feat(server): add in-flight certificate validity watchdog and dynamic SSLContext reloading in Server.py

src/Server.py

@@ -322,6 +322,72 @@ def init_mtls_server_context(cert_dir: str = "certs") -> ssl.SSLContext:
     return ctx
 
 
+def reload_mtls_context(ssl_ctx: ssl.SSLContext, cert_dir: str = "certs"):
+    """
+    Dynamically reloads server certificate chain and Root CA in an active SSLContext.
+    Allows in-flight TLS certificate rotation without dropping the listening socket.
+    """
+    ca_file = os.path.join(cert_dir, "ca.crt")
+    srv_cert = os.path.join(cert_dir, "server.crt")
+    srv_key = os.path.join(cert_dir, "server.key")
+
+    ssl_ctx.load_cert_chain(certfile=srv_cert, keyfile=srv_key)
+    ssl_ctx.load_verify_locations(cafile=ca_file)
+
+
+def check_and_rotate_server_certs(
+    cert_dir: str = "certs",
+    hostnames: Optional[List[str]] = None,
+    threshold_days: int = 30
+) -> bool:
+    """
+    Checks if Root CA or server TLS certificate are expiring within threshold_days.
+    If so, regenerates them, dynamically reloads the active SSLContext in-place,
+    and updates the server's in-memory CA reference so future enrollments use the new CA.
+    Returns True if renewed/reloaded, False otherwise.
+    """
+    ca_renewed, srv_renewed = enrollment.check_and_renew_hub_pki(
+        cert_dir=cert_dir,
+        hostnames=hostnames,
+        threshold_days=threshold_days
+    )
+    if ca_renewed or srv_renewed:
+        print(f"[!] Server Hub PKI certificates renewed (CA renewed: {ca_renewed}, Server cert renewed: {srv_renewed}).")
+        ca_cert, ca_key, ca_pem, ca_key_pem = enrollment.generate_ca_if_needed(cert_dir=cert_dir, force_renew=False)
+        SERVER_STATE["ca_cert"] = ca_cert
+        SERVER_STATE["ca_key"] = ca_key
+        SERVER_STATE["ca_cert_pem"] = ca_pem
+
+        ssl_ctx = SERVER_STATE.get("ssl_ctx")
+        if ssl_ctx is not None:
+            try:
+                reload_mtls_context(ssl_ctx, cert_dir=cert_dir)
+                print("[+] In-flight mTLS SSLContext successfully reloaded with updated certificates.")
+            except Exception as e:
+                print(f"[!] Failed to reload in-flight SSLContext: {e}")
+        return True
+    return False
+
+
+async def cert_validity_watchdog(interval_seconds: int = 43200, threshold_days: int = 30):
+    """
+    Periodically checks the validity of Hub Root CA and Server TLS certificates (default every 12 hours).
+    Triggers in-flight renewal and dynamic context reloading if expiration is within threshold_days.
+    """
+    config = SERVER_STATE.get("config", {})
+    cert_dir = config.get("cert_dir", "certs")
+    hostnames = [config.get("tcp_host", "0.0.0.0"), "127.0.0.1", "localhost"]
+    while True:
+        try:
+            await asyncio.sleep(interval_seconds)
+            check_and_rotate_server_certs(cert_dir=cert_dir, hostnames=hostnames, threshold_days=threshold_days)
+        except asyncio.CancelledError:
+            break
+        except Exception as e:
+            print(f"[!] Exception in cert_validity_watchdog: {e}")
+
+
+
 async def handle_socket_client(reader: asyncio.StreamReader, writer: asyncio.StreamWriter):
     """
     mTLS TCP socket handler.
@@ -631,10 +697,20 @@ async def run_server():
     print(f"[*] Hermes Reporting API available at http://{hermes_host}:{hermes_port}/api/hermes/report")
     print(f"[*] Client Enrollment API available at http://{hermes_host}:{hermes_port}/api/client/enroll")
 
-    await asyncio.gather(
-        tcp_server.serve_forever(),
-        uv_server.serve()
-    )
+    watchdog_task = asyncio.create_task(cert_validity_watchdog())
+
+    try:
+        await asyncio.gather(
+            tcp_server.serve_forever(),
+            uv_server.serve(),
+            watchdog_task
+        )
+    finally:
+        watchdog_task.cancel()
+        try:
+            await watchdog_task
+        except asyncio.CancelledError:
+            pass
 
 
 def main():