#!/usr/bin/env bash
# Single source of truth for Dankserver GLM-5.3 state.
#
# This exists because the ad-hoc status commands kept producing WRONG readings.
# The specific trap: /proc/meminfo separates key from value with a TAB, so the
# common idiom
#   grep MemAvailable /proc/meminfo | tr -s " " | cut -d" " -f2
# yields an empty field (tab is not a space) and awk then prints 0.0 -- which
# reads as "host out of memory" when the host actually has 240 GiB free.
# Everything below parses on a colon split, which is tab-agnostic, and the
# memory figure is cross-checked before it is shown.
set -uo pipefail

MB=1048576
GLM_CTR="${GLM_CTR:-glm-w4a16}"

mem_field() { awk -v k="$1:" '$1==k {printf "%.1f", $2/'"$MB"'; exit}' /proc/meminfo; }
section() { printf '\n== %s ==\n' "$1"; }

section "time / host"
printf '  %s   %s\n' "$(date +%H:%M:%S)" \
  "$(awk -F: '/model name/{print $2; exit}' /proc/cpuinfo | sed 's/^ *//')"

section "memory (GiB)"
TOT=$(mem_field MemTotal); AVAIL=$(mem_field MemAvailable)
printf '  MemTotal     %8s\n' "$TOT"
printf '  MemAvailable %8s\n' "$AVAIL"
printf '  Cached       %8s\n' "$(mem_field Cached)"
awk -v t="$TOT" -v a="$AVAIL" 'BEGIN{
  if (t+0 <= 0 || a+0 <= 0) { print "  *** PARSE BUG: zero value ***"; exit }
  if (a+0 > t+0)         { print "  *** PARSE BUG: available > total ***"; exit }
  printf "  check        ok (%.0f%% free)\n", 100*a/t
}'

section "swap"
swapon --show=NAME,SIZE,USED --noheadings 2>/dev/null \
  | awk '{printf "  %-12s %6s used of %s\n",$1,$3,$2}' || echo "  none"

section "gpu"
# CSV layout: device,VRAM Total Memory (B),VRAM Total Used Memory (B)
rocm-smi --showmeminfo vram --csv 2>/dev/null | awk -F, '
  NR>1 && $1 ~ /^card[0-9]+$/ {
    printf "  %-8s %7.2f GiB used of %.2f\n", $1, $3/1073741824, $2/1073741824
  }'
printf '  compute util: '
rocm-smi --showuse --csv 2>/dev/null | awk -F, 'NR>1 && $1 ~ /^card[0-9]+$/ {printf "%s=%s%% ", $1, $2}'
echo

section "disk"
df -h /home/dank 2>/dev/null | awk 'NR==2{printf "  %s  %s used  %s free  (%s)\n",$1,$3,$4,$5}'

section "llm containers"
if podman ps -a --format '{{.Names}}' 2>/dev/null | grep -qE 'glm|frank'; then
  podman ps -a --format '{{.Names}}|{{.Status}}' 2>/dev/null \
    | awk -F'|' '$1 ~ /glm|frank/ {printf "  %-18s %s\n",$1,$2}'
else
  echo "  none"
fi

section "frank-primary unit"
printf '  active:  %s\n' "$(systemctl is-active frank-primary 2>/dev/null | head -1)"
printf '  enabled: %s\n' "$(systemctl is-enabled frank-primary 2>/dev/null | head -1)"

section "glm serve tail"
if podman ps -a --format '{{.Names}}' 2>/dev/null | grep -qx "$GLM_CTR"; then
  podman logs "$GLM_CTR" 2>&1 | grep -viE 'multiproc_executor\.py:943' | tail -5 | sed 's/^/  /'
else
  echo "  (container $GLM_CTR not present)"
fi

section "done"