from __future__ import annotations import asyncio import uuid 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 steward.ansible import executor, sources as ansible_src from steward.auth.middleware import require_role from steward.core.audit import log_audit from steward.models.ansible import AnsibleRun, AnsibleRunStatus from steward.models.hosts import Host from steward.models.monitors import Monitor, MonitorResult from steward.models.users import UserRole from steward.core.status import _last_n_results, _uptime_by_monitor, _heartbeat_title hosts_bp = Blueprint("hosts", __name__, url_prefix="/hosts") def _ansible_source_names() -> list[str]: try: return [s["name"] for s in ansible_src.get_sources(current_app.config.get("ANSIBLE", {}))] except Exception: return [] async def _compute_uptime(db) -> dict[str, dict]: """Per-host uptime % for 24h/7d/30d, aggregated over the host's monitors. 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( Monitor.host_id, func.count(MonitorResult.id).label("total_30d"), func.sum(case((MonitorResult.is_up.is_(True), 1), else_=0)).label("up_30d"), func.sum(case((MonitorResult.checked_at >= cutoff_7d, 1), else_=0)).label("total_7d"), func.sum(case( (and_(MonitorResult.checked_at >= cutoff_7d, MonitorResult.is_up.is_(True)), 1), else_=0, )).label("up_7d"), func.sum(case((MonitorResult.checked_at >= cutoff_24h, 1), else_=0)).label("total_24h"), func.sum(case( (and_(MonitorResult.checked_at >= cutoff_24h, MonitorResult.is_up.is_(True)), 1), else_=0, )).label("up_24h"), ) .join(Monitor, Monitor.id == MonitorResult.monitor_id) .where(Monitor.host_id.isnot(None), MonitorResult.checked_at >= cutoff_30d) .group_by(Monitor.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 async def _host_status(db, host_ids: list[str]) -> dict[str, dict]: """Per-host status rollup from the latest result of each linked monitor. {host_id: {"state": "up"|"down"|"pending", "latency_ms": float|None, "count": int}}. State is down if ANY linked monitor's latest result is down (worst-case), up if at least one is up, else pending. """ if not host_ids: return {} rn = func.row_number().over( partition_by=MonitorResult.monitor_id, order_by=MonitorResult.checked_at.desc() ).label("rn") subq = ( select(MonitorResult.id, rn) .join(Monitor, Monitor.id == MonitorResult.monitor_id) .where(Monitor.host_id.in_(host_ids), Monitor.enabled.is_(True)) .subquery() ) rows = (await db.execute( select(MonitorResult, Monitor.host_id) .join(subq, MonitorResult.id == subq.c.id) .join(Monitor, Monitor.id == MonitorResult.monitor_id) .where(subq.c.rn == 1) )).all() out: dict[str, dict] = {} for res, host_id in rows: d = out.setdefault(host_id, {"state": "pending", "latency_ms": None, "count": 0}) d["count"] += 1 if not res.is_up: d["state"] = "down" elif d["state"] != "down": d["state"] = "up" if res.is_up and res.response_ms is not None: d["latency_ms"] = (res.response_ms if d["latency_ms"] is None else min(d["latency_ms"], res.response_ms)) return out async def _host_monitors(db, host_id: str) -> list[dict]: """Display rows for the monitors linked to one host (host hub section).""" monitors = (await db.execute( select(Monitor).where(Monitor.host_id == host_id).order_by(Monitor.name) )).scalars().all() ids = [m.id for m in monitors] recent = await _last_n_results(db, ids) uptime = await _uptime_by_monitor(db, ids) data = [] for m in monitors: mrows = recent.get(m.id, []) latest = mrows[-1] if mrows else None data.append({ "monitor": m, "latest": latest, "heartbeat": [{"state": "up" if r.is_up else "down", "title": _heartbeat_title(m.type, r)} for r in mrows], "uptime_pct": uptime.get(m.id, {}).get("24h"), }) return data async def _agent_metrics_by_host(db, host_names: list[str]) -> dict[str, dict]: """Latest agent cpu/mem per host name from the generic PluginMetric table. Read directly (PluginMetric is a core model) so the Hosts list can show an at-a-glance agent column without importing the host_agent plugin. """ from steward.models.metrics import PluginMetric if not host_names: return {} wanted = ("cpu_pct", "mem_used_pct") subq = ( select( PluginMetric.resource_name, PluginMetric.metric_name, func.max(PluginMetric.recorded_at).label("m"), ) .where( PluginMetric.source_module == "host_agent", PluginMetric.metric_name.in_(wanted), PluginMetric.resource_name.in_(host_names), ) .group_by(PluginMetric.resource_name, PluginMetric.metric_name) ).subquery() rows = (await db.execute( select(PluginMetric).join( subq, (PluginMetric.resource_name == subq.c.resource_name) & (PluginMetric.metric_name == subq.c.metric_name) & (PluginMetric.recorded_at == subq.c.m), ) )).scalars().all() out: dict[str, dict] = {} for r in rows: out.setdefault(r.resource_name, {})[r.metric_name] = r.value return out async def _agent_overview_by_host(db, host_names: list[str]) -> dict[str, dict]: """Per-host agent glance (cpu/mem/root-disk + freshness) from PluginMetric. Core-safe (no host_agent import). Freshness compares the latest host-level sample