API Breaking Changes Radar

If you operate a platform or gateway, or resell API access, a safety enforcement action can then apply to one end customer instead of your whole organization.

 are out of beta for Claude Enterprise organizations.
, so you can tell Anthropic which of your end customers each API request is for. If you operate a platform or gateway, or resell API access, a safety enforcement action can then apply to one end customer instead of your whole organization. The SDK and the 
/v1/organizations/webhooks
 register webhook endpoints for two event types: one for when Anthropic restricts or bans one of your organization's user profiles, and one for when the restriction or ban ends. To request access, contact your Anthropic account team.

Dependabot now supports npm 12, pnpm 11 and 12, and Bun 1.4

 Bulk migrate branch protections to rulesets for a repository 
 Updates to GitHub secret scanning 
 Dependabot alerts REST API now includes dependency versions 
 GitHub package firewall in public preview 
 Dependabot now supports npm 12, pnpm 11 and 12, and Bun 1.4 

Act now to secure your app: We're asking every app dev to act this week. We have new tools to help, including AI security scans, expiring tokens, and better log filtering. Read on to learn how.

Securing your app, together
Act now to secure your app: We're asking every app dev to act this week. We have new tools to help, including AI security scans, expiring tokens, and better log filtering. Read on to learn how.
 Metaobject analytics queryable capability available in the Admin API

DeepSeek V4.1 Flash is now available in Token Pass

WebSocket support is now generally available
WebSocket support in Vercel Functions, used for multiplayer apps, chat streaming, and AI Gateway's realtime models, is now GA.
DeepSeek V4.1 Flash is now available in Token Pass
DeepSeek V4.1 Flash joins Kimi K3 and GLM 5.3 in Token Pass.
Walter Korman, Krish Krish

The Voice Recording Account Default Configuration is a new API that enables customers to set and manage default call recording settings for your account.  Now Generally Available in us1.

The Voice Recording Account Default Configuration is now Generally Available in us1
The Voice Recording Account Default Configuration is a new API that enables customers to set and manage default call recording settings for your account.  Now Generally Available in us1.

OpenAI-hosted sandbox compute is now billed during active turns. You no longer pay for idle time between turns.

You can now choose 12-hour prompt caching in the API. 12-hour prompt caching keeps shared instructions, tools, and context cached longer to benefit from lower cached-input pricing, even when requests are hours apart. 12-hour cache writes cost 2.5x the input token price. Read more 
 in the Agents API now include the Artifact SDK and skills for creating and editing spreadsheets, presentations, and Word documents.
 with a supported model to reduce the time between generated tokens.
pre-warm an OpenAI-hosted sandbox
 before attaching it to an Agents API session. Prewarming improves latency by creating and configuring the sandbox before a user finishes sending their message. This means the user doesn't have to wait for all this work to complete.
OpenAI-hosted sandbox compute is now billed during active turns. You no longer pay for idle time between turns.

We've released the following Node Slack SDK-related updates

Release: Java Slack SDK v1.52.0
Release: Python Slack SDK v3.45.0
Release: Node Slack SDK updates
Release: Java Slack SDK v1.52.0
Release: Python Slack SDK v3.45.0
Release: Node Slack SDK updates
We've released the following Node Slack SDK-related updates:
Fly your freak, geek, or mild-mannered fl

This is a breaking change. @cloudflare/computer stores files in different tables from @cloudflare/shell, and there is no automatic data migration between workspace formats.

WAF Release - 2026-10-21 - Emergency - Cloudflare Managed Ruleset
This emergency release adds four rules to the Cloudflare Managed Ruleset to detect anomalous request patterns. Two rules block matching requests, and two log matches without blocking.
Generic Rules - Anomalous Execution - 1
Generic Rules - Anomalous Execution - 2
Generic Rules - Anomalous Execution - 3
Generic Rules - Anomalous Execution - 4
WAF Release - 2026-10-21 - Emergency - Cloudflare Free Ruleset
This emergency release adds two rules to the Cloudflare Free Ruleset to block anomalous request patterns.
Generic Rules - Anomalous Execution - 1
Generic Rules - Anomalous Execution - 2
Generic Rules - Anomalous Execution - 3
Generic Rules - Anomalous Execution - 4
Think agents now use a @cloudflare/computer workspace
 now use the workspace from 
 as well as the filesystem tools. A JavaScript execution environment can be configured by adding the 
 is deprecated, and so is Think's 
. These will no longer be developed nor supported from today onwards.
 { WorkerJavaScriptBackend } 
 "@cloudflare/computer/backends/worker-javascript"
 { WorkerJavaScriptBackend } 
 "@cloudflare/computer/backends/worker-javascript"
Migrate y

