Claude Code v2.1.206: /doctor Trims CLAUDE.md, /commit-push-pr Auto-Allow Git Push, Background Agent Upgrade

Anthropic shipped Claude Code v2.1.206 with a stack of quality-of-life improvements and critical fixes for MCP servers, background agents, and git integrations.
New Features
/cdpath suggestions: The/cdcommand now shows directory path completions, matching/add-dirbehavior./doctortrim proposal: A new check suggests cutting content from checked-inCLAUDE.mdfiles that Claude can derive directly from the codebase./commit-push-prauto-allow git push: Now automatically allowsgit pushto the repo's configured push remote (remote.pushDefault, or the sole remote when only one is configured) in addition toorigin.- Gateway
/login: Now supports Anthropic-operated public gateway endpoints. - EnterWorktree confirmation: Prompts before entering a git worktree outside
.claude/worktrees/. - Background agent upgrade: Background agents now upgrade in the background immediately after a Claude Code update, avoiding the slow stale-session upgrade on attach.
Fixes
- Expired login error message — now properly prompts for
/logininstead of showingThere's an issue with the selected model
. claude --resume/--continue— keyboard input now works on startup.- MCP
request_timeout_ms— per-server timeout settings from--mcp-configor.mcp.jsonare now respected; long-running MCP tool calls no longer time out at the 60s default in fresh sessions. CLAUDE_CODE_EXTRA_BODY— now correctly passed toclaude agents/--bgbackground workers.- OAuth MCP servers — no longer require manual re-authentication after a single failed token refresh.
--permission-prompt-tool— no longer crashes withMCP tool not found
on cold start before the server connects./modelpicker — fixed rows showing wrong price, stopped quoting first-party list prices on providers that don't bill them, and fixed misplaced server-provided rows when entitlement/allowlist restrictions drop a reference row.- Desktop sessions — no longer stuck showing
running
after mid-turn slash commands. - Windows agents view — keyboard input no longer ignored when a setup prompt appears before bare
claude --resume. claude rm— now properly removes the job from the daemon roster; deleted jobs stay deleted./remote-control— now explains how to sign in instead of showingUnknown command
when logged out.- Left arrow — now steps back out of a phase or agent in the workflow detail view.
/status— no longer lists the same broken-install warning twice.- LSP plugins — false
disused plugin
tips and skewed telemetry fixed. /doctorupdate check — for Homebrew installs, now compares against the cask's channel instead of the settings channel.- Fullscreen jump-to-bottom pill — fixed Ctrl+End suggestion on macOS, rebound chords now show, and the pill no longer wraps over the transcript.
- Bedrock — fixed multi-minute startup hang when using
awsCredentialExporthelper on networks with restricted egress.
Improvements
/code-review— findings quality improved onclaude-opus-4-8across all effort levels.- Agents view status column — now uses full terminal width instead of truncating at 64 characters.
- Ctrl+X in agents view permanently removes a completed session; deleted background jobs stay deleted. Sessions no longer render twice.
📖 Read the full source: GitHub Claude-Code
👀 See Also

Constrails: Early-Alpha External Governance Layer for AI Agents
Constrails is an external runtime governance layer for AI agents that places a control layer between agents and their tools, implementing capability checks, risk scoring, policy evaluation, and audit logging. The early-alpha project aims to address safety concerns by moving controls outside the agent itself.

Comparing Multi-Agent AI Systems: Anthropic's Harness vs Agyn's Engineering Org Model
Anthropic published a harness design for long-running application development, while Agyn's multi-agent system for team-based autonomous software engineering was open-sourced last month. Both systems reject monolithic agents in favor of role separation, structured handoffs, and review loops.
Multi-Agent Memory: Open Source Shared Memory System for AI Agents
Multi-Agent Memory is an open source project that provides a shared memory system for AI agents across different machines, tools, and frameworks. It supports four distinct memory types with specific behaviors and includes features like credential scrubbing, agent isolation, and LLM consolidation.

SIDJUA v0.9.7: Open Source Multi-Agent AI with Pre-Action Governance Enforcement
SIDJUA v0.9.7 is a self-hosted, open source multi-agent AI framework that enforces governance rules before agents act, blocking unauthorized actions like budget overruns or scope violations. It supports multiple LLM providers, runs on 4GB RAM, and includes a desktop GUI built with Tauri v2.