Split NodePerformanceProfile state storage into separate mappings

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

dashboard/src/lib/stores/app.svelte.ts

@@ -71,35 +71,36 @@ export interface Instance {
 	};
 }
 
-interface RawNodeProfile {
-	modelId?: string;
-	chipId?: string;
-	friendlyName?: string;
-	networkInterfaces?: Array<{
-		name?: string;
-		ipAddress?: string;
-		addresses?: Array<{ address?: string } | string>;
-		ipv4?: string;
-		ipv6?: string;
-		ipAddresses?: string[];
-		ips?: string[];
-	}>;
-	memory?: {
-		ramTotal?: { inBytes: number };
-		ramAvailable?: { inBytes: number };
-		swapTotal?: { inBytes: number };
-		swapAvailable?: { inBytes: number };
-	};
-	system?: {
-		gpuUsage?: number;
-		temp?: number;
-		sysPower?: number;
-	};
+// Split state interfaces
+interface RawNodeIdentity {
+	modelId: string;
+	chipId: string;
+	friendlyName: string;
+}
+
+interface RawNodeMemory {
+	ramTotal: { inBytes: number };
+	ramAvailable: { inBytes: number };
+	swapTotal: { inBytes: number };
+	swapAvailable: { inBytes: number };
+}
+
+interface RawNodeSystem {
+	gpuUsage?: number;
+	temp?: number;
+	sysPower?: number;
+	pcpuUsage?: number;
+	ecpuUsage?: number;
+	anePower?: number;
+}
+
+interface RawNetworkInterface {
+	name: string;
+	ipAddress: string;
 }
 
 interface RawTopologyNode {
 	nodeId: string;
-	nodeProfile: RawNodeProfile;
 }
 
 interface RawTopologyConnection {
@@ -115,8 +116,6 @@ interface RawTopology {
 	connections?: RawTopologyConnection[];
 }
 
-type RawNodeProfiles = Record<string, RawNodeProfile>;
-
 export interface DownloadProgress {
 	totalBytes: number;
 	downloadedBytes: number;
@@ -171,7 +170,11 @@ interface RawStateResponse {
 	>;
 	runners?: Record<string, unknown>;
 	downloads?: Record<string, unknown[]>;
-	nodeProfiles?: RawNodeProfiles;
+	// Split state fields
+	nodeIdentities?: Record<string, RawNodeIdentity>;
+	nodeMemories?: Record<string, RawNodeMemory>;
+	nodeSystems?: Record<string, RawNodeSystem>;
+	nodeNetworks?: Record<string, RawNetworkInterface[]>;
 }
 
 export interface MessageAttachment {
@@ -208,66 +211,41 @@ const STORAGE_KEY = "exo-conversations";
 
 function transformTopology(
 	raw: RawTopology,
-	profiles?: RawNodeProfiles,
+	identities?: Record<string, RawNodeIdentity>,
+	memories?: Record<string, RawNodeMemory>,
+	systems?: Record<string, RawNodeSystem>,
+	networks?: Record<string, RawNetworkInterface[]>,
 ): TopologyData {
 	const nodes: Record<string, NodeInfo> = {};
 	const edges: TopologyEdge[] = [];
 
 	for (const node of raw.nodes || []) {
-		const mergedProfile = profiles?.[node.nodeId];
-		const profile = { ...(node.nodeProfile ?? {}), ...(mergedProfile ?? {}) };
-		const ramTotal = profile?.memory?.ramTotal?.inBytes ?? 0;
-		const ramAvailable = profile?.memory?.ramAvailable?.inBytes ?? 0;
+		// Get split state fields (may be undefined if events haven't arrived yet)
+		const identity = identities?.[node.nodeId];
+		const memory = memories?.[node.nodeId];
+		const system = systems?.[node.nodeId];
+		const network = networks?.[node.nodeId];
+
+		const ramTotal = memory?.ramTotal?.inBytes ?? 0;
+		const ramAvailable = memory?.ramAvailable?.inBytes ?? 0;
 		const ramUsage = Math.max(ramTotal - ramAvailable, 0);
 
-		const networkInterfaces = (profile?.networkInterfaces || []).map(
-			(iface) => {
-				const addresses: string[] = [];
-				if (iface.ipAddress && typeof iface.ipAddress === "string") {
-					addresses.push(iface.ipAddress);
-				}
-				if (Array.isArray(iface.addresses)) {
-					for (const addr of iface.addresses) {
-						if (typeof addr === "string") addresses.push(addr);
-						else if (addr && typeof addr === "object" && addr.address)
-							addresses.push(addr.address);
-					}
-				}
-				if (Array.isArray(iface.ipAddresses)) {
-					addresses.push(
-						...iface.ipAddresses.filter(
-							(a): a is string => typeof a === "string",
-						),
-					);
-				}
-				if (Array.isArray(iface.ips)) {
-					addresses.push(
-						...iface.ips.filter((a): a is string => typeof a === "string"),
-					);
-				}
-				if (iface.ipv4 && typeof iface.ipv4 === "string")
-					addresses.push(iface.ipv4);
-				if (iface.ipv6 && typeof iface.ipv6 === "string")
-					addresses.push(iface.ipv6);
-
-				return {
-					name: iface.name,
-					addresses: Array.from(new Set(addresses)),
-				};
-			},
-		);
+		const networkInterfaces = (network ?? []).map((iface) => ({
+			name: iface.name,
+			addresses: [iface.ipAddress],
+		}));
 
