fix(onboard): revert incorrect N1x rebuild changes

Signed-off-by: San Dang <sdang@nvidia.com>

Author: sandl99

docs/inference/set-up-vllm.mdx

@@ -371,22 +371,6 @@ Accepting the preview prompt sets explicit managed-vLLM intent for the narrow pe
 Declining the prompt or setting only `NEMOCLAW_NO_EXPRESS=1` stops the installer before onboarding; neither path opens interactive provider selection.
 Set `NEMOCLAW_PROVIDER=install-vllm` when you need to bypass the prompt with the same explicit preview intent.
 
-On a host that still meets the N1x identity checks, `rebuild` reuses the recorded route as explicit preview intent only when all of these conditions hold:
-
-- The sandbox registry records provider `vllm-local`.
-- The registry records model `nvidia/Qwen3.6-35B-A3B-NVFP4`.
-- The registry records upstream endpoint `http://host.openshell.internal:8000/v1`.
-- The registry records `endpointSource` as `onboard` and `openshellDriver` as `docker`.
-- The replacement keeps the recorded provider and model, then re-derives the canonical local endpoint.
-- `hostLocalInferenceReceipt` is absent or `null`, or contains a canonical vLLM receipt for `host.openshell.internal:8000` and the same model.
-
-NemoClaw v0.0.109 can omit `hostLocalInferenceReceipt` or record it as `null`.
-Matching sandboxes from that release remain eligible only when every condition above passes.
-You do not need to set `NEMOCLAW_PROVIDER` again for a matching rebuild.
-Any unmet condition stops readiness preflight before NemoClaw deletes the existing sandbox.
-A malformed, non-vLLM, or conflicting receipt also stops readiness preflight before deletion.
-This reuse waives only the pending physical-validation finding and does not change the Deferred status.
-
 <Warning title="N1x Express Qualification Pending">
 Physical CUDA and CDI checks passed on one N1x host.
 The full NemoClaw Express E2E test is still pending, so the N1x platform status remains Deferred.

src/lib/actions/sandbox/rebuild-gpu-opt-out.ts

@@ -127,8 +127,6 @@ export type RebuildRecreateOnboardOpts = {
   rebuildRegistryInferenceRoute?: RebuildRouteHandoff;
   rebuildProviderReconfigure?: RebuildProviderReconfigureHandoff;
   providerRecoveryReceipt?: ProviderRecoveryReceipt;
-  /** Recorded managed-vLLM intent admitted only by the N1x readiness exception. */
-  allowDeferredN1xManagedVllm?: true;
   /** Target-scoped authority admitted by the authoritative rebuild preflight. */
   rebuildGatewayAuthority?: CheckpointGatewayAuthority;
   preparedImageRebuild?: PreparedImageRebuildHandoff;

…light-target-phase-orchestration.test.ts …-managed-workload-context-window.test.tssrc/lib/actions/sandbox/rebuild-preflight-target-phase-orchestration.test.ts renamed to src/lib/actions/sandbox/rebuild-managed-workload-context-window.test.ts src/lib/actions/sandbox/rebuild-preflight-target-phase-orchestration.test.ts renamed to src/lib/actions/sandbox/rebuild-managed-workload-context-window.test.ts

@@ -1,11 +1,10 @@
 // SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 // SPDX-License-Identifier: Apache-2.0
 
-import { beforeEach, describe, expect, it, vi } from "vitest";
+import { describe, expect, it, vi } from "vitest";
 
 const mocks = vi.hoisted(() => ({
   bail: vi.fn(),
-  preflightAuthoritativeOnboardRuntime: vi.fn(async (..._args: unknown[]) => false),
   prepareManagedWorkloadRebuildHandoff: vi.fn(),
   prepareSandboxWorkloadSourceFromRebuildHandoff: vi.fn(),
   prepareRebuildTargetConfig: vi.fn(),
@@ -34,7 +33,7 @@ vi.mock("../../onboard/workload/runtime", () => ({
 vi.mock("./rebuild-target-preflight", async (importOriginal) => ({
   ...(await importOriginal<typeof import("./rebuild-target-preflight")>()),
   hydrateMessagingConfigForRebuild: vi.fn(),
-  preflightAuthoritativeOnboardRuntime: mocks.preflightAuthoritativeOnboardRuntime,
+  preflightAuthoritativeOnboardRuntime: vi.fn(async () => false),
   prepareRebuildRecreateOptions: mocks.prepareRebuildRecreateOptions,
   prepareRebuildTargetConfig: mocks.prepareRebuildTargetConfig,
   stageRebuildHermesDashboardConfig: vi.fn(() => true),
@@ -51,64 +50,7 @@ vi.mock("./rebuild-messaging-conflict-preflight", () => ({
 import { managedRebuildProfileDependencies } from "./agents/managed-workload-rebuild-profile";
 import { prepareRebuildTargetPreflights } from "./rebuild-preflight-target-phase";
 
