workflow 5.0.0-beta.5 → 5.0.0-beta.51

package/docs/cookbook/common-patterns/idempotency.mdx

@@ -1,45 +1,29 @@
 ---
 title: Idempotency
-description: Ensure external side effects happen exactly once, even when steps are retried or workflows are replayed.
+description: Make step retries safe and coordinate duplicate workflow starts with hook tokens.
 type: guide
-summary: Use step IDs as idempotency keys for external APIs like Stripe so that retries and replays don't create duplicate charges.
+summary: Use step IDs for retry-safe external calls, and use deterministic hook tokens when duplicate requests must route to one active workflow.
 ---
 
-Workflow steps can be retried (on failure) and replayed (on cold start). If a step calls an external API that isn't idempotent, retries could create duplicate charges, send duplicate emails, or double-process records. Use idempotency keys to make these operations safe.
+<CopyPrompt
+  text="Make this workflow's side effects idempotent. For retry-safe external calls, read the deterministic step ID inside the &quot;use step&quot; function with `getStepMetadata()` from `workflow` and pass `stepId` as the idempotency key to the external API (for example Stripe's `Idempotency-Key` header) so step retries deduplicate. For duplicate workflow starts, derive a deterministic hook token from the domain key (for example `order:${orderId}`): in the API route, look up the active hook with `getHookByToken(token)` from `workflow/api` (catching `HookNotFoundError` from `workflow/errors`) and reuse its `runId`, otherwise call `start(...)`; inside the workflow, create the hook with the same token and check `await hook.getConflict()` before duplicate-sensitive work. Verify retried steps deduplicate, duplicate starts reuse the active run, and conflicts are handled."
+/>
+
+Use idempotency when a retry or duplicate request should not repeat the underlying work. In Workflow, there are two common patterns: use the step ID for retry-safe external calls, and use hook tokens to coordinate duplicate workflow starts.
 
 ## When to use this
 
-- Charging a payment (Stripe, PayPal)
-- Sending transactional emails or SMS
-- Creating records in external systems where duplicates are harmful
-- Any step that has side effects in systems you don't control
+- A step charges a payment, sends an email, enqueues work, or creates an external record.
+- A route may receive duplicate requests that should map to one active workflow run.
 
-## Pattern: Step ID as idempotency key
+## Step idempotency
 
 Every step has a unique, deterministic `stepId` available via `getStepMetadata()`. Pass this as the idempotency key to external APIs:
 
 ```typescript
 import { getStepMetadata } from "workflow";
 
-declare function createCharge(customerId: string, amount: number): Promise<{ id: string }>; // @setup
-declare function sendReceipt(customerId: string, chargeId: string): Promise<void>; // @setup
-
-export async function chargeCustomer(customerId: string, amount: number) {
-  "use workflow";
-
-  const charge = await createCharge(customerId, amount);
-  await sendReceipt(customerId, charge.id);
-
-  return { customerId, chargeId: charge.id, status: "completed" };
-}
-```
-
-### Step function with idempotency key
-
-```typescript
-import { getStepMetadata } from "workflow";
-
-async function createCharge(
+export async function createCharge(
   customerId: string,
   amount: number
 ): Promise<{ id: string }> {
@@ -69,39 +53,43 @@ async function createCharge(
 
   return charge.json();
 }
-
-async function sendReceipt(customerId: string, chargeId: string): Promise<void> {
-  "use step";
-
-  const { stepId } = getStepMetadata();
-
-  await fetch("https://api.example.com/receipts", {
-    method: "POST",
-    headers: { "Idempotency-Key": stepId },
-    body: JSON.stringify({ customerId, chargeId }),
-  });
-}
 ```
 
-## Race condition caveats
+See [Step Idempotency](/docs/foundations/idempotency#step-idempotency) for why `stepId` is stable across retries and how to think about external API conflicts.
 
-Workflow does not currently provide distributed locking or true exactly-once delivery across concurrent runs. If two workflow runs could process the same entity concurrently:
+## Run idempotency
 
-- **Rely on the external API's idempotency** (like Stripe's `Idempotency-Key`) rather than checking a local flag.
-- **Don't use check-then-act patterns** like "read a flag, then write if not set" -- another run could read the same flag between your read and write.
+For duplicate workflow-start requests, derive a hook token from your domain key. You can avoid obvious duplicate starts by checking whether an active hook already owns that token before calling `start()`:
 
-If your external API doesn't support idempotency keys natively, consider adding a deduplication layer (e.g., a database unique constraint on the operation ID).
+```typescript
+import { getHookByToken, start } from "workflow/api";
+import { HookNotFoundError } from "workflow/errors";
+import { processOrder } from "./workflows/process-order";
+
+export async function POST(request: Request) {
+  const { orderId } = await request.json();
+  const token = `order:${orderId}`;
+
+  try {
+    const hook = await getHookByToken(token); // [!code highlight]
+    return Response.json({ runId: hook.runId, reused: true });
+  } catch (error) {
+    if (!HookNotFoundError.is(error)) throw error;
+  }
 
-## Tips
+  const run = await start(processOrder, [orderId]); // [!code highlight]
+  return Response.json({ runId: run.runId, reused: false });
+}
+```
 
-- **`stepId` is deterministic.** It's the same value across retries and replays of the same step, making it a reliable idempotency key.
-- **Always provide idempotency keys for non-idempotent external calls.** Even if you think a step won't be retried, cold-start replay will re-execute it.
-- **Handle 409/conflict as success.** If an external API returns "already processed," treat that as a successful result, not an error.
-- **Make your own APIs idempotent** where possible. Accept an idempotency key and return the cached result on duplicate requests.
+The workflow should create the deterministic hook and check `await hook.getConflict()` before duplicate-sensitive work: awaiting `getConflict()` suspends the workflow to commit the hook registration and resolves with the conflicting run when another active run already owns the token (or `null` once the hook is registered). See [Run idempotency](/docs/foundations/idempotency#run-idempotency) for the full pattern, including how to steer an active run with `resumeHook()` and how to handle the current race between `start()` and hook registration.
 
