "de".to_string(),
deepscript_model: "premium".to_string(), deepscript_model: "premium".to_string(),
vocabulary: Vec::new(),
} }
} }
@@ -547,6 +552,7 @@ mod tests {
language: "de".to_string(), language: "de".to_string(),
model: "premium".to_string(), model: "premium".to_string(),
single_speaker, single_speaker,
vocabulary: Vec::new(),
}; };
assert_eq!( assert_eq!(
fake.submitted(), fake.submitted(),
@@ -557,6 +563,27 @@ mod tests {
); );
} }
#[tokio::test]
async fn pipeline_forwards_the_vocabulary_to_both_tracks() {
let f = fixture();
let fake = FakeTranscriber::returning(vec![], vec![]);
let opts = PipelineOptions {
vocabulary: vec!["Tschüss".to_string(), "Euvino".to_string()],
..opts()
};
process_call(&f.store, &fake, f.id, &opts, &f.work_dir())
.await
.unwrap();
for (_, submitted) in fake.submitted() {
assert_eq!(
submitted.vocabulary,
vec!["Tschüss".to_string(), "Euvino".to_string()]
);
}
}
#[tokio::test] #[tokio::test]
async fn pipeline_transcription_failure_sets_failed_keeps_audio() { async fn pipeline_transcription_failure_sets_failed_keeps_audio() {
let f = fixture(); let f = fixture();
+356
View File
@@ -0,0 +1,356 @@
//! Playback of a call in the detail view while its audio is still on disk:
//! both tracks are mixed into one cached mono WAV
//! (`<playback dir>/<id>.wav`), which the app serves to the main window
//! only (its `playback` URI scheme). The cache is rebuilt only when a track
//! is newer than it, and removed with the call's audio and when the player
//! lets go of it.
use std::fs;
use std::io::{self, ErrorKind};
use std::path::{Path, PathBuf};
use std::time::SystemTime;
use serde::Serialize;
use crate::audio::{has_audio, mix_wavs, SAMPLE_RATE};
use crate::model::{Call, CallId, CallStatus};
/// The call's audio was deleted (by retention).
pub const AUDIO_GONE: &str = "Audio nicht mehr vorhanden";
/// Neither track holds audio (files missing or empty), though nothing
/// deleted them.
pub const AUDIO_MISSING: &str = "Audio nicht vorhanden";
/// Mixing failed; the details (with file paths) only go to the log.
pub const PREPARE_FAILED: &str = "Audio konnte nicht vorbereitet werden.";
pub const RECORDING: &str = "Das Gespräch wird gerade aufgenommen";
pub const PROCESSING: &str = "Das Gespräch wird gerade verarbeitet – Wiedergabe danach möglich";
/// What the UI needs besides the call id (from which it builds the
/// `playback` URL): the mix's length.
#[derive(Serialize, Clone, Copy, Debug, PartialEq)]
pub struct PlaybackInfo {
pub duration_secs: f64,
}
/// Why `call` cannot be played, if it cannot: its tracks are still being
/// written (recording) or read for transcription (processing), or its
/// audio was deleted.
pub fn refusal(call: &Call) -> Option<&'static str> {
match call.status {
CallStatus::Recording => Some(RECORDING),
CallStatus::Processing => Some(PROCESSING),
_ if call.audio_deleted => Some(AUDIO_GONE),
_ => None,
}
}
/// Whether `call` still has audio to play: not deleted, and at least one
/// track [has audio](has_audio) — the same rule the mix goes by.
pub fn audio_available(call: &Call) -> bool {
!call.audio_deleted && (has_audio(&call.mic_path) || has_audio(&call.out_path))
}
/// Whether a cached mix last written at `cache` can be reused for tracks
/// last written at `sources` (`None`: that track does not exist). It can if
/// it exists and is newer than every existing track; with no track left
/// there is nothing it could still stand for.
pub fn is_fresh(cache: Option<SystemTime>, sources: &[Option<SystemTime>]) -> bool {
let Some(cache) = cache else {
return false;
};
let mut any = false;
for source in sources.iter().flatten() {
if *source >= cache {
return false;
}
any = true;
}
any
}
/// Where call `id`'s mix is cached in the playback directory `dir`.
pub fn cache_path(dir: &Path, id: CallId) -> PathBuf {
dir.join(format!("{id}.wav"))
}
/// Returns call `call`'s mix in the playback directory `dir`, building it
/// first unless a fresh one is cached ([`is_fresh`]). Refused (see
/// [`refusal`]) while the call records or is processed and once its audio
/// is gone; a cached mix of a call whose audio is gone is removed. Errors
/// are fit for the UI: they never contain a file path.
pub fn prepare(call: &Call, dir: &Path) -> Result<PlaybackInfo, String> {
let path = cache_path(dir, call.id);
if let Some(msg) = refusal(call) {
if msg == AUDIO_GONE {
remove_cached(dir, call.id);
}
return Err(msg.to_string());
}
let sources = [modified(&call.mic_path), modified(&call.out_path)];
if is_fresh(modified(&path), &sources) {
match duration_secs(&path) {
Ok(duration_secs) => return Ok(PlaybackInfo { duration_secs }),
Err(e) => log::warn!("call {}: rebuilding unreadable playback file: {e}", call.id),
}
}
let mixed =
fs::create_dir_all(dir).and_then(|()| mix_wavs(&call.mic_path, &call.out_path, &path));
match mixed {
Ok(samples) => Ok(PlaybackInfo {
duration_secs: samples as f64 / SAMPLE_RATE as f64,
}),
Err(e) if e.kind() == ErrorKind::NotFound => {
remove_cached(dir, call.id);
Err(AUDIO_MISSING.to_string())
}
Err(e) => {
log::error!("call {}: could not mix for playback: {e}", call.id);
Err(PREPARE_FAILED.to_string())
}
}
}
/// Removes call `id`'s cached mix, if any (with the call or its audio).
/// Failures are logged: the playback directory is emptied at every start.
pub fn remove_cached(dir: &Path, id: CallId) {
let path = cache_path(dir, id);
match fs::remove_file(&path) {
Ok(()) => {}
Err(e) if e.kind() == ErrorKind::NotFound => {}
Err(e) => log::warn!("could not remove {}: {e}", path.display()),
}
}
/// Removes every cached mix (at startup, so customer audio never lingers
/// in the cache).
pub fn clear_cache(dir: &Path) -> io::Result<()> {
match fs::remove_dir_all(dir) {
Err(e) if e.kind() == ErrorKind::NotFound => Ok(()),
other => other,
}
}
fn modified(path: &Path) -> Option<SystemTime> {
fs::metadata(path).and_then(|m| m.modified()).ok()
}
fn duration_secs(path: &Path) -> Result<f64, hound::Error> {
let reader = hound::WavReader::open(path)?;
Ok(reader.duration() as f64 / reader.spec().sample_rate as f64)
}
#[cfg(test)]
mod tests {
use std::fs::File;
use std::time::Duration;
use chrono::Local;
use super::*;
use crate::audio::TrackWriter;
fn call(dir: &Path, status: CallStatus) -> Call {
Call {
id: 7,
app: "Microsoft Teams".to_string(),
started_at: Local::now(),
ended_at: Some(Local::now()),
status,
interrupted: false,
error: None,
mic_path: dir.join("7-mic.wav"),
out_path: dir.join("7-out.wav"),
transcribed_at: None,
audio_deleted: false,
title: None,
crm_transcript_id: None,
crm_base_url: None,
uploaded_at: None,
}
}
fn write_track(path: &Path, samples: &[f32]) {
let mut writer = TrackWriter::create(path).unwrap();
writer.write(samples).unwrap();
writer.finalize().unwrap();
}
/// A call with one second on the mic and half a second on the output.
fn recorded_call(dir: &Path, status: CallStatus) -> Call {
let call = call(dir, status);
write_track(&call.mic_path, &vec![0.1; 16_000]);
write_track(&call.out_path, &vec![0.2; 8_000]);
call
}
fn set_modified(path: &Path, time: SystemTime) {
File::options()
.write(true)
.open(path)
.unwrap()
.set_modified(time)
.unwrap();
}
#[test]
fn a_cache_newer_than_every_track_is_fresh() {
let t = SystemTime::UNIX_EPOCH + Duration::from_secs(1_000);
let s = Duration::from_secs(1);
assert!(is_fresh(Some(t), &[Some(t - s), Some(t - s)]));
assert!(is_fresh(Some(t), &[None, Some(t - s)]));
assert!(!is_fresh(Some(t), &[Some(t - s), Some(t + s)]));
assert!(!is_fresh(Some(t), &[Some(t), Some(t - s)]), "same time");
assert!(!is_fresh(None, &[Some(t - s), Some(t - s)]), "no cache");
assert!(!is_fresh(Some(t), &[None, None]), "no tracks");
}
#[test]
fn recording_processing_and_deleted_calls_are_refused() {
let dir = Path::new("/nonexistent");
assert_eq!(refusal(&call(dir, CallStatus::Recording)), Some(RECORDING));
assert_eq!(
refusal(&call(dir, CallStatus::Processing)),
Some(PROCESSING)
);
let mut deleted = call(dir, CallStatus::Done);
deleted.audio_deleted = true;
assert_eq!(refusal(&deleted), Some(AUDIO_GONE));
for status in [
CallStatus::AwaitingDecision,
CallStatus::Done,
CallStatus::Failed,
] {
assert_eq!(refusal(&call(dir, status)), None, "{status:?}");
}
}
#[test]
fn audio_is_available_while_a_track_holds_audio() {
let dir = tempfile::tempdir().unwrap();
let mut c = call(dir.path(), CallStatus::Done);
assert!(!audio_available(&c), "no files");
write_track(&c.out_path, &[]);
assert!(!audio_available(&c), "header only");
write_track(&c.mic_path, &[0.1; 10]);
assert!(audio_available(&c));
c.audio_deleted = true;
assert!(!audio_available(&c), "deleted by retention");
}
#[test]
fn the_mix_is_built_once_and_reused() {
let dir = tempfile::tempdir().unwrap();
let playback = dir.path().join("playback");
let c = recorded_call(dir.path(), CallStatus::Done);
let info = prepare(&c, &playback).unwrap();
let mix = playback.join("7.wav");
assert!(mix.exists());
assert!((info.duration_secs - 1.0).abs() < 1e-9);
// Marked as written long ago: a rebuild would show a new time.
let old = SystemTime::now() - Duration::from_secs(60);
set_modified(&c.mic_path, old - Duration::from_secs(60));
set_modified(&c.out_path, old - Duration::from_secs(60));
set_modified(&mix, old);
assert_eq!(prepare(&c, &playback).unwrap(), info);
assert_eq!(modified(&mix), Some(old), "reused, not rebuilt");
}
#[test]
fn the_mix_is_rebuilt_when_a_track_is_newer() {
let dir = tempfile::tempdir().unwrap();
let playback = dir.path().join("playback");
let c = recorded_call(dir.path(), CallStatus::AwaitingDecision);
prepare(&c, &playback).unwrap();
let mix = cache_path(&playback, c.id);
let old = SystemTime::now() - Duration::from_secs(60);
set_modified(&mix, old);
// Two seconds now; the file is newer than the cache.
write_track(&c.mic_path, &vec![0.1; 32_000]);
let second = prepare(&c, &playback).unwrap();
assert!((second.duration_secs - 2.0).abs() < 1e-9);
assert_ne!(modified(&mix), Some(old));
}
#[test]
fn a_call_with_one_track_plays_that_track() {
let dir = tempfile::tempdir().unwrap();
let c = call(dir.path(), CallStatus::Failed);
write_track(&c.out_path, &vec![0.2; 4_000]);
let info = prepare(&c, &dir.path().join("playback")).unwrap();
assert!((info.duration_secs - 0.25).abs() < 1e-9);
}
#[test]
fn a_refused_call_builds_nothing() {
let dir = tempfile::tempdir().unwrap();
let playback = dir.path().join("playback");
for status in [CallStatus::Recording, CallStatus::Processing] {
let c = recorded_call(dir.path(), status);
assert!(prepare(&c, &playback).is_err());
assert!(!cache_path(&playback, c.id).exists());
}
}
#[test]
fn deleted_audio_removes_the_cached_mix() {
let dir = tempfile::tempdir().unwrap();
let playback = dir.path().join("playback");
let mut c = recorded_call(dir.path(), CallStatus::Done);
prepare(&c, &playback).unwrap();
let mix = cache_path(&playback, c.id);
// Retention deleted the audio.
