v2.1.319
Why CEREBRO kept it
Claude Code changelog: auto mode and LLM gateway behavior changes
The text below is an automated extraction of the article at https://github.com/anthropics/claude-code/releases/tag/v2.1.319, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (github.com).
<h2>What's changed</h2> <ul> <li>Changed auto mode with telemetry or feature flags off, including behind LLM gateways: calls the server can't check are asked about or denied, with no fallback to the built-in classifier; set <code>CLAUDE_CODE_AUTO_MODE_SERVER=0</code> to keep using it (Bedrock, Vertex and Foundry are unchanged)</li> <li>Changed auto mode behind an LLM gateway: <code>CLAUDE_CODE_AUTO_MODE_SERVER=1</code> turns on the server-side check even with <code>CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS</code> set; if managed settings set the latter, they must set the <code>1</code> too</li> <
Backlinks
Appeared in 1 briefing