Prompt caching correctly — the variable input goes LAST (step 6/9) · production tradeoffs

promptdojo_

This message has the user's question (variable) BEFORE the few-shot examples (stable). The cache prefix tries to match starting from the user's question — which differs every call — so the cache never fires. Hit rate: 0%.

Fix the message so the stable few-shot examples come FIRST (with cache_control), then the user's question comes last with no cache_control. Now the prefix is stable and cache fires on every call after the first.

Expected output:

first block: text? True, cached? True
second block: text? True, cached? False

The break is on lines 7, 8, 9, 10 — but read the whole snippet first.

Expected output:

first block: text? True, cached? True
second block: text? True, cached? False

The break is on lines 7, 8, 9, 10 — but read the whole snippet first.

full-screen editor opens — close anytime to keep reading.

Prompt caching correctly — the variable input goes LAST — step 6 of 9