Codeman/.github/workflows/ci.yml

name: CI

on:
  push:
    branches: [master, main]
  pull_request:

jobs:
  ci:
    name: Typecheck & Lint
    runs-on: ubuntu-latest

    steps:
      - uses: actions/checkout@v6

      - name: Setup Node.js
        uses: actions/setup-node@v6
        with:
          node-version: 22
          cache: 'npm'

      - name: Install dependencies
        run: npm ci

      - name: Check package-lock.json version sync
        run: npm run check:lockfile

      - name: Type check
        run: npm run typecheck

      - name: Lint
        run: npm run lint

      - name: Frontend JS syntax check
        run: npm run check:frontend-syntax

      - name: Format check
        run: npm run format:check

      # install.sh reaches users through `curl | bash` with nothing between it and
      # them, and until now nothing in this repo checked it at all: no shellcheck,
      # no bats, and the vitest gate is Node-only.
      - name: install.sh syntax
        run: bash -n install.sh

      # macOS ships bash 3.2 and this runner has bash 5, so the constructs that
      # actually break a Mac install are invisible here without a container. This
      # step is what catches them — in particular expanding an EMPTY array under
      # `set -u`, which bash 3.2 treats as an unbound variable and `bash -n`
      # cannot see because it is a runtime error, not a syntax one.
      - name: install.sh runs on bash 3.2 (macOS's version)
        run: |
          set -euo pipefail
          docker run --rm -v "$PWD":/w -w /w bash:3.2 bash -n /w/install.sh
          docker run --rm -v "$PWD":/w -w /w -e CODEMAN_INSTALL_SH_LIB=1 bash:3.2 bash -c '
            set -euo pipefail
            . /w/install.sh
            detect_all_clis
            # `shell` declares no binaries, so its offset/length window is length 0.
            # Iterating it is the empty-array case; reaching here means it did not abort.
            echo "bash $BASH_VERSION: ${#CLI_IDS[@]} CLIs, $CLI_FOUND_COUNT found"
            cli_catalog_names >/dev/null
            cli_catalog_print_install_hints >/dev/null
            # The install menu with nothing installed and the user answering "s":
            # skipping must warn and continue, never trip the "failed to install"
            # gate (it did once, aborting the install before the clone).
            has_tty() { return 0; }
            headless_guard() { return 0; }
            read_reply() { eval "$1=s"; }
            NONINTERACTIVE=0
            k=0; while [[ $k -lt ${#CLI_ALL_BINS[@]} ]]; do CLI_ALL_BINS[$k]="no-such-cli-$k"; k=$((k + 1)); done
            k=0; while [[ $k -lt ${#CLI_ALL_PATHS[@]} ]]; do CLI_ALL_PATHS[$k]="/nonexistent/$k"; k=$((k + 1)); done
            CLI_DETECT_DONE=""; detect_all_clis
            offer_ai_cli_install >/dev/null 2>&1
            echo "bash $BASH_VERSION: skipping the AI CLI install menu continues"
          '
          # Issue #382: the dsh identity probe builds an OPTIONAL `timeout` prefix as an
          # array, and on stock macOS there is no `timeout`, so the array is empty and the
          # expansion aborts the whole installer under `set -u`. The step above cannot
          # reach that branch: this image HAS `timeout`, and with no `dsh` on PATH the
          # probe is never called at all. So hide `timeout` and call it directly.
          docker run --rm -v "$PWD":/w -w /w -e CODEMAN_INSTALL_SH_LIB=1 bash:3.2 bash -c '
            set -euo pipefail
            . /w/install.sh
            printf "#!/bin/sh\necho \"DeepSeek Harness 0.1\"\n" > /tmp/dsh
            printf "#!/bin/sh\necho \"dancer shell (Debian dsh)\"\n" > /tmp/not-dsh
            chmod 755 /tmp/dsh /tmp/not-dsh
            # A PATH the probe can still work on, minus the binary under test.
            mkdir -p /tmp/nobin
            for b in grep sh; do ln -sf "$(command -v $b)" "/tmp/nobin/$b"; done
            export PATH=/tmp/nobin
            if command -v timeout >/dev/null 2>&1; then
              echo "timeout is still on PATH, so this is NOT exercising the empty-array branch" >&2
              exit 1
            fi
            dsh_banner_probe /tmp/dsh
            if dsh_banner_probe /tmp/not-dsh; then
              echo "identity probe accepted a foreign dsh" >&2
              exit 1
            fi
            echo "bash $BASH_VERSION: dsh identity probe survives a missing timeout"
          '
          # Installer v2: the question phase runs before the build, and every decision it
          # takes is bash logic over stubbed tailscale state. Drive the flags, the launch
          # default, the occupied-:443 menu and the rename question with canned answers,
          # so a bash-4 construct or a flipped default in any of them fails here, not on a
          # Mac. The JSON parsers need node (absent in this image) and are stubbed; their
          # own coverage is test/install-sh-invariants.test.ts plus the vitest gate.
          docker run --rm -v "$PWD":/w -w /w -e CODEMAN_INSTALL_SH_LIB=1 -e HOME=/tmp/h bash:3.2 bash -c '
            set -euo pipefail
            mkdir -p /tmp/h
            . /w/install.sh
            parse_flags --tailscale --service --name Build-Box --port 4000
            [[ "$CODEMAN_TAILSCALE" == "1" && "$LAUNCH_PRESET" == "2" && "$TS_NAME" == "Build-Box" && "$CODEMAN_PORT" == "4000" ]]
            [[ "$(ts_sanitize_name "$TS_NAME")" == "build-box" ]]
            has_tty() { return 0; }
            ANSWER=""; read_reply() { eval "$1=\"\$ANSWER\""; }
            systemctl() { return 0; }
            LAUNCH_PRESET=""; NONINTERACTIVE=0
            choose_launch_mode linux >/dev/null 2>&1
            [[ "$LAUNCH_CHOICE" == "2" ]]
            check_tailscale() { return 0; }
            ts_status_field() { case "$1" in "s.BackendState") printf Running ;; "s.Self && s.Self.DNSName") printf "box.tail.ts.net." ;; esac; }
            ts_backend_state() { printf Running; }
            ts_dns_name() { printf box.tail.ts.net; }
            ts_serve_443_target_port() { printf 8080; }
            ts_serve_find_port_mapping() { :; }
            ts_serve_port_used() { return 1; }
            detect_tailscale_serve_url() { :; }
            tailscale_choose_mapping >/dev/null 2>&1
            [[ "$TS_SERVE_MODE" == "path" && "$BIND_BASE_URL" == "/codeman" ]]
            RENAMED=""; tailscale_rename_node() { RENAMED="$1"; }
            TS_NAME=""; tailscale_choose_name >/dev/null 2>&1
            [[ -z "$RENAMED" ]]
            # A flag re-run keeps the password the unit already carries (and so
            # never writes the unauthenticated ack), and the hand-start line the
            # done screen prints carries every non-default value.
            read_existing_binding() { EXISTING_FOUND=1; EXISTING_HOST=0.0.0.0; EXISTING_PASSWORD=s3cret; EXISTING_ACK=0; EXISTING_BASE_URL=""; }
            CODEMAN_HOST=0.0.0.0; CODEMAN_TAILSCALE=0; unset CODEMAN_PASSWORD; BIND_ACK=0
            choose_network_binding >/dev/null 2>&1
            [[ "$BIND_PASSWORD" == "s3cret" && "$BIND_ACK" == "0" ]]
            BIND_HOST=0.0.0.0; BIND_PASSWORD=x; BIND_ACK=0; BIND_BASE_URL=/codeman; CODEMAN_PORT=4000
            [[ "$(start_command_hint)" == "CODEMAN_HOST=0.0.0.0 CODEMAN_PASSWORD="*" CODEMAN_BASE_URL=/codeman CODEMAN_PORT=4000 codeman web" ]]
            RECONFIGURE=0; parse_flags --port 4001; [[ "$RECONFIGURE" == "1" ]]
            echo "bash $BASH_VERSION: question phase (flags, launch default, occupied :443, rename opt-in, kept password, start line) ok"
          '

