benchmark.yml

# Benchmark CI with Statistical Analysis
# Runs benchmarks with reproducible seeds and reports confidence intervals

name: Benchmark

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

env:
  CARGO_TERM_COLOR: always
  PRESENTAR_BENCH_SEED: 12345
  CRITERION_DEBUG: 0

jobs:
  benchmark:
    runs-on: ubuntu-latest

    steps:
    - uses: actions/checkout@v4

    - name: Install Rust
      uses: dtolnay/rust-action@stable
      with:
        components: rustfmt, clippy

    - name: Cache cargo registry
      uses: actions/cache@v4
      with:
        path: |
          ~/.cargo/registry
          ~/.cargo/git
          target
        key: ${{ runner.os }}-cargo-bench-${{ hashFiles('**/Cargo.lock') }}

    - name: Run benchmarks
      run: |
        cargo criterion --message-format json > benchmark_results.json

    - name: Generate statistics report
      run: |
        echo "## Benchmark Results" >> $GITHUB_STEP_SUMMARY
        echo "" >> $GITHUB_STEP_SUMMARY
        echo "| Benchmark | Mean | 95% CI | Samples |" >> $GITHUB_STEP_SUMMARY
        echo "|-----------|------|--------|---------|" >> $GITHUB_STEP_SUMMARY

        # Parse Criterion JSON output
        jq -r '.[] | select(.reason == "benchmark-complete") |
          "| \(.id) | \(.mean.estimate | . / 1e6 | round)ms | [\(.mean.lower_bound | . / 1e6 | round)ms, \(.mean.upper_bound | . / 1e6 | round)ms] | \(.sample_count) |"' \
          benchmark_results.json >> $GITHUB_STEP_SUMMARY || echo "No benchmark data"

    - name: Check for regressions
      run: |
        # Compare against baseline if it exists
        if [ -f data/benchmarks/baselines/latest.json ]; then
          echo "Checking for performance regressions..."
          cargo criterion --baseline latest || true
        fi

    - name: Upload benchmark results
      uses: actions/upload-artifact@v4
      with:
        name: benchmark-results
        path: |
          benchmark_results.json
          target/criterion/