open-standards/.github/workflows/wai-byte-equality.yml

name: wai cross-architecture byte-equality

# The `replicate` determinism contract, checked on real silicon. WAI claims its
# integer-exact decode paths (rANS entropy coder, integer fixed-point synthesis)
# produce BYTE-IDENTICAL output on every machine. This matrix proves it: every
# OS/arch leg of the matrix below decodes the same fixtures and asserts the same golden
# bytes — rANS streams produced by CompressAI's upstream encoder, and an
# int_synth output hash produced on the reference machine (macOS arm64). One
# diverging byte anywhere fails the suite.
#
# Coverage is still-image AND temporal, classical AND learned: the rANS coder,
# integer fixed-point synthesis, the JPEG-AI entropy stage, the inter-frame video
# decoder (`wai.video.int_motion`), and the neural-keyframe variant
# (`wai.video.int_hyper`) whose I-frame comes out of a learned conditional codec,
# and the MLIC++-topology codec (`wai.neural.int_mlicpp`), whose entropy network runs
# before every checkerboard pass and must give every platform the encoder's scale
# bucket for every element. The learned integer audio and Gaussian-splat attribute codecs
# (`wai.audio.int_codec`, `wai.splat.int_codec`) decode their committed WIA1 and WIS1
# payloads to their PCM and attribute digests. The binary payloads SPEC §5 pins (WIV1,
# WIH1, WIA1, WIS1) are parsed
# with the wire parser a sink runs and decoded to the same digests, and the staged-delivery
# residual layers (WIR1) of the staged corpus are applied stage by stage to pinned digests.
# Video is the strictest leg — inter-frame decode is a
# feedback loop, so one divergent half-pel rounding does not stay one byte, it
# predicts the next frame and compounds for the rest of the clip.
#
# The conformance crate (`wai/byte-exact-conformance`) #[path]-includes the
# pure-integer sources from wai-rs — no system codec libraries, no ONNX runtime
# — so every leg runs in about a minute.

# One run per branch at a time. A push supersedes the run before it.
#
# There is one `macos` runner and it is the dev Mac, so every macOS job in this
# repo queues on it. With no concurrency group, a session pushing four versions
# of a branch queued four complete sets of runs and every one of them had to
# drain: on 2026-10-05 a PR's 21 contexts settled none in 70 minutes behind a
# backlog of 25 runs, and the queue grew faster than it cleared. Only the newest
# commit's verdict is wanted, so the older runs are cancelled.
#
# Verified on this forge (Forgejo 16.0.5) in `ci-test` before being added here:
# the key parses, and a newer push moves an older run to `cancelled` even while
# it is still queued, which is the case that matters.
#
# `cancel-in-progress: true` also applies to `main`. That is deliberate and
# safe here: main advances by merge commits whose tree contains the commits
# before them, so the newer run covers the older one's changes.
concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

