Whether tool calls wait for remote approval capacity is now controlled by CLAUDE_CODE_REMOTE_TOOLS_ASK_SEATS and new feature gates
What
- The function that decides whether tool calls wait on an "ask seat" (a unit of remote approval capacity) now reads the
CLAUDE_CODE_REMOTE_TOOLS_ASK_SEATSenvironment variable as an override, falling back to a feature gate namedtengu_unified_waterfall, which defaults to true. - A second new gate,
tengu_violin_speculative_classifier, was also added, but it is currently wired to a function that always returns false, meaning it exists in the code but is not yet active.
Why This gives more explicit control over remote tool-approval waiting behavior and lays groundwork for a speculative classifier feature that is not turned on yet.
tengu_unified_waterfall 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 v2.1.280: 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.
tengu_violin_speculative_classifier Gate removed from the codeThis release deleted the gate from the code while it was still reading on for the account this site reads, so the code path no longer asks a flag before running.
This account: on · anonymous baseline: on · compiled default in v2.1.280: 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 v2.1.280. It isn't a statement about your account. What a flag value here can and cannot tell you
What tengu_unified_waterfall and tengu_violin_speculative_classifier actually enable is not stated, and neither gate's on/off state for this…
New in this build: tengu_unified_waterfall