checkpoint-workflow-builder

Checkpoint Workflow Builder

Design and implement fault-tolerant workflows that can resume from any point of failure.

Overview

Complex workflows often fail mid-execution due to:

• Network timeouts
• System crashes
• Resource exhaustion
• External service failures
• User interruptions

This skill teaches you to build workflows that:

• Save progress at key checkpoints
• Resume from last successful state
• Handle partial failures gracefully
• Provide clear progress visibility
• Enable manual intervention points

When to Use

Use this skill when:

• Building multi-phase data pipelines
• Implementing long-running migration scripts
• Creating deployment workflows
• Processing large batches of items
• Orchestrating multi-system operations
• Building ETL (Extract, Transform, Load) workflows
• Implementing saga patterns for distributed systems
• Creating user-facing wizards with save/resume

Core Concepts

State Machine Pattern

┌─────────┐
│  INIT   │
└────┬────┘
     │
     ▼
┌────────────┐
│  DOWNLOAD  │
└─────┬──────┘
      │
      ▼
┌────────────┐
│  PROCESS   │
└─────┬──────┘
      │
      ▼
┌────────────┐
│  VALIDATE  │
└─────┬──────┘
      │
      ▼
┌────────────┐
│  FINALIZE  │
└─────┬──────┘
      │
      ▼
┌────────────┐
│  COMPLETE  │
└────────────┘

Each state:

• Has clear entry conditions
• Performs specific operations
• Saves checkpoint before transition
• Can be resumed independently

Basic Implementation

Simple State Machine

#!/bin/bash
# state-machine.sh - Basic resumable workflow

STATE_FILE=".workflow_state"

# Read current state (default: INIT)
CURRENT_STATE=$(cat "$STATE_FILE" 2>/dev/null || echo "INIT")

echo "Current state: $CURRENT_STATE"

case "$CURRENT_STATE" in
    INIT)
        echo "=== Phase 1: Initialization ==="

        # Initialize workspace
        mkdir -p workspace
        mkdir -p results

        # Download dependencies
        echo "Setting up environment..."

        # Save next state
        echo "DOWNLOAD" > "$STATE_FILE"
        echo "✓ Initialization complete"
        echo "Run again to continue"
        ;;

    DOWNLOAD)
        echo "=== Phase 2: Download Data ==="

        # Download data files
        echo "Downloading data..."
        # curl -o workspace/data.zip https://example.com/data.zip

        # Verify download
        if [ -f "workspace/data.zip" ]; then
            echo "EXTRACT" > "$STATE_FILE"
            echo "✓ Download complete"
            echo "Run again to continue"
        else
            echo "✗ Download failed - fix and run again"
            exit 1
        fi
        ;;

    EXTRACT)
        echo "=== Phase 3: Extract Data ==="

        # Extract files
        echo "Extracting data..."
        # unzip workspace/data.zip -d workspace/

        echo "PROCESS" > "$STATE_FILE"
        echo "✓ Extraction complete"
        echo "Run again to continue"
        ;;

    PROCESS)
        echo "=== Phase 4: Process Data ==="

        # Process data
        echo "Processing data..."
        # ./process_data.sh workspace/ results/

        echo "VALIDATE" > "$STATE_FILE"
        echo "✓ Processing complete"
        echo "Run again to continue"
        ;;

    VALIDATE)
        echo "=== Phase 5: Validate Results ==="

        # Validate results
        echo "Validating results..."
        # ./validate.sh results/

        if [ $? -eq 0 ]; then
            echo "FINALIZE" > "$STATE_FILE"
            echo "✓ Validation passed"
            echo "Run again to finalize"
        else
            echo "✗ Validation failed"
            echo "Fix issues and change state to PROCESS to reprocess"
            exit 1
        fi
        ;;

    FINALIZE)
        echo "=== Phase 6: Finalize ==="

        # Cleanup and finalize
        echo "Finalizing workflow..."
        # mv results/ final/
        # rm -rf workspace/

        echo "COMPLETE" > "$STATE_FILE"
        echo "✓ Workflow complete!"
        ;;

    COMPLETE)
        echo "=== Workflow Already Complete ==="
        echo "Results available in: final/"
        ;;

    *)
        echo "✗ Unknown state: $CURRENT_STATE"
        echo "Reset with: echo 'INIT' > $STATE_FILE"
        exit 1
        ;;
esac

