Releasesby GlyphCache diagnostics is out of beta on the Claude API and no longer requires the cache-diagnosis-2026-04-07 beta
Cache diagnostics is out of beta on the Claude API and no longer requires the cache-diagnosis-2026-04-07 beta header. Include the diagnostics object on a Messages request to opt in; requests that still send the header work as before.
Also shipped Sep 23, 2026Anthropic in September 2026 →
New features and improvements in Copilot for JetBrains
GitHub Copilot for JetBrains 1.18.0 brings AI-assisted tool approvals, more control over agent conversations, and shared skills and instructions for your organization. You can also review plans with the Codex agent and manage MCP tools with persistent controls.
Scalar and Batch Unity Catalog Python UDFs are now generally available
Scalar and Batch Unity Catalog Python UDFs are now generally available on all supported compute types. This release adds named handlers for row-at-a-time scalar UDFs, removes the five-UDF-call-per-query limit, and aligns scalar TIMESTAMP inputs with PySpark behavior.
Build governed data and AI apps without code (Beta)
You can now build governed data and AI apps without code. Genie App Builder authors apps in natural language, App Spaces enforce governance, and Serverless Micro Apps scale to zero when idle. See Governed agentic app building .
Non-deterministic aggregate functions are supported with dynamic table incremental refresh (General availability)
Non-deterministic aggregate functions such as approx count distinct , approx percentile , and approx top k are now supported with dynamic table incremental refresh in INCREMENTAL, AUTO, and ADAPTIVE refresh modes. For incremental refresh, these functions are supported only in the SELECT clause. any value remains unsupported.
More ways to request and configure Copilot code reviews
GitHub Copilot code review now offers additional personal configurations to an expanded set of Copilot plans and an enterprise-level default setting. These improvements are now generally available: A dedicated personal settings page for automatic review and your default review effort An enterprise-wide default review effort setting for organization-owned...
Node 20 is no longer available in GitHub Actions
This is the final notification that Node 20 is no longer available on GitHub Actions runners. Runners now use Node 24 for JavaScript actions. The temporary ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION opt-out is no longer available. If you maintain a JavaScript action, update its runs.using value to node24 and publish a new release as soon as possible.
More from Claude PlatformEvery Claude Platform release →
We're expanding which refusals are billed to include refusals that arrive before any output when
We're expanding which refusals are billed to include refusals that arrive before any output when stop_details.category is "bio", "frontier_llm", or "reasoning_extraction", the categories where we measure low volumes of false positives. Mid-stream refusals were already billed.
We're resuming billing for refusals that arrive before any output when stop_details.category is "bio"
We're resuming billing for refusals that arrive before any output when stop_details.category is "bio", "frontier_llm", or "reasoning_extraction", the categories where we measure low volumes of false positives. Mid-stream refusals were already billed. Refusals billed under this change are charged like any other request, at the rates of the model that ran it.
The Compliance API local session endpoints are out of beta for Claude for Microsoft 365 sessions in Excel
The Compliance API local session endpoints are out of beta for Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook (product_surface values beginning with office_agents). See Sessions on users' machines.
The Compliance API Activity Feed no longer returns file names, project document names, or artifact titles
The Compliance API Activity Feed no longer returns file names, project document names, or artifact titles. The filename and title fields on file, project document, and artifact activities are now always empty or omitted, including on activities recorded before this change.
Claude Opus 5.5 launches with a 1M token context window and 128k output
Anthropic released Claude Opus 5.5 for long-running agentic coding and knowledge work, with a default 1M token context, 128k max output and always-on adaptive thinking. It costs $4 / $20 per MTok, below Claude Opus 5, and is on the Claude API, Bedrock, Google Cloud and Microsoft Foundry.
Claude Opus 5.5 breaking changes: thinking can't be disabled, forced tool_choice removed
On Claude Opus 5.5, disabling or manually enabling thinking returns a 400; control depth with the effort parameter instead. tool_choice any and tool also return 400, so use auto with strict tool use, and computer use requires the computer_toolset_20260801 toolset.
Fast mode research preview available for Claude Opus 5.5 on the Claude API
Fast mode, in research preview, can now be used with Claude Opus 5.5 on the Claude API.
Claude API beta lets tools be defined inside mid-conversation system messages
With the inline-tools-2026-09-15 beta header, a tool_addition block can carry a full tool definition, so agents can add tools, change schemas or upgrade server tools mid-conversation without invalidating the prompt cache. The same header covers adding and removing tools by reference.