4a0a3ee46e
Adds cron-like recurring runs (the engine the maintenance-automation work needs). New AnsibleSchedule model + migration 0018; a core ScheduledTask (ansible_scheduled_runs, 60s) fires due schedules, each creating a system-triggered AnsibleRun (triggered_by=None). Centralises the resolve-inventory → create-run → launch flow in ansible/runner.trigger_run, shared by the manual route (refactored to use it) and the scheduler. Schedules UI under /ansible/schedules: create/edit/pause/delete/run-now, with interval presets, scope targeting (all / group / target), extra-vars / limit / tags / dry-run, and last-run status (resolved via last_run_id) + next-run. Unit test for the due-check. Task #549 (milestone #37). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
323 lines
13 KiB
Python
323 lines
13 KiB
Python
# steward/app.py
|
|
from __future__ import annotations
|
|
import asyncio
|
|
from pathlib import Path
|
|
from quart import Quart, render_template
|
|
from .config import load_bootstrap
|
|
from .database import init_db
|
|
|
|
|
|
def create_app(
|
|
config_path: Path | str | None = None,
|
|
testing: bool = False,
|
|
) -> Quart:
|
|
app = Quart(__name__, template_folder="templates")
|
|
|
|
# ── 1. Bootstrap: db_url + secret_key only ────────────────────────────────
|
|
if not testing:
|
|
bootstrap = load_bootstrap(config_path)
|
|
else:
|
|
bootstrap = {
|
|
"database_url": "postgresql+asyncpg://test/test",
|
|
"secret_key": "test-secret-key",
|
|
"plugin_dirs": ["plugins"],
|
|
"plugin_install_dir": "plugins",
|
|
}
|
|
|
|
app.config.update(
|
|
SECRET_KEY=bootstrap["secret_key"],
|
|
DATABASE_URL=bootstrap["database_url"],
|
|
PLUGIN_DIRS=bootstrap["plugin_dirs"],
|
|
PLUGIN_INSTALL_DIR=bootstrap["plugin_install_dir"],
|
|
TESTING=testing,
|
|
)
|
|
|
|
# ── 2. Init DB engine ──────────────────────────────────────────────────────
|
|
if not testing:
|
|
init_db(app)
|
|
else:
|
|
from unittest.mock import MagicMock
|
|
app.db_sessionmaker = MagicMock()
|
|
|
|
# ── 3. Core migrations only (creates app_settings table) ──────────────────
|
|
if not testing:
|
|
from .core.migration_runner import run_core_migrations
|
|
run_core_migrations(
|
|
app.config["DATABASE_URL"],
|
|
plugin_dirs=[Path(d).resolve() for d in app.config["PLUGIN_DIRS"]],
|
|
)
|
|
|
|
# ── 4. Load all settings from DB → populate app.config ────────────────────
|
|
if not testing:
|
|
from .core.settings import (
|
|
load_settings_sync, to_smtp_cfg, to_webhook_cfg,
|
|
to_ansible_cfg, to_plugins_cfg, to_oidc_cfg, to_ldap_cfg,
|
|
)
|
|
_settings = load_settings_sync(app.config["DATABASE_URL"])
|
|
app.config.update(
|
|
SESSION_LIFETIME_HOURS=_settings.get("session.lifetime_hours", 8),
|
|
DATA_RETENTION_DAYS=_settings.get("data.retention_days", 90),
|
|
MONITORS_POLL_INTERVAL=_settings.get("monitors.poll_interval_seconds", 60),
|
|
SMTP=to_smtp_cfg(_settings),
|
|
WEBHOOK=to_webhook_cfg(_settings),
|
|
ANSIBLE=to_ansible_cfg(_settings),
|
|
PLUGINS=to_plugins_cfg(_settings),
|
|
OIDC=to_oidc_cfg(_settings),
|
|
LDAP=to_ldap_cfg(_settings),
|
|
)
|
|
else:
|
|
app.config.update(
|
|
SESSION_LIFETIME_HOURS=8,
|
|
DATA_RETENTION_DAYS=90,
|
|
MONITORS_POLL_INTERVAL=60,
|
|
SMTP={},
|
|
WEBHOOK={},
|
|
ANSIBLE={},
|
|
PLUGINS={},
|
|
OIDC={"enabled": False},
|
|
LDAP={"enabled": False},
|
|
)
