Cloudflare Release Notes

The latest release of the Agents SDK ↗︎ makes it easier to build agents that can safely interact with real systems and keep working through interruptions.

Agents can now browse websites through Browser Run, write code against external tools through Code Mode, use client-provided tools when delegating to Think sub-agents, and recover more reliably from deploys, Durable Object evictions, and connection churn.

Safer browser automation

Agents can now use Browser Run through a single durable browser_execute tool. Instead of choosing from a fixed list of actions, the model writes code against the Chrome DevTools Protocol (CDP) and can inspect pages, capture screenshots, read rendered content, debug frontend behavior, and interact with live browser sessions.

const browserTools = createBrowserTools({
	ctx: this.ctx,
	browser: this.env.BROWSER,
	loader: this.env.LOADER,
	session: { mode: "dynamic" },
});

const browserTools = createBrowserTools({
	ctx: this.ctx,
	browser: this.env.BROWSER,
	loader: this.env.LOADER,
	session: { mode: "dynamic" },
});

Browser sessions can be one-time, reused, or promoted from one-time to persistent during a run. This is useful when an agent needs a human to log in, complete MFA, or approve a sensitive action. The run can pause, keep the same tabs and cookies, and resume after approval. …

These updates introduce new features for optimizing and manipulating with Images:

• New composite option: Control how overlays are blended with the base image.
• Percentage widths: Set the dimensions of an overlay as a fraction of the dimensions of the base image.
• New fit modes: Use aspect-crop to always preserve the target aspect ratio or scale-up to always enlarge images.
• New upscale parameter: Apply AI upscaling to produce sharper, more detailed results when enlarging images.

We are excited to announce GLM-5.2 on Workers AI, Z.ai's flagship agentic coding model.

@cf/zai-org/glm-5.2 is a text generation model built for agentic coding workflows. With function calling and reasoning support, it can handle long codebases, multi-step planning, and tool-augmented agents.

Key features and use cases:

• Agentic coding: Designed for autonomous coding tasks, long-horizon planning, and complex software engineering workflows
• Large context window: GLM-5.2 supports up to a 1,048,576 token context window. Workers AI is launching the model with a 262,144 token context window and plans to increase this in the future
• Function calling: Build agents that invoke tools and APIs across multiple conversation turns
• Reasoning: Tackles complex problem-solving and step-by-step reasoning tasks

Use GLM-5.2 through the Workers AI binding (env.AI.run()), the REST API at /run or /v1/chat/completions, or AI Gateway.

Pricing is available on the model page or pricing page.

VPC Network bindings now support the connect() Socket API for raw TCP connections to private destinations, in addition to HTTP traffic via fetch().

This means Workers can now open TCP sockets to any private service reachable through the bound Cloudflare Tunnel, Cloudflare Mesh, or Cloudflare WAN on-ramp — Redis, Memcached, MQTT, custom binary protocols, or any other TCP-based service.

{
  "$schema": "./node_modules/wrangler/config-schema.json",
  "vpc_networks": [
    {
      "binding": "PRIVATE_NETWORK",
      "network_id": "cf1:network",
      "remote": true
    }
  ]
}

[[vpc_networks]]
binding = "PRIVATE_NETWORK"
network_id = "cf1:network"
remote = true

At runtime, use connect() on the binding to open a TCP socket to a private destination:

export default {
	async fetch(request: Request, env: Env) {
		// Open a TCP connection to a private Redis instance
		const socket = await env.PRIVATE_NETWORK.connect("10.0.1.50:6379");

		// Write a Redis PING command
		const writer = socket.writable.getWriter();
		await writer.write(new TextEncoder().encode("PING\r\n"));
		await writer.close();

		return new Response(socket.readable);
	},
};

Note

connect() over VPC Networks currently supports plaintext TCP only. …

You can now create custom trace spans in your Workers code using tracing.enterSpan(). Custom spans appear alongside the automatic platform instrumentation (fetch calls, KV reads, D1 queries, and other platform operations) in your traces and OpenTelemetry exports, with correct parent-child nesting.

