resolver: a nameserver with a failed record type is not nodata (closes #253)

classifyResponse set nodata when every record type that answered had
no records, even when another type's query got no usable reply. That
type is listed in FailedTypes and its records are unknown, so the
nameserver has not said it has none. It now stays ok, the status
README describes for a nameserver with a failed type, and nodata is
set only when no type failed. The watcher saved nodata as ok already,
so saved state is unchanged; the live test that rejects nodata no
longer fails when one of a nameserver's queries is lost.

Model: opus-5-5

.dockerignore

@@ -1,6 +1,9 @@
-.git/
+# .git is sent, without its config: the builder stage derives the version it
+# stamps into the binary from it, and `git describe` does not need the config,
+# which can hold a credential (a password in the remote URL, a CI token). No
+# tracked file may be listed here: git in the build would see it as deleted
+# and mark the version -dirty, and an excluded .md would silently drop out of
+# the prettier check in Dockerfile.fmt.
+.git/config
 bin/
-*.md
-LICENSE
-.editorconfig
-.gitignore
+node_modules/

.gitea/workflows/check.yml

@@ -1,9 +1,17 @@
 name: check
 on: [push]
+# A new push to a branch cancels that branch's older run, queued or running;
+# runs on other branches, `next` and `main` among them, are left alone.
+concurrency:
+    group: ${{ github.workflow }}-${{ github.ref }}
+    cancel-in-progress: true
 jobs:
     check:
         runs-on: ubuntu-latest
         steps:
             # actions/checkout v4.2.2, 2026-02-28
             - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+              # script/cibuild needs no token, so none is left in .git/config.
+              with:
+                  persist-credentials: false
             - run: script/cibuild

.gitignore

@@ -1,4 +1,5 @@
 bin/
+node_modules/
 vendor/
 data/
 .env

.prettierignore

@@ -0,0 +1,5 @@
+bin/
+data/
+node_modules/
+.claude/
+static/css/tailwind.min.css

.prettierrc

@@ -0,0 +1,4 @@
+{
+    "tabWidth": 4,
+    "proseWrap": "always"
+}

Dockerfile

@@ -1,7 +1,9 @@
 # Lint stage - fast feedback on lint issues, before the build starts.
 # 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.
+# no docker daemon inside a docker build. For the same reason this stage
+# runs only the Go half of `make fmt-check`; script/cibuild runs the
+# markdown half after this 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
@@ -12,7 +14,7 @@ RUN go mod download
 
 COPY . .
 
-RUN make fmt-check
+RUN script/fmt-check-go
 RUN golangci-lint run --config .golangci.yml ./...
 
 # Build stage
@@ -22,6 +24,11 @@ FROM golang@sha256:f6751d823c26342f9506c03797d2527668d095b0a15f1862cddb4d927a7a4
 
 RUN apk add --no-cache git make gcc musl-dev binutils-gold
 
+# A build context sent as a tar archive keeps its files' owners, and git
+# refuses to read a checkout owned by another user. Trust this one
+# whoever owns it.
+RUN git config --system --add safe.directory /src
+
 # Force BuildKit to run the lint stage before proceeding
 COPY --from=lint /src/go.sum /dev/null
 
@@ -34,11 +41,26 @@ COPY . .
 # Run the tests - build fails if any test fails
 RUN make test
 
-# Build the binary. .dockerignore leaves out .git, so `git describe` in
-# the Makefile cannot find the version here: script/docker passes it as
-# --build-arg VERSION, and a build that passes none reports `dev`.
-ARG VERSION=dev
-RUN make build VERSION="${VERSION}"
+# Version stamped into the binary: the VERSION build arg when one is
+# given and not empty (script/docker passes one), otherwise what
+# `git describe` says of the .git in the build context, so a plain
+# `docker build .` of a clone stamps its tag or short commit. The build
+# arg reaches make through the environment.
+ARG VERSION
+
+# A context that carries .git, as a directory or as a file, must yield a
+# real version: one that is empty, `dev` or `unknown` cannot be traced
+# back to a commit.
+RUN version="$(make version)"; \
+    if [ -e .git ]; then \
+        case "$version" in \
+            "" | dev | unknown) \
+                echo "version is \"$version\" although the build context carries .git" >&2; \
+                exit 1 ;; \
+        esac; \
+    fi
+
+RUN make build
 
 # Runtime stage
 # alpine 3.21, 2026-02-28

Dockerfile.fmt

@@ -0,0 +1,54 @@
+# prettier over the markdown, in a container, so it is never installed
+# on the host. script/fmt-check-markdown builds the fmt-check stage;
+# script/fmt builds fmt-out and takes the formatted files back.
+
+# node:22-bookworm-slim, 2026-09-05
+FROM node:22-bookworm-slim@sha256:83f487e0a63425e5b4d146fb5e5be574bcbe1b7b843d3ebafdd95eaf7767a7e5 AS nodedeps
+
+# prettier lives outside /src so that a `COPY . .` of the repo cannot
+# overwrite it, and so that node_modules never appears in the tree
+# prettier is about to walk.
+WORKDIR /tools
+
+# package.json pins the version and yarn.lock pins the bytes:
+# --frozen-lockfile installs exactly the lockfile's resolution and fails
+# if package.json disagrees with it, so the tool cannot float between
+# runs. yarn is the one in the image above.
+COPY package.json yarn.lock ./
+RUN yarn install --frozen-lockfile --non-interactive --no-progress
+
+ENV PATH="/tools/node_modules/.bin:${PATH}"
+
+WORKDIR /src
+
+# Read-only markdown check. Must match $stage in
+# script/fmt-check-markdown.
+FROM nodedeps AS fmt-check
+
+COPY . .
+
+# --config, not discovery: a .prettierrc that failed to arrive would
+# otherwise leave prettier on its defaults, where proseWrap is "preserve"
+# and every wrap this check exists to enforce passes. Missing the file is
+# a hard error instead. --no-editorconfig so that .prettierrc alone sets
+# the style.
+RUN prettier --config .prettierrc --no-editorconfig --check "**/*.md"
+
+# Write path. Not a check: script/fmt builds this and takes the files.
+FROM nodedeps AS fmt
+
+COPY . .
+
+RUN prettier --config .prettierrc --no-editorconfig --write "**/*.md"
+
+# Only the markdown leaves, with its paths intact, so that the export
+# below cannot put anything else back over the caller's working tree.
+RUN mkdir -p /out && cd /src && \
+    find . -name '*.md' -type f -exec cp --parents '{}' /out/ ';'
+
+# Export target: `docker build --target fmt-out --output type=local`
+# writes /out's tree into a directory on the client, which is how
+# script/fmt gets formatted markdown back without a bind mount.
+# Must match $stage in script/fmt.
+FROM scratch AS fmt-out
+COPY --from=fmt /out/ /

Makefile

@@ -1,9 +1,13 @@
-.PHONY: all bootstrap setup build lint fmt fmt-check test check clean hooks docker
+.PHONY: all bootstrap setup build version lint fmt fmt-check test check clean hooks docker
 
 BINARY := dnswatcher
-# `make build VERSION=...` overrides this; the Dockerfile does so, as the
-# image has no .git to describe.
-VERSION := $(shell git describe --tags --always --dirty 2>/dev/null || echo "dev")
+# VERSION given on the command line (`make build VERSION=...`) or in the
+# environment, which is how the Dockerfile's VERSION build arg arrives,
+# wins over what `git describe` says of this checkout. An empty one counts
+# as not given; `override` is what replaces an empty command-line value.
+ifeq ($(VERSION),)
+override VERSION := $(shell git describe --tags --always --dirty 2>/dev/null || echo "dev")
+endif
 LDFLAGS := -X main.Version=$(VERSION)
 
 # Standard targets are thin shims; the implementations live in script/
@@ -21,6 +25,10 @@ setup:
 build:
 	go build -ldflags "$(LDFLAGS)" -o bin/$(BINARY) ./cmd/dnswatcher
 
+# Prints the version `make build` stamps; the Dockerfile checks it.
+version:
+	@echo "$(VERSION)"
+
 test:
 	@script/test
 

TESTING.md

@@ -2,44 +2,43 @@
 
 ## 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.
+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.
 
 ### Rationale
 
-The resolver performs iterative resolution from root nameservers through
-the full delegation chain. Mocked responses cannot faithfully represent
-the variety of real-world DNS behavior (truncation, referrals, glue
-records, DNSSEC, varied response times, EDNS, etc.). Testing against
-real servers ensures the resolver works correctly in production.
+The resolver performs iterative resolution from root nameservers through the
+full delegation chain. Mocked responses cannot faithfully represent the variety
+of real-world DNS behavior (truncation, referrals, glue records, DNSSEC, varied
+response times, EDNS, etc.). Testing against real servers ensures the resolver
+works correctly in production.
 
 ### Constraints
 
 - Tests hit real DNS infrastructure and require network access
-- Test duration depends on network conditions; timeout tuning keeps
-  the suite within the 60-second target
-- Query timeout is calibrated to 3× maximum antipodal RTT (~300ms)
-  plus processing margin
+- Test duration depends on network conditions; timeout tuning keeps the suite
+  within the 60-second target
+- 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/livednstest`,
-  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
+- Live lookups that expect an answer go through `internal/livednstest`, 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, 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 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
-  replays a previous run's output without querying anything, so a
-  cached pass is not evidence that live resolution works
+- **Do not remove `-count=1` from `script/test`** — Go's test cache replays a
+  previous run's output without querying anything, so a cached pass is not
+  evidence that live resolution works
 - **Do not modify linter configuration** to suppress findings

TODO.md

@@ -1,12 +1,12 @@
 # Workflow
 
-* branch (from `next`)
-* do the work in Next Step
-* move Next Step to the top of Completed Steps
-* move the top item of Future Steps into Next Step
-* commit (`TODO.md` changes in the same commit as the work)
-* push
-* open a PR against `next`
+- branch (from `next`)
+- do the work in Next Step
+- move Next Step to the top of Completed Steps
+- move the top item of Future Steps into Next Step
+- commit (`TODO.md` changes in the same commit as the work)
+- push
+- open a PR against `next`
 
 # Status
 
@@ -15,13 +15,92 @@ on the 1.0 milestone: https://git.eeqj.de/sneak/dnswatcher/milestone/7
 
 # Next Step
 
-NS failure and NS recovery notifications:
-https://git.eeqj.de/sneak/dnswatcher/issues/104
+trial run of the finished image: https://git.eeqj.de/sneak/dnswatcher/issues/149
 
 # Completed Steps
 
+- 2026-10-02: a nameserver whose query for one record type failed while the
+  others answered with no records is `ok`, not `nodata` (closes #253).
+- 2026-10-02: a domain that does not exist is shown so, with no nameservers; no
+  name gets a parent's nameservers when its own did not answer (closes #222).
+- 2026-10-02: the refused-query test sends one query to four operators' public
+  resolvers in turn until one replies, not eight to one operator (closes #251).
+- 2026-10-02: a name removed from `DNSWATCHER_TARGETS` leaves the state, and so
+  the dashboard and API, at startup, before the first check (closes #223).
+- 2026-10-02: a record type whose query to a nameserver fails keeps its previous
+  records and alerts nothing; the other types are still saved (closes #231).
+- 2026-10-02: a Port Change notification lists the port's domains on a
+  `Domains:` line and its hostnames on a `Hostnames:` line (closes #248).
+- 2026-10-02: the dashboard's Ports table and `/api/v1/status` port entries list
+  a port's domains apart from its hostnames (closes #245).
+- 2026-10-02: nameservers a referral names without addresses are looked up,
+  three deep at most; `pool.ntp.org`'s nameservers resolve (closes #221).
+- 2026-10-02: an apex domain is not counted or listed as a hostname; its records
+  show under Domains, and notifications about them say `Domain:` (closes #224).
+- 2026-10-02: the dashboard lists each nameserver's record types in one fixed
+  order, the README's, then any other type, not a random one (closes #226).
+- 2026-10-02: the dashboard and `/api/v1/status` show why a nameserver query or
+  a certificate check failed, which only the state file showed (closes #225).
+- 2026-10-02: a name's CNAME is stored once per nameserver, not once per record
+  type asked for; a state file with repeats loads each value once (closes #220).
+- 2026-10-02: a DNS lookup that shutdown cuts short logs no error; one that
+  fails otherwise, or runs out of time, still does (closes #229).
+- 2026-10-02: Record Change and Inconsistency notifications list only the record
+  types that differ, each with its values as plain text (closes #219).
+- 2026-10-02: the startup notification no longer says every notification
+  endpoint works; it says it is a test sent to each of them (closes #230).
+- 2026-10-02: a Mattermost webhook that answers an HTTP error is logged as
+  `mattermost notification failed`, not as a Slack failure (closes #227).
+- 2026-10-02: durations in the log are written as text such as `2m0s`, not as a
+  bare count of nanoseconds (closes #228).
+- 2026-10-02: a watched name whose nameservers answer with a CNAME and no
+  address gets port and TLS checks at the end of its CNAME chain (closes #203).
+- 2026-10-02: a resolver test that reads one record type from a nameserver's
+  answer asks again when that type is missing from it (closes #218).
+- 2026-10-02: a plain `docker build .` of a clone stamps its tag or short
+  commit, not `dev`: the build context now carries `.git` (closes #210).
+- 2026-10-02: a query a server refuses is not resent asking for recursion, and
+  every root server refusing is reported as DNS interception (closes #206).
+- 2026-10-02: a push to a branch cancels that branch's older CI run, and the
+  checkout leaves no token in `.git/config` (closes #216).
+- 2026-10-02: watcher tests send far fewer queries and a live attempt may take
+  18s; nameserver addresses are asked only for A, AAAA, CNAME (closes #214).
+- 2026-10-02: the resolver tries root servers, and every other server list it
+  walks, in a random order each time, not always from the top (closes #138).
+- 2026-10-02: a name listed more than once in `DNSWATCHER_TARGETS`, in any
+  letter case or with a trailing dot, is watched once (closes #207).
+- 2026-10-01: README checked against the code and corrected: metrics, CORS,
+  notification retries, CNAMEs, state file fields, Design tree (closes #108).
+- 2026-10-01: a certificate within the expiry warning period is warned about on
+  every TLS check, where some checks used to skip it at random (closes #204).
+- 2026-10-01: a domain's NS set is its delegation from the parent zone's
+  servers, not whichever of its own servers answered first (closes #200).
+- 2026-10-01: README has Getting Started, Rationale and TODO sections, and its
+  Architecture section is now Design, in the order policy sets (closes #173).
+- 2026-10-01: a zone's server that answers SERVFAIL or a referral leading no
+  closer is passed over for the next, as one that times out is (closes #197).
+- 2026-10-01: when none of a configured name's nameservers answered, the port
+  state saved for its addresses is kept, not removed (closes #193).
+- 2026-10-01: `ResolveIPAddresses` returns an error, not no addresses, when no
+  nameserver of the name's zone answered (closes #190).
+- 2026-10-01: `make fmt` and `make fmt-check` cover Markdown with prettier, run
+  in Docker at the version pinned by `yarn.lock` (closes #119).
+- 2026-10-01: `make fmt-check` fails on a file `goimports` would change; both
+  format scripts run `goimports` at its pinned commit, not from `PATH` (#119).
+- 2026-10-01: a hostname is queried at the servers of the zone it is in, found
+  by following delegations for the name, not its last two labels (closes #189).
+- 2026-10-01: each nameserver's addresses are saved with its domain, and a
+  change while it stays in the delegation is notified (closes #105).
+- 2026-10-01: the watcher saves state when it stops, and shutdown waits for that
+  save, so it no longer relies on the state's own stop hook (closes #114).
+- 2026-10-01: `DNSWATCHER_SENTRY_DSN` reports panics in HTTP handlers to Sentry,
+  and a DSN Sentry cannot parse stops startup (closes #107).
+- 2026-10-01: a port or TLS check that shutdown cuts short saves nothing and
+  sends no notification, as a cut-short DNS lookup already did (closes #185).
 - 2026-10-01: the client address from `X-Forwarded-For` is the last entry that
   is not a trusted proxy, not the first, which the client sets (closes #181).
+- 2026-10-01: a nameserver that does not answer is saved as `error` with the
+  reason, and NS failure and NS recovery are notified (closes #104).
 - 2026-10-01: a `DNSWATCHER_DNS_INTERVAL` or `DNSWATCHER_TLS_INTERVAL` that is
   not a positive duration stops startup; empty means the default (closes #177).
 - 2026-10-01: `/metrics` allows each client address 30 requests a minute,
@@ -98,18 +177,6 @@ https://git.eeqj.de/sneak/dnswatcher/issues/104
 
 # Future Steps
 
-- nameserver IP address changes: https://git.eeqj.de/sneak/dnswatcher/issues/105
-- `DNSWATCHER_SENTRY_DSN` does nothing:
-  https://git.eeqj.de/sneak/dnswatcher/issues/107
-- trial run of the finished image:
-  https://git.eeqj.de/sneak/dnswatcher/issues/149
 - 1.0 readiness: run it with a real config and read the logs:
   https://git.eeqj.de/sneak/dnswatcher/issues/66
-- `goimports` in `make fmt-check`, Markdown formatting:
-  https://git.eeqj.de/sneak/dnswatcher/issues/119
-- final state save at shutdown: https://git.eeqj.de/sneak/dnswatcher/issues/114
-- README accuracy sweep: https://git.eeqj.de/sneak/dnswatcher/issues/108
-- README sections required by policy:
-  https://git.eeqj.de/sneak/dnswatcher/issues/173
-- fixed root server order: https://git.eeqj.de/sneak/dnswatcher/issues/138
 - review toward 1.0: https://git.eeqj.de/sneak/dnswatcher/issues/144

go.mod

@@ -4,6 +4,7 @@ go 1.25.5
 
 require (
 	github.com/99designs/basicauth-go v0.0.0-20230316000542-bf6f9cbbf0f8
+	github.com/getsentry/sentry-go v0.49.0
 	github.com/go-chi/chi/v5 v5.2.5
 	github.com/go-chi/cors v1.2.2
 	github.com/go-chi/httprate v0.16.0
@@ -13,20 +14,20 @@ require (
 	github.com/spf13/viper v1.21.0
 	github.com/stretchr/testify v1.11.1
 	go.uber.org/fx v1.24.0
-	golang.org/x/net v0.50.0
-	golang.org/x/sync v0.19.0
+	golang.org/x/net v0.56.0
+	golang.org/x/sync v0.21.0
 )
 
 require (
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
-	github.com/davecgh/go-spew v1.1.1 // indirect
+	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/fsnotify/fsnotify v1.9.0 // indirect
 	github.com/go-viper/mapstructure/v2 v2.4.0 // indirect
 	github.com/klauspost/cpuid/v2 v2.2.10 // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/pelletier/go-toml/v2 v2.2.4 // indirect
-	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/prometheus/client_model v0.6.2 // indirect
 	github.com/prometheus/common v0.66.1 // indirect
 	github.com/prometheus/procfs v0.16.1 // indirect
@@ -42,10 +43,10 @@ require (
 	go.uber.org/zap v1.26.0 // indirect
 	go.yaml.in/yaml/v2 v2.4.2 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
-	golang.org/x/mod v0.32.0 // indirect
-	golang.org/x/sys v0.41.0 // indirect
-	golang.org/x/text v0.34.0 // indirect
-	golang.org/x/tools v0.41.0 // indirect
+	golang.org/x/mod v0.37.0 // indirect
+	golang.org/x/sys v0.46.0 // indirect
+	golang.org/x/text v0.39.0 // indirect
+	golang.org/x/tools v0.47.0 // indirect
 	google.golang.org/protobuf v1.36.8 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

go.sum

@@ -4,18 +4,22 @@ github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
 github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
-github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
-github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
+github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/frankban/quicktest v1.14.6 h1:7Xjx+VpznH+oBnejlPUj8oUpdxnVs4f8XU8WnHkI4W8=
 github.com/frankban/quicktest v1.14.6/go.mod h1:4ptaffx2x8+WTWXmUCuVU6aPUX1/Mz7zb5vbUoiM6w0=
 github.com/fsnotify/fsnotify v1.9.0 h1:2Ml+OJNzbYCTzsxtv8vKSFD9PbJjmhYF14k/jKC7S9k=
 github.com/fsnotify/fsnotify v1.9.0/go.mod h1:8jBTzvmWwFyi3Pb8djgCCO5IBqzKJ/Jwo8TRcHyHii0=
+github.com/getsentry/sentry-go v0.49.0 h1:Ehejknu1l023Ub7QoRBVLAI7g3Jnhqku4oWx4B4Sh5s=
+github.com/getsentry/sentry-go v0.49.0/go.mod h1:nuMJAoCfe1u0Bts2ocyNI+TW8HT84vRMqwA5Qq/SKUI=
 github.com/go-chi/chi/v5 v5.2.5 h1:Eg4myHZBjyvJmAFjFvWgrqDTXFyOzjj7YIm3L3mu6Ug=
 github.com/go-chi/chi/v5 v5.2.5/go.mod h1:X7Gx4mteadT3eDOMTsXzmI4/rwUpOwBHLpAfupzFJP0=
 github.com/go-chi/cors v1.2.2 h1:Jmey33TE+b+rB7fT8MUy1u0I4L+NARQlK6LhzKPSyQE=
 github.com/go-chi/cors v1.2.2/go.mod h1:sSbTewc+6wYHBBCW7ytsFSn836hqM7JxpglAy2Vzc58=
 github.com/go-chi/httprate v0.16.0 h1:8V5DH9j6pSK6UQoBsTpvMyFxycqaKEIToyPKzHJjUa8=
 github.com/go-chi/httprate v0.16.0/go.mod h1:A8lo+qRhk+s9LiuP5saS7XCGDXRXMcrueq0NfIuCa/I=
+github.com/go-errors/errors v1.4.2 h1:J6MZopCL4uSllY1OfXM374weqZFFItUbrImctkmUxIA=
+github.com/go-errors/errors v1.4.2/go.mod h1:sIVyrIiJhuEF+Pj9Ebtd6P/rEYROXFi3BopGUQ5a5Og=
 github.com/go-viper/mapstructure/v2 v2.4.0 h1:EBsztssimR/CONLSZZ04E8qAkxNYq4Qp9LvH92wZUgs=
 github.com/go-viper/mapstructure/v2 v2.4.0/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=
 github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
@@ -38,8 +42,12 @@ github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
 github.com/pelletier/go-toml/v2 v2.2.4 h1:mye9XuhQ6gvn5h28+VilKrrPoQVanw5PMw/TB0t5Ec4=
 github.com/pelletier/go-toml/v2 v2.2.4/go.mod h1:2gIqNv+qfxSVS7cM2xJQKtLSTLUE9V8t9Stt+h56mCY=
-github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
-github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/pingcap/errors v0.11.4 h1:lFuQV/oaUMGcD2tqt+01ROSmJs75VG1ToEOkZIZ4nE4=
+github.com/pingcap/errors v0.11.4/go.mod h1:Oi8TUi2kEtXXLMJk9l1cGmz20kV3TaQ0usTwv5KuLY8=
+github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
+github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
+github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
+github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/prometheus/client_golang v1.23.2 h1:Je96obch5RDVy3FDMndoUsjAhG5Edi49h0RJWRi/o0o=
 github.com/prometheus/client_golang v1.23.2/go.mod h1:Tb1a6LWHB3/SPIzCoaDXI4I8UHKeFTEQ1YCr+0Gyqmg=
 github.com/prometheus/client_model v0.6.2 h1:oBsgwpGs7iVziMvrGhE53c/GrLUsZdHnqNwqPLxwZyk=
@@ -48,8 +56,8 @@ github.com/prometheus/common v0.66.1 h1:h5E0h5/Y8niHc5DlaLlWLArTQI7tMrsfQjHV+d9Z
 github.com/prometheus/common v0.66.1/go.mod h1:gcaUsgf3KfRSwHY4dIMXLPV0K/Wg1oZ8+SbZk/HH/dA=
 github.com/prometheus/procfs v0.16.1 h1:hZ15bTNuirocR6u0JZ6BAHHmwS1p8B4P6MRqxtzMyRg=
 github.com/prometheus/procfs v0.16.1/go.mod h1:teAbpZRB1iIAJYREa1LsoWUXykVXA1KlTmWl8x/U+Is=
-github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
-github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
+github.com/rogpeppe/go-internal v1.14.1 h1:UQB4HGPB6osV0SQTLymcB4TgvyWu6ZyliaW0tI/otEQ=
+github.com/rogpeppe/go-internal v1.14.1/go.mod h1:MaRKkUm5W0goXpeCfT7UZI6fk/L7L7so1lCWt35ZSgc=
 github.com/sagikazarmark/locafero v0.11.0 h1:1iurJgmM9G3PA/I+wWYIOw/5SyBtxapeHDcg+AAIFXc=
 github.com/sagikazarmark/locafero v0.11.0/go.mod h1:nVIGvgyzw595SUSUE6tvCp3YYTeHs15MvlmU87WwIik=
 github.com/sourcegraph/conc v0.3.1-0.20240121214520-5f936abd7ae8 h1:+jumHNA0Wrelhe64i8F6HNlS8pkoyMv5sreGx2Ry5Rw=
@@ -84,18 +92,18 @@ go.yaml.in/yaml/v2 v2.4.2 h1:DzmwEr2rDGHl7lsFgAHxmNz/1NlQ7xLIrlN2h5d1eGI=
 go.yaml.in/yaml/v2 v2.4.2/go.mod h1:081UH+NErpNdqlCXm3TtEran0rJZGxAYx9hb/ELlsPU=
 go.yaml.in/yaml/v3 v3.0.4 h1:tfq32ie2Jv2UxXFdLJdh3jXuOzWiL1fo0bu/FbuKpbc=
 go.yaml.in/yaml/v3 v3.0.4/go.mod h1:DhzuOOF2ATzADvBadXxruRBLzYTpT36CKvDb3+aBEFg=
-golang.org/x/mod v0.32.0 h1:9F4d3PHLljb6x//jOyokMv3eX+YDeepZSEo3mFJy93c=
-golang.org/x/mod v0.32.0/go.mod h1:SgipZ/3h2Ci89DlEtEXWUk/HteuRin+HHhN+WbNhguU=
-golang.org/x/net v0.50.0 h1:ucWh9eiCGyDR3vtzso0WMQinm2Dnt8cFMuQa9K33J60=
-golang.org/x/net v0.50.0/go.mod h1:UgoSli3F/pBgdJBHCTc+tp3gmrU4XswgGRgtnwWTfyM=
-golang.org/x/sync v0.19.0 h1:vV+1eWNmZ5geRlYjzm2adRgW2/mcpevXNg50YZtPCE4=
-golang.org/x/sync v0.19.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI=
-golang.org/x/sys v0.41.0 h1:Ivj+2Cp/ylzLiEU89QhWblYnOE9zerudt9Ftecq2C6k=
-golang.org/x/sys v0.41.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
-golang.org/x/text v0.34.0 h1:oL/Qq0Kdaqxa1KbNeMKwQq0reLCCaFtqu2eNuSeNHbk=
-golang.org/x/text v0.34.0/go.mod h1:homfLqTYRFyVYemLBFl5GgL/DWEiH5wcsQ5gSh1yziA=
-golang.org/x/tools v0.41.0 h1:a9b8iMweWG+S0OBnlU36rzLp20z1Rp10w+IY2czHTQc=
-golang.org/x/tools v0.41.0/go.mod h1:XSY6eDqxVNiYgezAVqqCeihT4j1U2CCsqvH3WhQpnlg=
+golang.org/x/mod v0.37.0 h1:vF1DjpVEshcIqoEaauuHebaLk1O1forxjxBaVn884JQ=
+golang.org/x/mod v0.37.0/go.mod h1:m8S8VeM9r4dzDwjrKO0a1sZP3YjeMamRRlD+fmR2Q/0=
+golang.org/x/net v0.56.0 h1:Rw8j/hFzGvJUZwNBXnAtf5sVDVt+65SK2C7IxCxZt5o=
+golang.org/x/net v0.56.0/go.mod h1:D3Ku6r+V6JROoZK144D2XfMHFcMq/0zSfLelVTCFKec=
+golang.org/x/sync v0.21.0 h1:HLII4xRRTtCRkxYp4HNFF0Js/Og6q2i++KXbg0gHCwM=
+golang.org/x/sync v0.21.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=
+golang.org/x/sys v0.46.0 h1:noSf2Fq6F8DBgS+LysIkx7rIExoNHJsxOAtPp4rthXw=
+golang.org/x/sys v0.46.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
+golang.org/x/text v0.39.0 h1:UbZz4pLOvn600D6Oh6GGEI6VAmndrEBLv8/6BEXzyus=
+golang.org/x/text v0.39.0/go.mod h1:3UwRclnC2g0TU9x8PZiyfOajCd1zaUNHF9cvqcQZ+ZM=
+golang.org/x/tools v0.47.0 h1:7Kn5x/d1svx/PzryTsqeoZN4TZwqeH5pGWjefhLi/1Q=
+golang.org/x/tools v0.47.0/go.mod h1:dFHnyTvFWY212G+h7ZY4Vsp/K3U4/7W9TyVaAul8uCA=
 google.golang.org/protobuf v1.36.8 h1:xHScyCOEuuwZEc6UtSOvPbAT4zRh0xcNRYekJwfqyMc=
 google.golang.org/protobuf v1.36.8/go.mod h1:fuxRtAxBytpl4zzqUh6/eyUujkJdNiuEkXntxiD/uRU=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=

internal/config/classify.go

@@ -57,17 +57,22 @@ func ClassifyDNSName(name string) (DNSNameType, error) {
 
 // ClassifyTargets splits a list of DNS names into apex domains and
 // hostnames using the Public Suffix List. It returns an error if any
-// name cannot be classified.
+// name cannot be classified. A name given more than once, in any letter
+// case or with a trailing dot, is kept once.
 func ClassifyTargets(targets []string) ([]string, []string, error) {
 	var domains, hostnames []string
 
+	seen := make(map[string]bool)
+
 	for _, t := range targets {
 		normalized := strings.ToLower(strings.TrimSuffix(strings.TrimSpace(t), "."))
 
