Changelog

When using a Worker with the nodejs_compat compatibility flag enabled, the following Node.js APIs are now available:

• node:crypto
• node:tls

This make it easier to reuse existing Node.js code in Workers or use npm packages that depend on these APIs.

The full node:crypto ↗ API is now available in Workers.

You can use it to verify and sign data:

import { sign, verify } from "node:crypto";

const signature = sign("sha256", "-data to sign-", env.PRIVATE_KEY);
const verified = verify("sha256", "-data to sign-", env.PUBLIC_KEY, signature);

Or, to encrypt and decrypt data:

import { publicEncrypt, privateDecrypt } from "node:crypto";

const encrypted = publicEncrypt(env.PUBLIC_KEY, "some data");
const plaintext = privateDecrypt(env.PRIVATE_KEY, encrypted);

See the node:crypto documentation for more information.

The following APIs from node:tls are now available:

• connect ↗
• TLSSocket ↗
• checkServerIdentity ↗
• createSecureContext ↗

This enables secure connections over TLS (Transport Layer Security) to external services.

import { connect } from "node:tls";

// ... in a request handler ...
const connectionOptions = { key: env.KEY, cert: env.CERT };
const socket = connect(url, connectionOptions, () => {
	if (socket.authorized) {
		console.log("Connection authorized");
	}
});

socket.on("data", (data) => {
	console.log(data);
});

socket.on("end", () => {
	console.log("server ends connection");
});

See the node:tls documentation for more information.

The Cloudflare Vite plugin has reached v1.0 ↗ and is now Generally Available ("GA").

When you use @cloudflare/vite-plugin, you can use Vite's local development server and build tooling, while ensuring that while developing, your code runs in workerd ↗, the open-source Workers runtime.

This lets you get the best of both worlds for a full-stack app — you can use Hot Module Replacement ↗ from Vite right alongside Durable Objects and other runtime APIs and bindings that are unique to Cloudflare Workers.

@cloudflare/vite-plugin is made possible by the new environment API ↗ in Vite, and was built in partnership with the Vite team ↗.

You can build any type of application with @cloudflare/vite-plugin, using any rendering mode, from single page applications (SPA) and static sites to server-side rendered (SSR) pages and API routes.

React Router v7 (Remix) is the first full-stack framework to provide full support for Cloudflare Vite plugin, allowing you to use all parts of Cloudflare's developer platform, without additional build steps.

You can also build complete full-stack apps on Workers without a framework — "just use Vite" ↗ and React together, and build a back-end API in the same Worker. Follow our React SPA with an API tutorial to learn how.

If you're already using Vite ↗ in your build and development toolchain, you can start using our plugin with minimal changes to your vite.config.ts:

import { defineConfig } from "vite";
import { cloudflare } from "@cloudflare/vite-plugin";

export default defineConfig({
	plugins: [cloudflare()],
});

Take a look at the documentation for our Cloudflare Vite plugin for more information!

The Agents SDK now includes built-in support for building remote MCP (Model Context Protocol) servers directly as part of your Agent. This allows you to easily create and manage MCP servers, without the need for additional infrastructure or configuration.

The SDK includes a new MCPAgent class that extends the Agent class and allows you to expose resources and tools over the MCP protocol, as well as authorization and authentication to enable remote MCP servers.

export class MyMCP extends McpAgent {
	server = new McpServer({
		name: "Demo",
		version: "1.0.0",
	});

	async init() {
		this.server.resource(`counter`, `mcp://resource/counter`, (uri) => {
			// ...
		});

		this.server.tool(
			"add",
			"Add two numbers together",
			{ a: z.number(), b: z.number() },
			async ({ a, b }) => {
				// ...
			},
		);
	}
}

export class MyMCP extends McpAgent<Env> {
	server = new McpServer({
		name: "Demo",
		version: "1.0.0",
	});

	async init() {
		this.server.resource(`counter`, `mcp://resource/counter`, (uri) => {
			// ...
		});

		this.server.tool(
			"add",
			"Add two numbers together",
			{ a: z.number(), b: z.number() },
			async ({ a, b }) => {
				// ...
			},
		);
	}
}

See the example ↗ for the full code and as the basis for building your own MCP servers, and the client example ↗ for how to build an Agent that acts as an MCP client.

To learn more, review the announcement blog ↗ as part of Developer Week 2025.

We've made a number of improvements to the Agents SDK, including:

• Support for building MCP servers with the new MCPAgent class.
• The ability to export the current agent, request and WebSocket connection context using import { context } from "agents", allowing you to minimize or avoid direct dependency injection when calling tools.
• Fixed a bug that prevented query parameters from being sent to the Agent server from the useAgent React hook.
• Automatically converting the agent name in useAgent or useAgentChat to kebab-case to ensure it matches the naming convention expected by routeAgentRequest.

