Nothing to try yetTier: how much it should matter to you
3Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
ToolsArea: what it touches
In DevelopmentKind: in v2.1.257,
In DevelopmentSection of the release
A new model-capability flag, mid_conv_tool_change, joins existing flags like mid_conv_system and adaptive_thinking in the model-context flag lists used for deciding model behavior. It appears to gate whether tool definitions can change mid-conversation for a given model.
