{"version":"2.1.257","anchor":"server-assisted-tool-token-counting-cache-for-context-analys","canonical_anchor":"server-assisted-tool-token-counting-cache-for-context-analys","heading":"Server-assisted tool token counting cache for context analysis, still gated off by default","tier":"soon","area":"Context Usage","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.257\/e\/server-assisted-tool-token-counting-cache-for-context-analys","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.257","markdown":"### Server-assisted tool token counting cache for context analysis, still gated off by default\n\nTool token counts for context analysis can come from the server instead of local estimates, but the gate is off.\n\nA new run-deduped cache plus a server-backed tool-count path can replace local estimation of tool definition token counts when analyzing context usage, falling back to the previous local estimator on error or when the `tengu_peppy_zephyr` gate is off. The feature is still gated off by default.\n\n- Flag `tengu_peppy_zephyr`: Not enough to say (read for one account on one subscription tier against v2.1.257; this account: no value returned, anonymous baseline: no value returned, compiled default: off) These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.\n- Area: Context Usage\n- Tier: Nothing to try yet\n- Useful: 3\/5\n- Signal: 3\/5\n- Present in the build but not switched on"}