 		const ipToInterface: Record<string, string> = {};
 		for (const iface of networkInterfaces) {
-			for (const addr of iface.addresses || []) {
-				ipToInterface[addr] = iface.name ?? "";
+			for (const addr of iface.addresses) {
+				ipToInterface[addr] = iface.name;
 			}
 		}
 
 		nodes[node.nodeId] = {
 			system_info: {
-				model_id: profile?.modelId ?? "Unknown",
-				chip: profile?.chipId,
+				model_id: identity?.modelId ?? "Unknown",
+				chip: identity?.chipId,
 				memory: ramTotal,
 			},
 			network_interfaces: networkInterfaces,
@@ -278,17 +256,15 @@ function transformTopology(
 					ram_total: ramTotal,
 				},
 				temp:
-					profile?.system?.temp !== undefined
-						? { gpu_temp_avg: profile.system.temp }
+					system?.temp !== undefined
+						? { gpu_temp_avg: system.temp }
 						: undefined,
 				gpu_usage:
-					profile?.system?.gpuUsage !== undefined
-						? [0, profile.system.gpuUsage]
-						: undefined,
-				sys_power: profile?.system?.sysPower,
+					system?.gpuUsage !== undefined ? [0, system.gpuUsage] : undefined,
+				sys_power: system?.sysPower,
 			},
 			last_macmon_update: Date.now() / 1000,
-			friendly_name: profile?.friendlyName,
+			friendly_name: identity?.friendlyName,
 		};
 	}
 
@@ -868,7 +844,13 @@ class AppStore {
 			const data: RawStateResponse = await response.json();
 
 			if (data.topology) {
-				this.topologyData = transformTopology(data.topology, data.nodeProfiles);
+				this.topologyData = transformTopology(
+					data.topology,
+					data.nodeIdentities,
+					data.nodeMemories,
+					data.nodeSystems,
+					data.nodeNetworks,
+				);
 			}
 			if (data.instances) {
 				this.instances = data.instances;

src/exo/master/api.py

@@ -599,9 +599,8 @@ class API:
         """Calculate total available memory across all nodes in bytes."""
         total_available = Memory()
 
-        for node in self.state.topology.list_nodes():
-            if node.node_profile is not None:
-                total_available += node.node_profile.memory.ram_available
+        for memory in self.state.node_memories.values():
+            total_available += memory.ram_available
 
         return total_available
 

src/exo/master/placement.py

@@ -113,6 +113,7 @@ def place_instance(
                 node.node_profile.memory.ram_available
                 for node in cycle
                 if node.node_profile is not None
+                and node.node_profile.memory is not None
             ),
             start=Memory(),
         ),

src/exo/master/placement_utils.py

@@ -25,7 +25,10 @@ class NodeWithProfile(BaseModel):
 
 
 def narrow_all_nodes(nodes: list[NodeInfo]) -> TypeGuard[list[NodeWithProfile]]:
-    return all(node.node_profile is not None for node in nodes)
+    return all(
+        node.node_profile is not None and node.node_profile.memory is not None
+        for node in nodes
+    )
 
 
 def filter_cycles_by_memory(
@@ -36,8 +39,14 @@ def filter_cycles_by_memory(
         if not narrow_all_nodes(cycle):
             continue
 
+        # narrow_all_nodes guarantees memory is not None
         total_mem = sum(
-            (node.node_profile.memory.ram_available for node in cycle), start=Memory()
+            (
+                node.node_profile.memory.ram_available
+                for node in cycle
+                if node.node_profile.memory is not None
+            ),
+            start=Memory(),
         )
         if total_mem >= required_memory:
             filtered_cycles.append(cast(list[NodeInfo], cycle))
@@ -53,8 +62,13 @@ def get_shard_assignments_for_pipeline_parallel(
     model_meta: ModelMetadata,
     selected_cycle: list[NodeWithProfile],
 ):
+    # NodeWithProfile guarantees memory is not None
     cycle_memory = sum(
-        (node.node_profile.memory.ram_available for node in selected_cycle),
+        (
+            node.node_profile.memory.ram_available
+            for node in selected_cycle
+            if node.node_profile.memory is not None
+        ),
         start=Memory(),
     )
     total_layers = model_meta.n_layers
@@ -67,6 +81,8 @@ def get_shard_assignments_for_pipeline_parallel(
         if i == len(selected_cycle) - 1:
             node_layers = total_layers - layers_assigned
         else:
+            # NodeWithProfile guarantees memory is not None
+            assert node.node_profile.memory is not None
             node_layers = round(
                 total_layers
                 * (

