Clear agent.upgrade_attempts on upgrade complete

changelog/fragments/1740760469-Clear-agent-upgrade-attempts-when-upgrade-complete.yaml

@@ -0,0 +1,34 @@
+# Kind can be one of:
+# - breaking-change: a change to previously-documented behavior
+# - deprecation: functionality that is being removed in a later release
+# - bug-fix: fixes a problem in a previous version
+# - enhancement: extends functionality but does not break or fix existing behavior
+# - feature: new functionality
+# - known-issue: problems that we are aware of in a given version
+# - security: impacts on the security of a product or a user’s deployment.
+# - upgrade: important information for someone upgrading from a prior version
+# - other: does not fit into any of the other categories
+kind: enhancement
+
+# Change summary; a 80ish characters long description of the change.
+summary: Clear agent.upgrade_attempts when upgrade is complete.
+
+# Long description; in case the summary is not enough to describe the change
+# this field accommodate a description without length limits.
+# NOTE: This field will be rendered only for breaking-change and known-issue kinds at the moment.
+description: |
+  The new AutomaticAgentUpgradeTask Kibana task sets the upgrade_attempts property in agents it upgrades.
+  This property is used to track upgrade retries and should therefore be cleared when the upgrade is complete.
+
+# Affected component; usually one of "elastic-agent", "fleet-server", "filebeat", "metricbeat", "auditbeat", "all", etc.
+component: fleet-server
+
+# PR URL; optional; the PR number that added the changeset.
+# If not present is automatically filled by the tooling finding the PR where this changelog fragment has been added.
+# NOTE: the tooling supports backports, so it's able to fill the original PR number instead of the backport PR number.
+# Please provide it if you are adding a fragment for a different PR.
+pr: https://github.com/elastic/fleet-server/pull/4528
+
+# Issue URL; optional; the GitHub issue related to this changeset (either closes or is part of).
+# If not present is automatically filled by the tooling with the issue linked to the PR number.
+# issue: 

internal/pkg/api/handleCheckin.go

@@ -219,7 +219,7 @@ func (ct *CheckinT) validateRequest(zlog zerolog.Logger, w http.ResponseWriter,
 		}
 
 		wTime := pollDuration + time.Minute
-		rc := http.NewResponseController(w) //nolint:bodyclose // we are working with a ResponseWriter not a Respons
+		rc := http.NewResponseController(w)
 		if err := rc.SetWriteDeadline(start.Add(wTime)); err != nil {
 			zlog.Warn().Err(err).Time("write_deadline", start.Add(wTime)).Msg("Unable to set checkin write deadline.")
 		} else {
@@ -500,6 +500,10 @@ func (ct *CheckinT) processUpgradeDetails(ctx context.Context, agent *model.Agen
 	doc := bulk.UpdateFields{
 		dl.FieldUpgradeDetails: details,
 	}
+	if agent.UpgradeAttempts != nil && details.State == UpgradeDetailsStateUPGWATCHING {
+		doc[dl.FieldUpgradeAttempts] = nil
+	}
+
 	body, err := doc.Marshal()
 	if err != nil {
 		return err

internal/pkg/dl/constants.go

@@ -54,6 +54,7 @@ const (
 	FieldUpgradeStartedAt = "upgrade_started_at"
 	FieldUpgradeStatus    = "upgrade_status"
 	FieldUpgradeDetails   = "upgrade_details"
+	FieldUpgradeAttempts  = "upgrade_attempts"
 
 	FieldAuditUnenrolledTime   = "audit_unenrolled_time"
 	FieldAuditUnenrolledReason = "audit_unenrolled_reason"

model/schema.json

@@ -686,6 +686,13 @@
           "description": "Additional upgrade status details.",
           "type": "object"
         },
+        "upgrade_attempts": {
+          "description": "List of timestamps of attempts of Elastic Agent automatic upgrades",
+          "type": "array",
+          "items": {
+            "type": "string"
+          }
+        },
         "replace_token": {
           "description": "hash of token provided during enrollment that allows replacement by another enrollment with same ID",
           "type": "string"