Anthropic's agentic command-line coding tool. Updates to the Claude Code CLI, IDE integrations, and SDK.
Resolved an issue where MCP OAuth sign-in would fail with a redirect URI mismatch error when using pre-registered OAuth clients like Slack. This fix ensures proper OAuth handling for servers with pre-configured clients.
This release includes numerous enhancements and bug fixes across Remote Control sessions, streaming stability, plugin marketplace support, and IDE integration. Notable improvements include SSE keepalive pings to prevent idle timeouts, fixes for crashes in terminal output and file handling, better workflow optimization, and new VSCode features like session groups and resizable side panels.
Claude Code 2.1.228 includes multiple bug fixes for interactive sessions, Git integration on Windows, session management, and plugin caching, along with improvements to cross-session messaging, credential handling, and tool behavior. This release also hardens skills synced from claude.ai to prevent shadowing local commands and improves overall stability.
This release fixes feature flag evaluation for expired login sessions, corrects Bash command failures in GitHub-hosted runners, resolves /tui conversation rewinding issues, improves slash-command menu styling and selection, and reduces performance stalls in file-not-found suggestions and at-mention size checks.
Claude Code 2.1.225 adds gateway spend-limit support with detailed usage warnings, workspace trust prompts for agents, and fixes numerous issues including transient authentication failures in headless sessions, MCP OAuth server reliability on macOS, safety-filter retry behavior, cross-session message handling, conversation history corruption on Remote Control resume, session directory bugs, self-hosted runner initialization, web session reporting, Remote Control photo handling, Focus view folding issues, and improvements to SendMessage for starting conversations by name.
This release includes bug fixes and reliability improvements to enhance stability and user experience.
This release adds self-hosted environments for running Claude Code sessions on your own machines, introduces archive-based plugin installation, and adds cross-session messaging with improved sandbox credential masking. Multiple fixes address session directory resolution, message delivery reporting, filesystem deny entries, plugin installation corruption, and Remote Control reliability.
This release adds marketplace filtering via owner wildcards, improves permission and security controls including fixes for Bash permission bypasses and sandbox escapes, enhances model discovery and overrides handling, and refines session management and command review workflows.
This release fixes multiple security and stability issues including worktree isolation for git commands, tool restriction bypasses in background tasks, usage credit blocking, proxy connectivity, MCP server attribution, connector authorization display, and rare crashes. It also improves auto mode safety with permission classification for inter-session messages and refines diff viewing.
Claude Code 2.1.221 adds a Focus view to hide tool activity in VSCode, introduces credential file masking for sandboxes, and fixes numerous bugs across permissions, MCP server connections, plugin management, Vim mode, and session handling. Improvements include better tool search for Vertex AI, cache-efficient permission checks, and enhanced stats tracking.
This release includes various bug fixes and reliability improvements to enhance overall stability and performance.
Claude Code now features Claude Opus 5 as the default Opus model with 1M context and fast mode pricing. This release includes numerous improvements to sandbox security settings, MCP server handling, workflow management, self-hosted runner reliability, UI/UX enhancements, and bug fixes for permission handling, model selection, and remote control functionality.
Added Claude Opus 5 as the default model with 1M context and fast-mode support at $10/$50 per Mtok. Introduced sandbox network allowlist settings, DirectoryAdded hook for mid-session directory registration, improved MCP error handling and configuration validation, nested subagent forwarding in stream-json, and numerous bug fixes and UI improvements across the terminal, remote control, and model picker.
Claude Code 2.1.218 includes numerous fixes and improvements: /code-review now runs as a background subagent to avoid filling conversations, accessibility announcements were added for text deletions, Windows path corruption was fixed, and multi-line paste handling in terminals was improved. Many other fixes address issues with context reporting, tool execution, error messaging, screen reader support, MCP server connectivity, and session management.
This release refactors /code-review to run as a background subagent, fixes multiple critical bugs affecting file accessibility on Windows, terminal paste behavior, and accessibility features, and improves auto mode intelligence and trust dialog clarity.
This release adds emoji shortcode autocomplete in prompts, adds warnings for failing transcript writes and disabled session saving, and fixes multiple critical issues including a memory leak in MCP tool output truncation, Windows auto-update failures, background session directory canonicalization, auto-compact triggering, and various settings being ignored in Desktop sessions. Also fixes screen reader mode announcements, telemetry endpoint routing, transcript preview layout, subagent spawning controls, and budget enforcement for background agents.
