Claude Code

This release introduces new security measures in auto mode, including blocking tampering with session transcripts and adding context checks before running destructive commands. Several critical bugs were fixed across agent management, CLI operations, and Windows stability. Additionally, the agent view has been significantly improved to show clearer status headlines and better PR linking.

This release focuses on stability within headless environments. A critical bug was fixed where hook events failed to stream during SessionStart, which previously caused remote workers to be incorrectly terminated.

This release focuses heavily on stabilizing and fixing numerous issues related to background agents, particularly around session state, path inheritance, and worktree isolation. New features include an expiration warning for user logins and improved visibility for manual permission mode. Performance is also improved with reduced binary size and better responsiveness during long response streaming.

This release introduces configuration options for controlling dynamic workflow size and enhances observability by adding OpenTelemetry attributes to workflow agents. Numerous bugs have been resolved, including fixes for crashes during history search, issues with remote control commands, and improved reliability for session resumption and file downloads over flaky connections.

This release addresses an issue related to how Claude Sonnet 5 sessions handle system roles during conversations. Specifically, harness reminders will no longer incorrectly utilize the mid-conversation system role.

This release focuses heavily on stabilizing background agent operations, fixing numerous issues related to session stalling, daemon handovers, and roster corruption. Additionally, it introduces improved accessibility support for screen readers and refines default permission handling across the tool suite.

This release significantly improves reliability for streaming responses and subagent operations, ensuring partial work is preserved during errors and API failures are correctly reported. Several critical bugs related to background agent stability on Linux and macOS have been resolved. Additionally, transient server rate limits are now automatically retried for subscribers, enhancing workflow continuity.

This release makes Claude in Chrome generally available and introduces a new `/dataviz` skill for generating charts and dashboards. Key fixes address network stability, agent reliability, and UI issues across desktop and web clients. Additionally, background agents now automatically complete code work by committing and opening draft PRs.

This release introduces Claude Sonnet 5 as the new default model, featuring a native 1M-token context window. Users can take advantage of promotional pricing for this new model through August 31st.

This release introduces organization-level default models and improves session management with readable default names and clickable file attachments in chat. Significant stability improvements were made for background jobs and agents, ensuring they survive restarts and display status correctly. Numerous fixes address issues across PowerShell compatibility, MCP OAuth, and various agent panel behaviors.

This release introduces a new environment variable to control mouse interactions in fullscreen mode and significantly improves the reliability of voice dictation across different languages and operating systems. Several critical bugs affecting background job persistence, plugin management, and agent startup stability have also been resolved.

This release introduces several new capabilities, including live file path autocomplete in bash mode and enhanced configuration for auto-mode classification. Several bugs related to background agent persistence and UI state after login have been resolved, alongside improvements to MCP authentication and plugin renaming.

This release introduces the ability to resume conversations using the new /rewind command. Numerous bugs have been fixed across agent management, slash command handling, and UI rendering, especially in constrained terminal environments. Performance has also been improved with significant CPU usage reduction during streaming and better network error handling for MCP connections.

This release focuses primarily on stability and reliability improvements. Users can expect a more robust experience due to the resolution of several underlying issues.

This release introduces enhanced security with a new setting to block sandboxed credential access and organizational controls for model selection. Several critical bugs related to structured output, remote tool calls, and session resumption have been fixed, improving overall stability and reliability across various workflows.

This release introduces new CLI commands for MCP server authentication (`login/logout`) and adds status filtering to the `/workflows` view. Numerous bugs have been resolved, particularly around session streaming stability after sleep, background agent interaction, and improved permission handling for subagents. Additionally, memory usage is improved via proactive index compaction.

This release focuses on improving the user experience during API latency by updating the stream-stall hint message for better clarity. Additionally, the trigger threshold for this hint has been increased from 10 to 20 seconds.

This release significantly enhances safety in auto mode by blocking potentially destructive commands unless explicitly intended by the user. It also introduces a warning for deprecated models and improves the usability of the `/config` command. Several bugs related to TUI corruption, subagent communication, and background task handling have also been resolved.

This release introduces the ability to set configuration keys directly via prompt commands (e.g., /config thinking=false) and adds an opt-in setting for Apple Events on macOS. Numerous stability fixes address issues with prompt caching, file saving on network drives, startup delays, and various subagent panel behaviors.

