prole/installer/milestone.py
chrisfu 5618b662dd Remove prole-db-manager; simplify deployment via prole-authority; fix pg18 downgrade & cluster name
Summary:
Removed the prole-db-manager microservice and simplified deployment to use
prole-authority as the internal management and authorization point. Fixed two
blocking bugs that prevented silent install from completing on knoe-dev-cluster.

Removed: prole-db-manager
- Deleted db-manager-deployment.yaml and db-manager-service.yaml from opentofu manifests
- Deleted src/db-manager/ (Dockerfile, server.js, package.json, tests)
- Removed prole-db-manager port-forward mapping from installer/core/env.py
- Removed init_db_manager.sh from Initialization Scripts (milestones.py, actions.py)
- Removed init_certmgr.sh and init_db_manager.sh tabs from services screen (services.py)
- Removed live k8s Deployment/Service from knoe-dev-cluster

Fixed: PostgreSQL version downgrade error (pg17 -> pg18)
- Created conf/postgresql/.version with value 18
- Updated k8s/prole/prole-db.yaml and prole-db-recovery.yaml.tpl imageName to prole-db:18-089
- Fixed _init_database_options_state() to restore saved version_type from prole.cfg
  so db_version_type defaults to v18 (pg18) instead of silently reverting to pg17
- Added database_options.* keys to _collect_input_snapshot() in cfg.py so
  distribution, version_type, and all extension toggles persist to prole.cfg

Fixed: Cluster name inconsistency
- Removed stale prole-dev-cluster references; all scripts now use knoe-dev-cluster
- Added knoe-dev-cluster to mode-detection case in etc/prole_cfg.sh

Config: conf/prole.cfg
- Set kerberos_config.enabled = False, KERBEROS_AUTO_ENABLED = False
- Added database_options.distribution = percona, version_type = v18
- Added all 13 extension flags set to True (postgis, pgvector, pgcrypto, pgaudit,
  pg_repack, pg_stat_statements, pg_buffercache, pg_freespacemap, pgrowlocks,
  postgres_fdw, dblink, pg_stat_monitor, pgbadger)

Verification:
./install.py -s -l -v -c conf/prole.cfg completed successfully.
CNPG deployed prole-db:18-089 to knoe-dev-cluster; all milestones passed.

