Claude Code: No repository option for Anthropic-hosted cloud sessions

What changed

5 points

1. 1

   In cloud sessions, a No repository option is added, so a cloud session on an Anthropic-hosted environment can now start without picking a repository.

   Official wording · c8

   [Cloud sessions] Added a No repository option: a cloud session on an Anthropic-hosted environment can now start without picking a repository

2. 2

   The Claude apps gateway gains assume_role on mantle upstreams, for a role in another AWS account and for per-developer AWS cost attribution.

   Official wording · c1

   Added `assume_role` on `mantle` upstreams of the Claude apps gateway, for a role in another AWS account and for per-developer AWS cost attribution

3. 3

   A mod's $.model.fork gains an effort option, so a quick side job can run at low whatever effort the session uses, and the result reports the effort sent.

   Official wording · c2

   Added an `effort` option to a mod's `$.model.fork`, so a quick side job can run at `low` whatever effort the session uses; the result reports the effort sent

4. 4

   The date a stored claude.ai sign-in ends is added to claude auth status (loginExpiresAt) and to claude -p JSON results (credential_expires_at).

   Official wording · c3

   Added the date a stored claude.ai sign-in ends to `claude auth status` (`loginExpiresAt`) and to `claude -p` JSON results (`credential_expires_at`)

5. 5

   A one-line stderr warning is added to claude -p text output, starting 10 days before a stored claude.ai sign-in ends.

   Official wording · c4

   Added a one-line stderr warning to `claude -p` text output, starting 10 days before a stored claude.ai sign-in ends

Change details

Fields in this table are taken verbatim from the official text.

Version timeline

Published updates for this tool on this site, newest official date first.

1. 2026-11-04CurrentNo repository option for Anthropic-hosted cloud sessions
2. 2026-11-03Claude apps gateway admin API adds a cost report
3. 2026-10-20Added sandbox.allowNestedUserNamespaces for sandboxed Linux commands
4. 2026-10-14Cache write token fields added to OpenTelemetry api_request event

About this tool

Claude Code

Claude Code is Anthropic's coding agent for reading codebase context, editing files, running commands and assisting development work.

CategoriesAI Coding

View Claude Code details

Related guides

• Claude Code context: preserve constraints before compactionUse /context, persistent instructions and handoff notes to manage a long task, and distinguish session recovery from file recovery.
• AI coding tools: choose by workflow, sign-in and costsChoose an AI coding tool by IDE or terminal workflow, sign-in method and billing limits. Compare six listed tools using official sources; no performance tests.
• Claude Code GitHub Actions: triggers and authenticationCheck triggers, checkout, authentication and result location when integrating CI. An action reference is not an executed workflow; not tested.
• Claude Code hooks: checks before a tool callUse PreToolUse, matchers and exit codes to build an explainable command check. Source-based; not tested.
• Claude Code permissions: combining allow, ask and denyScope commands and file access with allow, ask and deny, then check precedence. Source-based; not tested.
• Claude Code MCP: project config and connection checksReview .mcp.json, HTTP transport and actual connection status separately. Configuration alone is not a working connection; not tested.
• Claude Code subagents for read-only code inspectionDefine an inspection task with separate context, an explicit tool list and an output contract. Source-based; not tested.
• AGENTS.md vs CLAUDE.md: which one Claude Code reads and how to share one fileBy default Claude Code reads AGENTS.md only when no CLAUDE.md exists; an @AGENTS.md import in CLAUDE.md shares one file. Not tested; check the official docs.
• Claude Code code-review plugin (a plugin command, not a Skill)Official Anthropic code-review plugin: /code-review runs multi-agent PR review, needs the gh CLI, not tested
• frontend-design: avoiding templated defaults in UI designAnthropic's frontend-design skill: plan the visual direction, check it against the brief, avoid templated defaults. Not tested; follow the official text.
• Splitting agent instructions by directory in a monorepoPer-directory AGENTS.md and CLAUDE.md in a monorepo: an example tree, then load scope, nesting and conflict rules per tool. Per official docs, not tested.
• skill-creator: Anthropic's skill for writing, editing and evaluating skillsAnthropic's skill-creator skill: draft a skill, run evals, revise it and tune its trigger description. Not tested here; follow the official text and docs.
• webapp-testing Skill: drive local web apps with PlaywrightOfficial Anthropic webapp-testing Skill: Python Playwright scripts for local web apps, not tested