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.

Dockerfile

@@ -2,7 +2,6 @@
 # The linter is invoked directly rather than through `make lint`: that
 # target shells out to `docker build -f Dockerfile.lint`, and there is
 # no docker daemon inside a docker build.
-# script/cibuild and script/docker name this stage in --no-cache-filter.
 # golangci/golangci-lint:v2.12.2 (Debian-based), 2026-08-10
 FROM golangci/golangci-lint:v2.12.2@sha256:5cceeef04e53efe1470638d4b4b4f5ceefd574955ab3941b2d9a68a8c9ad5240 AS lint
 
@@ -16,7 +15,6 @@ RUN make fmt-check
 RUN golangci-lint run --config .golangci.yml ./...
 
 # Build stage
-# script/cibuild and script/docker name this stage in --no-cache-filter.
 # golang 1.25-alpine, 2026-02-28
 FROM golang@sha256:f6751d823c26342f9506c03797d2527668d095b0a15f1862cddb4d927a7a4ced AS builder
 
@@ -43,33 +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
-# volume inherits this ownership; a bind-mounted host directory must be
-# owned by uid 10001 (see "Running under upaas" in README.md), or startup
-# fails.
-RUN addgroup -S -g 10001 dnswatcher \
-    && adduser -S -G dnswatcher -u 10001 dnswatcher \
-    && mkdir -p /var/lib/dnswatcher \
-    && chown dnswatcher:dnswatcher /var/lib/dnswatcher
+COPY --from=builder /src/bin/dnswatcher /app/dnswatcher
+
+# Create data directory
+RUN mkdir -p /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
-# 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"]
+ENTRYPOINT ["/app/dnswatcher"]

README.md

@@ -61,10 +61,6 @@ rejected.
   record types: A, AAAA, CNAME, MX, TXT, SRV, CAA, NS.
 - Stores results **per nameserver**. The state for a hostname is not a
   merged view — it is a map from nameserver to record set.
-- DNS names inside record values (CNAME, MX, SRV and NS targets) are
-  stored in lower case, because names are case-insensitive and
-  nameservers may answer in any letter case. TXT and CAA values keep
-  their letter case; they are not lower-cased.
 - Any observable change in any nameserver's response triggers a
   notification. This includes:
   - **Record change**: A nameserver returns different records than it
@@ -74,15 +70,8 @@ rejected.
     This is distinct from "responded with no records."
   - **NS recovery**: A previously-unreachable nameserver starts
     responding again.
-  - **Inconsistency detected**: Two nameservers return different record
-    sets for the same hostname and did not already differ on the previous
-    check. Every pair of nameservers is compared. The alert is sent once
-    for each such pair, on the check where they start to disagree, and not
-    again while they keep disagreeing, including after a restart. A
-    nameserver that was not in the previous check (newly added, or back
-    after dropping out) and answers differently is reported on the check
-    where it appears. If a pair agrees again and later disagrees, the
-    alert is sent again.
+  - **Inconsistency detected**: Two nameservers that previously agreed
+    now return different record sets for the same hostname.
 
 ### TCP Port Monitoring
 
@@ -278,8 +267,6 @@ internal/
   tlscheck/tlscheck.go        TLS certificate inspector
   notify/notify.go             Notification service (Slack, Mattermost, ntfy)
   watcher/watcher.go           Main monitoring orchestrator and scheduler
-  livedns/livedns.go           Retry and concurrency limit for tests
-                               against live DNS (imported only by tests)
 ```
 
 ### Design Principles
@@ -478,13 +465,9 @@ them. We provide:
 - `script/fmt` — format all code (gofmt -s, goimports)
 - `script/fmt-check` — check formatting (read-only)
 - `script/check` — run test, lint, and fmt-check
-- `script/docker` — build the Docker image tagged via `script/projectname`, with
-  `--no-cache-filter=lint,builder` so the lint stage and the builder stage,
-  which runs the tests, run on every invocation
-- `script/cibuild` — CI entrypoint: `docker build` with
-  `--no-cache-filter=lint,builder`, so the lint stage and the builder stage,
-  which runs the tests, run on every invocation, because a cached build lints
-  nothing and queries no DNS
+- `script/docker` — build the Docker image tagged via
+  `script/projectname`
+- `script/cibuild` — CI entrypoint: plain `docker build .`
 - `script/precommit` — run by the git pre-commit hook; `go mod tidy`
   guard, then `script/check`
 - `script/install-precommit` — install the git pre-commit hook
@@ -525,57 +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
-   with an error naming it if not. Load state from disk. If no state
-   file exists, start with empty state (first check will establish
-   baseline without triggering change notifications).
+1. **Startup**: Load state from disk. If no state file exists, start
+   with empty state (first check will establish 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):

TESTING.md

@@ -2,12 +2,8 @@
 
 ## DNS Resolution Tests
 
-DNS is never mocked in this project, not in tests and not anywhere
-else; see the README section "No DNS mocking. Ever." Every test that
-looks something up in DNS **MUST** query live DNS servers, never a
-stand-in. Logic that works on record data, such as comparing or
-formatting records, may be tested on that data directly with no
-lookup.
+All resolver tests **MUST** use live queries against real DNS servers.
+No mocking of the DNS client layer is permitted.
 
 ### Rationale
 
@@ -25,18 +21,14 @@ real servers ensures the resolver works correctly in production.
 - Query timeout is calibrated to 3× maximum antipodal RTT (~300ms)
   plus processing margin
 - Root server fan-out is limited to reduce parallel query load
-- Live lookups that expect an answer go through `internal/livedns`,
-  which limits how many run at once in a test binary and retries a
-  lookup that got none
 - Flaky failures from transient network issues are acceptable and
   should be investigated as potential resolver bugs, not papered over
   with mocks or skip flags
 
 ### What NOT to do
 
-- **Do not mock, fake or stub DNS** anywhere: no stand-in `DNSClient`,
-  no stand-in for the watcher's `DNSResolver`, no fake DNS server, no
-  canned responses
+- **Do not mock `DNSClient`** for resolver tests (the mock constructor
+  exists for unit-testing other packages that consume the resolver)
 - **Do not add `-short` flags** to skip slow tests
 - **Do not increase `-timeout`** to hide hanging queries
 - **Do not remove `-count=1` from `script/test`** — Go's test cache

TODO.md

@@ -10,7 +10,11 @@
 
 # Status
 
-pre-1.0. No git tags.
+pre-1.0. No git tags. Core resolver work in flight on feature/resolver
+(dirty: internal/resolver/resolver_test.go). Local checkout has diverged
+from origin: origin/main is 8 commits ahead (watcher orchestrator,
+unified TARGETS) and origin/feature/resolver already contains the full
+iterative resolver implementation with hermetic mocked tests.
 
 # Next Step
 
@@ -19,32 +23,6 @@ Rationale, Design, TODO, License, Author) if any are still missing.
 
 # Completed Steps
 
-- 2026-09-29: nothing stands in for DNS any more. Watcher tests that look
-  something up in DNS use the real resolver against live DNS servers and test
-  record and nameserver changes by preparing the saved state a check starts
-  from; the resolver timeout test queries an address that never answers, and
-  `NewFromLoggerWithClient`, used only by its stand-in client, is gone. The
-  live-DNS retry and concurrency limit moved to `internal/livedns`, which both
-  test packages use. `TESTING.md` states the README's rule (closes #159).
-- 2026-09-28: the inconsistency alert is sent once, on the check where two
-  nameservers start to disagree or where a nameserver that disagrees first
-  appears, instead of on every check while they disagree, and not again after
-  a restart. Every pair of nameservers is compared, not only neighbours in
-  sorted order of name (closes #158).
-- 2026-09-28: DNS names in record values (CNAME, MX, SRV and NS targets) are
-  lower-cased, so nameservers that answer in different letter case no longer
-  count as inconsistent or as a record change (closes #157).
-- 2026-09-28: `script/cibuild` and `script/docker` now pass
-  `--no-cache-filter=lint,builder` so lint and tests run every build (closes
-  #115).
-- 2026-09-28: the server timeout test now drives `Run` and checks the
-  `http.Server` it serves carries the timeouts; corrected the `ReadTimeout`
-  note in that test (closes #120).
-- 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`,
@@ -264,5 +242,6 @@ Infrastructure notes (from untracked TODO.md):
 - Module path sneak.berlin/go/dnswatcher differs from the git.eeqj.de
   remote intentionally; do not "fix" it
 - Dependencies: github.com/miekg/dns, golang.org/x/net/publicsuffix
-- DNS is never mocked; tests that look something up in DNS query live DNS
-  servers (README, "No DNS mocking. Ever.")
+- Resolver tests originally used live DNS against *.dns.sneak.cloud
+  (required records documented in the test file header); origin now has
+  mocked hermetic tests, keep them hermetic

internal/globals/globals_test.go

@@ -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")
-}

internal/healthcheck/healthcheck_test.go

@@ -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)
-}

internal/livedns/livedns.go

@@ -1,121 +0,0 @@
-// Package livedns runs the live DNS operations of tests. Tests that
-// look something up in DNS query live DNS servers, never a stand-in —
-// see TESTING.md. Nothing here mocks, fakes, stubs, records or replays
-// DNS, and nothing here skips a test: it only changes *how* the live
-// queries are issued, so that a single dropped UDP packet or one slow
-// authoritative server does not turn correct code into a red build.
-//
-// Two mechanisms:
-//
-//  1. Bounded concurrency. Tests run in parallel and the build hosts
-//     have many cores, so without a limit every test starts its own
-//     iterative resolution at the same instant and they all hit the
-//     first root server within a few milliseconds of each other. Root
-//     servers rate-limit that, which shows up as a different arbitrary
-//     subset of tests failing on each run. Run caps how many live
-//     operations are in flight at once in one test binary.
-//
-//  2. Retry with exponential backoff. Each live operation gets several
-//     attempts with its own timeout. An attempt is retried when it
-//     obtained nothing to check, never because of what the test
-//     asserts about the result, so a wrong result still fails on the
-//     first attempt. A fault in the code under test that leaves
-//     nothing to check looks the same as live DNS not answering, and
-//     fails only after the last attempt.
-package livedns
-
-import (
-	"context"
-	"errors"
-	"testing"
-	"time"
-)
-
-const (
-	// attempts is how many times a live DNS operation is attempted
-	// before the test fails.
-	attempts = 3
-
-	// AttemptTimeout bounds one attempt. Worst case for an operation
-	// is attempts * AttemptTimeout plus the backoff — about 26
-	// seconds, well inside the 90-second `go test -timeout` backstop
-	// even when several operations exhaust their attempts.
-	AttemptTimeout = 8 * time.Second
-
-	// backoffBase is the delay after the first failed attempt; it is
-	// multiplied by backoffFactor each time.
-	backoffBase = 500 * time.Millisecond
-
-	// backoffFactor is the exponential backoff multiplier.
-	backoffFactor = 2
-
-	// Concurrency caps how many live operations may be in flight
-	// across one test binary at once.
