TL;DR
/modelsaves as default again; presssfor session-only. If you customized themodelPicker:setAsDefaultkeybinding, rename it tomodelPicker:thisSessionOnlyin keybindings.json. (more below)Subagent MCP servers now enforce
--strict-mcp-config,--bare, and enterprise allow/deny policies. If you relied on strict MCP config to sandbox subagents, the fence was not actually up until this release. (more below)Custom API gateway credential leak fixed. A regression could send your Anthropic OAuth credential to the gateway instead of the gateway's own token.
/bgwhile Claude is mid-response now continues in background instead of dropping it. Previously backgrounding a running response silently discarded the output.subagent_type: 'claude'no longer runs in a hidden worktree that discards gitignored outputs. If agent tool results were mysteriously missing, this was likely the cause.
New in 2.1.153
2.1.153 (May 28, 2026)
- Added
skipLfsoption togithub/gitplugin marketplace sources to skip Git LFS downloads during clone and update - Claude Code now shows a one-time notice when your npm global install can't auto-update;
/doctorlists the fixes - Status line commands now receive
COLUMNSandLINESenvironment variables so scripts can size output to the terminal width claude agents: autocomplete in the dispatch input now suggests native slash commands and bundled skills, not just project skillsclaude agents: PR column now showsPR #Nfor a single PR orN PRsfor multipleclaude doctornow shows the result of your last update attempt- Combined the separate "needs authentication" startup notifications for MCP servers and connectors into a single message
- macOS: background agents now appear as "Claude Code" in Privacy & Security and keep their permission grants across upgrades
- Fixed stateful MCP servers without the optional GET SSE stream reconnect-looping on
tools/list(regression in v2.1.147) - Fixed a regression where a custom API gateway could receive the user's Anthropic OAuth credential instead of the gateway's own token
- Fixed subagent (Agent tool) frontmatter MCP servers ignoring
--strict-mcp-config,--bare, remote mode, enterprise managed MCP config, and managed-settings MCP server allow/deny policies --strict-mcp-configno longer strips inlinemcpServersfrom explicitly-passed agent definitions (--agents/ SDKagents), and blocked subagent MCP servers now surface a visible warning- Fixed the Windows PowerShell installer reporting "Installation complete!" when installation actually failed
- Fixed
claude updateinstalling the latest version instead of the configured release channel's version for npm installations - Fixed excessive memory usage (multiple GB) when resuming a session by transcript file path on machines with many stored sessions
- Fixed
claude agentsandclaude --bgrunning on a stale daemon started before binary-takeover support, even after upgrading - Fixed a hang where the CLI could fail to exit when stdin was closed without EOF in stream-json mode, leaving a stale session marker behind
- Fixed malformed
file://links in Claude's responses not being clickable in the terminal - Fixed
claude --helprendering unwrapped output on terminals narrower than 92 columns - Fixed MCP tool progress notifications not rendering in the collapsed tool view
- Fixed
Agenttool withsubagent_type: 'claude'running in an undocumented temporary worktree, which could silently discard outputs written to gitignored paths /bgwhile Claude is responding now continues the response in the background session instead of dropping it- Fixed
/btwkeyboard shortcuts becoming unresponsive in background sessions while a task is running - Fixed background sessions writing temp files to
$CLAUDE_JOB_DIRtriggering a "sensitive file" permission prompt - Fixed recovering a background agent whose working directory was deleted showing a truncated stack trace instead of a clear error message
- Fixed
EnterWorktreenot being available immediately in background sessions (previously requiredToolSearchfirst) - Fixed
cmd+kin iTerm2/Terminal.app not repainting attached background sessions - Fixed the IME candidate window appearing at the bottom of the screen instead of next to the input caret in attached background sessions on Windows
- Fixed background-color bleed when attaching to a background agent from 256-color-only terminals after the agent had rendered file diffs
- Fixed
/copyand copy-on-select silently failing to update the system clipboard when attached to a background session inside tmux - Fixed opening
claude agentswith Remote Control enabled leaving zombie session entries on the Code tab after exiting - Fixed
/renamein background sessions not updating the session banner immediately - Fixed Windows update rollback: if a Windows update fails, Claude Code now restores the original executable by copy and tells you how to recover
- [VSCode] Fixed Claude Code processes not shutting down cleanly when VS Code closed on Windows, causing false "unclean exit" reports and orphaned MCP servers
/modelnow saves your selection as the default for new sessions (matching the IDE). Presssin the picker to switch models for the current session only.- If you customized the
modelPicker:setAsDefaultkeybinding, rename it tomodelPicker:thisSessionOnlyin keybindings.json (thedaction was replaced bys)
Notes
/model behavior: another flip
In v2.1.144, /model was changed to affect only the current session, with a d key to set a persistent default. That was a deliberate move to prevent one session from accidentally changing every future session's model. v2.1.153 reverses course: /model now sets the default (matching the IDE extensions' behavior), and the escape hatch is s for session-only. If you had built the v2.1.144 muscle memory of "just /model for this session," retrain now. The old modelPicker:setAsDefault keybinding is gone; its replacement is modelPicker:thisSessionOnly.
Subagent MCP enforcement was silently missing
The fix for subagent MCP servers is broader than it looks. Before v2.1.153, a subagent spawned via the Agent tool with MCP servers in its frontmatter bypassed --strict-mcp-config, --bare mode, remote-mode restrictions, enterprise managed MCP config, and managed-settings allow/deny policies. If you were relying on any of these controls to prevent subagents from reaching external services, they were not enforced. This release closes that gap and surfaces a visible warning when a subagent MCP server is blocked by policy.