Racks, notes and to-do, OS support, suggested dependencies, Nginx Proxy Manager and Home Assistant

- Racks page and a network diagram (UniFi tree with servers, printable)
- Notes on servers and devices; To do list shown in Coming up and My work
- Agents report the operating system (Linux 7, Windows 6); end-of-life badge and alert
- Suggested dependencies from where a service is reached
- Nginx Proxy Manager integration: proxy hosts page, certificate and host alerts, suggested checks
- Home Assistant integration: watch chosen entities, history chart, limit and unavailable alerts
- TimeChart gets a "value" scale that fits negatives; docs updated

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
bobbanandClaude Sonnet 5.5 committed 2026-10-20 21:47:56 +02:00
1 parent 68b41b5586
commit 18ceed62e8
77 files changed
+20432 -35

No files matched your search

+32 -1
View File
@@ -17,7 +17,7 @@ set -euo pipefail
# 4 = also reports failed services, disk health (SMART) and ZFS pools, reads pacman, and can update itself when told to
# 5 = also says what the machine is (maker, model, serial number), from the firmware, for the inventory
# 6 = also says what it could not collect and why (no smartctl, no systemd, a package manager that failed ...), so the server can say what to fix
AGENT_VERSION=6
AGENT_VERSION=7
ENV_FILE="${ENV_FILE:-/etc/homelab-manager-agent.env}"
if [[ -f "$ENV_FILE" ]]; then
@@ -356,6 +356,30 @@ collect_hardware() {
'{} | (if $maker != "" then . + {manufacturer: $maker} else . end) | (if $model != "" then . + {model: $model} else . end) | (if $serial != "" then . + {serial: $serial} else . end)') || HARDWARE_JSON="null"
}
# What the machine runs, as /etc/os-release says (OS_RELEASE_FILE is for the tests): the distribution's id and version, so the app can say when that release stops
# being supported. Proxmox VE is Debian underneath, so it is asked by its own command. "null" when there is nothing to say.
collect_os() {
OS_JSON="null"
local file="${OS_RELEASE_FILE:-/etc/os-release}" id="" version="" pretty=""
if [[ -r "$file" ]]; then
id=$(sed -n 's/^ID=//p' "$file" | head -n 1 | tr -d '"' | tr 'A-Z' 'a-z' | head -c 40)
version=$(sed -n 's/^VERSION_ID=//p' "$file" | head -n 1 | tr -d '"' | head -c 40)
pretty=$(sed -n 's/^PRETTY_NAME=//p' "$file" | head -n 1 | tr -d '"' | head -c 80)
fi
if command -v pveversion >/dev/null 2>&1; then
local pve
pve=$(pveversion 2>/dev/null | sed -n 's#^pve-manager/\([0-9]*\.[0-9]*\).*#\1#p' | head -n 1)
if [[ -n "$pve" ]]; then
id="proxmox-ve"
version="$pve"
pretty="Proxmox VE $pve"
fi
fi
[[ -n "$id" ]] || return 0
OS_JSON=$(jq -n -c --arg id "$id" --arg version "$version" --arg name "$pretty" \
'{id: $id} | (if $version != "" then . + {version: $version} else . end) | (if $name != "" then . + {name: $name} else . end)') || OS_JSON="null"
}
# Services (systemd units) that have failed. systemctl is asked the way the timers are, so this works inside the sandbox.
collect_failed_units() {
FAILED_UNITS_JSON="null"
@@ -604,6 +628,8 @@ collect_system_info() {
fi
HARDWARE_JSON="null"
collect_hardware || HARDWARE_JSON="null"
OS_JSON="null"
collect_os || OS_JSON="null"
collect_diagnostics
HEALTH_JSON=$(jq -n -c --argjson failed "$FAILED_UNITS_JSON" --argjson smart "$SMART_JSON" --argjson zfs "$ZFS_JSON" \
'{} | (if $failed != null then . + {failed_units: $failed} else . end) | (if $smart != null then . + {smart: $smart} else . end) | (if $zfs != null then . + {zfs: $zfs} else . end)') || HEALTH_JSON="{}"
@@ -613,6 +639,7 @@ collect_system_info() {
--argjson updates "$UPDATES_JSON" \
--argjson health "$HEALTH_JSON" \
--argjson hardware "$HARDWARE_JSON" \
--argjson os "$OS_JSON" \
--argjson diagnostics "$DIAGNOSTICS_JSON" \
--argjson ip_addresses "$ip_json" \
--argjson listening_ports "$ports_json" \
@@ -631,6 +658,7 @@ collect_system_info() {
updates: $updates,
health: $health,
hardware: $hardware,
os: $os,
diagnostics: $diagnostics
}')
}
@@ -652,6 +680,9 @@ if [[ "$MODE" != "report" ]]; then
echo "ZFS pools (null means there is no zpool here):"
jq . <<<"$ZFS_JSON"
collect_hardware || true
collect_os || true
echo "What it runs (null means there is no os-release to read):"
jq . <<<"$OS_JSON"
echo "What could not be collected (empty means nothing was missed):"
diag_json | jq .
self_update