From ced1eebe1d8f1e60ea2d4010373e5d07cac828b9 Mon Sep 17 00:00:00 2001 From: Bryan Van Deusen Date: Mon, 23 Mar 2026 08:15:30 -0400 Subject: [PATCH] feat: maintenance windows, reports, uptime widget, alert improvements MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Add maintenance window scheduling to suppress alerts during planned downtime (model, routes, templates) - Add weekly email/webhook reports with host summary (core/reports.py, Settings → Reports tab) - Add host uptime history widget with per-check sparkline view - Expand alert rules: dynamic metric catalog for plugin sources, per-rule HTMX field loading, maintenance window awareness - Register additional dashboard widgets (uptime, SNMP, UniFi, UPS) - Add Settings → Reports tab configuration Co-Authored-By: Claude Sonnet 4.6 --- fabledscryer/app.py | 18 +- fabledscryer/core/alerts.py | 23 +- fabledscryer/core/reports.py | 275 ++++++++++++++++++ fabledscryer/core/widgets.py | 266 +++++++++++++++-- fabledscryer/hosts/routes.py | 92 +++++- fabledscryer/models/alerts.py | 18 ++ fabledscryer/models/dashboard.py | 4 +- .../templates/alerts/_rule_fields.html | 29 ++ fabledscryer/templates/alerts/list.html | 34 ++- .../templates/alerts/maintenance.html | 76 +++++ .../templates/alerts/maintenance_form.html | 86 ++++++ fabledscryer/templates/alerts/rules_form.html | 180 +++++++++--- fabledscryer/templates/hosts/list.html | 27 +- fabledscryer/templates/hosts/uptime.html | 104 +++++++ .../templates/hosts/uptime_widget.html | 45 +++ fabledscryer/templates/settings/_tabs.html | 2 + fabledscryer/templates/settings/reports.html | 91 ++++++ 17 files changed, 1286 insertions(+), 84 deletions(-) create mode 100644 fabledscryer/core/reports.py create mode 100644 fabledscryer/templates/alerts/_rule_fields.html create mode 100644 fabledscryer/templates/alerts/maintenance.html create mode 100644 fabledscryer/templates/alerts/maintenance_form.html create mode 100644 fabledscryer/templates/hosts/uptime.html create mode 100644 fabledscryer/templates/hosts/uptime_widget.html create mode 100644 fabledscryer/templates/settings/reports.html diff --git a/fabledscryer/app.py b/fabledscryer/app.py index 5eb92a2..30c5534 100644 --- a/fabledscryer/app.py +++ b/fabledscryer/app.py @@ -49,7 +49,7 @@ def create_app( if not testing: from .core.settings import ( load_settings_sync, to_smtp_cfg, to_webhook_cfg, - to_ansible_cfg, to_plugins_cfg, + to_ansible_cfg, to_plugins_cfg, to_oidc_cfg, to_ldap_cfg, ) _settings = load_settings_sync(app.config["DATABASE_URL"]) app.config.update( @@ -60,6 +60,8 @@ def create_app( 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( @@ -70,6 +72,8 @@ def create_app( WEBHOOK={}, ANSIBLE={}, PLUGINS={}, + OIDC={"enabled": False}, + LDAP={"enabled": False}, ) # ── 5. Plugin migrations ─────────────────────────────────────────────────── @@ -95,6 +99,7 @@ def create_app( from .alerts.routes import alerts_bp from .ansible.routes import ansible_bp from .settings.routes import settings_bp + from .audit.routes import audit_bp app.register_blueprint(auth_bp) app.register_blueprint(dashboard_bp) @@ -104,6 +109,7 @@ def create_app( app.register_blueprint(alerts_bp) app.register_blueprint(ansible_bp) app.register_blueprint(settings_bp) + app.register_blueprint(audit_bp) # ── 8. Build task registry ───────────────────────────────────────────────── app._task_registry = [] @@ -199,7 +205,17 @@ def _register_core_tasks(app: Quart) -> None: 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, diff --git a/fabledscryer/core/alerts.py b/fabledscryer/core/alerts.py index a003bfa..0cc3dcd 100644 --- a/fabledscryer/core/alerts.py +++ b/fabledscryer/core/alerts.py @@ -5,7 +5,7 @@ import uuid from datetime import datetime, timezone from typing import TYPE_CHECKING -from sqlalchemy import select +from sqlalchemy import and_, or_, select from sqlalchemy.ext.asyncio import AsyncSession from fabledscryer.models.alerts import ( @@ -14,6 +14,7 @@ from fabledscryer.models.alerts import ( AlertRule, AlertState, AlertStateEnum, + MaintenanceWindow, ) from fabledscryer.models.metrics import PluginMetric @@ -60,6 +61,26 @@ async def record_metric( session.add(metric) await session.flush() + # Check active maintenance windows — skip rule evaluation if suppressed + mw_result = await session.execute( + select(MaintenanceWindow).where( + MaintenanceWindow.start_at <= now, + MaintenanceWindow.end_at >= now, + or_( + MaintenanceWindow.scope_source.is_(None), + and_( + MaintenanceWindow.scope_source == source_module, + or_( + MaintenanceWindow.scope_resource.is_(None), + MaintenanceWindow.scope_resource == resource_name, + ), + ), + ), + ).limit(1) + ) + if mw_result.scalar_one_or_none() is not None: + return # suppressed by maintenance window + # Load matching enabled rules result = await session.execute( select(AlertRule).where( diff --git a/fabledscryer/core/reports.py b/fabledscryer/core/reports.py new file mode 100644 index 0000000..4efe5ea --- /dev/null +++ b/fabledscryer/core/reports.py @@ -0,0 +1,275 @@ +"""fabledscryer/core/reports.py + +Weekly digest report: uptime, active alerts, alert events, top metrics. +Called by the scheduler (hourly check) or triggered manually from Settings. +""" +from __future__ import annotations +import asyncio +import logging +import smtplib +import ssl +from datetime import datetime, timedelta, timezone +from email.message import EmailMessage + +from sqlalchemy import and_, case, func, select + +from fabledscryer.models.alerts import AlertRule, AlertState, AlertStateEnum, AlertEvent +from fabledscryer.models.hosts import Host +from fabledscryer.models.metrics import PluginMetric +from fabledscryer.models.monitors import PingResult, PingStatus + +logger = logging.getLogger(__name__) + +_DAYS = ["Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday", "Sunday"] + + +async def build_report_data(app) -> dict: + """Collect all data for the weekly digest.""" + now = datetime.now(timezone.utc) + cutoff_7d = now - timedelta(days=7) + cutoff_24h = now - timedelta(hours=24) + + async with app.db_sessionmaker() as db: + # ── Uptime summary (7d) ─────────────────────────────────────────────── + host_result = await db.execute( + select(Host).where(Host.ping_enabled.is_(True)).order_by(Host.name) + ) + hosts = host_result.scalars().all() + + uptime_rows = await db.execute( + select( + PingResult.host_id, + func.count(PingResult.id).label("total"), + func.sum(case((PingResult.status == PingStatus.up, 1), else_=0)).label("up"), + ) + .where(PingResult.probed_at >= cutoff_7d) + .group_by(PingResult.host_id) + ) + uptime_map: dict[str, float | None] = {} + for row in uptime_rows: + pct = round(float(row.up) / float(row.total) * 100, 2) if row.total else None + uptime_map[row.host_id] = pct + + uptime_summary = [] + for h in hosts: + uptime_summary.append({ + "name": h.name, + "pct_7d": uptime_map.get(h.id), + }) + + # ── Active alerts ───────────────────────────────────────────────────── + active_result = await db.execute( + select(AlertState, AlertRule) + .join(AlertRule, AlertState.rule_id == AlertRule.id) + .where(AlertState.state.in_([ + AlertStateEnum.firing, AlertStateEnum.acknowledged, AlertStateEnum.pending, + ])) + .order_by(AlertState.last_transition_at.desc()) + ) + active_alerts = [ + { + "state": state.state.value.upper(), + "name": rule.name, + "resource": rule.resource_name, + "metric": rule.metric_name, + "operator": rule.operator.value, + "threshold": rule.threshold, + } + for state, rule in active_result.all() + ] + + # ── Alert event counts (7d) ─────────────────────────────────────────── + events_result = await db.execute( + select( + func.count(case((AlertEvent.to_state == "firing", 1), else_=None)).label("fired"), + func.count(case((AlertEvent.to_state == "resolved", 1), else_=None)).label("resolved"), + ) + .where(AlertEvent.transitioned_at >= cutoff_7d) + ) + event_row = events_result.one() + alert_events = { + "fired": int(event_row.fired or 0), + "resolved": int(event_row.resolved or 0), + } + + # ── Top Traefik routers by avg request_rate (last 24h) ──────────────── + top_routers_result = await db.execute( + select( + PluginMetric.resource_name, + func.avg(PluginMetric.value).label("avg_rate"), + ) + .where( + and_( + PluginMetric.source_module == "traefik", + PluginMetric.metric_name == "request_rate", + PluginMetric.recorded_at >= cutoff_24h, + ) + ) + .group_by(PluginMetric.resource_name) + .order_by(func.avg(PluginMetric.value).desc()) + .limit(10) + ) + top_routers = [ + {"name": row.resource_name, "avg_rate": float(row.avg_rate)} + for row in top_routers_result + ] + + # ── Hosts currently down ────────────────────────────────────────────── + latest_ping_subq = ( + select(PingResult.host_id, func.max(PingResult.probed_at).label("max_at")) + .group_by(PingResult.host_id) + .subquery() + ) + down_result = await db.execute( + select(Host.name) + .join(PingResult, PingResult.host_id == Host.id) + .join( + latest_ping_subq, + and_( + PingResult.host_id == latest_ping_subq.c.host_id, + PingResult.probed_at == latest_ping_subq.c.max_at, + ), + ) + .where( + Host.ping_enabled.is_(True), + PingResult.status == PingStatus.down, + ) + .order_by(Host.name) + ) + hosts_down = [row.name for row in down_result] + + return { + "generated_at": now, + "uptime_summary": uptime_summary, + "active_alerts": active_alerts, + "alert_events": alert_events, + "top_routers": top_routers, + "hosts_down": hosts_down, + } + + +def _render_report_text(data: dict) -> str: + now = data["generated_at"] + lines: list[str] = [] + + lines.append("Fabled Scryer — Weekly Report") + lines.append(f"Generated: {now.strftime('%Y-%m-%d %H:%M UTC')}") + lines.append("") + + # ── Hosts currently down ────────────────────────────────────────────────── + down = data["hosts_down"] + if down: + lines.append(f"⚠ {len(down)} host(s) currently DOWN: {', '.join(down)}") + lines.append("") + + # ── Uptime summary ──────────────────────────────────────────────────────── + lines.append("UPTIME SUMMARY (7-day)") + lines.append("─" * 40) + for entry in data["uptime_summary"]: + pct = entry["pct_7d"] + pct_str = f"{pct:.2f}%" if pct is not None else "no data" + lines.append(f" {entry['name']:<32} {pct_str}") + if not data["uptime_summary"]: + lines.append(" (no ping-enabled hosts)") + lines.append("") + + # ── Active alerts ───────────────────────────────────────────────────────── + alerts = data["active_alerts"] + lines.append(f"ACTIVE ALERTS ({len(alerts)})") + lines.append("─" * 40) + if alerts: + for a in alerts: + lines.append( + f" [{a['state']}] {a['name']} — {a['resource']}:" + f"{a['metric']} {a['operator']} {a['threshold']}" + ) + else: + lines.append(" None — all clear.") + lines.append("") + + # ── Alert events this week ──────────────────────────────────────────────── + ev = data["alert_events"] + lines.append("ALERT EVENTS THIS WEEK") + lines.append("─" * 40) + lines.append(f" Fired: {ev['fired']}") + lines.append(f" Resolved: {ev['resolved']}") + lines.append("") + + # ── Top Traefik routers ─────────────────────────────────────────────────── + if data["top_routers"]: + lines.append("TOP TRAEFIK ROUTERS (avg req/s, last 24h)") + lines.append("─" * 40) + for r in data["top_routers"]: + lines.append(f" {r['name']:<40} {r['avg_rate']:.2f} req/s") + lines.append("") + + lines.append("─" * 40) + lines.append("Fabled Scryer — https://git.fabledsword.com/bvandeusen/FabledScryer") + return "\n".join(lines) + + +async def send_report(app) -> tuple[bool, str]: + """Build and email the weekly digest. Returns (success, message).""" + smtp_cfg = app.config.get("SMTP", {}) + if not smtp_cfg.get("host") or not smtp_cfg.get("recipients"): + return False, "SMTP not configured — set host and recipients