{"version":"2.1.275","anchor":"custom-system-prompt-strings-can-now-be-split-at-a-boundary","canonical_anchor":"custom-system-prompt-strings-can-now-be-split-at-a-boundary","heading":"Custom system prompt strings can now be split at a boundary marker for caching","tier":"internal","area":"System Prompt","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.275\/e\/custom-system-prompt-strings-can-now-be-split-at-a-boundary","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.275","markdown":"### Custom system prompt strings can now be split at a boundary marker for caching\n\nCustom system prompts can now be split into multiple cache segments\n\n**What**\n\nWhen Claude Code builds the system prompt used for analyzing context usage, a custom system prompt string is now passed through a new `splitSystemPromptAtBoundary()` helper instead of being included as one single block.\n\n**Why**\n\nSplitting the prompt at a boundary allows it to be broken into multiple segments for prompt caching (where Anthropic's API can reuse unchanged parts of a prompt across requests instead of reprocessing them), which can make repeated requests with a custom system prompt more efficient.\n\n- Area: System Prompt\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}