feat: add security response headers middleware (closes #98 )

Add SecurityHeaders() to internal/middleware and register it in the global middleware stack so every response - dashboard, embedded static assets, healthchecks, JSON API, and metrics - carries the six response headers required by REPO_POLICIES.md before tagging 1.0: Strict-Transport-Security: max-age=31536000; includeSubDomains Content-Security-Policy: default-src 'self'; script-src 'none'; style-src 'self'; img-src 'self'; font-src 'none'; connect-src 'none'; object-src 'none'; base-uri 'none'; form-action 'none'; frame-ancestors 'none' X-Frame-Options: DENY X-Content-Type-Options: nosniff Referrer-Policy: no-referrer Permissions-Policy: unused browser features denied The dashboard template ships no JavaScript, no inline styles, no inline event handlers and no images, and its only subresource is the embedded stylesheet at /s/css/tailwind.min.css, so the policy needs neither unsafe-inline nor unsafe-eval. frame-ancestors 'none' is the primary anti-framing control with X-Frame-Options as the legacy fallback. HSTS is emitted unconditionally rather than gated on r.TLS, because the service runs behind a TLS-terminating proxy and the browser must still enforce HTTPS end to end. The headers are set before the request reaches the next handler, so they are present on error responses too, including recovered panics and request timeouts. Tests cover each header's exact value, the CSP's required and forbidden directives, presence on a 500 response, and a render of the real dashboard through the middleware confirming the page still references its stylesheet.
2026-09-21 07:59:18 +00:00
8 changed files with 9 additions and 439 deletions
@@ -41,33 +41,15 @@ FROM alpine@sha256:c3f8e73fdb79deaebaa2037150150191b9dcbfba68b4a46d70103204c53f4
 RUN apk add --no-cache ca-certificates tzdata
-COPY --from=builder /src/bin/dnswatcher /usr/local/bin/dnswatcher
+WORKDIR /app
-# Run as an unprivileged user that owns the data directory. A fresh named
+COPY --from=builder /src/bin/dnswatcher /app/dnswatcher
-# volume inherits this ownership; a bind-mounted host directory must be
+
-# owned by uid 10001 (see "Running under upaas" in README.md), or startup
+# Create data directory
-# fails.
+RUN mkdir -p /var/lib/dnswatcher
 RUN addgroup -S -g 10001 dnswatcher \
    && adduser -S -G dnswatcher -u 10001 dnswatcher \
    && mkdir -p /var/lib/dnswatcher \
    && chown dnswatcher:dnswatcher /var/lib/dnswatcher
 ENV DNSWATCHER_DATA_DIR=/var/lib/dnswatcher
 # Config loading also reads a `.env` file and a file named `dnswatcher`
 # (any config extension, or none) from the working directory. `/` holds
 # neither, so every setting comes from the environment. Do not make the
 # data directory, or the binary's directory, the working directory.
 WORKDIR /
 USER dnswatcher
 EXPOSE 8080
-# busybox wget (already in alpine) probes the health endpoint every 10
+ENTRYPOINT ["/app/dnswatcher"]
 # seconds, so the container is healthy well before upaas reads its health
 # 60 seconds after a deploy and fails the deploy unless it is healthy.
 HEALTHCHECK --interval=10s --timeout=5s --start-period=10s --retries=3 \
    CMD wget -q -O /dev/null "http://127.0.0.1:${PORT:-8080}/.well-known/healthcheck" || exit 1
 ENTRYPOINT ["/usr/local/bin/dnswatcher"]
@@ -508,57 +508,11 @@ docker run -d \
 ---
 ## Running under upaas
 [upaas](https://git.eeqj.de/sneak/upaas) builds the image from this
 repository's `Dockerfile` and runs it. The app needs:
 - **Branch:** `prod`. `prod` is cut from `main`, and merging a `main` to
  `prod` pull request is a deploy.
 - **Volume:** one host directory mounted at `/var/lib/dnswatcher`, where
  the state file lives. upaas bind-mounts the host path it is given and
  does not create it. The container runs as uid 10001 and does not start
  unless it can write there. Create the directory before the first
  deploy:
  ```sh
  mkdir -p /path/to/data
  chown 10001:10001 /path/to/data
  chmod 700 /path/to/data
  ```
 - **Network and port:** the dashboard is unauthenticated and shows every
  watched name and recent alert, and upaas publishes every mapped port on
  all interfaces of the host
  ([upaas issue 113](https://git.eeqj.de/sneak/upaas/issues/113)). Add a
  port mapping to container port `8080` only if the dashboard should be
  public. Otherwise add none: set the app's Docker network in upaas to
  your reverse proxy's Docker network, and the proxy reaches the app at
  `upaas-` followed by the app name, port `8080`.
