Claude Code 2.1.211 Released
ClaudeCodeLog · x · 2026-07-16
Claude Code 2.1.211 has been released, bringing 37 CLI changes. Key updates include:
- Added --forward-subagent-text and environment variables to write subagent text and thought processes into stream-json output, making it easier for downstream systems to receive sub-agent results.
- During permission previews, bi-directional control characters, zero-width characters, and similar quotes are sanitized to reduce approval deception caused by "visual spoofing."
- Auto mode no longer overrides the ask decision from the PreToolUse hook for unsandboxed Bash; the hook will now force a prompt.
- Also fixed issues like multiple sessions disconnecting simultaneously, plugin MCP servers failing to reconnect after idle, and incorrectly attempting to default to the Opus model when starting Vertex/Bedrock.
Related event: Claude Code 2.1.211 Update Enhances Subagent Workflows(4 posts)→
More from coding & agent
- Dev builds talk on guardrails workflow for shipping AI-written code without reading it — TejasKumar_ · 2026-09-11
- banteg: Codex auto-review has regressed, blocking steps needed to complete authorized tasks — banteg · 2026-09-11
- A doc-anchored agent workflow: you write, the agent only critiques and finds disagreements — lucasmeijer · 2026-09-11
- SymKit MCP: 44 tools for AI agents to verify symbolic derivations — Foreign-Specific-604 · 2026-09-11
- GitHub Copilot team routes user bug reports to an AI agent via Slack — marlene_zw · 2026-09-11
- Scanning 23 agent sessions, a dev found 3 silent failure modes in memory systems — No_Advertising2536 · 2026-09-11