-	Concurrency = 6
-)
-
-// gate bounds concurrent live operations. It has to be package scoped:
-// the whole point is that it is shared by every parallel test in the
-// test binary.
-//
-//nolint:gochecknoglobals // package-wide live query rate limit
-var gate = make(chan struct{}, Concurrency)
-
-// ErrNoAnswer reports that a live operation produced no usable answer,
-// which is retried rather than asserted on.
-var ErrNoAnswer = errors.New("no answer from live DNS")
-
-// Run executes one attempt of a live operation, holding a slot in gate
-// for its duration and bounding it with its own timeout.
-func Run(op func(ctx context.Context) error) error {
-	gate <- struct{}{}
-	defer func() { <-gate }()
-
-	ctx, cancel := context.WithTimeout(
-		context.Background(), AttemptTimeout,
-	)
-	defer cancel()
-
-	return op(ctx)
-}
-
-// Retry runs op until it reports success, retrying failures with
-// exponential backoff, and fails the test if every attempt fails. op
-// returns an error only for a failure to obtain an answer — never for
-// an answer the test disagrees with, which belongs in an assertion so
-// that it fails immediately. op stores whatever it obtained where its
-// caller can find it.
-func Retry(
-	t *testing.T,
-	what string,
-	op func(ctx context.Context) error,
-) {
-	t.Helper()
-
-	var last error
-
-	backoff := backoffBase
-
-	for attempt := range attempts {
-		if attempt > 0 {
-			t.Logf(
-				"%s: attempt %d of %d failed (%v), "+
-					"retrying in %s",
-				what, attempt, attempts, last, backoff,
-			)
-			time.Sleep(backoff)
-
-			backoff *= backoffFactor
-		}
-
-		last = Run(op)
-		if last == nil {
-			return
-		}
-	}
-
-	t.Fatalf(
-		"%s: all %d live attempts failed: %v",
-		what, attempts, last,
-	)
-}

internal/livedns/livedns_test.go

@@ -1,103 +0,0 @@
-package livedns_test
-
-import (
-	"context"
-	"sync"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/assert"
-
-	"sneak.berlin/go/dnswatcher/internal/livedns"
-)
-
-// Tests for the retry and the concurrency limit themselves. They
-// perform no DNS resolution of any kind.
-
-func TestRetryRecoversFromTransientFailure(t *testing.T) {
-	t.Parallel()
-
-	const wantAttempts = 2
-
-	attempts := 0
-
-	livedns.Retry(t, "transient", func(_ context.Context) error {
-		attempts++
-
-		if attempts < wantAttempts {
-			return livedns.ErrNoAnswer
-		}
-
-		return nil
-	})
-
-	assert.Equal(t, wantAttempts, attempts)
-}
-
-func TestRetryGivesEachAttemptADeadline(t *testing.T) {
-	t.Parallel()
-
-	livedns.Retry(t, "deadline", func(ctx context.Context) error {
-		deadline, ok := ctx.Deadline()
-		assert.True(t, ok, "attempt should carry a deadline")
-
-		remaining := time.Until(deadline)
-
-		assert.LessOrEqual(t, remaining, livedns.AttemptTimeout)
-
-		// Lower bound too: without one this passes for a
-		// deadline far shorter than intended, which would
-		// silently turn every live attempt into an instant
-		// timeout.
-		assert.Greater(t, remaining, livedns.AttemptTimeout/2)
-
-		return nil
-	})
-}
-
-func TestRunBoundsConcurrency(t *testing.T) {
-	t.Parallel()
-
-	const workers = 24
-
-	var (
-		mu       sync.Mutex
-		wg       sync.WaitGroup
-		inFlight int
-		maxSeen  int
-	)
-
-	wg.Add(workers)
-
-	for range workers {
-		go func() {
-			defer wg.Done()
-
-			_ = livedns.Run(func(_ context.Context) error {
-				mu.Lock()
-				inFlight++
-
-				if inFlight > maxSeen {
-					maxSeen = inFlight
-				}
-				mu.Unlock()
-
-				time.Sleep(time.Millisecond)
-
-				mu.Lock()
-				inFlight--
-				mu.Unlock()
-
-				return nil
-			})
-		}()
-	}
-
-	wg.Wait()
-
-	assert.Positive(t, maxSeen)
-	assert.LessOrEqual(
-		t, maxSeen, livedns.Concurrency,
-		"live queries must stay under the package-wide gate",
-	)
-}

internal/logger/logger_test.go

@@ -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")
-}

internal/resolver/dns_client.go

@@ -7,8 +7,8 @@ import (
 	"github.com/miekg/dns"
 )
 
-// DNSClient sends one DNS message to a nameserver and returns the
-// reply. The resolver holds one for UDP and one for TCP.
+// DNSClient abstracts DNS wire-protocol exchanges so the resolver
+// can be tested without hitting real nameservers.
 type DNSClient interface {
 	ExchangeContext(
 		ctx context.Context,

internal/resolver/export_test.go

@@ -1,8 +0,0 @@
-package resolver
-
-import "github.com/miekg/dns"
-
-// ExtractRecordValue exports extractRecordValue for testing.
-func ExtractRecordValue(rr dns.RR) string {
-	return extractRecordValue(rr)
-}

internal/resolver/iterative.go

@@ -608,10 +608,7 @@ func classifyResponse(resp *NameserverResponse, state queryState) {
 	}
 }
 
-// extractRecordValue formats a DNS RR value as a string. DNS names
-// are case-insensitive and nameservers may answer in any letter case,
-// so names are lower-cased to compare equal. TXT and CAA values keep
-// their letter case.
+// extractRecordValue formats a DNS RR value as a string.
 func extractRecordValue(rr dns.RR) string {
 	switch r := rr.(type) {
 	case *dns.A:
@@ -619,22 +616,22 @@ func extractRecordValue(rr dns.RR) string {
 	case *dns.AAAA:
 		return r.AAAA.String()
 	case *dns.CNAME:
-		return strings.ToLower(r.Target)
+		return r.Target
 	case *dns.MX:
-		return fmt.Sprintf("%d %s", r.Preference, strings.ToLower(r.Mx))
+		return fmt.Sprintf("%d %s", r.Preference, r.Mx)
 	case *dns.TXT:
 		return strings.Join(r.Txt, "")
 	case *dns.SRV:
 		return fmt.Sprintf(
 			"%d %d %d %s",
-			r.Priority, r.Weight, r.Port, strings.ToLower(r.Target),
+			r.Priority, r.Weight, r.Port, r.Target,
 		)
 	case *dns.CAA:
 		return fmt.Sprintf(
 			"%d %s \"%s\"", r.Flag, r.Tag, r.Value,
 		)
 	case *dns.NS:
-		return strings.ToLower(r.Ns)
+		return r.Ns
 	default:
 		return ""
 	}

internal/resolver/iterative_test.go

@@ -1,62 +0,0 @@
-package resolver_test
-
-import (
-	"testing"
-
-	"github.com/miekg/dns"
-	"github.com/stretchr/testify/assert"
-
-	"sneak.berlin/go/dnswatcher/internal/resolver"
-)
-
-func TestExtractRecordValue_LetterCase(t *testing.T) {
-	t.Parallel()
-
-	tests := []struct {
-		name string
-		rr   dns.RR
-		want string
-	}{
-		{
-			name: "MX target lower-cased",
-			rr:   &dns.MX{Preference: 1, Mx: "ASPMX.L.GOOGLE.COM."},
-			want: "1 aspmx.l.google.com.",
-		},
-		{
-			name: "NS target lower-cased",
-			rr:   &dns.NS{Ns: "x.ns.joker.COM."},
-			want: "x.ns.joker.com.",
-		},
-		{
-			name: "CNAME target lower-cased",
-			rr:   &dns.CNAME{Target: "WWW.Example.Com."},
-			want: "www.example.com.",
-		},
-		{
-			name: "SRV target lower-cased",
-			rr: &dns.SRV{
-				Priority: 10, Weight: 5, Port: 443,
-				Target: "SIP.Example.Com.",
-			},
-			want: "10 5 443 sip.example.com.",
-		},
-		{
-			name: "TXT value keeps its case",
-			rr:   &dns.TXT{Txt: []string{"Verify=AbC123"}},
-			want: "Verify=AbC123",
-		},
-		{
-			name: "CAA value keeps its case",
-			rr:   &dns.CAA{Flag: 0, Tag: "issue", Value: "LetsEncrypt.org"},
-			want: `0 issue "LetsEncrypt.org"`,
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			assert.Equal(t, tt.want, resolver.ExtractRecordValue(tt.rr))
-		})
-	}
-}

internal/resolver/livedns_harness_test.go

@@ -1,7 +1,10 @@
 package resolver_test
 
 import (
+	"context"
+	"sync"
 	"testing"
+	"time"
 
 	"github.com/stretchr/testify/assert"
 
@@ -9,8 +12,9 @@ import (
 )
 
 // Tests for the live-DNS harness in livedns_test.go itself. These
-// exercise pure logic; they perform no DNS resolution of any kind, so
-// they neither mock DNS nor depend on it.
+// exercise pure logic and the retry/concurrency plumbing; they
+// perform no DNS resolution of any kind, so they neither mock DNS
+// nor depend on it.
 
 // Names for the synthetic status maps below. Nothing is ever queried
 // at them: they are map keys handed to the package's pure counting
@@ -86,6 +90,47 @@ func TestStatusCountingIgnoresSilentNameservers(t *testing.T) {
 	)
 }
 
+func TestRetryLiveRecoversFromTransientFailure(t *testing.T) {
+	t.Parallel()
+
+	const wantAttempts = 2
+
+	attempts := 0
+
+	retryLive(t, "transient", func(_ context.Context) error {
+		attempts++
+
+		if attempts < wantAttempts {
+			return errLiveNoAnswer
+		}
+
+		return nil
+	})
+
+	assert.Equal(t, wantAttempts, attempts)
+}
+
+func TestRetryLiveGivesEachAttemptADeadline(t *testing.T) {
+	t.Parallel()
+
+	retryLive(t, "deadline", func(ctx context.Context) error {
+		deadline, ok := ctx.Deadline()
+		assert.True(t, ok, "attempt should carry a deadline")
+
+		remaining := time.Until(deadline)
+
+		assert.LessOrEqual(t, remaining, liveAttemptTimeout)
+
+		// Lower bound too: without one this passes for a
+		// deadline far shorter than intended, which would
+		// silently turn every live attempt into an instant
+		// timeout.
+		assert.Greater(t, remaining, liveAttemptTimeout/2)
+
+		return nil
+	})
+}
+
 // TestUnsanctionedStatusesRejectsWrongAnswers is the regression test
 // for the defect this allowlist exists to prevent: a minority of
 // nameservers answering WRONGLY while quorum keeps the suite green.
