Official updates for developers building with @ClaudeAI
Joined February 2026
- Tweets546
- Following2
- Followers79K
- Likes99
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.
Elicitations let plugins ask users for input mid-task, such as confirming a refund or filling in a missing detail.
Tasks and Elicitations are available today in the Claude Code CLI, rolling out to more Claude products soon.
Building plugins for Claude? Add Tasks and Elicitations to your MCP server today.
code.claude.com/docs/en/mcp#…
code.claude.com/docs/en/mcp#…
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:
Your skills keep working, and the licenses don't change. Anyone can use the standard or contribute to it without joining the AAIF.
Engineers from Anthropic, Earendil (Pi), Google, Microsoft, OpenAI, and OpenCode will govern it as a Technical Steering Committee.
The committee's first priority is a roadmap: versioned releases, a formal proposal process, and security guidance for skill authors and users.
Want to contribute? Start with the spec at agentskills.io and the discussion on GitHub.
Full blog: anthropic.com/news/donating-…
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.
What changes in this version:
- temperature, top_p, and top_k are removed from the Messages API
- documents in assistant turns and citations in user turns return a 400
- a few deprecated Admin and Enterprise Analytics API fields are replaced
New major versions of the Anthropic SDKs and the ant CLI are out today and default to 2026-10-21.
You can use the /claude-api skill in Claude Code to update, or walk through each change in the migration guide: platform.claude.com/docs/en/…
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
nitter.cf/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/…
If you maintain a critical open source project, you can find more details on the application here:
anthropic.com/research/launc…
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.
Eligible Claude Enterprise orgs can claim at least $10,000 in Code Review credits by Jan 15. Credits expire 30 days after you claim them.
Terms: support.claude.com/en/articl…
Admins turn it on in Claude Code settings and pick repos. From there, reviews run on every new PR, with no setup for developers.
claude.com/resources/article…
