saga-orchestration

Saga Orchestration

Patterns for managing distributed transactions and long-running business processes.

Do not use this skill when

• The task is unrelated to saga orchestration
• You need a different domain or tool outside this scope

Instructions

• Clarify goals, constraints, and required inputs.
• Apply relevant best practices and validate outcomes.
• Provide actionable steps and verification.
• If detailed examples are required, open resources/implementation-playbook.md.

Use this skill when

• Coordinating multi-service transactions
• Implementing compensating transactions
• Managing long-running business workflows
• Handling failures in distributed systems
• Building order fulfillment processes
• Implementing approval workflows

Core Concepts

1. Saga Types

Choreography                    Orchestration
┌─────┐  ┌─────┐  ┌─────┐     ┌─────────────┐
│Svc A│─►│Svc B│─►│Svc C│     │ Orchestrator│
└─────┘  └─────┘  └─────┘     └──────┬──────┘
   │        │        │               │
   ▼        ▼        ▼         ┌─────┼─────┐
 Event    Event    Event       ▼     ▼     ▼
                            ┌────┐┌────┐┌────┐
                            │Svc1││Svc2││Svc3│
                            └────┘└────┘└────┘

2. Saga Execution States

Templates

Template 1: Saga Orchestrator Base

from abc import ABC, abstractmethod
from dataclasses import dataclass, field
from enum import Enum
from typing import List, Dict, Any, Optional
from datetime import datetime
import uuid

class SagaState(Enum):
    STARTED = "started"
    PENDING = "pending"
    COMPENSATING = "compensating"
    COMPLETED = "completed"
    FAILED = "failed"


@dataclass
class SagaStep:
    name: str
    action: str
    compensation: str
    status: str = "pending"
    result: Optional[Dict] = None
    error: Optional[str] = None
    executed_at: Optional[datetime] = None
    compensated_at: Optional[datetime] = None


@dataclass
class Saga:
    saga_id: str
    saga_type: str
    state: SagaState
    data: Dict[str, Any]
    steps: List[SagaStep]
    current_step: int = 0
    created_at: datetime = field(default_factory=datetime.utcnow)
    updated_at: datetime = field(default_factory=datetime.utcnow)


class SagaOrchestrator(ABC):
    """Base class for saga orchestrators."""

    def __init__(self, saga_store, event_publisher):
        self.saga_store = saga_store
        self.event_publisher = event_publisher

    @abstractmethod
    def define_steps(self, data: Dict) -> List[SagaStep]:
        """Define the saga steps."""
        pass

    @property
    @abstractmethod
    def saga_type(self) -> str:
        """Unique saga type identifier."""
        pass

    async def start(self, data: Dict) -> Saga:
        """Start a new saga."""
        saga = Saga(
            saga_id=str(uuid.uuid4()),
            saga_type=self.saga_type,
            state=SagaState.STARTED,
            data=data,
            steps=self.define_steps(data)
        )
        await self.saga_store.save(saga)
        await self._execute_next_step(saga)
        return saga

    async def handle_step_completed(self, saga_id: str, step_name: str, result: Dict):
        """Handle successful step completion."""
        saga = await self.saga_store.get(saga_id)

        # Update step
        for step in saga.steps:
            if step.name == step_name:
                step.status = "completed"
                step.result = result
                step.executed_at = datetime.utcnow()
                break

        saga.current_step += 1
        saga.updated_at = datetime.utcnow()

        # Check if saga is complete
        if saga.current_step >= len(saga.steps):
            saga.state = SagaState.COMPLETED
            await self.saga_store.save(saga)
            await self._on_saga_completed(saga)
        else:
            saga.state = SagaState.PENDING
            await self.saga_store.save(saga)
            await self._execute_next_step(saga)

    async def handle_step_failed(self, saga_id: str, step_name: str, error: str):
        """Handle step failure - start compensation."""
        saga = await self.saga_store.get(saga_id)

        # Mark step as failed
        for step in saga.steps:
            if step.name == step_name:
                step.status = "failed"
                step.error = error
                break

        saga.state = SagaState.COMPENSATING
        saga.updated_at = datetime.utcnow()
        await self.saga_store.save(saga)

