Skip to content
Back

AI posts

AI release notes

Anthropic's official release notes. Claude apps: the website, desktop and phone apps. Claude Code: Claude's coding assistant. Claude API: what developers use to build Claude into their own products.

Compiled by the Toolstash team · Updated

  1. Claude Code

    Claude Code 2.1.161

    1 new14 fixes7 other

    [VSCode] Added a tip suggesting disabling terminal GPU acceleration (or running /terminal-setup) to fix garbled glyphs.

  2. Claude Code

    Claude Code 2.1.160

    1 new18 fixes8 other

    Added a prompt before writing to shell startup files (.zshenv, .zlogin, .bash_login) and ~/.config/git/, which could otherwise lead to unintended command execution.

  3. Claude API

    The advisor tool now supports a max_tokens parameter to cap the advisor model’s output for each call,…

    Set tools[].max_tokens on the advisor tool definition; see Capping advisor output. On the Claude API, you are no longer billed for a request when it returns stop_reason: "refusal" without Claude having generated any output.

  4. Claude apps

    Enterprise plans can manage admin permissions with custom roles

    We extended the existing custom roles framework by adding admin permissions. Admin permissions give members access to specific administrative areas, like billing or privacy, without the need to make them Owners.

  5. Claude Code

    Claude Code 2.1.159

    1 other

    Internal infrastructure improvements (no user-facing changes).

  6. Claude Code

    Claude Code 2.1.158

    1 other

    Auto mode is now available on Bedrock, Vertex, and Foundry for Opus 4.7 and Opus 4.8. Opt in by setting CLAUDE_CODE_ENABLE_AUTO_MODE=1.

  7. Claude Code

    Claude Code 2.1.157

    3 new18 fixes12 other

    Added claude plugin init to scaffold a new plugin in .claude/skills. Added autocomplete for /plugin arguments: subcommands, installed plugin names, and plugins from known marketplaces.

  8. Claude Code

    Claude Code 2.1.156

    1 fix

    Fixed an issue when using Opus 4.8 where thinking blocks were modified, leading to API errors.

  9. Claude API

    Claude Managed Agents webhooks, multiagent orchestration, and self-hosted sandboxes are now available on…

  10. Claude Code

    Claude Code 2.1.154

    1 new22 fixes21 other

    Added Claude Opus 4.8 support and 4.7 → 4.8 migration guidance to the /claude-api skill.

  11. Claude Code

    Claude Code 2.1.153

    1 new24 fixes11 other

    Added skipLfs option to github/git plugin marketplace sources to skip Git LFS downloads during clone and update.

  12. Claude API

    We’ve launched mid-conversation system messages

    On Claude Opus 4.8, you can send role: "system" messages after a user turn (subject to placement rules) in the messages array, preserving prompt cache hits when instructions change during a long-running session. No beta header is required. The stop_details field on refusal responses is now publicly documented; it returns a category (cyber, bio, or null) and a human-readable explanation, so your application can route different classes of refusal to the right next step. On Claude Opus 4.8, the effort parameter defaults to high across all surfaces, including Claude Code and the Messages API. On Claude Opus 4.8, the minimum cacheable prompt length for prompt caching is 1,024 tokens, lower than on Claude Opus 4.7. With adaptive thinking enabled, Claude Opus 4.8 triggers reasoning only when a turn needs it, reducing wasted thinking tokens compared to Claude Opus 4.7 at the same effort level. Claude Opus 4.8 supports high-resolution image input (up to 2576 pixels on the long edge), same as Claude Opus 4.7. Task budgets now support Claude Opus 4.8. The advisor tool now supports Claude Opus 4.8. Computer use now supports Claude Opus 4.8. Fast mode for Claude Opus 4.8 is available as a research preview on the Claude API only. Setting the sampling parameters temperature, top_p, or top_k to a non-default value returns a 400 error on Claude Opus 4.8, same as on Claude Opus 4.7. In Claude Code, we’ve expanded Auto mode to more users for long-running tasks. In Claude Code, Max plan users now default to fast mode on Claude Opus 4.8. In Claude Code, Workflows are available as a research preview, letting you define and run multistep agentic plans. We’ve deprecated fast mode for Claude Opus 4.6, with removal approximately 30 days after launch. For updates to claude.ai, Cowork, Claude for Microsoft 365, and other Claude apps in this release, see the release notes for Claude Apps.

  13. Claude appsAnnouncement

    Claude Opus 4.8 launch, plus 1 more change

    We’ve upgraded Claude Opus to a new version. Claude Opus 4.8 shows improvements over Opus 4.7 in coding, agentic skills, reasoning, and practical knowledge work tasks. We added connector permissions to extend the existing custom roles framework and allow administrators to control which connectors, and which individual tools on those connectors, are available to each custom role.