 ## Key APIs
 
-- [`"use workflow"`](/docs/api-reference/workflow/use-workflow) -- declares the orchestrator function
-- [`"use step"`](/docs/api-reference/workflow/use-step) -- declares step functions with full Node.js access
-- [`getStepMetadata()`](/docs/api-reference/step/get-step-metadata) -- provides the deterministic `stepId` for idempotency keys
-- [`start()`](/docs/api-reference/workflow-api/start) -- starts a new workflow run
+- [`"use workflow"`](/docs/foundations/workflows-and-steps#workflow-functions): Declares the orchestrator function.
+- [`"use step"`](/docs/foundations/workflows-and-steps#step-functions): Declares step functions with full Node.js access.
+- [`getStepMetadata()`](/docs/api-reference/workflow/get-step-metadata): Provides the deterministic `stepId` for idempotency keys.
+- [`createHook()`](/docs/api-reference/workflow/create-hook): Creates a hook with an optional deterministic token.
+- [`getHookByToken()`](/docs/api-reference/workflow-api/get-hook-by-token): Finds the hook that owns a token.
+- [`resumeHook()`](/docs/api-reference/workflow-api/resume-hook): Resumes the active hook when the duplicate request carries data.
+- [`start()`](/docs/api-reference/workflow-api/start): Starts a new workflow run.

package/docs/cookbook/common-patterns/rate-limiting.mdx

@@ -5,6 +5,10 @@ type: guide
 summary: When an external API returns 429, throw RetryableError with the Retry-After value so the workflow runtime automatically reschedules the step after the specified delay.
 ---
 
+<CopyPrompt
+  text="Add durable rate-limit handling to external API steps. Import `RetryableError`, `FatalError`, `getStepMetadata`, and `sleep` from `workflow` as needed. In each HTTP-calling &quot;use step&quot; helper, if the response status is 429, read the `Retry-After` header and throw `new RetryableError(&quot;Rate limited&quot;, { retryAfter })`. For transient 5xx/network failures, throw `RetryableError` with an exponential delay based on `getStepMetadata().attempt`. For permanent 4xx failures, throw `FatalError`. If the dependency is completely down, add a workflow-level circuit breaker that `await sleep(&quot;30s&quot;)` before probing again. Make requests idempotent with stable keys, and verify 429, 5xx, fatal 4xx, and circuit-breaker behavior."
+/>
+
 Use this pattern when calling external APIs that enforce rate limits. Instead of writing manual retry loops, throw `RetryableError` with a `retryAfter` value and let the workflow runtime handle rescheduling.
 
 ## When to use this
@@ -63,7 +67,7 @@ async function upsertToWarehouse(contactId: string, contact: unknown) {
 }
 ```
 
-## Pattern: Exponential backoff
+## Pattern: exponential backoff
 
 Use `getStepMetadata()` to access the current attempt number and calculate increasing delays:
 
@@ -86,7 +90,7 @@ async function callFlakeyApi(endpoint: string) {
 }
 ```
 
-## Pattern: Circuit breaker with sleep
+## Pattern: circuit breaker with sleep
 
 When a dependency is completely down, stop hitting it for a cooldown period using `sleep()`, then probe with a single test request:
 
