feat(lidar): add dataset gateway boundary

README.md

@@ -121,6 +121,19 @@ performance, direct worker transport and bounded live fan-out remain open. See
 [ADR 0014](docs/adr/0014-bounded-external-perception-worker.md)
 and the [external worker contract](docs/10_EXTERNAL_PERCEPTION_WORKER.md).
 
+## LiDAR Dataset Gateway
+
+Mission Core now distinguishes a single native LiDAR scan, a normalized
+sensor-frame scan and a pose-registered rolling local map. The first Dataset
+Gateway adapter reads GOOSE/SemanticKITTI XYZI plus point-wise semantic and
+instance labels without silently accumulating or transforming them. Current
+K1 `lio_pcl` remains a post-LIO vendor-map increment and is not promoted to a
+raw scan. Large dataset bytes are admitted only on the Windows/WSL worker under
+`D:\NDC_MISSIONCORE\datasets`; no archive is downloaded automatically.
+
+See [the Dataset Gateway plan](docs/14_LIDAR_DATASET_GATEWAY.md) and
+[ADR 0021](docs/adr/0021-dataset-gateway-representation-boundary.md).
+
 ## Simulation Polygon
 
 Mission Core now has a parallel Polygon product branch for reproducible

apps/control-station/src/core/lidar/datasetGateway.ts

@@ -0,0 +1,243 @@
+export type DatasetRepresentationId =
+  | "native-scan"
+  | "normalized-scan"
+  | "rolling-local-map";
+
+export interface DatasetGatewayCatalog {
+  storage: {
+    configured: boolean;
+    admitted: boolean;
+    status: "ready" | "blocked-storage-policy";
+    requiredWindowsRoot: string;
+    requiredWslRoot: string;
+  };
+  source: {
+    sourceId: string;
+    displayName: string;
+    role: string;
+    license: string;
+    format: string;
+    frameSemantics: "one-lidar-revolution";
+    platforms: string[];
+    superclasses: string[];
+    validationArchiveGb: number;
+    admissionStatus: "ready-for-download" | "blocked-storage-policy";
+  };
+  representations: Array<{
+    id: DatasetRepresentationId;
+    title: string;
+    purpose: string;
+    accumulation: boolean;
+  }>;
+  pipeline: Array<{
+    stage: string;
+    requires: string[];
+    produces: string;
+  }>;
+  currentInput: {
+    representation: "vendor-mapped-increment";
+    nativeScan: false;
+    perPointTime: false;
+    ringOrLine: false;
+    admittedForPatchworkpp: false;
+    reason: string;
+  };
+  nextAction: string;
+}
+
+export class DatasetGatewayContractError extends Error {}
+
+type DatasetFetch = (
+  input: RequestInfo | URL,
+  init?: RequestInit,
+) => Promise<Response>;
+
+const SAFE_ID = /^[a-z0-9][a-z0-9._:/-]{0,159}$/;
+
+function record(value: unknown, label: string): Record<string, unknown> {
+  if (!value || typeof value !== "object" || Array.isArray(value)) {
+    throw new DatasetGatewayContractError(`${label}: ожидался объект`);
+  }
+  return value as Record<string, unknown>;
+}
+
+function array(value: unknown, label: string): unknown[] {
+  if (!Array.isArray(value)) {
+    throw new DatasetGatewayContractError(`${label}: ожидался массив`);
+  }
+  return value;
+}
+
+function string(value: unknown, label: string, safe = false): string {
+  if (
+    typeof value !== "string"
+    || !value
+    || (safe && !SAFE_ID.test(value))
+  ) {
+    throw new DatasetGatewayContractError(`${label}: некорректная строка`);
+  }
+  return value;
+}
+
+function strings(value: unknown, label: string): string[] {
+  return array(value, label).map((item, index) =>
+    string(item, `${label}[${index}]`, true)
+  );
+}
+
+function displayStrings(value: unknown, label: string): string[] {
+  return array(value, label).map((item, index) =>
+    string(item, `${label}[${index}]`)
+  );
+}
+
+function boolean(value: unknown, label: string): boolean {
+  if (typeof value !== "boolean") {
+    throw new DatasetGatewayContractError(`${label}: ожидался boolean`);
+  }
+  return value;
+}
+
+function number(value: unknown, label: string): number {
+  if (typeof value !== "number" || !Number.isFinite(value) || value < 0) {
+    throw new DatasetGatewayContractError(`${label}: некорректное число`);
+  }
+  return value;
+}
+
+export function parseDatasetGatewayCatalog(
+  value: unknown,
+): DatasetGatewayCatalog {
+  const source = record(value, "Dataset Gateway");
+  if (
+    source.schema_version !== "missioncore.dataset-gateway-catalog/v1"
+    || source.access !== "read-only"
+  ) {
+    throw new DatasetGatewayContractError("Dataset Gateway contract несовместим");
+  }
+  const storage = record(source.storage, "storage");
+  const storageStatus = storage.status;
+  if (storageStatus !== "ready" && storageStatus !== "blocked-storage-policy") {
+    throw new DatasetGatewayContractError("storage.status: неизвестное значение");
+  }
+  if (storage.path_exposed !== false) {
+    throw new DatasetGatewayContractError("Dataset Gateway раскрыл локальный путь");
+  }
+  const sources = array(source.sources, "sources");
+  if (sources.length !== 1) {
+    throw new DatasetGatewayContractError("Ожидался один первичный dataset source");
+  }
+  const dataset = record(sources[0], "sources[0]");
+  const download = record(dataset.download, "source.download");
+  const admission = record(dataset.admission, "source.admission");
+  if (download.automatic !== false) {
+    throw new DatasetGatewayContractError("Большой dataset нельзя загружать автоматически");
+  }
+  const admissionStatus = admission.status;
+  if (
+    admissionStatus !== "ready-for-download"
+    && admissionStatus !== "blocked-storage-policy"
+  ) {
+    throw new DatasetGatewayContractError("source admission status неизвестен");
+  }
+  const representations = array(
+    source.representations,
+    "representations",
+  ).map((value, index) => {
+    const item = record(value, `representations[${index}]`);
+    const id = item.id;
+    if (
+      id !== "native-scan"
+      && id !== "normalized-scan"
+      && id !== "rolling-local-map"
+    ) {
+      throw new DatasetGatewayContractError("Неизвестная LiDAR representation");
+    }
+    const normalizedId: DatasetRepresentationId = id;
+    return {
+      id: normalizedId,
+      title: string(item.title, "representation.title"),
+      purpose: string(item.purpose, "representation.purpose", true),
+      accumulation: boolean(item.accumulation, "representation.accumulation"),
+    };
+  });
+  const pipeline = array(source.pipeline, "pipeline").map((value, index) => {
+    const item = record(value, `pipeline[${index}]`);
+    return {
+      stage: string(item.stage, "pipeline.stage", true),
+      requires: strings(item.requires, "pipeline.requires"),
+      produces: string(item.produces, "pipeline.produces", true),
+    };
+  });
+  const inputs = array(source.known_inputs, "known_inputs");
+  const currentInput = record(inputs[0], "known_inputs[0]");
+  if (
+    currentInput.representation !== "vendor-mapped-increment"
+    || currentInput.native_scan !== false
+    || currentInput.per_point_time !== false
+    || currentInput.ring_or_line !== false
+    || currentInput.admitted_for_patchworkpp !== false
+  ) {
+    throw new DatasetGatewayContractError("Vendor-map boundary завышен");
+  }
+  if (dataset.frame_semantics !== "one-lidar-revolution") {
+    throw new DatasetGatewayContractError("GOOSE frame semantics несовместима");
+  }
+  return {
+    storage: {
+      configured: boolean(storage.configured, "storage.configured"),
+      admitted: boolean(storage.admitted, "storage.admitted"),
+      status: storageStatus,
+      requiredWindowsRoot: string(
+        storage.required_windows_root,
+        "storage.required_windows_root",
+      ),
+      requiredWslRoot: string(storage.required_wsl_root, "storage.required_wsl_root"),
+    },
+    source: {
+      sourceId: string(dataset.source_id, "source_id", true),
+      displayName: string(dataset.display_name, "display_name"),
+      role: string(dataset.role, "role", true),
+      license: string(dataset.license, "license"),
+      format: string(dataset.format, "format", true),
+      frameSemantics: "one-lidar-revolution",
+      platforms: displayStrings(dataset.platforms, "platforms"),
+      superclasses: strings(dataset.superclasses, "superclasses"),
+      validationArchiveGb: number(
+        download.validation_archive_gb,
+        "validation_archive_gb",
+      ),
+      admissionStatus,
+    },
+    representations,
+    pipeline,
+    currentInput: {
+      representation: "vendor-mapped-increment",
+      nativeScan: false,
+      perPointTime: false,
+      ringOrLine: false,
+      admittedForPatchworkpp: false,
+      reason: string(currentInput.reason, "known_inputs.reason", true),
+    },
+    nextAction: string(source.next_action, "next_action", true),
+  };
+}
+
+async function responseJson(response: Response): Promise<unknown> {
+  if (!response.ok) {
+    throw new Error(`Dataset Gateway HTTP ${response.status}`);
+  }
+  return response.json();
+}
+
+export async function fetchDatasetGatewayCatalog(
+  options: { signal?: AbortSignal; fetcher?: DatasetFetch } = {},
+): Promise<DatasetGatewayCatalog> {
+  const fetcher = options.fetcher ?? fetch;
+  const response = await fetcher("/api/v1/lidar/dataset-gateway", {
+    method: "GET",
+    headers: { Accept: "application/json" },
+    signal: options.signal,
+  });
+  return parseDatasetGatewayCatalog(await responseJson(response));
+}