This release focuses heavily on stability and usability, fixing numerous bugs related to connection handling, UI focus, and session state management. Key fixes include preserving partial responses during mid-stream connection drops and resolving a critical scrolling regression in WSL2 environments.

This release introduces granular permission control using tool parameters and improves skill loading in nested project structures. Numerous critical bugs have been fixed, including issues with authentication tokens, subagent transcript viewing, and background session state management. Usability is enhanced through clearer error messages, improved auto-mode safety checks, and refined workflow prompt detection.

This release introduces configurable link badges in the footer and ensures session titles are generated in the conversation's language. Numerous critical bugs were fixed across model enforcement, remote control stability, background session management, and Linux/Windows compatibility. Credential caching for Bedrock has also been significantly improved to respect expiration times.

This release introduces the `enforceAvailableModels` managed setting, which tightens security by ensuring the Default model respects the configured `availableModels` allowlist. If the default model is disallowed, it now gracefully falls back to the first available model.

This release introduces a new setting to control mouse-wheel scroll acceleration in fullscreen mode and enhances usage transparency by adding detailed attribution breakdowns to the VSCode Account & usage dialog. Several critical bugs were fixed, including issues with model selection display, background session environment inheritance, and authentication failures for idle workers.

This release focuses on stability and compatibility for Fable 5 users by correctly handling model name suffixes. Additionally, a misleading startup warning related to sandbox dependencies on Windows has been resolved.

This release introduces significant hierarchical agent capabilities, allowing sub-agents to spawn nested sub-agents up to five levels deep. Numerous bug fixes address stability issues related to 1M context sessions, model selection across various interfaces, and background agent operations. Performance has also been improved, particularly in long conversations and reducing idle CPU consumption.

This release introduces Claude Fable 5, a powerful new Mythos-class model, accessible by updating to version 2.1.170. A critical bug affecting session saving and resumption when launched from integrated terminals or specific shell environments has also been resolved.

This release introduces new configuration options for troubleshooting and managing bundled skills, including a new --safe-mode flag and a setting to disable built-in commands. Several critical bugs were fixed, particularly around MCP policy enforcement, UI responsiveness on macOS and Windows, and agent session management. Performance has also been improved with reduced CPU usage during streaming and better handling of long input lines.

This release focuses primarily on stability and reliability improvements. Users should experience fewer unexpected issues and a more robust coding environment.

This release focuses primarily on stability and reliability improvements. Users should experience fewer unexpected issues and a more robust coding environment.

This release introduces robust fallback model support, allowing sessions to automatically retry on secondary models when the primary API endpoint is overloaded. Security has been enhanced through hardened cross-session messaging, and several critical bugs affecting terminal input, remote sessions, and managed settings have been resolved. Additionally, glob pattern support has been added to tool deny rules for more flexible configuration.

This release focuses primarily on stability and reliability improvements. Users should experience fewer unexpected issues and a more robust coding environment.

This release introduces new managed settings for version enforcement and adds the `/plugin list` command for better plugin management. Several critical bugs were fixed, including hangs in background processes and permission rule application issues. Additionally, background agent sessions now update seamlessly without blocking the user upon restart.

This release focuses heavily on stability and user experience within the agents view and startup process. Key changes include fixing numerous bugs related to permission handling, agent status display, and session management reliability. Users will notice clearer startup messages, improved handling of failed turns, and better behavior when interacting with slash commands.

This release introduces better metric visibility by including custom dimensions on datapoints and improves parallel tool execution reliability by ensuring failures don't halt other concurrent calls. Numerous bugs were fixed, including issues with motion reduction settings, policy regressions affecting third-party providers, and various session/output corruption problems across different operating systems and environments.

This release introduces new safety prompts before writing to sensitive startup and configuration files, enhancing security during code generation. Numerous bugs related to background session management, Windows clipboard interaction, and agent view responsiveness have been fixed. Performance has also been improved for opening inactive agent sessions and for the auto mode classifier.

This release focused entirely on internal infrastructure improvements and contains no user-facing changes or new features.

This release introduces powerful new capabilities for code review, allowing fixes to be applied directly to the working tree, and enhances skill management with the ability to restrict tools and reload skills dynamically. Several quality-of-life improvements were made, including better handling of model fallbacks, clearer thinking indicators, and significant fixes to terminal rendering and plugin interaction stability.

This release focused entirely on internal infrastructure improvements and contains no user-facing changes or new features.

