108 lines
3.6 KiB
Bash
Executable File
108 lines
3.6 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
set -uo pipefail
|
|
|
|
PASS=0
|
|
WARN=0
|
|
FAIL=0
|
|
|
|
pass() { printf 'PASS %s\n' "$*"; PASS=$((PASS + 1)); }
|
|
warn() { printf 'WARN %s\n' "$*"; WARN=$((WARN + 1)); }
|
|
fail() { printf 'FAIL %s\n' "$*"; FAIL=$((FAIL + 1)); }
|
|
|
|
echo "== Local AI platform verification =="
|
|
|
|
ROOT_USE="$(df -P / | awk 'NR==2 {gsub(/%/, "", $5); print $5}')"
|
|
if [[ -n "$ROOT_USE" && "$ROOT_USE" -lt 85 ]]; then
|
|
pass "Systempartition bei ${ROOT_USE}%"
|
|
else
|
|
fail "Systempartition bei ${ROOT_USE:-unbekannt}% (Ziel: unter 85%)"
|
|
fi
|
|
|
|
if command -v nvidia-smi >/dev/null 2>&1; then
|
|
GPU_LIST="$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>/dev/null)"
|
|
GPU_COUNT="$(printf '%s\n' "$GPU_LIST" | sed '/^[[:space:]]*$/d' | wc -l)"
|
|
if [[ "$GPU_COUNT" -ge 2 ]]; then
|
|
pass "beide GPUs erkannt: $(printf '%s' "$GPU_LIST" | paste -sd ' | ' -)"
|
|
elif [[ "$GPU_COUNT" -eq 1 ]]; then
|
|
fail "nur eine von zwei erwarteten GPUs erkannt: $GPU_LIST"
|
|
else
|
|
fail "nvidia-smi liefert keine GPU"
|
|
fi
|
|
else
|
|
fail "nvidia-smi fehlt"
|
|
fi
|
|
|
|
if [[ -e /sys/class/net/lan0 ]] && \
|
|
[[ "$(< /sys/class/net/lan0/address)" == "58:11:22:bb:ad:0c" ]] && \
|
|
[[ "$(< /sys/class/net/lan0/operstate)" == "up" ]]; then
|
|
pass "stabiles LAN-Interface lan0 aktiv (58:11:22:bb:ad:0c)"
|
|
else
|
|
fail "stabiles LAN-Interface lan0 fehlt, ist down oder hat die falsche MAC"
|
|
fi
|
|
|
|
container_healthy() {
|
|
local name=$1 state health
|
|
state="$(docker inspect --format '{{.State.Status}}' "$name" 2>/dev/null || true)"
|
|
health="$(docker inspect --format '{{if .State.Health}}{{.State.Health.Status}}{{end}}' "$name" 2>/dev/null || true)"
|
|
[[ $state == running && ( -z $health || $health == healthy ) ]]
|
|
}
|
|
|
|
for container in mike-ai-profile-controller mike-ai-router mike-ai-xtts \
|
|
mike-ai-piper mike-ai-tts-gateway mike-ai-open-webui; do
|
|
if container_healthy "$container"; then
|
|
pass "$container gesund"
|
|
else
|
|
fail "$container fehlt oder ist nicht gesund"
|
|
fi
|
|
done
|
|
|
|
ACTIVE_LLAMA="$(docker ps --format '{{.Names}}' | grep -Ec '^mike-ai-llama-(fast|medium|large|ultra|uncensored|experimental)$' || true)"
|
|
if [[ $ACTIVE_LLAMA -eq 1 ]]; then
|
|
pass "exakt ein llama.cpp-Profil aktiv"
|
|
else
|
|
fail "$ACTIVE_LLAMA llama.cpp-Profile aktiv (erwartet: 1)"
|
|
fi
|
|
|
|
for optional in mike-ai-mcp-web mike-ai-mcp-homeassistant mike-ai-mcp-arr \
|
|
mike-ai-mcp-github mike-ai-mcp-platform-context mike-ai-mcp-unraid-official; do
|
|
if container_healthy "$optional"; then
|
|
pass "$optional aktiv"
|
|
else
|
|
warn "$optional nicht aktiv oder nicht installiert"
|
|
fi
|
|
done
|
|
|
|
if [[ -s /var/lib/mike-ai-platform-context/runtime.json ]]; then
|
|
snapshot_age=$(( $(date +%s) - $(stat -c %Y /var/lib/mike-ai-platform-context/runtime.json) ))
|
|
if (( snapshot_age <= 180 )); then
|
|
pass "Platform-Kontext-Snapshot aktuell (${snapshot_age}s)"
|
|
else
|
|
fail "Platform-Kontext-Snapshot veraltet (${snapshot_age}s)"
|
|
fi
|
|
else
|
|
fail "Platform-Kontext-Snapshot fehlt"
|
|
fi
|
|
|
|
if docker exec mike-ai-router python -c \
|
|
"import urllib.request; urllib.request.urlopen('http://127.0.0.1:8081/health', timeout=3)" \
|
|
>/dev/null 2>&1; then
|
|
pass "Router-Liveness intern erreichbar"
|
|
else
|
|
fail "Router-Liveness intern nicht erreichbar"
|
|
fi
|
|
|
|
if systemctl list-unit-files --no-legend 2>/dev/null | grep -Eq '(vision-rx|whisper-rx|granite-rx).*enabled'; then
|
|
warn "Aktivierte RX-Altlast gefunden"
|
|
else
|
|
pass "Keine aktivierte RX-Altlast"
|
|
fi
|
|
|
|
if systemctl list-unit-files --no-legend 2>/dev/null | grep -E '(benchmark|race).*enabled' >/dev/null; then
|
|
warn "Automatisch aktivierter Benchmark-/Race-Dienst gefunden"
|
|
else
|
|
pass "Keine automatisch aktivierten Benchmarks"
|
|
fi
|
|
|
|
printf '\nErgebnis: %d PASS, %d WARN, %d FAIL\n' "$PASS" "$WARN" "$FAIL"
|
|
[[ "$FAIL" -eq 0 ]]
|