fs::remove_file(&c.mic_path).unwrap();
fs::remove_file(&c.out_path).unwrap();
c.audio_deleted = true;
assert_eq!(prepare(&c, &playback), Err(AUDIO_GONE.to_string()));
assert!(!mix.exists());
}
#[test]
fn missing_files_remove_the_cached_mix() {
let dir = tempfile::tempdir().unwrap();
let playback = dir.path().join("playback");
let c = recorded_call(dir.path(), CallStatus::Done);
prepare(&c, &playback).unwrap();
let mix = cache_path(&playback, c.id);
fs::remove_file(&c.mic_path).unwrap();
fs::remove_file(&c.out_path).unwrap();
assert_eq!(prepare(&c, &playback), Err(AUDIO_MISSING.to_string()));
assert!(!mix.exists());
}
#[test]
fn a_failed_mix_reports_no_file_paths() {
let dir = tempfile::tempdir().unwrap();
let c = recorded_call(dir.path(), CallStatus::Done);
// The playback directory cannot be created: a file is in the way.
let blocked = dir.path().join("playback");
fs::write(&blocked, b"").unwrap();
assert_eq!(prepare(&c, &blocked), Err(PREPARE_FAILED.to_string()));
}
#[test]
fn the_cache_is_removed_per_call_and_cleared_as_a_whole() {
let dir = tempfile::tempdir().unwrap();
let playback = dir.path().join("playback");
let c = recorded_call(dir.path(), CallStatus::Done);
prepare(&c, &playback).unwrap();
fs::write(playback.join("8.wav"), b"other").unwrap();
remove_cached(&playback, c.id);
assert!(!cache_path(&playback, c.id).exists());
assert!(playback.join("8.wav").exists());
remove_cached(&playback, c.id); // already gone: no error
clear_cache(&playback).unwrap();
assert!(!playback.exists());
clear_cache(&playback).unwrap(); // already gone: no error
}
}
+181 -6
View File
@@ -27,6 +27,27 @@ pub const START_AFTER_SECS: RangeInclusive<u64> = 1..=30;
/// splits a call, e.g. when the headset is switched. /// splits a call, e.g. when the headset is switched.
pub const END_AFTER_SECS: RangeInclusive<u64> = 3..=120; pub const END_AFTER_SECS: RangeInclusive<u64> = 3..=120;
/// The only `deepscript_model` values the settings UI offers (DeepScript's
/// OpenAPI spec also lists `"standard"`, not offered here). An older
/// settings.json with `"standard"` or anything else falls back to the
/// default on load (see [`Settings::load`]) rather than failing.
pub const DEEPSCRIPT_MODELS: [&str; 2] = ["premium", "premium_jade"];
/// Default custom-vocabulary terms: short standalone German words/names
/// DeepScript otherwise tends to mistranscribe or drop.
const DEFAULT_VOCABULARY: [&str; 5] = ["Tschüss", "Perfekt", "Servus", "Moin", "Euvino"];
/// Hard cap on the vocabulary list sent with every DeepScript submission.
/// DeepScript's OpenAPI spec does not document a limit for the
/// per-transcription `vocabulary` field itself (only for its separate,
/// *saved* vocabularies, capped there at 500 words — see
/// `POST /v1/vocabularies`); these two numbers are ours, chosen to keep
/// that field small.
pub const MAX_VOCABULARY_TERMS: usize = 200;
/// Hard cap on one vocabulary term's length (characters), for the same
/// reason as [`MAX_VOCABULARY_TERMS`].
pub const MAX_VOCABULARY_TERM_LEN: usize = 60;
#[derive(Serialize, Deserialize, Clone, Debug, PartialEq)] #[derive(Serialize, Deserialize, Clone, Debug, PartialEq)]
#[serde(default)] #[serde(default)]
pub struct Settings { pub struct Settings {
@@ -35,6 +56,12 @@ pub struct Settings {
pub output_device: Option<String>, pub output_device: Option<String>,
pub language: String, pub language: String,
pub deepscript_model: String, pub deepscript_model: String,
/// Custom words/names submitted with every transcription (DeepScript's
/// `vocabulary` field), e.g. names and product terms that are often
/// misheard. Normalized on load and on every edit (see
/// [`normalize_vocabulary`]): trimmed, blanks dropped, deduplicated
/// case-insensitively, order kept.
pub vocabulary: Vec<String>,
pub retention_days: u32, pub retention_days: u32,
pub autostart: bool, pub autostart: bool,
pub start_after_secs: u64, pub start_after_secs: u64,
@@ -57,6 +84,7 @@ impl Default for Settings {
output_device: None, output_device: None,
language: "de".to_string(), language: "de".to_string(),
deepscript_model: "premium".to_string(), deepscript_model: "premium".to_string(),
vocabulary: DEFAULT_VOCABULARY.iter().map(|s| s.to_string()).collect(),
retention_days: 7, retention_days: 7,
autostart: true, autostart: true,
start_after_secs: 3, start_after_secs: 3,
@@ -85,13 +113,35 @@ impl Settings {
END_AFTER_SECS.end() END_AFTER_SECS.end()
)); ));
} }
if !DEEPSCRIPT_MODELS.contains(&self.deepscript_model.as_str()) {
return Err(format!(
"Transkriptionsmodell: nur {} möglich",
DEEPSCRIPT_MODELS.join(" oder ")
));
}
if self.vocabulary.len() > MAX_VOCABULARY_TERMS {
return Err(format!(
"Vokabular: höchstens {MAX_VOCABULARY_TERMS} Begriffe"
));
}
if let Some(term) = self
.vocabulary
.iter()
.find(|term| term.chars().count() > MAX_VOCABULARY_TERM_LEN)
{
return Err(format!(
"Vokabular: „{term}“ ist länger als {MAX_VOCABULARY_TERM_LEN} Zeichen"
));
}
Ok(()) Ok(())
} }
/// The settings after the user saved `edited` over these: checked, with /// The settings after the user saved `edited` over these: normalized
/// the backend login (which only the app changes) kept, so a settings /// (see [`normalize_vocabulary`]), checked, with the backend login
/// page loaded before a login cannot undo it. /// (which only the app changes) kept, so a settings page loaded before
/// a login cannot undo it.
pub fn edited(&self, mut edited: Settings) -> Result<Settings, String> { pub fn edited(&self, mut edited: Settings) -> Result<Settings, String> {
edited.vocabulary = normalize_vocabulary(edited.vocabulary);
edited.validate()?; edited.validate()?;
edited.backend_username = self.backend_username.clone(); edited.backend_username = self.backend_username.clone();
edited.backend_key_expires_at = self.backend_key_expires_at; edited.backend_key_expires_at = self.backend_key_expires_at;
@@ -100,12 +150,20 @@ impl Settings {
} }
/// Reads the settings file. A missing or unreadable file yields the /// Reads the settings file. A missing or unreadable file yields the
/// defaults; fields missing from the file take their default value. /// defaults; fields missing from the file take their default value. A
/// `deepscript_model` outside [`DEEPSCRIPT_MODELS`] (e.g. an older
/// file's `"standard"`) falls back to the default instead of failing;
/// `vocabulary` is normalized (see [`normalize_vocabulary`]).
pub fn load(path: &Path) -> Settings { pub fn load(path: &Path) -> Settings {
fs::read_to_string(path) let mut settings: Settings = fs::read_to_string(path)
.ok() .ok()
.and_then(|json| serde_json::from_str(&json).ok()) .and_then(|json| serde_json::from_str(&json).ok())
.unwrap_or_default() .unwrap_or_default();
if !DEEPSCRIPT_MODELS.contains(&settings.deepscript_model.as_str()) {
settings.deepscript_model = Settings::default().deepscript_model;
}
settings.vocabulary = normalize_vocabulary(settings.vocabulary);
settings
} }
/// Writes the settings file (creating its directory), replacing the old /// Writes the settings file (creating its directory), replacing the old
@@ -121,6 +179,23 @@ impl Settings {
} }
} }
/// Trims each term, drops blanks, and deduplicates case-insensitively while
/// keeping the first occurrence's spelling and order.
fn normalize_vocabulary(terms: Vec<String>) -> Vec<String> {
let mut seen = std::collections::HashSet::new();
terms
.into_iter()
.filter_map(|term| {
let trimmed = term.trim();
if trimmed.is_empty() {
return None;
}
seen.insert(trimmed.to_lowercase())
.then(|| trimmed.to_string())
})
.collect()
}
#[cfg(test)] #[cfg(test)]
mod tests { mod tests {
use super::*; use super::*;
@@ -143,6 +218,10 @@ mod tests {
assert_eq!(s.output_device, None); assert_eq!(s.output_device, None);
assert_eq!(s.language, "de"); assert_eq!(s.language, "de");
assert_eq!(s.deepscript_model, "premium"); assert_eq!(s.deepscript_model, "premium");
assert_eq!(
s.vocabulary,
vec!["Tschüss", "Perfekt", "Servus", "Moin", "Euvino"]
);
assert_eq!(s.retention_days, 7); assert_eq!(s.retention_days, 7);
assert!(s.autostart); assert!(s.autostart);
assert_eq!(s.start_after_secs, 3); assert_eq!(s.start_after_secs, 3);
@@ -170,6 +249,32 @@ mod tests {
); );
} }
#[test]
fn an_older_files_model_and_a_missing_vocabulary_fall_back_to_the_default() {
let dir = tempfile::tempdir().unwrap();
let path = dir.path().join("settings.json");
fs::write(&path, r#"{"deepscript_model": "standard"}"#).unwrap();
assert_eq!(Settings::load(&path), Settings::default());
fs::write(&path, r#"{"deepscript_model": "nonsense"}"#).unwrap();
assert_eq!(Settings::load(&path), Settings::default());
}
#[test]
fn loading_normalizes_the_stored_vocabulary() {
let dir = tempfile::tempdir().unwrap();
let path = dir.path().join("settings.json");
fs::write(
&path,
r#"{"vocabulary": [" Tschüss ", "", "TSCHÜSS", " ", "Euvino"]}"#,
)
.unwrap();
assert_eq!(
Settings::load(&path).vocabulary,
vec!["Tschüss".to_string(), "Euvino".to_string()]
);
}
fn logged_in() -> Settings { fn logged_in() -> Settings {
Settings { Settings {
backend_username: Some("hinrichs".into()), backend_username: Some("hinrichs".into()),
@@ -249,6 +354,76 @@ mod tests {
} }
} }
#[test]
fn validate_rejects_a_model_outside_the_offered_two() {
for model in ["standard", "nonsense", ""] {
let s = Settings {
deepscript_model: model.to_string(),
..Settings::default()
};
assert_eq!(
s.validate(),
Err("Transkriptionsmodell: nur premium oder premium_jade möglich".to_string())
);
}
for model in ["premium", "premium_jade"] {
let s = Settings {
deepscript_model: model.to_string(),
..Settings::default()
};
assert_eq!(s.validate(), Ok(()));
}
}
#[test]
fn validate_rejects_too_many_vocabulary_terms() {
let s = Settings {
vocabulary: (0..=MAX_VOCABULARY_TERMS).map(|n| n.to_string()).collect(),
..Settings::default()
};
assert_eq!(
s.validate(),
Err(format!(
"Vokabular: höchstens {MAX_VOCABULARY_TERMS} Begriffe"
))
);
}
#[test]
fn validate_rejects_a_too_long_vocabulary_term() {
let s = Settings {
vocabulary: vec!["a".repeat(MAX_VOCABULARY_TERM_LEN + 1)],
..Settings::default()
};
assert_eq!(
s.validate(),
Err(format!(
"Vokabular: „{}“ ist länger als {MAX_VOCABULARY_TERM_LEN} Zeichen",
"a".repeat(MAX_VOCABULARY_TERM_LEN + 1)
))
);
}
#[test]
fn an_edit_normalizes_the_vocabulary_before_validating_and_saving() {
let edited = Settings {
vocabulary: vec![
" Tschüss ".to_string(),
"".to_string(),
"TSCHÜSS".to_string(),
"Kisling".to_string(),
],
..Settings::default()
};
let saved = logged_in().edited(edited).unwrap();
assert_eq!(
saved.vocabulary,
vec!["Tschüss".to_string(), "Kisling".to_string()]
);
}
#[test] #[test]
fn settings_load_missing_file_returns_default() { fn settings_load_missing_file_returns_default() {
let dir = tempfile::tempdir().unwrap(); let dir = tempfile::tempdir().unwrap();
+61
View File
@@ -201,6 +201,15 @@ impl Transcriber for DeepScript {
value: "1".to_string(), value: "1".to_string(),
}); });
} }
if !opts.vocabulary.is_empty() {
parts.push(Part::Text {
name: "vocabulary".to_string(),
// The documented format: "JSON array of custom words, or
// comma-separated string."
