Reconnect when RIS Live ends or stalls the stream (closes #53)

When RIS Live ended the response normally, the reconnect loop stopped for good and the health check kept reporting the feed connected; a connection that stayed open but sent nothing blocked forever. Now only `Stop` ends the loop: any other end clears the connected flag and reconnects with the existing backoff. If no line arrives for 60 seconds, including while waiting for RIS Live to answer the request, the streamer drops the connection and reconnects. Tests use a local fake server. README "Reconnection" describes both.

Model: opus-5-5

internal/database/database.go

@@ -1632,16 +1632,17 @@ func (d *Database) GetASPeersContext(ctx context.Context, asn int) ([]ASPeer, er
 }
 
 // GetPrefixDetails returns detailed information about a prefix
-func (d *Database) GetPrefixDetails(prefix string) ([]LiveRoute, error) {
+func (d *Database) GetPrefixDetails(prefix string) ([]LiveRoute, map[int]ASN, error) {
 	return d.GetPrefixDetailsContext(context.Background(), prefix)
 }
 
-// GetPrefixDetailsContext returns detailed information about a prefix with context support
-func (d *Database) GetPrefixDetailsContext(ctx context.Context, prefix string) ([]LiveRoute, error) {
+// GetPrefixDetailsContext returns the live routes for a prefix and, keyed by
+// AS number, the handle and description of each AS that originates it.
+func (d *Database) GetPrefixDetailsContext(ctx context.Context, prefix string) ([]LiveRoute, map[int]ASN, error) {
 	// Determine if it's IPv4 or IPv6 by parsing the prefix
 	_, ipnet, err := net.ParseCIDR(prefix)
 	if err != nil {
-		return nil, fmt.Errorf("invalid prefix format: %w", err)
+		return nil, nil, fmt.Errorf("invalid prefix format: %w", err)
 	}
 
 	tableName := "live_routes_v4"
@@ -1663,11 +1664,12 @@ func (d *Database) GetPrefixDetailsContext(ctx context.Context, prefix string) (
 
 	rows, err := d.db.QueryContext(ctx, query, prefix)
 	if err != nil {
-		return nil, fmt.Errorf("failed to query prefix details: %w", err)
+		return nil, nil, fmt.Errorf("failed to query prefix details: %w", err)
 	}
 	defer func() { _ = rows.Close() }()
 
 	var routes []LiveRoute
+	origins := make(map[int]ASN)
 	for rows.Next() {
 		var route LiveRoute
 		var pathJSON string
@@ -1690,13 +1692,18 @@ func (d *Database) GetPrefixDetailsContext(ctx context.Context, prefix string) (
 		route.IPVersion = ipVersion
 		route.MaskLength, _ = ipnet.Mask.Size()
 		routes = append(routes, route)
+		origins[route.OriginASN] = ASN{
+			ASN:         route.OriginASN,
+			Handle:      handle.String,
+			Description: description.String,
+		}
 	}
 
 	if len(routes) == 0 {
-		return nil, fmt.Errorf("%w: %s", ErrNoRoute, prefix)
+		return nil, nil, fmt.Errorf("%w: %s", ErrNoRoute, prefix)
 	}
 
-	return routes, nil
+	return routes, origins, nil
 }
 
 // GetRandomPrefixesByLength returns a random sample of prefixes with the specified mask length

internal/database/interface.go

@@ -76,8 +76,8 @@ type Store interface {
 	GetASDetailsContext(ctx context.Context, asn int) (*ASN, []LiveRoute, error)
 	GetASPeers(asn int) ([]ASPeer, error)
 	GetASPeersContext(ctx context.Context, asn int) ([]ASPeer, error)
-	GetPrefixDetails(prefix string) ([]LiveRoute, error)
-	GetPrefixDetailsContext(ctx context.Context, prefix string) ([]LiveRoute, error)
+	GetPrefixDetails(prefix string) ([]LiveRoute, map[int]ASN, error)
+	GetPrefixDetailsContext(ctx context.Context, prefix string) ([]LiveRoute, map[int]ASN, error)
 	GetRandomPrefixesByLength(maskLength, ipVersion, limit int) ([]LiveRoute, error)
 	GetRandomPrefixesByLengthContext(ctx context.Context, maskLength, ipVersion, limit int) ([]LiveRoute, error)
 

internal/routewatch/app_integration_test.go

@@ -252,13 +252,15 @@ func (m *mockStore) GetASDetailsContext(ctx context.Context, asn int) (*database
 }
 