A new GA release for the Linux Cloudflare One Client is now available

Cloudflare One Client for Windows (version 2026.8.2115.0)
This hotfix addresses an issue building trusted certificate chains.
Cloudflare One Client for macOS (version 2026.8.2115.0)
This hotfix addresses an issue building trusted certificate chains.
Cloudflare One Client for Linux (version 2026.8.2115.0)
A new GA release for the Linux Cloudflare One Client is now available on the 
This hotfix addresses an issue building trusted certificate chains.
Cloudflare API MCP server now supports step-up authorization
Grant only the required scopes when you connect, then authorize more on demand as your agent performs a task. When a tool call needs a scope you have not granted, the server returns an 
 naming it, and your MCP client asks you to approve it. Scopes you already granted are kept.
To start with the least access, choose 
 on the consent page when you connect 
Available now in all MCP clients that support step-up authorization.
Introducing Clairic: an extraction model for typed values, now on Workers AI
 is now available on Workers AI as a preview. Clairic is the first 
: a System One model that answers with values instead of text. We intend to release the model with open weights soo

You can export any data you want to keep from the banner

capabilities.thinking.types.between_tools
thinking: {type: "between_tools"}
, which turns off up-front thinking. See 
, or earlier turns can also return a 400 error. Adaptive thinking is on by default, so a response can begin with 
 in the Console. You can export any data you want to keep from the banner and under your 
In the Console, users with the Developer role can now access the 

GitHub Copilot models deprecated on October 19, 2026

 Copilot model policy API for enterprise, orgs, and teams 
 GitHub Copilot models deprecated on October 19, 2026 
 Some Git over HTTPS may temporarily require authentication 
 CodeQL changes for macOS 27, Xcode 27, and Swift 6.4 

Manage packed product dimensions with the GraphQL Admin API

Hydrogen developer preview update: October 8, 2026
Hydrogen developer preview update: October 2, 2026
Manage packed product dimensions with the GraphQL Admin API
Hydrogen developer preview update: September 11, 2026

MiniMax M3.1 Flash now available on AI Gateway for free

Updates to Hobby and Pro Terms of Service
Updates to Vercel's Hobby and Pro Terms of Service.
Mercury 3 now available on AI Gateway
Call Inception's Mercury 3 through Vercel AI Gateway with one API key, no provider account, spend tracking, and request traces.
MiniMax M3.1 Flash now available on AI Gateway for free
Call MiniMax M3.1 Flash through Vercel AI Gateway with one API key: no provider account, automatic fallbacks, spend tracking, and traces on every request.

Cloud Workload Security is now available in Beta

Precursor adds Monitor mode
We released Monitor mode at customers' request so they can test Precursor and the Precursor Interstitial without updating bot score.
 means Precursor detections can affect bot score and Challenge clearance. Selecting 
 means Precursor detections do not affect bot score or Challenge clearance.
We also separated the Precursor Interstitial from the mode. Set the sitewide default with 
 to customize it for specific requests. For example, leave 
 off across most of your site, but require an interstitial Challenge on 
 to enforce a valid session before purchase.
Cloud Workload Security is now available in Beta
Cloud Workload Security (CWS)
 is now available in Beta. Apply policy controls to cloud API requests before they reach your cloud provider.
Define policies with request filters and Rego checks. For example, block requests that would make an R2 bucket public. Use workloads and policy sets to target your cloud environments.
Manage your policies in the Cloudflare dashboard. Run the CWS proxy in your environment and route client requests through it to enforce your policies.
CWS requires a Zero Trust subscription. The Zero Trust Free plan is sufficient.
To co

The Local Explorer API exposes the same operation for tools and AI agents.

Test Cron Triggers with Local Explorer
Local Explorer can now send one-off Cron Trigger invocations to a Worker's 
 handler during local development. This removes the need to construct request URLs when testing handler behavior.
Start your local development server with 
 on the server URL and select 
The browser interface supports the following tasks:
Invoke configured cron expressions
Set reusable scheduled times
Ad hoc triggers and scheduled time presets stay in your browser. They do not change 
, your Wrangler configuration, or deployed Cron Triggers. Local development does not run cron schedules automatically.
Full logs and traces are available in the development session that owns the Worker when that session has 
The following example uses port 
. Replace it with your development server port, such as 
The Local Explorer API exposes the same operation for tools and AI agents. The request targets an exact Worker name and accepts a cron expression and optional scheduled time:
 "http://localhost:8787/cdn-cgi/local/explorer/api/local/scheduled?worker=my-worker"
 "Content-Type: application/json"
 '{"cron":"0 * * * *","scheduled_time":1745856238000}'
For more details, refer to 
Test 

DeepSeek V4.1 Flash 1017 now available on AI Gateway

AI Gateway logs now show session affinity
Vercel AI Gateway logs now group requests into sessions, with cache hit rate, cost, turns, and the coding agent behind each conversation.
Sam Chitgopekar, Jerilyn Zheng
DeepSeek V4.1 Flash 1017 now available on AI Gateway
Call DeepSeek V4.1 Flash 1017 through Vercel AI Gateway with one API key, image input, spend tracking, and traces on every request.
Elorian AI's Glimpse now available on AI Gateway
Call Elorian's Glimpse through Vercel AI Gateway with one API key, no provider account, spend tracking, and request traces.
Jerilyn Zheng, Rohan Taneja, and 1 other