-describe("prepareRebuildTargetPreflights", () => {
-  beforeEach(() => {
-    vi.clearAllMocks();
-    mocks.prepareManagedWorkloadRebuildHandoff.mockResolvedValue(null);
-    mocks.preflightAuthoritativeOnboardRuntime.mockResolvedValue(false);
-  });
-
-  async function prepareN1xTarget(endpointSource: "onboard" | "inference-set") {
-    const resumeConfig = {
-      provider: "vllm-local",
-      model: "nvidia/Qwen3.6-35B-A3B-NVFP4",
-      preferredInferenceApi: "openai-completions",
-      pinEndpoint: true,
-      endpointUrl: null,
-      compatibleEndpointReasoning: null,
-      compatibleEndpointReasoningEffort: null,
-      registryInferenceRoute: null,
-    };
-    mocks.prepareRebuildTargetConfig.mockReturnValue({
-      agentDefinition: {},
-      resumeConfig,
-      durableConfig: {
-        toolDisclosure: "progressive",
-        dcodeAutoApprovalMode: "disabled",
-        webSearchConfig: null,
-      },
-      credentialEnv: null,
-      fromDockerfile: false,
-      hermesToolGateways: [],
-    });
-    mocks.prepareRebuildRecreateOptions.mockReturnValue({
-      controlUiPort: 18_789,
-      targetGatewayName: "nemoclaw",
-      toolDisclosure: "progressive",
-      dcodeAutoApprovalMode: "disabled",
-      observabilityEnabled: false,
-    });
-
-    await prepareRebuildTargetPreflights({
-      sandboxName: "my-assistant",
-      sandboxEntry: {
-        name: "my-assistant",
-        agent: "openclaw",
-        gatewayName: "nemoclaw",
-        openshellDriver: "docker",
-        provider: resumeConfig.provider,
-        model: resumeConfig.model,
-        endpointUrl: "http://host.openshell.internal:8000/v1",
-        endpointSource,
-      } as never,
-      rebuildAgent: "openclaw",
-      autoYes: true,
-      log: vi.fn(),
-      bail: mocks.bail as never,
-    });
-    return mocks.preflightAuthoritativeOnboardRuntime.mock.calls[0]?.[2];
-  }
-
+describe("managed workload rebuild context-window preflight", () => {
   it("resolves the Ollama context window through target preparation", async () => {
     const catalogHandoff = {
       agent: "openclaw",
@@ -181,18 +123,4 @@ describe("prepareRebuildTargetPreflights", () => {
     ).resolves.toBeNull();
     expect(mocks.resolveContextWindowForModel).toHaveBeenCalledWith("ollama-local", "qwen3.5:9b");
   });
-
-  it("passes exact legacy N1x intent into authoritative readiness (#9292)", async () => {
-    const readinessOptions = await prepareN1xTarget("onboard");
-
-    expect(readinessOptions).toEqual(
-      expect.objectContaining({ allowDeferredN1xManagedVllm: true }),
-    );
-  });
-
-  it("withholds N1x intent for a mismatched endpoint source (#9292)", async () => {
-    const readinessOptions = await prepareN1xTarget("inference-set");
-
-    expect(readinessOptions).not.toHaveProperty("allowDeferredN1xManagedVllm");
-  });
 });

src/lib/actions/sandbox/rebuild-preflight-target-phase.test.ts

@@ -3,22 +3,15 @@
 
 import { afterEach, describe, expect, it, vi } from "vitest";
 
-import {
-  hostLocalInferenceReceipt,
-  serializedHostLocalInferenceReceipt,
-  serializedLlamaCppHostLocalInferenceReceipt,
-} from "../../../../test/helpers/host-local-inference-receipt";
 import type {
   ProviderRecoveryReceipt,
   RegistryInferenceRoute,
 } from "../../onboard/rebuild-route-handoff";
-import { serializeHostLocalInferenceReceipt } from "../../onboard/runtime-provider/host-local-inference";
 import type { SandboxBaseImageResolutionMetadata } from "../../sandbox-base-image";
 import {
   pinRebuildTargetGatewayForReadiness,
   runRebuildGatewayRecoveryAfterReadiness,
   stageRebuildBaseImageResolutionHandoff,
-  stageRecordedManagedVllmIntent,
   stageRegistryProviderRecoveryReceipt,
 } from "./rebuild-preflight-target-phase";
 
@@ -128,145 +121,6 @@ describe("stageRegistryProviderRecoveryReceipt", () => {
   });
 });
 