 // GetPrefixDetails mock implementation
-func (m *mockStore) GetPrefixDetails(prefix string) ([]database.LiveRoute, error) {
+func (m *mockStore) GetPrefixDetails(prefix string) ([]database.LiveRoute, map[int]database.ASN, error) {
 	// Return empty routes for now
-	return []database.LiveRoute{}, nil
+	return []database.LiveRoute{}, map[int]database.ASN{}, nil
 }
 
 // GetPrefixDetailsContext mock implementation with context support
-func (m *mockStore) GetPrefixDetailsContext(ctx context.Context, prefix string) ([]database.LiveRoute, error) {
+func (m *mockStore) GetPrefixDetailsContext(
+	ctx context.Context, prefix string,
+) ([]database.LiveRoute, map[int]database.ASN, error) {
 	return m.GetPrefixDetails(prefix)
 }
 

internal/routewatch/cli.go

@@ -20,6 +20,8 @@ const (
 	debugInterval = 60 * time.Second
 	// bytesPerMB is bytes per megabyte
 	bytesPerMB = 1024 * 1024
+	// failureExitCode is the exit status when RouteWatch stops on an error
+	failureExitCode = 1
 )
 
 // logDebugStats logs goroutine count and memory usage
@@ -83,6 +85,9 @@ func CLIEntry() {
 					go func() {
 						if err := rw.Run(ctx); err != nil {
 							logger.Error("RouteWatch error", "error", err)
+							if err := shutdowner.Shutdown(fx.ExitCode(failureExitCode)); err != nil {
+								logger.Error("Failed to shutdown gracefully", "error", err)
+							}
 						}
 					}()
 

internal/routewatch/prefixhandler_test.go

@@ -170,7 +170,7 @@ func TestPrefixHandlerAppliesEachPeersLastUpdateInABatch(t *testing.T) {
 			}
 
 			ctx := context.Background()
-			routes, err := db.GetPrefixDetailsContext(ctx, prefix)
+			routes, _, err := db.GetPrefixDetailsContext(ctx, prefix)
 			if err != nil && !errors.Is(err, database.ErrNoRoute) {
 				t.Fatalf("GetPrefixDetailsContext: %v", err)
 			}

internal/server/handlers.go

@@ -759,7 +759,7 @@ func (s *Server) handlePrefixDetailJSON() http.HandlerFunc {
 		}
 		prefix := parsed.Masked().String()
 
-		routes, err := s.db.GetPrefixDetailsContext(r.Context(), prefix)
+		routes, _, err := s.db.GetPrefixDetailsContext(r.Context(), prefix)
 		if err != nil {
 			if errors.Is(err, database.ErrNoRoute) {
 				writeJSONError(w, http.StatusNotFound, err.Error())
@@ -930,7 +930,7 @@ func (s *Server) handlePrefixDetail() http.HandlerFunc {
 		}
 		prefix := parsed.Masked().String()
 
-		routes, err := s.db.GetPrefixDetailsContext(r.Context(), prefix)
+		routes, originASNs, err := s.db.GetPrefixDetailsContext(r.Context(), prefix)
 		if err != nil {
 			if errors.Is(err, database.ErrNoRoute) {
 				http.Error(w, "Prefix not found", http.StatusNotFound)
@@ -952,18 +952,10 @@ func (s *Server) handlePrefixDetail() http.HandlerFunc {
 		originMap := make(map[int]*ASNInfo)
 		for _, route := range routes {
 			if _, exists := originMap[route.OriginASN]; !exists {
-				// Get AS info from database
-				asInfo, _, _ := s.db.GetASDetailsContext(r.Context(), route.OriginASN)
-				handle := ""
-				description := ""
-				if asInfo != nil {
-					handle = asInfo.Handle
-					description = asInfo.Description
-				}
 				originMap[route.OriginASN] = &ASNInfo{
 					ASN:         route.OriginASN,
-					Handle:      handle,
-					Description: description,
+					Handle:      originASNs[route.OriginASN].Handle,
+					Description: originASNs[route.OriginASN].Description,
 					PeerCount:   0,
 				}
 			}

