pulse/pkg/server/server_test.go

package server

import (
	"context"
	"fmt"
	"net"
	"net/http"
	"net/http/httptest"
	"os"
	"path/filepath"
	"strings"
	"testing"
	"time"

	"github.com/gorilla/websocket"
	"github.com/rcourtman/pulse-go-rewrite/internal/agentexec"
	"github.com/rcourtman/pulse-go-rewrite/internal/config"
	"github.com/rcourtman/pulse-go-rewrite/internal/securityutil"
	"github.com/rcourtman/pulse-go-rewrite/internal/telemetry"
	"github.com/rcourtman/pulse-go-rewrite/internal/updates"
	"github.com/rcourtman/pulse-go-rewrite/pkg/extensions"
	pkglicensing "github.com/rcourtman/pulse-go-rewrite/pkg/licensing"
	"github.com/rcourtman/pulse-go-rewrite/pkg/metrics"
	"github.com/rcourtman/pulse-go-rewrite/pkg/reporting"
)

func TestRunBindsPackagedVersionIdentity(t *testing.T) {
	previous := updates.BuildVersion
	t.Cleanup(func() {
		updates.BuildVersion = previous
	})

	updates.BuildVersion = "stale-image-version"
	bindRuntimeVersion(" 6.2.2-patrol.qualification.5cffa5462 ")

	versionInfo, err := updates.GetCurrentVersion()
	if err != nil {
		t.Fatalf("get current version: %v", err)
	}
	if got, want := versionInfo.Version, "6.2.2-patrol.qualification.5cffa5462"; got != want {
		t.Fatalf("runtime version = %q, want packaged version %q", got, want)
	}
}

func TestAgentIngestHandler(t *testing.T) {
	var innerCalled bool
	inner := http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		innerCalled = true
		w.WriteHeader(http.StatusOK)
	})
	h := agentIngestHandler(inner)

	cases := []struct {
		path      string
		wantInner bool
		wantCode  int
	}{
		{"/api/agents/agent/report", true, http.StatusOK},
		{"/api/agents/docker/report", true, http.StatusOK},
		{"/api/agents/kubernetes/report", true, http.StatusOK},
		{"/api/agents/agent/lookup", true, http.StatusOK},
		{"/api/agents/agent/config", true, http.StatusOK},
		{"/api/agent/ws", true, http.StatusOK},
		{"/api/agent/version", true, http.StatusOK},
		{"/api/server/info", true, http.StatusOK},
		{"/install.sh", true, http.StatusOK},
		{"/install.ps1", true, http.StatusOK},
		{"/download/pulse-agent", true, http.StatusOK},
		// Everything outside the agent-ingest surface must be rejected so the
		// dedicated port never exposes the web UI or the rest of the REST API.
		{"/", false, http.StatusNotFound},
		{"/index.html", false, http.StatusNotFound},
		{"/api/health", false, http.StatusNotFound},
		{"/api/state", false, http.StatusNotFound},
		{"/api/security/status", false, http.StatusNotFound},
		{"/api/agents", false, http.StatusNotFound},
		{"/api/agents/../security/status", false, http.StatusNotFound},
		{"/api/agents//agent/report", false, http.StatusNotFound},
		{"/api/agent/ws/extra", false, http.StatusNotFound},
		{"/install.sh/extra", false, http.StatusNotFound},
	}
	for _, tc := range cases {
		innerCalled = false
		req := httptest.NewRequest(http.MethodPost, tc.path, nil)
		rec := httptest.NewRecorder()
		h.ServeHTTP(rec, req)
		if innerCalled != tc.wantInner {
			t.Errorf("path %q: innerCalled=%v, want %v", tc.path, innerCalled, tc.wantInner)
		}
		if rec.Code != tc.wantCode {
			t.Errorf("path %q: status=%d, want %d", tc.path, rec.Code, tc.wantCode)
		}
	}
}

func TestAgentControlPlaneListenerAdmitsCommandWebSocket(t *testing.T) {
	execServer := agentexec.NewServer(func(token, agentID, hostname string) bool {
		return token == "exec-token" && agentID == "docker-agent" && hostname == "docker-host"
	})
	t.Cleanup(execServer.Shutdown)
	server := httptest.NewServer(agentIngestHandler(http.HandlerFunc(execServer.HandleWebSocket)))
	defer server.Close()

