feat: OpenWhispr-inspired transcription polish pass
Major quality pass on top of Phase 2. Five substantive changes plus
cross-cutting touches across audio, hotkey, transcription, and Tauri
command layers.
Transcription quality
- Long-audio chunking in commands/transcription.rs: Parakeet and large
file transcription now chunk-and-recompose with overlap trimming, so
the live-path chunking advantage extends to file-based workflows.
- Stateful live speech gate in commands/live.rs on top of the earlier
duplicate-boundary filtering — distinguishes start-of-speech from
mid-speech and holds state across chunks.
Auto-learning corrections
- New crates/ai-formatting/src/correction_learning.rs: extracts user
text corrections from viewer edits and proposes additions to the
active profile's vocabulary.
- src-tauri/src/commands/profiles.rs bridge for frontend-driven
confirmation of learned terms.
- src/routes/viewer/+page.svelte hooks the learning path into the
segment-edit flow so corrections feed profile_terms without a
separate 'train this profile' UX.
Transcript profile provenance
- Migration v8 (crates/storage/src/migrations.rs) adds profile_id to
transcripts, defaulting to DEFAULT_PROFILE_ID so existing rows stay
valid.
- crates/storage/src/database.rs: TranscriptRow + CRUD carry profile_id.
- src-tauri/src/commands/transcripts.rs: add_transcript accepts and
persists profile_id.
- DictationPage.svelte + FilesPage.svelte send activeProfileId on
capture so learned corrections are attributed to the right profile.
Cleanup prompt contract
- crates/ai-formatting/src/llm_client.rs hardened: the CLEANUP_PROMPT
now specifies concrete do/do-not rules, ready for a real model-backed
cleanup pass. The llm_client is still a stub — kon-llm remains unwired
— but the prompt shape is final.
Cross-cutting polish
- Minor touches in audio (capture/decode/resample), hotkey (lib/linux/stub),
core, transcription (concurrency/model_manager/local_engine/whisper_rs),
and the rest of src-tauri/src/commands/*: error-path tightening, log
clarity, TS-migration follow-ups (@ts-nocheck additions for incremental
typing).
Verified locally: npm run check, cargo test -p kon-ai-formatting,
cargo test -p kon-storage, cargo test -p kon --lib commands::live::tests,
cargo check — all green.
Scope boundary: kon-llm crate is still a stub; task extraction remains
rule-based. Bundled local-LLM runtime is the next clean step and is not
in this commit.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -100,7 +100,9 @@ fn ensure_x11_on_wayland() {
|
||||
// SAFETY: setting env vars before any threads spawn (we are
|
||||
// pre-Tauri-Builder here). This block is the only place these
|
||||
// are written.
|
||||
unsafe { std::env::set_var(key, value); }
|
||||
unsafe {
|
||||
std::env::set_var(key, value);
|
||||
}
|
||||
eprintln!("[startup] Wayland workaround: {key}={value}");
|
||||
}
|
||||
};
|
||||
@@ -130,10 +132,8 @@ pub fn run() {
|
||||
// Initialise database (blocking in setup — runs once at startup)
|
||||
let db_path = database_path();
|
||||
let t0 = Instant::now();
|
||||
let db = tauri::async_runtime::block_on(async {
|
||||
init_db(&db_path).await
|
||||
})
|
||||
.map_err(|e| Box::new(e) as Box<dyn std::error::Error>)?;
|
||||
let db = tauri::async_runtime::block_on(async { init_db(&db_path).await })
|
||||
.map_err(|e| Box::new(e) as Box<dyn std::error::Error>)?;
|
||||
eprintln!("[startup] DB init: {:?}", t0.elapsed());
|
||||
|
||||
// Load saved preferences for webview injection
|
||||
@@ -158,37 +158,40 @@ pub fn run() {
|
||||
// signal and grant audio capture requests automatically.