        # Start compensation from current step backwards
        await self._compensate(saga)

    async def _execute_next_step(self, saga: Saga):
        """Execute the next step in the saga."""
        if saga.current_step >= len(saga.steps):
            return

        step = saga.steps[saga.current_step]
        step.status = "executing"
        await self.saga_store.save(saga)

        # Publish command to execute step
        await self.event_publisher.publish(
            step.action,
            {
                "saga_id": saga.saga_id,
                "step_name": step.name,
                **saga.data
            }
        )

    async def _compensate(self, saga: Saga):
        """Execute compensation for completed steps."""
        # Compensate in reverse order
        for i in range(saga.current_step - 1, -1, -1):
            step = saga.steps[i]
            if step.status == "completed":
                step.status = "compensating"
                await self.saga_store.save(saga)

                await self.event_publisher.publish(
                    step.compensation,
                    {
                        "saga_id": saga.saga_id,
                        "step_name": step.name,
                        "original_result": step.result,
                        **saga.data
                    }
                )

    async def handle_compensation_completed(self, saga_id: str, step_name: str):
        """Handle compensation completion."""
        saga = await self.saga_store.get(saga_id)

        for step in saga.steps:
            if step.name == step_name:
                step.status = "compensated"
                step.compensated_at = datetime.utcnow()
                break

        # Check if all compensations complete
        all_compensated = all(
            s.status in ("compensated", "pending", "failed")
            for s in saga.steps
        )

        if all_compensated:
            saga.state = SagaState.FAILED
            await self._on_saga_failed(saga)

        await self.saga_store.save(saga)

    async def _on_saga_completed(self, saga: Saga):
        """Called when saga completes successfully."""
        await self.event_publisher.publish(
            f"{self.saga_type}Completed",
            {"saga_id": saga.saga_id, **saga.data}
        )

    async def _on_saga_failed(self, saga: Saga):
        """Called when saga fails after compensation."""
        await self.event_publisher.publish(
            f"{self.saga_type}Failed",
            {"saga_id": saga.saga_id, "error": "Saga failed", **saga.data}
        )

Template 2: Order Fulfillment Saga

class OrderFulfillmentSaga(SagaOrchestrator):
    """Orchestrates order fulfillment across services."""

    @property
    def saga_type(self) -> str:
        return "OrderFulfillment"

    def define_steps(self, data: Dict) -> List[SagaStep]:
        return [
            SagaStep(
                name="reserve_inventory",
                action="InventoryService.ReserveItems",
                compensation="InventoryService.ReleaseReservation"
            ),
            SagaStep(
                name="process_payment",
                action="PaymentService.ProcessPayment",
                compensation="PaymentService.RefundPayment"
            ),
            SagaStep(
                name="create_shipment",
                action="ShippingService.CreateShipment",
                compensation="ShippingService.CancelShipment"
            ),
            SagaStep(
                name="send_confirmation",
                action="NotificationService.SendOrderConfirmation",
                compensation="NotificationService.SendCancellationNotice"
            )
        ]


# Usage
async def create_order(order_data: Dict):
    saga = OrderFulfillmentSaga(saga_store, event_publisher)
    return await saga.start({
        "order_id": order_data["order_id"],
        "customer_id": order_data["customer_id"],
        "items": order_data["items"],
        "payment_method": order_data["payment_method"],
        "shipping_address": order_data["shipping_address"]
    })


# Event handlers in each service
class InventoryService:
    async def handle_reserve_items(self, command: Dict):
        try:
            # Reserve inventory
            reservation = await self.reserve(
                command["items"],
                command["order_id"]
            )
            # Report success
            await self.event_publisher.publish(
                "SagaStepCompleted",
                {
                    "saga_id": command["saga_id"],
                    "step_name": "reserve_inventory",
                    "result": {"reservation_id": reservation.id}
                }
            )
        except InsufficientInventoryError as e:
            await self.event_publisher.publish(
                "SagaStepFailed",
                {
                    "saga_id": command["saga_id"],
                    "step_name": "reserve_inventory",
                    "error": str(e)
                }
            )

    async def handle_release_res

---

*Content truncated.*