{"version":"2.1.238","anchor":"model-and-effort-switch-warning-now-checks-whether-the-cache","canonical_anchor":"model-and-effort-switch-warning-now-checks-whether-the-cache","heading":"Model and effort switch warning now checks whether the cache is actually warm","tier":"notice","area":"Models","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.238\/e\/model-and-effort-switch-warning-now-checks-whether-the-cache","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.238","markdown":"### Model and effort switch warning now checks whether the cache is actually warm\n\nThe warm-cache warning when switching model or effort only appears when a warm cache actually exists.\n\n**What**\n\nThe confirmation shown when switching model or reasoning effort now depends on whether prompt caching is on for the current model and the last main-thread request is still within the cache lifetime, rather than a stored flag. The warning about discarding a warm cache appears only when there is one.\n\n**Details**\n\n- Setting `DISABLE_PROMPT_CACHING` (or the per-model equivalents) suppresses the warning entirely, since caching is off.\n\n**Evidence**\n\n`repl_main_thread`\n\n- Area: Models\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5"}