tier2.yml

name: Tier 2 — M2 / ANE (self-hosted)

on:
  pull_request:
    # `labeled` fires when run-m2 is first added; `synchronize`/`reopened`
    # re-run on every subsequent push while the label is present, so the
    # result tracks the PR head instead of going stale. The `if` below keeps
    # the run gated on the run-m2 label for all pull_request events.
    types: [labeled, synchronize, reopened]
  schedule:
    # Nightly at 04:00 UTC (~05/06 in PL). Keeps the M2 path honest
    # without burning the runner on every PR.
    - cron: "0 4 * * *"
  workflow_dispatch:

jobs:
  m2:
    if: |
      github.event_name == 'schedule' ||
      github.event_name == 'workflow_dispatch' ||
      (github.event_name == 'pull_request' &&
       contains(github.event.pull_request.labels.*.name, 'run-m2'))
    # Self-hosted Apple Silicon runner. Prerequisites: COMFY_DIR pointing at
    # a runner-owned ComfyUI clone, plus a cached SD1.5 checkpoint.
    runs-on: [self-hosted, macOS, ARM64, coreml]
    timeout-minutes: 90
    steps:
      - uses: actions/checkout@v4

      # Hybrid ComfyUI strategy:
      #   - schedule (nightly)  -> latest origin/master + ComfyUI's own
      #     requirements.txt (constrained). Canary for upstream API breakage.
      #   - PR label / dispatch -> the requires-comfyui version tag + the frozen
      #     `comfy` uv group. Reproducible merge gate, immune to overnight drift.
      - name: Resolve ComfyUI ref + mode
        run: |
          if [ "$GITHUB_EVENT_NAME" = "schedule" ]; then
            echo "COMFY_MODE=latest" >> "$GITHUB_ENV"
            echo "COMFY_REF=master"  >> "$GITHUB_ENV"
          else
            # requires-comfyui is a semver constraint (e.g. ">=0.3.27"); pin the
            # gate to the matching ComfyUI release tag (vX.Y.Z).
            VERSION="$(sed -nE 's/^requires-comfyui *= *"[^0-9]*([0-9]+\.[0-9]+\.[0-9]+).*/\1/p' pyproject.toml)"
            if [ -z "$VERSION" ]; then echo "could not parse requires-comfyui from pyproject.toml"; exit 1; fi
            echo "COMFY_MODE=pinned"      >> "$GITHUB_ENV"
            echo "COMFY_REF=v$VERSION"    >> "$GITHUB_ENV"
          fi

      - name: Set up ComfyUI checkout
        # COMFY_DIR is exported by the self-hosted runner's .env and MUST be a
        # runner-owned ComfyUI clone (never your dev checkout — this step does
        # git reset --hard and rewrites custom_nodes). Cloned on first run.
        run: |
          set -euo pipefail
          if [ -z "${COMFY_DIR:-}" ]; then echo "COMFY_DIR unset"; exit 1; fi
          # Init-in-place rather than `git clone`: COMFY_DIR may already hold the
          # cached checkpoint (models/checkpoints) or converted .mlmodelc, and
          # `git clone` refuses a non-empty target. init + fetch + `checkout -f`
          # populates the ComfyUI tree while leaving untracked files (the
          # checkpoint, the cached models) untouched — so setup order is free.
          if [ ! -d "$COMFY_DIR/.git" ]; then
            echo "initialising ComfyUI repo in $COMFY_DIR"
            mkdir -p "$COMFY_DIR"
            git -C "$COMFY_DIR" init -q
          fi
          git -C "$COMFY_DIR" remote get-url origin >/dev/null 2>&1 \
            || git -C "$COMFY_DIR" remote add origin https://github.com/comfyanonymous/ComfyUI.git
          git -C "$COMFY_DIR" fetch --quiet origin
          if [ "$COMFY_MODE" = "latest" ]; then
            git -C "$COMFY_DIR" checkout -f -B master origin/master
          else
            git -C "$COMFY_DIR" checkout -f "$COMFY_REF"
          fi
          COMFY_SHA="$(git -C "$COMFY_DIR" rev-parse HEAD)"
          echo "COMFY_SHA=$COMFY_SHA" >> "$GITHUB_ENV"
          echo "Tier 2 mode=$COMFY_MODE, ComfyUI \`$COMFY_SHA\`" >> "$GITHUB_STEP_SUMMARY"

          # Point ComfyUI's custom-node loader at this checkout. Refresh the
          # symlink only; refuse to clobber a real directory (guards against a
          # COMFY_DIR that is accidentally a dev checkout).
          NODE_LINK="$COMFY_DIR/custom_nodes/ComfyUI-CoreMLSuite"
          if [ -e "$NODE_LINK" ] && [ ! -L "$NODE_LINK" ]; then
            echo "ERROR: $NODE_LINK is a real directory, not a symlink."
            echo "COMFY_DIR must be a runner-owned ComfyUI, not your dev checkout."
            exit 1
          fi
          mkdir -p "$COMFY_DIR/custom_nodes"
          ln -sfn "$GITHUB_WORKSPACE" "$NODE_LINK"

      - name: Install dependencies
        run: |
          set -euo pipefail
          if [ "$COMFY_MODE" = "latest" ]; then
            # Node deps (our coremltools-9 toolchain), then ComfyUI's own
            # requirements for the pulled SHA, capped by the toolchain ceiling.
            uv sync
            uv pip install -r "$COMFY_DIR/requirements.txt" \
              -c constraints/comfy-ceiling.txt
          else
            # Pinned gate: the frozen group mirrors the known-good pinned SHA.
            uv sync --group comfy
          fi

      - name: Start ComfyUI server (background)
        run: |
          cd "$COMFY_DIR"
          nohup "$GITHUB_WORKSPACE/.venv/bin/python" main.py --port 8188 --cpu-vae > /tmp/comfyui-ci.log 2>&1 &
          # Poll the HTTP endpoint for readiness — robust to startup-banner
          # wording / colored-log changes in a floating-latest ComfyUI.
          for _ in $(seq 1 90); do
            if curl -sf -o /dev/null http://127.0.0.1:8188/system_stats; then
              echo "comfy ready (ComfyUI ${COMFY_SHA:-unknown})"; exit 0
            fi
            sleep 2
          done
          echo "comfy failed to start"; tail -100 /tmp/comfyui-ci.log; exit 1

      - name: Purge cached Core ML UNets (force fresh conversion)
        # The converter skips when a model of the same name already exists. That
        # cache key is conversion *parameters* only, not the conversion code or
        # toolchain — so a stale model would let a conversion regression pass.
        # Clear it so every Tier 2 run exercises the full convert -> compile ->
        # sample path end to end.
        run: |
          rm -rf "$COMFY_DIR"/models/unet/*.mlpackage "$COMFY_DIR"/models/unet/*.mlmodelc || true

      - name: Run Tier 2 (m2 marker)
        # Drives the Core ML Converter node, which converts the UNet from the
        # checkpoint on every run (cache purged above).
        run: uv run --no-sync pytest -m m2 tests/ -v

      - name: Stop ComfyUI server
        if: always()
        run: pkill -f "main.py.*8188" || true