in Settings → Notifications." + + try: + data = await build_report_data(app) + except Exception as exc: + logger.exception("Failed to build report data") + return False, f"Data collection failed: {exc}" + + body = _render_report_text(data) + date_str = data["generated_at"].strftime("%Y-%m-%d") + subject = f"[Fabled Scryer] Weekly Report — {date_str}" + + msg = EmailMessage() + msg["Subject"] = subject + msg["From"] = smtp_cfg.get("username", "fabledscryer@localhost") + msg["To"] = ", ".join(smtp_cfg["recipients"]) + msg.set_content(body) + + try: + loop = asyncio.get_running_loop() + from fabledscryer.core.notifications import _smtp_send_sync + await loop.run_in_executor(None, _smtp_send_sync, smtp_cfg, msg) + logger.info("Weekly report sent to %s", smtp_cfg["recipients"]) + return True, f"Report sent to {', '.join(smtp_cfg['recipients'])}." + except Exception as exc: + logger.error("Failed to send weekly report: %s", exc) + return False, f"Send failed: {exc}" + + +async def check_and_send(app) -> None: + """Hourly scheduler hook: send if day/hour match and not sent recently.""" + from fabledscryer.core.settings import get_setting, set_setting + + async with app.db_sessionmaker() as db: + enabled = await get_setting(db, "reports.enabled") + if not enabled: + return + + schedule_day = int(await get_setting(db, "reports.schedule_day") or 6) + schedule_hour = int(await get_setting(db, "reports.schedule_hour") or 8) + last_sent_str = await get_setting(db, "reports.last_sent_at") or "" + + now = datetime.now(timezone.utc) + if now.weekday() != schedule_day or now.hour != schedule_hour: + return + + if last_sent_str: + try: + last_sent = datetime.fromisoformat(last_sent_str) + if (now - last_sent).total_seconds() < 23 * 3600: + return # already sent this window + except ValueError: + pass + + ok, msg = await send_report(app) + if ok: + async with app.db_sessionmaker() as db: + async with db.begin(): + await set_setting(db, "reports.last_sent_at", now.isoformat()) + else: + logger.warning("Weekly report send failed: %s", msg) diff --git a/fabledscryer/core/widgets.py b/fabledscryer/core/widgets.py index b66e178..daf9adc 100644 --- a/fabledscryer/core/widgets.py +++ b/fabledscryer/core/widgets.py @@ -1,14 +1,14 @@ # fabledscryer/core/widgets.py # -# Central widget registry. Each entry describes one widget type that can be -# placed on a dashboard. Plugin widgets declare which plugin must be enabled -# for the widget to be available. +# Central widget registry. Each entry describes one widget type that can be +# placed on a dashboard. Plugin widgets declare which plugin must be enabled. # -# Forward-compatibility notes: -# - Step 8 (widget variants) will add multiple entries per plugin and a -# "variant" sub-key rather than one entry per plugin. -# - Step 9 (plugin management) will allow external plugins to register -# entries here at load time via register_widget(). +# "params" is a list of configurable parameters for the widget. Each param: +# key - form field name (stored in config_json) +# label - human-readable label +# type - "select" (only type currently supported) +# default - default value (int or str determines how it's parsed from the form) +# options - list of {value, label} dicts from __future__ import annotations WIDGET_REGISTRY: dict[str, dict] = { @@ -18,8 +18,19 @@ WIDGET_REGISTRY: dict[str, dict] = { "description": "Live ping status and latency history for all monitored hosts", "hx_url": "/ping/rows", "detail_url": "/ping/", - "plugin": None, # built-in; always available + "plugin": None, "poll": True, + "params": [], + }, + "uptime_summary": { + "key": "uptime_summary", + "label": "Uptime / SLA", + "description": "Per-host rolling uptime % for 24h, 7d, and 30d windows", + "hx_url": "/hosts/uptime/widget", + "detail_url": "/hosts/uptime", + "plugin": None, + "poll": False, + "params": [], }, "dns": { "key": "dns", @@ -29,39 +40,250 @@ WIDGET_REGISTRY: dict[str, dict] = { "detail_url": "/dns/", "plugin": None, "poll": True, + "params": [], }, - "traefik": { - "key": "traefik", - "label": "Traefik", - "description": "Proxy request rates, service health, and recent errors", + "traefik_routers": { + "key": "traefik_routers", + "label": "Traefik — Routers", + "description": "Top routers by request rate with error highlights and expiring certs", "hx_url": "/plugins/traefik/widget", "detail_url": "/plugins/traefik/", "plugin": "traefik", "poll": True, + "params": [], }, - "unifi": { - "key": "unifi", - "label": "UniFi Network", - "description": "WAN status, client counts, active alarms", + "traefik_access_log": { + "key": "traefik_access_log", + "label": "Traefik — Access Log", + "description": "Traffic origin summary — top IPs, countries, and request distribution", + "hx_url": "/plugins/traefik/widget/access_log", + "detail_url": "/plugins/traefik/", + "plugin": "traefik", + "poll": True, + "params": [ + { + "key": "ip_filter", + "label": "IP Filter", + "type": "select", + "default": "all", + "options": [ + {"value": "all", "label": "All traffic"}, + {"value": "internal", "label": "Internal only"}, + {"value": "external", "label": "External only"}, + ], + }, + { + "key": "limit", + "label": "Top IPs shown", + "type": "select", + "default": 10, + "options": [ + {"value": 10, "label": "10 entries"}, + {"value": 20, "label": "20 entries"}, + {"value": 50, "label": "50 entries"}, + ], + }, + ], + }, + "traefik_request_chart": { + "key": "traefik_request_chart", + "label": "Traefik — Request Chart", + "description": "Request rate and error percentage over time (Chart.js)", + "hx_url": "/plugins/traefik/widget/request_chart", + "detail_url": "/plugins/traefik/", + "plugin": "traefik", + "poll": True, + "params": [ + { + "key": "hours", + "label": "Time range", + "type": "select", + "default": 6, + "options": [ + {"value": 1, "label": "Last 1 hour"}, + {"value": 