Subagent results can be tagged to show which parts Claude Code wrote versus the model.
tengu_melodic_wolf 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 v2.1.242: on
tengu_auto_mode_config 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 v2.1.242: not a boolean we can read
Read once, for one account on one subscription tier, against v2.1.242. It isn't a statement about your account. What a flag value here can and cannot tell you
What's wrong with this entry?
Results handed back from a subagent can be wrapped in bookkeeping that marks which blocks Claude Code itself wrote versus what the model produced, so a hook rewriting the text can be told apart. When that framing covers the whole delivery, the classifier review of the hand-off is skipped.
- Framing is keyed off
tengu_melodic_wolf, which falls back to off in this build. - Skipping the review requires
classifyHandoffintengu_auto_mode_configto be false, and is logged asskipped_framed_handbackorskipped_enveloped_handbackundertengu_auto_mode_decision.
skipped_framed_handback
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
Related
Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.
-
v2.1.234
Another forged control tag is escaped in subagent output
Both mention subagent
-
v2.1.234
Spawned processes get
--flag=valuewhen the value looks like a flagBoth mention subagent
-
v2.1.235
New error for delegating to a subagent without naming one
Both mention subagent