 - **Required environment:** `DNSWATCHER_TARGETS`, a comma-separated list
  of the domains and hostnames to watch. dnswatcher refuses to start
  without it.
 - **Recommended environment:** at least one notification endpoint
  (`DNSWATCHER_SLACK_WEBHOOK`, `DNSWATCHER_MATTERMOST_WEBHOOK`,
  `DNSWATCHER_NTFY_TOPIC`); without one, changes show only on the
  dashboard. `DNSWATCHER_METRICS_USERNAME` and
  `DNSWATCHER_METRICS_PASSWORD` serve `/metrics` behind basic auth.
 - **Leave unset:** `DNSWATCHER_DATA_DIR`, which the image sets to
  `/var/lib/dnswatcher`, and `PORT`, which defaults to `8080`. Every
  setting comes from the environment; the image holds no config file.
 - **Health check:** the image's own, which requests
  `/.well-known/healthcheck` every 10 seconds. upaas reads the
  container's health 60 seconds after a deploy and marks the deploy
  failed unless it is `healthy`.
 ---
 ## Monitoring Lifecycle
-1. **Startup**: Check that the data directory can be written, and exit
+1. **Startup**: Load state from disk. If no state file exists, start
-   with an error naming it if not. Load state from disk. If no state
+   with empty state (first check will establish baseline without
-   file exists, start with empty state (first check will establish
+   triggering change notifications).
   baseline without triggering change notifications).
 2. **Initial check**: Immediately perform all DNS, port, and TLS checks
   on startup.
 3. **Periodic checks** (DNS always runs first):
@@ -23,11 +23,6 @@ Rationale, Design, TODO, License, Author) if any are still missing.
 # Completed Steps
 - 2026-09-28: upaas deploy readiness — runtime image runs as unprivileged
  `dnswatcher`, Docker `HEALTHCHECK`, startup fails when the data directory is
  not writable, README "Running under upaas" (closes #147).
 - 2026-09-21: added behavioural tests for `internal/globals`,
  `internal/healthcheck`, and `internal/logger` (closes #110).
 - 2026-09-21: `go mod tidy` dropped the redundant `golang.org/x/sync`
  `// indirect` line so `script/bootstrap` leaves a clean tree (#132)
 - 2026-08-10: comment-only corrections to `script/bootstrap`,
@@ -1,50 +0,0 @@
 package globals_test
 import (
 	"testing"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	"sneak.berlin/go/dnswatcher/internal/globals"
 )
 // TestGlobals exercises the package-level version and appname
 // variables through their setters and read-back via New. These are
 // shared package state, so the test mutates a global and must run
 // sequentially; it cannot use t.Parallel().
 //
 //nolint:paralleltest // mutates shared package-level globals, must run sequentially
 func TestGlobals(t *testing.T) {
 	versions := []string{"v1.2.3", "dev", "", "v1.2.3-4-gabcdef"}
 	for _, want := range versions {
 		globals.SetVersion(want)
 		g, err := globals.New(nil)
 		require.NoError(t, err)
 		assert.Equal(t, want, g.Version,
 			"New must surface the version set by SetVersion")
 	}
 	names := []string{"dnswatcher", "other", ""}
 	for _, want := range names {
 		globals.SetAppname(want)
 		g, err := globals.New(nil)
 		require.NoError(t, err)
 		assert.Equal(t, want, g.Appname,
 			"New must surface the appname set by SetAppname")
 	}
 	// New returns a snapshot: a later SetVersion must not mutate a
 	// Globals handed out earlier.
 	globals.SetVersion("first")
 	g, err := globals.New(nil)
 	require.NoError(t, err)
 	globals.SetVersion("second")
 	assert.Equal(t, "first", g.Version,
 		"a Globals returned by New must not change when the "+
 			"package variable is set again")
 }
@@ -1,134 +0,0 @@
 package healthcheck_test
 import (
 	"context"
 	"encoding/json"
 	"testing"
 	"time"
 	"go.uber.org/fx"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	"sneak.berlin/go/dnswatcher/internal/config"
 	"sneak.berlin/go/dnswatcher/internal/globals"
 	"sneak.berlin/go/dnswatcher/internal/healthcheck"
 	"sneak.berlin/go/dnswatcher/internal/logger"
 )
 // recordingLifecycle is a minimal fx.Lifecycle that records the hooks
 // appended to it, so healthcheck.New can be exercised through its real
 // constructor without standing up a whole fx application.
 type recordingLifecycle struct {
 	hooks []fx.Hook
 }
 func (l *recordingLifecycle) Append(hook fx.Hook) {
 	l.hooks = append(l.hooks, hook)
 }
 // newHealthcheck builds a Healthcheck through the real constructor and
 // runs the registered OnStart hook so StartupTime is set the same way
 // the fx lifecycle would set it.
