Show node diagnostics, E2B template builds, suspension policy and E2B disk

apps/web/DESIGN.md

@@ -594,13 +594,14 @@ still frame, the request is a plain block and no transition runs.
 Setting up hosted sandboxes, and changing the provider or resources in maintenance,
 is a set of pages inside the Nodes page, one decision each: where sandboxes run (own machines
 or E2B), then the backend (Docker or microsandbox, compared behind a help tip) or
-the E2B account, then the size of each sandbox (three presets), then a review.
+the E2B account, then the size of each sandbox (three presets; E2B skips it, since
+each sandbox takes the template build's size), then a review.
 Choices are large cards that advance on a click; short indigo dashes show the
 progress; pages slide and blur across. The review states where sandboxes run,
 the size, the Runtime (taken from this console's distribution manifest) and the
 Core address, asking for it only when the console's own address cannot serve.
-Advanced settings, one link away, hold the complete form: resources, the Core
-address, the Runtime release and the E2B template. A change keeps the saved size
+Advanced settings, one link away, hold the complete form: resources (not for
+E2B), the Core address, the Runtime release and the E2B template. A change keeps the saved size
 and Runtime while the backend stays the same (a saved size outside the presets is
 offered as Current); another backend starts from its standard size and this
 console's Runtime, and E2B always needs its key again. Rules sit behind help tips.

apps/web/PRODUCT.md

@@ -67,16 +67,20 @@ workbench.
   and offer Delete.
 - **Platform**: Projects and keys (projects, their assets and usage, named keys,
   write history), Nodes (sandbox setup as pages — where sandboxes run, the
-  backend or E2B account, the size of each sandbox, a review, and advanced settings
+  backend or E2B account, the size of each sandbox (own machines only; E2B takes the
+  template build's), a review, and advanced settings
   with the complete form — then the node list with each node's capacity, host
   figures and allocations, enrollment, renaming, sandbox limits and removal; Add node
   asks for the node's sandbox limits before it issues the one-time command), System (only the sandbox
   configuration every project shares: where sandboxes run, each sandbox's size, the
-  Runtime or E2B template, the Core address and maintenance).
+  Runtime or E2B template build, microsandbox's idle suspension, the Core address and maintenance).
+- A node whose provider is not ready names the reason (Docker unreachable, no Docker
+  limits, missing Runtime image, no KVM, missing microsandbox components, a host too
+  small) and its fix in the help tip beside its status, wherever that status shows.
 - **E2B deployments** have no machines: the Nodes entry becomes Sandbox backend,
   and Overview and Sandbox metrics show the sandboxes Core holds in E2B's cloud
-  (running, starting, size, template) instead of node capacity, with no node column
-  or Add node action.
+  (running, starting, size, template build) instead of node capacity, with no node column
+  or Add node action; a sandbox's dialog adds its disk use.
 - **microsandbox** suspends idle sandboxes into snapshots, so its nodes show how
   many sleep (Core's retained minus active) on the Nodes list, a node's page, Sandbox
   metrics and Overview; Docker never suspends and shows none of it.

apps/web/e2e/data/routes.mjs

@@ -77,7 +77,7 @@ export function buildDemo(now = Math.floor(Date.now() / 1000)) {
   sessions.sort((a, b) => b.created_at - a.created_at);
   const nodes = [
     { id: "node-local", name: "core-01", provider: "docker", online: true, provider_ready: true, diagnostic: "", cpu_count: 16, available_memory_bytes: 38 * 2 ** 30, available_disk_bytes: 410 * 2 ** 30, running: 5, snapshots: 2, last_seen_at: new Date((now - 8) * 1000).toISOString(), max_active: 8, max_retained: 16, active: 5, reserved: 1, retained: 2, cleanup_pending: 0, created_at: new Date((now - 86400 * 30) * 1000).toISOString() },
-    { id: "node-gpu", name: "gpu-worker-02", provider: "docker", online: true, provider_ready: true, diagnostic: "", cpu_count: 32, available_memory_bytes: 12 * 2 ** 30, available_disk_bytes: 96 * 2 ** 30, running: 7, snapshots: 5, last_seen_at: new Date((now - 12) * 1000).toISOString(), max_active: 8, max_retained: 16, active: 7, reserved: 0, retained: 5, cleanup_pending: 1, created_at: new Date((now - 86400 * 12) * 1000).toISOString() },
+    { id: "node-gpu", name: "gpu-worker-02", provider: "docker", online: true, provider_ready: false, diagnostic: "docker_limits_unsupported", cpu_count: 32, available_memory_bytes: 12 * 2 ** 30, available_disk_bytes: 96 * 2 ** 30, running: 7, snapshots: 5, last_seen_at: new Date((now - 12) * 1000).toISOString(), max_active: 8, max_retained: 16, active: 7, reserved: 0, retained: 5, cleanup_pending: 1, created_at: new Date((now - 86400 * 12) * 1000).toISOString() },
     { id: "node-edge", name: "edge-03", provider: "docker", online: false, provider_ready: false, diagnostic: "", cpu_count: 8, available_memory_bytes: null, available_disk_bytes: null, running: 0, snapshots: 0, last_seen_at: new Date((now - 5400) * 1000).toISOString(), max_active: 4, max_retained: 8, active: 0, reserved: 0, retained: 0, cleanup_pending: 0, created_at: new Date((now - 86400 * 3) * 1000).toISOString() },
   ];
   const hosted = sessions.filter((session) => session.environment.type === "openai_hosted");