src/exo/master/tests/test_master.py

@@ -19,16 +19,13 @@ from exo.shared.types.events import (
     ForwarderEvent,
     IndexedEvent,
     InstanceCreated,
-    NodePerformanceMeasured,
+    NodeIdentityMeasured,
+    NodeMemoryMeasured,
     TaskCreated,
 )
 from exo.shared.types.memory import Memory
 from exo.shared.types.models import ModelId, ModelMetadata
-from exo.shared.types.profiling import (
-    MemoryPerformanceProfile,
-    NodePerformanceProfile,
-    SystemPerformanceProfile,
-)
+from exo.shared.types.profiling import MemoryPerformanceProfile
 from exo.shared.types.tasks import ChatCompletion as ChatCompletionTask
 from exo.shared.types.tasks import TaskStatus
 from exo.shared.types.worker.instances import (
@@ -75,29 +72,39 @@ async def test_master():
         tg.start_soon(master.run)
 
         sender_node_id = NodeId(f"{keypair.to_peer_id().to_base58()}_sender")
-        # inject a NodePerformanceProfile event
-        logger.info("inject a NodePerformanceProfile event")
+        # inject NodeIdentityMeasured and NodeMemoryMeasured events
+        logger.info("inject NodeIdentityMeasured event")
         await local_event_sender.send(
             ForwarderEvent(
                 origin_idx=0,
                 origin=sender_node_id,
                 session=session_id,
                 event=(
-                    NodePerformanceMeasured(
+                    NodeIdentityMeasured(
                         when=str(datetime.now(tz=timezone.utc)),
                         node_id=node_id,
-                        node_profile=NodePerformanceProfile(
-                            model_id="maccy",
-                            chip_id="arm",
-                            friendly_name="test",
-                            memory=MemoryPerformanceProfile(
-                                ram_total=Memory.from_bytes(678948 * 1024),
-                                ram_available=Memory.from_bytes(678948 * 1024),
-                                swap_total=Memory.from_bytes(0),
-                                swap_available=Memory.from_bytes(0),
-                            ),
-                            network_interfaces=[],
-                            system=SystemPerformanceProfile(),
+                        model_id="maccy",
+                        chip_id="arm",
+                        friendly_name="test",
+                    )
+                ),
+            )
+        )
+        logger.info("inject NodeMemoryMeasured event")
+        await local_event_sender.send(
+            ForwarderEvent(
+                origin_idx=1,
+                origin=sender_node_id,
+                session=session_id,
+                event=(
+                    NodeMemoryMeasured(
+                        when=str(datetime.now(tz=timezone.utc)),
+                        node_id=node_id,
+                        memory=MemoryPerformanceProfile(
+                            ram_total=Memory.from_bytes(678948 * 1024),
+                            ram_available=Memory.from_bytes(678948 * 1024),
+                            swap_total=Memory.from_bytes(0),
+                            swap_available=Memory.from_bytes(0),
                         ),
                     )
                 ),
@@ -108,7 +115,7 @@ async def test_master():
         logger.info("wait for initial topology event")
         while len(list(master.state.topology.list_nodes())) == 0:
             await anyio.sleep(0.001)
-        while len(master.state.node_profiles) == 0:
+        while len(master.state.node_identities) == 0:
             await anyio.sleep(0.001)
 
         logger.info("inject a CreateInstance Command")
@@ -155,17 +162,19 @@ async def test_master():
                 ),
             )
         )
-        while len(_get_events()) < 3:
+        while len(_get_events()) < 4:
             await anyio.sleep(0.01)
 
         events = _get_events()
-        assert len(events) == 3
+        assert len(events) == 4
         assert events[0].idx == 0
         assert events[1].idx == 1
         assert events[2].idx == 2
-        assert isinstance(events[0].event, NodePerformanceMeasured)
-        assert isinstance(events[1].event, InstanceCreated)
-        created_instance = events[1].event.instance
+        assert events[3].idx == 3
+        assert isinstance(events[0].event, NodeIdentityMeasured)
+        assert isinstance(events[1].event, NodeMemoryMeasured)
+        assert isinstance(events[2].event, InstanceCreated)
+        created_instance = events[2].event.instance
         assert isinstance(created_instance, MlxRingInstance)
         runner_id = list(created_instance.shard_assignments.runner_to_shard.keys())[0]
         # Validate the shard assignments
@@ -197,10 +206,10 @@ async def test_master():
         assert len(created_instance.hosts_by_node[node_id]) == 1
         assert created_instance.hosts_by_node[node_id][0].ip == "0.0.0.0"
         assert created_instance.ephemeral_port > 0
-        assert isinstance(events[2].event, TaskCreated)
-        assert events[2].event.task.task_status == TaskStatus.Pending
-        assert isinstance(events[2].event.task, ChatCompletionTask)
-        assert events[2].event.task.task_params == ChatCompletionTaskParams(
+        assert isinstance(events[3].event, TaskCreated)
+        assert events[3].event.task.task_status == TaskStatus.Pending
+        assert isinstance(events[3].event.task, ChatCompletionTask)
+        assert events[3].event.task.task_params == ChatCompletionTaskParams(
             model="llama-3.2-1b",
             messages=[
                 ChatCompletionMessage(role="user", content="Hello, how are you?")

