Follow Discord
Sweep 06 Nov 2026 · 01:32Z Build v2.1.319 537 read Stable v2.1.311 Latest v2.1.318 Next v2.1.319 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeReleasesv2.1.271entry #184

Claude Code v2.1.271 ·

New relayFork option for forked agent queries

Forked-agent queries, including memory extraction, can now run in a new relayFork mode, off by default

Group of 3 Nothing to try yet In Development
JSON All of v2.1.271
Nothing to try yetTier: how much it should matter to you
1Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
MemoryArea: what it touches
In DevelopmentKind: in v2.1.271,
In DevelopmentSection of the release

What

  • The forked-agent execution function now accepts a new relayFork option and threads it into the underlying query call, alongside the existing compactionRequestKind and thinkingStripPlan options.
  • The memory-extraction path (extract_memories) sets relayFork based on a new gate combined with a sync check, and logs the value in telemetry as relay_fork.
  • The gate reads a feature flag (tengu_wild_tome), so relayFork is off by default.

Why

This is internal plumbing for a new relay-based mode for forked and background queries such as memory extraction; since it's gated behind a disabled flag, it has no visible effect yet.

Read from
Feature flag
tengu_wild_tome 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 v2.1.271: 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 v2.1.271. It isn't a statement about your account. What a flag value here can and cannot tell you

What has happened since
Flag reading moved The flag server now returns on for tengu_wild_tome, read as this 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.

See this across every release →

How sure we are
One source agreesOne thing we can check says the same as this entry.
The name it cites is new in this buildNew in this build: tengu_wild_tome

See this entry in the whole of v2.1.271 →

Feedback