gstack/.github/workflows/free-tests.yml

name: Free Tests

# A single duration-balanced plan covers every free test exactly once. Each
# shard runs serially on its own machine; the aggregate requires every receipt
# and strict outcome. Tree-mutating files, when present, get a separate machine.
#
# Deliberately SECRETLESS: free tests make no API calls, so this lane gets no
# provider keys at all — least privilege, and fork PRs get real test signal
# here (the eval matrix skips fork PRs because repository secrets can't reach
# them). test/free-tests-workflow-wiring.test.ts fails CI if a secret sneaks in.
#
# This is a REQUIRED check from day one (branch protection lists it). If it's
# red, fix or quarantine-with-issue — don't make it advisory; an advisory lane
# is permanent false comfort.
#
# Local `bun run test` still uses the existing bounded process pool.

on:
  pull_request:
    branches: [main]
  # Also on main pushes: two individually-green PRs can merge into a red
  # main; without this nothing runs the free suite on main until the next PR.
  push:
    branches: [main]
  workflow_dispatch:

# Keyed on the PR number, not head_ref: a bare branch name carries no fork
# prefix, so same-name branches from two forks would share one group and a
# push to fork B's PR would cancel fork A's in-flight REQUIRED check.
concurrency:
  group: free-tests-${{ github.event.pull_request.number || github.run_id }}
  cancel-in-progress: true

# Least privilege: this job executes PR-controlled code (install lifecycle
# scripts + the test suite), so the GITHUB_TOKEN gets read-only contents and
# the checkout doesn't persist it into .git/config.
permissions:
  contents: read

jobs:
  free-plan:
    runs-on: ubuntu-24.04
    timeout-minutes: 5
    outputs:
      matrix: ${{ steps.plan.outputs.matrix }}
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          persist-credentials: false
          # Full history: the seed ratchet compares the allowlist with its
          # merge-base copy, which a depth-1 checkout cannot read.
          fetch-depth: 0
      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
        with:
          bun-version: 1.4.2
      - id: plan
        name: Inventory and balance the complete free suite
        # Warns in the job summary when more than 5 files are unseeded.
        run: |
          matrix=$(bun run scripts/test-free-shards.ts --ci-plan "$RUNNER_TEMP/free-plan.json" --shards 20)
          echo "matrix=$matrix" >> "$GITHUB_OUTPUT"
      - name: Seed growth ratchet (60 s ceiling, shrink-only allowlist)
        run: |
          GSTACK_FREE_SEED_BASE="$(git merge-base HEAD origin/main)" bun test test/free-seed-ratchet.test.ts
      - uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
        with:
          name: free-plan
          path: ${{ runner.temp }}/free-plan.json
          if-no-files-found: error

  cso-macos-launcher:
    runs-on: macos-latest
    timeout-minutes: 15
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          persist-credentials: false
      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
        with:
          bun-version: 1.4.2
      - name: Install helper dependencies
        run: bun install --frozen-lockfile --ignore-scripts
      - name: Build and sign the native macOS startup boundary
        run: bun run build:cso
      - name: Exercise hardened-runtime startup and environment scrubbing
        run: bun run test:cso:macos
        env:
          GSTACK_CSO_MACOS_TESTS: "1"
      - name: Build browser lifecycle prerequisites
        run: |
          bunx playwright install chromium
          bun run build
      - name: Exercise native agent ownership and linked settings
        env:
          TMPDIR: /tmp
        run: |
          files=(browse/test/terminal-agent-lifecycle.test.ts browse/test/terminal-agent-native-observation.test.ts browse/test/terminal-agent-watchdog.test.ts browse/test/server-embedder-terminal-port.test.ts browse/test/server-factory.test.ts test/gstack-settings-hook-symlink.test.ts test/gstack-settings-hook-schema-aware.test.ts)
          for file in "${files[@]}"; do test -f "$file"; done
          bun test "${files[@]}"

