---
# Full dev/test cluster bring-up, in order (docs/02 sequencing; run AFTER
# `tofu apply` has created and cloud-init has baselined the VMs):
#   k3s HA install -> kube-vip control-plane VIP -> Cilium CNI -> verify readiness
#   -> Flux + SOPS hand-off.
# (kube-vip joined the chain 2026-09-06 — see the note at its import below; it is a
# prerequisite of the CNI now, not a separate operator step.)
#
# TARGET (R-ENV-02): every imported play takes its host pattern from a var that
# defaults to the dev group, so `ansible-playbook playbooks/site.yml` with no extra
# vars is byte-for-byte the dev run it always was. Extra vars are global and reach
# imported playbooks, so the whole chain retargets with three flags:
#   ansible-playbook playbooks/site.yml \
#     -e k3s_hosts=k3s_prod \
#     -e k3s_primary_hosts=k3s_prod_primary \
#     -e k3s_secondary_hosts=k3s_prod_secondary
# DO NOT run that yet — prod is blocked on the disk-layout decision
# (infra/PROD-PROVISIONING.md §2) and the §7 repo blockers, and the operator has ruled
# the prod cluster stays uninitialized until all three nodes are present (§8).
- name: Import - node baseline (packages, kernel modules, Longhorn disk, swap-off)
  ansible.builtin.import_playbook: node-baseline.yml

- name: Import - install k3s HA control plane
  ansible.builtin.import_playbook: k3s.yml

# ADDED 2026-09-07, after the k3s-prod-1 etcd I/O-starvation outage. It must come AFTER
# k3s.yml because it writes an IOWeight drop-in for k3s.service and verifies the value in
# that unit's LIVE cgroup — on a cold build the cgroup does not exist until k3s runs, and
# the role reports that rather than asserting on it. It restarts nothing.
#
# A NO-OP FOR DEV, by design: roles/etcd_io_priority defaults its master switch to false and
# only inventory/group_vars/k3s_prod/vars.yml sets it true. Dev has a dedicated etcd device
# and must not be dragged onto a different I/O scheduler by a shared role.
- name: Import - I/O arbitration for the shared etcd + Longhorn device (prod only)
  ansible.builtin.import_playbook: etcd-io-priority.yml

# ADDED 2026-09-06, AND ITS POSITION IS LOAD-BEARING: kube-vip MUST come up between k3s and
# Cilium. Cilium's k8sServiceHost is now the control-plane VIP (k3s_apiserver_endpoint =
# kube_vip_address) rather than the founder's own node IP, so installing Cilium before the
# VIP is announced would point every agent at an address nothing answers on — the exact
# shape of the 2026-09-01 incident, where agents that could not reach the API server
# deadlocked on a cold cluster.
#
# IT CANNOT COME EARLIER. kube-vip ships as a k3s auto-deploy manifest
# (<data-dir>/server/manifests), so a cluster must exist before it can be applied — hence
# after k3s.yml, not before.
#
# IT DOES NOT NEED THE CNI, which is what makes this ordering possible at all: the kube-vip
# DaemonSet is hostNetwork with KUBERNETES_SERVICE_HOST=127.0.0.1 (roles/kube_vip's template
# explains why), so it reaches the node-local apiserver with no CNI and no kube-proxy, and
# DaemonSet pods carry the default not-ready/network-unavailable tolerations that let them
# schedule onto a still-NotReady node. roles/kube_vip blocks until the VIP actually answers
# on 6443, so cilium.yml below cannot start against a VIP that is not up.
#
# Re-running this against the LIVE dev cluster is a no-op for this play: dev already runs
# kube-vip with the same rendered manifest, and the wait finds the VIP already answering.
- name: Import - float the control-plane HA VIP (kube-vip) BEFORE the CNI dials it
  ansible.builtin.import_playbook: kube-vip.yml

- name: Import - install Cilium CNI
  ansible.builtin.import_playbook: cilium.yml

- name: Import - verify cluster readiness
  ansible.builtin.import_playbook: verify.yml

- name: Import - Flux + SOPS bootstrap hand-off
  ansible.builtin.import_playbook: flux-bootstrap.yml