fix: harden single-machine load handling

loadtest/im-pressure/recorder_test.go

@@ -2,6 +2,9 @@ package main
 
 import (
 	"encoding/json"
+	"errors"
+	"fmt"
+	"sync"
 	"testing"
 	"time"
 )
@@ -111,6 +114,65 @@ func TestDeliveryRecorderSeparatesLocalAndCrossMachineLatency(t *testing.T) {
 	}
 }
 
+func TestDeliveryRecorderConcurrentGroupFanout(t *testing.T) {
+	const users = 32
+	const messages = 64
+	recorder := newDeliveryRecorder("run1", "a", users)
+	ledger := make([]AcceptedMessage, messages)
+	for messageIndex := range ledger {
+		ledger[messageIndex] = AcceptedMessage{
+			RunID: "run1", Kind: "group", Topic: "grp-one", Seq: 1,
+			ClientMid: fmt.Sprintf("run1-g-b-%04d-01", messageIndex+1), SenderMachine: "b",
+		}
+	}
+
+	var writers sync.WaitGroup
+	for receiver := 1; receiver <= users; receiver++ {
+		for _, message := range ledger {
+			writers.Add(1)
+			go func(receiver int, message AcceptedMessage) {
+				defer writers.Done()
+				recorder.onData(AccountRecord{Index: receiver}, testData(message, time.Now().Add(-time.Millisecond)))
+			}(receiver, message)
+		}
+	}
+	writers.Wait()
+
+	summary := recorder.summarize(AgentSummary{}, ledger)
+	want := int64(users * messages)
+	if summary.ExpectedGroup != want || summary.ReceivedGroup != want || summary.RealtimeLost != 0 {
+		t.Fatalf("group expected/received/lost = %d/%d/%d, want %d/%d/0",
+			summary.ExpectedGroup, summary.ReceivedGroup, summary.RealtimeLost, want, want)
+	}
+	if summary.Duplicates != 0 || summary.DeliveryLatency.Count != want {
+		t.Fatalf("duplicates=%d latency samples=%d want=0/%d", summary.Duplicates, summary.DeliveryLatency.Count, want)
+	}
+}
+
+func TestDeliveryRecorderDisconnectDiagnostics(t *testing.T) {
+	recorder := newDeliveryRecorder("run1", "a", 1)
+	recorder.onDisconnect(AccountRecord{Index: 1}, errors.New("websocket: close 1006 (abnormal closure): unexpected EOF"))
+	recorder.onDisconnect(AccountRecord{Index: 1}, errors.New("read tcp: connection reset by peer"))
+
+	summary := recorder.summarize(AgentSummary{}, nil)
+	if summary.Disconnects != 2 || summary.DisconnectReasons["abnormal_close"] != 1 ||
+		summary.DisconnectReasons["connection_reset"] != 1 || len(summary.DisconnectSamples) != 2 {
+		t.Fatalf("unexpected disconnect diagnostics: count=%d reasons=%v samples=%+v",
+			summary.Disconnects, summary.DisconnectReasons, summary.DisconnectSamples)
+	}
+	recorder.resetDisconnects()
+	summary = recorder.summarize(AgentSummary{}, nil)
+	if summary.Disconnects != 0 || len(summary.DisconnectReasons) != 0 || len(summary.DisconnectSamples) != 0 {
+		t.Fatalf("disconnect diagnostics were not reset: %+v", summary)
+	}
+}
+
+func TestBitsetCountCountsEachBitOnce(t *testing.T) {
+	if got := bitsetCount([]uint64{0b1011, 0b100000}); got != 4 {
+		t.Fatalf("bitset count=%d want=4", got)
+	}
+}
+
 func testData(message AcceptedMessage, sentAt time.Time) dataPacket {
 	content, _ := json.Marshal(map[string]any{"run_id": message.RunID, "scenario": message.Scenario,
 		"sender_machine": message.SenderMachine, "sender_index": message.SenderIndex,