@@ -134,7 +138,7 @@ async function callService(requestNum: number): Promise<boolean> {
 }
 ```
 
-## Pattern: Custom max retries
+## Pattern: custom max retries
 
 Override the default retry count (3) for steps that need more or fewer attempts:
 
@@ -224,5 +228,5 @@ export async function downloadWithRetry(url: string) {
 - [`"use step"`](/docs/foundations/workflows-and-steps) -- marks functions that run with full Node.js access
 - [`RetryableError`](/docs/api-reference/workflow/retryable-error) -- signals the runtime to retry after a delay
 - [`FatalError`](/docs/api-reference/workflow/fatal-error) -- signals a permanent failure, skipping retries
-- [`getStepMetadata()`](/docs/api-reference/step/get-step-metadata) -- provides the current attempt number and step ID
+- [`getStepMetadata()`](/docs/api-reference/workflow/get-step-metadata) -- provides the current attempt number and step ID
 - [`sleep()`](/docs/api-reference/workflow/sleep) -- durable pause for circuit breaker cooldowns

package/docs/cookbook/common-patterns/saga.mdx

@@ -5,6 +5,10 @@ type: guide
 summary: Run a sequence of steps where each registers a compensation. If any step throws a FatalError, compensations execute in reverse order to restore consistency.
 ---
 
+<CopyPrompt
+  text="Implement a saga-style workflow. Import `FatalError` from `workflow`. In the exported &quot;use workflow&quot; function, keep a compensation stack such as `const compensations: Array<() => Promise<void>> = []`. For each forward side effect, create a &quot;use step&quot; helper, await it, then push the matching compensation &quot;use step&quot; helper onto the stack. Throw `FatalError` for permanent business failures and normal errors for retryable failures. In the workflow catch block, run compensations in reverse order with `for (const compensate of compensations.reverse()) await compensate()`, then rethrow or return a failed status. Make each compensation idempotent. Verify successful completion, a fatal failure after multiple steps, and a replay/retry during rollback."
+/>
+
 Use the saga pattern when a business transaction spans multiple services and you need automatic rollback if any step fails. Each forward step registers a compensation, and on failure the workflow unwinds them in reverse order.
 
 ## When to use this
@@ -16,8 +20,8 @@ Use the saga pattern when a business transaction spans multiple services and you
 ## How it works
 
 1. Each forward step does work and registers a compensation function.
-2. If any step throws `FatalError`, the catch block runs compensations in reverse (LIFO) order to restore consistency.
-3. Regular errors are retried automatically (up to 3x by default). Use `FatalError` only for permanent failures where retrying won't help.
+2. If any step throws `FatalError`, the catch block runs compensations in reverse, or last in, first out (LIFO), order to restore consistency.
+3. Regular errors are retried automatically, up to three times by default. Use `FatalError` only for permanent failures where retrying won't help.
 
 ## Pattern
 
@@ -49,7 +53,7 @@ export async function subscriptionUpgradeSaga(accountId: string, seats: number)
     const entitlementId = await provisionSeats(accountId, seats);
     compensations.push(() => deprovisionSeats(accountId, entitlementId)); // [!code highlight]
 
-    // No compensation — notifications are fire-and-forget
+    // No compensation: notifications are fire-and-forget
     await sendConfirmation(accountId, invoiceId, entitlementId);
 
     return { status: "completed" };
@@ -66,7 +70,7 @@ export async function subscriptionUpgradeSaga(accountId: string, seats: number)
 
 ### Step functions
 
-Each step is a `"use step"` function with full Node.js access (fetch, fs, npm packages). Forward steps do the work and throw `FatalError` on permanent failure; compensation steps undo it and must be idempotent — safe to call multiple times if the workflow restarts mid-rollback.
+Each step is a `"use step"` function with full Node.js access (fetch, fs, npm packages). Forward steps do the work and throw `FatalError` on permanent failure; compensation steps undo it and must be idempotent: safe to call multiple times if the workflow restarts mid-rollback.
 
 ```typescript
 import { FatalError } from "workflow";
@@ -118,7 +122,7 @@ async function sendConfirmation(
   });
 }
 
-// Compensation steps — must be idempotent
+// Compensation steps: must be idempotent
 
 async function releaseSeats(accountId: string, reservationId: string): Promise<void> {
   "use step";
@@ -147,7 +151,7 @@ async function deprovisionSeats(accountId: string, entitlementId: string): Promi
 
