test.yml

name: Test

on:
  push:
    branches: [master]
  pull_request:
    branches: [master]
  # Manual dispatch lets a local dev/agent offload the suite to GitHub's
  # on-demand runners from ANY branch (see scripts/ship-remote-tests.sh).
  # Frees a load-saturated local machine (e.g. many Conductor agents running
  # their own bun-test suites at once — load avg 120 on 16 cores).
  workflow_dispatch:

permissions:
  contents: read

# Cancel a superseded run when a newer commit lands on the same PR/branch.
# Keyed on the PR number for pull_request events (unique per PR, so two PRs
# from forks sharing a branch name don't cancel each other) and falls back to
# github.ref for push/scheduled runs. Mirrors heavy-tests.yml; frees runners
# and stops a stale-SHA run from reporting a flaky failure on an obsolete commit.
concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true

jobs:
  # ──────────────────────────────────────────────────────────────────────
  # cache-check: runs first, computes the content hash of every tracked
  # file EXCEPT the deny-list (CHANGELOG.md, README.md, docs/**/*.md, etc.
  # — see scripts/ci-cache-hash.sh for the full list). Looks up
  # `ci-pass-<hash>` in actions/cache; if hit, the test matrix + verify
  # + serial jobs all skip and test-status reports green immediately.
  # If miss, the full suite runs and cache-write seals it on success.
  #
  # Hit rate covers re-pushes (same SHA twice), branch rebases that
  # don't touch tracked code, and any branch update that touches only
  # the deny-listed doc files.
  # ──────────────────────────────────────────────────────────────────────
  cache-check:
    runs-on: ubuntu-latest
    timeout-minutes: 10
    outputs:
      hit: ${{ steps.lookup.outputs.cache-hit }}
      hash: ${{ steps.compute.outputs.hash }}
    steps:
      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
      - name: Compute content hash
        id: compute
        run: |
          # --verbose writes the "X/Y files in hash" diagnostic to stderr;
          # stdout carries the 16-char hash. Capture both.
          HASH=$(bash scripts/ci-cache-hash.sh --verbose 2>/tmp/cache-diag)
          cat /tmp/cache-diag
          echo "Computed cache hash: $HASH"
          echo "hash=$HASH" >> "$GITHUB_OUTPUT"
      - name: Lookup actions/cache for ci-pass-<hash>
        id: lookup
        uses: actions/cache/restore@5a3ec84eff668545956fd18022155c47e93e2684  # v4.2.3
        with:
          key: ci-pass-${{ steps.compute.outputs.hash }}
          path: .ci-cache-marker
          # `lookup-only: true` means we only probe whether the cache
          # entry exists — we don't download it (the marker contents
          # don't matter, only the key match does). `cache-hit` returns
          # true only on EXACT key match (per actions/cache docs); a
          # restore-keys prefix fallback would set cache-hit=false, so
          # it's deliberately omitted here. Cross-branch scoping works
          # naturally: PR branches can read default-branch (master)
          # cache entries via exact key match when the content hash
          # matches, which happens whenever the tree is doc-only
          # different from a green master run.
          lookup-only: true
      - name: Cache status
        run: |
          if [ "${{ steps.lookup.outputs.cache-hit }}" = "true" ]; then
            echo "✓ cache HIT for hash ${{ steps.compute.outputs.hash }} — test jobs will skip"
          else
            echo "✗ cache MISS for hash ${{ steps.compute.outputs.hash }} — full suite will run"
          fi

  gitleaks:
    needs: cache-check
    if: needs.cache-check.outputs.hit != 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 10
    steps:
      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
        with:
          fetch-depth: 0
      - uses: gitleaks/gitleaks-action@ff98106e4c7b2bc287b24eaf42907196329070c7  # v2
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