apps/web/e2e/fixture-console.mjs

@@ -20,12 +20,14 @@ const release = { source_commit: "c0ffee".padEnd(40, "0"), image_id: `sha256:${h
 const manifest = { platform: "linux/amd64", source_commit: release.source_commit, images: { runtime: release.image_id }, image_manifest_digests: { runtime: release.image_manifest_digest }, runtime_ref: release.microsandbox_ref, microsandbox: { runtime_sha256: release.runtime_sha256, firmware_sha256: release.firmware_sha256 }, artifacts: {} };
 
 function configuredDeployment() {
-  return { installation_id: "7f3c2a90-fixture", provider: "docker", core_url: `http://127.0.0.1:${port}`, maintenance: false, owner_epoch: 3, generation: 1, mode: "nodes", resources: { allocations: 0, pending: 0 }, specification: { resources: { cpus: 2, memory_mib: 4096 }, runtime: release }, specification_digest: "fixture" };
+  return { installation_id: "7f3c2a90-fixture", provider: "docker", core_url: `http://127.0.0.1:${port}`, maintenance: false, owner_epoch: 3, generation: 1, mode: "nodes", resources: { allocations: 0, pending: 0 }, specification: { resources: { cpus: 2, memory_mib: 4096 }, runtime: release }, specification_digest: "fixture", suspension: null };
 }
+/** The E2B template build as Core read it when the selection was saved. */
+const templateBuild = { status: "ready", resources: { cpus: 2, memory_mib: 2048, root_disk_mib: 10240 } };
 
 // E2B runs sandboxes in its cloud: no nodes, only what Core holds there.
 function e2bDeployment() {
-  return { ...configuredDeployment(), provider: "e2b", mode: "direct", resources: { allocations: 3, pending: 1 }, specification: { resources: { cpus: 2, memory_mib: 2048 } }, e2b: { template: "parsar-runtime:0f1e2d3c-4b5a-6978-8a9b-0c1d2e3f4a5b", credential_configured: true } };
+  return { ...configuredDeployment(), provider: "e2b", mode: "direct", resources: { allocations: 3, pending: 1 }, specification: { resources: { cpus: 2, memory_mib: 2048 } }, e2b: { template: "parsar-runtime:0f1e2d3c-4b5a-6978-8a9b-0c1d2e3f4a5b", credential_configured: true, template_build: templateBuild } };
 }
 
 function reset(mode = "setup", fresh = false, sandbox = "configured") {
@@ -146,7 +148,9 @@ function adminRead(response, path, url) {
   if (path === "/projects") return send(response, 200, { data: a.projects.map(a.publicProject), has_more: false });
   if (path === "/summary") return send(response, 200, a.summary(url));
   if (path === "/runtime-observations") {
-    const data = a.runtimeObservations();
+    // Only E2B reports a sandbox's disk.
+    const e2b = state.deployment?.provider === "e2b";
+    const data = a.runtimeObservations().map((entry) => ({ ...entry, observation: { ...entry.observation, disk: e2b && entry.observation.status === "observed" ? { usage_bytes: 3 * 2 ** 30, limit_bytes: 10 * 2 ** 30 } : null } }));
     return send(response, 200, { object: "list", data, has_more: false, first_id: data[0]?.observation.id ?? null, last_id: data.at(-1)?.observation.id ?? null });
   }
   if (path === "/core-metrics") return send(response, 200, coreMetrics(url.searchParams.get("range") ?? "1h"));
@@ -206,12 +210,20 @@ async function sandboxRoute(request, response, path) {
   if (path === "/deployment" && request.method === "POST") {
     const input = await body(request);
     if (state.deployment) return error(response, 409, "The sandbox deployment is already configured.", "sandbox_deployment_conflict");
-    if (!input.resources || (input.provider !== "e2b" && !input.runtime)) return error(response, 400, "resources and runtime are required.", "invalid_sandbox_configuration");
-    state.deployment = { ...configuredDeployment(), provider: input.provider, core_url: input.core_url, mode: input.provider === "e2b" ? "direct" : "nodes", specification: { resources: input.resources, ...(input.runtime ? { runtime: input.runtime } : {}) } };
+    const e2b = input.provider === "e2b";
+    if (!e2b && (!input.resources || !input.runtime)) return error(response, 400, "resources and runtime are required.", "invalid_sandbox_configuration");
+    // As Core: E2B may omit resources and adopt its template build's CPU and memory; only microsandbox suspends.
+    const resources = input.resources ?? { cpus: templateBuild.resources.cpus, memory_mib: templateBuild.resources.memory_mib };
+    state.deployment = {
+      ...configuredDeployment(), provider: input.provider, core_url: input.core_url, mode: e2b ? "direct" : "nodes",
+      specification: { resources, ...(input.runtime ? { runtime: input.runtime } : {}) },
+      ...(e2b ? { e2b: { template: input.e2b?.template ?? "", credential_configured: true, template_build: templateBuild } } : {}),
+      suspension: input.provider === "microsandbox" ? { idle_seconds: 300, retention_seconds: 86400 } : null,
+    };
     return send(response, 201, state.deployment);
   }
   if (path === "/deployment") {
-    return send(response, 200, state.deployment ?? { installation_id: "7f3c2a90-fixture", provider: "", core_url: `http://127.0.0.1:${port}`, maintenance: false, owner_epoch: 3, generation: 0, mode: "", resources: { allocations: 0, pending: 0 } });
+    return send(response, 200, state.deployment ?? { installation_id: "7f3c2a90-fixture", provider: "", core_url: `http://127.0.0.1:${port}`, maintenance: false, owner_epoch: 3, generation: 0, mode: "", resources: { allocations: 0, pending: 0 }, suspension: null });
   }
   if (path === "/nodes") return send(response, 200, { data: state.nodes });
   if (path === "/enrollment-tokens" && request.method === "POST") {