 ### Streaming step progress (optional)
 
-Use `getWritable()` to stream progress events to a UI so users can see each step execute in real time.
+Use `getWritable()` to stream progress events to a user interface (UI) so users can see each step execute in real time.
 
 ```typescript
 import { FatalError } from "workflow";
@@ -200,7 +204,7 @@ export async function subscriptionUpgradeSaga(accountId: string, seats: number)
     compensations.push({ name: "Deprovision Seats", execute: () => deprovisionSeats(accountId, entitlementId) });
     await emit({ type: "step_done", step: "Provision Seats", detail: entitlementId });
 
-    // No compensation — notifications are fire-and-forget
+    // No compensation: notifications are fire-and-forget
     await emit({ type: "step_start", step: "Send Confirmation" });
     await sendConfirmation(accountId, invoiceId, entitlementId);
     await emit({ type: "step_done", step: "Send Confirmation", detail: "sent" });
@@ -227,21 +231,21 @@ export async function subscriptionUpgradeSaga(accountId: string, seats: number)
 ## Adapting to your use case
 
 - Replace the step functions with real API calls. Each `"use step"` function has full Node.js access.
-- Add or remove steps as needed — the pattern scales to any number of steps.
-- Make compensations idempotent — they may be retried if the workflow restarts mid-rollback.
-- The `emit()` calls and `SagaEvent` type are optional — remove them if you don't need real-time UI progress.
+- Add or remove steps as needed; the pattern scales to any number of steps.
+- Make compensations idempotent, since they may be retried if the workflow restarts mid-rollback.
+- The `emit()` calls and `SagaEvent` type are optional; remove them if you don't need real-time UI progress.
 
 ## Tips
 
-- **Use `FatalError` for permanent failures.** Regular errors trigger automatic retries (up to 3 by default). Throw `FatalError` when retrying won't help (e.g., insufficient funds, invalid input).
-- **Make compensations idempotent.** If a compensation step is retried, it should produce the same result. Check whether the resource was already released before releasing it again.
-- **Compensation steps are also `"use step"` functions.** This makes them durable — if the workflow restarts mid-rollback, it resumes where it left off.
-- **Capture values in closures carefully.** Use block-scoped variables or copy values before pushing compensations to avoid referencing stale state.
-- **Notifications don't need compensations.** Fire-and-forget steps like sending emails or Slack messages typically don't register a compensation.
+- **Use `FatalError` for permanent failures**: Regular errors trigger automatic retries, up to three times by default. Throw `FatalError` when retrying won't help, such as for insufficient funds or invalid input.
+- **Make compensations idempotent**: If a compensation step is retried, it should produce the same result. Check whether the resource was already released before releasing it again.
+- **Use `"use step"` functions for compensation steps**: This makes them durable. If the workflow restarts during rollback, it resumes where it left off.
+- **Capture values in closures carefully**: Use block-scoped variables or copy values before pushing compensations to avoid referencing stale state.
+- **Skip compensations for notifications**: Fire-and-forget steps such as sending emails or Slack messages typically don't register a compensation.
 
 ## Key APIs
 
-- [`"use workflow"`](/docs/api-reference/workflow/use-workflow) -- declares the orchestrator function
-- [`"use step"`](/docs/api-reference/workflow/use-step) -- declares step functions with full Node.js access
-- [`FatalError`](/docs/api-reference/workflow/fatal-error) -- non-retryable error that triggers compensation
-- [`getWritable()`](/docs/api-reference/workflow/get-writable) -- streams data from workflows for real-time UI updates
+- [`"use workflow"`](/docs/foundations/workflows-and-steps#workflow-functions): Declares the orchestrator function.
+- [`"use step"`](/docs/foundations/workflows-and-steps#step-functions): Declares step functions with full Node.js access.
+- [`FatalError`](/docs/api-reference/workflow/fatal-error): Represents a non-retryable error that triggers compensation.
+- [`getWritable()`](/docs/api-reference/workflow/get-writable): Streams data from workflows for real-time UI updates.

package/docs/cookbook/common-patterns/scheduling.mdx

@@ -5,17 +5,25 @@ type: guide
 summary: Schedule future actions with durable sleep that survives cold starts, and race sleeps against hooks to let external events cancel the workflow early.
 ---
 
-Workflow's `sleep()` is durable — it survives cold starts, restarts, and deployments. Combined with `defineHook()` and `Promise.race()`, it becomes the foundation for interruptible scheduled workflows like drip campaigns, reminders, and timed sequences.
+<CopyPrompt
+  text="Create an interruptible scheduled workflow. Import `defineHook` and `sleep` from `workflow`. Define a cancellation hook such as `export const cancelDrip = defineHook<{ reason?: string }>()`. In an exported workflow function with &quot;use workflow&quot;, create the hook once, send the first message in a &quot;use step&quot; helper, then `await Promise.race([sleep(&quot;2d&quot;).then(() => false), cancelHook.then(() => true)])` before each delayed action. If the hook wins, return a canceled status; if sleep wins, continue to the next step. Add an API route that calls `cancelDrip.resume(runIdOrToken, { reason })` or `resumeHook()` from `workflow/api`. Verify scheduled delivery, cancellation before sleep completes, and resume after server restart."
+/>
+
+Workflow's `sleep()` is durable: it survives cold starts, restarts, and deployments. Combined with `defineHook()` and `Promise.race()`, it becomes the foundation for interruptible scheduled workflows like drip campaigns, reminders, and timed sequences.
+
+<Callout type="info">
+Scheduled workflows are still pinned to the deployment that started them. If you are building recurring or indefinitely running schedules that should adopt newer code over time, see [Versioning](/docs/foundations/versioning) for the explicit `deploymentId: "latest"` continuation pattern.
+</Callout>
 
 ## When to use this
 
-- Sending emails on a schedule (drip campaigns, onboarding sequences, reminders)
-- Waiting for a deadline but allowing early cancellation
-- Any pattern where "do X, wait N hours, then do Y" needs to be both reliable and interruptible
+- Sending emails on a schedule, such as drip campaigns, onboarding sequences, or reminders
+- Waiting for a deadline while allowing early cancellation
+- Reliable, interruptible patterns that perform one action, wait for a specified time, and then perform another action
 
 ## Drip campaign with cancellation
 
-A drip campaign sends emails at intervals, sleeping between each. Each sleep races against a cancellation hook — if an external event fires the hook (e.g. user converts, unsubscribes), the campaign stops immediately.
+A drip campaign sends emails at intervals, sleeping between each message. Each sleep races against a cancellation hook. If an external event fires the hook, such as when a user converts or unsubscribes, the campaign stops immediately.
 
 ```typescript
 import { defineHook, sleep } from "workflow";
@@ -97,29 +105,33 @@ export async function POST(req: Request) {
 
 ## How it works
 
-1. **Durable sleep** — `sleep("2d")` persists through restarts at zero compute cost. The workflow resumes precisely when the timer fires.
-2. **Hook creation** — `cancelDrip.create({ token })` registers a hook that resolves when any external system calls `.resume()` with the same token.
-3. **Race** — `Promise.race([sleep(...), hook])` blocks until either the timer fires or the hook is resumed, whichever comes first.
-4. **Fresh hooks per window** — after a sleep completes normally, the previous hook instance is consumed. A new `.create()` call registers a fresh hook for the next sleep window, reusing the same token.
+1. **Durable sleep**: `sleep("2d")` persists through restarts at zero compute cost. The workflow resumes when the timer fires.
+2. **Hook creation**: `cancelDrip.create({ token })` registers a hook that resolves when any external system calls `.resume()` with the same token.
+3. **Race**: `Promise.race([sleep(...), hook])` blocks until either the timer fires or the hook is resumed, whichever comes first.
+4. **Fresh hooks per window**: After a sleep completes normally, the previous hook instance is consumed. A new `.create()` call registers a fresh hook for the next sleep window, reusing the same token.
+
+<Callout type="info">
+Deterministic hook tokens can also serve as the idempotency point for scheduled runs. If duplicate schedule starts would send duplicate campaigns or reminders, create a hook with a token derived from the campaign key near the beginning of the workflow and route retries through that hook. If two scheduled starts race, the duplicate run can detect the conflict early with `await hook.getConflict()`, which resolves with the active owner so the duplicate can defer to it. See [Idempotency](/docs/foundations/idempotency).
+</Callout>
 
