[CI] add flaky reports

Signed-off-by: sule <sule.sl@antgroup.com>

.github/workflows/flaky-report.yml

@@ -0,0 +1,77 @@
+name: Flaky Test Report
+
+on:
+  schedule:
+    # Run daily at midnight UTC
+    - cron: '0 0 * * *'
+  workflow_dispatch:
+    # Allow manual triggering
+    inputs:
+      num_artifacts:
+        description: 'Number of artifacts to fetch (default: 20)'
+        required: false
+        default: '20'
+        type: string
+      max_runs_to_check:
+        description: 'Maximum number of workflow runs to check (default: 50)'
+        required: false
+        default: '50'
+        type: string
+
+jobs:
+  generate-report:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      actions: read
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v3
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.10'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install requests
+
+    - name: Fetch artifacts
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        NUM_ARTIFACTS: ${{ github.event.inputs.num_artifacts || '20' }}
+        MAX_RUNS: ${{ github.event.inputs.max_runs_to_check || '50' }}
+      run: |
+        python ci/ray_ci/fetch_artifacts.py --num-artifacts $NUM_ARTIFACTS --max-runs $MAX_RUNS
+        echo "Artifacts fetched successfully"
+        ls -la artifacts/
+
+    - name: Generate flaky test report
+      run: |
+        python ci/ray_ci/flaky_report.py
+        echo "Report generated successfully"
+        ls -la flaky_report.html
+
+    - name: Upload report artifact
+      id: artifact-upload-step
+      uses: actions/upload-artifact@v4
+      with:
+        name: flaky-test-report
+        path: |
+          flaky_report.html
+        retention-days: 90
+
+    - name: Create Summary
+      run: |
+        echo "### 📊 Test Reports Available" >> $GITHUB_STEP_SUMMARY
+        echo "" >> $GITHUB_STEP_SUMMARY
+        echo "View detailed test results at:" >> $GITHUB_STEP_SUMMARY
+        echo "🔗 [Ant Ray Dashboard](https://ant-ray.streamlit.app?run_id=${{ github.run_id }}&artifact_id=${{ steps.artifact-upload-step.outputs.artifact-id }})" >> $GITHUB_STEP_SUMMARY
+        echo "" >> $GITHUB_STEP_SUMMARY
+        echo "This link contains test reports and analysis for commit \`${{ github.sha }}\`" >> $GITHUB_STEP_SUMMARY
+        echo "" >> $GITHUB_STEP_SUMMARY
+        echo "### 📈 Report Preview" >> $GITHUB_STEP_SUMMARY
+        echo "Download the [Flaky Test Report](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }})" >> $GITHUB_STEP_SUMMARY 

