12.3Test Runner Script

run-tests.sh

#!/bin/bash
set -euo pipefail

TEST_GROUP="${1:-all}"
BASE_URL="${TEST_BASE_URL:-http://localhost:3000}"
FAILURES_DIR="failures"
SCREENSHOTS_DIR="screenshots"

mkdir -p "$FAILURES_DIR" "$SCREENSHOTS_DIR"

PASSED=0
FAILED=0
TOTAL=0

# pw: run a CLI command inside this test's named session
pw() { playwright-cli -s="$CURRENT_TEST" "$@"; }
export -f pw
export BASE_URL

run_test() {
  local test_name="$1"
  local test_script="$2"
  TOTAL=$((TOTAL + 1))
  export CURRENT_TEST="$test_name"

  echo -n "  $test_name ... "

  # Execute test in its own session, capture output
  if output=$(bash -c "$test_script" 2>&1); then
    echo "PASS"
    PASSED=$((PASSED + 1))
  else
    echo "FAIL"
    FAILED=$((FAILED + 1))

    # Capture failure artifacts
    mkdir -p "$FAILURES_DIR/$test_name"
    echo "$output" > "$FAILURES_DIR/$test_name/output.txt"
    pw screenshot 2>/dev/null || true              # PNG lands in .playwright-cli/
    pw snapshot 2>/dev/null || true                # YAML a11y state
    pw eval "location.href" > "$FAILURES_DIR/$test_name/current_url.txt" 2>/dev/null || true
    cp -r .playwright-cli/ "$FAILURES_DIR/$test_name/workspace/" 2>/dev/null || true
  fi

  # Fresh session per test: always tear down
  pw close 2>/dev/null || true
}

echo "Running $TEST_GROUP tests against $BASE_URL"
echo "=========================================="

# Load and run tests for the group
case $TEST_GROUP in
  auth)
    run_test "login_valid" '
      pw open "$BASE_URL/login" &&
      pw snapshot &&
      pw fill e3 "test@example.com" &&
      pw fill e4 "password123" &&
      pw click e5 &&
      pw eval "document.querySelector(\"h1\").textContent" | grep -q "Dashboard"
    '

    run_test "login_invalid" '
      pw open "$BASE_URL/login" &&
      pw snapshot &&
      pw fill e3 "wrong@example.com" &&
      pw fill e4 "wrongpass" &&
      pw click e5 &&
      pw eval "document.querySelector(\".error\").textContent" | grep -qi "invalid"
    '
    ;;

  dashboard)
    run_test "dashboard_loads" '
      pw open "$BASE_URL/dashboard" &&
      pw eval "document.querySelector(\".metric-count\").textContent" | grep -qE "[0-9]+"
    '
    ;;

  *)
    echo "Unknown test group: $TEST_GROUP"
    exit 1
    ;;
esac

echo ""
echo "=========================================="
echo "Results: $PASSED passed, $FAILED failed, $TOTAL total"

# Exit with failure if any tests failed
[ "$FAILED" -eq 0 ]

A candid note on this script: hard-coding refs (e3, e4) in a shell script works only for pages whose snapshot layout is stable. That's fine for smoke tests. The moment refs drift, you want either the agent in the loop (it re-snapshots and re-resolves) or promoted, generated .spec.ts tests from the generator agent — scripted ref sequences are the least self-healing artifact in this stack. Use them deliberately.