-describe("stageRecordedManagedVllmIntent", () => {
-  const n1xExpressEntry = {
-    provider: "vllm-local",
-    model: "nvidia/Qwen3.6-35B-A3B-NVFP4",
-    endpointUrl: "http://host.openshell.internal:8000/v1",
-    endpointSource: "onboard" as const,
-    openshellDriver: "docker",
-  };
-  const n1xExpressSelection = {
-    provider: n1xExpressEntry.provider,
-    model: n1xExpressEntry.model,
-    pinEndpoint: true,
-    endpointUrl: null,
-  };
-
-  it.each([
-    { receiptState: "absent", sandboxEntry: n1xExpressEntry },
-    {
-      receiptState: "null",
-      sandboxEntry: { ...n1xExpressEntry, hostLocalInferenceReceipt: null },
-    },
-  ])(
-    "carries the v0.0.109 N1x Express selection with a $receiptState receipt into rebuild readiness (#9292)",
-    ({ sandboxEntry }) => {
-      const recreateOptions: { allowDeferredN1xManagedVllm?: true } = {};
-
-      stageRecordedManagedVllmIntent(recreateOptions, sandboxEntry, n1xExpressSelection);
-
-      expect(recreateOptions.allowDeferredN1xManagedVllm).toBe(true);
-    },
-  );
-
-  it("also accepts a canonical vLLM receipt on the exact N1x Express selection (#9292)", () => {
-    const recreateOptions: { allowDeferredN1xManagedVllm?: true } = {};
-    const genericReceipt = hostLocalInferenceReceipt("docker");
-    const n1xReceipt = serializeHostLocalInferenceReceipt({
-      ...genericReceipt,
-      endpoint: {
-        ...genericReceipt.endpoint,
-        host: "host.openshell.internal",
-      },
-      inference: {
-        protocol: "openai-chat-completions",
-        model: n1xExpressEntry.model,
-        toolCallingRequired: true,
-      },
-    });
-
-    stageRecordedManagedVllmIntent(
-      recreateOptions,
-      { ...n1xExpressEntry, hostLocalInferenceReceipt: n1xReceipt },
-      n1xExpressSelection,
-    );
-
-    expect(recreateOptions.allowDeferredN1xManagedVllm).toBe(true);
-  });
-
-  it.each([
-    {
-      caseName: "different recorded provider",
-      sandboxEntry: { ...n1xExpressEntry, provider: "compatible-endpoint" },
-      rebuildSelection: n1xExpressSelection,
-    },
-    {
-      caseName: "different recorded model",
-      sandboxEntry: { ...n1xExpressEntry, model: "meta-llama/Llama-3.1-8B-Instruct" },
-      rebuildSelection: n1xExpressSelection,
-    },
-    {
-      caseName: "different recorded endpoint",
-      sandboxEntry: { ...n1xExpressEntry, endpointUrl: "http://host.openshell.internal:8001/v1" },
-      rebuildSelection: n1xExpressSelection,
-    },
-    {
-      caseName: "different endpoint source",
-      sandboxEntry: { ...n1xExpressEntry, endpointSource: "inference-set" as const },
-      rebuildSelection: n1xExpressSelection,
-    },
-    {
-      caseName: "different OpenShell driver",
-      sandboxEntry: { ...n1xExpressEntry, openshellDriver: "podman" },
-      rebuildSelection: n1xExpressSelection,
-    },
-    {
-      caseName: "malformed receipt",
-      sandboxEntry: { ...n1xExpressEntry, hostLocalInferenceReceipt: "not-json" },
-      rebuildSelection: n1xExpressSelection,
-    },
-    {
-      caseName: "different host-local service",
-      sandboxEntry: {
-        ...n1xExpressEntry,
-        hostLocalInferenceReceipt: serializedLlamaCppHostLocalInferenceReceipt(),
-      },
-      rebuildSelection: n1xExpressSelection,
-    },
-    {
-      caseName: "conflicting vLLM receipt",
-      sandboxEntry: {
-        ...n1xExpressEntry,
-        hostLocalInferenceReceipt: serializedHostLocalInferenceReceipt(),
-      },
-      rebuildSelection: n1xExpressSelection,
-    },
-    {
-      caseName: "different rebuild provider",
-      sandboxEntry: n1xExpressEntry,
-      rebuildSelection: { ...n1xExpressSelection, provider: "compatible-endpoint" },
-    },
-    {
-      caseName: "different rebuild model",
-      sandboxEntry: n1xExpressEntry,
-      rebuildSelection: { ...n1xExpressSelection, model: "meta-llama/Llama-3.1-8B-Instruct" },
-    },
-    {
-      caseName: "unresolved rebuild endpoint",
-      sandboxEntry: n1xExpressEntry,
-      rebuildSelection: { ...n1xExpressSelection, pinEndpoint: false },
-    },
-    {
-      caseName: "noncanonical rebuild endpoint",
-      sandboxEntry: n1xExpressEntry,
-      rebuildSelection: {
-        ...n1xExpressSelection,
-        endpointUrl: "http://host.openshell.internal:8001/v1",
-      },
-    },
-  ])(
-    "does not infer N1x Express intent from a $caseName (#9292)",
-    ({ sandboxEntry, rebuildSelection }) => {
-      const recreateOptions: { allowDeferredN1xManagedVllm?: true } = {};
-
-      stageRecordedManagedVllmIntent(recreateOptions, sandboxEntry, rebuildSelection);
-
-      expect(recreateOptions).not.toHaveProperty("allowDeferredN1xManagedVllm");
-    },
-  );
-});
-
 describe("stageRebuildBaseImageResolutionHandoff", () => {
   it("binds outer resolver provenance to its immutable local handoff (#7144)", () => {
     const imageId = `sha256:${"a".repeat(64)}`;