This release introduces detailed usage breakdowns via the /usage command and enables GFM task list rendering in Markdown output. Several critical security and stability fixes address issues related to PowerShell permissions, sandbox write access in git worktrees, and crashes involving large directory trees or specific tool calls.

This release focuses on resolving a critical regression affecting the Bash tool. Specifically, it fixes an issue where the Bash tool was incorrectly returning exit code 127 for all commands for certain users.

This release introduces the new Workflow tool for deterministic multi-agent orchestration, which is enabled via an environment variable. It also renames and enhances the code review command to /code-review, allowing for effort-level specific feedback and direct PR commenting. Numerous stability fixes address issues across enterprise login, command parsing, PowerShell execution on Windows, and background session management.

This release introduces a renamed and enhanced /code-review command, now supporting effort levels. Several critical bugs have been resolved across Windows, GNOME Terminal, and background session handling. Additionally, auto-updater reliability has been improved, and auto mode behavior regarding user questions has been refined.

This release introduces significant usability enhancements, including JSON output for scripting agent sessions and improved interaction in fullscreen mode. Several critical bugs were resolved, addressing issues with permission bypasses, command validation errors, and UI freezing after terminal resizing. Additionally, the Read tool is now more resilient to large files by returning partial content instead of erroring.

This release significantly enhances background session management, introducing support for resuming sessions via /resume and displaying elapsed durations on completion. Numerous fixes address stability, particularly around terminal rendering, file handling errors, and background session crashes on macOS and Windows. Users will also notice improved feedback regarding plugin installation and clearer error messages for configuration issues.

This release introduces significant enhancements to plugin management, including dependency enforcement and cost visibility in the plugin marketplace. Several critical bugs related to session state preservation, Windows terminal input, and background job reliability have been resolved. Users will also benefit from new configuration options for background sessions via the `claude agents` command and a new setting to bypass worktree isolation.

This release introduces significant configuration flexibility for background sessions via new `claude agents` flags and improves plugin functionality by surfacing skills defined via `SKILL.md`. Numerous critical bugs affecting background session stability, macOS sleep/wake handling, Windows networking, and tool timeouts have been resolved, alongside several plugin and UI refinements.

This release introduces significant enhancements for advanced workflows, including new hook capabilities for desktop notifications and better session scoping via `claude agents --cwd`. Numerous bug fixes address stability across various environments, particularly around plugin configuration, background agent management, and permission handling. Users will also benefit from improved feedback mechanisms, such as an amber spinner for long thinking periods and better navigation in the plugin menu.

This release focuses heavily on stability and reliability, fixing numerous issues related to background service startup, configuration reloading, and tool call validation. Key improvements include better handling of agent type matching and clearer error messaging for hanging commands.

This release introduces powerful new session management features, including the Agent View and the `/goal` command for setting persistent completion conditions. Numerous bug fixes address stability, UI rendering issues across different themes and terminals, and improved reliability for plugin management and MCP connections. Users can now better manage sessions and control Claude's execution flow.

This release focuses on stability, specifically addressing an issue where the VSCode extension was failing to activate correctly on Windows systems. Users on Windows should now experience reliable extension startup.

This release focuses heavily on stability and correctness across various integrations, fixing numerous bugs related to MCP server state, OAuth token handling, and session persistence after commands like /clear or /resume. Key user-facing fixes include improved image pasting in WSL2 and better handling of file pickers and command resolution in slash commands.

This release introduces new configuration options for controlling worktree branching behavior and specifying sandbox binary paths on Linux/WSL. Several critical bugs have been resolved, including issues with parallel session authentication, permission checks on mapped drives, and inconsistent effort level propagation across concurrent sessions. Memory usage has also been improved by better managing background workers.

This release introduces new environment variables for controlling session IDs and disabling the alternate-screen renderer, along with a visual hint for image pasting. Numerous bugs have been fixed, including issues related to session resumption, terminal scrolling acceleration in IDEs, and handling of special characters during text input.

This release focuses on resolving critical stability and connectivity issues. Key fixes include resolving the VS Code extension activation failure on Windows and correcting an authentication error for the Mantle endpoint.

This release introduces new ways to manage plugins via URL, adds environment variables for forcing synchronized terminal output, and improves history search defaults. Several critical bugs related to session state, API error reporting, and cache TTLs have also been resolved.