apps/control-station/src/styles/responsive.css

@@ -137,6 +137,17 @@
 }
 
 @media (max-width: 760px) {
+  .dataset-gateway__representations,
+  .dataset-gateway__grid,
+  .dataset-gateway__footer {
+    grid-template-columns: 1fr;
+  }
+
+  .dataset-gateway__representations > div + div {
+    border-top: 1px solid rgb(255 255 255 / 0.07);
+    border-left: 0;
+  }
+
   .control-station .nodedc-header__profile-button {
     display: none;
   }

apps/control-station/src/styles/workspaces.css

@@ -807,6 +807,144 @@
   gap: 1rem;
 }
 
+.dataset-gateway {
+  display: grid;
+  gap: 1rem;
+  overflow: hidden;
+  border: 1px solid color-mix(in srgb, var(--nodedc-accent) 24%, transparent);
+  background:
+    radial-gradient(circle at 10% 0%, color-mix(in srgb, var(--nodedc-accent) 10%, transparent), transparent 32%),
+    rgb(255 255 255 / 0.025);
+}
+
+.dataset-gateway__heading p,
+.dataset-gateway__grid p,
+.dataset-gateway__pending {
+  margin: 0.4rem 0 0;
+  color: var(--nodedc-text-muted);
+  font-size: 0.68rem;
+  line-height: 1.55;
+}
+
+.dataset-gateway__representations {
+  display: grid;
+  grid-template-columns: repeat(3, minmax(0, 1fr));
+  overflow: hidden;
+  border: 1px solid rgb(255 255 255 / 0.07);
+  border-radius: 0.9rem;
+}
+
+.dataset-gateway__representations > div {
+  position: relative;
+  display: grid;
+  min-height: 7.4rem;
+  align-content: center;
+  gap: 0.3rem;
+  padding: 1rem 1.1rem 1rem 3.6rem;
+  background: rgb(255 255 255 / 0.025);
+}
+
+.dataset-gateway__representations > div + div {
+  border-left: 1px solid rgb(255 255 255 / 0.07);
+}
+
+.dataset-gateway__representations > div > span {
+  position: absolute;
+  top: 1rem;
+  left: 1rem;
+  color: var(--nodedc-accent);
+  font-size: 0.62rem;
+  letter-spacing: 0.14em;
+}
+
+.dataset-gateway__representations strong,
+.dataset-gateway__representations small,
+.dataset-gateway__representations em {
+  display: block;
+}
+
+.dataset-gateway__representations strong {
+  color: var(--nodedc-text-primary);
+  font-size: 0.76rem;
+}
+
+.dataset-gateway__representations small,
+.dataset-gateway__representations em {
+  color: var(--nodedc-text-muted);
+  font-size: 0.58rem;
+  line-height: 1.35;
+}
+
+.dataset-gateway__representations em {
+  color: color-mix(in srgb, var(--nodedc-accent) 72%, white);
+  font-style: normal;
+}
+
+.dataset-gateway__grid {
+  display: grid;
+  grid-template-columns: repeat(2, minmax(0, 1fr));
+  gap: 0.7rem;
+}
+
+.dataset-gateway__grid > section {
+  min-width: 0;
+  padding: 1rem;
+  border: 1px solid rgb(255 255 255 / 0.07);
+  border-radius: 0.9rem;
+  background: rgb(255 255 255 / 0.02);
+}
+
+.dataset-gateway__grid > section[data-warning="true"] {
+  border-color: rgb(255 181 71 / 0.2);
+}
+
+.dataset-gateway__grid h3 {
+  margin: 0.28rem 0 0;
+  color: var(--nodedc-text-primary);
+  font-size: 1rem;
+}
+
+.dataset-gateway__facts {
+  display: flex;
+  flex-wrap: wrap;
+  gap: 0.35rem;
+  margin-top: 0.8rem;
+}
+
+.dataset-gateway__facts span {
+  padding: 0.32rem 0.5rem;
+  border-radius: 999px;
+  background: rgb(255 255 255 / 0.045);
+  color: var(--nodedc-text-secondary);
+  font-size: 0.56rem;
+}
+
+.dataset-gateway__footer {
+  display: grid;
+  grid-template-columns: minmax(0, 0.8fr) minmax(0, 1.2fr);
+  gap: 1rem;
+  padding-top: 0.85rem;
+  border-top: 1px solid rgb(255 255 255 / 0.07);
+}
+
+.dataset-gateway__footer > div {
+  display: grid;
+  gap: 0.2rem;
+  min-width: 0;
+}
+
+.dataset-gateway__footer span,
+.dataset-gateway__footer small {
+  color: var(--nodedc-text-muted);
+  font-size: 0.58rem;
+}
+
+.dataset-gateway__footer strong {
+  overflow-wrap: anywhere;
+  color: var(--nodedc-text-primary);
+  font-size: 0.68rem;
+}
+
 .lidar-quality-message {
   display: grid;
   min-height: 12rem;