-		if normalized == "" {
+		if normalized == "" || seen[normalized] {
 			continue
 		}
 
+		seen[normalized] = true
+
 		typ, classErr := ClassifyDNSName(normalized)
 		if classErr != nil {
 			return nil, nil, classErr

internal/config/classify_test.go

@@ -1,6 +1,7 @@
 package config_test
 
 import (
+	"slices"
 	"testing"
 
 	"sneak.berlin/go/dnswatcher/internal/config"
@@ -93,6 +94,29 @@ func TestClassifyTargets(t *testing.T) {
 	}
 }
 
+func TestClassifyTargetsKeepsEachNameOnce(t *testing.T) {
+	t.Parallel()
+
+	domains, hostnames, err := config.ClassifyTargets([]string{
+		"example.org",
+		"Example.org.",
+		"www.example.org",
+		"EXAMPLE.ORG",
+		"WWW.Example.org.",
+	})
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+
+	if !slices.Equal(domains, []string{"example.org"}) {
+		t.Errorf("domains = %v, want [example.org]", domains)
+	}
+
+	if !slices.Equal(hostnames, []string{"www.example.org"}) {
+		t.Errorf("hostnames = %v, want [www.example.org]", hostnames)
+	}
+}
+
 func TestClassifyTargetsRejectsPublicSuffix(t *testing.T) {
 	t.Parallel()
 

internal/handlers/dashboard.go

@@ -1,11 +1,14 @@
 package handlers
 
 import (
+	"cmp"
 	"embed"
 	"fmt"
 	"html/template"
+	"maps"
 	"math"
 	"net/http"
+	"slices"
 	"strings"
 	"time"
 
@@ -40,12 +43,19 @@ func newDashboardTemplate() *template.Template {
 	)
 }
 
-// dashboardData is the data passed to the dashboard template.
+// dashboardData is the data passed to the dashboard template. Hostnames
+// and DomainRecords split the records in Snapshot.Hostnames, which also
+// holds the apex domains' own (see splitHostnames). Ports holds
+// Snapshot.Ports with each port's names split into domains and
+// hostnames, as /api/v1/status gives them (see buildPorts).
 type dashboardData struct {
-	Snapshot    state.Snapshot
-	Alerts      []notify.AlertEntry
-	StateAge    string
-	GeneratedAt string
+	Snapshot      state.Snapshot
+	Hostnames     map[string]*state.HostnameState
+	DomainRecords map[string]*state.HostnameState
+	Ports         map[string]*statusPortInfo
+	Alerts        []notify.AlertEntry
+	StateAge      string
+	GeneratedAt   string
 }
 
 // HandleDashboard returns the dashboard page handler.
@@ -58,12 +68,16 @@ func (h *Handlers) HandleDashboard() http.HandlerFunc {
 	) {
 		snap := h.state.GetSnapshot()
 		alerts := h.notifyHistory.Recent()
+		hostnames, domainRecords := splitHostnames(snap)
 
 		data := dashboardData{
-			Snapshot:    snap,
-			Alerts:      alerts,
-			StateAge:    relTime(snap.LastUpdated),
-			GeneratedAt: time.Now().UTC().Format("2006-01-02 15:04:05"),
+			Snapshot:      snap,
+			Hostnames:     hostnames,
+			DomainRecords: domainRecords,
+			Ports:         buildPorts(snap),
+			Alerts:        alerts,
+			StateAge:      relTime(snap.LastUpdated),
+			GeneratedAt:   time.Now().UTC().Format("2006-01-02 15:04:05"),
 		}
 
 		writer.Header().Set(
@@ -122,16 +136,37 @@ func joinStrings(items []string, sep string) string {
 }
 
 // formatRecords formats a map of record type → values into a
-// compact display string.
+// compact display string. Record types are listed in the order the
+// README lists them, any other type after them in alphabetical order,
+// so rows of nameservers with the same records read the same.
 func formatRecords(records map[string][]string) string {
 	if len(records) == 0 {
 		return "-"
 	}
 
+	order := []string{"A", "AAAA", "CNAME", "MX", "TXT", "SRV", "CAA", "NS"}
+
+	position := func(rtype string) int {
+		i := slices.Index(order, rtype)
+		if i < 0 {
+			return len(order)
+		}
+
+		return i
+	}
+
+	rtypes := slices.Collect(maps.Keys(records))
+	slices.SortFunc(rtypes, func(a, b string) int {
+		return cmp.Or(
+			cmp.Compare(position(a), position(b)),
+			strings.Compare(a, b),
+		)
+	})
+
 	var parts []string
 
-	for rtype, values := range records {
-		for _, v := range values {
+	for _, rtype := range rtypes {
+		for _, v := range records[rtype] {
 			parts = append(parts, rtype+": "+v)
 		}
 	}

internal/handlers/dashboard_test.go

@@ -1,6 +1,8 @@
 package handlers_test
 
 import (
+	"regexp"
+	"strings"
 	"testing"
 	"time"
 
@@ -78,3 +80,194 @@ func TestFormatRecords(t *testing.T) {
 		t.Errorf("unexpected format: %q", got)
 	}
 }
+
+// TestFormatRecordsTypeOrder checks that record types are listed in
+// the README's order (A, AAAA, CNAME, MX, TXT, SRV, CAA, NS), with
+// any other type after them in alphabetical order.
+func TestFormatRecordsTypeOrder(t *testing.T) {
+	t.Parallel()
+
+	got := handlers.FormatRecords(map[string][]string{
+		"SOA":   {"ns1.example.com. hostmaster.example.com. 1 2 3 4 5"},
+		"NS":    {"ns1.example.com.", "ns2.example.com."},
+		"CAA":   {`0 issue "letsencrypt.org"`},
+		"DNAME": {"example.net."},
+		"TXT":   {"v=spf1 -all"},
+		"SRV":   {"10 5 443 www.example.com."},
+		"MX":    {"10 mail.example.com."},
+		"CNAME": {"www.example.com."},
+		"AAAA":  {"2001:db8::1"},
+		"A":     {"192.0.2.1"},
+	})
+
+	want := strings.Join([]string{
+		"A: 192.0.2.1",
+		"AAAA: 2001:db8::1",
+		"CNAME: www.example.com.",
+		"MX: 10 mail.example.com.",
+		"TXT: v=spf1 -all",
+		"SRV: 10 5 443 www.example.com.",
+		`CAA: 0 issue "letsencrypt.org"`,
+		"NS: ns1.example.com.",
+		"NS: ns2.example.com.",
+		"DNAME: example.net.",
+		"SOA: ns1.example.com. hostmaster.example.com. 1 2 3 4 5",
+	}, ", ")
+
+	if got != want {
+		t.Errorf("FormatRecords lists types out of order:\n got %q\nwant %q",
+			got, want)
+	}
+}
+
+// dashboardRow returns the table row of page that contains name.
+func dashboardRow(t *testing.T, page string, name string) string {
+	t.Helper()
+
+	for row := range strings.SplitSeq(page, "<tr") {
+		if strings.Contains(row, name) {
+			return row
+		}
+	}
+
+	t.Fatalf("dashboard has no row containing %q", name)
+
+	return ""
+}
+
+// TestDashboardShowsFailureReasons checks that the dashboard shows the
+// reason in the row of a failed nameserver and of a failed certificate,
+// and not in the row of a nameserver that answered.
+func TestDashboardShowsFailureReasons(t *testing.T) {
+	t.Parallel()
+
+	page := get(t, newHandlersWithFailures(t).HandleDashboard())
+
+	if !strings.Contains(dashboardRow(t, page, failedNS), nsFailureReason) {
+		t.Errorf("row of %s does not show %q", failedNS, nsFailureReason)
+	}
+
+	if strings.Contains(dashboardRow(t, page, answeringNS), nsFailureReason) {
+		t.Errorf("row of %s shows %q", answeringNS, nsFailureReason)
+	}
+
+	if !strings.Contains(dashboardRow(t, page, certKey), certFailedReason) {
+		t.Errorf("row of %s does not show %q", certKey, certFailedReason)
+	}
+}
+
+// dashboardSection returns the section of page under heading.
+func dashboardSection(t *testing.T, page string, heading string) string {
+	t.Helper()
+
+	for section := range strings.SplitSeq(page, "<section") {
+		words := strings.Join(strings.Fields(section), " ")
+		if strings.Contains(words, "> "+heading+" </h2>") {
+			return section
+		}
+	}
+
+	t.Fatalf("dashboard has no section headed %q", heading)
+
+	return ""
+}
+
+// TestDashboardShowsDomainRecordsUnderDomains checks that the dashboard
+// shows an apex domain's own records in the Domains section, and
+// neither lists nor counts the domain as a hostname.
+func TestDashboardShowsDomainRecordsUnderDomains(t *testing.T) {
+	t.Parallel()
+
+	page := get(t, newHandlersWithFailures(t).HandleDashboard())
+
+	domains := dashboardSection(t, page, "Domains")
+	if !strings.Contains(dashboardRow(t, domains, domainAddress), testDomain) {
+		t.Errorf("row of %s does not name %s", domainAddress, testDomain)
+	}
+
+	if strings.Contains(dashboardSection(t, page, "Hostnames"), testDomain) {
+		t.Errorf("Hostnames section lists the domain %s", testDomain)
+	}
+
+	words := strings.Join(strings.Fields(page), " ")
+
+	footer := "monitoring 2 domains + 1 hostnames"
+	if !strings.Contains(words, footer) {
+		t.Errorf("dashboard does not say %q", footer)
+	}
+
+	// With the tags taken out, the summary bar starts "Domains 2
+	// Hostnames 1".
+	text := regexp.MustCompile(`<[^>]*>`).ReplaceAllString(page, " ")
+	summary := "Domains 2 Hostnames 1"
+
+	if !strings.Contains(strings.Join(strings.Fields(text), " "), summary) {
+		t.Errorf("summary bar does not say %q", summary)
+	}
+}
+
+// TestDashboardMarksDomainThatDoesNotExist checks that the Domains
+// section says a domain that does not exist does not exist, and does
+// not say so of a domain that exists.
+func TestDashboardMarksDomainThatDoesNotExist(t *testing.T) {
+	t.Parallel()
+
+	page := get(t, newHandlersWithFailures(t).HandleDashboard())
+	domains := dashboardSection(t, page, "Domains")
+
+	if !strings.Contains(dashboardRow(t, domains, missingDomain), "does not exist") {
+		t.Errorf("row of %s does not say it does not exist", missingDomain)
+	}
+
+	if strings.Contains(dashboardRow(t, domains, testDomain), "does not exist") {
+		t.Errorf("row of %s says it does not exist", testDomain)
+	}
+}
+
+// rowCells returns the text of each cell of a dashboard table row
+// whose cells start with tag, "<th" or "<td".
+func rowCells(row string, tag string) []string {
+	tags := regexp.MustCompile(`<[^>]*>`)
+	parts := strings.Split(row, tag)[1:]
+	cells := make([]string, 0, len(parts))
+
+	for _, cell := range parts {
+		text := tags.ReplaceAllString(tag+cell, " ")
+		cells = append(cells, strings.Join(strings.Fields(text), " "))
+	}
+
+	return cells
+}
+
+// TestDashboardPortsTellDomainsFromHostnames checks that the Ports
+// table lists an apex domain under Domains and a hostname under
+// Hostnames when both resolve to the port's address.
+func TestDashboardPortsTellDomainsFromHostnames(t *testing.T) {
+	t.Parallel()
+
+	page := get(t, newHandlersWithFailures(t).HandleDashboard())
+	ports := dashboardSection(t, page, "Ports")
+
+	headings := rowCells(dashboardRow(t, ports, "Address</th>"), "<th")
+	cells := rowCells(dashboardRow(t, ports, sharedPort), "<td")
+
+	if len(cells) != len(headings) {
+		t.Fatalf("row of %s has cells %q under headings %q",
+			sharedPort, cells, headings)
+	}
+
+	under := make(map[string]string)
+	for i, heading := range headings {
+		under[heading] = cells[i]
+	}
+
+	if under["Domains"] != testDomain {
+		t.Errorf("row of %s lists %q under Domains, want %q",
+			sharedPort, under["Domains"], testDomain)
+	}
+
+	if under["Hostnames"] != testHostname {
+		t.Errorf("row of %s lists %q under Hostnames, want %q",
+			sharedPort, under["Hostnames"], testHostname)
+	}
+}

internal/handlers/status.go

@@ -9,15 +9,21 @@ import (
 )
 
 // statusDomainInfo holds status information for a monitored domain.
+// RecordsByNameserver holds the domain's own records, in the form a
+// hostname's Nameservers holds the hostname's. NXDomain is true when
+// the domain's parent zone's servers answered that it does not exist.
 type statusDomainInfo struct {
-	Nameservers []string  `json:"nameservers"`
-	LastChecked time.Time `json:"lastChecked"`
+	Nameservers         []string                         `json:"nameservers"`
+	RecordsByNameserver map[string]*statusHostnameNSInfo `json:"recordsByNameserver"`
+	NXDomain            bool                             `json:"nxdomain"`
+	LastChecked         time.Time                        `json:"lastChecked"`
 }
 
 // statusHostnameNSInfo holds per-nameserver status for a hostname.
 type statusHostnameNSInfo struct {
 	Records     map[string][]string `json:"records"`
 	Status      string              `json:"status"`
+	Error       string              `json:"error,omitempty"`
 	LastChecked time.Time           `json:"lastChecked"`
 }
 
@@ -28,8 +34,11 @@ type statusHostnameInfo struct {
 }
 
 // statusPortInfo holds status information for a monitored port.
+// Domains and Hostnames list the apex domains and the hostnames that
+// resolve to its address.
 type statusPortInfo struct {
 	Open        bool      `json:"open"`
+	Domains     []string  `json:"domains"`
 	Hostnames   []string  `json:"hostnames"`
 	LastChecked time.Time `json:"lastChecked"`
 }
@@ -41,6 +50,7 @@ type statusCertificateInfo struct {
 	NotAfter                time.Time `json:"notAfter"`
 	SubjectAlternativeNames []string  `json:"subjectAlternativeNames"`
 	Status                  string    `json:"status"`
+	Error                   string    `json:"error,omitempty"`
 	LastChecked             time.Time `json:"lastChecked"`
 }
 
@@ -94,21 +104,44 @@ func buildStatusResponse(
 		LastUpdated:  snap.LastUpdated,
 		Domains:      make(map[string]*statusDomainInfo),
 		Hostnames:    make(map[string]*statusHostnameInfo),
-		Ports:        make(map[string]*statusPortInfo),
 		Certificates: make(map[string]*statusCertificateInfo),
 	}
 
-	buildDomains(snap, resp)
-	buildHostnames(snap, resp)
-	buildPorts(snap, resp)
+	hostnames, domainRecords := splitHostnames(snap)
+
+	buildDomains(snap, domainRecords, resp)
+	buildHostnames(hostnames, resp)
+	resp.Ports = buildPorts(snap)
 	buildCertificates(snap, resp)
 	buildCounts(resp)
 
 	return resp
 }
 
+// splitHostnames returns the records saved in snap.Hostnames in two
+// maps: the hostnames' and the apex domains' own. The watcher saves a
+// domain's own records there under the domain's name, which has an
+// entry in snap.Domains too.
+func splitHostnames(
+	snap state.Snapshot,
+) (map[string]*state.HostnameState, map[string]*state.HostnameState) {
+	hostnames := make(map[string]*state.HostnameState)
+	domainRecords := make(map[string]*state.HostnameState)
+
+	for name, hs := range snap.Hostnames {
+		if _, isDomain := snap.Domains[name]; isDomain {
+			domainRecords[name] = hs
+		} else {
+			hostnames[name] = hs
+		}
+	}
+
+	return hostnames, domainRecords
+}
+
 func buildDomains(
 	snap state.Snapshot,
+	domainRecords map[string]*state.HostnameState,
 	resp *statusResponse,
 ) {
 	for name, ds := range snap.Domains {
@@ -116,57 +149,87 @@ func buildDomains(
 		copy(ns, ds.Nameservers)
 		sort.Strings(ns)
 
+		records := make(map[string]*statusHostnameNSInfo)
+		if hs, ok := domainRecords[name]; ok {
+			records = nameserverInfo(hs)
+		}
+
 		resp.Domains[name] = &statusDomainInfo{
-			Nameservers: ns,
-			LastChecked: ds.LastChecked,
+			Nameservers:         ns,
+			RecordsByNameserver: records,
+			NXDomain:            ds.NXDomain,
+			LastChecked:         ds.LastChecked,
 		}
 	}
 }
 
 func buildHostnames(
-	snap state.Snapshot,
+	hostnames map[string]*state.HostnameState,
 	resp *statusResponse,
 ) {
-	for name, hs := range snap.Hostnames {
-		info := &statusHostnameInfo{
-			Nameservers: make(map[string]*statusHostnameNSInfo),
+	for name, hs := range hostnames {
+		resp.Hostnames[name] = &statusHostnameInfo{
+			Nameservers: nameserverInfo(hs),
 			LastChecked: hs.LastChecked,
 		}
-
-		for ns, nsState := range hs.RecordsByNameserver {
-			recs := make(map[string][]string, len(nsState.Records))
-			for rtype, vals := range nsState.Records {
-				copied := make([]string, len(vals))
-				copy(copied, vals)
-				recs[rtype] = copied
-			}
-
-			info.Nameservers[ns] = &statusHostnameNSInfo{
-				Records:     recs,
-				Status:      nsState.Status,
-				LastChecked: nsState.LastChecked,
-			}
-		}
-
-		resp.Hostnames[name] = info
 	}
 }
 
-func buildPorts(
-	snap state.Snapshot,
-	resp *statusResponse,
-) {
+// nameserverInfo copies each nameserver's answer saved in hs.
+func nameserverInfo(
+	hs *state.HostnameState,
+) map[string]*statusHostnameNSInfo {
+	info := make(map[string]*statusHostnameNSInfo)
+
+	for ns, nsState := range hs.RecordsByNameserver {
+		recs := make(map[string][]string, len(nsState.Records))
+		for rtype, vals := range nsState.Records {
+			copied := make([]string, len(vals))
+			copy(copied, vals)
+			recs[rtype] = copied
+		}
+
+		info[ns] = &statusHostnameNSInfo{
+			Records:     recs,
+			Status:      nsState.Status,
+			Error:       nsState.Error,
+			LastChecked: nsState.LastChecked,
+		}
+	}
+
+	return info
+}
+
+// buildPorts returns the port entries saved in snap. A port entry
+// saves apex domains with its hostnames; they are told apart as in
+// splitHostnames, by a domain entry in snap.Domains.
+func buildPorts(snap state.Snapshot) map[string]*statusPortInfo {
+	ports := make(map[string]*statusPortInfo, len(snap.Ports))
+
 	for key, ps := range snap.Ports {
-		hostnames := make([]string, len(ps.Hostnames))
-		copy(hostnames, ps.Hostnames)
+		domains := []string{}
+		hostnames := []string{}
+
+		for _, name := range ps.Hostnames {
+			if _, isDomain := snap.Domains[name]; isDomain {
+				domains = append(domains, name)
+			} else {
+				hostnames = append(hostnames, name)
+			}
+		}
+
+		sort.Strings(domains)
 		sort.Strings(hostnames)
 
-		resp.Ports[key] = &statusPortInfo{
+		ports[key] = &statusPortInfo{
 			Open:        ps.Open,
+			Domains:     domains,
 			Hostnames:   hostnames,
 			LastChecked: ps.LastChecked,
 		}
 	}
+
+	return ports
 }
 
 func buildCertificates(
@@ -183,6 +246,7 @@ func buildCertificates(
 			NotAfter:                cs.NotAfter,
 			SubjectAlternativeNames: sans,
 			Status:                  cs.Status,
+			Error:                   cs.Error,
 			LastChecked:             cs.LastChecked,
 		}
 	}

internal/handlers/status_test.go

@@ -0,0 +1,309 @@
+package handlers_test
+
+import (
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"slices"
+	"testing"
+	"time"
+
+	"go.uber.org/fx/fxtest"
+
+	"sneak.berlin/go/dnswatcher/internal/config"
+	"sneak.berlin/go/dnswatcher/internal/globals"
+	"sneak.berlin/go/dnswatcher/internal/handlers"
+	"sneak.berlin/go/dnswatcher/internal/logger"
+	"sneak.berlin/go/dnswatcher/internal/notify"
+	"sneak.berlin/go/dnswatcher/internal/state"
+)
+
+// The state the handler tests serve: www.example.com has one nameserver
+// that answered and one whose query failed, and its certificate check
+// failed. example.net is an apex domain, whose own records are saved
+// with the hostnames' records, as the watcher saves them. Both names
+// resolve to domainAddress, whose port 443 entry lists them.
+// missingDomain is an apex domain whose parent zone's servers answered
+// that it does not exist, saved with no nameservers and no records.
+const (
+	missingDomain    = "does-not-exist.example"
+	testHostname     = "www.example.com"
+	answeringNS      = "ns1.example.com."
+	failedNS         = "ns2.example.com."
+	nsFailureReason  = "server returned a referral"
+	certKey          = "192.0.2.1:443:www.example.com"
+	certFailedReason = "x509: certificate has expired or is not yet valid"
+	testDomain       = "example.net"
+	domainNS         = "a.iana-servers.net."
+	domainAddress    = "192.0.2.2"
+	sharedPort       = domainAddress + ":443"
+)
+
+// newHandlersWithFailures builds real Handlers whose state holds the
+// entries described above.
+func newHandlersWithFailures(t *testing.T) *handlers.Handlers {
+	t.Helper()
+
+	glob, err := globals.New(nil)
+	if err != nil {
+		t.Fatalf("globals.New: %v", err)
+	}
+
+	log, err := logger.New(nil, logger.Params{Globals: glob})
+	if err != nil {
+		t.Fatalf("logger.New: %v", err)
+	}
+
+	notifier, err := notify.New(fxtest.NewLifecycle(t), notify.Params{
+		Logger: log,
+		Config: &config.Config{},
+	})
+	if err != nil {
+		t.Fatalf("notify.New: %v", err)
+	}
+
+	st, err := state.New(fxtest.NewLifecycle(t), state.Params{
+		Logger: log,
+		Config: &config.Config{DataDir: t.TempDir()},
+	})
+	if err != nil {
+		t.Fatalf("state.New: %v", err)
+	}
+
+	setTestState(st)
+
+	hnd, err := handlers.New(nil, handlers.Params{
+		Logger:  log,
+		Globals: glob,
+		State:   st,
+		Notify:  notifier,
+	})
+	if err != nil {
+		t.Fatalf("handlers.New: %v", err)
+	}
+
+	return hnd
+}
+
+// setTestState sets the entries described above in st.
+func setTestState(st *state.State) {
+	now := time.Now()
+
+	st.SetHostnameState(testHostname, &state.HostnameState{
+		RecordsByNameserver: map[string]*state.NameserverRecordState{
+			answeringNS: {
+				Records: map[string][]string{
+					"A": {"192.0.2.1", domainAddress},
+				},
+				Status:      "ok",
+				LastChecked: now,
+			},
+			failedNS: {
+				Records:     map[string][]string{},
+				Status:      "error",
+				Error:       nsFailureReason,
+				LastChecked: now,
+			},
+		},
+		LastChecked: now,
+	})
+
+	st.SetCertificateState(certKey, &state.CertificateState{
+		Status:      "error",
+		Error:       certFailedReason,
+		LastChecked: now,
+	})
+
+	st.SetDomainState(testDomain, &state.DomainState{
+		Nameservers: []string{domainNS},
+		LastChecked: now,
+	})
+
+	st.SetHostnameState(testDomain, &state.HostnameState{
+		RecordsByNameserver: map[string]*state.NameserverRecordState{
+			domainNS: {
+				Records:     map[string][]string{"A": {domainAddress}},
+				Status:      "ok",
+				LastChecked: now,
+			},
+		},
+		LastChecked: now,
+	})
+
+	st.SetPortState(sharedPort, &state.PortState{
+		Open:        true,
+		Hostnames:   []string{testDomain, testHostname},
+		LastChecked: now,
+	})
+
+	st.SetDomainState(missingDomain, &state.DomainState{
+		Nameservers: []string{},
+		NXDomain:    true,
+		LastChecked: now,
+	})
+}
+
+// get serves one GET request to handler and returns the response body.
+func get(t *testing.T, handler http.HandlerFunc) string {
+	t.Helper()
+
+	rec := httptest.NewRecorder()
+	req := httptest.NewRequestWithContext(
+		t.Context(), http.MethodGet, "/", nil,
+	)
+
+	handler(rec, req)
+
+	if rec.Code != http.StatusOK {
+		t.Fatalf("status = %d, want 200", rec.Code)
+	}
+
+	return rec.Body.String()
+}
+
+// TestStatusGivesFailureReasons checks that /api/v1/status gives the
+// reason for a failed nameserver entry and a failed certificate entry,
+// and no error for a nameserver that answered.
+func TestStatusGivesFailureReasons(t *testing.T) {
+	t.Parallel()
+
+	body := get(t, newHandlersWithFailures(t).HandleStatus())
+
+	var resp struct {
+		Hostnames map[string]struct {
+			Nameservers map[string]map[string]any `json:"nameservers"`
+		} `json:"hostnames"`
+		Certificates map[string]map[string]any `json:"certificates"`
+	}
+
+	err := json.Unmarshal([]byte(body), &resp)
+	if err != nil {
+		t.Fatalf("decoding response: %v", err)
+	}
+
+	nameservers := resp.Hostnames[testHostname].Nameservers
+
+	got := nameservers[failedNS]["error"]
+	if got != nsFailureReason {
+		t.Errorf("failed nameserver error = %v, want %q",
+			got, nsFailureReason)
+	}
+
+	_, has := nameservers[answeringNS]["error"]
+	if has {
+		t.Errorf("answering nameserver has an error field: %v",
+			nameservers[answeringNS])
+	}
+
+	got = resp.Certificates[certKey]["error"]
+	if got != certFailedReason {
+		t.Errorf("failed certificate error = %v, want %q",
+			got, certFailedReason)
+	}
+}
+
+// TestStatusGivesDomainRecordsUnderTheDomain checks that /api/v1/status
+// gives an apex domain's own records in its domain entry, and neither
+// lists nor counts the domain as a hostname.
+func TestStatusGivesDomainRecordsUnderTheDomain(t *testing.T) {
+	t.Parallel()
+
+	body := get(t, newHandlersWithFailures(t).HandleStatus())
+
+	var resp struct {
+		Counts struct {
+			Hostnames int `json:"hostnames"`
+		} `json:"counts"`
+		Domains map[string]struct {
+			RecordsByNameserver map[string]struct {
+				Records map[string][]string `json:"records"`
+			} `json:"recordsByNameserver"`
+		} `json:"domains"`
+		Hostnames map[string]any `json:"hostnames"`
+	}
+
+	err := json.Unmarshal([]byte(body), &resp)
+	if err != nil {
+		t.Fatalf("decoding response: %v", err)
+	}
+
+	if resp.Counts.Hostnames != 1 {
+		t.Errorf("counts.hostnames = %d, want 1", resp.Counts.Hostnames)
+	}
+
+	if _, listed := resp.Hostnames[testDomain]; listed {
+		t.Errorf("hostnames lists the domain %s", testDomain)
+	}
+
+	records := resp.Domains[testDomain].RecordsByNameserver[domainNS].Records
+	if !slices.Equal(records["A"], []string{domainAddress}) {
+		t.Errorf("domain %s records at %s = %v, want A %s",
+			testDomain, domainNS, records, domainAddress)
+	}
+}
+
+// TestStatusMarksDomainThatDoesNotExist checks that /api/v1/status sets
+// nxdomain for a domain that does not exist, with no nameservers or
+// records, and not for a domain that exists.
+func TestStatusMarksDomainThatDoesNotExist(t *testing.T) {
+	t.Parallel()
+
+	body := get(t, newHandlersWithFailures(t).HandleStatus())
+
+	var resp struct {
+		Domains map[string]struct {
+			Nameservers         []string       `json:"nameservers"`
+			RecordsByNameserver map[string]any `json:"recordsByNameserver"`
+			NXDomain            bool           `json:"nxdomain"`
+		} `json:"domains"`
+	}
+
+	err := json.Unmarshal([]byte(body), &resp)
+	if err != nil {
+		t.Fatalf("decoding response: %v", err)
+	}
+
+	missing := resp.Domains[missingDomain]
+	if !missing.NXDomain || len(missing.Nameservers) != 0 ||
+		len(missing.RecordsByNameserver) != 0 {
+		t.Errorf("domain %s = %+v, want nxdomain and nothing else",
+			missingDomain, missing)
+	}
+
+	if resp.Domains[testDomain].NXDomain {
+		t.Errorf("domain %s has nxdomain set", testDomain)
+	}
+}
+
+// TestStatusPortsTellDomainsFromHostnames checks that a port entry in
+// /api/v1/status lists an apex domain in domains and a hostname in
+// hostnames when both resolve to its address.
+func TestStatusPortsTellDomainsFromHostnames(t *testing.T) {
+	t.Parallel()
+
+	body := get(t, newHandlersWithFailures(t).HandleStatus())
+
+	var resp struct {
+		Ports map[string]struct {
+			Domains   []string `json:"domains"`
+			Hostnames []string `json:"hostnames"`
+		} `json:"ports"`
+	}
+
+	err := json.Unmarshal([]byte(body), &resp)
+	if err != nil {
+		t.Fatalf("decoding response: %v", err)
+	}
+
+	port := resp.Ports[sharedPort]
+
+	if !slices.Equal(port.Domains, []string{testDomain}) {
+		t.Errorf("port %s domains = %v, want [%s]",
+			sharedPort, port.Domains, testDomain)
+	}
+
+	if !slices.Equal(port.Hostnames, []string{testHostname}) {
+		t.Errorf("port %s hostnames = %v, want [%s]",
+			sharedPort, port.Hostnames, testHostname)
+	}
+}

internal/handlers/templates/dashboard.html

@@ -39,7 +39,7 @@
             Hostnames
           </div>
           <div class="text-2xl font-bold text-teal-400 mt-1">
-            {{ len .Snapshot.Hostnames }}
+            {{ len .Hostnames }}
           </div>
         </div>
         <div class="bg-surface-800 border border-slate-700/50 rounded-lg p-4">
@@ -84,7 +84,11 @@
                   {{ $name }}
                 </td>
                 <td class="py-2 px-3 text-slate-400 break-all">
+                  {{ if $ds.NXDomain }}
+                  <span class="text-red-400">does not exist</span>
+                  {{ else }}
                   {{ joinStrings $ds.Nameservers ", " }}
+                  {{ end }}
                 </td>
                 <td class="py-2 px-3 text-slate-500 whitespace-nowrap">
                   {{ relTime $ds.LastChecked }}
@@ -94,6 +98,24 @@
             </tbody>
           </table>
         </div>
+        {{ if .DomainRecords }}
+        <div class="overflow-x-auto mt-4">
+          <table class="w-full text-left text-xs">
+            <thead>
+              <tr class="text-slate-500 uppercase tracking-wider">
+                <th class="py-2 px-3">Domain</th>
+                <th class="py-2 px-3">NS</th>
+                <th class="py-2 px-3">Status</th>
+                <th class="py-2 px-3">Records</th>
+                <th class="py-2 px-3">Checked</th>
+              </tr>
+            </thead>
+            <tbody class="divide-y divide-slate-800">
+              {{ template "records" .DomainRecords }}
+            </tbody>
+          </table>
+        </div>
+        {{ end }}
         {{ else }}
         <p class="text-slate-600 italic text-xs">
           No domains configured.
@@ -108,7 +130,7 @@
         >
           Hostnames
         </h2>
-        {{ if .Snapshot.Hostnames }}
+        {{ if .Hostnames }}
         <div class="overflow-x-auto">
           <table class="w-full text-left text-xs">
             <thead>
@@ -121,39 +143,7 @@
               </tr>
             </thead>
             <tbody class="divide-y divide-slate-800">
-              {{ range $name, $hs := .Snapshot.Hostnames }}
-              {{ range $ns, $nsr := $hs.RecordsByNameserver }}
-              <tr class="hover:bg-surface-800/50">
-                <td class="py-2 px-3 text-slate-200 font-medium">
-                  {{ $name }}
-                </td>
-                <td class="py-2 px-3 text-slate-400 break-all">
-                  {{ $ns }}
-                </td>
-                <td class="py-2 px-3">
-                  {{ if eq $nsr.Status "ok" }}
-                  <span
-                    class="inline-block px-1.5 py-0.5 rounded text-[10px] font-bold uppercase bg-teal-900/50 text-teal-400 border border-teal-700/30"
-                    >ok</span
-                  >
-                  {{ else }}
-                  <span
-                    class="inline-block px-1.5 py-0.5 rounded text-[10px] font-bold uppercase bg-red-900/50 text-red-400 border border-red-700/30"
-                    >{{ $nsr.Status }}</span
-                  >
-                  {{ end }}
-                </td>
-                <td
-                  class="py-2 px-3 text-slate-400 break-all max-w-xs"
-                >
-                  {{ formatRecords $nsr.Records }}
-                </td>
-                <td class="py-2 px-3 text-slate-500 whitespace-nowrap">
-                  {{ relTime $nsr.LastChecked }}
-                </td>
-              </tr>
-              {{ end }}
-              {{ end }}
+              {{ template "records" .Hostnames }}
             </tbody>
           </table>
         </div>
@@ -171,19 +161,20 @@
         >
           Ports
         </h2>
-        {{ if .Snapshot.Ports }}
+        {{ if .Ports }}
         <div class="overflow-x-auto">
           <table class="w-full text-left text-xs">
             <thead>
               <tr class="text-slate-500 uppercase tracking-wider">
                 <th class="py-2 px-3">Address</th>
                 <th class="py-2 px-3">State</th>
+                <th class="py-2 px-3">Domains</th>
                 <th class="py-2 px-3">Hostnames</th>
                 <th class="py-2 px-3">Checked</th>
               </tr>
             </thead>
             <tbody class="divide-y divide-slate-800">
-              {{ range $key, $ps := .Snapshot.Ports }}
+              {{ range $key, $ps := .Ports }}
               <tr class="hover:bg-surface-800/50">
                 <td class="py-2 px-3 text-slate-200 font-medium">
                   {{ $key }}
@@ -201,6 +192,9 @@
                   >
                   {{ end }}
                 </td>
+                <td class="py-2 px-3 text-slate-400 break-all">
+                  {{ joinStrings $ps.Domains ", " }}
+                </td>
                 <td class="py-2 px-3 text-slate-400 break-all">
                   {{ joinStrings $ps.Hostnames ", " }}
                 </td>
@@ -258,6 +252,11 @@
                   >
                   {{ end }}
                 </td>
+                {{ if $cs.Error }}
+                <td colspan="3" class="py-2 px-3 text-red-400 break-all">
+                  <div class="max-w-xs">{{ $cs.Error }}</div>
+                </td>
+                {{ else }}
                 <td class="py-2 px-3 text-slate-200">
                   {{ $cs.CommonName }}
                 </td>
@@ -285,6 +284,7 @@
                     {{ end }}
                   {{ end }}
                 </td>
+                {{ end }}
                 <td class="py-2 px-3 text-slate-500 whitespace-nowrap">
                   {{ relTime $cs.LastChecked }}
                 </td>
@@ -363,8 +363,48 @@
         class="text-[11px] text-slate-700 border-t border-slate-800 pt-4 mt-8"
       >
         dnswatcher &middot; monitoring {{ len .Snapshot.Domains }} domains +
-        {{ len .Snapshot.Hostnames }} hostnames
+        {{ len .Hostnames }} hostnames
       </div>
     </div>
   </body>
 </html>
+{{/* ---- One row per nameserver of each name in the map it is given ---- */}}
+{{ define "records" }}
+{{ range $name, $hs := . }}
+{{ range $ns, $nsr := $hs.RecordsByNameserver }}
+<tr class="hover:bg-surface-800/50">
+  <td class="py-2 px-3 text-slate-200 font-medium">
+    {{ $name }}
+  </td>
+  <td class="py-2 px-3 text-slate-400 break-all">
+    {{ $ns }}
+  </td>
+  <td class="py-2 px-3">
+    {{ if eq $nsr.Status "ok" }}
+    <span
+      class="inline-block px-1.5 py-0.5 rounded text-[10px] font-bold uppercase bg-teal-900/50 text-teal-400 border border-teal-700/30"
+      >ok</span
+    >
+    {{ else }}
+    <span
+      class="inline-block px-1.5 py-0.5 rounded text-[10px] font-bold uppercase bg-red-900/50 text-red-400 border border-red-700/30"
+      >{{ $nsr.Status }}</span
+    >
+    {{ end }}
+  </td>
+  <td
+    class="py-2 px-3 text-slate-400 break-all max-w-xs"
+  >
+    {{ if $nsr.Error }}
+    <span class="text-red-400">{{ $nsr.Error }}</span>
+    {{ else }}
+    {{ formatRecords $nsr.Records }}
+    {{ end }}
+  </td>
+  <td class="py-2 px-3 text-slate-500 whitespace-nowrap">
+    {{ relTime $nsr.LastChecked }}
+  </td>
+</tr>
+{{ end }}
+{{ end }}
+{{ end }}

internal/livednstest/livednstest.go

@@ -9,11 +9,11 @@
 //
 //  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.
+//     iterative resolution at the same instant and they all send their
+//     first queries to the root servers 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
@@ -36,11 +36,18 @@ const (
 	// 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
+	// AttemptTimeout bounds one attempt. It must fit the longest
+	// operation, a watcher check, which sends over a hundred queries one
+	// after another and on a slow build host takes several times as long
+	// as the few seconds it takes on a fast one. An operation whose
+	// every attempt fails takes attempts * AttemptTimeout plus the
+	// backoff, about 56 seconds, after it waits for one of the
+	// Concurrency slots that every live operation in the test binary
+	// shares. So when live DNS does not answer at all, a test binary
+	// with more live operations than slots runs into the 90-second
+	// `go test -timeout` backstop instead of each test failing on its
+	// own.
+	AttemptTimeout = 18 * time.Second
 
