refactor(iac): cluster split — 1 cluster per plane, breakpilot-* naming (#6)
ci / shared (push) Successful in 9s
ci / validate (push) Successful in 4s

3 Orca clusters (breakpilot-edge / breakpilot-control / breakpilot-app), 1 plane each. Single-VM core with Keycloak co-tenant on vm-edge. App cluster gets prod + stage VMs. Manifests reorganized into clusters/<name>/services/; validator now enforces per-cluster node whitelist. Multi-VM rollout gated on legal entity.
This commit was merged in pull request #6.
This commit is contained in:
2026-06-30 20:30:14 +00:00
parent f1c3fd14b9
commit 6be727d404
44 changed files with 428 additions and 125 deletions
+19 -5
View File
@@ -11,7 +11,16 @@ import sys, tomllib, pathlib
root = pathlib.Path(sys.argv[1])
errs = []
count = 0
for p in sorted(root.glob('manifests/**/*.toml')):
# Cluster → expected node names. Each cluster ships its own VM(s); a service's
# placement.node must be one of the cluster's declared VMs.
CLUSTER_NODES = {
'breakpilot-edge': {'vm-edge'},
'breakpilot-control': {'vm-control'},
'breakpilot-app': {'vm-app-prod', 'vm-app-stage'},
}
for p in sorted(root.glob('clusters/*/services/**/*.toml')):
count += 1
try:
data = tomllib.load(open(p, 'rb'))
@@ -22,6 +31,13 @@ for p in sorted(root.glob('manifests/**/*.toml')):
if not svcs:
errs.append(f'{p}: no [[service]] block')
continue
# cluster name = first path component under clusters/
rel = p.relative_to(root)
cluster = rel.parts[1] # clusters/<cluster>/services/...
expected_nodes = CLUSTER_NODES.get(cluster)
if expected_nodes is None:
errs.append(f'{p}: unknown cluster "{cluster}" (expected one of {sorted(CLUSTER_NODES)})')
continue
for svc in svcs:
for required in ('name', 'image'):
if required not in svc:
@@ -32,13 +48,11 @@ for p in sorted(root.glob('manifests/**/*.toml')):
for fb in ('depends_on', 'extra_ports', 'cmd', 'mounts'):
if fb in svc[sub]:
errs.append(f'{p}: "{fb}" nested under [service.{sub}] — must be at [[service]] level')
# placement.node must match parent vm directory
node = (svc.get('placement') or {}).get('node')
vm_dir = p.parent.name
if node and node != vm_dir:
errs.append(f'{p}: placement.node "{node}" mismatches dir "{vm_dir}"')
if not node:
errs.append(f'{p}: missing placement.node')
elif node not in expected_nodes:
errs.append(f'{p}: placement.node "{node}" not valid for cluster "{cluster}" (expected one of {sorted(expected_nodes)})')
mem = (svc.get('resources') or {}).get('memory')
if not mem:
errs.append(f'{p}: missing resources.memory (mandatory per §8 rule 5)')