To install or update the Agents SDK, run npm i agents@latest in an existing project, or explore the agents-starter project:

npm create cloudflare@latest -- --template cloudflare/agents-starter

See the full release notes and changelog on the Agents SDK repository ↗ and

AutoRAG is now in open beta, making it easy for you to build fully-managed retrieval-augmented generation (RAG) pipelines without managing infrastructure. Just upload your docs to R2, and AutoRAG handles the rest: embeddings, indexing, retrieval, and response generation via API.

With AutoRAG, you can:

• Customize your pipeline: Choose from Workers AI models, configure chunking strategies, edit system prompts, and more.
• Instant setup: AutoRAG provisions everything you need from Vectorize, AI gateway, to pipeline logic for you, so you can go from zero to a working RAG pipeline in seconds.
• Keep your index fresh: AutoRAG continuously syncs your index with your data source to ensure responses stay accurate and up to date.
• Ask questions: Query your data and receive grounded responses via a Workers binding or API.

Whether you're building internal tools, AI-powered search, or a support assistant, AutoRAG gets you from idea to deployment in minutes.

Get started in the Cloudflare dashboard ↗ or check out the guide for instructions on how to build your RAG pipeline today.

We’re excited to announce Browser Rendering is now available on the Workers Free plan ↗, making it even easier to prototype and experiment with web search and headless browser use-cases when building applications on Workers.

The Browser Rendering REST API is now Generally Available, allowing you to control browser instances from outside of Workers applications. We've added three new endpoints to help automate more browser tasks:

• Extract structured data – Use /json to retrieve structured data from a webpage.
• Retrieve links – Use /links to pull all links from a webpage.
• Convert to Markdown – Use /markdown to convert webpage content into Markdown format.

For example, to fetch the Markdown representation of a webpage:

curl -X 'POST' 'https://api.cloudflare.com/client/v4/accounts/<accountId>/browser-rendering/markdown' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer <apiToken>' \
  -d '{
    "url": "https://example.com"
  }'

For the full list of endpoints, check out our REST API documentation. You can also interact with Browser Rendering via the Cloudflare TypeScript SDK ↗.

We also recently landed support for Playwright in Browser Rendering for browser automation from Cloudflare Workers, in addition to Puppeteer, giving you more flexibility to test across different browser environments.

Visit the Browser Rendering docs to learn more about how to use headless browsers in your applications.

Durable Objects can now be used with zero commitment on the Workers Free plan allowing you to build AI agents with Agents SDK, collaboration tools, and real-time applications like chat or multiplayer games.

Durable Objects let you build stateful, serverless applications with millions of tiny coordination instances that run your application code alongside (in the same thread!) your durable storage. Each Durable Object can access its own SQLite database through a Storage API. A Durable Object class is defined in a Worker script encapsulating the Durable Object's behavior when accessed from a Worker. To try the code below, click the button:

import { DurableObject } from "cloudflare:workers";

// Durable Object
export class MyDurableObject extends DurableObject {
  ...
	async sayHello(name) {
		return `Hello, ${name}!`;
	}
}

// Worker
export default {
	async fetch(request, env) {
		// Every unique ID refers to an individual instance of the Durable Object class
		const id = env.MY_DURABLE_OBJECT.idFromName("foo");

		// A stub is a client used to invoke methods on the Durable Object
		const stub = env.MY_DURABLE_OBJECT.get(id);

		// Methods on the Durable Object are invoked via the stub
		const response = await stub.sayHello("world");

		return response;
	},
};

Free plan limits apply to Durable Objects compute and storage usage. Limits allow developers to build real-world applications, with every Worker request able to call a Durable Object on the free plan.

For more information, checkout:

• Documentation
• Zero-latency SQLite storage in every Durable Object blog ↗

SQLite in Durable Objects is now generally available (GA) with 10GB SQLite database per Durable Object. Since the public beta ↗ in September 2024, we've added feature parity and robustness for the SQLite storage backend compared to the preexisting key-value (KV) storage backend for Durable Objects.

SQLite-backed Durable Objects are recommended for all new Durable Object classes, using new_sqlite_classes Wrangler configuration. Only SQLite-backed Durable Objects have access to Storage API's SQL and point-in-time recovery methods, which provide relational data modeling, SQL querying, and better data management.

export class MyDurableObject extends DurableObject {
  sql: SqlStorage
  constructor(ctx: DurableObjectState, env: Env) {
    super(ctx, env);
    this.sql = ctx.storage.sql;
  }

  async sayHello() {
    let result = this.sql
      .exec("SELECT 'Hello, World!' AS greeting")
      .one();
    return result.greeting;
  }
}

KV-backed Durable Objects remain for backwards compatibility, and a migration path from key-value storage to SQL storage for existing Durable Object classes will be offered in the future.

