Commit Graph
53 Commits
Author SHA1 Message Date
Mikei386 c6517ee137 Simplify Athena runtime and document current architecture 2026-08-30 08:45:52 +02:00
Mikei386 c721db47d0 Move Deemix MCP to standalone repository 2026-08-28 22:42:55 +02:00
Mikei386 d570a06911 Add standalone Unraid ARR MCP package 2026-08-27 21:49:01 +02:00
Mikei386 167448d778 publish MCPs through a filtered Hermes group 2026-08-26 11:34:15 +02:00
Mikei386 2595bab17b let Hermes manage MCPHub through its API 2026-08-26 11:28:51 +02:00
Mikei386 bc902261b9 simplify MCPHub extensions and restore Hermes web tools 2026-08-26 11:08:47 +02:00
Mikei386 ab671a6396 simplify Athena runtime and centralize MCP management 2026-08-26 09:57:38 +02:00
Mikei386 896c12193e Replace compression sidecar with Hermes micro-compaction 2026-08-26 06:18:51 +02:00
Mikei386 438bd34b72 Keep experimental compressor stopped by default 2026-08-26 01:42:14 +02:00
Mikei386 aaadc57c07 Harden and demote experimental Hermes compressor 2026-08-26 01:40:38 +02:00
Mikei386 43d9903d13 Add dedicated Hermes compression model 2026-08-26 00:45:32 +02:00
Mikei386 e872829b11 Route Athena operator through MCPHub 2026-08-26 00:25:44 +02:00
Mikei386 3ab7c57043 Document Hermes migration to Unraid 2026-08-25 23:52:55 +02:00
Mikei386 5087048e0c Add official Hermes Agent Unraid template 2026-08-25 23:32:18 +02:00
Mikei386 cca1fb217e Consolidate portable MCPs in Unraid MCPHub 2026-08-25 23:21:29 +02:00
Mikei386 069da8b4f0 Simplify Athena stack and recovery 2026-08-25 22:27:26 +02:00
Mikei386 0a640e76ea Simplify Athena operator architecture 2026-08-25 21:53:12 +02:00
Mikei386 348ca1324e Add Hermes Agent as reproducible second client 2026-08-24 17:00:39 +02:00
Mikei386 c402ea79f7 feat(vpn): expose Athena services directly over WireGuard 2026-08-24 07:33:16 +02:00
Mikei386 e24839bfe1 fix(tools): harden OpenWebUI tool workflows 2026-08-24 00:40:32 +02:00
Mikei386 94f3758795 Add controlled Athena platform operator 2026-08-23 21:10:44 +02:00
Mikei386 288dc62e7e Document controlled GitHub MCP write mode 2026-08-23 18:20:01 +02:00
Mikei386 3dbb66037d Add self-maintaining Athena platform context MCP 2026-08-23 17:31:05 +02:00
Mikei386 64d36ad838 Document Qwen operator context and safety model 2026-08-23 17:05:02 +02:00
Mikei386 3d528f2716 Add encrypted bare-metal recovery workflow 2026-08-23 15:48:41 +02:00
Mikei386 727827ac32 Add spoken tool progress acknowledgements 2026-08-23 13:54:39 +02:00
Mikei386 f90fc93f9c Add XTTS primary voice with Piper fallback 2026-08-23 12:22:59 +02:00
Mikei386 2ef894160a Add final Qwen3.8 runtime and uncensored profile 2026-08-23 00:10:53 +02:00
Mikei386 af6abf54ae Add SSH-only emergency access fallback 2026-08-22 21:08:58 +02:00
Mikei386 0e5876f1a9 Add fail-closed WireGuard container gateway 2026-08-22 20:48:49 +02:00
Mikei386 ce5bbc2e69 Add unattended host recovery safeguards 2026-08-22 19:27:34 +02:00
Mikei386 7ac93befc4 Add RTX 5080 FLUX hot-swap worker 2026-08-22 17:40:32 +02:00
Mikei386 8267a85a96 Offload vision projector to RTX 3060 2026-08-22 17:19:56 +02:00
Mikei386 41b9c17f0f Define four-profile production matrix with Medium default 2026-08-22 11:30:38 +02:00
Mikei386 977f8f5c76 Validate Pure quant for 256K Ultra profile 2026-08-22 11:01:13 +02:00
Mikei386 f52cf14069 Add tested 256K Ultra profile 2026-08-22 10:44:14 +02:00
Mikei386 a5cf11582a Add reproducible Piper TTS service 2026-08-21 17:02:32 +02:00
Mikei386 c0cbeb0f15 Add global Midnight Aurora Open WebUI theme 2026-08-21 15:28:39 +02:00
Mikei386 bf90698b99 Document Athena rebuild and clarify tool volume ownership 2026-08-21 14:35:52 +02:00
Mikei386 f0d552ef58 Containerize MCP tool services 2026-08-20 23:54:02 +02:00
Mikei386 3ab9628088 Document centralized isolated MCP tool plane 2026-08-20 21:42:40 +02:00
Mikei386 e83c0e2c70 Add reproducible Docker and WireGuard host bootstrap 2026-08-20 21:23:16 +02:00
Mikei386 cb07779f5a Replace vision hotswap with native multimodal profiles 2026-08-20 14:24:56 +02:00
Mikei386 fd4a3055e8 Rebuild profile router as secure recoverable v2 2026-08-20 13:41:00 +02:00
Mikei386 bdd6c08643 Document complete recovery requirements and reference state 2026-08-20 13:05:27 +02:00
Mikei386 0e4a9de5ba Expand router into reproducible local AI platform 2026-08-20 12:56:53 +02:00
Mike a84220725a Vision: Q3-Augen-Orchestrierung + Folgefragen-Sanitize
- Automatische Vision-Orchestrierung: temporärer Q3-Vision-Server
  (llama.cpp + mmproj) analysiert Bilder, Hauptmodell (Fast/Medium/Long)
  erzeugt die finale Antwort. Zentrale GPU-Lock (Ausschluss mit FLUX),
  Drain, Timeouts, Restore in jedem Fehlerfall.
- Vision-Analyse wird als interne User-Message injiziert (nie als
  Assistant-Turn in Open WebUI).
- Analyse-Cache (LRU, keyed by Bild-Hash): Folgefragen triggern keinen
  neuen Hotswap.
- Sanitize: alle Bild-Parts (image_url/Base64) werden bei jedem Request
  durch die gecachte Analyse ersetzt, Bilddaten entfernt - das
  Nicht-Vision-Hauptmodell bekommt keine Bilder mehr (kein
  image input is not supported).
- /v1/streams/lookup fail-fast während Vision-Swap; /props-Regression
  behoben; POST /vision/test für direkten Test.
- systemd-Unit: VISION_*-Umgebungsvariablen; README dokumentiert Vision.
2026-08-20 07:48:25 +02:00
Mikei386 d399d2b4f7 TTS: Kokoro → XTTS-v2 (CPU-only, Claribel Dervla)
- Neues xtts_worker.py: Coqui XTTS-v2, HTTP-API auf Port 8085
- Router: TTS_WORKER_URL → 8085, TTS_MODEL → xtts-v2, TTS_VOICES → claribel
- deploy: mike-ai-xtts.service, install.sh + deploy.sh aktualisiert
- Tests: 54/54 bestanden (mock_tts_worker + test_local.sh auf XTTS umgestellt)
- README: TTS-Section auf XTTS-v2 aktualisiert
- Kokoro-Service gestoppt und deaktiviert (Dateien bleiben als Backup)
2026-08-19 22:01:58 +02:00
Mikei386 51ef07c874 router: deutsche Spracherkennung mit whisper.cpp (CPU-only)
- STT-Worker (stt_worker.py): langlebiger HTTP-Service auf Port 8084
  - whisper-cli als Subprozess (CPU-only, 8 Threads)
  - Audio-Vorbereitung via ffmpeg (WebM/Opus/M4A → 16 kHz WAV)
  - Nativ: WAV, MP3, OGG, FLAC
  - Health-Endpunkt: GET /status
  - Transkription: POST /transcribe (Multipart-Form-Data)

- Router-Integration:
  - POST /v1/audio/transcriptions (OpenAI-kompatibel)
  - GET /v1/audio/models (whisper-1, kokoro-german)
  - GET /v1/audio/voices (martin, victoria)
  - /status mit stt-Section
  - model=whisper-1 akzeptiert
  - response_format: json, verbose_json

- systemd-Service: mike-ai-whisper.service
  - Boot-Start, Restart on failure, journald
  - CPU-only, kein GPU-Lock

- Deploy-Dateien aktualisiert (deploy.sh, install.sh)
- Mock-STT-Worker für lokale Tests (dev/mock_stt_worker.py)
- Tests ergänzt: STT Status, WAV, language=de, unbekanntes Modell,
  Worker down, Recovery, Audio-Modelle, Audio-Voices,
  STT+Qwen parallel, STT+TTS parallel
- README.md: STT-Section mit Endpunkten, Benchmarks, Doku

Benchmarks (CPU-only, 8 Threads):
  7.3 s Audio → 8.9 s (RTF 1.22×)
  30 s Audio → 16.8 s (RTF 0.56×)
  50 s Audio → 18.5 s (RTF 0.37×)
  RAM: ~1.7 GB (Modell), Worker: ~20 MB
2026-08-19 13:53:22 +02:00
Mikei386 ff064685ce router: TTS auf offiziellen Kikiri-Deutsche-Pfad umgestellt
Ersetzt die alte Implementierung (kokoro 0.7.16 + espeak.EspeakG2P)
durch den offiziellen Kikiri-Deutsche-Inferenzpfad:

- semidark/kokoro-Fork (0.9.4) mit lang_code='d'
- semidark/misaki-Fork (0.9.4) mit misaki.de.DEG2P
  (Text-Normalisierung + espeak-ng + Aussprache-Overrides)
- Verbessertes Chunking (Split an Satzgrenzen, 400 Zeichen)
- repo_id='hexgrad/Kokoro-82M' für KModel/KPipeline

Änderungen:
- router/tts_worker.py: KModel/KPipeline API aktualisiert,
  Monkey-Patching entfernt, Docstring aktualisiert
- deploy/install.sh: semidark-Forks installieren (misaki[de],
  kokoro --no-deps, spacy für misaki.en-Import)
- README.md: G2P-Pfad, Chunking, Python-Pakete, Python-3.13-Hinweis

Getestet: 43/43 lokale Tests, E2E auf Zielsystem (WAV/MP3,
LAN-Zugriff, parallele Qwen/TTS-Operation, Chat intakt).
2026-08-19 13:09:29 +02:00