feat(core,webapp): expose cached cost on the run span API

The span API ai object now returns cachedCost and cacheCreationCost
alongside inputCost/outputCost/totalCost. Since inputCost covers only the
non-cached input, these fields let consumers reconstruct the full cost
breakdown for prompt-cached calls instead of seeing an unexplained gap
below totalCost.

Author: ericallam

.changeset/span-api-cached-cost.md

@@ -0,0 +1,5 @@
+---
+"@trigger.dev/core": patch
+---
+
+The run span API response now includes `cachedCost` and `cacheCreationCost` on the `ai` object, alongside the existing `inputCost` / `outputCost` / `totalCost`. `inputCost` reflects only the non-cached input, so these fields let you reconstruct the full cost breakdown for prompt-cached calls.

apps/webapp/app/components/runs/v3/ai/extractAISpanData.ts

@@ -110,6 +110,8 @@ export function extractAISpanData(
     inputCost: num(triggerLlm.input_cost),
     outputCost: num(triggerLlm.output_cost),
     totalCost: num(triggerLlm.total_cost),
+    cachedCost: num(triggerLlm.cached_cost),
+    cacheCreationCost: num(triggerLlm.cache_creation_cost),
     responseText: isV7
       ? extractGenAiAssistantText(gOutput.messages) || undefined
       : str(aiResponse.text) || undefined,

apps/webapp/app/components/runs/v3/ai/extractAISummarySpanData.ts

@@ -108,6 +108,8 @@ export function extractAISummarySpanData(
     inputCost: num(triggerLlm.input_cost),
     outputCost: num(triggerLlm.output_cost),
     totalCost: num(triggerLlm.total_cost),
+    cachedCost: num(triggerLlm.cached_cost),
+    cacheCreationCost: num(triggerLlm.cache_creation_cost),
     responseText: str(aiResponse.text) || undefined,
     responseObject: str(aiResponse.object) || undefined,
     toolDefinitions: undefined,

apps/webapp/app/components/runs/v3/ai/types.ts

@@ -104,6 +104,8 @@ export type AISpanData = {
   inputCost?: number;
   outputCost?: number;
   totalCost?: number;
+  cachedCost?: number;
+  cacheCreationCost?: number;
 
   // Response text (final assistant output)
   responseText?: string;

apps/webapp/app/routes/api.v1.runs.$runId.spans.$spanId.ts

@@ -170,6 +170,8 @@ export const loader = createLoaderApiRoute(
               inputCost: aiData.inputCost,
               outputCost: aiData.outputCost,
               totalCost: aiData.totalCost,
+              cachedCost: aiData.cachedCost,
+              cacheCreationCost: aiData.cacheCreationCost,
               tokensPerSecond: aiData.tokensPerSecond,
               msToFirstChunk: aiData.msToFirstChunk,
               durationMs: aiData.durationMs,

apps/webapp/app/v3/utils/enrichCreatableEvents.server.ts

@@ -110,6 +110,8 @@ function enrichLlmMetrics(event: CreateEventInput): void {
       "trigger.llm.input_cost": cost.inputCost,
       "trigger.llm.output_cost": cost.outputCost,
       "trigger.llm.total_cost": cost.totalCost,
+      "trigger.llm.cached_cost": cost.costDetails["input_cached_tokens"] ?? 0,
+      "trigger.llm.cache_creation_cost": cost.costDetails["cache_creation_input_tokens"] ?? 0,
       "trigger.llm.matched_model": cost.matchedModelName,
       "trigger.llm.matched_model_id": cost.matchedModelId,
       "trigger.llm.pricing_tier": cost.pricingTierName,

packages/core/src/v3/schemas/api.ts

@@ -1993,6 +1993,8 @@ export const RetrieveSpanDetailResponseBody = z.object({
       inputCost: z.number().optional(),
       outputCost: z.number().optional(),
       totalCost: z.number().optional(),
+      cachedCost: z.number().optional(),
+      cacheCreationCost: z.number().optional(),
       tokensPerSecond: z.number().optional(),
       msToFirstChunk: z.number().optional(),
       durationMs: z.number(),