 func newHealthcheck(
 	t *testing.T,
 	maintenance bool,
 	version string,
 ) *healthcheck.Healthcheck {
 	t.Helper()
 	g := &globals.Globals{Appname: "dnswatcher", Version: version}
 	log, err := logger.New(nil, logger.Params{Globals: g})
 	require.NoError(t, err)
 	lifecycle := &recordingLifecycle{}
 	hc, err := healthcheck.New(lifecycle, healthcheck.Params{
 		Globals: g,
 		Config:  &config.Config{MaintenanceMode: maintenance},
 		Logger:  log,
 	})
 	require.NoError(t, err)
 	require.Len(t, lifecycle.hooks, 1,
 		"New must register exactly one lifecycle hook")
 	require.NotNil(t, lifecycle.hooks[0].OnStart)
 	require.NoError(t, lifecycle.hooks[0].OnStart(context.Background()))
 	return hc
 }
 func TestCheckStatusAndPayloadShape(t *testing.T) {
 	t.Parallel()
 	hc := newHealthcheck(t, false, "v9.9.9")
 	resp := hc.Check()
 	assert.Equal(t, "ok", resp.Status)
 	// The JSON shape and field names are part of the contract for the
 	// /health and /.well-known/healthcheck routes, so assert on the
 	// exact set of keys the response marshals to.
 	raw, err := json.Marshal(resp)
 	require.NoError(t, err)
 	var fields map[string]json.RawMessage
 	require.NoError(t, json.Unmarshal(raw, &fields))
 	wantKeys := []string{
 		"status",
 		"now",
 		"uptimeSeconds",
 		"uptimeHuman",
 		"version",
 		"appname",
 		"maintenanceMode",
 	}
 	assert.Len(t, fields, len(wantKeys),
 		"response must marshal to exactly the documented fields")
 	for _, key := range wantKeys {
 		assert.Contains(t, fields, key, "missing JSON field %q", key)
 	}
 	// The Now field is documented as RFC3339Nano; a change to the
 	// format constant should turn this red.
 	_, err = time.Parse(time.RFC3339Nano, resp.Now)
 	assert.NoError(t, err, "Now must be RFC3339Nano")
 }
 func TestCheckMaintenanceModeReflectsConfig(t *testing.T) {
 	t.Parallel()
 	tests := []struct {
 		name        string
 		maintenance bool
 	}{
 		{"maintenance off", false},
 		{"maintenance on", true},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			t.Parallel()
 			hc := newHealthcheck(t, tt.maintenance, "test")
 			resp := hc.Check()
 			assert.Equal(t, tt.maintenance, resp.Maintenance,
 				"maintenanceMode must mirror Config.MaintenanceMode")
 		})
 	}
 }
 func TestCheckSurfacesVersionAndAppname(t *testing.T) {
 	t.Parallel()
 	hc := newHealthcheck(t, false, "surfaced-version-123")
 	resp := hc.Check()
 	assert.Equal(t, "surfaced-version-123", resp.Version,
 		"version from globals must appear in the payload")
 	assert.Equal(t, "dnswatcher", resp.Appname)
 }
@@ -1,66 +0,0 @@
 package logger_test
 import (
 	"context"
 	"log/slog"
 	"testing"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	"sneak.berlin/go/dnswatcher/internal/globals"
 	"sneak.berlin/go/dnswatcher/internal/logger"
 )
 func newTestLogger(t *testing.T) *logger.Logger {
 	t.Helper()
 	g := &globals.Globals{Appname: "dnswatcher", Version: "test"}
 	l, err := logger.New(nil, logger.Params{Globals: g})
 	require.NoError(t, err)
 	return l
 }
 // TestNewReturnsUsableLogger checks that the constructor yields a
 // working *slog.Logger.
 func TestNewReturnsUsableLogger(t *testing.T) {
 	t.Parallel()
 	l := newTestLogger(t)
 	require.NotNil(t, l.Get(), "Get must return a non-nil logger")
 }
 // TestDefaultLevelExcludesDebug verifies the default configuration
 // logs at info: debug records are suppressed, info records pass.
 func TestDefaultLevelExcludesDebug(t *testing.T) {
 	t.Parallel()
 	log := newTestLogger(t).Get()
 	ctx := context.Background()
 	assert.False(t, log.Enabled(ctx, slog.LevelDebug),
 		"debug must be suppressed at the default level")
 	assert.True(t, log.Enabled(ctx, slog.LevelInfo),
 		"info must be enabled at the default level")
 }
 // TestEnableDebugLoggingChangesLevel verifies the debug and non-debug
 // configurations differ as intended: enabling debug makes debug
 // records pass where they previously did not.
 func TestEnableDebugLoggingChangesLevel(t *testing.T) {
 	t.Parallel()
 	l := newTestLogger(t)
 	log := l.Get()
 	ctx := context.Background()
 	require.False(t, log.Enabled(ctx, slog.LevelDebug),
 		"debug must start disabled")
 	l.EnableDebugLogging()
 	assert.True(t, log.Enabled(ctx, slog.LevelDebug),
 		"debug must be enabled after EnableDebugLogging")
 }
@@ -148,11 +148,6 @@ func New(
 	lifecycle.Append(fx.Hook{
 		OnStart: func(_ context.Context) error {
 			err := state.checkDataDirWritable()
 			if err != nil {
 				return err
 			}
 			return state.Load()
 		},
 		OnStop: func(_ context.Context) error {
@@ -350,27 +345,3 @@ func (s *State) GetCertificateState(
 	return cs, ok
 }
 // checkDataDirWritable creates the data directory if needed, then writes
 // and removes the temp file that Save uses. It runs at startup so that an
 // unwritable directory stops the process, instead of the process running
 // with every save failing and only logged.
 func (s *State) checkDataDirWritable() error {
 	dir := s.config.DataDir
 	tmpPath := s.config.StatePath() + ".tmp"
 	err := os.MkdirAll(dir, dirPermissions)
 	if err == nil {
 		err = os.WriteFile(tmpPath, nil, filePermissions)
 	}
 	if err == nil {
 		err = os.Remove(tmpPath)
 	}
 	if err != nil {
 		return fmt.Errorf("data directory %s is not writable: %w", dir, err)
 	}
 	return nil
 }
@@ -4,16 +4,10 @@ import (
 	"encoding/json"
 	"os"
 	"path/filepath"
 	"strings"
 	"sync"
 	"testing"
 	"time"
 	"go.uber.org/fx/fxtest"
 	"sneak.berlin/go/dnswatcher/internal/config"
 	"sneak.berlin/go/dnswatcher/internal/globals"
 	"sneak.berlin/go/dnswatcher/internal/logger"
 	"sneak.berlin/go/dnswatcher/internal/state"
 )
@@ -499,82 +493,6 @@ func TestSaveWritePermissionError(t *testing.T) {
 	}
 }
 // startState builds a State through the real constructor and runs its
 // startup hook against dataDir, returning the startup error.
 func startState(t *testing.T, dataDir string) error {
 	t.Helper()
 	g, err := globals.New(nil)
 	if err != nil {
 		t.Fatalf("globals.New: %v", err)
 	}
 	log, err := logger.New(nil, logger.Params{Globals: g})
 	if err != nil {
 		t.Fatalf("logger.New: %v", err)
 	}
 	lifecycle := fxtest.NewLifecycle(t)
 	_, err = state.New(lifecycle, state.Params{
 		Logger: log,
 		Config: &config.Config{DataDir: dataDir},
 	})
 	if err != nil {
 		t.Fatalf("state.New: %v", err)
 	}
 	return lifecycle.Start(t.Context())
 }
 // TestStartupFailsWhenDataDirNotWritable verifies that startup stops
 // with an error naming the data directory when it cannot be written.
 // The directory's parent is a regular file, which also fails as root.
 func TestStartupFailsWhenDataDirNotWritable(t *testing.T) {
 	t.Parallel()
 	parent := filepath.Join(t.TempDir(), "file")
 	err := os.WriteFile(parent, nil, 0o600)
 	if err != nil {
 		t.Fatalf("writing file: %v", err)
 	}
 	dataDir := filepath.Join(parent, "data")
 	err = startState(t, dataDir)
 	if err == nil {
 		t.Fatal("startup should fail when the data directory is not writable")
 	}
 	want := "data directory " + dataDir + " is not writable"
 	if !strings.Contains(err.Error(), want) {
 		t.Errorf("startup error %q does not contain %q", err, want)
 	}
 }
 // TestStartupCreatesDataDir verifies that startup creates a missing
 // data directory and leaves nothing behind in it.
 func TestStartupCreatesDataDir(t *testing.T) {
 	t.Parallel()
 	dataDir := filepath.Join(t.TempDir(), "data")
 	err := startState(t, dataDir)
 	if err != nil {
 		t.Fatalf("startup error: %v", err)
 	}
 	entries, err := os.ReadDir(dataDir)
 	if err != nil {
 		t.Fatalf("reading data directory: %v", err)
 	}
 	if len(entries) != 0 {
 		t.Errorf("startup left %d entries in the data directory", len(entries))
 	}
 }
 // TestPortStateUnmarshalJSON_NewFormat verifies deserialization of the
 // current multi-hostname format.
 func TestPortStateUnmarshalJSON_NewFormat(t *testing.T) {