@@ -190,3 +235,50 @@ func TestUnsanctionedStatusesToleratesSilenceOnly(t *testing.T) {
 		unsanctionedStatuses(results, allowed...),
 	)
 }
+
+func TestRunLiveBoundsConcurrency(t *testing.T) {
+	t.Parallel()
+
+	const workers = 24
+
+	var (
+		mu       sync.Mutex
+		wg       sync.WaitGroup
+		inFlight int
+		maxSeen  int
+	)
+
+	wg.Add(workers)
+
+	for range workers {
+		go func() {
+			defer wg.Done()
+
+			_ = runLive(func(_ context.Context) error {
+				mu.Lock()
+				inFlight++
+
+				if inFlight > maxSeen {
+					maxSeen = inFlight
+				}
+				mu.Unlock()
+
+				time.Sleep(time.Millisecond)
+
+				mu.Lock()
+				inFlight--
+				mu.Unlock()
+
+				return nil
+			})
+		}()
+	}
+
+	wg.Wait()
+
+	assert.Positive(t, maxSeen)
+	assert.LessOrEqual(
+		t, maxSeen, liveConcurrency,
+		"live queries must stay under the package-wide gate",
+	)
+}

internal/resolver/livedns_test.go

@@ -8,8 +8,8 @@ import (
 	"sort"
 	"strings"
 	"testing"
+	"time"
 
-	"sneak.berlin/go/dnswatcher/internal/livedns"
 	"sneak.berlin/go/dnswatcher/internal/resolver"
 )
 
@@ -17,34 +17,144 @@ import (
 // Live DNS test support
 // ----------------------------------------------------------------
 //
-// Tests that look something up in DNS query live DNS servers, never a
-// stand-in; logic that works on record data may be tested on that
-// data with no lookup (see TESTING.md). Each live operation below goes
-// through livedns.Retry, which bounds how many resolutions are in
-// flight at once and retries an operation that got no answer (see
-// package livedns).
+// Every test in this package resolves against the real, live DNS —
+// see TESTING.md. Nothing here mocks, fakes, stubs, records or
+// replays DNS, and nothing here skips or gates a test: the helpers
+// below only change *how* the live queries are issued, so that a
+// single dropped UDP packet or one slow authoritative server does
+// not turn a correct resolver into a red build.
 //
-// Where an assertion spans several independent nameservers, a quorum
-// is enough: a strict majority answering as expected. A server that
-// fails to answer is tolerated, while a server that answers *wrongly*
-// still fails the test.
+// Three mechanisms, all test-side:
 //
-// That tolerance is expressed as an ALLOWLIST of sanctioned statuses,
-// never as a blocklist of known-bad ones. A blocklist bans the one
-// wrong answer its author thought of and silently admits every other
-// status, including any added to the resolver later; an allowlist
-// fails on anything nobody explicitly sanctioned. Silence (timeout,
-// error) is the only thing quorum exists to tolerate. A *wrong
-// answer* — nxdomain for a name that exists, ok for one that does
-// not, nodata for either — is never tolerated at any count.
+//  1. Bounded concurrency. The package's tests are parallel and the
+//     build hosts have many cores, so without a limit every test
+//     starts its own iterative resolution at the same instant and
+//     they all hit the first root server in rootServerList() within
+//     a few milliseconds of each other. Root servers rate-limit
+//     that, which shows up as a different arbitrary subset of tests
+//     failing on each run. liveGate caps how many resolutions are
+//     in flight at once.
+//
+//  2. Retry with exponential backoff. Each live operation gets
+//     several attempts with its own timeout. The retry predicate is
+//     strictly transport-level — "did a nameserver answer at all" —
+//     never the assertion the test is making. A resolver that
+//     answers incorrectly still fails on the first attempt.
+//
+//  3. Quorum. Where an assertion spans several independent
+//     nameservers, a strict majority answering as expected is
+//     enough; a server that fails to answer is tolerated, while a
+//     server that answers *wrongly* still fails the test.
+//
+// The tolerance in (3) is expressed as an ALLOWLIST of sanctioned
+// statuses, never as a blocklist of known-bad ones. A blocklist bans
+// the one wrong answer its author thought of and silently admits
+// every other status, including any added to the resolver later; an
+// allowlist fails on anything nobody explicitly sanctioned. Silence
+// (timeout, error) is the only thing quorum exists to tolerate. A
+// *wrong answer* — nxdomain for a name that exists, ok for one that
+// does not, nodata for either — is never tolerated at any count.
 
-// minNameservers is the smallest nameserver count a well-run zone is
-// expected to publish.
-const minNameservers = 2
+const (
+	// liveAttempts is how many times a live DNS operation is
+	// attempted before the test fails.
+	liveAttempts = 3
 
-// errLiveNoQuorum reports that too few of a domain's nameservers
-// answered for a quorum assertion to be made.
-var errLiveNoQuorum = errors.New("no nameserver quorum")
+	// liveAttemptTimeout bounds one attempt. Worst case for an
+	// operation is liveAttempts * liveAttemptTimeout plus the
+	// backoff — about 26 seconds, well inside the 90-second
+	// `go test -timeout` backstop even when several operations
+	// exhaust their attempts.
+	liveAttemptTimeout = 8 * time.Second
+
+	// liveBackoffBase is the delay after the first failed
+	// attempt; it is multiplied by liveBackoffFactor each time.
+	liveBackoffBase = 500 * time.Millisecond
+
+	// liveBackoffFactor is the exponential backoff multiplier.
+	liveBackoffFactor = 2
+
+	// liveConcurrency caps how many live resolutions may be in
+	// flight across the whole package at once.
+	liveConcurrency = 6
+
+	// minNameservers is the smallest nameserver count a
+	// well-run zone is expected to publish.
+	minNameservers = 2
+)
+
+// liveGate bounds concurrent live resolutions package-wide. It has
+// to be package scoped: the whole point is that it is shared by
+// every parallel test in the package.
+//
+//nolint:gochecknoglobals // package-wide live query rate limit
+var liveGate = make(chan struct{}, liveConcurrency)
+
+var (
+	// errLiveNoAnswer reports that a live operation produced no
+	// usable answer, which is retried rather than asserted on.
+	errLiveNoAnswer = errors.New("no answer from live DNS")
+
+	// errLiveNoQuorum reports that too few of a domain's
+	// nameservers answered for a quorum assertion to be made.
+	errLiveNoQuorum = errors.New("no nameserver quorum")
+)
+
+// runLive executes one attempt of a live operation, holding a slot
+// in liveGate for its duration and bounding it with its own
+// timeout.
+func runLive(op func(ctx context.Context) error) error {
+	liveGate <- struct{}{}
+	defer func() { <-liveGate }()
+
+	ctx, cancel := context.WithTimeout(
+		context.Background(), liveAttemptTimeout,
+	)
+	defer cancel()
+
+	return op(ctx)
+}
+
+// retryLive runs op until it reports success, retrying transport
+// failures with exponential backoff, and fails the test if every
+// attempt fails. op returns an error only for a failure to obtain
+// an answer — never for an answer the test disagrees with, which
+// belongs in an assertion so that it fails immediately. op stores
+// whatever it obtained where its caller can find it.
+func retryLive(
+	t *testing.T,
+	what string,
+	op func(ctx context.Context) error,
+) {
+	t.Helper()
+
+	var last error
+
+	backoff := liveBackoffBase
+
+	for attempt := range liveAttempts {
+		if attempt > 0 {
+			t.Logf(
+				"%s: attempt %d of %d failed (%v), "+
+					"retrying in %s",
+				what, attempt, liveAttempts, last, backoff,
+			)
+			time.Sleep(backoff)
+
+			backoff *= liveBackoffFactor
+		}
+
+		last = runLive(op)
+		if last == nil {
+			return
+		}
+	}
+
+	t.Fatalf(
+		"%s: no answer after %d live attempts: %v",
+		what, liveAttempts, last,
+	)
+}
 
 // liveQuorum is how many of total nameservers must agree for a
 // multi-nameserver assertion to hold: a strict majority.
@@ -162,7 +272,7 @@ func liveFindAuthoritative(
 
 	var out []string
 
-	livedns.Retry(
+	retryLive(
 		t,
 		"FindAuthoritativeNameservers("+domain+")",
 		func(ctx context.Context) error {
@@ -174,7 +284,7 @@ func liveFindAuthoritative(
 			if len(ns) == 0 {
 				return fmt.Errorf(
 					"%w: %s has no nameservers",
-					livedns.ErrNoAnswer, domain,
+					errLiveNoAnswer, domain,
 				)
 			}
 
@@ -198,7 +308,7 @@ func liveLookupNS(
 
 	var out []string
 
-	livedns.Retry(
+	retryLive(
 		t,
 		"LookupNS("+domain+")",
 		func(ctx context.Context) error {
@@ -210,7 +320,7 @@ func liveLookupNS(
 			if len(ns) == 0 {
 				return fmt.Errorf(
 					"%w: %s has no nameservers",
-					livedns.ErrNoAnswer, domain,
+					errLiveNoAnswer, domain,
 				)
 			}
 
@@ -240,7 +350,7 @@ func liveQueryNameserver(
 
 	var out *resolver.NameserverResponse
 
-	livedns.Retry(
+	retryLive(
 		t,
 		what,
 		func(ctx context.Context) error {
@@ -255,7 +365,7 @@ func liveQueryNameserver(
 				resp.Status == resolver.StatusError {
 				return fmt.Errorf(
 					"%w: %s returned %s: %s",
-					livedns.ErrNoAnswer, nameserver,
+					errLiveNoAnswer, nameserver,
 					resp.Status, resp.Error,
 				)
 			}
@@ -282,7 +392,7 @@ func liveQueryAllNameservers(
 
 	var out map[string]*resolver.NameserverResponse
 
-	livedns.Retry(
+	retryLive(
 		t,
 		"QueryAllNameservers("+hostname+")",
 		func(ctx context.Context) error {
@@ -294,7 +404,7 @@ func liveQueryAllNameservers(
 			if len(results) == 0 {
 				return fmt.Errorf(
 					"%w: no nameservers queried for %s",
-					livedns.ErrNoAnswer, hostname,
+					errLiveNoAnswer, hostname,
 				)
 			}
 
@@ -327,7 +437,7 @@ func liveResolveIPs(
 
 	var out []string
 
-	livedns.Retry(
+	retryLive(
 		t,
 		"ResolveIPAddresses("+hostname+")",
 		func(ctx context.Context) error {
@@ -339,7 +449,7 @@ func liveResolveIPs(
 			if len(ips) == 0 {
 				return fmt.Errorf(
 					"%w: no addresses for %s",
-					livedns.ErrNoAnswer, hostname,
+					errLiveNoAnswer, hostname,
 				)
 			}
 
@@ -366,7 +476,7 @@ func liveResolveIPsAllowingEmpty(
 
 	var out []string
 
-	livedns.Retry(
+	retryLive(
 		t,
 		"ResolveIPAddresses("+hostname+")",
 		func(ctx context.Context) error {

internal/resolver/resolver.go

@@ -67,4 +67,17 @@ func NewFromLogger(log *slog.Logger) *Resolver {
 	}
 }
 
+// NewFromLoggerWithClient creates a Resolver with a custom DNS
+// client, useful for testing with mock DNS responses.
+func NewFromLoggerWithClient(
+	log *slog.Logger,
+	client DNSClient,
+) *Resolver {
+	return &Resolver{
+		log:    log,
+		client: client,
+		tcp:    client,
+	}
+}
+
 // Method implementations are in iterative.go.

