Move benchmarks from GH Actions to ADO; remove cb job from GH workflow

Author: RyAuld

.github/workflows/python-package.yml

@@ -5,91 +5,9 @@ name: CI/CD
 
 on:
   push:
-  pull_request:
-    branches: [ dev ]
-
-    # This guards against unknown PR until a community member vet it and label it.
-    types: [ labeled ]
 
 jobs:
-  ci:
-    env:
-      # Fake a TRAVIS env so that the pre-existing test cases would behave like before
-      TRAVIS: true
-      LAB_APP_CLIENT_ID: ${{ secrets.LAB_APP_CLIENT_ID }}
-      LAB_APP_CLIENT_CERT_BASE64: ${{ secrets.LAB_APP_CLIENT_CERT_BASE64 }}
-      LAB_APP_CLIENT_CERT_PFX_PATH: lab_cert.pfx
-
-    # Derived from https://docs.github.com/en/actions/guides/building-and-testing-python#starting-with-the-python-workflow-template
-    runs-on: ubuntu-22.04
-    strategy:
-      matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12', '3.13', '3.14']
-
-    steps:
-    - uses: actions/checkout@v4
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v5
-      # It automatically takes care of pip cache, according to
-      # https://docs.github.com/en/actions/using-workflows/caching-dependencies-to-speed-up-workflows#about-caching-workflow-dependencies
-      with:
-        python-version: ${{ matrix.python-version }}
-        cache: 'pip'
-
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        python -m pip install flake8 pytest
-        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-    - name: Populate lab cert.pfx
-      # https://docs.github.com/en/actions/security-guides/using-secrets-in-github-actions#storing-base64-binary-blobs-as-secrets
-      run: echo $LAB_APP_CLIENT_CERT_BASE64 | base64 -d > $LAB_APP_CLIENT_CERT_PFX_PATH
-    - name: Test with pytest
-      run: pytest --benchmark-skip
-    - name: Lint with flake8
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        #flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-        #flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-
-  cb:
-    # Benchmark only after the correctness has been tested by CI,
-    # and then run benchmark only once (sampling with only one Python version).
-    needs: ci
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-    steps:
-    - uses: actions/checkout@v4
-    - name: Set up Python 3.9
-      uses: actions/setup-python@v5
-      with:
-        python-version: 3.9
-        cache: 'pip'
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-    - name: Setup an updatable cache for Performance Baselines
-      uses: actions/cache@v4
-      with:
-        path: .perf.baseline
-        key: ${{ runner.os }}-performance-${{ hashFiles('tests/test_benchmark.py') }}
-        restore-keys: ${{ runner.os }}-performance-
-    - name: Run benchmark
-      run: pytest --benchmark-only --benchmark-json benchmark.json --log-cli-level INFO tests/test_benchmark.py
-    - name: Render benchmark result
-      uses: benchmark-action/github-action-benchmark@v1
-      with:
-        tool: 'pytest'
-        output-file-path: benchmark.json
-        fail-on-alert: true
-    - name: Publish Gibhub Pages
-      run: git push origin gh-pages
-
   cd:
-    needs: ci
     # Note: github.event.pull_request.draft == false WON'T WORK in "if" statement,
     # because the triggered event is a push, not a pull_request.
     # This means each commit will trigger a release on TestPyPI.

azure-pipelines.yml

@@ -24,3 +24,46 @@ stages:
 - template: .Pipelines/template-pipeline-stages.yml
   parameters:
     runPublish: false
+
+- stage: Benchmark
+  displayName: 'Run benchmarks'
+  dependsOn: CI
+  # Only run on post-merge pushes to dev — not on PRs or scheduled runs.
+  # Benchmarks are noisy and the baseline cache is only meaningful on a stable branch.
+  condition: |
+    and(
+      succeeded('CI'),
+      eq(variables['Build.Reason'], 'IndividualCI')
+    )
+  jobs:
+  - job: Benchmark
+    displayName: 'Performance benchmarks (Python 3.9)'
+    pool:
+      vmImage: ubuntu-latest
+    steps:
+    - task: UsePythonVersion@0
+      inputs:
+        versionSpec: '3.9'
+      displayName: 'Set up Python 3.9'
+
+    - script: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+      displayName: 'Install dependencies'
+
+    - task: Cache@2
+      displayName: 'Restore performance baseline cache'
+      inputs:
+        key: '"perf-baseline" | "$(Agent.OS)" | tests/test_benchmark.py'
+        path: .perf.baseline
+
+    - bash: |
+        pytest --benchmark-only --benchmark-json benchmark.json --log-cli-level INFO tests/test_benchmark.py
+      displayName: 'Run benchmarks'
+
+    - task: PublishBuildArtifacts@1
+      displayName: 'Publish benchmark results'
+      condition: succeededOrFailed()
+      inputs:
+        PathtoPublish: 'benchmark.json'
+        ArtifactName: 'benchmark-results'