 	// backoffBase is the delay after the first failed attempt; it is
 	// multiplied by backoffFactor each time.

internal/notify/delivery_test.go

@@ -6,9 +6,11 @@ import (
 	"encoding/json"
 	"errors"
 	"io"
+	"maps"
 	"net/http"
 	"net/http/httptest"
 	"net/url"
+	"strings"
 	"sync"
 	"testing"
 	"time"
@@ -413,7 +415,8 @@ func sendSlackInfo(
 	svc *notify.Service, target *url.URL,
 ) error {
 	return svc.SendSlack(
-		context.Background(), target, "t", "m", prioInfo,
+		context.Background(), target, notify.ErrSlackFailed,
+		"t", "m", prioInfo,
 	)
 }
 
@@ -506,6 +509,7 @@ func TestSendSlackPayloadFields(t *testing.T) {
 	err := svc.SendSlack(
 		context.Background(),
 		webhookURL,
+		notify.ErrSlackFailed,
 		"Alert Title",
 		"Alert body text",
 		"warning",
@@ -608,7 +612,8 @@ func TestSendSlackAllColors(t *testing.T) {
 
 			err := svc.SendSlack(
 				context.Background(),
-				webhookURL, "t", "m", tc.priority,
+				webhookURL, notify.ErrSlackFailed,
+				"t", "m", tc.priority,
 			)
 			if err != nil {
 				t.Fatalf("SendSlack error: %v", err)
@@ -659,7 +664,8 @@ func TestSendSlackNetworkError(t *testing.T) {
 	)
 
 	err := svc.SendSlack(
-		context.Background(), webhookURL, "t", "m", "info",
+		context.Background(), webhookURL, notify.ErrSlackFailed,
+		"t", "m", "info",
 	)
 	if err == nil {
 		t.Fatal("expected error for network failure")
@@ -1028,6 +1034,66 @@ func TestSendNotificationMattermostError(t *testing.T) {
 	)
 }
 
+// TestSendNotificationErrorNamesEndpoint verifies that, with both
+// Slack and Mattermost set, a failed delivery's logged error names
+// the endpoint that failed. Both are sent by the Slack sender.
+func TestSendNotificationErrorNamesEndpoint(t *testing.T) {
+	t.Parallel()
+
+	srv := httptest.NewServer(
+		http.HandlerFunc(
+			func(w http.ResponseWriter, _ *http.Request) {
+				w.WriteHeader(http.StatusServiceUnavailable)
+			}),
+	)
+	defer srv.Close()
+
+	target, _ := url.Parse(srv.URL)
+
+	svc, logs := newLoggingService(http.DefaultTransport)
+	svc.SetSlackWebhookURL(target)
+	svc.SetMattermostWebhookURL(target)
+	svc.SetSleepFunc(instantSleep)
+	svc.SetRetryConfig(notify.RetryConfig{
+		MaxRetries: 1,
+		BaseDelay:  time.Millisecond,
+		MaxDelay:   time.Millisecond,
+	})
+
+	svc.SendNotification(
+		context.Background(), "t", "m", prioError,
+	)
+
+	waitForCondition(t, func() bool {
+		return svc.OutstandingDeliveries() == 0
+	})
+
+	got := map[string]string{}
+
+	for line := range strings.Lines(logs.String()) {
+		var record struct {
+			Msg      string `json:"msg"`
+			Endpoint string `json:"endpoint"`
+			Error    string `json:"error"`
+		}
+
+		_ = json.Unmarshal([]byte(line), &record)
+
+		if record.Msg == "failed to send notification after retries" {
+			got[record.Endpoint] = record.Error
+		}
+	}
+
+	want := map[string]string{
+		"slack":      "slack notification failed: status 503",
+		"mattermost": "mattermost notification failed: status 503",
+	}
+
+	if !maps.Equal(got, want) {
+		t.Errorf("logged errors = %v, want %v", got, want)
+	}
+}
+
 // ── SlackPayload JSON marshaling ──────────────────────────
 
 func TestSlackPayloadJSON(t *testing.T) {

internal/notify/export_test.go

@@ -85,10 +85,11 @@ func (svc *Service) SendNtfy(
 func (svc *Service) SendSlack(
 	ctx context.Context,
 	webhookURL *url.URL,
+	failed error,
 	title, message, priority string,
 ) error {
 	return svc.sendSlack(
-		ctx, webhookURL, title, message, priority,
+		ctx, webhookURL, failed, title, message, priority,
 	)
 }
 

internal/notify/notify.go

@@ -277,7 +277,8 @@ func (svc *Service) dispatchSlack(
 
 	svc.dispatch(ctx, "slack", func(c context.Context) error {
 		return svc.sendSlack(
-			c, svc.slackWebhookURL, title, message, priority,
+			c, svc.slackWebhookURL, ErrSlackFailed,
+			title, message, priority,
 		)
 	})
 }
@@ -294,7 +295,7 @@ func (svc *Service) dispatchMattermost(
 		ctx, "mattermost",
 		func(c context.Context) error {
 			return svc.sendSlack(
-				c, svc.mattermostWebhookURL,
+				c, svc.mattermostWebhookURL, ErrMattermostFailed,
 				title, message, priority,
 			)
 		},
@@ -370,9 +371,14 @@ type SlackAttachment struct {
 	Text  string `json:"text"`
 }
 
+// sendSlack posts to a Slack or Mattermost incoming webhook, which
+// take the same payload. An HTTP error status is returned wrapped in
+// failed, ErrSlackFailed or ErrMattermostFailed, so the error names
+// the endpoint.
 func (svc *Service) sendSlack(
 	ctx context.Context,
 	webhookURL *url.URL,
+	failed error,
 	title, message, priority string,
 ) error {
 	ctx, cancel := context.WithTimeout(
@@ -420,7 +426,7 @@ func (svc *Service) sendSlack(
 	if resp.StatusCode >= httpStatusClientError {
 		return fmt.Errorf(
 			"%w: status %d",
-			ErrSlackFailed, resp.StatusCode,
+			failed, resp.StatusCode,
 		)
 	}
 

internal/notify/retry.go

@@ -115,7 +115,9 @@ func (svc *Service) deliverWithRetry(
 			"endpoint", endpoint,
 			"attempt", attempt+1,
 			"maxAttempts", cfg.MaxRetries+1,
-			"retryIn", delay,
+			// As text: the JSON log writes a time.Duration as
+			// bare nanoseconds.
+			"retryIn", delay.String(),
 			"error", lastErr,
 		)
 

internal/notify/retry_test.go

@@ -2,6 +2,7 @@ package notify_test
 
 import (
 	"context"
+	"encoding/json"
 	"errors"
 	"net/http"
 	"net/http/httptest"
@@ -189,6 +190,50 @@ func TestDeliverWithRetryExhaustsAttempts(t *testing.T) {
 	}
 }
 
+// TestDeliverWithRetryLogsRetryInAsText checks that the wait
+// before a retry is logged as text such as "1.02s", not as a
+// count of nanoseconds.
+func TestDeliverWithRetryLogsRetryInAsText(t *testing.T) {
+	t.Parallel()
+
+	svc, logs := newLoggingService(http.DefaultTransport)
+	svc.SetRetryConfig(notify.RetryConfig{
+		MaxRetries: 1,
+		BaseDelay:  time.Second,
+		MaxDelay:   time.Second,
+	})
+
+	var waited time.Duration
+
+	svc.SetSleepFunc(func(d time.Duration) <-chan time.Time {
+		waited = d
+
+		return instantSleep(d)
+	})
+
+	_ = svc.DeliverWithRetry(
+		context.Background(), "test",
+		func(_ context.Context) error {
+			return errFail
+		},
+	)
+
+	// With one retry, only the first failure is logged.
+	var record map[string]any
+
+	err := json.Unmarshal([]byte(logs.String()), &record)
+	if err != nil {
+		t.Fatalf("log is not one JSON record: %v\n%s", err, logs)
+	}
+
+	if record["retryIn"] != waited.String() {
+		t.Errorf(
+			"retryIn logged as %v, want %q",
+			record["retryIn"], waited.String(),
+		)
+	}
+}
+
 func TestDeliverWithRetryRespectsContextCancellation(
 	t *testing.T,
 ) {

internal/portcheck/portcheck.go

@@ -193,7 +193,9 @@ func (c *Checker) checkConnection(
 	c.log.Debug(
 		"port check succeeded",
 		"target", target,
-		"latency", latency,
+		// As text: the JSON log writes a time.Duration as bare
+		// nanoseconds.
+		"latency", latency.String(),
 	)
 
 	return &PortResult{

internal/resolver/errors.go

@@ -10,12 +10,46 @@ var (
 		"no authoritative nameservers found",
 	)
 
+	// ErrNXDomain is returned when the servers of the zone a domain
+	// is in answer NXDOMAIN: the domain does not exist.
+	ErrNXDomain = errors.New("domain does not exist")
+
+	// ErrNoNameserverAnswered is returned when every nameserver
+	// asked about a name timed out, failed or returned a referral,
+	// so whether the name has addresses is unknown.
+	ErrNoNameserverAnswered = errors.New("no nameserver answered")
+
+	// ErrUnusableReply is returned when a server replied with an
+	// error such as SERVFAIL, or with a referral that leads no
+	// closer to the name asked about.
+	ErrUnusableReply = errors.New(
+		"reply is an error or a referral that leads no closer",
+	)
+
+	// ErrTruncated is the reason given for a reply too large for UDP
+	// whose retry over TCP failed.
+	ErrTruncated = errors.New(
+		"reply truncated and its retry over TCP failed",
+	)
+
+	// ErrIntercepted is returned when every root server refused a
+	// query. Root servers refuse no query, so the refusals came from
+	// something on the network answering in their place.
+	ErrIntercepted = errors.New("this network intercepts DNS queries")
+
 	// ErrCNAMEDepthExceeded is returned when a CNAME chain
 	// exceeds MaxCNAMEDepth.
 	ErrCNAMEDepthExceeded = errors.New(
 		"CNAME chain depth exceeded",
 	)
 
+	// ErrLookupDepthExceeded is returned when nameserver addresses
+	// were not looked up because lookups were already maxLookupDepth
+	// deep, one inside another.
+	ErrLookupDepthExceeded = errors.New(
+		"lookups of nameserver addresses go too deep",
+	)
+
 	// ErrContextCanceled wraps context cancellation for the
 	// resolver's iterative queries.
 	ErrContextCanceled = errors.New("context canceled")

internal/resolver/export_test.go

@@ -1,8 +1,146 @@
 package resolver
 
-import "github.com/miekg/dns"
+import (
+	"context"
+	"log/slog"
+	"time"
+
+	"github.com/miekg/dns"
+)
+
+// NewWithFailingTCP returns a Resolver whose TCP client gives up before
+// it can connect, so the retry over TCP of every truncated reply fails.
+func NewWithFailingTCP(log *slog.Logger) *Resolver {
+	r := NewFromLogger(log)
+	r.tcp = &tcpClient{timeout: time.Nanosecond}
+
+	return r
+}
+
+// NewWithQueryTimeout returns a Resolver whose queries over UDP give up
+// after timeout, so a test that asks an address where nothing answers
+// does not wait out the usual timeout.
+func NewWithQueryTimeout(log *slog.Logger, timeout time.Duration) *Resolver {
+	r := NewFromLogger(log)
+	r.client = &udpClient{timeout: timeout}
+
+	return r
+}
+
+// FollowDelegation exports followDelegation for testing.
+func (r *Resolver) FollowDelegation(
+	ctx context.Context,
+	domain string,
+	servers []string,
+) ([]string, error) {
+	return r.followDelegation(ctx, domain, servers)
+}
+
+// FindAuthoritativeNameserversFrom exports findAuthoritativeNameservers
+// for testing.
+func (r *Resolver) FindAuthoritativeNameserversFrom(
+	ctx context.Context,
+	domain string,
+	servers []string,
+) ([]string, error) {
+	return r.findAuthoritativeNameservers(ctx, domain, servers)
+}
+
+// ResolveNSIterative exports resolveNSIterative for testing.
+func (r *Resolver) ResolveNSIterative(
+	ctx context.Context,
+	domain string,
+) ([]string, error) {
+	return r.resolveNSIterative(ctx, domain)
+}
 
 // ExtractRecordValue exports extractRecordValue for testing.
 func ExtractRecordValue(rr dns.RR) string {
 	return extractRecordValue(rr)
 }
+
+// CollectAnswerRecords exports collectAnswerRecords for testing.
+func CollectAnswerRecords(msg *dns.Msg, resp *NameserverResponse) {
+	var state queryState
+
+	collectAnswerRecords(msg, resp, &state)
+}
+
+// UsableReply exports usableReply for testing.
+func UsableReply(resp *dns.Msg, zone string, name string) bool {
+	return usableReply(resp, zone, name)
+}
+
+// NSSetFrom exports nsSetFrom for testing.
+func NSSetFrom(resp *dns.Msg, domain string) []string {
+	return nsSetFrom(resp, domain)
+}
+
+// CollectIPs exports collectIPs for testing.
+func CollectIPs(
+	results map[string]*NameserverResponse,
+) ([]string, string, error) {
+	return collectIPs(results)
+}
+
+// QueryServers exports queryServers for testing.
+func (r *Resolver) QueryServers(
+	ctx context.Context,
+	servers []string,
+	zone string,
+	name string,
+	qtype uint16,
+) (*dns.Msg, error) {
+	return r.queryServers(ctx, servers, zone, name, qtype)
+}
+
+// QueryEachNS exports queryEachNS for testing.
+func (r *Resolver) QueryEachNS(
+	ctx context.Context,
+	nameservers []string,
+	hostname string,
+) (map[string]*NameserverResponse, error) {
+	return r.queryEachNS(ctx, nameservers, hostname, recordTypes())
+}
+
+// ResolveNSIPs exports resolveNSIPs for testing, looking each name up
+// as a lookup that no other lookup started.
+func (r *Resolver) ResolveNSIPs(
+	ctx context.Context,
+	nsNames []string,
+) []string {
+	ips, _ := r.resolveNSIPs(ctx, nsNames, 1)
+
+	return ips
+}
+
+// MaxLookupDepth exports maxLookupDepth for testing.
+const MaxLookupDepth = maxLookupDepth
+
+// QueryZone exports queryZone for testing.
+func (r *Resolver) QueryZone(
+	ctx context.Context,
+	given []string,
+	withoutAddresses []string,
+	zone string,
+	name string,
+	qtype uint16,
+	depth int,
+) (*dns.Msg, error) {
+	return r.queryZone(
+		ctx, given, withoutAddresses, zone, name, qtype, depth,
+	)
+}
+
+// RootServerList exports rootServerList for testing.
+func RootServerList() []string {
+	return rootServerList()
+}
+
+// Shuffled exports shuffled for testing.
+func Shuffled(
+	servers []string,
+	shuffle func(n int, swap func(i, j int)),
+) []string {
+	return shuffled(servers, shuffle)
+}

internal/resolver/iterative_internal_test.go

@@ -0,0 +1,149 @@
+package resolver
+
+import (
+	"strconv"
+	"syscall"
+	"testing"
+
+	"github.com/miekg/dns"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// TestClassifyResponse sets a nameserver's status from the results of
+// its queries and the record types whose query failed, built here. One
+// that answered some record types, even with no records, has not failed
+// when its query for another type got no usable reply, whatever the
+// reason, and is ok, not nodata: that type may have records. One whose
+// every query got none has failed. Only one whose every type answered
+// with no records is nodata.
+func TestClassifyResponse(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name        string
+		results     queryState
+		failedTypes []string
+		wantStatus  string
+		wantError   string
+	}{
+		{
+			"every type answered with no records",
+			queryState{answered: true},
+			nil,
+			StatusNoData, "",
+		},
+		{
+			"some types answered with no records, another timed out",
+			queryState{answered: true, gotTimeout: true},
+			[]string{"A"},
+			StatusOK, "",
+		},
+		{
+			"some types answered with no records, another got SERVFAIL",
+			queryState{
+				answered: true, gotErrorReply: true, errorReply: "SERVFAIL",
+			},
+			[]string{"A"},
+			StatusOK, "",
+		},
+		{
+			"some types answered with no records, another was refused",
+			queryState{answered: true, gotRefused: true},
+			[]string{"A"},
+			StatusOK, "",
+		},
+		{
+			"some types answered with no records, another got a network error",
+			queryState{answered: true, netErr: syscall.ECONNREFUSED},
+			[]string{"A"},
+			StatusOK, "",
+		},
+		{
+			"some types answered with no records, another's reply was " +
+				"truncated and its retry over TCP failed",
+			queryState{answered: true, netErr: ErrTruncated},
+			[]string{"TXT"},
+			StatusOK, "",
+		},
+		{
+			"some types answered with no records, another got a referral",
+			queryState{answered: true, gotReferral: true},
+			[]string{"A"},
+			StatusOK, "",
+		},
+		{
+			"every query timed out",
+			queryState{gotTimeout: true},
+			[]string{"A", "AAAA", "CNAME"},
+			StatusTimeout, "all queries timed out",
+		},
+		{
+			"every query got NOTIMP",
+			queryState{gotErrorReply: true, errorReply: "NOTIMP"},
+			[]string{"A", "AAAA", "CNAME"},
+			StatusError, "server returned NOTIMP",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			resp := &NameserverResponse{Status: StatusOK, FailedTypes: tt.failedTypes}
+			classifyResponse(resp, tt.results)
+
+			assert.Equal(t, tt.wantStatus, resp.Status)
+			assert.Equal(t, tt.wantError, resp.Error)
+			assert.Equal(t, tt.failedTypes, resp.FailedTypes)
+		})
+	}
+}
+
+// TestReadReply checks which replies to a query about one record type,
+// built here, are an answer: one with the code NOERROR or NXDOMAIN. A
+// reply with any other code is not, and the type's query has failed; a
+// nameserver whose only reply it is has failed, and Error gives the
+// code, or its number when the code has no name.
+func TestReadReply(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		rcode      int
+		wantStatus string
+		wantError  string
+	}{
+		{dns.RcodeSuccess, StatusNoData, ""},
+		{dns.RcodeNameError, StatusNXDomain, ""},
+		{dns.RcodeServerFailure, StatusError, "server returned SERVFAIL"},
+		{dns.RcodeNotImplemented, StatusError, "server returned NOTIMP"},
+		{dns.RcodeFormatError, StatusError, "server returned FORMERR"},
+		{12, StatusError, "server returned 12"}, // unassigned, no name
+	}
+
+	for _, tt := range tests {
+		t.Run(strconv.Itoa(tt.rcode), func(t *testing.T) {
+			t.Parallel()
+
+			msg := new(dns.Msg)
+			msg.Authoritative = true
+			msg.Rcode = tt.rcode
+
+			resp := &NameserverResponse{Records: map[string][]string{}}
+
+			var state queryState
+
+			err := readReply(msg, resp, &state)
+			classifyResponse(resp, state)
+
+			if tt.wantStatus == StatusError {
+				require.ErrorIs(t, err, ErrUnusableReply)
+			} else {
+				require.NoError(t, err)
+			}
+
+			assert.Equal(t, tt.wantStatus, resp.Status)
+			assert.Equal(t, tt.wantError, resp.Error)
+		})
+	}
+}

internal/resolver/iterative_test.go

@@ -1,14 +1,210 @@
 package resolver_test
 
 import (
+	"math/rand/v2"
+	"slices"
 	"testing"
 
 	"github.com/miekg/dns"
 	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
 
 	"sneak.berlin/go/dnswatcher/internal/resolver"
 )
 
+// TestCollectIPs_OneAnswerIsEnough checks that one nameserver answering
+// NXDOMAIN says the name has no addresses, though the other timed out.
+func TestCollectIPs_OneAnswerIsEnough(t *testing.T) {
+	t.Parallel()
+
+	ips, _, err := resolver.CollectIPs(
+		map[string]*resolver.NameserverResponse{
+			"ns1.example.": {Status: resolver.StatusTimeout},
+			"ns2.example.": {Status: resolver.StatusNXDomain},
+		},
+	)
+	require.NoError(t, err)
+	assert.Empty(t, ips)
+}
+
+// TestCollectIPs_FailedIsNoAnswer checks that nameservers that all have
+// status error, from a refusal, a server failure, a network error or a
+// referral, are no answer rather than a name with no addresses.
+func TestCollectIPs_FailedIsNoAnswer(t *testing.T) {
+	t.Parallel()
+
+	ips, _, err := resolver.CollectIPs(
+		map[string]*resolver.NameserverResponse{
+			"ns1.example.": {Status: resolver.StatusError},
+			"ns2.example.": {Status: resolver.StatusError},
+		},
+	)
+	require.ErrorIs(t, err, resolver.ErrNoNameserverAnswered)
+	assert.Empty(t, ips)
+}
+
+// TestCollectIPs_FailedTypeIsNoAnswer checks that a nameserver whose
+// query for one of the types failed is no answer: its addresses are
+// only part of them.
+func TestCollectIPs_FailedTypeIsNoAnswer(t *testing.T) {
+	t.Parallel()
+
+	ips, _, err := resolver.CollectIPs(
+		map[string]*resolver.NameserverResponse{
+			nsExample1: {
+				Records:     map[string][]string{"A": {"192.0.2.1"}},
+				FailedTypes: []string{"AAAA"},
+				Status:      resolver.StatusOK,
+			},
+		},
+	)
+	require.ErrorIs(t, err, resolver.ErrNoNameserverAnswered)
+	assert.Empty(t, ips)
+}
+
+const (
+	// exampleCom is the zone most cases of TestUsableReply and
+	// TestNSSetFrom are about, and wwwExampleCom a name in it.
+	exampleCom    = "example.com."
+	wwwExampleCom = "www.example.com."
+
+	// exampleNS is the server the NS records nsRecord builds name.
+	exampleNS = "ns1.example.net."
+)
+
+// nsRecord builds an NS record that names a server of zone.
+func nsRecord(zone string) *dns.NS {
+	return &dns.NS{
+		Hdr: dns.RR_Header{
+			Name: zone, Rrtype: dns.TypeNS, Class: dns.ClassINET,
+		},
+		Ns: exampleNS,
+	}
+}
+
+// referralTo builds a reply that refers the query to the servers of
+// zone.
+func referralTo(zone string) *dns.Msg {
+	msg := new(dns.Msg)
+	msg.Ns = []dns.RR{nsRecord(zone)}
+
+	return msg
+}
+
+// TestUsableReply checks which replies from one of a zone's servers are
+// used. A reply that is not usable moves the query on to the zone's
+// next server.
+func TestUsableReply(t *testing.T) {
+	t.Parallel()
+
+	servfail := new(dns.Msg)
+	servfail.Rcode = dns.RcodeServerFailure
+
+	answer := new(dns.Msg)
+	answer.Authoritative = true
+	answer.Answer = []dns.RR{nsRecord(exampleCom)}
+
+	nxdomain := new(dns.Msg)
+	nxdomain.Authoritative = true
+	nxdomain.Rcode = dns.RcodeNameError
+
+	tests := []struct {
+		name  string
+		resp  *dns.Msg
+		zone  string
+		query string
+		want  bool
+	}{
+		{
+			name: "SERVFAIL", resp: servfail,
+			zone: exampleCom, query: exampleCom, want: false,
+		},
+		{
+			name: "answer", resp: answer,
+			zone: exampleCom, query: exampleCom, want: true,
+		},
+		{
+			name: "NXDOMAIN", resp: nxdomain,
+			zone: ".", query: exampleCom, want: true,
+		},
+		{
+			name: "root refers to com", resp: referralTo("com."),
+			zone: ".", query: exampleCom, want: true,
+		},
+		{
+			name: "com refers to example.com", resp: referralTo(exampleCom),
+			zone: "com.", query: wwwExampleCom, want: true,
+		},
+		{
+			name: "referral back to the zone", resp: referralTo(exampleCom),
+			zone: exampleCom, query: exampleCom, want: false,
+		},
+		{
+			name: "referral up to the root", resp: referralTo("."),
+			zone: exampleCom, query: exampleCom, want: false,
+		},
+		{
+			name: "referral sideways", resp: referralTo("net."),
+			zone: ".", query: exampleCom, want: false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			assert.Equal(t, tt.want,
+				resolver.UsableReply(tt.resp, tt.zone, tt.query),
+			)
+		})
+	}
+}
+
+// TestNSSetFrom checks which NS set a reply gives for a domain; a set
+// that is not empty ends the walk. The referral to example.com that
+// com's servers all send alike gives its delegation, so the set is the
+// same whichever of them answered, and example.com's own servers, which
+// can disagree, are not asked.
+func TestNSSetFrom(t *testing.T) {
+	t.Parallel()
+
+	answer := new(dns.Msg)
+	answer.Authoritative = true
+	answer.Answer = []dns.RR{nsRecord(exampleCom)}
+
+	tests := []struct {
+		name   string
+		resp   *dns.Msg
+		domain string
+		want   []string
+	}{
+		{
+			name: "com refers to example.com", resp: referralTo(exampleCom),
+			domain: exampleCom, want: []string{exampleNS},
+		},
+		{
+			name: "com refers on, for www.example.com",
+			resp: referralTo(exampleCom), domain: wwwExampleCom,
+			want: nil,
+		},
+		{
+			name: "answer from a server that holds example.com",
+			resp: answer, domain: exampleCom,
+			want: []string{exampleNS},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			assert.ElementsMatch(t, tt.want,
+				resolver.NSSetFrom(tt.resp, tt.domain),
+			)
+		})
+	}
+}
+
 func TestExtractRecordValue_LetterCase(t *testing.T) {
 	t.Parallel()
 
@@ -60,3 +256,62 @@ func TestExtractRecordValue_LetterCase(t *testing.T) {
 		})
 	}
 }
+
+// TestCollectAnswerRecords_CNAMEOnce collects the answers a nameserver
+// gives for a name with a CNAME, one for each record type a check asks
+// for. Each answer holds the CNAME, which must be stored once.
+func TestCollectAnswerRecords_CNAMEOnce(t *testing.T) {
+	t.Parallel()
+
+	cname := &dns.CNAME{
+		Hdr: dns.RR_Header{
+			Name: "git.eeqj.de.", Rrtype: dns.TypeCNAME, Class: dns.ClassINET,
+		},
+		Target: "fsn1app1.datavi.be.",
+	}
+
+	resp := &resolver.NameserverResponse{Records: map[string][]string{}}
+
+	for _, qtype := range []uint16{
+		dns.TypeA, dns.TypeAAAA, dns.TypeCNAME, dns.TypeMX,
+		dns.TypeTXT, dns.TypeSRV, dns.TypeCAA, dns.TypeNS,
+	} {
+		msg := new(dns.Msg)
+		msg.SetQuestion("git.eeqj.de.", qtype)
+		msg.Answer = []dns.RR{cname}
+
+		resolver.CollectAnswerRecords(msg, resp)
+	}
+
+	assert.Equal(t,
+		map[string][]string{"CNAME": {"fsn1app1.datavi.be."}},
+		resp.Records,
+	)
+}
+
+// TestShuffled shuffles the root servers with many seeds. Every order
+// must hold each root server once, so each is tried before a
+// resolution fails; each root server must come first for some seed, so
+// no one root server gets every first query; and the list passed in
+// must be left as it was.
+func TestShuffled(t *testing.T) {
+	t.Parallel()
+
+	const seeds = 1000
+
+	roots := resolver.RootServerList()
+	before := slices.Clone(roots)
+	first := make(map[string]bool)
+
+	for seed := range uint64(seeds) {
+		rng := rand.New(rand.NewPCG(seed, 0)) //nolint:gosec // seeded on purpose
+		order := resolver.Shuffled(roots, rng.Shuffle)
+
+		assert.ElementsMatch(t, roots, order)
+
+		first[order[0]] = true
+	}
+
+	assert.Len(t, first, len(roots))
+	assert.Equal(t, before, roots)
+}

internal/resolver/livedns_test.go

@@ -187,8 +187,8 @@ func liveFindAuthoritative(
 	return out
 }
 
-// liveLookupNS is liveFindAuthoritative through the LookupNS entry
-// point, so that both entry points stay independently exercised.
+// liveLookupNS looks up the NS record set of domain, a domain that has
+// one, retrying until the delegation chain can be walked.
 func liveLookupNS(
 	t *testing.T,
 	r *resolver.Resolver,
@@ -226,11 +226,17 @@ func liveLookupNS(
 // liveQueryNameserver queries one nameserver, retrying while that
 // nameserver fails to answer. NXDOMAIN and NODATA are answers and
 // are returned to the caller to assert on.
+//
+// QueryNameserver sends one query per record type, so one lost query
+// leaves its type out of an answer that is otherwise fine. A test names
+// in types the record types it reads; an answer holding records of none
+// of them is retried too.
 func liveQueryNameserver(
 	t *testing.T,
 	r *resolver.Resolver,
 	nameserver string,
 	hostname string,
+	types ...string,
 ) *resolver.NameserverResponse {
 	t.Helper()
 
@@ -260,6 +266,18 @@ func liveQueryNameserver(
 				)
 			}
 
+			hasRecords := func(recordType string) bool {
+				return len(resp.Records[recordType]) > 0
+			}
+
+			if len(types) > 0 && !slices.ContainsFunc(types, hasRecords) {
+				return fmt.Errorf(
+					"%w: %s returned no %s records",
+					livednstest.ErrNoAnswer, nameserver,
+					strings.Join(types, " or "),
+				)
+			}
+
 			out = resp
 
 			return nil
@@ -383,3 +401,37 @@ func liveResolveIPsAllowingEmpty(
 
 	return out
 }
+
+// liveResolveNSIPs looks up the addresses of the nameservers named
+// names, retrying until there are at least atLeast of them: a name
+// whose lookup got no reply is left out of the result, not an error.
+func liveResolveNSIPs(
+	t *testing.T,
+	r *resolver.Resolver,
+	names []string,
+	atLeast int,
+) []string {
+	t.Helper()
+
+	var out []string
+
+	livednstest.Retry(
+		t,
+		"ResolveNSIPs("+strings.Join(names, ", ")+")",
+		func(ctx context.Context) error {
+			ips := r.ResolveNSIPs(ctx, names)
+			if len(ips) < atLeast {
+				return fmt.Errorf(
+					"%w: %d addresses, expected at least %d",
+					livednstest.ErrNoAnswer, len(ips), atLeast,
+				)
+			}
+
+			out = ips
+
+			return nil
+		},
+	)
+
+	return out
+}

internal/resolver/resolver.go

@@ -31,11 +31,15 @@ type Params struct {
 }
 
 // NameserverResponse holds one nameserver's response for a query.
+// FailedTypes lists the record types whose query got no usable reply,
+// and Records holds nothing for them: their records are not known. When
+// no record type got one, Status and Error say the nameserver failed.
 type NameserverResponse struct {
-	Nameserver string
-	Records    map[string][]string
-	Status     string
-	Error      string
+	Nameserver  string
+	Records     map[string][]string
+	FailedTypes []string
+	Status      string
+	Error       string
 }
 