internal/resolver/resolver_test.go

@@ -10,6 +10,7 @@ import (
 	"testing"
 	"time"
 
+	"github.com/miekg/dns"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
@@ -32,8 +33,8 @@ func newTestResolver(t *testing.T) *resolver.Resolver {
 }
 
 // findOneNSForDomain picks one authoritative nameserver to aim a
-// test at. Quorum handling lives in livedns_test.go, and the live-DNS
-// retry and concurrency limit in package livedns.
+// test at. Live-DNS retry, concurrency and quorum handling live in
+// livedns_test.go.
 func findOneNSForDomain(
 	t *testing.T,
 	r *resolver.Resolver,
@@ -525,18 +526,21 @@ func TestQueryAllNameservers_ContextCanceled(t *testing.T) {
 func TestQueryNameserverIP_Timeout(t *testing.T) {
 	t.Parallel()
 
-	r := newTestResolver(t)
+	log := slog.New(slog.NewTextHandler(
+		os.Stderr,
+		&slog.HandlerOptions{Level: slog.LevelDebug},
+	))
+
+	r := resolver.NewFromLoggerWithClient(
+		log, &timeoutClient{},
+	)
 
-	// Nothing answers at 192.0.2.1, a documentation address. The
-	// resolver tries each query twice, and the first try gives up
-	// after two seconds. A deadline that ends during the first try
-	// makes the status vary from run to run between nodata and
-	// timeout, so the deadline must outlast the first try.
 	ctx, cancel := context.WithTimeout(
-		context.Background(), 3*time.Second,
+		context.Background(), 10*time.Second,
 	)
 	t.Cleanup(cancel)
 
+	// Query any IP — the client always returns a timeout error.
 	resp, err := r.QueryNameserverIP(
 		ctx, "unreachable.test.", "192.0.2.1",
 		"example.com",
@@ -547,6 +551,27 @@ func TestQueryNameserverIP_Timeout(t *testing.T) {
 	assert.NotEmpty(t, resp.Error)
 }
 
+// timeoutClient simulates DNS timeout errors for testing.
+type timeoutClient struct{}
+
+func (c *timeoutClient) ExchangeContext(
+	_ context.Context,
+	_ *dns.Msg,
+	_ string,
+) (*dns.Msg, time.Duration, error) {
+	return nil, 0, &net.OpError{
+		Op:  "read",
+		Net: "udp",
+		Err: &timeoutError{},
+	}
+}
+
+type timeoutError struct{}
+
+func (e *timeoutError) Error() string   { return "i/o timeout" }
+func (e *timeoutError) Timeout() bool   { return true }
+func (e *timeoutError) Temporary() bool { return true }
+
 func TestResolveIPAddresses_ContextCanceled(t *testing.T) {
 	t.Parallel()
 

internal/server/export_test.go

@@ -5,20 +5,15 @@ import (
 	"time"
 )
 
+// NewHTTPServer exports newHTTPServer for testing.
+func NewHTTPServer(
+	listenAddr string,
+	handler http.Handler,
+) *http.Server {
+	return newHTTPServer(listenAddr, handler)
+}
+
 // RequestTimeout exports the handler execution budget applied by
 // chimw.Timeout in SetupRoutes, so tests can assert the relationship
 // between it and the server's WriteTimeout.
 const RequestTimeout time.Duration = requestTimeout
-
-// SetListenPort overrides the port Run binds. A test uses it to hand
-// Run an unbindable port so ListenAndServe fails immediately and Run
-// returns after storing its http.Server.
-func SetListenPort(s *Server, port int) {
-	s.port = port
-}
-
-// HTTPServerOf returns the http.Server that Run built and stored, so a
-// test can inspect the timeouts the running server actually carries.
-func HTTPServerOf(s *Server) *http.Server {
-	return s.httpServer
-}

internal/server/server_test.go

@@ -1,130 +1,112 @@
 package server_test
 
 import (
+	"net/http"
 	"testing"
 
-	"github.com/spf13/viper"
-	"go.uber.org/fx"
-
-	"sneak.berlin/go/dnswatcher/internal/config"
-	"sneak.berlin/go/dnswatcher/internal/globals"
-	"sneak.berlin/go/dnswatcher/internal/handlers"
-	"sneak.berlin/go/dnswatcher/internal/healthcheck"
-	"sneak.berlin/go/dnswatcher/internal/logger"
-	"sneak.berlin/go/dnswatcher/internal/middleware"
-	"sneak.berlin/go/dnswatcher/internal/notify"
 	"sneak.berlin/go/dnswatcher/internal/server"
-	"sneak.berlin/go/dnswatcher/internal/state"
 )
 
-// buildServer wires a *server.Server exactly as cmd/dnswatcher does,
-// minus the watcher/resolver subtree that would touch live DNS. fx
-// builds the object graph but the lifecycle is never started, so no
-// OnStart hook runs and nothing listens or resolves. The caller must
-// first configure viper (config.New reads it), which is also why the
-// caller cannot run in parallel.
-func buildServer(t *testing.T) *server.Server {
-	t.Helper()
-
-	var srv *server.Server
-
-	app := fx.New(
-		fx.NopLogger,
-		fx.Provide(
-			globals.New,
-			logger.New,
-			config.New,
-			state.New,
-			healthcheck.New,
-			notify.New,
-			middleware.New,
-			handlers.New,
-			server.New,
-		),
-		fx.Populate(&srv),
+// noopHandler stands in for the router; newHTTPServer only stores it.
+func noopHandler() http.Handler {
+	return http.HandlerFunc(
+		func(w http.ResponseWriter, _ *http.Request) {
+			w.WriteHeader(http.StatusOK)
+		},
 	)
-
-	err := app.Err()
-	if err != nil {
-		t.Fatalf("building server graph: %v", err)
-	}
-
-	return srv
 }
 
-// TestRunWiresSocketTimeouts pins that the http.Server the running
-// server actually serves — the one Run builds and hands to
-// ListenAndServe — carries every socket-level timeout, plus the two
-// relationships the values must satisfy.
+// TestHTTPServerTimeoutsAreSet asserts that every socket-level
+// timeout is configured. A zero value in net/http means "no limit",
+// so a refactor that silently drops one of these reintroduces the
+// slowloris / unreaped-keep-alive exposure this guards against.
 //
-// Run is driven to completion with an unbindable port: it builds and
-// stores s.httpServer, then ListenAndServe fails at once and Run
-// returns without ever listening. The assertions run in the same
-// goroutine after Run returns, so reading s.httpServer is free of any
-// data race. Nothing here measures elapsed time.
-//
-// ReadTimeout must be at least ReadHeaderTimeout. net/http reads the
-// headers under ReadHeaderTimeout, then sets the read deadline for the
-// rest of the request to ReadTimeout, counted from when it started
-// reading the request. If ReadTimeout were smaller, a request whose
-// headers arrived after ReadTimeout but within ReadHeaderTimeout would
-// get a read deadline that had already passed, so reading its body
-// would fail at once.
-func TestRunWiresSocketTimeouts(t *testing.T) {
-	// Sets an env var and touches viper global state, so like the
-	// config tests it cannot use t.Parallel.
-	viper.Reset()
-	t.Setenv("DNSWATCHER_TARGETS", "example.com")
+// The assertions are on the configured field values only; nothing
+// here measures elapsed time, so the test cannot flake on timing.
+func TestHTTPServerTimeoutsAreSet(t *testing.T) {
+	t.Parallel()
 
-	srv := buildServer(t)
-	server.SetListenPort(srv, -1)
+	srv := server.NewHTTPServer(":8080", noopHandler())
 
-	srv.Run()
-
-	hs := server.HTTPServerOf(srv)
-	if hs == nil {
-		t.Fatal("Run did not build an http.Server")
-	}
-
-	if hs.ReadTimeout <= 0 {
-		t.Errorf("ReadTimeout must be non-zero, got %v", hs.ReadTimeout)
-	}
-
-	if hs.ReadHeaderTimeout <= 0 {
+	if srv.ReadTimeout <= 0 {
 		t.Errorf(
-			"ReadHeaderTimeout must be non-zero, got %v",
-			hs.ReadHeaderTimeout,
+			"ReadTimeout must be non-zero, got %v",
+			srv.ReadTimeout,
 		)
 	}
 
-	if hs.WriteTimeout <= 0 {
-		t.Errorf("WriteTimeout must be non-zero, got %v", hs.WriteTimeout)
+	if srv.ReadHeaderTimeout <= 0 {
+		t.Errorf(
+			"ReadHeaderTimeout must be non-zero, got %v",
+			srv.ReadHeaderTimeout,
+		)
 	}
 
-	if hs.IdleTimeout <= 0 {
-		t.Errorf("IdleTimeout must be non-zero, got %v", hs.IdleTimeout)
+	if srv.WriteTimeout <= 0 {
+		t.Errorf(
+			"WriteTimeout must be non-zero, got %v",
+			srv.WriteTimeout,
+		)
 	}
 
-	if hs.WriteTimeout <= server.RequestTimeout {
+	if srv.IdleTimeout <= 0 {
+		t.Errorf(
+			"IdleTimeout must be non-zero, got %v",
+			srv.IdleTimeout,
+		)
+	}
+}
+
+// TestWriteTimeoutExceedsHandlerBudget pins the one relationship the
+// values must satisfy. net/http arms the write deadline once request
+// headers are read, so it covers handler execution plus the response
+// flush. If WriteTimeout were not greater than the chimw.Timeout
+// handler budget, the connection would be severed before a handler
+// that used its full budget could respond, making that budget
+// unreachable.
+func TestWriteTimeoutExceedsHandlerBudget(t *testing.T) {
+	t.Parallel()
+
+	srv := server.NewHTTPServer(":8080", noopHandler())
+
+	if srv.WriteTimeout <= server.RequestTimeout {
 		t.Errorf(
 			"WriteTimeout (%v) must exceed handler budget (%v)",
-			hs.WriteTimeout,
+			srv.WriteTimeout,
 			server.RequestTimeout,
 		)
 	}
+}
 
-	if hs.ReadTimeout < hs.ReadHeaderTimeout {
+// TestReadTimeoutCoversHeaderTimeout asserts the read deadline for
+// the whole request is at least as long as the header-only deadline;
+// a smaller ReadTimeout would make ReadHeaderTimeout unreachable.
+func TestReadTimeoutCoversHeaderTimeout(t *testing.T) {
+	t.Parallel()
+
+	srv := server.NewHTTPServer(":8080", noopHandler())
+
+	if srv.ReadTimeout < srv.ReadHeaderTimeout {
 		t.Errorf(
 			"ReadTimeout (%v) must be >= ReadHeaderTimeout (%v)",
-			hs.ReadTimeout,
-			hs.ReadHeaderTimeout,
-		)
-	}
-
-	if hs.Handler != srv {
-		t.Errorf(
-			"Run wired handler %T, want the *server.Server",
-			hs.Handler,
+			srv.ReadTimeout,
+			srv.ReadHeaderTimeout,
 		)
 	}
 }
+
+// TestHTTPServerAddrAndHandler covers the rest of the constructor so
+// a future edit cannot drop the listen address or the handler.