value: serde_json::to_string(&opts.vocabulary)
.expect("Vec<String> always serializes"),
});
}
let req = HttpRequest { let req = HttpRequest {
method: Method::Post, method: Method::Post,
@@ -385,6 +394,7 @@ mod tests {
language: language.to_string(), language: language.to_string(),
model: model.to_string(), model: model.to_string(),
single_speaker, single_speaker,
vocabulary: Vec::new(),
} }
} }
@@ -439,6 +449,57 @@ mod tests {
transport.assert_done(); transport.assert_done();
} }
#[tokio::test]
async fn submit_sends_vocabulary_as_a_json_array_string() {
let transport = Arc::new(FakeTransport::new());
transport.expect(
Method::Post,
&format!("{BASE}/transcriptions"),
202,
r#"{"data":{"id":"job-voc","status":"queued","model":"premium","originalFileName":"mic.flac","createdOn":"2026-01-01T00:00:00Z"}}"#,
);
let ds = deep_script(&transport);
let mut vocab_opts = opts("premium", "de", true);
vocab_opts.vocabulary = vec!["Tschüss".to_string(), "Euvino".to_string()];
ds.submit(Path::new("mic.flac"), &vocab_opts).await.unwrap();
let requests = transport.requests();
let HttpBody::Multipart(parts) = &requests[0].body else {
panic!("expected multipart body");
};
assert!(parts.contains(&Part::Text {
name: "vocabulary".to_string(),
value: r#"["Tschüss","Euvino"]"#.to_string(),
}));
transport.assert_done();
}
#[tokio::test]
async fn submit_omits_vocabulary_when_empty() {
let transport = Arc::new(FakeTransport::new());
transport.expect(
Method::Post,
&format!("{BASE}/transcriptions"),
202,
r#"{"data":{"id":"job-novoc","status":"queued","model":"premium","originalFileName":"mic.flac","createdOn":"2026-01-01T00:00:00Z"}}"#,
);
let ds = deep_script(&transport);
ds.submit(Path::new("mic.flac"), &opts("premium", "de", true))
.await
.unwrap();
let requests = transport.requests();
let HttpBody::Multipart(parts) = &requests[0].body else {
panic!("expected multipart body");
};
assert!(!parts
.iter()
.any(|p| matches!(p, Part::Text { name, .. } if name == "vocabulary")));
transport.assert_done();
}
#[tokio::test] #[tokio::test]
async fn submit_without_hint_for_output_track() { async fn submit_without_hint_for_output_track() {
let transport = Arc::new(FakeTransport::new()); let transport = Arc::new(FakeTransport::new());
+3
View File
@@ -24,6 +24,9 @@ pub struct TranscribeOptions {
/// the user) — the output track may have several, so this is left /// the user) — the output track may have several, so this is left
/// unset there. /// unset there.
pub single_speaker: bool, pub single_speaker: bool,
/// Custom words/names to bias the transcription towards (DeepScript's
/// `vocabulary` field); empty omits the field entirely.
pub vocabulary: Vec<String>,
} }
/// Uploads an audio file to a remote speech-to-text service, waits for the /// Uploads an audio file to a remote speech-to-text service, waits for the
+4 -4
View File
@@ -1,10 +1,10 @@
{ {
"version": "0.2.2", "version": "0.2.4",
"pub_date": "2026-11-09T11:05:43Z", "pub_date": "2026-11-10T11:50:14Z",
"platforms": { "platforms": {
"windows-x86_64": { "windows-x86_64": {
"signature": "dW50cnVzdGVkIGNvbW1lbnQ6IHNpZ25hdHVyZSBmcm9tIHRhdXJpIHNlY3JldCBrZXkKUlVUdGpRa1ZvalU2SVB0NjJZT09kazJxZlBBWi9tQWZFSUtZVTRaVnNDdnFsSUJZeDc2QWZybytFL2lUR1E5QStWY3k5Tk5xSUMxM1M3TFlhU1A5VUNkNzh0UlBvVDRMcndnPQp0cnVzdGVkIGNvbW1lbnQ6IHRpbWVzdGFtcDoxNzk0MjIyMzIxCWZpbGU6R2VzcHLDpGNoc3Jla29yZGVyXzAuMi4yX3g2NC1zZXR1cC5leGUJdmVyc2lvbjowLjIuMgpObWpiWWJKc1hodm1penNPc3BDM244elhiQ0kvUmF2ZUZVKzJSTkZ2aVArQzRTSUIvUXZ6Y0VYSUU1R3k3eFBnU1pid1ZMRHpDak9GYWtzYXdrSmlEZz09Cg==", "signature": "dW50cnVzdGVkIGNvbW1lbnQ6IHNpZ25hdHVyZSBmcm9tIHRhdXJpIHNlY3JldCBrZXkKUlVUdGpRa1ZvalU2SUJzeVppQWszcm5oN2s1Q2xIenE4U0lUWkhKbEVhVncyZkhtZzFPeFdjajVqOXRuZCswSVhhVHlhenJhL2Z5UzYwbFFRWUVQbDJPZmtWZm5MUkNvV1FZPQp0cnVzdGVkIGNvbW1lbnQ6IHRpbWVzdGFtcDoxNzk0MzExMzkxCWZpbGU6R2VzcHLDpGNoc3Jla29yZGVyXzAuMi40X3g2NC1zZXR1cC5leGUJdmVyc2lvbjowLjIuNApmOGpXV2pWb1Fsem9lUlpVYmtoSFdlU2ovSGtYdDNINnlSa3A2Qm5WL0VDeDdVdldLWnlzb3hxOEtCRm1BUEtnYXNNaUk2ZUhZUCt3Vm9Ua0tLeGhDUT09Cg==",
"url": "https://gitea.euvino.eu/public/call-recorder/releases/download/v0.2.2/Gespraechsrekorder_0.2.2_x64-setup.exe" "url": "https://gitea.euvino.eu/public/call-recorder/releases/download/v0.2.4/Gespraechsrekorder_0.2.4_x64-setup.exe"
} }
} }
} }
+2 -1
View File
@@ -1,6 +1,6 @@
[package] [package]
name = "call-recorder" name = "call-recorder"
version = "0.2.3" version = "0.3.0"
description = "Gesprächsrekorder desktop app" description = "Gesprächsrekorder desktop app"
edition = "2021" edition = "2021"
@@ -30,3 +30,4 @@ tauri-plugin-updater = "2"
tauri-plugin-opener = "2" tauri-plugin-opener = "2"
tokio = { version = "1", features = ["sync"] } tokio = { version = "1", features = ["sync"] }
async-trait = "0.1" async-trait = "0.1"
http-range = "0.1.6"
+21 -1
View File
@@ -19,7 +19,8 @@ use tauri_plugin_autostart::ManagerExt;
use crate::processing; use crate::processing;
use crate::state::{ use crate::state::{
AppState, CallBrief, DeviceLevels, DiscardError, Ended, PendingPrompt, RecordingState, AppState, CallBrief, DeviceLevels, DiscardError, Ended, PendingPrompt, PreparedPlayback,
RecordingState,
}; };
const LEVELS_INTERVAL: Duration = Duration::from_millis(100); const LEVELS_INTERVAL: Duration = Duration::from_millis(100);
@@ -208,6 +209,25 @@ pub fn rename_call(
Ok(()) Ok(())
} }
/// Mixes the call's two tracks into one file to play in the detail view
/// (or reuses the cached mix); the main window plays it from the
/// `playback` scheme ([`crate::playback`]).
#[tauri::command]
pub async fn prepare_playback(app: AppHandle, id: CallId) -> CmdResult<PreparedPlayback> {
blocking(app, move |app| app.state::<AppState>().prepare_playback(id)).await
}
/// The player is done with the mix of `lease`: it is removed from disk
/// unless a newer player of the same call holds it.
#[tauri::command]
pub async fn release_playback(app: AppHandle, id: CallId, lease: u64) -> CmdResult<()> {
blocking(app, move |app| {
app.state::<AppState>().release_playback(id, lease);
Ok(())
})
.await
}
/// Deletes a finished call's audio and row. Closes the prompt if no call /// Deletes a finished call's audio and row. Closes the prompt if no call
/// waits for it any more; otherwise the prompt reloads and shows the next. /// waits for it any more; otherwise the prompt reloads and shows the next.
/// While its DeepScript jobs are still on record, nothing is deleted and a /// While its DeepScript jobs are still on record, nothing is deleted and a
+23
View File
@@ -1,6 +1,7 @@
mod backend; mod backend;
mod commands; mod commands;
mod detection; mod detection;
mod playback;
mod processing; mod processing;
mod state; mod state;
mod tray; mod tray;
@@ -43,6 +44,21 @@ pub fn run() {
.open_js_links_on_click(false) .open_js_links_on_click(false)
.build(), .build(),
) )
// A call's mix for the player: only for the main window, whatever
// other webviews (the remote backend login) ask for.
.register_asynchronous_uri_scheme_protocol(playback::SCHEME, |ctx, request, responder| {
let webview = ctx.webview_label().to_string();
let dir = ctx
.app_handle()
.try_state::<AppState>()
.map(|state| state.playback_dir().to_path_buf());
tauri::async_runtime::spawn_blocking(move || {
responder.respond(match dir {
Some(dir) => playback::respond(&webview, &request, &dir),
None => playback::unavailable(),
})
});
})
.setup(|app| { .setup(|app| {
// Release builds log to a file in the app log directory (on // Release builds log to a file in the app log directory (on
// Windows %LOCALAPPDATA%\eu.euvino.callrecorder\logs), debug // Windows %LOCALAPPDATA%\eu.euvino.callrecorder\logs), debug
@@ -72,6 +88,8 @@ pub fn run() {
let data_dir = app.path().app_data_dir()?; let data_dir = app.path().app_data_dir()?;
let config_dir = app.path().app_config_dir()?; let config_dir = app.path().app_config_dir()?;
// Served to the main window only, by the `playback` scheme.
let playback_dir = app.path().app_cache_dir()?.join("playback");
std::fs::create_dir_all(&data_dir)?; std::fs::create_dir_all(&data_dir)?;
let store = Store::open(&data_dir.join("calls.sqlite"))?; let store = Store::open(&data_dir.join("calls.sqlite"))?;
let recovery = pipeline::recover_on_startup(&store)?; let recovery = pipeline::recover_on_startup(&store)?;
@@ -82,6 +100,7 @@ pub fn run() {
Box::new(KeyringSecrets), Box::new(KeyringSecrets),
config_dir.join("settings.json"), config_dir.join("settings.json"),
data_dir.join("recordings"), data_dir.join("recordings"),
playback_dir,
); );
let leftover_jobs = state.store.calls_with_remote_jobs().unwrap_or_else(|e| { let leftover_jobs = state.store.calls_with_remote_jobs().unwrap_or_else(|e| {
log::error!("could not read leftover remote jobs: {e}"); log::error!("could not read leftover remote jobs: {e}");
@@ -96,6 +115,8 @@ pub fn run() {
std::thread::spawn(KeyringSecrets::remove_unused_keys); std::thread::spawn(KeyringSecrets::remove_unused_keys);
// Before anything can start a run. // Before anything can start a run.
processing::clear_upload_dir(app.handle()); processing::clear_upload_dir(app.handle());
// Before any window can ask for a mix.
state.clear_playback_cache();
app.manage(state); app.manage(state);
app.manage(PendingUpdate::default()); app.manage(PendingUpdate::default());
app.manage(UpdateSchedule::default()); app.manage(UpdateSchedule::default());
@@ -154,6 +175,8 @@ pub fn run() {
commands::merge_speakers, commands::merge_speakers,
commands::unmerge_speaker, commands::unmerge_speaker,
commands::rename_call, commands::rename_call,
commands::prepare_playback,
commands::release_playback,
backend::backend_server, backend::backend_server,
backend::backend_status, backend::backend_status,
backend::backend_login, backend::backend_login,
+293
View File
@@ -0,0 +1,293 @@
//! The `playback` URI scheme: serves a call's cached mix
//! ([`recorder_core::playback`]) to the main window, and to no other
//! webview — the backend-login window shows a remote page, which must
//! never read customer audio.