|
||||
#[cfg(target_os = "linux")]
|
||||
{
|
||||
main_window.with_webview(|webview| {
|
||||
use webkit2gtk::{
|
||||
PermissionRequest, PermissionRequestExt,
|
||||
SettingsExt, WebViewExt,
|
||||
};
|
||||
main_window
|
||||
.with_webview(|webview| {
|
||||
use webkit2gtk::{
|
||||
PermissionRequest, PermissionRequestExt, SettingsExt, WebViewExt,
|
||||
};
|
||||
|
||||
let wv: webkit2gtk::WebView = webview.inner().clone();
|
||||
let wv: webkit2gtk::WebView = webview.inner().clone();
|
||||
|
||||
// Enable media stream in WebKit settings
|
||||
if let Some(settings) = WebViewExt::settings(&wv) {
|
||||
settings.set_enable_media_stream(true);
|
||||
settings.set_enable_media_capabilities(true);
|
||||
}
|
||||
// Enable media stream in WebKit settings
|
||||
if let Some(settings) = WebViewExt::settings(&wv) {
|
||||
settings.set_enable_media_stream(true);
|
||||
settings.set_enable_media_capabilities(true);
|
||||
}
|
||||
|
||||
// Auto-grant all permission requests (audio/video capture)
|
||||
WebViewExt::connect_permission_request(&wv, |_wv, request: &PermissionRequest| {
|
||||
request.allow();
|
||||
true
|
||||
// Auto-grant all permission requests (audio/video capture)
|
||||
WebViewExt::connect_permission_request(
|
||||
&wv,
|
||||
|_wv, request: &PermissionRequest| {
|
||||
request.allow();
|
||||
true
|
||||
},
|
||||
);
|
||||
})
|
||||
.unwrap_or_else(|e| {
|
||||
// Non-fatal: WebKitGTK may already have media
|
||||
// capture wired by some compositors, or the
|
||||
// signal binding may fail on unusual builds.
|
||||
// Falling back means getUserMedia() prompts (or
|
||||
// silently denies) instead of auto-granting,
|
||||
// which is degraded but recoverable.
|
||||
eprintln!(
|
||||
"[startup] failed to configure webview media permissions: {e}",
|
||||
);
|
||||
});
|
||||
})
|
||||
.unwrap_or_else(|e| {
|
||||
// Non-fatal: WebKitGTK may already have media
|
||||
// capture wired by some compositors, or the
|
||||
// signal binding may fail on unusual builds.
|
||||
// Falling back means getUserMedia() prompts (or
|
||||
// silently denies) instead of auto-granting,
|
||||
// which is degraded but recoverable.
|
||||
eprintln!(
|
||||
"[startup] failed to configure webview media permissions: {e}",
|
||||
);
|
||||
});
|
||||
}
|
||||
|
||||
// Close-to-tray: hide window instead of exiting
|
||||
@@ -209,12 +212,8 @@ pub fn run() {
|
||||
app.manage(commands::live::LiveTranscriptionState::default());
|
||||
|
||||
app.manage(AppState {
|
||||
whisper_engine: Arc::new(LocalEngine::new(
|
||||
EngineName::new("whisper"),
|
||||
)),
|
||||
parakeet_engine: Arc::new(LocalEngine::new(
|
||||
EngineName::new("parakeet"),
|
||||
)),
|
||||
whisper_engine: Arc::new(LocalEngine::new(EngineName::new("whisper"))),
|
||||
parakeet_engine: Arc::new(LocalEngine::new(EngineName::new("parakeet"))),
|
||||
db,
|
||||
llm_engine: Arc::new(LlmEngine::new()),
|
||||
});
|
||||
@@ -273,6 +272,7 @@ pub fn run() {
|
||||
commands::profiles::delete_profile_cmd,
|
||||
commands::profiles::list_profile_terms_cmd,
|
||||
commands::profiles::add_profile_term_cmd,
|
||||
commands::profiles::learn_profile_terms_from_edit_cmd,
|
||||
commands::profiles::delete_profile_term_cmd,
|
||||
// Transcripts (canonical SQLite-backed history) — Day 4
|
||||
commands::transcripts::add_transcript,
|
||||
|
||||
Reference in New Issue
Block a user