apps/web/e2e/monitoring.spec.ts

@@ -20,6 +20,8 @@ test("shows the deployment's health on Overview and each monitor page", async ({
   await expect(page.getByLabel("Agent run summary")).toContainText("Requests");
   await page.getByRole("button", { name: "Sandbox metrics" }).click();
   await expect(page.getByRole("table").first()).toContainText("core-01");
+  // A degraded node names why its provider is not ready.
+  await expect(page.getByRole("button", { name: "Docker limits unsupported" })).toBeVisible();
 });
 
 test("opens a Session's conversation from the Session log, read-only", async ({ page, request }) => {
@@ -50,6 +52,8 @@ test("opens a node and a sandbox in dialogs from Sandbox metrics", async ({ page
 test("shows E2B's cloud instead of machines", async ({ page, request }) => {
   await openConsole(page, request, "sandbox-metrics", { sandbox: "e2b" });
   await expect(page.getByRole("heading", { name: "E2B cloud" })).toBeVisible();
+  // Each sandbox takes the template build's size, disk included.
+  await expect(page.getByText("10 GiB disk")).toBeVisible();
   await expect(page.getByRole("button", { name: "Add node" })).toHaveCount(0);
   await expect(page.getByRole("columnheader", { name: "Node", exact: true })).toHaveCount(0);
 

apps/web/e2e/nodes.spec.ts

@@ -73,18 +73,17 @@ test("keeps the saved size and Runtime for the same backend, and starts another
   expect(submitted?.resources).toEqual({ cpus: 2, memory_mib: 4096, root_disk_mib: 8192, environment_disk_mib: 8192 });
   expect(submitted?.runtime).toMatchObject({ source_commit: "c0ffee".padEnd(40, "0") });
 
-  // E2B needs its key again and takes no Runtime or disks.
+  // E2B needs its key again and takes its size from the template build: no size, Runtime or disks.
   await back.click();
   await back.click();
   await back.click();
   await page.getByRole("button", { name: "E2B cloud" }).click();
   await page.getByLabel("E2B API key").fill("fixture-private-key");
   await page.getByLabel("Template build").fill("template:94be54a1-138c-4f30-bc87-b13686272dbe");
   await page.getByRole("button", { name: "Next" }).click();
-  await page.getByRole("button", { name: /^Standard/ }).click();
   await save.click();
   await expect.poll(() => submitted?.provider).toBe("e2b");
-  expect(submitted?.resources).toEqual({ cpus: 2, memory_mib: 2048 });
+  expect(submitted?.resources).toBeUndefined();
   expect(submitted?.runtime).toBeUndefined();
 });
 

apps/web/src/features/fleet/DiagnosticTip.tsx

@@ -0,0 +1,16 @@
+import { useTranslation } from "react-i18next";
+
+import { HelpTip } from "../../components/console-ui";
+import { sandboxDiagnosticMessage } from "../../lib/sandbox-diagnostic";
+
+/** The specific reason behind a node's status, in the help tip beside it: what is wrong, then how to fix it. */
+export function DiagnosticTip({ code }: { code: string }) {
+  const { i18n } = useTranslation();
+  const message = sandboxDiagnosticMessage(code, i18n.resolvedLanguage?.startsWith("zh") ? "zh" : "en");
+  if (!message) return null;
+  return (
+    <HelpTip label={message.label}>
+      <strong className="help-tip-title">{message.label}</strong> {message.advice}
+    </HelpTip>
+  );
+}