 // Resolver performs iterative DNS resolution from root servers.

internal/resolver/resolver_test.go

@@ -1,7 +1,10 @@
 package resolver_test
 
 import (
+	"bytes"
 	"context"
+	"errors"
+	"fmt"
 	"log/slog"
 	"net"
 	"os"
@@ -10,9 +13,11 @@ import (
 	"testing"
 	"time"
 
+	"github.com/miekg/dns"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
+	"sneak.berlin/go/dnswatcher/internal/livednstest"
 	"sneak.berlin/go/dnswatcher/internal/resolver"
 )
 
@@ -20,6 +25,13 @@ import (
 // Test helpers
 // ----------------------------------------------------------------
 
+// nonexistentDomain is a .com domain that does not exist.
+const nonexistentDomain = "dnswatcher-test-does-not-exist.com"
+
+// noAnswerAddress is 192.0.2.1, a documentation address: nothing
+// answers there.
+const noAnswerAddress = "192.0.2.1"
+
 func newTestResolver(t *testing.T) *resolver.Resolver {
 	t.Helper()
 
@@ -77,9 +89,51 @@ func TestFindAuthoritativeNameservers_Subdomain(
 	t.Parallel()
 
 	r := newTestResolver(t)
-	nameservers := liveFindAuthoritative(t, r, "www.google.com")
+	fromHost := liveFindAuthoritative(t, r, "www.google.com")
+	fromZone := liveFindAuthoritative(t, r, "google.com")
 
-	assert.NotEmpty(t, nameservers)
+	assert.Equal(t, fromZone, fromHost)
+}
+
+// TestFindAuthoritativeNameservers_DelegatedSubdomain looks up the
+// nameservers of www.cs.cmu.edu, a name in cs.cmu.edu, a zone that
+// cmu.edu delegates to other servers. The servers of cs.cmu.edu answer
+// that the name has no delegation of its own, so it gets their names,
+// not those of the cmu.edu servers. Every referral on the way gives the
+// nameservers' addresses, so the walk sends few queries.
+func TestFindAuthoritativeNameservers_DelegatedSubdomain(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+	fromHost := liveFindAuthoritative(t, r, "www.cs.cmu.edu")
+	fromZone := liveLookupNS(t, r, "cs.cmu.edu")
+	fromParent := liveLookupNS(t, r, "cmu.edu")
+
+	assert.Equal(t, fromZone, fromHost)
+	assert.NotEqual(t, fromParent, fromHost)
+}
+
+// TestFindAuthoritativeNameservers_NoAnswer starts each walk for
+// www.google.com at 192.0.2.1, a documentation address where nothing
+// answers. A walk that got no answer does not say that the name has no
+// delegation of its own, so the lookup returns that walk's error, about
+// www.google.com, and tries no parent name: trying google.com and com
+// would end in ErrNoNameservers, or in the error of a walk for one of
+// them.
+func TestFindAuthoritativeNameservers_NoAnswer(t *testing.T) {
+	t.Parallel()
+
+	r := resolver.NewWithQueryTimeout(slog.Default(), 100*time.Millisecond)
+
+	nameservers, err := r.FindAuthoritativeNameserversFrom(
+		t.Context(), "www.google.com", []string{noAnswerAddress},
+	)
+	require.Error(t, err)
+	require.NotErrorIs(t, err, resolver.ErrNoNameservers)
+	assert.Contains(t, err.Error(), "query www.google.com. @"+noAnswerAddress)
+	assert.Empty(t, nameservers)
 }
 
 func TestFindAuthoritativeNameservers_ReturnsSorted(
@@ -136,6 +190,134 @@ func TestFindAuthoritativeNameservers_CloudflareDomain(
 	}
 }
 
+// TestResolveNSIPs_EveryNameserver looks up the addresses of two of
+// google.com's nameservers together, as the walk does when a referral
+// names a zone's nameservers without their addresses, and compares them
+// with each looked up alone. Together they must give the addresses of
+// both, not only of the first that resolves, so that when one gives no
+// usable reply the walk goes on to the other.
+func TestResolveNSIPs_EveryNameserver(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+	names := []string{"ns3.google.com.", "ns4.google.com."}
+	want := make([]string, 0, len(names))
+
+	for _, name := range names {
+		want = append(want, liveResolveNSIPs(t, r, []string{name}, 1)...)
+	}
+
+	got := liveResolveNSIPs(t, r, names, len(want))
+
+	assert.ElementsMatch(t, want, got)
+}
+
+// TestResolveNSIPs_ZoneDelegatedWithoutAddresses looks up the address
+// of a.ntpns.org, a nameserver of pool.ntp.org. The org servers delegate
+// ntpns.org to nameservers in other zones and give none of their
+// addresses, so those are looked up on the way.
+func TestResolveNSIPs_ZoneDelegatedWithoutAddresses(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+	ips := liveResolveNSIPs(t, r, []string{"a.ntpns.org."}, 1)
+
+	for _, ip := range ips {
+		assert.NotNil(t, net.ParseIP(ip), "should be valid IP: %s", ip)
+	}
+}
+
+// TestQueryZone_GivenAddressesFail asks the servers of ntp.org about
+// pool.ntp.org, as the walk to a name under ntp.org does after the org
+// servers' referral. That referral names four nameservers and gives an
+// address for ns1.everett.org alone; here the given address is
+// 192.0.2.1, where nothing answers, so the other three must be looked
+// up and asked.
+func TestQueryZone_GivenAddressesFail(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+
+	var resp *dns.Msg
+
+	livednstest.Retry(
+		t,
+		"QueryZone(192.0.2.1 and three ntp.org nameservers, pool.ntp.org)",
+		func(ctx context.Context) error {
+			var err error
+
+			resp, err = r.QueryZone(
+				ctx, []string{"192.0.2.1"},
+				[]string{"anyns.pch.net.", "dns1.udel.edu.", "dns2.udel.edu."},
+				"ntp.org.", "pool.ntp.org.", dns.TypeNS, 0,
+			)
+
+			return err
+		},
+	)
+
+	assert.NotEmpty(t, resolver.NSSetFrom(resp, "pool.ntp.org."))
+}
+
+// TestQueryZone_LookupDepth asks the servers of g.ntpns.org, a
+// nameserver of pool.ntp.org, for its address, as looking that address
+// up does when anyns.pch.net, one of the servers of ntpns.org, gives the
+// referral to g.ntpns.org without addresses. Their addresses are looked
+// up (here only a.ntpns.org's), and that needs a bitnames.com
+// nameserver's address, as the org servers delegate ntpns.org without
+// addresses. From depth 1, where looking up g.ntpns.org's address
+// starts, that makes three lookups and the address is found. From one
+// below maxLookupDepth, the bitnames.com lookup would be past the limit,
+// so nothing can be asked, and the error says the limit is why.
+func TestQueryZone_LookupDepth(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+	withoutAddresses := []string{"a.ntpns.org."}
+
+	var resp *dns.Msg
+
+	livednstest.Retry(
+		t,
+		"QueryZone(a.ntpns.org without its address, g.ntpns.org)",
+		func(ctx context.Context) error {
+			var err error
+
+			resp, err = r.QueryZone(
+				ctx, nil, withoutAddresses, "g.ntpns.org.", "g.ntpns.org.",
+				dns.TypeA, 1,
+			)
+
+			return err
+		},
+	)
+
+	assert.NotEmpty(t, resp.Answer)
+
+	var limitErr error
+
+	// Any other error is live DNS not answering, and is retried.
+	livednstest.Retry(
+		t,
+		"QueryZone(a.ntpns.org without its address, g.ntpns.org, "+
+			"one below the limit)",
+		func(ctx context.Context) error {
+			_, limitErr = r.QueryZone(
+				ctx, nil, withoutAddresses, "g.ntpns.org.", "g.ntpns.org.",
+				dns.TypeA, resolver.MaxLookupDepth-1,
+			)
+			if limitErr == nil ||
+				errors.Is(limitErr, resolver.ErrLookupDepthExceeded) {
+				return nil
+			}
+
+			return limitErr
+		},
+	)
+
+	require.ErrorIs(t, limitErr, resolver.ErrLookupDepthExceeded)
+}
+
 // ----------------------------------------------------------------
 // QueryNameserver tests
 // ----------------------------------------------------------------
@@ -145,7 +327,7 @@ func TestQueryNameserver_BasicA(t *testing.T) {
 
 	r := newTestResolver(t)
 	ns := findOneNSForDomain(t, r, "google.com")
-	resp := liveQueryNameserver(t, r, ns, "www.google.com")
+	resp := liveQueryNameserver(t, r, ns, "www.google.com", "A", "CNAME")
 
 	require.NotNil(t, resp)
 
@@ -159,12 +341,26 @@ func TestQueryNameserver_BasicA(t *testing.T) {
 	)
 }
 
+// TestQueryNameserver_ZoneDelegatedWithoutAddresses asks a.ntpns.org, a
+// nameserver of pool.ntp.org, about pool.ntp.org, as the watcher does.
+// The org servers delegate ntpns.org without the addresses of its
+// nameservers, so finding a.ntpns.org's address needs a lookup inside
+// the one QueryNameserver starts.
+func TestQueryNameserver_ZoneDelegatedWithoutAddresses(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+	resp := liveQueryNameserver(t, r, "a.ntpns.org.", "pool.ntp.org", "A")
+
+	assert.Equal(t, resolver.StatusOK, resp.Status)
+}
+
 func TestQueryNameserver_AAAA(t *testing.T) {
 	t.Parallel()
 
 	r := newTestResolver(t)
 	ns := findOneNSForDomain(t, r, "cloudflare.com")
-	resp := liveQueryNameserver(t, r, ns, "cloudflare.com")
+	resp := liveQueryNameserver(t, r, ns, "cloudflare.com", "AAAA")
 
 	aaaaRecords := resp.Records["AAAA"]
 	require.NotEmpty(t, aaaaRecords,
@@ -184,7 +380,7 @@ func TestQueryNameserver_MX(t *testing.T) {
 
 	r := newTestResolver(t)
 	ns := findOneNSForDomain(t, r, "google.com")
-	resp := liveQueryNameserver(t, r, ns, "google.com")
+	resp := liveQueryNameserver(t, r, ns, "google.com", "MX")
 
 	mxRecords := resp.Records["MX"]
 	require.NotEmpty(t, mxRecords,
@@ -197,7 +393,7 @@ func TestQueryNameserver_TXT(t *testing.T) {
 
 	r := newTestResolver(t)
 	ns := findOneNSForDomain(t, r, "google.com")
-	resp := liveQueryNameserver(t, r, ns, "google.com")
+	resp := liveQueryNameserver(t, r, ns, "google.com", "TXT")
 
 	txtRecords := resp.Records["TXT"]
 	require.NotEmpty(t, txtRecords,
@@ -219,6 +415,30 @@ func TestQueryNameserver_TXT(t *testing.T) {
 	)
 }
 
+// TestQueryNameserver_TruncatedReplyWhoseTCPRetryFails asks a google.com
+// nameserver about google.com with a resolver whose retries over TCP
+// fail. google.com's TXT records do not fit in a reply over UDP, so TXT
+// is reported as failed, holding none of the records that fit, and
+// logged with the reason, while the nameserver, which answered the other
+// types, is ok.
+func TestQueryNameserver_TruncatedReplyWhoseTCPRetryFails(t *testing.T) {
+	t.Parallel()
+
+	ns := findOneNSForDomain(t, newTestResolver(t), "google.com")
+
+	var logs bytes.Buffer
+
+	r := resolver.NewWithFailingTCP(slog.New(slog.NewTextHandler(&logs, nil)))
+	resp := liveQueryNameserver(t, r, ns, "google.com")
+
+	assert.Equal(t, resolver.StatusOK, resp.Status)
+	assert.Contains(t, resp.FailedTypes, "TXT")
+	assert.NotContains(t, resp.Records, "TXT")
+	assert.Contains(t, logs.String(),
+		"hostname=google.com. nameserver="+ns+" type=TXT error=",
+	)
+}
+
 func TestQueryNameserver_NXDomain(t *testing.T) {
 	t.Parallel()
 
@@ -231,6 +451,223 @@ func TestQueryNameserver_NXDomain(t *testing.T) {
 	assert.Equal(t, resolver.StatusNXDomain, resp.Status)
 }
 
+// TestQueryNameserver_Refused asks a google.com nameserver about
+// cloudflare.com, a zone it does not serve, which it refuses. Refusing
+// is a failure to answer, not an answer with no records.
+func TestQueryNameserver_Refused(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+	ns := findOneNSForDomain(t, r, "google.com")
+
+	var resp *resolver.NameserverResponse
+
+	livednstest.Retry(
+		t,
+		"QueryNameserver("+ns+", cloudflare.com)",
+		func(ctx context.Context) error {
+			var err error
+
+			resp, err = r.QueryNameserver(ctx, ns, "cloudflare.com")
+			if err != nil {
+				return err
+			}
+
+			// A timeout or a network error is no reply at all.
+			if resp.Status == resolver.StatusTimeout ||
+				strings.HasPrefix(resp.Error, "network error") {
+				return fmt.Errorf(
+					"%w: %s: %s",
+					livednstest.ErrNoAnswer, ns, resp.Error,
+				)
+			}
+
+			return nil
+		},
+	)
+
+	assert.Equal(t, resolver.StatusError, resp.Status)
+	assert.Equal(t, "server returned REFUSED", resp.Error)
+}
+
+// TestQueryServers_RecursiveResolverRefused passes a public recursive
+// resolver to QueryServers as the server of google.com. These resolvers
+// refuse a query that does not ask for recursion and answer one that
+// does. The resolver never asks for recursion, so the query must be
+// reported as refused, never answered. Each resolver is run by a
+// different operator, and they are asked in turn until one replies, so
+// one operator not answering does not fail the test.
+func TestQueryServers_RecursiveResolverRefused(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+	resolvers := []string{
+		"64.6.64.6", "185.222.222.222", "4.2.2.1", "9.9.9.9",
+	}
+
+	var err error
+
+	livednstest.Retry(
+		t,
+		"QueryServers(public recursive resolvers, google.com)",
+		func(ctx context.Context) error {
+			for _, ip := range resolvers {
+				_, err = r.QueryServers(
+					ctx, []string{ip}, "google.com.", "google.com.",
+					dns.TypeA,
+				)
+
+				// A refusal or an answer is a reply; anything else may
+				// be no reply at all, so the next resolver is asked.
+				if err == nil || errors.Is(err, resolver.ErrRefused) {
+					return nil
+				}
+			}
+
+			return fmt.Errorf("%w: %w", livednstest.ErrNoAnswer, err)
+		},
+	)
+
+	require.ErrorIs(t, err, resolver.ErrRefused)
+}
+
+// googleNameserverIPv4s returns the IPv4 addresses of google.com's
+// nameservers, the only addresses the resolver asks servers at.
+func googleNameserverIPv4s(t *testing.T, r *resolver.Resolver) []string {
+	t.Helper()
+
+	names := liveFindAuthoritative(t, r, "google.com")
+
+	return liveResolveNSIPs(t, r, names, len(names))
+}
+
+// TestQueryServers_EveryServerRefused asks all of google.com's
+// nameservers about cloudflare.com, a zone they do not serve, which
+// they all refuse. The error says every server refused; it is not
+// ErrIntercepted, which only the root servers refusing shows.
+func TestQueryServers_EveryServerRefused(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+	servers := googleNameserverIPv4s(t, r)
+
+	var err error
+
+	livednstest.Retry(
+		t,
+		"QueryServers(google.com servers, cloudflare.com)",
+		func(ctx context.Context) error {
+			_, err = r.QueryServers(
+				ctx, servers, "google.com.", "cloudflare.com.",
+				dns.TypeNS,
+			)
+
+			// When not every server refused, one may have given no
+			// reply at all, so the attempt is tried again.
+			if err != nil &&
+				!strings.HasPrefix(err.Error(), "every server of") {
+				return fmt.Errorf(
+					"%w: %w", livednstest.ErrNoAnswer, err,
+				)
+			}
+
+			return nil
+		},
+	)
+
+	require.ErrorIs(t, err, resolver.ErrRefused)
+	require.NotErrorIs(t, err, resolver.ErrIntercepted)
+	require.EqualError(
+		t, err,
+		"every server of google.com. refused a query for "+
+			"cloudflare.com.: dns query refused",
+	)
+}
+
+// TestQueryServers_EveryRootServerRefused passes google.com's
+// nameservers to QueryServers as the servers of the root zone. They
+// refuse a query about cloudflare.com, as root servers would if
+// something on the network answered in their place, so the error is
+// ErrIntercepted.
+func TestQueryServers_EveryRootServerRefused(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+	servers := googleNameserverIPv4s(t, r)
+
+	var err error
+
+	livednstest.Retry(
+		t,
+		"QueryServers(google.com servers as root servers, cloudflare.com)",
+		func(ctx context.Context) error {
+			_, err = r.QueryServers(
+				ctx, servers, ".", "cloudflare.com.", dns.TypeNS,
+			)
+
+			// When not every server refused, one may have given no
+			// reply at all, so the attempt is tried again. Both errors
+			// for every server refusing say "refused a query for".
+			if err != nil &&
+				!strings.Contains(err.Error(), "refused a query for") {
+				return fmt.Errorf(
+					"%w: %w", livednstest.ErrNoAnswer, err,
+				)
+			}
+
+			return nil
+		},
+	)
+
+	require.ErrorIs(t, err, resolver.ErrIntercepted)
+	require.EqualError(
+		t, err,
+		"every root server refused a query for cloudflare.com.: "+
+			"this network intercepts DNS queries",
+	)
+}
+
+// TestQueryServers_NotEveryRootServerRefused passes google.com's
+// nameservers and 192.0.2.1 to QueryServers as the servers of the root
+// zone. The google.com nameservers refuse a query about cloudflare.com,
+// but nothing answers at 192.0.2.1, a documentation address, so not
+// every server refused, wherever 192.0.2.1 falls in the random order:
+// the error is not ErrIntercepted and does not say every server refused.
+func TestQueryServers_NotEveryRootServerRefused(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+	servers := googleNameserverIPv4s(t, r)
+	servers = append(servers, "192.0.2.1")
+
+	var err error
+
+	livednstest.Retry(
+		t,
+		"QueryServers(google.com servers and 192.0.2.1, cloudflare.com)",
+		func(ctx context.Context) error {
+			_, err = r.QueryServers(
+				ctx, servers, ".", "cloudflare.com.", dns.TypeNS,
+			)
+
+			// An attempt that ran out of time may not have asked every
+			// server, so it is tried again.
+			if ctx.Err() != nil {
+				return fmt.Errorf(
+					"%w: %w", livednstest.ErrNoAnswer, err,
+				)
+			}
+
+			return nil
+		},
+	)
+
+	require.Error(t, err)
+	require.NotErrorIs(t, err, resolver.ErrIntercepted)
+	// Both errors for every server refusing say "refused a query for".
+	require.NotContains(t, err.Error(), "refused a query for")
+}
+
 func TestQueryNameserver_RecordsSorted(t *testing.T) {
 	t.Parallel()
 
@@ -309,37 +746,58 @@ func TestQueryAllNameservers_ReturnsAllNS(t *testing.T) {
 func TestQueryAllNameservers_AllReturnOK(t *testing.T) {
 	t.Parallel()
 
-	r := newTestResolver(t)
-	results := liveQueryAllNameservers(t, r, "google.com")
+	// The last two names are in zones other than their last two
+	// labels: google.co.uk, under the two-label suffix co.uk, and
+	// compute-1.amazonaws.com, which amazonaws.com delegates to other
+	// servers and which has a host name for each of its addresses.
+	// Servers above a name's zone only refer onward, which gives
+	// nodata, so ok shows the name was asked at its own zone's
+	// servers.
+	hostnames := []string{
+		"google.com",
+		"www.google.co.uk",
+		"ec2-3-80-0-1.compute-1.amazonaws.com",
+	}
 
-	// A quorum, not unanimity: one authoritative server being
-	// slow or rate-limiting us is a property of the live
-	// internet, not a resolver defect.
-	assert.GreaterOrEqual(
-		t,
-		countStatus(results, resolver.StatusOK),
-		liveQuorum(len(results)),
-		"a quorum of nameservers should answer OK: %s",
-		describeStatuses(results),
-	)
+	for _, hostname := range hostnames {
+		t.Run(hostname, func(t *testing.T) {
+			t.Parallel()
 
-	// Quorum tolerates SILENCE only. Every individual result must
-	// be either the expected answer or a non-answer: ok, timeout
-	// or error, and nothing else. Stated as a closed allowlist so
-	// that a wrong answer no one thought to ban — nxdomain and
-	// nodata today, any status added later — fails here rather
-	// than sliding through under the quorum.
-	assert.Empty(
-		t,
-		unsanctionedStatuses(
-			results,
-			resolver.StatusOK,
-			resolver.StatusTimeout,
-			resolver.StatusError,
-		),
-		"every nameserver must answer OK or not answer at all: %s",
-		describeStatuses(results),
-	)
+			r := newTestResolver(t)
+			results := liveQueryAllNameservers(t, r, hostname)
+
+			// A quorum, not unanimity: one authoritative server
+			// being slow or rate-limiting us is a property of the
+			// live internet, not a resolver defect.
+			assert.GreaterOrEqual(
+				t,
+				countStatus(results, resolver.StatusOK),
+				liveQuorum(len(results)),
+				"a quorum of nameservers should answer OK: %s",
+				describeStatuses(results),
+			)
+
+			// Quorum tolerates SILENCE only. Every individual
+			// result must be either the expected answer or a
+			// non-answer: ok, timeout or error, and nothing else.
+			// Stated as a closed allowlist so that a wrong answer
+			// no one thought to ban — nxdomain and nodata today,
+			// any status added later — fails here rather than
+			// sliding through under the quorum.
+			assert.Empty(
+				t,
+				unsanctionedStatuses(
+					results,
+					resolver.StatusOK,
+					resolver.StatusTimeout,
+					resolver.StatusError,
+				),
+				"every nameserver must answer OK or not answer "+
+					"at all: %s",
+				describeStatuses(results),
+			)
+		})
+	}
 }
 
 func TestQueryAllNameservers_NXDomainFromAllNS(
@@ -414,6 +872,145 @@ func TestLookupNS_MatchesFindAuthoritative(t *testing.T) {
 	assert.Equal(t, fromFind, fromLookup)
 }
 
+// TestLookupNS_ParentZoneDelegatedWithoutAddresses looks up the
+// nameservers of g.ntpns.org. The org servers delegate its parent zone,
+// ntpns.org, without the addresses of its nameservers, so the walk has
+// to look them up to ask them. If it did not, the walk for g.ntpns.org
+// would fail.
+func TestLookupNS_ParentZoneDelegatedWithoutAddresses(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+	nameservers := liveLookupNS(t, r, "g.ntpns.org")
+
+	assert.Contains(t, nameservers, "a.ntpns.org.")
+}
+
+// TestLookupNS_DomainThatDoesNotExist looks up the nameservers of a .com
+// domain that does not exist. The .com servers answer NXDOMAIN, so the
+// error is ErrNXDomain, and the domain does not get their names.
+func TestLookupNS_DomainThatDoesNotExist(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+
+	var (
+		nameservers []string
+		err         error
+	)
+
+	livednstest.Retry(
+		t,
+		"LookupNS("+nonexistentDomain+")",
+		func(ctx context.Context) error {
+			nameservers, err = r.LookupNS(ctx, nonexistentDomain)
+			if errors.Is(err, resolver.ErrNXDomain) {
+				return nil
+			}
+
+			return err
+		},
+	)
+
+	require.ErrorIs(t, err, resolver.ErrNXDomain)
+	assert.Empty(t, nameservers)
+}
+
+// TestLookupNS_NoDelegationOfItsOwn looks up the nameservers of
+// www.google.com, a name in the google.com zone with no delegation of
+// its own, as a domain such as octocat.github.io is. The google.com
+// servers answer with no NS records for it: the set is empty, and it is
+// not ErrNXDomain.
+func TestLookupNS_NoDelegationOfItsOwn(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+
+	var nameservers []string
+
+	livednstest.Retry(
+		t,
+		"LookupNS(www.google.com)",
+		func(ctx context.Context) error {
+			var err error
+
+			nameservers, err = r.LookupNS(ctx, "www.google.com")
+
+			return err
+		},
+	)
+
+	assert.Empty(t, nameservers)
+}
+
+// TestFollowDelegation_NoAnswer starts the walk LookupNS uses, for
+// google.com, at 192.0.2.1, a documentation address where nothing
+// answers. A walk that got no answer is an error, not an empty set,
+// which the watcher would report as an NS Change with every nameserver
+// removed.
+func TestFollowDelegation_NoAnswer(t *testing.T) {
+	t.Parallel()
+
+	r := resolver.NewWithQueryTimeout(slog.Default(), 100*time.Millisecond)
+
+	nameservers, err := r.FollowDelegation(
+		t.Context(), "google.com.", []string{noAnswerAddress},
+	)
+	require.Error(t, err)
+	assert.Empty(t, nameservers)
+}
+
+// TestResolveNSIterative_NoDelegationOfItsOwn walks to the nameservers
+// of www.google.com as the fallback walk does. As in
+// TestLookupNS_NoDelegationOfItsOwn, the set is empty, with no error.
+func TestResolveNSIterative_NoDelegationOfItsOwn(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+
+	var nameservers []string
+
+	livednstest.Retry(
+		t,
+		"ResolveNSIterative(www.google.com)",
+		func(ctx context.Context) error {
+			var err error
+
+			nameservers, err = r.ResolveNSIterative(ctx, "www.google.com")
+
+			return err
+		},
+	)
+
+	assert.Empty(t, nameservers)
+}
+
+// TestResolveNSIterative_DomainThatDoesNotExist walks to the nameservers
+// of a .com domain that does not exist as the fallback walk does. As in
+// TestLookupNS_DomainThatDoesNotExist, the error is ErrNXDomain.
+func TestResolveNSIterative_DomainThatDoesNotExist(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+
+	var err error
+
+	livednstest.Retry(
+		t,
+		"ResolveNSIterative("+nonexistentDomain+")",
+		func(ctx context.Context) error {
+			_, err = r.ResolveNSIterative(ctx, nonexistentDomain)
+			if errors.Is(err, resolver.ErrNXDomain) {
+				return nil
+			}
+
+			return err
+		},
+	)
+
+	require.ErrorIs(t, err, resolver.ErrNXDomain)
+}
+
 // ----------------------------------------------------------------
 // ResolveIPAddresses tests
 // ----------------------------------------------------------------
@@ -477,6 +1074,34 @@ func TestResolveIPAddresses_CloudflareDomain(t *testing.T) {
 	assert.NotEmpty(t, ips)
 }
 
+// TestResolveIPAddresses_NameserverIPv4AndIPv6 looks up the addresses of
+// one of cloudflare.com's nameservers, as a domain check does for each
+// nameserver. That name has A and AAAA records, so both kinds of address
+// come back.
+func TestResolveIPAddresses_NameserverIPv4AndIPv6(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+	ns := findOneNSForDomain(t, r, "cloudflare.com")
+	ips := liveResolveIPs(t, r, ns)
+
+	var ipv4, ipv6 int
+
+	for _, ip := range ips {
+		parsed := net.ParseIP(ip)
+		require.NotNil(t, parsed, "should be valid IP: %s", ip)
+
+		if parsed.To4() != nil {
+			ipv4++
+		} else {
+			ipv6++
+		}
+	}
+
+	assert.Positive(t, ipv4, "no IPv4 address for %s: %v", ns, ips)
+	assert.Positive(t, ipv6, "no IPv6 address for %s: %v", ns, ips)
+}
+
 // ----------------------------------------------------------------
 // Context cancellation tests
 // ----------------------------------------------------------------
@@ -518,6 +1143,29 @@ func TestQueryAllNameservers_ContextCanceled(t *testing.T) {
 	assert.Error(t, err)
 }
 
+// TestQueryEachNS_CanceledDuringQuery cancels the context while a
+// nameserver is being queried, as shutdown does. A lookup cut short
+// says nothing about the nameserver, so it must return an error, not a
+// failed response for it.
+func TestQueryEachNS_CanceledDuringQuery(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+	ctx, cancel := context.WithCancel(context.Background())
+	t.Cleanup(cancel)
+
+	// Finding the nameserver's address alone starts at the root
+	// servers and takes several round trips, so a cancel a few
+	// milliseconds in lands during the query.
+	time.AfterFunc(5*time.Millisecond, cancel)
+
+	results, err := r.QueryEachNS(
+		ctx, []string{"ns1.google.com."}, "google.com",
+	)
+	require.ErrorIs(t, err, resolver.ErrContextCanceled)
+	assert.Nil(t, results)
+}
+
 // ----------------------------------------------------------------
 // Timeout tests
 // ----------------------------------------------------------------
@@ -530,7 +1178,7 @@ func TestQueryNameserverIP_Timeout(t *testing.T) {
 	// 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
+	// makes the status vary from run to run between error and
 	// timeout, so the deadline must outlast the first try.
 	ctx, cancel := context.WithTimeout(
 		context.Background(), 3*time.Second,
@@ -547,6 +1195,105 @@ func TestQueryNameserverIP_Timeout(t *testing.T) {
 	assert.NotEmpty(t, resp.Error)
 }
 
+// TestQueryNameserverIP_CancelledLogsNothing cancels the context while
+// a query to 192.0.2.1, where nothing answers, is waiting for a reply,
+// as shutdown does. The query was cut short, not failed, so nothing is
+// logged.
+func TestQueryNameserverIP_CancelledLogsNothing(t *testing.T) {
+	t.Parallel()
+
+	var logs bytes.Buffer
+
+	r := resolver.NewFromLogger(slog.New(slog.NewTextHandler(&logs, nil)))
+
+	ctx, cancel := context.WithCancel(context.Background())
+	t.Cleanup(cancel)
+	time.AfterFunc(100*time.Millisecond, cancel)
+
+	_, err := r.QueryNameserverIP(
+		ctx, "unreachable.test.", "192.0.2.1", "example.com",
+	)
+	require.NoError(t, err)
+
+	assert.Empty(t, logs.String())
+}
+
+// TestCollectIPs_NoNameserverAnswered takes the response of a
+// nameserver at 192.0.2.1, where nothing answers, as
+// TestQueryNameserverIP_Timeout does. Addresses collected from
+// nameservers that all failed to answer are an error, not none.
+func TestCollectIPs_NoNameserverAnswered(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+
+	// The deadline outlasts the first try, as in
+	// TestQueryNameserverIP_Timeout.
+	ctx, cancel := context.WithTimeout(
+		context.Background(), 3*time.Second,
+	)
+	t.Cleanup(cancel)
+
+	resp, err := r.QueryNameserverIP(
+		ctx, "unreachable.test.", "192.0.2.1",
+		"example.com",
+	)
+	require.NoError(t, err)
+
+	ips, _, err := resolver.CollectIPs(
+		map[string]*resolver.NameserverResponse{resp.Nameserver: resp},
+	)
+	require.ErrorIs(t, err, resolver.ErrNoNameserverAnswered)
+	assert.Empty(t, ips)
+}
+
+// TestCollectIPs_ReferralIsNoAnswer asks a root server about
+// example.com, which the root zone does not hold, so it only refers the
+// query to the com servers. That reply is no answer, as is a parent
+// zone's when every server of the name's own zone failed.
+func TestCollectIPs_ReferralIsNoAnswer(t *testing.T) {
+	t.Parallel()
+
+	r := newTestResolver(t)
+
+	var resp *resolver.NameserverResponse
+
+	livednstest.Retry(
+		t,
+		"QueryNameserverIP(a.root-servers.net, example.com)",
+		func(ctx context.Context) error {
+			var err error
+
+			resp, err = r.QueryNameserverIP(
+				ctx, "a.root-servers.net.", "198.41.0.4",
+				"example.com",
+			)
+			if err != nil {
+				return err
+			}
+
+			// A timeout or a network error is no reply at all.
+			if resp.Status == resolver.StatusTimeout ||
+				strings.HasPrefix(resp.Error, "network error") {
+				return fmt.Errorf(
+					"%w: %s", livednstest.ErrNoAnswer, resp.Error,
+				)
+			}
+
+			return nil
+		},
+	)
+
+	assert.Equal(t, resolver.StatusError, resp.Status)
+	assert.Equal(t, "server returned a referral", resp.Error)
+
+	ips, _, err := resolver.CollectIPs(
+		map[string]*resolver.NameserverResponse{resp.Nameserver: resp},
+	)
+	require.ErrorIs(t, err, resolver.ErrNoNameserverAnswered)
+	assert.Empty(t, ips)
+}
+
 func TestResolveIPAddresses_ContextCanceled(t *testing.T) {
 	t.Parallel()
 

internal/server/export_test.go

@@ -3,6 +3,8 @@ package server
 import (
 	"net/http"
 	"time"
+
+	"github.com/go-chi/chi/v5"
 )
 
