fusion/.github/workflows/full-suite.yml

name: Full Suite (non-blocking)

# The demoted test tier (docs/plans/2026-06-04-001-refactor-fast-trusted-test-gate-plan.md).
# Runs the full sharded suite, the engine slow tier, and the dashboard
# inventory guard on every push to main — post-merge signal only. These jobs
# are NON-BLOCKING by design: they never run on PRs and must never be added
# to branch-protection required checks. A red run here is information, not a
# merge stopper; see docs/testing.md for the quarantine ratchet that keeps
# this tier honest.

on:
  push:
    branches: [main]

# Key the concurrency group by SHA, not ref: on push to main the ref is
# always refs/heads/main, so a ref-keyed group with cancel-in-progress would
# let consecutive merges cancel each other's runs — silently skipping the
# only coverage for everything the gate dropped. Per-SHA groups never collide.
concurrency:
  group: full-suite-${{ github.sha }}
  cancel-in-progress: false

# Least-privilege token: jobs only read the repo (checkout + cache) and upload
# workflow artifacts (timings), which needs no extra permission scope.
permissions:
  contents: read

# FN-4863: Opt JavaScript actions into Node 24 ahead of GitHub's forced cutover on 2026-06-02.
env:
  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"

jobs:
  test-shards:
    name: Test shard ${{ matrix.shard }}/4
    runs-on: ubuntu-latest
    # FNXC:FixPgTestsAndCi 2026-06-26-09:10:
    # Provision a PostgreSQL service container so the postgres/*.pg.test.ts
    # suites run in the non-blocking full suite too (parity with the gate).
    # The pg-test-harness probe skips gracefully if unreachable.
    services:
      postgres:
        image: postgres:15
        env:
          POSTGRES_USER: postgres
          POSTGRES_PASSWORD: postgres
          POSTGRES_DB: postgres
        ports:
          - 5432:5432
        options: >-
          --health-cmd "pg_isready -h localhost -p 5432 -U postgres"
          --health-interval 5s
          --health-timeout 5s
          --health-retries 10
    env:
      FUSION_PG_TEST_URL_BASE: "postgresql://postgres:postgres@localhost:5432"
      PGPASSWORD: "postgres"
    # Backstop for a wedged shard. The per-invocation watchdog (L2,
    # scripts/lib/run-vitest-watchdog.mjs) kills any single hung invocation at
    # its budget ceiling (<=30min), so this job budget only fires if L2 itself
    # wedges — and it must sit strictly above that ceiling so L2 fires first.
    # Without this, a hang ran to GitHub's 6h default (the silent-black-hole bug
    # this plan closes).
    timeout-minutes: 60
    strategy:
      fail-fast: false
      matrix:
        shard: [1, 2, 3, 4]

    steps:
      - name: Checkout
        uses: actions/checkout@v4
        with:
          # Engine tests run real git operations (merge-base against main,
          # case-variant ref checks) that require full history. Shallow
          # clones silently break tests like worktree-acquisition's resume
          # misbinding path.
          fetch-depth: 0

      - name: Setup Node.js and pnpm
        uses: ./.github/actions/setup-node-pnpm

      # Dist-artifact cache (L1): ensureTestArtifacts otherwise rebuilds dist/
      # for 8 packages (~71s) on every shard because CI starts with no dist.
      # Key on a stable, pre-build, git-based hash of ALL build packages' source
      # inputs. Exact-match only — NO restore-keys: a partial/stale dist hit is
      # the exact failure mode this repo has been bitten by (FN-4232/FN-4605),
      # and ensureTestArtifacts still validates/rebuilds anything missing-or-stale
      # after restore, so a miss is safe but a wrong-content hit would not be.
      # NEVER add node_modules here (breaks Windows pnpm junctions elsewhere).
      - name: Compute dist source hash
        id: dist-hash
        run: echo "hash=$(node scripts/ensure-test-artifacts.mjs --print-source-hash)" >> "$GITHUB_OUTPUT"

      - name: Cache built dist artifacts
        id: dist-cache
        uses: actions/cache@v6
        with:
          path: |
            packages/core/dist
            packages/dashboard/dist
            packages/engine/dist
            packages/plugin-sdk/dist
            plugins/fusion-plugin-dependency-graph/dist
            plugins/fusion-plugin-hermes-runtime/dist
            plugins/fusion-plugin-openclaw-runtime/dist
            plugins/fusion-plugin-paperclip-runtime/dist
          key: dist-${{ runner.os }}-${{ steps.dist-hash.outputs.hash }}

