From 80af9b1fd0ac4978eb0904a784d4d703e571566c Mon Sep 17 00:00:00 2001
From: rock <locartrock@gmail.com>
Date: Tue, 27 Oct 2026 00:11:50 -0700
Subject: [PATCH] feat(iam): provision and activate the SMTP provider

ZITADEL sends verification codes and password resets by SMTP only, and nothing
delivered until the instance had an *active* SMTP config. Two traps, both now
handled here instead of by hand:

- POST /admin/v1/smtp creates the config INACTIVE (state 3). An inactive config
  makes GET /admin/v1/smtp answer 404 "SMTP configuration not found", so the API
  reports success while every send is dropped. The _activate call is mandatory.
- The target is the in-cluster smtp-gotify relay, which forwards to Gotify.

The phase is idempotent: an active config short-circuits and only logs.

Also fix the role-exists check: ZITADEL returns `key`, not `roleKey`, so the set
was always empty and every re-run died on the first 409 "Role already exists".

Verified: `zitadel-provision.py apply` now completes, reporting
`smtp : already active`, `roles : 21 ensured`, `oidc apps : 11 ensured`.
A resend then produced Gotify message 1185 ("Verify email, Code ZVYLQG") and
submitting that code set verified_email for user riotpiao.
---
 scripts/iam/zitadel-provision.py | 52 +++++++++++++++++++++++++++++++-
 1 file changed, 51 insertions(+), 1 deletion(-)

diff --git a/scripts/iam/zitadel-provision.py b/scripts/iam/zitadel-provision.py
index eca1409..4b9c1ef 100755
--- a/scripts/iam/zitadel-provision.py
+++ b/scripts/iam/zitadel-provision.py
@@ -49,6 +49,10 @@ CONF_DIR = Path(os.environ.get("ZITADEL_CONF_DIR", Path.home() / ".config" / "zi
 STATE_FILE = CONF_DIR / "state.json"
 NAMESPACE = os.environ.get("ZITADEL_NAMESPACE", "iam")
 BASE_URL = os.environ.get("ZITADEL_BASE_URL", "https://zitadel.riotpiao.com")
+# Notification delivery target: the in-cluster SMTP -> Gotify relay.
+SMTP_HOST = os.environ.get("ZITADEL_SMTP_HOST", "smtp-gotify.iam.svc.cluster.local:2525")
+SMTP_FROM = os.environ.get("ZITADEL_SMTP_FROM", "zitadel@riotpiao.com")
+SMTP_FROM_NAME = os.environ.get("ZITADEL_SMTP_FROM_NAME", "ZITADEL")
 
 # ── desired ZITADEL state ──────────────────────────────────────────────────
 # Declared here, applied through the API by the `apply` phase. This replaces the
@@ -319,7 +323,10 @@ def _ensure_builtin_login(token: str) -> None:
 
 def _ensure_roles(token: str, project_id: str, roles: dict[str, str]) -> None:
     code, d = _api("POST", f"/management/v1/projects/{project_id}/roles/_search", token, {})
-    have = {r.get("roleKey") for r in (d.get("result") or [])}
+    # ZITADEL answers with `key`, not `roleKey`. Reading the wrong field left
+    # this set empty, so every re-run tried to recreate existing roles and died
+    # on the first 409.
+    have = {(r.get("key") or r.get("roleKey")) for r in (d.get("result") or [])}
     for key, display in roles.items():
         if key in have:
             continue
@@ -368,6 +375,48 @@ def _ensure_oidc_apps(token: str, project_id: str, apps: dict[str, dict]) -> tup
     return ids, secrets
 
 
+def _ensure_smtp(token: str) -> str:
+    """Make sure the instance has one active SMTP provider.
+
+    ZITADEL sends verification codes and password resets by SMTP only. A
+    freshly added config is created INACTIVE (state 3), and an inactive config
+    makes GetSMTPConfig answer 404 "SMTP configuration not found", so nothing is
+    ever delivered. Activating it is what enables sending: after the activate
+    call the same GET returns the config and a resend reaches the relay.
+
+    This is instance state in the database, not a values key, so it must be
+    applied explicitly. The host points at the in-cluster smtp-gotify relay
+    (k8s/infra/iam/smtp-gotify.yaml), which forwards to Gotify.
+    """
+    code, d = _api("GET", "/admin/v1/smtp", token)
+    if code == 200 and (d.get("smtpConfig") or {}).get("id"):
+        smtp_id = d["smtpConfig"]["id"]
+        print(f"smtp      : already active ({smtp_id})")
+        return smtp_id
+
+    code, d = _api("POST", "/admin/v1/smtp", token, {
+        "senderAddress": SMTP_FROM,
+        "senderName": SMTP_FROM_NAME,
+        "host": SMTP_HOST,
+        "tls": False,
+    })
+    if code not in (200, 201) or not d.get("id"):
+        die(f"create smtp config failed: {code} {d}")
+    smtp_id = d["id"]
+
+    # The activate call is mandatory: without it the config stays inactive and
+    # every send is dropped while the API still reports success.
+    code, d = _api("POST", f"/admin/v1/smtp/{smtp_id}/_activate", token, {})
+    if code not in (200, 201):
+        die(f"activate smtp config {smtp_id} failed: {code} {d}")
+
+    code, d = _api("GET", "/admin/v1/smtp", token)
+    if code != 200 or not (d.get("smtpConfig") or {}).get("id"):
+        die(f"smtp config {smtp_id} still not visible after activate: {code} {d}")
+    print(f"smtp      : active ({smtp_id}) -> {SMTP_HOST}")
+    return smtp_id
+
+
 def phase_apply(_args: argparse.Namespace) -> int:
     """Declare the ZITADEL objects through the API. No Terraform, no state drift."""
     token = bootstrap_token()
@@ -375,6 +424,7 @@ def phase_apply(_args: argparse.Namespace) -> int:
         die("no iam-admin PAT — run the keys phase first")
 
     _ensure_builtin_login(token)
+    _ensure_smtp(token)
     project_id = _ensure_project(token, PROJECT_NAME)
     print(f"project   : {PROJECT_NAME} ({project_id})")
     _ensure_roles(token, project_id, ROLES)