fusion/.github/workflows/pr-checks.yml

name: PR Checks

# The thin trusted merge gate (docs/plans/2026-06-04-001-refactor-fast-trusted-test-gate-plan.md).
# Blocking checks are exactly: Lint, Typecheck, Build, Gate.
#
# BRANCH-PROTECTION CUTOVER: required status checks are matched by job name.
# When this file changes job names, update the repo's branch-protection
# required checks to exactly [Lint, Typecheck, Build, Gate] — a stale required
# name (e.g. "Test shard 1/4") that no longer reports will block every PR
# with "Expected — waiting for status". Open PRs must rebase onto main after
# the cutover so they run this workflow shape.
#
# Everything that used to run here as shards / slow tier / inventory guard is
# non-blocking and lives in full-suite.yml (push to main).

on:
  pull_request:
    branches: [main]

concurrency:
  group: pr-checks-${{ github.ref }}
  cancel-in-progress: true

# Least-privilege token: every job here only reads the repo (checkout + cache).
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:
  lint:
    name: Lint
    runs-on: ubuntu-latest

    steps:
      - name: Checkout
        uses: actions/checkout@v7

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

      - name: Lint
        run: pnpm lint

      - name: Changeset format
        run: pnpm check:changesets

      - name: Dashboard route modularity
        run: pnpm check:routes-modular

      # The lifecycle-column ratchet was advisory until now: the census existed only as
      # `pnpm census:lifecycle-columns` (no --strict) and nothing ran it, so three PRs
      # lowered counts without re-recording and left allowances the deleted guards could
      # return through while this gate stayed green. ~2s over ~1950 files.
      - name: Lifecycle-column ratchet
        run: pnpm check:lifecycle-columns
      - name: SQL-column ratchet
        run: pnpm check:sql-column-literals
      - name: Move-target ratchet
        run: pnpm check:move-target-literals
      - name: Inert lane/flag seams
        run: pnpm check:inert-flag-seams
      - name: FNXC stamp dates
        run: pnpm check:fnxc-future-dates
      - name: Lane-wiring ratchet
        run: pnpm check:lane-wiring
      - name: Plugin interop declarations match the dashboard API
        run: pnpm check:plugin-interop-drift
      # AGENTS.md states the deletion ratchet as policy — "A quarantined test is DELETED after 14
      # days (quarantinedAt + 2 weeks) unless rescued" — and nothing enforced it. Same shape as the
      # lifecycle-column note above: the script supports `--strict`, the package script omitted it,
      # and no workflow ran it, so it could not fail however long an entry sat there. It fires 5 days
      # BEFORE the deadline so the choice is still delete-or-rescue rather than an overdue entry.
      - name: Quarantine deletion ratchet
        run: pnpm check:quarantine-ledger

  typecheck:
    name: Typecheck
    runs-on: ubuntu-latest

    steps:
      - name: Checkout
        uses: actions/checkout@v7

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

      # FNXC:CIGateSpeed 2026-07-23-00:05:
      # tsc incremental buildinfo cache. tsconfig.base.json enables
      # `incremental` with per-package dist/.tsbuildinfo; a restored buildinfo
      # is SELF-VALIDATING (tsc hashes every input against it and re-checks
      # whatever changed), so restore-keys can never let a stale check through
      # — it only shrinks the re-checked set. Cold typecheck was ~4 min of the
      # PR critical path. Keyed by SHA so every commit saves a fresh snapshot;
      # restore-keys picks the nearest prior one (same PR, or main via the
      # warm-gate-build-cache job in full-suite.yml, which must keep an
      # identical path list — actions/cache versions caches by path list).
      - 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
        run: pnpm typecheck

  build:
    name: Build
    runs-on: ubuntu-latest

    steps:
      - name: Checkout
        uses: actions/checkout@v7

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

      # FNXC:CIGateSpeed 2026-07-23-00:05:
      # RESTORE-ONLY tap of the gate's incremental dist cache (see the gate
      # job's cache block for the full safety rationale: `pnpm build` always
      # runs and reconciles a near-match restore per package by content hash).
      # Restore-only (actions/cache/restore, never save) because this job runs
      # FULL CLI packaging (CI=true → desktop + bundled plugins + DTS), and
      # saving that shape would swap the cache's canonical fast-CLI contents
      # out from under the Gate job. Full CLI packaging itself is never skipped
      # regardless of cache state (ensureFullPackageCliPlanned force-plans the
      # CLI in full mode), so this job's distinctive coverage is preserved.
      # Path list must stay byte-identical to the gate job's block.
      - name: Compute dist source hash
        id: dist-hash
        run: echo "hash=$(node scripts/ensure-test-artifacts.mjs --print-source-hash)" >> "$GITHUB_OUTPUT"