	origin, err := securityutil.HTTPOriginForWebSocketBaseURL(server.URL)
	if err != nil {
		t.Fatalf("origin: %v", err)
	}
	headers := http.Header{}
	headers.Set("Origin", origin)
	wsURL := "ws" + strings.TrimPrefix(server.URL, "http") + "/api/agent/ws"
	conn, _, err := websocket.DefaultDialer.Dial(wsURL, headers)
	if err != nil {
		t.Fatalf("dial dedicated agent command websocket: %v", err)
	}
	defer conn.Close()

	registration, err := agentexec.NewMessage(agentexec.MsgTypeAgentRegister, "", agentexec.AgentRegisterPayload{
		AgentID: "docker-agent", Hostname: "docker-host", Token: "exec-token",
	})
	if err != nil {
		t.Fatalf("registration message: %v", err)
	}
	if err := conn.WriteJSON(registration); err != nil {
		t.Fatalf("write registration: %v", err)
	}
	var response agentexec.Message
	if err := conn.ReadJSON(&response); err != nil {
		t.Fatalf("read registration acknowledgement: %v", err)
	}
	var acknowledged agentexec.RegisteredPayload
	if err := response.DecodePayload(&acknowledged); err != nil {
		t.Fatalf("decode acknowledgement: %v", err)
	}
	if !acknowledged.Success || !execServer.IsAgentConnected("docker-agent") {
		t.Fatalf("dedicated listener did not admit command channel: %+v", acknowledged)
	}
}

func TestBusinessHooks(t *testing.T) {
	called := false
	hook := func(store *metrics.Store) {
		called = true
	}

	SetBusinessHooks(BusinessHooks{
		OnMetricsStoreReady: hook,
	})

	globalHooksMu.Lock()
	defer globalHooksMu.Unlock()

	if globalHooks.OnMetricsStoreReady == nil {
		t.Error("expected OnMetricsStoreReady to be set")
	}

	// Manually trigger to verify it works
	globalHooks.OnMetricsStoreReady(nil)
	if !called {
		t.Error("expected hook to be called")
	}

}

func TestRuntimeIdentityForBusinessHooks(t *testing.T) {
	if got := runtimeIdentityForBusinessHooks(BusinessHooks{}); got.Build != pkglicensing.RuntimeBuildCommunity {
		t.Fatalf("empty hooks runtime build=%q, want community", got.Build)
	}

	got := runtimeIdentityForBusinessHooks(BusinessHooks{
		BindAuditAdminEndpoints: func(defaults extensions.AuditAdminEndpoints, runtime extensions.AuditAdminRuntime) extensions.AuditAdminEndpoints {
			return defaults
		},
	})
	if got.Build != pkglicensing.RuntimeBuildPro {
		t.Fatalf("enterprise hooks runtime build=%q, want pro", got.Build)
	}

	got = runtimeIdentityForBusinessHooks(BusinessHooks{
		ResolveAuditStoreConfig: func(string) extensions.AuditStoreConfig {
			return extensions.AuditStoreConfig{}
		},
	})
	if got.Build != pkglicensing.RuntimeBuildPro {
		t.Fatalf("audit store config hook runtime build=%q, want pro", got.Build)
	}

	got = runtimeIdentityForBusinessHooks(BusinessHooks{
		ResolveMonitoredSystemAdmissionPolicy: func(context.Context, extensions.MonitoredSystemAdmissionInput) extensions.MonitoredSystemAdmissionDecision {
			return extensions.MonitoredSystemAdmissionDecision{}
		},
	})
	if got.Build != pkglicensing.RuntimeBuildPro {
		t.Fatalf("commercial admission hook runtime build=%q, want pro", got.Build)
	}
	got = runtimeIdentityForBusinessHooks(BusinessHooks{
		GenerateBackupHealthReport: func(reporting.BackupHealthData, reporting.ReportFormat) ([]byte, string, error) { return nil, "", nil },
	})
	if got.Build != pkglicensing.RuntimeBuildPro {
		t.Fatalf("private backup renderer hook runtime build=%q, want pro", got.Build)
	}
}

func TestPerformAutoImport_Success(t *testing.T) {
	capture := setCaptureAuditLogger(t)

	// Setup temp directory
	tmpDir := t.TempDir()
	t.Setenv("PULSE_DATA_DIR", tmpDir)

	// Create a persistence instance to generate valid encrypted payload
	sourceDir := t.TempDir()
	sourcePersistence := config.NewConfigPersistence(sourceDir)

	passphrase := "test-pass"
	encryptedData, err := sourcePersistence.ExportConfig(passphrase)
	if err != nil {
		t.Fatalf("failed to generate export data: %v", err)
	}

	t.Setenv("PULSE_INIT_CONFIG_DATA", encryptedData)
	t.Setenv("PULSE_INIT_CONFIG_FILE", "")
	t.Setenv("PULSE_INIT_CONFIG_PASSPHRASE", passphrase)