 // RequestTimeout exports the handler execution budget applied by
@@ -22,3 +24,15 @@ func SetListenPort(s *Server, port int) {
 func HTTPServerOf(s *Server) *http.Server {
 	return s.httpServer
 }
+
+// EnableSentry runs the Sentry setup that the start hook runs, without
+// starting the HTTP server.
+func EnableSentry(s *Server) error {
+	return s.enableSentry()
+}
+
+// RouterOf returns the router SetupRoutes built, so a test can add a
+// route that panics.
+func RouterOf(s *Server) *chi.Mux {
+	return s.router
+}

internal/server/routes.go

@@ -4,6 +4,7 @@ import (
 	"net/http"
 	"time"
 
+	sentryhttp "github.com/getsentry/sentry-go/http"
 	"github.com/go-chi/chi/v5"
 	chimw "github.com/go-chi/chi/v5/middleware"
 	"github.com/prometheus/client_golang/prometheus/promhttp"
@@ -25,6 +26,16 @@ func (s *Server) SetupRoutes() {
 	s.router.Use(s.mw.Logging())
 	s.router.Use(chimw.Timeout(requestTimeout))
 
+	// Report panics in handlers to Sentry when DNSWATCHER_SENTRY_DSN is
+	// set. Repanic passes each panic on to chimw.Recoverer above, which
+	// still answers the request.
+	if s.sentryEnabled {
+		sentryHandler := sentryhttp.New(sentryhttp.Options{
+			Repanic: true,
+		})
+		s.router.Use(sentryHandler.Handle)
+	}
+
 	// Public, unauthenticated, read-only routes, the only ones
 	// REPO_POLICIES.md allows wildcard CORS on. CORS is middleware of
 	// this whole router, not of a Group, so that it also answers

internal/server/sentry_test.go

@@ -0,0 +1,190 @@
+package server_test
+
+import (
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"strings"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/getsentry/sentry-go"
+	"github.com/spf13/viper"
+	"go.uber.org/fx"
+
+	"sneak.berlin/go/dnswatcher/internal/server"
+)
+
+// The tests below set env vars and touch the global state of viper and
+// of Sentry, so they cannot use t.Parallel.
+
+// standInDelay is how long the Sentry stand-in takes to answer. It
+// records a report only then, so a report that Shutdown did not wait
+// for has not been recorded yet when Shutdown returns.
+const standInDelay = 100 * time.Millisecond
+
+// sentryStandIn is a local HTTP server in place of Sentry's, so that
+// nothing a test reports leaves the host. It keeps the body of every
+// request it receives.
+type sentryStandIn struct {
+	server *httptest.Server
+	mu     sync.Mutex
+	bodies []string
+}
+
+func newSentryStandIn(t *testing.T) *sentryStandIn {
+	t.Helper()
+
+	standIn := &sentryStandIn{}
+	standIn.server = httptest.NewServer(http.HandlerFunc(
+		func(_ http.ResponseWriter, r *http.Request) {
+			body, err := io.ReadAll(r.Body)
+			if err != nil {
+				t.Errorf("reading request to the Sentry stand-in: %v", err)
+			}
+
+			time.Sleep(standInDelay)
+
+			standIn.mu.Lock()
+			defer standIn.mu.Unlock()
+
+			standIn.bodies = append(standIn.bodies, string(body))
+		},
+	))
+	t.Cleanup(standIn.server.Close)
+
+	return standIn
+}
+
+// dsn returns a DSN that points Sentry at the stand-in.
+func (s *sentryStandIn) dsn(t *testing.T) string {
+	t.Helper()
+
+	dsn, err := url.Parse(s.server.URL)
+	if err != nil {
+		t.Fatalf("parsing the stand-in URL: %v", err)
+	}
+
+	dsn.User = url.User("public-key")
+	dsn.Path = "/1"
+
+	return dsn.String()
+}
+
+// received reports whether a request to the stand-in contained text.
+func (s *sentryStandIn) received(text string) bool {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	for _, body := range s.bodies {
+		if strings.Contains(body, text) {
+			return true
+		}
+	}
+
+	return false
+}
+
+func TestSentryUnsetDoesNothing(t *testing.T) {
+	viper.Reset()
+	t.Setenv("DNSWATCHER_TARGETS", "example.com")
+	t.Setenv("DNSWATCHER_SENTRY_DSN", "")
+
+	srv := buildServer(t)
+
+	err := server.EnableSentry(srv)
+	if err != nil {
+		t.Fatalf("Sentry setup with no DSN: %v", err)
+	}
+
+	if sentry.CurrentHub().Client() != nil {
+		t.Error("Sentry was set up with no DSN configured")
+	}
+}
+
+// TestSentryReportsHandlerPanic checks that with a valid DSN a panic in
+// a handler is reported to Sentry, still reaches chimw.Recoverer, and
+// has been sent by the time Shutdown returns, and that nothing else is
+// sent to Sentry.
+func TestSentryReportsHandlerPanic(t *testing.T) {
+	standIn := newSentryStandIn(t)
+
+	viper.Reset()
+	t.Setenv("DNSWATCHER_TARGETS", "example.com")
+	t.Setenv("DNSWATCHER_SENTRY_DSN", standIn.dsn(t))
+
+	srv := buildServer(t)
+
+	err := server.EnableSentry(srv)
+	if err != nil {
+		t.Fatalf("Sentry setup with a valid DSN: %v", err)
+	}
+
+	// Sentry's client is global: close it so later tests find none.
+	t.Cleanup(func() {
+		sentry.CurrentHub().Client().Close()
+		sentry.CurrentHub().BindClient(nil)
+	})
+
+	const panicMessage = "handler panic in the Sentry test"
+
+	srv.SetupRoutes()
+	server.RouterOf(srv).Get(
+		"/panic",
+		func(http.ResponseWriter, *http.Request) {
+			panic(panicMessage)
+		},
+	)
+
+	// An ordinary request first: with client reports on, Sentry would
+	// add a count of its dropped transaction to the panic report.
+	serve(srv, httptest.NewRequestWithContext(
+		t.Context(), http.MethodGet, "/.well-known/healthcheck", nil,
+	))
+
+	rec := serve(srv, httptest.NewRequestWithContext(
+		t.Context(), http.MethodGet, "/panic", nil,
+	))
+	if rec.Code != http.StatusInternalServerError {
+		t.Errorf(
+			"status %d, want %d from the recoverer",
+			rec.Code, http.StatusInternalServerError,
+		)
+	}
+
+	err = srv.Shutdown(t.Context())
+	if err != nil {
+		t.Fatalf("Shutdown: %v", err)
+	}
+
+	if !standIn.received(panicMessage) {
+		t.Error("the panic had not been sent to Sentry when Shutdown returned")
+	}
+
+	if standIn.received("client_report") {
+		t.Error("Sentry was sent a client report, not only the panic")
+	}
+}
+
+func TestSentryInvalidDSNStopsStartup(t *testing.T) {
+	viper.Reset()
+	t.Setenv("DNSWATCHER_TARGETS", "example.com")
+	t.Setenv("DNSWATCHER_DATA_DIR", t.TempDir())
+	// Sentry cannot parse this: it has no public key before the host.
+	t.Setenv("DNSWATCHER_SENTRY_DSN", "https://sentry.test/1")
+
+	app := newServerApp(fx.Invoke(func(*server.Server) {}))
+
+	err := app.Start(t.Context())
+	if err == nil {
+		_ = app.Stop(t.Context())
+
+		t.Fatal("startup succeeded with an invalid DSN")
+	}
+
+	if !strings.Contains(err.Error(), "invalid DNSWATCHER_SENTRY_DSN") {
+		t.Errorf("startup error does not name the setting: %v", err)
+	}
+}

internal/server/server.go

@@ -9,6 +9,7 @@ import (
 	"net/http"
 	"time"
 
+	"github.com/getsentry/sentry-go"
 	"github.com/go-chi/chi/v5"
 	"go.uber.org/fx"
 
@@ -33,6 +34,10 @@ type Params struct {
 // shutdownTimeout is how long to wait for graceful shutdown.
 const shutdownTimeout = 30 * time.Second
 
+// sentryFlushTimeout is how long shutdown waits for Sentry to send the
+// error reports it still holds.
+const sentryFlushTimeout = 2 * time.Second
+
 // Socket-level timeouts for the HTTP server.
 //
 // These bound time spent on the connection itself and are a distinct
@@ -82,14 +87,15 @@ const (
 
 // Server is the HTTP server.
 type Server struct {
-	startupTime time.Time
-	port        int
-	log         *slog.Logger
-	router      *chi.Mux
-	httpServer  *http.Server
-	params      Params
-	mw          *middleware.Middleware
-	handlers    *handlers.Handlers
+	startupTime   time.Time
+	port          int
+	sentryEnabled bool
+	log           *slog.Logger
+	router        *chi.Mux
+	httpServer    *http.Server
+	params        Params
+	mw            *middleware.Middleware
+	handlers      *handlers.Handlers
 }
 
 // New creates a new Server instance.
@@ -108,6 +114,12 @@ func New(
 	lifecycle.Append(fx.Hook{
 		OnStart: func(_ context.Context) error {
 			srv.startupTime = time.Now()
+
+			err := srv.enableSentry()
+			if err != nil {
+				return err
+			}
+
 			go srv.Run()
 
 			return nil
@@ -152,8 +164,11 @@ func (s *Server) Run() {
 	}
 }
 
-// Shutdown gracefully shuts down the server.
+// Shutdown gracefully shuts down the server, then sends the error
+// reports Sentry still holds.
 func (s *Server) Shutdown(ctx context.Context) error {
+	defer s.flushSentry()
+
 	if s.httpServer == nil {
 		return nil
 	}
@@ -184,3 +199,45 @@ func (s *Server) ServeHTTP(
 ) {
 	s.router.ServeHTTP(writer, request)
 }
+
+// enableSentry turns on Sentry error reporting when
+// DNSWATCHER_SENTRY_DSN is set, and does nothing when it is not. A DSN
+// that Sentry cannot parse is an error, so that startup stops instead
+// of running without the error reporting the operator asked for.
+func (s *Server) enableSentry() error {
+	if s.params.Config.SentryDSN == "" {
+		return nil
+	}
+
+	err := sentry.Init(sentry.ClientOptions{
+		Dsn:     s.params.Config.SentryDSN,
+		Release: s.params.Globals.Appname + "-" + s.params.Globals.Version,
+		// Use the transport that queues each report as it is made. With
+		// the default one, Flush can return before sending a report made
+		// just before it, such as one from the last request at shutdown.
+		DisableTelemetryBuffer: true,
+		// Send panic reports only, not Sentry's counts of what it dropped,
+		// such as the transaction it starts for every request.
+		DisableClientReports: true,
+	})
+	if err != nil {
+		return fmt.Errorf("invalid DNSWATCHER_SENTRY_DSN: %w", err)
+	}
+
+	s.log.Info("sentry error reporting activated")
+	s.sentryEnabled = true
+
+	return nil
+}
+
+// flushSentry sends the error reports Sentry still holds, waiting at
+// most sentryFlushTimeout.
+func (s *Server) flushSentry() {
+	if !s.sentryEnabled {
+		return
+	}
+
+	if !sentry.Flush(sentryFlushTimeout) {
+		s.log.Warn("sentry flush timed out; some error reports were not sent")
+	}
+}

internal/server/server_test.go

@@ -17,18 +17,13 @@ import (
 	"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(
+// newServerApp builds an fx app holding a *server.Server wired exactly
+// as cmd/dnswatcher wires it, minus the watcher/resolver subtree that
+// would touch live DNS, plus the given option. config.New reads viper,
+// so the caller must first configure it, which is also why the caller
+// cannot run in parallel.
+func newServerApp(option fx.Option) *fx.App {
+	return fx.New(
 		fx.NopLogger,
 		fx.Provide(
 			globals.New,
@@ -41,8 +36,18 @@ func buildServer(t *testing.T) *server.Server {
 			handlers.New,
 			server.New,
 		),
-		fx.Populate(&srv),
+		option,
 	)
+}
+
+// buildServer builds the server without starting the app's lifecycle,
+// so no OnStart hook runs and nothing listens or resolves.
+func buildServer(t *testing.T) *server.Server {
+	t.Helper()
+
+	var srv *server.Server
+
+	app := newServerApp(fx.Populate(&srv))
 
 	err := app.Err()
 	if err != nil {

internal/state/state.go

@@ -8,6 +8,7 @@ import (
 	"log/slog"
 	"os"
 	"path/filepath"
+	"slices"
 	"sync"
 	"time"
 
@@ -35,22 +36,41 @@ type Params struct {
 }
 
 // DomainState holds the monitoring state for an apex domain.
+// NameserverAddresses holds the sorted addresses each nameserver's name
+// resolves to, by nameserver name. A state file written before it
+// existed loads with it nil. NXDomain is true when the domain's parent
+// zone's servers answered that it does not exist; it then has no
+// nameservers.
 type DomainState struct {
-	Nameservers []string  `json:"nameservers"`
-	LastChecked time.Time `json:"lastChecked"`
+	Nameservers         []string            `json:"nameservers"`
+	NameserverAddresses map[string][]string `json:"nameserverAddresses"`
+	NXDomain            bool                `json:"nxdomain,omitempty"`
+	LastChecked         time.Time           `json:"lastChecked"`
 }
 
 // NameserverRecordState holds one NS's response for a hostname.
+// FailedTypes lists the record types whose query to the nameserver
+// failed on this check: Records holds for them the records saved by the
+// previous check, which are kept. UnknownTypes lists those of them whose
+// records the previous check did not know either, as when the
+// nameserver was new or failing then: Records holds nothing for them.
 type NameserverRecordState struct {
-	Records     map[string][]string `json:"records"`
-	Status      string              `json:"status"`
-	Error       string              `json:"error,omitempty"`
-	LastChecked time.Time           `json:"lastChecked"`
+	Records      map[string][]string `json:"records"`
+	FailedTypes  []string            `json:"failedTypes,omitempty"`
+	UnknownTypes []string            `json:"unknownTypes,omitempty"`
+	Status       string              `json:"status"`
+	Error        string              `json:"error,omitempty"`
+	LastChecked  time.Time           `json:"lastChecked"`
 }
 
 // HostnameState holds per-nameserver monitoring state for a hostname.
+// CNAMEAddresses holds the sorted addresses at the end of the name's
+// CNAME chain, found when its nameservers answered with a CNAME and no
+// address; it is empty otherwise. It is nil when they are not known: a
+// state file written before it existed loads with it nil.
 type HostnameState struct {
 	RecordsByNameserver map[string]*NameserverRecordState `json:"recordsByNameserver"`
+	CNAMEAddresses      []string                          `json:"cnameAddresses"`
 	LastChecked         time.Time                         `json:"lastChecked"`
 }
 
@@ -112,6 +132,8 @@ type CertificateState struct {
 }
 
 // Snapshot is the complete monitoring state persisted to disk.
+// Hostnames also holds each apex domain's own records, under the
+// domain's name, which has an entry in Domains too.
 type Snapshot struct {
 	Version      int                          `json:"version"`
 	LastUpdated  time.Time                    `json:"lastUpdated"`
@@ -192,6 +214,19 @@ func (s *State) Load() error {
 		return fmt.Errorf("parsing state file: %w", err)
 	}
 
+	// A state file saved before each record value was stored once can
+	// hold a hostname's CNAME once for every record type asked for.
+	// Each value is kept once, so the first check does not see a
+	// record change.
+	for _, hs := range snapshot.Hostnames {
+		for _, ns := range hs.RecordsByNameserver {
+			for recordType, values := range ns.Records {
+				slices.Sort(values)
+				ns.Records[recordType] = slices.Compact(values)
+			}
+		}
+	}
+
 	s.snapshot = &snapshot
 	s.log.Info("loaded state from disk", "path", path)
 
@@ -266,6 +301,27 @@ func (s *State) GetDomainState(
 	return ds, ok
 }
 
+// DeleteDomainState removes a domain state entry.
+func (s *State) DeleteDomainState(domain string) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	delete(s.snapshot.Domains, domain)
+}
+
+// GetAllDomainNames returns the names of all domain state entries.
+func (s *State) GetAllDomainNames() []string {
+	s.mu.RLock()
+	defer s.mu.RUnlock()
+
+	names := make([]string, 0, len(s.snapshot.Domains))
+	for name := range s.snapshot.Domains {
+		names = append(names, name)
+	}
+
+	return names
+}
+
 // SetHostnameState updates the state for a hostname.
 func (s *State) SetHostnameState(
 	hostname string,
@@ -289,6 +345,28 @@ func (s *State) GetHostnameState(
 	return hs, ok
 }
 
+// DeleteHostnameState removes a hostname state entry.
+func (s *State) DeleteHostnameState(hostname string) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	delete(s.snapshot.Hostnames, hostname)
+}
+
+// GetAllHostnames returns the names of all hostname state entries,
+// which include each apex domain's own records.
+func (s *State) GetAllHostnames() []string {
+	s.mu.RLock()
+	defer s.mu.RUnlock()
+
+	names := make([]string, 0, len(s.snapshot.Hostnames))
+	for name := range s.snapshot.Hostnames {
+		names = append(names, name)
+	}
+
+	return names
+}
+
 // SetPortState updates the state for a port.
 func (s *State) SetPortState(key string, ps *PortState) {
 	s.mu.Lock()
@@ -351,6 +429,27 @@ func (s *State) GetCertificateState(
 	return cs, ok
 }
 
+// DeleteCertificateState removes a certificate state entry.
+func (s *State) DeleteCertificateState(key string) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	delete(s.snapshot.Certificates, key)
+}
+
+// GetAllCertificateKeys returns all certificate state keys.
+func (s *State) GetAllCertificateKeys() []string {
+	s.mu.RLock()
+	defer s.mu.RUnlock()
+
+	keys := make([]string, 0, len(s.snapshot.Certificates))
+	for k := range s.snapshot.Certificates {
+		keys = append(keys, k)
+	}
+
+	return keys
+}
+
 // 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

internal/state/state_test.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"os"
 	"path/filepath"
+	"reflect"
 	"strings"
 	"sync"
 	"testing"
@@ -37,6 +38,10 @@ func populateState(t *testing.T, s *state.State) {
 
 	s.SetDomainState("example.com", &state.DomainState{
 		Nameservers: []string{testNS1, testNS2},
+		NameserverAddresses: map[string][]string{
+			testNS1: {testIP, testIPv4},
+			testNS2: {testIPv4},
+		},
 		LastChecked: now,
 	})
 
@@ -123,6 +128,261 @@ func TestSaveLoadRoundTrip_Domains(t *testing.T) {
 	if len(dom.Nameservers) != 2 {
 		t.Errorf("expected 2 nameservers, got %d", len(dom.Nameservers))
 	}
+
+	want := map[string][]string{
+		testNS1: {testIP, testIPv4},
+		testNS2: {testIPv4},
+	}
+	if !reflect.DeepEqual(dom.NameserverAddresses, want) {
+		t.Errorf(
+			"nameserver addresses: got %v, want %v",
+			dom.NameserverAddresses, want,
+		)
+	}
+}
+
+// TestLoadStateFromBeforeNameserverAddresses loads a state file written
+// before nameserver addresses were saved.
+func TestLoadStateFromBeforeNameserverAddresses(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+
+	data := []byte(`{
+		"version": 1,
+		"lastUpdated": "2026-02-19T12:00:00Z",
+		"domains": {
+			"example.com": {
+				"nameservers": ["ns1.example.com.", "ns2.example.com."],
+				"lastChecked": "2026-02-19T12:00:00Z"
+			}
+		}
+	}`)
+
+	err := os.WriteFile(filepath.Join(dir, "state.json"), data, 0o600)
+	if err != nil {
+		t.Fatalf("writing state file: %v", err)
+	}
+
+	s := state.NewForTestWithDataDir(dir)
+
+	err = s.Load()
+	if err != nil {
+		t.Fatalf("Load() error: %v", err)
+	}
+
+	dom, ok := s.GetDomainState("example.com")
+	if !ok {
+		t.Fatal("missing domain example.com")
+	}
+
+	if !reflect.DeepEqual(dom.Nameservers, []string{testNS1, testNS2}) {
+		t.Errorf("nameservers: got %v", dom.Nameservers)
+	}
+
+	if dom.NameserverAddresses != nil {
+		t.Errorf(
+			"nameserver addresses: got %v, want none",
+			dom.NameserverAddresses,
+		)
+	}
+}
+
+// TestSaveLoadRoundTrip_CNAMEAddresses checks that no addresses at the
+// end of a hostname's CNAME chain load as an empty list, and addresses
+// that are not known load as nil: the watcher tells the two apart.
+func TestSaveLoadRoundTrip_CNAMEAddresses(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	s := state.NewForTestWithDataDir(dir)
+
+	want := map[string][]string{
+		"cname.example.com":     {testIP},
+		"none.example.com":      {},
+		"not-known.example.com": nil,
+	}
+
+	for name, addresses := range want {
+		s.SetHostnameState(name, &state.HostnameState{
+			CNAMEAddresses: addresses,
+		})
+	}
+
+	err := s.Save()
+	if err != nil {
+		t.Fatalf("Save() error: %v", err)
+	}
+
+	loaded := state.NewForTestWithDataDir(dir)
+
+	err = loaded.Load()
+	if err != nil {
+		t.Fatalf("Load() error: %v", err)
+	}
+
+	for name, addresses := range want {
+		hs, ok := loaded.GetHostnameState(name)
+		if !ok {
+			t.Fatalf("missing hostname %s", name)
+		}
+
+		if !reflect.DeepEqual(hs.CNAMEAddresses, addresses) {
+			t.Errorf(
+				"%s: loaded %#v, want %#v",
+				name, hs.CNAMEAddresses, addresses,
+			)
+		}
+	}
+}
+
+// TestSaveLoadRoundTrip_FailedTypes checks that a nameserver's
+// failedTypes and unknownTypes survive a save and load. Without
+// unknownTypes, a type whose records were not known would load as one
+// with no records.
+func TestSaveLoadRoundTrip_FailedTypes(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	s := state.NewForTestWithDataDir(dir)
+
+	failed := []string{"TXT", "CAA"}
+	unknown := []string{"CAA"}
+
+	s.SetHostnameState(testHostname, &state.HostnameState{
+		RecordsByNameserver: map[string]*state.NameserverRecordState{
+			testNS1: {
+				Records:      map[string][]string{"TXT": {"v=spf1 -all"}},
+				FailedTypes:  failed,
+				UnknownTypes: unknown,
+				Status:       "ok",
+			},
+		},
+	})
+
+	err := s.Save()
+	if err != nil {
+		t.Fatalf("Save() error: %v", err)
+	}
+
+	loaded := state.NewForTestWithDataDir(dir)
+
+	err = loaded.Load()
+	if err != nil {
+		t.Fatalf("Load() error: %v", err)
+	}
+
+	hs, ok := loaded.GetHostnameState(testHostname)
+	if !ok {
+		t.Fatal("missing hostname " + testHostname)
+	}
+
+	ns1 := hs.RecordsByNameserver[testNS1]
+	if ns1 == nil {
+		t.Fatal("missing nameserver " + testNS1)
+	}
+
+	if !reflect.DeepEqual(ns1.FailedTypes, failed) {
+		t.Errorf("failedTypes: got %#v", ns1.FailedTypes)
+	}
+
+	if !reflect.DeepEqual(ns1.UnknownTypes, unknown) {
+		t.Errorf("unknownTypes: got %#v", ns1.UnknownTypes)
+	}
+}
+
+// TestLoadStateFromBeforeCNAMEAddresses loads a state file written
+// before the addresses at the end of a hostname's CNAME chain were
+// saved. They load as not known (nil), not as none.
+func TestLoadStateFromBeforeCNAMEAddresses(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+
+	data := []byte(`{
+		"version": 1,
+		"lastUpdated": "2026-02-19T12:00:00Z",
+		"hostnames": {
+			"www.example.com": {
+				"recordsByNameserver": {},
+				"lastChecked": "2026-02-19T12:00:00Z"
+			}
+		}
+	}`)
+
+	err := os.WriteFile(filepath.Join(dir, "state.json"), data, 0o600)
+	if err != nil {
+		t.Fatalf("writing state file: %v", err)
+	}
+
+	s := state.NewForTestWithDataDir(dir)
+
+	err = s.Load()
+	if err != nil {
+		t.Fatalf("Load() error: %v", err)
+	}
+
+	hs, ok := s.GetHostnameState(testHostname)
+	if !ok {
+		t.Fatal("missing hostname " + testHostname)
+	}
+
+	if hs.CNAMEAddresses != nil {
+		t.Errorf("CNAME addresses: got %#v, want nil", hs.CNAMEAddresses)
+	}
+}
+
+// TestLoadStateWithRepeatedValues loads a state file saved when a
+// hostname's CNAME was stored once for every record type asked for.
+// Each value must load once, and every different value must load.
+func TestLoadStateWithRepeatedValues(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+
+	data := []byte(`{
+		"version": 1,
+		"hostnames": {
+			"www.example.com": {
+				"recordsByNameserver": {
+					"ns1.example.com.": {
+						"records": {
+							"A": ["192.0.2.2", "192.0.2.1", "192.0.2.2", "192.0.2.1"],
+							"CNAME": ["a.example.net.", "a.example.net.", "a.example.net."]
+						},
+						"status": "ok"
+					}
+				}
+			}
+		}
+	}`)
+
+	err := os.WriteFile(filepath.Join(dir, "state.json"), data, 0o600)
+	if err != nil {
+		t.Fatalf("writing state file: %v", err)
+	}
+
+	s := state.NewForTestWithDataDir(dir)
+
+	err = s.Load()
+	if err != nil {
+		t.Fatalf("Load() error: %v", err)
+	}
+
+	hs, ok := s.GetHostnameState(testHostname)
+	if !ok {
+		t.Fatal("missing hostname " + testHostname)
+	}
+
+	want := map[string][]string{
+		"A":     {"192.0.2.1", "192.0.2.2"},
+		"CNAME": {"a.example.net."},
+	}
+
+	got := hs.RecordsByNameserver[testNS1].Records
+	if !reflect.DeepEqual(got, want) {
+		t.Errorf("records: got %v, want %v", got, want)
+	}
 }
 
 // TestSaveLoadRoundTrip_Hostnames verifies hostname data survives a save/load cycle.

internal/watcher/cancelled_test.go

@@ -0,0 +1,153 @@
+package watcher_test
+
+import (
+	"bytes"
+	"context"
+	"log/slog"
+	"reflect"
+	"strings"
+	"testing"
+	"time"
+
+	"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"
+)
+
+// TestCancelledCheckSavesNothing runs a check with its context already
+// cancelled, which is how the rest of a check runs once shutdown cuts it
+// short. The real resolver drops the DNS lookup without sending a query,
+// and the real port and TLS checkers fail without connecting. The port
+// and certificate state the last check saved must stay as it was, and
+// nothing may be notified.
+func TestCancelledCheckSavesNothing(t *testing.T) {
+	t.Parallel()
+
+	cfg := defaultTestConfig(t)
+	cfg.Hostnames = []string{host}
+
+	// newTestWatcher's watcher has stand-in checkers. This one, on the
+	// same state and notifier, has the real ones.
+	_, deps := newTestWatcher(t, cfg)
+	w := watcher.NewForTest(
+		cfg,
+		deps.state,
+		resolver.NewFromLogger(slog.Default()),
+		portcheck.NewStandalone(),
+		tlscheck.NewStandalone(),
+		deps.notifier,
+	)
+
+	// The last check found host at a local address, with both ports
+	// open and a good certificate.
+	const localIP = "127.0.0.1"
+
+	deps.state.SetHostnameState(host, hostnameState(
+		map[string]map[string][]string{nsA: {"A": {localIP}}},
+	))
+
+	ports := map[string]*state.PortState{
+		localIP + ":80":  {Open: true, Hostnames: []string{host}},
+		localIP + ":443": {Open: true, Hostnames: []string{host}},
+	}
+	for key, ps := range ports {
+		deps.state.SetPortState(key, ps)
+	}
+
+	certKey := localIP + ":443:" + host
+	cert := &state.CertificateState{CommonName: host, Status: "ok"}
+	deps.state.SetCertificateState(certKey, cert)
+
+	ctx, cancel := context.WithCancel(t.Context())
+	cancel()
+
+	w.RunOnce(ctx)
+
+	for key, want := range ports {
+		got, _ := deps.state.GetPortState(key)
+		if !reflect.DeepEqual(got, want) {
+			t.Errorf("port %s saved as %+v, want %+v", key, got, want)
+		}
+	}
+
+	got, _ := deps.state.GetCertificateState(certKey)
+	if !reflect.DeepEqual(got, cert) {
+		t.Errorf("certificate saved as %+v, want %+v", got, cert)
+	}
+
+	notifications := deps.notifier.getNotifications()
+	if len(notifications) != 0 {
+		t.Errorf("sent %v, want no notifications", notifications)
+	}
+}
+
+// newLoggingWatcher returns a watcher for a domain and a hostname, with
+// the real resolver, that writes what it logs at warning level or above
+// into the returned buffer.
+func newLoggingWatcher(t *testing.T) (*watcher.Watcher, *bytes.Buffer) {
+	t.Helper()
+
+	cfg := defaultTestConfig(t)
+	cfg.Domains = []string{testSmallDomain}
+	cfg.Hostnames = []string{host}
+
+	w, _ := newTestWatcher(t, cfg)
+
+	logs := &bytes.Buffer{}
+	w.SetLogger(slog.New(slog.NewJSONHandler(
+		logs, &slog.HandlerOptions{Level: slog.LevelWarn},
+	)))
+
+	return w, logs
+}
+
+// TestLookupCutShortIsNotLogged checks a domain and a hostname, looks
+// up a nameserver's addresses and follows a CNAME, with the context
+// cancelled, as shutdown leaves it. The real resolver fails each lookup
+// without sending a query. Shutdown cutting a lookup short is not a
+// failure, so nothing may be logged at warning level or above.
+func TestLookupCutShortIsNotLogged(t *testing.T) {
+	t.Parallel()
+
+	w, logs := newLoggingWatcher(t)
+
+	ctx, cancel := context.WithCancel(t.Context())
+	cancel()
+
+	w.RunOnce(ctx)
+	w.ResolveNameserverAddresses(ctx, []string{nsA}, nil)
+	w.ResolveCNAMEAddresses(ctx, host, cnameState(), nil)
+
+	if logs.Len() > 0 {
+		t.Errorf("logged at warning level or above:\n%s", logs)
+	}
+}
+
+// TestLookupOutOfTimeIsLoggedAsError does what
+// TestLookupCutShortIsNotLogged does, with the context's deadline passed
+// instead. A lookup that ran out of time did fail, so the domain's NS
+// lookup, the hostname's lookup, the nameserver's address lookup and the
+// CNAME's are each logged as an error.
+func TestLookupOutOfTimeIsLoggedAsError(t *testing.T) {
+	t.Parallel()
+
+	w, logs := newLoggingWatcher(t)
+
+	ctx, cancel := context.WithDeadline(t.Context(), time.Now())
+	t.Cleanup(cancel)
+
+	w.RunOnce(ctx)
+	w.ResolveNameserverAddresses(ctx, []string{nsA}, nil)
+	w.ResolveCNAMEAddresses(ctx, host, cnameState(), nil)
+
+	const want = 4
+
+	lines := strings.Count(logs.String(), "\n")
+	errorLines := strings.Count(logs.String(), `"level":"ERROR"`)
+
+	if lines != want || errorLines != want {
+		t.Errorf("logged:\n%s\nwant %d lines, each at error level", logs, want)
+	}
+}