+func TestHTTPServerAddrAndHandler(t *testing.T) {
+	t.Parallel()
+
+	srv := server.NewHTTPServer(":9999", noopHandler())
+
+	if srv.Addr != ":9999" {
+		t.Errorf("Addr = %q, want %q", srv.Addr, ":9999")
+	}
+
+	if srv.Handler == nil {
+		t.Error("Handler must not be nil")
+	}
+}

internal/state/state.go

@@ -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
-}

internal/state/state_test.go

@@ -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"
 )
 
@@ -499,107 +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)
-	}
-}
-
-// TestStartupFailsWhenExistingDataDirNotWritable verifies that startup
-// stops when the data directory exists but the temp file that saving uses
-// cannot be written in it. A directory sitting at the temp file's path
-// makes that write fail, which also holds as root.
-func TestStartupFailsWhenExistingDataDirNotWritable(t *testing.T) {
-	t.Parallel()
-
-	dataDir := t.TempDir()
-
-	err := os.Mkdir(filepath.Join(dataDir, "state.json.tmp"), 0o700)
-	if err != nil {
-		t.Fatalf("creating directory: %v", err)
-	}
-
-	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) {

internal/watcher/export_test.go

@@ -1,25 +0,0 @@
-package watcher
-
-import (
-	"context"
-
-	"sneak.berlin/go/dnswatcher/internal/state"
-)
-
-// NewlyDisagreeingPairs exports newlyDisagreeingPairs for testing.
-func NewlyDisagreeingPairs(
-	prev *state.HostnameState,
-	current map[string]map[string][]string,
-) [][2]string {
-	return newlyDisagreeingPairs(prev, current)
-}
-
-// DetectHostnameChanges exports detectHostnameChanges for testing.
-func (w *Watcher) DetectHostnameChanges(
-	ctx context.Context,
-	hostname string,
-	prev *state.HostnameState,
-	current map[string]map[string][]string,
-) {
-	w.detectHostnameChanges(ctx, hostname, prev, current)
-}

internal/watcher/inconsistency_test.go

@@ -1,182 +0,0 @@
-package watcher_test
-
-import (
-	"slices"
-	"testing"
-
-	"sneak.berlin/go/dnswatcher/internal/state"
-	"sneak.berlin/go/dnswatcher/internal/watcher"
-)
-
-const (
-	host = "www.example.net"
-	nsA  = "a.ns.example.net."
-	nsB  = "b.ns.example.net."
-	nsC  = "c.ns.example.net."
-	ip1  = "192.0.2.1"
-	ip2  = "192.0.2.2"
-	ip3  = "192.0.2.3"
-)
-
-// hostnameState builds the state a check with these records leaves behind.
-func hostnameState(
-	records map[string]map[string][]string,
-) *state.HostnameState {
-	hs := &state.HostnameState{
-		RecordsByNameserver: make(map[string]*state.NameserverRecordState),
-	}
-
-	for ns, recs := range records {
-		hs.RecordsByNameserver[ns] = &state.NameserverRecordState{
-			Records: recs,
-			Status:  "ok",
-		}
-	}
-
-	return hs
-}
-
-func TestNewlyDisagreeingPairs(t *testing.T) {
-	t.Parallel()
-
-	onlyA := map[string]map[string][]string{nsA: {"A": {ip1}}}
-	agree := map[string]map[string][]string{nsA: {"A": {ip1}}, nsB: {"A": {ip1}}}
-	disagree := map[string]map[string][]string{nsA: {"A": {ip1}}, nsB: {"A": {ip2}}}
-	alert := [][2]string{{nsA, nsB}}
-
-	// b already disagrees with a and c; then c changes, so a and c,
-	// which agreed, now differ.
-	bDiffers := map[string]map[string][]string{
-		nsA: {"A": {ip1}}, nsB: {"A": {ip2}}, nsC: {"A": {ip1}},
-	}
-	cChanges := map[string]map[string][]string{
-		nsA: {"A": {ip1}}, nsB: {"A": {ip2}}, nsC: {"A": {ip3}},
-	}
-
-	// Each case starts from the state loaded at startup and runs the
-	// checks in order; want[i] is what check i alerts for.
-	tests := []struct {
-		name   string
-		loaded map[string]map[string][]string
-		checks []map[string]map[string][]string
-		want   [][][2]string
-	}{
-		{
-			name:   "disagreement persisting across checks alerts once",
-			loaded: agree,
-			checks: []map[string]map[string][]string{disagree, disagree, disagree},
-			want:   [][][2]string{alert, nil, nil},
-		},
-		{
-			name:   "disagreement starting on a later check alerts on it",
-			loaded: agree,
-			checks: []map[string]map[string][]string{agree, agree, disagree},
-			want:   [][][2]string{nil, nil, alert},
-		},
-		{
-			name:   "disagreement in the loaded state does not alert",
-			loaded: disagree,
-			checks: []map[string]map[string][]string{disagree, disagree},
-			want:   [][][2]string{nil, nil},
-		},
-		{
-			name:   "nameserver new on the first check and disagreeing alerts once",
-			loaded: onlyA,
-			checks: []map[string]map[string][]string{disagree, disagree},
-			want:   [][][2]string{alert, nil},
-		},
-		{
-			name:   "disagreement after agreeing again alerts again",
-			loaded: agree,
-			checks: []map[string]map[string][]string{disagree, agree, disagree},
-			want:   [][][2]string{alert, nil, alert},
-		},
-		{
-			name:   "new disagreement while another nameserver differs alerts",
-			loaded: bDiffers,
-			checks: []map[string]map[string][]string{cChanges, cChanges},
-			want:   [][][2]string{{{nsA, nsC}}, nil},
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			prev := hostnameState(tt.loaded)
-
-			for i, current := range tt.checks {
-				got := watcher.NewlyDisagreeingPairs(prev, current)
-				if !slices.Equal(got, tt.want[i]) {
-					t.Errorf(
-						"check %d: alerted for %v, want %v",
-						i, got, tt.want[i],
-					)
-				}
-
-				prev = hostnameState(current)
-			}
-		})
-	}
-}
-
-func TestInconsistencyAlert(t *testing.T) {
-	t.Parallel()
-
-	onlyA := map[string]map[string][]string{nsA: {"A": {ip1}}}
-	agree := map[string]map[string][]string{nsA: {"A": {ip1}}, nsB: {"A": {ip1}}}
-	disagree := map[string]map[string][]string{nsA: {"A": {ip1}}, nsB: {"A": {ip2}}}
-
-	// Each case starts from the state loaded at startup and then sees
-	// the nameservers disagree on three checks in a row.
-	tests := []struct {
-		name   string
-		loaded map[string]map[string][]string
-		want   int
-	}{
-		{
-			name:   "disagreement lasting several checks alerts once",
-			loaded: agree,
-			want:   1,
-		},
-		{
-			name:   "disagreement in the loaded state does not alert",
-			loaded: disagree,
-			want:   0,
-		},
-		{
-			name:   "nameserver new on the first check and disagreeing alerts once",
-			loaded: onlyA,
-			want:   1,
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			t.Parallel()
-
-			// The hostname change detection uses only the notifier.
-			notifier := &mockNotifier{}
-			w := watcher.NewForTest(nil, nil, nil, nil, nil, notifier)
-
-			prev := hostnameState(tt.loaded)
-
-			for range 3 {
-				w.DetectHostnameChanges(t.Context(), host, prev, disagree)
-				prev = hostnameState(disagree)
-			}
-
-			got := 0
-
-			for _, n := range notifier.getNotifications() {
-				if n.Title == "Inconsistency: "+host {
-					got++
-				}
-			}
-
-			if got != tt.want {
-				t.Errorf("sent %d inconsistency alerts, want %d", got, tt.want)
-			}
-		})
-	}
-}

internal/watcher/watcher.go

@@ -366,7 +366,7 @@ func (w *Watcher) detectHostnameChanges(
 ) {
 	w.detectRecordChanges(ctx, hostname, prev, current)
 	w.detectNSDisappearances(ctx, hostname, prev, current)
-	w.detectInconsistencies(ctx, hostname, prev, current)
+	w.detectInconsistencies(ctx, hostname, current)
 }
 
 func (w *Watcher) detectRecordChanges(
@@ -448,11 +448,22 @@ func (w *Watcher) detectNSDisappearances(
 func (w *Watcher) detectInconsistencies(
 	ctx context.Context,
 	hostname string,
-	prev *state.HostnameState,
 	current map[string]map[string][]string,
 ) {
-	for _, pair := range newlyDisagreeingPairs(prev, current) {
-		ns1, ns2 := pair[0], pair[1]
+	nameservers := make([]string, 0, len(current))
+	for ns := range current {
+		nameservers = append(nameservers, ns)
+	}
+
+	sort.Strings(nameservers)
+
+	for i := range len(nameservers) - 1 {
+		ns1 := nameservers[i]
+		ns2 := nameservers[i+1]
+
+		if recordsEqual(current[ns1], current[ns2]) {
+			continue
+		}
 
 		msg := fmt.Sprintf(
 			"Hostname: %s\n%s: %v\n%s: %v",
@@ -470,43 +481,6 @@ func (w *Watcher) detectInconsistencies(
 	}
 }
 
-// newlyDisagreeingPairs returns every pair of nameservers whose records
-// differ in current, in sorted order of name, except pairs where both
-// nameservers were in prev and already differed there. A nameserver
-// missing from prev is paired with every nameserver it differs from.
-func newlyDisagreeingPairs(
-	prev *state.HostnameState,
-	current map[string]map[string][]string,
-) [][2]string {
-	nameservers := make([]string, 0, len(current))
-	for ns := range current {
-		nameservers = append(nameservers, ns)
-	}
-
-	sort.Strings(nameservers)
-
-	var pairs [][2]string
-
-	for i, ns1 := range nameservers {
-		for _, ns2 := range nameservers[i+1:] {
-			if recordsEqual(current[ns1], current[ns2]) {
-				continue
-			}
-
-			prev1, ok1 := prev.RecordsByNameserver[ns1]
-			prev2, ok2 := prev.RecordsByNameserver[ns2]
-
-			if ok1 && ok2 && !recordsEqual(prev1.Records, prev2.Records) {
-				continue
-			}
-
-			pairs = append(pairs, [2]string{ns1, ns2})
-		}
-	}
-
-	return pairs
-}
-
 func (w *Watcher) checkAllPorts(ctx context.Context) {
 	// Phase 1: Build current IP:port → hostname associations
 	// from fresh DNS data.