	// Run PerformAutoImport
	if err := PerformAutoImport(); err != nil {
		t.Fatalf("PerformAutoImport failed: %v", err)
	}

	if len(capture.events) != 1 {
		t.Fatalf("expected 1 audit event, got %d", len(capture.events))
	}

	event := capture.events[0]
	if event.EventType != "config_auto_import" {
		t.Fatalf("unexpected event type: %s", event.EventType)
	}
	if !event.Success {
		t.Fatal("expected success audit event")
	}
	if event.User != "system" {
		t.Fatalf("unexpected audit user: %q", event.User)
	}
	if event.Path != "/startup/auto-import" {
		t.Fatalf("unexpected audit path: %q", event.Path)
	}
	if !strings.Contains(event.Details, "source=env_data") {
		t.Fatalf("expected source in details, got %q", event.Details)
	}

	// Verify persistence file created (nodes.enc is a good indicator)
	_, err = os.Stat(filepath.Join(tmpDir, "nodes.enc"))
	if err != nil {
		if os.IsNotExist(err) {
			t.Error("expected nodes.enc to be created")
		} else {
			t.Error(err)
		}
	}
}

func availableTCPPort(t *testing.T) int {
	t.Helper()

	listener, err := net.Listen("tcp", "127.0.0.1:0")
	if err != nil {
		t.Fatalf("listen: %v", err)
	}
	defer listener.Close()

	return listener.Addr().(*net.TCPAddr).Port
}

func waitForHTTPStatus(t *testing.T, url string, want int) {
	t.Helper()

	client := &http.Client{Timeout: 200 * time.Millisecond}
	deadline := time.Now().Add(5 * time.Second)
	var lastErr error
	var lastStatus int
	for time.Now().Before(deadline) {
		resp, err := client.Get(url)
		if err == nil {
			lastStatus = resp.StatusCode
			resp.Body.Close()
			if lastStatus == want {
				return
			}
		} else {
			lastErr = err
		}
		time.Sleep(50 * time.Millisecond)
	}

	if lastErr != nil {
		t.Fatalf("timed out waiting for %s: last error: %v", url, lastErr)
	}
	t.Fatalf("timed out waiting for %s: last status %d, want %d", url, lastStatus, want)
}

// Minimal test for Server startup context cancellation
func TestServerRun_Shutdown(t *testing.T) {
	// Setup minimal environment
	tmpDir := t.TempDir()
	// Run() reports startup failures over outbound telemetry; a test boot is
	// not an installation, so opt this process out at the config layer too.
	t.Setenv("PULSE_TELEMETRY", "false")
	t.Setenv("PULSE_DATA_DIR", tmpDir)
	t.Setenv("PULSE_CONFIG_PATH", tmpDir)
	t.Setenv("BIND_ADDRESS", "127.0.0.1")
	t.Setenv("FRONTEND_PORT", fmt.Sprintf("%d", availableTCPPort(t)))

	oldMetricsPort := MetricsPort
	MetricsPort = 0
	defer func() { MetricsPort = oldMetricsPort }()

	// Create a minimal config; environment variables own the listener ports for this test.
	configFile := filepath.Join(tmpDir, "config.yaml")
	if err := os.WriteFile(configFile, []byte("bindAddress: 127.0.0.1\nfrontendPort: 0"), 0644); err != nil {
		t.Fatal(err)
	}

	ctx, cancel := context.WithCancel(context.Background())

	// Cancel immediately/shortly to trigger shutdown path
	go func() {
		time.Sleep(100 * time.Millisecond)
		cancel()
	}()

	err := Run(ctx, "test-version")

	if err != nil && err != context.Canceled {
		t.Logf("Run returned: %v", err)
	}
}

func TestServerRunFailsFastWhenFrontendPortIsAlreadyBound(t *testing.T) {
	// Run() reports startup failures over outbound telemetry; a test boot is
	// not an installation, so opt this process out at the config layer too.
	t.Setenv("PULSE_TELEMETRY", "false")
	listener, err := net.Listen("tcp", "127.0.0.1:0")
	if err != nil {
		t.Fatalf("listen: %v", err)
	}
	defer listener.Close()

	tmpDir := t.TempDir()
	t.Setenv("PULSE_DATA_DIR", tmpDir)
	t.Setenv("BIND_ADDRESS", "127.0.0.1")
	t.Setenv("FRONTEND_PORT", fmt.Sprintf("%d", listener.Addr().(*net.TCPAddr).Port))