      - name: Restore built dist artifacts (incremental, restore-only)
        uses: actions/cache/restore@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
        run: pnpm build

  # The only merge-blocking TEST signal (R3). Runs the boot smoke (the app
  # starts and serves) plus the curated engine-core suite and the CI-shape
  # test — see `test:gate` in the root package.json. Gate membership is the
  # explicit allow-list in packages/engine/vitest.config.ts (engine-core
  # project); a flaky gate test is evicted by removing it from that list.
  gate:
    name: Gate
    runs-on: ubuntu-latest
    # FNXC:FixPgTestsAndCi 2026-06-26-09:10:
    # Provision a PostgreSQL service container so the postgres/*.pg.test.ts
    # suites (pgDescribe) run in the merge gate. The pg-test-harness probe
    # detects reachability via a TCP probe on localhost:5432 and skips when
    # unavailable, so this service is what makes the 57 PG twin tests actually
    # execute instead of being silently skipped.
    services:
      postgres:
        image: postgres:15
        env:
          POSTGRES_USER: postgres
          POSTGRES_PASSWORD: postgres
          POSTGRES_DB: postgres
        ports:
          - 5432:5432
        # Mark the service healthy only when pg_isready succeeds on the mapped
        # port, so job steps don't start before Postgres accepts connections.
        options: >-
          --health-cmd "pg_isready -h localhost -p 5432 -U postgres"
          --health-interval 5s
          --health-timeout 5s
          --health-retries 10
    env:
      # Point the PG test harness at the service container. psql admin DDL
      # (CREATE/DROP DATABASE) runs against this URL's maintenance database.
      FUSION_PG_TEST_URL_BASE: "postgresql://postgres:postgres@localhost:5432"
      PGPASSWORD: "postgres"
    # The gate's value is speed; without a job timeout a hung build or
    # deadlocked vitest worker blocks every PR for GitHub's default 6 hours.
    # Expected runtime is ~3-5 min.
    timeout-minutes: 15
    steps:
      - name: Checkout
        uses: actions/checkout@v7

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

      # FNXC:CIGateSpeed 2026-07-22-23:30:
      # Gate-scoped INCREMENTAL dist cache (`gate-dist-*` namespace, distinct from
      # the shard jobs' exact-match `dist-*` contract). Unlike the shard jobs —
      # where restore-keys is forbidden because tests consume restored dist
      # WITHOUT a build (stale dist was the FN-4232/FN-4605 failure mode) — the
      # gate always runs `pnpm build` after restore. build-workspace.mjs verifies
      # every package's git content hash against .fusion/cache/plugin-build-cache.json
      # (cached below alongside dist) and rebuilds anything changed, missing, or
      # unhashed, so a near-match restore can only speed the build up, never let
      # stale dist through. Measured before this change: every PR missed the
      # exact key and paid a full ~6-8 min build for ~45s of actual gate tests.
      # NEVER add node_modules here (breaks Windows pnpm junctions elsewhere).
      # The warm-gate-build-cache job in full-suite.yml saves this same cache
      # (identical path list — actions/cache versions caches by path list, so
      # the two blocks must stay in sync) on every push to main so a PR's FIRST
      # gate run restores main's build instead of building cold.
      - 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 }}-

      # Only seed the mtime-defeating artifact hash-cache on an EXACT hit; on a
      # restore-keys near-hit the restored dist may be stale for changed
      # packages, and `pnpm build` below is what reconciles it.
      - 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

      # FNXC:CIGateSpeed 2026-07-22-23:30:
      # Boot smoke needs the built workspace including the CLI. Fast CLI
      # packaging (bin.js + extension.js, no desktop/bundled-plugin/DTS staging)
      # is sufficient for boot smoke + test:gate and is the same shape
      # `pnpm verify:fast` proves locally; CI=true would otherwise force the
      # multi-minute full packaging tail on every gate run. Full CLI packaging
      # coverage stays blocking in the separate Build job.
      - name: Build
        run: pnpm build
        env:
          FUSION_CLI_FULL_PACKAGE: "0"

      - name: Boot smoke (app starts and serves)
        run: node scripts/boot-smoke.mjs

      - name: Gate tests (curated engine-core + CI-shape)
        run: pnpm test:gate

  # Advisory desktop-packaging validation lives in its OWN workflow (desktop-packaging.yml) so this
  # thin gate stays exactly [Lint, Typecheck, Build, Gate] — the job set here maps 1:1 to the
  # branch-protection required checks (CI-shape test enforces the invariant).