 ## Adapting to your use case
 
-- **Change durations** — replace `"2d"` with any duration string (`"1h"`, `"7d"`, `"30m"`) or a `Date` object for absolute times.
-- **Add more steps** — the pattern scales to any number of email-then-sleep pairs.
-- **Snooze instead of cancel** — resolve the hook with a `snooze` payload and sleep again: `sleep(new Date(Date.now() + payload.snoozeMs))`.
-- **Timeout any operation** — the same `Promise.race(sleep, work)` pattern works for adding deadlines to slow steps.
-- **Real providers** — swap the `sendEmail` step body for Resend, Postmark, or any HTTP API. The `"use step"` function has full Node.js access.
+- **Change durations**: Replace `"2d"` with any duration string (`"1h"`, `"7d"`, or `"30m"`) or a `Date` object for absolute times.
+- **Add more steps**: The pattern scales to any number of email-then-sleep pairs.
+- **Snooze instead of cancel**: Resolve the hook with a `snooze` payload and sleep again with `sleep(new Date(Date.now() + payload.snoozeMs))`.
+- **Set a timeout for any operation**: Use the same `Promise.race(sleep, work)` pattern to add deadlines to slow steps.
+- **Use production providers**: Replace the `sendEmail` step body with Resend, Postmark, or any HTTP API. The `"use step"` function has full Node.js access.
 
 ## Tips
 
-- **`sleep()` accepts** duration strings (`"1d"`, `"2h"`, `"30s"`), milliseconds, or `Date` objects for sleeping until a specific time.
-- **Durable means durable.** A `sleep("7d")` workflow costs nothing while sleeping — no compute, no memory.
-- **Use `sleep()` in workflow context only.** Step functions cannot call `sleep()` directly. If a step needs a delay, use `setTimeout` inside the step.
+- **Pass supported values to `sleep()`**: Use duration strings (`"1d"`, `"2h"`, or `"30s"`), milliseconds, or `Date` objects for sleeping until a specific time.
+- **Sleeping consumes no compute or memory**: A workflow waiting on `sleep("7d")` consumes no compute or memory while sleeping.
+- **Use `sleep()` only in workflow context**: Step functions cannot call `sleep()` directly. If a step needs a delay, use `setTimeout` inside the step.
 
 ## Key APIs
 
-- [`"use workflow"`](/docs/foundations/workflows-and-steps) — marks the orchestrator function
-- [`"use step"`](/docs/foundations/workflows-and-steps) — marks functions that run with full Node.js access
-- [`sleep()`](/docs/api-reference/workflow/sleep) — durable wait (survives restarts, zero compute cost)
-- [`defineHook()`](/docs/api-reference/workflow/define-hook) — creates a typed hook that external systems can fire
-- [`Promise.race()`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise/race) — races sleep against hooks for interruptible waits
+- [`"use workflow"`](/docs/foundations/workflows-and-steps): Marks the orchestrator function.
+- [`"use step"`](/docs/foundations/workflows-and-steps): Marks functions that run with full Node.js access.
+- [`sleep()`](/docs/api-reference/workflow/sleep): Provides a durable wait that survives restarts with zero compute cost.
+- [`defineHook()`](/docs/api-reference/workflow/define-hook): Creates a typed hook that external systems can fire.
+- [`Promise.race()`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise/race): Races sleep against hooks for interruptible waits.

package/docs/cookbook/common-patterns/sequential-and-parallel.mdx

@@ -1,22 +1,26 @@
 ---
 title: Sequential & Parallel Execution
-description: Compose steps with familiar async/await patterns — sequential await, Promise.all, and Promise.race.
+description: Compose steps with familiar async/await patterns, sequential await, Promise.all, and Promise.race.
 type: guide
-summary: Workflows are just async functions, so all the standard composition primitives (await, Promise.all, Promise.race) apply unchanged — including racing webhooks against durable sleeps.
+summary: Workflows are plain async functions, so all the standard composition primitives (await, Promise.all, Promise.race) apply unchanged, including racing webhooks against durable sleeps.
 related:
   - /docs/foundations/workflows-and-steps
   - /cookbook/common-patterns/timeouts
   - /cookbook/common-patterns/scheduling
 ---
 
