Claude Code 2.1.273
By Steven Van ·
Claude Code 2.1.273 adds LLM gateway request headers, MCP disconnect alerts, remote-control session forking, and several permission and error-message fixes.
Claude Code 2.1.273 adds request headers for LLM gateways: x-claude-code-request-class, x-claude-code-agent-type, x-claude-code-prev-tool-durations, x-claude-code-compaction and x-claude-code-context-compacted. They are off by default; set CLAUDE_CODE_GATEWAY_HINT_HEADERS=1 to enable them.
Other changes in this release of Claude Code:
- A notification now appears when an MCP server disconnects mid-session and automatic reconnection gives up, pointing to /mcp.
- A session started with claude --remote-control or /remote-control can now be forked from the Claude app, with the fork running as a background session on your computer.
- Bash commands the permission checker cannot fully analyze no longer skip the prompt under permissions.blockReadsOutsideWorkingDirectories, and a subshell can no longer hide a dangerous rm in bypass mode.
- Skills synced from claude.ai now move to the recoverable trash, rather than staying available, when an organization turns Skills off.
- allowManagedMcpServersOnly, deniedMcpServers and disableClaudeAiConnectors set via MDM or managed-settings.json are no longer ignored when server-managed settings are also present.
- 401/403 errors on Bedrock, Vertex and Foundry, and Claude apps gateway 403s, now name the credential to refresh or point to your gateway admin, instead of telling you to run /login.
Full details are in the changelog.
Claude Code
Anthropic's agentic coding tool — Claude in your terminal, IDE, desktop app and browser, reading and editing your codebase, running commands, opening pull requests and working on tasks in the cloud.
View Claude Code →