//!
//! The URL carries only the call id: `playback://localhost/<id>` on Linux
//! and macOS, `http://playback.localhost/<id>` on Windows (what the UI's
//! `convertFileSrc(id, 'playback')` builds). Range requests are answered
//! so the player can seek without loading the whole file.
use std::fs::File;
use std::io::{self, ErrorKind, Read, Seek, SeekFrom};
use std::path::Path;
use http_range::HttpRange;
use recorder_core::model::CallId;
use recorder_core::playback::cache_path;
use tauri::http::header::{
ACCEPT_RANGES, ACCESS_CONTROL_ALLOW_ORIGIN, ACCESS_CONTROL_EXPOSE_HEADERS, CACHE_CONTROL,
CONTENT_LENGTH, CONTENT_RANGE, CONTENT_TYPE, RANGE,
};
use tauri::http::{response, Method, Request, Response, StatusCode};
/// The scheme's name (see the module docs for its URLs).
pub const SCHEME: &str = "playback";
/// The only webview the scheme answers.
pub const PLAYER_WEBVIEW: &str = "main";
/// The most bytes one range response carries (like Tauri's asset protocol).
const MAX_RANGE_LEN: u64 = 1024 * 1024;
/// Answers `request` from webview `webview` with call `<id>`'s mix in the
/// playback directory `dir`: 403 for any webview but the main window, 404
/// for anything but a plain numeric id or a mix that is not there, 206 for
/// a satisfiable range (at most [`MAX_RANGE_LEN`] bytes), 416 otherwise.
pub fn respond(webview: &str, request: &Request<Vec<u8>>, dir: &Path) -> Response<Vec<u8>> {
if webview != PLAYER_WEBVIEW {
log::warn!("playback refused to webview {webview}");
return empty(StatusCode::FORBIDDEN);
}
let method = request.method();
if method != Method::GET && method != Method::HEAD {
return empty(StatusCode::METHOD_NOT_ALLOWED);
}
let Some(id) = call_id(request.uri().path()) else {
return empty(StatusCode::NOT_FOUND);
};
let range = request
.headers()
.get(RANGE)
.map(|value| value.to_str().unwrap_or_default());
match serve(&cache_path(dir, id), range, method == Method::HEAD) {
Ok(response) => response,
Err(e) if e.kind() == ErrorKind::NotFound => empty(StatusCode::NOT_FOUND),
Err(e) => {
log::error!("call {id}: could not serve the playback file: {e}");
empty(StatusCode::INTERNAL_SERVER_ERROR)
}
}
}
/// The answer while the app state is not set up yet (no window can play
/// before it is, so this is never expected).
pub fn unavailable() -> Response<Vec<u8>> {
empty(StatusCode::SERVICE_UNAVAILABLE)
}
/// The call id of a request path: exactly `/<digits>`.
fn call_id(path: &str) -> Option<CallId> {
let digits = path.strip_prefix('/')?;
if digits.is_empty() || !digits.bytes().all(|b| b.is_ascii_digit()) {
return None;
}
digits.parse().ok()
}
fn serve(path: &Path, range: Option<&str>, head: bool) -> io::Result<Response<Vec<u8>>> {
let mut file = File::open(path)?;
let len = file.metadata()?.len();
let builder = headers();
let Some(range) = range else {
let mut body = Vec::new();
if !head {
file.read_to_end(&mut body)?;
}
return Ok(build(builder.header(CONTENT_LENGTH, len), body));
};
// A media element asks for one range at a time; of several, the first.
let Some(range) = HttpRange::parse(range, len)
.ok()
.and_then(|r| r.first().copied())
else {
return Ok(build(
builder
.status(StatusCode::RANGE_NOT_SATISFIABLE)
.header(CONTENT_RANGE, format!("bytes */{len}")),
Vec::new(),
));
};
let start = range.start;
let count = range.length.min(MAX_RANGE_LEN);
let mut body = Vec::new();
if !head {
file.seek(SeekFrom::Start(start))?;
file.take(count).read_to_end(&mut body)?;
}
Ok(build(
builder
.status(StatusCode::PARTIAL_CONTENT)
.header(
CONTENT_RANGE,
format!("bytes {start}-{}/{len}", start + count - 1),
)
.header(CONTENT_LENGTH, count),
body,
))
}
/// Headers of every answer that carries the mix. Any origin may read it:
/// only the main window's own page can reach the scheme at all (the
/// webview check above), and on Linux it fetches the mix cross-origin.
fn headers() -> response::Builder {
Response::builder()
.header(CONTENT_TYPE, "audio/wav")
.header(CACHE_CONTROL, "no-store")
.header(ACCEPT_RANGES, "bytes")
.header(ACCESS_CONTROL_ALLOW_ORIGIN, "*")
.header(ACCESS_CONTROL_EXPOSE_HEADERS, "content-range")
}
fn build(builder: response::Builder, body: Vec<u8>) -> Response<Vec<u8>> {
builder
.body(body)
.unwrap_or_else(|_| empty(StatusCode::INTERNAL_SERVER_ERROR))
}
fn empty(status: StatusCode) -> Response<Vec<u8>> {
let mut response = Response::new(Vec::new());
*response.status_mut() = status;
response
.headers_mut()
.insert(CACHE_CONTROL, "no-store".parse().unwrap());
response
}
#[cfg(test)]
mod tests {
use std::fs;
use super::*;
/// A playback directory with a 10-byte "mix" for call 7.
fn dir() -> tempfile::TempDir {
let dir = tempfile::tempdir().unwrap();
fs::write(cache_path(dir.path(), 7), b"0123456789").unwrap();
dir
}
fn get(uri: &str, range: Option<&str>) -> Request<Vec<u8>> {
let mut builder = Request::builder().uri(uri);
if let Some(range) = range {
builder = builder.header(RANGE, range);
}
builder.body(Vec::new()).unwrap()
}
#[test]
fn only_the_main_window_gets_the_mix() {
let dir = dir();
let request = get("playback://localhost/7", None);
for webview in ["backend-login", "prompt", "recorder", "", "Main"] {
let response = respond(webview, &request, dir.path());
assert_eq!(response.status(), StatusCode::FORBIDDEN, "{webview}");
assert!(response.body().is_empty());
}
let response = respond("main", &request, dir.path());
assert_eq!(response.status(), StatusCode::OK);
assert_eq!(response.body(), b"0123456789");
assert_eq!(response.headers()[CONTENT_TYPE], "audio/wav");
assert_eq!(response.headers()[CACHE_CONTROL], "no-store");
assert_eq!(response.headers()[CONTENT_LENGTH], "10");
}
#[test]
fn both_platform_url_forms_name_the_call() {
let dir = dir();
for uri in ["playback://localhost/7", "http://playback.localhost/7"] {
let response = respond("main", &get(uri, None), dir.path());
assert_eq!(response.status(), StatusCode::OK, "{uri}");
}
}
#[test]
fn nothing_but_a_numeric_call_id_is_served() {
let dir = dir();
fs::write(dir.path().join("secret.wav"), b"x").unwrap();
fs::write(dir.path().join("7.wav.part"), b"x").unwrap();
for path in [
"/",
"/7.wav",
"/secret",
"/../7",
"/%2e%2e%2f7",
"/7/",
"/7.wav.part",
"/-7",
"/+7",
"/%EF%BC%97",
"/99999999999999999999999",
"/8",
] {
let request = get(&format!("playback://localhost{path}"), None);
let response = respond("main", &request, dir.path());
assert_eq!(response.status(), StatusCode::NOT_FOUND, "{path}");
}
assert_eq!(call_id("/7"), Some(7));
assert_eq!(call_id("/0012"), Some(12));
}
#[test]
fn a_range_is_served_partially() {
let dir = dir();
let response = respond(
"main",
&get("playback://localhost/7", Some("bytes=2-5")),
dir.path(),
);
assert_eq!(response.status(), StatusCode::PARTIAL_CONTENT);
assert_eq!(response.body(), b"2345");
assert_eq!(response.headers()[CONTENT_RANGE], "bytes 2-5/10");
assert_eq!(response.headers()[CONTENT_LENGTH], "4");
let open_ended = respond(
"main",
&get("playback://localhost/7", Some("bytes=8-")),
dir.path(),
);
assert_eq!(open_ended.body(), b"89");
assert_eq!(open_ended.headers()[CONTENT_RANGE], "bytes 8-9/10");
}
#[test]
fn a_range_beyond_the_end_is_not_satisfiable() {
let dir = dir();
let response = respond(
"main",
&get("playback://localhost/7", Some("bytes=20-30")),
dir.path(),
);
assert_eq!(response.status(), StatusCode::RANGE_NOT_SATISFIABLE);
assert_eq!(response.headers()[CONTENT_RANGE], "bytes */10");
assert!(response.body().is_empty());
}
#[test]
fn a_long_range_is_cut_to_the_maximum() {
let dir = tempfile::tempdir().unwrap();
let len = MAX_RANGE_LEN as usize * 2 + 3;
fs::write(cache_path(dir.path(), 1), vec![1u8; len]).unwrap();
let response = respond(
"main",
&get("playback://localhost/1", Some("bytes=1-")),
dir.path(),
);
assert_eq!(response.body().len(), MAX_RANGE_LEN as usize);
assert_eq!(
response.headers()[CONTENT_RANGE],
format!("bytes 1-{}/{len}", MAX_RANGE_LEN).as_str()
);
}
#[test]
fn head_has_no_body_and_other_methods_are_refused() {
let dir = dir();
let head = Request::builder()
.method(Method::HEAD)
.uri("playback://localhost/7")
.body(Vec::new())
.unwrap();
let response = respond("main", &head, dir.path());
assert_eq!(response.status(), StatusCode::OK);
assert_eq!(response.headers()[CONTENT_LENGTH], "10");
assert!(response.body().is_empty());
let post = Request::builder()
.method(Method::POST)
.uri("playback://localhost/7")
.body(Vec::new())
.unwrap();
let response = respond("main", &post, dir.path());
assert_eq!(response.status(), StatusCode::METHOD_NOT_ALLOWED);
}
}
+1
View File
@@ -78,6 +78,7 @@ pub fn start(app: &AppHandle, id: CallId, retry: bool) -> Result<(), String> {
let opts = PipelineOptions { let opts = PipelineOptions {
language: settings.language, language: settings.language,
deepscript_model: settings.deepscript_model, deepscript_model: settings.deepscript_model,
vocabulary: settings.vocabulary,
}; };
// A fresh client per run, so a key changed in the settings applies to // A fresh client per run, so a key changed in the settings applies to
// the next run. // the next run.
+253 -5
View File
@@ -2,11 +2,12 @@
//! //!