on:
  pull_request:
    paths:
      - 'wai/byte-exact-conformance/**'
      - 'wai/wai-rs/src/neural/int_synth.rs'
      - 'wai/wai-rs/src/neural/jpegai_mans.rs'
      # Every source the crate #[path]-includes must be able to fire this
      # workflow, or a change can break cross-arch equality and merge green.
      - 'wai/wai-rs/src/int_synth.rs'
      - 'wai/wai-rs/src/int_entropy.rs'
      - 'wai/wai-rs/src/jpegai_mans.rs'
      - 'wai/wai-rs/src/rans.rs'
      - 'wai/wai-rs/src/int_video.rs'
      - 'wai/wai-rs/src/int_transform.rs'
      - 'wai/wai-rs/src/int_hyper_synth.rs'
      - 'wai/wai-rs/src/int_mlicpp.rs'
      - 'wai/wai-rs/src/int_audio.rs'
      - 'wai/wai-rs/src/int_splat.rs'
      - 'wai/wai-rs/src/int_payload/wire.rs'
      - 'wai/wai-rs/src/staged/predict.rs'
      - 'wai/wai-rs/src/staged/wir1.rs'
      - 'wai/wai-rs/src/staged/wir1_arith.rs'
      - 'wai/staged-conformance/**'
      # The fast kernels int_synth, int_transform and int_hyper_synth dispatch to
      # by default: the goldens here decode through them.
      - 'wai/wai-rs/src/int_kernels.rs'
      # The integer operator set and the bridge to it: the goldens decode int_synth,
      # the audio and splat codecs, the conditional codec (WIH1, the WIV1 keyframe)
      # and the MLIC++-topology codec through their lowerings too.
      - 'wai/wai-rs/src/int_ops.rs'
      - 'wai/wai-ops/**'
      - 'wai/wai-rs/tests/vectors/int_video/**'
      - 'wai/wai-rs/tests/vectors/int_hyper/**'
      - 'wai/wai-rs/tests/vectors/int_mlicpp/**'
      - 'wai/wai-rs/tests/vectors/int_audio/**'
      - 'wai/wai-rs/tests/vectors/int_splat/**'
      - '.github/workflows/wai-byte-equality.yml'
  push:
    branches:
      - main
    paths:
      - 'wai/byte-exact-conformance/**'
      - 'wai/wai-rs/src/neural/int_synth.rs'
      - 'wai/wai-rs/src/neural/jpegai_mans.rs'
      # Every source the crate #[path]-includes must be able to fire this
      # workflow, or a change can break cross-arch equality and merge green.
      - 'wai/wai-rs/src/int_synth.rs'
      - 'wai/wai-rs/src/int_entropy.rs'
      - 'wai/wai-rs/src/jpegai_mans.rs'
      - 'wai/wai-rs/src/rans.rs'
      - 'wai/wai-rs/src/int_video.rs'
      - 'wai/wai-rs/src/int_transform.rs'
      - 'wai/wai-rs/src/int_hyper_synth.rs'
      - 'wai/wai-rs/src/int_mlicpp.rs'
      - 'wai/wai-rs/src/int_audio.rs'
      - 'wai/wai-rs/src/int_splat.rs'
      - 'wai/wai-rs/src/int_payload/wire.rs'
      - 'wai/wai-rs/src/staged/predict.rs'
      - 'wai/wai-rs/src/staged/wir1.rs'
      - 'wai/wai-rs/src/staged/wir1_arith.rs'
      - 'wai/staged-conformance/**'
      # The fast kernels int_synth, int_transform and int_hyper_synth dispatch to
      # by default: the goldens here decode through them.
      - 'wai/wai-rs/src/int_kernels.rs'
      # The integer operator set and the bridge to it: the goldens decode int_synth,
      # the audio and splat codecs, the conditional codec (WIH1, the WIV1 keyframe)
      # and the MLIC++-topology codec through their lowerings too.
      - 'wai/wai-rs/src/int_ops.rs'
      - 'wai/wai-ops/**'
      - 'wai/wai-rs/tests/vectors/int_video/**'
      - 'wai/wai-rs/tests/vectors/int_hyper/**'
      - 'wai/wai-rs/tests/vectors/int_mlicpp/**'
      - 'wai/wai-rs/tests/vectors/int_audio/**'
      - 'wai/wai-rs/tests/vectors/int_splat/**'
      - '.github/workflows/wai-byte-equality.yml'

jobs:
  # Does this pull request's own diff touch the paths below? This forge matches a
  # workflow's `paths:` against the push, so a merge of main into a branch fires the
  # workflow whatever the pull request changes; every job here waits on this answer.
  # A push to main, a schedule, or anything the script cannot determine answers
  # `true` (scripts/pr-touches-paths.py).
  relevant:
    name: does this change touch it
    runs-on: linux
    outputs:
      run: ${{ steps.gate.outputs.run }}
    steps:
      - uses: actions/checkout@v5
        with:
          fetch-depth: 0
      - id: gate
        run: |
          set -euo pipefail
          r=$(python3 scripts/pr-touches-paths.py .github/workflows/wai-byte-equality.yml \
                "${{ github.event.pull_request.base.sha }}" \
                "${{ github.event.pull_request.head.sha }}")
          echo "this change touches wai-byte-equality: $r"
          echo "run=$r" >> "$GITHUB_OUTPUT"