  # Named regressions that only reproduce on macOS's default temp root:
  # $TMPDIR sits under /var/folders and /var is a symlink to /private/var, so
  # code that compares a realpath with an unresolved path passes on Linux's
  # /tmp and fails here (#2982). TMPDIR is deliberately left at the runner's
  # default, and the job fails if that layout is not symlinked. It also sources
  # the Codex probe from zsh, macOS's default shell (#3024; no paid call).
  macos-named-regressions:
    runs-on: macos-latest
    timeout-minutes: 20
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          persist-credentials: false
      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
        with:
          bun-version: 1.4.2
      - name: Install dependencies
        run: bun install --frozen-lockfile --ignore-scripts
      - name: Build browser prerequisites
        run: |
          bunx playwright install chromium
          bun run build
      - name: Configure git identity (tests init temp repos)
        run: |
          git config --global user.email "free-tests-ci@gstack.test"
          git config --global user.name "Free Tests CI"
          git config --global init.defaultBranch main
      - name: Codex probe selects a model from zsh, run as a command and sourced (macOS default shell, no paid call)
        working-directory: ${{ runner.temp }}
        run: |
          set -euo pipefail
          run="$(zsh -c '"$GITHUB_WORKSPACE/bin/gstack-codex-probe" select-model exec' 2>&1)"
          printf '%s\n' "$run"
          printf '%s\n' "$run" | grep -E '^CODEX_SEL: [A-Za-z0-9._:/-]+$'
          out="$(zsh -c 'source "$GITHUB_WORKSPACE/bin/gstack-codex-probe" && _gstack_codex_select_model exec' 2>&1)"
          printf '%s\n' "$out"
          printf '%s\n' "$out" | grep -E '^CODEX_MODEL: [A-Za-z0-9._:/-]+ \(exec; source: '
      - name: Run the named macOS regressions on the default temp root
        run: |
          set -euo pipefail
          tmp="${TMPDIR:-/tmp}"
          resolved="$(realpath "$tmp")"
          echo "temp root: $tmp -> $resolved"
          test "$resolved" != "${tmp%/}"
          files=(test/gstack-design-detect.test.ts browse/test/chromium-profile-isolation.test.ts test/cso-git-hardening.test.ts test/plan-count-file-permission.test.ts test/spec-quality-gate-secret-sink.test.ts test/gstack-memory-ingest.test.ts test/regression-issue3024-zsh-sourced-helpers.test.ts test/codex-probe-subcommands.test.ts)
          for file in "${files[@]}"; do test -f "$file"; done
          bun test "${files[@]}"

  cso-windows-launcher:
    runs-on: windows-latest
    timeout-minutes: 15
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          persist-credentials: false
      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
        with:
          bun-version: 1.4.2
      - name: Install helper dependencies
        run: bun install --frozen-lockfile --ignore-scripts
      - name: Build the native Windows startup boundary from Git Bash
        shell: bash
        run: bun run build:cso
      - name: Exercise native startup, environment, and argument forwarding
        run: bun run test:cso:windows
        env:
          GSTACK_CSO_WINDOWS_TESTS: "1"
      - name: Upload #2894 lease diagnostics
        if: failure()
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
        with:
          name: cso-lease-diagnostics-a${{ github.run_attempt }}
          path: ${{ runner.temp }}/cso-lease-diagnostics
          if-no-files-found: ignore
          retention-days: 14

  cso-docker-integration:
    runs-on: ubuntu-24.04
    timeout-minutes: 20
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          persist-credentials: false
      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
        with:
          bun-version: 1.4.2
      - name: Require local Docker containment prerequisites
        # A missing daemon is a failed gate, never a skipped integration test.
        run: |
          command -v docker
          docker --host unix:///var/run/docker.sock info
          command -v cc
      - name: Install helper dependencies
        run: bun install --frozen-lockfile --ignore-scripts
      - name: Compile trusted CSO helper and watchdog
        run: bun run build:cso
      # Only the file that can run here: the node-lifecycle and stack-cold
      # files need GSTACK_CSO_TEST_STACK images and run in the CSO runtime
      # workflows (test:cso:docker), so in this job they always skipped.
      - name: Run CSO Docker integration gate
        run: |
          bun test --max-concurrency 1 test/cso-docker-integration.test.ts
        env:
          GSTACK_CSO_DOCKER_TESTS: "1"
          DOCKER_HOST: unix:///var/run/docker.sock

  typecheck:
    runs-on: ubuntu-24.04
    timeout-minutes: 10
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          persist-credentials: false
      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
        with:
          bun-version: 1.4.2
      - name: Install dependencies
        run: bun install --frozen-lockfile --ignore-scripts
      - name: Typecheck product code (zero errors)
        run: bun run typecheck
      - name: Test-code type-debt ratchet
        run: bun run typecheck:test
      - name: CSO source formatting
        run: bun run format:cso:check

  free-suite:
    needs: free-plan
    runs-on: ubicloud-standard-8
    timeout-minutes: 20
    strategy:
      fail-fast: false
      max-parallel: 20
      matrix: ${{ fromJSON(needs.free-plan.outputs.matrix) }}
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          persist-credentials: false