For more details on SQLite storage, checkout Zero-latency SQLite storage in every Durable Object blog ↗.

You can now capture a maximum of 256 KB of log events per Workers invocation, helping you gain better visibility into application behavior.

All console.log() statements, exceptions, request metadata, and headers are automatically captured during the Worker invocation and emitted as JSON object. Workers Logs deserializes this object before indexing the fields and storing them. You can also capture, transform, and export the JSON object in a Tail Worker.

256 KB is a 2x increase from the previous 128 KB limit. After you exceed this limit, further context associated with the request will not be recorded in your logs.

This limit is automatically applied to all Workers.

Workflows is now Generally Available (or "GA"): in short, it's ready for production workloads. Alongside marking Workflows as GA, we've introduced a number of changes during the beta period, including:

• A new waitForEvent API that allows a Workflow to wait for an event to occur before continuing execution.
• Increased concurrency: you can run up to 4,500 Workflow instances concurrently — and this will continue to grow.
• Improved observability, including new CPU time metrics that allow you to better understand which Workflow instances are consuming the most resources and/or contributing to your bill.
• Support for vitest for testing Workflows locally and in CI/CD pipelines.

Workflows also supports the new increased CPU limits that apply to Workers, allowing you to run more CPU-intensive tasks (up to 5 minutes of CPU time per instance), not including the time spent waiting on network calls, AI models, or other I/O bound tasks.

The new step.waitForEvent API allows a Workflow instance to wait on events and data, enabling human-in-the-the-loop interactions, such as approving or rejecting a request, directly handling webhooks from other systems, or pushing event data to a Workflow while it's running.

Because Workflows are just code, you can conditionally execute code based on the result of a waitForEvent call, and/or call waitForEvent multiple times in a single Workflow based on what the Workflow needs.

For example, if you wanted to implement a human-in-the-loop approval process, you could use waitForEvent to wait for a user to approve or reject a request, and then conditionally execute code based on the result.

import {
	WorkflowEntrypoint,
	WorkflowStep,
	WorkflowEvent,
} from "cloudflare:workers";

export class MyWorkflow extends WorkflowEntrypoint {
	async run(event, step) {
		// Other steps in your Workflow
		let stripeEvent = await step.waitForEvent(
			"receive invoice paid webhook from Stripe",
			{ type: "stripe-webhook", timeout: "1 hour" },
		);
		// Rest of your Workflow
	}
}

import { WorkflowEntrypoint, WorkflowStep, WorkflowEvent } from "cloudflare:workers";

export class MyWorkflow extends WorkflowEntrypoint<Env, Params> {
	async run(event: WorkflowEvent<Params>, step: WorkflowStep) {
		// Other steps in your Workflow
		let stripeEvent = await step.waitForEvent<IncomingStripeWebhook>("receive invoice paid webhook from Stripe", { type: "stripe-webhook", timeout: "1 hour" })
		// Rest of your Workflow
	}
}

You can then send a Workflow an event from an external service via HTTP or from within a Worker using the Workers API for Workflows:

export default {
	async fetch(req, env) {
		const instanceId = new URL(req.url).searchParams.get("instanceId");
		const webhookPayload = await req.json();

		let instance = await env.MY_WORKFLOW.get(instanceId);
		// Send our event, with `type` matching the event type defined in
		// our step.waitForEvent call
		await instance.sendEvent({
			type: "stripe-webhook",
			payload: webhookPayload,
		});

		return Response.json({
			status: await instance.status(),
		});
	},
};

export default {
  async fetch(req: Request, env: Env) {
    const instanceId = new URL(req.url).searchParams.get("instanceId")
    const webhookPayload = await req.json<Payload>()

    let instance = await env.MY_WORKFLOW.get(instanceId);
    // Send our event, with `type` matching the event type defined in
    // our step.waitForEvent call
    await instance.sendEvent({type: "stripe-webhook", payload: webhookPayload})

    return Response.json({
      status: await instance.status(),
    });
  },
};

Read the GA announcement blog ↗ to learn more about what landed as part of the Workflows GA.

We're excited to share that you can now use Playwright's browser automation capabilities ↗ from Cloudflare Workers.