internal/watcher/watcher_test.go

@@ -2,77 +2,151 @@ package watcher_test
 
 import (
 	"context"
+	"errors"
 	"fmt"
-	"log/slog"
-	"slices"
 	"sync"
 	"testing"
 	"time"
 
 	"sneak.berlin/go/dnswatcher/internal/config"
-	"sneak.berlin/go/dnswatcher/internal/livedns"
 	"sneak.berlin/go/dnswatcher/internal/portcheck"
-	"sneak.berlin/go/dnswatcher/internal/resolver"
 	"sneak.berlin/go/dnswatcher/internal/state"
 	"sneak.berlin/go/dnswatcher/internal/tlscheck"
 	"sneak.berlin/go/dnswatcher/internal/watcher"
 )
 
-// The watcher looks these names up in live DNS with the real resolver,
-// so tests assert on what the watcher does with the answers, never on
-// the records these zones publish. testHost's nameservers and addresses
-// stay the same from one check to the next, which the tests that check
-// it twice rely on.
+// errNotFound is returned when mock data is missing.
+var errNotFound = errors.New("not found")
+
+// Fixture values shared across tests.
 const (
-	testDomain = "google.com"
-	testHost   = "cloudflare.com"
+	testDomain = "example.com"
+	testHost   = "www.example.com"
+	testNS1    = "ns1.example.com."
+	testNS2    = "ns2.example.com."
+	testIPv4   = "93.184.216.34"
+	testIP     = "1.2.3.4"
 	testIssuer = "DigiCert"
 )
 
-// Saved-state values that live DNS never returns: nameserver names
-// under .invalid and a documentation address.
-const (
-	oldNS1 = "ns1.example.invalid."
-	oldNS2 = "ns2.example.invalid."
-	oldIP  = "192.0.2.1"
-)
+// --- Mock implementations ---
 
-// --- Stand-ins for the port checker, TLS checker and notifier ---
-//
-// DNS has none: the watchers built here use the real resolver (see
-// TESTING.md).
+type mockResolver struct {
+	mu             sync.Mutex
+	nsRecords      map[string][]string
+	allRecords     map[string]map[string]map[string][]string
+	ipAddresses    map[string][]string
+	lookupNSErr    error
+	allRecordsErr  error
+	resolveIPErr   error
+	lookupNSCalls  int
+	allRecordCalls int
+}
+
+func (m *mockResolver) LookupNS(
+	_ context.Context,
+	domain string,
+) ([]string, error) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	m.lookupNSCalls++
+
+	if m.lookupNSErr != nil {
+		return nil, m.lookupNSErr
+	}
+
+	ns, ok := m.nsRecords[domain]
+	if !ok {
+		return nil, fmt.Errorf(
+			"%w: NS for %s", errNotFound, domain,
+		)
+	}
+
+	return ns, nil
+}
+
+func (m *mockResolver) LookupAllRecords(
+	_ context.Context,
+	hostname string,
+) (map[string]map[string][]string, error) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	m.allRecordCalls++
+
+	if m.allRecordsErr != nil {
+		return nil, m.allRecordsErr
+	}
+
+	recs, ok := m.allRecords[hostname]
+	if !ok {
+		return nil, fmt.Errorf(
+			"%w: records for %s", errNotFound, hostname,
+		)
+	}
+
+	return recs, nil
+}
+
+func (m *mockResolver) ResolveIPAddresses(
+	_ context.Context,
+	hostname string,
+) ([]string, error) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	if m.resolveIPErr != nil {
+		return nil, m.resolveIPErr
+	}
+
+	ips, ok := m.ipAddresses[hostname]
+	if !ok {
+		return nil, fmt.Errorf(
+			"%w: IPs for %s", errNotFound, hostname,
+		)
+	}
+
+	return ips, nil
+}
 
-// mockPortChecker reports every port open until closed is set.
 type mockPortChecker struct {
-	mu     sync.Mutex
-	closed bool
-	calls  int
+	mu      sync.Mutex
+	results map[string]bool
+	err     error
+	calls   int
 }
 
 func (m *mockPortChecker) CheckPort(
 	_ context.Context,
-	_ string,
-	_ int,
+	address string,
+	port int,
 ) (*portcheck.PortResult, error) {
 	m.mu.Lock()
 	defer m.mu.Unlock()
 
 	m.calls++
 
-	return &portcheck.PortResult{Open: !m.closed}, nil
+	if m.err != nil {
+		return nil, m.err
+	}
+
+	key := fmt.Sprintf("%s:%d", address, port)
+	open := m.results[key]
+
+	return &portcheck.PortResult{Open: open}, nil
 }
 
-// mockTLSChecker returns a certificate for the requested hostname that
-// expires at notAfter.
 type mockTLSChecker struct {
-	mu       sync.Mutex
-	notAfter time.Time
-	calls    int
+	mu    sync.Mutex
+	certs map[string]*tlscheck.CertificateInfo
+	err   error
+	calls int
 }
 
 func (m *mockTLSChecker) CheckCertificate(
 	_ context.Context,
-	_ string,
+	ip string,
 	hostname string,
 ) (*tlscheck.CertificateInfo, error) {
 	m.mu.Lock()
@@ -80,12 +154,20 @@ func (m *mockTLSChecker) CheckCertificate(
 
 	m.calls++
 
-	return &tlscheck.CertificateInfo{
-		CommonName:              hostname,
-		Issuer:                  testIssuer,
-		NotAfter:                m.notAfter,
-		SubjectAlternativeNames: []string{hostname},
-	}, nil
+	if m.err != nil {
+		return nil, m.err
+	}
+
+	key := fmt.Sprintf("%s:%s", ip, hostname)
+	cert, ok := m.certs[key]
+
+	if !ok {
+		return nil, fmt.Errorf(
+			"%w: cert for %s", errNotFound, key,
+		)
+	}
+
+	return cert, nil
 }
 
 type notification struct {
@@ -123,9 +205,10 @@ func (m *mockNotifier) getNotifications() []notification {
 	return result
 }
 
-// --- Helpers to build a Watcher and run its checks against live DNS ---
+// --- Helper to build a Watcher for testing ---
 
 type testDeps struct {
+	resolver    *mockResolver
 	portChecker *mockPortChecker
 	tlsChecker  *mockTLSChecker
 	notifier    *mockNotifier
@@ -140,9 +223,16 @@ func newTestWatcher(
 	t.Helper()
 
 	deps := &testDeps{
-		portChecker: &mockPortChecker{},
+		resolver: &mockResolver{
+			nsRecords:   make(map[string][]string),
+			allRecords:  make(map[string]map[string]map[string][]string),
+			ipAddresses: make(map[string][]string),
+		},
+		portChecker: &mockPortChecker{
+			results: make(map[string]bool),
+		},
 		tlsChecker: &mockTLSChecker{
-			notAfter: time.Now().Add(90 * 24 * time.Hour),
+			certs: make(map[string]*tlscheck.CertificateInfo),
 		},
 		notifier: &mockNotifier{},
 		config:   cfg,
@@ -153,7 +243,7 @@ func newTestWatcher(
 	w := watcher.NewForTest(
 		deps.config,
 		deps.state,
-		resolver.NewFromLogger(slog.Default()),
+		deps.resolver,
 		deps.portChecker,
 		deps.tlsChecker,
 		deps.notifier,
@@ -173,122 +263,6 @@ func defaultTestConfig(t *testing.T) *config.Config {
 	}
 }
 
-// checkOnce runs the watcher's checks once and returns an error when a
-// configured name has no hostname state saved by this check, or that
-// state holds no address. Either live DNS gave no answer for the name,
-// or the watcher saved no fresh result for it.
-func checkOnce(
-	ctx context.Context,
-	w *watcher.Watcher,
-	deps *testDeps,
-) error {
-	started := time.Now()
-
-	w.RunOnce(ctx)
-
-	names := slices.Concat(deps.config.Domains, deps.config.Hostnames)
-
-	for _, name := range names {
-		hs, ok := deps.state.GetHostnameState(name)
-		if !ok || hs.LastChecked.Before(started) ||
-			len(addresses(hs)) == 0 {
-			return fmt.Errorf(
-				"%s: %w, or the watcher saved no fresh "+
-					"result for it",
-				name, livedns.ErrNoAnswer,
-			)
-		}
-	}
-
-	return nil
-}
-
-// runChecks builds a watcher, lets prepare set up the saved state and
-// stand-ins it starts from, and runs its checks once against live DNS.
-// If change is not nil, change then alters the saved state or stand-ins
-// and the checks run a second time. When either check finds no fresh
-// address for a name (see checkOnce), the watcher is thrown away and
-// all of this runs again on a new one, so a failed attempt leaves
-// nothing behind in the saved state, the stand-ins or the notifications.
-func runChecks(
-	t *testing.T,
-	cfg *config.Config,
-	prepare, change func(deps *testDeps),
-) *testDeps {
-	t.Helper()
-
-	var deps *testDeps
-
-	livedns.Retry(t, "watcher checks", func(ctx context.Context) error {
-		var w *watcher.Watcher
-
-		w, deps = newTestWatcher(t, cfg)
-
-		if prepare != nil {
-			prepare(deps)
-		}
-
-		err := checkOnce(ctx, w, deps)
-		if err != nil || change == nil {
-			return err
-		}
-
-		change(deps)
-
-		return checkOnce(ctx, w, deps)
-	})
-
-	return deps
-}
-
-// addresses returns the A and AAAA values saved for a hostname.
-func addresses(hs *state.HostnameState) []string {
-	var ips []string
-
-	for _, nsState := range hs.RecordsByNameserver {
-		ips = append(ips, nsState.Records["A"]...)
-		ips = append(ips, nsState.Records["AAAA"]...)
-	}
-
-	return ips
-}
-
-// assertNotified checks that a notification with this title and
-// priority was sent.
-func assertNotified(
-	t *testing.T,
-	deps *testDeps,
-	title, priority string,
-) {
-	t.Helper()
-
-	notifications := deps.notifier.getNotifications()
-
-	for _, n := range notifications {
-		if n.Title == title && n.Priority == priority {
-			return
-		}
-	}
-
-	t.Errorf(
-		"expected %s notification %q, got: %v",
-		priority, title, notifications,
-	)
-}
-
-// countNotifications counts the notifications sent with this title.