      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
        with:
          bun-version: 1.4.2

      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          name: free-plan
          path: ${{ runner.temp }}

      - uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6
        with:
          path: ~/.bun/install/cache
          key: linux-bun-${{ hashFiles('bun.lock') }}
          # A lockfile bump starts from the previous cache instead of cold.
          restore-keys: |
            linux-bun-

      - name: Install dependencies
        run: bun install --frozen-lockfile

      - uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6
        with:
          path: ~/.cache/ms-playwright
          key: linux-playwright-${{ hashFiles('bun.lock') }}
          restore-keys: |
            linux-playwright-

      # Cache restores browser binaries; install is still required for system
      # deps and is a fast no-op for already-present browsers.
      - name: Install Playwright Chromium
        run: npx playwright install --with-deps chromium

      - name: Configure the bundled Chromium sandbox helper
        run: |
          set -euo pipefail
          chrome=$(bun -e 'import { chromium } from "playwright"; import { realpathSync } from "node:fs"; console.log(realpathSync(chromium.executablePath()))')
          case "$chrome" in
            "$HOME"/.cache/ms-playwright/chromium-*/chrome-linux*/chrome) ;;
            *) echo "Unexpected Chromium installation path" >&2; exit 1 ;;
          esac
          helper="${chrome%/*}/chrome_sandbox"
          installed="${chrome%/*}/chrome-sandbox"
          test -f "$helper" && test ! -L "$helper"
          sudo install -T -o root -g root -m 4755 "$helper" "$installed"
          test "$(stat -c '%u:%a' "$installed")" = '0:4755'
          cmp -s "$helper" "$installed"

      # Headed-browser tests (handoff, extension sidepanel DOM) need a real
      # DISPLAY — first Linux run failed with Playwright's "launched a headed
      # browser without an XServer" banner. xvfb-run below provides it;
      # x11-utils ships xdpyinfo for display probing. poppler-utils ships
      # pdftotext/pdffonts/pdftoppm for the make-pdf e2e gates;
      # fonts-noto-color-emoji is the emoji-gate's render font (playwright
      # --with-deps usually installs it, but the gate must not depend on a
      # transitive package list). Fonts must land BEFORE the first browse
      # daemon launch — Chromium snapshots fontconfig at startup. zsh is not
      # in the runner image; without it the bash+zsh portability arms (#2669)
      # skip instead of running.
      - name: Install Xvfb + X11 utilities + gate tools
        run: sudo apt-get install -y --no-install-recommends xvfb x11-utils poppler-utils fonts-noto-color-emoji zsh

      - name: Configure git identity (tests init temp repos)
        run: |
          git config --global user.email "free-tests-ci@gstack.test"
          git config --global user.name "Free Tests CI"
          git config --global init.defaultBranch main
          # Some tests run git against the checkout itself; CI checkouts can be
          # owned by a different uid than the runner user.
          git config --global --add safe.directory '*'

      - name: Generate host SKILL.md outputs (.agents, .factory)
        # Golden-file tests read generated host outputs that are gitignored.
        run: bun run gen:skill-docs --host all

      - name: Vendor xterm assets into the extension
        # extension/lib/xterm* are gitignored (vendored from npm at build
        # time). Without them the sidepanel's terminal script bails and the
        # sidepanel DOM tests time out waiting on init that never happens.
        run: bun run vendor:xterm

      - name: Build server-node bundle (loaded by browse cli imports)
        run: bash browse/scripts/build-node-server.sh

      # Narrowed gate build: the make-pdf e2e gates probe make-pdf/dist/pdf,
      # browse/dist/browse, and the diagram-render bundle, then self-skip when
      # absent — which made them silently skip on Linux for their whole life
      # (this lane never built binaries). Full `bun run build` compiles five
      # binaries and would add ~60-90s to the ONLY required check; the gates
      # need exactly these three artifacts.
      - name: Build gate binaries (make-pdf e2e gates)
        run: bun run build:gates

      - name: Build trusted CSO helper used by free contract tests
        run: bun run build:cso

