Follow Discord
Sweep 22 Oct 2026 · 21:04Z Build v2.1.309 528 read Stable v2.1.308 Latest v2.1.309 Next v2.1.309 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.302 ·

Context measuring now builds the system prompt in a different way

The part of Claude Code that measures what fills the context now assembles the system prompt differently

Under the hood Internal Changes
JSON All of v2.1.302
Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
1Signal: worth watching, 1 to 5
ElsewhereArea: what it touches
Internal ChangesKind: in v2.1.302,
Internal ChangesSection of the release
What

The system prompt is the standing set of instructions Claude Code gives the model, and the context is everything the model can see at once. The part of Claude Code that analyses what fills the context now builds the system prompt from its base with the command-line sections added, instead of splitting it at a boundary and appending a further prompt.

Why

This concerns how the system prompt is put together for measurement, and no visible effect has been identified.

See this entry in the whole of v2.1.302 →

Feedback