feat(28-03): merge Hermes runtime data into stateJson and add HermesRuntimeCard

- Add OllamaPsResponse interface and getOllamaMemoryUsage() to ollama.ts
- Import getOllamaMemoryUsage in heartbeat.ts
- Add hermes_local block in updateRuntimeState: COALESCE jsonb merge of hermesModel + hermesMemoryBytes
- Add HermesRuntimeCard component in AgentDetail.tsx
- Render HermesRuntimeCard in AgentOverview gated by adapterType === hermes_local
- Native skill count derived from agentsApi.skills entries with originLabel === Hermes skill

server/src/services/heartbeat.ts

@@ -59,6 +59,7 @@ import {
   resolveSessionCompactionPolicy,
   type SessionCompactionPolicy,
 } from "@paperclipai/adapter-utils";
+import { getOllamaMemoryUsage } from "./ollama.js";
 
 const MAX_LIVE_LOG_CHUNK_BYTES = 8 * 1024;
 const HEARTBEAT_MAX_CONCURRENT_RUNS_DEFAULT = 1;
@@ -1905,6 +1906,27 @@ export function heartbeatService(db: Db) {
         occurredAt: new Date(),
       });
     }
+
+    if (agent.adapterType === "hermes_local") {
+      const hermesModel = result.model ?? null;
+      // Query Ollama /api/ps for memory usage (non-blocking, best-effort)
+      let hermesMemoryBytes: number | null = null;
+      try {
+        hermesMemoryBytes = await getOllamaMemoryUsage(hermesModel);
+      } catch {
+        // Ollama may not be running or model not loaded — acceptable
+      }
+      // Merge into stateJson using jsonb concat to avoid overwriting other fields
+      await db
+        .update(agentRuntimeState)
+        .set({
+          stateJson: sql`COALESCE(${agentRuntimeState.stateJson}, '{}'::jsonb) || ${JSON.stringify({
+            hermesModel,
+            hermesMemoryBytes,
+          })}::jsonb`,
+        })
+        .where(eq(agentRuntimeState.agentId, agent.id));
+    }
   }
 
   async function startNextQueuedRunForAgent(agentId: string) {

server/src/services/ollama.ts

@@ -1,4 +1,3 @@
-import { createRequire } from "node:module";
 import { fileURLToPath } from "node:url";
 import path from "node:path";
 import fs from "node:fs";
@@ -41,6 +40,25 @@ interface OllamaTagsResponse {
   }>;
 }
 
+interface OllamaPsResponse {
+  models: Array<{
+    name: string;
+    model: string;
+    size: number;
+    digest: string;
+    details: {
+      parent_model: string;
+      format: string;
+      family: string;
+      families: string[];
+      parameter_size: string;
+      quantization_level: string;
+    };
+    expires_at: string;
+    size_vram: number;
+  }>;
+}
+
 interface CatalogVariant {
   name: string;
   ramGb: number;
@@ -111,6 +129,25 @@ export async function listOllamaModels(): Promise<OllamaModel[]> {
   }
 }
 
+export async function getOllamaMemoryUsage(modelName: string | null): Promise<number | null> {
+  if (!modelName) return null;
+  const controller = new AbortController();
+  const timeout = setTimeout(() => controller.abort(), OLLAMA_TIMEOUT_MS);
+  try {
+    const res = await fetch(`${OLLAMA_BASE_URL}/api/ps`, {
+      signal: controller.signal,
+    });
+    if (!res.ok) return null;
+    const body = (await res.json()) as OllamaPsResponse;
+    const match = (body.models ?? []).find((m) => m.name === modelName || m.model === modelName);
+    return match?.size_vram ?? null;
+  } catch {
+    return null;
+  } finally {
+    clearTimeout(timeout);
+  }
+}
+
 const QUALITY_RANK: Record<string, number> = {
   best: 4,
   reasoning: 3,

ui/src/pages/AgentDetail.tsx

@@ -1163,6 +1163,52 @@ function LatestRunCard({ runs, agentId }: { runs: HeartbeatRun[]; agentId: strin
   );
 }
 
+/* ---- Hermes Runtime Card ---- */
+
+function HermesRuntimeCard({ runtimeState, agentId }: { runtimeState: AgentRuntimeState; agentId: string }) {
+  const hermesModel = runtimeState.stateJson?.hermesModel as string | undefined;
+  const hermesMemoryBytes = runtimeState.stateJson?.hermesMemoryBytes as number | null | undefined;
+
+  // Derive native skill count from existing skills query
+  const { data: skillsData } = useQuery({
+    queryKey: ["agents", agentId, "skills"],
+    queryFn: () => agentsApi.skills(agentId),
+  });
+  const nativeSkillCount = useMemo(() => {
+    if (!skillsData?.entries) return 0;
+    return skillsData.entries.filter((e) => e.originLabel === "Hermes skill").length;
+  }, [skillsData]);
+
+  const formatBytes = (bytes: number) => {
+    const gb = bytes / (1024 * 1024 * 1024);
+    return gb >= 1 ? `${gb.toFixed(1)} GB` : `${(bytes / (1024 * 1024)).toFixed(0)} MB`;
+  };
+
+  return (
+    <div className="rounded-lg border border-border p-4 space-y-3">
+      <h3 className="text-sm font-medium flex items-center gap-2">
+        Hermes Runtime
+      </h3>
+      <div className="grid grid-cols-3 gap-4">
+        <div>
+          <p className="text-xs text-muted-foreground">Model</p>
+          <p className="text-sm font-mono">{hermesModel ?? "Not set"}</p>
+        </div>
+        <div>
+          <p className="text-xs text-muted-foreground">Native Skills</p>
+          <p className="text-sm">{nativeSkillCount}</p>
+        </div>
+        <div>
+          <p className="text-xs text-muted-foreground">Memory (VRAM)</p>
+          <p className="text-sm">
+            {hermesMemoryBytes != null ? formatBytes(hermesMemoryBytes) : "Not loaded"}
+          </p>
+        </div>
+      </div>
+    </div>
+  );
+}
+
 /* ---- Agent Overview (main single-page view) ---- */
 
 function AgentOverview({
@@ -1201,6 +1247,11 @@ function AgentOverview({
         </ChartCard>
       </div>
 
+      {/* Hermes Runtime Info */}
+      {agent.adapterType === "hermes_local" && runtimeState && (
+        <HermesRuntimeCard runtimeState={runtimeState} agentId={agentId} />
+      )}
+
       {/* Recent Issues */}
       <div className="space-y-3">
         <div className="flex items-center justify-between">