akadmin/Funk-lab
1
0
Fork 0
mirror of https://github.com/Alkatrazz24/Funk-lab.git synced 2026-07-08 22:44:43 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions
187 commits 10 branches 0 tags 10 MiB
Commit graph

111 commits

Author SHA1 Message Date
alkatrazz
0c89d262d1 docs: cluster.md — procédures allumage/extinction détaillées 
Ajout des procédures pas-à-pas pour démarrer/éteindre avec et sans k8s.
Note sur WOL compute nodes (BIOS non configuré → allumage manuel).
Mise à jour section aliases → fonctions bash avec support --k8s.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-13 15:11:47 +02:00
alkatrazz
763b29495e docs: incident EXT4 2026-05-13 + hermes-agent nouvelle archi SSD 
- incidents.md : incident corruption EXT4 après arrêt brutal (655 erreurs,
  e2fsck, réinstall hermes-agent, nouveau chemin /opt/hermes/.hermes/)
- hermes.md : arborescence mise à jour (code SSD vs données RAID5),
  chemins pip/venv/frontend corrigés
- Ansible role hermes_agent : venv path et wrapper mis à jour
  (hermes_home/.hermes/hermes-agent/venv/ au lieu de hermes_data_dir/)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-13 14:49:53 +02:00
alkatrazz
a1826fe339 docs: gestion cluster + script funk-cluster mis à jour 
- admin/cluster.md : nouveau guide démarrage/arrêt (funk-start/stop/--k8s)
- admin/README.md : lien vers cluster.md
- admin/systeme.md : services llama-server mis à jour (GPU + 2 CPU)
- ansible/roles/litellm/files/funk-cluster : script versionné
  (talosctl fix, storage-01 shutdown, --k8s optionnel, stop timeout)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-13 02:11:21 +02:00
alkatrazz
07b94fe8a8 docs: profils Hermes multi-modèles + progression 12-13 mai 
- admin/hermes.md : section profils complète (funk-ai/brain/system/monitor),
  architecture multi-modèles gpu-01, arborescence profiles/
- PROGRESS.md : entrées 2026-05-12 et 2026-05-13

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-13 01:52:58 +02:00
alkatrazz
0ce6be04bb docs: réorganisation install/ — guides séparés par machine 
- admin/install/README.md        — index + ordre d'installation recommandé
- admin/install/storage-01.md   — AlmaLinux + RAID5 + Ansible + stack IA (Hermes/LiteLLM/Qdrant/PostgreSQL)
- admin/install/gpu-01.md       — AlmaLinux + ROCm + llama-server (RX 6700XT, HSA_OVERRIDE)
- admin/install/kubernetes.md   — ex admin/installe.md (Talos + MetalLB + Traefik)
- admin/README.md               — séparation install/ vs référence opérationnelle

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-12 23:03:05 +02:00
alkatrazz
0bdfe49d75 docs: guide d'installation complet cluster Talos/k8s 
Couvre de A à Z : outils, SOPS/age, talconfig, installation des 3 nœuds,
bootstrap etcd, MetalLB, Traefik, DNS wildcard. Section pièges documentant
toutes les erreurs rencontrées lors de l'installation réelle.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-12 22:51:03 +02:00
alkatrazz
c8a1faa632 feat: MetalLB + Traefik + wildcard DNS lab.local 
- MetalLB pool 192.168.10.200-230 (L2 mode)
- Traefik LoadBalancer sur 192.168.10.200 (HTTP/HTTPS)
- dnsmasq wildcard *.lab.local → 192.168.10.200
- Fix Flannel CrashLoopBackOff : ClusterRoleBinding corrigée (kube-flannel → kube-system)
- Doc talos.md : procédure complète MetalLB + Traefik + pièges Flannel

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-12 22:45:06 +02:00
alkatrazz
bb72145365 feat(talos): bootstrap Kubernetes cluster funk (3 nodes, v1.33.1) 
- Add talconfig.yaml with compute-01/02/03 (nvme0n1, Flannel CNI)
- Add SOPS/age encryption for talsecret.sops.yaml
- Add patches: NTP/DNS → storage-01, kubelet reserved for 8GB workers
- Fix nftables: open DHCP port 67 for cluster LAN
- Add dnsmasq DHCP with static leases for all 3 compute nodes
- Add admin/talos.md: full install procedure + admin commands
- Install kubectl + talosctl on storage-01

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-12 22:11:38 +02:00
alkatrazz
a87d1baf76 docs(hermes): add update procedure and post-update checks 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-12 20:28:27 +02:00
alkatrazz
6d375da7b2 docs: add Funk/ reference docs and update hermes TUI instructions 
- Remove Funk/ from .gitignore (repo is private)
- Add HOMELAB.md and agent configs for Hermes context
- Update hermes TUI doc: must run as hermes user from /srv/data/hermes

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-12 19:51:42 +02:00
alkatrazz
dca71144d6 docs(admin): add ops documentation and fix hermes dashboard service 
- Remove admin/ from .gitignore (repo is now private)
- Add --tui flag to hermes-dashboard.service template
- Document hermes-tui wrapper, dashboard access, TUI usage

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-12 18:50:43 +02:00