//! Holds the store, the settings, the secret store, the HTTP transport, the //! Holds the store, the settings, the secret store, the HTTP transport, the
//! recording that is currently running, the call detector, the calls //! recording that is currently running, the call detector, the calls
//! awaiting a decision in the end-of-call prompt and the calls being //! awaiting a decision in the end-of-call prompt, the calls being
//! processed. Everything here is independent of windows and //! processed and the cached mixes for playback. Everything here is
//! events; the command layer turns results into UI updates. //! independent of windows and events; the command layer turns results into
//! UI updates.
use std::collections::{HashSet, VecDeque}; use std::collections::{HashMap, HashSet, VecDeque};
use std::fs; use std::fs;
use std::io::ErrorKind; use std::io::ErrorKind;
use std::path::{Path, PathBuf}; use std::path::{Path, PathBuf};
@@ -23,6 +24,7 @@ use recorder_core::capture::{CaptureSource, OutputTarget};
use recorder_core::detect::{CallDetector, DetectorEvent, MicSession}; use recorder_core::detect::{CallDetector, DetectorEvent, MicSession};
use recorder_core::http::{HttpTransport, ReqwestTransport}; use recorder_core::http::{HttpTransport, ReqwestTransport};
use recorder_core::model::{Call, CallId, CallStatus, Speaker}; use recorder_core::model::{Call, CallId, CallStatus, Speaker};
use recorder_core::playback;
use recorder_core::recorder::Recorder; use recorder_core::recorder::Recorder;
use recorder_core::secrets::{SecretStore, Service}; use recorder_core::secrets::{SecretStore, Service};
use recorder_core::settings::Settings; use recorder_core::settings::Settings;
@@ -147,6 +149,12 @@ pub struct AppState {
settings: Mutex<Settings>, settings: Mutex<Settings>,
settings_path: PathBuf, settings_path: PathBuf,
recordings_dir: PathBuf, recordings_dir: PathBuf,
/// Where the mixes for playback are cached (`<app cache>/playback`),
/// served to the main window by [`crate::playback`].
playback_dir: PathBuf,
/// The leases on cached mixes. Held while a mix is built or removed,
/// so a call deleted meanwhile never leaves its mix behind.
playback: Mutex<PlaybackLeases>,
current: Mutex<Option<CurrentRecording>>, current: Mutex<Option<CurrentRecording>>,
detector: Mutex<CallDetector>, detector: Mutex<CallDetector>,
/// Stopped calls awaiting the end-of-call prompt's decision, oldest /// Stopped calls awaiting the end-of-call prompt's decision, oldest
@@ -173,6 +181,23 @@ pub struct AppState {
upload_confirmed_unsaved: Mutex<HashSet<CallId>>, upload_confirmed_unsaved: Mutex<HashSet<CallId>>,
} }
/// A mix ready to play, from [`AppState::prepare_playback`].
#[derive(Serialize, Clone, Copy, Debug, PartialEq)]
pub struct PreparedPlayback {
pub duration_secs: f64,
/// Hand back to [`AppState::release_playback`] when the player is done.
pub lease: u64,
}
/// Which player holds each cached mix: the lease of the latest
/// [`AppState::prepare_playback`] per call. A player that lets go of an
/// older lease (it was replaced by a newer one meanwhile) removes nothing.
#[derive(Default)]
struct PlaybackLeases {
next: u64,
latest: HashMap<CallId, u64>,
}
/// An upload reserved with [`AppState::claim_upload`]; released when /// An upload reserved with [`AppState::claim_upload`]; released when
/// dropped, also if the upload fails or panics. /// dropped, also if the upload fails or panics.
pub struct UploadClaim<'a> { pub struct UploadClaim<'a> {
@@ -201,6 +226,7 @@ impl AppState {
secrets: Box<dyn SecretStore>, secrets: Box<dyn SecretStore>,
settings_path: PathBuf, settings_path: PathBuf,
recordings_dir: PathBuf, recordings_dir: PathBuf,
playback_dir: PathBuf,
) -> Self { ) -> Self {
let settings = Settings::load(&settings_path); let settings = Settings::load(&settings_path);
let detector = CallDetector::new(detector_config(&settings)); let detector = CallDetector::new(detector_config(&settings));
@@ -211,6 +237,8 @@ impl AppState {
settings: Mutex::new(settings), settings: Mutex::new(settings),
settings_path, settings_path,
recordings_dir, recordings_dir,
playback_dir,
playback: Mutex::new(PlaybackLeases::default()),
current: Mutex::new(None), current: Mutex::new(None),
detector: Mutex::new(detector), detector: Mutex::new(detector),
pending_prompts: Mutex::new(VecDeque::new()), pending_prompts: Mutex::new(VecDeque::new()),
@@ -647,11 +675,77 @@ impl AppState {
let segments = self.store.segments(id).map_err(|e| e.to_string())?; let segments = self.store.segments(id).map_err(|e| e.to_string())?;
let names = self.store.speaker_names(id).map_err(|e| e.to_string())?; let names = self.store.speaker_names(id).map_err(|e| e.to_string())?;
let merges = self.store.speaker_merges(id).map_err(|e| e.to_string())?; let merges = self.store.speaker_merges(id).map_err(|e| e.to_string())?;
let mut detail = CallDetail::of(&call, &segments, names, &merges, &self.backend_url); let mut detail = CallDetail::of(
&call,
&segments,
names,
&merges,
&self.backend_url,
&self.settings().language,
);
detail.uploading = self.is_uploading(id); detail.uploading = self.is_uploading(id);
detail.audio_available = playback::audio_available(&call);
Ok(detail) Ok(detail)
} }
/// Mixes call `id`'s tracks for playback (or reuses the cached mix,
/// see [`playback::prepare`]) under a new lease. Refused while the call
/// is recorded or processed, and once its audio is gone.
pub fn prepare_playback(&self, id: CallId) -> Result<PreparedPlayback, String> {
if lock(&self.current)
.as_ref()
.is_some_and(|cur| cur.call_id == id)
{
return Err(playback::RECORDING.to_string());
}
let mut leases = lock(&self.playback);
// Read under the lock: a call deleted before it is not mixed, one
// deleted meanwhile has its mix removed once the lock is free.
let call = self.find_call(id)?;
let info = playback::prepare(&call, &self.playback_dir)?;
leases.next += 1;
let lease = leases.next;
leases.latest.insert(id, lease);
Ok(PreparedPlayback {
duration_secs: info.duration_secs,
lease,
})
}
/// The player of `lease` is done with call `id`'s mix: removes it,
/// unless a newer lease (another player of the same call) holds it.
pub fn release_playback(&self, id: CallId, lease: u64) {
let mut leases = lock(&self.playback);
if leases.latest.get(&id) == Some(&lease) {
leases.latest.remove(&id);
playback::remove_cached(&self.playback_dir, id);
}
}
/// Removes call `id`'s cached mix whoever holds it: with the call, and
/// once its audio is deleted. The retention job, when it deletes a
/// call's audio, calls this too.
pub fn remove_playback(&self, id: CallId) {
let mut leases = lock(&self.playback);
leases.latest.remove(&id);
playback::remove_cached(&self.playback_dir, id);
}
/// Where the mixes are cached ([`crate::playback`] serves them).
pub fn playback_dir(&self) -> &Path {
&self.playback_dir
}
/// Empties the playback cache (at startup), so mixed customer audio
/// never lingers from an earlier run.
pub fn clear_playback_cache(&self) {
let dir = &self.playback_dir;
match playback::clear_cache(dir) {
Ok(()) => log::info!("cleared the playback cache {}", dir.display()),
Err(e) => log::warn!("could not empty {}: {e}", dir.display()),
}
}
/// Renames a speaker of call `id`; a blank `name` restores the default /// Renames a speaker of call `id`; a blank `name` restores the default
/// label ("Ich", "Sprecher N"). /// label ("Ich", "Sprecher N").
pub fn rename_speaker(&self, id: CallId, speaker_key: &str, name: &str) -> Result<(), String> { pub fn rename_speaker(&self, id: CallId, speaker_key: &str, name: &str) -> Result<(), String> {
@@ -782,6 +876,7 @@ impl AppState {
} }
drop(uploading); drop(uploading);
drop(processing); drop(processing);
self.remove_playback(id);
Ok(self.prompts_waiting()) Ok(self.prompts_waiting())
} }
@@ -960,6 +1055,7 @@ mod tests {
Box::new(MemorySecrets::default()), Box::new(MemorySecrets::default()),
dir.path().join("settings.json"), dir.path().join("settings.json"),
dir.path().join("recordings"), dir.path().join("recordings"),
dir.path().join("playback"),
); );
Fixture { state, dir } Fixture { state, dir }
} }
@@ -1890,4 +1986,156 @@ mod tests {
OutputTarget::Device("id-Lautsprecher".into()) OutputTarget::Device("id-Lautsprecher".into())
); );
} }
/// A finished call whose tracks hold real audio: one second on the mic,
/// half a second on the output.
fn playable_call(f: &Fixture, name: &str) -> CallId {
let (id, mic, out) = finished_call(f, name);
for (path, samples) in [(&mic, 16_000), (&out, 8_000)] {
let mut writer = recorder_core::audio::TrackWriter::create(path).unwrap();
writer.write(&vec![0.1; samples]).unwrap();
writer.finalize().unwrap();
}
id
}
fn playback_file(f: &Fixture, id: CallId) -> PathBuf {
f.dir.path().join("playback").join(format!("{id}.wav"))
}
#[test]
fn a_finished_call_is_mixed_into_the_playback_cache() {
let f = fixture();
let id = playable_call(&f, "a");
assert!(f.state.call_detail(id).unwrap().audio_available);
let prepared = f.state.prepare_playback(id).unwrap();
assert!((prepared.duration_secs - 1.0).abs() < 1e-9);
assert!(playback_file(&f, id).exists());
}
#[test]
fn the_player_holding_the_latest_lease_removes_the_mix() {
let f = fixture();
let id = playable_call(&f, "a");
let first = f.state.prepare_playback(id).unwrap().lease;
// The call was shown again before the first player let go.
let second = f.state.prepare_playback(id).unwrap().lease;
assert_ne!(first, second);
f.state.release_playback(id, first);
assert!(
playback_file(&f, id).exists(),
"the second player still plays"
);
f.state.release_playback(id, second);
assert!(!playback_file(&f, id).exists());
f.state.release_playback(id, second); // already gone: no error
// A lease of one call never removes another call's mix.
let other = playable_call(&f, "b");
let lease = f.state.prepare_playback(other).unwrap().lease;
f.state.release_playback(id, lease);
assert!(playback_file(&f, other).exists());
}
#[test]
fn missing_files_are_no_audio_but_not_deleted_audio() {
let f = fixture();
let (id, mic, out) = finished_call(&f, "a"); // a few junk bytes each
let detail = f.state.call_detail(id).unwrap();
assert!(!detail.audio_available);
assert!(!detail.audio_deleted);
fs::remove_file(mic).unwrap();
fs::remove_file(out).unwrap();
assert_eq!(
f.state.prepare_playback(id),
Err(playback::AUDIO_MISSING.to_string())
);
}
#[test]
fn recording_and_processing_calls_are_not_played() {
let f = fixture();
let dir = f.dir.path();
let recording = f
.state
.store
.create_call(
"Microsoft Teams",
at(10, 0, 0),
&dir.join("r-mic.wav"),
&dir.join("r-out.wav"),
)
.unwrap();
assert_eq!(
f.state.prepare_playback(recording),
Err(playback::RECORDING.to_string())
);
let processing = playable_call(&f, "p");
f.state
.store
.set_status(processing, CallStatus::Processing, None)
.unwrap();
assert_eq!(
f.state.prepare_playback(processing),
Err(playback::PROCESSING.to_string())
);
assert!(!playback_file(&f, processing).exists());
assert_eq!(
f.state.prepare_playback(999),
Err("Gespräch nicht gefunden".to_string())
);
}
#[test]
fn deleted_audio_is_not_played_and_its_mix_is_removed() {
let f = fixture();
let id = playable_call(&f, "a");
f.state.prepare_playback(id).unwrap();
// What the retention sweep does to a transcribed call's audio.
