Follow Discord
Sweep 22 Oct 2026 · 21:04Z Build v2.1.309 528 read Stable v2.1.308 Latest v2.1.309 Next v2.1.309 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.273 ·

Forked agent queries now compute and report a relayEligible flag

Forked or background agent queries now track whether they're eligible for relay, gated by tengu_wild_tome, and report it in telemetry

Group of 2 You'll notice Internal Changes
JSON All of v2.1.273
You'll noticeTier: how much it should matter to you
3Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
SubagentsArea: what it touches
Internal ChangesKind: in v2.1.273,
ImprovementsSection of the release

Unclear The finding does not say what the relay is used for beyond eligibility tracking, and no reading has been taken of any related gate yet.

What

When running a forked or background agent query, Claude Code now computes a relayEligible flag (on), which is true only when the fork has no separate agent ID, has forked context messages, keeps the same tool set as its parent, and the tengu_wild_tome feature flag is enabled (it's off by default).

  • This flag is passed into the query as relayFork.
  • It's recorded as relayEligible in the tengu_fork_agent_query telemetry event and in fork-completion telemetry.

Why

This lays groundwork for relaying forked/background agent queries under certain conditions, while the telemetry field lets this be tracked and rolled out safely via the tengu_wild_tome flag.

How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtThe finding does not say what the relay is used for beyond eligibility tracking, and no reading has been taken of any related gate yet.

See this entry in the whole of v2.1.273 →

Feedback