- CHANGELOG.md (+6 / -0)
• ## 2.0.24
• - Fixed a bug where project-level skills were not loading when --setting-sources 'project' was specified
• - Claude Code Web: Support for Web -> CLI teleport
• - Sandbox: Releasing a sandbox mode for the BashTool on Linux & Mac
- CHANGELOG.md (+4 / -0)
• ## 2.0.20
• - Added support for Claude Skills
- api.md (+8 / -0)
• #### October 16, 2025
• * We've launched [Agent Skills](https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills) (`skills-2025-10-02` beta), a new way to extend Claude's capabilities. Skills are organized folders of instructions, scripts, and resources that Claude loads dynamically to perform specialized tasks. The initial release includes:
- claude-apps.md (+4 / -0)
• #### October 16, 2025
• * **Agent Skills** are now available on [claude.ai](https://www.claude.ai). Skills extend Claude's capabilities with specialized expertise for common tasks. Use pre-built Anthropic-managed Skills in conversations with extended thinking enabled to create and edit documents.
- CHANGELOG.md (+14 / -0)
• ## 2.0.19
• - Auto-background long-running bash commands instead of killing them. Customize with BASH_DEFAULT_TIMEOUT_MS
• - Fixed a bug where Haiku was unnecessarily called in print mode
• ## 2.0.17
• - Added Haiku 4.5 to model selector!
• - Haiku 4.5 automatically uses Sonnet in plan mode, and Haiku for execution (i.e. SonnetPlan by default)
- api.md (+5 / -1)
• #### October 15, 2025
• * We've launched [Claude Haiku 4.5](https://www.anthropic.com/news/claude-haiku-4-5), our fastest and most intelligent Haiku model with near-frontier performance. Ideal for real-time applications, high-volume processing, and cost-sensitive deployments requiring strong reasoning. Learn more in our [Models & Pricing documentation](/en/docs/about-claude/models).
• * We've launched [Claude Sonnet 4.5](https://www.anthropic.com/news/claude-sonnet-4-5), our best model for complex agents and coding, with the highest intelligence across most tasks. Learn more in [What's new in Claude 4.5](/en/docs/about-claude/models/whats-new-claude-4-5).
- claude-apps.md (+4 / -0)
• #### October 15, 2025
• * We've added [Claude Haiku 4.5](https://www.anthropic.com/news/claude-haiku-4-5) to [claude.ai](https://www.claude.ai). Claude Haiku 4.5 is our fastest and most intelligent Haiku model with near-frontier performance, ideal for real-time applications, high-volume processing, and cost-sensitive deployments requiring strong reasoning.
- system-prompts.md (+89 / -0)
• ## Claude Haiku 4.5
- CHANGELOG.md (+5 / -0)
• ## 2.0.15
• - Fixed bug with resuming where previously created files needed to be read again before writing
• - Fixed bug with `-p` mode where @-mentioned files needed to be read again before writing
- system-prompts.md (+2 / -2)
• The assistant is Claude, created by Anthropic. The current date is \{\{currentDateTime}}. Claude's knowledge base was last updated in July 2024 and it answers user questions about events before July 2024 and after July 2024 the same way a highly informed individual from July 2024 would if they were talking to someone from \{\{currentDateTime}}. If asked about events or news that may have happened after its cutoff date (for example current events like elections), Claude does not answer the user with certainty. Claude never claims or implies these events are unverified or rumors or that they only allegedly happened or that they are inaccurate, since Claude can't know either way and lets the human know this.
• The current date is \{\{currentDateTime}}.
- CHANGELOG.md (+18 / -0)
• ## 2.0.13
• - Fixed `/plugin` not working on native build
• ## 2.0.12
• - **Plugin System Released**: Extend Claude Code with custom commands, agents, hooks, and MCP servers from marketplaces
• - `/plugin install`, `/plugin enable/disable`, `/plugin marketplace` commands for plugin management
• - Repository-level plugin configuration via `extraKnownMarketplaces` for team collaboration
- CHANGELOG.md (+4 / -0)
• ## 2.0.9
• - Fix regression where bash backgrounding stopped working
- system-prompts.md (+5 / -5)
• Claude is accessible via an API. The person can access Claude Opus 4.1 with the model string ‘claude-opus-4-1-20250805’. Claude is accessible via Claude Code, a command line tool for agentic coding. Claude Code lets developers delegate coding tasks to Claude directly from their terminal. If the person asks Claude about Claude Code, Claude should point them to check the documentation at [https://docs.anthropic.com/en/docs/claude-code](https://docs.anthropic.com/en/docs/claude-code).
