Anthropic shipped Claude Code version 2.1.218 with a significant behavioral change: /code-review now runs as a background subagent so review work no longer occupies the main conversation thread. The release includes accessibility improvements for screen-reader users, a fix for Windows paths with Unicode prefixes being corrupted into CJK characters, and a large set of bug fixes spanning MCP server diagnostics, multi-line paste handling, Bedrock spend metering, agent trust model enforcement, and session/compaction reliability. Several auto-mode permission dialog behaviors were also tightened, with the auto-mode classifier now adjudicating dangerous-command checks instead of opening dialogs.
Anthropic released Claude Code version 2.1.210, a substantial patch addressing over 30 bugs and adding several improvements to the agentic coding tool. Notable fixes include hardening against indirect prompt injection via subagent-read content, correcting git worktree isolation for subagents, fixing hook callback timeouts that caused unattended sessions to stall, and resolving MCP server teardown during mid-session re-syncs. The release also improves auto-mode permission classification by defaulting to Sonnet 5 for external sessions and adds UX enhancements for the multi-agent dashboard.
Anthropic released Claude Code version 2.1.208, a substantial patch addressing dozens of bugs and adding several new features. Key additions include screen reader accessibility mode, vim insert-mode remapping, and a corporate process wrapper for enterprise deployments. The release fixes significant issues including memory leaks in long sessions, background agent reliability problems, streaming output truncation, and multi-second per-turn slowdowns from permission rule matching, alongside performance improvements yielding up to 7x faster tool rounds at high MCP tool counts.
Anthropic released Claude Code version 2.1.203, a substantial patch addressing over 25 bugs primarily affecting background agent sessions, subagent orchestration, and worktree isolation. Key fixes include automatic recovery when daemon session tokens go stale, correct subagent state carry-over when returning to sessions, and PATH/environment variable inheritance issues on Windows. The release also adds MCP roots/list integration for working directories and improves streaming responsiveness.
Anthropic released Claude Code version 2.1.211 with a new --forward-subagent-text flag to expose subagent thinking in stream-json output, and a significant security fix neutralizing bidirectional-override and zero-width characters in permission previews that could visually alter approval messages. The release also fixes a prompt-caching regression on Bedrock, Vertex, Mantle, and Foundry that was incorrectly billing trailing system context blocks as fresh input tokens on every request. Dozens of additional bug fixes address session management, background agent lifecycle, Windows compatibility, MCP reconnection, and rendering performance.
Anthropic released Claude Code version 2.1.217 with a notable new cap on concurrently-running subagents (default 20, configurable via CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS) and a change preventing nested subagent spawning by default. The release also fixes a memory leak in MCP tool output handling, resolves auto-compact failures for Claude Opus 4.8 on Bedrock, and patches several Windows, corporate proxy/TLS, and session isolation bugs. The subagent concurrency and budget enforcement changes are architecturally significant for agentic workflows, preventing unbounded fan-out.
Anthropic shipped Claude Code version 2.1.212 with several notable behavioral changes: /fork now copies conversations into independent background sessions (previously launched in-session subagents), and new per-session caps on WebSearch calls (default 200) and subagent spawns (default 200) guard against runaway loops. MCP tool calls exceeding 2 minutes are automatically backgrounded to keep sessions responsive. The release also includes roughly 40 bug fixes spanning plan-mode permission bypasses, SIGTERM process-tree orphaning, Windows PowerShell compatibility, /ultrareview edge cases, OpenTelemetry export failures, and prompt caching improvements for LLM gateways.
Anthropic released Claude Code version 2.1.206 with a range of new features and bug fixes. Notable additions include background agent auto-upgrade after Claude Code updates, /login support for Anthropic-operated public gateway endpoints, /doctor checks for trimming CLAUDE.md files, and auto-allow for git push to configured remotes in /commit-push-pr. The release also fixes numerous bugs including MCP server timeout handling, OAuth re-authentication loops, model picker pricing display errors, and a multi-minute Bedrock startup hang on restricted networks.
Anthropic released Claude Code version 2.1.200 with a notable default behavior change: the permission mode now defaults to 'Manual' across CLI, VS Code, and JetBrains integrations, replacing the previous auto-continue behavior for AskUserQuestion dialogs. The release includes extensive fixes for background agent reliability issues including daemon lock conflicts, session stalls after sleep/wake cycles, rate-limit handling, and MCP server configuration errors. Accessibility improvements for screen readers and terminal rendering fixes under tmux 3.4+ are also included.