From b2fcc2daa146b67903bebad2e0226639cdc13411 Mon Sep 17 00:00:00 2001 From: krzychdre Date: Fri, 15 May 2026 23:42:44 +0200 Subject: [PATCH] ui-svelte: fix cached tokens total counting -1 sentinel (#760) The backend uses cache_tokens=-1 as a sentinel for endpoints that don't report cache stats (embeddings, vLLM). The activity table correctly renders these as "-", but the totals widget summed the sentinels directly, so each such request subtracted 1 from the displayed total. - clamp cache_tokens with Math.max(0, ...) when reducing --- ui-svelte/src/components/ActivityStats.svelte | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ui-svelte/src/components/ActivityStats.svelte b/ui-svelte/src/components/ActivityStats.svelte index 870ecdc9..eaced0d5 100644 --- a/ui-svelte/src/components/ActivityStats.svelte +++ b/ui-svelte/src/components/ActivityStats.svelte @@ -11,7 +11,7 @@ const totalRequests = $metrics.length; const totalInputTokens = $metrics.reduce((sum, m) => sum + m.tokens.input_tokens, 0); const totalOutputTokens = $metrics.reduce((sum, m) => sum + m.tokens.output_tokens, 0); - const totalCacheTokens = $metrics.reduce((sum, m) => sum + m.tokens.cache_tokens, 0); + const totalCacheTokens = $metrics.reduce((sum, m) => sum + Math.max(0, m.tokens.cache_tokens), 0); const promptPerSecond = $metrics.filter((m) => m.tokens.prompt_per_second > 0).map((m) => m.tokens.prompt_per_second);