A feature flag tengu_moth_copse controls whether the MCP URL elicitation flow (asking users to provide a URL for MCP server connection) is active. When the flag is on, a separate function rVi() is also checked.
Feature-flagged (tengu_moth_copse)
- The gated function
POe()returnstrueif eithertengu_moth_copseis set orrVi()returns true;rVi()returns true when theCLAUDE_MEMORY_STORESenv var is non-empty or the internal discovery latchYXnhas fired (set bynVi(), which emits thev6cevent when an external store announces itself) - When
POe()istrue,AutoMem-type local auto-memory entries are suppressed in two places:uso()filters them from context arrays andYAu()returnsfalsefor them, preventing local CLAUDE.md auto-memory from appearing in the model context alongside externally-discovered stores - Auto-memory prompt variant injection (
prompt_variant: "base") is suppressed whenPOe()istrue, removing local-index writing instructions from the system prompt - Full local memory-index content injection in
I$u()is disabled whenPOe()istrue(thespath is only taken when!POe()) - The per-turn memory selector
oHs()— which routes memory writes to the appropriate registered external store — only activates when bothEm()(auto-memory globally on) andPOe()aretrue; withoutPOe(), the selector never runs even when auto-memory is otherwise active
POe() function (search for "tengu_moth_copse" inside it), AutoMem suppression callers (search for "e.type === \"AutoMem\" && POe()" in YAu() and "filter((t) => t.type !== \"AutoMem\"" in uso()), memory selector guard (search for "!n || t.agentId || !Em() || !POe()" in oHs())
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
tengu_moth_copse Off in both readingsThe 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 v2.1.217: off
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 v2.1.217. It isn't a statement about your account. What a flag value here can and cannot tell you
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.