let call = f.state.store.get_call(id).unwrap().unwrap();
fs::remove_file(&call.mic_path).unwrap();
fs::remove_file(&call.out_path).unwrap();
f.state.store.mark_audio_deleted(id).unwrap();
let detail = f.state.call_detail(id).unwrap();
assert!(!detail.audio_available);
assert!(detail.audio_deleted);
assert_eq!(
f.state.prepare_playback(id),
Err(playback::AUDIO_GONE.to_string())
);
assert!(!playback_file(&f, id).exists());
}
#[test]
fn deleting_a_call_removes_its_mix() {
let f = fixture();
let id = playable_call(&f, "a");
let other = playable_call(&f, "b");
f.state.prepare_playback(id).unwrap();
f.state.prepare_playback(other).unwrap();
f.state.discard_call(id).unwrap();
assert!(!playback_file(&f, id).exists());
assert!(playback_file(&f, other).exists());
assert_eq!(
f.state.prepare_playback(id),
Err("Gespräch nicht gefunden".to_string())
);
}
#[test]
fn the_playback_cache_is_emptied_at_startup() {
let f = fixture();
let id = playable_call(&f, "a");
f.state.prepare_playback(id).unwrap();
f.state.clear_playback_cache();
assert!(!f.dir.path().join("playback").exists());
f.state.clear_playback_cache(); // nothing left: no error
}
} }
+1 -1
View File
@@ -1,7 +1,7 @@
{ {
"$schema": "https://schema.tauri.app/config/2", "$schema": "https://schema.tauri.app/config/2",
"productName": "Gesprächsrekorder", "productName": "Gesprächsrekorder",
"version": "0.2.3", "version": "0.3.0",
"identifier": "eu.euvino.callrecorder", "identifier": "eu.euvino.callrecorder",
"build": { "build": {
"frontendDist": "../ui/dist", "frontendDist": "../ui/dist",
+1 -1
View File
@@ -1,7 +1,7 @@
{ {
"name": "ui", "name": "ui",
"private": true, "private": true,
"version": "0.2.3", "version": "0.3.0",
"type": "module", "type": "module",
"scripts": { "scripts": {
"dev": "vite", "dev": "vite",
+20 -2
View File
@@ -28,12 +28,15 @@
aria-current={call.id === selectedId} aria-current={call.id === selectedId}
onclick={() => onselect(call.id)} onclick={() => onselect(call.id)}
> >
{#if call.needs_action}
<span class="dot" title="Offen" aria-label="Offen"></span>
{/if}
<span class="title">{call.title ?? appLine(call)}</span> <span class="title">{call.title ?? appLine(call)}</span>
<span class="meta"> <span class="meta">
<span class="muted"> <span class="muted">
{call.title ? `${appLine(call)} · ` : ''}{formatListTime(call.started_at)} {call.title ? `${appLine(call)} · ` : ''}{formatListTime(call.started_at)}
</span> </span>
<StatusPill status={call.status} interrupted={call.interrupted} /> <StatusPill state={call.list_state} interrupted={call.interrupted} />
</span> </span>
</button> </button>
</li> </li>
@@ -53,11 +56,12 @@
} }
.row { .row {
position: relative;
display: flex; display: flex;
flex-direction: column; flex-direction: column;
gap: 3px; gap: 3px;
width: 100%; width: 100%;
padding: 9px 10px; padding: 9px 10px 9px 18px;
border: none; border: none;
border-radius: 8px; border-radius: 8px;
background: none; background: none;
@@ -67,6 +71,20 @@
cursor: pointer; cursor: pointer;
} }
.dot {
position: absolute;
left: 7px;
top: 50%;
transform: translateY(-50%);
width: 7px;
height: 7px;
border-radius: 50%;
background: var(--primary);
/* A thin ring so the dot stays visible against the selected row's
primary-soft background (and the hover background). */
box-shadow: 0 0 0 2px var(--surface);
}
.row:hover { .row:hover {
background: var(--bg); background: var(--bg);
} }
+248
View File
@@ -0,0 +1,248 @@
<script lang="ts">
import { onDestroy } from 'svelte'
import { errorText, playbackUrl, preparePlayback, releasePlayback, type CallId } from './api'
import { formatOffset } from './format'
let {
callId,
estimate,
ontime,
onplaying,
}: {
callId: CallId
/** The call's length from its times, shown until the mix is ready. */
estimate: number
/** The playback position, once the mix is loaded (also while paused). */
ontime?: (secs: number) => void
onplaying?: (playing: boolean) => void
} = $props()
let audio: HTMLAudioElement
/** Resolves once the mix is loaded; `false` if preparing it failed. */
let loading: Promise<boolean> | null = null
let preparing = $state(false)
let playing = $state(false)
// svelte-ignore state_referenced_locally
let duration = $state(estimate)
let position = $state(0)
/** While the slider is dragged it shows the drag, not the audio. */
let dragging = $state(false)
let error = $state('')
/** The mix held in memory where the webview cannot stream it (Linux). */
let blobUrl: string | null = null
/** This player's hold on the mix on disk (see `releasePlayback`). */
let lease: number | null = null
/** Set once the player is gone: a load still under way stops at the next
* step and keeps nothing (no blob, no mix on disk). */
let destroyed = false
const abort = new AbortController()
const LOAD_FAILED = 'Audio konnte nicht geladen werden.'
/** Lets go of the mix on disk (once). */
function release() {
if (lease === null) return
releasePlayback(callId, lease).catch(() => {})
lease = null
}
/** Mixes the call (first use only) and loads the mix into the player. */
function load(): Promise<boolean> {
loading ??= (async () => {
preparing = true
error = ''
try {
const prepared = await preparePlayback(callId)
lease = prepared.lease
if (destroyed) return false
duration = prepared.duration_secs
const url = playbackUrl(callId)
try {
await loadSource(url)
} catch (err) {
if (destroyed) return false
if (!(err instanceof MediaError) || err.code !== MediaError.MEDIA_ERR_SRC_NOT_SUPPORTED) {
throw err
}
// WebKitGTK (Linux) plays no media from a custom scheme such as
// playback:// (WebView2 gets http://playback.localhost instead),
// but fetches it fine: there the mix is played from memory, and
// the file is not needed any more.
const response = await fetch(url, { signal: abort.signal })
if (!response.ok) throw new Error(LOAD_FAILED)
const blob = await response.blob()
if (destroyed) return false
blobUrl = URL.createObjectURL(blob)
release()
await loadSource(blobUrl)
}
return !destroyed
} catch (err) {
if (destroyed) return false
error = err instanceof MediaError ? LOAD_FAILED : errorText(err)
loading = null // a later click tries again
return false
} finally {
if (destroyed) release()
preparing = false
}
})()
return loading
}
/** Loads `src` into the player; rejects with its `MediaError`. */
function loadSource(src: string): Promise<void> {
const ready = new Promise<void>((resolve, reject) => {
const ok = () => {
audio.removeEventListener('error', fail)
resolve()
}
const fail = () => {
audio.removeEventListener('loadedmetadata', ok)
reject(audio.error)
}
audio.addEventListener('loadedmetadata', ok, { once: true })
audio.addEventListener('error', fail, { once: true })
})
audio.src = src
return ready
}
async function start() {
try {
await audio.play()
} catch (err) {
error = `Wiedergabe nicht möglich: ${errorText(err)}`
}
}
async function toggle() {
if (playing) {
audio.pause()
} else if (await load()) {
await start()
}
}
/** Jumps to `secs` and plays from there (a click on a transcript line). */
export async function playFrom(secs: number) {
if (!(await load())) return
audio.currentTime = Math.min(secs, duration)
position = audio.currentTime
if (audio.paused) await start()
}
async function seekTo(secs: number) {
dragging = false
position = secs
if (!(await load())) return
audio.currentTime = secs
}
function ontimeupdate() {
if (!dragging) position = audio.currentTime
ontime?.(audio.currentTime)
}
function setPlaying(value: boolean) {
playing = value
onplaying?.(value)
}
onDestroy(() => {
destroyed = true
abort.abort()
// Lets go of the file and the memory, so the call can be deleted right
// away and no customer audio stays behind.
audio?.pause()
audio?.removeAttribute('src')
audio?.load()
if (blobUrl) URL.revokeObjectURL(blobUrl)
blobUrl = null
release()
onplaying?.(false)
})
</script>
<div class="player">
<audio
bind:this={audio}
preload="metadata"
{ontimeupdate}
onplay={() => setPlaying(true)}
onpause={() => setPlaying(false)}
onended={() => setPlaying(false)}
></audio>
<button
class="play"
disabled={preparing}
title={playing ? 'Pause' : 'Abspielen'}
aria-label={playing ? 'Pause' : 'Abspielen'}
onclick={toggle}
>
{#if preparing}…{:else if playing}❚❚{:else}▶{/if}
</button>
<input
class="timeline"
type="range"
min="0"
max={duration || 1}
step="0.1"
value={position}
disabled={preparing}
aria-label="Position"
oninput={(e) => {
dragging = true
position = Number(e.currentTarget.value)
}}
onchange={(e) => seekTo(Number(e.currentTarget.value))}
/>
<span class="time">{formatOffset(position)} / {formatOffset(duration)}</span>
{#if preparing}
<span class="muted">Audio wird vorbereitet…</span>
{:else if error}
<span class="error">{error}</span>
{/if}
</div>
<style>
.player {
display: flex;
align-items: center;
flex-wrap: wrap;
gap: 6px 10px;
min-width: 0;
flex: 1;
}
.play {
flex-shrink: 0;
width: 30px;
height: 30px;
border-radius: 50%;
border: none;
background: var(--primary);
color: #fff;
font-size: 11px;
line-height: 1;
cursor: pointer;
}
.play:disabled {
opacity: 0.6;
cursor: default;
}
.timeline {
flex: 1 1 160px;
min-width: 120px;
accent-color: var(--primary);
}
.time {
color: var(--muted);
font-size: 12px;
font-variant-numeric: tabular-nums;
white-space: nowrap;
}
</style>
+11 -5
View File
@@ -1,21 +1,22 @@
<script lang="ts"> <script lang="ts">
import type { CallStatus } from './api' import type { ListState } from './api'
let { status, interrupted = false }: { status: CallStatus; interrupted?: boolean } = $props() let { state, interrupted = false }: { state: ListState; interrupted?: boolean } = $props()
const pills: Record<CallStatus, { text: string; kind: string }> = { const pills: Record<ListState, { text: string; kind: string }> = {
done: { text: 'fertig', kind: 'done' }, done: { text: 'fertig', kind: 'done' },
ready_to_upload: { text: 'bereit zum Hochladen', kind: 'ready' },
processing: { text: 'wird verarbeitet…', kind: 'processing' }, processing: { text: 'wird verarbeitet…', kind: 'processing' },
awaiting_decision: { text: 'nicht transkribiert', kind: 'awaiting' }, awaiting_decision: { text: 'nicht transkribiert', kind: 'awaiting' },
failed: { text: 'fehlgeschlagen', kind: 'failed' }, failed: { text: 'fehlgeschlagen', kind: 'failed' },
recording: { text: 'Aufnahme läuft', kind: 'recording' }, recording: { text: 'Aufnahme läuft', kind: 'recording' },
} }
let pill = $derived(pills[status]) let pill = $derived(pills[state])
</script> </script>
<span class="pill status {pill.kind}"> <span class="pill status {pill.kind}">
{pill.text}{#if interrupted && status === 'awaiting_decision'}, unterbrochen{/if} {pill.text}{#if interrupted && state === 'awaiting_decision'}, unterbrochen{/if}
</span> </span>
<style> <style>
@@ -28,6 +29,11 @@
color: var(--ok); color: var(--ok);
} }
.ready {
background: var(--primary-soft);
color: var(--primary);
}
.processing { .processing {
background: #fff4d6; background: #fff4d6;
color: #8a6100; color: #8a6100;
+101 -5
View File
@@ -8,6 +8,9 @@
onrename, onrename,
onmerge, onmerge,
onunmerge, onunmerge,
activeIndex = null,
follow = false,
onseek,
}: { }: {
/** The transcript with merges applied: merged speakers no longer appear. */ /** The transcript with merges applied: merged speakers no longer appear. */
segments: SegmentView[] segments: SegmentView[]
@@ -18,8 +21,45 @@
onmerge: (fromKey: string, intoKey: string) => Promise<void> onmerge: (fromKey: string, intoKey: string) => Promise<void>
/** Undoes the merge of `fromKey`. */ /** Undoes the merge of `fromKey`. */
onunmerge: (fromKey: string) => Promise<void> onunmerge: (fromKey: string) => Promise<void>
/** The line being heard; it is highlighted. */
activeIndex?: number | null
/** Scrolls the line being heard into view when it leaves the view. */
follow?: boolean
/** Plays from `secs`, a line's start (only while the audio is there). */
onseek?: (secs: number) => void
} = $props() } = $props()
let lineElements: HTMLElement[] = $state([])
/** A click on a line's text plays from it, unless text was selected. */
function lineClick(start: number) {
if (window.getSelection()?.toString()) return
onseek?.(start)
}
/** The nearest ancestor that scrolls vertically. */
function scrollParent(node: HTMLElement): HTMLElement | null {
for (let el = node.parentElement; el; el = el.parentElement) {
if (/(auto|scroll)/.test(getComputedStyle(el).overflowY)) return el
}
return null
}
// Following the playback scrolls only once the line has left the view
// (also when it hides under the sticky player), and then centres it.
