fix(sample-data): exclude Observability (otel) sample set on AnalyticEngine data sources (#12216)

* fix(sample-data): exclude Observability (otel) sample set on AnalyticEngine

The sample data list route already limits the available sample sets for an
AnalyticEngine (Mustang) data source. It kept both 'logs' and 'otel', but the
Observability sample set (otel) cannot be installed on a Mustang domain: its
trace index mappings declare 'nested' fields (events/links), which the
pluggable data format rejects at index creation:

  mapper_parsing_exception: nested type is not supported with pluggable data
  format on field [links]

so the install fails with an internal server error
('Unable to install sample data set: Sample Observability Logs, Traces, and
Metrics'). Restrict the AnalyticEngine sample set list to 'logs' (Sample web
logs), which has no nested fields and installs cleanly.

Updates the route's unit test to assert only 'logs' is returned for an
AnalyticEngine data source; non-AnalyticEngine sources are unchanged.

Signed-off-by: Shenoy Pratik <pshenoy36@gmail.com>

* chore: add changelog fragment for #12216

Signed-off-by: Shenoy Pratik <pshenoy36@gmail.com>

* Update src/plugins/home/server/services/sample_data/routes/list.ts

Co-authored-by: Joshua Li <joshuali925@gmail.com>
Signed-off-by: Shenoy Pratik <sgguruda@amazon.com>

---------

Signed-off-by: Shenoy Pratik <pshenoy36@gmail.com>
Signed-off-by: Shenoy Pratik <sgguruda@amazon.com>
Co-authored-by: Joshua Li <joshuali925@gmail.com>

Author: ps48

changelogs/fragments/12216.yml

@@ -0,0 +1,2 @@
+fix:
+- Exclude the Observability (otel) sample data set on AnalyticEngine data sources, since its nested-field trace mappings cannot be created on a pluggable-dataformat domain ([#12216](https://github.com/opensearch-project/OpenSearch-Dashboards/pull/12216))

src/plugins/home/server/services/sample_data/routes/list.test.ts

@@ -274,7 +274,7 @@ describe('sample data list route', () => {
     );
   });
 
-  it('filters sample datasets to only logs and otel for AnalyticEngine data source', async () => {
+  it('filters sample datasets to only logs for AnalyticEngine data source', async () => {
     const mockDataSourceId = 'analyticEngineDataSource';
     const mockClient = jest.fn().mockResolvedValueOnce(true).mockResolvedValueOnce({ count: 1 });
 
@@ -342,10 +342,11 @@ describe('sample data list route', () => {
     expect(mockSOClient.get).toHaveBeenCalledWith('data-source', mockDataSourceId);
     expect(mockResponse.ok).toBeCalled();
 
-    // Verify that only logs and otel datasets are returned
+    // Verify that only the logs dataset is returned (otel is excluded because its
+    // nested-field trace mappings cannot be created on an AnalyticEngine domain)
     const responseBody = mockResponse.ok.mock.calls[0]?.[0]?.body as any[];
-    expect(responseBody).toHaveLength(2);
-    expect(responseBody.map((ds) => ds.id).sort()).toEqual(['logs', 'otel']);
+    expect(responseBody).toHaveLength(1);
+    expect(responseBody.map((ds) => ds.id).sort()).toEqual(['logs']);
   });
 
   it('returns all sample datasets for non-AnalyticEngine data source', async () => {

src/plugins/home/server/services/sample_data/routes/list.ts

@@ -54,12 +54,14 @@ export const createListRoute = (router: IRouter, sampleDatasets: SampleDatasetSc
       const workspaceState = getWorkspaceState(req);
       const workspaceId = workspaceState?.requestWorkspaceId;
 
-      // For AnalyticEngine (Mustang) datasource, only support Sample Observability Logs (otel) and Sample web logs (logs)
+      // For AnalyticEngine datasource, only support Sample web logs (logs). The
+      // Observability sample set (otel) is excluded because its trace index mappings use
+      // `nested` fields (events/links), which the pluggable data format rejects at index
+      // creation ("nested type is not supported with pluggable data format"), so installing
+      // it against an AnalyticEngine domain fails with an internal server error.
       let filteredSampleDatasets = sampleDatasets;
       if (await isAnalyticEngineDataSource(dataSourceId, context.core.savedObjects.client)) {
-        filteredSampleDatasets = sampleDatasets.filter(
-          (dataset) => dataset.id === 'logs' || dataset.id === 'otel'
-        );
+        filteredSampleDatasets = sampleDatasets.filter((dataset) => dataset.id === 'logs');
       }
 
       const registeredSampleDatasets = filteredSampleDatasets.map((sampleDataset) => {