{"version":"2.1.315","anchor":"prompt-cache-diagnostics-keep-a-per-source-hashed-prefix","canonical_anchor":"prompt-cache-diagnostics-keep-a-per-source-hashed-prefix","heading":"Prompt cache diagnostics now keep separate records for each source","tier":"internal","area":"Telemetry","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.315\/e\/prompt-cache-diagnostics-keep-a-per-source-hashed-prefix","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.315","markdown":"### Prompt cache diagnostics now keep separate records for each source\n\nClaude Code's internal prompt cache diagnostics now store fingerprints of instructions and tools separately for each source\n\n**What**\n\nThe prompt cache lets the model reuse work it has already done on the start of a conversation. Claude Code tracks when that cache stops matching, using fingerprints of the instructions and the tool list. It now stores these fingerprints separately for each source rather than as a single pair, and uses the previous record when making new ones.\n\n**Why**\n\nThis only affects diagnostics and changes nothing you see.\n\n- Area: Telemetry\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}