We've added support for the following Slack Code API methods

Release: Java SDK v1.52.0
Release: Python SDK v3.45.0
Release: Node SDK updates
Release: Java SDK v1.52.0
 type) and related fields, as well as 
 type) and related fields.
We've added support for the following Slack Code API methods:
agents.conversations.archive
agents.conversations.create
agents.conversations.getCanvas
agents.conversations.listViews
agents.conversations.removeView
agents.conversations.setCanvasContent
agents.conversations.setCommands
agents.conversations.setProperties
agents.conversations.setView
Release: Python SDK v3.45.0
 type) and related fields.
We've added support for the following Slack Code API methods:
agents.conversations.archive
agents.conversations.create
agents.conversations.getCanvas
agents.conversations.listViews
agents.conversations.removeView
agents.conversations.setCanvasContent
agents.conversations.setCommands
agents.conversations.setProperties
agents.conversations.setView
Release: Node SDK updates
We've released the following Node SDK-related updates:
The default dispatcher now pins the WebSocket connection to HTTP/1.1, since 
 offers HTTP/2 by default. To do the same with a custom 
requestTls: { allowH2: false }

Your builds now run on newer versions of Node.js, Python, Ruby, Go, Bun, Yarn, and Python package managers by default, so you get the latest fixes and features without changing your build…

AI Search keyword search supports Japanese, Chinese, and Korean queries
 tokenizer now matches Japanese, Chinese, and Korean queries, including full natural-language questions such as 
. Previously, a query without spaces was treated as a single exact phrase and usually returned no keyword results.
 tokenizer does not work well for these languages. If your content is in Japanese, Chinese, or Korean, set 
. Changing the tokenizer triggers a full reindex.
Search Cloudflare documentation with the Cloudflare CLI
, so you and your coding agent can find Cloudflare documentation without leaving the terminal. Search for guides, tutorials, and examples across Cloudflare products.
To install or update to the latest release:
 install --global cf@latest
Describe what you want to do, or ask a question:
 "rate limit requests with WAF"
The command searches live Cloudflare documentation and returns up to five ranked JSON results. Each result includes a title, description, and documentation URL. An Internet connection is required.
Agents can parse the results and fetch a complete page as Markdown. For example, use 
 to select the first result, then request its URL with the 
This release also standa

Multi-repository support and other improvements for GitHub in Slack and Teams

 Open source license compliance generally available 
 Xcode 27 runner image generally available 
 Multi-repository support and other improvements for GitHub in Slack and Teams 

Checkout MCP and Cart MCP now support UCP buyer consent

Checkout MCP and Cart MCP now support UCP buyer consent

Reflection AI's Beam now available on AI Gateway for free

Perplexity's Decider V1.2 models now available on AI Gateway
Call Perplexity Decider V1.2 and Decider Flash V1.2 through Vercel AI Gateway with one API key, shared budgets, and usage tracking.
Reflection AI's Beam now available on AI Gateway for free
Try Reflection AI's Beam for free for a limited time on Vercel AI Gateway with one API key, spend tracking, and request traces
Jerilyn Zheng, Kevin Dawkins, and 2 others

Voice Integrity now supports all three major US networks

Voice Integrity now supports all three major US networks
Voice Integrity, part of Twilio’s Voice Trust offering, enables businesses to register their details and associated outbound phone numbers directly with major US analytics vendors. This proactive registration helps carriers identify legitimate business traffic, reducing the likelihood of your calls being blocked or labeled as spam.

Create a custom voice from a text description through the API or voice Playground, then reuse it in GPT-Live sessions.

 Windows app and CLI deployment 
 Designing failover across OpenAI model providers 
 for all API customers. Create a custom voice from a text description through the API or voice Playground, then reuse it in GPT-Live sessions. Creating a prompt-generated voice is free; speech generation uses regular GPT-Live session billing.
natural voices for GPT-Live
: Nuri, Juni, and Flitz (German); Brise and Sillage (French); Nira (Hindi); Harema and Shida (Japanese); and Noeul (Korean).

Cloudflare WAN and Magic Transit IPsec and GRE tunnels now support BGP import and export filtering.

