@standardagents/builder 0.24.4 → 0.24.5

package/dist/built-in-routes.js

@@ -252,14 +252,14 @@ function calculateUsageCost(usage, pricing) {
   const inputPrice = useLongContext ? pricing.longInputPrice ?? pricing.inputPrice : pricing.inputPrice;
   const outputPrice = useLongContext ? pricing.longOutputPrice ?? pricing.outputPrice : pricing.outputPrice;
   const cachedTokenPrice = useLongContext ? pricing.longCachedPrice ?? pricing.cachedPrice ?? pricing.inputPrice : pricing.cachedPrice ?? pricing.inputPrice;
-  const costInput = roundCost(
-    (uncachedPromptTokens * inputPrice + cachedTokens * cachedTokenPrice) / TOKENS_PER_MILLION
-  );
+  const costInput = roundCost(uncachedPromptTokens * inputPrice / TOKENS_PER_MILLION);
+  const costCached = roundCost(cachedTokens * cachedTokenPrice / TOKENS_PER_MILLION);
   const costOutput = roundCost(billableOutputTokens * outputPrice / TOKENS_PER_MILLION);
   return {
     costInput,
+    costCached,
     costOutput,
-    costTotal: roundCost(costInput + costOutput)
+    costTotal: roundCost(costInput + costCached + costOutput)
   };
 }
 var TOKENS_PER_MILLION;
@@ -2136,6 +2136,7 @@ var init_LLMRequest = __esm({
             reasoning_tokens: response.usage.completion_tokens_details?.reasoning_tokens || 0,
             total_tokens: response.usage.total_tokens,
             cost_input: calculatedCost?.costInput,
+            cost_cached: calculatedCost?.costCached,
             cost_output: calculatedCost?.costOutput,
             latency_ms: Date.now() - startTime,
             time_to_first_token_ms: timing?.latencyMs ?? void 0,
@@ -2165,19 +2166,20 @@ var init_LLMRequest = __esm({
               reasoning_tokens = ?5,
               total_tokens = ?6,
               cost_input = ?7,
-              cost_output = ?8,
-              latency_ms = ?9,
-              finish_reason = ?10,
-              tools_called = ?11,
-              cost_total = ?12,
-              is_complete = ?13,
-              reasoning_content = ?14,
-              provider_tools = ?15,
-              actual_provider = ?16,
-              standard_agents_router_used = ?17,
-              time_to_first_token_ms = ?18,
-              generation_ms = ?19
-            WHERE id = ?20
+              cost_cached = ?8,
+              cost_output = ?9,
+              latency_ms = ?10,
+              finish_reason = ?11,
+              tools_called = ?12,
+              cost_total = ?13,
+              is_complete = ?14,
+              reasoning_content = ?15,
+              provider_tools = ?16,
+              actual_provider = ?17,
+              standard_agents_router_used = ?18,
+              time_to_first_token_ms = ?19,
+              generation_ms = ?20
+            WHERE id = ?21
           `,
                 logData.response_body,
                 logData.input_tokens,
@@ -2186,6 +2188,7 @@ var init_LLMRequest = __esm({
                 logData.reasoning_tokens,
                 logData.total_tokens,
                 logData.cost_input ?? null,
+                logData.cost_cached ?? null,
                 logData.cost_output ?? null,
                 logData.latency_ms,
                 logData.finish_reason,