feat(dashboard): unified Hosts widget + grouped widget picker

Bring the dashboard in line with the unified host IA + improved displays.

- New core "Hosts — Overview" widget (/hosts/overview/widget): one row per host
  combining monitor status (ping dot + latency, uptime 24h) with the agent
  glance (CPU / memory / disk root + stale flag), each row linking to the host
  hub. Reads agent data from the generic PluginMetric table via a core-safe
  _agent_overview_by_host helper (no host_agent import); freshness vs the
  plugin's stale window. The granular Ping/DNS/Uptime/Agent widgets stay.
- Group the add-widget picker into Core monitors / Monitoring capabilities /
  Integrations (a `group` field on every WIDGET_REGISTRY entry + section
  headings in _edit_panels.html), matching the Settings → Plugins taxonomy.
- Fix the agent fleet widget rows to link to the host hub (/hosts/<id>) instead
  of the old /plugins/host_agent/<id>/ page.

Scribe #903.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

steward/core/widgets.py

@@ -32,6 +32,16 @@ WIDGET_REGISTRY: dict[str, dict] = {
         "poll": True,
         "params": [],
     },
+    "hosts_overview": {
+        "key": "hosts_overview",
+        "label": "Hosts — Overview",
+        "description": "One row per host: monitor status + uptime and agent CPU/memory/disk, linking to the host hub",
+        "hx_url": "/hosts/overview/widget",
+        "detail_url": "/hosts/",
+        "plugin": None,
+        "poll": True,
+        "params": [],
+    },
     "uptime_summary": {
         "key": "uptime_summary",
         "label": "Uptime / SLA",
@@ -292,8 +302,34 @@ WIDGET_REGISTRY: dict[str, dict] = {
 }
 
 
+# Group each widget for the picker (Core monitors / Monitoring capabilities /
+# Integrations), mirroring the Settings → Plugins taxonomy. Capability plugins
+# are host/monitoring facets; traefik/unifi are discrete vendor integrations.
+_CORE_WIDGETS = {"ping", "dns", "status_overview", "uptime_summary", "hosts_overview"}
+_INTEGRATION_PLUGINS = {"traefik", "unifi"}
+GROUP_LABELS = {
+    "core": "Core monitors",
+    "capability": "Monitoring capabilities",
+    "integration": "Integrations",
+}
+GROUP_ORDER = ["core", "capability", "integration"]
+
+
+def _group_for(w: dict) -> str:
+    if w["key"] in _CORE_WIDGETS:
+        return "core"
+    if w.get("plugin") in _INTEGRATION_PLUGINS:
+        return "integration"
+    return "capability"
+
+
+for _w in WIDGET_REGISTRY.values():
+    _w["group"] = _group_for(_w)
+
+
 def register_widget(definition: dict) -> None:
     """Register a widget at runtime (used by external plugins)."""
+    definition.setdefault("group", _group_for(definition))
     WIDGET_REGISTRY[definition["key"]] = definition
 
 

steward/hosts/routes.py

@@ -104,6 +104,91 @@ async def _agent_metrics_by_host(db, host_names: list[str]) -> dict[str, dict]:
     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
+
+
+@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()
+        latest_ping_subq = (
+            select(PingResult.host_id, func.max(PingResult.probed_at).label("max_at"))
+            .group_by(PingResult.host_id).subquery()
+        )
+        latest_pings = {r.host_id: r for r in (await db.execute(
+            select(PingResult).join(
+                latest_ping_subq,
+                (PingResult.host_id == latest_ping_subq.c.host_id)
+                & (PingResult.probed_at == latest_ping_subq.c.max_at),
+            ))).scalars()}
+        latest_dns_subq = (
+            select(DnsResult.host_id, func.max(DnsResult.resolved_at).label("max_at"))
+            .group_by(DnsResult.host_id).subquery()
+        )
+        latest_dns = {r.host_id: r for r in (await db.execute(
+            select(DnsResult).join(
+                latest_dns_subq,
+                (DnsResult.host_id == latest_dns_subq.c.host_id)
+                & (DnsResult.resolved_at == latest_dns_subq.c.max_at),
+            ))).scalars()}
+        uptime = await _compute_uptime(db)
+        agent = await _agent_overview_by_host(db, [h.name for h in hosts])
+
+    return await render_template(
+        "hosts/overview_widget.html",
+        hosts=hosts, latest_pings=latest_pings, latest_dns=latest_dns,
+        uptime=uptime, agent=agent,
+    )
+
+
 @hosts_bp.get("/")
 @require_role(UserRole.viewer)
 async def list_hosts():

