Claude Code v2.1.217: Subagent Depth Cap, Emoji Autocomplete, and Critical Fixes
Anthropic released Claude Code v2.1.217 with notable changes to subagent governance, a long-requested emoji autocomplete feature, and a dozen bug fixes addressing memory leaks, session isolation, and Windows auto-update corruption.
Subagent Controls
The release introduces two environment variables to prevent runaway background agents:
CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS(default: 20) — caps how many subagents can run in parallel from a single message.CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH— subagents no longer spawn nested agents by default. Set this to allow deeper nesting.
Also, --max-budget-usd now stops background subagents: once the budget cap is hit, new spawns are denied and running background agents are halted.
Emoji Autocomplete
You can now type :heart: to insert ❤️, or :hea for suggestions. Disable with the emojiCompletionEnabled setting.
Notable Bug Fixes
- Memory leak fixed — truncated MCP tool outputs no longer keep the full untruncated result in memory for the rest of the session.
- Windows auto-update corruption — failed updates that could leave
claude.exemissing now restore the preserved executable automatically. - Background session isolation — symlinked working directories are now canonicalized, preventing sessions from escaping their workspace folder.
- Claude Opus 4.8 on Bedrock — auto-compact now triggers properly, and
/compactno longer fails once over the limit. - Corporate settings — mTLS, TLS-verify, OAuth scope, and proxy settings are now respected in Claude Desktop sessions.
- Screen reader mode — startup announcement no longer cut off, and the thinking status row re-renders efficiently.
- Telemetry routing — managed
OTEL_EXPORTER_OTLP_ENDPOINTnow governs all signals; lower-scope overrides no longer redirect telemetry away. - Transcript handling —
--resumeand/resumeno longer crash with malformed attachment entries; warnings added when transcript writes fail (e.g., disk full). - Remote Control — permission prompt now shows to viewers that connect after the prompt appears.
- Brace expansion —
CLAUDE.md/SKILL.mdpaths with many brace groups no longer OOM-kill the CLI; expansion is now budget-bounded. - Footer links — PR badge links are clickable hyperlinks even over ssh/tmux; set
FORCE_HYPERLINK=0to opt out.
Other Changes
- Login-expiry warning moved from 5 to 3 days before expiry.
- Frontend-design plugin suggestion tip capped at 3 lifetime impressions.
- Transcript preview gap fixed when attaching to a starting background session.
📖 Read the full source: GitHub Claude-Code
👀 See Also
Outworked v0.3.0 adds iMessage support, built-in browser, and scheduling for Claude Code agents
Outworked v0.3.0 introduces iMessage channel support for agent communication, a built-in browser for web interaction, scheduling via cron, tunneling for local sharing, and enhanced MCP/Skills support. The desktop app orchestrates Claude Code agents as a team to handle coding tasks, web research, and automated workflows.
AI Writes Dead Code? The Go Team's deadcode Tool Finds It in One Command
AI coding agents often leave dead code behind. The Go team's deadcode tool scans your entire module and reports unreachable functions in one command — here's how to run it.
Kstack: Skill Pack for Claude Code to Monitor and Troubleshoot Kubernetes
Kstack is an open-source skill pack that adds slash commands like /investigate, /audit-security, and /cluster-status to Claude Code (and other AI agents) for monitoring and troubleshooting K8s clusters. It uses kubectl, Kubetail, Trivy, and Pluto behind the scenes.
quorum: AI Code Governance Tool Enforces Independent Model Review
quorum is a governance layer for AI-assisted development that enforces a consensus protocol requiring code to be independently reviewed by a different model before committing. It includes three structural gates that block progress: audit, retro, and quality gates.