TODO.md

@@ -19,6 +19,8 @@ trial run of the finished image: https://git.eeqj.de/sneak/dnswatcher/issues/149
 
 # Completed Steps
 
+- 2026-10-13: a check saving the state while the dashboard or `/api/v1/status`
+  is read cannot crash the process (closes #261).
 - 2026-10-06: canonical files re-fetched from `sneak/prompts` at `dd4027b`; lint
   and test are phases of the `Dockerfile`, every scripted build uncached (closes
   #257).

internal/state/state.go

@@ -6,6 +6,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"log/slog"
+	"maps"
 	"os"
 	"path/filepath"
 	"slices"
@@ -270,12 +271,21 @@ func (s *State) Save() error {
 	return nil
 }
 
-// GetSnapshot returns a copy of the current snapshot.
+// GetSnapshot returns a copy of the current snapshot, with copies of
+// its maps, so that a caller can range over them while the state is
+// written. The entries in the maps are not copied: an entry saved in the
+// state must be replaced, never changed in place.
 func (s *State) GetSnapshot() Snapshot {
 	s.mu.RLock()
 	defer s.mu.RUnlock()
 
-	return *s.snapshot
+	snap := *s.snapshot
+	snap.Domains = maps.Clone(snap.Domains)
+	snap.Hostnames = maps.Clone(snap.Hostnames)
+	snap.Ports = maps.Clone(snap.Ports)
+	snap.Certificates = maps.Clone(snap.Certificates)
+
+	return snap
 }
 
 // SetDomainState updates the state for a domain.

internal/state/state_test.go

@@ -995,7 +995,8 @@ func TestPortStateUnmarshalJSON_BothFormats(t *testing.T) {
 	}
 }
 
-// TestGetSnapshot_ReturnsCopy verifies that GetSnapshot returns a value copy.
+// TestGetSnapshot_ReturnsCopy verifies that the maps in the snapshot
+// GetSnapshot returns are not the state's own.
 func TestGetSnapshot_ReturnsCopy(t *testing.T) {
 	t.Parallel()
 
@@ -1005,15 +1006,67 @@ func TestGetSnapshot_ReturnsCopy(t *testing.T) {
 
 	snap := s.GetSnapshot()
 
-	// Mutate the returned snapshot's map.
-	snap.Domains["mutated.example.com"] = &state.DomainState{
-		Nameservers: []string{"ns1.mutated.com."},
+	const added = "added.example.com"
+
+	snap.Domains[added] = &state.DomainState{}
+	snap.Hostnames[added] = &state.HostnameState{}
+	snap.Ports[added] = &state.PortState{}
+	snap.Certificates[added] = &state.CertificateState{}
+
+	if _, ok := s.GetDomainState(added); ok {
+		t.Error("the snapshot's Domains map is the state's own")
 	}
 
-	// The original domain data should still be accessible.
-	_, ok := s.GetDomainState("example.com")
-	if !ok {
-		t.Error("original domain should still exist")
+	if _, ok := s.GetHostnameState(added); ok {
+		t.Error("the snapshot's Hostnames map is the state's own")
+	}
+
+	if _, ok := s.GetPortState(added); ok {
+		t.Error("the snapshot's Ports map is the state's own")
+	}
+
+	if _, ok := s.GetCertificateState(added); ok {
+		t.Error("the snapshot's Certificates map is the state's own")
+	}
+}
+
+// TestGetSnapshot_WhileWritten ranges over snapshots while another
+// goroutine writes the state, as the dashboard does while a check runs.
+// Under -race it fails when a snapshot's maps are the state's own.
+func TestGetSnapshot_WhileWritten(t *testing.T) {
+	t.Parallel()
+
+	s := state.NewForTestWithDataDir(t.TempDir())
+
+	const writes = 1000
+
+	written := make(chan struct{})
+
+	go func() {
+		defer close(written)
+
+		for range writes {
+			s.SetDomainState("example.com", &state.DomainState{})
+			s.SetHostnameState(testHostname, &state.HostnameState{})
+			s.SetPortState(testIPv4+":443", &state.PortState{})
+			s.SetCertificateState(
+				testIPv4+":443:"+testHostname, &state.CertificateState{},
+			)
+		}
+	}()
+
+	for {
+		select {
+		case <-written:
+			return
+		default:
+		}
+
+		// json.Marshal ranges over each of the snapshot's maps.
+		_, err := json.Marshal(s.GetSnapshot())
+		if err != nil {
+			t.Fatal(err)
+		}
 	}
 }