The API is available via import { tracing } from "cloudflare:workers" or through the handler context as ctx.tracing:

import { tracing } from "cloudflare:workers";

export default {
  async fetch(request, env, ctx) {
    return tracing.enterSpan("handleRequest", async (span) => {
      span.setAttribute("url.path", new URL(request.url).pathname);
      const data = await env.MY_KV.get("key");
      return new Response(data);
    });
  },
};

Spans nest automatically based on the JavaScript async context, and are auto-ended when the callback returns or its returned promise settles. The Span object provides setAttribute(key, value) for attaching metadata and an isTraced property to check whether the current request is being sampled.

Trace waterfall showing custom spans nested alongside automatic KV and fetch instrumentation

Tracing must be enabled in your Wrangler configuration for spans to be recorded. …

You can now configure advanced Pay Per Crawl settings for your zone, including:

• Disable Pay Per Crawl by URI pattern using Configuration Rules to offer free access to specific pages while charging for others.
• Dynamic pricing by having your origin return a crawler-price response header, or by using a Cloudflare Worker to set prices based on request properties.

When dynamic pricing is enabled, Pay Per Crawl adds a cf-pay-per-crawl request header to origin requests so your origin or Worker can determine the appropriate price.

Refer to the Advanced configuration documentation for details.

Cloudflare Images

These updates introduce new features for optimizing and manipulating with Images:

• New composite option: Control how overlays are blended with the base image.
• Percentage widths: Set the dimensions of an overlay as a fraction of the dimensions of the base image.
• New fit modes: Use aspect-crop to always preserve the target aspect ratio or scale-up to always enlarge images.
• New upscale parameter: Apply AI upscaling to produce sharper, more detailed results when enlarging images.

You can now match incoming requests against Cloudforce One threat intelligence in your WAF rules. A new detection looks up the client IP address of each request against the threat intelligence database. If the IP was involved in threat activity in the past seven days, Cloudflare populates cf.intel.ip.* fields that you can use in custom rules and rate limiting rules.

The detection populates the following fields. Use the any() function with the [*] wildcard to match array values:

• cf.intel.ip.datasets — the dataset that flagged the IP address (ddos or waf).
• cf.intel.ip.target_industries — industries the IP address has targeted.
• cf.intel.ip.attacker_names — known threat actors associated with the IP address.
• cf.intel.ip.attacker_countries — source countries of the threat activity.
• cf.intel.ip.target_countries — countries the IP address has targeted.

For example, the following custom rule expression blocks requests from IP addresses associated with DDoS activity that have targeted France:

