| Age | Commit message (Collapse) | Author |
|
|
|
Per the FE's backend-handoff.md (2026-06-11) the frontend shipped the NumberField
renderer, conversation-scoped subscriptions, the Cache Warming view, and warmNow().
Removed those sections; kept only the new cache-rate fix + expectedCacheRate
(retention) metric the FE has not yet consumed.
|
|
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%.
|
|
NumberField render, conversationId on the surface WS protocol, the cache-warming
control surface (toggle/interval/last-%), and POST /chat/warm.
|