src/exo/shared/apply.py

@@ -13,8 +13,10 @@ from exo.shared.types.events import (
     InstanceDeleted,
     NodeCreated,
     NodeDownloadProgress,
+    NodeIdentityMeasured,
     NodeMemoryMeasured,
-    NodePerformanceMeasured,
+    NodeNetworkMeasured,
+    NodeSystemMeasured,
     NodeTimedOut,
     RunnerDeleted,
     RunnerStatusUpdated,
@@ -27,7 +29,13 @@ from exo.shared.types.events import (
     TopologyEdgeCreated,
     TopologyEdgeDeleted,
 )
-from exo.shared.types.profiling import NodePerformanceProfile, SystemPerformanceProfile
+from exo.shared.types.profiling import (
+    MemoryPerformanceProfile,
+    NetworkInterfaceInfo,
+    NodeIdentity,
+    NodePerformanceProfile,
+    SystemPerformanceProfile,
+)
 from exo.shared.types.state import State
 from exo.shared.types.tasks import Task, TaskId, TaskStatus
 from exo.shared.types.topology import NodeInfo
@@ -51,8 +59,12 @@ def event_apply(event: Event, state: State) -> State:
             return apply_topology_node_created(event, state)
         case NodeTimedOut():
             return apply_node_timed_out(event, state)
-        case NodePerformanceMeasured():
-            return apply_node_performance_measured(event, state)
+        case NodeIdentityMeasured():
+            return apply_node_identity_measured(event, state)
+        case NodeSystemMeasured():
+            return apply_node_system_measured(event, state)
+        case NodeNetworkMeasured():
+            return apply_node_network_measured(event, state)
         case NodeDownloadProgress():
             return apply_node_download_progress(event, state)
         case NodeMemoryMeasured():
@@ -190,8 +202,19 @@ def apply_runner_deleted(event: RunnerDeleted, state: State) -> State:
 def apply_node_timed_out(event: NodeTimedOut, state: State) -> State:
     topology = copy.copy(state.topology)
     state.topology.remove_node(event.node_id)
-    node_profiles = {
-        key: value for key, value in state.node_profiles.items() if key != event.node_id
+    node_identities = {
+        key: value
+        for key, value in state.node_identities.items()
+        if key != event.node_id
+    }
+    node_memories = {
+        key: value for key, value in state.node_memories.items() if key != event.node_id
+    }
+    node_systems = {
+        key: value for key, value in state.node_systems.items() if key != event.node_id
+    }
+    node_networks = {
+        key: value for key, value in state.node_networks.items() if key != event.node_id
     }
     last_seen = {
         key: value for key, value in state.last_seen.items() if key != event.node_id
@@ -199,32 +222,120 @@ def apply_node_timed_out(event: NodeTimedOut, state: State) -> State:
     return state.model_copy(
         update={
             "topology": topology,
-            "node_profiles": node_profiles,
+            "node_identities": node_identities,
+            "node_memories": node_memories,
+            "node_systems": node_systems,
+            "node_networks": node_networks,
             "last_seen": last_seen,
         }
     )
 
