monitoring/scripts/homelab-audit.sh

@@ -30,6 +30,9 @@ MEM_WARN=85
 ZOMBIE_WARN=1
 SWAP_WARN=512
 
+HOSTS_FILTER="" # comma-separated host list from --hosts; empty = audit all
+JSON_OUTPUT=0   # set to 1 by --json
+
 while [[ $# -gt 0 ]]; do
   case "$1" in
     --output-dir)
@@ -40,6 +43,18 @@ while [[ $# -gt 0 ]]; do
       REPORT_DIR="$2"
       shift 2
       ;;
+    --hosts)
+      if [[ $# -lt 2 ]]; then
+        echo "Error: --hosts requires an argument" >&2
+        exit 1
+      fi
+      HOSTS_FILTER="$2"
+      shift 2
+      ;;
+    --json)
+      JSON_OUTPUT=1
+      shift
+      ;;
     *)
       echo "Unknown option: $1" >&2
       exit 1
@@ -50,6 +65,7 @@ done
 mkdir -p "$REPORT_DIR"
 SSH_FAILURES_LOG="$REPORT_DIR/ssh-failures.log"
 FINDINGS_FILE="$REPORT_DIR/findings.txt"
+AUDITED_HOSTS=() # populated in main; used by generate_summary for per-host counts
 
 # ---------------------------------------------------------------------------
 # Remote collector script
@@ -281,6 +297,18 @@ generate_summary() {
   printf "  Critical      : %d\n" "$crit_count"
   echo "=============================="
 
+  if [[ ${#AUDITED_HOSTS[@]} -gt 0 ]] && ((warn_count + crit_count > 0)); then
+    echo ""
+    printf "  %-30s %8s %8s\n" "Host" "Warnings" "Critical"
+    printf "  %-30s %8s %8s\n" "----" "--------" "--------"
+    for host in "${AUDITED_HOSTS[@]}"; do
+      local hw hc
+      hw=$(grep -c "^WARN  ${host}:" "$FINDINGS_FILE" 2>/dev/null || true)
+      hc=$(grep -c "^CRIT  ${host}:" "$FINDINGS_FILE" 2>/dev/null || true)
+      ((hw + hc > 0)) && printf "  %-30s %8d %8d\n" "$host" "$hw" "$hc"
+    done
+  fi
+
   if ((warn_count + crit_count > 0)); then
     echo ""
     echo "Findings:"
@@ -293,6 +321,9 @@ generate_summary() {
     grep '^SSH_FAILURE' "$SSH_FAILURES_LOG" | awk '{print "  " $2 " (" $3 ")"}'
   fi
 
+  echo ""
+  printf "Total: %d warning(s), %d critical across %d host(s)\n" \
+    "$warn_count" "$crit_count" "$host_count"
   echo ""
   echo "Reports: $REPORT_DIR"
 }
@@ -383,6 +414,69 @@ check_cert_expiry() {
   done
 }
 
+# ---------------------------------------------------------------------------
+# JSON report — writes findings.json to $REPORT_DIR when --json is used
+# ---------------------------------------------------------------------------
+write_json_report() {
+  local host_count="$1"
+  local json_file="$REPORT_DIR/findings.json"
+  local ssh_failure_count=0
+  local warn_count=0
+  local crit_count=0
+
+  [[ -f "$SSH_FAILURES_LOG" ]] &&
+    ssh_failure_count=$(grep -c '^SSH_FAILURE' "$SSH_FAILURES_LOG" 2>/dev/null || true)
+  [[ -f "$FINDINGS_FILE" ]] &&
+    warn_count=$(grep -c '^WARN' "$FINDINGS_FILE" 2>/dev/null || true)
+  [[ -f "$FINDINGS_FILE" ]] &&
+    crit_count=$(grep -c '^CRIT' "$FINDINGS_FILE" 2>/dev/null || true)
+
+  python3 - "$json_file" "$host_count" "$ssh_failure_count" \
+    "$warn_count" "$crit_count" "$FINDINGS_FILE" <<'PYEOF'
+import sys, json, datetime
+
+json_file = sys.argv[1]
+host_count = int(sys.argv[2])
+ssh_failure_count = int(sys.argv[3])
+warn_count = int(sys.argv[4])
+crit_count = int(sys.argv[5])
+findings_file = sys.argv[6]
+
+findings = []
+try:
+    with open(findings_file) as f:
+        for line in f:
+            line = line.strip()
+            if not line:
+                continue
+            parts = line.split(None, 2)
+            if len(parts) < 3:
+                continue
+            severity, host_colon, message = parts[0], parts[1], parts[2]
+            findings.append({
+                "severity": severity,
+                "host": host_colon.rstrip(":"),
+                "message": message,
+            })
+except FileNotFoundError:
+    pass
+
+output = {
+    "timestamp": datetime.datetime.utcnow().isoformat() + "Z",
+    "hosts_audited": host_count,
+    "warnings": warn_count,
+    "critical": crit_count,
+    "ssh_failures": ssh_failure_count,
+    "total_findings": warn_count + crit_count,
+    "findings": findings,
+}
+
+with open(json_file, "w") as f:
+    json.dump(output, f, indent=2)
+print(f"JSON report: {json_file}")
+PYEOF
+}
+
 # ---------------------------------------------------------------------------
 # Main
 # ---------------------------------------------------------------------------
@@ -390,22 +484,46 @@ main() {
   echo "Starting homelab audit — $(date)"
   echo "Report dir: $REPORT_DIR"
   echo "STUCK_PROC_CPU_WARN threshold: ${STUCK_PROC_CPU_WARN}%"
+  [[ -n "$HOSTS_FILTER" ]] && echo "Host filter: $HOSTS_FILTER"
   echo ""
 
   >"$FINDINGS_FILE"
 
-  echo "  Checking Proxmox backup recency..."
-  check_backup_recency
-
   local host_count=0
-  while read -r label addr; do
-    echo "  Auditing $label ($addr)..."
-    parse_and_report "$label" "$addr"
-    check_cert_expiry "$label" "$addr"
-    ((host_count++)) || true
-  done < <(collect_inventory)
+
+  if [[ -n "$HOSTS_FILTER" ]]; then
+    # --hosts mode: audit specified hosts directly, skip Proxmox inventory
+    local check_proxmox=0
+    IFS=',' read -ra filter_hosts <<<"$HOSTS_FILTER"
+    for host in "${filter_hosts[@]}"; do
+      [[ "$host" == "proxmox" ]] && check_proxmox=1
+    done
+    if ((check_proxmox)); then
+      echo "  Checking Proxmox backup recency..."
+      check_backup_recency
+    fi
+    for host in "${filter_hosts[@]}"; do
+      echo "  Auditing $host..."
+      parse_and_report "$host" "$host"
+      check_cert_expiry "$host" "$host"
+      AUDITED_HOSTS+=("$host")
+      ((host_count++)) || true
+    done
+  else
+    echo "  Checking Proxmox backup recency..."
+    check_backup_recency
+
+    while read -r label addr; do
+      echo "  Auditing $label ($addr)..."
+      parse_and_report "$label" "$addr"
+      check_cert_expiry "$label" "$addr"
+      AUDITED_HOSTS+=("$label")
+      ((host_count++)) || true
+    done < <(collect_inventory)
+  fi
 
   generate_summary "$host_count"
+  [[ "$JSON_OUTPUT" -eq 1 ]] && write_json_report "$host_count"
 }
 
 main "$@"