---
# Runbooks tier — reconciled by its OWN non-gating post-platform Flux Kustomization
# (clusters/base/runbooks.yaml, dependsOn platform-config, wait:false). Same placement and rationale as
# platform/homepage: a leaf web server must never sit in the gating `platform` tier, where a UI's
# unhealth once stalled the whole chain (DECISIONS-LOG: "Headlamp gating stall").
#
# WHY THE MANIFESTS LIVE HERE, ALONGSIDE THE DOCS, RATHER THAN IN platform/runbooks/.
# The markdown is the source of truth and the task is to serve it verbatim, which means the ConfigMap must
# be GENERATED from these files — there must not be a second hand-maintained copy of 34 documents that can
# drift from the originals. `configMapGenerator` does that, and its `files:` paths are resolved relative to
# THIS directory. A `platform/runbooks/kustomization.yaml` would therefore need `../../runbooks/<name>.md`,
# which depends on kustomize load restrictions being relaxed — true for Flux's kustomize-controller,
# refused by a plain `kustomize build`, and so a divergence between what the gate can verify and what the
# cluster does. Making this directory the Flux path removes the question entirely: no `../`, identical
# behaviour locally and in-cluster, one copy of every document. The serving manifests are tucked under
# `serving/` so `runbooks/*.md` stays exactly the flat set of pages the URLs name.
apiVersion: kustomize.config.k8s.io/v1beta1
kind: Kustomization
namespace: runbooks
resources:
  - serving/namespace.yaml
  - serving/nginx-config.yaml
  - serving/deployment.yaml
  - serving/service.yaml
  # default-deny baseline + Cilium gateway-ingress allow (DNS-only egress from the baseline).
  - serving/networkpolicy.yaml
  - serving/httproute.yaml   # apex `/runbooks` prefix (binds the Gateway `https-apex` listener)

configMapGenerator:
  # ONE ConfigMap holding every runbook, keyed by the EXACT name the alert annotations use.
  #
  # THE KEYS ARE EXTENSIONLESS ON PURPOSE. The annotations are `https://${BASE_DOMAIN}/runbooks/<name>`
  # with NO `.md`, and this repo must not change them (they are spread across four alerts.yaml files that
  # other work is editing). `<key>=<file>` maps `node-down.md` on disk to the key `node-down`, the volume
  # mount turns each key into a file under the nginx root, and `/runbooks/node-down` becomes a plain static
  # lookup — no rewrite rule, nothing to get subtly wrong at 3am. Drop the `<key>=` and every key would
  # carry `.md`, so every alert link would 404 while this file still looked correct.
  #
  # The generated name carries kustomize's content hash, so editing any runbook rolls the server
  # automatically and a stale projection is impossible.
  #
  # ADDING A RUNBOOK: add the file AND its line here. The L0 check
  # conformance/tests/l0-static/alert-runbooks-resolvable asserts both halves, because a file in git with
  # no generator entry is reviewed, merged, apparently done — and still a 404 in the cluster.
  - name: runbooks-content
    options:
      labels:
        app.kubernetes.io/name: runbooks
    files:
      # The index, served at /runbooks/ (nginx `try_files /runbooks/README`).
      - README=README.md
      - backup-failure=backup-failure.md
      - backup-missed=backup-missed.md
      - backup-partial=backup-partial.md
      - cdi-import-stuck=cdi-import-stuck.md
      - cert-expiry=cert-expiry.md
      - cert-issuance=cert-issuance.md
      - cnpg-archiving=cnpg-archiving.md
      - cnpg-backup-missed=cnpg-backup-missed.md
      - cnpg-exporter=cnpg-exporter.md
      - cnpg-primary-spread=cnpg-primary-spread.md
      - cnpg-wal-growth=cnpg-wal-growth.md
      - denied-flows=denied-flows.md
      - flux-reconcile=flux-reconcile.md
      - flux-suspended=flux-suspended.md
      - image-automation=image-automation.md
      - image-policy-stalled=image-policy-stalled.md
      - keycloak-client-secrets=keycloak-client-secrets.md
      - keycloak-db=keycloak-db.md
      - keycloak-down=keycloak-down.md
      - kubevirt-control-plane=kubevirt-control-plane.md
      - kubevirt-crashloop=kubevirt-crashloop.md
      - kubevirt-launch-failed=kubevirt-launch-failed.md
      - longhorn-capacity=longhorn-capacity.md
      - longhorn-degraded=longhorn-degraded.md
      - longhorn-faulted=longhorn-faulted.md
      - monitoring-capacity=monitoring-capacity.md
      - node-cpu=node-cpu.md
      - node-disk=node-disk.md
      - node-down=node-down.md
      - node-io=node-io.md
      - node-memory=node-memory.md
      - node-memory-swap=node-memory-swap.md
      # Operator procedure, not an alert page (no alert links to it — the
      # alert-runbooks-resolvable check treats that as advisory). It is served
      # because the 4-minute plex.tv claim window is not a thing to go looking
      # for in git: /runbooks/plex-claim has to resolve the moment it is needed.
      - plex-claim=plex-claim.md
      - pvc-capacity=pvc-capacity.md
      - targets-down=targets-down.md
      - update-rollback=update-rollback.md
      - vpn-down=vpn-down.md
      - vpn-egress-stale=vpn-egress-stale.md