node metrics

.claude/memory/project-status.md

@@ -8,6 +8,11 @@ metadata:
 
 # Project Status (2026-07-13)
 
+## Selected-node model placement (2026-07-14)
+
+- Admin Model placement now opens a node selector for load and release; the control-plane accepts optional `node_id` and targets only that registry assignment. Multi-model serving remains supported through `ADD_SHARD` and `max_loaded_shards`.
+- Total node pool resource values are rendered from `/v1/network/map`'s `node.capacity` contract. Route selection remains assignment/capability/throughput/queue based; capacity is used for placement and falls back to tracker defaults only if a node truly omits it.
+
 ## Distributed inference performance (2026-07-14)
 
 `DIP-001` is done in `.scratch/distributed-inference-performance/`: the deterministic two-node Route Session stub benchmark covers direct/relay plus cached/stateless prefill and decode. Its JSON and concise summary explicitly attribute model execution, activation encode/decode, compression, connection setup, relay queueing, local HTTP forwarding, and end-to-end seam latency. `PYTHONPATH=packages/node pytest -q tests/test_route_session_benchmark.py` passed (7); the fixture assertion checks output-token identity and connection attempts.

_DEV_NOTES.md

@@ -16,12 +16,9 @@
 
 
 .\.venv\Scripts\meshnet-node.exe start http://192.168.0.179:8081 --model-id Qwen/Qwen2.5-0.5B-Instruct  --advertise-host 192.168.0.20
- .\.venv\Scripts\meshnet-node.exe start --tracker http://ai.neuron.d-popov.com  --model-id Qwen/Qwen2.5-0.5B-Instruct  --advertise-host 192.168.0.20      
+ .\.venv\Scripts\meshnet-node.exe start --tracker http://ai.neuron.d-popov.com  --model Qwen/Qwen2.5-0.5B-Instruct  --advertise-host 192.168.0.20      
 
- we .\.venv\Scripts\meshnet-node.exe start `                                                                                                                                            
+ we .\.venv\Scripts\meshnet-node.exe start --tracker http://192.168.0.179:8081 --model Qwen/Qwen2.5-0.5B-Instruct
-    --tracker http://192.168.0.179:8081 `                                                                                                                                             
-    --model Qwen/Qwen2.5-0.5B-Instruct `                                                                                                                                              
-    --advertise-host 192.168.0.20                                                                                                                                                     
    #  trackers:
  https://meshnet.2.d-popov.com 
  https://ai.neuron.d-popov.com 

packages/tracker/meshnet_tracker/dashboard.html

@@ -44,12 +44,15 @@
   .empty { color:var(--dim); font-style:italic; }
   .pill { display:inline-block; padding:0 7px; border-radius:9px;
           border:1px solid var(--border); font-size:11px; }
-  input, button { font:inherit; color:var(--fg); background:var(--bg);
+  input, button, select { font:inherit; color:var(--fg); background:var(--bg);
           border:1px solid var(--border); border-radius:6px; padding:5px 8px; }
   input { width:100%; margin-bottom:6px; }
   button { cursor:pointer; color:var(--accent); }
   button:hover { border-color:var(--accent); }
   button.small { font-size:11px; padding:1px 7px; }
+  dialog { color:var(--fg); background:var(--panel); border:1px solid var(--border); border-radius:8px; min-width:min(420px,calc(100vw - 32px)); }
+  dialog::backdrop { background:rgba(0,0,0,.55); }
+  .placement-dialog-actions { display:flex; justify-content:flex-end; gap:8px; margin-top:12px; }
   .form-row { display:flex; gap:8px; }
   .form-row button { white-space:nowrap; }
   .error-msg { color:var(--bad); font-size:12px; min-height:16px; }
@@ -324,6 +327,14 @@
     <div id="testing-log" class="console empty">no test output yet</div>
   </section>
 </main>
+<dialog id="model-placement-dialog">
+  <form method="dialog">
+    <div id="model-placement-dialog-title"></div>
+    <label for="model-placement-node">Node</label>
+    <select id="model-placement-node"></select>
+    <div class="placement-dialog-actions"><button value="cancel">Cancel</button><button value="confirm">Confirm</button></div>
+  </form>
+</dialog>
 <script>
 "use strict";
 const $ = id => document.getElementById(id);
@@ -1801,16 +1812,16 @@ async function requestSelectedModelLoad() {
   $("chat-status").textContent = `load queued on ${short(assignment.node_id || "node")} for layers ${assignment.shard_start}-${assignment.shard_end}`;
 }
 
-async function requestAdminModelLoad(model) {
+async function requestAdminModelLoad(model, nodeId) {
-  const result = await apiCall("/v1/models/load", "POST", { model, force: true });
+  const result = await apiCall("/v1/models/load", "POST", { model, node_id: nodeId, force: true });
   if (!result.ok) return showAdminModelPlacementStatus(result.data.error || "model load request failed", true);
   const assignment = result.data.assignment || {};
   showAdminModelPlacementStatus(`Load queued on ${short(assignment.node_id || "node")} for ${model}.`);
   await refreshActiveTab(true);
 }
 