steward/templates/dashboard/_edit_panels.html

@@ -37,8 +37,13 @@
   <div>
     <div class="section-title" style="margin-bottom:0.75rem;">Available Widgets</div>
     {% if addable %}
+    {% set _groups = [("core", "Core monitors"), ("capability", "Monitoring capabilities"), ("integration", "Integrations")] %}
+    {% for _gkey, _glabel in _groups %}
+    {% set _gw = addable | selectattr("group", "equalto", _gkey) | list %}
+    {% if _gw %}
+    <div style="font-size:0.72rem;text-transform:uppercase;letter-spacing:0.04em;color:var(--text-dim);margin:0.85rem 0 0.35rem;">{{ _glabel }}</div>
     <div style="display:grid;gap:0.5rem;">
-      {% for w in addable %}
+      {% for w in _gw %}
       <div class="card" style="margin-bottom:0;padding:0;overflow:hidden;">
         <details>
           <summary style="display:flex;align-items:center;justify-content:space-between;gap:0.75rem;
@@ -97,6 +102,8 @@
       </div>
       {% endfor %}
     </div>
+    {% endif %}
+    {% endfor %}
     {% else %}
     <div style="color:var(--text-muted);font-size:0.85rem;padding:1rem 0;">
       No plugin widgets available. Enable plugins in Settings → Plugins.

steward/templates/hosts/overview_widget.html

@@ -0,0 +1,42 @@
+{# Unified Hosts widget — monitor status + agent glance per host, links to the hub. #}
+{% if hosts %}
+<div style="display:grid;gap:0.1rem;">
+  {% for host in hosts %}
+  {% set ping = latest_pings.get(host.id) %}
+  {% set dns = latest_dns.get(host.id) %}
+  {% set ut = uptime.get(host.id, {}) %}
+  {% set a = agent.get(host.name, {}) %}
+  {% set down = host.ping_enabled and ping and ping.status.value != 'up' %}
+  <div style="display:flex;align-items:center;gap:0.6rem;font-size:0.82rem;padding:0.3rem 0;border-bottom:1px solid var(--border);">
+    <span class="dot {% if down %}dot-down{% elif host.ping_enabled and ping %}dot-up{% else %}dot-dim{% endif %}"
+          title="{% if not host.ping_enabled %}ping off{% elif ping %}{{ ping.status.value }}{% else %}no data{% endif %}"></span>
+    <a href="/hosts/{{ host.id }}"
+       style="flex:1;min-width:0;white-space:nowrap;overflow:hidden;text-overflow:ellipsis;font-weight:500;">
+      {{ host.name }}
+    </a>
+    <span style="display:flex;gap:0.75rem;font-variant-numeric:tabular-nums;color:var(--text-muted);font-size:0.75rem;flex-shrink:0;">
+      {# Monitors #}
+      {% if host.ping_enabled and ping and ping.response_time_ms is not none %}
+      <span title="Ping latency"><span style="color:var(--text-dim);">ping</span> {{ "%.0f"|format(ping.response_time_ms) }}ms</span>
+      {% endif %}
+      {% if ut.get('24h') is not none %}
+      <span title="Uptime 24h"><span style="color:var(--text-dim);">24h</span> {{ "%.1f"|format(ut['24h']) }}%</span>
+      {% endif %}
+      {# Agent glance #}
+      {% if a %}
+      {% if a.get('cpu_pct') is not none %}<span title="CPU"><span style="color:var(--text-dim);">cpu</span> {{ "%.0f"|format(a.cpu_pct) }}%</span>{% endif %}
+      {% if a.get('mem_used_pct') is not none %}<span title="Memory"><span style="color:var(--text-dim);">mem</span> {{ "%.0f"|format(a.mem_used_pct) }}%</span>{% endif %}
+      {% if a.get('disk_root') is not none %}<span title="Root filesystem (/)"><span style="color:var(--text-dim);">disk /</span> {{ "%.0f"|format(a.disk_root) }}%</span>{% endif %}
+      {% if not a.fresh %}<span title="Agent data is stale" style="color:var(--yellow);">stale</span>{% endif %}
+      {% else %}
+      <span style="color:var(--text-dim);" title="No agent reporting">no agent</span>
+      {% endif %}
+    </span>
+  </div>
+  {% endfor %}
+</div>
+{% else %}
+<div class="empty" style="color:var(--text-muted);font-size:0.85rem;padding:0.5rem 0;">
+  No hosts yet. <a href="/hosts/new">Add one.</a>
+</div>
+{% endif %}