ON/OFF: WorldMonitor group toggle — controller supports multi-target groups (aggregate state, one switch for 4 containers), console card wired (admin), partial-state pill

deploy/service-controller/service_controller.py

@@ -101,23 +101,49 @@ def _do(kind: str, action: str, target: str) -> str:
     return _systemd_user_state(target)
 
 
-def _describe(s: dict[str, Any]) -> dict[str, Any]:
-    state = "unknown"
-    if s["kind"] == "container":
-        state = _container_state(s["target"])
+def _targets(s: dict[str, Any]) -> list[str]:
+    """A service is either a single `target` or a group `targets` list."""
+    t = s.get("targets")
+    if isinstance(t, list) and t:
+        return [str(x) for x in t]
+    single = s.get("target")
+    return [single] if single else []
+
+
+def _probe(s: dict[str, Any]) -> tuple[str, list[str]]:
+    """Collect the state of every target. Returns (aggregate, per-target list).
+    Aggregate: running if ANY is running; stopped if ALL stopped; else partial."""
+    kind = s["kind"]
+    states = []
+    for tgt in _targets(s):
+        if kind == "container":
+            states.append(_container_state(tgt))
+        else:
+            states.append(_systemd_user_state(tgt))
+    n_ok = sum(1 for st in states if st in ("running", "active", "started"))
+    n_none = sum(1 for st in states if st in ("unknown",)) or 0
+    if n_ok == len(states):
+        agg = "running"
+    elif n_ok == 0 and len(states):
+        agg = "stopped"
     else:
-        state = _systemd_user_state(s["target"])
+        agg = "partial" if len(states) else "unknown"
+    return agg, states
+
+
+def _describe(s: dict[str, Any]) -> dict[str, Any]:
+    agg, states = _probe(s)
     return {
         "id": s["id"],
         "kind": s["kind"],
-        "target": s["target"],
+        "target": s.get("target", ""),
+        "targets": s.get("targets", []),
         "group": s.get("group", ""),
         "label": s.get("label", s["id"]),
         "ram_mb": s.get("ram_mb"),
         "default_state": s.get("default_state", "stopped"),
         "who": s.get("who", []),
-        "state": "running" if state in ("running", "active") else
-                ("stopped" if state in ("stopped", "inactive", "exited") else "unknown"),
+        "state": agg,
         "error": None,
     }
 
@@ -158,9 +184,12 @@ async def service_action(sid: str, action: str,
     if s is None:
         raise HTTPException(status_code=404, detail="unknown service")
     actor = (who or "unknown-user").strip()[:40]
-    state = _do(s["kind"], action, s["target"])
-    audit(f"{actor} {action} {sid} -> {state}")
-    return {"ok": True, "id": sid, "state": state}
+    results = {}
+    for tgt in _targets(s):
+        results[tgt] = _do(s["kind"], action, tgt)
+    agg, _ = _probe(s)
+    audit(f"{actor} {action} {sid} -> {agg} ({len(_targets(s))} targets)")
+    return {"ok": True, "id": sid, "state": agg, "targets": results}
 
 
 if __name__ == "__main__":

deploy/service-controller/services.toml

@@ -83,3 +83,14 @@ label = "Photo pipeline dashboard"
 ram_mb = 112
 default_state = "running"
 who = ["sam"]
+
+# WorldMonitor — 4-container group (UI + relay + redis + rest). One switch for all.
+[[services]]
+id = "worldmonitor"
+kind = "container"
+targets = ["worldmonitor", "worldmonitor-ais-relay", "worldmonitor-redis", "worldmonitor-redis-rest"]
+group = "admin"
+label = "World Monitor"
+ram_mb = 120
+default_state = "running"
+who = ["sam"]

portal/static/app.css

@@ -401,6 +401,7 @@ button.button, input[type="submit"].button { font-family: inherit; }
 .svc-dot.svc-off { background: var(--ink-faint, #a39e98); }
 .svc-dot.svc-trans { background: var(--accent-orange, #dd5b00); animation: pulse 1.2s ease-in-out infinite; }
 .svc-dot.svc-fail { background: #d33a2b; }
+.svc-dot.svc-part { background: var(--accent-orange, #dd5b00); } /* partial: some group members running */
 @keyframes pulse { 0%,100% { opacity: 1; } 50% { opacity: .35; } }
 .svc-ram { margin-left: auto; font: var(--type-caption); color: var(--ink-faint); white-space: nowrap; }
 .button-sm { padding: 4px 10px; font-size: 12px; }

portal/templates/partials/_sections.html

@@ -126,8 +126,10 @@
         var can = svcState[id] && svcState[id].can_toggle;
         var transitional = st === "starting" || st === "stopping";
         if (ram && svcState[id] && svcState[id].ram_mb) ram.textContent = "~" + svcState[id].ram_mb + "MB";
-        dot.className = "svc-dot svc-" + (st === "running" ? "on" : st === "stopped" ? "off" : st === "failed" ? "fail" : "trans");
-        if (lab) lab.textContent = st === "running" ? "Running" : st === "stopped" ? "Stopped" : st === "failed" ? (svcState[id].error || "Failed") : (st[0].toUpperCase() + st.slice(1));
+        var cls = st === "running" ? "on" : st === "stopped" ? "off" : (st === "failed" ? "fail" : st === "partial" ? "part" : "trans");
+        dot.className = "svc-dot svc-" + cls;
+        if (lab) lab.textContent = st === "running" ? "Running" : st === "stopped" ? "Stopped" : st === "failed" ? (svcState[id].error || "Failed") : st === "partial" ? "Partial" : (st[0].toUpperCase() + st.slice(1));
+        // partial behaves like running for the button (offered action: stop the rest)
         // failed -> offer the logs deep link (dozzle)
         var logs = strip.querySelector("[data-svc-logs]");
         if (logs) {

portal/tools.py

@@ -282,7 +282,9 @@ def _cat() -> list[Tool]:
         Tool("ntfy", "Ntfy", "infra",
              "Push notifications (LAN)", "https://ntfy.home.lab", login=True, lan=True),
         Tool("worldmonitor", "World Monitor", "infra",
-             "Global monitoring", "https://worldmonitor.lab.audasmedia.com.au", login=True, admin=True),
+             "Global monitoring", "https://worldmonitor.lab.audasmedia.com.au", login=True, admin=True,
+             service_id="worldmonitor", ram_mb=120, togglable=True,
+             admin_service=True),
         Tool("homepage", "Homepage", "infra",
              "Start page", "https://homepage.lab.audasmedia.com.au", login=True),
         Tool("librenms", "LibreNMS", "network",