  verify:
    # Pre-test gates: privacy/jsonb/source-id/etc + typecheck + admin-build.
    # Lives in its own runner so the matrix shards aren't carrying ~2-3min
    # of verify work in addition to their test files (the old shape stuffed
    # this into `test (1)` via `if: matrix.shard == 1`, which made shard 1
    # the slowest matrix worker). scripts/run-verify-parallel.sh fans out
    # the 20 checks via & + wait (~5s vs ~15-25s sequential).
    needs: cache-check
    if: needs.cache-check.outputs.hit != 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 12
    steps:
      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
        with:
          bun-version: 1.3.13
      - uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684  # v4.2.3
        with:
          path: ~/.bun/install/cache
          key: bun-cache-${{ runner.os }}-${{ hashFiles('bun.lock') }}
      - run: bun install
      - run: bun run verify
      # Guard: no bare `bun test` in workflows/scripts — bun ignores
      # bunfig.toml's timeout, and hooks (beforeAll/afterAll) get the 5s
      # default regardless of per-test third-arg timeouts. Runs directly
      # (not via verify's CHECKS array) to avoid a package.json edit.
      - run: bash scripts/check-bun-test-timeout.sh

  serial-tests:
    # *.serial.test.ts at --max-concurrency=1. Lives in its own runner so
    # the matrix shards aren't carrying the serial-pass tail (the old shape
    # stuffed this into `test (1)` after the matrix work, which compounded
    # shard 1's overload).
    needs: cache-check
    if: needs.cache-check.outputs.hit != 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 15
    steps:
      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
        with:
          bun-version: 1.3.13
      - uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684  # v4.2.3
        with:
          path: ~/.bun/install/cache
          key: bun-cache-${{ runner.os }}-${{ hashFiles('bun.lock') }}
      - run: bun install
      - run: bun run test:serial

  slow-eval-longmemeval:
    # Dedicated runner for the LongMemEval end-to-end test file. The file
    # was originally 359s. TODO #1 (engine-sharing in runEvalLongMemEval
    # via RunOpts.engine) cut it to ~200s by amortizing PGLite cold-create
    # across all 13 runEvalLongMemEval calls in one beforeAll-shared brain.
    # Pulled out of the matrix (see scripts/test-shard.sh) so a single 200s
    # atom doesn't dominate a shard's wallclock. Companion file
    # test/eval-longmemeval.slow.test.ts (the pure-bucket half) stays in
    # the matrix because it's light (~42s).
    needs: cache-check
    if: needs.cache-check.outputs.hit != 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 12
    steps:
      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
        with:
          bun-version: 1.3.13
      - uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684  # v4.2.3
        with:
          path: ~/.bun/install/cache
          key: bun-cache-${{ runner.os }}-${{ hashFiles('bun.lock') }}
      - run: bun install
      - run: bun test test/eval-longmemeval-e2e.slow.test.ts --timeout=60000

  slow-entity-resolve-perf:
    # Dedicated runner for the entity-resolve perf test (~159s, single perf
    # describe with one test that builds 5000+ pages and asserts the NEW
    # tryPrefixExpansion shape is 5x faster than the OLD shape — not
    # subdivisible without weakening the perf guarantee). Pulled out of the
    # matrix (see scripts/test-shard.sh) so a single 159s atom doesn't
    # dominate a shard's wallclock. Runs in parallel with the matrix.
    needs: cache-check
    if: needs.cache-check.outputs.hit != 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 12
    steps:
      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
        with:
          bun-version: 1.3.13
      - uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684  # v4.2.3
        with:
          path: ~/.bun/install/cache
          key: bun-cache-${{ runner.os }}-${{ hashFiles('bun.lock') }}
      - run: bun install
      - run: bun test test/entity-resolve-perf.slow.test.ts --timeout=300000

  test:
    # Pure matrix shard — no verify, no serial. Each shard runs its slice
    # of the unit test set under one `bun test` invocation.
    #
    # 10 shards (was 6) drops per-shard total from 532s → 287s. With the two
    # dedicated jobs (slow-eval-longmemeval, slow-entity-resolve-perf) also
    # pulled out, the matrix is bounded by ~287s ≈ 4.8 min. Total CI ≈ max
    # of matrix + slow-eval (~3.3 min after engine-sharing in TODO #1) +
    # slow-entity-resolve-perf (~2.6 min) ≈ 4.8 min.
    #
    # Concurrency budget: 10 shards + verify + serial + slow-eval +
    # slow-entity-resolve-perf + gitleaks + cache-check + cache-write +
    # test-status = ~18 jobs × 2 concurrent PRs = 36. GitHub free-tier
    # caps at ~20 concurrent jobs, so multi-PR days will see some queue
    # pressure. Single-PR runs are unaffected.
    #
    # Partition policy is weight-aware LPT bin-packing via scripts/sharding.ts
    # (replaces FNV-1a path hash). Weights live in scripts/test-weights.json,
    # mined from real CI logs via scripts/mine-shard-weights.ts. Missing
    # weights fall back to corpus median — new test files work immediately.
    needs: cache-check
    if: needs.cache-check.outputs.hit != 'true'
    runs-on: ubuntu-latest
    # 22, not 15: under parallel PR load the PGLite WASM cold-starts stretch a
    # shard past 15 min while every test is still passing — the timeout then
    # cancels the job and the test-status gate reads it as a failure. 13 runs
    # died this way on 2026-07-21/22 alone.
    timeout-minutes: 22
    strategy:
      fail-fast: false
      matrix:
        shard: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
    steps:
      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262  # v4
      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6  # v2
        with:
          bun-version: 1.3.13
      - uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684  # v4.2.3
        with:
          path: ~/.bun/install/cache
          key: bun-cache-${{ runner.os }}-${{ hashFiles('bun.lock') }}
      - run: bun install
      - name: Run test shard ${{ matrix.shard }}/10
        run: scripts/test-shard.sh ${{ matrix.shard }} 10

