← All briefs
Matins
35 changes / 5 actionable / 2 deep dives
Claude Code

TL;DR

  • /model saves as default again; press s for session-only. If you customized the modelPicker:setAsDefault keybinding, rename it to modelPicker:thisSessionOnly in 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.

  • /bg while 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 skipLfs option to github/git plugin 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; /doctor lists the fixes
  • Status line commands now receive COLUMNS and LINES environment 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 skills
  • claude agents: PR column now shows PR #N for a single PR or N PRs for multiple
  • claude doctor now 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-config no longer strips inline mcpServers from explicitly-passed agent definitions (--agents / SDK agents), and blocked subagent MCP servers now surface a visible warning
  • Fixed the Windows PowerShell installer reporting "Installation complete!" when installation actually failed
  • Fixed claude update installing 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 agents and claude --bg running 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 --help rendering unwrapped output on terminals narrower than 92 columns
  • Fixed MCP tool progress notifications not rendering in the collapsed tool view
  • Fixed Agent tool with subagent_type: 'claude' running in an undocumented temporary worktree, which could silently discard outputs written to gitignored paths
  • /bg while Claude is responding now continues the response in the background session instead of dropping it
  • Fixed /btw keyboard shortcuts becoming unresponsive in background sessions while a task is running
  • Fixed background sessions writing temp files to $CLAUDE_JOB_DIR triggering 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 EnterWorktree not being available immediately in background sessions (previously required ToolSearch first)
  • Fixed cmd+k in 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 /copy and copy-on-select silently failing to update the system clipboard when attached to a background session inside tmux
  • Fixed opening claude agents with Remote Control enabled leaving zombie session entries on the Code tab after exiting
  • Fixed /rename in 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
  • /model now saves your selection as the default for new sessions (matching the IDE). Press s in the picker to switch models for the current session only.
  • If you customized the modelPicker:setAsDefault keybinding, rename it to modelPicker:thisSessionOnly in keybindings.json (the d action was replaced by s)

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.