Playwright ↗ is an open-source package developed by Microsoft that can do browser automation tasks; it's commonly used to write software tests, debug applications, create screenshots, and crawl pages. Like Puppeteer, we forked ↗ Playwright and modified it to be compatible with Cloudflare Workers and Browser Rendering.

Below is an example of how to use Playwright with Browser Rendering to test a TODO application using assertions:

import { launch, type BrowserWorker } from "@cloudflare/playwright";
import { expect } from "@cloudflare/playwright/test";

interface Env {
	MYBROWSER: BrowserWorker;
}

export default {
	async fetch(request: Request, env: Env) {
		const browser = await launch(env.MYBROWSER);
		const page = await browser.newPage();

		await page.goto("https://demo.playwright.dev/todomvc");

		const TODO_ITEMS = [
			"buy some cheese",
			"feed the cat",
			"book a doctors appointment",
		];

		const newTodo = page.getByPlaceholder("What needs to be done?");
		for (const item of TODO_ITEMS) {
			await newTodo.fill(item);
			await newTodo.press("Enter");
		}

		await expect(page.getByTestId("todo-title")).toHaveCount(TODO_ITEMS.length);

		await Promise.all(
			TODO_ITEMS.map((value, index) =>
				expect(page.getByTestId("todo-title").nth(index)).toHaveText(value),
			),
		);
	},
};

Playwright is available as an npm package at @cloudflare/playwright ↗ and the code is at GitHub ↗.

Learn more in our documentation.

Queues now supports the ability to pause message delivery and/or purge (delete) messages on a queue. These operations can be useful when:

• Your consumer has a bug or downtime, and you want to temporarily stop messages from being processed while you fix the bug
• You have pushed invalid messages to a queue due to a code change during development, and you want to clean up the backlog
• Your queue has a backlog that is stale and you want to clean it up to allow new messages to be consumed

To pause a queue using Wrangler, run the pause-delivery command. Paused queues continue to receive messages. And you can easily unpause a queue using the resume-delivery command.

$ wrangler queues pause-delivery my-queue
Pausing message delivery for queue my-queue.
Paused message delivery for queue my-queue.

$ wrangler queues resume-delivery my-queue
Resuming message delivery for queue my-queue.
Resumed message delivery for queue my-queue.

Purging a queue permanently deletes all messages in the queue. Unlike pausing, purging is an irreversible operation:

$ wrangler queues purge my-queue
✔ This operation will permanently delete all the messages in queue my-queue. Type my-queue to proceed. … my-queue
Purged queue 'my-queue'

You can also do these operations using the Queues REST API, or the dashboard page for a queue.

This feature is available on all new and existing queues. Head over to the pause and purge documentation to learn more. And if you haven't used Cloudflare Queues before, get started with the Cloudflare Queues guide.

You can now run a Worker for up to 5 minutes of CPU time for each request.

Previously, each Workers request ran for a maximum of 30 seconds of CPU time — that is the time that a Worker is actually performing a task (we still allowed unlimited wall-clock time, in case you were waiting on slow resources). This meant that some compute-intensive tasks were impossible to do with a Worker. For instance, you might want to take the cryptographic hash of a large file from R2. If this computation ran for over 30 seconds, the Worker request would have timed out.

By default, Workers are still limited to 30 seconds of CPU time. This protects developers from incurring accidental cost due to buggy code.

By changing the cpu_ms value in your Wrangler configuration, you can opt in to any value up to 300,000 (5 minutes).

{
	// ...rest of your configuration...
	"limits": {
		"cpu_ms": 300000,
	},
	// ...rest of your configuration...
}

[limits]
cpu_ms = 300_000

For more information on the updates limits, see the documentation on Wrangler configuration for cpu_ms and on Workers CPU time limits.

For building long-running tasks on Cloudflare, we also recommend checking out Workflows and Queues.

Source maps are now Generally Available (GA). You can now be uploaded with a maximum gzipped size of 15 MB. Previously, the maximum size limit was 15 MB uncompressed.

Source maps help map between the original source code and the transformed/minified code that gets deployed to production. By uploading your source map, you allow Cloudflare to map the stack trace from exceptions onto the original source code making it easier to debug.

With no source maps uploaded: notice how all the Javascript has been minified to one file, so the stack trace is missing information on file name, shows incorrect line numbers, and incorrectly references js instead of ts.

With source maps uploaded: all methods reference the correct files and line numbers.

Uploading source maps and stack trace remapping happens out of band from the Worker execution, so source maps do not affect upload speed, bundle size, or cold starts. The remapped stack traces are accessible through Tail Workers, Workers Logs, and Workers Logpush.