$effect(() => {
if (!follow || activeIndex === null) return
const line = lineElements[activeIndex]
const parent = line && scrollParent(line)
if (!line || !parent) return
const view = parent.getBoundingClientRect()
const box = line.getBoundingClientRect()
const covered = parseFloat(getComputedStyle(line).scrollMarginTop) || 0
if (box.top < view.top + covered || box.bottom > view.bottom) {
line.scrollIntoView({ block: 'center' })
}
})
// "Ich" is always the primary blue; remote speakers cycle through the rest. // "Ich" is always the primary blue; remote speakers cycle through the rest.
const ME_COLOR = '#3b5bdb' const ME_COLOR = '#3b5bdb'
const REMOTE_COLORS = ['#2b8a3e', '#c2255c', '#e8590c', '#7048e8', '#0c8599', '#5c940d'] const REMOTE_COLORS = ['#2b8a3e', '#c2255c', '#e8590c', '#7048e8', '#0c8599', '#5c940d']
@@ -186,8 +226,27 @@
<div class="lines"> <div class="lines">
{#each segments as segment, i (i)} {#each segments as segment, i (i)}
<div class="line"> <!-- The time is the keyboard-accessible way to play a line. -->
<span class="time">{formatOffset(segment.start)}</span> <!-- svelte-ignore a11y_click_events_have_key_events, a11y_no_static_element_interactions -->
<div
class="line"
class:active={i === activeIndex}
class:seekable={onseek !== undefined}
bind:this={lineElements[i]}
onclick={() => lineClick(segment.start)}
>
{#if onseek}
<button
class="time"
title="Ab hier abspielen"
onclick={(e) => {
e.stopPropagation()
onseek(segment.start)
}}>{formatOffset(segment.start)}</button
>
{:else}
<span class="time">{formatOffset(segment.start)}</span>
{/if}
<span class="speaker" style:color={speakerColor(segment.speaker_key)}>{segment.label}</span> <span class="speaker" style:color={speakerColor(segment.speaker_key)}>{segment.label}</span>
<span class="text">{segment.text}</span> <span class="text">{segment.text}</span>
</div> </div>
@@ -324,12 +383,33 @@
.lines { .lines {
display: grid; display: grid;
grid-template-columns: auto auto 1fr; grid-template-columns: auto auto 1fr;
gap: 8px 12px; column-gap: 12px;
margin-top: 14px; margin: 10px -8px 0;
} }
/* One row of the transcript grid that can be highlighted as a whole. */
.line { .line {
display: contents; display: grid;
grid-column: 1 / -1;
grid-template-columns: subgrid;
padding: 4px 8px;
border-radius: 6px;
/* Room for the sticky player when the line is scrolled into view. */
scroll-margin-top: 64px;
}
.line.seekable {
cursor: pointer;
}
.line.seekable:hover {
background: var(--bg);
}
.line.active,
.line.active:hover {
background: var(--primary-soft);
box-shadow: inset 3px 0 0 var(--primary);
} }
.time { .time {
@@ -339,6 +419,22 @@
padding-top: 1px; padding-top: 1px;
} }
button.time {
align-self: start;
border: none;
background: none;
padding: 1px 0 0;
font-family: inherit;
line-height: inherit;
text-align: left;
cursor: pointer;
}
button.time:hover {
color: var(--primary);
text-decoration: underline;
}
.speaker { .speaker {
font-weight: 600; font-weight: 600;
max-width: 160px; max-width: 160px;
+41 -1
View File
@@ -1,6 +1,6 @@
// Typed wrappers around the Tauri commands and events of the app shell. // Typed wrappers around the Tauri commands and events of the app shell.
import { invoke } from '@tauri-apps/api/core' import { convertFileSrc, invoke } from '@tauri-apps/api/core'
import { listen, type UnlistenFn } from '@tauri-apps/api/event' import { listen, type UnlistenFn } from '@tauri-apps/api/event'
export type CallId = number export type CallId = number
@@ -11,6 +11,8 @@ export interface Settings {
output_device: string | null output_device: string | null
language: string language: string
deepscript_model: string deepscript_model: string
/** Custom words/names submitted with every transcription. */
vocabulary: string[]
retention_days: number retention_days: number
autostart: boolean autostart: boolean
start_after_secs: number start_after_secs: number
@@ -79,6 +81,18 @@ export interface PendingPrompt extends CallBrief {
export type CallStatus = 'recording' | 'awaiting_decision' | 'processing' | 'done' | 'failed' export type CallStatus = 'recording' | 'awaiting_decision' | 'processing' | 'done' | 'failed'
/** What the status pill shows and whether the row needs the user's
* attention. Mirrors `CallStatus`, except `done` splits into `done`
* (uploaded to this build's backend — "fertig") and `ready_to_upload`
* (not uploaded here yet — "bereit zum Hochladen"). */
export type ListState =
| 'recording'
| 'awaiting_decision'
| 'processing'
| 'failed'
| 'done'
| 'ready_to_upload'
/** A row of the main window's call list. Times are RFC 3339. */ /** A row of the main window's call list. Times are RFC 3339. */
export interface CallListItem { export interface CallListItem {
id: CallId id: CallId
@@ -87,6 +101,10 @@ export interface CallListItem {
/** 0 while recording. */ /** 0 while recording. */
duration_secs: number duration_secs: number
status: CallStatus status: CallStatus
list_state: ListState
/** Whether this row needs the user to act on it (the dot in the list,
* counted in the sidebar header's "N offen"). */
needs_action: boolean
interrupted: boolean interrupted: boolean
/** The name the user gave the call, if any. */ /** The name the user gave the call, if any. */
title: string | null title: string | null
@@ -122,6 +140,18 @@ export interface CallDetail {
merges: SpeakerMerge[] merges: SpeakerMerge[]
/** The transcript is being uploaded right now. */ /** The transcript is being uploaded right now. */
uploading: boolean uploading: boolean
/** The call's audio is still on this PC and can be played. */
audio_available: boolean
/** Retention deleted the call's audio (not just: the files are missing). */
audio_deleted: boolean
}
/** A call's two tracks mixed into one file, ready to play from
* `playbackUrl`. */
export interface PreparedPlayback {
duration_secs: number
/** Hand back with `releasePlayback` once the player is done. */
lease: number
} }
/** A newer version the release feed offers. */ /** A newer version the release feed offers. */
@@ -170,6 +200,16 @@ export const getCallBrief = (id: CallId) => invoke<CallBrief>('get_call_brief',
export const transcribeCall = (id: CallId) => invoke<void>('transcribe_call', { id }) export const transcribeCall = (id: CallId) => invoke<void>('transcribe_call', { id })
export const retryCall = (id: CallId) => invoke<void>('retry_call', { id }) export const retryCall = (id: CallId) => invoke<void>('retry_call', { id })
export const discardCall = (id: CallId) => invoke<void>('discard_call', { id }) export const discardCall = (id: CallId) => invoke<void>('discard_call', { id })
/** Mixes the call's tracks (or reuses the cached mix); refused while the
* call is recorded or processed and once its audio is gone. */
export const preparePlayback = (id: CallId) =>
invoke<PreparedPlayback>('prepare_playback', { id })
/** The player is done with the mix: it is removed from disk. */
export const releasePlayback = (id: CallId, lease: number) =>
invoke<void>('release_playback', { id, lease })
/** Where the main window plays a prepared mix from (the app's `playback`
* scheme; other windows are refused). */
export const playbackUrl = (id: CallId) => convertFileSrc(String(id), 'playback')
export const listCalls = () => invoke<CallListItem[]>('list_calls') export const listCalls = () => invoke<CallListItem[]>('list_calls')
export const getCall = (id: CallId) => invoke<CallDetail>('get_call', { id }) export const getCall = (id: CallId) => invoke<CallDetail>('get_call', { id })
/** An empty name restores the default label. */ /** An empty name restores the default label. */
+21
View File
@@ -0,0 +1,21 @@
// Couples playback to the transcript: which line is being heard.
/** The part of a transcript line the lookup needs. */
export interface Timed {
start: number
end: number
}
/** Index of the line heard at `secs`: the one whose `[start, end)` holds
* it — of overlapping lines (both sides talking at once) the one that
* started last. `null` before the first line, in a pause between lines and
* after the last one. */
export function segmentAt(segments: readonly Timed[], secs: number): number | null {
let found: number | null = null
segments.forEach((segment, i) => {
if (segment.start <= secs && secs < segment.end) {
if (found === null || segment.start >= segments[found].start) found = i
}
})
return found
}
+167 -8
View File
@@ -5,6 +5,7 @@
errorText, errorText,
getCall, getCall,
getRecordingState, getRecordingState,
getSettings,
listCalls, listCalls,
mergeSpeakers, mergeSpeakers,
onBackendLoginError, onBackendLoginError,
@@ -27,6 +28,8 @@
} from '../lib/api' } from '../lib/api'
import CallList from '../lib/CallList.svelte' import CallList from '../lib/CallList.svelte'
import { formatDateTime, formatDetailTime, formatMinutes } from '../lib/format' import { formatDateTime, formatDetailTime, formatMinutes } from '../lib/format'
import Player from '../lib/Player.svelte'
import { segmentAt } from '../lib/playback'
import StatusPill from '../lib/StatusPill.svelte' import StatusPill from '../lib/StatusPill.svelte'
import TranscriptView from '../lib/TranscriptView.svelte' import TranscriptView from '../lib/TranscriptView.svelte'
import UpdateBanner from '../lib/UpdateBanner.svelte' import UpdateBanner from '../lib/UpdateBanner.svelte'
@@ -56,6 +59,16 @@
let uploading = $state<CallId[]>([]) let uploading = $state<CallId[]>([])
let uploadErrors = $state<Record<CallId, string>>({}) let uploadErrors = $state<Record<CallId, string>>({})
// Playback of the shown call (the player itself lives in `Player`).