.github/workflows/ray-ci.yml

@@ -227,6 +227,7 @@ jobs:
         else
           echo "exists=false" >> $GITHUB_OUTPUT
         fi
+
     - name: Build core CI Base
       if: steps.check_core_image.outputs.exists != 'true'
       uses: docker/build-push-action@v3
@@ -250,6 +251,7 @@ jobs:
         elif ! docker ps --format '{{.Names}}' | grep -q '^local-registry$'; then
           docker start local-registry
         fi
+
     - name: Push core build image to local registry
       if: '!cancelled()'
       run: |
@@ -272,6 +274,7 @@ jobs:
       if: '!cancelled()'
       run: |
         bash ci/env/install-bazel.sh
+
     - name: Check Manylinux Image Existence
       id: check_manylinux_image
       run: |
@@ -280,6 +283,7 @@ jobs:
         else
           echo "exists=false" >> $GITHUB_OUTPUT
         fi
+
     - name: Build Manylinux Image
       if: steps.check_manylinux_image.outputs.exists != 'true'
       uses: docker/build-push-action@v3
@@ -292,6 +296,7 @@ jobs:
         build-args: |
           BUILDKITE_BAZEL_CACHE_URL
           HOSTTYPE=x86_64
+
     - name: Run Core Python Tests (1)
       if: '!cancelled()'
       env:
@@ -302,16 +307,19 @@ jobs:
           --workers 1 --worker-id 0 --parallelism-per-worker 12 \
           --except-tags debug_tests,asan_tests,post_wheel_build,ha_integration,mem_pressure,tmpfs,container,manual,use_all_core,multi_gpu,large_size_python_tests_shard_2 \
           --test-env=BAZEL_DIR=$(realpath ${{ env.BAZEL_DIR }}) \
+
     - name: Grant Permissions
       if: '!cancelled()'
       run: |
         sudo chmod -R 777 ${{ env.BAZEL_DIR }}
+
     - name: Generate Report For Label
       if: '!cancelled()'
       env:
         REPORT_LABEL: ${{ env.REPORT_LABEL_1 }}
       run: |
         python ci/ray_ci/report_gen.py
+
     - name: Run Core Python Tests (2)
       if: '!cancelled()'
       env:
@@ -324,16 +332,19 @@ jobs:
           --except-tags debug_tests,asan_tests,post_wheel_build,ha_integration,mem_pressure,tmpfs,container,manual,use_all_core,multi_gpu,large_size_python_tests_shard_2 \
           --test-env=BAZEL_DIR=$(realpath ${{ env.BAZEL_DIR }}) \
           --skip-ray-installation
+
     - name: Grant Permissions
       if: '!cancelled()'
       run: |
         sudo chmod -R 777 ${{ env.BAZEL_DIR }}
+
     - name: Generate Report For Label
       if: '!cancelled()'
       env:
         REPORT_LABEL: ${{ env.REPORT_LABEL_2 }}
       run: |
         python ci/ray_ci/report_gen.py
+
     - name: Run Core Python Tests (3)
       if: '!cancelled()'
       env:
@@ -345,16 +356,19 @@ jobs:
           --workers 1 --worker-id 0 --parallelism-per-worker 12 --skip-ray-installation \
           --only-tags use_all_core \
           --test-env=BAZEL_DIR=$(realpath ${{ env.BAZEL_DIR }})
+
     - name: Grant Permissions
       if: '!cancelled()'
       run: |
         sudo chmod -R 777 ${{ env.BAZEL_DIR }}
+
     - name: Generate Report For Label
       if: '!cancelled()'
       env:
         REPORT_LABEL: ${{ env.REPORT_LABEL_3 }}
       run: |
         python ci/ray_ci/report_gen.py
+
     - name: Update Test Image
       if: '!cancelled()'
       run: |
@@ -371,10 +385,12 @@ jobs:
         bazel run //ci/ray_ci:test_in_docker -- //:all //src/... core --build-type clang \
           --workers 1 --worker-id 0 --parallelism-per-worker 12 --skip-ray-installation \
           --test-env=BAZEL_DIR=$(realpath ${{ env.BAZEL_DIR }})
+
     - name: Grant Permissions
       if: '!cancelled()'
       run: |
         sudo chmod -R 777 ${{ env.BAZEL_DIR }}
+
     - name: Generate Report For Label
       if: '!cancelled()'
       env:
@@ -391,16 +407,19 @@ jobs:
         bazel run //ci/ray_ci:test_in_docker -- python/ray/dashboard/... core \
           --parallelism-per-worker 12 --skip-ray-installation \
           --test-env=BAZEL_DIR=$(realpath ${{ env.BAZEL_DIR }})
+
     - name: Grant Permissions
       if: '!cancelled()'
       run: |
         sudo chmod -R 777 ${{ env.BAZEL_DIR }}
+
     - name: Generate Report For Label
       if: '!cancelled()'
       env:
         REPORT_LABEL: ${{ env.REPORT_LABEL_5 }}
       run: |
         python ci/ray_ci/report_gen.py
+
     - name: Run Workflow Tests
       if: '!cancelled()'
       env:
@@ -424,12 +443,14 @@ jobs:
       if: '!cancelled()'
       run: |
         sudo chmod -R 777 ${{ env.BAZEL_DIR }}
+
     - name: Generate Report For Label
       if: '!cancelled()'
       env:
         REPORT_LABEL: ${{ env.REPORT_LABEL_6 }}
       run: |
         python ci/ray_ci/report_gen.py
+
     - name: Run Debug Tests
       if: '!cancelled()'
       env:
@@ -444,16 +465,19 @@ jobs:
           --except-tags kubernetes,manual \
           --test-env=BAZEL_DIR=$(realpath ${{ env.BAZEL_DIR }}) \
           --skip-ray-installation
+
     - name: Grant Permissions
       if: '!cancelled()'
       run: |
         sudo chmod -R 777 ${{ env.BAZEL_DIR }}
+
     - name: Generate Report For Label
       if: '!cancelled()'
       env:
         REPORT_LABEL: ${{ env.REPORT_LABEL_7 }}
       run: |
         python ci/ray_ci/report_gen.py
+
     - name: Run ASAN Tests
       if: '!cancelled()'
       env:
@@ -468,6 +492,7 @@ jobs:
           --except-tags kubernetes,manual \
           --skip-ray-installation \
           --test-env=BAZEL_DIR=$(realpath ${{ env.BAZEL_DIR }})
+
     - name: Grant Permissions
       if: '!cancelled()'
       run: |
@@ -494,6 +519,7 @@ jobs:
         docker ps -a --filter ancestor=localhost:5000/citemp:${{ env.RAYCI_BUILD_ID }}-corebuild -q | xargs -r docker rm --force || true
         # Clean up any dangling containers
         docker ps -a --filter status=exited -q | xargs -r docker rm || true
+
     - name: Upload Test Reports
       id: artifact-upload-step
       continue-on-error: true
@@ -502,6 +528,7 @@ jobs:
       with:
         name: test-reports-${{ github.sha }}
         path: ${{ env.artifacts_path }}/reports/
+        retention-days: 90
 
     - name: Create Summary
       if: '!cancelled()'