To enable source maps, add the following to your Pages Function's or Worker's wrangler configuration:

{
	"upload_source_maps": true
}

upload_source_maps = true

Update: Mon Mar 24th, 11PM UTC: Next.js has made further changes to address a smaller vulnerability introduced in the patches made to its middleware handling. Users should upgrade to Next.js versions 15.2.4, 14.2.26, 13.5.10 or 12.3.6. If you are unable to immediately upgrade or are running an older version of Next.js, you can enable the WAF rule described in this changelog as a mitigation.

Update: Mon Mar 24th, 8PM UTC: Next.js has now backported the patch for this vulnerability ↗ to cover Next.js v12 and v13. Users on those versions will need to patch to 13.5.9 and 12.3.5 (respectively) to mitigate the vulnerability.

Update: Sat Mar 22nd, 4PM UTC: We have changed this WAF rule to opt-in only, as sites that use auth middleware with third-party auth vendors were observing failing requests.

We strongly recommend updating your version of Next.js (if eligible) to the patched versions, as your app will otherwise be vulnerable to an authentication bypass attack regardless of auth provider.

This rule is opt-in only for sites on the Pro plan or above in the WAF managed ruleset.

To enable the rule:

1. Head to Security > WAF > Managed rules in the Cloudflare dashboard for the zone (website) you want to protect.
2. Click the three dots next to Cloudflare Managed Ruleset and choose Edit
3. Scroll down and choose Browse Rules
4. Search for CVE-2025-29927 (ruleId: 34583778093748cc83ff7b38f472013e)
5. Change the Status to Enabled and the Action to Block. You can optionally set the rule to Log, to validate potential impact before enabling it. Log will not block requests.
6. Click Next
7. Scroll down and choose Save

This will enable the WAF rule and block requests with the x-middleware-subrequest header regardless of Next.js version.

For users on the Free plan, or who want to define a more specific rule, you can create a Custom WAF rule to block requests with the x-middleware-subrequest header regardless of Next.js version.

To create a custom rule:

1. Head to Security > WAF > Custom rules in the Cloudflare dashboard for the zone (website) you want to protect.
2. Give the rule a name - e.g. next-js-CVE-2025-29927
3. Set the matching parameters for the rule match any request where the x-middleware-subrequest header exists per the rule expression below.

(len(http.request.headers["x-middleware-subrequest"]) > 0)

4. Set the action to 'block'. If you want to observe the impact before blocking requests, set the action to 'log' (and edit the rule later).
5. Deploy the rule.

We've made a WAF (Web Application Firewall) rule available to all sites on Cloudflare to protect against the Next.js authentication bypass vulnerability ↗ (CVE-2025-29927) published on March 21st, 2025.

Note: This rule is not enabled by default as it blocked requests across sites for specific authentication middleware.

• This managed rule protects sites using Next.js on Workers and Pages, as well as sites using Cloudflare to protect Next.js applications hosted elsewhere.
• This rule has been made available (but not enabled by default) to all sites as part of our WAF Managed Ruleset and blocks requests that attempt to bypass authentication in Next.js applications.
• The vulnerability affects almost all Next.js versions, and has been fully patched in Next.js 14.2.26 and 15.2.4. Earlier, interim releases did not fully patch this vulnerability.
• Users on older versions of Next.js (11.1.4 to 13.5.6) did not originally have a patch available, but this the patch for this vulnerability and a subsequent additional patch have been backported to Next.js versions 12.3.6 and 13.5.10 as of Monday, March 24th. Users on Next.js v11 will need to deploy the stated workaround or enable the WAF rule.

The managed WAF rule mitigates this by blocking external user requests with the x-middleware-subrequest header regardless of Next.js version, but we recommend users using Next.js 14 and 15 upgrade to the patched versions of Next.js as an additional mitigation.

Smart Placement is a unique Cloudflare feature that can make decisions to move your Worker to run in a more optimal location (such as closer to a database). Instead of always running in the default location (the one closest to where the request is received), Smart Placement uses certain “heuristics” (rules and thresholds) to decide if a different location might be faster or more efficient.

Previously, if these heuristics weren't consistently met, your Worker would revert to running in the default location—even after it had been optimally placed. This meant that if your Worker received minimal traffic for a period of time, the system would reset to the default location, rather than remaining in the optimal one.

Now, once Smart Placement has identified and assigned an optimal location, temporarily dropping below the heuristic thresholds will not force a return to default locations. For example in the previous algorithm, a drop in requests for a few days might return to default locations and heuristics would have to be met again. This was problematic for workloads that made requests to a geographically located resource every few days or longer. In this scenario, your Worker would never get placed optimally. This is no longer the case.

We are excited to announce that AI Gateway now supports real-time AI interactions with the new Realtime WebSockets API.

