fix: add trackFailOnError option to control kubedog exit code (#2576)

* fix: add trackFailOnError option to control kubedog exit code behavior

When kubedog release tracking fails (e.g. pod ImagePullBackOff), helmfile
exits with code 0 instead of a non-zero exit code. Add a trackFailOnError
configuration option (default: false) that when set to true, propagates
kubedog tracking failures to the exit code.

The option is available as:
- Per-release YAML: trackFailOnError: true
- CLI flag: --track-fail-on-error (sync and apply commands)

Extract trackReleaseIfEnabled helper to consolidate kubedog tracking logic
from two duplicated call sites into a single maintainable method.

Fixes #2507

Signed-off-by: yxxhero <aiopsclub@163.com>

* fix: add //go:build ignore to server.go to fix go test CI failure

The test/integration/test-cases/issue-2103/input/server.go is a
package main helper binary used by the issue-2103 integration test.
When go test -coverprofile runs on this package, it fails with
"go: no such tool covdata" in the CI environment.

Adding //go:build ignore excludes the file from go list ./... (and
therefore from PKGS in the Makefile), while still allowing the
integration test to build it explicitly via file path:
  go build -o server ./path/to/server.go

Agent-Logs-Url: https://github.com/helmfile/helmfile/sessions/8a7000af-72b7-48f8-8a82-24813b5df341

Co-authored-by: yxxhero <11087727+yxxhero@users.noreply.github.com>

* fix: update TestGenerateID expected hashes after adding TrackFailOnError field

Adding TrackFailOnError *bool to ReleaseSpec changed the spew
serialization of the struct, which changed the FNV-32a hash values
produced by generateValuesID. Update temp_test.go with the new
expected hash strings.

Agent-Logs-Url: https://github.com/helmfile/helmfile/sessions/caa86cd9-73d1-4894-b745-fd70c0811fd6

Co-authored-by: yxxhero <11087727+yxxhero@users.noreply.github.com>

---------

Signed-off-by: yxxhero <aiopsclub@163.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>

pkg/state/helmx.go

@@ -197,6 +197,32 @@ func (st *HelmState) shouldUseKubedog(release *ReleaseSpec, ops *SyncOpts) bool
 	return st.getTrackMode(release, ops) == string(kubedog.TrackModeKubedog)
 }
 
+func (st *HelmState) shouldFailOnTrackError(release *ReleaseSpec, ops *SyncOpts) bool {
+	if release.TrackFailOnError != nil {
+		return *release.TrackFailOnError
+	}
+	if ops != nil {
+		return ops.TrackFailOnError
+	}
+	return false
+}
+
+// trackReleaseIfEnabled performs kubedog tracking for a release if trackMode is "kubedog".
+// It returns a ReleaseError if tracking fails and shouldFailOnTrackError is true.
+// The caller is responsible for mutating affectedReleases when needed.
+func (st *HelmState) trackReleaseIfEnabled(ctx context.Context, release *ReleaseSpec, helm helmexec.Interface, opts *SyncOpts) *ReleaseError {
+	if !st.shouldUseKubedog(release, opts) {
+		return nil
+	}
+	if trackErr := st.trackWithKubedog(ctx, release, helm, opts); trackErr != nil {
+		st.logger.Warnf("kubedog tracking failed for release %s: %v", release.Name, trackErr)
+		if st.shouldFailOnTrackError(release, opts) {
+			return newReleaseFailedError(release, trackErr)
+		}
+	}
+	return nil
+}
+
 func (st *HelmState) getTrackMode(release *ReleaseSpec, ops *SyncOpts) string {
 	trackMode := release.TrackMode
 	if trackMode == "" && ops != nil && ops.TrackMode != "" {

pkg/state/state.go

@@ -478,6 +478,8 @@ type ReleaseSpec struct {
 	KubedogQPS *float32 `yaml:"kubedogQPS,omitempty"`
 	// KubedogBurst specifies the burst for kubedog kubernetes client
 	KubedogBurst *int `yaml:"kubedogBurst,omitempty"`
+	// TrackFailOnError controls whether kubedog tracking failures cause a non-zero exit code
+	TrackFailOnError *bool `yaml:"trackFailOnError,omitempty"`
 }
 
