From 4fb4cf99c37b6767ec41d0068a3fc4c5c27b0eea Mon Sep 17 00:00:00 2001
From: sjat <sjat@ziethen.dk>
Date: Thu, 18 Jun 2026 12:28:06 +0200
Subject: [PATCH] fix(integration-vm): boot-id-verified reboot + actionable
 timeouts + inventory guard (review)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 scripts/integration-vm.py | 44 +++++++++++++++++++++++++++++----------
 1 file changed, 33 insertions(+), 11 deletions(-)

diff --git a/scripts/integration-vm.py b/scripts/integration-vm.py
index bc879ee..191cf60 100644
--- a/scripts/integration-vm.py
+++ b/scripts/integration-vm.py
@@ -153,7 +153,7 @@ def net_ensure():
         sh(["virsh", "net-define", str(xml)])
         sh(["virsh", "net-autostart", NET_NAME])
     active = sh(["virsh", "net-info", NET_NAME], capture=True).stdout
-    if "Active:         yes" not in active:
+    if not re.search(r"Active:\s+yes", active):
         sh(["virsh", "net-start", NET_NAME])
 
 
@@ -210,7 +210,8 @@ def wait_for_ip(name, timeout=120):
         if ip:
             return ip
         time.sleep(4)
-    raise SystemExit(f"timed out waiting for {name} to get a DHCP lease")
+    raise SystemExit(f"timed out waiting for {name} to get a DHCP lease — "
+                     "VM left defined; run `integration-vm prune` to remove it")
 
 
 def wait_for_ssh(ip, user, timeout=180):
@@ -222,7 +223,8 @@ def wait_for_ssh(ip, user, timeout=180):
         if r.returncode == 0:
             return
         time.sleep(5)
-    raise SystemExit(f"timed out waiting for SSH to {ip}")
+    raise SystemExit(f"timed out waiting for SSH to {ip} — "
+                     "VM left defined; run `integration-vm prune` to remove it")
 
 
 def _read_current():
@@ -236,11 +238,11 @@ def write_run_inventory(name, ip, groups):
         render_run_hosts(name, ip, "ansible", groups))
     link = RUN_DIR / "group_vars"
     target = REPO_ROOT / "inventories" / "production" / "group_vars"
-    if link.is_symlink() or link.exists():
-        if link.is_symlink():
-            link.unlink()
-    if not link.exists():
-        link.symlink_to(target)
+    if link.is_symlink():
+        link.unlink()
+    elif link.exists():
+        raise SystemExit(f"{link} exists and is not a symlink; remove it manually")
+    link.symlink_to(target)
 
 
 def apply(host, certs):
@@ -261,12 +263,32 @@ def apply(host, certs):
     print(f"applied {host} profile to {name}")
 
 
+def _boot_id(ip, user):
+    r = sh(["ssh", "-o", "StrictHostKeyChecking=no",
+            "-o", "UserKnownHostsFile=/dev/null", "-o", "ConnectTimeout=5",
+            f"{user}@{ip}", "cat /proc/sys/kernel/random/boot_id"],
+           check=False, capture=True)
+    return r.stdout.strip() if r.returncode == 0 else None
+
+
+def wait_for_reboot(ip, user, before_boot_id, timeout=240):
+    """Confirm a REAL reboot: SSH back up AND boot_id changed (not the pre-reboot sshd)."""
+    end = time.time() + timeout
+    while time.time() < end:
+        bid = _boot_id(ip, user)
+        if bid and bid != before_boot_id:
+            return
+        time.sleep(5)
+    raise SystemExit(f"timed out waiting for {ip} to reboot (boot_id unchanged) — "
+                     "VM left defined; run `integration-vm prune` to remove it")
+
+
 def reboot_vm():
     name, ip, _ = _read_current()
+    before = _boot_id(ip, "ansible")
     sh(["virsh", "reboot", name])
-    time.sleep(5)
-    wait_for_ssh(ip, "ansible")
-    print(f"{name} rebooted, SSH back at {ip}")
+    wait_for_reboot(ip, "ansible", before)
+    print(f"{name} rebooted (boot_id changed), SSH back at {ip}")
 
 
 def run_assert(host, certs):