|
|
|
|
# ── 5. Plugin migrations ───────────────────────────────────────────────────
|
|
# Step 3 already applied all plugin migrations via discover_all_plugin_migration_dirs,
|
|
# so this is a no-op on normal startup. We still run it with all discovered dirs so
|
|
# Alembic can resolve the full revision graph regardless of which plugins are enabled.
|
|
if not testing:
|
|
from .core.migration_runner import run_plugin_migrations, discover_all_in
|
|
_plugin_dirs = [Path(d).resolve() for d in app.config["PLUGIN_DIRS"]]
|
|
_all_plugin_dirs = discover_all_in(_plugin_dirs)
|
|
run_plugin_migrations(app.config["DATABASE_URL"], _all_plugin_dirs)
|
|
|
|
# ── 6. Alert pipeline ──────────────────────────────────────────────────────
|
|
from .core.alerts import init_alerts
|
|
init_alerts(app)
|
|
|
|
# ── 7. Register core blueprints ────────────────────────────────────────────
|
|
from .auth.routes import auth_bp
|
|
from .dashboard.routes import dashboard_bp
|
|
from .hosts.routes import hosts_bp
|
|
from .ping.routes import ping_bp
|
|
from .dns.routes import dns_bp
|
|
from .status.routes import status_bp
|
|
from .alerts.routes import alerts_bp
|
|
from .ansible.routes import ansible_bp
|
|
from .ansible.inventory_routes import inventory_bp
|
|
from .settings.routes import settings_bp
|
|
from .audit.routes import audit_bp
|
|
|
|
app.register_blueprint(auth_bp)
|
|
app.register_blueprint(dashboard_bp)
|
|
app.register_blueprint(hosts_bp)
|
|
app.register_blueprint(ping_bp)
|
|
app.register_blueprint(dns_bp)
|
|
app.register_blueprint(status_bp)
|
|
app.register_blueprint(alerts_bp)
|
|
app.register_blueprint(ansible_bp)
|
|
app.register_blueprint(inventory_bp)
|
|
app.register_blueprint(settings_bp)
|
|
app.register_blueprint(audit_bp)
|
|
|
|
# Register the core (ping/DNS) status sources for the unified Status page.
|
|
# Plugins register their own sources from setup() (e.g. http). Idempotent.
|
|
from .core.status import register_status_source, ping_status_source, dns_status_source
|
|
register_status_source(ping_status_source)
|
|
register_status_source(dns_status_source)
|
|
|
|
# ── 8. Build task registry ─────────────────────────────────────────────────
|
|
app._task_registry = []
|
|
|
|
if not testing:
|
|
_register_core_tasks(app)
|
|
|
|
# ── 9. Load plugins ────────────────────────────────────────────────────────
|
|
if not testing:
|
|
from .core.plugin_manager import load_plugins
|
|
load_plugins(app)
|
|
|
|
# ── 10. Template context: inject plugin_failures into every response ───────
|
|
@app.context_processor
|
|
def _inject_plugin_failures():
|
|
from .core.plugin_manager import get_plugin_failures
|
|
return {"plugin_failures": get_plugin_failures()}
|
|
|
|
# ── 11. Share-token middleware ─────────────────────────────────────────────
|
|
@app.before_request
|
|
async def _validate_share_token():
|
|
"""If ?s=<token> is present, validate it and set g.share_viewer."""
|
|
from quart import request, g
|
|
raw = request.args.get("s")
|
|
if not raw:
|
|
return
|
|
try:
|
|
import hashlib
|
|
from datetime import datetime, timezone
|
|
from sqlalchemy import select
|
|
from .models.dashboard import DashboardShareToken
|
|
token_hash = hashlib.sha256(raw.encode()).hexdigest()
|
|
async with app.db_sessionmaker() as db:
|
|
result = await db.execute(
|
|
select(DashboardShareToken)
|
|
.where(DashboardShareToken.token_hash == token_hash)
|
|
)
|
|
share = result.scalar_one_or_none()
|
|
if share:
|
|
now = datetime.now(timezone.utc)
|
|
if share.expires_at is None or share.expires_at > now:
|
|
g.share_viewer = True
|
|
g.share_dashboard_id = share.dashboard_id
|
|
except Exception:
|
|
pass # never block a request due to token validation failure
|
|
|
|
# ── 11. Health check ───────────────────────────────────────────────────────
|
|
@app.get("/health")
|
|
async def health():
|
|
return {"status": "ok"}
|
|
|
|
# ── 12. Error handlers ─────────────────────────────────────────────────────
|
|
@app.errorhandler(404)
|
|
async def not_found(_):
|
|
return await render_template("errors/404.html"), 404
|
|
|
|
@app.errorhandler(500)
|
|
