Official updates for developers building with @ClaudeAI
Joined February 2026
- Tweets579
- Following2
- Followers817K
- Likes99
New video: @dejno and @luccasiau discuss how we launch new models on our API and the features that ship with them.
They also dig into how to rethink your harness and measure cost per task when you upgrade to a new model.
Watch the full conversation:
youtu.be/p2xvJAbF-i4
Self-hosted Claude Managed Agents is now in private beta.
You can host the agent harness, sandboxes, and session history, in your own cloud or on-premises, and choose where requests to Claude are sent.
Use self-hosted Managed Agents for work that needs access to your code and internal systems, like fixing broken builds or triaging alerts.
This private beta is only available to eligible orgs, and you can request access with your Anthropic account team.
claude.com/resources/article…
We've given all Pro, Max, Ultra, and Team users one free full reset, across all models and limits. Use it anytime before December 10 at 2:00PM PT.
We recently fixed a few small issues that used more limits than intended, and the Fable resets didn't do much for those of you who'd already hit your weekly limits for all models. While these issues didn't affect everyone, we want to make up for the trouble.
You'll find it in Settings > Usage, or at clau.de/reset.
Claude now supports more of the MCP Apps extension, such as app tools and embedded sites, so your full app can run inside Claude.
Start building: claude.com/docs/connectors/b…
Which Claude model should you build with?
Our new guide breaks down when to use Fable 5.2, Opus 5.5, Sonnet or Haiku. It also covers when to adjust effort instead of switching models, and how to save cost by putting subagents on smaller models.
claude.dev/blog/which-claude…
Fable 5.2 is now available in the Claude Platform and Claude Code.
It’s up to 30% faster than Fable 5.1, and costs $8/$40 per 1M tokens, down from $10/$50.
We've made it easier to get your repo running in Claude Code cloud sessions on Pro, Max, and Ultra.
Claude figures out what dependencies, network access, and API keys it needs, then saves the environment for next time. API keys are saved securely, so Claude never sees them.
Background subagents in Claude Code now use less of your usage limit.
A running subagent updates its status line every 30 seconds, and each update used to re-read its whole conversation. Now Haiku 5.5 writes it from short notes instead, so each update costs about 99% less.
Users can now auto-connect plugins when they log in to Claude, with MCP servers that accept Claude as a trusted issuer.
If you’re building plugins for Claude, add support so users get started faster and stay connected without re-authorizing.
Enterprise-managed auth (EMA) lets admins connect plugins for their entire organization through their identity provider, so members don’t have to search for, sign in to, and authorize each plugin themselves. It’s built on an open extension to MCP.
modelcontextprotocol.io/exte…
October was a big month for Claude Code 🍁
We shipped mods, made the desktop app better at running lots of sessions side by side, gave you more insight into where your usage goes, and plenty more. Here's a recap!
Coming back to an old session got lighter on your usage.
Claude Code now compacts long idle sessions right before the prompt cache expires (~1h). If you come back to one later, it only has to reprocess the summary instead of the entire conversation.
And on Pro and Max, resuming a really long conversation now gives you a heads-up first if picking it back up would use a big chunk of your 5-hour limit.
Message threads are now in public beta on the Messages API.
The API caches your conversation on the server between turns, so instead of resending the full conversation, you send only new messages and the previous message ID, and Claude starts responding sooner.
We've raised the max request size for Messages and Token Counting on the Claude API from 32 MB to 128 MB.
Image-heavy requests like long computer-use sessions and big PDFs were previously hitting 32 MB with plenty of context window left. Now you get ~4x more room.
For requests with more than 20 images, we've also raised the per-image limit from 2000 px to 3000 px.
128 MB applies on the first-party Claude API. Through cloud platforms, the limit is between 20 and 32 MB.
Docs: platform.claude.com/docs/en/…
We’re adding support for MCP Tasks and Elicitations in Claude.
Tasks let Claude give plugins long-running jobs such as deep research and report back when they’re done.
We’ve added a new way to access Claude on Google Cloud.
You can now use the full Claude API from your Google Cloud account, including Claude Managed Agents, code execution, Opus 5.5 fast mode, and new features as they launch.
It uses your Google Cloud IAM credentials, and usage draws down your Google Cloud commitment. It’s available today with US and Global endpoints.
Check out the docs: platform.claude.com/docs/en/…
We're donating Agent Skills to the Agentic AI Foundation (@AgenticAIFdn), the same foundation we donated MCP to.
Since December 2025, 70+ agent platforms have integrated the standard, including ChatGPT, Cursor, GitHub Copilot, and VS Code.
Here's what that means for you:
API version 2026-10-21 is now available.
The Claude API has evolved a lot, but this is our first official version release since 2023. We plan to release versions more often so you can handle breaking changes before a new model requires them.
2023-06-01 is not deprecated.
We launched OSS Scanner, which gives critical open source projects free, periodic vulnerability scans from our strongest models.
Each finding includes a proof-of-concept, and a patch where possible.
red.anthropic.com/oss-scanne…
The first scans have already reported 77 critical and 803 high model-rated findings to maintainers, and we're still scanning more projects.
@thepunit shared an update, including a curl fix and what we've learned in the first week
xitter.twitterapi.xyz/thepunit/status/211226…
A fix I'm excited about: curl, used by countless apps/devices to move data over the internet, just patched CVE-2026-92392. It's a high-severity memory-safety bug (a use-after-free) found with an early version of OSS Scanner.
@bagder called it one of curl's worst vulns in a long time, even if a crash is the likeliest outcome.
Thanks to Daniel and the curl team for fixing and writing it up so openly.
daniel.haxx.se/blog/2026/10/…
We keep improving performance across Claude, and you may have noticed it starts responding sooner!
Claude Code now gzips the conversation it sends on every turn, so it reaches the model faster. Cloud sessions also start up as soon as you start typing.
Claude writes about 90% of Claude Code's code.
From June to September, merged PRs more than doubled while the share reverted fell by more than 40%.
We wrote about how we changed code review to get there, and how to adopt it:
claude.dev/blog/solving-code…
Code Review is now generally available for Claude Team and Enterprise plans.
Reviews are now faster, catch more of the bugs that matter, and admins can pick from Quick, Standard, or Deep review levels for each repo.