internal/watcher/cname_test.go

@@ -0,0 +1,372 @@
+package watcher_test
+
+import (
+	"context"
+	"log/slog"
+	"slices"
+	"testing"
+
+	"sneak.berlin/go/dnswatcher/internal/livednstest"
+	"sneak.berlin/go/dnswatcher/internal/resolver"
+	"sneak.berlin/go/dnswatcher/internal/state"
+	"sneak.berlin/go/dnswatcher/internal/watcher"
+)
+
+// TestCNAMEIntoAnotherZonePortAndTLSChecks runs the port and TLS
+// checks on hostname state built here: the name's nameserver answered
+// with a CNAME into another zone, and following it found ip1. Both
+// checks must use ip1. They look nothing up, so the watcher has no
+// resolver.
+func TestCNAMEIntoAnotherZonePortAndTLSChecks(t *testing.T) {
+	t.Parallel()
+
+	cfg := defaultTestConfig(t)
+	cfg.Hostnames = []string{host}
+
+	deps := newTestDeps(t, cfg)
+	w := watcher.NewForTest(
+		cfg, deps.state, nil,
+		deps.portChecker, deps.tlsChecker, deps.notifier,
+	)
+
+	deps.state.SetHostnameState(host, cnameState(ip1))
+
+	w.CheckAllPorts(t.Context())
+	w.RunTLSChecks(t.Context())
+
+	snap := deps.state.GetSnapshot()
+
+	ps, ok := snap.Ports[ip1+":443"]
+	if !ok || !slices.Contains(ps.Hostnames, host) {
+		t.Errorf("no port state for %s at %s:443", host, ip1)
+	}
+
+	certKey := ip1 + ":443:" + host
+	if _, ok := snap.Certificates[certKey]; !ok {
+		t.Errorf("no certificate state %s", certKey)
+	}
+}
+
+// TestCNAMEThatCannotBeFollowedKeepsPrevious runs a check of a name, not
+// the watcher's first, from the point where its records have been looked
+// up: they hold a CNAME to a target under .invalid, whose lookup fails.
+// The previous check found the same records, and oldIP at the end of the
+// CNAME. The check must keep oldIP and send nothing.
+func TestCNAMEThatCannotBeFollowedKeepsPrevious(t *testing.T) {
+	t.Parallel()
+
+	w, deps := newTestWatcher(t, defaultTestConfig(t))
+	w.SetFirstRun(false)
+
+	records := map[string]map[string][]string{
+		nsA: cnameTo("target.example.invalid."),
+	}
+
+	prev := hostnameState(records)
+	prev.CNAMEAddresses = []string{oldIP}
+	deps.state.SetHostnameState(host, prev)
+
+	// The result is the same whether or not live DNS answers, so the
+	// lookup is not retried.
+	_ = livednstest.Run(func(ctx context.Context) error {
+		w.UpdateHostnameState(ctx, host, hostnameState(records))
+
+		return nil
+	})
+
+	hs, _ := deps.state.GetHostnameState(host)
+	if !slices.Equal(hs.CNAMEAddresses, prev.CNAMEAddresses) {
+		t.Errorf(
+			"saved %v, want %v",
+			hs.CNAMEAddresses, prev.CNAMEAddresses,
+		)
+	}
+
+	notifications := deps.notifier.getNotifications()
+	if len(notifications) != 0 {
+		t.Errorf("sent %v, want no notifications", notifications)
+	}
+}
+
+// followLive follows in live DNS the CNAMEs in a name's records, built
+// from records, and returns the addresses saved for the name. The
+// previous check saved oldIP, which is kept when a target cannot be
+// followed; that is retried. The tests point CNAMEs only at names in
+// zones with two nameservers, to keep queries few (see the top of
+// watcher_test.go).
+func followLive(
+	t *testing.T,
+	records map[string]map[string][]string,
+) []string {
+	t.Helper()
+
+	w := watcher.NewForTest(
+		nil, nil, resolver.NewFromLogger(slog.Default()), nil, nil, nil,
+	)
+	prev := cnameState(oldIP)
+
+	var current *state.HostnameState
+
+	livednstest.Retry(t, "following CNAMEs", func(ctx context.Context) error {
+		current = hostnameState(records)
+
+		w.ResolveCNAMEAddresses(ctx, host, current, prev)
+
+		if slices.Equal(current.CNAMEAddresses, prev.CNAMEAddresses) {
+			return livednstest.ErrNoAnswer
+		}
+
+		return nil
+	})
+
+	return current.CNAMEAddresses
+}
+
+// TestCNAMEAddressesOfEveryTarget gives a name's two nameservers
+// different CNAME targets, as when a secondary still serves an old one.
+// The addresses at the end of both are saved, whichever answer is read
+// first: one.one.one.one has 1.1.1.1, and dns.adguard-dns.com has
+// 94.140.14.14.
+func TestCNAMEAddressesOfEveryTarget(t *testing.T) {
+	t.Parallel()
+
+	found := followLive(t, map[string]map[string][]string{
+		nsA: cnameTo("one.one.one.one."),
+		nsB: cnameTo("dns.adguard-dns.com."),
+	})
+
+	for _, ip := range []string{"1.1.1.1", "94.140.14.14"} {
+		if !slices.Contains(found, ip) {
+			t.Errorf("saved %v, want %s among them", found, ip)
+		}
+	}
+}
+
+// TestCNAMEChainEndingInNoAddressSavesEmptyList follows a CNAME to a
+// name live DNS answers with NXDOMAIN. An empty list is saved, not nil,
+// which would mean the addresses are not known.
+func TestCNAMEChainEndingInNoAddressSavesEmptyList(t *testing.T) {
+	t.Parallel()
+
+	found := followLive(t, map[string]map[string][]string{
+		nsA: cnameTo("this-surely-does-not-exist-xyz.example.org."),
+	})
+
+	if found == nil || len(found) != 0 {
+		t.Errorf("saved %#v, want an empty list", found)
+	}
+}
+
+// TestCNAMEBesideAnAddressNotFollowed gives one nameserver of a name an
+// address and another a CNAME. The CNAME is not followed: an empty list
+// is saved, not nil, and nothing is looked up, the watcher having no
+// resolver.
+func TestCNAMEBesideAnAddressNotFollowed(t *testing.T) {
+	t.Parallel()
+
+	w := watcher.NewForTest(nil, nil, nil, nil, nil, nil)
+
+	current := hostnameState(map[string]map[string][]string{
+		nsA: {"A": {ip1}},
+		nsB: cnameTo("target.example.org."),
+	})
+
+	w.ResolveCNAMEAddresses(t.Context(), host, current, nil)
+
+	if current.CNAMEAddresses == nil || len(current.CNAMEAddresses) != 0 {
+		t.Errorf("saved %#v, want an empty list", current.CNAMEAddresses)
+	}
+}
+
+// TestCNAMEWhoseNameserversAllFailedKeepsPrevious checks a name none of
+// whose nameservers answered. The addresses the previous check saved
+// from following its CNAME are kept, and nothing is looked up: the
+// watcher has no resolver.
+func TestCNAMEWhoseNameserversAllFailedKeepsPrevious(t *testing.T) {
+	t.Parallel()
+
+	w := watcher.NewForTest(nil, nil, nil, nil, nil, nil)
+
+	current := saved(map[string]*state.NameserverRecordState{
+		nsA: failed(), nsB: failed(),
+	})
+	prev := cnameState(oldIP)
+
+	w.ResolveCNAMEAddresses(t.Context(), host, current, prev)
+
+	if !slices.Equal(current.CNAMEAddresses, prev.CNAMEAddresses) {
+		t.Errorf(
+			"saved %v, want %v",
+			current.CNAMEAddresses, prev.CNAMEAddresses,
+		)
+	}
+}
+
+// TestCNAMEWhoseAddressQueryFailedKeepsPrevious checks a name whose
+// nameserver answered, but whose query for A, AAAA or CNAME failed with
+// nothing kept for it. That is not an answer with no address: the
+// addresses the previous check saved from following its CNAME are kept,
+// and nothing is looked up, the watcher having no resolver.
+func TestCNAMEWhoseAddressQueryFailedKeepsPrevious(t *testing.T) {
+	t.Parallel()
+
+	for _, rtype := range []string{"A", "AAAA", "CNAME"} {
+		t.Run(rtype, func(t *testing.T) {
+			t.Parallel()
+
+			w := watcher.NewForTest(nil, nil, nil, nil, nil, nil)
+
+			current := saved(map[string]*state.NameserverRecordState{
+				nsA: {
+					Records:      map[string][]string{},
+					FailedTypes:  []string{rtype},
+					UnknownTypes: []string{rtype},
+					Status:       "ok",
+				},
+			})
+			prev := cnameState(oldIP)
+
+			w.ResolveCNAMEAddresses(t.Context(), host, current, prev)
+
+			if !slices.Equal(current.CNAMEAddresses, prev.CNAMEAddresses) {
+				t.Errorf(
+					"saved %v, want %v",
+					current.CNAMEAddresses, prev.CNAMEAddresses,
+				)
+			}
+		})
+	}
+}
+
+// cnameTo builds the records of a nameserver that answered with a CNAME
+// to target and no address.
+func cnameTo(target string) map[string][]string {
+	return map[string][]string{"CNAME": {target}}
+}
+
+// cnameState builds the state a check leaves behind for a name whose
+// nameserver answered with a CNAME and no address, when following the
+// CNAME found these addresses, which may be none.
+func cnameState(addresses ...string) *state.HostnameState {
+	hs := hostnameState(map[string]map[string][]string{
+		nsA: cnameTo("target.example.org."),
+	})
+
+	hs.CNAMEAddresses = append([]string{}, addresses...)
+
+	return hs
+}
+
+func TestCNAMEAddressChangeAlerts(t *testing.T) {
+	t.Parallel()
+
+	// A state file written before the addresses were saved loads with
+	// them nil.
+	olderStateFile := cnameState()
+	olderStateFile.CNAMEAddresses = nil
+
+	// Each case is the state saved by the previous check and by the
+	// current one. The name's records are the same in both.
+	tests := []struct {
+		name          string
+		prev, current *state.HostnameState
+		want          int
+	}{
+		{
+			"same addresses",
+			cnameState(ip1, ip2), cnameState(ip1, ip2), 0,
+		},
+		{
+			"same addresses in another order",
+			cnameState(ip2, ip1), cnameState(ip1, ip2), 0,
+		},
+		{
+			"address replaced",
+			cnameState(ip1), cnameState(ip2), 1,
+		},
+		{
+			"address added",
+			cnameState(ip1), cnameState(ip1, ip2), 1,
+		},
+		{
+			"no address at the end of the chain now",
+			cnameState(ip1), cnameState(), 1,
+		},
+		{
+			"addresses at the end of the chain again",
+			cnameState(), cnameState(ip1), 1,
+		},
+		{
+			"state file from before addresses were saved",
+			olderStateFile, cnameState(ip1), 0,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			notifier := &mockNotifier{}
+			w := watcher.NewForTest(nil, nil, nil, nil, nil, notifier)
+
+			w.DetectHostnameChanges(t.Context(), host, tt.prev, tt.current)
+
+			got := len(notifier.getNotifications())
+			if got != tt.want {
+				t.Errorf("sent %d notifications, want %d", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestCNAMEAddressChangeAlertNamesHostnameAndAddresses(t *testing.T) {
+	t.Parallel()
+
+	notifier := &mockNotifier{}
+	w := watcher.NewForTest(nil, nil, nil, nil, nil, notifier)
+
+	w.DetectHostnameChanges(
+		t.Context(), host, cnameState(ip1), cnameState(ip2, ip3),
+	)
+
+	want := notification{
+		Title: "CNAME Address Change: " + host,
+		Message: "Hostname: " + host +
+			"\nOld: " + ip1 + "\nNew: " + ip2 + ", " + ip3,
+		Priority: "warning",
+	}
+
+	got := notifier.getNotifications()
+	if len(got) != 1 || got[0] != want {
+		t.Errorf("sent %v, want %v", got, want)
+	}
+}
+
+// TestNameMovedFromARecordsToCNAMEAlerts checks a name that answers
+// with an A record and then with a CNAME whose chain ends in ip2. The
+// second check is notified as a CNAME address change from no addresses,
+// beside the record change. Nothing is looked up: the watcher has no
+// resolver.
+func TestNameMovedFromARecordsToCNAMEAlerts(t *testing.T) {
+	t.Parallel()
+
+	notifier := &mockNotifier{}
+	w := watcher.NewForTest(nil, nil, nil, nil, nil, notifier)
+
+	prev := hostnameState(map[string]map[string][]string{
+		nsA: {"A": {ip1}},
+	})
+	w.ResolveCNAMEAddresses(t.Context(), host, prev, nil)
+
+	w.DetectHostnameChanges(t.Context(), host, prev, cnameState(ip2))
+
+	title := "CNAME Address Change: " + host
+	message := "Hostname: " + host + "\nOld: \nNew: " + ip2
+
+	got := notifier.getNotifications()
+	if !slices.ContainsFunc(got, func(n notification) bool {
+		return n.Title == title && n.Message == message
+	}) {
+		t.Errorf("sent %v, want %q with %q among them", got, title, message)
+	}
+}

internal/watcher/export_test.go

@@ -6,10 +6,12 @@ import (
 	"time"
 
 	"sneak.berlin/go/dnswatcher/internal/config"
+	"sneak.berlin/go/dnswatcher/internal/resolver"
 	"sneak.berlin/go/dnswatcher/internal/state"
 )
 
-// NewForTest creates a Watcher without fx for unit testing.
+// NewForTest creates a Watcher without fx for unit testing. A nil cfg
+// is an empty configuration.
 func NewForTest(
 	cfg *config.Config,
 	st *state.State,
@@ -18,33 +20,113 @@ func NewForTest(
 	tc TLSChecker,
 	n Notifier,
 ) *Watcher {
-	return &Watcher{
-		log:            slog.Default(),
-		config:         cfg,
-		state:          st,
-		resolver:       res,
-		portCheck:      pc,
-		tlsCheck:       tc,
-		notify:         n,
-		firstRun:       true,
-		expiryNotified: make(map[string]time.Time),
+	if cfg == nil {
+		cfg = &config.Config{}
 	}
+
+	return &Watcher{
+		log:       slog.Default(),
+		config:    cfg,
+		state:     st,
+		resolver:  res,
+		portCheck: pc,
+		tlsCheck:  tc,
+		notify:    n,
+		firstRun:  true,
+	}
+}
+
+// SetLogger replaces the watcher's logger, so a test can read what it
+// logs.
+func (w *Watcher) SetLogger(log *slog.Logger) {
+	w.log = log
 }
 
 // NewlyDisagreeingPairs exports newlyDisagreeingPairs for testing.
 func NewlyDisagreeingPairs(
-	prev *state.HostnameState,
-	current map[string]map[string][]string,
+	prev, current *state.HostnameState,
 ) [][2]string {
 	return newlyDisagreeingPairs(prev, current)
 }
 
+// SetFirstRun sets whether the watcher is on its first check, in which
+// nothing is compared with the previous check. NewForTest's watcher is.
+func (w *Watcher) SetFirstRun(firstRun bool) {
+	w.firstRun = firstRun
+}
+
+// UpdateHostnameState exports updateHostnameState for testing.
+func (w *Watcher) UpdateHostnameState(
+	ctx context.Context,
+	hostname string,
+	newState *state.HostnameState,
+) {
+	w.updateHostnameState(ctx, hostname, newState)
+}
+
 // DetectHostnameChanges exports detectHostnameChanges for testing.
 func (w *Watcher) DetectHostnameChanges(
 	ctx context.Context,
 	hostname string,
-	prev *state.HostnameState,
-	current map[string]map[string][]string,
+	prev, current *state.HostnameState,
 ) {
 	w.detectHostnameChanges(ctx, hostname, prev, current)
 }
+
+// ResolveNameserverAddresses exports resolveNameserverAddresses for
+// testing.
+func (w *Watcher) ResolveNameserverAddresses(
+	ctx context.Context,
+	nameservers []string,
+	prev map[string][]string,
+) map[string][]string {
+	return w.resolveNameserverAddresses(ctx, nameservers, prev)
+}
+
+// ResolveCNAMEAddresses exports resolveCNAMEAddresses for testing.
+func (w *Watcher) ResolveCNAMEAddresses(
+	ctx context.Context,
+	hostname string,
+	current, prev *state.HostnameState,
+) {
+	w.resolveCNAMEAddresses(ctx, hostname, current, prev)
+}
+
+// DetectNSAddressChanges exports detectNSAddressChanges for testing.
+func (w *Watcher) DetectNSAddressChanges(
+	ctx context.Context,
+	domain string,
+	prev, current map[string][]string,
+) {
+	w.detectNSAddressChanges(ctx, domain, prev, current)
+}
+
+// MaybeSendTestNotification exports maybeSendTestNotification for
+// testing.
+func (w *Watcher) MaybeSendTestNotification(ctx context.Context) {
+	w.maybeSendTestNotification(ctx)
+}
+
+// CleanupRemovedTargets exports cleanupRemovedTargets for testing.
+func (w *Watcher) CleanupRemovedTargets() {
+	w.cleanupRemovedTargets()
+}
+
+// CheckAllPorts exports checkAllPorts for testing.
+func (w *Watcher) CheckAllPorts(ctx context.Context) {
+	w.checkAllPorts(ctx)
+}
+
+// RunTLSChecks exports runTLSChecks for testing.
+func (w *Watcher) RunTLSChecks(ctx context.Context) {
+	w.runTLSChecks(ctx)
+}
+
+// BuildHostnameState exports buildHostnameState for testing.
+func BuildHostnameState(
+	results map[string]*resolver.NameserverResponse,
+	prev *state.HostnameState,
+	now time.Time,
+) *state.HostnameState {
+	return buildHostnameState(results, prev, now)
+}

internal/watcher/failedtype_test.go

@@ -0,0 +1,364 @@
+package watcher_test
+
+import (
+	"maps"
+	"slices"
+	"testing"
+	"time"
+
+	"sneak.berlin/go/dnswatcher/internal/resolver"
+	"sneak.berlin/go/dnswatcher/internal/state"
+	"sneak.berlin/go/dnswatcher/internal/watcher"
+)
+
+const (
+	// txt is the record type whose query fails in these tests.
+	txt  = "TXT"
+	spf1 = "v=spf1 -all"
+	spf2 = "v=spf1 include:example.net -all"
+)
+
+// response is a nameserver's response with these records, whose queries
+// for failedTypes failed.
+func response(
+	records map[string][]string,
+	failedTypes ...string,
+) *resolver.NameserverResponse {
+	return &resolver.NameserverResponse{
+		Records:     records,
+		FailedTypes: failedTypes,
+		Status:      resolver.StatusOK,
+	}
+}
+
+// savedChecks saves the state of each check in turn from the
+// nameservers' responses, each from the state the check before saved.
+func savedChecks(
+	checks ...map[string]*resolver.NameserverResponse,
+) []*state.HostnameState {
+	states := make([]*state.HostnameState, 0, len(checks))
+
+	var prev *state.HostnameState
+
+	for _, results := range checks {
+		prev = watcher.BuildHostnameState(results, prev, time.Now())
+		states = append(states, prev)
+	}
+
+	return states
+}
+
+// TestFailedTypeKeepsPreviousRecords saves a check in which nsA's query
+// for TXT failed, after previous checks of several kinds. TXT is always
+// saved in FailedTypes, and in UnknownTypes when there was nothing to
+// keep.
+func TestFailedTypeKeepsPreviousRecords(t *testing.T) {
+	t.Parallel()
+
+	aOnly := map[string][]string{"A": {ip1}}
+	withTXT := map[string][]string{"A": {ip1}, txt: {spf1}}
+	txtKept := &state.NameserverRecordState{
+		Records: withTXT, FailedTypes: []string{txt}, Status: "ok",
+	}
+	txtNotKnown := &state.NameserverRecordState{
+		Records:      aOnly,
+		FailedTypes:  []string{txt},
+		UnknownTypes: []string{txt},
+		Status:       "ok",
+	}
+
+	tests := []struct {
+		name        string
+		prev        *state.HostnameState
+		wantRecords map[string][]string
+		wantUnknown []string
+	}{
+		{
+			"previous TXT records are kept",
+			saved(map[string]*state.NameserverRecordState{nsA: answered(withTXT)}),
+			withTXT, nil,
+		},
+		{
+			"previous check had no TXT records",
+			saved(map[string]*state.NameserverRecordState{nsA: answered(aOnly)}),
+			aOnly, nil,
+		},
+		{
+			"TXT failed on the previous check, which kept its records",
+			saved(map[string]*state.NameserverRecordState{nsA: txtKept}),
+			withTXT, nil,
+		},
+		{"first check", nil, aOnly, []string{txt}},
+		{
+			"nameserver new on this check",
+			saved(map[string]*state.NameserverRecordState{nsB: answered(withTXT)}),
+			aOnly, []string{txt},
+		},
+		{
+			"nameserver failed on the previous check",
+			saved(map[string]*state.NameserverRecordState{nsA: failed()}),
+			aOnly, []string{txt},
+		},
+		{
+			"TXT failed on the previous check with nothing to keep",
+			saved(map[string]*state.NameserverRecordState{nsA: txtNotKnown}),
+			aOnly, []string{txt},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			hs := watcher.BuildHostnameState(
+				map[string]*resolver.NameserverResponse{
+					nsA: response(map[string][]string{"A": {ip1}}, txt),
+				},
+				tt.prev, time.Now(),
+			)
+
+			got := hs.RecordsByNameserver[nsA]
+			if got.Status != "ok" ||
+				!maps.EqualFunc(got.Records, tt.wantRecords, slices.Equal) ||
+				!slices.Equal(got.FailedTypes, []string{txt}) ||
+				!slices.Equal(got.UnknownTypes, tt.wantUnknown) {
+				t.Errorf(
+					"saved status %q, records %v, failed types %v, "+
+						"unknown types %v; want ok, %v, [%s], %v",
+					got.Status, got.Records, got.FailedTypes,
+					got.UnknownTypes, tt.wantRecords, txt, tt.wantUnknown,
+				)
+			}
+		})
+	}
+}
+
+// TestFailedTypeAlerts saves the checks of each case in turn from the
+// nameservers' responses, the first being the state loaded at startup,
+// and counts the alerts sent. nsB's TXT query fails on one check, and
+// nothing changes.
+func TestFailedTypeAlerts(t *testing.T) {
+	t.Parallel()
+
+	records := map[string][]string{"A": {ip1}, txt: {spf1}}
+	aOnly := map[string][]string{"A": {ip1}}
+
+	bothAnswer := map[string]*resolver.NameserverResponse{
+		nsA: response(records), nsB: response(records),
+	}
+	bTXTFails := map[string]*resolver.NameserverResponse{
+		nsA: response(records), nsB: response(aOnly, txt),
+	}
+	onlyA := map[string]*resolver.NameserverResponse{
+		nsA: response(records),
+	}
+	bFails := map[string]*resolver.NameserverResponse{
+		nsA: response(records),
+		nsB: {
+			Records: map[string][]string{},
+			Status:  resolver.StatusTimeout,
+			Error:   "all queries timed out",
+		},
+	}
+
+	tests := []struct {
+		name   string
+		checks []map[string]*resolver.NameserverResponse
+		want   alertCounts
+	}{
+		{
+			"type failing at one nameserver alerts nothing, nor its next answer",
+			[]map[string]*resolver.NameserverResponse{
+				bothAnswer, bTXTFails, bothAnswer,
+			},
+			alertCounts{},
+		},
+		{
+			"type failing on the first check alerts nothing on the next",
+			[]map[string]*resolver.NameserverResponse{bTXTFails, bothAnswer},
+			alertCounts{},
+		},
+		{
+			"type failing at a nameserver new on that check alerts nothing",
+			[]map[string]*resolver.NameserverResponse{
+				onlyA, bTXTFails, bothAnswer,
+			},
+			alertCounts{},
+		},
+		{
+			"type failing at a recovering nameserver alerts the recovery",
+			[]map[string]*resolver.NameserverResponse{
+				bFails, bTXTFails, bothAnswer,
+			},
+			alertCounts{recoveries: 1},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			states := savedChecks(tt.checks...)
+
+			got := countAlerts(t, states[0], states[1:])
+			if got != tt.want {
+				t.Errorf("sent %+v, want %+v", got, tt.want)
+			}
+		})
+	}
+}
+
+// TestFailedTypeComparedOnceItAnswers saves the checks of each case in
+// turn as TestFailedTypeAlerts does. nsB's TXT query fails on one check,
+// and the TXT record changes: the change is sent as a Record Change for
+// each nameserver on the check where it answers it, and an Inconsistency
+// only when nsB still answers the old record.
+func TestFailedTypeComparedOnceItAnswers(t *testing.T) {
+	t.Parallel()
+
+	records := map[string][]string{"A": {ip1}, txt: {spf1}}
+	changed := map[string][]string{"A": {ip1}, txt: {spf2}}
+	aOnly := map[string][]string{"A": {ip1}}
+
+	bothAnswer := map[string]*resolver.NameserverResponse{
+		nsA: response(records), nsB: response(records),
+	}
+	bTXTFails := map[string]*resolver.NameserverResponse{
+		nsA: response(records), nsB: response(aOnly, txt),
+	}
+	bothChange := map[string]*resolver.NameserverResponse{
+		nsA: response(changed), nsB: response(changed),
+	}
+	aChangesBTXTFails := map[string]*resolver.NameserverResponse{
+		nsA: response(changed), nsB: response(aOnly, txt),
+	}
+	bStillOld := map[string]*resolver.NameserverResponse{
+		nsA: response(changed), nsB: response(records),
+	}
+
+	tests := []struct {
+		name   string
+		checks []map[string]*resolver.NameserverResponse
+		want   alertCounts
+	}{
+		{
+			"change made while the type failed",
+			[]map[string]*resolver.NameserverResponse{
+				bothAnswer, bTXTFails, bothChange,
+			},
+			alertCounts{recordChanges: 2},
+		},
+		{
+			"change seen at one nameserver while the other's type failed",
+			[]map[string]*resolver.NameserverResponse{
+				bothAnswer, aChangesBTXTFails, bothChange,
+			},
+			alertCounts{recordChanges: 2},
+		},
+		{
+			"old record answered after the type failed",
+			[]map[string]*resolver.NameserverResponse{
+				bothAnswer, aChangesBTXTFails, bStillOld,
+			},
+			alertCounts{recordChanges: 1, inconsistencies: 1},
+		},
+		{
+			"change after the type failed on the first check and answered",
+			[]map[string]*resolver.NameserverResponse{
+				bTXTFails, bothAnswer, bothChange,
+			},
+			alertCounts{recordChanges: 2},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			states := savedChecks(tt.checks...)
+
+			got := countAlerts(t, states[0], states[1:])
+			if got != tt.want {
+				t.Errorf("sent %+v, want %+v", got, tt.want)
+			}
+		})
+	}
+}
+
+// TestFailedTypeLeftOutOfMessages checks that a Record Change and an
+// Inconsistency name only the record types they compared. nsB's TXT
+// records are not known on the first check, and on the second either
+// answered or still not known; nsB's A record changes, so both alerts
+// are sent and name the A record alone.
+func TestFailedTypeLeftOutOfMessages(t *testing.T) {
+	t.Parallel()
+
+	withTXT := map[string][]string{"A": {ip1}, txt: {spf1}}
+	txtNotKnown := func(address string) *state.NameserverRecordState {
+		return &state.NameserverRecordState{
+			Records:      map[string][]string{"A": {address}},
+			FailedTypes:  []string{txt},
+			UnknownTypes: []string{txt},
+			Status:       "ok",
+		}
+	}
+
+	before := saved(map[string]*state.NameserverRecordState{
+		nsA: answered(withTXT), nsB: txtNotKnown(ip1),
+	})
+
+	tests := []struct {
+		name  string
+		after *state.HostnameState
+	}{
+		{
+			"TXT answers",
+			saved(map[string]*state.NameserverRecordState{
+				nsA: answered(withTXT),
+				nsB: answered(map[string][]string{"A": {ip2}, txt: {spf1}}),
+			}),
+		},
+		{
+			"TXT still not known",
+			saved(map[string]*state.NameserverRecordState{
+				nsA: answered(withTXT), nsB: txtNotKnown(ip2),
+			}),
+		},
+	}
+
+	want := map[string]string{
+		"Record Change: " + host: "Hostname: " + host +
+			"\nNameserver: " + nsB + "\nType: A\nOld: " + ip1 + "\nNew: " + ip2,
+		"Inconsistency: " + host: "Hostname: " + host +
+			"\nType: A\n" + nsA + ": " + ip1 + "\n" + nsB + ": " + ip2,
+	}
+
+	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)
+
+			w.DetectHostnameChanges(t.Context(), host, before, tt.after)
+
+			notifications := notifier.getNotifications()
+			if len(notifications) != len(want) {
+				t.Fatalf(
+					"sent %d notifications, want %d: %v",
+					len(notifications), len(want), notifications,
+				)
+			}
+
+			for _, n := range notifications {
+				if n.Message != want[n.Title] {
+					t.Errorf(
+						"%s message:\n%s\nwant:\n%s",
+						n.Title, n.Message, want[n.Title],
+					)
+				}
+			}
+		})
+	}
+}

internal/watcher/inconsistency_test.go

@@ -105,7 +105,9 @@ func TestNewlyDisagreeingPairs(t *testing.T) {
 
 			prev := hostnameState(tt.loaded)
 
-			for i, current := range tt.checks {
+			for i, records := range tt.checks {
+				current := hostnameState(records)
+
 				got := watcher.NewlyDisagreeingPairs(prev, current)
 				if !slices.Equal(got, tt.want[i]) {
 					t.Errorf(
@@ -114,7 +116,7 @@ func TestNewlyDisagreeingPairs(t *testing.T) {
 					)
 				}
 
-				prev = hostnameState(current)
+				prev = current
 			}
 		})
 	}
@@ -162,8 +164,9 @@ func TestInconsistencyAlert(t *testing.T) {
 			prev := hostnameState(tt.loaded)
 
 			for range 3 {
-				w.DetectHostnameChanges(t.Context(), host, prev, disagree)
-				prev = hostnameState(disagree)
+				current := hostnameState(disagree)
+				w.DetectHostnameChanges(t.Context(), host, prev, current)
+				prev = current
 			}
 
 			got := 0
@@ -180,3 +183,58 @@ func TestInconsistencyAlert(t *testing.T) {
 		})
 	}
 }
+
+// TestFirstCheckAfterRepeatedValuesLoaded saves a state file holding a
+// hostname's CNAME once for every record type asked for, as checks did
+// before each value was stored once, and two addresses each repeated,
+// and loads it. A check that then finds each value once at each
+// nameserver must notify nothing.
+func TestFirstCheckAfterRepeatedValuesLoaded(t *testing.T) {
+	t.Parallel()
+
+	const (
+		cnameType = "CNAME"
+		cname     = "c.example.net."
+	)
+
+	cfg := defaultTestConfig(t)
+	repeated := map[string][]string{
+		"A":       {ip2, ip1, ip2, ip1},
+		cnameType: {cname, cname, cname, cname, cname, cname, cname, cname},
+	}
+	once := map[string][]string{"A": {ip1, ip2}, cnameType: {cname}}
+
+	saved := newTestDeps(t, cfg).state
+	saved.SetHostnameState(host, hostnameState(map[string]map[string][]string{
+		nsA: repeated, nsB: repeated,
+	}))
+
+	err := saved.Save()
+	if err != nil {
+		t.Fatalf("saving the state file: %v", err)
+	}
+
+	deps := newTestDeps(t, cfg)
+
+	err = deps.state.Load()
+	if err != nil {
+		t.Fatalf("loading the state file: %v", err)
+	}
+
+	prev, ok := deps.state.GetHostnameState(host)
+	if !ok {
+		t.Fatal("the state file has no state for " + host)
+	}
+
+	current := hostnameState(map[string]map[string][]string{
+		nsA: once, nsB: once,
+	})
+
+	// The hostname change detection uses only the notifier.
+	w := watcher.NewForTest(nil, nil, nil, nil, nil, deps.notifier)
+	w.DetectHostnameChanges(t.Context(), host, prev, current)
+
+	if got := deps.notifier.getNotifications(); len(got) != 0 {
+		t.Errorf("sent %v, want no notification", got)
+	}
+}

internal/watcher/interfaces.go

@@ -5,23 +5,26 @@ import (
 	"context"
 
 	"sneak.berlin/go/dnswatcher/internal/portcheck"
+	"sneak.berlin/go/dnswatcher/internal/resolver"
 	"sneak.berlin/go/dnswatcher/internal/tlscheck"
 )
 
 // DNSResolver performs iterative DNS resolution.
 type DNSResolver interface {
-	// LookupNS discovers authoritative nameservers for a domain.
+	// LookupNS returns a domain's NS record set, as its parent zone's
+	// servers delegate it: empty when they answer that it has none, and
+	// resolver.ErrNXDomain when they answer that it does not exist.
 	LookupNS(
 		ctx context.Context,
 		domain string,
 	) ([]string, error)
 
 	// LookupAllRecords queries all record types for a hostname,
-	// returning results keyed by nameserver then record type.
+	// returning each nameserver's response keyed by nameserver.
 	LookupAllRecords(
 		ctx context.Context,
 		hostname string,
-	) (map[string]map[string][]string, error)
+	) (map[string]*resolver.NameserverResponse, error)
 