      # On a cache HIT, restored dist files carry their save-time mtimes while
      # checkout rewrites src mtimes to "now" (src newer than dist), which would
      # make ensureTestArtifacts' mtime fallback rebuild everything and defeat
      # the cache. Seed the per-package content-hash cache so its content-hash
      # short-circuit fires instead. ensureTestArtifacts still runs (inside
      # test:ci:shard) and rebuilds anything genuinely missing/changed.
      - name: Seed artifact hash-cache on cache hit
        if: steps.dist-cache.outputs.cache-hit == 'true'
        run: node scripts/ensure-test-artifacts.mjs --seed-artifact-cache

      - name: Test (deterministic shard)
        run: pnpm test:ci:shard --shard ${{ matrix.shard }} --total 4

      # Each shard emits per-file vitest JSON timing reporter output under
      # .timings/. Upload as an artifact so the timing snapshot can be
      # refreshed locally/from the default branch via
      # `node scripts/ci-test-shard.mjs --write-timings`. We do NOT commit the
      # snapshot automatically — refresh is manual/scheduled only.
      - name: Upload per-shard test timings
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: test-timings-shard-${{ matrix.shard }}
          # Relative outputFile paths mean each package writes its own
          # <pkgDir>/.timings/ file — glob the whole tree, not just the root.
          path: |
            .timings/timings-*.json
            packages/*/.timings/timings-*.json
            plugins/*/.timings/timings-*.json
            plugins/examples/*/.timings/timings-*.json
          if-no-files-found: ignore
          # FNXC:TestInfrastructure 2026-07-24-01:05:
          # .timings/ is a dot-directory and upload-artifact@v4 excludes hidden
          # files by default, so this step silently uploaded NOTHING since it was
          # added ("No files were found") and the timing snapshot could never be
          # refreshed from CI. Hidden files must be included for the glob to match.
          include-hidden-files: true
          retention-days: 14

  # The dashboard quality gate used to enumerate its test files by hand, so any
  # unenumerated app/ or src/ test file ran in NO project. This guard fails when
  # a dashboard test file is neither executed by a quality project (curated +
  # backfill lanes) nor on the reviewed skip-list. Cheap: it only runs
  # `vitest list`, not the tests.
  test-inventory-guard:
    name: Dashboard curated-gate guard
    runs-on: ubuntu-latest
    # Runs only `vitest list` (no tests execute), so this is generous headroom,
    # not a tight bound — but no CI job should be able to hang to the 6h ceiling.
    timeout-minutes: 20
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Setup Node.js and pnpm
        uses: ./.github/actions/setup-node-pnpm

      # Same dist-artifact cache as test-shards (L1): the curated-gate guard runs
      # `vitest list`, whose config resolution can touch built dist, so it also
      # pays the cold-dist rebuild. Exact-match key on the pre-build source hash;
      # NO restore-keys (stale dist is the failure mode), NO node_modules.
      - name: Compute dist source hash
        id: dist-hash
        run: echo "hash=$(node scripts/ensure-test-artifacts.mjs --print-source-hash)" >> "$GITHUB_OUTPUT"

      - name: Cache built dist artifacts
        id: dist-cache
        uses: actions/cache@v6
        with:
          path: |
            packages/core/dist
            packages/dashboard/dist
            packages/engine/dist
            packages/plugin-sdk/dist
            plugins/fusion-plugin-dependency-graph/dist
            plugins/fusion-plugin-hermes-runtime/dist
            plugins/fusion-plugin-openclaw-runtime/dist
            plugins/fusion-plugin-paperclip-runtime/dist
          key: dist-${{ runner.os }}-${{ steps.dist-hash.outputs.hash }}

      - name: Seed artifact hash-cache on cache hit
        if: steps.dist-cache.outputs.cache-hit == 'true'
        run: node scripts/ensure-test-artifacts.mjs --seed-artifact-cache

      - name: Assert every dashboard test file is gated or skip-listed
        run: node scripts/check-test-inventory.mjs --dashboard-curated

  line-count-audit:
    name: Line-count audit
    runs-on: ubuntu-latest
    timeout-minutes: 10
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Setup Node.js and pnpm
        uses: ./.github/actions/setup-node-pnpm

      # FNXC:TestInfrastructure 2026-06-21-10:26:
      # Keep line-count drift visible in automated post-merge signal without restoring it to the blocking PR gate.
      # The guard is intentionally absent from pretest/pr-checks so task verification and merge progress are not blocked by file-size cleanup work.
      - name: Run line-count audit
        continue-on-error: true
        run: pnpm check:line-count

