Compare commits

..
Author SHA1 Message Date
claude-botandClaude Opus 5 7903c81c9a feat(network-policies): let Home Assistant reach the chat model
ci/woodpecker/pr/ci-manifests-test Pipeline was successful
ci/woodpecker/pr/ci-scripts-test Pipeline was successful
ci/woodpecker/pr/pr-review Pipeline was successful
HA 2026.8.3 ships a native `llama_cpp` integration, so an Assist
conversation agent backed by the cluster's own model needs no custom
component — only a path from the HA pod to llama-server, which two
default-deny policies currently block in both directions. Verified from
inside the pod: the call to llama-server.ai.svc.cluster.local:8080 times
out today.

Both grants are scoped to the single pod and port, mirroring the
paperless grant next to them, so neither widens if something else is
placed in the other namespace. llama-embed is deliberately excluded: the
conversation agent uses chat completions only.

Tool calling was verified against the running model before adding this —
the Assist API requires it, and llama.cpp only exposes it for some
builds. b10731 returns finish_reason=tool_calls and parses German
commands into the right arguments without --jinja.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-02 14:18:30 +02:00
8 changed files with 27 additions and 229 deletions
@@ -1,36 +0,0 @@
# Scrapes CrowdSec. Until this landed, nothing did: `up{namespace="crowdsec"}`
# returned zero series and Prometheus held no cs_* metric at all, so the
# detection side of the ingress path was invisible — including whether the
# agents were reading logs and whether any bouncer was pulling decisions.
#
# One monitor for both services. They carry the same shape (a `metrics` port on
# 6060) and differ only in `app`, so a matchExpressions selector keeps this to
# a single object rather than two near-identical ones:
#
# crowdsec-service the LAPI — decisions, bouncer + machine requests
# crowdsec-agent-service the agents — acquisition, parsers, scenarios
#
# The crowdsec-ns CiliumNetworkPolicy already admits the monitoring namespace
# without a port restriction, so no policy change is needed.
#
# `release: kube-prometheus-stack` is what the chart's Prometheus selects on.
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
name: crowdsec
namespace: crowdsec
labels:
app.kubernetes.io/name: crowdsec
release: kube-prometheus-stack
spec:
selector:
matchExpressions:
- key: app
operator: In
values:
- crowdsec-service
- crowdsec-agent-service
endpoints:
- port: metrics
path: /metrics
interval: 30s
@@ -23,7 +23,6 @@ resources:
- prometheusrule-cnpg-backup.yaml
- alloy-servicemonitor.yaml
- cnpg-podmonitors.yaml
- crowdsec-servicemonitor.yaml
- home-assistant-servicemonitor.yaml
- immich-servicemonitor.yaml
- loki-servicemonitor.yaml
@@ -1,163 +0,0 @@
{
"annotations": {"list": []},
"description": "CrowdSec: Erkennung im Cluster, Durchsetzung am NetBird-Edge",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
"links": [],
"panels": [
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"description": "Aktive Ban-Entscheidungen in der LAPI, ganz überwiegend aus den CAPI-Community-Blocklisten. Das ist die Menge, die ein scharfgeschalteter Bouncer durchsetzt.",
"fieldConfig": {
"defaults": {"color": {"mode": "thresholds"}, "mappings": [], "thresholds": {"mode": "absolute", "steps": [{"color": "text", "value": null}]}, "unit": "short"},
"overrides": []
},
"gridPos": {"h": 4, "w": 6, "x": 0, "y": 0},
"id": 1,
"options": {"colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "textMode": "auto"},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "sum(cs_active_decisions)", "refId": "A"}],
"title": "Aktive Decisions",
"type": "stat"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"description": "Bouncer, die in den letzten 10 Minuten Decisions abgeholt haben. Fällt das unter die erwartete Zahl, holt ein Bouncer nichts mehr — und setzt damit einen veralteten Stand durch, ohne dass irgendetwas ausfällt.",
"fieldConfig": {
"defaults": {"color": {"mode": "thresholds"}, "mappings": [], "thresholds": {"mode": "absolute", "steps": [{"color": "red", "value": null}, {"color": "green", "value": 1}]}, "unit": "short"},
"overrides": []
},
"gridPos": {"h": 4, "w": 6, "x": 6, "y": 0},
