Add hostname parsers + find_drift() to capacity-scan.py

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

scripts/capacity-scan.py

@@ -78,3 +78,33 @@ def compute_rollup(node_rows, workload_rows):
             or node["alloc_disk_gb"] > node["disk_gb"]
         )
     return nodes
+
+
+def parse_tf_hostnames(tf_json):
+    """Hostnames from `terraform output -json` (the `vms` map keys)."""
+    data = json.loads(tf_json)
+    return set(data.get("vms", {}).get("value", {}).keys())
+
+
+def parse_inventory_hostnames(inv_json):
+    """Hostnames from `ansible-inventory --list` (_meta.hostvars keys)."""
+    data = json.loads(inv_json)
+    return set(data.get("_meta", {}).get("hostvars", {}).keys())
+
+
+def find_drift(workload_rows, known_hostnames):
+    """Warn when reference.md workloads and live hostnames disagree. Silent when
+    no hostnames are known (pre-provisioning) — nothing to compare against."""
+    warnings = []
+    declared = {w["workload"] for w in workload_rows}
+    if not known_hostnames:
+        return warnings
+    for name in sorted(declared - known_hostnames):
+        warnings.append(
+            f"reference.md lists '{name}' but no Terraform/inventory host declares it"
+        )
+    for name in sorted(known_hostnames - declared):
+        warnings.append(
+            f"host '{name}' exists in Terraform/inventory but is absent from reference.md"
+        )
+    return warnings

tests/test_capacity_scan.py

@@ -58,3 +58,25 @@ def test_compute_rollup_ignores_workloads_on_unknown_nodes():
         [{"workload": "ghost", "node": "nope", "cores": "1", "ram_mb": "512", "disk_gb": "10"}],
     )
     assert nodes["pve0"]["alloc_cores"] == 0
+
+
+def test_parse_tf_hostnames_reads_vms_value_keys():
+    tf_json = '{"vms": {"value": {"dns1": {"ip": "10.20.0.10", "group": "docker_hosts"}}}}'
+    assert cs.parse_tf_hostnames(tf_json) == {"dns1"}
+
+
+def test_parse_inventory_hostnames_reads_meta_hostvars():
+    inv_json = '{"_meta": {"hostvars": {"dns1": {}, "proxy": {}}}}'
+    assert cs.parse_inventory_hostnames(inv_json) == {"dns1", "proxy"}
+
+
+def test_find_drift_reports_both_directions():
+    workload_rows = [{"workload": "dns1", "node": "pve0", "cores": "1", "ram_mb": "512", "disk_gb": "10"}]
+    warnings = cs.find_drift(workload_rows, {"proxy"})
+    assert any("dns1" in w and "no Terraform" in w for w in warnings)
+    assert any("proxy" in w and "absent from reference.md" in w for w in warnings)
+
+
+def test_find_drift_silent_when_no_hostnames_known():
+    workload_rows = [{"workload": "dns1", "node": "pve0", "cores": "1", "ram_mb": "512", "disk_gb": "10"}]
+    assert cs.find_drift(workload_rows, set()) == []