any(cf.intel.ip.target_countries[*] == "FR") and any(cf.intel.ip.datasets[*] == "ddos")
``` …

This week's release introduces new managed protection to address a critical SQL injection vulnerability in Ghost CMS (CVE-2026-26980) and a new generic rule designed to identify and block sophisticated SQL Injection (SQLi) bypass attempts leveraging obfuscated boolean logic. These rules protect affected installations from unauthorized data exfiltration at the network edge.

Key Findings

• CVE-2026-26980: A blind SQL injection vulnerability in the Ghost CMS Content API (versions 3.24.0 to 6.19.0) allows unauthenticated remote attackers to inject malicious SQL commands via query parameters due to improper input validation.

Ruleset

Rule ID

Legacy Rule ID

Description

Previous Action

New Action

Comments

Cloudflare Managed Ruleset

...b4c29bc6

N/A

Ghost CMS - SQLi - CVE:CVE-2026-26980

Log

Block

This is a new detection.

Cloudflare Managed Ruleset

...b56f403f

N/A

SQLi - Obfuscated Boolean - URI

Log

Disabled

This is a new detection.

You can now filter the Metrics tab for a Durable Objects namespace by an individual Durable Object's ID or name in the Cloudflare dashboard. Previously, metrics charts only showed aggregate, namespace-level data, making it difficult to isolate the behavior of a specific object.

Go to Durable Objects ↗ The Durable Objects Metrics tab filtered to a single object by ID, showing per-object requests and errors by invocation status.

Start typing an ID or name into the filter and select a match from the autocomplete dropdown. The autocomplete only shows objects with invocations during the selected time range, so an object that does not appear has not been invoked in that window. This does not necessarily mean the object has been deleted. Every chart on the page updates to reflect only the selected object. This makes it easier to identify and investigate a single Durable Object when debugging a high-traffic object, an error spike, or unexpected storage usage. Clear the filter to return to namespace-level metrics. …

@cf/moonshotai/kimi-k2.7-code is now available on Workers AI. Kimi K2.7 Code is a code-optimized variant of the Kimi K2 family, built on a Mixture-of-Experts architecture with 1T total parameters and 32B active per token.

Improved coding and agent performance

K2.7 Code delivers meaningful gains over K2.6 on coding and agentic benchmarks:

• +21.8% on Kimi Code Bench v2
• +11.0% on Program Bench
• +31.5% on MLS Bench Lite

Reasoning efficiency

K2.7 Code uses 30% fewer reasoning tokens compared to K2.6, reducing overthinking and lowering inference cost for reasoning-heavy workloads.

Key capabilities

• 262.1k token context window for retaining full conversation history, tool definitions, and codebases across long-running agent sessions
• Long-horizon coding with improved instruction following and higher end-to-end coding task success rates
• Vision inputs for processing images alongside text
• Thinking mode with configurable reasoning depth via chat_template_kwargs.thinking
• Multi-turn tool calling for building agents that invoke tools across multiple conversation turns
• Structured outputs with JSON schema support

Differences from Kimi K2.6

If you are migrating from Kimi K2.6, note the following: …

Cloudflare's Terraform v5 Provider makes it easy for developers to manage their Cloudflare infrastructure using a configuration as code approach. It releases every 2-3 weeks ↗︎ to ensure that you can always manage the latest features in the platform. This week, we launched Terraform v5.20.0, which adds 24 new resources, bumps the underlying Go SDK to cloudflare-go v7, and includes a range of bug fixes and state upgraders based on community feedback.

New resources

• cloudflare_ai_search_namespace: Manage AI Search namespaces
• cloudflare_custom_csr: Manage custom certificate signing requests
• cloudflare_dls_prefix_binding: Manage DLS regional service prefix bindings
• cloudflare_flagship_app: Manage Flagship feature flag apps
• cloudflare_flagship_flag: Manage Flagship feature flags
• cloudflare_google_tag_gateway: Manage Google Tag Gateway
• cloudflare_load_balancer_monitor_group: Manage load balancer monitor groups
• cloudflare_oauth_client: Manage IAM OAuth clients
• cloudflare_origin_cloud_region: Manage origin cloud regions (v2 endpoints)
• cloudflare_secrets_store: Manage Secrets Store instances
• cloudflare_secrets_store_secret: Manage Secrets Store secrets
• cloudflare_share: Manage resource shares
• cloudflare_share_recipient: Manage share recipients …

You can now define custom topics for AI prompt protection. Predefined AI prompt topics cover common content and intent categories such as PII, source code, and jailbreak attempts. Custom topics let you detect unique or proprietary concepts that are not included in predefined categories.

You describe a custom topic in natural language, and Cloudflare DLP detects whether a prompt matches that topic based on context rather than specific keywords. For example, a topic that describes confidential merger discussions matches a prompt that paraphrases the deal, even when the prompt never uses the word merger or names the companies involved. To detect literal values such as internal codenames or product identifiers, use a custom wordlist or pattern entry instead.

Custom topics run through the same application granular controls path as predefined AI prompt topics. Custom topics are available for ChatGPT, Google Gemini, Perplexity, and Claude.

