aiqbench analysis
Claude Code's auto-mode safety checks are moving from the client to Anthropic's API, and gateways like LiteLLM must forward the new request and response fields unchanged for that to work. Teams running Claude Code behind a gateway, especially on Enterprise or API-key accounts, should confirm their LiteLLM version includes the fix before the September 25 default-mode change. The piece is a vendor-adjacent rollout note, so the timelines and behavior described should be checked against Anthropic's own documentation.
Claude Code server-side auto mode through LiteLLM

From LiteLLM Blog
ExcerptAnthropic is moving Claude Code auto mode's safety classifier to server side. LiteLLM's native /v1/messages route now passes the safety contract through to the Anthropic API, Bedrock InvokeModel, Bedrock Mantle and Vertex AI. Here's the contract, what's changed, which releases have it, and how to verify it.
Anthropic is moving Claude Code auto mode's safety classifier from the client to the Claude API. Starting with Claude Code v2.1.278, released September 19, sessions on Enterprise plans and Claude API accounts ask the server to run those checks as part of their own model requests, and Anthropic does not charge for the checks when the server performs them. Anthropic told us the rollout started on September 18 and is gradual, beginning with the Claude Code CLI and VS Code extension and followed by the desktop app and Claude Code on the web over the following week, and that on September 25 auto mode becomes the default permission mode in Claude Code.
Today the built-in default is auto on Pro, Max and Team plans and Manual on Enterprise plans and Claude API keys, the accounts that typically sit behind a gateway, per Anthropic's permission modes reference.
Server-side auto mode depends on a contract between Claude Code and the API that some gateways did not preserve, LiteLLM included.
Excerpt shown under the publisher's RSS terms · 167 words · full text and figures are on the publisher's site