Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeReleasesv2.1.302entry #15

Claude Code v2.1.302 ·

CLAUDE_CODE_AUTO_MODE_MODEL can now be overridden by server settings or policy

The model you pin with CLAUDE_CODE_AUTO_MODE_MODEL for auto mode's safety check is ignored, with a warning, when server or policy says otherwise

You'll notice Improvements
JSON All of v2.1.302
You'll noticeTier: how much it should matter to you
3Useful: my rating, 1 to 5
4Signal: worth watching, 1 to 5
Auto ModeArea: what it touches
ImprovementsKind: in v2.1.302,
What probably matters to youSection of the release
What

In auto mode, Claude acts without asking you each time, and a classifier checks whether each action is safe. A classifier is a model that sorts actions into safe or not. Claude Code now picks the classifier's model in this order:

  • A model set in Anthropic's server configuration.
  • The model you name in the CLAUDE_CODE_AUTO_MODE_MODEL environment variable.
  • A built-in default.

Claude Code ignores CLAUDE_CODE_AUTO_MODE_MODEL and shows a warning in these cases:

  • A server model is set.
  • Your organization's model policy does not allow that model.
  • The API's safeguards refuse the classifier's stricter check on that model.
Why

If you pin the classifier's model with CLAUDE_CODE_AUTO_MODE_MODEL, it may not be the one actually used. Watch for the warning that starts "Auto mode classifier: ignoring CLAUDE_CODE_AUTO_MODE_MODEL=".

Read from
Names in the bundleCLAUDE_CODE_AUTO_MODE_MODEL
Feature flag
tengu_auto_mode_config Not enough to say

Nothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.

This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.302: not a boolean we can read

These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.

Read once, for one account on one subscription tier, against v2.1.302. It isn't a statement about your account. What a flag value here can and cannot tell you

Since it was published

The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.

Added since A small documentation edit on Model configuration touched a line naming CLAUDE_CODE_AUTO_MODE_MODEL after this was published. * **`CLAUDE_CODE_AUTO_MODE_MODEL`**: Claude Code ignores the variable and picks the model for its [auto mode classifier requests](/docs/en/permission-modes#default-classifier-model) as if you hadn't set it model-config see the edit
Confirmed since Anthropic's documentation has since written up CLAUDE_CODE_AUTO_MODE_MODEL, on Error reference. * If the message returns on every retry and names the model you set in [`CLAUDE_CODE_AUTO_MODE_MODEL`](/docs/en/permission-modes#choose-the-classifier-model), check that the API or cloud provider your session runs on serves that model ID. … errors see the edit
How sure we are
Two sources agreeTwo things we can check say the same as this entry.
Anthropic's documentation agreesAnthropic's documentation has since written up CLAUDE_CODE_AUTO_MODE_MODEL, on Error reference.
Anthropic's release notes agreeAdded CLAUDE_CODE_AUTO_MODE_MODEL to choose the model the client-side auto mode classifier uses; it does not change the model for…

See this entry in the whole of v2.1.302 →

Feedback