From 4089dae91da0368dfbcdcf1d2a70d2d4502d2a7a Mon Sep 17 00:00:00 2001
From: ViditOstwal <viditostwal@gmail.com>
Date: Thu, 6 Aug 2026 20:10:40 +0530
Subject: [PATCH] Fix Anthropic native provider to include cache tokens in
 input totals.

Anthropic reports cache read and cache creation separately from input_tokens; fold them into input_tokens and total_tokens so billed usage is not underreported on cached workloads.
---
 .../crewai/llms/providers/anthropic/completion.py  | 14 +++++++++-----
 lib/crewai/tests/llms/anthropic/test_anthropic.py  | 11 ++++++++---
 2 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/lib/crewai/src/crewai/llms/providers/anthropic/completion.py b/lib/crewai/src/crewai/llms/providers/anthropic/completion.py
index 7deecbf60..cdeef692a 100644
--- a/lib/crewai/src/crewai/llms/providers/anthropic/completion.py
+++ b/lib/crewai/src/crewai/llms/providers/anthropic/completion.py
@@ -12,6 +12,7 @@ from crewai.llms.base_llm import BaseLLM, JsonResponseFormat, llm_call_context
 from crewai.llms.hooks.base import BaseInterceptor
 from crewai.llms.hooks.transport import AsyncHTTPTransport, HTTPTransport
 from crewai.llms.providers.utils.common import safe_tool_conversion
+from crewai.types.usage_metrics import _coerce_int
 from crewai.utilities.agent_utils import is_context_length_exceeded
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededError,
@@ -1965,12 +1966,15 @@ class AnthropicCompletion(BaseLLM):
         """Extract token usage and response metadata from Anthropic response."""
         if hasattr(response, "usage") and response.usage:
             usage = response.usage
-            input_tokens = getattr(usage, "input_tokens", 0)
-            output_tokens = getattr(usage, "output_tokens", 0)
-            cache_read_tokens = getattr(usage, "cache_read_input_tokens", 0) or 0
-            cache_creation_tokens = (
-                getattr(usage, "cache_creation_input_tokens", 0) or 0
+            input_tokens = _coerce_int(getattr(usage, "input_tokens", 0))
+            output_tokens = _coerce_int(getattr(usage, "output_tokens", 0))
+            cache_read_tokens = _coerce_int(
+                getattr(usage, "cache_read_input_tokens", 0)
             )
+            cache_creation_tokens = _coerce_int(
+                getattr(usage, "cache_creation_input_tokens", 0)
+            )
+            input_tokens = input_tokens + cache_read_tokens + cache_creation_tokens
             result: dict[str, Any] = {
                 "input_tokens": input_tokens,
                 "output_tokens": output_tokens,
diff --git a/lib/crewai/tests/llms/anthropic/test_anthropic.py b/lib/crewai/tests/llms/anthropic/test_anthropic.py
index fd21d3b8a..375246bb4 100644
--- a/lib/crewai/tests/llms/anthropic/test_anthropic.py
+++ b/lib/crewai/tests/llms/anthropic/test_anthropic.py
@@ -549,7 +549,12 @@ def test_anthropic_token_usage_tracking():
     with patch.object(llm._client.messages, 'create') as mock_create:
         mock_response = MagicMock()
         mock_response.content = [MagicMock(text="test response")]
-        mock_response.usage = MagicMock(input_tokens=50, output_tokens=25)
+        mock_response.usage = MagicMock(
+            input_tokens=50,
+            output_tokens=25,
+            cache_read_input_tokens=0,
+            cache_creation_input_tokens=0,
+        )
         mock_create.return_value = mock_response
 
         result = llm.call("Hello")
@@ -1653,9 +1658,9 @@ def test_anthropic_cache_creation_tokens_extraction():
     mock_response.model = None
 
     usage = llm._extract_anthropic_token_usage(mock_response)
-    assert usage["input_tokens"] == 100
+    assert usage["input_tokens"] == 150
     assert usage["output_tokens"] == 50
-    assert usage["total_tokens"] == 150
+    assert usage["total_tokens"] == 200
     assert usage["cached_prompt_tokens"] == 30
     assert usage["cache_creation_tokens"] == 20