Capture current Ansible control plane state

Commit the accumulated infrastructure work that was living only in the working tree: monitoring stack, emergency access/bot, gyro allocator, grimmory, adguard, backup audit and the OpenCode agent definitions. Also ignore Python bytecode, local archives and Nix/direnv artifacts. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01GTocXkGUUazHdKKd3r9k71
2026-08-26 21:39:28 +03:00
parent 4bafa7d09e
commit c676be81ec
126 changed files with 10583 additions and 44 deletions
@@ -0,0 +1,70 @@
+#!/bin/sh
+# Managed by Ansible: HomeLab PBS backup audit (L0 freshness)
+set -eu
+
+LOG_FILE="{{ backup_audit_log_file }}"
+METRICS_DIR="{{ backup_audit_metrics_dir }}"
+METRICS_FILE="$METRICS_DIR/homelab_backup_audit_pbs.prom"
+METRICS_TMP=$(mktemp "$METRICS_FILE.XXXXXX")
+STATUS=OK
+NOW_EPOCH=$(date +%s)
+
+trap 'rm -f "$METRICS_TMP"' EXIT
+
+publish_metrics() {
+  chmod 0644 "$METRICS_TMP"
+  mv "$METRICS_TMP" "$METRICS_FILE"
+}
+
+ts() { date '+%Y-%m-%dT%H:%M:%S%z'; }
+log() { echo "[$(ts)] [pbs] $*" | tee -a "$LOG_FILE"; }
+
+get_latest_snapshot() {
+  pvesm list pbs --vmid "$1" 2>/dev/null \
+    | tail -n +2 \
+    | awk '{print $1}' \
+    | sort -t/ -k4 \
+    | tail -1
+}
+
+{% for entry in backup_audit_pbs_vmids %}
+audit_vmid_{{ entry.vmid }}() {
+  vmid={{ entry.vmid }}
+  max_age={{ entry.max_age_hours }}
+  latest=$(get_latest_snapshot "$vmid")
+  if [ -z "$latest" ]; then
+    log "FAIL L0: vmid $vmid — no snapshots in PBS"
+    printf 'homelab_backup_audit_snapshot_age_hours{profile="pbs",vmid="%s"} -1\n' "$vmid" >> "$METRICS_TMP"
+    printf 'homelab_backup_audit_snapshot_success{profile="pbs",vmid="%s"} 0\n' "$vmid" >> "$METRICS_TMP"
+    STATUS=FAIL
+    return
+  fi
+  ts_str=$(printf '%s' "$latest" | sed -n 's#.*/\([0-9T:Z-]*\)$#\1#p')
+  snap_epoch=$(date -d "$ts_str" +%s 2>/dev/null || echo 0)
+  age_hours=$(( (NOW_EPOCH - snap_epoch) / 3600 ))
+  if [ "$age_hours" -gt "$max_age" ]; then
+    log "FAIL L0: vmid $vmid — latest snapshot age ${age_hours}h > ${max_age}h (snapshot: $ts_str)"
+    printf 'homelab_backup_audit_snapshot_success{profile="pbs",vmid="%s"} 0\n' "$vmid" >> "$METRICS_TMP"
+    STATUS=FAIL
+  else
+    log "OK L0: vmid $vmid — latest snapshot age ${age_hours}h"
+    printf 'homelab_backup_audit_snapshot_success{profile="pbs",vmid="%s"} 1\n' "$vmid" >> "$METRICS_TMP"
+  fi
+  printf 'homelab_backup_audit_snapshot_age_hours{profile="pbs",vmid="%s"} %s\n' "$vmid" "$age_hours" >> "$METRICS_TMP"
+}
+audit_vmid_{{ entry.vmid }}
+
+{% endfor %}
+if [ "$STATUS" = "OK" ]; then
+  log "AUDIT PASSED"
+  printf 'homelab_backup_audit_success{profile="pbs"} 1\n' >> "$METRICS_TMP"
+  printf 'homelab_backup_audit_timestamp_seconds{profile="pbs"} %s\n' "$NOW_EPOCH" >> "$METRICS_TMP"
+  publish_metrics
+  exit 0
+else
+  log "AUDIT FAILED"
+  printf 'homelab_backup_audit_success{profile="pbs"} 0\n' >> "$METRICS_TMP"
+  printf 'homelab_backup_audit_timestamp_seconds{profile="pbs"} %s\n' "$NOW_EPOCH" >> "$METRICS_TMP"
+  publish_metrics
+  exit 1
+fi