This new capability allows developers to establish persistent, low-latency connections between their applications and AI models, enabling natural, real-time conversational AI experiences, including speech-to-speech interactions.

The Realtime WebSockets API works with the OpenAI Realtime API ↗, Google Gemini Live API ↗, and supports real-time text and speech interactions with models from Cartesia ↗, and ElevenLabs ↗.

Here's how you can connect AI Gateway to OpenAI's Realtime API ↗ using WebSockets:

import WebSocket from "ws";

const url =
	"wss://gateway.ai.cloudflare.com/v1/<account_id>/<gateway>/openai?model=gpt-4o-realtime-preview-2024-12-17";
const ws = new WebSocket(url, {
	headers: {
		"cf-aig-authorization": process.env.CLOUDFLARE_API_KEY,
		Authorization: "Bearer " + process.env.OPENAI_API_KEY,
		"OpenAI-Beta": "realtime=v1",
	},
});

ws.on("open", () => console.log("Connected to server."));
ws.on("message", (message) => console.log(JSON.parse(message.toString())));

ws.send(
	JSON.stringify({
		type: "response.create",
		response: { modalities: ["text"], instructions: "Tell me a joke" },
	}),
);

Get started by checking out the Realtime WebSockets API documentation.

In Cloudflare Terraform Provider ↗ versions 5.2.0 and above, dozens of resources now have proper drift detection. Before this fix, these resources would indicate they needed to be updated or replaced — even if there was no real change. Now, you can rely on your terraform plan to only show what resources are expected to change.

This issue affected resources ↗ related to these products and features:

• API Shield
• Argo Smart Routing
• Argo Tiered Caching
• Bot Management
• BYOIP
• D1
• DNS
• Email Routing
• Hyperdrive
• Observatory
• Pages
• R2
• Rules
• SSL/TLS
• Waiting Room
• Workers
• Zero Trust

In the Cloudflare Terraform Provider ↗ versions 5.2.0 and above, sensitive properties of resources are redacted in logs. Sensitive properties in Cloudflare's OpenAPI Schema ↗ are now annotated with x-sensitive: true. This results in proper auto-generation of the corresponding Terraform resources, and prevents sensitive values from being shown when you run Terraform commands.

This issue affected resources ↗ related to these products and features:

• Alerts and Audit Logs
• Device API
• DLP
• DNS
• Magic Visibility
• Magic WAN
• TLS Certs and Hostnames
• Tunnels
• Turnstile
• Workers
• Zaraz

Document conversion plays an important role when designing and developing AI applications and agents. Workers AI now provides the toMarkdown utility method that developers can use to for quick, easy, and convenient conversion and summary of documents in multiple formats to Markdown language.

You can call this new tool using a binding by calling env.AI.toMarkdown() or the using the REST API endpoint.

In this example, we fetch a PDF document and an image from R2 and feed them both to env.AI.toMarkdown(). The result is a list of converted documents. Workers AI models are used automatically to detect and summarize the image.

import { Env } from "./env";

export default {
	async fetch(request: Request, env: Env, ctx: ExecutionContext) {
		// https://pub-979cb28270cc461d94bc8a169d8f389d.r2.dev/somatosensory.pdf
		const pdf = await env.R2.get("somatosensory.pdf");

		// https://pub-979cb28270cc461d94bc8a169d8f389d.r2.dev/cat.jpeg
		const cat = await env.R2.get("cat.jpeg");

		return Response.json(
			await env.AI.toMarkdown([
				{
					name: "somatosensory.pdf",
					blob: new Blob([await pdf.arrayBuffer()], {
						type: "application/octet-stream",
					}),
				},
				{
					name: "cat.jpeg",
					blob: new Blob([await cat.arrayBuffer()], {
						type: "application/octet-stream",
					}),
				},
			]),
		);
	},
};

This is the result:

[
	{
		"name": "somatosensory.pdf",
		"mimeType": "application/pdf",
		"format": "markdown",
		"tokens": 0,
		"data": "# somatosensory.pdf\n## Metadata\n- PDFFormatVersion=1.4\n- IsLinearized=false\n- IsAcroFormPresent=false\n- IsXFAPresent=false\n- IsCollectionPresent=false\n- IsSignaturesPresent=false\n- Producer=Prince 20150210 (www.princexml.com)\n- Title=Anatomy of the Somatosensory System\n\n## Contents\n### Page 1\nThis is a sample document to showcase..."
	},
	{
		"name": "cat.jpeg",
		"mimeType": "image/jpeg",
		"format": "markdown",
		"tokens": 0,
		"data": "The image is a close-up photograph of Grumpy Cat, a cat with a distinctive grumpy expression and piercing blue eyes. The cat has a brown face with a white stripe down its nose, and its ears are pointed upright. Its fur is light brown and darker around the face, with a pink nose and mouth. The cat's eyes are blue and slanted downward, giving it a perpetually grumpy appearance. The background is blurred, but it appears to be a dark brown color. Overall, the image is a humorous and iconic representation of the popular internet meme character, Grumpy Cat. The cat's facial expression and posture convey a sense of displeasure or annoyance, making it a relatable and entertaining image for many people."
	}
]

See Markdown Conversion for more information on supported formats, REST API and pricing.

