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 v2.1.110 Home All releases olderv2.1.109 v2.1.111newer
Claude Code v2.1.110

Context Hint / Time-Based Microcompact [In Development]

Feature flag
tengu_hazel_osprey 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 v2.1.110: 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 v2.1.110. It isn't a statement about your account. What a flag value here can and cannot tell you

What

An intelligent context window management system that automatically removes older tool results to stay within context limits, triggered by server-side hints.

Status

Feature-flagged via tengu_hazel_osprey (default: false), with beta header context-hint-2026-04-09

Details
  • When the context window approaches limits, old tool result content is replaced with "[Old tool result content cleared]"
  • Handles HTTP 422/424 status codes as context-hint rejection signals
  • Tracks telemetry for tengu_time_based_microcompact with token savings metrics
  • Clears cached thinking tokens on context-hint triggers
Evidence

Microcompact system (gated by tengu_hazel_osprey, search for "[Old tool result content cleared]" and "tengu_time_based_microcompact")

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

See this entry in the whole of v2.1.110 →