multiplication

The passage around this formula

The growth is monotonic and the response is a threshold rule, which is worth writing down because it is the one piece of real mechanism in this section rather than product description. Treat |$c_t$| as the token size of the context at step t and $C_{\mathrm{max}}$ as the model’s context limit. Compaction is triggered once accumulated context crosses a configurable fraction $\tau$ of that limit: $|c_t| > \tau \cdot C_{\mathrm{max}} \implies c_t \to \hat{c}_t, \quad |\hat{c}_t| \ll |c_t|$. Concretely, Claude Code “clears older tool outputs first, then summarizes the conversation if needed,” preserving “requests and key code snippets” while allowing “detailed instructions from early in the conversation” to be lost [ 2 ] . This is a lossy operation by design, and what…

Read this part in the article →