{"version":"2.1.251","anchor":"prompt-cache-state-is-now-reported-in-status-output","canonical_anchor":"prompt-cache-state-is-now-reported-in-status-output","heading":"Prompt-cache state is now reported in status output","tier":"notice","area":"Status Output","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.251\/e\/prompt-cache-state-is-now-reported-in-status-output","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.251","markdown":"### Prompt-cache state is now reported in status output\n\nStatus and debug output now show whether the prompt cache is warm, its hit ratio and misses.\n\n**What**\n\nEach turn's status and debug payload now includes a prompt-cache block, and there is a one-line summary of the main conversation's cache: whether it is warm, how many requests and misses there have been, the hit ratio, and how many rebuilds are expected.\n\n**Details**\n\n- Fields recorded: warm, caching_observed, ttl, expires_at, requests, misses, expected_rebuilds, hit_ratio, cache_write_tokens, and miss_recache_tokens, the tokens that would need recaching if the cache went cold.\n- Sits alongside the existing cost and context window fields.\n- Computed only once there has been at least one request; with zero requests the block is empty.\n\n**Evidence**\n\n`Prompt cache (main):`, `prompt_cache`, `recache_tokens_if_cold`\n\n- Area: Status Output\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 3\/5"}