"id": 2,
"options": {"colorMode": "value", "graphMode": "none", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "textMode": "auto"},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "count(sum by (bouncer) (rate(cs_lapi_bouncer_requests_total[10m])) > 0)", "refId": "A"}],
"title": "Bouncer, die abholen",
"type": "stat"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"description": "Vom Agent gelesene Logzeilen pro Sekunde. Steht das auf 0, detektiert CrowdSec nichts mehr — der häufigste stille Ausfall, weil alles andere weiterläuft.",
"fieldConfig": {
"defaults": {"color": {"mode": "thresholds"}, "mappings": [], "thresholds": {"mode": "absolute", "steps": [{"color": "red", "value": null}, {"color": "green", "value": 0.01}]}, "unit": "reqps"},
"overrides": []
},
"gridPos": {"h": 4, "w": 6, "x": 12, "y": 0},
"id": 3,
"options": {"colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "textMode": "auto"},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "sum(rate(cs_filesource_hits_total[5m]))", "refId": "A"}],
"title": "Gelesene Logzeilen/s",
"type": "stat"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"description": "Szenario-Overflows der letzten 24 h — also lokal erkannte Angriffe, im Gegensatz zu den von CAPI übernommenen.",
"fieldConfig": {
"defaults": {"color": {"mode": "thresholds"}, "mappings": [], "thresholds": {"mode": "absolute", "steps": [{"color": "text", "value": null}]}, "unit": "short"},
"overrides": []
},
"gridPos": {"h": 4, "w": 6, "x": 18, "y": 0},
"id": 4,
"options": {"colorMode": "value", "graphMode": "area", "justifyMode": "auto", "orientation": "auto", "reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "textMode": "auto"},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "sum(increase(cs_bucket_overflowed_total[24h]))", "refId": "A"}],
"title": "Lokale Overflows (24 h)",
"type": "stat"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"description": "Abholrate je Bouncer. Der Firewall-Bouncer auf den Proxies fragt alle 10 s. Die LAPI legt bei jeder neuen beobachteten Client-Adresse einen Eintrag `<name>@<ip>` an, und beobachtet wird die Pod-IP des netbird-ingress-Peers — deshalb erscheint ein logischer Bouncer hier mehrfach und nach Pod-Rollen unter neuen Namen.",
"fieldConfig": {
"defaults": {"color": {"mode": "palette-classic"}, "custom": {"axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "never", "spanNulls": false, "stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}}, "mappings": [], "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]}, "unit": "reqps"},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 4},
"id": 5,
"options": {"legend": {"calcs": ["lastNotNull"], "displayMode": "table", "placement": "right", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "sum by (bouncer) (rate(cs_lapi_bouncer_requests_total[5m]))", "legendFormat": "{{bouncer}}", "refId": "A"}],
"title": "Bouncer-Abholrate",
"type": "timeseries"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"description": "Aktive Decisions nach Grund. `http:scan` dominiert und stammt aus den CAPI-Blocklisten.",
"fieldConfig": {
"defaults": {"color": {"mode": "palette-classic"}, "custom": {"axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 20, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "never", "spanNulls": false, "stacking": {"group": "A", "mode": "normal"}, "thresholdsStyle": {"mode": "off"}}, "mappings": [], "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]}, "unit": "short"},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 12, "y": 4},
"id": 6,
"options": {"legend": {"calcs": ["lastNotNull"], "displayMode": "table", "placement": "right", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "sum by (reason) (cs_active_decisions)", "legendFormat": "{{reason}}", "refId": "A"}],
"title": "Aktive Decisions nach Grund",
"type": "timeseries"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"description": "Welche Szenarien lokal auslösen. Das ist das, was CrowdSec selbst aus den Traefik-Logs erkennt.",
"fieldConfig": {
