Observer agents now automatically propagate to watch subagents spawned by the observed agent, forming an observer tree. Previously, an observer only watched the single top-level agent it was paired with.
- New
observeSubagentsboolean field in agent frontmatter: defaults totrue(observers inherited); set tofalseto stop observer propagation at that agent - A depth cap prevents unbounded chaining; agents beyond the cap run unobserved (logged as a warning)
- Observer agents paired with workers (subagents of a coordinating agent) now report to the coordinator, not the worker. The ObserverReport tool description now says "report target" rather than "the agent you are observing"
- Activity digests sent to observers now include two new event types:
guidance-loaded(when Claude reads CLAUDE.md or similar guidance files) andskills-discovered(when skills are found in a directory) - Controlled by
tengu_observer_subagent_fanoutfeature flag (default: enabled)
New observeSubagents field (search for "If false, subagents this agent spawns do not inherit its observer")
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
tengu_observer_subagent_fanout Not enough to sayNothing 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 v2.1.218: on
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 v2.1.218. It isn't a statement about your account. What a flag value here can and cannot tell you
New in this build: tengu_observer_subagent_fanout