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

@@ -139,6 +139,9 @@ func uploadLibraries(ctx context.Context, b *bundle.Bundle, libs map[string][]li
 // The deploy phase deploys artifacts and resources.
 // If readPlanPath is provided, the plan is loaded from that file instead of being calculated.
 func Deploy(ctx context.Context, b *bundle.Bundle, outputHandler sync.OutputHandler, engine engine.EngineType, libs map[string][]libraries.LocationToUpdate, plan *deployplan.Plan) {
+	// Always log deploy telemetry, even on error.
+	defer logDeployTelemetry(ctx, b)
+
 	log.Info(ctx, "Phase: deploy")
 
 	// Core mutators that CRUD resources and modify deployment state. These
@@ -208,7 +211,6 @@ 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

@@ -10,6 +10,7 @@ import (
 	"github.com/databricks/cli/bundle/libraries"
 	"github.com/databricks/cli/libs/dyn"
 	"github.com/databricks/cli/libs/log"
+	"github.com/databricks/cli/libs/logdiag"
 	"github.com/databricks/cli/libs/telemetry"
 	"github.com/databricks/cli/libs/telemetry/protos"
 )
@@ -149,6 +150,7 @@ func logDeployTelemetry(ctx context.Context, b *bundle.Bundle) {
 		BundleDeployEvent: &protos.BundleDeployEvent{
 			BundleUuid:   bundleUuid,
 			DeploymentId: b.Metrics.DeploymentId.String(),
+			ErrorMessage: logdiag.GetFirstErrorSummary(ctx),
 
 			ResourceCount:                     resourcesCount,
 			ResourceJobCount:                  int64(len(b.Config.Resources.Jobs)),

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"`