Merge branch 'main' into fix/flaky-286496-trusted-apps-hash-sync-input-cf20b8f5c047e232

Author: gergoabraham

…ions/kibana-scout-report-flaky-tests.yml …efinitions/kibana-report-flaky-tests.yml.buildkite/pipeline-resource-definitions/kibana-scout-report-flaky-tests.yml renamed to .buildkite/pipeline-resource-definitions/kibana-report-flaky-tests.yml .buildkite/pipeline-resource-definitions/kibana-scout-report-flaky-tests.yml renamed to .buildkite/pipeline-resource-definitions/kibana-report-flaky-tests.yml

@@ -2,10 +2,10 @@
 apiVersion: backstage.io/v1alpha1
 kind: Resource
 metadata:
-  name: bk-kibana-scout-report-flaky-tests
-  description: Aggregates test events from the AppEx QA cluster into a flaky test report and publishes it as a build artifact
+  name: bk-kibana-report-flaky-tests
+  description: Aggregates test events from the AppEx QA cluster into a flaky test report, publishes it as a build artifact and checks which flaky suites already have a GitHub issue
   links:
-    - url: 'https://buildkite.com/elastic/kibana-scout-report-flaky-tests'
+    - url: 'https://buildkite.com/elastic/kibana-report-flaky-tests'
       title: Pipeline link
 spec:
   type: buildkite-pipeline
@@ -15,27 +15,30 @@ spec:
     apiVersion: buildkite.elastic.dev/v1
     kind: Pipeline
     metadata:
-      name: kibana / scout / report-flaky-tests
-      description: Aggregates test events from the AppEx QA cluster into a flaky test report and publishes it as a build artifact
+      name: kibana / report-flaky-tests
+      description: Aggregates test events from the AppEx QA cluster into a flaky test report, publishes it as a build artifact and checks which flaky suites already have a GitHub issue
     spec:
       env:
         # Set a channel and flip to 'true' once the report has an owning channel
         KIBANA_SLACK_NOTIFICATIONS_ENABLED: 'false'
-        # Inputs of .buildkite/scripts/steps/scout_report_flaky_tests.sh. Schedules may override
+        # Inputs of .buildkite/scripts/steps/report_flaky_tests.sh. Schedules may override
         # them to produce different reports (other pipelines, consistently failing tests, ...).
         FLAKY_TESTS_PIPELINES: 'kibana-on-merge'
         FLAKY_TESTS_LOOKBACK_DAYS: '7'
         FLAKY_TESTS_CLASSIFICATIONS: 'flaky'
+        # Repository whose failed-test issues .buildkite/scripts/steps/check_flaky_test_issues.sh
+        # checks for the flaky suites; read-only
+        FLAKY_TESTS_GITHUB_REPO: 'elastic/kibana'
       allow_rebuilds: true
       branch_configuration: main
       cancel_intermediate_builds: true
       default_branch: main
       repository: elastic/kibana
-      pipeline_file: .buildkite/pipelines/scout_report_flaky_tests.yml
+      pipeline_file: .buildkite/pipelines/report_flaky_tests.yml
       initial_step_plugins:
         - sparse-checkout#v1.6.0:
             paths:
-              - .buildkite/pipelines/scout_report_flaky_tests.yml
+              - .buildkite/pipelines/report_flaky_tests.yml
             cleanup_sparse_state: true
       provider_settings:
         build_branches: false

.buildkite/pipeline-resource-definitions/locations.yml

@@ -48,7 +48,7 @@ spec:
     - https://github.com/elastic/kibana/blob/main/.buildkite/pipeline-resource-definitions/kibana-pr.yml
     - https://github.com/elastic/kibana/blob/main/.buildkite/pipeline-resource-definitions/kibana-purge-cloud-deployments.yml
     - https://github.com/elastic/kibana/blob/main/.buildkite/pipeline-resource-definitions/kibana-renovate-helper.yml
-    - https://github.com/elastic/kibana/blob/main/.buildkite/pipeline-resource-definitions/kibana-scout-report-flaky-tests.yml
+    - https://github.com/elastic/kibana/blob/main/.buildkite/pipeline-resource-definitions/kibana-report-flaky-tests.yml
     - https://github.com/elastic/kibana/blob/main/.buildkite/pipeline-resource-definitions/kibana-scout-update-metadata.yml
     - https://github.com/elastic/kibana/blob/main/.buildkite/pipeline-resource-definitions/kibana-security-solution-on-merge.yml
     - https://github.com/elastic/kibana/blob/main/.buildkite/pipeline-resource-definitions/kibana-serverless-emergency-release.yml

.buildkite/pipelines/fleet/notify_smoke_tests.yml

@@ -4,7 +4,7 @@ notify:
 
 steps:
   - label: ':smoke: Check fleet-smoke-tests for consecutive failures'
-    command: ts-node .buildkite/scripts/pipelines/fleet_smoke_tests/notify_fleet_smoke_tests.ts
+    command: node .buildkite/scripts/pipelines/fleet_smoke_tests/notify_fleet_smoke_tests.ts
     env:
       DRY_RUN: ${DRY_RUN:-false}
     agents:

.buildkite/pipelines/gen_ai_product_docs.yml

@@ -40,13 +40,17 @@ steps:
       FTR_CONFIG_GROUP_KEY: 'ftr-ai-infra-gen-ai-inference-api'
       FTR_GEN_AI: '1'
       FTR_EIS_CCM: '1'
+      # Keep ES/Kibana server logs on disk so mocha log capture does not OOM on ML-heavy suites
+      FTR_EXTRA_ARGS: '--writeLogsToPath=data/ftr_servers_logs'
     timeout_in_minutes: 180
     parallelism: 1
     agents:
       image: family/kibana-ubuntu-2404
       imageProject: elastic-images-prod
       provider: gcp
       machineType: n2-standard-4
+      # ES|QL enrichment + multi-product semantic indices need more than the default boot disk
+      diskSizeGb: 180
       preemptible: true
     retry:
       automatic:

.buildkite/pipelines/gen_ai_security_labs.yml

@@ -39,6 +39,8 @@ steps:
       FTR_CONFIG_GROUP_KEY: 'ftr-ai-infra-gen-ai-security-labs'
       FTR_GEN_AI: '1'
       FTR_EIS_CCM: '1'
+      # Keep ES/Kibana server logs on disk so mocha log capture does not OOM on ML-heavy suites
+      FTR_EXTRA_ARGS: '--writeLogsToPath=data/ftr_servers_logs'
     timeout_in_minutes: 120
     parallelism: 1
     agents:

.buildkite/pipelines/gen_ai_testing.yml

@@ -30,6 +30,8 @@ steps:
       FTR_CONFIG: 'x-pack/platform/test/functional_gen_ai/inference/config.ts'
       FTR_CONFIG_GROUP_KEY: 'ftr-ai-infra-gen-ai-inference-api'
       FTR_GEN_AI: '1'
+      # Keep ES/Kibana server logs on disk so mocha log capture does not OOM on ML-heavy suites
+      FTR_EXTRA_ARGS: '--writeLogsToPath=data/ftr_servers_logs'
       FTR_EIS_CCM: '1'
     label: AppEx AI-Infra Inference APIs FTR tests
     key: ai-infra-gen-ai-inference-api
@@ -40,6 +42,8 @@ steps:
       imageProject: elastic-images-prod
       provider: gcp
       machineType: n2-standard-4
+      # Product-doc installs (ELSER/E5) are disk-heavy; avoid ES flood-stage / merge stalls
+      diskSizeGb: 130
       preemptible: true
     artifact_paths:
       - 'target/llm_smoke_judgements.jsonl'

.buildkite/pipelines/pull_request/ai_infra_gen_ai.yml

@@ -11,13 +11,17 @@ steps:
           FTR_CONFIG: 'x-pack/platform/test/functional_gen_ai/inference/config.ts'
           FTR_CONFIG_GROUP_KEY: 'ftr-ai-infra-gen-ai-inference-api'
           FTR_GEN_AI: '1'
+          # Keep ES/Kibana server logs on disk so mocha log capture does not OOM on ML-heavy suites
+          FTR_EXTRA_ARGS: '--writeLogsToPath=data/ftr_servers_logs'
           FTR_EIS_CCM: '1'
         label: AppEx AI-Infra Inference APIs FTR tests
         key: ai-infra-gen-ai-inference-api
         timeout_in_minutes: 50
         parallelism: 1
         agents:
           machineType: n2-standard-4
+          # Product-doc installs (ELSER/E5) are disk-heavy; avoid ES flood-stage / merge stalls
+          diskSizeGb: 130
           preemptible: true
           spotZones: us-central1-f,us-central1-c,us-central1-a
         artifact_paths:

.buildkite/pipelines/report_flaky_tests.yml

@@ -0,0 +1,33 @@
+steps:
+  - command: .buildkite/scripts/steps/report_flaky_tests.sh
+    label: ':mag: Discover flaky tests'
+    key: discover-flaky-tests
+    timeout_in_minutes: 30
+    agents:
+      image: family/kibana-ubuntu-2404
+      imageProject: elastic-images-prod
+      provider: gcp
+      machineType: n2-standard-4
+      preemptible: true
+      spotZones: us-central1-f,us-central1-c,us-central1-a
+    retry:
+      automatic:
+        - exit_status: '-1'
+          limit: 3
+
+  - command: .buildkite/scripts/steps/check_flaky_test_issues.sh
+    label: ':github: Check GitHub issues of flaky suites'
+    key: check-flaky-test-issues
+    depends_on: discover-flaky-tests
+    timeout_in_minutes: 30
+    agents:
+      image: family/kibana-ubuntu-2404
+      imageProject: elastic-images-prod
+      provider: gcp
+      machineType: n2-standard-4
+      preemptible: true
+      spotZones: us-central1-f,us-central1-c,us-central1-a
+    retry:
+      automatic:
+        - exit_status: '-1'
+          limit: 3

.buildkite/pipelines/scout_report_flaky_tests.yml

@@ -14,6 +14,7 @@ import { execSync } from 'child_process';
 import fs from 'fs';
 import os from 'os';
 import path from 'path';
+import { fileURLToPath } from 'url';
 
 import { BuildkiteClient } from '#pipeline-utils';
 
@@ -126,7 +127,7 @@ async function main() {
   sendSlackNotification(message);
 }
 
-if (require.main === module) {
+if (process.argv[1] === fileURLToPath(import.meta.url)) {
   main().catch((error) => {
     console.error(error);
     process.exit(1);