 
-def apply_node_performance_measured(
-    event: NodePerformanceMeasured, state: State
-) -> State:
-    new_profiles: Mapping[NodeId, NodePerformanceProfile] = {
-        **state.node_profiles,
-        event.node_id: event.node_profile,
+def _reconstruct_profile(
+    node_id: NodeId,
+    state: State,
+    *,
+    identity: NodeIdentity | None = None,
+    memory: MemoryPerformanceProfile | None = None,
+    system: SystemPerformanceProfile | None = None,
+    network_interfaces: list[NetworkInterfaceInfo] | None = None,
+) -> NodePerformanceProfile:
+    """Reconstruct a NodePerformanceProfile from split state storage.
+
+    Uses provided overrides, falling back to state values.
+    """
+    ident = identity or state.node_identities.get(node_id)
+    mem = memory or state.node_memories.get(node_id)
+    sys = system or state.node_systems.get(node_id)
+    nets = (
+        network_interfaces
+        if network_interfaces is not None
+        else state.node_networks.get(node_id, [])
+    )
+
+    return NodePerformanceProfile(
+        model_id=ident.model_id if ident else None,
+        chip_id=ident.chip_id if ident else None,
+        friendly_name=ident.friendly_name if ident else None,
+        memory=mem,
+        network_interfaces=nets,
+        system=sys,
+    )
+
+
+def apply_node_identity_measured(event: NodeIdentityMeasured, state: State) -> State:
+    topology = copy.copy(state.topology)
+
+    identity = NodeIdentity(
+        model_id=event.model_id,
+        chip_id=event.chip_id,
+        friendly_name=event.friendly_name,
+    )
+    new_identities: Mapping[NodeId, NodeIdentity] = {
+        **state.node_identities,
+        event.node_id: identity,
     }
     last_seen: Mapping[NodeId, datetime] = {
         **state.last_seen,
         event.node_id: datetime.fromisoformat(event.when),
     }
-    state = state.model_copy(update={"node_profiles": new_profiles})
-    topology = copy.copy(state.topology)
-    # TODO: NodeCreated
     if not topology.contains_node(event.node_id):
         topology.add_node(NodeInfo(node_id=event.node_id))
-    topology.update_node_profile(event.node_id, event.node_profile)
+    reconstructed = _reconstruct_profile(event.node_id, state, identity=identity)
+    topology.update_node_profile(event.node_id, reconstructed)
     return state.model_copy(
         update={
-            "node_profiles": new_profiles,
+            "node_identities": new_identities,
+            "topology": topology,
+            "last_seen": last_seen,
+        }
+    )
+
+
+def apply_node_system_measured(event: NodeSystemMeasured, state: State) -> State:
+    topology = copy.copy(state.topology)
+
+    new_systems: Mapping[NodeId, SystemPerformanceProfile] = {
+        **state.node_systems,
+        event.node_id: event.system,
+    }
+    last_seen: Mapping[NodeId, datetime] = {
+        **state.last_seen,
+        event.node_id: datetime.fromisoformat(event.when),
+    }
+    if not topology.contains_node(event.node_id):
+        topology.add_node(NodeInfo(node_id=event.node_id))
+    reconstructed = _reconstruct_profile(event.node_id, state, system=event.system)
+    topology.update_node_profile(event.node_id, reconstructed)
+    return state.model_copy(
+        update={
+            "node_systems": new_systems,
+            "topology": topology,
+            "last_seen": last_seen,
+        }
+    )
+
+
+def apply_node_network_measured(event: NodeNetworkMeasured, state: State) -> State:
+    topology = copy.copy(state.topology)
+
+    new_networks: Mapping[NodeId, list[NetworkInterfaceInfo]] = {
+        **state.node_networks,
+        event.node_id: event.network_interfaces,
+    }
+    last_seen: Mapping[NodeId, datetime] = {
+        **state.last_seen,
+        event.node_id: datetime.fromisoformat(event.when),
+    }
+    if not topology.contains_node(event.node_id):
+        topology.add_node(NodeInfo(node_id=event.node_id))
+    reconstructed = _reconstruct_profile(
+        event.node_id, state, network_interfaces=event.network_interfaces
+    )
+    topology.update_node_profile(event.node_id, reconstructed)
+    return state.model_copy(
+        update={
+            "node_networks": new_networks,
             "topology": topology,
             "last_seen": last_seen,
         }
@@ -232,57 +343,26 @@ def apply_node_performance_measured(
 
 
 def apply_node_memory_measured(event: NodeMemoryMeasured, state: State) -> State:
-    existing = state.node_profiles.get(event.node_id)
     topology = copy.copy(state.topology)
 
-    if existing is None:
-        created = NodePerformanceProfile(
-            model_id="unknown",
-            chip_id="unknown",
-            friendly_name="Unknown",
-            memory=event.memory,
-            network_interfaces=[],
-            system=SystemPerformanceProfile(
-                # TODO: flops_fp16=0.0,
-                gpu_usage=0.0,
-                temp=0.0,
-                sys_power=0.0,
-                pcpu_usage=0.0,
-                ecpu_usage=0.0,
-                ane_power=0.0,
-            ),
-        )
-        created_profiles: Mapping[NodeId, NodePerformanceProfile] = {
-            **state.node_profiles,
-            event.node_id: created,
-        }
-        last_seen: Mapping[NodeId, datetime] = {
-            **state.last_seen,
-            event.node_id: datetime.fromisoformat(event.when),
-        }
-        if not topology.contains_node(event.node_id):
-            topology.add_node(NodeInfo(node_id=event.node_id))
-            # TODO: NodeCreated
-        topology.update_node_profile(event.node_id, created)
-        return state.model_copy(
-            update={
-                "node_profiles": created_profiles,
-                "topology": topology,
-                "last_seen": last_seen,
-            }
-        )
-
-    updated = existing.model_copy(update={"memory": event.memory})
-    updated_profiles: Mapping[NodeId, NodePerformanceProfile] = {
-        **state.node_profiles,
-        event.node_id: updated,
+    new_memories: Mapping[NodeId, MemoryPerformanceProfile] = {
+        **state.node_memories,
+        event.node_id: event.memory,
+    }
+    last_seen: Mapping[NodeId, datetime] = {
+        **state.last_seen,
+        event.node_id: datetime.fromisoformat(event.when),
     }
-    # TODO: NodeCreated
     if not topology.contains_node(event.node_id):
         topology.add_node(NodeInfo(node_id=event.node_id))
-    topology.update_node_profile(event.node_id, updated)
+    reconstructed = _reconstruct_profile(event.node_id, state, memory=event.memory)
+    topology.update_node_profile(event.node_id, reconstructed)
     return state.model_copy(
-        update={"node_profiles": updated_profiles, "topology": topology}
+        update={
+            "node_memories": new_memories,
+            "topology": topology,
+            "last_seen": last_seen,
+        }
     )
 