Application Library now supports custom applications
Starting today, you can create 
 and reference them in Gateway DNS, Network, and HTTP policies. You can define an application with hostnames, IP subnets, or both. Then, optionally add TCP or UDP ports or port ranges to restrict HTTP and Network matching.
This release also improves search and filtering in the Application Library, updates the interfaces, data, and metrics used to review applications, and makes it easier to select and manage applications in the Gateway policy builder.
Applications and app types
Validate data loss prevention matches with Cloudflare Workers
Data loss prevention (DLP) custom pattern entries can use Cloudflare Workers in your account to validate matches with organization-specific logic. Your Worker can adjust a match's confidence or reject the match.
For setup steps and the Worker contract, refer to 
Validate data loss prevention matches with Cloudflare Workers
BGP route filtering for IPsec and GRE tunnels
Cloudflare WAN and Magic Transit IPsec and GRE tunnels now support BGP import and export filtering.
Create reusable filter profiles that specify an 
 action and a list of Classless Inter-Domain Routin

Requests to Claude Opus 5.5 no longer require

 now returns the text each organization member saved as 
 in Cowork, in beta for Claude Enterprise organizations. Call 
GET /v1/compliance/organizations/{org_uuid}/user_preferences
 with your existing Compliance Access Key and the 
 is out of research preview for Claude Opus 5.5, and you no longer need to request access. Requests to Claude Opus 5.5 no longer require the 
 beta header, and requests that still send it keep working. Claude Opus 5.5 now has a default fast mode rate limit in the Start, Build, and Scale usage tiers. Fast mode for Claude Opus 5 and Claude Opus 4.8 remains in research preview. Keep sending the beta header with fast mode requests to those models.
 for Claude Opus 5.5 is now available on 
 for deployments hosted on Azure.

Upcoming deprecation of selected GitHub Copilot models in mid-November

 Multi-repo support and other improvements for GitHub Copilot in Slack and Microsoft Teams 
 Download GitHub Code Quality license usage as a CSV 
 Upcoming deprecation of selected GitHub Copilot models in mid-November 
 AI Scan for pull requests generally available 
 Agentic autofix for code scanning alerts general availability 
 Email notifications for repository push events have been retired 

Check your app for security vulnerabilities with `shopify app security check`. Run it before you submit an app, and on every release, to catch problems in your own code and get remediation guidance.

Build with confidence: Shopify AI Toolkit's security check 
Check your app for security vulnerabilities with `shopify app security check`. Run it before you submit an app, and on every release, to catch problems in your own code and get remediation guidance.

Cat Jam is now available in stealth for free on AI Gateway

Vercel Token Pass, now in early access, gives your team $80 in monthly credit for featured open-weight models for $30, starting with GLM 5.3 and Kimi K3. Use it with your coding agent or to power a personal agent on Vercel.
Jas Garcha, Krish Krish, and 2 others
Vercel Daemons is now in public beta
Run queue consumers, workflow workers, and self-hosted CI runners on Vercel.
Steren, Gal Schlezinger, and 2 others
Liquid AI's d1-ultra now available on AI Gateway
Call Liquid AI's d1-ultra through Vercel AI Gateway with one API key, unified spend tracking, and request logs.
Muse Spark Open now available on AI Gateway
Call Meta's Muse Spark Open through Vercel AI Gateway with one API key, no provider account, automatic fallbacks, spend tracking, and request traces.
Vercel Connect now supports Secure Compute
Connectors can now reach providers that restrict access by IP address, using your Secure Compute network’s static IPs.
Dima Voytenko, Hedi Zandi, and 2 others
Cat Jam is now available in stealth for free on AI Gateway
Call the stealth model Cat Jam for free through Vercel AI Gateway with one API key: no provider account, spend tracking, and traces on every request.
Vercel Drives is now

Using the Webhook Configuration API, customers can configure how Twilio authenticates and delivers outbound webhooks, per URL. The API consists of two resources: Webhook Settings and Webhook Rules.

Webhook Configuration API is now Generally Available
Using the Webhook Configuration API, customers can configure how Twilio authenticates and delivers outbound webhooks, per URL. The API consists of two resources: Webhook Settings and Webhook Rules.

Your app can act while your user is speaking or react to what Live says. Let Live call Decisions directly through native delegation, or trigger decisions as input or output transcript deltas arrive.

Decisions integration in GPT-Live
. Your app can act while your user is speaking or react to what Live says. Let Live call Decisions directly through native delegation, or trigger decisions as input or output transcript deltas arrive.

Accounts are no longer limited to 5 numbered sets. Create a set once and assign it to one or more zones in the same account.

Infrastructure applications support a configurable session duration
Infrastructure applications
 now have a configurable session duration with a default value of 24 hours. You can set the session duration when creating or editing an infrastructure application in the dashboard or via the API.
When the session duration elapses, any active SSH connections through that application will be closed, and users will need to reconnect. Previously, infrastructure applications did not enforce a session duration limit. Sessions could persist beyond 24 hours in some cases, but were never guaranteed beyond 10 hours due to 
Gateway connection limits
When a target matches multiple infrastructure applications, the shortest session duration applies.
Configure Advanced Custom Nameservers with nameserver sets (beta)
 are now available in beta to Enterprise accounts. A nameserver set groups two to five custom nameserver names with Cloudflare-assigned IP addresses. You can assign the set to zones in the same account.
Enterprise customers using Cloudflare DNS can create Advanced Custom Nameserver sets. These sets distribute addresses across Advanced anycast network groups to improve resiliency.
 sets, mod

The official Supabase Go SDK v0.1.0-alpha.1 is in public alpha. Its initial feature set lets your backend verify end-user access tokens and query your database as that user under Row Level Security.

