Matins
← All briefs
Matins
Tuesday 23 June — v2.1.186
33 changes / 4 actionable / 2 deep dives
Claude Code

TL;DR

  • ! bash commands now trigger Claude to respond to the output automatically. Set "respondToBashCommands": false in settings.json to keep the previous context-only behavior.

  • Background subagents now surface permission prompts in the main session instead of auto-denying. The dialog identifies which agent is asking, and Esc denies just that tool (more below).

  • CLAUDE_CODE_MAX_RETRIES is now capped at 15. For unattended sessions, switch to CLAUDE_CODE_RETRY_WATCHDOG instead (more below).

  • Agent(type) deny rules and allowed-types restrictions are now enforced for named subagent spawns. If you rely on agent-type restrictions, they were silently bypassed before this fix.

New in 2.1.186

2.1.186 (June 23, 2026)

  • Added claude mcp login <name> and claude mcp logout <name> to authenticate MCP servers from the CLI without opening the interactive /mcp menu, with --no-browser stdin redirect support for completing over SSH
  • Added status filtering (press f) to the /workflows agent detail view
  • Added a "Skills" section to the /plugin Installed tab
  • Added teammateMode: "iterm2" setting with a warning when auto mode cannot find the it2 CLI
  • Added "Claude Platform on AWS - refresh credentials" option to /login when awsAuthRefresh is configured
  • ! bash commands now trigger Claude to respond to the output automatically; set "respondToBashCommands": false in settings.json to keep the previous context-only behavior
  • Fixed streaming requests failing with "Content block not found" or JSON parse errors after the machine wakes from sleep
  • Fixed subagent transcript scroll position bleeding into the main transcript on exit
  • Fixed background task previews flashing raw tool names before the agent's plan loaded
  • Fixed Chrome tab-group isolation not applying when the in-product permissions gate is off for concurrent CLI sessions
  • Fixed background session recaps being duplicated; the agent's own end-of-turn summary now shows as the recap line
  • Fixed opening a background session from claude agents leaving the previous screen painted behind it
  • Fixed Agent(type) deny rules and Agent(x,y) allowed-types restrictions not being enforced for named subagent spawns
  • Fixed Esc and Ctrl+C not responding while background agents are still running after the main turn ends
  • Fixed misaligned option numbers in permission prompts when the option text overflows
  • Fixed pressing x on a finished subagent in the agent panel not dismissing it
  • Fixed a misleading "MCP server disconnected" notice for intentionally retired tools when resuming older sessions
  • Fixed /plugin Installed showing a "more above" indicator when already scrolled to the top
  • Fixed ~~strikethrough~~ showing literal tildes in assistant messages instead of rendering as strikethrough
  • Fixed --tools allowing feature-gated tools to slip through before flags loaded on a cold first launch
  • Fixed background job status in claude agents showing a stale "needs input" message after replying
  • Fixed a dark-theme flash when opening a background session from claude agents on a light terminal
  • Fixed mouse-selected text staying highlighted after deleting it in claude agents
  • Fixed session cost not showing for usage-based Enterprise and Team subscribers
  • Fixed agent teams: teammates spawned via tmux/pane backends now inherit the leader's --effort level
  • Fixed Workflow agent({schema}) subagents looping forever on repeated schema validation failures instead of aborting after 5 attempts
  • Improved claude mcp get and claude mcp remove to suggest the closest configured server name on a typo and truncate long server lists
  • Improved memory: the agent is now reminded to compact its MEMORY.md index when nearing the size limit
  • Improved skill frontmatter: display-name, default-enabled, fallback, and metadata.* keys now accept kebab-case, snake_case, and camelCase
  • Improved malformed SKILL.md YAML frontmatter handling: loads the skill body with empty metadata instead of failing silently
  • Changed CLAUDE_CODE_MAX_RETRIES to cap at 15; for unattended sessions, use CLAUDE_CODE_RETRY_WATCHDOG instead
  • Changed background subagents to surface permission prompts in the main session instead of auto-denying; the dialog shows which agent is asking, and Esc denies just that tool
  • Changed /review <pr> to use the same review engine as /code-review medium

Notes

Background subagent permissions are no longer silently auto-denied. Before 2.1.186, any tool call requiring permission inside a background subagent was automatically denied without surfacing to the user. This meant background agents could silently fail on operations that needed approval. The new behavior bubbles these prompts up to the main session, which is a meaningful workflow change if you run background agents that hit permission boundaries (file writes outside the project, network calls, destructive git operations). If you see unexpected permission dialogs appearing mid-session, this is why.

CLAUDE_CODE_MAX_RETRIES cap continues the shift toward RETRY_WATCHDOG for unattended use. The MAX_RETRIES env var was previously unbounded, letting headless pipelines retry indefinitely. The cap at 15 means any value above that is silently clamped. CLAUDE_CODE_RETRY_WATCHDOG (introduced in an earlier release) is the intended replacement for unattended sessions, offering a timeout-based approach rather than a count-based one.