apps/control-station/src/workspaces/DatasetGatewayPanel.tsx

@@ -0,0 +1,133 @@
+import { useEffect, useState } from "react";
+import { GlassSurface, StatusBadge } from "@nodedc/ui-react";
+
+import {
+  fetchDatasetGatewayCatalog,
+  type DatasetGatewayCatalog,
+} from "../core/lidar/datasetGateway";
+
+const representationLabels: Record<string, string> = {
+  "native-scan": "Один оборот / скан",
+  "normalized-scan": "Deskew + bounded cleanup",
+  "rolling-local-map": "Pose + TTL + voxel map",
+};
+
+export function DatasetGatewayPanel() {
+  const [catalog, setCatalog] = useState<DatasetGatewayCatalog | null>(null);
+  const [error, setError] = useState<string | null>(null);
+
+  useEffect(() => {
+    const controller = new AbortController();
+    void fetchDatasetGatewayCatalog({ signal: controller.signal })
+      .then((value) => {
+        if (!controller.signal.aborted) setCatalog(value);
+      })
+      .catch((loadError: unknown) => {
+        if (controller.signal.aborted) return;
+        setError(
+          loadError instanceof Error
+            ? loadError.message
+            : "Dataset Gateway недоступен",
+        );
+      });
+    return () => controller.abort();
+  }, []);
+
+  return (
+    <GlassSurface className="dataset-gateway" padding="lg">
+      <header className="panel-heading dataset-gateway__heading">
+        <div>
+          <span className="section-eyebrow">DATASET GATEWAY · S0</span>
+          <h2>Три разных LiDAR-продукта</h2>
+          <p>
+            Кольцевой одиночный скан, очищенный sensor-frame и накопленная карта
+            больше не считаются одним облаком.
+          </p>
+        </div>
+        <StatusBadge
+          tone={error ? "danger" : catalog?.storage.admitted ? "success" : "warning"}
+        >
+          {error
+            ? "Gateway недоступен"
+            : catalog?.storage.admitted
+              ? "D: допущен"
+              : "Ожидает D:"}
+        </StatusBadge>
+      </header>
+
+      {catalog ? (
+        <>
+          <div className="dataset-gateway__representations">
+            {catalog.representations.map((representation, index) => (
+              <div key={representation.id}>
+                <span>0{index + 1}</span>
+                <strong>
+                  {representationLabels[representation.id] ?? representation.title}
+                </strong>
+                <small>{representation.title}</small>
+                <em>
+                  {representation.accumulation
+                    ? "накопление включено явно"
+                    : "без накопления"}
+                </em>
+              </div>
+            ))}
+          </div>
+
+          <div className="dataset-gateway__grid">
+            <section>
+              <span className="section-eyebrow">ПЕРВЫЙ BASELINE</span>
+              <h3>{catalog.source.displayName}</h3>
+              <p>
+                Один оборот VLS-128 в SemanticKITTI XYZI + point-wise semantic и
+                instance labels. Это то самое разреженное кольцевое облако,
+                которое корректно сравнивать с алгоритмами.
+              </p>
+              <div className="dataset-gateway__facts">
+                <span>{catalog.source.platforms.join(" · ")}</span>
+                <span>{catalog.source.superclasses.length} superclasses</span>
+                <span>val {catalog.source.validationArchiveGb} ГБ</span>
+                <span>{catalog.source.license}</span>
+              </div>
+            </section>
+            <section data-warning="true">
+              <span className="section-eyebrow">ТЕКУЩИЙ DEVICE INPUT</span>
+              <h3>Mapped feed ≠ raw scan</h3>
+              <p>
+                Внешний MQTT содержит vendor-mapped increment после LIO. В нём
+                нет per-point time и line/ring, поэтому из него нельзя честно
+                восстановить один исходный скан или выполнить deskew.
+              </p>
+              <div className="dataset-gateway__facts">
+                <span>Patchwork++: diagnostic only</span>
+                <span>rolling map: возможно</span>
+                <span>raw reconstruction: невозможно</span>
+              </div>
+            </section>
+          </div>
+
+          <footer className="dataset-gateway__footer">
+            <div>
+              <span>Storage gate</span>
+              <strong>{catalog.storage.requiredWindowsRoot}</strong>
+              <small>{catalog.storage.requiredWslRoot}</small>
+            </div>
+            <div>
+              <span>Следующий исполнимый шаг</span>
+              <strong>
+                {catalog.storage.admitted
+                  ? "Скачать GOOSE validation и импортировать первый кадр"
+                  : "Подключить Dataset Root на D: worker"}
+              </strong>
+              <small>Автозагрузка 3.3 ГБ намеренно запрещена</small>
+            </div>
+          </footer>
+        </>
+      ) : (
+        <p className="dataset-gateway__pending">
+          {error ?? "Читаем входные контракты Dataset Gateway…"}
+        </p>
+      )}
+    </GlassSurface>
+  );
+}

apps/control-station/src/workspaces/LidarQualityWorkspace.tsx

@@ -26,6 +26,7 @@ import {
   LidarGroundPointCloud,
   type LidarGroundViewMode,
 } from "./LidarGroundPointCloud";
+import { DatasetGatewayPanel } from "./DatasetGatewayPanel";
 
 function formatNumber(value: number | null, digits = 1): string {
   if (value === null) return "—";
@@ -220,6 +221,8 @@ export function LidarQualityWorkspace({
         <span className="workspace-lead__note">Только проверенные replay-артефакты</span>
       </section>
 