📝 We've renamed the Agents package to agents!

If you've already been building with the Agents SDK, you can update your dependencies to use the new package name, and replace references to agents-sdk with agents:

# Install the new package
npm i agents

# Remove the old (deprecated) package
npm uninstall agents-sdk

# Find instances of the old package name in your codebase
grep -r 'agents-sdk' .
# Replace instances of the old package name with the new one
# (or use find-replace in your editor)
sed -i 's/agents-sdk/agents/g' $(grep -rl 'agents-sdk' .)

All future updates will be pushed to the new agents package, and the older package has been marked as deprecated.

We've added a number of big new features to the Agents SDK over the past few weeks, including:

• You can now set cors: true when using routeAgentRequest to return permissive default CORS headers to Agent responses.
• The regular client now syncs state on the agent (just like the React version).
• useAgentChat bug fixes for passing headers/credentials, including properly clearing cache on unmount.
• Experimental /schedule module with a prompt/schema for adding scheduling to your app (with evals!).
• Changed the internal zod schema to be compatible with the limitations of Google's Gemini models by removing the discriminated union, allowing you to use Gemini models with the scheduling API.

We've also fixed a number of bugs with state synchronization and the React hooks.

// via https://github.com/cloudflare/agents/tree/main/examples/cross-domain
export default {
	async fetch(request, env) {
		return (
			// Set { cors: true } to enable CORS headers.
			(await routeAgentRequest(request, env, { cors: true })) ||
			new Response("Not found", { status: 404 })
		);
	},
};

// via https://github.com/cloudflare/agents/tree/main/examples/cross-domain
export default {
	async fetch(request: Request, env: Env) {
		return (
			// Set { cors: true } to enable CORS headers.
			(await routeAgentRequest(request, env, { cors: true })) ||
			new Response("Not found", { status: 404 })
		);
	},
} satisfies ExportedHandler<Env>;

We've added a new @unstable_callable() decorator for defining methods that can be called directly from clients. This allows you call methods from within your client code: you can call methods (with arguments) and get native JavaScript objects back.

// server.ts
import { unstable_callable, Agent } from "agents";

export class Rpc extends Agent {
	// Use the decorator to define a callable method
	@unstable_callable({
		description: "rpc test",
	})
	async getHistory() {
		return this.sql`SELECT * FROM history ORDER BY created_at DESC LIMIT 10`;
	}
}

// server.ts
import { unstable_callable, Agent, type StreamingResponse } from "agents";
import type { Env } from "../server";

export class Rpc extends Agent<Env> {
	// Use the decorator to define a callable method
	@unstable_callable({
		description: "rpc test",
	})
	async getHistory() {
		return this.sql`SELECT * FROM history ORDER BY created_at DESC LIMIT 10`;
	}
}

// client.tsx
const { call } = useAgent({ agent: "rpc" });

const fetchUserHistory = async () => {
	try {
		setLoading(true);
		// Call methods directly on the Agent!
		const result = await call("getHistory");
		addToast(`RPC result: ${result}`, "success");
	} catch (error) {
		addToast(`Error: ${error}`, "error");
	} finally {
		setLoading(false);
	}
};

We've fixed a number of small bugs in the agents-starter ↗ project — a real-time, chat-based example application with tool-calling & human-in-the-loop built using the Agents SDK. The starter has also been upgraded to use the latest wrangler v4 release.

If you're new to Agents, you can install and run the agents-starter project in two commands:

# Install it
$ npm create cloudflare@latest agents-starter -- --template="cloudflare/agents-starter"
# Run it
$ npm run start

You can use the starter as a template for your own Agents projects: open up src/server.ts and src/client.tsx to see how the Agents SDK is used.

We've heard your feedback on the Agents SDK documentation, and we're shipping more API reference material and usage examples, including:

• Expanded API reference documentation, covering the methods and properties exposed by the Agents SDK, as well as more usage examples.
• More Client API documentation that documents useAgent, useAgentChat and the new @unstable_callable RPC decorator exposed by the SDK.
• New documentation on how to route requests to agents and (optionally) authenticate clients before they connect to your Agents.