 	// ResolveIPAddresses resolves a hostname to all IP addresses.
 	ResolveIPAddresses(

internal/watcher/message_test.go

@@ -0,0 +1,215 @@
+package watcher_test
+
+import (
+	"maps"
+	"strings"
+	"testing"
+
+	"sneak.berlin/go/dnswatcher/internal/config"
+	"sneak.berlin/go/dnswatcher/internal/state"
+	"sneak.berlin/go/dnswatcher/internal/watcher"
+)
+
+// When one nameserver's A record changes and its TXT record does not,
+// the record change and the inconsistency it starts name the A record
+// alone, with its values written as plain text.
+func TestChangeMessagesNameTheChangedType(t *testing.T) {
+	t.Parallel()
+
+	// A nameserver's records: this A address and the same TXT record.
+	records := func(address string) map[string][]string {
+		return map[string][]string{
+			"A":   {address},
+			"TXT": {"v=spf1 -all"},
+		}
+	}
+
+	before := hostnameState(map[string]map[string][]string{
+		nsA: records(ip1),
+		nsB: records(ip1),
+	})
+	after := hostnameState(map[string]map[string][]string{
+		nsA: records(ip1),
+		nsB: records(ip2),
+	})
+
+	// The hostname change detection uses only the notifier.
+	notifier := &mockNotifier{}
+	w := watcher.NewForTest(nil, nil, nil, nil, nil, notifier)
+
+	w.DetectHostnameChanges(t.Context(), host, before, after)
+
+	want := map[string]string{
+		"Record Change: " + host: `Hostname: www.example.net
+Nameserver: b.ns.example.net.
+Type: A
+Old: 192.0.2.1
+New: 192.0.2.2`,
+		"Inconsistency: " + host: `Hostname: www.example.net
+Type: A
+a.ns.example.net.: 192.0.2.1
+b.ns.example.net.: 192.0.2.2`,
+	}
+
+	notifications := notifier.getNotifications()
+	if len(notifications) != len(want) {
+		t.Fatalf(
+			"sent %d notifications, want %d: %v",
+			len(notifications), len(want), notifications,
+		)
+	}
+
+	for _, n := range notifications {
+		if n.Message != want[n.Title] {
+			t.Errorf(
+				"%s message:\n%s\nwant:\n%s",
+				n.Title, n.Message, want[n.Title],
+			)
+		}
+	}
+}
+
+// Every kind of notification about a configured apex domain's own
+// records names it as a domain.
+func TestDomainRecordNotificationsNameTheDomain(t *testing.T) {
+	t.Parallel()
+
+	notifier := &mockNotifier{}
+	w := watcher.NewForTest(
+		&config.Config{Domains: []string{domain}},
+		nil, nil, nil, nil, notifier,
+	)
+
+	// nsA's address changes, which also makes it differ from nsC; nsB
+	// fails; nsC answers again; nsD is gone.
+	nsD := "d.ns.example.net."
+	w.DetectHostnameChanges(t.Context(), domain,
+		saved(map[string]*state.NameserverRecordState{
+			nsA: answered(map[string][]string{"A": {ip1}}),
+			nsB: answered(map[string][]string{"A": {ip1}}),
+			nsC: failed(),
+			nsD: answered(map[string][]string{"A": {ip1}}),
+		}),
+		saved(map[string]*state.NameserverRecordState{
+			nsA: answered(map[string][]string{"A": {ip2}}),
+			nsB: failed(),
+			nsC: answered(map[string][]string{"A": {ip1}}),
+		}),
+	)
+
+	// The address at the end of its CNAME chain changes.
+	w.DetectHostnameChanges(
+		t.Context(), domain, cnameState(ip1), cnameState(ip2),
+	)
+
+	// NS Failure is sent for nsB failing and for nsD being gone.
+	want := map[string]int{
+		"Record Change":        1,
+		"Inconsistency":        1,
+		"NS Failure":           2,
+		"NS Recovery":          1,
+		"CNAME Address Change": 1,
+	}
+
+	sent := make(map[string]int)
+
+	for _, n := range notifier.getNotifications() {
+		kind, _, _ := strings.Cut(n.Title, ":")
+		sent[kind]++
+
+		if !strings.HasPrefix(n.Message, "Domain: "+domain+"\n") {
+			t.Errorf("%s message does not name the domain:\n%s",
+				n.Title, n.Message)
+		}
+	}
+
+	if !maps.Equal(sent, want) {
+		t.Errorf("sent %v, want %v", sent, want)
+	}
+}
+
+// The startup notification counts the configured domains and hostnames,
+// although the state's hostnames also hold the apex domain's own
+// records. Nothing is looked up: the watcher has no resolver.
+func TestStartupNotificationCountsConfiguredNames(t *testing.T) {
+	t.Parallel()
+
+	cfg := defaultTestConfig(t)
+	cfg.SendTestNotification = true
+	cfg.Domains = []string{domain}
+	cfg.Hostnames = []string{host}
+
+	deps := newTestDeps(t, cfg)
+	w := watcher.NewForTest(cfg, deps.state, nil, nil, nil, deps.notifier)
+
+	// The state a check of both names saves.
+	deps.state.SetDomainState(domain, &state.DomainState{
+		Nameservers: []string{nsA},
+	})
+
+	for _, name := range []string{domain, host} {
+		deps.state.SetHostnameState(name, saved(
+			map[string]*state.NameserverRecordState{
+				nsA: answered(map[string][]string{"A": {ip1}}),
+			},
+		))
+	}
+
+	w.MaybeSendTestNotification(t.Context())
+
+	notifications := deps.notifier.getNotifications()
+
+	counts := "\nMonitoring 1 domain(s) and 1 hostname(s).\n"
+	if len(notifications) != 1 ||
+		!strings.Contains(notifications[0].Message, counts) {
+		t.Errorf("sent %v, want one message with %q", notifications, counts)
+	}
+}
+
+// A Port Change notification lists the configured apex domain and the
+// hostname that resolve to the port's address on separate lines. The
+// port checks read the saved hostname state and look nothing up, so the
+// watcher has no resolver.
+func TestPortChangeListsDomainsApartFromHostnames(t *testing.T) {
+	t.Parallel()
+
+	cfg := defaultTestConfig(t)
+	cfg.Domains = []string{domain}
+	cfg.Hostnames = []string{host}
+
+	deps := newTestDeps(t, cfg)
+	w := watcher.NewForTest(
+		cfg, deps.state, nil,
+		deps.portChecker, deps.tlsChecker, deps.notifier,
+	)
+	w.SetFirstRun(false)
+
+	// Both names resolve to ip1, whose port 443 the previous check
+	// found open. It is closed now.
+	for _, name := range []string{domain, host} {
+		deps.state.SetHostnameState(name, saved(
+			map[string]*state.NameserverRecordState{
+				nsA: answered(map[string][]string{"A": {ip1}}),
+			},
+		))
+	}
+
+	key := ip1 + ":443"
+	deps.state.SetPortState(key, &state.PortState{
+		Open: true, Hostnames: []string{domain, host},
+	})
+	deps.portChecker.closed = true
+
+	w.CheckAllPorts(t.Context())
+
+	title := "Port Change: " + key
+	want := `Domains: example.net
+Hostnames: www.example.net
+Address: 192.0.2.1:443
+Port now closed`
+
+	got := deps.notifier.getNotifications()
+	if len(got) != 1 || got[0].Title != title || got[0].Message != want {
+		t.Errorf("sent %v, want one %q with message:\n%s", got, title, want)
+	}
+}

internal/watcher/nsaddress_test.go

@@ -0,0 +1,151 @@
+package watcher_test
+
+import (
+	"context"
+	"log/slog"
+	"reflect"
+	"testing"
+
+	"sneak.berlin/go/dnswatcher/internal/livednstest"
+	"sneak.berlin/go/dnswatcher/internal/resolver"
+	"sneak.berlin/go/dnswatcher/internal/watcher"
+)
+
+const domain = "example.net"
+
+func TestNSAddressChangeAlerts(t *testing.T) {
+	t.Parallel()
+
+	// Each case is the nameserver addresses saved by the previous check
+	// and by the current one.
+	tests := []struct {
+		name          string
+		prev, current map[string][]string
+		want          int
+	}{
+		{
+			"same addresses",
+			map[string][]string{nsA: {ip1, ip2}},
+			map[string][]string{nsA: {ip1, ip2}},
+			0,
+		},
+		{
+			"same addresses in another order",
+			map[string][]string{nsA: {ip2, ip1}},
+			map[string][]string{nsA: {ip1, ip2}},
+			0,
+		},
+		{
+			"address replaced",
+			map[string][]string{nsA: {ip1}},
+			map[string][]string{nsA: {ip2}},
+			1,
+		},
+		{
+			"address added",
+			map[string][]string{nsA: {ip1}},
+			map[string][]string{nsA: {ip1, ip2}},
+			1,
+		},
+		{
+			"two nameservers changed",
+			map[string][]string{nsA: {ip1}, nsB: {ip2}},
+			map[string][]string{nsA: {ip3}, nsB: {ip3}},
+			2,
+		},
+		{
+			"nameserver added",
+			map[string][]string{nsA: {ip1}},
+			map[string][]string{nsA: {ip1}, nsB: {ip2}},
+			0,
+		},
+		{
+			"nameserver removed",
+			map[string][]string{nsA: {ip1}, nsB: {ip2}},
+			map[string][]string{nsA: {ip1}},
+			0,
+		},
+		{
+			"state file from before addresses were saved",
+			nil,
+			map[string][]string{nsA: {ip1}, nsB: {ip2}},
+			0,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			notifier := &mockNotifier{}
+			w := watcher.NewForTest(nil, nil, nil, nil, nil, notifier)
+
+			w.DetectNSAddressChanges(t.Context(), domain, tt.prev, tt.current)
+
+			got := len(notifier.getNotifications())
+			if got != tt.want {
+				t.Errorf("sent %d address changes, want %d", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestNSAddressChangeAlertNamesDomainNameserverAndAddresses(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	notifier := &mockNotifier{}
+	w := watcher.NewForTest(nil, nil, nil, nil, nil, notifier)
+
+	w.DetectNSAddressChanges(
+		t.Context(), domain,
+		map[string][]string{nsA: {ip1}},
+		map[string][]string{nsA: {ip2, ip3}},
+	)
+
+	want := notification{
+		Title: "NS Address Change: " + domain,
+		Message: "Domain: " + domain + "\nNameserver: " + nsA +
+			"\nOld: " + ip1 + "\nNew: " + ip2 + ", " + ip3,
+		Priority: "warning",
+	}
+
+	got := notifier.getNotifications()
+	if len(got) != 1 || got[0] != want {
+		t.Errorf("sent %v, want %v", got, want)
+	}
+}
+
+// TestNameserverWithNoAddressKeepsPrevious looks up nameserver names
+// with no address: two under .invalid, whose lookup fails with an
+// error, and one that does not exist under a real zone, which live DNS
+// answers with no address and no error. Each one with addresses saved
+// by the previous check keeps them; the one without gets none.
+func TestNameserverWithNoAddressKeepsPrevious(t *testing.T) {
+	t.Parallel()
+
+	w := watcher.NewForTest(
+		nil, nil, resolver.NewFromLogger(slog.Default()), nil, nil, nil,
+	)
+
+	nonexistentNS := "this-surely-does-not-exist-xyz." + testSmallDomain + "."
+
+	prev := map[string][]string{oldNS1: {oldIP}, nonexistentNS: {oldIP}}
+
+	var got map[string][]string
+
+	// The result is the same whether or not live DNS answers, so the
+	// lookup is not retried.
+	_ = livednstest.Run(func(ctx context.Context) error {
+		got = w.ResolveNameserverAddresses(
+			ctx, []string{oldNS1, oldNS2, nonexistentNS}, prev,
+		)
+
+		return nil
+	})
+
+	if !reflect.DeepEqual(got, prev) {
+		t.Errorf("saved %v, want %v", got, prev)
+	}
+}

internal/watcher/nsfailure_test.go

@@ -0,0 +1,448 @@
+package watcher_test
+
+import (
+	"context"
+	"fmt"
+	"log/slog"
+	"strings"
+	"testing"
+	"time"
+
+	"sneak.berlin/go/dnswatcher/internal/livednstest"
+	"sneak.berlin/go/dnswatcher/internal/resolver"
+	"sneak.berlin/go/dnswatcher/internal/state"
+	"sneak.berlin/go/dnswatcher/internal/watcher"
+)
+
+// answered is what a check saves for a nameserver that answered with
+// these records.
+func answered(records map[string][]string) *state.NameserverRecordState {
+	return &state.NameserverRecordState{Records: records, Status: "ok"}
+}
+
+// failed is what a check saves for a nameserver that did not answer.
+func failed() *state.NameserverRecordState {
+	return &state.NameserverRecordState{
+		Records: map[string][]string{},
+		Status:  "error",
+		Error:   "all queries timed out",
+	}
+}
+
+// saved builds the hostname state a check saves.
+func saved(
+	byNameserver map[string]*state.NameserverRecordState,
+) *state.HostnameState {
+	return &state.HostnameState{RecordsByNameserver: byNameserver}
+}
+
+// alertCounts counts the hostname alerts sent, by kind.
+type alertCounts struct {
+	failures, recoveries, recordChanges, inconsistencies int
+}
+
+// countAlerts runs the hostname change detection from the state loaded
+// at startup through each check in turn, and counts the alerts sent.
+func countAlerts(
+	t *testing.T,
+	loaded *state.HostnameState,
+	checks []*state.HostnameState,
+) alertCounts {
+	t.Helper()
+
+	// The hostname change detection uses only the notifier.
+	notifier := &mockNotifier{}
+	w := watcher.NewForTest(nil, nil, nil, nil, nil, notifier)
+
+	prev := loaded
+
+	for _, current := range checks {
+		w.DetectHostnameChanges(t.Context(), host, prev, current)
+		prev = current
+	}
+
+	var got alertCounts
+
+	for _, n := range notifier.getNotifications() {
+		kind, _, _ := strings.Cut(n.Title, ":")
+
+		switch kind {
+		case "NS Failure":
+			got.failures++
+		case "NS Recovery":
+			got.recoveries++
+		case "Record Change":
+			got.recordChanges++
+		case "Inconsistency":
+			got.inconsistencies++
+		}
+	}
+
+	return got
+}
+
+func TestNSFailureAndRecoveryAlerts(t *testing.T) {
+	t.Parallel()
+
+	records := map[string][]string{"A": {ip1}}
+
+	bothAnswer := saved(map[string]*state.NameserverRecordState{
+		nsA: answered(records), nsB: answered(records),
+	})
+	bFails := saved(map[string]*state.NameserverRecordState{
+		nsA: answered(records), nsB: failed(),
+	})
+	onlyA := saved(map[string]*state.NameserverRecordState{
+		nsA: answered(records),
+	})
+	bAnswersNoRecords := saved(map[string]*state.NameserverRecordState{
+		nsA: answered(records), nsB: answered(map[string][]string{}),
+	})
+	bAnswersDifferently := saved(map[string]*state.NameserverRecordState{
+		nsA: answered(records), nsB: answered(map[string][]string{"A": {ip2}}),
+	})
+
+	// Each case starts from the state loaded at startup and runs the
+	// checks in order.
+	tests := []struct {
+		name   string
+		loaded *state.HostnameState
+		checks []*state.HostnameState
+		want   alertCounts
+	}{
+		{
+			"failure lasting several checks alerts once",
+			bothAnswer, []*state.HostnameState{bFails, bFails, bFails},
+			alertCounts{failures: 1},
+		},
+		{
+			"recovery alerts once",
+			bFails, []*state.HostnameState{bothAnswer, bothAnswer},
+			alertCounts{recoveries: 1},
+		},
+		{
+			"failing again after recovering alerts again",
+			bothAnswer, []*state.HostnameState{bFails, bothAnswer, bFails},
+			alertCounts{failures: 2, recoveries: 1},
+		},
+		{
+			"nameserver failing when first seen does not alert",
+			onlyA, []*state.HostnameState{bFails, bFails},
+			alertCounts{},
+		},
+		{
+			"answer with no records is a record change, not a failure",
+			bothAnswer, []*state.HostnameState{bAnswersNoRecords},
+			alertCounts{recordChanges: 1, inconsistencies: 1},
+		},
+		{
+			"recovered nameserver that answers differently disagrees",
+			bFails, []*state.HostnameState{bAnswersDifferently},
+			alertCounts{recoveries: 1, inconsistencies: 1},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			got := countAlerts(t, tt.loaded, tt.checks)
+			if got != tt.want {
+				t.Errorf("sent %+v, want %+v", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestNSFailureAlertNamesHostnameNameserverAndReason(t *testing.T) {
+	t.Parallel()
+
+	records := map[string][]string{"A": {ip1}}
+
+	notifier := &mockNotifier{}
+	w := watcher.NewForTest(nil, nil, nil, nil, nil, notifier)
+
+	w.DetectHostnameChanges(
+		t.Context(), host,
+		saved(map[string]*state.NameserverRecordState{nsA: answered(records)}),
+		saved(map[string]*state.NameserverRecordState{nsA: failed()}),
+	)
+
+	notifications := notifier.getNotifications()
+	if len(notifications) != 1 {
+		t.Fatalf("sent %v, want one NS Failure", notifications)
+	}
+
+	msg := notifications[0].Message
+	if !strings.Contains(msg, host) || !strings.Contains(msg, nsA) ||
+		!strings.Contains(msg, failed().Error) {
+		t.Errorf(
+			"message %q does not name %s, %s and the reason",
+			msg, host, nsA,
+		)
+	}
+}
+
+// TestNameserverThatNeverAnswers asks a nameserver address where
+// nothing answers, 192.0.2.1, and checks what the watcher saves for it.
+// The deadline outlasts the resolver's first two-second try, as in the
+// resolver's timeout test.
+func TestNameserverThatNeverAnswers(t *testing.T) {
+	t.Parallel()
+
+	ctx, cancel := context.WithTimeout(t.Context(), 3*time.Second)
+	t.Cleanup(cancel)
+
+	res := resolver.NewFromLogger(slog.Default())
+
+	resp, err := res.QueryNameserverIP(ctx, nsA, "192.0.2.1", host)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	hs := watcher.BuildHostnameState(
+		map[string]*resolver.NameserverResponse{nsA: resp}, nil, time.Now(),
+	)
+
+	got := hs.RecordsByNameserver[nsA]
+	if got.Status != "error" || got.Error == "" {
+		t.Errorf(
+			"saved status %q, error %q; want status error with a reason",
+			got.Status, got.Error,
+		)
+	}
+}
+
+// TestNameserverThatAnswersNXDOMAIN asks a real nameserver about a name
+// that does not exist and checks what the watcher saves for it: NXDOMAIN
+// is an answer, so the nameserver is saved as ok with no error.
+func TestNameserverThatAnswersNXDOMAIN(t *testing.T) {
+	t.Parallel()
+
+	res := resolver.NewFromLogger(slog.Default())
+	name := "this-surely-does-not-exist-xyz." + testDomain
+
+	var (
+		ns   string
+		resp *resolver.NameserverResponse
+	)
+
+	livednstest.Retry(t, "QueryNameserver("+name+")", func(ctx context.Context) error {
+		nameservers, err := res.LookupNS(ctx, testDomain)
+		if err != nil {
+			return err
+		}
+
+		ns = nameservers[0]
+
+		resp, err = res.QueryNameserver(ctx, ns, name)
+		if err != nil {
+			return err
+		}
+
+		// A timeout or a failure is no answer to check.
+		if resp.Status == resolver.StatusTimeout ||
+			resp.Status == resolver.StatusError {
+			return fmt.Errorf(
+				"%w: %s: %s", livednstest.ErrNoAnswer, ns, resp.Error,
+			)
+		}
+
+		return nil
+	})
+
+	if resp.Status != resolver.StatusNXDomain {
+		t.Fatalf("%s answered %q for %s, want NXDOMAIN", ns, resp.Status, name)
+	}
+
+	hs := watcher.BuildHostnameState(
+		map[string]*resolver.NameserverResponse{ns: resp}, nil, time.Now(),
+	)
+
+	got := hs.RecordsByNameserver[ns]
+	if got.Status != "ok" || got.Error != "" {
+		t.Errorf(
+			"saved status %q, error %q; want status ok with no error",
+			got.Status, got.Error,
+		)
+	}
+}
+
+// TestNameserverThatRefuses asks a google.com nameserver about
+// cloudflare.com, a zone it does not serve, which it refuses, and checks
+// what the watcher saves for it: REFUSED is no answer, so the nameserver
+// is saved as error with the reason.
+func TestNameserverThatRefuses(t *testing.T) {
+	t.Parallel()
+
+	const reason = "server returned REFUSED"
+
+	res := resolver.NewFromLogger(slog.Default())
+
+	var (
+		ns   string
+		resp *resolver.NameserverResponse
+	)
+
+	livednstest.Retry(
+		t,
+		"QueryNameserver(cloudflare.com)",
+		func(ctx context.Context) error {
+			nameservers, err := res.LookupNS(ctx, testDomain)
+			if err != nil {
+				return err
+			}
+
+			ns = nameservers[0]
+
+			resp, err = res.QueryNameserver(ctx, ns, "cloudflare.com")
+			if err != nil {
+				return err
+			}
+
+			// A timeout or a network error is no reply at all.
+			if resp.Status == resolver.StatusTimeout ||
+				strings.HasPrefix(resp.Error, "network error") {
+				return fmt.Errorf(
+					"%w: %s: %s", livednstest.ErrNoAnswer, ns, resp.Error,
+				)
+			}
+
+			return nil
+		},
+	)
+
+	if resp.Error != reason {
+		t.Fatalf(
+			"%s answered %q (%s) for cloudflare.com, want REFUSED",
+			ns, resp.Status, resp.Error,
+		)
+	}
+
+	hs := watcher.BuildHostnameState(
+		map[string]*resolver.NameserverResponse{ns: resp}, nil, time.Now(),
+	)
+
+	got := hs.RecordsByNameserver[ns]
+	if got.Status != failed().Status || got.Error != reason {
+		t.Errorf(
+			"saved status %q, error %q; want status %q, error %q",
+			got.Status, got.Error, failed().Status, reason,
+		)
+	}
+}
+
+// TestPortStateWhenNoNameserverAnswered runs the port checks on
+// hostname state built here, which gives the name no address. The port
+// state saved for its old address is kept only when the name is a
+// configured hostname or domain and none of its nameservers answered.
+func TestPortStateWhenNoNameserverAnswered(t *testing.T) {
+	t.Parallel()
+
+	noneAnswered := saved(map[string]*state.NameserverRecordState{
+		nsA: failed(), nsB: failed(),
+	})
+	oneAnsweredNoAddress := saved(map[string]*state.NameserverRecordState{
+		nsA: answered(map[string][]string{}), nsB: failed(),
+	})
+
+	configured := []string{host}
+
+	tests := []struct {
+		name      string
+		hostname  *state.HostnameState
+		hostnames []string
+		domains   []string
+		wantKept  bool
+	}{
+		{"no nameserver answered", noneAnswered, configured, nil, true},
+		{
+			"no nameserver answered, configured as a domain",
+			noneAnswered, nil, configured, true,
+		},
+		{
+			"one answered with no address",
+			oneAnsweredNoAddress, configured, nil, false,
+		},
+		{"no nameserver answered, not configured", noneAnswered, nil, nil, false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			cfg := defaultTestConfig(t)
+			cfg.Hostnames = tt.hostnames
+			cfg.Domains = tt.domains
+
+			// The port checks read the saved hostname state and look
+			// nothing up, so the watcher has no resolver.
+			deps := newTestDeps(t, cfg)
+			w := watcher.NewForTest(
+				cfg, deps.state, nil,
+				deps.portChecker, deps.tlsChecker, deps.notifier,
+			)
+
+			key := ip1 + ":443"
+
+			deps.state.SetHostnameState(host, tt.hostname)
+			deps.state.SetPortState(key, &state.PortState{
+				Open: true, Hostnames: []string{host},
+			})
+
+			w.CheckAllPorts(t.Context())
+
+			_, kept := deps.state.GetPortState(key)
+			if kept != tt.wantKept {
+				t.Errorf("port state %s kept: %v, want %v", key, kept, tt.wantKept)
+			}
+		})
+	}
+}
+
+// TestPortStateWhenNoNameserverAnsweredAndOtherNameMovesAway saves the
+// port state of an address two configured hostnames resolve to. While
+// none of the first one's nameservers answer, the port checks run with
+// the other one still at that address, then after it moved away; the
+// port state is kept both times.
+func TestPortStateWhenNoNameserverAnsweredAndOtherNameMovesAway(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	const other = "mail.example.net"
+
+	cfg := defaultTestConfig(t)
+	cfg.Hostnames = []string{host, other}
+
+	// The port checks read the saved hostname state and look nothing
+	// up, so the watcher has no resolver.
+	deps := newTestDeps(t, cfg)
+	w := watcher.NewForTest(
+		cfg, deps.state, nil,
+		deps.portChecker, deps.tlsChecker, deps.notifier,
+	)
+
+	key := ip1 + ":443"
+
+	deps.state.SetPortState(key, &state.PortState{
+		Open: true, Hostnames: []string{host, other},
+	})
+	deps.state.SetHostnameState(host, saved(
+		map[string]*state.NameserverRecordState{nsA: failed(), nsB: failed()},
+	))
+
+	for _, otherIP := range []string{ip1, ip2} {
+		deps.state.SetHostnameState(other, saved(
+			map[string]*state.NameserverRecordState{
+				nsA: answered(map[string][]string{"A": {otherIP}}),
+			},
+		))
+
+		w.CheckAllPorts(t.Context())
+
+		if _, kept := deps.state.GetPortState(key); !kept {
+			t.Fatalf("port state %s removed with %s at %s", key, other, otherIP)
+		}
+	}
+}

internal/watcher/removed_test.go

@@ -0,0 +1,224 @@
+package watcher_test
+
+import (
+	"maps"
+	"slices"
+	"testing"
+
+	"sneak.berlin/go/dnswatcher/internal/state"
+	"sneak.berlin/go/dnswatcher/internal/watcher"
+)
+
+// TestRemovedTargetsLeaveTheState loads a state saved while a domain
+// and a hostname now removed from the configuration were still in it,
+// and runs the removal that Run does before the first check. The
+// removed names' domain, hostname and certificate entries are gone,
+// the configured names' are kept, and nothing is notified. Nothing is
+// looked up: the watcher has no resolver.
+func TestRemovedTargetsLeaveTheState(t *testing.T) {
+	t.Parallel()
+
+	const (
+		removedDomain = "example.com"
+		removedHost   = "www.example.com"
+	)
+
+	cfg := defaultTestConfig(t)
+	cfg.Domains = []string{domain}
+	cfg.Hostnames = []string{host}
+
+	deps := newTestDeps(t, cfg)
+	w := watcher.NewForTest(
+		cfg, deps.state, nil,
+		deps.portChecker, deps.tlsChecker, deps.notifier,
+	)
+
+	// The state a check of all four names saves, each name at ip1.
+	for _, name := range []string{domain, removedDomain} {
+		deps.state.SetDomainState(name, &state.DomainState{
+			Nameservers: []string{nsA},
+		})
+	}
+
+	for _, name := range []string{domain, host, removedDomain, removedHost} {
+		deps.state.SetHostnameState(name, saved(
+			map[string]*state.NameserverRecordState{
+				nsA: answered(map[string][]string{"A": {ip1}}),
+			},
+		))
+		deps.state.SetCertificateState(
+			ip1+":443:"+name, &state.CertificateState{Status: "ok"},
+		)
+	}
+
+	err := deps.state.Save()
+	if err != nil {
+		t.Fatalf("saving the state: %v", err)
+	}
+
+	err = deps.state.Load()
+	if err != nil {
+		t.Fatalf("loading the state: %v", err)
+	}
+
+	w.CleanupRemovedTargets()
+
+	snap := deps.state.GetSnapshot()
+
+	got := slices.Sorted(maps.Keys(snap.Domains))
+	if want := []string{domain}; !slices.Equal(got, want) {
+		t.Errorf("domain entries %v, want %v", got, want)
+	}
+
+	got = slices.Sorted(maps.Keys(snap.Hostnames))
+	if want := []string{domain, host}; !slices.Equal(got, want) {
+		t.Errorf("hostname entries %v, want %v", got, want)
+	}
+
+	got = slices.Sorted(maps.Keys(snap.Certificates))
+	if want := []string{
+		ip1 + ":443:" + domain, ip1 + ":443:" + host,
+	}; !slices.Equal(got, want) {
+		t.Errorf("certificate entries %v, want %v", got, want)
+	}
+
+	if sent := deps.notifier.getNotifications(); len(sent) != 0 {
+		t.Errorf("sent %v, want nothing", sent)
+	}
+}
+
+// TestRemovedTargetsLeaveThePortEntries loads a state whose port
+// entries name a domain and a hostname now removed from the
+// configuration, and runs the removal that Run does before the first
+// check. The removed names are off each port entry's list of names, the
+// entry only they had is gone, the entry that also names configured
+// names is kept for the port checks, and nothing is notified.
+func TestRemovedTargetsLeaveThePortEntries(t *testing.T) {
+	t.Parallel()
+
+	const (
+		removedDomain = "example.com"
+		removedHost   = "www.example.com"
+	)
+
+	cfg := defaultTestConfig(t)
+	cfg.Domains = []string{domain}
+	cfg.Hostnames = []string{host}
+
+	deps := newTestDeps(t, cfg)
+	w := watcher.NewForTest(
+		cfg, deps.state, nil,
+		deps.portChecker, deps.tlsChecker, deps.notifier,
+	)
+
+	// The port 443 entries a check of all four names saves: each name
+	// at ip1, except the removed hostname, at ip2.
+	deps.state.SetPortState(ip1+":443", &state.PortState{
+		Open: true, Hostnames: []string{removedDomain, domain, host},
+	})
+	deps.state.SetPortState(ip2+":443", &state.PortState{
+		Open: true, Hostnames: []string{removedHost},
+	})
+
+	err := deps.state.Save()
+	if err != nil {
+		t.Fatalf("saving the state: %v", err)
+	}
+
+	err = deps.state.Load()
+	if err != nil {
+		t.Fatalf("loading the state: %v", err)
+	}
+
+	w.CleanupRemovedTargets()
+
+	if sent := deps.notifier.getNotifications(); len(sent) != 0 {
+		t.Errorf("sent %v, want nothing", sent)
+	}
+
+	snap := deps.state.GetSnapshot()
+
+	got := slices.Sorted(maps.Keys(snap.Ports))
+	if want := []string{ip1 + ":443"}; !slices.Equal(got, want) {
+		t.Fatalf("port entries %v, want %v", got, want)
+	}
+
+	got = snap.Ports[ip1+":443"].Hostnames
+	if want := []string{domain, host}; !slices.Equal(got, want) {
+		t.Errorf("names of port entry %s:443 %v, want %v", ip1, got, want)
+	}
+}
+
+// TestCertificateStateForAnAddressGone runs the port checks on hostname
+// state built here for a configured hostname, with certificate entries
+// saved for it at ip1, ip2 and an IPv6 address. When its nameservers
+// answered with ip1 and the IPv6 address, the entry for ip2 is removed.
+// When none of them answered, its addresses are not known, and every
+// entry is kept. Nothing is notified, and nothing is looked up.
+func TestCertificateStateForAnAddressGone(t *testing.T) {
+	t.Parallel()
+
+	const ip6 = "2001:db8::1"
+
+	tests := []struct {
+		name     string
+		hostname *state.HostnameState
+		want     []string
+	}{
+		{
+			"answered without ip2",
+			saved(map[string]*state.NameserverRecordState{
+				nsA: answered(map[string][]string{
+					"A": {ip1}, "AAAA": {ip6},
+				}),
+			}),
+			[]string{ip1 + ":443:" + host, ip6 + ":443:" + host},
+		},
+		{
+			"no nameserver answered",
+			saved(map[string]*state.NameserverRecordState{
+				nsA: failed(), nsB: failed(),
+			}),
+			[]string{
+				ip1 + ":443:" + host,
+				ip2 + ":443:" + host,
+				ip6 + ":443:" + host,
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			cfg := defaultTestConfig(t)
+			cfg.Hostnames = []string{host}
+
+			deps := newTestDeps(t, cfg)
+			w := watcher.NewForTest(
+				cfg, deps.state, nil,
+				deps.portChecker, deps.tlsChecker, deps.notifier,
+			)
+			w.SetFirstRun(false)
+
+			deps.state.SetHostnameState(host, tt.hostname)
+
+			for _, ip := range []string{ip1, ip2, ip6} {
+				deps.state.SetCertificateState(
+					ip+":443:"+host, &state.CertificateState{Status: "ok"},
+				)
+			}
+
+			w.CheckAllPorts(t.Context())
+
+			got := slices.Sorted(maps.Keys(deps.state.GetSnapshot().Certificates))
+			if !slices.Equal(got, tt.want) {
+				t.Errorf("certificate entries %v, want %v", got, tt.want)
+			}
+
+			if sent := deps.notifier.getNotifications(); len(sent) != 0 {
+				t.Errorf("sent %v, want nothing", sent)
+			}
+		})
+	}
+}

internal/watcher/watcher_test.go

@@ -4,7 +4,9 @@ import (
 	"context"
 	"fmt"
 	"log/slog"
+	"os"
 	"slices"
+	"strings"
 	"sync"
 	"testing"
 	"time"
@@ -24,13 +26,23 @@ import (
 
 // 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.
+// the records these zones publish. The nameservers of testHost and
+// testSmallDomain stay the same between a test looking them up and its
+// check. Every query a check sends is one more that can be lost, so the
+// tests keep them few. A check asks each of a name's nameservers about
+// every record type, and both names have two. A domain check also looks
+// up each nameserver's addresses at every nameserver of the zone that
+// nameserver is in: testSmallDomain's nameservers are in zones with two
+// nameservers, while a domain whose nameservers are in, say,
+// cloudflare.com, which has five, makes each domain check much longer.
+// A test checks a domain only when it is about domains, and checks once,
+// from saved state it builds, rather than twice. The tests that query
+// testDomain's nameservers directly do no domain check.
 const (
-	testDomain = "google.com"
-	testHost   = "cloudflare.com"
-	testIssuer = "DigiCert"
+	testDomain      = "google.com"
+	testSmallDomain = "desec.io"
+	testHost        = "example.org"
+	testIssuer      = "DigiCert"
 )
 
