fix: stop archived-thread and guild paging when the cursor does not advance

CHANGELOG.md

@@ -2,6 +2,10 @@
 
 ## Unreleased
 
+### Fixes
+
+- Stop guild and archived-thread pagination with a cursor error when Discord repeats a page instead of hanging sync. Thanks @SebTardif.
+
 ### Maintenance
 
 - Require Go 1.27.0, refresh SQLite and terminal dependencies, and update container, analyzer, security-scan, and docs-build tooling.

docs/commands/sync.md

@@ -76,6 +76,7 @@ discrawl sync --with-media
 - Heartbeat logs (`message sync waiting`) name the oldest active channel and per-channel page activity if in-flight channels stop completing for a while.
 - Every run ends with a `message sync finished` summary.
 - Each channel crawl has a bounded runtime budget; pathological channels are deferred and retried next sync.
+- Guild and archived-thread pagination reports a cursor error if Discord repeats a page instead of continuing indefinitely.
 - Retryable failures and unavailable-channel markers are tracked per channel; stale unavailable markers are cleared after a later successful crawl.
 - Marker cleanup is best-effort, so one missing local sync-state row cannot crash the run.
 - Member refresh is best-effort and gives up after five minutes without a caller-supplied deadline. Routine latest-only syncs skip it unless `--with-members` is set.

internal/discord/client.go

@@ -295,10 +295,17 @@ func (c *Client) Guilds(ctx context.Context) ([]*discordgo.UserGuild, error) {
 			return out, nil
 		}
 		out = append(out, page...)
-		before = page[len(page)-1].ID
 		if len(page) < 200 {
 			return out, nil
 		}
+		nextBefore := page[len(page)-1].ID
+		if nextBefore == "" {
+			return nil, errors.New("guild page missing id")
+		}
+		if nextBefore == before {
+			return nil, errors.New("guild page cursor did not advance")
+		}
+		before = nextBefore
 	}
 }
 
@@ -375,6 +382,9 @@ func (c *Client) ThreadsArchived(ctx context.Context, channelID string, private
 			return uniqueChannels(out), nil
 		}
 		archiveAt := oldest.ThreadMetadata.ArchiveTimestamp
+		if before != nil && archiveAt.Equal(*before) {
+			return nil, fmt.Errorf("channel %s archived thread page cursor did not advance", channelID)
+		}
 		before = &archiveAt
 	}
 }

internal/discord/client_test.go

@@ -362,6 +362,130 @@ func TestGuildMembersErrorsWhenCursorDoesNotAdvance(t *testing.T) {
 	require.Equal(t, 2, requests)
 }
 
+func TestGuildsErrorsWhenCursorDoesNotAdvance(t *testing.T) {
+	page := make([]map[string]any, 200)
+	for i := range page {
+		page[i] = map[string]any{
+			"id":   fmt.Sprintf("g%03d", i),
+			"name": "Guild",
+		}
+	}
+
+	requests := 0
+	mux := http.NewServeMux()
+	mux.HandleFunc("/api/v10/users/@me/guilds", func(w http.ResponseWriter, r *http.Request) {
+		requests++
+		if requests > 5 {
+			writeJSON([]map[string]any{})(w, r)
+			return
+		}
+		writeJSON(page)(w, r)
+	})
+	server := httptest.NewServer(mux)
+	t.Cleanup(server.Close)
+
+	restore := patchDiscordEndpoints(server.URL + "/api/v10/")
+	t.Cleanup(restore)
+
+	client, err := New("token")
+	require.NoError(t, err)
+	t.Cleanup(func() { _ = client.Close() })
+
+	guilds, err := client.Guilds(context.Background())
+	require.ErrorContains(t, err, "guild page cursor did not advance")
+	require.Nil(t, guilds)
+	require.Equal(t, 2, requests)
+}
+
+func TestGuildsErrorsWhenFullPageHasEmptyID(t *testing.T) {
+	page := make([]map[string]any, 200)
+	for i := range 199 {
+		page[i] = map[string]any{
+			"id":   fmt.Sprintf("g%03d", i),
+			"name": "Guild",
+		}
+	}
+	page[199] = map[string]any{"id": "", "name": "Guild"}
+
+	requests := 0
+	mux := http.NewServeMux()
+	mux.HandleFunc("/api/v10/users/@me/guilds", func(w http.ResponseWriter, r *http.Request) {
+		requests++
+		if requests > 5 {
+			writeJSON([]map[string]any{})(w, r)
+			return
+		}
+		writeJSON(page)(w, r)
+	})
+	server := httptest.NewServer(mux)
+	t.Cleanup(server.Close)
+
+	restore := patchDiscordEndpoints(server.URL + "/api/v10/")
+	t.Cleanup(restore)
+
+	client, err := New("token")
+	require.NoError(t, err)
+	t.Cleanup(func() { _ = client.Close() })
+
+	guilds, err := client.Guilds(context.Background())
+	require.ErrorContains(t, err, "guild page missing id")
+	require.Nil(t, guilds)
+	require.Equal(t, 1, requests)
+}
+
+func TestThreadsArchivedErrorsWhenCursorDoesNotAdvance(t *testing.T) {
+	archivedAt := "2024-01-15T12:00:00Z"
+	page := map[string]any{
+		"threads": []map[string]any{
+			{
+				"id":        "t1",
+				"guild_id":  "g1",
+				"parent_id": "c1",
+				"name":      "archived-public",
+				"type":      11,
+				"thread_metadata": map[string]any{
+					"archived":              true,
+					"auto_archive_duration": 60,
+					"archive_timestamp":     archivedAt,
+					"locked":                false,
+					"invitable":             true,
+				},
+			},
+		},
+		"members":  []any{},
+		"has_more": true,
+	}
+
+	requests := 0
+	mux := http.NewServeMux()
+	mux.HandleFunc("/api/v10/channels/c1/threads/archived/public", func(w http.ResponseWriter, r *http.Request) {
+		requests++
+		if requests > 5 {
+			writeJSON(map[string]any{
+				"threads":  []any{},
+				"members":  []any{},
+				"has_more": false,
+			})(w, r)
+			return
+		}
+		writeJSON(page)(w, r)
+	})
+	server := httptest.NewServer(mux)
+	t.Cleanup(server.Close)
+
+	restore := patchDiscordEndpoints(server.URL + "/api/v10/")
+	t.Cleanup(restore)
+
+	client, err := New("token")
+	require.NoError(t, err)
+	t.Cleanup(func() { _ = client.Close() })
+
+	threads, err := client.ThreadsArchived(context.Background(), "c1", false, time.Time{})
+	require.ErrorContains(t, err, "archived thread page cursor did not advance")
+	require.Nil(t, threads)
+	require.Equal(t, 2, requests)
+}
+
 func TestLastMemberUserID(t *testing.T) {
 	t.Parallel()