Note that the Agents SDK is continually growing: the type definitions included in the SDK will always include the latest APIs exposed by the agents package.

If you're still wondering what Agents are, read our blog on building AI Agents on Cloudflare ↗ and/or visit the Agents documentation to learn more.

Workers AI is excited to add 4 new models to the catalog, including 2 brand new classes of models with a text-to-speech and reranker model. Introducing:

• @cf/baai/bge-m3 - a multi-lingual embeddings model that supports over 100 languages. It can also simultaneously perform dense retrieval, multi-vector retrieval, and sparse retrieval, with the ability to process inputs of different granularities.
• @cf/baai/bge-reranker-base - our first reranker model! Rerankers are a type of text classification model that takes a query and context, and outputs a similarity score between the two. When used in RAG systems, you can use a reranker after the initial vector search to find the most relevant documents to return to a user by reranking the outputs.
• @cf/openai/whisper-large-v3-turbo - a faster, more accurate speech-to-text model. This model was added earlier but is graduating out of beta with pricing included today.
• @cf/myshell-ai/melotts - our first text-to-speech model that allows users to generate an MP3 with voice audio from inputted text.

Pricing is available for each of these models on the Workers AI pricing page.

This docs update includes a few minor bug fixes to the model schema for llama-guard, llama-3.2-1b, which you can review on the product changelog.

Try it out and let us know what you think! Stay tuned for more models in the coming days.

You can now access bindings from anywhere in your Worker by importing the env object from cloudflare:workers.

Previously, env could only be accessed during a request. This meant that bindings could not be used in the top-level context of a Worker.

Now, you can import env and access bindings such as secrets or environment variables in the initial setup for your Worker:

import { env } from "cloudflare:workers";
import ApiClient from "example-api-client";

// API_KEY and LOG_LEVEL now usable in top-level scope
const apiClient = ApiClient.new({ apiKey: env.API_KEY });
const LOG_LEVEL = env.LOG_LEVEL || "info";

export default {
	fetch(req) {
		// you can use apiClient or LOG_LEVEL, configured before any request is handled
	},
};

Additionally, env was normally accessed as a argument to a Worker's entrypoint handler, such as fetch. This meant that if you needed to access a binding from a deeply nested function, you had to pass env as an argument through many functions to get it to the right spot. This could be cumbersome in complex codebases.

Now, you can access the bindings from anywhere in your codebase without passing env as an argument:

// helpers.js
import { env } from "cloudflare:workers";

// env is *not* an argument to this function
export async function getValue(key) {
	let prefix = env.KV_PREFIX;
	return await env.KV.get(`${prefix}-${key}`);
}

For more information, see documentation on accessing env.

You can now retry your Cloudflare Pages and Workers builds directly from GitHub. No need to switch to the Cloudflare Dashboard for a simple retry!

Let\u2019s say you push a commit, but your build fails due to a spurious error like a network timeout. Instead of going to the Cloudflare Dashboard to manually retry, you can now rerun the build with just a few clicks inside GitHub, keeping you inside your workflow.

For Pages and Workers projects connected to a GitHub repository:

1. When a build fails, go to your GitHub repository or pull request
2. Select the failed Check Run for the build
3. Select "Details" on the Check Run
4. Select "Rerun" to trigger a retry build for that commit

Learn more about Pages Builds and Workers Builds.

We've released the next major version of Wrangler, the CLI for Cloudflare Workers — wrangler@4.0.0. Wrangler v4 is a major release focused on updates to underlying systems and dependencies, along with improvements to keep Wrangler commands consistent and clear.

You can run the following command to install it in your projects:

npm i wrangler@latest

yarn add wrangler@latest

pnpm add wrangler@latest

bun add wrangler@latest

Unlike previous major versions of Wrangler, which were foundational rewrites ↗ and rearchitectures ↗ — Version 4 of Wrangler includes a much smaller set of changes. If you use Wrangler today, your workflow is very unlikely to change.

A detailed migration guide is available and if you find a bug or hit a roadblock when upgrading to Wrangler v4, open an issue on the cloudflare/workers-sdk repository on GitHub ↗.

Going forward, we'll continue supporting Wrangler v3 with bug fixes and security updates until Q1 2026, and with critical security updates until Q1 2027, at which point it will be out of support.

You can now debug your Workers tests with our Vitest integration by running the following command:

vitest --inspect --no-file-parallelism

Attach a debugger to the port 9229 and you can start stepping through your Workers tests. This is available with @cloudflare/vitest-pool-workers v0.7.5 or later.

Learn more in our documentation.