-func countNotifications(deps *testDeps, title string) int {
-	count := 0
-
-	for _, n := range deps.notifier.getNotifications() {
-		if n.Title == title {
-			count++
-		}
-	}
-
-	return count
-}
-
 func TestFirstRunBaseline(t *testing.T) {
 	t.Parallel()
 
@@ -296,12 +270,51 @@ func TestFirstRunBaseline(t *testing.T) {
 	cfg.Domains = []string{testDomain}
 	cfg.Hostnames = []string{testHost}
 
-	deps := runChecks(t, cfg, nil, nil)
+	w, deps := newTestWatcher(t, cfg)
+	setupBaselineMocks(deps)
+
+	w.RunOnce(t.Context())
 
 	assertNoNotifications(t, deps)
 	assertStatePopulated(t, deps)
 }
 
+func setupBaselineMocks(deps *testDeps) {
+	deps.resolver.nsRecords[testDomain] = []string{
+		testNS1,
+		testNS2,
+	}
+	deps.resolver.allRecords[testDomain] = map[string]map[string][]string{
+		testNS1: {"A": {testIPv4}},
+		testNS2: {"A": {testIPv4}},
+	}
+	deps.resolver.allRecords[testHost] = map[string]map[string][]string{
+		testNS1: {"A": {testIPv4}},
+		testNS2: {"A": {testIPv4}},
+	}
+	deps.resolver.ipAddresses[testHost] = []string{
+		testIPv4,
+	}
+	deps.portChecker.results["93.184.216.34:80"] = true
+	deps.portChecker.results["93.184.216.34:443"] = true
+	deps.tlsChecker.certs["93.184.216.34:www.example.com"] = &tlscheck.CertificateInfo{
+		CommonName: testHost,
+		Issuer:     testIssuer,
+		NotAfter:   time.Now().Add(90 * 24 * time.Hour),
+		SubjectAlternativeNames: []string{
+			testHost,
+		},
+	}
+	deps.tlsChecker.certs["93.184.216.34:example.com"] = &tlscheck.CertificateInfo{
+		CommonName: testDomain,
+		Issuer:     testIssuer,
+		NotAfter:   time.Now().Add(90 * 24 * time.Hour),
+		SubjectAlternativeNames: []string{
+			testDomain,
+		},
+	}
+}
+
 func assertNoNotifications(
 	t *testing.T,
 	deps *testDeps,
@@ -348,7 +361,26 @@ func TestDomainPortAndTLSChecks(t *testing.T) {
 	cfg := defaultTestConfig(t)
 	cfg.Domains = []string{testDomain}
 
-	deps := runChecks(t, cfg, nil, nil)
+	w, deps := newTestWatcher(t, cfg)
+
+	deps.resolver.nsRecords[testDomain] = []string{
+		testNS1,
+	}
+	deps.resolver.allRecords[testDomain] = map[string]map[string][]string{
+		testNS1: {"A": {testIPv4}},
+	}
+	deps.portChecker.results["93.184.216.34:80"] = true
+	deps.portChecker.results["93.184.216.34:443"] = true
+	deps.tlsChecker.certs["93.184.216.34:example.com"] = &tlscheck.CertificateInfo{
+		CommonName: testDomain,
+		Issuer:     testIssuer,
+		NotAfter:   time.Now().Add(90 * 24 * time.Hour),
+		SubjectAlternativeNames: []string{
+			testDomain,
+		},
+	}
+
+	w.RunOnce(t.Context())
 
 	snap := deps.state.GetSnapshot()
 
@@ -387,18 +419,50 @@ func TestNSChangeDetection(t *testing.T) {
 	cfg := defaultTestConfig(t)
 	cfg.Domains = []string{testDomain}
 
-	// The saved state lists nameservers that live DNS does not.
-	deps := runChecks(t, cfg, func(deps *testDeps) {
-		deps.state.SetDomainState(testDomain, &state.DomainState{
-			Nameservers: []string{oldNS1, oldNS2},
-		})
-	}, nil)
+	w, deps := newTestWatcher(t, cfg)
 
-	assertNotified(t, deps, "NS Change: "+testDomain, "warning")
+	deps.resolver.nsRecords[testDomain] = []string{
+		testNS1,
+		testNS2,
+	}
+	deps.resolver.allRecords[testDomain] = map[string]map[string][]string{
+		testNS1: {"A": {testIP}},
+		testNS2: {"A": {testIP}},
+	}
+	deps.portChecker.results["1.2.3.4:80"] = false
+	deps.portChecker.results["1.2.3.4:443"] = false
 
-	ds, _ := deps.state.GetDomainState(testDomain)
-	if slices.Contains(ds.Nameservers, oldNS1) {
-		t.Errorf("saved nameservers not updated: %v", ds.Nameservers)
+	ctx := t.Context()
+	w.RunOnce(ctx)
+
+	deps.resolver.mu.Lock()
+	deps.resolver.nsRecords[testDomain] = []string{
+		testNS1,
+		"ns3.example.com.",
+	}
+	deps.resolver.allRecords[testDomain] = map[string]map[string][]string{
+		testNS1:            {"A": {testIP}},
+		"ns3.example.com.": {"A": {testIP}},
+	}
+	deps.resolver.mu.Unlock()
+
+	w.RunOnce(ctx)
+
+	notifications := deps.notifier.getNotifications()
+	if len(notifications) == 0 {
+		t.Error("expected notification for NS change")
+	}
+
+	found := false
+
+	for _, n := range notifications {
+		if n.Priority == "warning" {
+			found = true
+		}
+	}
+
+	if !found {
+		t.Error("expected warning-priority NS change notification")
 	}
 }
 
@@ -408,18 +472,40 @@ func TestRecordChangeDetection(t *testing.T) {
 	cfg := defaultTestConfig(t)
 	cfg.Hostnames = []string{testHost}
 
-	// Between the checks, save for every nameserver an address live DNS
-	// never returns.
-	deps := runChecks(t, cfg, nil, func(deps *testDeps) {
-		hs, _ := deps.state.GetHostnameState(testHost)
-		for _, nsState := range hs.RecordsByNameserver {
-			nsState.Records = map[string][]string{"A": {oldIP}}
-		}
+	w, deps := newTestWatcher(t, cfg)
 
-		deps.state.SetHostnameState(testHost, hs)
-	})
+	deps.resolver.allRecords[testHost] = map[string]map[string][]string{
+		testNS1: {"A": {testIPv4}},
+	}
+	deps.resolver.ipAddresses[testHost] = []string{
+		testIPv4,
+	}
+	deps.portChecker.results["93.184.216.34:80"] = false
+	deps.portChecker.results["93.184.216.34:443"] = false
 
-	assertNotified(t, deps, "Record Change: "+testHost, "warning")
+	ctx := t.Context()
+	w.RunOnce(ctx)
+
+	deps.resolver.mu.Lock()
+	deps.resolver.allRecords[testHost] = map[string]map[string][]string{
+		testNS1: {"A": {"93.184.216.35"}},
+	}
+	deps.resolver.ipAddresses[testHost] = []string{
+		"93.184.216.35",
+	}
+	deps.resolver.mu.Unlock()
+
+	deps.portChecker.mu.Lock()
+	deps.portChecker.results["93.184.216.35:80"] = false
+	deps.portChecker.results["93.184.216.35:443"] = false
+	deps.portChecker.mu.Unlock()
+
+	w.RunOnce(ctx)
+
+	notifications := deps.notifier.getNotifications()
+	if len(notifications) == 0 {
+		t.Error("expected notification for record change")
+	}
 }
 
 func TestPortStateChange(t *testing.T) {
@@ -428,23 +514,38 @@ func TestPortStateChange(t *testing.T) {
 	cfg := defaultTestConfig(t)
 	cfg.Hostnames = []string{testHost}
 
-	// Between the checks, every port closes.
-	deps := runChecks(t, cfg, nil, func(deps *testDeps) {
-		deps.portChecker.mu.Lock()
-		deps.portChecker.closed = true
-		deps.portChecker.mu.Unlock()
-	})
+	w, deps := newTestWatcher(t, cfg)
 
-	hs, _ := deps.state.GetHostnameState(testHost)
-	assertNotified(
-		t, deps, "Port Change: "+addresses(hs)[0]+":443", "warning",
-	)
-}
+	deps.resolver.allRecords[testHost] = map[string]map[string][]string{
+		testNS1: {"A": {testIP}},
+	}
+	deps.resolver.ipAddresses[testHost] = []string{
+		testIP,
+	}
+	deps.portChecker.results["1.2.3.4:80"] = true
+	deps.portChecker.results["1.2.3.4:443"] = true
+	deps.tlsChecker.certs["1.2.3.4:www.example.com"] = &tlscheck.CertificateInfo{
+		CommonName: testHost,
+		Issuer:     testIssuer,
+		NotAfter:   time.Now().Add(90 * 24 * time.Hour),
+		SubjectAlternativeNames: []string{
+			testHost,
+		},
+	}
 
-// expiresInThreeDays makes the TLS checker return certificates that
-// expire within the seven-day warning period.
-func expiresInThreeDays(deps *testDeps) {
-	deps.tlsChecker.notAfter = time.Now().Add(3 * 24 * time.Hour)
+	ctx := t.Context()
+	w.RunOnce(ctx)
+
+	deps.portChecker.mu.Lock()
+	deps.portChecker.results["1.2.3.4:443"] = false
+	deps.portChecker.mu.Unlock()
+
+	w.RunOnce(ctx)
+
+	notifications := deps.notifier.getNotifications()
+	if len(notifications) == 0 {
+		t.Error("expected notification for port state change")
+	}
 }
 
 func TestTLSExpiryWarning(t *testing.T) {
@@ -453,9 +554,49 @@ func TestTLSExpiryWarning(t *testing.T) {
 	cfg := defaultTestConfig(t)
 	cfg.Hostnames = []string{testHost}
 
-	deps := runChecks(t, cfg, expiresInThreeDays, nil)
+	w, deps := newTestWatcher(t, cfg)
 
-	assertNotified(t, deps, "TLS Expiry Warning: "+testHost, "warning")
+	deps.resolver.allRecords[testHost] = map[string]map[string][]string{
+		testNS1: {"A": {testIP}},
+	}
+	deps.resolver.ipAddresses[testHost] = []string{
+		testIP,
+	}
+	deps.portChecker.results["1.2.3.4:80"] = true
+	deps.portChecker.results["1.2.3.4:443"] = true
+	deps.tlsChecker.certs["1.2.3.4:www.example.com"] = &tlscheck.CertificateInfo{
+		CommonName: testHost,
+		Issuer:     testIssuer,
+		NotAfter:   time.Now().Add(3 * 24 * time.Hour),
+		SubjectAlternativeNames: []string{
+			testHost,
+		},
+	}
+
+	ctx := t.Context()
+
+	// First run = baseline
+	w.RunOnce(ctx)
+
+	// Second run should warn about expiry
+	w.RunOnce(ctx)
+
+	notifications := deps.notifier.getNotifications()
+
+	found := false
+
+	for _, n := range notifications {
+		if n.Priority == "warning" {
+			found = true
+		}
+	}
+
+	if !found {
+		t.Errorf(
+			"expected expiry warning, got: %v",
+			notifications,
+		)
+	}
 }
 
 func TestTLSExpiryWarningDedup(t *testing.T) {
@@ -465,25 +606,50 @@ func TestTLSExpiryWarningDedup(t *testing.T) {
 	cfg.Hostnames = []string{testHost}
 	cfg.TLSInterval = 24 * time.Hour
 
-	title := "TLS Expiry Warning: " + testHost
+	w, deps := newTestWatcher(t, cfg)
 
-	// The second check comes within the TLS interval of the first,
-	// so it must not warn again.