      - name: CLI catalogue artifacts are in sync with stock.ts
        run: npm run generate:cli-catalog -- --check

      - name: Server boot smoke test
        run: |
          set -u
          if ! command -v tmux >/dev/null; then
            sudo apt-get update -qq
            sudo apt-get install -y tmux
          fi
          npx tsx src/index.ts web --port 3151 > /tmp/boot.log 2>&1 &
          SERVER_PID=$!
          trap "kill $SERVER_PID 2>/dev/null || true" EXIT
          for i in $(seq 1 30); do
            if curl -fsS http://localhost:3151/api/status -o /dev/null; then
              echo "Server booted in ${i}s"
              exit 0
            fi
            if ! kill -0 $SERVER_PID 2>/dev/null; then
              echo "Server exited before becoming ready. Logs:"
              cat /tmp/boot.log
              exit 1
            fi
            sleep 1
          done
          echo "Server did not respond on /api/status within 30s. Logs:"
          cat /tmp/boot.log
          exit 1

  test:
    name: Unit & integration tests
    runs-on: ubuntu-latest

    steps:
      - uses: actions/checkout@v6

      - name: Setup Node.js
        uses: actions/setup-node@v6
        with:
          node-version: 22
          cache: 'npm'

      - name: Install dependencies
        run: npm ci

      - name: Install tmux
        run: |
          if ! command -v tmux >/dev/null; then
            sudo apt-get update -qq
            sudo apt-get install -y tmux
          fi

      - name: Run unit & integration tests
        # Excludes the suites that need chromium, per-machine PNG baselines or a
        # quiet machine — see config/test-suites.ts for the list and the reason
        # behind each entry. Identical to what `npm test` runs locally.
        # Safe in CI: TmuxManager no-ops all shell commands under VITEST (test/setup.ts).
        run: npm run test:ci

      - name: Run xterm-zerolag-input package tests
        # Layers 1-3 of the predictive-echo suites (unit laws, fixture replay,
        # seeded fuzz): deterministic, no browser, no live server. Depends on
        # the ROOT `npm ci` above — workspaces hoist the package's vitest into
        # the root node_modules; do not add a separate install here.
        run: npx vitest run
        working-directory: packages/xterm-zerolag-input

# Note: three suites are excluded from CI, each with its own local runner:
#   npm run test:browser  Playwright + chromium (+ a live server, and a real
#                         codex binary for codex-predictive-echo)
#   npm run test:mobile   the above plus environment-specific PNG baselines
#   npm run test:perf     wall-clock benchmarks; need an otherwise idle machine
# config/test-suites.ts holds the globs; the configs derive from it so the
# exclusions here and those runners cannot drift apart. Everything else runs in
# the `test` job above, which is the same thing `npm test` runs.