+      <DatasetGatewayPanel />
+
       {loading && !detail ? (
         <GlassSurface className="lidar-quality-message" padding="lg">
           <StatusBadge tone="accent">Проверка evidence</StatusBadge>

apps/control-station/test/datasetGateway.test.mjs

@@ -0,0 +1,139 @@
+import assert from "node:assert/strict";
+import { after, before, test } from "node:test";
+
+import { createServer } from "vite";
+
+let server;
+let parseDatasetGatewayCatalog;
+let fetchDatasetGatewayCatalog;
+let DatasetGatewayContractError;
+
+before(async () => {
+  server = await createServer({
+    appType: "custom",
+    logLevel: "silent",
+    server: { middlewareMode: true },
+  });
+  ({
+    parseDatasetGatewayCatalog,
+    fetchDatasetGatewayCatalog,
+    DatasetGatewayContractError,
+  } = await server.ssrLoadModule("/src/core/lidar/datasetGateway.ts"));
+});
+
+after(async () => {
+  await server?.close();
+});
+
+function catalog(overrides = {}) {
+  return {
+    schema_version: "missioncore.dataset-gateway-catalog/v1",
+    access: "read-only",
+    storage: {
+      configured: false,
+      required_windows_root: "D:\\NDC_MISSIONCORE\\datasets",
+      required_wsl_root: "/mnt/d/NDC_MISSIONCORE/datasets",
+      admitted: false,
+      status: "blocked-storage-policy",
+      path_exposed: false,
+    },
+    sources: [{
+      source_id: "goose-3d/v2025-08-22",
+      display_name: "GOOSE 3D",
+      role: "primary-offroad-semantic-baseline",
+      license: "CC-BY-SA-4.0",
+      format: "semantickitti-xyzi-label",
+      frame_semantics: "one-lidar-revolution",
+      platforms: ["MuCAR-3", "ALICE", "Spot"],
+      annotations: ["semantic-point", "instance-point"],
+      superclasses: ["natural-ground", "obstacle"],
+      download: {
+        automatic: false,
+        reason: "operator-admitted-large-artifact-only",
+        validation_archive_gb: 3.3,
+      },
+      admission: {
+        status: "blocked-storage-policy",
+      },
+    }],
+    representations: [
+      {
+        id: "native-scan",
+        title: "Одиночный исходный скан",
+        purpose: "dataset-ground-truth-and-sensor-domain",
+        accumulation: false,
+      },
+      {
+        id: "normalized-scan",
+        title: "Нормализованный sensor-frame скан",
+        purpose: "deskew-filter-inference-and-algorithm-comparison",
+        accumulation: false,
+      },
+      {
+        id: "rolling-local-map",
+        title: "Накопленная локальная карта",
+        purpose: "stable-operator-view-and-local-planning",
+        accumulation: true,
+      },
+    ],
+    pipeline: [{
+      stage: "deskew",
+      requires: ["per-point-time", "imu-or-odometry"],
+      produces: "normalized-scan",
+    }],
+    known_inputs: [{
+      source_id: "current-recorded-lidar/vendor-map",
+      representation: "vendor-mapped-increment",
+      native_scan: false,
+      per_point_time: false,
+      ring_or_line: false,
+      admitted_for_patchworkpp: false,
+      reason: "post-lio-map-product-cannot-be-reconstructed-as-a-native-scan",
+    }],
+    next_action: "configure-dataset-root-on-worker-d",
+    ...overrides,
+  };
+}
+
+test("parses three distinct LiDAR representations and current-input boundary", () => {
+  const parsed = parseDatasetGatewayCatalog(catalog());
+  assert.deepEqual(
+    parsed.representations.map((item) => item.id),
+    ["native-scan", "normalized-scan", "rolling-local-map"],
+  );
+  assert.equal(parsed.representations[2].accumulation, true);
+  assert.equal(parsed.currentInput.admittedForPatchworkpp, false);
+  assert.equal(parsed.source.frameSemantics, "one-lidar-revolution");
+});
+
+test("rejects path exposure and upgraded K1 semantics", () => {
+  const exposed = catalog();
+  exposed.storage.path_exposed = true;
+  assert.throws(
+    () => parseDatasetGatewayCatalog(exposed),
+    DatasetGatewayContractError,
+  );
+
+  const upgraded = catalog();
+  upgraded.known_inputs[0].per_point_time = true;
+  assert.throws(
+    () => parseDatasetGatewayCatalog(upgraded),
+    DatasetGatewayContractError,
+  );
+});
+
+test("fetches the read-only gateway endpoint", async () => {
+  const calls = [];
+  const parsed = await fetchDatasetGatewayCatalog({
+    fetcher: async (url, init) => {
+      calls.push({ url, init });
+      return new Response(JSON.stringify(catalog()), {
+        status: 200,
+        headers: { "Content-Type": "application/json" },
+      });
+    },
+  });
+  assert.equal(calls[0].url, "/api/v1/lidar/dataset-gateway");
+  assert.equal(calls[0].init.method, "GET");
+  assert.equal(parsed.source.displayName, "GOOSE 3D");
+});

docs/13_LIDAR_WORKER_PRODUCT_AND_ROADMAP.md

@@ -1,8 +1,8 @@
 # LiDAR worker: product value, evidence boundary and implementation roadmap
 
 Date: 2026-07-25
-Status: accepted architecture plan; L0/L1 implemented; L2 diagnostic A/B complete,
+Status: accepted architecture plan; L0/L1 implemented; L2 diagnostic A/B complete;
-independent labels pending
+Dataset Gateway S0 implemented, first real GOOSE import pending worker D storage
 Scope: real scanner records, replay and future live shadow processing
 Explicitly out of scope: Unreal U0/U1, Gaussian assets and simulator rendering
 
@@ -110,7 +110,9 @@ unknown, camera-only velocity is not metric, 374 conflicts remain, and the
 benchmark is not independent ground truth.
 
 The next work must therefore improve the LiDAR-native input and evaluation
-surface, not add another visual smoothing pass.
+surface, not add another visual smoothing pass. Mission Core will use
+independently labeled public datasets before requesting any new manual K1
+annotation. The current K1 evidence stays an unlabeled out-of-domain smoke test.
 
 ## 4. Market and stack assessment
 
@@ -236,10 +238,10 @@ quality line. It is not repaired or hidden by replay.
   distributions in `missioncore.lidar-ground-benchmark/v1`.
 - [x] Create an immutable eight-frame annotation template in which every point
   starts as `ignore-unreviewed`; it is explicitly not ground truth.
-- [ ] Complete independent human review for ground, curb, low obstacle,
+- [ ] Keep the K1 annotation template frozen as an optional later
-  reflection noise and other non-ground points.
+  domain-adaptation asset; do not make manual review the current critical path.
-- [ ] Measure accepted ground IoU, curb/low-obstacle recall and
+- [ ] Measure accepted ground IoU and obstacle recall first against an admitted
-  reflection-noise rejection against that reviewed generation.
+  GOOSE native scan and its published point-wise labels.
 
 The real diagnostic run is
 `ground-benchmark-68cfd7a8f1dd4c0006183bb4f63a23f9ff1dd7459317ff0886e995f6c320d984`.
@@ -285,16 +287,43 @@ geometry is not exported. The measured 1.27 m estimate can be reproduced as a
 named diagnostic profile; tuning that offset until Patchwork++ merely looks
 plausible would still invalidate the comparison.
 
-The independent-label exit remains open. It can be closed by reviewing the
+The K1-specific independent-label exit remains open, but it is no longer the
-content-bound template
+next step. The Dataset Gateway provides a labeled public-domain evaluation
-`ground-annotation-template-12e12eab0756c14f5e06adcaf13189e93188df9bb6d31224cb9b7d566ec15b18`,
+path. K1 manual review or a new real vehicle dataset is reserved for later
-or by acquiring an admitted raw sensor scan with known physical sensor height
+domain adaptation after a public baseline proves that the pipeline and metric
-and then producing a new benchmark generation.
+harness work.
+
+### L2.5 — Dataset Gateway — S0 complete, real import pending
+
+- [x] Define separate `native-scan`, `normalized-scan` and
+  `rolling-local-map` representations.
+- [x] Add a lossless GOOSE/SemanticKITTI XYZI + packed semantic/instance label
+  reader with point-alignment and finite-value gates.
+- [x] Publish the read-only Dataset Gateway contract in React.
+- [x] Refuse to relabel current `lio_pcl` as a native scan or to invent missing
+  per-point time and line/ring fields.
+- [x] Require operator-admitted storage under
+  `D:\NDC_MISSIONCORE\datasets`.
+- [ ] Configure the worker dataset root and record disk/resource baseline.
+- [ ] Download only the 3.3 GB GOOSE validation archive first and record its
+  hash/license/provenance.
+- [ ] Show one real labeled revolution in React with native remission and
+  ground-truth superclass coloring.
+- [ ] Admit an explicit frame/mounting profile before normalization.
+- [ ] Run current ground and Patchwork++ against GOOSE ground truth.
+- [ ] Add named range/FOV/density/noise/dropout degradation profiles without
+  overwriting the native frame.
+
+The architectural contract and run sequence are fixed in
+`docs/14_LIDAR_DATASET_GATEWAY.md` and ADR 0021. GOOSE is first because its
+published 3D format is one LiDAR revolution with point-wise semantic and
+instance labels in off-road environments. RELLIS-3D remains the second-source
+cross-check after the GOOSE harness is stable.
 
 ### L3 — LiDAR-native 3D detection
 
-- [ ] Freeze independent 3D annotations covering people, vehicles, cyclists,
+- [ ] Establish the public-dataset baseline first; freeze K1-specific 3D
-  stroller groups, vegetation and confusing static structures.
+  annotations only when a measured domain gap justifies them.
 - [ ] Run NVIDIA PointPillars through the existing external worker/Triton seam.
 - [ ] Treat pretrained output as a baseline, not an accepted product model.
 - [ ] Measure class precision/recall, center/range/yaw error, distance-bucket
@@ -358,6 +387,8 @@ The near-term value is not a prettier point cloud:
 - hardware selection becomes evidence-driven: a future vehicle LiDAR is
   accepted by its timing/fields/profile, not by vendor marketing.
 
-The highest-value immediate work is L1, followed by L2 and L3. Nvblox and
+The highest-value immediate work is the worker-side GOOSE validation import,
-alternative SLAM are useful, but starting them before their input gates would
+the first labeled native scan in React and an accuracy-bearing ground A/B.
-produce attractive demos with unqualified geometry.
+LiDAR-native detection follows on the same gateway. Nvblox and alternative
+SLAM remain later because their timing, pose and scan-geometry gates are not yet
+satisfied.

docs/14_LIDAR_DATASET_GATEWAY.md

@@ -0,0 +1,140 @@
+# LiDAR Dataset Gateway
+
+## Product value
+
+The Dataset Gateway gives Mission Core a repeatable perception laboratory
+before the production vehicle and its final sensor installation exist. It
+separates four questions that were previously mixed together:
+
+- whether the transport preserved the sensor evidence;
+- whether preprocessing produces a valid one-scan perception input;
+- whether an algorithm is accurate against independent labels;
+- whether several scans form a stable local map for an operator or planner.
+
+This prevents tuning an algorithm until a visually dense vendor map merely
+looks plausible. It also keeps work reusable across Gazebo, Unreal, public
+datasets and future real onboard sensors.
+
+## Current S0 slice
+
+Implemented now:
+
+- `missioncore.dataset-gateway-catalog/v1`, exposed read-only at
+  `GET /api/v1/lidar/dataset-gateway`;
+- explicit `native-scan`, `normalized-scan` and `rolling-local-map`
+  representations;
+- a lossless GOOSE/SemanticKITTI frame reader for little-endian float32 XYZI
+  and packed uint32 semantic/instance labels;
+- count, finite-value and maximum-point safety gates;
+- immutable point-aligned arrays;
+- a fail-closed K1 `lio_pcl` boundary;
+- worker storage admission for `D:\NDC_MISSIONCORE\datasets` and
+  `/mnt/d/NDC_MISSIONCORE/datasets`;
+- a visible Dataset Gateway panel in **Данные → Качество LiDAR**.
+
+Not implemented in S0:
+
+- no automatic 3.3 GB validation archive download;
+- no implicit coordinate conversion;
+- no fake ring/timestamp reconstruction for K1 MQTT evidence;
+- no model training or production promotion;
+- no rolling-map implementation yet.
+
+## Why public recordings look different
+
+GOOSE stores one VLS-128 revolution per annotated `.bin` file. A rotating
+multi-channel sensor produces discrete scan lines, so a single sensor-frame
+view looks like sparse rings.
+
+The current field review is explicitly an accumulated map-frame window. It
+combines many source publications after pose registration. This fills surfaces
+and hides the original scan pattern. The external K1 stream is also already a
+post-LIO/modeling product and lacks the raw driver fields needed to reconstruct
+an original scan.
+
+Livox sensors additionally use a scan pattern that differs from classic fixed
+vertical channels. Time integration therefore changes their visual density in
+a different way. “Ring-like” is a sensor geometry property, not a universal
+quality target.
+
+## Canonical processing profiles
+
+### P0 — native evidence
+
+Required:
+
+- source ID and immutable frame ID;
+- XYZ and the original return/remission/intensity field;
+- semantic and instance labels when present;
+- calibration/mounting/timing evidence as separate metadata;
+- no accumulation and no hidden world transform.
+
+Output: `native-scan`.
+
+### P1 — normalized perception scan
+
+Ordered operations:
+
+1. decode and apply only evidenced factory calibration;
+2. assign an explicit sensor coordinate frame;
+3. deskew when per-point time and synchronized motion are available;
+4. apply bounded range and field-of-view policy;
+5. remove the vehicle/self mask;
+6. apply named outlier and voxel policies;
+7. retain a reversible index/provenance map to the native frame.
+
+Output: `normalized-scan`.
+
+### P2 — inference
+
+Ground, semantic and object providers consume P1. Patchwork++ belongs here. It
+does not own P0/P1 or P3.
+
+Output: point-aligned predictions and reproducible metrics against labels.
+
+### P3 — rolling local map
+
+Ordered operations:
+
+1. bind each normalized scan to an evidenced pose;
+2. transform to `odom` or a declared local-map frame;
+3. deduplicate with a named voxel policy;
+4. expire points by TTL or travelled distance;
+5. keep dynamic points short-lived or track them separately;
+6. publish bounded map state and its contributing frame identities.
+
+Output: `rolling-local-map`.
+
+This is the stage that should stop static geometry from “jumping”. Deskew
+reduces within-scan motion distortion; registration stabilizes scans across
+time; TTL/dynamic filtering prevents stale ghosts.
+
+## First dataset sequence
+
+1. Configure `MISSIONCORE_DATASET_ROOT=/mnt/d/NDC_MISSIONCORE/datasets` on the
+   Windows/WSL worker.
+2. Verify free space and record archive size/hash/license.
+3. Download only the GOOSE 3D validation archive first (published size 3.3 GB).
+4. Import one labeled frame and expose it in React as `native-scan`.
+5. Show native remission and ground-truth superclass coloring.
+6. Add a declared GOOSE frame/mounting profile and produce `normalized-scan`.
+7. Run current ground heuristic and Patchwork++ against independent labels.
+8. Add sensor-degradation profiles for range, FOV, density, noise and dropout.
+9. Only after the one-frame contract passes, expand to the validation split and
+   add a rolling-map sequence with localization evidence.
+
+## Acceptance checklist
+
+- [x] Representations cannot be silently interchanged.
+- [x] Large artifacts require operator-admitted D-only storage.
+- [x] GOOSE XYZI and labels remain point aligned.
+- [x] Invalid length and non-finite frames fail closed.
+- [x] K1 mapped increments cannot claim raw-scan fields.
+- [x] React exposes the architectural truth before dataset bytes exist.
+- [ ] Worker D root configured.
+- [ ] GOOSE validation archive hash recorded.
+- [ ] First real labeled frame visible in React.
+- [ ] Coordinate and mounting profile admitted.
+- [ ] Patchwork++ accuracy measured against ground truth.
+- [ ] Sensor-degradation matrix qualified.
+- [ ] Rolling local map with pose/TTL/dynamic policy qualified.

docs/adr/0021-dataset-gateway-representation-boundary.md

@@ -0,0 +1,90 @@
+# ADR 0021: separate native scans, normalized scans and rolling local maps
+
+Status: accepted
+Date: 2026-07-25
+
+## Context
+
+Public autonomous-driving and field-robotics dataset viewers commonly display
+one LiDAR revolution. Fixed-channel rotating sensors therefore produce the
+familiar sparse rings. The current XGRIDS K1 MQTT `lio_pcl` evidence is a
+different product: firmware evidence places it after LIO/modeling, and the
+field-review UI accumulates multiple already registered increments in the map
+frame.
+
+Point count alone does not make these representations comparable. A cloud can
+be sparse per publication and still look dense after several seconds of pose
+registration. Conversely, voxel downsampling does not restore timing, scan
+lines or raw sensor geometry that the source no longer carries.
+
+Patchwork++ is a ground classifier. It does not decode sensor packets, deskew
+motion distortion, estimate pose, stabilize a rolling map or remove ghosts
+from stale/dynamic observations. A successful Patchwork++ call against
+`lio_pcl` remains diagnostic and does not repair the input domain.
+
+## Decision
+
+Mission Core defines three non-interchangeable LiDAR products:
+
+1. `native-scan`: one losslessly decoded source scan/frame with its native
+   point-aligned fields and labels. It is never accumulated.
+2. `normalized-scan`: one sensor-frame scan after an explicit transform,
+   deskew and bounded cleanup profile. Every transformation retains source
+   identity and point alignment.
+3. `rolling-local-map`: normalized scans registered by pose into a bounded
+   local map with explicit TTL, voxel deduplication and dynamic-point policy.
+
+The Dataset Gateway is the first producer of this contract. GOOSE 3D is the
+first admitted source because it publishes off-road point-wise semantic and
+instance labels in SemanticKITTI-compatible `XYZI + uint32 label` files. Its
+annotated point-cloud file represents one LiDAR revolution.
+
+The gateway:
+
+- preserves the native GOOSE frame before adaptation;
+- never transforms labels independently of their points;
+- does not assume a coordinate convention, mounting transform or sensor height
+  unless source metadata supplies it;
+- refuses automatic downloads of large archives;
+- admits storage only under `D:\NDC_MISSIONCORE\datasets` or its WSL mirror;
+- never promotes K1 `lio_pcl` to `native-scan`.
+
+The normalized pipeline is:
+
+```text
+native packet/source frame
+  -> decode + calibration
+  -> per-point-time deskew
+  -> range/self/outlier/voxel policy
+  -> normalized-scan
+  -> ground/object inference
+  -> pose registration + TTL + voxel deduplication
+  -> rolling-local-map
+```
+
+Deskew is conditional: it requires per-point time plus synchronized IMU or
+odometry. If those fields are missing, the gateway reports the stage as
+unavailable rather than inventing timestamps.
+
+## Consequences
+
+- The UI must label accumulated K1 evidence as a map product, not a scan.
+- Dataset and device inputs can share downstream algorithms only after their
+  normalized contracts match.
+- Sensor adaptation may change range, FOV, point density, noise and dropout for
+  robustness experiments, but it cannot recreate lost timestamps, occlusions
+  or material response.
+- Patchwork++ becomes eligible for a real quality gate only on a sensor-centric
+  scan with declared scan geometry and physical mounting height plus
+  independent labels.
+- Stable operator visualization is owned by rolling-map policy, not by the
+  ground classifier.
+
+## Primary references
+
+- [GOOSE dataset structure](https://goose-dataset.de/docs/dataset-structure/)
+- [GOOSE setup and archive sizes](https://goose-dataset.de/docs/setup/)
+- [GOOSE 3D challenge ontology](https://goose-dataset.de/docs/3d-semantic-segmentation-challenge/)
+- [Livox ROS Driver 2 point formats](https://github.com/Livox-SDK/livox_ros_driver2)
+- [Livox LIO motion-distortion handling](https://github.com/Livox-SDK/LIO-Livox)
+- [ROS FilterDeskew timestamp requirement](https://docs.ros.org/en/noetic/api/mp2p_icp/html/classmp2p__icp__filters_1_1FilterDeskew.html)

src/k1link/datasets/__init__.py

@@ -0,0 +1,17 @@
+"""Vendor-neutral dataset ingress for perception qualification."""
+
+from k1link.datasets.gateway import (
+    DATASET_GATEWAY_CATALOG_SCHEMA,
+    DatasetFrameError,
+    DatasetPointFrame,
+    dataset_gateway_catalog,
+    read_semantic_kitti_frame,
+)
+
+__all__ = [
+    "DATASET_GATEWAY_CATALOG_SCHEMA",
+    "DatasetFrameError",
+    "DatasetPointFrame",
+    "dataset_gateway_catalog",
+    "read_semantic_kitti_frame",
+]

