- Bash prompt rule denials are now classified as
safetyChecktype (rather thanother) withclassifierApprovable: false, ensuring auto-mode cannot override safety denials. (search for"Denied by Bash prompt rule")
- Precomputed compact is now correctly gated: it can activate for non-user-query sources that have a precomputed swap available, fixing cases where compaction would not trigger when it should. (search for
"precomputed compact: arm gated")
- WIF (Workload Identity Federation) token refresh now checks sibling-process-rotated tokens before performing a new refresh grant, avoiding redundant token rotations in multi-process scenarios. (search for
"wif: adopting sibling-rotated access token from credentials file")
- Agent list attachment is no longer gated by
tengu_agent_list_attach— the check that previously required the feature flag is removed, making agent context more consistently available. (search for"tengu_agent_list_attach"absent from new code)
- Design OAuth credential error messages are improved: the
expand_failedcase now includes guidance to run/design-loginas an alternative, rather than only suggesting/login. (search for"Could not add design scopes to the token","or run /design-login to authorize design access separately")
Feature flag
tengu_agent_list_attach 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 v2.1.178: not a boolean we can read
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 v2.1.178. It isn't a statement about your account. What a flag value here can and cannot tell you
Flag reading moved
The flag server now returns off for tengu_agent_list_attach, 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.
Flag reading moved
The flag server now returns nothing at all, having stopped carrying it for tengu_agent_list_attach, 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.