Claude Code

This release focuses on general bug fixes and reliability improvements. While no new features were introduced, the overall stability and performance of the tool have been enhanced.

This release introduces several new features to enhance user control and workflow, including improved organization policy visibility and expanded output limits for commands and background tasks. Key bug fixes address issues with input handling, session management, and remote control functionality across various platforms and integrations.

This release introduces a new diff panel for viewing uncommitted changes in fullscreen mode and adds several new commands and configurations for headless sessions and advanced IdP scenarios. Numerous bug fixes address permission issues, model handling, prompt caching, and session management, alongside improvements to structured output and resource utilization.

This release introduces several new features, including organizational control over MCP servers and enhanced headless host capabilities. Numerous bug fixes address issues with concurrent sessions, prompt caching, fullscreen mode, and various command/script execution scenarios. Performance and user experience are also improved with faster terminal rendering and better workflow agent details.

This release addresses two critical bugs. Claude Code will now launch correctly on macOS 12 (Monterey). Additionally, issues with remote and scheduled sessions failing due to permission approval problems have been resolved.

This release introduces the new Claude Fable 5.1 model as the default, featuring a 1 million token context window. Users can now customize time formats and time zones for timestamps, and enhanced security measures are in place for cloud metadata fetches. Numerous bug fixes improve session management, tool interactions, and overall stability across different operating systems and configurations.

This release addresses several critical bugs. It resolves issues with Bash commands on Macs, ensures "always allow" settings are saved correctly, and improves the stability of Remote Control sessions when network conditions are poor. Additionally, it prevents background task notifications with large error outputs from causing API request size limit issues.

This release introduces new hook events for model switches and live streaming of subagent tool calls to Remote Control clients. It also includes significant improvements to session management, file tool security, and error handling across various tools and integrations, alongside numerous bug fixes for a more stable experience.

This release focuses on general bug fixes and reliability improvements. While no new features were introduced, users can expect a more stable and dependable experience with the tool.

This release introduces enhanced security features with the new `--restricted` mode and improved cross-session messaging capabilities. Several bug fixes address prompt caching, session management, and tool behavior, while improvements focus on reducing prompt footprints and refining user experience for features like `/ultrareview` and PR badges.

This release introduces several new tools and commands, including a `SendFeedback` tool for easier issue reporting and `/claude-api cost-optimize` for managing API expenses. Several bugs have been fixed, improving the reliability of history search, sub-agent error handling, and terminal shortcut functionality across different keyboard layouts and terminals. Additionally, performance and user experience are enhanced with collapsed peer messages, improved hyperlink rendering, and more robust session management.

This release introduces an Auto mode tab for managing classifier rules in /permissions and provides the turn's completion time for better session tracking. Numerous bug fixes address issues with fullscreen mode, transcript rendering, background session stability, markdown display, tool call handling, plugin management, and UI consistency across various scenarios.

This release addresses a critical startup crash affecting specific Linux distributions with glibc 2.44. Users on affected systems should now be able to launch the application without encountering this issue.

This release introduces significant enhancements to usage tracking, model selection, and cost management with new settings and breakdowns. It also addresses numerous bugs across various features like auto mode, session management, and tool usage, improving overall stability and user experience.

This release focuses on general bug fixes and reliability improvements. While no new features were introduced, users can expect a more stable and dependable experience with the latest update.

This release focuses on general bug fixes and reliability improvements. Users can expect a more stable and dependable experience with the tool.

This release introduces several new features, including a fullscreen renderer offer for specific platforms and a command to upgrade Python projects to the latest Anthropic library. It also enhances cloud session capabilities with synced plugins and improves the user experience with better cost estimates and usage limit notifications.

This release introduces several new features for customizing keybindings and managing plugins with HTTP header support. It also significantly enhances the stability and reliability of Remote Control sessions and self-hosted runners, fixing numerous bugs related to memory usage, session management, and network communication.