[Public Alpha] Supabase Go SDK
The official Supabase Go SDK v0.1.0-alpha.1 is in public alpha. Its initial feature set lets your backend verify end-user access tokens and query your database as that user under Row Level Security.

The Claude SDK emits spans in Python, TypeScript, C#, Go, Java, PHP, and Ruby.

 in beta, so you can trace Messages API requests and Claude Managed Agents sessions in your observability backend. The Claude SDK emits spans in Python, TypeScript, C#, Go, Java, PHP, and Ruby. To get spans from the API, 
add an OpenTelemetry destination

GitHub Actions workflow lockfiles in public preview

 HydraFusion updates and new Max option 
 GitHub Actions workflow lockfiles in public preview 

Amazon S3 is now available in the Vercel Marketplace and v0 with guided setup and automatic project configuration built into the Vercel dashboard.

Amazon S3 joins the Vercel Marketplace
Amazon S3 is now available in the Vercel Marketplace and v0 with guided setup and automatic project configuration built into the Vercel dashboard. 
Nemotron 3.5 Lightning now available on AI Gateway for free
Use Nvidia's Nemotron 3.5 Lightning for free through Vercel AI Gateway with one API key: no provider account, spend tracking, and traces on every request.

Twilio Cohorts is now available in Private Beta, providing a set of APIs designed to handle list building, audience segmentation, and bulk execution natively within the Twilio platform.

Unified Login for SendGrid Marketplace Customers
SendGrid marketplace customers can now take advantage of the 
 that lets you create a Twilio login for every individual user accessing your SendGrid account. This provides a more secure access pattern with the ability to define permissions for each user instead of a single, shared admin permission set. 
When accessing your SendGrid marketplace account from one of the marketplace integrations - Microsoft Azure, Google Cloud, Heroku, or Amazon Web Services - you will be prompted to provide an email address to create your Twilio login. If you already use another Twilio product and have an existing Twilio login, you can use that email address and password for SendGrid access.
This will be rolled out over the next couple weeks for all SendGrid marketplace customers. For more details, see the documentation 
Twilio Cohorts for Native List Building and Bulk Messaging
Twilio Cohorts is now available in Private Beta, providing a set of APIs designed to handle list building, audience segmentation, and bulk execution natively within the Twilio platform. Set up your customer profiles, segment them, and trigger messages using your existing Twilio 

Maintaining software with the GPT-6 family

 Maintaining software with the GPT-6 family 

Bot scores, verified bot status, and JA3/JA4 fingerprints no longer represent the internal connection between Cloudflare services.

Cloudflare API MCP server sends Workers Issues as MCP Events
 provides built-in error monitoring for Cloudflare Workers. It detects production failures and groups related failures into issues without an SDK or application wrapper.
 now sends these issues as 
, the first event it exposes. MCP clients discover 
cloudflare.alert.workers_observability_real_time_issue
, scoped to an account or a single Worker. When Issues detects a new or recurring issue, the server posts a signed event to the client's webhook, so an agent can start investigating without polling.
 on your Worker and connect 
 with the Notifications Write and Workers Observability Write permissions to a client that supports MCP Events webhooks.
New persistent browser tool in the Agents SDK, with tabs and logins that last between turns
 browser it can return to on later turns. Your agent can open a website, inspect a page, and come back to it with its tabs, cookies, and login session intact while the browser session remains alive.
 to your agent, the model writes code that drives the browser through the 
Chrome DevTools Protocol (CDP)
. Screenshots return as images that an image-capable model can inspect and your UI can d

You get the SDK's calls in the same traces as the rest of your app: which ran, how long they took, whether they failed.

OpenTelemetry traces and metrics in the Supabase .NET SDK
 emit traces and metrics through 
. Each client exposes its own 
, so you subscribe to them the same way you subscribe to any other .NET instrumentation. The SDK takes no dependency on the OpenTelemetry packages, and the clients stay silent until something subscribes, so there is no overhead when you are not collecting.
This covers the Auth, Postgrest, Storage, and Functions clients. Realtime is not yet instrumented. URLs are recorded with the query string stripped, and no token, credential, or payload is placed in a tag.
) to tell apart operations that share an HTTP verb
supabase.postgrest.http.request.duration
, …), with a child span for the HTTP call
supabase.gotrue.http.request.duration
storage.transfer.direction
 tag on uploads and downloads; a resumable (TUS) upload is a single span for the whole transfer
supabase.storage.http.request.duration
supabase.storage.transfer.duration
supabase.storage.transfer.size
One per invocation, with a 
 tag; a relay error is a failed span even when the HTTP status succeeds
supabase.functions.invoke.duration
Add the OpenTelemetry hosting package and an exporter alongside the SDK:
<Packa