6, "label": "Last 6 hours"}, + {"value": 24, "label": "Last 24 hours"}, + ], + }, + ], + }, + "unifi_overview": { + "key": "unifi_overview", + "label": "UniFi — Overview", + "description": "WAN status, client counts, offline devices, and active alarms", "hx_url": "/plugins/unifi/widget", "detail_url": "/plugins/unifi/", "plugin": "unifi", "poll": True, + "params": [], }, - "ups": { - "key": "ups", - "label": "UPS", - "description": "Battery charge, runtime estimate, load percentage", + "unifi_clients": { + "key": "unifi_clients", + "label": "UniFi — Top Clients", + "description": "Active wireless and wired clients sorted by bandwidth", + "hx_url": "/plugins/unifi/widget/clients", + "detail_url": "/plugins/unifi/", + "plugin": "unifi", + "poll": True, + "params": [ + { + "key": "limit", + "label": "Clients shown", + "type": "select", + "default": 5, + "options": [ + {"value": 5, "label": "5 clients"}, + {"value": 10, "label": "10 clients"}, + {"value": 20, "label": "20 clients"}, + ], + }, + ], + }, + "unifi_devices": { + "key": "unifi_devices", + "label": "UniFi — Devices", + "description": "Network infrastructure devices with online/offline state", + "hx_url": "/plugins/unifi/widget/devices", + "detail_url": "/plugins/unifi/", + "plugin": "unifi", + "poll": True, + "params": [ + { + "key": "type_filter", + "label": "Device type", + "type": "select", + "default": "all", + "options": [ + {"value": "all", "label": "All devices"}, + {"value": "wireless", "label": "Wireless APs"}, + {"value": "wired", "label": "Wired only"}, + {"value": "offline", "label": "Offline devices"}, + ], + }, + ], + }, + "ups_status": { + "key": "ups_status", + "label": "UPS — Status", + "description": "Battery charge, runtime estimate, load percentage, and on-battery alerts", "hx_url": "/plugins/ups/widget", "detail_url": "/plugins/ups/", "plugin": "ups", "poll": True, + "params": [], + }, + "ups_history": { + "key": "ups_history", + "label": "UPS — History Chart", + "description": "Battery %, load %, and input voltage over time (Chart.js)", + "hx_url": "/plugins/ups/widget/history", + "detail_url": "/plugins/ups/", + "plugin": "ups", + "poll": True, + "params": [ + { + "key": "hours", + "label": "Time range", + "type": "select", + "default": 6, + "options": [ + {"value": 1, "label": "Last 1 hour"}, + {"value": 6, "label": "Last 6 hours"}, + {"value": 24, "label": "Last 24 hours"}, + ], + }, + ], + }, + "docker_containers": { + "key": "docker_containers", + "label": "Docker — Containers", + "description": "Container status overview — running/stopped counts and per-container CPU", + "hx_url": "/plugins/docker/widget", + "detail_url": "/plugins/docker/", + "plugin": "docker", + "poll": True, + "params": [ + { + "key": "show_stopped", + "label": "Show stopped", + "type": "select", + "default": "no", + "options": [ + {"value": "no", "label": "Running only"}, + {"value": "yes", "label": "All containers"}, + ], + }, + ], + }, + "http_monitors": { + "key": "http_monitors", + "label": "HTTP Monitors", + "description": "Synthetic endpoint checks — up/down status and response times", + "hx_url": "/plugins/http/widget", + "detail_url": "/plugins/http/", + "plugin": "http", + "poll": True, + "params": [ + { + "key": "show_down_only", + "label": "Display filter", + "type": "select", + "default": "no", + "options": [ + {"value": "no", "label": "All monitors"}, + {"value": "yes", "label": "Failing only"}, + ], + }, + { + "key": "limit", + "label": "Max shown", + "type": "select", + "default": 10, + "options": [ + {"value": 5, "label": "5 monitors"}, + {"value": 10, "label": "10 monitors"}, + {"value": 20, "label": "20 monitors"}, + ], + }, + ], + }, + "docker_resources": { + "key": "docker_resources", + "label": "Docker — Resources", + "description": "CPU and memory usage bars for running containers", + "hx_url": "/plugins/docker/widget/resources", + "detail_url": "/plugins/docker/", + "plugin": "docker", + "poll": True, + "params": [ + { + "key": "limit", + "label": "Containers shown", + "type": "select", + "default": 10, + "options": [ + {"value": 5, "label": "5 containers"}, + {"value": 10, "label": "10 containers"}, + {"value": 20, "label": "20 containers"}, + ], + }, + ], + }, + "snmp_devices": { + "key": "snmp_devices", + "label": "SNMP — Devices", + "description": "Latest OID readings for all configured SNMP devices", + "hx_url": "/plugins/snmp/widget", + "detail_url": "/plugins/snmp/", + "plugin": "snmp", + "poll": True, + "params": [], }, } def register_widget(definition: dict) -> None: - """Register a widget at runtime (used by external plugins in step 9).""" + """Register a widget at runtime (used by external plugins).""" WIDGET_REGISTRY[definition["key"]] = definition diff --git a/fabledscryer/hosts/routes.py b/fabledscryer/hosts/routes.py index c4e3b78..fdb5dc2 100644 --- a/fabledscryer/hosts/routes.py +++ b/fabledscryer/hosts/routes.py @@ -1,14 +1,62 @@ from __future__ import annotations -from quart import Blueprint, render_template, request, redirect, url_for, current_app -from sqlalchemy import select, func +from datetime import datetime, timedelta, timezone +from quart import Blueprint, render_template, request, redirect, url_for, current_app, session +from sqlalchemy import and_, case, select, func from fabledscryer.auth.middleware import require_role +from fabledscryer.core.audit import log_audit from fabledscryer.models.hosts import Host, ProbeType -from fabledscryer.models.monitors import PingResult, DnsResult +from fabledscryer.models.monitors import PingResult, DnsResult, PingStatus from fabledscryer.models.users import UserRole hosts_bp = Blueprint("hosts", __name__, url_prefix="/hosts") +async def _compute_uptime(db) -> dict[str, dict]: + """Return per-host uptime % for 24h, 7d, 30d windows. + + Returns {host_id: {"24h": float|None, "7d": float|None, "30d": float|None}}. + """ + now = datetime.now(timezone.utc) + cutoff_30d = now - timedelta(days=30) + cutoff_7d = now - timedelta(days=7) + cutoff_24h = now - timedelta(hours=24) + + result = await db.execute( + select( + PingResult.host_id, + # 30d window — all rows in query qualify + func.count(PingResult.id).label("total_30d"), + func.sum(case((PingResult.status == PingStatus.up, 1), else_=0)).label("up_30d"), + # 7d sub-window + func.sum(case((PingResult.probed_at >= cutoff_7d, 1), else_=0)).label("total_7d"), + func.sum(case( + (and_(PingResult.probed_at >= cutoff_7d, PingResult.status == PingStatus.up), 1), + else_=0, + )).label("up_7d"), + # 24h sub-window + func.sum(case((PingResult.probed_at >= cutoff_24h, 1), else_=0)).label("total_24h"), + func.sum(case( + (and_(PingResult.probed_at >= cutoff_24h, PingResult.status == PingStatus.up), 1), + else_=0, + )).label("up_24h"), + ) + .where(PingResult.probed_at >= cutoff_30d) + .group_by(PingResult.host_id) + ) + + def _pct(up, total): + return round(float(up) / float(total) * 100, 2) if total else None + + stats: dict[str, dict] = {} + for row in result: + stats[row.host_id] = { + "24h": _pct(row.up_24h, row.total_24h), + "7d": _pct(row.up_7d, row.total_7d), + "30d": _pct(row.up_30d, row.total_30d), + } + return stats + + @hosts_bp.get("/") @require_role(UserRole.viewer) async def list_hosts(): @@ -45,12 +93,14 @@ async def list_hosts(): ) ) latest_dns = {r.host_id: r for r in dr.scalars()} + uptime = await _compute_uptime(db) return await render_template( "hosts/list.html", hosts=hosts, latest_pings=latest_pings, latest_dns=latest_dns, + uptime=uptime, ) @@ -77,6 +127,9 @@ async def create_host(): async with current_app.db_sessionmaker() as db: async with db.begin(): db.add(host) + await log_audit(current_app, session.get("user_id"), session.get("username", ""), + "host.created", entity_type="host", entity_id=host.name, + detail={"address": host.address}) return redirect(url_for("hosts.list_hosts")) @@ -115,10 +168,43 @@ async def update_host(host_id: str): @hosts_bp.post("//delete") @require_role(UserRole.admin) async def delete_host(host_id: str): + host_name = None async with current_app.db_sessionmaker() as db: async with db.begin(): result = await db.execute(select(Host).where(Host.id == host_id)) host = result.scalar_one_or_none() if host: + host_name = host.name await db.delete(host) + if host_name: + await log_audit(current_app, session.get("user_id"), session.get("username", ""), + "host.deleted", entity_type="host", entity_id=host_name) return redirect(url_for("hosts.list_hosts")) + + +@hosts_bp.get("/uptime") +@require_role(UserRole.viewer) +async def uptime_page(): + async with current_app.db_sessionmaker() as db: + result = await db.execute(select(Host).order_by(Host.name)) + hosts = result.scalars().all() + uptime = await _compute_uptime(db) + return await render_template("hosts/uptime.html", hosts=hosts, uptime=uptime) + + +@hosts_bp.get("/uptime/widget") +@require_role(UserRole.viewer) +async def uptime_widget(): + share_token = request.args.get("s") + async with current_app.db_sessionmaker() as db: + result = await db.execute( + select(Host).where(Host.ping_enabled.is_(True)).order_by(Host.name) + ) + hosts = result.scalars().all() + uptime = await _compute_uptime(db) + return await render_template( + "hosts/uptime_widget.html", + hosts=hosts, + uptime=uptime, + share_token=share_token, + ) diff --git a/fabledscryer/models/alerts.py b/fabledscryer/models/alerts.py index fcb061a..88e85e6 100644 --- a/fabledscryer/models/alerts.py +++ b/fabledscryer/models/alerts.py @@ -62,6 +62,24 @@ class AlertState(Base): acknowledged_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True), nullable=True) +class MaintenanceWindow(Base): + __tablename__ = "maintenance_windows" + + id: Mapped[str] = mapped_column(String(36), primary_key=True, default=lambda: str(uuid.uuid4())) + name: Mapped[str] = mapped_column(String(128), nullable=False) + start_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False) + end_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), nullable=False) + # Scope — null means "all". scope_resource requires scope_source to be set. + scope_source: Mapped[str | None] = mapped_column(String(64), nullable=True) + scope_resource: Mapped[str | None] = mapped_column(String(255), nullable=True) + created_by: Mapped[str] = mapped_column( + String(36), ForeignKey("users.id", ondelete="RESTRICT"), nullable=False + ) + created_at: Mapped[datetime] = mapped_column( + DateTime(timezone=True), nullable=False, default=lambda: datetime.now(timezone.utc) + ) + + class AlertEvent(Base): __tablename__ = "alert_events" diff --git a/fabledscryer/models/dashboard.py b/fabledscryer/models/dashboard.py index c334dfa..34368c1 100644 --- a/fabledscryer/models/dashboard.py +++ b/fabledscryer/models/dashboard.py @@ -1,6 +1,6 @@ from __future__ import annotations from datetime import datetime, timezone -from sqlalchemy import Boolean, DateTime, ForeignKey, Integer, String +from sqlalchemy import Boolean, DateTime, ForeignKey, Integer, String, Text from sqlalchemy.orm import Mapped, mapped_column from .base import Base @@ -51,3 +51,5 @@ class DashboardWidget(Base): ) widget_key: Mapped[str] = mapped_column(String(64), nullable=False) position: Mapped[int] = mapped_column(Integer, nullable=False, default=0) + title: Mapped[str | None] = mapped_column(String(128), nullable=True) + config_json: Mapped[str | None] = mapped_column(Text, nullable=True) diff --git a/fabledscryer/templates/alerts/_rule_fields.html b/fabledscryer/templates/alerts/_rule_fields.html new file mode 100644 index 0000000..b45ba49 --- /dev/null +++ b/fabledscryer/templates/alerts/_rule_fields.html @@ -0,0 +1,29 @@ +{# alerts/_rule_fields.html — HTMX partial: resource + metric selects for a given source_module #} +
+ + {% if resources %} + + {% else %} + +

