chore(gpu-01): retire les serveurs llama CPU system/monitor/dev (inutilisés) (#31)

Trois instances llama-server CPU manuelles (hors Ansible) tournaient sur gpu-01
sans servir : déjà orphelines de LiteLLM (alias absents de config.yaml, d'où le
bruit "Invalid model name"). Suppression complète :

gpu-01 (opérationnel, déjà fait) :
- systemctl disable --now + rm des units llama-server-{system,monitor,dev}
- ports firewall 1235/1236/1237 fermés

Repo :
- monitoring : scrape jobs (values.yaml) + alertes LlamaServer{System,Monitor}Down
  (alerts-ai.yaml) retirés → plus de "target down"/alertes fantômes ; panneaux de
  statut dashboard-infrastructure recyclés (system→llama-embed, monitor supprimé).
- docs admin/ + hermes-skills (souls funk-ai/brain, SKILL agent-delegation) mises à
  jour : inventaire modèles, profils Hermès system/monitor sans backend (à repointer
  sur qwen3-8b), litellm, ops, monitoring.

Les profils Hermès system/monitor existent toujours mais sans backend dédié.
Dashboards Grafana dashboard-ai (panneaux graphiques CPU) laissés tels quels
(cosmétique, séries vides, aucune alerte).

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

k8s/infra/monitoring/alerts/alerts-ai.yaml

@@ -21,24 +21,6 @@ spec:
             summary: "llama-server GPU (Qwen3-8B) inaccessible"
             description: "Le serveur LLM GPU sur gpu-01:1234 ne répond plus depuis 2 min. Inférence GPU unavailable."
 
-        - alert: LlamaServerSystemDown
-          expr: up{job="llama-server-system"} == 0
-          for: 2m
-          labels:
-            severity: warning
-          annotations:
-            summary: "llama-server CPU system (Qwen3-1.7B) inaccessible"
-            description: "Le serveur LLM CPU system sur gpu-01:1236 ne répond plus. Profil Hermes system degraded."
-
-        - alert: LlamaServerMonitorDown
-          expr: up{job="llama-server-monitor"} == 0
-          for: 2m
-          labels:
-            severity: warning
-          annotations:
-            summary: "llama-server CPU monitor (Qwen3-1.7B) inaccessible"
-            description: "Le serveur LLM CPU monitor sur gpu-01:1237 ne répond plus. Profil Hermes monitor degraded."
-
         # --- GPU temperature (ROCm via textfile_collector) ---
         - alert: GPUTemperatureHigh
           expr: rocm_gpu_temperature_celsius > 80

k8s/infra/monitoring/dashboards/dashboard-infrastructure.yaml

@@ -1413,33 +1413,15 @@ data:
               "color": {"mode": "thresholds"},
               "thresholds": {"mode": "absolute", "steps": [{"color": "red", "value": null}, {"color": "green", "value": 1}]},
               "unit": "none",
-              "mappings": [{"type": "value", "options": {"1": {"text": "llama-server system", "color": "green", "index": 0}, "0": {"text": "ARRÊTÉ", "color": "red", "index": 1}}}]
+              "mappings": [{"type": "value", "options": {"1": {"text": "llama-embed nomic", "color": "green", "index": 0}, "0": {"text": "ARRÊTÉ", "color": "red", "index": 1}}}]
             },
             "overrides": []
           },
           "gridPos": {"h": 3, "w": 6, "x": 6, "y": 61},
           "id": 61,
           "options": {"reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "textMode": "auto", "colorMode": "background", "graphMode": "none"},
-          "title": "llama-server CPU system (:1236)",
-          "targets": [{"datasource": {"type": "prometheus", "uid": "${datasource}"}, "expr": "node_systemd_unit_state{job=\"gpu-01-node\",name=\"llama-server-system.service\",state=\"active\"}", "legendFormat": "", "refId": "A"}],
-          "type": "stat"
-        },
-        {
-          "datasource": {"type": "prometheus", "uid": "${datasource}"},
-          "fieldConfig": {
-            "defaults": {
-              "color": {"mode": "thresholds"},
-              "thresholds": {"mode": "absolute", "steps": [{"color": "red", "value": null}, {"color": "green", "value": 1}]},
-              "unit": "none",
-              "mappings": [{"type": "value", "options": {"1": {"text": "llama-server monitor", "color": "green", "index": 0}, "0": {"text": "ARRÊTÉ", "color": "red", "index": 1}}}]
-            },
-            "overrides": []
-          },
-          "gridPos": {"h": 3, "w": 6, "x": 12, "y": 61},
-          "id": 62,
-          "options": {"reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "textMode": "auto", "colorMode": "background", "graphMode": "none"},
-          "title": "llama-server CPU monitor (:1237)",
-          "targets": [{"datasource": {"type": "prometheus", "uid": "${datasource}"}, "expr": "node_systemd_unit_state{job=\"gpu-01-node\",name=\"llama-server-monitor.service\",state=\"active\"}", "legendFormat": "", "refId": "A"}],
+          "title": "llama-embed nomic (:1238)",
+          "targets": [{"datasource": {"type": "prometheus", "uid": "${datasource}"}, "expr": "node_systemd_unit_state{job=\"gpu-01-node\",name=\"llama-embed.service\",state=\"active\"}", "legendFormat": "", "refId": "A"}],
           "type": "stat"
         },
         {

k8s/infra/monitoring/values.yaml

@@ -81,22 +81,6 @@ prometheus:
               model: qwen3-8b
               type: gpu
 
-      - job_name: llama-server-system
-        static_configs:
-          - targets: ['192.168.10.20:1236']
-            labels:
-              instance: gpu-01
-              model: qwen3-1.7b-system
-              type: cpu
-
-      - job_name: llama-server-monitor
-        static_configs:
-          - targets: ['192.168.10.20:1237']
-            labels:
-              instance: gpu-01
-              model: qwen3-1.7b-monitor
-              type: cpu
-
 alertmanager:
   ingress:
     enabled: true