feat(monitoring): add mana-geocoding + Pelias to prod compose, Prometheus, Grafana, and status.mana.how

Production deployment + observability for the self-hosted geocoding stack:

**docker-compose.macmini.yml**
- New mana-geocoding container (port 3018, internal-only — no traefik
  labels, no Cloudflare route). Uses host.docker.internal to reach the
  Pelias API on the host's pelias compose stack. Dockerfile added under
  services/mana-geocoding/ using the same Bun/Hono pattern as mana-events.

**Prometheus**
- New blackbox-internal job probing mana-geocoding:3018/health, the
  Pelias API on host.docker.internal:4000/v1/status, and Elasticsearch
  at host.docker.internal:9200/_cluster/health. Kept separate from
  blackbox-api which is reserved for public HTTPS endpoints.

**status.mana.how (generate-status-page.sh)**
- Include blackbox-internal in the metric query and add an "Interne
  Dienste" section with its own summary card, right between Infrastruktur
  and GPU Dienste. Summary grid goes from 4 to 5 columns with a
  900px breakpoint.
- friendly_name() now handles http:// URLs and rewrites container-name
  hosts like mana-geocoding:3018/health → "Mana Geocoding",
  host.docker.internal:4000 → "Pelias API",
  host.docker.internal:9200 → "Pelias Elasticsearch".

**Grafana uptime dashboard**
- Add an "Internal" series to the "Alle Dienste — Uptime-Verlauf" panel
- New "Interne Dienste Status" table panel showing per-instance up/down
- New "Geocoding Ø Latenz" stat panel for probe_duration_seconds

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

docker-compose.macmini.yml

@@ -362,6 +362,40 @@ services:
       - "traefik.http.routers.mana-events.tls=true"
       - "traefik.http.services.mana-events.loadbalancer.server.port=3065"
 
+  # ─── Geocoding ───────────────────────────────────────────
+  # Thin Hono wrapper in front of a self-hosted Pelias stack.
+  # Pelias itself (elasticsearch + api + libpostal) runs from a separate
+  # compose file in services/mana-geocoding/pelias/ — see
+  # services/mana-geocoding/CLAUDE.md for the initial import procedure.
+  # Internal-only: no traefik labels, not exposed via Cloudflare.
+  mana-geocoding:
+    build:
+      context: services/mana-geocoding
+      dockerfile: Dockerfile
+    image: mana-geocoding:local
+    container_name: mana-geocoding
+    restart: always
+    mem_limit: 128m
+    # Pelias runs on host network via its own compose, so the wrapper
+    # reaches it via host.docker.internal (Pelias API at :4000).
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    environment:
+      TZ: Europe/Berlin
+      PORT: 3018
+      PELIAS_API_URL: http://host.docker.internal:4000/v1
+      CORS_ORIGINS: https://mana.how,http://localhost:5173
+      CACHE_MAX_ENTRIES: "5000"
+      CACHE_TTL_MS: "86400000"
+    ports:
+      - "3018:3018"
+    healthcheck:
+      test: ["CMD", "bun", "-e", "fetch('http://127.0.0.1:3018/health').then(r=>process.exit(r.ok?0:1)).catch(()=>process.exit(1))"]
+      interval: 120s
+      timeout: 10s
+      retries: 3
+      start_period: 15s
+
   mana-user:
     build:
       context: services/mana-user

docker/prometheus/prometheus.yml

@@ -283,6 +283,27 @@ scrape_configs:
       - target_label: __address__
         replacement: blackbox-exporter:9115
 
+  # Internal-only services (not exposed via Cloudflare).
+  # Probed over the Docker network so the blackbox exporter reaches
+  # them by container name.
+  - job_name: 'blackbox-internal'
+    metrics_path: /probe
+    params:
+      module: [http_2xx]
+    static_configs:
+      - targets:
+          - http://mana-geocoding:3018/health
+          # Pelias stack runs on host network, reached via host gateway
+          - http://host.docker.internal:4000/v1/status
+          - http://host.docker.internal:9200/_cluster/health
+    relabel_configs:
+      - source_labels: [__address__]
+        target_label: __param_target
+      - source_labels: [__param_target]
+        target_label: instance
+      - target_label: __address__
+        replacement: blackbox-exporter:9115
+
   # Infrastructure & Monitoring Tools
   - job_name: 'blackbox-infra'
     metrics_path: /probe

scripts/generate-status-page.sh

@@ -25,8 +25,8 @@ fetch_metric() {
     2>/dev/null || echo '{"status":"error","data":{"result":[]}}'
 }
 
-SUCCESS_JSON="$(fetch_metric 'probe_success{job=~"blackbox-web|blackbox-api|blackbox-infra|blackbox-gpu"}')"
+SUCCESS_JSON="$(fetch_metric 'probe_success{job=~"blackbox-web|blackbox-api|blackbox-infra|blackbox-internal|blackbox-gpu"}')"
-DURATION_JSON="$(fetch_metric 'probe_duration_seconds{job=~"blackbox-web|blackbox-api|blackbox-infra|blackbox-gpu"}')"
+DURATION_JSON="$(fetch_metric 'probe_duration_seconds{job=~"blackbox-web|blackbox-api|blackbox-infra|blackbox-internal|blackbox-gpu"}')"
 