Co-authored-by: Junie <junie@jetbrains.com>
2026-03-01 20:40:44 -08:00

236 lines
8.2 KiB
Python

"""Milestone abstraction for the UI-agnostic installer core."""
from __future__ import annotations
from abc import ABC, abstractmethod
from typing import Callable, Sequence
from . import config as inst_config
from .state import InstallerState
ProgressCallback = Callable[[str, float | None], None]
ValidationResult = str | Sequence[str] | None
class Milestone(ABC):
"""Base class for installer milestones.
Milestones encapsulate business logic, validation, and flow control.
They must not import or depend on UI toolkits.
"""
id: str
title: str
def __init__(self, milestone_id: str, title: str):
self.id = milestone_id
self.title = title
def validate(self, state: InstallerState) -> ValidationResult:
"""Return a validation error or None when valid."""
return None
@abstractmethod
def execute(
self, state: InstallerState, progress: ProgressCallback | None = None
) -> None:
"""Execute milestone logic. Use the progress callback to emit updates."""
raise NotImplementedError
def next(self, state: InstallerState) -> str | None:
"""Return the next milestone id or None to finish."""
return None
def _parse_bool(self, val: any, default: bool | None = False) -> bool | None:
return inst_config._parse_bool(val, default)
def _run_cmd(
self,
cmd: str | list[str],
cwd: str | None = None,
on_stdout: callable | None = None,
) -> int:
if isinstance(cmd, str):
cmd = ["bash", "-c", cmd]
import subprocess
try:
proc = subprocess.Popen(
cmd,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT,
text=True,
bufsize=1,
cwd=cwd,
)
for line in iter(proc.stdout.readline, ""):
if on_stdout:
on_stdout(line)
return proc.wait()
except Exception:
return 1
def _get_script_env(self, state: InstallerState) -> dict:
import os
from pathlib import Path
env = os.environ.copy()
project_root = inst_config.PROJECT_ROOT
env["PROLE_HOME"] = str(project_root)
env["PROLE_SERVICE"] = str(project_root)
namespace = state.inputs.get("init_password.db_namespace", "default")
env["NAMESPACE"] = namespace
# Paths
env["PROLE_CONF"] = state.inputs.get(
"env_setup.PROLE_CONF", str(project_root / "conf")
)
env["PROLE_DATA"] = state.inputs.get(
"env_setup.PROLE_DATA", str(project_root / "prole-db" / "data")
)
env["PROLE_LOGS"] = state.inputs.get(
"env_setup.PROLE_LOGS", str(project_root / "logs")
)
env["PROLE_SERVICE"] = state.inputs.get(
"env_setup.PROLE_SERVICE", str(project_root / "etc")
)
service_ns = (
(state.config_data.get("Global", {}) or {})
.get("SERVICE_NAMESPACE", "")
.strip()
)
if not service_ns:
service_ns = (os.environ.get("SERVICE_NAMESPACE") or "").strip()
if not service_ns:
service_ns = namespace or "default"
env["SERVICE_NAMESPACE"] = service_ns
from installer.core.env import _deployment_mode_from_env
cluster_env = state.inputs.get("init_cluster.cluster_env", "dev")
mode = _deployment_mode_from_env(cluster_env) or "k3d"
env["PROLE_MODE"] = mode
# Kubeconfig
if mode == "k3s":
kc = Path(env["PROLE_SERVICE"]) / "secrets" / "k3s.kubeconfig"
if not kc.exists():
kc = project_root / "etc" / "secrets" / "k3s.kubeconfig"
if kc.exists():
env["KUBECONFIG"] = str(kc)
elif mode == "k3d":
# Ensure k3d dev clusters have a resolvable KUBECONFIG.
# The cluster may already be running from a previous session;
# merge the kubeconfig so downstream scripts can reach it.
if not (env.get("KUBECONFIG") or "").strip():
import subprocess as _sp
cluster_name = "knoe-dev-cluster"
try:
_sp.run(
[
"k3d",
"kubeconfig",
"merge",
cluster_name,
"--kubeconfig-switch-context",
],
capture_output=True,
text=True,
timeout=10,
)
except Exception:
pass
default_kube = str(Path.home() / ".kube" / "config")
if Path(default_kube).exists():
env["KUBECONFIG"] = default_kube
db_pw = state.inputs.get("init_password.db_password", "").strip()
if db_pw:
db_pw = inst_config._resolve_secret_value(db_pw)
env["DB_PASSWORD"] = db_pw
env["OPENTOFU_ADMIN_PASSWORD"] = db_pw
grafana_pw = (
(state.config_data.get("Monitoring", {}) or {})
.get("GRAFANA_ADMIN_PASSWORD", "")
.strip()
)
resolved_grafana = (
inst_config._resolve_secret_value(grafana_pw) if grafana_pw else ""
)
if (
resolved_grafana
and not inst_config._is_openbao_ref(resolved_grafana)
and not inst_config._is_prole_secret(resolved_grafana)
):
env["GRAFANA_ADMIN_PASSWORD"] = resolved_grafana
elif db_pw:
env["GRAFANA_ADMIN_PASSWORD"] = db_pw
db_user = (state.inputs.get("init_password.db_username", "") or "").strip()
if db_user:
env["PROLE_DB_USER"] = db_user
# Kerberos
env["KRB5_REALM"] = state.inputs.get("kerberos_config.realm", "")
realm = (state.inputs.get("kerberos_config.realm", "") or "").strip()
env["KRB5_KDC"] = state.inputs.get("kerberos_config.kdc", "")
if realm:
env["REALM"] = realm
env["DOMAIN"] = realm.lower()
env["KRB5_USER"] = state.inputs.get("kerberos_config.user", "")
krb_pw = state.inputs.get("kerberos_config.password", "")
if krb_pw:
env["KRB5_PASSWORD"] = inst_config._resolve_secret_value(krb_pw)
if state.inputs.get("kerberos_config.kdc", ""):
env["KRB5_ADMIN"] = state.inputs.get("kerberos_config.kdc", "")
kerberos_enabled = self._parse_bool(
state.inputs.get("kerberos_config.enabled", "False"), default=False
)
if kerberos_enabled is None:
kerberos_enabled = False
env["KERBEROS_ENABLED"] = "True" if kerberos_enabled else "False"
env["ENABLED"] = env["KERBEROS_ENABLED"]
at_rest = state.inputs.get("init_cluster.at_rest_encryption_enabled", "")
if at_rest != "":
env["AT_REST_ENCRYPTION_ENABLED"] = str(at_rest)
argocd_ns = (
(state.config_data.get("Global", {}) or {})
.get("ARGOCD_NAMESPACE", "")
.strip()
)
if not argocd_ns:
argocd_ns = (os.environ.get("ARGOCD_NAMESPACE") or "").strip() or "argocd"
env["ARGOCD_NAMESPACE"] = argocd_ns
registry_ns = (
(state.config_data.get("Global", {}) or {})
.get("REGISTRY_NAMESPACE", "")
.strip()
)
if not registry_ns:
registry_ns = (
os.environ.get("REGISTRY_NAMESPACE") or ""
).strip() or "default"
env["REGISTRY_NAMESPACE"] = registry_ns
if mode == "k3s":
server = state.inputs.get("init_cluster.k3s_server_url", "").strip()
token = state.inputs.get("init_cluster.k3s_token", "").strip()
if token:
token = inst_config._resolve_secret_value(token)
if server:
if not server.startswith("http"):
server = f"https://{server}"
env["PROLE_K3S_SERVER"] = server
if token:
env["PROLE_K3S_TOKEN"] = token
return env