Claude-Code v2.1.110 adds TUI mode, push notifications, and multiple fixes

Claude-Code v2.1.110 is a feature update to the AI coding assistant's command-line interface, adding new rendering options, notification tools, and addressing multiple stability issues.
New Features and Commands
/tuicommand andtuisetting – run/tui fullscreento switch to flicker-free rendering in the same conversation/focuscommand – toggles focus view separately (Ctrl+O now only toggles between normal and verbose transcript)- Push notification tool – Claude can send mobile push notifications when Remote Control and "Push when Claude decides" config are enabled
autoScrollEnabledconfig – disables conversation auto-scroll in fullscreen mode- Option to show Claude's last response as commented context in the Ctrl+G external editor (enable via
/config)
Improvements
/pluginInstalled tab – items needing attention and favorites appear at the top, disabled items are hidden behind a fold, andffavorites the selected item/doctor– warns when an MCP server is defined in multiple config scopes with different endpoints--resume/--continue– now resurrects unexpired scheduled tasks/autocompact,/context,/exit, and/reload-plugins– now work from Remote Control (mobile/web) clients- Write tool – informs the model when you edit the proposed content in the IDE diff before accepting
- Bash tool – enforces the documented maximum timeout instead of accepting arbitrarily large values
- SDK/headless sessions – now read
TRACEPARENT/TRACESTATEfrom the environment for distributed trace linking - Session recap – now enabled for users with telemetry disabled (Bedrock, Vertex, Foundry,
DISABLE_TELEMETRY). Opt out via/configorCLAUDE_CODE_ENABLE_AWAY_SUMMARY=0.
Bug Fixes
- Fixed MCP tool calls hanging indefinitely when the server connection drops mid-response on SSE/HTTP transports
- Fixed non-streaming fallback retries causing multi-minute hangs when the API is unreachable
- Fixed session recap, local slash-command output, and other system status lines not appearing in focus mode
- Fixed high CPU usage in fullscreen when text is selected while a tool is running
- Fixed plugin install not honoring dependencies declared in
plugin.jsonwhen the marketplace entry omits them;/plugininstall now lists auto-installed dependencies - Fixed skills with
disable-model-invocation: truefailing when invoked via/<skill>mid-message - Fixed
--resumesometimes showing the first prompt instead of the/renamename for sessions still running or exited uncleanly - Fixed queued messages briefly appearing twice during multi-tool-call turns
- Fixed session cleanup not removing the full session directory including subagent transcripts
- Fixed dropped keystrokes after the CLI relaunches (e.g.
/tui, provider setup wizards) - Fixed garbled startup rendering in macOS Terminal.app and other terminals that don't support synchronized output
- Hardened "Open in editor" actions against command injection from untrusted filenames
- Fixed
PermissionRequesthooks returningupdatedInputnot being re-checked againstpermissions.denyrules;setMode:'bypassPermissions'updates now respectdisableBypassPermissionsMode - Fixed
PreToolUsehookadditionalContextbeing dropped when the tool call fails - Fixed stdio MCP servers that print stray non-JSON lines to stdout being disconnected on the first stray line (regression in 2.1.105)
- Fixed headless/SDK session auto-title firing an extra Haiku request when
CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFICorCLAUDE_CODE_DISABLE_TERMINAL_TITLEis set - Fixed potential excessive memory allocation when piped (non-TTY) Ink output contains a single very wide line
- Fixed
/skillsmenu not scrolling when the list overflows the modal in fullscreen mode - Fixed Remote Control sessions showing a generic error instead of prompting for re-login when the session is too old
- Fixed Remote Control session renames from claude.ai not persisting the title to the local CLI session
📖 Read the full source: GitHub Claude-Code
👀 See Also

Xiaomi Open-Sources MiMo-V2.5-Pro: Nears Claude Opus 4.6 on Coding Benchmarks
Xiaomi released MiMo-V2.5-Pro, an open-source coding model that scored 233/233 on a university compiler project, built a video editor autonomously, and ranks within 1% of Claude Opus 4.6 on SWE-Bench and Terminal-Bench.

Claude Code v2.1.191: /rewind, CPU fixes, MCP reliability improvements
Claude Code v2.1.191 adds /rewind to resume cleared conversations, cuts streaming CPU usage 37%, fixes agent resurrection, and improves MCP reliability with retries.
Alphabet Stock Sheds $700B as AI Bills Climb
Alphabet's stock is down 15% from its May peak, erasing ~$700B in value as AI bills climb and Gemini faces delays, with co-founder Sergey Brin returning to ops.

Local LLM Benchmark: Backend Generation by Function Calling – GLM, Qwen, DeepSeek Compared
A rigorous benchmark of local and frontier LLMs for backend code generation via function calling, with scoring rubric. Key findings: qwen3.5-35b-a3b matches gpt-5.4 on DB/API design, and dense Qwen 27B beats 397B MoE. Frontier models dropped due to cost.