      # GSTACK_EXPECT_BINARIES=1 arms make-pdf/test/e2e/ci-prereqs.test.ts:
      # if a future edit drops the gate build (or poppler), the lane FAILS
      # instead of the gates silently self-skipping back to false green.
      - name: Run free suite
        run: xvfb-run -a bun run test:free --ci-run "$RUNNER_TEMP/free-plan.json" --shard ${{ matrix.shard }} --result "$RUNNER_TEMP/free-results/shard-${{ matrix.shard }}.json"
        env:
          GSTACK_EXPECT_BINARIES: "1"
          # WS1 flake telemetry: a single timing flake must not red the only
          # required lane — the runner's attribution-gated retry pass (cap 5,
          # truncation veto) re-runs failing files once, serially, and a
          # clean retry downgrades to a LOUD flaky-pass. Every flaky-pass is
          # appended to the ledger (single writer: the parent runner) and
          # uploaded below, so repeat offenders are an enumerable series —
          # recorded and ranked, never masked. Pinned by
          # test/free-tests-workflow-wiring.test.ts.
          GSTACK_FREE_RETRY_FLAKY: "1"
          GSTACK_FLAKE_LEDGER: ${{ runner.temp }}/flake-ledger.jsonl

      - name: Upload strict shard result
        if: always()
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
        with:
          name: free-result-${{ matrix.shard }}
          path: ${{ runner.temp }}/free-results/*.json
          if-no-files-found: error

      # Uploaded unconditionally (not just on failure): a flaky-pass run is
      # GREEN — that's the point — so its evidence must survive green runs.
      - name: Upload flake ledger
        if: always()
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
        with:
          name: flake-ledger-${{ matrix.shard }}
          path: ${{ runner.temp }}/flake-ledger.jsonl
          if-no-files-found: ignore
          retention-days: 90

      - name: Detect recovered failures for log retention
        id: flake_spool
        if: always()
        run: |
          if [ -s "$RUNNER_TEMP/flake-ledger.jsonl" ]; then
            echo 'present=true' >> "$GITHUB_OUTPUT"
          fi

      # The quiet console omits assertion details. Preserve the original spool
      # after a recovered retry too, so a green job retains its first failure.
      - name: Upload shard logs on failure or recovered retry
        if: failure() || steps.flake_spool.outputs.present == 'true'
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
        with:
          name: free-test-shard-logs-${{ matrix.shard }}
          path: .context/free-test-logs/gstack-free-test-*.log
          include-hidden-files: true
          if-no-files-found: ignore

  # Branch protection already requires the `free-tests` context. Keep that
  # stable name as an always-running aggregate so every platform-specific CSO
  # gate is merge-blocking without a separate branch-protection migration.
  free-tests:
    if: always()
    needs: [free-suite, typecheck, cso-macos-launcher, macos-named-regressions, cso-windows-launcher, cso-docker-integration]
    runs-on: ubuntu-24.04
    timeout-minutes: 5
    steps:
      - name: Require the free suite, typecheck, macOS regressions, and every CSO platform gate
        env:
          FREE_SUITE_RESULT: ${{ needs.free-suite.result }}
          TYPECHECK_RESULT: ${{ needs.typecheck.result }}
          CSO_MACOS_RESULT: ${{ needs.cso-macos-launcher.result }}
          MACOS_REGRESSIONS_RESULT: ${{ needs.macos-named-regressions.result }}
          CSO_WINDOWS_RESULT: ${{ needs.cso-windows-launcher.result }}
          CSO_DOCKER_RESULT: ${{ needs.cso-docker-integration.result }}
        run: |
          set -eu
          test "$FREE_SUITE_RESULT" = success
          test "$TYPECHECK_RESULT" = success
          test "$CSO_MACOS_RESULT" = success
          test "$MACOS_REGRESSIONS_RESULT" = success
          test "$CSO_WINDOWS_RESULT" = success
          test "$CSO_DOCKER_RESULT" = success
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          persist-credentials: false
      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2
        with:
          bun-version: 1.4.2
      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          name: free-plan
          path: ${{ runner.temp }}
      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          pattern: free-result-*
          merge-multiple: true
          path: ${{ runner.temp }}/free-results
      # Per-shard ledgers land in their own subdirectories (all are named
      # flake-ledger.jsonl). A green run is where a retried flake hides, so the
      # summary runs before strict verification.
      - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          pattern: flake-ledger-*
          path: ${{ runner.temp }}/flake-ledgers
      - name: Summarize flaky passes absorbed by the serial retry
        run: bun run scripts/test-health-report.ts flake-summary "$RUNNER_TEMP/flake-ledgers" >> "$GITHUB_STEP_SUMMARY"
      - name: Require exact coverage and complete strict results
        run: bun run scripts/test-free-shards.ts --ci-verify "$RUNNER_TEMP/free-plan.json" --results "$RUNNER_TEMP/free-results"