bootstrap: register a managed realm in the ecosystem on first boot

A managed realm's child core only registered on the hourly telemetry loop,
so it stayed PROVISIONING for up to an hour and raced the ecosystem's
provisioning timeout. Register in the ecosystem right after bootstrap
(best-effort; the telemetry loop remains the retrying fallback).

Author: gmelikov

exordos_core/bootstrap/defaults.py

@@ -22,6 +22,7 @@
 import typing as tp
 import uuid as sys_uuid
 
+import bazooka
 from gcl_sdk.infra.dm import models as infra_models
 from restalchemy.dm import filters as dm_filters
 from restalchemy.storage import exceptions as ra_exceptions
@@ -673,3 +674,36 @@ def set_iam_default_client_secret_var(spec: dict) -> bool:
         spec["iam"]["default_client_secret"],
         c.VAR_IAM_DEFAULT_CLIENT_SECRET_UUID,
     )
+
+
+def register_realm_in_ecosystem(spec: dict[str, tp.Any]) -> bool:
+    """Self-register this realm in the ecosystem right after bootstrap.
+
+    Without this the first registration happens on the telemetry loop
+    (hourly), so a managed realm stays PROVISIONING for up to an hour
+    and races the ecosystem's provisioning timeout. Best-effort: the
+    telemetry loop remains the retrying fallback, so a failure here
+    must not fail the bootstrap.
+    """
+    endpoint = spec.get("ecosystem_endpoint", "")
+    realm_uuid = spec.get("realm_uuid", "")
+    realm_secret = spec.get("realm_secret", "")
+    if not (endpoint and realm_uuid and realm_secret):
+        LOG.info("No realm identity in spec, skipping realm registration")
+        return True
+
+    url = f"{endpoint.rstrip('/')}/api/ecosystem/v1/realms/"
+    try:
+        client = bazooka.Client(default_timeout=30)
+        client.post(
+            url,
+            json={"uuid": realm_uuid, "secret": realm_secret},
+            headers={"Content-Type": "application/json"},
+        )
+        LOG.info("Realm %s registered in ecosystem", realm_uuid)
+    except Exception:
+        LOG.exception(
+            "Failed to register realm in ecosystem (the telemetry "
+            "service will retry hourly)"
+        )
+    return True

exordos_core/cmd/bootstrap.py

@@ -327,6 +327,10 @@ def _set_defaults_vs(spec: dict[str, tp.Any]):
         {"func": bootstrap_defaults.set_realm_secret_var, "args": [spec]},
         {"func": bootstrap_defaults.set_realm_access_token_var, "args": [spec]},
         {"func": bootstrap_defaults.set_realm_refresh_token_var, "args": [spec]},
+        # Register in the ecosystem right away: waiting for the hourly
+        # telemetry loop leaves a managed realm PROVISIONING for up to an
+        # hour, racing the ecosystem's provisioning timeout.
+        {"func": bootstrap_defaults.register_realm_in_ecosystem, "args": [spec]},
         {
             "func": bootstrap_defaults.set_hs256_jwks_encryption_key_var,
             "args": [CONF["iam"].hs256_jwks_encryption_key],