From 4cf628c937db7f88a61f063ff1ed90a009e42ed4 Mon Sep 17 00:00:00 2001
From: Narendranath Gogineni <narenrockstar1@gmail.com>
Date: Tue, 28 Oct 2025 16:05:50 +0530
Subject: [PATCH 1/2] fix anthropic cache creation token mapping in vertex ai

---
 .../google-vertex-ai/chatComplete.ts          | 44 +++++++++++++++----
 1 file changed, 36 insertions(+), 8 deletions(-)

diff --git a/src/providers/google-vertex-ai/chatComplete.ts b/src/providers/google-vertex-ai/chatComplete.ts
index 55b9f48c4..eaf68e67c 100644
--- a/src/providers/google-vertex-ai/chatComplete.ts
+++ b/src/providers/google-vertex-ai/chatComplete.ts
@@ -772,7 +772,15 @@ export const VertexAnthropicChatCompleteResponseTransform: (
   }
 
   if ('content' in response) {
-    const { input_tokens = 0, output_tokens = 0 } = response?.usage ?? {};
+    const {
+      input_tokens = 0,
+      output_tokens = 0,
+      cache_creation_input_tokens,
+      cache_read_input_tokens,
+    } = response?.usage;
+
+    const shouldSendCacheUsage =
+      cache_creation_input_tokens || cache_read_input_tokens;
 
     let content: AnthropicContentItem[] | string = strictOpenAiCompliance
       ? ''
@@ -827,7 +835,15 @@ export const VertexAnthropicChatCompleteResponseTransform: (
       usage: {
         prompt_tokens: input_tokens,
         completion_tokens: output_tokens,
-        total_tokens: input_tokens + output_tokens,
+        total_tokens:
+          input_tokens +
+          output_tokens +
+          (cache_creation_input_tokens ?? 0) +
+          (cache_read_input_tokens ?? 0),
+        ...(shouldSendCacheUsage && {
+          cache_read_input_tokens: cache_read_input_tokens,
+          cache_creation_input_tokens: cache_creation_input_tokens,
+        }),
       },
     };
   }
@@ -895,11 +911,20 @@ export const VertexAnthropicChatCompleteStreamChunkTransform: (
     );
   }
 
+  const shouldSendCacheUsage =
+    parsedChunk.message?.usage?.cache_read_input_tokens ||
+    parsedChunk.message?.usage?.cache_creation_input_tokens;
+
   if (parsedChunk.type === 'message_start' && parsedChunk.message?.usage) {
     streamState.model = parsedChunk?.message?.model ?? '';
-
     streamState.usage = {
-      prompt_tokens: parsedChunk.message.usage?.input_tokens,
+      prompt_tokens: parsedChunk.message?.usage?.input_tokens,
+      ...(shouldSendCacheUsage && {
+        cache_read_input_tokens:
+          parsedChunk.message?.usage?.cache_read_input_tokens,
+        cache_creation_input_tokens:
+          parsedChunk.message?.usage?.cache_creation_input_tokens,
+      }),
     };
     return (
       `data: ${JSON.stringify({
@@ -926,6 +951,11 @@ export const VertexAnthropicChatCompleteStreamChunkTransform: (
   }
 
   if (parsedChunk.type === 'message_delta' && parsedChunk.usage) {
+    const totalTokens =
+      (streamState?.usage?.prompt_tokens ?? 0) +
+      (streamState?.usage?.cache_creation_input_tokens ?? 0) +
+      (streamState?.usage?.cache_read_input_tokens ?? 0) +
+      (parsedChunk.usage.output_tokens ?? 0);
     return (
       `data: ${JSON.stringify({
         id: fallbackId,
@@ -945,10 +975,8 @@ export const VertexAnthropicChatCompleteStreamChunkTransform: (
         ],
         usage: {
           completion_tokens: parsedChunk.usage?.output_tokens,
-          prompt_tokens: streamState.usage?.prompt_tokens,
-          total_tokens:
-            (streamState.usage?.prompt_tokens || 0) +
-            (parsedChunk.usage?.output_tokens || 0),
+          ...streamState.usage,
+          total_tokens: totalTokens,
         },
       })}` + '\n\n'
     );

From 973ec2cd7e8f1994d335539e93f2e13f1d84ea9c Mon Sep 17 00:00:00 2001
From: Narendranath Gogineni <narenrockstar1@gmail.com>
Date: Tue, 28 Oct 2025 16:25:21 +0530
Subject: [PATCH 2/2] add null check

---
 src/providers/google-vertex-ai/chatComplete.ts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/providers/google-vertex-ai/chatComplete.ts b/src/providers/google-vertex-ai/chatComplete.ts
index eaf68e67c..a66a2c793 100644
--- a/src/providers/google-vertex-ai/chatComplete.ts
+++ b/src/providers/google-vertex-ai/chatComplete.ts
@@ -777,7 +777,7 @@ export const VertexAnthropicChatCompleteResponseTransform: (
       output_tokens = 0,
       cache_creation_input_tokens,
       cache_read_input_tokens,
-    } = response?.usage;
+    } = response?.usage ?? {};
 
     const shouldSendCacheUsage =
       cache_creation_input_tokens || cache_read_input_tokens;