internal/server/handlers_test.go

@@ -3,10 +3,13 @@ package server
 import (
 	"context"
 	"encoding/json"
+	"errors"
+	"html"
 	"net/http"
 	"net/http/httptest"
 	"runtime"
 	"slices"
+	"strings"
 	"testing"
 	"time"
 
@@ -15,6 +18,7 @@ import (
 	"git.eeqj.de/sneak/routewatch/internal/logger"
 	"git.eeqj.de/sneak/routewatch/internal/metrics"
 	"git.eeqj.de/sneak/routewatch/internal/streamer"
+	"git.eeqj.de/sneak/routewatch/pkg/asinfo"
 	"github.com/google/uuid"
 )
 
@@ -200,6 +204,72 @@ func TestPrefixDetailHandlersParsePrefix(t *testing.T) {
 	}
 }
 
+// failingASDetailsDB wraps a real store and fails every AS details lookup.
+type failingASDetailsDB struct {
+	database.Store
+}
+
+func (failingASDetailsDB) GetASDetailsContext(_ context.Context, _ int) (*database.ASN, []database.LiveRoute, error) {
+	return nil, nil, errors.New("AS details lookup failed")
+}
+
+// TestPrefixDetailShowsOriginNames checks that the prefix page shows each
+// origin AS's handle and description without looking up the AS's details,
+// which also read every route the AS originates. Before the fix the page did
+// that lookup once per origin, so with it failing the names were missing
+// (https://git.eeqj.de/sneak/routewatch/issues/67). The AS path column shows
+// handles too, so the test looks for the origin list's "(handle)" form.
+func TestPrefixDetailShowsOriginNames(t *testing.T) {
+	db, err := database.New(&config.Config{StateDir: t.TempDir()}, logger.New())
+	if err != nil {
+		t.Fatalf("database.New: %v", err)
+	}
+	t.Cleanup(func() { _ = db.Close() })
+
+	ts := time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC)
+	origins := []int{15169, 13335}
+	for _, asn := range origins {
+		if _, err := db.GetOrCreateASN(asn, ts); err != nil {
+			t.Fatalf("GetOrCreateASN(%d): %v", asn, err)
+		}
+	}
+	if err := db.UpsertLiveRouteBatch([]*database.LiveRoute{
+		{
+			ID: uuid.New(), Prefix: "192.0.2.0/24", MaskLength: 24, IPVersion: 4,
+			OriginASN: origins[0], PeerIP: "198.51.100.1", ASPath: []int{origins[0]}, NextHop: "198.51.100.1",
+			LastUpdated: ts,
+		},
+		{
+			ID: uuid.New(), Prefix: "192.0.2.0/24", MaskLength: 24, IPVersion: 4,
+			OriginASN: origins[1], PeerIP: "198.51.100.2", ASPath: []int{origins[1]}, NextHop: "198.51.100.2",
+			LastUpdated: ts,
+		},
+	}); err != nil {
+		t.Fatalf("UpsertLiveRouteBatch: %v", err)
+	}
+
+	s := New(failingASDetailsDB{db}, streamer.New(logger.New(), metrics.New()), logger.New(), &config.Config{})
+	rec := httptest.NewRecorder()
+	s.router.ServeHTTP(rec, httptest.NewRequest(http.MethodGet, "/prefix/192.0.2.0/24", nil))
+	if rec.Code != http.StatusOK {
+		t.Fatalf("status %d, want %d; body %s", rec.Code, http.StatusOK, rec.Body)
+	}
+
+	page := rec.Body.String()
+	for _, asn := range origins {
+		info, ok := asinfo.Get(asn)
+		if !ok {
+			t.Fatalf("AS%d is not in the AS info data", asn)
+		}
+		if want := "(" + html.EscapeString(info.Handle) + ")"; !strings.Contains(page, want) {
+			t.Errorf("page does not show AS%d's handle %q", asn, want)
+		}
+		if want := html.EscapeString(info.Description); !strings.Contains(page, want) {
+			t.Errorf("page does not show AS%d's description %q", asn, want)
+		}
+	}
+}
+
 // settledGoroutineCount lets transient goroutines finish, then reports the
 // current count.
 func settledGoroutineCount() int {