let player = $state<ReturnType<typeof Player>>()
/** The playback position once the mix is loaded, else `null`. */
let playerTime = $state<number | null>(null)
let playing = $state(false)
/** Whether the transcript scrolls along; scrolling by hand ends it. */
let follow = $state(true)
/** For "… werden N Tage nach der Transkription gelöscht". */
let retentionDays = $state<number | null>(null)
let editingTitle = $state(false) let editingTitle = $state(false)
let titleDraft = $state('') let titleDraft = $state('')
let savingTitle = $state(false) let savingTitle = $state(false)
@@ -103,9 +116,16 @@
} }
} }
function resetPlayback() {
playerTime = null
playing = false
follow = true
}
function select(id: CallId) { function select(id: CallId) {
if (id === selectedId) return if (id === selectedId) return
selectedId = id selectedId = id
resetPlayback()
detail = null detail = null
detailError = '' detailError = ''
actionError = '' actionError = ''
@@ -118,6 +138,7 @@
function clearSelection() { function clearSelection() {
selectedId = null selectedId = null
resetPlayback()
detail = null detail = null
detailError = '' detailError = ''
actionError = '' actionError = ''
@@ -145,6 +166,12 @@
}), }),
] ]
refreshList() refreshList()
// Read on every visit: the settings page is a route of this window, so
// a changed retention period is shown on the way back. Without it the
// "no audio" line just leaves the period out.
getSettings()
.then((settings) => (retentionDays = settings.retention_days))
.catch((err) => console.warn('settings not read:', errorText(err)))
getRecordingState() getRecordingState()
.then((state) => (recordingState = state)) .then((state) => (recordingState = state))
.catch((err) => (recordError = errorText(err))) .catch((err) => (recordError = errorText(err)))
@@ -310,6 +337,28 @@
node.select() node.select()
} }
/** A click on a transcript line: plays from there and follows again. */
function playFrom(secs: number) {
follow = true
player?.playFrom(secs)
}
const SCROLL_KEYS = ['ArrowUp', 'ArrowDown', 'PageUp', 'PageDown', 'Home', 'End', ' ']
/** Scrolling the detail by hand while playing stops following the
* playback (until "folgen" or a click on a line). Only user input counts:
* the transcript's own scrolling raises none of these events. */
function manualScroll(event: Event) {
if (!playing) return
if (event instanceof KeyboardEvent) {
const target = event.target as HTMLElement
if (!SCROLL_KEYS.includes(event.key) || target.closest('input, textarea, button')) return
}
// A press on the scroll bar (not on the content).
if (event instanceof PointerEvent && event.target !== event.currentTarget) return
follow = false
}
/** "Microsoft Teams · heute 10:14 · 32 min" (no duration while recording). */ /** "Microsoft Teams · heute 10:14 · 32 min" (no duration while recording). */
function defaultTitle(call: CallListItem): string { function defaultTitle(call: CallListItem): string {
const parts = [call.app, formatDetailTime(call.started_at)] const parts = [call.app, formatDetailTime(call.started_at)]
@@ -326,13 +375,22 @@
// A failed start (e.g. missing key) also marks the call failed; its // A failed start (e.g. missing key) also marks the call failed; its
// error is then shown once, in the failure box. // error is then shown once, in the failure box.
let shownActionError = $derived(actionError !== detail?.call.error ? actionError : '') let shownActionError = $derived(actionError !== detail?.call.error ? actionError : '')
// Calls that still need the user's attention (not transcribed, or
// transcribed but not uploaded here) — shown as "Gespräche · N offen".
let openCount = $derived(calls.filter((c) => c.needs_action).length)
/** The transcript line being heard, highlighted while the mix is loaded. */
let activeIndex = $derived(
detail && playerTime !== null ? segmentAt(detail.segments, playerTime) : null,
)
</script> </script>
<main class="main"> <main class="main">
<UpdateBanner /> <UpdateBanner />
<aside class="sidebar"> <aside class="sidebar">
<header class="sidebar-header"> <header class="sidebar-header">
<h1>Gespräche</h1> <h1>Gespräche{#if openCount > 0}<span class="open-count" title="{openCount} offen" aria-label="{openCount} offen">{openCount}</span>{/if}</h1>
<div class="header-actions"> <div class="header-actions">
<button <button
class="btn small record-btn" class="btn small record-btn"
@@ -360,7 +418,15 @@
</div> </div>
</aside> </aside>
<section class="detail"> <!-- The handlers only watch for scrolling by hand (see manualScroll). -->
<!-- svelte-ignore a11y_no_static_element_interactions -->
<section
class="detail"
onwheel={manualScroll}
ontouchmove={manualScroll}
onkeydown={manualScroll}
onpointerdown={manualScroll}
>
{#if detail} {#if detail}
{@const call = detail.call} {@const call = detail.call}
<header class="detail-header"> <header class="detail-header">
@@ -381,7 +447,7 @@
<button class="edit-title" title="Titel ändern" onclick={startTitleEdit}>✎</button> <button class="edit-title" title="Titel ändern" onclick={startTitleEdit}>✎</button>
</h1> </h1>
{/if} {/if}
<StatusPill status={call.status} interrupted={call.interrupted} /> <StatusPill state={call.list_state} interrupted={call.interrupted} />
</div> </div>
{#if editingTitle} {#if editingTitle}
<p class="muted subline">Enter speichert, Esc bricht ab. Leer = Standardtitel.</p> <p class="muted subline">Enter speichert, Esc bricht ab. Leer = Standardtitel.</p>
@@ -429,6 +495,40 @@
{/if} {/if}
</header> </header>
{#if call.status !== 'recording' && call.status !== 'processing'}
{#if detail.audio_available}
<div class="playback-bar">
{#key call.id}
<Player
bind:this={player}
callId={call.id}
estimate={call.duration_secs}
ontime={(secs) => (playerTime = secs)}
onplaying={(value) => (playing = value)}
/>
{/key}
{#if call.status === 'done' && detail.segments.length > 0}
<button
class="btn small follow"
class:on={follow}
aria-pressed={follow}
title="Das Transkript scrollt mit der Wiedergabe mit"
onclick={() => (follow = !follow)}>folgen</button
>
{/if}
</div>
{:else if detail.audio_deleted && retentionDays !== null}
<p class="muted no-audio">
Audio nicht mehr vorhanden – Aufnahmen werden {retentionDays} Tage nach der
Transkription gelöscht (<a href="#/settings">Einstellungen</a>).
</p>
{:else if detail.audio_deleted}
<p class="muted no-audio">Audio nicht mehr vorhanden.</p>
{:else}
<p class="muted no-audio">Audio nicht vorhanden.</p>
{/if}
{/if}
<div class="body"> <div class="body">
{#if call.status === 'recording'} {#if call.status === 'recording'}
<p class="state rec">● Aufnahme läuft</p> <p class="state rec">● Aufnahme läuft</p>
@@ -452,6 +552,9 @@
onrename={rename} onrename={rename}
onmerge={merge} onmerge={merge}
onunmerge={unmerge} onunmerge={unmerge}
{activeIndex}
follow={follow && playing}
onseek={detail.audio_available ? playFrom : undefined}
/> />
{/if} {/if}
</div> </div>
@@ -527,21 +630,47 @@
display: flex; display: flex;
align-items: center; align-items: center;
justify-content: space-between; justify-content: space-between;
padding: 14px 12px 10px 16px; gap: 4px;
padding: 12px 6px 8px 10px;
border-bottom: 1px solid var(--border); border-bottom: 1px solid var(--border);
} }
.sidebar-header h1 { .sidebar-header h1 {
font-size: 16px; flex: 0 1 auto;
min-width: 0;
font-size: 15px;
white-space: nowrap;
overflow: hidden;
text-overflow: ellipsis;
}
.open-count {
display: inline-flex;
align-items: center;
justify-content: center;
margin-left: 4px;
min-width: 14px;
height: 14px;
padding: 0 3px;
border-radius: 999px;
background: var(--primary-soft);
color: var(--primary);
font-size: 10px;
font-weight: 700;
line-height: 1;
vertical-align: middle;
} }
.header-actions { .header-actions {
display: flex; display: flex;
flex-shrink: 0;
align-items: center; align-items: center;
gap: 6px; gap: 3px;
} }
.record-btn { .record-btn {
padding: 2px 6px;
font-size: 11px;
white-space: nowrap; white-space: nowrap;
} }
@@ -558,9 +687,9 @@
.gear { .gear {
color: var(--muted); color: var(--muted);
font-size: 18px; font-size: 15px;
line-height: 1; line-height: 1;
padding: 4px 6px; padding: 3px 4px;
border-radius: 6px; border-radius: 6px;
text-decoration: none; text-decoration: none;
} }
@@ -651,6 +780,36 @@
margin: 10px 0 0; margin: 10px 0 0;
} }
/* Stays at the top while the transcript scrolls under it. */
.playback-bar {
position: sticky;
top: -18px; /* the detail's top padding: flush with its edge */
z-index: 2;
display: flex;
align-items: center;
gap: 10px;
margin: 0 -24px 14px;
padding: 8px 24px;
background: var(--bg);
border-bottom: 1px solid var(--border);
}
.follow {
flex-shrink: 0;
color: var(--muted);
font-weight: 600;
}
.follow.on {
border-color: var(--primary);
background: var(--primary-soft);
color: var(--primary);
}
.no-audio {
margin: 0 0 14px;
}
.state { .state {
color: var(--muted); color: var(--muted);
} }
+43
View File
@@ -43,6 +43,10 @@
] ]
let settings = $state<Settings | null>(null) let settings = $state<Settings | null>(null)
/** The vocabulary textarea's raw text, one term per line; converted
* to/from `settings.vocabulary` on load/save (the backend trims, drops
* blanks and deduplicates — see `Settings::edited`). */
let vocabularyText = $state('')
let devices = $state<Devices>({ inputs: [], outputs: [] }) let devices = $state<Devices>({ inputs: [], outputs: [] })
let keySaved = $state<Record<Service, boolean>>({ deepscript: false }) let keySaved = $state<Record<Service, boolean>>({ deepscript: false })
let keyInput = $state<Record<Service, string>>({ deepscript: '' }) let keyInput = $state<Record<Service, string>>({ deepscript: '' })
@@ -207,6 +211,7 @@
async function load() { async function load() {
try { try {
settings = await getSettings() settings = await getSettings()
vocabularyText = settings.vocabulary.join('\n')
for (const { id } of services) keySaved[id] = await hasApiKey(id) for (const { id } of services) keySaved[id] = await hasApiKey(id)
devices = await listDevices() devices = await listDevices()
} catch (err) { } catch (err) {
@@ -268,7 +273,12 @@
if (!Number.isInteger(settings.retention_days) || settings.retention_days < 1) { if (!Number.isInteger(settings.retention_days) || settings.retention_days < 1) {
throw 'Aufbewahrung: bitte eine ganze Zahl ab 1 eingeben' throw 'Aufbewahrung: bitte eine ganze Zahl ab 1 eingeben'
} }
settings.vocabulary = vocabularyText.split('\n')
await saveSettings($state.snapshot(settings)) await saveSettings($state.snapshot(settings))
// Re-read: the backend trims/dedupes the vocabulary, so the textarea
// should show the cleaned-up list, not what was just typed.
settings = await getSettings()
vocabularyText = settings.vocabulary.join('\n')
} }
async function runTest() { async function runTest() {
@@ -474,6 +484,24 @@
</div> </div>
</section> </section>
<section class="card">
<h2>Transkription</h2>
<div class="grid">
<label for="deepscript-model">Modell</label>
<select id="deepscript-model" bind:value={settings.deepscript_model}>
<option value="premium">Premium</option>
<option value="premium_jade">Premium Jade</option>
</select>
<span></span>
<span class="muted">Gilt für neue Transkriptionen.</span>
</div>
<label for="vocabulary" class="vocabulary-label">Vokabular (ein Begriff pro Zeile)</label>
<textarea id="vocabulary" rows="6" bind:value={vocabularyText}></textarea>
<p class="muted">
Namen, Firmen- und Produktbegriffe, die oft falsch erkannt werden.
</p>
</section>
<section class="card"> <section class="card">
<h2>Updates</h2> <h2>Updates</h2>
<div class="grid"> <div class="grid">
@@ -575,6 +603,21 @@
justify-self: start; justify-self: start;
} }
.vocabulary-label {
display: block;
margin-top: 12px;
font-weight: 600;
}
textarea#vocabulary {
width: 100%;
max-width: 420px;
margin-top: 6px;
font-family: inherit;
font-size: 13px;
resize: vertical;
}
.hint { .hint {
margin: 12px 0; margin: 12px 0;
padding: 8px 10px; padding: 8px 10px;