This release introduces a new "Concise" output style, allowing Claude to deliver results more directly by skipping preamble and narration. Additionally, a bug affecting prompt caching with LLM gateways or custom base URLs has been resolved.

This release introduces new environment variables for default model selection and cross-session notifications on macOS and Linux. Several bugs have been fixed, including issues with file deletion, fullscreen rendering, model picker display, and subprocess failures. Performance and auto mode have been improved, with clearer model selection highlighting and better handling of git status and cloud environment classifications.

This release introduces an optional spellcheck feature to underline misspelled words as you type. Several bugs have been fixed, including issues with prompt highlights, markdown lists, and cache invalidation. Performance improvements have been made to background cloud sessions and the embedded `grep` utility.

This release introduces several new features including enhanced GitLab integration, automatic session continuation at usage limits, and improved security for file access. Key bug fixes address issues with markdown rendering, API response handling, and permission management across various scenarios. Additionally, user experience is improved with better prompt rendering, clearer error messages, and more intuitive dialog behavior during active tasks.

This release introduces several new features, including enhanced GitLab integration, user identity forwarding for apps gateways, and memory cgroup support for Bash commands. It also addresses numerous bugs, such as issues with cloud session loss, MCP connections, and permission prompt notifications, while improving session start times and error handling.

This release introduces enhanced subagent capabilities, allowing them to inherit conversation history and run in the background by default. You can now mention other Claude sessions directly and enjoy improved GitLab integration for plugin marketplaces. Several security enhancements have been added, including secret redaction for GitLab tokens and improved sandbox hardening.

This release addresses a critical bug affecting MCP OAuth sign-in. The fix resolves redirect URI mismatch errors encountered when using pre-registered OAuth clients, ensuring smoother authentication with services like Slack.

This release introduces enhanced plugin management with local command sources and improved session organization in VSCode. Several critical bugs have been fixed, including issues with long responses, tool call errors, and crashes on Windows. Additionally, performance and security have been improved with keepalive pings, better workflow handling, and stricter sandbox network configurations.

This release enhances the Write tool for newer models, allowing them to overwrite existing files without prior reading. It also hardens synced skills from claude.ai for improved security and reliability. Numerous bug fixes address issues with session redrawing, Git integration, model reverting, cross-session messaging, self-hosted runners, and settings merging.

This release addresses several critical bugs, including issues with feature flag evaluation, Bash command failures on GitHub runners, and conversation rewinding. Performance has also been improved with fewer event-loop stalls, and the slash-command menu has been refined for a clearer user experience.

This release focuses on enhancing the overall stability and reliability of the tool. While no new features are introduced, users can expect a more robust and dependable experience due to general bug fixes and improvements.

This release enhances Claude Code with gateway spend-limit support and a workspace trust prompt for agents, improving usage monitoring and security. Several bugs have been fixed, including issues with OAuth tokens, session handling, and cross-session messaging, ensuring a more stable and reliable experience.

This release introduces self-hosted environments for Claude Code, allowing you to run sessions on your own infrastructure. You can now also install plugins from zip archives and message between Claude Code sessions on your machines. Several bugs have been fixed, including issues with long project paths, message sending failures, and sandbox violations.

This release introduces enhanced managed settings for marketplace repositories and improved handling of restricted subagent models. Several critical bugs have been fixed, including permission bypasses, sandbox violations, and issues with session resumption and model discovery.

This release focuses on enhancing security and usability within agent sessions. Key improvements include better isolation for destructive Git commands, more robust handling of tool restrictions, and clearer error reporting for usage credits and connection issues. Additionally, diff views have been refined to use raw git blob content for greater accuracy.

This release introduces a new Focus view in VSCode for a streamlined chat experience and enhanced security features for credential files on Linux and WSL. Several bugs have been fixed, including permission check bypasses, path handling issues, and crashes related to tool calls and API requests.

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.