Claude Code 2.1.206 has been released. 27 CLI changes Highlights: • Security help restricted to authorized/educational use; DoS, supply-chain and evasion requests are refused • Background agents auto-upgrade after Claude Code updates to avoid slow stale-session upgrades on attach • Expired logins now prompt to run /login instead of a misleading model error, showing correct auth guidance Complete details in thread ↓

Claude Code CLI 2.1.206 changelog: New features: • Added directory path suggestions to /cd, matching /add-dir behavior • Added a /doctor check that proposes trimming checked-in CLAUDE.md files by cutting content Claude could derive from the codebase Fixes: • Fixed an expired login failing every model with a misleading "There's an issue with the selected model" error instead of prompting to run /login • Fixed claude --resume and --continue not responding to keyboard input on startup • Fixed MCP servers configured via --mcp-config or .mcp.json ignoring a per-server request_timeout_ms, which caused long-running MCP tool calls to time out at the 60s default in fresh sessions • Fixed CLAUDE_CODE_EXTRA_BODY being silently ignored by claude agents / --bg background workers; the shell-exported override now follows the dispatching session • Fixed OAuth MCP servers requiring manual re-authentication after a single failed token refresh • Fixed --permission-prompt-tool pointing at an MCP server crashing with "MCP tool not found" on cold start before the server finishes connecting • Fixed /model picker rows printing a price for a different model than the row named, and stopped quoting first-party list prices on providers that don't bill them • Fixed server-provided model rows being misplaced in the /model picker when an entitlement or allowlist restriction drops the row they were positioned against • Fixed desktop sessions getting stuck showing "running" after a slash command was sent mid-turn • Fixed keyboard input being ignored in the agents view when a setup prompt appeared before a bare claude --resume on Windows • Fixed claude rm leaving the removed job in the daemon roster, causing the row to reappear in claude agents • Fixed /remote-control showing "Unknown command" when logged out — it now explains how to sign in • Fixed left arrow not stepping back out of a phase or agent in the workflow detail view • Fixed /status listing the same broken-install warning twice • Fixed false "disused plugin" tips and skewed disuse telemetry for LSP plugins • Fixed /doctor's update check to compare Homebrew installs against their cask's channel instead of the settings channel • Fixed the fullscreen jump-to-bottom pill suggesting Ctrl+End on macOS, not showing rebound chords, and wrapping over the transcript • Bedrock: fixed a multi-minute startup hang when using an awsCredentialExport helper on networks with restricted egress Improvements: • Improved /code-review findings quality on claude-opus-4-8 across all effort levels • Improved agents view: status column now uses full terminal width instead of truncating at 64 characters Other changes: • /commit-push-pr now auto-allows git push to the repo's configured push remote (remote.pushDefault, or the sole remote when only one is configured) in addition to origin • Gateway: /login now supports Anthropic-operated public gateway endpoints • EnterWorktree now asks for confirmation before entering a git worktree outside the project's .claude/worktrees/ directory • Background agents now upgrade to a new version in the background right after a Claude Code update, instead of paying a slow stale-session upgrade when you attach • Changed agents view: Ctrl+X now permanently removes a completed session, and sessions no longer render twice; deleted background jobs stay deleted Source: #21206" target="_blank" rel="nofollow noopener">github.com/anthropics/cla…

Claude Code 2.1.206 further changes CLI surface: Added: • env vars: CLAUDE_BRIDGE_REATTACH_GROUPING, CLAUDE_CODE_REFUSAL_FALLBACK_CATCH_ALL, CLAUDE_INTERNAL_FC_OVERRIDES Removed: • env vars: CLAUDE_CODE_VERIFY_PROMPT File: #diff-662031a066e433468319e799350331e143e4635468b9c2924019d16654027e31L7-R7" target="_blank" rel="nofollow noopener">github.com/marckrenn/clau… Metadata: • Time since 2.1.205 release: 7h 59m 25s • Bundle file size: +440.4 kB (+1.3%) • Prompt files: +3 (+6.2%) • Prompt tokens: +12,320 (+10.3%) Prompt token mix by kind: • system-reminder: 57.3%→57.5% • tools: 42.0%→41.8% • system: 0.5%→0.4% • agent: 0.3%→0.2% Files: • metadata: #diff-a08dfa163baef97ea4f56d29009ac65f5f7dbc46e3a58e80d7aa06a2a2520899L10-R10" target="_blank" rel="nofollow noopener">github.com/marckrenn/clau… • prompt stats: #diff-fa8e31336ece71d159f37b6fd4ed0c61939849140bd5c08c7ca793b5b2ae7f58L1-R1" target="_blank" rel="nofollow noopener">github.com/marckrenn/clau… Other prompt/string highlights: 1) Clarified grep's help text to note it's ripgrep-based, recommend using Grep for searches, and explain output_mode, head_limit, and offset behavior. Links: 1) #diff-98f084cc9ae739dcef3d2c75ea5cf55429dbb647973737f30693e59689d25d58R3" target="_blank" rel="nofollow noopener">github.com/marckrenn/clau… More details: github.com/marckrenn/clau…

@ClaudeCodeLog the /doctor check that trims CLAUDE.md to what the model cant already infer is the sleeper feature here. every rule you keep fires on every single turn, so a doc that looks harmless is a standing token bill.