feat(#3494): provision the claude-usage dashboard

Dashboard 2 of the set the operator asked for: how Claude is being used
rather than which agent is using it, so the axes are model, effort, token
type and query source. The only deliberate overlap with the agents page
is the cost/token headline.

Every panel was run against the live store before this landed. Three
panels were dropped rather than shipped, because their label has exactly
one live value today and a page of single-bar charts is the same silent
failure as an empty one.

Turn count and turn length are PROXIES and say so in their descriptions:
nothing exports turn stats, so a session record stands in for a turn,
which holds because each turn runs a new claude process.

nix/host-modules/swarm-grafana.nix

@@ -46,10 +46,15 @@ let
   # Grafana's file provider wants a DIRECTORY to scan, so the rendered files are
   # collected into one.
   dashboardDir = pkgs.linkFarm "hyperhive-grafana-dashboards" (
-    map (name: {
-      inherit name;
-      path = renderDashboard name;
-    }) [ "agents.json" ]
+    map
+      (name: {
+        inherit name;
+        path = renderDashboard name;
+      })
+      [
+        "agents.json"
+        "claude-usage.json"
+      ]
   );
 
   # Total on a null swarm domain for the same reason every sibling module is: