typedef struct XrSpatialCapabilityConfigurationObjectTrackingEXT {
    XrStructureType                     type;
    const void*                         next;
    XrSpatialCapabilityEXT              capability;
    uint32_t                            enabledComponentCount;
    const XrSpatialComponentTypeEXT*    enabledComponents;
} XrSpatialCapabilityConfigurationObjectTrackingEXT;

typedef enum XrSpatialObjectSemanticLabelEXT {
    XR_SPATIAL_OBJECT_SEMANTIC_LABEL_UNCATEGORIZED_EXT = 1,
    XR_SPATIAL_OBJECT_SEMANTIC_LABEL_SOFA_EXT = 2,
    XR_SPATIAL_OBJECT_SEMANTIC_LABEL_BED_EXT = 3,
    XR_SPATIAL_OBJECT_SEMANTIC_LABEL_CHAIR_EXT = 4,
    XR_SPATIAL_OBJECT_SEMANTIC_LABEL_TABLE_EXT = 5,
    XR_SPATIAL_OBJECT_SEMANTIC_LABEL_LAMP_EXT = 6,
    XR_SPATIAL_OBJECT_SEMANTIC_LABEL_PLANT_EXT = 7,
    XR_SPATIAL_OBJECT_SEMANTIC_LABEL_DISPLAY_SCREEN_EXT = 8,
    XR_SPATIAL_OBJECT_SEMANTIC_LABEL_WALL_ART_EXT = 9,
    XR_SPATIAL_OBJECT_SEMANTIC_LABEL_CABINET_EXT = 10,
    XR_SPATIAL_OBJECT_SEMANTIC_LABEL_MAX_ENUM_EXT = 0x7FFFFFFF
} XrSpatialObjectSemanticLabelEXT;

typedef struct XrSpatialComponentObjectSemanticLabelListEXT {
    XrStructureType                     type;
    void*                               next;
    uint32_t                            semanticLabelCount;
    XrSpatialObjectSemanticLabelEXT*    semanticLabels;
} XrSpatialComponentObjectSemanticLabelListEXT;

typedef struct XrSpatialFeatureObjectSemanticLabelSubsetEXT {
    XrStructureType                           type;
    const void*                               next;
    uint32_t                                  semanticLabelCount;
    const XrSpatialObjectSemanticLabelEXT*    semanticLabels;
} XrSpatialFeatureObjectSemanticLabelSubsetEXT;

typedef enum XrSpatialKeyboardSemanticLabelEXT {
    XR_SPATIAL_KEYBOARD_SEMANTIC_LABEL_UNCATEGORIZED_EXT = 1,
    XR_SPATIAL_KEYBOARD_SEMANTIC_LABEL_KEYBOARD_EXT = 2,
    XR_SPATIAL_KEYBOARD_SEMANTIC_LABEL_MAX_ENUM_EXT = 0x7FFFFFFF
} XrSpatialKeyboardSemanticLabelEXT;

typedef struct XrSpatialComponentKeyboardSemanticLabelListEXT {
    XrStructureType                       type;
    void*                                 next;
    uint32_t                              semanticLabelCount;
    XrSpatialKeyboardSemanticLabelEXT*    semanticLabels;
} XrSpatialComponentKeyboardSemanticLabelListEXT;

typedef enum XrSpatialMouseSemanticLabelEXT {
    XR_SPATIAL_MOUSE_SEMANTIC_LABEL_UNCATEGORIZED_EXT = 1,
    XR_SPATIAL_MOUSE_SEMANTIC_LABEL_MOUSE_EXT = 2,
    XR_SPATIAL_MOUSE_SEMANTIC_LABEL_MAX_ENUM_EXT = 0x7FFFFFFF
} XrSpatialMouseSemanticLabelEXT;

typedef struct XrSpatialComponentMouseSemanticLabelListEXT {
    XrStructureType                    type;
    void*                              next;
    uint32_t                           semanticLabelCount;
    XrSpatialMouseSemanticLabelEXT*    semanticLabels;
} XrSpatialComponentMouseSemanticLabelListEXT;

// Check if object tracking capability is supported
uint32_t capabilityCount;
CHK_XR(xrEnumerateSpatialCapabilitiesEXT(instance, systemId, 0, &capabilityCount, nullptr));
std::vector<XrSpatialCapabilityEXT> capabilities(capabilityCount);
CHK_XR(xrEnumerateSpatialCapabilitiesEXT(instance, systemId, capabilityCount, &capabilityCount, capabilities.data()));

if (std::find(capabilities.begin(), capabilities.end(), XR_SPATIAL_CAPABILITY_OBJECT_TRACKING_EXT) == capabilities.end()) {
  return;
}

// Enumerate supported components for object tracking capability
XrSpatialCapabilityComponentTypesEXT objectComponents{XR_TYPE_SPATIAL_CAPABILITY_COMPONENT_TYPES_EXT};
CHK_XR(xrEnumerateSpatialCapabilityComponentTypesEXT(instance, systemId, XR_SPATIAL_CAPABILITY_OBJECT_TRACKING_EXT, &objectComponents));
std::vector<XrSpatialComponentTypeEXT> objectCapabilityComponents(objectComponents.componentTypeCountOutput);
objectComponents.componentTypeCapacityInput = objectCapabilityComponents.size();
objectComponents.componentTypes = objectCapabilityComponents.data();
CHK_XR(xrEnumerateSpatialCapabilityComponentTypesEXT(instance, systemId, XR_SPATIAL_CAPABILITY_OBJECT_TRACKING_EXT, &objectComponents));

// Check if the object & keyboard semantic labels component is supported
const auto supportsComponent = [&objectCapabilityComponents](XrSpatialComponentTypeEXT component) {
  return std::find(objectCapabilityComponents.begin(), objectCapabilityComponents.end(), component) != objectCapabilityComponents.end();
};

const bool supportsObjectSemanticLabel = supportsComponent(XR_SPATIAL_COMPONENT_TYPE_OBJECT_SEMANTIC_LABEL_EXT);
const bool supportsKeyboardSemanticLabel = supportsComponent(XR_SPATIAL_COMPONENT_TYPE_KEYBOARD_SEMANTIC_LABEL_EXT);

// Enumerate supported features for object tracking capability
uint32_t featureCount;
CHK_XR(xrEnumerateSpatialCapabilityFeaturesEXT(instance, systemId, XR_SPATIAL_CAPABILITY_OBJECT_TRACKING_EXT, 0, &featureCount, nullptr));
std::vector<XrSpatialCapabilityFeatureEXT> features(featureCount);
CHK_XR(xrEnumerateSpatialCapabilityFeaturesEXT(instance, systemId, XR_SPATIAL_CAPABILITY_OBJECT_TRACKING_EXT, featureCount, &featureCount, features.data()));

const bool supportsObjectSemanticLabelSubsetFeature = std::find(features.begin(), features.end(), XR_SPATIAL_CAPABILITY_FEATURE_OBJECT_SEMANTIC_LABEL_SUBSET_EXT) != features.end();

// Create a spatial context
XrSpatialContextEXT spatialContext{};

// Enable the guaranteed components of the object tracking capability
std::vector<XrSpatialComponentTypeEXT> enabledComponents = {
  XR_SPATIAL_COMPONENT_TYPE_BOUNDED_3D_EXT,
};
// Optionally enable the supported semantic labels
if (supportsObjectSemanticLabel) {
  enabledComponents.push_back(XR_SPATIAL_COMPONENT_TYPE_OBJECT_SEMANTIC_LABEL_EXT);
}
if (supportsKeyboardSemanticLabel) {
  enabledComponents.push_back(XR_SPATIAL_COMPONENT_TYPE_KEYBOARD_SEMANTIC_LABEL_EXT);
}

// We only want to track sofa and table.
std::vector<XrSpatialObjectSemanticLabelEXT> objectSemanticLabelSubset = {
  XR_SPATIAL_OBJECT_SEMANTIC_LABEL_SOFA_EXT,
  XR_SPATIAL_OBJECT_SEMANTIC_LABEL_TABLE_EXT
};
XrSpatialFeatureObjectSemanticLabelSubsetEXT subsetFeature{XR_TYPE_SPATIAL_FEATURE_OBJECT_SEMANTIC_LABEL_SUBSET_EXT};
subsetFeature.semanticLabelCount = objectSemanticLabelSubset.size();
subsetFeature.semanticLabels = objectSemanticLabelSubset.data();

XrSpatialCapabilityConfigurationObjectTrackingEXT objectTrackingConfig{XR_TYPE_SPATIAL_CAPABILITY_CONFIGURATION_OBJECT_TRACKING_EXT};
objectTrackingConfig.capability = XR_SPATIAL_CAPABILITY_OBJECT_TRACKING_EXT;
objectTrackingConfig.enabledComponentCount = enabledComponents.size();
objectTrackingConfig.enabledComponents = enabledComponents.data();
if (supportsObjectSemanticLabelSubsetFeature) {
  objectTrackingConfig.next = &subsetFeature;
}

std::array<XrSpatialCapabilityConfigurationBaseHeaderEXT*, 1> capabilityConfigs = {
  reinterpret_cast<XrSpatialCapabilityConfigurationBaseHeaderEXT*>(&objectTrackingConfig),
};

XrSpatialContextCreateInfoEXT spatialContextCreateInfo{XR_TYPE_SPATIAL_CONTEXT_CREATE_INFO_EXT};
spatialContextCreateInfo.capabilityConfigCount = capabilityConfigs.size();
spatialContextCreateInfo.capabilityConfigs = capabilityConfigs.data();
XrFutureEXT createContextFuture;
CHK_XR(xrCreateSpatialContextAsyncEXT(session, &spatialContextCreateInfo, &createContextFuture));

waitUntilReady(createContextFuture);

XrCreateSpatialContextCompletionEXT completion{XR_TYPE_CREATE_SPATIAL_CONTEXT_COMPLETION_EXT};
CHK_XR(xrCreateSpatialContextCompleteEXT(session, createContextFuture, &completion));
if (completion.futureResult != XR_SUCCESS) {
  return;
}

spatialContext = completion.spatialContext;

// ...
// Discovery entities with the spatial context
// ...

CHK_XR(xrDestroySpatialContextEXT(spatialContext));

XrFutureEXT future = XR_NULL_FUTURE_EXT;

// We want to look for entities that have the following components.
std::vector<XrSpatialComponentTypeEXT> snapshotComponents = {
  XR_SPATIAL_COMPONENT_TYPE_BOUNDED_3D_EXT,
};
if (supportsKeyboardSemanticLabel) {
  snapshotComponents.push_back(XR_SPATIAL_COMPONENT_TYPE_KEYBOARD_SEMANTIC_LABEL_EXT);
}

auto discoverSpatialEntities = [&](XrSpatialContextEXT spatialContext, XrTime time) {
  XrSpatialDiscoverySnapshotCreateInfoEXT snapshotCreateInfo{XR_TYPE_SPATIAL_DISCOVERY_SNAPSHOT_CREATE_INFO_EXT};
  snapshotCreateInfo.componentTypeCount = snapshotComponents.size();
  snapshotCreateInfo.componentTypes = snapshotComponents.data();
  CHK_XR(xrCreateSpatialDiscoverySnapshotAsyncEXT(spatialContext, &snapshotCreateInfo, &future));

  waitUntilReady(future);

  XrCreateSpatialDiscoverySnapshotCompletionInfoEXT completionInfo{XR_TYPE_CREATE_SPATIAL_DISCOVERY_SNAPSHOT_COMPLETION_INFO_EXT};
  completionInfo.baseSpace = localSpace;
  completionInfo.time = time;
  completionInfo.future = future;

  XrCreateSpatialDiscoverySnapshotCompletionEXT completion{XR_TYPE_CREATE_SPATIAL_DISCOVERY_SNAPSHOT_COMPLETION_EXT};
  CHK_XR(xrCreateSpatialDiscoverySnapshotCompleteEXT(spatialContext, &completionInfo, &completion));
  if (completion.futureResult == XR_SUCCESS) {