src/k1link/datasets/gateway.py

@@ -0,0 +1,227 @@
+"""Dataset-first LiDAR ingress with explicit representation boundaries.
+
+The gateway never treats a registered map increment as a native sensor scan.
+It first preserves one source frame and its labels. Normalization and rolling
+map construction are separate, provenance-bearing products.
+"""
+
+from __future__ import annotations
+
+import os
+from dataclasses import dataclass
+from pathlib import Path, PureWindowsPath
+from typing import Final, Literal
+
+import numpy as np
+import numpy.typing as npt
+
+DATASET_GATEWAY_CATALOG_SCHEMA: Final = "missioncore.dataset-gateway-catalog/v1"
+DATASET_ROOT_ENV: Final = "MISSIONCORE_DATASET_ROOT"
+Representation = Literal["native-scan", "normalized-scan", "rolling-local-map"]
+
+
+class DatasetFrameError(ValueError):
+    """A dataset frame cannot satisfy its declared lossless source contract."""
+
+
+@dataclass(frozen=True)
+class DatasetPointFrame:
+    """One SemanticKITTI-compatible labeled LiDAR frame.
+
+    GOOSE publishes one LiDAR revolution per ``.bin`` frame. Coordinates and
+    remission stay source-native here; no vehicle transform or accumulation is
+    silently applied.
+    """
+
+    points_xyz_m: npt.NDArray[np.float32]
+    remission: npt.NDArray[np.float32]
+    semantic_labels: npt.NDArray[np.uint16]
+    instance_labels: npt.NDArray[np.uint16]
+    representation: Representation = "native-scan"
+
+    @property
+    def point_count(self) -> int:
+        return int(self.points_xyz_m.shape[0])
+
+
+def read_semantic_kitti_frame(
+    point_path: Path,
+    label_path: Path,
+    *,
+    maximum_points: int = 2_000_000,
+) -> DatasetPointFrame:
+    """Read one GOOSE/SemanticKITTI XYZI + packed-label frame losslessly."""
+
+    if maximum_points <= 0:
+        raise DatasetFrameError("maximum_points must be positive")
+    try:
+        point_size = point_path.stat().st_size
+        label_size = label_path.stat().st_size
+    except OSError as exc:
+        raise DatasetFrameError("dataset point or label file is unavailable") from exc
+    if point_size == 0 or point_size % 16:
+        raise DatasetFrameError("point frame must contain little-endian float32 XYZI tuples")
+    if label_size % 4:
+        raise DatasetFrameError("label frame must contain packed little-endian uint32 values")
+    point_count = point_size // 16
+    if point_count > maximum_points:
+        raise DatasetFrameError("dataset point frame exceeds the configured safety limit")
+    if label_size // 4 != point_count:
+        raise DatasetFrameError("point and label counts do not match")
+
+    try:
+        xyzi = np.fromfile(point_path, dtype="<f4").reshape((-1, 4))
+        packed_labels = np.fromfile(label_path, dtype="<u4")
+    except (OSError, ValueError) as exc:
+        raise DatasetFrameError("dataset frame cannot be decoded") from exc
+    if not np.isfinite(xyzi).all():
+        raise DatasetFrameError("dataset point frame contains non-finite values")
+
+    points = np.ascontiguousarray(xyzi[:, :3], dtype=np.float32)
+    remission = np.ascontiguousarray(xyzi[:, 3], dtype=np.float32)
+    semantic = np.ascontiguousarray(packed_labels & np.uint32(0xFFFF), dtype=np.uint16)
+    instance = np.ascontiguousarray(packed_labels >> np.uint32(16), dtype=np.uint16)
+    for values in (points, remission, semantic, instance):
+        values.setflags(write=False)
+    return DatasetPointFrame(points, remission, semantic, instance)
+
+
+def _configured_dataset_root() -> Path | None:
+    raw = os.environ.get(DATASET_ROOT_ENV, "").strip()
+    return Path(raw).expanduser().absolute() if raw else None
+
+
+def _is_worker_d_storage(root: Path | None) -> bool:
+    if root is None:
+        return False
+    raw = str(root)
+    windows = PureWindowsPath(raw)
+    if windows.drive.upper() == "D:":
+        return True
+    normalized = raw.replace("\\", "/").rstrip("/").lower()
+    return normalized == "/mnt/d/ndc_missioncore/datasets" or normalized.startswith(
+        "/mnt/d/ndc_missioncore/datasets/"
+    )
+
+
+def dataset_gateway_catalog(dataset_root: Path | None = None) -> dict[str, object]:
+    """Return the path-free, read-only ingress plan and current admission state."""
+
+    root = dataset_root if dataset_root is not None else _configured_dataset_root()
+    storage_admitted = _is_worker_d_storage(root)
+    return {
+        "schema_version": DATASET_GATEWAY_CATALOG_SCHEMA,
+        "access": "read-only",
+        "storage": {
+            "configured": root is not None,
+            "required_windows_root": r"D:\NDC_MISSIONCORE\datasets",
+            "required_wsl_root": "/mnt/d/NDC_MISSIONCORE/datasets",
+            "admitted": storage_admitted,
+            "status": "ready" if storage_admitted else "blocked-storage-policy",
+            "path_exposed": False,
+        },
+        "sources": [
+            {
+                "source_id": "goose-3d/v2025-08-22",
+                "display_name": "GOOSE 3D",
+                "role": "primary-offroad-semantic-baseline",
+                "license": "CC-BY-SA-4.0",
+                "format": "semantickitti-xyzi-label",
+                "frame_semantics": "one-lidar-revolution",
+                "platforms": ["MuCAR-3", "ALICE", "Spot"],
+                "annotations": ["semantic-point", "instance-point"],
+                "superclasses": [
+                    "other",
+                    "artificial-structures",
+                    "artificial-ground",
+                    "natural-ground",
+                    "obstacle",
+                    "vehicle",
+                    "vegetation",
+                    "human",
+                    "sky",
+                ],
+                "download": {
+                    "automatic": False,
+                    "reason": "operator-admitted-large-artifact-only",
+                    "training_archive_gb": 27.0,
+                    "validation_archive_gb": 3.3,
+                    "test_archive_gb": 3.3,
+                },
+                "admission": {
+                    "status": (
+                        "ready-for-download" if storage_admitted else "blocked-storage-policy"
+                    ),
+                    "native_scan": "ready-after-download",
+                    "normalized_scan": "requires-explicit-frame-and-mounting-contract",
+                    "rolling_local_map": "requires-pose-timing-and-map-policy",
+                },
+            }
+        ],
+        "representations": [
+            {
+                "id": "native-scan",
+                "title": "Одиночный исходный скан",
+                "retains": ["xyz", "remission", "semantic-label", "instance-label"],
+                "purpose": "dataset-ground-truth-and-sensor-domain",
+                "accumulation": False,
+            },
+            {
+                "id": "normalized-scan",
+                "title": "Нормализованный sensor-frame скан",
+                "retains": ["source-provenance", "point-alignment", "labels"],
+                "purpose": "deskew-filter-inference-and-algorithm-comparison",
+                "accumulation": False,
+            },
+            {
+                "id": "rolling-local-map",
+                "title": "Накопленная локальная карта",
+                "retains": ["source-frame-ids", "pose-provenance", "age"],
+                "purpose": "stable-operator-view-and-local-planning",
+                "accumulation": True,
+            },
+        ],
+        "pipeline": [
+            {
+                "stage": "decode-and-calibrate",
+                "requires": ["native-packets-or-source-frame", "calibration"],
+                "produces": "native-scan",
+            },
+            {
+                "stage": "deskew",
+                "requires": ["per-point-time", "imu-or-odometry"],
+                "produces": "normalized-scan",
+            },
+            {
+                "stage": "bounded-cleanup",
+                "requires": ["range-policy", "self-mask", "outlier-policy", "voxel-policy"],
+                "produces": "normalized-scan",
+            },
+            {
+                "stage": "ground-and-object-inference",
+                "requires": ["normalized-scan", "declared-sensor-height-and-geometry"],
+                "produces": "point-aligned-predictions",
+            },
+            {
+                "stage": "pose-registration-and-rolling-map",
+                "requires": ["normalized-scan", "pose", "ttl", "voxel-deduplication"],
+                "produces": "rolling-local-map",
+            },
+        ],
+        "known_inputs": [
+            {
+                "source_id": "current-recorded-lidar/vendor-map",
+                "representation": "vendor-mapped-increment",
+                "native_scan": False,
+                "per_point_time": False,
+                "ring_or_line": False,
+                "admitted_for_patchworkpp": False,
+                "reason": "post-lio-map-product-cannot-be-reconstructed-as-a-native-scan",
+            }
+        ],
+        "next_action": (
+            "download-goose-validation-to-d"
+            if storage_admitted
+            else "configure-dataset-root-on-worker-d"
+        ),
+    }