Enhanced with Progress Tracking

#!/bin/bash
# enhanced-state-machine.sh - With detailed progress

STATE_FILE=".workflow_state"
PROGRESS_FILE=".workflow_progress.json"

# Initialize progress tracking
init_progress() {
    cat > "$PROGRESS_FILE" << EOF
{
  "current_state": "INIT",
  "started_at": "$(date -Iseconds)",
  "updated_at": "$(date -Iseconds)",
  "phases": {
    "INIT": {"status": "pending", "started": null, "completed": null},
    "DOWNLOAD": {"status": "pending", "started": null, "completed": null},
    "PROCESS": {"status": "pending", "started": null, "completed": null},
    "VALIDATE": {"status": "pending", "started": null, "completed": null},
    "FINALIZE": {"status": "pending", "started": null, "completed": null}
  }
}
EOF
}

# Update progress
update_progress() {
    local state="$1"
    local status="$2"  # "running", "completed", "failed"

    local timestamp="$(date -Iseconds)"

    if [ ! -f "$PROGRESS_FILE" ]; then
        init_progress
    fi

    jq --arg state "$state" \
       --arg status "$status" \
       --arg timestamp "$timestamp" \
       '.current_state = $state |
        .updated_at = $timestamp |
        .phases[$state].status = $status |
        (.phases[$state].started //= $timestamp) |
        (if $status == "completed" then .phases[$state].completed = $timestamp else . end)' \
       "$PROGRESS_FILE" > "$PROGRESS_FILE.tmp"

    mv "$PROGRESS_FILE.tmp" "$PROGRESS_FILE"
}

# Show progress
show_progress() {
    if [ ! -f "$PROGRESS_FILE" ]; then
        echo "No progress file found"
        return
    fi

    echo "=== Workflow Progress ==="
    echo ""
    jq -r '.phases | to_entries | .[] |
        "[\(.value.status | ascii_upcase)] \(.key)" +
        (if .value.started then " (started: " + .value.started + ")" else "" end)' \
        "$PROGRESS_FILE"
    echo ""
    echo "Current: $(jq -r '.current_state' $PROGRESS_FILE)"
    echo "Updated: $(jq -r '.updated_at' $PROGRESS_FILE)"
}

# Workflow implementation
run_workflow() {
    CURRENT_STATE=$(cat "$STATE_FILE" 2>/dev/null || echo "INIT")

    # Show progress before executing
    show_progress

    case "$CURRENT_STATE" in
        INIT)
            update_progress "INIT" "running"
            echo "Initializing..."
            # ... initialization logic ...
            update_progress "INIT" "completed"
            echo "DOWNLOAD" > "$STATE_FILE"
            ;;

        DOWNLOAD)
            update_progress "DOWNLOAD" "running"
            echo "Downloading..."
            # ... download logic ...
            update_progress "DOWNLOAD" "completed"
            echo "PROCESS" > "$STATE_FILE"
            ;;

        # ... other states ...
    esac
}

run_workflow

Advanced Patterns

Pattern 1: Batched Checkpoint

#!/bin/bash
# batched-checkpoint.sh - Process items with batch checkpoints

ITEMS_FILE="items.txt"
CHECKPOINT_FILE=".batch_checkpoint"
BATCH_SIZE=10

# Load checkpoint
if [ -f "$CHECKPOINT_FILE" ]; then
    LAST_COMPLETED=$(cat "$CHECKPOINT_FILE")
    echo "Resuming from item $LAST_COMPLETED"
else
    LAST_COMPLETED=0
fi

TOTAL_ITEMS=$(wc -l < "$ITEMS_FILE")
ITEMS_PROCESSED=0

# Process in batches
tail -n +$((LAST_COMPLETED + 1)) "$ITEMS_FILE" | while read -r item; do
    # Process item
    echo "Processing: $item"
    process_item "$item"

    ITEMS_PROCESSED=$((ITEMS_PROCESSED + 1))

    # Checkpoint every batch
    if [ $((ITEMS_PROCESSED % BATCH_SIZE)) -eq 0 ]; then
        CURRENT_POSITION=$((LAST_COMPLETED + ITEMS_PROCESSED))
        echo "$CURRENT_POSITION" > "$CHECKPOINT_FILE"

        echo "Checkpoint: $CURRENT_POSITION/$TOTAL_ITEMS"

        # Optional: Break for timeout management
        if [ $((ITEMS_PROCESSED)) -ge $((BATCH_SIZE * 5)) ]; then
            echo "Processed 5 bat