This release introduces several usability enhancements, including support for loading plugins from .zip archives and improved handling of MCP server reconnections. Numerous bugs have been resolved, particularly around focus management, large input handling, and ensuring correct behavior for markdown links and parallel tool calls. Additionally, subprocesses now correctly isolate environment variables, improving stability for instrumented applications.

This release introduces a powerful new `claude project purge` command for cleaning up project state and enhances model discovery by supporting Anthropic-compatible gateways in the model picker. Several critical bugs related to OAuth timeouts, image pasting, and stream idle errors have been resolved, improving overall stability and login reliability.

This release addresses a specific authentication issue related to the CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS environment variable. Users will no longer encounter a 401 retry loop during OAuth authentication when this setting is active.

This release introduces granular control over Bedrock service tiers via an environment variable and improves session recovery by allowing PR URLs to be used in the `/resume` command. Several critical bugs were fixed, including issues with tool usage in branched sessions, structured output errors with Vertex AI/Bedrock, and incorrect image resizing for newer models.

This release introduces significant quality-of-life improvements, including a type-to-filter search for skills and better handling of tool output replacement via PostToolUse hooks. Numerous critical bugs have been resolved, focusing heavily on fixing memory leaks related to image processing and transcript history, and improving session stability during restarts and network transients. Users will also notice better scrolling behavior in fullscreen mode and enhanced clipboard support in certain terminal setups.

This release introduces non-interactive UltraReview via a new subcommand and allows skills to dynamically reference the current effort level. Numerous bugs have been resolved, including fixes for server connection stability during Esc presses and improved handling of telemetry suppression and terminal scrolling issues. Additionally, Windows users no longer strictly require Git Bash, as PowerShell is now used as a fallback shell.

This release introduces significant configuration persistence, allowing settings like theme and editor mode to be saved locally and respected across overrides. Key updates include expanded support for various Git provider URLs in the `--from-pr` flag and improved handling of tool execution context in print mode and hooks. Numerous bugs were fixed, addressing issues with multi-line pasting, configuration overrides, and various command behaviors across different operating systems.

This release introduces significant enhancements to Vim editing support, including visual and visual-line modes, and overhauls theme management by allowing named custom themes and plugin-shipped themes. Additionally, it brings numerous stability fixes, particularly around MCP server authentication, OAuth token handling, and session management across different operating systems.

This release introduces significant improvements to plugin management, including better dependency handling and enforcement of marketplace restrictions. Users will also notice faster startup times when multiple MCP servers are configured and improved session resumption behavior. Several critical bugs related to token expiration, proxy handling, and context window calculation for Opus 4.7 have also been resolved.

This release focuses heavily on performance and stability, bringing significant speedups to resuming large sessions and improving terminal interaction, especially for Indic scripts and Kitty keyboard protocol users. New features include inline thinking progress indicators and enhanced search capabilities within the `/config` command. Several bugs related to terminal scrolling, session loading, and plugin management have also been resolved.

This release focuses on stability, specifically addressing a crash that occurred within the permission dialog when a teammate requested tool access. No new features were introduced in this update.

This release introduces new network sandboxing controls via `sandbox.network.deniedDomains` and enables Remote Control clients to query file autocomplete suggestions. Numerous stability fixes address issues with session archiving, transcript display, markdown pasting, and various error conditions across CLI and UI interactions.

This release focuses on stability by resolving an availability error encountered when using auto mode with the claude-opus-4-7 model. No new features or general improvements were introduced in this update.

This release introduces the powerful Claude Opus 4.7 xhigh model, allowing fine-grained control over speed and intelligence via the updated `/effort` command. Key new capabilities include the comprehensive `/ultrareview` skill for multi-agent code analysis and an automatic theme matching your terminal settings. Several critical bugs related to file suggestions, permission prompts, and terminal rendering have also been resolved.

This release introduces significant new interaction methods, including a flicker-free TUI mode and a mobile push notification tool for remote control. Several critical bugs related to hanging API calls, session state management, and UI rendering have been resolved. Additionally, usability is improved with better plugin management and enhanced external editor integration.

This release focuses on enhancing the user experience by refining the extended-thinking indicator. Users will now see a rotating progress hint during extended thinking processes.

This release introduces a new session recap feature to restore context when returning to ongoing work, and enables the model to invoke built-in slash commands directly via the Skill tool. Several quality-of-life improvements include better error messaging, reduced memory usage for file operations, and configuration options for prompt caching TTLs.