 # ── Hilfsfunktionen ─────────────────────────────────────────────────────────
 
@@ -59,10 +59,20 @@ get_instances() {
 # Freundlicher Name aus URL
 friendly_name() {
   url="$1"
-  # Entferne https://
+  # Entferne https:// oder http://
   name="${url#https://}"
-  # Route-basierte URLs: mana.how/chat → Chat
+  name="${name#http://}"
+  # Interne Services (Docker-Netz): mana-geocoding:3018/health → Mana Geocoding
   case "$name" in
+    mana-geocoding:*)
+      name="Mana Geocoding"
+      ;;
+    host.docker.internal:4000*)
+      name="Pelias API"
+      ;;
+    host.docker.internal:9200*)
+      name="Pelias Elasticsearch"
+      ;;
     mana.how/*)
       name="${name#mana.how/}"
       ;;
@@ -71,8 +81,10 @@ friendly_name() {
       name="${name%.mana.how}"
       ;;
   esac
-  # Entferne /health suffix
+  # Entferne /health, /_cluster/health, /v1/status suffixe
   name="${name%/health}"
+  name="${name%/_cluster/health}"
+  name="${name%/v1/status}"
   # mana.how (ohne Route) → Mana
   [ "$name" = "mana.how" ] && name="Mana"
   # Erster Buchstabe groß (POSIX-kompatibel)
@@ -131,11 +143,12 @@ render_rows() {
 
 web_up="$(count_up blackbox-web)";   web_total="$(count_total blackbox-web)"
 api_up="$(count_up blackbox-api)";   api_total="$(count_total blackbox-api)"
+internal_up="$(count_up blackbox-internal)"; internal_total="$(count_total blackbox-internal)"
 infra_up="$(count_up blackbox-infra)"; infra_total="$(count_total blackbox-infra)"
 gpu_up="$(count_up blackbox-gpu)";   gpu_total="$(count_total blackbox-gpu)"
 
-total_up=$(( web_up + api_up + infra_up + gpu_up ))
+total_up=$(( web_up + api_up + internal_up + infra_up + gpu_up ))
-total_all=$(( web_total + api_total + infra_total + gpu_total ))
+total_all=$(( web_total + api_total + internal_total + infra_total + gpu_total ))
 total_down=$(( total_all - total_up ))
 
 if [ "$total_down" -eq 0 ] && [ "$total_all" -gt 0 ]; then
@@ -276,10 +289,11 @@ cat > "${OUTPUT}.tmp" << HTMLEOF
     /* ── Summary Row ── */
     .summary {
       display: grid;
-      grid-template-columns: repeat(4, 1fr);
+      grid-template-columns: repeat(5, 1fr);
       gap: 12px;
       margin-bottom: 32px;
     }
+    @media (max-width: 900px) { .summary { grid-template-columns: repeat(3, 1fr); } }
     @media (max-width: 600px) { .summary { grid-template-columns: repeat(2, 1fr); } }
 
     .summary-card {
@@ -385,6 +399,10 @@ cat > "${OUTPUT}.tmp" << HTMLEOF
       <div class="count $([ "$api_up" -eq "$api_total" ] && echo green || echo yellow)">${api_up}/${api_total}</div>
       <div class="label">API Backends</div>
     </div>
+    <div class="summary-card">
+      <div class="count $([ "$internal_up" -eq "$internal_total" ] && echo green || echo yellow)">${internal_up}/${internal_total}</div>
+      <div class="label">Interne</div>
+    </div>
     <div class="summary-card">
       <div class="count $([ "$infra_up" -eq "$infra_total" ] && echo green || echo yellow)">${infra_up}/${infra_total}</div>
       <div class="label">Infrastruktur</div>
@@ -415,6 +433,16 @@ $(render_rows blackbox-api)
     </table>
   </div>
 
+  <div class="section">
+    <div class="section-header">
+      <h2>Interne Dienste</h2>
+      <span class="fraction">${internal_up} von ${internal_total} online</span>
+    </div>
+    <table>
+$(render_rows blackbox-internal)
+    </table>
+  </div>
+
   <div class="section">
     <div class="section-header">
       <h2>Infrastruktur</h2>

services/mana-geocoding/Dockerfile

@@ -0,0 +1,16 @@
+FROM oven/bun:1 AS production
+
+WORKDIR /app
+
+COPY package.json bun.lock* ./
+RUN bun install --frozen-lockfile 2>/dev/null || bun install
+
+COPY src ./src
+COPY tsconfig.json ./
+
+EXPOSE 3018
+
+HEALTHCHECK --interval=30s --timeout=10s --start-period=10s --retries=3 \
+  CMD bun -e "fetch('http://localhost:3018/health').then(r => process.exit(r.ok ? 0 : 1)).catch(() => process.exit(1))"
+
+CMD ["bun", "run", "src/index.ts"]