[Fleet] Add unhealthy reason (input/output/other) to agent metrics (#178605)

## Summary

Closes elastic/ingest-dev#2522

Added `unhealthy_reason` aggregation when querying agent metrics.

The [mapping
change](elastic/elasticsearch#106246) and
[fleet-server change](elastic/fleet-server#3338)
is needed to be merged first to verify end to end.

Steps to verify:
- enroll an agent with docker
- add endpoint integration, expect an input and output unit error status
on the agent doc
- wait a few seconds so that the agent metrics are published
- verify that the agent metrics include `unhealthy_reason`, using the
query below

```
GET metrics-fleet_server.agent_status-default/_search
{
  "_source": ["fleet.agents"]
}

  "hits": [
      {
        "_index": ".ds-metrics-fleet_server.agent_status-default-2024.03.11-000001",
        "_id": "3JdPioUh-9j8DxQrAAABjjclRhU",
        "_score": 1,
        "_source": {
          "fleet": {
            "agents": {
              "enrolled": 12,
              "healthy": 0,
              "inactive": 0,
              "offline": 11,
              "total": 13,
              "unenrolled": 1,
              "unhealthy": 1,
              "updating": 0,
              "upgrading_step": {
                "downloading": 0,
                "extracting": 0,
                "failed": 0,
                "replacing": 0,
                "requested": 0,
                "restarting": 0,
                "rollback": 0,
                "scheduled": 0,
                "watching": 0
              },
              "unhealthy_reason": {
                  "input": 1,
                  "output": 1
                }
            }
          }
        }
      },
```


### Checklist

- [x] [Unit or functional
tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html)
were updated or added to match the most common scenarios

Author: juliaElastic

x-pack/plugins/fleet/common/types/models/agent.ts

@@ -107,6 +107,13 @@ interface AgentBase {
   tags?: string[];
   components?: FleetServerAgentComponent[];
   agent?: FleetServerAgentMetadata;
+  unhealthy_reason?: UnhealthyReason[];
+}
+
+export enum UnhealthyReason {
+  INPUT = 'input',
+  OUTPUT = 'output',
+  OTHER = 'other',
 }
 
 export interface AgentMetrics {
@@ -336,6 +343,11 @@ export interface FleetServerAgent {
    * Outputs map
    */
   outputs?: OutputMap;
+
+  /**
+   * Unhealthy reason: input, output, other
+   */
+  unhealthy_reason?: UnhealthyReason[];
 }
 
 /**

x-pack/plugins/fleet/server/services/agents/helpers.ts

@@ -92,6 +92,7 @@ export function searchHitToAgent(
     // key-value pairs
     user_provided_metadata: hit._source?.user_provided_metadata!,
     local_metadata: hit._source?.local_metadata!,
+    unhealthy_reason: hit._source?.unhealthy_reason,
   };
 
   if (!hit.fields?.status?.length) {

x-pack/plugins/fleet/server/services/metrics/fetch_agent_metrics.test.ts

@@ -71,6 +71,22 @@ describe('fetchAgentMetrics', () => {
             },
           ],
         },
+        unhealthy_reason: {
+          buckets: [
+            {
+              key: 'input',
+              doc_count: 2,
+            },
+            {
+              key: 'output',
+              doc_count: 1,
+            },
+            {
+              key: 'other',
+              doc_count: 3,
+            },
+          ],
+        },
       },
     });
 
@@ -95,6 +111,11 @@ describe('fetchAgentMetrics', () => {
         scheduled: 0,
         watching: 0,
       },
+      unhealthy_reason: {
+        input: 2,
+        output: 1,
+        other: 3,
+      },
     });
   });
 });

x-pack/plugins/fleet/server/services/metrics/fetch_agent_metrics.ts

@@ -20,6 +20,7 @@ export interface AgentMetrics {
   agents: AgentUsage;
   agents_per_version: AgentPerVersion[];
   upgrading_step: UpgradingSteps;
+  unhealthy_reason: UnhealthyReason;
 }
 
 export interface UpgradingSteps {
@@ -34,6 +35,12 @@ export interface UpgradingSteps {
   failed: number;
 }
 
+export interface UnhealthyReason {
+  input: number;
+  output: number;
+  other: number;
+}
+
 export const fetchAgentMetrics = async (
   core: CoreSetup,
   abortController: AbortController
@@ -63,6 +70,7 @@ export const fetchAgentMetrics = async (
     agents: await getAgentUsage(soClient, esClient),
     agents_per_version: await getAgentsPerVersion(esClient, abortController),
     upgrading_step: await getUpgradingSteps(esClient, abortController),
+    unhealthy_reason: await getUnhealthyReason(esClient, abortController),
   };
   return usage;
 };
@@ -195,3 +203,53 @@ export const getUpgradingSteps = async (
     return upgradingSteps;
   }
 };
+
+export const getUnhealthyReason = async (
+  esClient: ElasticsearchClient,
+  abortController: AbortController
+): Promise<UnhealthyReason> => {
+  const unhealthyReason = {
+    input: 0,
+    output: 0,
+    other: 0,
+  };
+  try {
+    const response = await retryTransientEsErrors(() =>
+      esClient.search(
+        {
+          index: AGENTS_INDEX,
+          size: 0,
+          aggs: {
+            unhealthy_reason: {
+              terms: { field: 'unhealthy_reason' },
+            },
+          },
+        },
+        { signal: abortController.signal }
+      )
+    );
+    ((response?.aggregations?.unhealthy_reason as any)?.buckets ?? []).forEach((bucket: any) => {
+      switch (bucket.key) {
+        case 'input':
+          unhealthyReason.input = bucket.doc_count;
+          break;
+        case 'output':
+          unhealthyReason.output = bucket.doc_count;
+          break;
+        case 'other':
+          unhealthyReason.other = bucket.doc_count;
+          break;
+        default:
+          break;
+      }
+    });
+    return unhealthyReason;
+  } catch (error) {
+    if (error.statusCode === 404) {
+      appContextService.getLogger().debug('Index .fleet-agents does not exist yet.');
+    } else {
+      throw error;
+    }
+    return unhealthyReason;
+  }
+};

x-pack/plugins/fleet/server/services/metrics/fleet_metrics_task.test.ts

@@ -104,6 +104,11 @@ describe('fleet metrics task', () => {
             count: 2,
           },
         ],
+        unhealthy_reason: {
+          input: 2,
+          output: 1,
+          other: 3,
+        },
       });
     });
 
@@ -149,6 +154,11 @@ describe('fleet metrics task', () => {
                   scheduled: 1,
                   requested: 1,
                 },
+                unhealthy_reason: {
+                  input: 2,
+                  output: 1,
+                  other: 3,
+                },
               },
             },
           }),

x-pack/plugins/fleet/server/services/metrics/fleet_metrics_task.ts

@@ -20,7 +20,7 @@ import { appContextService } from '../app_context';
 import type { AgentMetrics } from './fetch_agent_metrics';
 
 export const TYPE = 'Fleet-Metrics-Task';
-export const VERSION = '1.0.0';
+export const VERSION = '1.1.0';
 const TITLE = 'Fleet Metrics Task';
 const TIMEOUT = '1m';
 const SCOPE = ['fleet'];
@@ -115,6 +115,7 @@ export class FleetMetricsTask {
             unhealthy: agents.unhealthy,
             inactive: agents.inactive,
             upgrading_step: agentMetrics.upgrading_step,
+            unhealthy_reason: agentMetrics.unhealthy_reason,
           },
         },
       };