 

src/exo/shared/types/events.py

@@ -2,10 +2,14 @@ from datetime import datetime
 
 from pydantic import Field
 
-from exo.shared.topology import Connection, NodePerformanceProfile
+from exo.shared.topology import Connection
 from exo.shared.types.chunks import GenerationChunk
 from exo.shared.types.common import CommandId, Id, NodeId, SessionId
-from exo.shared.types.profiling import MemoryPerformanceProfile
+from exo.shared.types.profiling import (
+    MemoryPerformanceProfile,
+    NetworkInterfaceInfo,
+    SystemPerformanceProfile,
+)
 from exo.shared.types.tasks import Task, TaskId, TaskStatus
 from exo.shared.types.worker.downloads import DownloadProgress
 from exo.shared.types.worker.instances import Instance, InstanceId
@@ -85,13 +89,35 @@ class NodeTimedOut(BaseEvent):
     node_id: NodeId
 
 
-class NodePerformanceMeasured(BaseEvent):
+class NodeIdentityMeasured(BaseEvent):
+    """Static identity info - emitted once at startup."""
+
     node_id: NodeId
     when: str  # this is a manually cast datetime overrode by the master when the event is indexed, rather than the local time on the device
-    node_profile: NodePerformanceProfile
+    model_id: str
+    chip_id: str
+    friendly_name: str
+
+
+class NodeSystemMeasured(BaseEvent):
+    """Dynamic system metrics (GPU, temp, power) - emitted at 1s intervals."""
+
+    node_id: NodeId
+    when: str  # this is a manually cast datetime overrode by the master when the event is indexed, rather than the local time on the device
+    system: SystemPerformanceProfile
+
+
+class NodeNetworkMeasured(BaseEvent):
+    """Semi-static network interface info - emitted at 30s intervals."""
+
+    node_id: NodeId
+    when: str  # this is a manually cast datetime overrode by the master when the event is indexed, rather than the local time on the device
+    network_interfaces: list[NetworkInterfaceInfo]
 
 
 class NodeMemoryMeasured(BaseEvent):
+    """Dynamic memory metrics - emitted at 0.5s intervals."""
+
     node_id: NodeId
     when: str  # this is a manually cast datetime overrode by the master when the event is indexed, rather than the local time on the device
     memory: MemoryPerformanceProfile
@@ -127,7 +153,9 @@ Event = (
     | RunnerDeleted
     | NodeCreated
     | NodeTimedOut
-    | NodePerformanceMeasured
+    | NodeIdentityMeasured
+    | NodeSystemMeasured
+    | NodeNetworkMeasured
     | NodeMemoryMeasured
     | NodeDownloadProgress
     | ChunkGenerated

src/exo/shared/types/profiling.py

@@ -52,13 +52,21 @@ class NetworkInterfaceInfo(CamelCaseModel):
     ip_address: str
 
 
-class NodePerformanceProfile(CamelCaseModel):
+class NodeIdentity(CamelCaseModel):
+    """Static identity info for a node."""
+
     model_id: str
     chip_id: str
     friendly_name: str
-    memory: MemoryPerformanceProfile
+
+
+class NodePerformanceProfile(CamelCaseModel):
+    model_id: str | None = None
+    chip_id: str | None = None
+    friendly_name: str | None = None
+    memory: MemoryPerformanceProfile | None = None
     network_interfaces: list[NetworkInterfaceInfo] = []
-    system: SystemPerformanceProfile
+    system: SystemPerformanceProfile | None = None
 
 
 class ConnectionProfile(CamelCaseModel):

src/exo/shared/types/state.py

@@ -7,7 +7,12 @@ from pydantic.alias_generators import to_camel
 
 from exo.shared.topology import Topology, TopologySnapshot
 from exo.shared.types.common import NodeId
-from exo.shared.types.profiling import NodePerformanceProfile
+from exo.shared.types.profiling import (
+    MemoryPerformanceProfile,
+    NetworkInterfaceInfo,
+    NodeIdentity,
+    SystemPerformanceProfile,
+)
 from exo.shared.types.tasks import Task, TaskId
 from exo.shared.types.worker.downloads import DownloadProgress
 from exo.shared.types.worker.instances import Instance, InstanceId
@@ -35,7 +40,10 @@ class State(CamelCaseModel):
     runners: Mapping[RunnerId, RunnerStatus] = {}
     downloads: Mapping[NodeId, Sequence[DownloadProgress]] = {}
     tasks: Mapping[TaskId, Task] = {}
-    node_profiles: Mapping[NodeId, NodePerformanceProfile] = {}
+    node_identities: Mapping[NodeId, NodeIdentity] = {}
+    node_memories: Mapping[NodeId, MemoryPerformanceProfile] = {}
+    node_systems: Mapping[NodeId, SystemPerformanceProfile] = {}
+    node_networks: Mapping[NodeId, list[NetworkInterfaceInfo]] = {}
     last_seen: Mapping[NodeId, datetime] = {}
     topology: Topology = Field(default_factory=Topology)
     last_event_applied_idx: int = Field(default=-1, ge=-1)