"defaults": {"color": {"mode": "palette-classic"}, "custom": {"axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "bars", "fillOpacity": 70, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "never", "spanNulls": false, "stacking": {"group": "A", "mode": "normal"}, "thresholdsStyle": {"mode": "off"}}, "mappings": [], "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]}, "unit": "short"},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 12},
"id": 7,
"options": {"legend": {"calcs": ["sum"], "displayMode": "table", "placement": "right", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "sum by (name) (increase(cs_bucket_overflowed_total[1h]))", "legendFormat": "{{name}}", "refId": "A"}],
"title": "Szenario-Overflows (je Stunde)",
"type": "timeseries"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"description": "Geparste gegen nicht geparste Zeilen. Ein Anstieg bei `ko` heißt meist, dass sich ein Logformat geändert hat und der Parser nicht mehr greift — CrowdSec liest dann weiter, erkennt aber nichts mehr.",
"fieldConfig": {
"defaults": {"color": {"mode": "palette-classic"}, "custom": {"axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "never", "spanNulls": false, "stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}}, "mappings": [], "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]}, "unit": "reqps"},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 12, "y": 12},
"id": 8,
"options": {"legend": {"calcs": ["lastNotNull"], "displayMode": "list", "placement": "bottom", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}},
"targets": [
{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "sum(rate(cs_parser_hits_ok_total[5m]))", "legendFormat": "geparst", "refId": "A"},
{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "sum(rate(cs_parser_hits_ko_total[5m]))", "legendFormat": "nicht geparst", "refId": "B"}
],
"title": "Parser",
"type": "timeseries"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"description": "Whitelist-Treffer nach Grund. Nützlich beim Scharfschalten: was hier zählt, wäre sonst ein Kandidat für einen Ban gewesen.",
"fieldConfig": {
"defaults": {"color": {"mode": "palette-classic"}, "custom": {"axisCenteredZero": false, "axisColorMode": "text", "axisLabel": "", "axisPlacement": "auto", "barAlignment": 0, "drawStyle": "line", "fillOpacity": 10, "gradientMode": "none", "hideFrom": {"legend": false, "tooltip": false, "viz": false}, "lineInterpolation": "linear", "lineWidth": 1, "pointSize": 5, "scaleDistribution": {"type": "linear"}, "showPoints": "never", "spanNulls": false, "stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}}, "mappings": [], "thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]}, "unit": "reqps"},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 20},
"id": 9,
"options": {"legend": {"calcs": ["lastNotNull"], "displayMode": "table", "placement": "right", "showLegend": true}, "tooltip": {"mode": "multi", "sort": "desc"}},
"targets": [{"datasource": {"type": "prometheus", "uid": "prometheus"}, "expr": "sum by (reason) (rate(cs_node_wl_hits_ok_total[5m]))", "legendFormat": "{{reason}}", "refId": "A"}],
"title": "Whitelist-Treffer",
"type": "timeseries"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"gridPos": {"h": 8, "w": 12, "x": 12, "y": 20},
"id": 10,
"options": {
"code": {"language": "plaintext", "showLineNumbers": false, "showMiniMap": false},
"content": "## Was dieses Dashboard NICHT zeigt\n\nAlle Panels stammen aus der LAPI und den Agents im Cluster. Die **Bouncer auf proxy-1 und proxy-2 exportieren eigene Metriken**, die hier fehlen:\n\n- `fw_bouncer_active_decisions` — was tatsächlich in den nftables-Sets steht\n- `fw_bouncer_dropped_packets` / `_bytes` — was wirklich verworfen wurde\n- `lapi_requests_total` / `_failures_total` — aus Sicht des Bouncers\n\nSie liegen auf `127.0.0.1:60601` der Proxy-Hosts. Die Hosts sind öffentlich und haben bisher keinerlei Metrik-Pfad; den Port ins Internet zu öffnen, nur um ein Scrape-Ziel zu bekommen, wäre der falsche Tausch.\n\n**Konsequenz:** „Bouncer-Abholrate\" oben zeigt, dass ein Bouncer *fragt* — nicht, dass er die Antwort auch angewandt hat. Solange der Modus `dry-run` ist, wendet er ohnehin nichts an.\n\nEin Scrape-Pfad für die Hosts ist eigene Arbeit und Voraussetzung dafür, dass „was wird wirklich geblockt\" beantwortbar wird."