-	var warnings int
-
-	deps := runChecks(t, cfg, expiresInThreeDays, func(deps *testDeps) {
-		warnings = countNotifications(deps, title)
-	})
-
-	if warnings == 0 {
-		t.Fatal("expected expiry warnings from the first check")
+	deps.resolver.allRecords[testHost] = map[string]map[string][]string{
+		testNS1: {"A": {testIP}},
+	}
+	deps.resolver.ipAddresses[testHost] = []string{
+		testIP,
+	}
+	deps.portChecker.results["1.2.3.4:80"] = true
+	deps.portChecker.results["1.2.3.4:443"] = true
+	deps.tlsChecker.certs["1.2.3.4:www.example.com"] = &tlscheck.CertificateInfo{
+		CommonName: testHost,
+		Issuer:     testIssuer,
+		NotAfter:   time.Now().Add(3 * 24 * time.Hour),
+		SubjectAlternativeNames: []string{
+			testHost,
+		},
 	}
 
-	got := countNotifications(deps, title)
-	if got != warnings {
+	ctx := t.Context()
+
+	// First run = baseline, no notifications
+	w.RunOnce(ctx)
+
+	// Second run should fire one expiry warning
+	w.RunOnce(ctx)
+
+	// Third run should NOT fire another warning (dedup)
+	w.RunOnce(ctx)
+
+	notifications := deps.notifier.getNotifications()
+
+	expiryCount := 0
+
+	for _, n := range notifications {
+		if n.Title == "TLS Expiry Warning: www.example.com" {
+			expiryCount++
+		}
+	}
+
+	if expiryCount != 1 {
 		t.Errorf(
-			"expected %d expiry warnings (dedup), got %d",
-			warnings, got,
+			"expected exactly 1 expiry warning (dedup), got %d",
+			expiryCount,
 		)
 	}
 }
@@ -491,12 +657,21 @@ func TestTLSExpiryWarningDedup(t *testing.T) {
 func TestGracefulShutdown(t *testing.T) {
 	t.Parallel()
 
-	// No domains or hostnames: stopping does not involve DNS.
 	cfg := defaultTestConfig(t)
+	cfg.Domains = []string{testDomain}
 	cfg.DNSInterval = 100 * time.Millisecond
 	cfg.TLSInterval = 100 * time.Millisecond
 
-	w, _ := newTestWatcher(t, cfg)
+	w, deps := newTestWatcher(t, cfg)
+
+	deps.resolver.nsRecords[testDomain] = []string{
+		testNS1,
+	}
+	deps.resolver.allRecords[testDomain] = map[string]map[string][]string{
+		testNS1: {"A": {testIP}},
+	}
+	deps.portChecker.results["1.2.3.4:80"] = false
+	deps.portChecker.results["1.2.3.4:443"] = false
 
 	ctx, cancel := context.WithCancel(t.Context())
 
@@ -518,52 +693,90 @@ func TestGracefulShutdown(t *testing.T) {
 	}
 }
 
+func setupHostnameIP(
+	deps *testDeps,
+	hostname, ip string,
+) {
+	deps.resolver.allRecords[hostname] = map[string]map[string][]string{
+		testNS1: {"A": {ip}},
+	}
+	deps.portChecker.results[ip+":80"] = true
+	deps.portChecker.results[ip+":443"] = true
+	deps.tlsChecker.certs[ip+":"+hostname] = &tlscheck.CertificateInfo{
+		CommonName:              hostname,
+		Issuer:                  testIssuer,
+		NotAfter:                time.Now().Add(90 * 24 * time.Hour),
+		SubjectAlternativeNames: []string{hostname},
+	}
+}
+
+func updateHostnameIP(deps *testDeps, hostname, ip string) {
+	deps.resolver.mu.Lock()
+	deps.resolver.allRecords[hostname] = map[string]map[string][]string{
+		testNS1: {"A": {ip}},
+	}
+	deps.resolver.mu.Unlock()
+
+	deps.portChecker.mu.Lock()
+	deps.portChecker.results[ip+":80"] = true
+	deps.portChecker.results[ip+":443"] = true
+	deps.portChecker.mu.Unlock()
+
+	deps.tlsChecker.mu.Lock()
+	deps.tlsChecker.certs[ip+":"+hostname] = &tlscheck.CertificateInfo{
+		CommonName:              hostname,
+		Issuer:                  testIssuer,
+		NotAfter:                time.Now().Add(90 * 24 * time.Hour),
+		SubjectAlternativeNames: []string{hostname},
+	}
+	deps.tlsChecker.mu.Unlock()
+}
+
 func TestDNSRunsBeforePortAndTLSChecks(t *testing.T) {
 	t.Parallel()
 
 	cfg := defaultTestConfig(t)
 	cfg.Hostnames = []string{testHost}
 
-	// The saved state says the last check found testHost at oldIP.
-	deps := runChecks(t, cfg, func(deps *testDeps) {
-		deps.state.SetHostnameState(testHost, &state.HostnameState{
-			RecordsByNameserver: map[string]*state.NameserverRecordState{
-				oldNS1: {
-					Records: map[string][]string{"A": {oldIP}},
-					Status:  "ok",
-				},
-			},
-		})
-	}, nil)
+	w, deps := newTestWatcher(t, cfg)
+
+	setupHostnameIP(deps, testHost, "10.0.0.1")
+
+	ctx := t.Context()
+	w.RunOnce(ctx)
 
 	snap := deps.state.GetSnapshot()
-
-	if _, ok := snap.Ports[oldIP+":80"]; ok {
-		t.Error("port check used stale DNS: found " + oldIP + ":80")
+	if _, ok := snap.Ports["10.0.0.1:80"]; !ok {
+		t.Fatal("expected port state for 10.0.0.1:80")
 	}
 
-	// Port and TLS checks must use the addresses this check found.
-	for _, ip := range addresses(snap.Hostnames[testHost]) {
-		if _, ok := snap.Ports[ip+":80"]; !ok {
-			t.Error("port check used stale DNS: missing " + ip + ":80")
-		}
+	// DNS changes to a new IP; port and TLS must pick it up.
+	updateHostnameIP(deps, testHost, "10.0.0.2")
 
-		certKey := ip + ":443:" + testHost
-		if _, ok := snap.Certificates[certKey]; !ok {
-			t.Error("TLS check used stale DNS: missing " + certKey)
-		}
+	w.RunOnce(ctx)
+
+	snap = deps.state.GetSnapshot()
+
+	if _, ok := snap.Ports["10.0.0.2:80"]; !ok {
+		t.Error("port check used stale DNS: missing 10.0.0.2:80")
+	}
+
+	certKey := "10.0.0.2:443:www.example.com"
+	if _, ok := snap.Certificates[certKey]; !ok {
+		t.Error("TLS check used stale DNS: missing " + certKey)
 	}
 }
 
 func TestSendTestNotification_Enabled(t *testing.T) {
 	t.Parallel()
 
-	// No domains or hostnames: the startup notification does not
-	// involve DNS.
 	cfg := defaultTestConfig(t)
+	cfg.Domains = []string{testDomain}
+	cfg.Hostnames = []string{testHost}
 	cfg.SendTestNotification = true
 
 	w, deps := newTestWatcher(t, cfg)
+	setupBaselineMocks(deps)
 
 	w.RunOnce(t.Context())
 
@@ -584,11 +797,14 @@ func TestSendTestNotification_ViaRun(t *testing.T) {
 	t.Parallel()
 
 	cfg := defaultTestConfig(t)
+	cfg.Domains = []string{testDomain}
+	cfg.Hostnames = []string{testHost}
 	cfg.SendTestNotification = true
 	cfg.DNSInterval = 24 * time.Hour
 	cfg.TLSInterval = 24 * time.Hour
 
 	w, deps := newTestWatcher(t, cfg)
+	setupBaselineMocks(deps)
 
 	ctx, cancel := context.WithCancel(t.Context())
 
@@ -628,11 +844,14 @@ func TestSendTestNotification_Disabled(t *testing.T) {
 	t.Parallel()
 
 	cfg := defaultTestConfig(t)
+	cfg.Domains = []string{testDomain}
+	cfg.Hostnames = []string{testHost}
 	cfg.SendTestNotification = false
 	cfg.DNSInterval = 24 * time.Hour
 	cfg.TLSInterval = 24 * time.Hour
 
 	w, deps := newTestWatcher(t, cfg)
+	setupBaselineMocks(deps)
 
 	ctx, cancel := context.WithCancel(t.Context())
 
@@ -665,22 +884,32 @@ func TestNSFailureAndRecovery(t *testing.T) {
 	cfg := defaultTestConfig(t)
 	cfg.Hostnames = []string{testHost}
 
-	// Between the checks, save every nameserver the first check found
-	// as failed, and add, as answering, one that live DNS does not list.
-	deps := runChecks(t, cfg, nil, func(deps *testDeps) {
-		hs, _ := deps.state.GetHostnameState(testHost)
-		for _, nsState := range hs.RecordsByNameserver {
-			nsState.Status = "error"
-		}
+	w, deps := newTestWatcher(t, cfg)
 
-		hs.RecordsByNameserver[oldNS1] = &state.NameserverRecordState{
-			Records: map[string][]string{"A": {oldIP}},
-			Status:  "ok",
-		}
+	deps.resolver.allRecords[testHost] = map[string]map[string][]string{
+		testNS1: {"A": {testIP}},
+		testNS2: {"A": {testIP}},
+	}
+	deps.resolver.ipAddresses[testHost] = []string{
+		testIP,
+	}
+	deps.portChecker.results["1.2.3.4:80"] = false
+	deps.portChecker.results["1.2.3.4:443"] = false
 
-		deps.state.SetHostnameState(testHost, hs)
-	})
+	ctx := t.Context()
 
-	assertNotified(t, deps, "NS Failure: "+testHost, "error")
-	assertNotified(t, deps, "NS Recovery: "+testHost, "success")
+	w.RunOnce(ctx)
+
+	deps.resolver.mu.Lock()
+	deps.resolver.allRecords[testHost] = map[string]map[string][]string{
+		testNS1: {"A": {testIP}},
+	}
+	deps.resolver.mu.Unlock()
+
+	w.RunOnce(ctx)
+
+	notifications := deps.notifier.getNotifications()
+	if len(notifications) == 0 {
+		t.Error("expected notification for NS disappearance")
+	}
 }

script/cibuild

@@ -1,18 +1,14 @@
 #!/bin/sh
 # script/cibuild: run the CI build. The Dockerfile's lint stage runs
 # make fmt-check and golangci-lint; its builder stage runs make test
-# and make build.
-#
-# --no-cache-filter=lint,builder runs both stages on every invocation;
-# otherwise an unchanged tree is served from the layer cache and passes
-# without linting or querying live DNS.
+# and make build. A successful build implies all of those passed.
 set -eu
 
 ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
 
 main() {
     cd "$ROOT"
-    docker build --no-cache-filter=lint,builder .
+    docker build .
 }
 
 main "$@"

script/docker

@@ -1,10 +1,6 @@
 #!/bin/sh
 # script/docker: build the Docker image tagged with the project name.
-# The tag comes from script/projectname.
-#
-# --no-cache-filter=lint,builder runs the lint stage and the builder
-# stage (make test) on every invocation; otherwise an unchanged tree is
-# served from the layer cache without linting or querying live DNS.
+# Identical in all repos; the tag comes from script/projectname.
 set -eu
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
@@ -12,7 +8,7 @@ ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
 
 main() {
     cd "$ROOT"
-    docker build --no-cache-filter=lint,builder -t "$("$SCRIPT_DIR/projectname")" .
+    docker build -t "$("$SCRIPT_DIR/projectname")" .
 }
 
 main "$@"