-Workflows are written in plain async/await — there's no new control-flow API to learn. Sequential awaits chain steps that depend on each other, `Promise.all` runs independent steps in parallel, and `Promise.race` returns whichever finishes first. These compose with workflow primitives like [`sleep()`](/docs/api-reference/workflow/sleep) and [`createWebhook()`](/docs/api-reference/workflow/create-webhook) since those are also just promises.
+<CopyPrompt
+  text="Compose these workflow steps with standard async/await patterns. In the exported &quot;use workflow&quot; function, chain dependent &quot;use step&quot; calls with sequential `await`; run independent steps concurrently by starting them without `await` and awaiting `Promise.all([...])`; and use `Promise.race([...])` to act on whichever promise settles first. These compose with durable primitives: race a step or a webhook from `createWebhook()` against `sleep()` from `workflow` for deadlines. Keep every step input and output serializable, and remember `Promise.race` does not cancel the losing branch (it keeps running), so side-effectful losers need idempotency keys. Verify sequential ordering, parallel execution, and both race outcomes."
+/>
+
+Workflows are written in plain async/await: there's no new control-flow API to learn. Sequential awaits chain steps that depend on each other, `Promise.all` runs independent steps in parallel, and `Promise.race` returns whichever finishes first. These compose with workflow primitives like [`sleep()`](/docs/api-reference/workflow/sleep) and [`createWebhook()`](/docs/api-reference/workflow/create-webhook) since those are also promises.
 
 ## When to use this
 
-- **Pipelines** — each step depends on the previous step's output (validate → process → store)
-- **Independent fan-out** — fetch multiple resources or perform multiple actions that don't depend on each other
-- **Race conditions** — return as soon as one of N operations completes (timeout, first-responder, deadline)
-- **Mixing primitives** — running steps, sleeps, and webhooks side-by-side in the same control-flow expression
+- **Pipelines**: Each step depends on the previous step's output (validate → process → store).
+- **Independent fan-out**: Fetch multiple resources or perform multiple actions that don't depend on each other.
+- **Race conditions**: Return as soon as one operation completes, such as for a timeout, first responder, or deadline.
+- **Mixing primitives**: Run steps, sleeps, and webhooks side by side in the same control-flow expression.
 
 ## Pattern
 
@@ -64,7 +68,7 @@ export async function fetchUserData(userId: string) {
 
 ### Race with `Promise.race`
 
-`Promise.race` resolves as soon as the first promise settles. Since [`sleep()`](/docs/api-reference/workflow/sleep) and [`createWebhook()`](/docs/api-reference/workflow/create-webhook) return promises, they compose naturally — for example, waiting for a webhook callback with a deadline:
+`Promise.race` resolves as soon as the first promise settles. Since [`sleep()`](/docs/api-reference/workflow/sleep) and [`createWebhook()`](/docs/api-reference/workflow/create-webhook) return promises, they compose naturally. For example, waiting for a webhook callback with a deadline:
 
 ```typescript lineNumbers
 import { sleep, createWebhook } from "workflow";
@@ -86,11 +90,11 @@ export async function runExternalTask(userId: string) {
 }
 ```
 
-For racing operations against deadlines specifically (timeouts), see the dedicated [Timeouts](/cookbook/common-patterns/timeouts) recipe — it covers result discrimination, `FatalError` semantics, and the "loser keeps running" caveat.
+For racing operations against deadlines specifically (timeouts), see the dedicated [Timeouts](/cookbook/common-patterns/timeouts) recipe, which covers result discrimination, `FatalError` semantics, and the "loser keeps running" caveat.
 
