Claude Code v2.1.211: Subagent Text Forwarding, Permission Fixes, and Vim Mode Changes

Claude Code v2.1.211 is out with a mix of new features, security fixes, and quality-of-life improvements. The headline addition is the --forward-subagent-text flag (and corresponding CLAUDE_CODE_FORWARD_SUBAGENT_TEXT environment variable) that includes subagent text and thinking in stream-json output — useful for headless or scripted workflows that need visibility into subagent reasoning.
Key Changes
- Subagent text forwarding: New flag
--forward-subagent-text/ env varCLAUDE_CODE_FORWARD_SUBAGENT_TEXTincludes subagent text and thinking in stream-json output. - Security fix for permission previews: Permission previews relayed to chat channels now neutralize bidirectional-override, zero-width, and look-alike quote characters, preventing tool inputs from visually altering the approval message.
- PreToolUse hook 'ask' decision honored: Auto mode no longer overrides a PreToolUse hook's
askdecision for unsandboxed Bash. A hookasknow floors the decision at a prompt. - Subagent model override persistence: Subagents spawned with an explicit model override no longer revert to the parent's model when resumed or sent a follow-up message.
- Vim mode improvements:
sandS(substitute char/line) now work in NORMAL mode, matching vim behavior. - Session cost reset:
/clearnow resets the session cost counter — the statusline's cost starts at $0 after/clear. - Integer env vars: Environment variables for timeouts, token budgets, and retry counts now accept scientific notation and digit separators like
1e6and64_000. - Background agent reporting: Improved — Claude now reports the status of still-running agents and waits for real completion instead of fabricating results.
- Prompt caching regression fixed: Fixed a caching regression on Bedrock, Vertex, Mantle, and Foundry that billed the trailing system context block as fresh input tokens on every request.
- File upload validation: Filenames ending in DOS device suffix (
.prn) or trailing dot are now accepted; files with multiple hard links are refused. - Always allow rules: Permission rules now save at the repository root, so approvals granted in a git worktree persist across sessions and worktrees.
This release also fixes a number of edge cases: parallel sessions logging out after wake-from-sleep, plugin MCP servers not reconnecting after idle web sessions, subagent model overrides reverting, nested .claude/rules/*.md files loading when excluded, and more.
For VSCode users, the Remote Control banner has been updated to clarify what it does. Claude in Chrome gets hardened file-upload path validation and a working save_to_disk on screenshot actions (now writes the image to disk and returns the path).
If you're using Claude Code on Vertex or Bedrock, note the fix for a spurious fallback notice when a model is explicitly configured — the client no longer attempts the default Opus model at startup.
📖 Read the full source: GitHub Claude-Code
👀 See Also

Claude-Code v2.1.74 Release: Memory Leak Fixes, Context Optimization, and Plugin Improvements
Claude-Code v2.1.74 fixes a critical memory leak in streaming API responses that caused unbounded RSS growth on Node.js/npm code paths. The update adds actionable suggestions to the /context command and introduces the autoMemoryDirectory setting for custom auto-memory storage.

OpenClaw 0.9 CLI Removal Causes Agent Disruption
A user reported that attempting to update OpenClaw via an AI agent resulted in the CLI being removed, breaking gateway commands and Telegram chat functionality. OpenClaw 0.9 dropped the CLI entirely, removing commands like 'openclaw gateway start' and 'openclaw status'.

Claude Code v2.1.199 Patches 20+ Bugs: SSL, Subagents, Daemon Crashes Fixed
Claude Code v2.1.199 fixes SSL certificate errors, subagent silent failures, a Linux daemon crash loop, and 20+ other bugs. Key fixes include immediate SSL error hints, partial stream retention, and subagent error propagation.

Anthropic's circuit-tracing research reveals Claude 3.5 Haiku's internal mechanisms
Anthropic published circuit-tracing research on a simplified Claude 3.5 Haiku, revealing six specific behaviors including its default "I don't know" state, backward poem writing, and dual-path math processing.