benchmarks.yml

name: Performance Benchmarking

on:
  push:
    branches: [main]
  pull_request:
    branches: [main]
  workflow_dispatch:

permissions:
  contents: read

jobs:
  benchmark:
    name: Seeded Drift Research Benchmark
    runs-on: ubuntu-latest
    timeout-minutes: 10
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: "3.11"

      - name: Run deterministic benchmark
        run: |
          python benchmarks/run_benchmark.py \
            --iterations 20000 \
            --evaluation-samples 2000 \
            --output benchmark-results.json

      - name: Validate benchmark schema
        run: |
          python - <<'PY'
          import json
          from pathlib import Path

          result = json.loads(Path("benchmark-results.json").read_text())
          required = {"latency_us", "throughput_ops_s", "peak_tracemalloc_mib", "quality"}
          missing = required - result.keys()
          if missing:
              raise SystemExit(f"missing benchmark fields: {sorted(missing)}")
          if result["throughput_ops_s"] <= 0 or result["latency_us"]["p99"] <= 0:
              raise SystemExit("benchmark produced invalid performance metrics")
          if result["quality"]["f1"] < 0.95:
              raise SystemExit("synthetic drift regression: F1 below 0.95")
          PY

      - name: Upload raw benchmark evidence
        uses: actions/upload-artifact@v4
        with:
          name: sentinelai-benchmark-${{ github.sha }}
          path: benchmark-results.json
          if-no-files-found: error
          retention-days: 30