async def server_error(_):
|
|
return await render_template("errors/500.html"), 500
|
|
|
|
# ── 11. Startup hook ───────────────────────────────────────────────────────
|
|
@app.before_serving
|
|
async def startup():
|
|
if not testing:
|
|
await _mark_interrupted_runs(app)
|
|
asyncio.create_task(_run_scheduler(app))
|
|
|
|
return app
|
|
|
|
|
|
def _register_core_tasks(app: Quart) -> None:
|
|
from .core.scheduler import ScheduledTask
|
|
|
|
poll_interval = app.config.get("MONITORS_POLL_INTERVAL", 60)
|
|
cleanup_interval = 3600 # hourly
|
|
|
|
async def run_ping_monitors():
|
|
from sqlalchemy import select
|
|
from .models.hosts import Host
|
|
from .monitors.ping import ping_check
|
|
async with app.db_sessionmaker() as session:
|
|
async with session.begin():
|
|
result = await session.execute(
|
|
select(Host).where(Host.ping_enabled.is_(True))
|
|
)
|
|
for host in result.scalars().all():
|
|
try:
|
|
await ping_check(host, session)
|
|
except Exception:
|
|
app.logger.exception(f"Ping check failed for host {host.name!r}")
|
|
|
|
async def run_dns_monitors():
|
|
from sqlalchemy import select
|
|
from .models.hosts import Host
|
|
from .monitors.dns import dns_check
|
|
async with app.db_sessionmaker() as session:
|
|
async with session.begin():
|
|
result = await session.execute(
|
|
select(Host).where(Host.dns_enabled.is_(True))
|
|
)
|
|
for host in result.scalars().all():
|
|
try:
|
|
await dns_check(host, session)
|
|
except Exception:
|
|
app.logger.exception(f"DNS check failed for host {host.name!r}")
|
|
|
|
async def run_cleanup():
|
|
from .core.cleanup import run_cleanup as _cleanup
|
|
await _cleanup(app)
|
|
|
|
async def run_report_check():
|
|
from .core.reports import check_and_send
|
|
await check_and_send(app)
|
|
|
|
app._task_registry.extend([
|
|
ScheduledTask(
|
|
name="weekly_report_check",
|
|
coro_factory=run_report_check,
|
|
interval_seconds=3600,
|
|
run_on_startup=False,
|
|
),
|
|
ScheduledTask(
|
|
name="ping_monitor",
|
|
coro_factory=run_ping_monitors,
|
|
interval_seconds=poll_interval,
|
|
run_on_startup=True,
|
|
),
|
|
ScheduledTask(
|
|
name="dns_monitor",
|
|
coro_factory=run_dns_monitors,
|
|
interval_seconds=poll_interval,
|
|
run_on_startup=True,
|
|
),
|
|
ScheduledTask(
|
|
name="data_cleanup",
|
|
coro_factory=run_cleanup,
|
|
interval_seconds=cleanup_interval,
|
|
run_on_startup=False,
|
|
),
|
|
])
|
|
|
|
# Register git-pull tasks for each ansible git source
|
|
ansible_cfg = app.config.get("ANSIBLE", {})
|
|
from .ansible.sources import get_sources
|
|
for source in get_sources(ansible_cfg):
|
|
if source["type"] != "git":
|
|
continue
|
|
_source = source
|
|
|
|
async def run_git_pull(src=_source):
|
|
from .ansible.sources import git_pull
|
|
await git_pull(src)
|
|
|
|
app._task_registry.append(
|
|
ScheduledTask(
|
|
name=f"ansible_git_pull_{_source['name']}",
|
|
coro_factory=run_git_pull,
|
|
interval_seconds=_source["pull_interval_seconds"],
|
|
run_on_startup=True,
|
|
)
|
|
)
|
|
|
|
# Fire due Ansible schedules (recurring playbook runs). Checks every minute;
|
|
# each schedule's own interval gates whether it actually runs.
|
|
async def run_ansible_schedules():
|
|
from .ansible.scheduler import run_due_schedules
|
|
await run_due_schedules(app)
|
|
|
|
app._task_registry.append(
|
|
ScheduledTask(
|
|
name="ansible_scheduled_runs",
|
|
coro_factory=run_ansible_schedules,
|
|
interval_seconds=60,
|
|
run_on_startup=False,
|
|
)
|
|
)
|
|
|
|
|
|
async def _mark_interrupted_runs(app: Quart) -> None:
|
|
from sqlalchemy import update
|
|
from .models.ansible import AnsibleRun, AnsibleRunStatus
|
|
from datetime import datetime, timezone
|
|
|
|
async with app.db_sessionmaker() as session:
|
|
async with session.begin():
|
|
await session.execute(
|
|
update(AnsibleRun)
|
|
.where(AnsibleRun.status == AnsibleRunStatus.running)
|
|
.values(
|
|
status=AnsibleRunStatus.interrupted,
|
|
finished_at=datetime.now(timezone.utc),
|
|
)
|
|
)
|
|
|
|
|
|
async def _run_scheduler(app: Quart) -> None:
|
|
from .core.scheduler import start_scheduler
|
|
await start_scheduler(app._task_registry)
|