    // Query for the semantic label component data
    XrSpatialComponentDataQueryConditionEXT queryCond{XR_TYPE_SPATIAL_COMPONENT_DATA_QUERY_CONDITION_EXT};
    queryCond.componentTypeCount = snapshotComponents.size();
    queryCond.componentTypes = snapshotComponents.data();

    XrSpatialComponentDataQueryResultEXT queryResult{XR_TYPE_SPATIAL_COMPONENT_DATA_QUERY_RESULT_EXT};
    CHK_XR(xrQuerySpatialComponentDataEXT(completion.snapshot, &queryCond, &queryResult));

    std::vector<XrSpatialEntityIdEXT> entityIds(queryResult.entityIdCountOutput);
    std::vector<XrSpatialEntityTrackingStateEXT> entityStates(queryResult.entityIdCountOutput);
    queryResult.entityIdCapacityInput = entityIds.size();
    queryResult.entityIds = entityIds.data();
    queryResult.entityStateCapacityInput = entityStates.size();
    queryResult.entityStates = entityStates.data();

    std::vector<XrBoxf> bounded3D(queryResult.entityIdCountOutput);
    XrSpatialComponentBounded3DListEXT bounded3DList{XR_TYPE_SPATIAL_COMPONENT_BOUNDED_3D_LIST_EXT};
    bounded3DList.boundCount = bounded3D.size();
    bounded3DList.bounds = bounded3D.data();
    queryResult.next = &bounded3DList;

    std::vector<XrSpatialKeyboardSemanticLabelEXT> semanticLabels;
    XrSpatialComponentKeyboardSemanticLabelListEXT semanticLabelsList{XR_TYPE_SPATIAL_COMPONENT_KEYBOARD_SEMANTIC_LABEL_LIST_EXT};
    if (supportsKeyboardSemanticLabel) {
      semanticLabels.resize(queryResult.entityIdCountOutput);
      semanticLabelsList.semanticLabelCount = semanticLabels.size();
      semanticLabelsList.semanticLabels = semanticLabels.data();
      semanticLabelsList.next = queryResult.next;
      queryResult.next = &semanticLabelsList;
    }

    CHK_XR(xrQuerySpatialComponentDataEXT(completion.snapshot, &queryCond, &queryResult));

    for (int32_t i = 0; i < queryResult.entityIdCountOutput; ++i) {
      if (entityStates[i] != XR_SPATIAL_ENTITY_TRACKING_STATE_TRACKING_EXT) {
        continue;
      }

      // 3D bounds for entity entityIds[i] is bounded3D[i].extents centered on bounded3D[i].center.

      if (supportsKeyboardSemanticLabel) {
        // semantic label for entity entityIds[i] is semanticLabels[i].
      }
    }

    CHK_XR(xrDestroySpatialSnapshotEXT(completion.snapshot));
  }
};

while (1) {
  // ...
  // For every frame in frame loop
  // ...

  XrFrameState frameState;  // previously returned from xrWaitFrame
  const XrTime time = frameState.predictedDisplayTime;

  // Poll for the XR_TYPE_EVENT_DATA_SPATIAL_DISCOVERY_RECOMMENDED_EXT event
  XrEventDataBuffer event = {XR_TYPE_EVENT_DATA_BUFFER};
  XrResult result = xrPollEvent(instance, &event);
  if (result == XR_SUCCESS) {
      switch (event.type) {
          case XR_TYPE_EVENT_DATA_SPATIAL_DISCOVERY_RECOMMENDED_EXT: {
              const XrEventDataSpatialDiscoveryRecommendedEXT& eventdata =
                  *reinterpret_cast<XrEventDataSpatialDiscoveryRecommendedEXT*>(&event);
              // Discover spatial entities for the context that we received the "discovery
              // recommended" event for.
              discoverSpatialEntities(eventdata.spatialContext, time);
              break;
          }
      }
  }

  // ...
  // Finish frame loop
  // ...
}