Claude Code v2.1.166: Fallback Models, Glob Deny Rules, Cross-Session Hardening

Claude Code v2.1.166: Fallback Models, Glob Deny Rules, Cross-Session Hardening

Anthropic released Claude Code v2.1.166 with several notable improvements for reliability, security, and terminal compatibility. Here's what changed.

Key Features

• Fallback models: The new fallbackModel setting lets you configure up to three fallback models tried in order when the primary model is overloaded or unavailable. The --fallback-model CLI flag now also applies to interactive sessions. Additionally, Claude Code retries a turn once on the fallback model when the API rejects an unexpected non-retryable error (auth, rate-limit, request-size, and transport errors still surface immediately).
• Glob pattern support in deny rules: The tool-name position in deny rules now supports glob patterns — using * denies all tools. Allow rules reject non-MCP globs, and unknown tool names in deny rules warn at startup.
• Hardened cross-session messaging: Messages relayed via SendMessage from other Claude sessions no longer carry user authority. Receivers refuse relayed permission requests, and auto mode blocks them entirely.
• Thinking token control: Setting MAX_THINKING_TOKENS=0, passing --thinking disabled, or toggling the per-model thinking toggle now disables thinking on models that think by default via the Claude API (third-party providers unchanged).
• Update UX improvement: claude update now announces the target version before downloading.
• Agent list filtering: In claude agents, typing a URL into the list filters to the session whose first prompt contained that URL.

Bug Fixes

• Fixed recurring "image could not be processed" error and extra token usage when an unprocessable image was sent.
• Fixed remote sessions permanently stuck after a brief backend disruption during worker registration at startup.
• Fixed flickering in JetBrains IDE terminals (IntelliJ, PyCharm, WebStorm etc.) on 2026.1+ by enabling synchronized output.
• Fixed Shift+non-ASCII characters (e.g. Shift+ä → Ä) being dropped in terminals using the Kitty keyboard protocol (WezTerm, Ghostty, kitty).
• Fixed PowerShell command validation occasionally hanging far past its time budget on Windows when a killed process's children held its output pipes.
• Fixed orphaned claude --bg-pty-host processes spinning at 100% CPU after the daemon dies while connected on macOS.
• Fixed voice mode requiring /login to clear a stale auth check after toggling /voice.
• Fixed managed settings with an invalid entry silently disabling enforcement of remaining valid policies.
• Fixed managed-settings allowedMcpServers / deniedMcpServers predicates not matching when they use ${VAR} references.
• Fixed background agent sessions that entered a git worktree crash-looping with "No conversation found" when reopened from claude agents.
• Fixed duplicated thinking text in the Ctrl+O transcript view while streaming.
• Fixed /doctor showing a contradictory failed "Not inside a remote session" check when run inside a remote session.
• Fixed the cursor sticking at the end of the first line when typing a multiline prompt in the claude agents dispatch and reply inputs.
• Fixed blank lines appearing between background agent rows in the task list on terminals without Unicode support.

Who It's For

Anyone using Claude Code for agentic coding, especially those relying on API reliability, custom deny rules, or multi-session orchestration.