This release adds sandbox filesystem control, fixes message normalization performance degradation in long sessions, resolves OAuth token rotation issues, and addresses numerous stability problems including file attachment failures, symlink handling, permission validation, and UI rendering issues across the desktop and web clients.
The /verify and /code-review skills are no longer run automatically by Claude. Users must now explicitly invoke them using /verify or /code-review commands when needed.
This release fixes multiple permission-check bypasses affecting Windows PowerShell, Bash, and remote sessions; adds the EndConversation tool for handling abusive users; improves diagnostics with progress heartbeats and structured logging; and resolves numerous stability issues including memory leaks, file encoding bugs, and background session management problems.
Version 2.1.212 introduces significant improvements to session management with /fork now creating background sessions, adds safeguards against runaway loops with search and subagent caps, and includes numerous bug fixes for stability, performance, and edge cases across workspace operations, streaming, and integrations.
Claude Code 2.1.211 adds support for forwarding subagent text and thinking in stream-json output, fixes critical security issues with permission preview character filtering and session management bugs, resolves model override and MCP server reconnection problems, and improves terminal performance and background agent reporting.
This release adds a live elapsed-time counter for tool calls, fixes critical issues with git isolation for worktree subagents, session crashes, and background worker stability, and improves permission handling, error messages, and agent UI interactions across multiple surfaces.
Fixed an issue where /model and other dialogs were incorrectly blocked in Claude Agents background sessions due to an overly broad guard. This reverts the problematic restriction.
This release adds accessibility features like screen reader mode and vim insert-mode remaps, introduces corporate launcher support via CLAUDE_CODE_PROCESS_WRAPPER, and fixes numerous stability issues including context window resets, memory leaks, slowdowns in permission-heavy sessions, and various tool failures.
This release makes auto mode available without opt-in on Bedrock, Vertex AI, and Foundry; fixes terminal freezing during streaming, remote settings consent dialogs, spurious prompt-injection warnings, and numerous issues with auto-updater, transcripts, worktrees, Remote Control sessions, and plugin configuration handling.
Claude Code 2.1.206 adds directory path suggestions for the /cd command, introduces a /doctor check for optimizing checked-in CLAUDE.md files, and improves git operations by auto-allowing pushes to configured remotes. This release includes numerous bug fixes for MCP server configuration, OAuth authentication, model picker display, keyboard input handling, and agent view management, plus improvements to code review quality and the agents view interface.
This release includes numerous bug fixes for session management, file handling, agent status display, and MCP server integration, along with improvements to auto mode, the agent view, and memory usage during updates. A new /doctor command provides comprehensive setup diagnostics.
This release adds login expiration warnings, improves background session stability and performance, fixes multiple crashes and stalling issues on macOS and Windows, and enhances the agent interface with better visibility and error messages.
Corrected an issue where hook events failed to stream during SessionStart hooks in headless sessions, preventing remote workers from being incorrectly idle-reaped while processing hooks.
This release adds dynamic workflow size configuration, improves OpenTelemetry telemetry with workflow attributes, and fixes numerous crashes and failures in workflow execution, session management, remote control, voice dictation, and file handling. It also enhances UI layouts and error messaging for better developer experience.
Claude Sonnet 5 sessions have been updated to remove the use of mid-conversation system roles for harness reminders, simplifying the conversation flow and behavior.
This release includes numerous stability and usability improvements: fixed crashes at startup when MCP server configuration is malformed, resolved background session hangs and reconnection issues, corrected daemon management to prevent stale locks, fixed subagent output handling under rate limiting, and enhanced accessibility including screen reader support and synchronized terminal rendering for tmux.
This release contains multiple bug fixes and improvements, including fixes for stacked skill invocations now loading up to 5 skills instead of just the first, SSL certificate error handling with immediate failure and guidance, streaming response preservation with incomplete-response notices, and subagent error handling. Additionally, fixes address background agent daemon stability on Linux, cold-start issues on macOS over SSH, and various UI improvements for agent visibility and session management.
Major release featuring subagents running in background by default, general availability of Claude in Chrome, new /dataviz skill, AWS platform support, improved agent notifications and error handling, and numerous bug fixes for agent teams, branch management, UI rendering, and network resilience.
Adds organization default models, readable session names, and clickable file attachments in chat. Includes security improvements for MCP server handling, numerous bug fixes for background jobs, rate limiting, PowerShell commands, agent panels, voice dictation, and streaming reliability enhancements.
Claude Code now defaults to Claude Sonnet 5, featuring a native 1-million-token context window. Promotional pricing is available at $2 per million tokens for input and $10 per million tokens for output through August 31.