Search and filter for budgets now available

 GitHub App improvements for least privilege and management 
 Gemini 4 Argon in GitHub Copilot 
 Audit GitHub Code Quality finding dismissals and reopenings 
 Secret scanning blocks Anthropic keys by default, adds Salesforce 
 Enterprise managed settings enforcement updates 
 Improved detection for withdrawn Dependabot alerts 
 Search and filter for budgets now available 
 Code scanning AI Scan metrics in security overview 

Cart updates that result in no changes to the cart no longer trigger carts/update webhooks

Add shopping and Shop Pay checkout to any agent with Shop MCP 
Cart updates that result in no changes to the cart no longer trigger carts/update webhooks

MAI-Image-2.6 and MAI-Image-2.6-Flash now available on AI Gateway

Drama 3 now available on AI Gateway
Generate expressive speech with Fish Audio's Drama 3 through Vercel AI Gateway, using one API key with spend tracking and request traces
MAI-Image-2.6 and MAI-Image-2.6-Flash now available on AI Gateway
Generate and edit images with MAI-Image-2.6 and Flash through Vercel AI Gateway, with one API key, unified billing, and request traces
Kevin Dawkins, Jerilyn Zheng, and 1 other
Repository checkout and Git LFS downloads are now faster
Git deployments now spend less time getting your project's files ready before the build runs. The improvements apply automatically.
Gemini 4 Argon now available on AI Gateway
Call Google's Gemini 4 Argon through Vercel AI Gateway with one API key: no provider account, spend tracking, and traces on every request.
Zachary Chen, Jerilyn Zheng

Intelligent Alerts is now available in the new Twilio Console, giving Messaging customers a more unified and consistent way to investigate anomalous events.

Intelligent Alerts in the new Twilio Console
Intelligent Alerts is now available in the new Twilio Console, giving Messaging customers a more unified and consistent way to investigate anomalous events. This update includes improved alert summaries, the ability to provide feedback on alerts, and a dynamic set up notifications prompt when email alerts have not yet been configured.
Rich Communication Services
RCS messaging now supported on all major Canadian carriers
You can now send RCS messages to Rogers phone numbers, completing RCS coverage across Canada’s major carriers.
When requesting RCS Sender approval in Canada, Twilio will now submit the Sender for review across all major carriers, including Rogers. RCS Senders already approved by other Canadian carriers will automatically be submitted to Rogers for review and approval. No action is required.
To start sending branded RCS messages, go to the Twilio 
 to create and submit an RCS Sender.
For more information, see our RCS 
Traffic Optimization Engine (TOE) is now generally available
Traffic Optimization Engine (TOE) is now Generally Available for short code and toll-free traffic in North America and all sender types internation

will be displayed for basic sandboxes (previously we only showed the type label for partner sandboxes, to differentiate from developer sandboxes).

Release: Slack CLI v4.10.0
Release: Slack CLI v4.10.0
 command now automatically syncs the manifest from app settings to your local project.
We've made a small change to the output of the 
 command: status and type previously displayed lowercase, and now 
 will be displayed for basic sandboxes (previously we only showed the type label for partner sandboxes, to differentiate from developer sandboxes).

As part of this change, the Zero Trust Network items were removed in favor of the new experiences available

Cloudflare One Client for Windows (version 2026.8.2110.0)
This hotfix resolves an issue where the client could repeatedly disconnect and reconnect when a split tunnel configuration with hostname-based entries failed to apply.
Cloudflare One Client for macOS (version 2026.8.2110.0)
This hotfix resolves an issue where the client could repeatedly disconnect and reconnect when a split tunnel configuration with hostname-based entries failed to apply.
Cloudflare One Client for Linux (version 2026.8.2110.0)
This hotfix resolves an issue where the client could repeatedly disconnect and reconnect when a split tunnel configuration with hostname-based entries failed to apply.
New web_fetch tool in the Agents SDK for reading webpages and documents, with automatic markdown conversion
 tool that reads webpages, PDFs, and supported Office documents, using 
Workers AI Markdown Conversion
 to turn them into text the model can read. The tool requests Markdown directly from sites that support 
 and formats JSON for the model.
 tool to your agent, the model provides a URL and receives back the page content, along with the final URL, HTTP status, and content type. Long pages come back in smaller sectio

In the past 30 days, fewer than 0.0001% of connections to Supabase projects negotiated these ciphers, so we expect little to no impact.