  # The engine-slow tier (src/**/*.slow.test.ts) runs here with a non-empty
  # execution assertion, so a glob/config drift that silently empties the tier
  # fails this workflow instead of passing vacuously. Engine slow tests do real
  # git operations, so a full clone (fetch-depth: 0) is required.
  test-slow:
    name: Engine slow tier
    runs-on: ubuntu-latest
    # FNXC:FixPgTestsAndCi 2026-07-14-00:00:
    # Provision a PostgreSQL service container so reliability-interaction test
    # helpers (which now require a PG-backed TaskStore after SQLite removal
    # VAL-REMOVAL-005) can run in the engine-slow tier too.
    services:
      postgres:
        image: postgres:15
        env:
          POSTGRES_USER: postgres
          POSTGRES_PASSWORD: postgres
          POSTGRES_DB: postgres
        ports:
          - 5432:5432
        options: >-
          --health-cmd "pg_isready -h localhost -p 5432 -U postgres"
          --health-interval 5s
          --health-timeout 5s
          --health-retries 10
    env:
      FUSION_PG_TEST_URL_BASE: "postgresql://postgres:postgres@localhost:5432"
      PGPASSWORD: "postgres"
    # Real-git slow suites; same backstop rationale as test-shards. Sits above
    # the L2 per-invocation ceiling so the watchdog fires first on a single hang.
    timeout-minutes: 60
    steps:
      - name: Checkout
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Setup Node.js and pnpm
        uses: ./.github/actions/setup-node-pnpm

      - name: Run engine-slow with non-empty-execution assertion
        run: node scripts/assert-engine-slow-nonempty.mjs

  # FNXC:CIGateSpeed 2026-07-22-23:30:
  # Warm the PR gate's incremental build cache from main. The Gate job in
  # pr-checks.yml restores `gate-dist-*` with restore-keys; caches saved on a
  # PR merge ref are invisible to other PRs, so without this job every PR's
  # FIRST gate run builds cold (~6-8 min). Saving main's built dist plus
  # .fusion/cache/plugin-build-cache.json here lets that first run rebuild only
  # the packages the PR actually changed. The path list MUST stay byte-identical
  # to the Gate job's cache block (actions/cache versions caches by path list —
  # a drifted list makes the caches mutually invisible). Fast CLI packaging
  # matches the Gate's consumer shape. This is a cache warmer, not a test or
  # verification step; the blocking Build job on PRs keeps full-build coverage.
  warm-gate-build-cache:
    name: Warm gate build cache
    runs-on: ubuntu-latest
    timeout-minutes: 20
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Setup Node.js and pnpm
        uses: ./.github/actions/setup-node-pnpm

      - name: Compute dist source hash
        id: dist-hash
        run: echo "hash=$(node scripts/ensure-test-artifacts.mjs --print-source-hash)" >> "$GITHUB_OUTPUT"

      - name: Cache built dist artifacts (incremental)
        id: dist-cache
        uses: actions/cache@v6
        with:
          path: |
            packages/core/dist
            packages/dashboard/dist
            packages/engine/dist
            packages/plugin-sdk/dist
            packages/cli/dist
            plugins/fusion-plugin-dependency-graph/dist
            plugins/fusion-plugin-hermes-runtime/dist
            plugins/fusion-plugin-openclaw-runtime/dist
            plugins/fusion-plugin-paperclip-runtime/dist
            .fusion/cache/plugin-build-cache.json
          key: gate-dist-${{ runner.os }}-${{ steps.dist-hash.outputs.hash }}
          restore-keys: |
            gate-dist-${{ runner.os }}-

      - name: Build (incremental against restored cache)
        run: pnpm build
        env:
          FUSION_CLI_FULL_PACKAGE: "0"

      # FNXC:CIGateSpeed 2026-07-23-00:05:
      # Also warm the Typecheck job's tsc incremental buildinfo cache from main
      # (same PR-invisibility rationale as the dist cache above). The path list
      # must stay byte-identical to the Typecheck job's cache block in
      # pr-checks.yml. Restored buildinfo is self-validating — tsc re-checks
      # anything that changed — so restore-keys is correctness-neutral.
      - name: Cache TypeScript incremental buildinfo
        uses: actions/cache@v6
        with:
          path: |
            packages/*/dist/.tsbuildinfo
            packages/dashboard/dist/.tsbuildinfo-app
            plugins/*/dist/.tsbuildinfo
          key: typecheck-tsbuildinfo-${{ runner.os }}-${{ github.sha }}
          restore-keys: |
            typecheck-tsbuildinfo-${{ runner.os }}-

      - name: Typecheck (warms incremental buildinfo)
        run: pnpm typecheck