infra: full IaC state after hf-pdocker-01 rebuild (2026-03-08)

Replaces initial Nomad/Consul/Terraform skeleton with current Docker-based infrastructure across all three nodes (hf-pdocker-01, hf-pdocker-02, bart). Key changes: - CLAUDE.md: updated service distribution reflecting hf-pdocker-01 restored - docs/plans/2026-03-08-hf-pdocker-01-rebuild.md: new rebuild plan doc - compose/bart/: ai-agents, guacamole, matrix, media, openvas, smarthome, watchtower - compose/hf-pdocker-02/: traefik, monitoring, adguard, gitea, semaphore, wikijs, unifi, vaultwarden, actual-budget, mcpo, netclaw, trivy, watchtower, n8n - compose/hf-pdocker-01/: frigate, frigate-notify, farm-agent - stacks/: all Swarm stack definitions (monitoring, traefik, smarthome, matrix, guacamole, media, ai-agents, frigate, gitea, semaphore, wikijs, unifi, etc.) - .gitignore: exclude .env credential files and acme.json certs - .env.example: placeholder credential files for all services - .claude/agents/: gitea-backup and other infrastructure agent configs - scripts/: frigate media cleanup and NAS sync scripts Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-08 18:51:25 -05:00
parent b1d111a011
commit de1d9e1d93
102 changed files with 12634 additions and 3 deletions
@@ -0,0 +1,55 @@
+http:
+  address: 0.0.0.0
+  port: 9094
+  alerts-path-prefix: /alerts
+  metrics-path: /metrics
+  metrics-enabled: true
+  # basic-password is required - the app has a hardcoded default basic-username of "alertmanager"
+  # and will exit silently if basic-password is not set
+  basic-password: "alertmanager-webhook"
+
+matrix:
+  # Matrix Synapse is on bart (failover from hf-pdocker-01)
+  homeserver-url: http://192.168.86.167:8008
+  user-id: "@alertbot:hobbs.farm"
+  # Access token stored directly - ${MATRIX_ACCESS_TOKEN} env var syntax is NOT supported
+  # (the app uses yaml parsing, not shell interpolation)
+  access-token: "syt_YWxlcnRib3Q_eOVAYjYKWBZxymfdxhPE_0iYlOZ"
+  room-mapping:
+    notifications: "!jYmqxbzEsvRgKYvwMP:hobbs.farm"
+
+templating:
+  external-url-mapping:
+    # Alertmanager and Prometheus are on hf-pdocker-02 (failover from hf-pdocker-01)
+    "http://alertmanager:9093": "http://192.168.86.100:9093"
+  generator-url-mapping:
+    "http://prometheus:9090": "http://192.168.86.100:9095"
+  computed-values:
+    - values:
+        color: red
+      when-matching-labels:
+        severity: critical
+    - values:
+        color: orange
+      when-matching-labels:
+        severity: warning
+    - values:
+        color: blue
+      when-matching-labels:
+        severity: info
+  # NOTE: Templates use .Alert (singular) not .Alerts (plural)
+  # This application calls the template once per individual alert, not per group
+  firing-template: |
+    <h3>ALERT: {{ .Alert.Labels.alertname }}</h3>
+    <table>
+    <tr><td><b>Instance:</b></td><td>{{ .Alert.Labels.instance }}</td></tr>
+    <tr><td><b>Severity:</b></td><td>{{ .Alert.Labels.severity }}</td></tr>
+    <tr><td><b>Summary:</b></td><td>{{ .Alert.Annotations.summary }}</td></tr>
+    <tr><td><b>Description:</b></td><td>{{ .Alert.Annotations.description }}</td></tr>
+    </table>
+  resolved-template: |
+    <h3>RESOLVED: {{ .Alert.Labels.alertname }}</h3>
+    <table>
+    <tr><td><b>Instance:</b></td><td>{{ .Alert.Labels.instance }}</td></tr>
+    <tr><td><b>Summary:</b></td><td>{{ .Alert.Annotations.summary }}</td></tr>
+    </table>