 ### Combining sequential, parallel, and durable primitives
 
-Most real workflows combine all three. Here's a simplified version of the [birthday card generator demo](https://github.com/vercel/workflow-examples/tree/main/birthday-card-generator) — sequential card generation, parallel RSVP fan-out, non-blocking webhook collection, and a durable sleep until the birthday:
+Most workflows combine all three patterns. The following simplified version of the [birthday card generator demo](https://github.com/vercel/workflow-examples/tree/main/birthday-card-generator) uses sequential card generation, parallel invitation-response fan-out, non-blocking webhook collection, and a durable sleep until the birthday:
 
 ```typescript lineNumbers
 import { createWebhook, sleep, type Webhook } from "workflow";
@@ -132,24 +136,24 @@ export async function birthdayWorkflow(
 
 ## How it works
 
-1. **`await` is durable.** When the workflow awaits a step, the runtime persists the step's input, suspends the workflow, runs the step, and replays the workflow with the step's result on resume. The same applies to `sleep()` and `createWebhook()`.
-2. **`Promise.all` runs steps concurrently.** Each promise in the array is suspended on its own and the workflow resumes only when all have settled. Failures propagate — if any promise rejects, the whole `Promise.all` rejects.
-3. **`Promise.race` resolves on the first settle.** The losing promises keep running in the background but their results are discarded by the workflow.
-4. **All primitives are promises.** `sleep("1 day")` and `createWebhook()` return promises, so they compose with `Promise.all` / `Promise.race` exactly like steps do — this is what makes patterns like "race a webhook against a 24-hour deadline" a one-liner.
+1. **`await` is durable**: When the workflow awaits a step, the runtime persists the step's input, suspends the workflow, runs the step, and replays the workflow with the step's result on resume. The same applies to `sleep()` and `createWebhook()`.
+2. **`Promise.all` runs steps concurrently**: Each promise in the array is suspended on its own, and the workflow resumes only when all have settled. If any promise rejects, the whole `Promise.all` rejects.
+3. **`Promise.race` resolves when the first promise settles**: The losing promises keep running in the background, but the workflow discards their results.
+4. **All primitives are promises**: `sleep("1 day")` and `createWebhook()` return promises, so they compose with `Promise.all` and `Promise.race` like steps do. This behavior enables patterns such as racing a webhook against a 24-hour deadline.
 
 ## Adapting to your use case
 
-- **Replace `Promise.all` with `Promise.allSettled`** when partial failures should not abort the rest. You'll get an array of `{ status, value | reason }` instead of throwing on the first rejection.
-- **Bound the parallelism** — `Promise.all` over 1000 items will fan out 1000 concurrent steps. If your downstream APIs can't handle that, batch the array into chunks (see [Batching](/cookbook/common-patterns/batching)).
-- **Add a deadline to any race** — pair the operation with `sleep("30s").then(() => "timeout" as const)` and check the discriminated result. See [Timeouts](/cookbook/common-patterns/timeouts).
-- **Mix steps and hooks in a race** — wait for an external signal *or* a deadline *or* a step result, all in the same `Promise.race`. The first one to resolve wins.
+- **Replace `Promise.all` with `Promise.allSettled`**: Use this option when partial failures shouldn't abort the remaining operations. You'll get an array of `{ status, value | reason }` instead of an error on the first rejection.
+- **Bound the parallelism**: `Promise.all` over 1,000 items will fan out 1,000 concurrent steps. If your downstream APIs can't handle that, batch the array into chunks (see [Batching](/cookbook/common-patterns/batching)).
+- **Add a deadline to any race**: Pair the operation with `sleep("30s").then(() => "timeout" as const)` and check the discriminated result. See [Timeouts](/cookbook/common-patterns/timeouts).
+- **Mix steps and hooks in a race**: Wait for an external signal, a deadline, or a step result in the same `Promise.race`. The first promise to resolve wins.
 
 ## Key APIs
 
-- [`"use workflow"`](/docs/foundations/workflows-and-steps) — marks the orchestrator function
-- [`"use step"`](/docs/foundations/workflows-and-steps) — marks functions with full Node.js access
-- [`sleep()`](/docs/api-reference/workflow/sleep) — durable sleep that survives restarts
-- [`createWebhook()`](/docs/api-reference/workflow/create-webhook) — webhook URL the workflow can race against
-- [`Promise.all()`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise/all) — wait for all promises
-- [`Promise.race()`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise/race) — wait for the first to settle
-- [`Promise.allSettled()`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise/allSettled) — wait for all, including failures
+- [`"use workflow"`](/docs/foundations/workflows-and-steps): Marks the orchestrator function.
+- [`"use step"`](/docs/foundations/workflows-and-steps): Marks functions with full Node.js access.
+- [`sleep()`](/docs/api-reference/workflow/sleep): Provides durable sleep that survives restarts.
+- [`createWebhook()`](/docs/api-reference/workflow/create-webhook): Provides a webhook URL that the workflow can race against.
+- [`Promise.all()`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise/all): Waits for all promises.
+- [`Promise.race()`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise/race): Waits for the first promise to settle.
+- [`Promise.allSettled()`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise/allSettled): Waits for all promises, including failures.

package/docs/cookbook/common-patterns/timeouts.mdx

@@ -2,7 +2,7 @@
 title: Timeouts
 description: Add deadlines to slow operations by racing them against a durable sleep.
 type: guide
-summary: Use `Promise.race` with `sleep()` to bound the time any step, hook, or webhook is allowed to take — and recover gracefully when the deadline fires first.
+summary: Use `Promise.race` with `sleep()` to bound the time any step, hook, or webhook is allowed to take, and recover gracefully when the deadline fires first.
 related:
   - /docs/api-reference/workflow/sleep
   - /docs/foundations/hooks
@@ -10,14 +10,18 @@ related:
   - /cookbook/common-patterns/webhooks
 ---
 
-A common requirement is bounding how long a workflow waits for something to finish — a slow step, an external webhook, a human approval. Race the operation against a durable `sleep()` with `Promise.race()` — whichever finishes first wins, and the loser keeps running but its result is ignored.
+<CopyPrompt
+  text="Add a deadline to this slow workflow operation. Import `sleep` from `workflow`. In the exported &quot;use workflow&quot; function, race the operation against a durable sleep: `await Promise.race([slowStep(...), deadline(&quot;10m&quot;)])`, where `deadline` is a helper that awaits `sleep(duration)` and returns a sentinel value or throws. Branch on the winner: continue normally on success, run the fallback or compensation path on timeout. Use the same pattern to bound hooks and webhooks. `Promise.race` does not cancel the loser (the underlying step keeps running), so pass an `AbortSignal` into the step for cooperative cancellation and make non-idempotent side effects retry-safe with idempotency keys. Verify the fast path, the timeout path, and side-effect safety when the loser completes late."
+/>
+
+Workflows often need to limit how long they wait for a slow step, an external webhook, or human approval. Race the operation against a durable `sleep()` with `Promise.race()`. The first operation to finish wins, while the other keeps running and its result is ignored.
 
 ## When to use this
 
-- **Slow steps** — bound the time spent waiting on third-party APIs, model calls, or expensive computation
-- **External callbacks** — give webhooks a deadline so the workflow doesn't hang forever waiting for an event that may never arrive
-- **Human approvals** — auto-decline or escalate when a hook isn't resumed within a window
-- **Polling loops** — give an outer poll-until-ready loop an overall budget
+- **Slow steps**: bound the time spent waiting on third-party APIs, model calls, or expensive computation
+- **External callbacks**: give webhooks a deadline so the workflow doesn't hang forever waiting for an event that may never arrive
+- **Human approvals**: auto-decline or escalate when a hook isn't resumed within a window
+- **Polling loops**: give an outer poll-until-ready loop an overall budget
 
 ## Pattern
 
@@ -46,7 +50,7 @@ export async function processWithTimeout(data: string) {
 
 ### Timeout on a webhook
 
-The same pattern works for any promise — including hooks and webhooks. Here a webhook waits for an external service to call back, with a hard deadline of 7 days:
+The same pattern works for any promise, including hooks and webhooks. Here a webhook waits for an external service to call back, with a hard deadline of 7 days:
 