Create a custom AI prompt topic

…

Browser Run's /snapshot endpoint now supports a formats parameter that lets you return multiple page formats in a single API call. Previously, /snapshot returned only HTML content and a screenshot. You can now also include Markdown and the accessibility tree in the same response.

These formats are particularly useful for AI agent workflows:

• Markdown provides a token-efficient representation of page content that LLMs can process directly, without parsing HTML markup.
• The accessibility tree provides a structured representation of a page's elements, including roles, labels, and hierarchy, helping LLMs understand page structure and navigate its contents.

The following example returns a screenshot, Markdown, and the accessibility tree in one call:

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

import Cloudflare from "cloudflare";

const client = new Cloudflare({
	apiToken: process.env["CLOUDFLARE_API_TOKEN"],
});

const snapshot = await client.browserRendering.snapshot.create({
	account_id: process.env["CLOUDFLARE_ACCOUNT_ID"],
	url: "https://example.com/", …

Dynamic Workers usage on the Workers overview page

Customers can now view the number of Dynamic Workers invoked during their billing period from the Workers overview page in the Cloudflare dashboard.

This count reflects the number of Dynamic Workers that Cloudflare would bill for during the selected billing period. Dynamic Workers usage data only goes back to June 1, 2026.

You can also query this count through the GraphQL Analytics API by using workersInvocationsByOwnerAndScriptGroups and selecting distinctDynamicWorkerCount:

query getDynamicWorkersCount(
	$accountTag: string!
	$filter: AccountWorkersInvocationsByOwnerAndScriptGroupsFilter_InputObject
) {
	viewer {
		accounts(filter: { accountTag: $accountTag }) {
			workersInvocationsByOwnerAndScriptGroups(limit: 10000, filter: $filter) {
				uniq {
					distinctDynamicWorkerCount
				}
			}
		}
	}
}

Use variables to set the account and billing-period date range:

{
	"accountTag": "<ACCOUNT_ID>",
	"filter": {
		"date_geq": "2026-06-01",
		"date_leq": "2026-06-30"
	}
}

For more information, refer to Dynamic Workers pricing.

AI Search now supports namespace-level Wrangler commands, making it easier to manage namespaces from your terminal, scripts, and agent workflows.

The following commands are available:

Command

Description

wrangler ai-search namespace list

List AI Search namespaces

wrangler ai-search namespace create

Create a new AI Search namespace

wrangler ai-search namespace get

Get details for a namespace

wrangler ai-search namespace update

Update a namespace description

wrangler ai-search namespace delete

Delete an AI Search namespace

Create a namespace for a new application or tenant directly from the CLI:

wrangler ai-search namespace create docs-production --description "Production documentation search"

List namespaces with pagination or filter by name or description:

wrangler ai-search namespace list --search docs --page 1 --per-page 10

Use --json with list, create, get, and update to return structured output that automation and AI agents can parse directly.

Instance-level commands also now support a --namespace flag, so you can interact with instances inside a specific namespace from the CLI:

wrangler ai-search list --namespace docs-production

For full usage details, refer to the AI Search Wrangler commands documentation.

The Flagship API reference is now available. You can use the Cloudflare API to create and update apps, and to create, update, delete, and list feature flags without using the dashboard.

For example, create a new boolean flag with the API:

curl https://api.cloudflare.com/client/v4/accounts/$ACCOUNT_ID/flagship/apps/$APP_ID/flags \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  -d '{
    "key": "new-checkout",
    "enabled": true,
    "default_variation": "off",
    "variations": {
      "off": false,
      "on": true
    },
    "rules": []
  }'

To create an API token, go to Account API Tokens ↗︎ in the Cloudflare dashboard and search for Flagship.

The API reference includes endpoints for Flagship apps, flags, changelog entries, and flag evaluation. Agents can also use the Flagship reference in the Cloudflare skill ↗︎ to create and manage Flagship resources.

Refer to the Flagship documentation to learn more about evaluating feature flags from your applications.

Use the Images binding to upload, list, retrieve, update, and delete images stored in Images directly from your Worker without managing API tokens or making HTTP requests.

The env.IMAGES.hosted namespace supports the following storage and management operations:

• .upload(image, options) — Upload a new image to your account.
• .list(options) — List images with pagination.
• .image(imageId).details() — Get image metadata.
• .image(imageId).bytes() — Stream the original image bytes.
• .image(imageId).update(options) — Update metadata or access controls.
• .image(imageId).delete() — Delete an image.

For example, you can upload an image from a request body and return its metadata:

const image = await env.IMAGES.hosted.upload(request.body, {
	filename: "upload.jpg",
	metadata: { source: "worker" },
});

return Response.json(image);

Or retrieve and serve the original bytes of a hosted image:

const bytes = await env.IMAGES.hosted.image("IMAGE_ID").bytes(); …