 // TrackResourceSpec specifies a resource to track
@@ -912,6 +914,7 @@ type SyncOpts struct {
 	TrackMode            string
 	TrackTimeout         int
 	TrackLogs            bool
+	TrackFailOnError     bool
 	Description          string
 }
 
@@ -1138,10 +1141,8 @@ func (st *HelmState) SyncReleases(affectedReleases *AffectedReleases, helm helme
 					}
 				} else if release.UpdateStrategy == UpdateStrategyReinstallIfForbidden {
 					relErr = st.performSyncOrReinstallOfRelease(affectedReleases, helm, context, release, chart, m, flags...)
-					if relErr == nil && st.shouldUseKubedog(release, opts) {
-						if trackErr := st.trackWithKubedog(gocontext.Background(), release, helm, opts); trackErr != nil {
-							st.logger.Warnf("kubedog tracking failed for release %s: %v", release.Name, trackErr)
-						}
+					if relErr == nil {
+						relErr = st.trackReleaseIfEnabled(gocontext.Background(), release, helm, opts)
 					}
 				} else {
 					if err := helm.SyncRelease(context, release.Name, chart, release.Namespace, flags...); err != nil {
@@ -1160,10 +1161,11 @@ func (st *HelmState) SyncReleases(affectedReleases *AffectedReleases, helm helme
 							release.installedVersion = installedVersion
 						}
 
-						if st.shouldUseKubedog(release, opts) {
-							if trackErr := st.trackWithKubedog(gocontext.Background(), release, helm, opts); trackErr != nil {
-								st.logger.Warnf("kubedog tracking failed for release %s: %v", release.Name, trackErr)
-							}
+						if trackErr := st.trackReleaseIfEnabled(gocontext.Background(), release, helm, opts); trackErr != nil {
+							m.Lock()
+							affectedReleases.Failed = append(affectedReleases.Failed, release)
+							m.Unlock()
+							relErr = trackErr
 						}
 					}
 				}

pkg/state/temp_test.go

@@ -38,39 +38,39 @@ func TestGenerateID(t *testing.T) {
 	run(testcase{
 		subject: "baseline",
 		release: ReleaseSpec{Name: "foo", Chart: "incubator/raw"},
-		want:    "foo-values-6ccb848dcd",
+		want:    "foo-values-7f6f8d74dd",
 	})
 
 	run(testcase{
 		subject: "different bytes content",
 		release: ReleaseSpec{Name: "foo", Chart: "incubator/raw"},
 		data:    []byte(`{"k":"v"}`),
-		want:    "foo-values-5bcbbc4c85",
+		want:    "foo-values-5fc74c864c",
 	})
 
 	run(testcase{
 		subject: "different map content",
 		release: ReleaseSpec{Name: "foo", Chart: "incubator/raw"},
 		data:    map[string]any{"k": "v"},
-		want:    "foo-values-7c6468f955",
+		want:    "foo-values-77df88dd65",
 	})
 
 	run(testcase{
 		subject: "different chart",
 		release: ReleaseSpec{Name: "foo", Chart: "stable/envoy"},
-		want:    "foo-values-8645f5847f",
+		want:    "foo-values-77c96457f7",
 	})
 
 	run(testcase{
 		subject: "different name",
 		release: ReleaseSpec{Name: "bar", Chart: "incubator/raw"},
-		want:    "bar-values-54bd8c865",
+		want:    "bar-values-6695f7ff4c",
 	})
 
 	run(testcase{
 		subject: "specific ns",
 		release: ReleaseSpec{Name: "foo", Chart: "incubator/raw", Namespace: "myns"},
-		want:    "myns-foo-values-b4849b445",
+		want:    "myns-foo-values-9b9484d4c",
 	})
 
 	for id, n := range ids {