13 Commits
Author SHA1 Message Date
LogiFlowandClaude 6fc38d335b feat: serveur MCP, heures calmes, mode mission, widget glanceable, barge-in (v2.4.0) (#14)
Serveur MCP local
- Endpoint /mcp (JSON-RPC 2.0, Streamable HTTP, réponses JSON) sur le serveur
  webhook : initialize, tools/list, tools/call, ping. Même secret que le
  webhook. 14 outils : capture_screen (image MCP), lock_session, open_app,
  open_url, media_key, clipboard_get/set, find_files, speak_text,
  notify_user, set_hud_state, get_app_status, get_conversation_history,
  show_message. Les outils UI transitent par IPC vers le renderer.
- Les mêmes actions système sont proposées au modèle en chat completions.

Notifications
- Heures calmes (plage horaire, franchissement de minuit), mots prioritaires,
  échecs de crons toujours lus, résumé vocal des messages entrants (n premières
  phrases), thème nuit automatique, compteur de non-lus.

Conversation
- Mode mission : bouton dans la barre de commande, second modèle Hermes
  (hermes.missionModel) pour les tâches longues.
- Barge-in : la parole de l'utilisateur coupe la voix ; seuil d'énergie et
  ratio relevés pendant la synthèse pour ignorer l'écho.

Widget compact
- Bandeau glanceable : état, dernière phrase, non-lus, indicateurs heures
  calmes et mission.

Tests : 28 tests unitaires (heures calmes, priorité, résumé), e2e Electron
sous Xvfb : MCP initialize/tools/list/tools/call (presse-papiers, capture en
image, état et message via le renderer), bandeau compact, aucune erreur.


Claude-Session: https://claude.ai/code/session_017Wn5VX9HNbJ7N54hR24u9Y

Co-authored-by: Claude <noreply@anthropic.com>
2026-09-04 00:47:34 +02:00
LogiFlowandClaude af8bdc5e9d feat: fin de phrase Silero, vision d'écran et actions locales (v2.3.0) (#13)
Écoute permanente
- Silero VAD dans le worker sherpa-onnx (vad.start/audio/stop) ; le renderer
  envoie des trames de 128 ms pendant la commande et reçoit le segment WAV
  complet (speech-start / segment). Repli sur le VAD énergétique si le modèle
  n'est pas installé ou si l'option est désactivée.
- Modèle « silero-vad » (0,6 Mo) dans le catalogue, section « Fin de phrase »
  dans Modèles locaux, réglage dans Paramètres → Micro.

Vision d'écran
- IPC system:screen-capture (desktopCapturer, JPEG 1600 px) ; bouton dans la
  barre de commande ; « regarde mon écran… » joint la capture à la question
  envoyée à Hermes (transport chat completions pour les images).

Actions locales
- IPC system:action à liste blanche : verrouiller la session, touches média
  (volume, mute, lecture, piste), ouvrir une application connue ou une URL
  http(s), presse-papiers, recherche de fichiers dans les dossiers utilisateur.
- Routeur d'intentions FR/EN exécuté avant Hermes (« coupe le son », « ouvre
  Spotify », « verrouille la session »…), résultat affiché et lu ; désactivable.

Correctif
- Chat completions : les premiers fragments SSE arrivés avant l'événement de
  démarrage étaient perdus (premier mot manquant) ; ils sont maintenant rejoués.

Tests : 26 tests unitaires (intentions locales ajoutées), e2e Electron sous
Xvfb avec les vrais modèles (Silero : un segment par phrase, 6,7 s d'audio
traités en 190 ms ; capture 109 ko reçue par Hermes ; intention locale
traitée sans Hermes).


