From 0ff08d500c926ea7933c1eb388af05406c862e7a Mon Sep 17 00:00:00 2001
From: "Vinicius C." <vinny.cardoso96@gmail.com>
Date: Thu, 5 Dec 2024 19:13:10 +0000
Subject: [PATCH] Show failed command after atmos workflow failure (#767)

* add feature for failed commands workflow

* chore: clean code cmd msg

* fix: general fixes for workflow cmd output

* clean up error message

* move workflow error message

* move workflow msg

* remove cd command

---------

Co-authored-by: Erik Osterman (CEO @ Cloud Posse) <erik@cloudposse.com>
---
 cmd/workflow.go                               |  5 ++-
 internal/exec/workflow_utils.go               | 29 ++++++++++++----
 .../core-concepts/workflows/workflows.mdx     | 34 +++++++++++++++++++
 3 files changed, 61 insertions(+), 7 deletions(-)

diff --git a/cmd/workflow.go b/cmd/workflow.go
index c19241dc1..206382eed 100644
--- a/cmd/workflow.go
+++ b/cmd/workflow.go
@@ -16,7 +16,10 @@ var workflowCmd = &cobra.Command{
 	Example: "atmos workflow\n" +
 		"atmos workflow <name> -f <file>\n" +
 		"atmos workflow <name> -f <file> -s <stack>\n" +
-		"atmos workflow <name> -f <file> --from-step <step-name>",
+		"atmos workflow <name> -f <file> --from-step <step-name>\n\n" +
+		"To resume the workflow from this step, run:\n" +
+		"atmos workflow deploy-infra -f workflow1 --from-step deploy-vpc\n\n" +
+		"For more details refer to https://atmos.tools/cli/commands/workflow/",
 	FParseErrWhitelist: struct{ UnknownFlags bool }{UnknownFlags: false},
 	Run: func(cmd *cobra.Command, args []string) {
 		err := e.ExecuteWorkflowCmd(cmd, args)
diff --git a/internal/exec/workflow_utils.go b/internal/exec/workflow_utils.go
index 08fed48cd..b788db98d 100644
--- a/internal/exec/workflow_utils.go
+++ b/internal/exec/workflow_utils.go
@@ -4,6 +4,7 @@ import (
 	"fmt"
 	"os"
 	"path"
+	"path/filepath"
 	"sort"
 	"strings"
 
@@ -70,11 +71,10 @@ func ExecuteWorkflow(
 			commandType = "atmos"
 		}
 
+		var err error
 		if commandType == "shell" {
 			commandName := fmt.Sprintf("%s-step-%d", workflow, stepIdx)
-			if err := ExecuteShell(cliConfig, command, commandName, ".", []string{}, dryRun); err != nil {
-				return err
-			}
+			err = ExecuteShell(cliConfig, command, commandName, ".", []string{}, dryRun)
 		} else if commandType == "atmos" {
 			args := strings.Fields(command)
 
@@ -101,12 +101,29 @@ func ExecuteWorkflow(
 				logFunc(cliConfig, fmt.Sprintf("Stack: %s", finalStack))
 			}
 
-			if err := ExecuteShellCommand(cliConfig, "atmos", args, ".", []string{}, dryRun, ""); err != nil {
-				return err
-			}
+			err = ExecuteShellCommand(cliConfig, "atmos", args, ".", []string{}, dryRun, "")
 		} else {
 			return fmt.Errorf("invalid workflow step type '%s'. Supported types are 'atmos' and 'shell'", commandType)
 		}
+
+		if err != nil {
+			workflowFileName := filepath.Base(workflowPath)
+			workflowFileName = strings.TrimSuffix(workflowFileName, filepath.Ext(workflowFileName))
+
+			failedMsg := color.New(color.FgRed).Sprintf("\nStep '%s' failed!", step.Name)
+
+			u.LogDebug(cliConfig, fmt.Sprintf("\nCommand failed: %s", command))
+			u.LogDebug(cliConfig, fmt.Sprintf("Error: %v", err))
+
+			resumeMsg := color.New(color.FgGreen).Sprintf(
+				"\nTo resume the workflow from this step, run:\natmos workflow %s -f %s --from-step %s",
+				workflow,
+				workflowFileName,
+				step.Name,
+			)
+
+			return fmt.Errorf("%s\n%s", failedMsg, resumeMsg)
+		}
 	}
 
 	return nil
diff --git a/website/docs/core-concepts/workflows/workflows.mdx b/website/docs/core-concepts/workflows/workflows.mdx
index c419c6555..f13a6b2e7 100644
--- a/website/docs/core-concepts/workflows/workflows.mdx
+++ b/website/docs/core-concepts/workflows/workflows.mdx
@@ -371,6 +371,40 @@ The Atmos stack used by the workflow commands of type `atmos` can be specified i
   atmos workflow my-workflow -f workflow1 -s tenant1-ue2-dev
   ```
 
+## Workflow Failure Handling and Resume
+
+When a workflow step fails, Atmos will:
+1. Display which step failed
+2. Show the exact command that failed 
+3. Provide a ready-to-use command to resume the workflow from the failed step
+
+Given this workflow:
+
+```yaml title="stacks/workflows/networking.yaml"
+workflows:
+  provision-vpcs:
+    description: "Deploy vpc components"
+    steps:
+      - command: terraform plan vpc -s plat-ue2-dev
+        name: step-1
+      - command: terraform plan vpc -s plat-ue2-staging
+        name: step-2
+      - command: terraform plan vpc -s plat-ue2-prod
+        name: step-3
+```
+
+If step-2 fails, you'll see:
+
+```console
+Step 'step-2' failed!
+
+Command failed: 
+terraform plan vpc -s plat-ue2-staging
+
+To resume the workflow from this step, run:
+atmos workflow provision-vpcs -f networking --from-step step-2
+```
+
 ### Stack Precedence
 
 The stack defined inline in the command itself has the lowest priority, it can and will be overridden by any other stack definition.