Claude Code v2.1.299 · 14 Oct 2026

Managed settings can hold their CLAUDE_CODE_ATTRIBUTION_HEADER value against a host program

Under some conditions, the managed-settings value of CLAUDE_CODE_ATTRIBUTION_HEADER now wins over one passed in by the program that starts Claude Code

You'll notice Improvements

JSON All of v2.1.299

You'll noticeTier: how much it should matter to you

2Useful: my rating, 1 to 5

2Signal: worth watching, 1 to 5

Managed SettingsArea: what it touches

ImprovementsKind: in v2.1.299, 14 Oct 26

ImprovementsSection of the release

Unclear The conditions under which the managed value wins are not stated.

What

CLAUDE_CODE_ATTRIBUTION_HEADER controls whether Claude Code includes the attribution block. Managed settings are settings an organisation's administrator puts on a machine. When another program starts Claude Code and passes in its own environment variables, the managed-settings value of CLAUDE_CODE_ATTRIBUTION_HEADER can now win over the value that program supplies, when certain conditions hold. Before, there was no such exception.

Why

Administrators can fix this setting so that programs which launch Claude Code cannot change it.

Read from

Names in the bundleCLAUDE_CODE_ATTRIBUTION_HEADER

How sure we are

Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.

The writer flagged doubtThe conditions under which the managed value wins are not stated.

Anthropic's release notes agreeAdded support for turning off the attribution block in Claude Desktop's Code tab: set CLAUDE_CODE_ATTRIBUTION_HEADER=0 in the env of a…

See this entry in the whole of v2.1.299 →

The build it came inv2.1.299

14 Oct 2026 · 439 entries, this one is #141.

Use it now28
You'll notice272
Nothing to try yet19
Under the hood120

Either side of it

v2.1.296Older
v2.1.300Newer

Open the release →

Names in this entry

envCLAUDE_CODE_ATTRIBUTION_HEADER
Set to 0 to omit the attribution block, which carries the client version and a prompt fingerprint, from the start of the system prompt. Caching on a direct connection to the Anthropic API is unaffected either way. In some direct-connection setups, Claude Code keeps the block on auto mode classifier requests even when you set 0. In System prompt attribution block, check which connections and credentials this covers. Before v2.1.181 the block included a per-request token on custom base URLs and Microsoft Foundry connections, so on those versions set it to 0 when your LLM gateway caches on the request body or forwards requests to a third-party provider, or when you connect to Microsoft Foundry directly

Anthropic's notes

Upstream's own release notes for v2.1.299 name something this entry names, so the two are probably about the same change. Probably: the pairing is made on a shared name rather than on the words around it.

Added support for turning off the attribution block in Claude Desktop's Code tab: set CLAUDE_CODE_ATTRIBUTION_HEADER=0 in the env of a Claude apps gateway's code policy
Added a field to the attribution block in Claude Code sessions behind a Claude apps gateway; remove the block with CLAUDE_CODE_ATTRIBUTION_HEADER=0

Is this right?

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

v2.1.227 Billing attribution header carries a prompt id and validates its values
Both mention attribution header
v2.1.229 Attribution header can override the environment opt-out
Both mention attribution header
v2.1.229 Auto-mode side queries always send the billing attribution header
Both mention attribution header