against the plugin's stale window (config), defaulting to 180s. """ from steward.models.metrics import PluginMetric if not host_names: return {} now = datetime.now(timezone.utc) stale_after = int( (current_app.config.get("PLUGINS", {}).get("host_agent", {}) or {}) .get("stale_after_seconds", 180)) resources = list(host_names) + [h + ":/" for h in host_names] subq = ( select( PluginMetric.resource_name, PluginMetric.metric_name, func.max(PluginMetric.recorded_at).label("m"), ) .where( PluginMetric.source_module == "host_agent", PluginMetric.resource_name.in_(resources), PluginMetric.metric_name.in_(("cpu_pct", "mem_used_pct", "disk_used_pct")), ) .group_by(PluginMetric.resource_name, PluginMetric.metric_name) ).subquery() rows = (await db.execute( select(PluginMetric).join( subq, (PluginMetric.resource_name == subq.c.resource_name) & (PluginMetric.metric_name == subq.c.metric_name) & (PluginMetric.recorded_at == subq.c.m), ).where(PluginMetric.source_module == "host_agent") )).scalars().all() out: dict[str, dict] = {} for r in rows: if r.resource_name.endswith(":/") and r.metric_name == "disk_used_pct": out.setdefault(r.resource_name[:-2], {})["disk_root"] = r.value elif r.resource_name in host_names: d = out.setdefault(r.resource_name, {}) d[r.metric_name] = r.value if d.get("_ts") is None or r.recorded_at > d["_ts"]: d["_ts"] = r.recorded_at for d in out.values(): ts = d.pop("_ts", None) d["fresh"] = bool(ts and (now - ts).total_seconds() <= stale_after) return out async def _agent_cpu_sparks_by_host(db, host_names: list[str], hours: int = 1) -> dict[str, str]: """{host_name: inline-SVG cpu sparkline} over the last `hours` (core-safe). A tiny at-a-glance trend in each row — the host-view sparkline, on the widget. """ from steward.models.metrics import PluginMetric from steward.core.status import sparkline_svg if not host_names: return {} cutoff = datetime.now(timezone.utc) - timedelta(hours=hours) rows = (await db.execute( select(PluginMetric.resource_name, PluginMetric.value, PluginMetric.recorded_at) .where( PluginMetric.source_module == "host_agent", PluginMetric.metric_name == "cpu_pct", PluginMetric.resource_name.in_(host_names), PluginMetric.recorded_at >= cutoff, ) .order_by(PluginMetric.recorded_at) )).all() by_host: dict[str, list[float]] = {} for r in rows: by_host.setdefault(r.resource_name, []).append(r.value) # Amber line to read as "CPU"; only draw when there are a couple of points. return { name: sparkline_svg(vals[-40:], width=64, height=18, stroke="#c8a840") for name, vals in by_host.items() if len(vals) >= 2 } @hosts_bp.get("/overview/widget") @require_role(UserRole.viewer) async def overview_widget(): """Dashboard widget: unified per-host monitor + agent glance, linking to the hub.""" async with current_app.db_sessionmaker() as db: hosts = (await db.execute(select(Host).order_by(Host.name))).scalars().all() host_status = await _host_status(db, [h.id for h in hosts]) uptime = await _compute_uptime(db) host_names = [h.name for h in hosts] agent = await _agent_overview_by_host(db, host_names) cpu_sparks = await _agent_cpu_sparks_by_host(db, host_names) return await render_template( "hosts/overview_widget.html", hosts=hosts, host_status=host_status, uptime=uptime, agent=agent, cpu_sparks=cpu_sparks, ) @hosts_bp.get("/") @require_role(UserRole.viewer) async def list_hosts(): async with current_app.db_sessionmaker() as db: result = await db.execute(select(Host).order_by(Host.name)) hosts = result.scalars().all() host_status = await _host_status(db, [h.id for h in hosts]) uptime = await _compute_uptime(db) agent_metrics = await _agent_metrics_by_host(db, [h.name for h in hosts]) return await render_template( "hosts/list.html", hosts=hosts, host_status=host_status, uptime=uptime, agent_metrics=agent_metrics, ) @hosts_bp.get("/") @require_role(UserRole.viewer) async def host_detail(host_id: str): """The host hub: monitors + agent (embedded fragment) + Ansible, one view.""" from steward.models.ansible_inventory import AnsibleTarget from sqlalchemy.orm import selectinload async with current_app.db_sessionmaker() as db: host = (await db.execute( select(Host).where(Host.id == host_id))).scalar_one_or_none() if host is None: return "Not found", 404 monitors = await _host_monitors(db, host_id) uptime = (await _compute_uptime(db)).get(host_id) linked_target = (await db.execute( select(AnsibleTarget).where(AnsibleTarget.host_id == host_id) .options(selectinload(AnsibleTarget.groups)))).scalar_one_or_none() linkable_targets = (await db.execute( select(AnsibleTarget).where(AnsibleTarget.host_id.is_(None)) .order_by(AnsibleTarget.name))).scalars().all() from steward.models.monitors import MonitorType return await render_template( "hosts/detail.html", host=host, monitors=monitors, uptime=uptime, monitor_types=list(MonitorType), linked_target=linked_target, linkable_targets=linkable_targets, ansible_sources=_ansible_source_names(), ) @hosts_bp.get("/new") @require_role(UserRole.operator) async def