-async function releaseAdminModel(model) {
+async function releaseAdminModel(model, nodeId) {
-  const result = await apiCall("/v1/models/release", "POST", { model });
+  const result = await apiCall("/v1/models/release", "POST", { model, node_id: nodeId });
   if (!result.ok) return showAdminModelPlacementStatus(result.data.error || "model release request failed", true);
   showAdminModelPlacementStatus(`Release queued for ${result.data.released || 0} node(s) serving ${model}.`);
   await refreshActiveTab(true);
@@ -1836,6 +1847,9 @@ function renderAdminNodePool(map) {
     html += table(["node", "assignment", "state / slots", "RAM", "GPU / VRAM", "model drive"], nodes.map(node => {
       const hw = node.hardware_profile || {};
       const cap = node.capacity || {};
+      // The network map keeps reported resource capacity under `capacity`.
+      node.ram_bytes = cap.ram_bytes ?? node.ram_bytes;
+      node.vram_bytes = cap.vram_bytes ?? node.vram_bytes;
       const disk = hw.model_drive_free_bytes ?? hw.model_path_free_bytes ?? hw.disk_free_bytes;
       const gpu = hw.gpu_name || (hw.cuda_available ? "CUDA GPU" : "CPU only");
       return [nodeDisplayCell(node), esc(node.hf_repo || node.model || "unassigned"),
@@ -1866,10 +1880,26 @@ function renderAdminModelPlacement(models, map) {
 $("admin-model-placement").addEventListener("click", event => {
   const load = event.target.closest("[data-admin-model-load]");
   const release = event.target.closest("[data-admin-model-release]");
-  if (load) void requestAdminModelLoad(load.dataset.adminModelLoad);
+  if (load) void chooseModelPlacementNode("load", load.dataset.adminModelLoad);
-  if (release) void releaseAdminModel(release.dataset.adminModelRelease);
+  if (release) void chooseModelPlacementNode("release", release.dataset.adminModelRelease);
 });
 
+function chooseModelPlacementNode(action, model) {
+  const dialog = $("model-placement-dialog");
+  const select = $("model-placement-node");
+  const aliases = new Set([model].filter(Boolean));
+  const nodes = (lastNetworkMap?.nodes || []).filter(node => action === "load" || aliases.has(node.model) || aliases.has(node.hf_repo));
+  if (!nodes.length) return showAdminModelPlacementStatus(`No node can ${action} ${model}.`, true);
+  $("model-placement-dialog-title").textContent = `${action === "load" ? "Load" : "Release"} ${model} on a node`;
+  select.innerHTML = nodes.map(node => `<option value="${esc(node.node_id)}">${esc(short(node.friendly_name || node.node_id, 20))} — ${esc(node.hf_repo || node.model || "unassigned")}</option>`).join("");
+  dialog.onclose = () => {
+    if (dialog.returnValue !== "confirm") return;
+    if (action === "load") void requestAdminModelLoad(model, select.value);
+    else void releaseAdminModel(model, select.value);
+  };
+  dialog.showModal();
+}
+
 function chatAuthToken() {
   if (accountApiKeys.length) return accountApiKeys[0];
   return null;
@@ -2512,6 +2542,7 @@ async function fetchAdminTab() {
   if (isAdmin) fetches.push(apiCall("/v1/admin/accounts"));
   const results = await Promise.all(fetches);
   const [raft, consoleData, summary, wallets, models, map, adminResp] = results;
+  if (map) lastNetworkMap = map;
   renderIfChanged("hive", raft, renderHive);
   renderIfChanged("console", consoleData, renderConsole);
   renderIfChanged("billing-summary", summary, data => renderBilling(data));

packages/tracker/meshnet_tracker/server.py

@@ -1494,7 +1494,9 @@ def _scale_demanded_models_locked(server: "_TrackerHTTPServer") -> None:
             break
 
 
-def _request_model_load_locked(server: "_TrackerHTTPServer", model_key: str) -> dict | None:
+def _request_model_load_locked(
+    server: "_TrackerHTTPServer", model_key: str, node_id: str | None = None,
+) -> dict | None:
     """Queue an explicitly requested model on the best available joined node."""
     resolved_name, preset = _resolve_model_preset(server.model_presets, model_key)
     if preset is None or not preset.get("hf_repo"):
@@ -1510,6 +1512,8 @@ def _request_model_load_locked(server: "_TrackerHTTPServer", model_key: str) ->
             continue
         host_nodes = [server.registry[item["node_id"]] for item in host["loaded"] if item["node_id"] in server.registry]
         placeable = [node for node in host_nodes if _has_usable_quantization(node)]
+        if node_id is not None:
+            placeable = [node for node in placeable if node.node_id == node_id]
         if not placeable:
             continue
         anchor = max(placeable, key=lambda node: node.benchmark_tokens_per_sec)
@@ -1556,13 +1560,17 @@ def _force_model_load_locked(server: "_TrackerHTTPServer", model_key: str) -> di
             "shard_start": start, "shard_end": shard_end, "replaced_model": replaced}
 
