end

open-sse/handlers/chatCore/requestDetail.js

@@ -1,5 +1,6 @@
 import { saveRequestUsage, appendRequestLog, saveRequestDetail } from "@/lib/usageDb.js";
 import { COLORS } from "../../utils/stream.js";
+import { canonicalizeUsage } from "../../utils/usageTracking.js";
 
 const OPTIONAL_PARAMS = [
   "temperature", "top_p", "top_k",
@@ -48,7 +49,8 @@ export function extractUsageFromResponse(responseBody) {
     return {
       prompt_tokens: responseBody.usageMetadata.promptTokenCount || 0,
       completion_tokens: responseBody.usageMetadata.candidatesTokenCount || 0,
-      reasoning_tokens: responseBody.usageMetadata.thoughtsTokenCount
+      cached_tokens: responseBody.usageMetadata.cachedContentTokenCount || 0,
+      reasoning_tokens: responseBody.usageMetadata.thoughtsTokenCount || 0
     };
   }
 
@@ -96,8 +98,14 @@ export function saveUsageStats({ provider, model, tokens, connectionId, apiKey,
   msg += `${COLORS.reset}`;
   console.log(msg);
 
+<<<<<<< HEAD
   // Normalize to OpenAI token shape for storage (include all token types)
   const normalized = {
+=======
+  // Canonicalize to one storage convention (prompt_tokens cache-inclusive) so
+  // cached/cache-creation tokens survive to cost calc + stats. See canonicalizeUsage.
+  const normalized = canonicalizeUsage(tokens) || {
+>>>>>>> 7f436e2792be4fa5a4d1c4d6b8e9bc85eaaa6a3d
     prompt_tokens: tokens.prompt_tokens ?? tokens.input_tokens ?? 0,
     completion_tokens: tokens.completion_tokens ?? tokens.output_tokens ?? 0,
     cache_read_input_tokens: cacheRead,