Three new plugin host verbs sit behind tengu_plugin_hooks_modules, false in source, and the flag reader is additionally blocked by a constant-false internal check.
The plugin host API gains three verbs: one reporting whether the caller is the desktop app or a terminal, one aborting a turn, and one reading a feature flag as $.flag.value(name, fallback). All of this sits behind tengu_plugin_hooks_modules, whose in-source default is false, so plugin JS modules do not load at all without a server value and the loader logs that it skipped them and names the flag. The flag reader is doubly off: it refuses unless an internal-build check passes, and that check is a constant false here.
- With the flag reader refusing, the
flagobject is filtered out of the method table advertised to plugins. - The plugin-types prompt and doc injection now opens on the same rollout flag instead of its previous condition.
reads a feature flag, which this build has no table of
Strings lifted out of the shipped bundle, so the claim above can be checked against them.
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.
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.
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.
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.
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.
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.
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.
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.