This release focuses on improving the user experience during long operations by providing thinking hints sooner. There are no major new features or bug fixes noted in this update.

This release introduces significant enhancements to tool capabilities, including adding a `path` parameter to `EnterWorktree` and enabling background monitor support for plugins. Numerous fixes address issues related to UI rendering, queued message handling, and network error reporting, alongside several quality-of-life improvements for configuration and debugging.

This release introduces a new \/team-onboarding command for generating ramp-up guides and enables enterprise TLS proxy support by trusting the OS CA certificate store by default. Numerous stability and usability improvements were made, particularly around session resumption, error messaging for tool usage, and handling of settings and plugins.

This release introduces significant security and configuration enhancements, including an interactive Vertex AI setup wizard and new subprocess sandboxing features for Linux. Numerous bug fixes address critical issues related to Bash command permissions, streaming response fallbacks, and configuration overrides across various modes like fullscreen and resume.

This release introduces significant enhancements to the NO_FLICKER mode, including a new focus view toggle and numerous stability fixes for terminal rendering and input handling. Several critical bugs related to permissions, configuration persistence, and API retries have been resolved, alongside improvements to image token usage and CJK input handling for slash commands.

This release addresses a critical regression affecting Bedrock requests. Specifically, it resolves an issue where authorization headers were missing, causing 403 errors when using specific Bedrock authentication methods.

This release introduces support for Amazon Bedrock powered by Mantle and enhances plugin functionality by stabilizing invocation names and improving hook reliability. Several critical bugs were fixed, including silent login failures on macOS and issues with rate-limiting handling, ensuring a more robust user experience.

This release introduces an interactive Bedrock setup wizard for easier AWS integration and adds detailed cost breakdowns for subscription users. Several critical bugs have been resolved, including issues with subagent spawning in tmux sessions and incorrect hook behavior. Additionally, the /release-notes command is now interactive, and the /vim command has been replaced by a configuration toggle.

This release introduces significant new capabilities, including support for larger MCP tool results (up to 500K chars) and the ability for plugins to ship and execute their own binaries. Several critical bugs were resolved, such as fixing conversation history loss during resume operations and correcting `cmd+delete` behavior across major terminals.

This release introduces interactive lessons via /powerup to help users learn Claude Code features, alongside a new environment variable for better offline marketplace caching. Several critical bugs were fixed, including an infinite loop crash related to usage limits and regressions affecting `--resume` functionality. Performance has also been significantly improved for SDK sessions and large streamed data handling.

This release introduces significant new capabilities for headless sessions with deferred permission handling and enhanced tool usage hooks. Numerous bugs have been resolved across file operations, history persistence, and tool execution, particularly for Windows and large file handling. Quality of life improvements include better tool summaries, updated PowerShell guidance, and disabling default thinking summaries.

This release introduces significant stability improvements for long sessions, fixing numerous memory leaks, rendering issues, and tool execution bugs across various operating systems and environments. Key new capabilities include flicker-free rendering options and a new `PermissionDenied` hook for better auto-mode control. Users will notice fixes for issues related to large file editing, prompt history corruption, and improved behavior in PowerShell environments.

This release focuses on a critical fix for message delivery within the Cowork Dispatch system. Users should now see reliable message transmission in that module.

This release focuses heavily on stability and efficiency, fixing numerous bugs related to session handling, file operations, and UI responsiveness across various platforms. Key improvements include reduced token overhead for file mentions and better performance during startup when many connectors are configured.

This release introduces significant enhancements to hook execution, allowing conditional running based on permission rules and enabling headless integrations via PreToolUse hooks. Several critical bugs related to session compaction, plugin management, and OpenTelemetry logging have been resolved. Performance improvements were also made, particularly around scrolling large transcripts and file autocomplete.

This release introduces several new configuration options via environment variables for advanced model pinning and streaming timeouts, alongside the opt-in preview of the PowerShell tool for Windows. Key fixes address issues with voice input, terminal key responsiveness, and startup performance, while general improvements enhance readability for large token counts and streamline MCP server configuration.

This release introduces significant enhancements for environment management, including new hook events and policy configuration options, alongside a highly requested transcript search feature. Users will also benefit from improved startup performance, better handling of large file diffs, and fixes for several stability issues across macOS and Linux, particularly concerning voice mode and remote sessions.