Source Intelligence

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

All of v2.1.219 Home All releases olderv2.1.218 v2.1.220newer
Claude Code v2.1.219

Auto-mode permission classifier can emit a numeric severity instead of a yes/no block

Not switched on
Useful3 Signal4
Permissions Notable

Auto-mode permission checks can score risk 0-100 instead of yes/no, but only for configured models.

A numeric severity prompt variant is present, used only when severityByModel lists your model in tengu_auto_mode_config.

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 v2.1.219: 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 v2.1.219. It isn't a statement about your account. What a flag value here can and cannot tell you

What

When a severity config exists for the current model, the auto-mode classifier prompt is rewritten to ask for a numeric score rather than a block decision. Without that config the prompt keeps its existing form.

Details
  • the trailing "## Output Format" section is replaced to demand <severity>N</severity> on a 0 to 100 scale, with 50 as the allow/block boundary, instead of <block>yes/no</block>
  • gated on severityByModel in tengu_auto_mode_config; models absent from that map take the unchanged path
  • the permission rules injected into the classifier prompt are wrapped in <cc_automode_permissions> tags
  • denials taken because auto-mode is active use a distinct user-facing message naming the mode
Evidence

Permission to use ${e} has been denied because Claude Code is running in don't ask mode.

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

See this entry in the whole of v2.1.219 →