Claude-Session: https://claude.ai/code/session_017Wn5VX9HNbJ7N54hR24u9Y

Co-authored-by: Claude <noreply@anthropic.com>
2026-09-03 20:46:26 +02:00
Claude 0d284fea9e feat: always-on wake word with sherpa-onnx keyword spotting (v2.2.0)
- Catalog: 3.3 MB zipformer keyword-spotting model (kws-en).
- shared/keywords: BPE encoding of wake phrases (SentencePiece table for common words,
  greedy longest-match fallback over the model vocabulary) and keywords file builder.
- Worker: KeywordSpotter stream fed with 16-bit PCM, detections pushed as unsolicited
  messages; engine derives the keywords file, maps sensitivity to threshold/score,
  forwards detections to the renderer and re-arms after a worker restart.
- Renderer: WakeListener keeps one microphone stream, batches 256 ms frames to the
  spotter and captures the command on the same stream after detection (pre-roll, VAD),
  then resumes spotting; the wake word also interrupts speech. Settings: wake mode
  (off / always-on / transcript filter), keyword, sensitivity, status and one-click
  model download; HUD caption shows the active keyword.
- Validated: detection in the worker (fork) and through the real Electron IPC path on
  Kokoro audio, no false positive on an English recording; 23 unit tests.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017Wn5VX9HNbJ7N54hR24u9Y
2026-09-03 18:21:35 +00:00
Claude eefc36aca8 feat: local offline voice models (sherpa-onnx) with model manager and wake word (v2.1.0)
- electron/voice: model catalog (Whisper base/small/turbo, SenseVoice, Kokoro v1.0,
  Piper fr), streaming tar.bz2 downloader with progress, sherpa-onnx worker running in
  an Electron utilityProcess (transcribe / synthesize / status / unload), IPC + bridge.
- Renderer: 'local' providers for STT and TTS, Settings → Modèles locaux (download,
  progress, delete, activate), speaker selection, hands-free wake word with a tolerant
  matcher (accents, punctuation, edit distance) and attention window after a bare wake word.
- Packaging: native addon and worker unpacked from the asar; release 2.1.0.

Validated on Linux: Kokoro (fr) → Whisper base round trip, Piper (fr) → Whisper round trip.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017Wn5VX9HNbJ7N54hR24u9Y
2026-09-03 17:43:52 +00:00
Claude 2471add00b build: four-part releaseVersion (2.0.0.1) injected at packaging time
electron-builder refuses a non-semver package.json version, so the published
number lives in package.json releaseVersion and scripts/dist.mjs passes it as
extraMetadata.version (plus the hotfix digit as Windows build number). The
workflow tags and names the release from the same field.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017Wn5VX9HNbJ7N54hR24u9Y
2026-09-03 15:47:32 +00:00
Claude 127a2083a1 feat!: rebuild EveFlow as a JARVIS-style voice HUD for Hermes Agent (v2.0.0)
Complete rewrite of the application:

- Toolchain: Electron 44, Vite 8, React 19, TypeScript 5.9, Zustand, Vitest;
  main process rewritten in TypeScript (electron/), typed IPC contract (shared/),
  sandboxed renderer with webSecurity on and an HTTP/SSE proxy in the main process.
- Voice: AudioWorklet microphone capture at 16 kHz with adaptive energy VAD and
  auto-stop, WAV encoder, OpenAI-compatible STT, TTS queue with sentence-level
  streaming, prefetch and Web Audio playback feeding an analyser; hands-free mode,
  global push-to-talk hotkey, system-voice fallback.
- Hermes: full API client (capabilities, health, models, skills, toolsets,
  sessions, jobs) with automatic transport selection: runs API (SSE lifecycle,
  approvals, steer, stop) > sessions stream > chat completions with local tools;
  tolerant event normalisation; webhook receiver hardened (secret, size limit).
- UI: JARVIS arc-reactor core on Canvas 2D reacting to the real audio signal,
  holographic HUD layout (transcript, core, Hermes ops panel with tools/crons/
  skills/sessions/link tabs, telemetry), settings drawer, approval modals,
  compact floating widget, four themes, tray icon and global shortcuts.
- Removed the 3D Eve robot, three.js and legacy assets; migrated 1.x settings.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017Wn5VX9HNbJ7N54hR24u9Y
2026-09-03 13:40:59 +00:00
Michael 5217eee53a fix: downsample audio to 16kHz to prevent ASR 500 error, add permission check handler, and render errors in compact view (v1.0.8) 2026-06-08 20:44:31 +02:00
Michael 221bb7062c 1.0.7 2026-06-08 20:38:05 +02:00
Michael cf52a610d4 1.0.6 2026-06-08 19:44:33 +02:00
Michael 5c6c3a9e30 1.0.5 2026-06-08 19:36:07 +02:00
Michael c25875d8be 1.0.4 2026-06-08 19:16:49 +02:00
LogiFlow 115996c7d9 Remove image table from README
Removed the table displaying the main cockpit and compact widget images.
2026-05-22 16:02:19 +02:00
Michael 9dc19db942 docs: add comprehensive README.md with high-fidelity UI screenshots 2026-05-21 19:36:30 +02:00