  # ──────────────────────────────────────────────────────────────────────
  # cache-write: ONLY runs when every gated job succeeded. Writes the
  # cache entry under `ci-pass-<hash>` so future runs at the same hash
  # hit cache. Codex's load-bearing correctness point: writing the
  # cache before the matrix completes would permanently bless bad states
  # (a future run at the same hash would skip tests because of a cache
  # entry written when tests hadn't actually passed).
  # ──────────────────────────────────────────────────────────────────────
  cache-write:
    needs: [cache-check, gitleaks, verify, serial-tests, slow-eval-longmemeval, slow-entity-resolve-perf, test]
    if: success() && needs.cache-check.outputs.hit != 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 5
    steps:
      - name: Create cache marker
        run: |
          mkdir -p .ci-cache-marker
          echo "${{ needs.cache-check.outputs.hash }}" > .ci-cache-marker/hash
          echo "$GITHUB_SHA" > .ci-cache-marker/sha
          echo "$GITHUB_REF" > .ci-cache-marker/ref
      - uses: actions/cache/save@5a3ec84eff668545956fd18022155c47e93e2684  # v4.2.3
        with:
          key: ci-pass-${{ needs.cache-check.outputs.hash }}
          path: .ci-cache-marker

  # ──────────────────────────────────────────────────────────────────────
  # test-status: the single user-visible "did CI pass?" check.
  # Runs always (if: always()), succeeds when EITHER cache-check.hit==true
  # OR all gated jobs (gitleaks, verify, serial-tests, test) succeeded.
  # Branch protection (when configured) gates on this single job name.
  # ──────────────────────────────────────────────────────────────────────
  test-status:
    needs: [cache-check, gitleaks, verify, serial-tests, slow-eval-longmemeval, slow-entity-resolve-perf, test]
    if: always()
    runs-on: ubuntu-latest
    timeout-minutes: 5
    steps:
      - name: Aggregate result
        run: |
          HIT="${{ needs.cache-check.outputs.hit }}"
          GITLEAKS="${{ needs.gitleaks.result }}"
          VERIFY="${{ needs.verify.result }}"
          SERIAL="${{ needs.serial-tests.result }}"
          SLOW_EVAL="${{ needs.slow-eval-longmemeval.result }}"
          SLOW_PERF="${{ needs.slow-entity-resolve-perf.result }}"
          TEST="${{ needs.test.result }}"
          echo "cache-check.hit=$HIT"
          echo "gitleaks=$GITLEAKS  verify=$VERIFY  serial-tests=$SERIAL  slow-eval-longmemeval=$SLOW_EVAL  slow-entity-resolve-perf=$SLOW_PERF  test=$TEST"
          if [ "$HIT" = "true" ]; then
            echo "✓ cache HIT for hash ${{ needs.cache-check.outputs.hash }} — CI green"
            exit 0
          fi
          # Cache miss: every gated job must have succeeded.
          for r in "$GITLEAKS" "$VERIFY" "$SERIAL" "$SLOW_EVAL" "$SLOW_PERF" "$TEST"; do
            if [ "$r" != "success" ]; then
              echo "✗ gated job did not succeed (got $r) — CI fail"
              exit 1
            fi
          done
          echo "✓ all gated jobs succeeded — CI green"