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 v2.1.120 Home All releases olderv2.1.119 v2.1.121newer
Claude Code v2.1.120

Lean Prompt System [Gradual Rollout]

Feature flag
tengu_vellum_lantern Off in both readings

The flag server returned off for the account this site reads and for the anonymous baseline. A reading of off cannot rule out a rollout these two readings sit outside of.

This account: off · anonymous baseline: off · compiled default in v2.1.120: no gate table built for this version

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 v2.1.120. It isn't a statement about your account. What a flag value here can and cannot tell you

What

The full lean prompt system that compresses all tool descriptions and system prompt content for reduced token usage.

Status

Feature-flagged behind tengu_vellum_lantern (default false), overridable with CLAUDE_CODE_LEAN_PROMPT=1.

Details
  • Currently restricted to Opus 4.6+ and Opus 4.7 models
  • The tengu_ochre_finch flag controls lean memory prompts independently
  • When fully enabled, tool descriptions are 60-80% shorter while preserving essential usage information
  • Users can preview it now via the environment variable

See this entry in the whole of v2.1.120 →