src/lib/actions/sandbox/rebuild-preflight-target-phase.ts

@@ -6,7 +6,6 @@ import { CLI_NAME } from "../../cli/branding";
 import type { SandboxMessagingPlan } from "../../messaging";
 import { isSandboxBaseImageRefreshRequested } from "../../onboard/base-image-resolution-flow";
 import type { DcodeAutoApprovalMode } from "../../onboard/dcode-auto-approval";
-import { parseHostLocalInferenceReceipt } from "../../onboard/runtime-provider/host-local-inference";
 import {
   createRebuildProviderReconfigureHandoff,
   mintProviderRecoveryReceipt,
@@ -84,62 +83,6 @@ export function stageRegistryProviderRecoveryReceipt(
   );
 }
 
-const N1X_EXPRESS_PROVIDER = "vllm-local";
-const N1X_EXPRESS_MODEL = "nvidia/Qwen3.6-35B-A3B-NVFP4";
-const N1X_EXPRESS_ENDPOINT_URL = "http://host.openshell.internal:8000/v1";
-
-/** Reuse only the exact N1x Express selection recorded by onboarding. */
-export function stageRecordedManagedVllmIntent(
-  recreateOptions: Pick<RebuildRecreateOnboardOpts, "allowDeferredN1xManagedVllm">,
-  sandboxEntry: Pick<
-    RebuildSandboxEntry,
-    | "provider"
-    | "model"
-    | "endpointUrl"
-    | "endpointSource"
-    | "openshellDriver"
-    | "hostLocalInferenceReceipt"
-  >,
-  rebuildSelection: {
-    provider: string;
-    model: string;
-    pinEndpoint: boolean;
-    endpointUrl: string | null;
-  },
-): void {
-  if (
-    sandboxEntry.provider !== N1X_EXPRESS_PROVIDER ||
-    sandboxEntry.model !== N1X_EXPRESS_MODEL ||
-    sandboxEntry.endpointUrl !== N1X_EXPRESS_ENDPOINT_URL ||
-    sandboxEntry.endpointSource !== "onboard" ||
-    sandboxEntry.openshellDriver !== "docker" ||
-    rebuildSelection.provider !== sandboxEntry.provider ||
-    rebuildSelection.model !== sandboxEntry.model ||
-    rebuildSelection.pinEndpoint !== true ||
-    rebuildSelection.endpointUrl !== null
-  ) {
-    return;
-  }
-  const serialized = sandboxEntry.hostLocalInferenceReceipt;
-  if (serialized === undefined || serialized === null) {
-    recreateOptions.allowDeferredN1xManagedVllm = true;
-    return;
-  }
-  try {
-    const receipt = parseHostLocalInferenceReceipt(serialized);
-    if (
-      receipt.service === "vllm" &&
-      receipt.endpoint.host === "host.openshell.internal" &&
-      receipt.endpoint.port === 8000 &&
-      receipt.inference?.model === N1X_EXPRESS_MODEL
-    ) {
-      recreateOptions.allowDeferredN1xManagedVllm = true;
-    }
-  } catch {
-    // Malformed durable state must not grant the narrow N1x readiness exception.
-  }
-}
-
 export interface RebuildPreparedTarget {
   targetConfig: RebuildTargetConfig;
   recreateOptions: RebuildRecreateOnboardOpts;
@@ -290,7 +233,6 @@ export async function prepareRebuildTargetPreflights(args: {
   recreateOptions.observabilityEnabled =
     requestedObservabilityEnabled ?? recreateOptions.observabilityEnabled;
   recreateOptions.observabilityRequestedExplicitly = requestedObservabilityEnabled !== undefined;
-  stageRecordedManagedVllmIntent(recreateOptions, sandboxEntry, resumeConfig);
   if (
     !stageRebuildHermesDashboardConfig(
       rebuildAgent,