summaryrefslogtreecommitdiffhomepage
path: root/packages/transport-contract/src
diff options
context:
space:
mode:
authorAdam Malczewski <[email protected]>2026-06-11 14:11:13 +0900
committerAdam Malczewski <[email protected]>2026-06-11 14:11:13 +0900
commit7ffb6b28f5b6bdbfc53ebed94fc68af557612189 (patch)
treee66d9ea9d326ef771cc473d81ca5716ff78b08a8 /packages/transport-contract/src
parent763e5fb1c7fbfb4c7bbd43ffb935e42e5f5b5a42 (diff)
downloaddispatch-7ffb6b28f5b6bdbfc53ebed94fc68af557612189.tar.gz
dispatch-7ffb6b28f5b6bdbfc53ebed94fc68af557612189.zip
fix(cache-warming): accurate cache rate + expectedCacheRate (retention) metric
The Claude cache % read 100% whenever anything was cached, because the metric's denominator (inputTokens) excluded cached tokens on Anthropic. Fixed upstream in ../claude/provider-anthropic (inputTokens = total prompt); this commit adds the companion retention metric and exposes it: - transport-contract: WarmResponse += expectedCacheRate - transport-http: POST /chat/warm returns expectedCacheRate = cacheRead/(cacheRead+cacheWrite) - cache-warming: computeExpectedCacheRate + a per-conversation 'cache retention' surface stat - handoff: documents the fix + cache-rate vs expected-cache (cross-turn) for the FE Live-verified vs claude haiku: real turn cache rate 61% (was inflated 100%); warm within TTL expectedCacheRate=100%, after expiry=0%.
Diffstat (limited to 'packages/transport-contract/src')
-rw-r--r--packages/transport-contract/src/index.ts15
1 files changed, 13 insertions, 2 deletions
diff --git a/packages/transport-contract/src/index.ts b/packages/transport-contract/src/index.ts
index fbb61fc..95111ae 100644
--- a/packages/transport-contract/src/index.ts
+++ b/packages/transport-contract/src/index.ts
@@ -192,10 +192,21 @@ export interface WarmResponse {
readonly cacheReadTokens: number;
readonly cacheWriteTokens: number;
/**
- * Cache-hit percent: `round(clamp(cacheReadTokens / inputTokens, 0, 1) * 100)`
- * (0 when `inputTokens <= 0`).
+ * **Cache rate** — what fraction of THIS request's prompt was served from cache:
+ * `round(cacheReadTokens / inputTokens * 100)` (0 when `inputTokens <= 0`).
+ * (`inputTokens` is the TOTAL prompt incl. cached, so this is in [0,100].)
*/
readonly cachePct: number;
+ /**
+ * **Expected cache (retention)** — of the cacheable prefix this warm touched, how
+ * much was still warm and read back vs. had to be (re)written:
+ * `round(cacheReadTokens / (cacheReadTokens + cacheWriteTokens) * 100)` (0 when the
+ * sum is 0). For a healthy warm this is ~**100%** (the whole prefix was still
+ * cached); it drops toward 0 as the cache expires/busts and the warm has to rewrite
+ * it. This is the warming HEALTH signal — distinct from `cachePct` (which a warm's
+ * tiny fresh probe makes ~equal, but which on a real turn reflects new content).
+ */
+ readonly expectedCacheRate: number;
}
// ─── WebSocket chat ops ───────────────────────────────────────────────────────