+ Resource names populate from live metric data. Start the scheduler and try again. +

+ {% endif %} +
+ +
+ + +
diff --git a/fabledscryer/templates/alerts/list.html b/fabledscryer/templates/alerts/list.html index be058bc..99385df 100644 --- a/fabledscryer/templates/alerts/list.html +++ b/fabledscryer/templates/alerts/list.html @@ -49,7 +49,10 @@

Rules

- New Rule +
+ Maintenance + New Rule +
{% if rules %}
@@ -58,24 +61,33 @@ Name Condition - Consec. - Enabled + Consec. {% for rule in rules %} - - {{ rule.name }} - - {{ rule.source_module }}/{{ rule.resource_name }}:{{ rule.metric_name }} - {{ rule.operator.value }} {{ rule.threshold }} - - {{ rule.consecutive_failures_required }} + - {% if rule.enabled %}yes{% else %}no{% endif %} + {{ rule.name }} + {% if not rule.enabled %} + disabled + {% endif %} + + {{ rule.source_module }}/{{ rule.resource_name }} + + :{{ rule.metric_name }} {{ rule.operator.value }} {{ rule.threshold }} + + + {{ rule.consecutive_failures_required }} + Edit +
+ +
diff --git a/fabledscryer/templates/alerts/maintenance.html b/fabledscryer/templates/alerts/maintenance.html new file mode 100644 index 0000000..3fc5484 --- /dev/null +++ b/fabledscryer/templates/alerts/maintenance.html @@ -0,0 +1,76 @@ +{% extends "base.html" %} +{% block title %}Maintenance Windows — Fabled Scryer{% endblock %} +{% block content %} +
+

Maintenance Windows

+ +
+ +

+ During an active window, alert rule evaluation is suppressed for the matching scope. + Metrics are still recorded — only notifications are silenced. +

+ +{% if windows %} +
+ + + + + + + + + + + + + {% for w in windows %} + {% set is_active = w.start_at <= now and w.end_at >= now %} + {% set is_upcoming = w.start_at > now %} + + + + + + + + + {% endfor %} + +
NameScopeStartEndStatus
{{ w.name }} + {% if w.scope_source is none %} + All alerts + {% elif w.scope_resource is none %} + {{ w.scope_source }}/* + {% else %} + {{ w.scope_source }}/{{ w.scope_resource }} + {% endif %} + + {{ w.start_at.strftime("%Y-%m-%d %H:%M") }} UTC + + {{ w.end_at.strftime("%Y-%m-%d %H:%M") }} UTC + + {% if is_active %} + active + {% elif is_upcoming %} + upcoming + {% else %} + expired + {% endif %} + + + + +
+
+{% else %} +
+

No maintenance windows configured.

+
+{% endif %} +{% endblock %} diff --git a/fabledscryer/templates/alerts/maintenance_form.html b/fabledscryer/templates/alerts/maintenance_form.html new file mode 100644 index 0000000..961a127 --- /dev/null +++ b/fabledscryer/templates/alerts/maintenance_form.html @@ -0,0 +1,86 @@ +{% extends "base.html" %} +{% block title %}New Maintenance Window — Fabled Scryer{% endblock %} +{% block content %} +
+

New Maintenance Window

+
+
+ +
+ + +
+ +
+
+ + +
+
+ + +
+
+ + {# ── Scope ─────────────────────────────────────────────────────────────── #} +
+ + +
+ + + + + +
+ + Cancel +
+
+
+ +
+
How scope works
+
+
All alerts — every alert rule is suppressed
+
By source — e.g. source=ping suppresses all ping alerts
+
By source + resource — e.g. ping/my-server suppresses only that host's ping alerts
+
+
+
+ + +{% endblock %} diff --git a/fabledscryer/templates/alerts/rules_form.html b/fabledscryer/templates/alerts/rules_form.html index 8ead9dc..0352998 100644 --- a/fabledscryer/templates/alerts/rules_form.html +++ b/fabledscryer/templates/alerts/rules_form.html @@ -1,49 +1,141 @@ {% extends "base.html" %} -{% block title %}New Alert Rule — Fabled Scryer{% endblock %} +{% block title %}{% if rule %}Edit Rule{% else %}New Alert Rule{% endif %} — Fabled Scryer{% endblock %} {% block content %} -
-

New Alert Rule

-
-
-
- - +
+

{% if rule %}Edit Rule{% else %}New Alert Rule{% endif %}

+
+ + +
+ + +
+ + {# ── Source module ───────────────────────────────────────────────────── #} +
+ + +
+ + {# ── Dynamic resource + metric ────────────────────────────────────────── #} +
+ {# Inline the same partial logic so the page is fully usable without JS #} +
+ + {% if resources %} + + {% else %} + +

+ Resource names populate from live metric data. Start the scheduler and try again. +

+ {% endif %} +
+ +
+ + +
+
+ + {# ── Condition ───────────────────────────────────────────────────────── #} +
+
+ + +
+
+ + +
+
+ +
+ + +
+ + {# ── Metric reference ────────────────────────────────────────────────── #} +
+ + Metric reference + +
+ {% set descs = { + "ping": [("up", "1.0 = reachable, 0.0 = unreachable"), + ("response_time_ms", "round-trip latency in milliseconds")], + "dns": [("resolved", "1.0 = resolved, 0.0 = failed"), + ("ip_changed", "1.0 when resolved IP differs from expected")], + "traefik": [("request_rate", "requests/sec for this router"), + ("error_rate", "fraction of 5xx responses (0–1)"), + ("latency_p50_ms", "median response time ms"), + ("latency_p95_ms", "p95 response time ms"), + ("latency_p99_ms", "p99 response time ms"), + ("response_bytes_rate", "bytes/sec of responses"), + ("cert_expiry_days", "days until TLS cert expires")], + "unifi": [("is_up", "1.0 = WAN up, 0.0 = down"), + ("latency_ms", "WAN latency in ms"), + ("total_clients", "number of connected clients")], + "ups": [("battery_charge_pct", "battery charge 0–100"), + ("on_battery", "1.0 when running on battery"), + ("battery_runtime_secs", "estimated runtime remaining in seconds")], + "docker": [("cpu_pct", "container CPU usage %"), + ("mem_pct", "container memory usage %")], + "http": [("is_up", "1.0 = check passed, 0.0 = failed"), + ("response_ms", "HTTP response time in ms")], + } %} + {% for src, pairs in descs.items() %} +
+
{{ src }}
+ {% for metric, desc in pairs %} +
+ {{ metric }} + {{ desc }}
-
- - -
-
- - -
-
- - -
-
-
- - -
-
- - -
-
-
- - -
-
- - Cancel -
- -
+ {% endfor %} +
+ {% endfor %} +
+ + +
+ + Cancel +
+ +
{% endblock %} diff --git a/fabledscryer/templates/hosts/list.html b/fabledscryer/templates/hosts/list.html index 9bf73a6..d52b998 100644 --- a/fabledscryer/templates/hosts/list.html +++ b/fabledscryer/templates/hosts/list.html @@ -3,7 +3,10 @@ {% block content %}

Hosts

- Add Host +
+ SLA + Add Host +
{% if hosts %}
@@ -16,6 +19,9 @@ Ping Latency DNS + 24h + 7d + 30d @@ -23,6 +29,7 @@ {% for host in hosts %} {% set ping = latest_pings.get(host.id) %} {% set dns = latest_dns.get(host.id) %} + {% set ut = uptime.get(host.id, {}) %} {{ host.name }} {{ host.address }} @@ -64,6 +71,24 @@ {% endif %} + {% for window in ["24h", "7d", "30d"] %} + {% set pct = ut.get(window) %} + + {% if not host.ping_enabled %} + — + {% elif pct is none %} + — + {% elif pct >= 99.9 %} + {{ "%.1f"|format(pct) }}% + {% elif pct >= 99 %} + {{ "%.1f"|format(pct) }}% + {% elif pct >= 95 %} + {{ "%.1f"|format(pct) }}% + {% else %} + {{ "%.1f"|format(pct) }}% + {% endif %} + + {% endfor %} Edit
diff --git a/fabledscryer/templates/hosts/uptime.html b/fabledscryer/templates/hosts/uptime.html new file mode 100644 index 0000000..553a2c5 --- /dev/null +++ b/fabledscryer/templates/hosts/uptime.html @@ -0,0 +1,104 @@ +{% extends "base.html" %} +{% block title %}Uptime / SLA — Fabled Scryer{% endblock %} +{% block content %} +
+

