Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
Long ContextArea: what it touches
Internal ChangesKind: in v2.1.295,
Internal ChangesSection of the release
What
Some models can work with a context window, the amount of text the model can consider at once, of 1 million tokens. Claude Code now keeps a per-model record of models that refused that larger window, next to its existing record of refused optional features.
Two smaller changes ship with it:
Reading usage from a gateway (a server between Claude Code and the model) now also runs in a case where it was skipped before.
An update to the instructions MCP servers provide can now include instructions attached to it. MCP servers are add-on tool servers that connect to Claude Code.
Why
Once a model refuses the 1-million-token window, Claude Code can remember that for the model.