src/exo/worker/main.py

@@ -16,8 +16,10 @@ from exo.shared.types.events import (
     ForwarderEvent,
     IndexedEvent,
     NodeDownloadProgress,
+    NodeIdentityMeasured,
     NodeMemoryMeasured,
-    NodePerformanceMeasured,
+    NodeNetworkMeasured,
+    NodeSystemMeasured,
     TaskCreated,
     TaskStatusUpdated,
     TopologyEdgeCreated,
@@ -25,7 +27,11 @@ from exo.shared.types.events import (
 )
 from exo.shared.types.models import ModelId
 from exo.shared.types.multiaddr import Multiaddr
-from exo.shared.types.profiling import MemoryPerformanceProfile, NodePerformanceProfile
+from exo.shared.types.profiling import (
+    MemoryPerformanceProfile,
+    NetworkInterfaceInfo,
+    SystemPerformanceProfile,
+)
 from exo.shared.types.state import State
 from exo.shared.types.tasks import (
     CreateRunner,
@@ -51,7 +57,13 @@ from exo.worker.download.download_utils import (
 from exo.worker.download.shard_downloader import RepoDownloadProgress, ShardDownloader
 from exo.worker.plan import plan
 from exo.worker.runner.runner_supervisor import RunnerSupervisor
-from exo.worker.utils import start_polling_memory_metrics, start_polling_node_metrics
+from exo.worker.utils import (
+    IdentityMetrics,
+    start_polling_identity_metrics,
+    start_polling_memory_metrics,
+    start_polling_network_metrics,
+    start_polling_system_metrics,
+)
 from exo.worker.utils.net_profile import check_reachable
 
 
@@ -98,37 +110,51 @@ class Worker:
     async def run(self):
         logger.info("Starting Worker")
 
-        # TODO: CLEANUP HEADER
-        async def resource_monitor_callback(
-            node_performance_profile: NodePerformanceProfile,
-        ) -> None:
+        async def identity_callback(identity: IdentityMetrics) -> None:
             await self.event_sender.send(
-                NodePerformanceMeasured(
+                NodeIdentityMeasured(
                     node_id=self.node_id,
-                    node_profile=node_performance_profile,
+                    model_id=identity.model_id,
+                    chip_id=identity.chip_id,
+                    friendly_name=identity.friendly_name,
                     when=str(datetime.now(tz=timezone.utc)),
                 ),
             )
 
-        async def memory_monitor_callback(
-            memory_profile: MemoryPerformanceProfile,
-        ) -> None:
+        async def system_callback(system: SystemPerformanceProfile) -> None:
+            await self.event_sender.send(
+                NodeSystemMeasured(
+                    node_id=self.node_id,
+                    system=system,
+                    when=str(datetime.now(tz=timezone.utc)),
+                ),
+            )
+
+        async def network_callback(interfaces: list[NetworkInterfaceInfo]) -> None:
+            await self.event_sender.send(
+                NodeNetworkMeasured(
+                    node_id=self.node_id,
+                    network_interfaces=interfaces,
+                    when=str(datetime.now(tz=timezone.utc)),
+                ),
+            )
+
+        async def memory_callback(memory: MemoryPerformanceProfile) -> None:
             await self.event_sender.send(
                 NodeMemoryMeasured(
                     node_id=self.node_id,
-                    memory=memory_profile,
+                    memory=memory,
                     when=str(datetime.now(tz=timezone.utc)),
                 )
             )
 
-        # END CLEANUP
-
         async with create_task_group() as tg:
             self._tg = tg
             tg.start_soon(self.plan_step)
-            tg.start_soon(start_polling_node_metrics, resource_monitor_callback)
-
-            tg.start_soon(start_polling_memory_metrics, memory_monitor_callback)
+            tg.start_soon(start_polling_identity_metrics, identity_callback)
+            tg.start_soon(start_polling_system_metrics, system_callback)
+            tg.start_soon(start_polling_network_metrics, network_callback)
+            tg.start_soon(start_polling_memory_metrics, memory_callback)
             tg.start_soon(self._emit_existing_download_progress)
             tg.start_soon(self._connection_message_event_writer)
             tg.start_soon(self._resend_out_for_delivery)

src/exo/worker/utils/__init__.py

@@ -1,6 +1,15 @@
-from .profile import start_polling_memory_metrics, start_polling_node_metrics
+from .profile import (
+    IdentityMetrics,
+    start_polling_identity_metrics,
+    start_polling_memory_metrics,
+    start_polling_network_metrics,
+    start_polling_system_metrics,
+)
 
