Weekly Tooling Brief — 2026-10-25

You can now choose which service tiers projects can use in Platform settings. Organization settings can restrict service tiers for all projects.

- Fixed sandboxed commands and auto-accepted edits being able to modify the MCP config file passed with `--mcp-config`

- Added `sandbox.allowNestedUserNamespaces` so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets them get around the sandbox's file protections

We’ve launched Claude Models on Google Cloud (Anthropic managed), the Claude API operated by Anthropic and reached through your Google Cloud project. Google Cloud IAM controls access. Google Cloud Marketplace handles billing.

Organization admins can now turn off web fetch for their organization on the Capabilities page of the Claude Console. With web fetch off, a Messages API request that includes the web fetch tool fails with a 400 error. In a Claude Managed Agents session, web_fetch calls return an error result to the agent instead. With web fetch on, admins can also set allowed or blocked domains for web fetch on the same page.

- Fixed requests failing behind some gateways and compatible servers that reject the `effort-2025-11-24` beta value or mid-conversation system messages; Claude Code now retries without them

The Decisions API is now generally available with gpt-6-luna. Cache shared input across requests for prompt-cache discounts, include images in individual question instructions, and pass structured data directly with input_json. Each request now supports up to 400 questions, increased from 200 in public beta.

- Fixed `claude --worktree` removing the worktree and its branch without asking at exit when HEAD was detached or on another branch, which could lose commits

* add Vertex AI support for the Responses API ([#4139](https://github.com/openai/openai-python/issues/4139)) ([3e63d33](https://github.com/openai/openai-python/commit/3e63d33f6258f47285007aaee30df251d5127820))

* **api:** This minor release includes a breaking change to Decisions types. In Live response models, question `instructions` can now be a string or a list of structured text, image, or JSON parts; check `isinstance(question.instructions, str)` before using string operations and handle the structured form. Decisions request input types also include additional message roles and tool-history items, so update exhaustive type checks accordingly. Existing string instructions and `DecisionInputMessageParam` user-message inputs remain supported.

* **api:** add support for new API version 2026-10-21

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.

- Fixed HTTP MCP tool calls being sent twice when the connection closed mid-call; only read-only or idempotent tools are now retried

We’ve released new versions of the client SDKs and the ant CLI that send API version 2026-10-21 by default: Python SDK 2.0.0, TypeScript SDK 1.0.0, C# SDK 13.0.0, Go SDK 2.0.0, Java SDK 3.0.0, PHP SDK 1.0.0, Ruby SDK 2.0.0, and ant CLI 2.0.0. See Switch to 2026-10-21. The new SDK and CLI versions also have breaking changes that don’t depend on the API version, and they are licensed under Apache 2.0 instead of the MIT License. See SDK and CLI changes.

* **api:** make User Profiles generally available

* **api:** add Claude Tag endpoints for Claude Enterprise organizations

The Claude Tag API is available in beta for Claude Enterprise organizations with the experimental-claude-tag-2026-10-21 beta header. Its /v1/organizations/claude_tag/ endpoints read and change Claude Tag settings on Slack channels and Slack workspaces, show which settings apply in a channel and where each comes from, and attach Access bundles.

* **api:** add usage and cost reports by dimension, mark older reports legacy