  byte-equality:
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    name: ${{ matrix.label }}
    runs-on: ${{ matrix.os }}
    strategy:
      fail-fast: false
      matrix:
        # Self-hosted fleet labels, not hosted images. macos-x86_64 is
        # dropped: no Intel-Mac runner exists in the fleet, and by the same
        # argument the cargo-classes matrix already makes, it adds no arch
        # coverage — x86_64 is held by linux-x86_64, arm64 by linux-aarch64
        # and the macos-arm64 reference.
        # Windows x86_64 leg removed 2026-09-30: runner offline. Restore by
        # re-adding `- { os: windows, label: windows-x86_64 }` here once the
        # runner is back online.
        # The two disk steps below are bash, and skip on Windows.
        include:
          - { os: linux,       label: linux-x86_64 }
          - { os: linux-arm64, label: linux-aarch64 }
          - { os: macos,       label: macos-arm64 (reference) }
    env:
      # The floor of the disk check below, in GiB. The leg writes under 1 GiB (a
      # shallow checkout of about 0.3 GiB plus its pack, and a release target under
      # 0.1 GiB, measured 2026-11-03), and a cold toolchain install about 1 GiB more
      # under HOME; the rest is room for the jobs that share the disk. Measured with the
      # step's own loop on 2026-11-04, every label had 50 GiB or more free under all
      # four directories, so the floor fails a leg only on a host within a few GiB of
      # full. The macOS runner's HOME and TMPDIR sit on its internal disk, which has
      # gone from 7 GiB free to 118 MiB within hours, and at that level its jobs failed
      # writing under HOME.
      DISK_FLOOR_GIB: '4'
    steps:
      # Infrastructure first, before the checkout writes anything. Main's run 17676
      # failed on both arm64 legs with "No space left on device", linux-aarch64 in
      # `git fetch` and macOS in the toolchain's temporary files: the hosts' disks were
      # full and no fixture was decoded, yet the matrix read as a byte-equality failure.
      # This step measures the free space under every directory the leg writes to (the
      # workspace, the runner's temporary directory, TMPDIR, and HOME, where the
      # toolchain lives), and writes and syncs 32 MiB once on each filesystem, which a
      # disk out of inodes or remounted read-only fails though df shows room. Below the
      # floor, or on a write refused for space, an I/O error or a read-only filesystem,
      # it fails, and its name and its error say infrastructure.
      #
      # On linux-aarch64 the four directories are on the runner VM's data disk, so df
      # reads the guest's free space, not the host volume's. The disk is an image file
      # on that volume, and on 2026-11-04 all but 0.7 of its 200 GiB were already
      # allocated there, so a full host volume could take back at most that much; the
      # write probe catches the rest.
      #
      # The forge still reports the leg's own status context as failed (`wai
      # cross-architecture byte-equality / <label>`), as for a divergence; the class is
      # in the failed step's name and its error. A job of its own per label would put it
      # in the context, but the `linux` label has two hosts, so that job could measure
      # another host's disk than the leg's.
      - name: "infrastructure: this runner's disk has room for the leg"
        id: disk
        if: matrix.os != 'windows'
        shell: bash
        run: |
          set -euo pipefail
          short=0; seen=""
          for d in "${GITHUB_WORKSPACE:-$PWD}" "${RUNNER_TEMP:-/tmp}" "${TMPDIR:-/tmp}" "$HOME"; do
            p=$d; while [ ! -e "$p" ]; do p=$(dirname "$p"); done
            set -- $(df -Pk "$p" | awk 'NR == 2 {print $4, $6}')
            echo "$d: $(($1 / 1048576)) GiB free on $2"
            if [ "$1" -lt $((DISK_FLOOR_GIB * 1048576)) ]; then
              echo "::error::infrastructure: ${{ matrix.label }}: $d is on $2, which has $(($1 / 1024)) MiB free, below the floor of $DISK_FLOOR_GIB GiB. The runner host's disk is full: no fixture was decoded, so this is not a byte-equality failure."
              short=1; continue
            fi
            case " $seen " in *" $2 "*) continue ;; esac
            seen="$seen $2"; f="$p/.wai-disk-probe.$$"
            if ! err=$(dd if=/dev/zero of="$f" bs=1048576 count=32 conv=fsync 2>&1); then
              case "$err" in
                *"No space left"*|*"Input/output error"*|*"Read-only file system"*|*"quota"*)
                  echo "::error::infrastructure: ${{ matrix.label }}: a 32 MiB write under $p, on $2, failed: $(printf '%s' "$err" | head -n 1). The runner host's disk cannot take the leg's writes: no fixture was decoded, so this is not a byte-equality failure."
                  short=1 ;;
                *) echo "::warning::a 32 MiB write under $p failed for another reason: $(printf '%s' "$err" | head -n 1)" ;;
              esac
            fi
            rm -f "$f"
          done
          exit $short

