Merge branch 'main' into gl/feat/native-multimodal-files

lib/crewai/src/crewai/utilities/types.py

@@ -28,4 +28,4 @@ class KickoffInputs(TypedDict, total=False):
         files: Named file inputs accessible to tasks during execution.
     """
 
-    files: dict[str, FileInput]
+    files: dict[str, FileInput]

lib/crewai/tests/cassettes/llms/google/test_gemini_token_usage_tracking.yaml

@@ -0,0 +1,64 @@
+interactions:
+- request:
+    body: '{"contents": [{"parts": [{"text": "Hello"}], "role": "user"}], "generationConfig":
+      {}}'
+    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
+      accept:
+      - '*/*'
+      accept-encoding:
+      - ACCEPT-ENCODING-XXX
+      connection:
+      - keep-alive
+      content-length:
+      - '86'
+      content-type:
+      - application/json
+      host:
+      - generativelanguage.googleapis.com
+      x-goog-api-client:
+      - google-genai-sdk/1.49.0 gl-python/3.13.3
+      x-goog-api-key:
+      - X-GOOG-API-KEY-XXX
+    method: POST
+    uri: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash-001:generateContent
+  response:
+    body:
+      string: "{\n  \"candidates\": [\n    {\n      \"content\": {\n        \"parts\":
+        [\n          {\n            \"text\": \"Hi there! How can I help you today?\\n\"\n
+        \         }\n        ],\n        \"role\": \"model\"\n      },\n      \"finishReason\":
+        \"STOP\",\n      \"avgLogprobs\": -0.13875236294486307\n    }\n  ],\n  \"usageMetadata\":
+        {\n    \"promptTokenCount\": 1,\n    \"candidatesTokenCount\": 11,\n    \"totalTokenCount\":
+        12,\n    \"promptTokensDetails\": [\n      {\n        \"modality\": \"TEXT\",\n
+        \       \"tokenCount\": 1\n      }\n    ],\n    \"candidatesTokensDetails\":
+        [\n      {\n        \"modality\": \"TEXT\",\n        \"tokenCount\": 11\n
+        \     }\n    ]\n  },\n  \"modelVersion\": \"gemini-2.0-flash-001\",\n  \"responseId\":
+        \"RM9yabK9GeLCjMcPivCRyA4\"\n}\n"
+    headers:
+      Alt-Svc:
+      - h3=":443"; ma=2592000,h3-29=":443"; ma=2592000
+      Content-Type:
+      - application/json; charset=UTF-8
+      Date:
+      - Fri, 23 Jan 2026 01:30:44 GMT
+      Server:
+      - scaffolding on HTTPServer2
+      Server-Timing:
+      - gfet4t7; dur=469
+      Transfer-Encoding:
+      - chunked
+      Vary:
+      - Origin
+      - X-Origin
+      - Referer
+      X-Content-Type-Options:
+      - X-CONTENT-TYPE-XXX
+      X-Frame-Options:
+      - X-FRAME-OPTIONS-XXX
+      X-XSS-Protection:
+      - '0'
+    status:
+      code: 200
+      message: OK
+version: 1

lib/crewai/tests/llms/google/test_google.py

@@ -617,35 +617,22 @@ def test_gemini_environment_variable_api_key():
         assert llm.api_key == "test-google-key"
 
 
+@pytest.mark.vcr()
 def test_gemini_token_usage_tracking():
     """
     Test that token usage is properly tracked for Gemini responses
     """
     llm = LLM(model="google/gemini-2.0-flash-001")
 
-    # Mock the Gemini response with usage information
+    result = llm.call("Hello")
-    with patch.object(llm.client.models, 'generate_content') as mock_generate:
-        mock_response = MagicMock()
-        mock_response.text = "test response"
-        mock_response.candidates = []
-        mock_response.usage_metadata = MagicMock(
-            prompt_token_count=50,
-            candidates_token_count=25,
-            total_token_count=75
-        )
-        mock_generate.return_value = mock_response
 
-        result = llm.call("Hello")
+    assert result.strip() == "Hi there! How can I help you today?"
 
-        # Verify the response
+    usage = llm.get_token_usage_summary()
-        assert result == "test response"
+    assert usage.successful_requests == 1
-
+    assert usage.prompt_tokens > 0
-        # Verify token usage was extracted
+    assert usage.completion_tokens > 0
-        usage = llm._extract_token_usage(mock_response)
+    assert usage.total_tokens > 0
-        assert usage["prompt_token_count"] == 50
-        assert usage["candidates_token_count"] == 25
-        assert usage["total_token_count"] == 75
-        assert usage["total_tokens"] == 75
 
 
 def test_gemini_stop_sequences_sync():