internal/server/server.go

@@ -3,6 +3,8 @@ package server
 
 import (
 	"context"
+	"fmt"
+	"net"
 	"net/http"
 	"strconv"
 	"time"
@@ -53,9 +55,12 @@ func New(db database.Store, streamer *streamer.Streamer, logger *logger.Logger,
 	return s
 }
 
-// Start starts the HTTP server
+// Start listens on the configured port and serves HTTP in the background.
+// It returns an error if it cannot listen, for example because the port is
+// already in use.
 func (s *Server) Start() error {
 	const (
+		network           = "tcp"
 		readHeaderTimeout = 40 * time.Second
 		readTimeout       = 60 * time.Second
 		writeTimeout      = 60 * time.Second
@@ -73,10 +78,15 @@ func (s *Server) Start() error {
 
 	s.logger.Info("Starting HTTP server", "port", s.port, "addr", s.srv.Addr)
 
-	// Start in goroutine but log when actually listening
+	listener, err := net.Listen(network, s.srv.Addr)
+	if err != nil {
+		return fmt.Errorf("starting HTTP server: %w", err)
+	}
+
+	s.logger.Info("HTTP server listening", "addr", listener.Addr().String())
+
 	go func() {
-		s.logger.Info("HTTP server listening", "addr", s.srv.Addr)
-		if err := s.srv.ListenAndServe(); err != nil && err != http.ErrServerClosed {
+		if err := s.srv.Serve(listener); err != nil && err != http.ErrServerClosed {
 			s.logger.Error("HTTP server error", "error", err)
 		}
 	}()

internal/server/server_test.go

@@ -0,0 +1,33 @@
+package server
+
+import (
+	"context"
+	"net"
+	"testing"
+
+	"git.eeqj.de/sneak/routewatch/internal/config"
+	"git.eeqj.de/sneak/routewatch/internal/logger"
+	"git.eeqj.de/sneak/routewatch/internal/metrics"
+	"git.eeqj.de/sneak/routewatch/internal/streamer"
+)
+
+// TestStartFailsWhenPortIsHeld holds a port with a listener of its own and
+// checks that Start on that port returns an error. Before the fix Start
+// listened in a goroutine, only logged the failure and returned nil, so the
+// daemon kept running without its web server.
+func TestStartFailsWhenPortIsHeld(t *testing.T) {
+	held, err := net.Listen("tcp", ":0")
+	if err != nil {
+		t.Fatalf("failed to open the test listener: %v", err)
+	}
+	defer func() { _ = held.Close() }()
+
+	port := held.Addr().(*net.TCPAddr).Port
+	log := logger.New()
+	s := New(nil, streamer.New(log, metrics.New()), log, &config.Config{Port: port})
+	defer func() { _ = s.Stop(context.Background()) }()
+
+	if err := s.Start(); err == nil {
+		t.Fatalf("Start returned nil while port %d was held by another listener", port)
+	}
+}

internal/templates/prefix_detail.html

@@ -283,6 +283,7 @@
                 <div class="origin-item">
                     <a href="/as/{{.ASN}}" class="as-link">AS{{.ASN}}</a>
                     {{if .Handle}} ({{.Handle}}){{end}}
+                    {{if .Description}} {{.Description}}{{end}}
                     <span style="color: #7f8c8d; margin-left: 10px;">{{.PeerCount}} peer{{if ne .PeerCount 1}}s{{end}}</span>
                 </div>
                 {{end}}