Claude Code

• /model now validates provided model names
• Fixed Bash tool crashes caused by malformed shell syntax parsing

• SDK: Added partial message streaming support via --include-partial-messages CLI flag

• Windows: Fixed path permission matching to consistently use POSIX format (e.g., Read(//c/Users/...))

• Settings: /doctor now validates permission rule syntax and suggests corrections

• Vertex: add support for global endpoints for supported models
• /memory command now allows direct editing of all imported memory files
• SDK: Add custom tools as callbacks
• Added /todos command to list current todo items

• Windows: Add alt + v shortcut for pasting images from clipboard
• Support NO_PROXY environment variable to bypass proxy for specified hostnames and IPs

• Settings file changes take effect immediately - no restart required

• Added /context to help users self-serve debug context issues
• SDK: Added UUID support for all SDK messages
• SDK: Added --replay-user-messages to replay user messages back to stdout

• Fixed issue causing "OAuth authentication is currently not supported"
• Status line input now includes exceeds_200k_tokens
• Fixed incorrect usage tracking in /cost
• Introduced ANTHROPIC_DEFAULT_SONNET_MODEL and ANTHROPIC_DEFAULT_OPUS_MODEL for controlling model aliases
• Bedrock: Updated default Sonnet model to Sonnet 4

• Status line input now includes session cost info
• Hooks: Introduced SessionEnd hook

• Fix tool_use/tool_result id mismatch error when network is unstable
• Fix Claude sometimes ignoring real-time steering when wrapping up a task
• @-mention: Add ~/.claude/* files to suggestions for easier agent, output style, and slash command editing
• Use built-in ripgrep by default; opt out by setting USE_BUILTIN_RIPGREP=0

• @-mention: Support files with spaces in path
• New shimmering spinner

• SDK: Add request cancellation support
• SDK: New additionalDirectories option to search custom paths, improved slash command processing
• Settings: Validation prevents invalid fields in .claude/settings.json files
• MCP: Improve tool name consistency
• Bash: Fix crash when Claude tries to automatically read large files

• Bash tool: Fix heredoc and multiline string escaping, improve stderr redirection handling
• SDK: Add session support and permission denial tracking
• Fix token limit errors in conversation summarization
• Opus Plan Mode: New setting in /model to run Opus only in plan mode, Sonnet otherwise

• UI improvements: Fix text contrast for custom subagent colors and spinner rendering issues

Released output styles, including new built-in educational output styles "Explanatory" and "Learning". Agents now fix custom agent loading when agent files are unparsable.

• Ask permissions: have Claude Code always ask for confirmation to use specific tools with /permissions

• MCP: Support multiple config files with --mcp-config file1.json file2.json
• MCP: Press Esc to cancel OAuth authentication flows
• Bash: Improved command validation and reduced false security warnings
• UI: Enhanced spinner animations and status line visual hierarchy
• Linux: Added support for Alpine and musl-based distributions (requires separate ripgrep installation)

• Performance: Optimized message rendering for better performance with large contexts
• Windows: Fixed native file search, ripgrep, and subagent functionality
• Added support for @-mentions in slash command arguments

• Background commands: (Ctrl-b) to run any Bash command in the background so Claude can keep working (great for dev servers, tailing logs, etc.)
• Customizable status line: add your terminal prompt to Claude Code with /statusline