Answer image requests with 503 in maintenance mode (closes #71)

maintenance_mode was only reported by the health check; every request
was still served. One middleware in routes.go, applied to /v1/image/
and /v1/e/ only, now answers them with 503, a Retry-After of
MaintenanceRetryAfterSeconds and the JSON error body while it is on.
It calls Server.MaintenanceMode(), which had no caller.

The health check stays 200 and reports maintenance_mode: the image's
Docker HEALTHCHECK requests it, a 503 there would make the container
unhealthy, and upaas marks a deploy failed when its container is
unhealthy. The login and URL generator pages and /metrics keep working.
Documented in README.md and config.example.yml.

Model: opus-5-5

internal/server/maintenance_internal_test.go

@@ -0,0 +1,169 @@
+package server
+
+import (
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"strconv"
+	"testing"
+
+	"sneak.berlin/go/pixa/internal/healthcheck"
+)
+
+// unsignedImagePath is an image URL that carries no signature.
+const unsignedImagePath = "/v1/image/cdn.example.com/cat.jpg/100x100.jpeg"
+
+// TestMaintenanceModeRefusesImageRequests verifies that while maintenance
+// mode is on, both image routes answer 503 Service Unavailable with a
+// Retry-After header and the JSON error body the image handlers send.
+func TestMaintenanceModeRefusesImageRequests(t *testing.T) {
+	t.Parallel()
+
+	s := newTestServer(t)
+	s.config.MaintenanceMode = true
+
+	requests := []struct {
+		method string
+		path   string
+	}{
+		{http.MethodGet, unsignedImagePath},
+		{http.MethodHead, unsignedImagePath},
+		{http.MethodGet, "/v1/e/token/cat.jpg"},
+	}
+
+	for _, tc := range requests {
+		t.Run(tc.method+" "+tc.path, func(t *testing.T) {
+			t.Parallel()
+
+			rec := httptest.NewRecorder()
+			s.ServeHTTP(rec, httptest.NewRequestWithContext(
+				t.Context(), tc.method, tc.path, nil))
+			t.Logf("status %d, body %s", rec.Code, rec.Body.String())
+
+			if rec.Code != http.StatusServiceUnavailable {
+				t.Fatalf("status = %d, want %d",
+					rec.Code, http.StatusServiceUnavailable)
+			}
+
+			retryAfter := rec.Header().Get("Retry-After")
+
+			seconds, err := strconv.Atoi(retryAfter)
+			if err != nil || seconds <= 0 {
+				t.Errorf("Retry-After = %q, want a positive number of seconds",
+					retryAfter)
+			}
+
+			// A HEAD response carries no body.
+			if tc.method == http.MethodHead {
+				return
+			}
+
+			var body struct {
+				Error     string `json:"error"`
+				Status    int    `json:"status"`
+				Timestamp string `json:"timestamp"`
+			}
+
+			err = json.NewDecoder(rec.Body).Decode(&body)
+			if err != nil {
+				t.Fatalf("body is not JSON: %v", err)
+			}
+
+			if body.Error == "" || body.Status != http.StatusServiceUnavailable ||
+				body.Timestamp == "" {
+				t.Errorf("body = %+v, want an error, status %d and a timestamp",
+					body, http.StatusServiceUnavailable)
+			}
+		})
+	}
+}
+
+// TestImageRequestsServedWithoutMaintenanceMode verifies that while
+// maintenance mode is off, image requests reach the image handlers instead
+// of the 503. The handlers refuse an unsigned image URL with 401 and a token
+// they cannot decrypt with 400, so either status shows a request got through.
+func TestImageRequestsServedWithoutMaintenanceMode(t *testing.T) {
+	t.Parallel()
+
+	s := newTestServer(t)
+	s.config.MaintenanceMode = false
+
+	requests := []struct {
+		method string
+		path   string
+		want   int
+	}{
+		{http.MethodGet, unsignedImagePath, http.StatusUnauthorized},
+		{http.MethodHead, unsignedImagePath, http.StatusUnauthorized},
+		{http.MethodGet, "/v1/e/token/cat.jpg", http.StatusBadRequest},
+	}
+
+	for _, tc := range requests {
+		t.Run(tc.method+" "+tc.path, func(t *testing.T) {
+			t.Parallel()
+
+			rec := httptest.NewRecorder()
+			s.ServeHTTP(rec, httptest.NewRequestWithContext(
+				t.Context(), tc.method, tc.path, nil))
+			t.Logf("status %d, body %s", rec.Code, rec.Body.String())
+
+			if rec.Code != tc.want {
+				t.Errorf("status = %d, want %d from the image handler",
+					rec.Code, tc.want)
+			}
+		})
+	}
+}
+
+// TestMaintenanceModeKeepsOtherRoutes verifies that while maintenance mode
+// is on, the health check still answers 200 and reports it, and the login
+// page and /metrics still answer 200. The image's Docker HEALTHCHECK
+// requests the health check: a 503 there would make the container
+// unhealthy, and upaas marks a deploy failed when its container is
+// unhealthy.
+func TestMaintenanceModeKeepsOtherRoutes(t *testing.T) {
+	t.Parallel()
+
+	s := newTestServer(t)
+	s.config.MaintenanceMode = true
+
+	// /metrics is routed only when its username is set.
+	s.config.MetricsUsername = "metrics"
+	s.config.MetricsPassword = "metrics-password"
+	s.SetupRoutes()
+
+	rec := httptest.NewRecorder()
+	s.ServeHTTP(rec, httptest.NewRequestWithContext(t.Context(),
+		http.MethodGet, "/.well-known/healthcheck.json", nil))
+	t.Logf("health check status %d, body %s", rec.Code, rec.Body.String())
+
+	if rec.Code != http.StatusOK {
+		t.Fatalf("health check status = %d, want %d", rec.Code, http.StatusOK)
+	}
+
+	var health healthcheck.Response
+
+	err := json.NewDecoder(rec.Body).Decode(&health)
+	if err != nil || !health.Maintenance {
+		t.Errorf("health check maintenance_mode = %v (error %v), want true",
+			health.Maintenance, err)
+	}
+
+	rec = httptest.NewRecorder()
+	s.ServeHTTP(rec, clientRequest(t, http.MethodGet, nil, firstClient, ""))
+
+	if rec.Code != http.StatusOK {
+		t.Errorf("login page status = %d, want %d", rec.Code, http.StatusOK)
+	}
+
+	req := httptest.NewRequestWithContext(t.Context(),
+		http.MethodGet, "/metrics", nil)
+	req.SetBasicAuth(s.config.MetricsUsername, s.config.MetricsPassword)
+
+	rec = httptest.NewRecorder()
+	s.ServeHTTP(rec, req)
+
+	if rec.Code != http.StatusOK {
+		t.Errorf("/metrics status = %d, want %d", rec.Code, http.StatusOK)
+	}
+}