[9.4][ML] Harden dev-tools Python CI: pytest on bookworm, deps, narrow changelog unittest (#3052)

.buildkite/pipelines/format_and_validation.yml.sh

@@ -18,6 +18,15 @@ steps:
     notify:
       - github_commit_status:
           context: "Validate formatting with clang-format"
+  - label: "dev-tools pytest"
+    key: "dev_tools_pytest"
+    command: ".buildkite/scripts/steps/dev_tools_pytest.sh"
+    agents:
+      # bookworm (not slim): stable Python minor + curl/git for Buildkite hooks; avoids python:3 tag drift
+      image: "python:3.11-bookworm"
+    notify:
+      - github_commit_status:
+          context: "dev-tools pytest"
   - label: "Validate changelog entries"
     key: "validate_changelogs"
     command: ".buildkite/scripts/steps/validate-changelogs.sh"

.buildkite/scripts/steps/dev_tools_pytest.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+# Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+# or more contributor license agreements. Licensed under the Elastic License
+# 2.0 and the following additional limitation. Functionality enabled by the
+# files subject to the Elastic License 2.0 may only be used in production when
+# invoked by an Elasticsearch process with a license key installed that permits
+# use of machine learning features. You may not use this file except in
+# compliance with the Elastic License 2.0 and the foregoing additional
+# limitation.
+#
+# Installs dev-tools pytest deps once per job (PyPI), then runs run_dev_tools_tests.sh.
+# Keeping pip here isolates network/bootstrap from the test runner; baking deps into
+# the agent image would avoid live PyPI on every PR if desired.
+
+set -euo pipefail
+
+REPO_ROOT="${REPO_ROOT:-$(git rev-parse --show-toplevel)}"
+cd "${REPO_ROOT}"
+
+if ! python3 -m pip install -q -r "${REPO_ROOT}/dev-tools/test-requirements.txt"; then
+    echo "ERROR: pip install failed for dev-tools/test-requirements.txt (network or PyPI?)." >&2
+    echo "Install manually on this agent, then re-run:" >&2
+    echo "  python3 -m pip install -r ${REPO_ROOT}/dev-tools/test-requirements.txt" >&2
+    exit 1
+fi
+
+exec "${REPO_ROOT}/dev-tools/run_dev_tools_tests.sh" -q --tb=short

.buildkite/scripts/steps/test-changelog-tools.sh

@@ -18,4 +18,6 @@ python3 -m pip install --quiet --break-system-packages pyyaml jsonschema 2>/dev/
   || python3 -m pip install --quiet pyyaml jsonschema
 
 echo "Running Python unit tests for dev-tools changelog scripts..."
-python3 -m unittest discover -s dev-tools/unittest -p 'test_*.py' -v
+# Only test_changelog_tools.py: other modules under unittest/ may be pytest-only
+# (e.g. test_version_bump_validation) and are run by the dev-tools pytest step.
+python3 -m unittest discover -s dev-tools/unittest -p 'test_changelog_tools.py' -v

dev-tools/pytest.ini

@@ -0,0 +1,6 @@
+[pytest]
+testpaths = unittest
+pythonpath = .
+
+markers =
+    integration: requires git fetch from origin; opt-in via VERSION_BUMP_GIT_INTEGRATION=1 (see test file)

dev-tools/run_dev_tools_tests.sh

@@ -0,0 +1,41 @@
+#!/bin/bash
+#
+# Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+# or more contributor license agreements. Licensed under the Elastic License
+# 2.0 and the following additional limitation. Functionality enabled by the
+# files subject to the Elastic License 2.0 may only be used in production when
+# invoked by an Elasticsearch process with a license key installed that permits
+# use of machine learning features. You may not use this file except in
+# compliance with the Elastic License 2.0 and the foregoing additional
+# limitation.
+#
+# Runs dev-tools/unittest via pytest (see dev-tools/test-requirements.txt).
+# Does not install packages — pytest must already be importable (venv, image, or
+# a prior pip install). PR CI runs .buildkite/scripts/steps/dev_tools_pytest.sh,
+# which performs one pip install per job from dev-tools/test-requirements.txt
+# (PyPI); a future improvement is baking deps into the CI image to reduce that
+# dependency.
+#
+# Usage (from repository root):
+#   ./dev-tools/run_dev_tools_tests.sh
+#   ./dev-tools/run_dev_tools_tests.sh -q --tb=short
+
+set -euo pipefail
+
+ROOT="$(git rev-parse --show-toplevel 2>/dev/null)" || true
+if [[ -z "${ROOT}" ]]; then
+    echo "ERROR: not inside a git repository (git rev-parse --show-toplevel failed)." >&2
+    echo "Run this script from a checkout of ml-cpp." >&2
+    exit 1
+fi
+cd "${ROOT}/dev-tools"
+
+if ! python3 -m pytest --version >/dev/null 2>&1; then
+    echo "pytest is not installed in the current environment." >&2
+    echo "Install dev-tools test dependencies first, for example:" >&2
+    echo "  python3 -m pip install -r ${ROOT}/dev-tools/test-requirements.txt" >&2
+    echo "On Buildkite, .buildkite/scripts/steps/dev_tools_pytest.sh installs this before invoking this script." >&2
+    exit 1
+fi
+
+exec python3 -m pytest -c pytest.ini "$@"

dev-tools/test-requirements.txt

@@ -0,0 +1,5 @@
+# Python dependencies for dev-tools/unittest (pytest).
+pytest>=7.0.0,<9
+# Import-time deps for changelog scripts exercised by tests (bundle_changelogs, etc.).
+PyYAML>=6.0
+jsonschema>=4.0.0