Skip to content

fix(observability): exclude capacity-wait correlation gaps #244

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rldyourmnd merged 1 commit into from
Aug 27, 2026
Merged

fix(observability): exclude capacity-wait correlation gaps #244

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions internal/fleetobserve/observe.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -596,7 +596,7 @@ func summarizeQueue(snapshot queueintent.Snapshot, platform config.Config, now t
correlationAge := now.Sub(intent.QueueTime)
if !strings.Contains(intent.Repository, "/") {
summary.UnboundRepository++
if correlationAge >= queueCorrelationGracePeriod {
if intent.State != queueintent.StateQueued && correlationAge >= queueCorrelationGracePeriod {
summary.UnboundRepositoryBeyondGrace++
}
}
Expand All @@ -609,7 +609,11 @@ func summarizeQueue(snapshot queueintent.Snapshot, platform config.Config, now t
}
if intent.WorkflowRunID == 0 {
summary.MissingWorkflowRunID++
if correlationAge >= queueCorrelationGracePeriod {
// A rehydrated GitHub job can wait in queued state for capacity
// without a workflow-run identity; the authenticated runner claim
// supplies that identity after assignment. Keep the raw gap visible,
// but page only after the intent has actually left the queue.
if intent.State != queueintent.StateQueued && correlationAge >= queueCorrelationGracePeriod {
summary.MissingWorkflowRunIDBeyondGrace++
}
}
Expand Down
20 changes: 20 additions & 0 deletions internal/fleetobserve/observe_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -284,6 +284,26 @@ func TestQueueSummarySeparatesTransientAndPersistentCorrelationGaps(t *testing.T
}
}

func TestQueueSummaryDoesNotPageOnRehydratedJobWaitingForCapacity(t *testing.T) {
queued := queueintent.Intent{
Key: "rehydrated", ScaleSetID: 11, JobID: "5c3077ba-3664-5824-b2cf-e22a31b25f43",
ScaleSetName: "nddev-linux-integration", Repository: "owner",
WorkflowRef: "authoritative-rehydration", EventName: "push",
QueueTime: observationTime.Add(-10 * queueCorrelationGracePeriod),
State: queueintent.StateQueued, Priority: 1,
StateEnteredAt: observationTime.Add(-time.Minute), UpdatedAt: observationTime.Add(-time.Second),
ExpiresAt: observationTime.Add(time.Minute),
}
summary, err := summarizeQueue(queueintent.Snapshot{Active: []queueintent.Intent{queued}}, testPlatform(t), observationTime)
if err != nil {
t.Fatal(err)
}
if summary.MissingWorkflowRunID != 1 || summary.MissingWorkflowRunIDBeyondGrace != 0 ||
summary.UnboundRepository != 1 || summary.UnboundRepositoryBeyondGrace != 0 {
t.Fatalf("queued correlation classification = %#v", summary)
}
}

func TestCollectorMarksRunningIntentWithoutExecutionLeaseUnhealthy(t *testing.T) {
collector := healthyCollector(t)
collector.Journal = func(context.Context) (providerjournal.Journal, error) {
Expand Down