• Claude is accessible via an API. The person can access Claude Opus 4 with the model string ‘claude-opus-4-20250514’. Claude is accessible via Claude Code, a command line tool for agentic coding. Claude Code lets developers delegate coding tasks to Claude directly from their terminal. If the person asks Claude about Claude Code, Claude should point them to check the documentation at [https://docs.anthropic.com/en/docs/claude-code](https://docs.anthropic.com/en/docs/claude-code).
• Claude is accessible via an API. The person can access Claude Opus 4 with the model string ‘claude-opus-4-20250514’. Claude is accessible via Claude Code, a command line tool for agentic coding. Claude Code lets developers delegate coding tasks to Claude directly from their terminal. If the person asks Claude about Claude Code, Claude should point them to check the documentation at [https://docs.anthropic.com/en/docs/claude-code](https://docs.anthropic.com/en/docs/claude-code).
- CHANGELOG.md (+13 / -3)
• ## 2.0.8
• - Update Bedrock default Sonnet model to `global.anthropic.claude-sonnet-4-5-20250929-v1:0`
• - IDE: Add drag-and-drop support for files and folders in chat
• - /context: Fix counting for thinking blocks
• - Improve message rendering for users with light themes on dark terminals
• - Remove deprecated .claude.json allowedTools, ignorePatterns, env, and todoFeatureEnabled config options (instead, configure these in your settings.json)
- CHANGELOG.md (+5 / -0)
• ## 2.0.1
• - Skip Sonnet 4.5 default model setting change for Bedrock and Vertex
• - Various bug fixes and presentation improvements
- api.md (+1 / -0)
• * We've introduced [global endpoint pricing](/en/docs/about-claude/pricing#third-party-platform-pricing) for AWS Bedrock and Google Vertex AI. The Claude API (1P) pricing is unaffected.
- CHANGELOG.md (+13 / -0)
• ## 2.0.0
• - New native VS Code extension
• - Fresh coat of paint throughout the whole app
• - /rewind a conversation to undo code changes
• - /usage command to see plan limits
• - Tab to toggle thinking (sticky across sessions)
- api.md (+8 / -1)
• #### September 29, 2025
• * We've launched [Claude Sonnet 4.5](https://www.anthropic.com/news/claude-sonnet-4-5), our best model for complex agents and coding, with the highest intelligence across most tasks. Learn more in [What's new in Claude Sonnet 4.5](/en/docs/about-claude/models/whats-new-sonnet-4-5).
• * We've introduced a new stop reason `model_context_window_exceeded` that allows you to request the maximum possible tokens without calculating input size. Learn more in our [handling stop reasons documentation](/en/api/handling-stop-reasons).
• * We've launched the memory tool in beta, enabling Claude to store and consult information across conversations. Learn more in our [memory tool documentation](/en/docs/agents-and-tools/tool-use/memory-tool).
• * We've launched context editing in beta, providing strategies to automatically manage conversation context. The initial release supports clearing older tool results and calls when approaching token limits. Learn more in our [context editing documentation](/en/docs/build-with-claude/context-editing).
• * We announced the deprecation of the Claude Sonnet 3.5 models (`claude-3-5-sonnet-20240620` and `claude-3-5-sonnet-20241022`). These models will be retired on October 22, 2025. We recommend migrating to Claude Sonnet 4.5 (`claude-sonnet-4-5-20250929`) for improved performance and capabilities. Read more in the [Model deprecations documentation](/en/docs/about-claude/model-deprecations).
- claude-apps.md (+4 / -0)
• #### September 29, 2025
• * We've added [Claude Sonnet 4.5](http://www.anthropic.com/news/claude-sonnet-4-5) to [claude.ai](https://www.claude.ai). Claude Sonnet 4.5 is our best model for complex agents and coding, with the highest intelligence across most tasks.