  14. New modelAnnouncement

    New model: Claude Opus 4.8

    We’ve launched Claude Opus 4.8 (claude-opus-4-8), our most capable model. Claude Opus 4.8 supports a 1M token context window by default on the Claude API, Amazon Bedrock, Google Cloud, and Microsoft Foundry, 128k max output tokens, and the same set of tools and platform features as Claude Opus 4.7.

  15. Claude Code

    Claude Code 2.1.152

    4 new16 fixes13 other

    Added /reload-skills command to re-scan skill directories without restarting the session. Added a MessageDisplay hook event that lets hooks transform or hide assistant message text as it is displayed.

  16. Claude API

    The Messages API response now includes usage.output_tokens_details.thinking_tokens, reporting how many of…

    When streaming, the breakdown appears only on the final message_delta event. No beta header is required.

  17. Claude Code

    Claude Code 2.1.150

    1 other

    Internal infrastructure improvements (no user-facing changes).

  18. Claude Code

    Claude Code 2.1.149

    1 new21 fixes4 other

    Enterprise: added the allowAllClaudeAiMcps managed setting to load claude.ai cloud MCP connectors alongside managed-mcp.json.

  19. Claude Code

    Claude Code 2.1.148

    1 fix

    Fixed the Bash tool returning exit code 127 on every command for some users (a regression introduced in 2.1.147).

  20. Claude Code

    Claude Code 2.1.147

    26 fixes7 other

    Pinned background sessions (Ctrl+T in claude agents) now stay alive when idle, are restarted in place to apply Claude Code updates, and are shed under memory pressure only after non-pinned sessions. Renamed /simplify to /code-review. It now reports correctness bugs at a chosen effort level (e.g., /code-review high); pass --comment to post findings as inline GitHub PR comments. The old cleanup-and-fix behavior has been removed.

  21. Claude Code

    Claude Code 2.1.146

    12 fixes4 other

    Renamed /simplify to /code-review with an optional effort level (e.g. /code-review high). Auto mode no longer suppresses AskUserQuestion when the user or a skill explicitly relies on it.

  22. Claude apps

    Claude now works with more security and compliance tools

    We introduced Claude Compliance API integrations with notable security and compliance tools. Now IT and security teams can govern Claude across our platform and suite of products, the same way they govern other applications in their stack. Learn how to get started with Claude Compliance API integrations.

  23. Claude Code

    Claude Code 2.1.145

    2 new12 fixes6 other

    Added claude agents --json to list live Claude sessions as JSON for scripting (tmux-resurrect, status bars, session pickers). Added agent_id and parent_agent_id attributes to claude_code.tool OTEL spans, and fixed trace parenting so background subagent spans nest under the dispatching Agent tool span.

  24. Claude Code

    Claude Code 2.1.144

    2 new30 fixes18 other

    Added /resume support for background sessions — sessions started via claude --bg or agent view now appear alongside interactive ones, marked with bg. Added elapsed duration to background subagent completion notifications (e.g. "Agent completed · 3h 2m 5s").

  25. Claude API

    MCP tunnels is now available as a research preview, so you can connect to MCP servers in your private network

    Self-hosted sandboxes are now available for Claude Managed Agents, as an alternative to running tool execution in Anthropic’s infrastructure. With Claude Managed Agents, you can now update the agent’s MCP server and tool configurations associated with an active session. With Claude Managed Agents, large outputs from agent_toolset and MCP tools exceeding 100K characters (about 25K tokens) are now automatically spilled to a file in the sandbox.

  26. Claude API

    The web search tool now returns richer SEC filing data, making it easier to ground financial research…

  27. Claude Code

    Claude Code 2.1.143

    3 new16 fixes14 other

    Added plugin dependency enforcement: claude plugin disable now refuses when another enabled plugin depends on the target (with a copy-pasteable disable-chain hint), and claude plugin enable force-enables transitive dependencies. Added projected context cost (per-turn and per-invocation token estimates) to the /plugin marketplace browse pane.

  28. Claude Code

    Claude Code 2.1.142

    1 new16 fixes7 other

    Added new claude agents flags: --add-dir, --settings, --mcp-config, --plugin-dir, --permission-mode, --model, --effort, and --dangerously-skip-permissions to configure dispatched background sessions.

  29. Claude Code

    Claude Code 2.1.141

    4 new44 fixes13 other

    Added terminalSequence field to hook JSON output so hooks can emit desktop notifications, window titles, and bells without a controlling terminal. Added CLAUDE_CODE_PLUGIN_PREFER_HTTPS to clone GitHub plugin sources over HTTPS instead of SSH, for environments without a GitHub SSH key.

  30. Claude API

    We’ve launched cache diagnostics in beta

    Pass diagnostics.previous_message_id on a Messages request and the API reports a cache_miss_reason explaining where the prompt cache prefix diverged from the previous turn. Include the cache-diagnosis-2026-04-07 beta header in your requests.