An outdated subset of TLS 1.2 ciphers will be disabled on project HTTP APIs
Most users won't notice any change. Starting November 10, 2026 at the earliest, Supabase will stop offering some outdated TLS configurations on project HTTP APIs (
 and custom domains). Users on old, unsupported operating systems, or embedded devices that haven't been updated, may lose access if their device only supports the configurations being removed.
The configurations being removed are four CBC-mode TLS 1.2 cipher suites. Cipher suites determine how a connection is encrypted. These older suites have known security weaknesses and often trigger warnings in security scans. We plan to stop offering these ciphers on TLS 1.2:
TLS_ECDHE_ECDSA_WITH_AES_128_CBC_SHA256
ECDHE-ECDSA-AES128-SHA256
TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256
TLS_ECDHE_ECDSA_WITH_AES_256_CBC_SHA384
ECDHE-ECDSA-AES256-SHA384
TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA384
Supabase has only supported TLS 1.2 and 1.3 for several years. There is no change for TLS 1.3.
Auth, the Data API, Storage, Realtime, and Edge Functions are all sub-routes of the Supabase HTTP API, so all five are affected. Direct Postgres connections, pooler connections, and the M

Push attribution for commits in limited public preview

 Client telemetry user attribution and configurable capture 
 Push attribution for commits in limited public preview 
 Anonymous organization-level registries for Dependabot 

Identify the published version running in a POS extension

Detect when a POS extension screen finishes navigating
Identify the published version running in a POS extension

Muse Wonder now available on AI Gateway

Muse Wonder now available on AI Gateway
Call Meta's Muse Wonder through Vercel AI Gateway with one API key, no provider account, spend tracking, and request traces.
Jerilyn Zheng, Zachary Chen

You can now manually request an API Shield schema learning run without waiting for the weekly schedule. Use this during testing after sending representative traffic to your API.

Run schema learning on demand
You can now manually request an API Shield schema learning run without waiting for the weekly schedule. Use this during testing after sending representative traffic to your API.
 menu for the operations table and select 
. The run covers the entire zone and uses observed traffic. Existing learning thresholds still apply.
The dialog shows the learning status and last completed run for the zone. The 
 view shows the learning result and last learning run for each operation. You can review individual results while the zone-wide run continues.
For instructions and traffic requirements, refer to 
Run schema learning manually

Scoped personal access tokens are now available to everyone. Limit a token to specific projects or organizations and grant only the permissions it needs on the Management API, MCP server, and CLI.

ASP.NET Core dependency injection for the Supabase .NET SDK
Supabase.Extensions.DependencyInjection
 is a new package that provides an easier way to plug the Supabase .NET SDK into your application. It exposes a new method on 
 which registers the main client and all sub-clients:
builder.Services.AddSupabase(
 supabaseUrl: "https://xyz.supabase.co",
 supabaseKey: builder.Configuration["Supabase:Key"]!,
 configureOptions: options =>
 options.AutoConnectRealtime = true;
 options.PostgrestRetry = new RetryOptions { MaxRetries = 3 };
It registers all clients (
) with a scoped lifecycle, so you can resolve them wherever you need them:
app.MapGet("/movies", async (IPostgrestClient postgrest) =>
 await postgrest.Table<Movie>().Get());
The package is available on 
dotnet add package Supabase.Extensions.DependencyInjection
You can always register all the required clients in 
 yourself. This package simply does it all for you and removes boilerplate from your codebase.
The Supabase .NET SDK is now officially supported
 is now a first-party, officially supported SDK. It started as a community project, went through a period of low activity, and is now maintained by Supabase with a team behind 

New controls and chat improvements in Copilot for JetBrains

 New controls and chat improvements in Copilot for JetBrains 

is not supported, and manual extended thinking budgets and assistant prefill are not supported (both return a 400 error).

You can now let a Claude Managed Agents agent use 
 beta header. For work with many pieces, such as reviewing hundreds of documents, the agent can write a workflow. A workflow is a program that runs many agents in phases and combines their results. The server runs it in the background as a workflow run. To 
turn dynamic workflows on
{"type": "multiagent_20261001", "workflows": {"type": "enabled"}}
. To guide the agent, tell it in its system prompt when to start a run. Follow each run through 
 events on the session's event stream. See 
The Compliance API can now download Claude Docs documents as Word files, in beta. See 
Retrieve files and artifacts
), the sampling parameters 
, and assistant message prefill can each return a 400 error. 
 also returns a 400 error: use the 
 toolset on the Claude API and Google Cloud, or 
 on Amazon Bedrock. A request that sends thinking blocks back after a change to 
, or earlier turns can also return a 400 error. On Amazon Bedrock, structured outputs aren't available for Claude Haiku 5.5. Adaptive thinking is on by default, so a response can begin with 
 blocks, and their text is omitted unless you set 
. The same text also counts as more tokens. 

