metrics: rate limit /metrics per client address before Basic Auth (closes #101)

/metrics is behind a password, and REPO_POLICIES.md requires rate
limiting on password logins. Each client address may now send it 30
requests a minute, counted by httprate before Basic Auth, so failed
logins use up the allowance and a request over it gets 429 without
the password being checked. The address is the one the existing
trusted-proxy logic in internal/middleware works out, with IPv6
addresses grouped by /64; an IPv4 address a proxy reports in
IPv6-mapped form counts as the plain IPv4 address. A Prometheus
server scraping every 15 seconds sends 4 requests a minute.

Model: opus-5-5

Dockerfile

@@ -34,8 +34,11 @@ COPY . .
 # Run the tests - build fails if any test fails
 RUN make test
 
-# Build the binary
+# Build the binary. .dockerignore leaves out .git, so `git describe` in
-RUN make build
+# 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}"
 
 # Runtime stage
 # alpine 3.21, 2026-02-28

Makefile

@@ -1,6 +1,8 @@
 .PHONY: all bootstrap setup build 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 := $(shell git describe --tags --always --dirty 2>/dev/null || echo "dev")
 LDFLAGS := -X main.Version=$(VERSION)
 

README.md

@@ -489,7 +489,8 @@ them. We provide:
 - `script/check` — run test, lint, and fmt-check
 - `script/docker` — build the Docker image tagged via `script/projectname`, with
   `--no-cache-filter=lint,builder` so the lint stage and the builder stage,
-  which runs the tests, run on every invocation
+  which runs the tests, run on every invocation, and with the version from
+  `git describe` passed as `--build-arg VERSION`
 - `script/cibuild` — CI entrypoint: `docker build` with
   `--no-cache-filter=lint,builder`, so the lint stage and the builder stage,
   which runs the tests, run on every invocation, because a cached build lints
@@ -511,11 +512,14 @@ make clean      # Remove build artifacts
 
 ### Build-Time Variables
 
-Version is injected via `-ldflags`:
+`make build` sets the version with `-ldflags "-X main.Version=..."`, taking
+it from `git describe --tags --always --dirty`, or from `VERSION` when given
+on the command line (`make build VERSION=1.2.3`). The version appears in the
+startup log and in the health check response.
 
-```sh
+The Docker image has no `.git`, so the `Dockerfile` takes the version as
-go build -ldflags "-X main.Version=$(git describe --tags --always)" ./cmd/dnswatcher
+`--build-arg VERSION`. `make docker` passes it; a plain `docker build`
-```
+passes none, and that image reports `dev`.
 
 ---
 

TODO.md

@@ -22,6 +22,10 @@ https://git.eeqj.de/sneak/dnswatcher/issues/104
 
 - 2026-10-01: `/metrics` allows each client address 30 requests a minute,
   counted before Basic Auth, and answers 429 beyond that (closes #101).
+- 2026-10-01: the image built by `make docker` reports the `git describe`
+  version, not `dev`, and the startup log now shows it (closes #109).
+- 2026-10-01: two notify shutdown tests always release the delivery they hold,
+  so a drain that returns early fails them instead of hanging (closes #176).
 - 2026-10-01: `script/install-precommit` asks git for the repository's git
   directory, so `make hooks` also works where `.git` is a file (closes #129).
 - 2026-10-01: `TODO.md` brought up to date: open issues listed by URL, every
@@ -95,7 +99,6 @@ https://git.eeqj.de/sneak/dnswatcher/issues/104
   https://git.eeqj.de/sneak/dnswatcher/issues/107
 - invalid DNS or TLS interval silently replaced by the default:
   https://git.eeqj.de/sneak/dnswatcher/issues/177
-- images report version `dev`: https://git.eeqj.de/sneak/dnswatcher/issues/109
 - 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:
@@ -103,8 +106,6 @@ https://git.eeqj.de/sneak/dnswatcher/issues/104
 - `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
-- `internal/notify` shutdown tests hang when a drain returns early:
-  https://git.eeqj.de/sneak/dnswatcher/issues/176
 - README accuracy sweep: https://git.eeqj.de/sneak/dnswatcher/issues/108
 - README sections required by policy:
   https://git.eeqj.de/sneak/dnswatcher/issues/173

cmd/dnswatcher/main.go

@@ -63,6 +63,7 @@ func main() {
 				return n
 			},
 		),
+		fx.Invoke(func(l *logger.Logger) { l.Identify() }),
 		fx.Invoke(func(*server.Server, *watcher.Watcher) {}),
 	).Run()
 }

internal/notify/shutdown_test.go

@@ -143,6 +143,12 @@ func TestDrainWaitsForInFlightDelivery(t *testing.T) {
 	srv := blockingNtfyServer(entered, release, &served)
 	defer srv.Close()
 
+	// srv.Close waits for the handler, so release it however the
+	// test ends; otherwise a drain that returns early hangs the
+	// package instead of failing this test.
+	releaseHandler := sync.OnceFunc(func() { close(release) })
+	defer releaseHandler()
+
 	topicURL, _ := url.Parse(srv.URL)
 
 	svc := notify.NewTestService(http.DefaultTransport)
@@ -167,9 +173,7 @@ func TestDrainWaitsForInFlightDelivery(t *testing.T) {
 	// delay alone.
 	start := time.Now()
 
-	timer := time.AfterFunc(inFlightHold, func() {
+	timer := time.AfterFunc(inFlightHold, releaseHandler)
-		close(release)
-	})
 	defer timer.Stop()
 
 	ctx, cancel := context.WithTimeout(
@@ -268,7 +272,7 @@ func TestDrainBoundedByContextDeadline(t *testing.T) {
 	// all never returns here (the delivery is parked in a backoff
 	// that never fires), so an unbounded drain must fail this
 	// test promptly instead of hanging the package until the test
-	// binary's 30s timeout.
+	// binary's -timeout.
 	returned := make(chan struct{})
 
 	go func() {
@@ -447,6 +451,11 @@ func TestNewRegistersDrainingStopHook(t *testing.T) {
 	srv := blockingNtfyServer(entered, release, &served)
 	defer srv.Close()
 
+	// As in TestDrainWaitsForInFlightDelivery: release the handler
+	// however the test ends, before srv.Close waits for it.
+	releaseHandler := sync.OnceFunc(func() { close(release) })
+	defer releaseHandler()
+
 	lifecycle := &recordingLifecycle{}
 	svc := newNotifyService(t, lifecycle, srv.URL)
 
@@ -472,9 +481,7 @@ func TestNewRegistersDrainingStopHook(t *testing.T) {
 		t.Fatal("delivery never reached the endpoint")
 	}
 
-	timer := time.AfterFunc(inFlightHold, func() {
+	timer := time.AfterFunc(inFlightHold, releaseHandler)
-		close(release)
-	})
 	defer timer.Stop()
 
 	ctx, cancel := context.WithTimeout(

script/docker

@@ -12,7 +12,15 @@ ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
 
 main() {
     cd "$ROOT"
-    docker build --no-cache-filter=lint,builder -t "$("$SCRIPT_DIR/projectname")" .
+    # Own line: a failing command substitution inside an argument does
+    # not trip `set -e`, so the inline form degrades silently to an
+    # empty constant. VERSION is computed here because .dockerignore
+    # excludes .git, so `git describe` in a build stage cannot find it.
+    version="$(git describe --tags --always --dirty 2>/dev/null || true)"
+    [ -n "$version" ] || version="unknown"
+    docker build --no-cache-filter=lint,builder \
+        --build-arg VERSION="$version" \
+        -t "$("$SCRIPT_DIR/projectname")" .
 }
 
 main "$@"