- system-prompts.md (+91 / -0)
• ## Claude Sonnet 4.5
- CHANGELOG.md (+8 / -0)
• ## 1.0.124
• - Set `CLAUDE_BASH_NO_LOGIN` environment variable to 1 or true to to skip login shell for BashTool
• - Fix Bedrock and Vertex environment variables evaluating all strings as truthy
• - No longer inform Claude of the list of allowed tools when permission is denied
• - Fixed security vulnerability in Bash tool permission checks
• - Improved VSCode extension performance for large files
- CHANGELOG.md (+21 / -2)
• ## 1.0.120
• - Fix input lag during typing, especially noticeable with large prompts
• ## 1.0.119
• - Fix Windows issue where process visually freezes on entering interactive mode
• - Support dynamic headers for MCP servers via headersHelper configuration
• - Fix thinking mode not working in headless sessions
- api.md (+1 / -1)
• * We've launched tool helpers in beta for the Python and TypeScript SDKs, simplifying tool creation and execution with type-safe input validation and a tool runner for automated tool handling in conversations. For details, see the documentation for [the Python SDK](https://github.com/anthropics/anthropic-sdk-python/blob/main/tools.md) and [the TypeScript SDK](https://github.com/anthropics/anthropic-sdk-typescript/blob/main/helpers.md#tool-helpers).
- api.md (+4 / -0)
• #### September 17, 2025
• * We've launched tool helpers in beta for the Python and TypeScript SDKs, simplifying tool creation and execution with automatic input validation and a tool runner for automated tool handling in conversations. For details, see the [`anthropic-sdk-python`](https://github.com/anthropics/anthropic-sdk-python/blob/main/helpers.md) and [`anthropic-sdk-typescript`](https://github.com/anthropics/anthropic-sdk-typescript/blob/main/helpers.md) repos. To learn more about tool use, see our [tool use documentation](/en/docs/agents-and-tools/tool-use/overview).
- CHANGELOG.md (+9 / -0)
• ## 1.0.115
• - Improve thinking mode display with enhanced visual effects
• - Type /t to temporarily disable thinking mode in your prompt
• - Improve path validation for glob and grep tools
• - Show condensed output for post-tool hooks to reduce visual clutter
• - Fix visual feedback when loading state completes
- api.md (+27 / -15)
• # Claude Developer Platform
• #### September 16, 2025
• * We've unified our developer offerings under the Claude brand. You should see updated naming and URLs across our platform and documentation, but **our developer interfaces will remain the same**. Here are some notable changes:
• * We've increased rate limits on the [1M token context window](/en/docs/build-with-claude/context-windows#1m-token-context-window) for Claude Sonnet 4 on the Claude API. For more information, see [Long context rate limits](/en/api/rate-limits#long-context-rate-limits).
• * We've launched beta support for a [1M token context window](/en/docs/build-with-claude/context-windows#1m-token-context-window) in Claude Sonnet 4 on the Claude API and Amazon Bedrock.
• * Search result content blocks are now generally available on the Claude API and Google Cloud's Vertex AI. This feature enables natural citations for RAG applications with proper source attribution. The beta header `search-results-2025-06-09` is no longer required. Learn more in our [search results documentation](/en/docs/build-with-claude/search-results).
- CHANGELOG.md (+8 / -0)
• ## 1.0.112
• - Transcript mode (Ctrl+R): Added the model used to generate each assistant message
• - Addressed issue where some Claude Max users were incorrectly recognized as Claude Pro users
• - Hooks: Added systemMessage support for SessionEnd hooks
• - Added `spinnerTipsEnabled` setting to disable spinner tips
• - IDE: Various improvements and bug fixes
- api.md (+1 / -1)
• * Some customers might encounter 429 (`rate_limit_error`) [errors](/en/api/errors) following a sharp increase in API usage due to acceleration limits on the API. Previously, 529 (`overloaded_error`) errors would occur in similar scenarios.
- CHANGELOG.md (+5 / -1)
• ## 1.0.111
• - Fixed Bash tool crashes caused by malformed shell syntax parsing
• ## 1.0.110
- api.md (+5 / -0)
• #### September 10, 2025
• * We've launched the web fetch tool in beta, allowing Claude to retrieve full content from specified web pages and PDF documents. Learn more in our [web fetch tool documentation](/en/docs/agents-and-tools/tool-use/web-fetch-tool).
• * We've launched the [Claude Code Analytics API](/en/api/claude-code-analytics-api), enabling organizations to programmatically access daily aggregated usage metrics for Claude Code, including productivity metrics, tool usage statistics, and cost data.
zebbern