      - name: Checkout
        uses: actions/checkout@v4

      # unix: bootstrap rustup (docker image ships no Rust; macOS host has it but
      # launchd's PATH omits ~/.cargo/bin). Windows is a host executor with rustup
      # already present, and must use pwsh — its `bash` is the WSL stub.
      - name: Install Rust 1.99.1 (unix)
        if: matrix.os != 'windows'
        shell: bash
        run: |
          export PATH="$HOME/.cargo/bin:$PATH"
          command -v rustup >/dev/null 2>&1 || \
            curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --profile minimal --default-toolchain 1.99.1
          rustup toolchain install 1.99.1 --profile minimal
          rustup default 1.99.1
          echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
      - name: Install Rust 1.99.1 (Windows)
        if: matrix.os == 'windows'
        shell: pwsh
        run: |
          rustup toolchain install 1.99.1 --profile minimal
          rustup default 1.99.1

      - name: Decode fixtures, assert golden bytes
        working-directory: wai/byte-exact-conformance
        run: cargo test --release -- --nocapture

      # A disk can also fill while the leg runs, from the jobs that share it (three
      # conformance jobs at once filled the arm64 VM's data disk mid-link). When a step
      # after the check failed, the same measurement and write are made again: below the
      # floor, or on a write refused for space, the failure is named infrastructure; with
      # room, it stands as it is.
      - name: "infrastructure: was the disk full when the leg failed?"
        if: failure() && steps.disk.outcome == 'success'
        shell: bash
        run: |
          set -euo pipefail
          short=0; seen=""
          for d in "${GITHUB_WORKSPACE:-$PWD}" "${RUNNER_TEMP:-/tmp}" "${TMPDIR:-/tmp}" "$HOME"; do
            p=$d; while [ ! -e "$p" ]; do p=$(dirname "$p"); done
            set -- $(df -Pk "$p" | awk 'NR == 2 {print $4, $6}')
            echo "$d: $(($1 / 1048576)) GiB free on $2"
            if [ "$1" -lt $((DISK_FLOOR_GIB * 1048576)) ]; then
              echo "::error::infrastructure: ${{ matrix.label }}: $d is on $2, which has $(($1 / 1024)) MiB free, below the floor of $DISK_FLOOR_GIB GiB. The disk filled while the leg ran: read the failure above as the runner host's disk, not as a byte-equality failure."
              short=1; continue
            fi
            case " $seen " in *" $2 "*) continue ;; esac
            seen="$seen $2"; f="$p/.wai-disk-probe.$$"
            if ! err=$(dd if=/dev/zero of="$f" bs=1048576 count=32 conv=fsync 2>&1); then
              case "$err" in
                *"No space left"*|*"Input/output error"*|*"Read-only file system"*|*"quota"*)
                  echo "::error::infrastructure: ${{ matrix.label }}: a 32 MiB write under $p, on $2, failed: $(printf '%s' "$err" | head -n 1). The disk filled while the leg ran: read the failure above as the runner host's disk, not as a byte-equality failure."
                  short=1 ;;
                *) echo "::warning::a 32 MiB write under $p failed for another reason: $(printf '%s' "$err" | head -n 1)" ;;
              esac
            fi
            rm -f "$f"
          done
          [ "$short" = 1 ] || echo "Every disk this leg writes to has room: the failure above is not the disk."
          exit $short