knowledge: relocate metis doc; monitoring: add cpu high alert

.gitignore

@@ -4,3 +4,5 @@
 !services/comms/knowledge/**/*.md
 __pycache__/
 *.py[cod]
+.pytest_cache
+.venv

knowledge/software/metis.md

@@ -0,0 +1,26 @@
+# Metis (node recovery)
+
+## Node classes (current map)
+- rpi5 Ubuntu workers: titan-04,05,06,07,08,09,10,11,20,21 (Ubuntu 24.04.3, k3s agent)
+- rpi5 control-plane: titan-0a/0b/0c (Ubuntu 24.04.1, k3s server, control-plane taint)
+- rpi4 Armbian longhorn: titan-13/15/17/19 (Armbian 6.6.x, k3s agent, longhorn disks)
+- rpi4 Armbian standard: titan-12/14/18 (Armbian 6.6.x, k3s agent)
+- amd64 agents: titan-22/24 (Debian 13, k3s agent)
+- External/non-cluster: tethys, titan-db, titan-jh, oceanus/titan-23, future titan-20/21 (when added), plus any newcomers.
+
+## Longhorn disk UUIDs (critical nodes)
+- titan-13: /mnt/astreae UUID=6031fa8b-f28c-45c3-b7bc-6133300e07c6 (ext4); /mnt/asteria UUID=cbd4989d-62b5-4741-8b2a-28fdae259cae (ext4)
+- titan-15: /mnt/astreae UUID=f3362f14-5822-449f-944b-ac570b5cd615 (ext4); /mnt/asteria UUID=9c5316e6-f847-4884-b502-11f2d0d15d6f (ext4)
+- titan-17: /mnt/astreae UUID=1fecdade-08b0-49cb-9ae3-be6c188b0a96 (ext4); /mnt/asteria UUID=2fe9f613-d372-47ca-b84f-82084e4edda0 (ext4)
+- titan-19: /mnt/astreae UUID=4890abb9-dda2-4f4f-9c0f-081ee82849cf (ext4); /mnt/asteria UUID=2b4ea28d-b0e6-4fa3-841b-cd7067ae9153 (ext4)
+
+## Metis repo (~/Development/metis)
+- CLI skeleton in Go (`cmd/metis`), inventory loader (`pkg/inventory`), plan builder (`pkg/plan`).
+- `inventory.example.yaml` shows expected schema (classes + per-node overlay, Longhorn disks, labels, taints).
+- `AGENTS.md` in repo is untracked and holds raw notes.
+
+## Next implementation steps
+- Add per-class golden image refs and checksums (Harbor or file://) when ready.
+- Implement burn execution: download with checksum, write via dd/etcher-equivalent, mount boot/root to inject hostname/IP/k3s tokens/labels/taints, journald/GC drop-ins, and Longhorn fstab entries. Add Windows writer (diskpart + wmic) and Linux writer (dd + sgdisk) paths.
+- Add Keycloak/SSH bootstrap: ensure ssh user, authorized keys, and k3s token/URL injection for agents; control-plane restore path with etcd snapshot selection.
+- Add per-host inventory entries for tethys, titan-db, titan-jh, oceanus/titan-23, future 20/21 once audited.

services/monitoring/grafana-alerting-config.yaml

@@ -125,6 +125,58 @@ data:
               summary: "{{ $labels.instance }} rootfs grew >1Gi in the last hour"
             labels:
               severity: warning
+      - orgId: 1
+        name: atlas-cpu
+        folder: Alerts
+        interval: 1m
+        rules:
+          - uid: cpu-high-10m
+            title: "Node CPU high (>90% for 10m)"
+            condition: C
+            data:
+              - refId: A
+                relativeTimeRange:
+                  from: 600
+                  to: 0
+                datasourceUid: atlas-vm
+                model:
+                  intervalMs: 60000
+                  maxDataPoints: 43200
+                  expr: avg_over_time((1 - avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m]))) * 100)[10m:1m]
+                  legendFormat: '{{instance}}'
+                  datasource:
+                    type: prometheus
+                    uid: atlas-vm
+              - refId: B
+                datasourceUid: __expr__
+                model:
+                  expression: A
+                  intervalMs: 60000
+                  maxDataPoints: 43200
+                  reducer: last
+                  type: reduce
+              - refId: C
+                datasourceUid: __expr__
+                model:
+                  expression: B
+                  intervalMs: 60000
+                  maxDataPoints: 43200
+                  type: threshold
+                  conditions:
+                    - evaluator:
+                        params: [90]
+                        type: gt
+                      operator:
+                        type: and
+                      reducer:
+                        type: last
+                      type: query
+            noDataState: NoData
+            execErrState: Error
+            annotations:
+              summary: "{{ $labels.instance }} CPU >90% for 10m"
+            labels:
+              severity: warning
       - orgId: 1
         name: maintenance
         folder: Alerts