},
"title": "Blinder Fleck",
"type": "text"
}
],
"refresh": "30s",
"schemaVersion": 38,
"style": "dark",
"tags": ["homelab", "crowdsec", "security"],
"templating": {"list": []},
"time": {"from": "now-6h", "to": "now"},
"timepicker": {},
"timezone": "",
"title": "CrowdSec Overview",
"uid": "crowdsec-overview",
"version": 1,
"weekStart": ""
}
@@ -38,9 +38,6 @@ configMapGenerator:
- name: dashboard-blackbox-overview
files:
- blackbox-overview.json
- name: dashboard-crowdsec-overview
files:
- crowdsec-overview.json
- name: dashboard-disk-health
files:
- disk-health.json
@@ -108,24 +108,6 @@ spec:
lapi:
replicas: 1
service:
# Backend wiring for the public LAPI Ingress (lapi-ingress.yaml).
#
# These belong on the SERVICE, not on the Ingress: under the Kubernetes
# Ingress provider `traefik.ingress.kubernetes.io/service.*` are service
# annotations, and on an Ingress they are silently ignored. The symptom
# is Traefik speaking plaintext to a TLS-only backend, which the LAPI
# answers with "Client sent an HTTP request to an HTTPS server." and a
# 400 — an error that looks like a malformed request rather than a
# scheme mismatch.
#
# With tls.enabled the LAPI serves HTTPS on 8080 and offers no
# plaintext port, so https here is mandatory rather than a hardening
# choice. The ServersTransport carries the chart's own CA, since that
# certificate is self-signed.
annotations:
traefik.ingress.kubernetes.io/service.serversscheme: https
traefik.ingress.kubernetes.io/service.serverstransport: crowdsec-crowdsec-lapi@kubernetescrd
# Far below the chart default, which reserves half a core per LAPI for a
# workload that draws single-digit millicores — enough to leave the
# cluster unschedulable with one node out. Only the reservation shrinks;
@@ -44,8 +44,8 @@ metadata:
namespace: crowdsec
spec:
serverName: crowdsec-service.crowdsec.svc.cluster.local
rootCAs:
- secret: crowdsec-root-secret
rootCAsSecrets:
- crowdsec-root-secret
---
apiVersion: networking.k8s.io/v1
kind: Ingress
@@ -60,12 +60,8 @@ metadata:
cert-manager.io/cluster-issuer: letsencrypt-cluster
# NOT behind the Authentik gate: the client is a daemon with an API key,
# not a browser that can complete an OIDC flow.
#
# The backend scheme and ServersTransport are NOT set here. Under the
# Kubernetes Ingress provider, `traefik.ingress.kubernetes.io/service.*`
# are SERVICE annotations — on an Ingress they are silently ignored, and
# Traefik then talks plaintext to a TLS-only backend. They live on the
# chart's Service instead, via lapi.service.annotations in helmrelease.yaml.
traefik.ingress.kubernetes.io/service.serversscheme: https
traefik.ingress.kubernetes.io/service.serverstransport: crowdsec-crowdsec-lapi@kubernetescrd
spec:
ingressClassName: traefik
rules:
@@ -34,6 +34,17 @@ spec:
- ports:
- port: "8080"
protocol: TCP
# Home Assistant's llama.cpp conversation agent calls the chat model only —
# it has no use for the embedding endpoint, so unlike paperless above this
# grant does not extend to llama-embed.
- fromEndpoints:
- matchLabels:
"k8s:io.kubernetes.pod.namespace": home-assistant
app.kubernetes.io/name: home-assistant
toPorts:
- ports:
- port: "8080"
protocol: TCP
- fromEndpoints:
- matchLabels:
"k8s:io.kubernetes.pod.namespace": monitoring
@@ -167,6 +167,18 @@ spec:
- toEndpoints:
- matchLabels:
"k8s:io.kubernetes.pod.namespace": influxdb
# The cluster's own chat model, for the llama.cpp conversation agent that
# backs Assist. Scoped to the one pod and port rather than the ai namespace
# as a whole, so this grant cannot widen if something else is placed there —
# the embedding endpoint next to it is deliberately not included.
- toEndpoints:
- matchLabels:
"k8s:io.kubernetes.pod.namespace": ai
app.kubernetes.io/name: llama-server
toPorts:
- ports:
- port: "8080"
protocol: TCP
# traefik for east-west OIDC roundtrips that go through the
# public hostname via k8s_gateway.
- toEndpoints: