Claude Code v2.1.278 Defaults Auto Mode to Server-Side Classifier
Claude Code v2.1.278 changes how auto mode picks its classifier. For Claude API and Enterprise users, plus anyone running on Bedrock, Vertex, Foundry, or gateways, auto mode now defaults to the server-side classifier. The practical upside: that path does not charge for classifier overhead.
What changed
- Server-side classifier is now the default for Claude API users, Enterprise users, and deployments on Bedrock, Vertex, Foundry, and gateways.
- No billed classifier overhead on that server-side path.
- Opt-out flag:
CLAUDE_CODE_AUTO_MODE_SERVER=0disables the server-side classifier on Bedrock, Vertex, Foundry, and gateways. - Billed fallback warning: the CLI warns you when it falls back to a path that bills for classifier work.
Checking which classifier your session uses
v2.1.278 adds an Auto mode server row to the /status output. Run /status in a session and you can see whether that session's auto mode classifier is running on the server or falling back locally. Useful when you're debugging cost or behavior differences across environments.
Opting out
If you're on Bedrock, Vertex, Foundry, or a gateway and want to keep the client-side classifier, set the environment variable before launching:
CLAUDE_CODE_AUTO_MODE_SERVER=0 claude
Per the release notes, this opt-out applies to those four deployment paths specifically; Claude API and Enterprise users get the server-side classifier by default.
Billing details
The release points to Anthropic's docs for the full billing behavior of the auto mode classifier: https://code.claude.com/docs/en/auto-mode-classifier-billing. If you're tracking per-token or per-request costs on a gateway or cloud marketplace deployment, read that page before flipping the env var — the whole point of the default change is that the server-side path is the cheaper one.
Who this matters for
Anyone running Claude Code auto mode through Bedrock, Vertex, Foundry, or a self-managed gateway, and Enterprise accounts watching classifier line items on their bill.
📖 Read the full source: GitHub Claude-Code
👀 See Also
Claude Code v2.1.139 Adds Agent View, /goal Command, and Major MCP Improvements
Claude Code v2.1.139 introduces a new agent view for session management, a /goal command for multi-turn tasks, expanded hook capabilities, and fixes for MCP server memory issues and terminal corruption.
Claude Loses Ability to Retrieve Product Pricing Across Retailers
As of April 27, Claude no longer returns pricing for Amazon, Best Buy, Newegg, or B&H Photo. Walmart is the only retailer still showing prices.
Mercor Breach: 4TB of Voice Samples + IDs Stolen – What Attackers Can Do Now
4TB of voice recordings paired with government IDs stolen from 40,000 Mercor contractors. Attackers can clone voices from 15 seconds of clean audio and bypass bank voiceprint verification, deepfake calls, and insurance fraud.
Terry Tao on AI Proof Checkers: Lean, Collaboration, and Formal Maths
Terry Tao predicts mathematicians will collaborate in hundreds and have proofs checked by computers like Lean, not humans. A Quanta Magazine excerpt explores this vision.