feat: sample terminal business latency

internal/observability/business.go

@@ -25,6 +25,14 @@ type BusinessSnapshot struct {
 	Truncated bool
 	// RecentEvents 固定事件类别在最近窗口内的有界数量。
 	RecentEvents map[string]uint64
+	// TaskTerminalLatencySeconds 最近窗口终态任务创建到完成的平均耗时样本。
+	TaskTerminalLatencySeconds float64
+	// TaskTerminalLatencyMaxSeconds 最近窗口终态任务样本最大耗时。
+	TaskTerminalLatencyMaxSeconds float64
+	// WorkflowTerminalLatencySeconds 最近窗口终态流程创建到完成的平均耗时样本。
+	WorkflowTerminalLatencySeconds float64
+	// WorkflowTerminalLatencyMaxSeconds 最近窗口终态流程样本最大耗时。
+	WorkflowTerminalLatencyMaxSeconds float64
 }
 
 // RecordBusinessSnapshot records one bounded database sample. A failed sample
@@ -58,6 +66,10 @@ func (r *Registry) RecordBusinessSnapshot(snapshot BusinessSnapshot, started tim
 	for _, eventType := range eventTypes {
 		r.SetGauge("orbit_business_events_recent", float64(snapshot.RecentEvents[eventType]), Labels{"event": eventType})
 	}
+	r.SetGauge("orbit_pulse_task_terminal_latency_seconds", snapshot.TaskTerminalLatencySeconds, nil)
+	r.SetGauge("orbit_pulse_task_terminal_latency_max_seconds", snapshot.TaskTerminalLatencyMaxSeconds, nil)
+	r.SetGauge("orbit_weave_workflow_terminal_latency_seconds", snapshot.WorkflowTerminalLatencySeconds, nil)
+	r.SetGauge("orbit_weave_workflow_terminal_latency_max_seconds", snapshot.WorkflowTerminalLatencyMaxSeconds, nil)
 	r.SetGauge("orbit_pulse_tasks_oldest_age_seconds", snapshot.TaskOldestAgeSeconds, nil)
 	r.SetGauge("orbit_result_delivery_oldest_age_seconds", snapshot.DeliveryOldestAgeSeconds, nil)
 	r.SetGauge("orbit_weave_workflow_oldest_age_seconds", snapshot.WorkflowOldestAgeSeconds, nil)

internal/observability/catalog.go

@@ -44,6 +44,10 @@ func catalog() map[string]descriptor {
 	c["orbit_weave_workflows_state"] = descriptor{gauge, "Bounded count of Weave instances by durable state", map[string][]string{"state": workflowStates}}
 	c["orbit_weave_workflow_oldest_age_seconds"] = descriptor{gauge, "Age of the oldest sampled unfinished Weave instance", nil}
 	c["orbit_business_events_recent"] = descriptor{gauge, "Bounded count of fixed event categories in the recent window", map[string][]string{"event": eventTypes}}
+	c["orbit_pulse_task_terminal_latency_seconds"] = descriptor{gauge, "Average sampled Pulse task create-to-terminal latency in seconds", nil}
+	c["orbit_pulse_task_terminal_latency_max_seconds"] = descriptor{gauge, "Maximum sampled Pulse task create-to-terminal latency in seconds", nil}
+	c["orbit_weave_workflow_terminal_latency_seconds"] = descriptor{gauge, "Average sampled Weave workflow create-to-terminal latency in seconds", nil}
+	c["orbit_weave_workflow_terminal_latency_max_seconds"] = descriptor{gauge, "Maximum sampled Weave workflow create-to-terminal latency in seconds", nil}
 	c["orbit_business_snapshot_total"] = descriptor{counter, "Completed bounded business-state snapshots by outcome", map[string][]string{"outcome": {"success", "error", "timeout"}}}
 	c["orbit_business_snapshot_duration_seconds"] = descriptor{histogram, "Bounded business-state snapshot duration in seconds", nil}
 	c["orbit_business_snapshot_last_success_timestamp_seconds"] = descriptor{gauge, "Unix time of the last successful bounded business-state snapshot", nil}

internal/observability/metrics_test.go

@@ -117,14 +117,16 @@ func TestBusinessSnapshotKeepsLastGoodStateOnFailure(t *testing.T) {
 	r := NewRegistry()
 	started := time.Now().Add(-25 * time.Millisecond)
 	r.RecordBusinessSnapshot(BusinessSnapshot{
-		TaskStates:               map[string]uint64{"WAITING": 3},
-		TaskOldestAgeSeconds:     12.5,
-		DeliveryStates:           map[string]uint64{"PENDING": 2},
-		DeliveryOldestAgeSeconds: 8.25,
-		WorkflowStates:           map[string]uint64{"RUNNING": 1},
-		WorkflowOldestAgeSeconds: 4.75,
-		RecentEvents:             map[string]uint64{"task.accepted": 5},
-		Truncated:                true,
+		TaskStates:                 map[string]uint64{"WAITING": 3},
+		TaskOldestAgeSeconds:       12.5,
+		DeliveryStates:             map[string]uint64{"PENDING": 2},
+		DeliveryOldestAgeSeconds:   8.25,
+		WorkflowStates:             map[string]uint64{"RUNNING": 1},
+		WorkflowOldestAgeSeconds:   4.75,
+		RecentEvents:               map[string]uint64{"task.accepted": 5},
+		TaskTerminalLatencySeconds: 2.5, TaskTerminalLatencyMaxSeconds: 7.5,
+		WorkflowTerminalLatencySeconds: 3.5, WorkflowTerminalLatencyMaxSeconds: 9.5,
+		Truncated: true,
 	}, started, nil)
 	first := r.Render()
 	for _, want := range []string{
@@ -132,6 +134,8 @@ func TestBusinessSnapshotKeepsLastGoodStateOnFailure(t *testing.T) {
 		`orbit_result_deliveries_state{state="PENDING"} 2`,
 		`orbit_weave_workflows_state{state="RUNNING"} 1`,
 		`orbit_business_events_recent{event="task.accepted"} 5`,
+		"orbit_pulse_task_terminal_latency_seconds 2.5",
+		"orbit_weave_workflow_terminal_latency_max_seconds 9.5",
 		"orbit_pulse_tasks_oldest_age_seconds 12.5",
 		"orbit_business_snapshot_truncated 1",
 		`orbit_business_snapshot_total{outcome="success"} 1`,