mirror of
https://github.com/R0m1k3/EveFlow.git
synced 2026-10-11 17:29:03 +02:00
Electron main - utility-process channel: sherpa output copied into V8 buffers (Electron rejects external buffers), audio exchanged as base64; worker restart on timeout, identity-safe exit handling, deterministic native unload by restart - webhook: loopback by default without secret, UTF-8-safe body assembly, clean restart, port validation - files IPC: realpath-based root check, openPath allow-list (reveal-only outside document folders), Windows reserved names; store: debounced async atomic writes with backup of corrupt files; logger: streaming writes with rotation; log message size cap - HTTP stream proxy: socket released on idle timeout / renderer destroyed, id validation - model manager: inactivity timeout, retrying rm/rename (Windows locks), engine stopped before replacing a model; WAV decoder handles float/24-bit; IPC payload validation - window: opaque rounded window on Windows, navigation lock-down, visibility events; Ctrl+Alt+Escape instead of the Task Manager shortcut; single-instance guard; EVEFLOW_USER_DATA Voice pipeline - abort semantics (SendHandle.aborted), abort before the stream opens, session id prefixes per transport - hands-free re-arm after replies without speech, start/stop race, no chime on auto re-arm, no silence shipped to STT (400 ms pre-roll), no transcription of empty manual stops - TTS: bounded prefetch, cancellable segments, non-interrupting notices, volume applied at play time - SSE CRLF split, usage in chat completions, finish_reason length, phonetic regex hoisted HUD - core renderer: no canvas shadows, cached colours, reusable spectrum buffer, theme read on change, 30 fps idle, stops when the window is hidden; ping flashes on send / tool / speech - deltas coalesced per animation frame; stable auto-scroll; narrow selectors everywhere - bundled fonts (offline), reduce-motion fix, error toasts, ops drawer below 1180 px, interim transcript and first-token latency in the core caption, Ctrl+K, dialog semantics, switch/aria roles, compact widget cleanup, Whisper small recommended for French - docs/ROADMAP.md: audit results, e2e results and the plan towards a real JARVIS Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017Wn5VX9HNbJ7N54hR24u9Y
67 lines
1.9 KiB
TypeScript
67 lines
1.9 KiB
TypeScript
/**
|
|
* Singleton facade over the TTS engine bound to the settings store, exposing speaking state
|
|
* to the voice and chat stores.
|
|
*/
|
|
import { useChat } from '../../state/chat';
|
|
import { useSettings } from '../../state/settings';
|
|
import { useVoice } from '../../state/voice';
|
|
import { TtsEngine } from './tts';
|
|
|
|
class SpeechFacade {
|
|
private engine: TtsEngine | null = null;
|
|
private streaming = false;
|
|
private streamEnabled = true;
|
|
|
|
private get tts(): TtsEngine {
|
|
if (!this.engine) {
|
|
const settings = useSettings.getState().settings;
|
|
this.engine = new TtsEngine(settings.speech);
|
|
this.engine.onState((state) => {
|
|
useVoice.getState().setTts(state);
|
|
const chat = useChat.getState();
|
|
if (state === 'speaking') chat.setHud('speaking');
|
|
else if (state === 'idle' && chat.hud === 'speaking') chat.setHud(chat.isSending ? 'thinking' : 'idle');
|
|
});
|
|
useSettings.subscribe((s) => this.engine?.updateConfig(s.settings.speech));
|
|
}
|
|
return this.engine;
|
|
}
|
|
|
|
init(): void {
|
|
this.tts;
|
|
}
|
|
|
|
isSpeaking(): boolean {
|
|
return this.engine?.isActive ?? false;
|
|
}
|
|
|
|
say(text: string, options: { interrupt?: boolean } = {}): void {
|
|
if (useSettings.getState().settings.speech.provider === 'off') return;
|
|
// While an answer streams, spoken notices are inserted without discarding the rest.
|
|
this.tts.speak(text, { interrupt: options.interrupt ?? !this.streaming });
|
|
}
|
|
|
|
pushStream(delta: string): void {
|
|
if (!useSettings.getState().settings.speech.autoSpeak) return;
|
|
this.streaming = true;
|
|
if (this.streamEnabled) this.tts.pushStream(delta);
|
|
}
|
|
|
|
endStream(): void {
|
|
if (this.streaming) this.tts.endStream();
|
|
this.streaming = false;
|
|
}
|
|
|
|
discardStream(): void {
|
|
this.streaming = false;
|
|
this.tts.stop();
|
|
}
|
|
|
|
stop(): void {
|
|
this.streaming = false;
|
|
this.engine?.stop();
|
|
}
|
|
}
|
|
|
|
export const speech = new SpeechFacade();
|