src/k1link/web/lidar_api.py

@@ -20,6 +20,7 @@ from k1link.compute import (
     lidar_pack_catalog_item,
     lidar_pack_detail,
 )
+from k1link.datasets import dataset_gateway_catalog
 
 LIDAR_CATALOG_SCHEMA: Final = "missioncore.lidar-replay-pack-catalog/v1"
 LIDAR_GROUND_CATALOG_SCHEMA: Final = "missioncore.lidar-ground-benchmark-catalog/v1"
@@ -53,6 +54,10 @@ def build_lidar_router(
 ) -> APIRouter:
     router = APIRouter(prefix="/api/v1/lidar", tags=["lidar"])
 
+    @router.get("/dataset-gateway")
+    def get_dataset_gateway() -> dict[str, object]:
+        return dataset_gateway_catalog()
+
     @router.get("/replay-packs")
     def list_lidar_replay_packs(
         limit: int = Query(default=20, ge=1, le=100),

tests/test_dataset_gateway.py

@@ -0,0 +1,107 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+import numpy as np
+import pytest
+from fastapi import APIRouter
+from fastapi.routing import APIRoute
+
+from k1link.datasets import (
+    DatasetFrameError,
+    dataset_gateway_catalog,
+    read_semantic_kitti_frame,
+)
+from k1link.web.lidar_api import build_lidar_router
+
+
+def _endpoint(router: APIRouter, path: str) -> object:
+    for route in router.routes:
+        if isinstance(route, APIRoute) and route.path == path and "GET" in route.methods:
+            return route.endpoint
+    raise AssertionError(f"GET {path} route is missing")
+
+
+def test_goose_semantickitti_frame_retains_xyzi_and_packed_labels(
+    tmp_path: Path,
+) -> None:
+    points_path = tmp_path / "frame_vls128.bin"
+    labels_path = tmp_path / "frame_goose.label"
+    np.asarray(
+        [
+            [1.0, 2.0, 3.0, 0.25],
+            [-4.0, 5.0, 0.5, 0.75],
+        ],
+        dtype="<f4",
+    ).tofile(points_path)
+    np.asarray(
+        [
+            (12 << 16) | 3,
+            (99 << 16) | 42,
+        ],
+        dtype="<u4",
+    ).tofile(labels_path)
+
+    frame = read_semantic_kitti_frame(points_path, labels_path)
+
+    assert frame.representation == "native-scan"
+    assert frame.point_count == 2
+    assert frame.points_xyz_m.tolist() == [[1.0, 2.0, 3.0], [-4.0, 5.0, 0.5]]
+    assert frame.remission.tolist() == [0.25, 0.75]
+    assert frame.semantic_labels.tolist() == [3, 42]
+    assert frame.instance_labels.tolist() == [12, 99]
+    assert frame.points_xyz_m.flags.writeable is False
+
+
+def test_dataset_frame_fails_closed_on_misaligned_or_nonfinite_input(
+    tmp_path: Path,
+) -> None:
+    points_path = tmp_path / "frame.bin"
+    labels_path = tmp_path / "frame.label"
+    np.asarray([[1.0, 2.0, 3.0, 0.25]], dtype="<f4").tofile(points_path)
+    np.asarray([1, 2], dtype="<u4").tofile(labels_path)
+    with pytest.raises(DatasetFrameError, match="counts do not match"):
+        read_semantic_kitti_frame(points_path, labels_path)
+
+    np.asarray([[np.nan, 2.0, 3.0, 0.25]], dtype="<f4").tofile(points_path)
+    np.asarray([1], dtype="<u4").tofile(labels_path)
+    with pytest.raises(DatasetFrameError, match="non-finite"):
+        read_semantic_kitti_frame(points_path, labels_path)
+
+
+def test_dataset_gateway_enforces_d_storage_and_representation_boundaries(
+    tmp_path: Path,
+) -> None:
+    blocked = dataset_gateway_catalog(tmp_path / "datasets")
+    admitted = dataset_gateway_catalog(Path("/mnt/d/NDC_MISSIONCORE/datasets"))
+
+    assert blocked["storage"]["status"] == "blocked-storage-policy"  # type: ignore[index]
+    assert admitted["storage"]["status"] == "ready"  # type: ignore[index]
+    assert admitted["next_action"] == "download-goose-validation-to-d"
+    representations = admitted["representations"]
+    assert isinstance(representations, list)
+    assert [item["id"] for item in representations] == [  # type: ignore[index]
+        "native-scan",
+        "normalized-scan",
+        "rolling-local-map",
+    ]
+    inputs = admitted["known_inputs"]
+    assert isinstance(inputs, list)
+    assert inputs[0]["admitted_for_patchworkpp"] is False  # type: ignore[index]
+
+
+def test_dataset_gateway_api_is_read_only_and_path_free(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    monkeypatch.setenv("MISSIONCORE_DATASET_ROOT", "/mnt/d/NDC_MISSIONCORE/datasets")
+    route = _endpoint(build_lidar_router(), "/api/v1/lidar/dataset-gateway")
+    response = route()  # type: ignore[operator]
+
+    assert response["schema_version"] == "missioncore.dataset-gateway-catalog/v1"
+    assert response["access"] == "read-only"
+    assert response["storage"]["admitted"] is True
+    assert response["storage"]["path_exposed"] is False
+    assert "/mnt/d/NDC_MISSIONCORE/datasets" not in repr(response).replace(
+        response["storage"]["required_wsl_root"],  # type: ignore[index]
+        "",
+    )