{"version":"2.1.207","anchor":"schedulewakeup-cache-ttl-aware-delay-guidance","canonical_anchor":"schedulewakeup-cache-ttl-aware-delay-guidance","heading":"ScheduleWakeup: Cache-TTL-Aware Delay Guidance","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.207\/e\/schedulewakeup-cache-ttl-aware-delay-guidance","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.207","markdown":"### ScheduleWakeup: Cache-TTL-Aware Delay Guidance\n\n**What**\n\nThe `ScheduleWakeup` tool's `## Picking delaySeconds` instructions are now context-aware, giving different guidance based on the session's prompt-cache TTL.\n\n**Details**\n\n- Sessions with a 1-hour TTL (Claude.ai subscriber sessions) receive guidance that ignores cache-window considerations \u2014 any delay in [60, 3600] is warm, so just pick based on what you're polling.\n- Sessions with the default 5-minute TTL receive the classic \"don't pick 300s\" guidance.\n- Sessions where the TTL is unknown receive a combined explanation covering both regimes.\n\n**Evidence**\n\nContext-aware delay guidance (search for `\"1-hour Anthropic prompt-cache TTL\"`)"}