Copilot code review: New organization billing options and controls

 GitHub Copilot weekly releases — October 5 
 CodeQL 2.27.2 improves C++, Go, Rust, and JavaScript analysis 
 Copilot code review: New organization billing options and controls 

Global Catalog REST API stops serving traffic on November 2, 2026

Global Catalog REST API stops serving traffic on November 2, 2026
Catalog API now returns compare-at prices as 
 field for metafield declarations in Checkout and Customer Account UI extensions, required in 2027-01

Microsoft Decision-1 now available on AI Gateway

Agents can now buy domains with the Vercel CLI
Agents can now use the Vercel CLI to purchase domains.
Melkey Moksyakov, Esteban Suárez
New Pro teams now default to 30-day deployment retention
New Pro teams use 30-day deployment retention by default, with the option to keep longer history.
Pranav Kanchi, Jay Gengelbach, and 1 other
Deployment Storage billing begins for existing Pro teams
Existing Pro teams will pay $0.10 per GB-month for Deployment Storage and Functions Storage, and the retention window moves to 30 days on October 23.
Jay Gengelbach, Pranav Kanchi, and 1 other
Microsoft Decision-1 now available on AI Gateway
Call Microsoft's Decision-1 through Vercel AI Gateway with one API key to classify text, route requests, and track usage and spend
Jerilyn Zheng, Kevin Dawkins, and 2 others
Liquid AI's d1 is available on AI Gateway
Evaluate typed questions with Liquid d1 on Vercel AI Gateway using the AI SDK, HTTP API, or TypeSafe-compatible API.
Zachary Chen, Rohan Taneja, and 2 others

Both tags appear in the Call Summary in Console, in the Voice Insights REST API, and through Event Streams. You can also filter the Call Insights dashboard by either one.

Voice Insights now tags HD audio calls
Voice Insights now tags calls as 
 when they connect with the AMR-WB or Opus codec.
Use the tag to confirm your endpoints negotiated what you configured, and to correlate HD usage with transcription accuracy, AI agent performance, and customer satisfaction.
Calls that carry HD audio are tagged as 
 when the longest portion of the call connects to a component or another endpoint that does not support HD. Twilio converts the audio to narrowband to keep the call connected.
Both tags appear in the Call Summary in Console, in the Voice Insights REST API, and through Event Streams. You can also filter the Call Insights dashboard by either one.

is removed from converted responses rather than recalculated, because the Markdown body is streamed.

Cloudflare API MCP server serves Cloudflare skills
Cloudflare API MCP server
Skills over MCP extension
. MCP clients that support the extension discover the skills with 
https://mcp.cloudflare.com/mcp
MCP client that supports the extension
Improved HTTP/3 client cancellation reporting
Cloudflare has improved how it handles and reports client-cancelled HTTP/3 requests across Free, Pro, Business, and Enterprise plans. Customers now get a clearer view of client behavior in Cloudflare analytics and, where available, logs.
Previously, Cloudflare did not always stop an HTTP/3 request when the client cancelled its request stream. Some cancellations were already recorded as 
, while others continued to the origin and showed the eventual upstream status.
Cloudflare now stops affected requests sooner, reducing unnecessary origin work, and records them as 
. Customers may notice more 
 status codes for HTTP/3 traffic. This reflects more consistent reporting of existing cancellations, not an increase in failed requests.
 status codes in availability calculations should consider excluding them from server-side error rates because they represent requests cancelled by clients.
More efficient Mark

OpenAI Ultrafast mode now available on AI Gateway

Skip sending request bodies to Routing Middleware
Set skipMiddlewareRequestBody to stop forwarding the client request body to Routing Middleware, reducing Fast Origin Transfer usage and helping improve Time to First Byte.
Vercel Sandbox creation now returns a ready sandbox
Vercel Sandbox creation is now more consistent and now includes startup time previously spent waiting in the first command.
Software Engineer, Infrastructure
Grok Imagine Video 1.5 Lite on AI Gateway
Call xAI's Grok Imagine Video 1.5 Lite through Vercel AI Gateway with one API key, unified billing, and request traces.
Step 5 Preview now available on AI Gateway
Call StepFun's Step 5 Preview through Vercel AI Gateway with one API key, no provider account, spend tracking, and request traces.
OpenAI Ultrafast mode now available on AI Gateway
Use OpenAI Ultrafast for GPT-6 Astra and GPT-6.1 Sol on AI Gateway with the AI SDK, Responses API, Chat Completions, or WebSocket.
Kevin Dawkins, Jerilyn Zheng, and 1 other
FLUX 3 Image now available on AI Gateway
Generate and edit images with FLUX 3 Image through Vercel AI Gateway, with one API key, unified billing, and request traces.
Jerilyn Zheng, Rohan Taneja, and 1 other

Starting October 5, 2026, paid support customers can reach Twilio through live chat for help with Segment and all Twilio platform applications and products.

Live support coverage across the Twilio platform and Segment
Starting October 5, 2026, paid support customers can reach Twilio through live chat for help with Segment and all Twilio platform applications and products.