Follow Discord
Sweep 01 Oct 2026 · 17:27Z Build v2.1.287 508 read Stable v2.1.285 Latest v2.1.287 Next v2.1.287 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.286 ·

Built-in gateway documentation updated for unknown fields, auto-mode safeguards and managed settings

Gateway docs inside Claude Code now say to ignore unknown input, describe auto-mode safeguards fields, and change the managed settings response format

Group of 2 You'll notice Improvements
JSON All of v2.1.286
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
GatewaysArea: what it touches
ImprovementsKind: in v2.1.286,
ImprovementsSection of the release

What

Claude Code includes documentation for people running a sign-in server or an LLM gateway, a server that sits between Claude Code and the model. That text changed:

  • Servers must ignore request parameters, body fields and headers they do not recognize ("Don't reject what you don't recognize."). They should pass body fields and anthropic-beta values through unchanged.
  • In auto mode, the client adds an anthropic-beta value and a top-level safeguards field to requests, and reads safeguard_results from responses. A gateway that does not support this should answer with a 400 error naming safeguards.
  • The managed settings response is now wrapped as {uuid, checksum, settings}, with a sha256 checksum used for If-None-Match and 304 (not modified) replies. Before, the documentation described returning the bare managed-settings.json with an ETag.

Why

If you run a gateway, requests can carry fields your server has not seen before and should not be rejected. The findings suggest a managed settings response in the old shape may be treated as a failed fetch.

See this entry in the whole of v2.1.286 →

Feedback