	oldMetricsPort := MetricsPort
	MetricsPort = 0
	defer func() { MetricsPort = oldMetricsPort }()

	err = Run(context.Background(), "test-version")
	if err == nil || !strings.Contains(err.Error(), "failed to bind UI/API server") {
		t.Fatalf("expected frontend bind failure, got %v", err)
	}
}

func TestServerRunKeepsFrontendWhenMetricsPortConflicts(t *testing.T) {
	// Run() reports startup failures over outbound telemetry; a test boot is
	// not an installation, so opt this process out at the config layer too.
	t.Setenv("PULSE_TELEMETRY", "false")
	port := availableTCPPort(t)

	tmpDir := t.TempDir()
	t.Setenv("PULSE_DATA_DIR", tmpDir)
	t.Setenv("BIND_ADDRESS", "127.0.0.1")
	t.Setenv("FRONTEND_PORT", fmt.Sprintf("%d", port))

	oldMetricsPort := MetricsPort
	MetricsPort = port
	defer func() { MetricsPort = oldMetricsPort }()

	ctx, cancel := context.WithCancel(context.Background())
	defer cancel()

	errCh := make(chan error, 1)
	go func() {
		errCh <- Run(ctx, "test-version")
	}()

	waitForHTTPStatus(t, fmt.Sprintf("http://127.0.0.1:%d/api/health", port), http.StatusOK)

	cancel()
	select {
	case err := <-errCh:
		if err != nil {
			t.Fatalf("Run returned error: %v", err)
		}
	case <-time.After(5 * time.Second):
		t.Fatal("timed out waiting for Run to shut down")
	}
}

func TestServerRun_RejectsWildcardTrustedProxyCIDR(t *testing.T) {
	tmpDir := t.TempDir()
	// Run() reports startup failures over outbound telemetry; a test boot is
	// not an installation, so opt this process out at the config layer too.
	t.Setenv("PULSE_TELEMETRY", "false")
	t.Setenv("PULSE_DATA_DIR", tmpDir)
	t.Setenv("PULSE_CONFIG_PATH", tmpDir)
	t.Setenv("PULSE_TRUSTED_PROXY_CIDRS", "0.0.0.0/0")

	configFile := filepath.Join(tmpDir, "config.yaml")
	if err := os.WriteFile(configFile, []byte("bindAddress: 127.0.0.1\nfrontendPort: 0"), 0644); err != nil {
		t.Fatal(err)
	}

	err := Run(context.Background(), "test-version")
	if err == nil || !strings.Contains(err.Error(), "wildcard trust range") {
		t.Fatalf("expected wildcard trusted proxy configuration to be rejected, got %v", err)
	}
}

// Node connection test counts must reach the telemetry snapshot, and counts
// older than the reporting window must not, otherwise the add-node stall this
// counter exists to measure cannot be read from the fleet.
func TestApplyNodeTestTelemetrySnapshotReadsTallyWithinWindow(t *testing.T) {
	dir := t.TempDir()
	persistence := config.NewConfigPersistence(dir)
	now := time.Now().UTC()

	if err := persistence.RecordNodeTestOutcome(true, now.AddDate(0, 0, -40)); err != nil {
		t.Fatalf("record stale outcome: %v", err)
	}
	if err := persistence.RecordNodeTestOutcome(true, now); err != nil {
		t.Fatalf("record failure: %v", err)
	}
	if err := persistence.RecordNodeTestOutcome(false, now); err != nil {
		t.Fatalf("record success: %v", err)
	}

	var snap telemetry.Snapshot
	applyNodeTestTelemetrySnapshot(&snap, persistence, now)

	if snap.NodeTestAttempts30d != 2 {
		t.Fatalf("NodeTestAttempts30d = %d, want 2", snap.NodeTestAttempts30d)
	}
	if snap.NodeTestFailures30d != 1 {
		t.Fatalf("NodeTestFailures30d = %d, want 1", snap.NodeTestFailures30d)
	}
}

// A missing tally is the normal state on an install that has never opened the
// add-node dialog, and must report zero rather than fail the snapshot.
func TestApplyNodeTestTelemetrySnapshotToleratesMissingTally(t *testing.T) {
	var snap telemetry.Snapshot
	applyNodeTestTelemetrySnapshot(&snap, config.NewConfigPersistence(t.TempDir()), time.Now().UTC())
	if snap.NodeTestAttempts30d != 0 || snap.NodeTestFailures30d != 0 {
		t.Fatalf("counts = %d/%d, want 0/0", snap.NodeTestAttempts30d, snap.NodeTestFailures30d)
	}
}