new_host(): return await render_template("hosts/form.html", host=None) @hosts_bp.post("/") @require_role(UserRole.operator) async def create_host(): form = await request.form host = Host( name=form["name"].strip(), address=form["address"].strip(), ) 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}) # Land on the new host's hub so monitors/agent/ansible can be set up next. return redirect(url_for("hosts.host_detail", host_id=host.id)) @hosts_bp.get("//edit") @require_role(UserRole.operator) async def edit_host(host_id: str): # Pure host config (name/address/monitors). Agent, Ansible target linking, # and playbook runs live on the host detail page (the hub), not here. async with current_app.db_sessionmaker() as db: result = await db.execute(select(Host).where(Host.id == host_id)) host = result.scalar_one_or_none() if host is None: return "Not found", 404 return await render_template("hosts/form.html", host=host) @hosts_bp.post("/") @require_role(UserRole.operator) async def update_host(host_id: str): form = await request.form 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 is None: return "Not found", 404 host.name = form["name"].strip() host.address = form["address"].strip() return redirect(url_for("hosts.host_detail", host_id=host_id)) @hosts_bp.post("//ansible-link") @require_role(UserRole.operator) async def ansible_link(host_id: str): """Link, unlink, or create an AnsibleTarget from this host.""" from steward.models.ansible_inventory import AnsibleTarget form = await request.form action = form.get("action", "") async with current_app.db_sessionmaker() as db: async with db.begin(): if action == "unlink": linked_result = await db.execute( select(AnsibleTarget).where(AnsibleTarget.host_id == host_id) ) linked = linked_result.scalar_one_or_none() if linked: linked.host_id = None elif action == "link": target_id = form.get("target_id", "").strip() if target_id: result = await db.execute( select(AnsibleTarget).where(AnsibleTarget.id == target_id) ) target = result.scalar_one_or_none() if target: # Clear any previous link for this host first old_result = await db.execute( select(AnsibleTarget).where(AnsibleTarget.host_id == host_id) ) old = old_result.scalar_one_or_none() if old and old.id != target_id: old.host_id = None target.host_id = host_id elif action == "create": host_result = await db.execute(select(Host).where(Host.id == host_id)) host = host_result.scalar_one_or_none() if host: new_target = AnsibleTarget( id=str(uuid.uuid4()), name=host.name, address=host.address, host_id=host_id, ) db.add(new_target) return redirect(f"/hosts/{host_id}") @hosts_bp.post("//run-playbook") @require_role(UserRole.operator) async def run_playbook(host_id: str): """Run an Ansible playbook against just this host (ephemeral one-host inventory).""" form = await request.form async with current_app.db_sessionmaker() as db: host = (await db.execute(select(Host).where(Host.id == host_id))).scalar_one_or_none() if host is None: return "Not found", 404 source_name = (form.get("source_name", "") or "").strip() playbook = (form.get("playbook_path", "") or "").strip() if not source_name or not playbook: return "source and playbook are required", 400 try: srcs = ansible_src.get_sources(current_app.config.get("ANSIBLE", {})) except Exception: return "Ansible sources are misconfigured", 400 source = next((s for s in srcs if s["name"] == source_name), None) if source is None: return "Source not found", 404 if playbook not in ansible_src.discover_playbooks(source["path"]): return f"Playbook '{playbook}' not found in source '{source_name}'", 404 # Shared parser: discovered var__ fields → extra_vars_map, secret__ → secret_vars # (unpersisted), plus tags/check. No --limit — there's exactly one host. from steward.ansible.routes import _parse_run_params params_or_none, secret_vars, err = _parse_run_params(form) if err: return err, 400 run_id = str(uuid.uuid4()) inv_content = ansible_src.host_inventory_content(host) run = AnsibleRun( id=run_id, playbook_path=playbook, inventory_path=f"host: {host.name}", source_name=source_name, triggered_by=session.get("user_id"), status=AnsibleRunStatus.running, params=params_or_none, ) async with current_app.db_sessionmaker() as db: async with db.begin(): db.add(run) task = asyncio.create_task( executor.start_run( current_app._get_current_object(), # type: ignore[attr-defined] run_id, playbook, f"host: {host.name}", source["path"], params_or_none, inv_content, secret_vars=secret_vars, ) ) task.add_done_callback( lambda t: t.exception() and current_app.logger.error( "Host playbook run %s raised: %s", run_id, t.exception())) await log_audit(current_app, session.get("user_id"), session.get("username", ""), "ansible.host_run", entity_type="host", entity_id=host.name, detail={"playbook": playbook, "source": source_name}) return redirect(url_for("ansible.run_detail", run_id=run_id)) @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).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, )