max-sixty__worktrunk/.github/workflows/benchmarks.yaml

name: benchmarks
# Full criterion suite plus the time-series gist append. Runs ~80 min and
# checks performance, not correctness, so it stands apart from the PR/merge
# flow and from nightly's correctness checks: a slow or failing bench never
# gates a merge. The daily cron is the perf-history feed (it appends to the
# gist); workflow_dispatch covers on-demand runs against a chosen branch.
#
# Not run on PRs or pushes, so the daily run is the only signal that the bench
# harness still builds — create-issue-on-benchmark-failure surfaces a break.
#
# Runner version pinned; see ci.yaml header comment for rationale.

on:
  schedule:
    # 3:47 UTC daily. Off-peak, offset from nightly's 5:37 so the two long
    # runs don't contend, and off :00 to be a good citizen w.r.t. GitHub's
    # cron scheduler.
    - cron: '47 3 * * *'
  workflow_dispatch:

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: false

env:
  # Match ci.yaml/nightly.yaml: Swatinem/rust-cache hashes CARGO*/RUST* into
  # the cache key, so the shared `test` cache only restores when these agree
  # (see .github/CLAUDE.md).
  CARGO_TERM_COLOR: always
  CARGO_INCREMENTAL: 0
  RUSTFLAGS: -C debuginfo=0

jobs:
  benchmarks:
    runs-on: ubuntu-24.04
    steps:
    - name: 📂 Checkout code
      uses: actions/checkout@v7

    - name: 💰 Cache
      uses: Swatinem/rust-cache@v2
      with:
        # Restore the shared `test` cache (registry + deps), never save —
        # `cargo bench` is release-profile so it rebuilds its own artifacts,
        # but the dependency download/extract is still worth restoring.
        prefix-key: v1-rust
        shared-key: shared
        cache-bin: "false"
        save-if: false

    - name: Install shells and jq
      run: sudo apt-get update && sudo apt-get install -y zsh fish jq

    - name: Install nushell
      uses: hustcer/setup-nu@v3
      with:
        version: '0.114.1'

    - name: 💰 Imported fixture cache
      uses: actions/cache@v6
      with:
        # The fixture file pins the corpus revision. Including its hash keeps
        # a prior corpus out of the cache after either constant changes.
        path: target/wt-perf/bench-repos
        key: bench-repos-imported-${{ runner.os }}-${{ hashFiles('benches/imported-fixture') }}

    - name: 📊 Run benchmarks
      run: cargo bench

    - name: 📦 Upload benchmark results
      uses: actions/upload-artifact@v7
      with:
        name: benchmark-results-${{ github.run_id }}
        path: target/criterion

  # Time-series benchmark store, owned by worktrunk-bot:
  # https://gist.github.com/worktrunk-bot/19bb23cb9658722abfe69479d0a4f9bf
  #
  # Cron-only: workflow_dispatch runs aren't appended (would pollute the
  # time series). Skipped on forks: the environment's secrets aren't exposed
  # there.
  #
  # Its own job so the token stays off `benchmarks`. The copy this job reads
  # is in the `tend` environment, whose policy admits `main` alone, so a job
  # naming it is refused on every other ref — which would take
  # workflow_dispatch against a chosen branch with it. A job GitHub skips
  # never requests its environment, so the cron gate above keeps the gate off
  # the dispatch path.
  append-gist:
    needs: benchmarks
    if: github.repository_owner == 'max-sixty' && github.event_name == 'schedule'
    runs-on: ubuntu-24.04
    environment:
      name: tend
      # A secret scope, not a deploy target — see .github/CLAUDE.md.
      deployment: false
    permissions:
      contents: read
    steps:
    - name: 📦 Download benchmark results
      uses: actions/download-artifact@v8
      with:
        name: benchmark-results-${{ github.run_id }}
        path: target/criterion

    - name: 💾 Append results to gist
      env:
        GITHUB_TOKEN: ${{ secrets.TEND_BOT_TOKEN }}
        GIST_ID: 19bb23cb9658722abfe69479d0a4f9bf
      run: |
        set -euo pipefail
        timestamp="$(date -u +'%Y-%m-%dT%H:%M:%SZ')"
        find target/criterion -path '*/new/estimates.json' -print0 \
          | sort -z \
          | xargs -0 -r jq -c --arg ts "$timestamp" --arg sha "$GITHUB_SHA" '
              {
                ts: $ts,
                sha: $sha,
                bench: (
                  input_filename
                  | sub("^target/criterion/"; "")
                  | sub("/new/estimates\\.json$"; "")
                ),
                mean_ns: .mean.point_estimate,
                stddev_ns: .std_dev.point_estimate
              }
            ' > new-rows.jsonl
        test -s new-rows.jsonl
        git clone "https://x-access-token:${GITHUB_TOKEN}@gist.github.com/${GIST_ID}.git" /tmp/gist
        cat new-rows.jsonl >> /tmp/gist/results.jsonl
        git -C /tmp/gist \
          -c user.name=worktrunk-bot \
          -c user.email=worktrunk-bot@users.noreply.github.com \
          commit -am "benchmarks: ${GITHUB_SHA::7}"
        git -C /tmp/gist push

  create-issue-on-benchmark-failure:
    needs:
      - benchmarks
      - append-gist
    if: always() && contains(needs.*.result, 'failure') && github.repository_owner == 'max-sixty' && github.event_name == 'schedule'
    runs-on: ubuntu-24.04
    environment:
      name: tend
      # A secret scope, not a deploy target — see .github/CLAUDE.md.
      deployment: false
    permissions:
      contents: read
      issues: write
    steps:
    - name: 📂 Checkout code
      uses: actions/checkout@v7

    - uses: JasonEtco/create-an-issue@v2
      env:
        # Use TEND_BOT_TOKEN for a consistent bot identity (per
        # .github/CLAUDE.md) and so any future issue-triage automation can
        # cascade off issue creation — events from the default GITHUB_TOKEN
        # don't trigger other workflows.
        GITHUB_TOKEN: ${{ secrets.TEND_BOT_TOKEN }}
        LINK: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
      with:
        filename: .github/benchmark-failure.md
        update_existing: true
        search_existing: open