 __all__ = [
-    "start_polling_node_metrics",
+    "IdentityMetrics",
+    "start_polling_identity_metrics",
     "start_polling_memory_metrics",
+    "start_polling_network_metrics",
+    "start_polling_system_metrics",
 ]

src/exo/worker/utils/profile.py

@@ -1,6 +1,7 @@
 import asyncio
 import os
 import platform
+from dataclasses import dataclass
 from typing import Any, Callable, Coroutine
 
 import anyio
@@ -9,7 +10,7 @@ from loguru import logger
 from exo.shared.types.memory import Memory
 from exo.shared.types.profiling import (
     MemoryPerformanceProfile,
-    NodePerformanceProfile,
+    NetworkInterfaceInfo,
     SystemPerformanceProfile,
 )
 
@@ -27,6 +28,13 @@ from .system_info import (
 )
 
 
+@dataclass(frozen=True)
+class IdentityMetrics:
+    model_id: str
+    chip_id: str
+    friendly_name: str
+
+
 async def get_metrics_async() -> Metrics | None:
     """Return detailed Metrics on macOS or a minimal fallback elsewhere."""
 
@@ -67,48 +75,73 @@ async def start_polling_memory_metrics(
             await anyio.sleep(poll_interval_s)
 
 
-async def start_polling_node_metrics(
-    callback: Callable[[NodePerformanceProfile], Coroutine[Any, Any, None]],
-):
-    poll_interval_s = 1.0
+async def start_polling_identity_metrics(
+    callback: Callable[[IdentityMetrics], Coroutine[Any, Any, None]],
+    *,
+    poll_interval_s: float = 30.0,
+) -> None:
+    """Continuously poll and emit identity metrics at 30s intervals."""
+    while True:
+        try:
+            model_id, chip_id = await get_model_and_chip()
+            friendly_name = await get_friendly_name()
+            await callback(
+                IdentityMetrics(
+                    model_id=model_id,
+                    chip_id=chip_id,
+                    friendly_name=friendly_name,
+                )
+            )
+        except Exception as e:
+            logger.opt(exception=e).error("Failed to emit identity metrics")
+        finally:
+            await anyio.sleep(poll_interval_s)
+
+
+async def start_polling_system_metrics(
+    callback: Callable[[SystemPerformanceProfile], Coroutine[Any, Any, None]],
+    *,
+    poll_interval_s: float = 1.0,
+) -> None:
+    """Continuously poll and emit system metrics (GPU, temp, power) at 1s intervals."""
     while True:
         try:
             metrics = await get_metrics_async()
             if metrics is None:
                 return
 
-            network_interfaces = get_network_interfaces()
-            # these awaits could be joined but realistically they should be cached
-            model_id, chip_id = await get_model_and_chip()
-            friendly_name = await get_friendly_name()
-
-            # do the memory profile last to get a fresh reading to not conflict with the other memory profiling loop
-            memory_profile = get_memory_profile()
-
             await callback(
-                NodePerformanceProfile(
-                    model_id=model_id,
-                    chip_id=chip_id,
-                    friendly_name=friendly_name,
-                    network_interfaces=network_interfaces,
-                    memory=memory_profile,
-                    system=SystemPerformanceProfile(
-                        gpu_usage=metrics.gpu_usage[1],
-                        temp=metrics.temp.gpu_temp_avg,
-                        sys_power=metrics.sys_power,
-                        pcpu_usage=metrics.pcpu_usage[1],
-                        ecpu_usage=metrics.ecpu_usage[1],
-                        ane_power=metrics.ane_power,
-                    ),
+                SystemPerformanceProfile(
+                    gpu_usage=metrics.gpu_usage[1],
+                    temp=metrics.temp.gpu_temp_avg,
+                    sys_power=metrics.sys_power,
+                    pcpu_usage=metrics.pcpu_usage[1],
+                    ecpu_usage=metrics.ecpu_usage[1],
+                    ane_power=metrics.ane_power,
                 )
             )
-
         except asyncio.TimeoutError:
             logger.warning(
-                "[resource_monitor] Operation timed out after 30s, skipping this cycle."
+                "[system_monitor] Operation timed out after 30s, skipping this cycle."
             )
         except MacMonError as e:
-            logger.opt(exception=e).error("Resource Monitor encountered error")
+            logger.opt(exception=e).error("System Monitor encountered error")
             return
         finally:
             await anyio.sleep(poll_interval_s)
+
+
+async def start_polling_network_metrics(
+    callback: Callable[[list[NetworkInterfaceInfo]], Coroutine[Any, Any, None]],
+    *,
+    poll_interval_s: float = 30.0,
+) -> None:
+    """Continuously poll and emit network interface info at 30s intervals."""
+    while True:
+        try:
+            network_interfaces = get_network_interfaces()
+            await callback(network_interfaces)
+        except Exception as e:
+            logger.opt(exception=e).error("Network Monitor encountered error")
+        finally:
+            await anyio.sleep(poll_interval_s)