Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
3Signal: worth watching, 1 to 5
SettingsArea: what it touches
Internal ChangesKind: in v2.1.302,
Internal ChangesSection of the release
Unclear Which feature this configuration belongs to is not known.
What
A configuration that used to hold only how often something refreshes now also holds a mode, set to "full", and a maximum number of input tokens. Tokens are the small chunks of text a model reads, so this is a cap on how much input is used.
Why
It looks like a new limit on input size for whatever this setting controls.
How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtWhich feature this configuration belongs to is not known.
