titan-iac/ci/Jenkinsfile.titan-iac

pipeline {
  agent {
    kubernetes {
      defaultContainer 'python'
      yaml """
apiVersion: v1
kind: Pod
spec:
  nodeSelector:
    hardware: rpi5
    kubernetes.io/arch: arm64
    node-role.kubernetes.io/worker: "true"
  containers:
    - name: python
      image: python:3.12-slim
      command:
        - cat
      tty: true
"""
    }
  }
  environment {
    PIP_DISABLE_PIP_VERSION_CHECK = '1'
    PYTHONUNBUFFERED = '1'
    SUITE_NAME = 'titan-iac'
    PUSHGATEWAY_URL = 'http://platform-quality-gateway.monitoring.svc.cluster.local:9091'
  }
  stages {
    stage('Checkout') {
      steps {
        checkout scm
      }
    }
    stage('Install deps') {
      steps {
        sh 'pip install --no-cache-dir -r ci/requirements.txt'
      }
    }
    stage('Glue tests') {
      steps {
        sh '''
          set -eu
          mkdir -p build
          pytest -q ci/tests/glue --junitxml=build/junit-glue.xml
        '''
      }
    }
    stage('Resolve Flux branch') {
      steps {
        script {
          env.FLUX_BRANCH = sh(
            returnStdout: true,
            script: "awk '/branch:/{print $2; exit}' clusters/atlas/flux-system/gotk-sync.yaml"
          ).trim()
          if (!env.FLUX_BRANCH) {
            error('Flux branch not found in gotk-sync.yaml')
          }
          echo "Flux branch: ${env.FLUX_BRANCH}"
        }
      }
    }
    stage('Promote') {
      when {
        expression {
          def branch = env.BRANCH_NAME ?: (env.GIT_BRANCH ?: '').replaceFirst('origin/', '')
          return env.FLUX_BRANCH && branch == env.FLUX_BRANCH
        }
      }
      steps {
        withCredentials([usernamePassword(credentialsId: 'gitea-pat', usernameVariable: 'GIT_USER', passwordVariable: 'GIT_TOKEN')]) {
          sh '''
            set +x
            git config user.email "jenkins@bstein.dev"
            git config user.name "jenkins"
            git remote set-url origin https://${GIT_USER}:${GIT_TOKEN}@scm.bstein.dev/bstein/titan-iac.git
            git push origin HEAD:${FLUX_BRANCH}
          '''
        }
      }
    }
  }
  post {
    always {
      script {
        env.QUALITY_STATUS = currentBuild.currentResult == 'SUCCESS' ? 'ok' : 'failed'
      }
      sh '''
        set -eu
        python - <<'PY'
import os
import urllib.request
import xml.etree.ElementTree as ET
from pathlib import Path

suite = os.getenv("SUITE_NAME", "titan-iac")
status = os.getenv("QUALITY_STATUS", "failed")
gateway = os.getenv("PUSHGATEWAY_URL", "http://platform-quality-gateway.monitoring.svc.cluster.local:9091").rstrip("/")
junit_path = Path("build/junit-glue.xml")

totals = {"tests": 0, "failures": 0, "errors": 0, "skipped": 0}
if junit_path.exists():
    root = ET.parse(junit_path).getroot()
    suites = [root] if root.tag == "testsuite" else list(root.findall("testsuite")) if root.tag == "testsuites" else []
    for node in suites:
        for key in totals:
            raw = node.attrib.get(key) or "0"
            try:
                totals[key] += int(float(raw))
            except ValueError:
                pass

passed = max(totals["tests"] - totals["failures"] - totals["errors"] - totals["skipped"], 0)

def read_metrics() -> str:
    try:
        with urllib.request.urlopen(f"{gateway}/metrics", timeout=10) as resp:
            return resp.read().decode("utf-8", errors="replace")
    except Exception:
        return ""

def read_counter(text: str, counter_status: str) -> float:
    for line in text.splitlines():
        if not line.startswith("platform_quality_gate_runs_total{"):
            continue
        if 'job="platform-quality-ci"' not in line:
            continue
        if f'suite="{suite}"' not in line:
            continue
        if f'status="{counter_status}"' not in line:
            continue
        parts = line.split()
        if len(parts) < 2:
            continue
        try:
            return float(parts[1])
        except ValueError:
            return 0.0
    return 0.0

metrics = read_metrics()
ok_count = read_counter(metrics, "ok")
failed_count = read_counter(metrics, "failed")
if status == "ok":
    ok_count += 1
else:
    failed_count += 1

payload = "\n".join(
    [
        "# TYPE platform_quality_gate_runs_total counter",
        f'platform_quality_gate_runs_total{{suite="{suite}",status="ok"}} {ok_count:.0f}',
        f'platform_quality_gate_runs_total{{suite="{suite}",status="failed"}} {failed_count:.0f}',
        "# TYPE titan_iac_quality_gate_tests_total gauge",
        f'titan_iac_quality_gate_tests_total{{suite="{suite}",result="passed"}} {passed}',
        f'titan_iac_quality_gate_tests_total{{suite="{suite}",result="failed"}} {totals["failures"]}',
        f'titan_iac_quality_gate_tests_total{{suite="{suite}",result="error"}} {totals["errors"]}',
        f'titan_iac_quality_gate_tests_total{{suite="{suite}",result="skipped"}} {totals["skipped"]}',
    ]
) + "\n"

req = urllib.request.Request(
    f"{gateway}/metrics/job/platform-quality-ci/suite/{suite}",
    data=payload.encode("utf-8"),
    method="POST",
    headers={"Content-Type": "text/plain"},
)
with urllib.request.urlopen(req, timeout=10) as resp:
    if resp.status >= 400:
        raise RuntimeError(f"push failed: {resp.status}")
PY
      '''
      archiveArtifacts artifacts: 'build/junit-glue.xml', allowEmptyArchive: true
    }
  }
}