 ```typescript lineNumbers
 import { sleep, createWebhook } from "workflow";
@@ -74,26 +78,27 @@ export async function waitForApproval(requestId: string) {
 
 ## How it works
 
-1. **Durable sleep** — `sleep("30s")` persists through restarts at zero compute cost. The workflow resumes precisely when the timer fires.
-2. **Race** — `Promise.race([work, sleep(...)])` returns the value of whichever promise resolves first. The loser keeps running in the background but its result is ignored by the workflow.
-3. **Discriminated result** — tagging the sleep branch with a sentinel value (`"timeout" as const`, `{ timedOut: true }`) lets TypeScript narrow the result and pick the right branch.
-4. **Throw to fail the workflow** — inside a workflow function, throwing an `Error` exits the run with that error. Use `FatalError` inside steps; throw plain errors inside workflows.
+1. **Durable sleep**: `sleep("30s")` persists through restarts at zero compute cost. The workflow resumes precisely when the timer fires.
+2. **Race**: `Promise.race([work, sleep(...)])` returns the value of whichever promise resolves first. The loser keeps running in the background but its result is ignored by the workflow.
+3. **Discriminated result**: tagging the sleep branch with a sentinel value (`"timeout" as const`, `{ timedOut: true }`) lets TypeScript narrow the result and pick the right branch.
+4. **Throw to fail the workflow**: inside a workflow function, throwing an `Error` exits the run with that error. Use `FatalError` inside steps; throw plain errors inside workflows.
 
 <Callout type="warn">
-**The losing operation keeps running.** `Promise.race` doesn't cancel — when the sleep wins, the underlying step (or model call, or HTTP request) continues to completion in the background. This is fine for idempotent reads but matters when the operation has side effects or costs money. Pass an `AbortSignal` into the step to cancel it cooperatively — see the [Cancellation Guide](/docs/foundations/cancellation) for patterns.
+**The losing operation keeps running.** `Promise.race` doesn't cancel: when the sleep wins, the underlying step (or model call, or HTTP request) continues to completion in the background. This is fine for idempotent reads but matters when the operation has side effects or costs money. Pass an `AbortSignal` into the step to cancel it cooperatively, and use idempotency keys for non-idempotent side effects. See the [Cancellation Guide](/docs/foundations/cancellation) and [Idempotency](/docs/foundations/idempotency) for patterns.
 </Callout>
 
 ## Adapting to your use case
 
-- **Different durations** — `sleep()` accepts duration strings (`"30s"`, `"5m"`, `"7 days"`), milliseconds, or `Date` objects for absolute deadlines.
-- **Soft timeout (retry)** — instead of throwing, loop and retry with a fresh `Promise.race` and a backoff.
-- **Soft timeout (fallback)** — return a default value when the timer wins instead of throwing: `if (result === "timeout") return cachedFallback`.
-- **Combine with cancellation** — race three promises: the operation, a deadline `sleep()`, and a cancellation hook. See the [Scheduling cookbook](/cookbook/common-patterns/scheduling) for the cancellation half of this pattern.
-- **Per-step deadlines** — wrap each step in its own `Promise.race` for independent budgets, or use a single outer race for an overall workflow deadline.
+- **Different durations**: `sleep()` accepts duration strings (`"30s"`, `"5m"`, `"7 days"`), milliseconds, or `Date` objects for absolute deadlines.
+- **Soft timeout (retry)**: instead of throwing, loop and retry with a fresh `Promise.race` and a backoff.
+- **Soft timeout (fallback)**: return a default value when the timer wins instead of throwing: `if (result === "timeout") return cachedFallback`.
+- **Combine with cancellation**: race three promises: the operation, a deadline `sleep()`, and a cancellation hook. See the [Scheduling cookbook](/cookbook/common-patterns/scheduling) for the cancellation half of this pattern.
+- **Per-step deadlines**: wrap each step in its own `Promise.race` for independent budgets, or use a single outer race for an overall workflow deadline.
 
 ## Key APIs
 
-- [`sleep()`](/docs/api-reference/workflow/sleep) — durable wait (survives restarts, zero compute cost)
-- [`createWebhook()`](/docs/api-reference/workflow/create-webhook) — create a webhook URL the workflow can race against
-- [`defineHook()`](/docs/api-reference/workflow/define-hook) — typed hook for in-process cancellation
-- [`Promise.race()`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise/race) — race operations against deadlines
+- [`sleep()`](/docs/api-reference/workflow/sleep): durable wait (survives restarts, zero compute cost)
+- [`createWebhook()`](/docs/api-reference/workflow/create-webhook): create a webhook URL the workflow can race against
+- [`defineHook()`](/docs/api-reference/workflow/define-hook): typed hook for in-process cancellation
+- [Idempotency](/docs/foundations/idempotency): protect side effects that may keep running after a timeout
+- [`Promise.race()`](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise/race): race operations against deadlines