 // Saved-state values that live DNS never returns: nameserver names
@@ -135,6 +147,7 @@ type testDeps struct {
 	notifier    *mockNotifier
 	state       *state.State
 	config      *config.Config
+	log         *logger.Logger
 }
 
 func newTestWatcher(
@@ -143,6 +156,23 @@ func newTestWatcher(
 ) (*watcher.Watcher, *testDeps) {
 	t.Helper()
 
+	deps := newTestDeps(t, cfg)
+
+	w := watcher.NewForTest(
+		deps.config,
+		deps.state,
+		resolver.NewFromLogger(slog.Default()),
+		deps.portChecker,
+		deps.tlsChecker,
+		deps.notifier,
+	)
+
+	return w, deps
+}
+
+func newTestDeps(t *testing.T, cfg *config.Config) *testDeps {
+	t.Helper()
+
 	deps := &testDeps{
 		portChecker: &mockPortChecker{},
 		tlsChecker: &mockTLSChecker{
@@ -157,30 +187,21 @@ func newTestWatcher(
 		t.Fatalf("globals.New: %v", err)
 	}
 
-	log, err := logger.New(nil, logger.Params{Globals: g})
+	deps.log, err = logger.New(nil, logger.Params{Globals: g})
 	if err != nil {
 		t.Fatalf("logger.New: %v", err)
 	}
 
 	// The watcher saves state after every check, into cfg.DataDir.
 	deps.state, err = state.New(fxtest.NewLifecycle(t), state.Params{
-		Logger: log,
+		Logger: deps.log,
 		Config: cfg,
 	})
 	if err != nil {
 		t.Fatalf("state.New: %v", err)
 	}
 
-	w := watcher.NewForTest(
-		deps.config,
-		deps.state,
-		resolver.NewFromLogger(slog.Default()),
-		deps.portChecker,
-		deps.tlsChecker,
-		deps.notifier,
-	)
-
-	return w, deps
+	return deps
 }
 
 func defaultTestConfig(t *testing.T) *config.Config {
@@ -196,8 +217,10 @@ 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.
+// state holds no address, or a configured domain's nameserver has no
+// address saved or still has oldIP, which the tests save and live DNS
+// never returns. 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,
@@ -221,48 +244,76 @@ func checkOnce(
 		}
 	}
 
+	for _, name := range deps.config.Domains {
+		ds, _ := deps.state.GetDomainState(name)
+		for _, ns := range ds.Nameservers {
+			ips := ds.NameserverAddresses[ns]
+			if len(ips) == 0 || slices.Contains(ips, oldIP) {
+				return fmt.Errorf(
+					"%s: nameserver %s: %w, or the watcher saved "+
+						"no fresh addresses for it",
+					name, ns, livednstest.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.
+// When the 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 {
+	prepare func(deps *testDeps),
+) (*watcher.Watcher, *testDeps) {
 	t.Helper()
 
-	var deps *testDeps
+	var (
+		w    *watcher.Watcher
+		deps *testDeps
+	)
 
 	livednstest.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
+	return w, deps
 }
 
-// addresses returns the A and AAAA values saved for a hostname.
+// lookupNameservers returns the nameservers live DNS lists for name,
+// for a test to save in the state its check starts from.
+func lookupNameservers(t *testing.T, name string) []string {
+	t.Helper()
+
+	res := resolver.NewFromLogger(slog.Default())
+
+	var nameservers []string
+
+	livednstest.Retry(t, "LookupNS("+name+")", func(ctx context.Context) error {
+		var err error
+
+		nameservers, err = res.LookupNS(ctx, name)
+
+		return err
+	})
+
+	return nameservers
+}
+
+// addresses returns the A and AAAA values saved for a hostname, and the
+// addresses saved at the end of its CNAME chain.
 func addresses(hs *state.HostnameState) []string {
 	var ips []string
 
@@ -271,7 +322,7 @@ func addresses(hs *state.HostnameState) []string {
 		ips = append(ips, nsState.Records["AAAA"]...)
 	}
 
-	return ips
+	return append(ips, hs.CNAMEAddresses...)
 }
 
 // assertNotified checks that a notification with this title and
@@ -314,13 +365,21 @@ func TestFirstRunBaseline(t *testing.T) {
 	t.Parallel()
 
 	cfg := defaultTestConfig(t)
-	cfg.Domains = []string{testDomain}
+	cfg.Domains = []string{testSmallDomain}
 	cfg.Hostnames = []string{testHost}
 
-	deps := runChecks(t, cfg, nil, nil)
+	_, deps := runChecks(t, cfg, nil)
 
 	assertNoNotifications(t, deps)
 	assertStatePopulated(t, deps)
+
+	// testHost answers with an address, so the check saves an empty list
+	// of CNAME addresses for it; nil would mean the check did not look
+	// at whether to follow a CNAME.
+	hs, _ := deps.state.GetHostnameState(testHost)
+	if hs.CNAMEAddresses == nil || len(hs.CNAMEAddresses) != 0 {
+		t.Errorf("saved CNAME addresses %#v, want []", hs.CNAMEAddresses)
+	}
 }
 
 func assertNoNotifications(
@@ -367,9 +426,9 @@ func TestDomainPortAndTLSChecks(t *testing.T) {
 	t.Parallel()
 
 	cfg := defaultTestConfig(t)
-	cfg.Domains = []string{testDomain}
+	cfg.Domains = []string{testSmallDomain}
 
-	deps := runChecks(t, cfg, nil, nil)
+	_, deps := runChecks(t, cfg, nil)
 
 	snap := deps.state.GetSnapshot()
 
@@ -406,38 +465,236 @@ func TestNSChangeDetection(t *testing.T) {
 	t.Parallel()
 
 	cfg := defaultTestConfig(t)
-	cfg.Domains = []string{testDomain}
+	cfg.Domains = []string{testSmallDomain}
 
 	// The saved state lists nameservers that live DNS does not.
-	deps := runChecks(t, cfg, func(deps *testDeps) {
-		deps.state.SetDomainState(testDomain, &state.DomainState{
+	_, deps := runChecks(t, cfg, func(deps *testDeps) {
+		deps.state.SetDomainState(testSmallDomain, &state.DomainState{
 			Nameservers: []string{oldNS1, oldNS2},
 		})
-	}, nil)
+	})
 
-	assertNotified(t, deps, "NS Change: "+testDomain, "warning")
+	assertNotified(t, deps, "NS Change: "+testSmallDomain, "warning")
 
-	ds, _ := deps.state.GetDomainState(testDomain)
+	ds, _ := deps.state.GetDomainState(testSmallDomain)
 	if slices.Contains(ds.Nameservers, oldNS1) {
 		t.Errorf("saved nameservers not updated: %v", ds.Nameservers)
 	}
 }
 
+// TestDomainThatDoesNotExist checks a .com domain that does not exist,
+// with nameservers and records saved by an earlier check. The .com
+// servers answer that it does not exist, so it is saved with nxdomain
+// set and no nameservers, an NS Change removes them all, and its saved
+// records are removed rather than asked for at the .com servers.
+func TestDomainThatDoesNotExist(t *testing.T) {
+	t.Parallel()
+
+	const domain = "dnswatcher-test-does-not-exist.com"
+
+	cfg := defaultTestConfig(t)
+	cfg.Domains = []string{domain}
+
+	var deps *testDeps
+
+	livednstest.Retry(t, "watcher checks", func(ctx context.Context) error {
+		var w *watcher.Watcher
+
+		w, deps = newTestWatcher(t, cfg)
+
+		deps.state.SetDomainState(domain, &state.DomainState{
+			Nameservers: []string{oldNS1, oldNS2},
+		})
+		deps.state.SetHostnameState(domain, &state.HostnameState{
+			RecordsByNameserver: map[string]*state.NameserverRecordState{
+				oldNS1: {
+					Records: map[string][]string{"A": {oldIP}},
+					Status:  "ok",
+				},
+			},
+		})
+
+		started := time.Now()
+
+		w.RunOnce(ctx)
+
+		// When no server answered, the domain's state is not saved.
+		ds, _ := deps.state.GetDomainState(domain)
+		if ds.LastChecked.Before(started) {
+			return fmt.Errorf("%s: %w", domain, livednstest.ErrNoAnswer)
+		}
+
+		return nil
+	})
+
+	ds, _ := deps.state.GetDomainState(domain)
+	if !ds.NXDomain || len(ds.Nameservers) != 0 {
+		t.Errorf("saved nxdomain %v and nameservers %v, want true and none",
+			ds.NXDomain, ds.Nameservers)
+	}
+
+	if hs, ok := deps.state.GetHostnameState(domain); ok {
+		t.Errorf("records saved for %s: %v", domain, hs.RecordsByNameserver)
+	}
+
+	assertNotified(t, deps, "NS Change: "+domain, "warning")
+
+	// That is the only notification, and it removes both nameservers,
+	// in either order.
+	for _, n := range deps.notifier.getNotifications() {
+		removed := strings.TrimPrefix(
+			n.Message, "Domain: "+domain+"\nAdded: \nRemoved: ",
+		)
+		if removed != oldNS1+", "+oldNS2 && removed != oldNS2+", "+oldNS1 {
+			t.Errorf("unexpected notification: %v", n)
+		}
+	}
+}
+
+// TestDomainWithNoDelegationOfItsOwn checks a domain with no delegation
+// of its own: codeberg.page is on the public suffix list, so
+// docs.codeberg.page is a domain, but the .page servers delegate only
+// codeberg.page, whose servers answer for it. It is saved with no
+// nameservers and without nxdomain, and its records, asked at the
+// codeberg.page servers, are saved. Those are testSmallDomain's two
+// nameservers; github.io, the zone of the README's example, has eight.
+func TestDomainWithNoDelegationOfItsOwn(t *testing.T) {
+	t.Parallel()
+
+	const domain = "docs.codeberg.page"
+
+	cfg := defaultTestConfig(t)
+	cfg.Domains = []string{domain}
+
+	var deps *testDeps
+
+	livednstest.Retry(t, "watcher checks", func(ctx context.Context) error {
+		var w *watcher.Watcher
+
+		w, deps = newTestWatcher(t, cfg)
+
+		err := checkOnce(ctx, w, deps)
+
+		// A domain saved as not existing has no records to wait for;
+		// the checks below fail on it.
+		if ds, ok := deps.state.GetDomainState(domain); ok && ds.NXDomain {
+			return nil
+		}
+
+		return err
+	})
+
+	ds, _ := deps.state.GetDomainState(domain)
+	if ds.NXDomain || len(ds.Nameservers) != 0 {
+		t.Errorf("saved nxdomain %v and nameservers %v, want false and none",
+			ds.NXDomain, ds.Nameservers)
+	}
+
+	if _, ok := deps.state.GetHostnameState(domain); !ok {
+		t.Errorf("no records saved for %s", domain)
+	}
+}
+
+func TestNSAddressChangeDetection(t *testing.T) {
+	t.Parallel()
+
+	cfg := defaultTestConfig(t)
+	cfg.Domains = []string{testSmallDomain}
+
+	nameservers := lookupNameservers(t, testSmallDomain)
+
+	// The saved state lists the nameservers live DNS lists, each at an
+	// address live DNS never returns.
+	_, deps := runChecks(t, cfg, func(deps *testDeps) {
+		nsAddresses := make(map[string][]string, len(nameservers))
+		for _, ns := range nameservers {
+			nsAddresses[ns] = []string{oldIP}
+		}
+
+		deps.state.SetDomainState(testSmallDomain, &state.DomainState{
+			Nameservers:         nameservers,
+			NameserverAddresses: nsAddresses,
+		})
+	})
+
+	title := "NS Address Change: " + testSmallDomain
+	ds, _ := deps.state.GetDomainState(testSmallDomain)
+
+	// One alert per nameserver, naming it and the address it had.
+	for _, ns := range ds.Nameservers {
+		prefix := "Domain: " + testSmallDomain + "\nNameserver: " + ns +
+			"\nOld: " + oldIP + "\nNew: "
+
+		sent := 0
+
+		for _, n := range deps.notifier.getNotifications() {
+			if n.Title == title && strings.HasPrefix(n.Message, prefix) {
+				sent++
+			}
+		}
+
+		if sent != 1 {
+			t.Errorf("sent %d address changes for %s, want 1", sent, ns)
+		}
+	}
+
+	if n := countNotifications(deps, title); n != len(ds.Nameservers) {
+		t.Errorf(
+			"sent %d address changes for %d nameservers",
+			n, len(ds.Nameservers),
+		)
+	}
+
+	if n := countNotifications(deps, "NS Change: "+testSmallDomain); n != 0 {
+		t.Errorf("sent %d NS changes, want 0", n)
+	}
+}
+
+func TestNSAddedAndRemovedIsNoAddressChange(t *testing.T) {
+	t.Parallel()
+
+	cfg := defaultTestConfig(t)
+	cfg.Domains = []string{testSmallDomain}
+
+	nameservers := lookupNameservers(t, testSmallDomain)
+
+	// The saved state lists oldNS1, which live DNS does not, in place of
+	// the first nameserver live DNS lists, so that the check finds that
+	// one added and oldNS1 removed. Only oldNS1 has addresses saved.
+	_, deps := runChecks(t, cfg, func(deps *testDeps) {
+		deps.state.SetDomainState(testSmallDomain, &state.DomainState{
+			Nameservers:         append([]string{oldNS1}, nameservers[1:]...),
+			NameserverAddresses: map[string][]string{oldNS1: {oldIP}},
+		})
+	})
+
+	if n := countNotifications(deps, "NS Change: "+testSmallDomain); n != 1 {
+		t.Errorf("sent %d NS changes, want 1", n)
+	}
+
+	title := "NS Address Change: " + testSmallDomain
+	if n := countNotifications(deps, title); n != 0 {
+		t.Errorf("sent %d address changes, want 0", n)
+	}
+}
+
 func TestRecordChangeDetection(t *testing.T) {
 	t.Parallel()
 
 	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}}
+	nameservers := lookupNameservers(t, testHost)
+
+	// The saved state has every nameserver live DNS lists answering
+	// with an address live DNS never returns.
+	_, deps := runChecks(t, cfg, func(deps *testDeps) {
+		byNameserver := make(map[string]*state.NameserverRecordState)
+		for _, ns := range nameservers {
+			byNameserver[ns] = answered(map[string][]string{"A": {oldIP}})
 		}
 
-		deps.state.SetHostnameState(testHost, hs)
+		deps.state.SetHostnameState(testHost, saved(byNameserver))
 	})
 
 	assertNotified(t, deps, "Record Change: "+testHost, "warning")
@@ -449,12 +706,15 @@ 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 := runChecks(t, cfg, nil)
+
+	// Every port closes, and the port checks run again. They look
+	// nothing up.
+	deps.portChecker.mu.Lock()
+	deps.portChecker.closed = true
+	deps.portChecker.mu.Unlock()
+
+	w.CheckAllPorts(t.Context())
 
 	hs, _ := deps.state.GetHostnameState(testHost)
 	assertNotified(
@@ -474,38 +734,59 @@ func TestTLSExpiryWarning(t *testing.T) {
 	cfg := defaultTestConfig(t)
 	cfg.Hostnames = []string{testHost}
 
-	deps := runChecks(t, cfg, expiresInThreeDays, nil)
+	_, deps := runChecks(t, cfg, expiresInThreeDays)
 
 	assertNotified(t, deps, "TLS Expiry Warning: "+testHost, "warning")
 }
 
-func TestTLSExpiryWarningDedup(t *testing.T) {
+// TestTLSExpiryWarningEachCheck runs the TLS checks three times in a
+// row on hostname and port state built here, for a certificate that
+// expires within the warning period. Each check warns once, whether the
+// TLS interval is a nanosecond, shorter than the time between two
+// checks, or a day, longer than it.
+func TestTLSExpiryWarningEachCheck(t *testing.T) {
 	t.Parallel()
 
-	cfg := defaultTestConfig(t)
-	cfg.Hostnames = []string{testHost}
-	cfg.TLSInterval = 24 * time.Hour
+	title := "TLS Expiry Warning: " + host
 
-	title := "TLS Expiry Warning: " + testHost
+	for _, interval := range []time.Duration{time.Nanosecond, 24 * time.Hour} {
+		t.Run(interval.String(), func(t *testing.T) {
+			t.Parallel()
 
-	// The second check comes within the TLS interval of the first,
-	// so it must not warn again.
-	var warnings int
+			cfg := defaultTestConfig(t)
+			cfg.Hostnames = []string{host}
+			cfg.TLSInterval = interval
 
-	deps := runChecks(t, cfg, expiresInThreeDays, func(deps *testDeps) {
-		warnings = countNotifications(deps, title)
-	})
+			// The TLS checks read the saved hostname and port state and
+			// look nothing up, so the watcher has no resolver.
+			deps := newTestDeps(t, cfg)
+			w := watcher.NewForTest(
+				cfg, deps.state, nil,
+				deps.portChecker, deps.tlsChecker, deps.notifier,
+			)
 
-	if warnings == 0 {
-		t.Fatal("expected expiry warnings from the first check")
-	}
+			expiresInThreeDays(deps)
+			deps.state.SetHostnameState(host, saved(
+				map[string]*state.NameserverRecordState{
+					nsA: answered(map[string][]string{"A": {ip1}}),
+				},
+			))
+			deps.state.SetPortState(ip1+":443", &state.PortState{
+				Open: true, Hostnames: []string{host},
+			})
 
-	got := countNotifications(deps, title)
-	if got != warnings {
-		t.Errorf(
-			"expected %d expiry warnings (dedup), got %d",
-			warnings, got,
-		)
+			for check := 1; check <= 3; check++ {
+				w.RunTLSChecks(t.Context())
+
+				got := countNotifications(deps, title)
+				if got != check {
+					t.Fatalf(
+						"after check %d: %d expiry warnings, want %d",
+						check, got, check,
+					)
+				}
+			}
+		})
 	}
 }
 
@@ -539,6 +820,85 @@ func TestGracefulShutdown(t *testing.T) {
 	}
 }
 
+// TestStopSavesState stops a watcher built by New the way fx stops it,
+// and checks that a change made to the state after the last check is in
+// the state file afterwards. The state's own stop hook never runs here,
+// so only the watcher can have saved it. Nothing is configured to
+// check, so no DNS is involved.
+func TestStopSavesState(t *testing.T) {
+	t.Parallel()
+
+	cfg := defaultTestConfig(t)
+	deps := newTestDeps(t, cfg)
+	lc := fxtest.NewLifecycle(t)
+
+	_, err := watcher.New(lc, watcher.Params{
+		Logger:    deps.log,
+		Config:    cfg,
+		State:     deps.state,
+		Resolver:  resolver.NewFromLogger(slog.Default()),
+		PortCheck: deps.portChecker,
+		TLSCheck:  deps.tlsChecker,
+		Notify:    deps.notifier,
+	})
+	if err != nil {
+		t.Fatalf("watcher.New: %v", err)
+	}
+
+	lc.RequireStart()
+
+	// The first check saves state once. Wait for that save before
+	// changing the state, so the change can reach the file only
+	// through the save made at stop.
+	deadline := time.Now().Add(5 * time.Second)
+
+	for {
+		_, err = os.Stat(cfg.StatePath())
+		if err == nil {
+			break
+		}
+
+		if time.Now().After(deadline) {
+			t.Fatalf("the first check saved no state: %v", err)
+		}
+
+		time.Sleep(10 * time.Millisecond)
+	}
+
+	deps.state.SetDomainState(testDomain, &state.DomainState{
+		Nameservers: []string{oldNS1},
+	})
+
+	ctx, cancel := context.WithTimeout(t.Context(), 5*time.Second)
+	defer cancel()
+
+	err = lc.Stop(ctx)
+	if err != nil {
+		t.Fatalf("stopping the watcher: %v", err)
+	}
+
+	saved, err := state.New(fxtest.NewLifecycle(t), state.Params{
+		Logger: deps.log,
+		Config: cfg,
+	})
+	if err != nil {
+		t.Fatalf("state.New: %v", err)
+	}
+
+	err = saved.Load()
+	if err != nil {
+		t.Fatalf("loading the state file: %v", err)
+	}
+
+	ds, ok := saved.GetDomainState(testDomain)
+	if !ok || !slices.Equal(ds.Nameservers, []string{oldNS1}) {
+		t.Errorf(
+			"state file after stop has %+v for %s, want nameservers %v",
+			ds, testDomain, []string{oldNS1},
+		)
+	}
+}
+
 func TestDNSRunsBeforePortAndTLSChecks(t *testing.T) {
 	t.Parallel()
 
@@ -546,7 +906,7 @@ func TestDNSRunsBeforePortAndTLSChecks(t *testing.T) {
 	cfg.Hostnames = []string{testHost}
 
 	// The saved state says the last check found testHost at oldIP.
-	deps := runChecks(t, cfg, func(deps *testDeps) {
+	_, deps := runChecks(t, cfg, func(deps *testDeps) {
 		deps.state.SetHostnameState(testHost, &state.HostnameState{
 			RecordsByNameserver: map[string]*state.NameserverRecordState{
 				oldNS1: {
@@ -555,7 +915,7 @@ func TestDNSRunsBeforePortAndTLSChecks(t *testing.T) {
 				},
 			},
 		})
-	}, nil)
+	})
 
 	snap := deps.state.GetSnapshot()
 
@@ -628,18 +988,27 @@ func TestSendTestNotification_ViaRun(t *testing.T) {
 
 	notifications := deps.notifier.getNotifications()
 
+	// No names are configured, so every count is 0.
+	wantMessage := "dnswatcher has started and completed its initial scan.\n" +
+		"Monitoring 0 domain(s) and 0 hostname(s).\n" +
+		"Tracking 0 port endpoint(s) and 0 TLS certificate(s).\n" +
+		"This is a test notification, sent to every configured " +
+		"notification endpoint."
+
 	found := false
 
 	for _, n := range notifications {
 		if n.Priority == "success" &&
-			n.Title == "✅ dnswatcher startup complete" {
+			n.Title == "✅ dnswatcher startup complete" &&
+			n.Message == wantMessage {
 			found = true
 		}
 	}
 
 	if !found {
 		t.Errorf(
-			"expected startup test notification, got: %v",
+			"expected startup test notification with message %q, got: %v",
+			wantMessage,
 			notifications,
 		)
 	}
@@ -686,22 +1055,28 @@ 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"
+	nameservers := lookupNameservers(t, testHost)
+
+	// The saved state has every nameserver live DNS lists as one that
+	// did not answer, and, as answering, one that live DNS does not
+	// list, which then disappears.
+	_, deps := runChecks(t, cfg, func(deps *testDeps) {
+		byNameserver := map[string]*state.NameserverRecordState{
+			oldNS1: answered(map[string][]string{"A": {oldIP}}),
+		}
+		for _, ns := range nameservers {
+			byNameserver[ns] = failed()
 		}
 
-		hs.RecordsByNameserver[oldNS1] = &state.NameserverRecordState{
-			Records: map[string][]string{"A": {oldIP}},
-			Status:  "ok",
-		}
-
-		deps.state.SetHostnameState(testHost, hs)
+		deps.state.SetHostnameState(testHost, saved(byNameserver))
 	})
 
 	assertNotified(t, deps, "NS Failure: "+testHost, "error")
 	assertNotified(t, deps, "NS Recovery: "+testHost, "success")
+
+	// A nameserver that did not answer has no records to compare, so
+	// its recovery is not also a record change.
+	if n := countNotifications(deps, "Record Change: "+testHost); n != 0 {
+		t.Errorf("sent %d record changes on recovery, want 0", n)
+	}
 }

package.json

@@ -0,0 +1,9 @@
+{
+    "name": "dnswatcher-tooling",
+    "version": "0.0.0",
+    "private": true,
+    "description": "Pins the prettier that script/fmt and script/fmt-check run against this repo's markdown. Not a JavaScript project; nothing here is imported, published, or shipped.",
+    "devDependencies": {
+        "prettier": "3.9.6"
+    }
+}

script/bootstrap

@@ -3,20 +3,16 @@
 # this repo. Idempotent: every install is guarded by a check so already
 # installed tools are skipped. Base tooling comes from nix, apt, brew,
 # or apk (detected in that order); assumes nothing is present.
-# goimports is installed via `go install` at a pinned commit (never
-# "latest") because script/fmt runs it on the host; script/fmt-check
-# does not (it runs gofmt only).
+# goimports is not installed here: script/fmt and script/fmt-check-go
+# run it with `go run` at a pinned commit.
 # The linter is NOT installed here: golangci-lint runs via docker only
 # (script/lint), pinned by image digest, so its only prerequisite is a
-# working docker.
+# working docker. Nor is prettier: script/fmt and
+# script/fmt-check-markdown run it in a container from Dockerfile.fmt.
 set -eu
 
 ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
 
-# Pinned version, 2026-08-07 (same pin as the Dockerfile)
-# goimports v0.42.0
-GOIMPORTS_REF="golang.org/x/tools/cmd/goimports@009367f5c17a8d4c45a961a3a509277190a9a6f0"
-
 PKGMGR=""
 SUDO=""
 APT_UPDATED=""
@@ -71,15 +67,12 @@ main() {
     if missing make; then pkg_install gnumake make make make; fi
     if missing go; then pkg_install go golang go go; fi
 
-    # Format tools, pinned via go install (installs into
-    # "$(go env GOPATH)/bin"; ensure that is on your PATH).
-    if missing goimports; then go install "$GOIMPORTS_REF"; fi
-
-    # Linting runs via docker only (script/lint). Warn, don't fail:
-    # everything except `make lint` works without it.
+    # Linting and the markdown formatter run via docker only. Warn,
+    # don't fail: building and testing work without it.
     if missing docker; then
         echo "bootstrap: WARNING: docker not found; install it to" \
-            "run make lint and make docker." >&2
+            "run make lint, make fmt, make fmt-check, make check" \
+            "and make docker." >&2
     fi
 
     go mod download

script/cibuild

@@ -1,18 +1,23 @@
 #!/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.
+# the Go half of make fmt-check and golangci-lint; its builder stage
+# runs make test and make build. The markdown half of make fmt-check
+# runs after that build, as its own build of Dockerfile.fmt, because
+# there is no docker inside a docker 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.
+# without linting or querying live DNS. script/fmt-check-markdown busts
+# its own cache the same way.
 set -eu
 
-ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
+ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
 
 main() {
     cd "$ROOT"
     docker build --no-cache-filter=lint,builder .
+    "$SCRIPT_DIR/fmt-check-markdown"
 }
 
 main "$@"

script/docker

@@ -14,8 +14,8 @@ main() {
     cd "$ROOT"
     # Own line: a failing command substitution inside an argument does
     # not trip `set -e`, so the inline form degrades silently to an
-    # empty constant. VERSION is computed here because .dockerignore
-    # excludes .git, so `git describe` in a build stage cannot find it.
+    # empty constant. The VERSION build arg takes precedence over what
+    # the build would derive from the .git in its context.
     version="$(git describe --tags --always --dirty 2>/dev/null || true)"
     [ -n "$version" ] || version="unknown"
     docker build --no-cache-filter=lint,builder \

script/fmt

@@ -1,13 +1,65 @@
 #!/bin/sh
-# script/fmt: format all files (writes).
+# script/fmt: format all files (writes). Go with gofmt and goimports on
+# the host, markdown with the prettier pinned by Dockerfile.fmt.
+#
+# goimports runs with `go run` at a pinned commit, never from PATH, so
+# every machine formats with the same version and nothing installs it.
+#
+# The markdown pass is a `docker build --output type=local` rather than a
+# `docker run -v`, so it needs no bind mount and behaves the same against
+# a remote daemon; the formatted documents come back out of the build and
+# are copied over the tree here.
+#
+# Unlike script/fmt-check-markdown this does not bust the cache: it is
+# not a gate, and any edit to a document changes the COPY layer above the
+# prettier step, so a cached result is a result over this exact tree.
 set -eu
 
 ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
 
+# goimports v0.42.0, 2026-08-07. Must match script/fmt-check-go.
+GOIMPORTS_REF="golang.org/x/tools/cmd/goimports@009367f5c17a8d4c45a961a3a509277190a9a6f0"
+
+# Must match the export stage name in Dockerfile.fmt.
+stage=fmt-out
+
+die() {
+    echo "script/fmt: $*" >&2
+    exit 1
+}
+
 main() {
     cd "$ROOT"
     gofmt -s -w .
-    goimports -w .
+    go run "$GOIMPORTS_REF" -w .
+
+    tmp="$(mktemp -d "${TMPDIR:-/tmp}/dnswatcher-fmt.XXXXXX")"
+    trap 'rm -rf "$tmp"' EXIT INT TERM
+
+    docker build \
+        --target "$stage" \
+        --output "type=local,dest=$tmp/out" \
+        -f Dockerfile.fmt .
+
+    # An empty export means prettier was handed nothing, which must not
+    # read as "already formatted".
+    (cd "$tmp/out" && find . -type f -name '*.md') |
+        sed 's|^\./||' | LC_ALL=C sort >"$tmp/files"
+
+    [ -s "$tmp/files" ] ||
+        die "the formatting build produced no markdown; the build" \
+            "context reached prettier empty"
+
+    # Copied only where the bytes differ, so an already-formatted tree
+    # keeps its timestamps and says nothing.
+    while IFS= read -r f; do
+        [ -n "$f" ] || continue
+        if [ -f "$f" ] && cmp -s "$tmp/out/$f" "$f"; then
+            continue
+        fi
+        cp "$tmp/out/$f" "$f"
+        echo "prettier: reformatted $f"
+    done <"$tmp/files"
 }
 
 main "$@"

script/fmt-check

@@ -1,18 +1,14 @@
 #!/bin/sh
-# script/fmt-check: check formatting (read-only). Same scope as
-# script/fmt, but fails instead of writing.
+# script/fmt-check: check formatting (read-only). Same tools and scope
+# as script/fmt, but fails instead of writing: the Go on the host, the
+# markdown with prettier in a container.
 set -eu
 
-ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
 
 main() {
-    cd "$ROOT"
-    files="$(gofmt -l .)"
-    if [ -n "$files" ]; then
-        echo "gofmt: files not formatted:" >&2
-        echo "$files" >&2
-        exit 1
-    fi
+    "$SCRIPT_DIR/fmt-check-go"
+    "$SCRIPT_DIR/fmt-check-markdown"
 }
 
 main "$@"

script/fmt-check-go

@@ -0,0 +1,31 @@
+#!/bin/sh
+# script/fmt-check-go: fail unless every Go source is formatted the way
+# script/fmt would leave it, and name the files that are not. Read-only.
+#
+# Its own script because the Dockerfile's lint stage runs this half
+# alone: there is no docker inside a docker build to run the markdown
+# half in.
+set -eu
+
+ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
+
+# goimports v0.42.0, 2026-08-07. Must match script/fmt.
+GOIMPORTS_REF="golang.org/x/tools/cmd/goimports@009367f5c17a8d4c45a961a3a509277190a9a6f0"
+
+main() {
+    cd "$ROOT"
+    files="$(gofmt -s -l .)"
+    if [ -n "$files" ]; then
+        echo "gofmt: files not formatted:" >&2
+        echo "$files" >&2
+        exit 1
+    fi
+    files="$(go run "$GOIMPORTS_REF" -l .)"
+    if [ -n "$files" ]; then
+        echo "goimports: files not formatted:" >&2
+        echo "$files" >&2
+        exit 1
+    fi
+}
+
+main "$@"

script/fmt-check-markdown

@@ -0,0 +1,29 @@
+#!/bin/sh
+# script/fmt-check-markdown: fail unless every .md is formatted the way
+# script/fmt would leave it. Read-only.
+#
+# prettier is never installed on the host: it runs in a container built
+# from Dockerfile.fmt, pinned by package.json and yarn.lock.
+# --no-cache-filter is here for the reason script/lint gives: a cached
+# build checks nothing.
+#
+# Its own script because script/cibuild runs this half alone, after the
+# Dockerfile's lint stage has checked the Go.
+set -eu
+
+ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
+
+# Must match the markdown check stage name in Dockerfile.fmt.
+stage=fmt-check
+
+main() {
+    cd "$ROOT"
+    docker build \
+        --progress=plain \
+        --no-cache-filter="$stage" \
+        --target "$stage" \
+        -f Dockerfile.fmt \
+        .
+}
+
+main "$@"

yarn.lock

@@ -0,0 +1,8 @@
+# THIS IS AN AUTOGENERATED FILE. DO NOT EDIT THIS FILE DIRECTLY.
+# yarn lockfile v1
+
+
+prettier@3.9.6:
+  version "3.9.6"
+  resolved "https://registry.yarnpkg.com/prettier/-/prettier-3.9.6.tgz#b3ea5146515d40fc53f18aa63f74dfab1e10dbf6"
+  integrity sha512-OpN0zzVdiaiAhxpuuj5efpIS4sY9j7bY6uR5mnj5yPzGkdkjNKSJeUThPb60Jw29QuAZgA4o+/iB49kFiaBX6g==