Fixes for hook matchers, voice dictation across languages, plugin handling, background jobs stability, and Remote session startup. Adds mouse click disable option in fullscreen mode and improves voice mode on Linux with better error messaging.
This release adds autoMode.classifyAllShell to route all Bash/PowerShell commands through the auto-mode classifier, introduces auto-mode denial reasons in transcripts and toasts, adds live file path autocomplete for bash mode, and includes a new OpenTelemetry log event for assistant responses. It also fixes several issues with /model UI stale state after login, background task cancellation, pinned agent re-prompting, and agent panel visibility, while improving background agents, MCP authentication, and plugin auto-rename functionality.
This release adds conversation rewind support, fixes scroll jumping during streaming, resolves background agent resurrection issues, and improves MCP server reliability with retry logic and better error messages. Performance has been optimized with reduced CPU usage during streaming responses.
This release includes bug fixes and improvements to reliability for Claude Code.
This release adds sandbox credential blocking, org-configured model restrictions, mouse support in menus, and fixes numerous issues including MCP tool timeouts, session startup delays, Korean text rendering, agent tracking, and channel connections.
Multiple improvements and bug fixes including localized session titles, better Bedrock credential caching, fixed model enforcement and auto mode fallback, corrected tool path patterns, fixed clipboard issues in tmux/SSH, improved Remote Control stability, and numerous background session and daemon fixes.
A new enforceAvailableModels managed setting constrains the Default model to the availableModels allowlist, preventing default models from resolving to disallowed models and blocking users or projects from widening the managed list.
This release includes numerous bug fixes and improvements across model selection, billing displays, environment variable handling, and performance. Notable changes include fixes for the /model picker display, Bedrock GovCloud inference profiles, background session environment inheritance, and skill hot-reload efficiency.
Corrected Fable 5 model names with [1m] suffix to normalize properly since 1M context is now included by default. Also fixed a spurious sandbox dependencies warning that appeared on Windows startup.
This release adds recursive sub-agent spawning (up to 5 levels deep), improves AWS region detection from config files, includes a marketplace plugin search bar, and fixes numerous bugs across sessions, agents, model selection, permissions, and performance. Key fixes address context limits, image processing errors, agent state management, model restrictions, WebFetch rules, and memory recall in remote sessions.
Introducing Claude Fable 5, a new Mythos-class model now available for general use with enhanced capabilities. Also fixed an issue where sessions failed to save transcripts and appear in resume when launched from VS Code integrated terminal or shells with inherited environment variables.
This release adds post-session lifecycle hooks for self-hosted runners, a safe mode flag for troubleshooting with customizations disabled, a /cd command to change working directories, and numerous bug fixes for UI responsiveness, MCP policy enforcement, Git credential handling, remote sessions, and background agents. Performance improvements include reduced CPU usage during streaming and restored idle timeouts for Vertex/Foundry.
This release includes bug fixes and reliability improvements to enhance overall stability and performance of Claude Code.
This release adds fallback model configuration for handling API unavailability, glob pattern support in deny rules for tools, hardened cross-session messaging security, improved thinking token controls across models, and numerous bug fixes including terminal rendering issues, image processing errors, and session stability improvements.
This release includes bug fixes and reliability improvements to enhance overall system stability and performance.
This release includes bug fixes and reliability improvements to enhance overall system stability and performance.
This release adds version control via requiredMinimumVersion and requiredMaximumVersion settings, introduces a /plugin list command with filtering, adds a copy shortcut to /btw, expands hook capabilities with additionalContext support, and includes numerous bug fixes for command execution, session management, terminal handling, and permission rules.
Claude Code 2.1.162 includes improvements to the agents CLI with better status output, new explicit tools support for Grep/Glob, UI refinements for slash commands and Remote Control, multiple bug fixes for config handling, permission rules, terminal rendering, and background session management, plus quieter startup messaging.
This release includes OpenTelemetry metric labels for custom dimension filtering, improved UX for fanned-out work display and clipboard handling in fullscreen mode, fixes for motion-accessibility settings, managed-settings policies, background subagent output, tool call failures, various Git and MCP command issues, and performance optimizations for terminal and file rendering.
This release includes security improvements with prompts before writing to sensitive shell and build-tool config files, fixes for background sessions losing chat history, clipboard functionality on WSL, keyboard responsiveness on Windows, and various stability improvements for the agents view and auto mode.
53 more changes from Claude Code. Sign up to read the whole changelog.
Sign up freeGitHub or email — no card needed.