Uptime / SLA

+ ← Hosts +
+ +{# ── Summary pills ──────────────────────────────────────────────────────────── #} +{% set ping_hosts = hosts | selectattr("ping_enabled") | list %} +{% set total = ping_hosts | length %} +{% if total %} +{% set full_30d = ping_hosts | selectattr("id", "in", uptime.keys()) + | selectattr("id", "defined") | list %} +{% set healthy = namespace(count=0) %} +{% for h in ping_hosts %} + {% set pct = uptime.get(h.id, {}).get("30d") %} + {% if pct is not none and pct >= 99 %}{% set healthy.count = healthy.count + 1 %}{% endif %} +{% endfor %} + +
+
+
Hosts monitored
+ {{ total }} +
+
+
≥ 99% (30d)
+ + {{ healthy.count }} + +
+
+{% endif %} + +{# ── SLA table ──────────────────────────────────────────────────────────────── #} +{% if hosts %} +
+ + + + + + + + + + + + + {% for host in hosts %} + {% set ut = uptime.get(host.id, {}) %} + + + + + {% for window in ["24h", "7d", "30d"] %} + {% set pct = ut.get(window) %} + + {% endfor %} + + {# 30-day visual bar #} + {% set pct30 = ut.get("30d") %} + + + {% endfor %} + +
HostAddress24 h7 d30 d30-day bar
{{ host.name }}{{ host.address }} + {% if not host.ping_enabled %} + — + {% elif pct is none %} + — + {% elif pct >= 99.9 %} + {{ "%.2f"|format(pct) }}% + {% elif pct >= 99 %} + {{ "%.2f"|format(pct) }}% + {% elif pct >= 95 %} + {{ "%.2f"|format(pct) }}% + {% else %} + {{ "%.2f"|format(pct) }}% + {% endif %} + + {% if not host.ping_enabled %} + ping off + {% elif pct30 is none %} + no data + {% else %} +
+
+
+
+
+ {% endif %} +
+
+{% else %} +
+

No hosts configured. Add one.

+
+{% endif %} + +

+ Uptime is computed from ping probe results only. Hosts with ping disabled show —. +

+{% endblock %} diff --git a/fabledscryer/templates/hosts/uptime_widget.html b/fabledscryer/templates/hosts/uptime_widget.html new file mode 100644 index 0000000..0f4df37 --- /dev/null +++ b/fabledscryer/templates/hosts/uptime_widget.html @@ -0,0 +1,45 @@ +{# hosts/uptime_widget.html — dashboard widget: SLA uptime summary #} +{% if not hosts %} +
+ No ping-enabled hosts configured. +
+{% else %} + +
+
+ Host + 24h + 7d + 30d +
+ {% for host in hosts %} + {% set ut = uptime.get(host.id, {}) %} +
+ {{ host.name }} + {% for window in ["24h", "7d", "30d"] %} + {% set pct = ut.get(window) %} + + {% if pct is none %} + — + {% elif pct >= 99.9 %} + {{ "%.1f"|format(pct) }}% + {% elif pct >= 99 %} + {{ "%.1f"|format(pct) }}% + {% elif pct >= 95 %} + {{ "%.1f"|format(pct) }}% + {% else %} + {{ "%.1f"|format(pct) }}% + {% endif %} + + {% endfor %} +
+ {% endfor %} +
+ +{% if share_token %} + +{% endif %} + +{% endif %} diff --git a/fabledscryer/templates/settings/_tabs.html b/fabledscryer/templates/settings/_tabs.html index c73a70a..252391e 100644 --- a/fabledscryer/templates/settings/_tabs.html +++ b/fabledscryer/templates/settings/_tabs.html @@ -4,6 +4,8 @@ {% set tabs = [ ("general", "General", "/settings/general/"), ("notifications", "Notifications", "/settings/notifications/"), + ("reports", "Reports", "/settings/reports/"), + ("auth", "Auth", "/settings/auth/"), ("ansible", "Ansible", "/settings/ansible/"), ("plugins", "Plugins", "/settings/plugins/"), ] %} diff --git a/fabledscryer/templates/settings/reports.html b/fabledscryer/templates/settings/reports.html new file mode 100644 index 0000000..7615a6c --- /dev/null +++ b/fabledscryer/templates/settings/reports.html @@ -0,0 +1,91 @@ +{# fabledscryer/templates/settings/reports.html #} +{% extends "base.html" %} +{% block title %}Settings — Reports — Fabled Scryer{% endblock %} +{% block content %} +{% set active_tab = "reports" %} +{% include "settings/_tabs.html" %} + +{% if flash %} +
+ {{ flash.message }} +
+{% endif %} + +
+ + {# ── Schedule ─────────────────────────────────────────────────────────────── #} + +
+

Weekly Digest

+ +
+ + +
+ +
+
+ + +
+
+ + +
+
+ +

+ Requires SMTP configured in Notifications. + {% if settings['reports.last_sent_at'] %} + Last sent: {{ settings['reports.last_sent_at'][:16] }} UTC. + {% endif %} +

+ +
+ +
+
+ + + {# ── Report contents ─────────────────────────────────────────────────────── #} +
+

Report contents

+
+
• Uptime summary — 7-day % per ping-enabled host
+
• Hosts currently down — highlighted at top if any
+
• Active alerts — firing, acknowledged, pending rules
+
• Alert events (7d) — fired and resolved counts
+
• Top Traefik routers — avg req/s over last 24h (if plugin enabled)
+
+
+ + {# ── Send now ─────────────────────────────────────────────────────────────── #} +
+

Send Now

+

+ Send a report immediately regardless of schedule. Useful for testing. +

+
+ +
+
+ +
+{% endblock %}