Add error_message field to bundle deploy telemetry

Track the first error diagnostic summary encountered during bundle deploy
in telemetry. Move telemetry logging into a defer so it's always captured,
even when deploy fails.

Co-authored-by: Isaac

Author: shreyas-goenka

bundle/phases/deploy.go

@@ -208,7 +208,6 @@ func Deploy(ctx context.Context, b *bundle.Bundle, outputHandler sync.OutputHand
 		return
 	}
 
-	logDeployTelemetry(ctx, b)
 	bundle.ApplyContext(ctx, b, scripts.Execute(config.ScriptPostDeploy))
 }
 

bundle/phases/telemetry.go

@@ -33,7 +33,8 @@ func getExecutionTimes(b *bundle.Bundle) []protos.IntMapEntry {
 	return executionTimes
 }
 
-func logDeployTelemetry(ctx context.Context, b *bundle.Bundle) {
+// LogDeployTelemetry logs a telemetry event for a bundle deploy command.
+func LogDeployTelemetry(ctx context.Context, b *bundle.Bundle, errMsg string) {
 	resourcesCount := int64(0)
 	_, err := dyn.MapByPattern(b.Config.Value(), dyn.NewPattern(dyn.Key("resources"), dyn.AnyKey(), dyn.AnyKey()), func(p dyn.Path, v dyn.Value) (dyn.Value, error) {
 		resourcesCount++
@@ -149,6 +150,7 @@ func logDeployTelemetry(ctx context.Context, b *bundle.Bundle) {
 		BundleDeployEvent: &protos.BundleDeployEvent{
 			BundleUuid:   bundleUuid,
 			DeploymentId: b.Metrics.DeploymentId.String(),
+			ErrorMessage: errMsg,
 
 			ResourceCount:                     resourcesCount,
 			ResourceJobCount:                  int64(len(b.Config.Resources.Jobs)),

cmd/bundle/utils/process.go

@@ -80,7 +80,7 @@ func ProcessBundle(cmd *cobra.Command, opts ProcessOptions) (*bundle.Bundle, err
 	return b, err
 }
 
-func ProcessBundleRet(cmd *cobra.Command, opts ProcessOptions) (*bundle.Bundle, *statemgmt.StateDesc, error) {
+func ProcessBundleRet(cmd *cobra.Command, opts ProcessOptions) (b *bundle.Bundle, stateDesc *statemgmt.StateDesc, retErr error) {
 	var err error
 	ctx := cmd.Context()
 	if opts.SkipInitContext {
@@ -93,7 +93,24 @@ func ProcessBundleRet(cmd *cobra.Command, opts ProcessOptions) (*bundle.Bundle,
 	}
 
 	// Load bundle config and apply target
-	b := root.MustConfigureBundle(cmd)
+	b = root.MustConfigureBundle(cmd)
+
+	// Log deploy telemetry on all exit paths. This is a defer to ensure
+	// telemetry is logged even when the deploy command fails, for both
+	// diagnostic errors and regular Go errors.
+	if opts.Deploy {
+		defer func() {
+			if b == nil {
+				return
+			}
+			errMsg := logdiag.GetFirstErrorSummary(ctx)
+			if errMsg == "" && retErr != nil && !errors.Is(retErr, root.ErrAlreadyPrinted) {
+				errMsg = retErr.Error()
+			}
+			phases.LogDeployTelemetry(ctx, b, errMsg)
+		}()
+	}
+
 	if logdiag.HasError(ctx) {
 		return b, nil, root.ErrAlreadyPrinted
 	}
@@ -147,8 +164,6 @@ func ProcessBundleRet(cmd *cobra.Command, opts ProcessOptions) (*bundle.Bundle,
 		}
 	}
 
-	var stateDesc *statemgmt.StateDesc
-
 	shouldReadState := opts.ReadState || opts.AlwaysPull || opts.InitIDs || opts.ErrorOnEmptyState || opts.PreDeployChecks || opts.Deploy || opts.ReadPlanPath != ""
 
 	if shouldReadState {

libs/logdiag/logdiag.go

@@ -30,6 +30,9 @@ type LogDiagData struct {
 	// If Collect is true, diagnostics are appended to Collected. Use SetCollected() to set.
 	Collect   bool
 	Collected []diag.Diagnostic
+
+	// Summary of the first error diagnostic logged, if any.
+	FirstErrorSummary string
 }
 
 // IsSetup returns whether InitContext() was already called.
@@ -117,6 +120,16 @@ func FlushCollected(ctx context.Context) diag.Diagnostics {
 	return result
 }
 
+// GetFirstErrorSummary returns the summary of the first error diagnostic
+// logged, or an empty string if no errors have been logged.
+func GetFirstErrorSummary(ctx context.Context) string {
+	val := read(ctx)
+	val.mu.Lock()
+	defer val.mu.Unlock()
+
+	return val.FirstErrorSummary
+}
+
 func LogDiag(ctx context.Context, d diag.Diagnostic) {
 	val := read(ctx)
 	val.mu.Lock()
@@ -125,6 +138,9 @@ func LogDiag(ctx context.Context, d diag.Diagnostic) {
 	switch d.Severity {
 	case diag.Error:
 		val.Errors += 1
+		if val.FirstErrorSummary == "" {
+			val.FirstErrorSummary = d.Summary
+		}
 	case diag.Warning:
 		val.Warnings += 1
 	case diag.Recommendation:

libs/telemetry/protos/bundle_deploy.go

@@ -7,6 +7,9 @@ type BundleDeployEvent struct {
 	// UUID associated with the deployment.
 	DeploymentId string `json:"deployment_id,omitempty"`
 
+	// Error message encountered during the bundle deploy command, if any.
+	ErrorMessage string `json:"error_message,omitempty"`
+
 	ResourceCount                     int64 `json:"resource_count"`
 	ResourceJobCount                  int64 `json:"resource_job_count"`
 	ResourcePipelineCount             int64 `json:"resource_pipeline_count"`