Claude can propose a session goal; modelProposedGoals lets you always confirm or turn it off.
What's wrong with this entry?
A new tool lets the model propose a goal for the session. The modelProposedGoals setting takes auto (the default when the key is absent), alwaysAsk to route every proposal through an approval dialog, and disabled to turn the tool off. Because the setting affects consent, it is only read from user, policy and command-line settings; project and local settings in the workspace are ignored.
- The tool refuses to run inside agent contexts, and it can set a goal but never clear one.
{ "modelProposedGoals": "alwaysAsk" }'alwaysAsk' routes every model-proposed goal through the approval dialog; 'disabled' turns the tool off.
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.
-
v2.1.229
Goals record where they came from
Both mention goal
-
v2.1.229
Goal-set events gain an origin, one-shot warnings share a registry
Both mention goal
-
v2.1.229
Queued goals record where they came from
Both mention goal