 
-def _release_model_locked(server: "_TrackerHTTPServer", model_key: str) -> int:
+def _release_model_locked(
+    server: "_TrackerHTTPServer", model_key: str, node_id: str | None = None,
+) -> int:
     """Queue DROP_SHARD for every served shard and remove it from routing immediately."""
     resolved_name, preset = _resolve_model_preset(server.model_presets, model_key)
     if preset is None:
         return 0
     released = 0
     for node in server.registry.values():
+        if node_id is not None and node.node_id != node_id:
+            continue
         if not _node_matches_preset(node, resolved_name, preset) or node.shard_start is None or node.shard_end is None:
             continue
         node.pending_directives.append(_drop_directive(node, str(preset.get("hf_repo") or resolved_name), node.shard_start, node.shard_end, node.quantization or "bfloat16"))
@@ -4880,10 +4888,14 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
         if not isinstance(model, str) or not model.strip():
             self._send_json(400, {"error": "model is required"})
             return
+        node_id = body.get("node_id")
+        if node_id is not None and (not isinstance(node_id, str) or not node_id):
+            self._send_json(400, {"error": "node_id must be a non-empty string"})
+            return
         with server.lock:
             self._purge_expired_nodes()
-            assignment = _request_model_load_locked(server, model)
+            assignment = _request_model_load_locked(server, model, node_id)
-            if assignment is None and body.get("force") is True:
+            if assignment is None and node_id is None and body.get("force") is True:
                 assignment = _force_model_load_locked(server, model)
         if assignment is None:
             self._send_json(409, {"error": "no ready joined node has an available model slot and sufficient capacity"})
@@ -4901,9 +4913,13 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
         if not isinstance(model, str) or not model.strip():
             self._send_json(400, {"error": "model is required"})
             return
+        node_id = body.get("node_id")
+        if node_id is not None and (not isinstance(node_id, str) or not node_id):
+            self._send_json(400, {"error": "node_id must be a non-empty string"})
+            return
         with server.lock:
             self._purge_expired_nodes()
-            released = _release_model_locked(server, model)
+            released = _release_model_locked(server, model, node_id)
         if not released:
             self._send_json(404, {"error": "no served shards found for model"})
             return

tests/test_dashboard.py

@@ -120,6 +120,12 @@ def test_dashboard_exposes_admin_model_inventory_and_release_controls():
     assert 'id="admin-node-pool"' in html
     assert "renderAdminNodePool" in html
     assert "model drive" in html
+    # RAM and VRAM live in the network-map capacity object, not at node top level.
+    assert "node.ram_bytes = cap.ram_bytes" in html
+    assert "node.vram_bytes = cap.vram_bytes" in html
+    assert 'id="model-placement-dialog"' in html
+    assert "chooseModelPlacementNode" in html
+    assert "node_id: nodeId" in html
 
 
 def test_network_map_includes_node_friendly_name():

tests/test_tracker_routing.py

@@ -2869,6 +2869,43 @@ def test_same_endpoint_can_register_multiple_models():
         tracker.stop()
 
 
+def test_explicit_model_placement_targets_only_the_selected_node():
+    "An admin can add and release a model on one chosen multi-model node.\n\nTags: http, routing, tracker"
+    from meshnet_tracker.server import _release_model_locked, _request_model_load_locked
+
+    tracker = _tracker(model_presets={
+        "model-a": {"total_layers": 4, "bytes_per_layer": {"bfloat16": 1_000}, "hf_repo": "org/ModelA"},
+        "model-b": {"total_layers": 4, "bytes_per_layer": {"bfloat16": 1_000}, "hf_repo": "org/ModelB"},
+    })
+    tracker_port = tracker.start()
+    try:
+        registrations = []
+        for port in (9062, 9063):
+            registrations.append(_post_json(
+                f"http://127.0.0.1:{tracker_port}/v1/nodes/register",
+                {"endpoint": f"http://127.0.0.1:{port}", "model": "model-a", "hf_repo": "org/ModelA",
+                 "num_layers": 4, "shard_start": 0, "shard_end": 3, "max_loaded_shards": 2,
+                 "vram_bytes": 20_000, "ram_bytes": 20_000, "quantizations": ["bfloat16"],
+                 "benchmark_tokens_per_sec": 1.0, "hardware_profile": {}, "score": 1.0},
+            ))
+        selected, other = (item["node_id"] for item in registrations)
+
+        with tracker._lock:
+            assignment = _request_model_load_locked(tracker._server, "model-b", selected)  # type: ignore[arg-type]
+        assert assignment is not None
+        assert assignment["node_id"] == selected
+        assert tracker._registry[selected].pending_new_assignment is not None
+        assert tracker._registry[other].pending_new_assignment is None
+
+        with tracker._lock:
+            released = _release_model_locked(tracker._server, "model-a", selected)  # type: ignore[arg-type]
+        assert released == 1
+        assert len(tracker._registry[selected].pending_directives) == 2
+        assert tracker._registry[other].pending_directives == []
+    finally:
+        tracker.stop()
+
+
 def test_scale_demanded_models_queues_add_shard_on_spare_host():
     "Scale demanded models queues add shard on spare host\n\nTags: http, routing, tracker"
     tracker = _tracker(model_presets={