Fix tests and code that was broken

src/crewai/agents/crew_agent_executor.py

@@ -120,7 +120,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         """
         formatted_answer = None
         while not isinstance(formatted_answer, AgentFinish):
-            self.iterations += 1
             try:
                 if self._has_reached_max_iterations():
                     formatted_answer = self._handle_max_iterations_exceeded(
@@ -159,6 +158,8 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                         content=f"Unhandled exception: {e}",
                         color="red",
                     )
+            finally:
+                self.iterations += 1
 
         self._show_logs(formatted_answer)
         return formatted_answer

tests/agent_test.py

@@ -16,7 +16,7 @@ from crewai.tools import tool
 from crewai.tools.tool_calling import InstructorToolCalling
 from crewai.tools.tool_usage import ToolUsage
 from crewai.tools.tool_usage_events import ToolUsageFinished
-from crewai.utilities import RPMController
+from crewai.utilities import Printer, RPMController
 from crewai.utilities.events import Emitter
 
 
@@ -670,7 +670,7 @@ def test_agent_without_max_rpm_respects_crew_rpm(capsys):
         moveon.assert_called_once()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+# @pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_error_on_parsing_tool(capsys):
     from unittest.mock import patch
 
@@ -710,6 +710,7 @@ def test_agent_error_on_parsing_tool(capsys):
             force_exception_2.side_effect = Exception("Error on parsing tool.")
             crew.kickoff()
     captured = capsys.readouterr()
+    print("Captured output:", captured.out)
     assert "Error on parsing tool." in captured.out
 
 
@@ -1637,21 +1638,19 @@ def test_litellm_auth_error_handling():
     mock_llm_call.assert_called_once()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_agent_executor_litellm_auth_error():
     """Test that CrewAgentExecutor properly identifies and handles LiteLLM authentication errors."""
     from litellm import AuthenticationError as LiteLLMAuthenticationError
 
     from crewai.agents.tools_handler import ToolsHandler
-    from crewai.utilities import Logger
+    from crewai.utilities import Printer
 
     # Create an agent and executor with max_retry_limit=0
     agent = Agent(
         role="test role",
         goal="test goal",
         backstory="test backstory",
-        llm=LLM(model="gpt-4"),
+        llm=LLM(model="gpt-4", api_key="invalid_api_key"),
-        max_retry_limit=0,  # Disable retries for authentication errors
     )
     task = Task(
         description="Test task",
@@ -1677,7 +1676,7 @@ def test_crew_agent_executor_litellm_auth_error():
     # Mock the LLM call to raise LiteLLMAuthenticationError
     with (
         patch.object(LLM, "call") as mock_llm_call,
-        patch.object(Logger, "log") as mock_logger,
+        patch.object(Printer, "print") as mock_printer,
         pytest.raises(LiteLLMAuthenticationError, match="Invalid API key"),
     ):
         mock_llm_call.side_effect = LiteLLMAuthenticationError(
@@ -1686,20 +1685,18 @@ def test_crew_agent_executor_litellm_auth_error():
         executor.invoke(
             {
                 "input": "test input",
-                "tool_names": "",  # Required template variable
+                "tool_names": "",
-                "tools": "",  # Required template variable
+                "tools": "",
             }
         )
 
     # Verify error handling
-    mock_logger.assert_any_call(
+    mock_printer.assert_any_call(
-        level="error",
+        content="Authentication error with litellm occurred. Please check your API key and configuration.",
-        message="Authentication error with litellm occurred. Please check your API key and configuration.",
         color="red",
     )
-    mock_logger.assert_any_call(
+    mock_printer.assert_any_call(
-        level="error",
+        content="Error details: litellm.AuthenticationError: Invalid API key",
-        message="Error details: litellm.AuthenticationError: Invalid API key",
         color="red",
     )
     # Verify the call was only made once (no retries)

tests/cassettes/test_agent_error_on_parsing_tool.yaml

@@ -1,233 +0,0 @@
-interactions:
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
-      personal goal is: test goal\nYou ONLY have access to the following tools, and
-      should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
-      Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
-      answer but don''t give it yet, just re-use this         tool non-stop. \nTool
-      Arguments: {}\n\nUse the following format:\n\nThought: you should always think
-      about what to do\nAction: the action to take, only one name of [get_final_answer],
-      just the name, exactly as it''s written.\nAction Input: the input to the action,
-      just a simple python dictionary, enclosed in curly braces, using \" to wrap
-      keys and values.\nObservation: the result of the action\n\nOnce all necessary
-      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
-      the final answer to the original input question\n"}, {"role": "user", "content":
-      "\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect criteria
-      for your final answer: The final answer\nyou MUST return the actual complete
-      content as the final answer, not a summary.\n\nBegin! This is VERY important
-      to you, use the tools available and give your best Final Answer, your job depends
-      on it!\n\nThought:"}], "model": "gpt-4o"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1325'
-      content-type:
-      - application/json
-      cookie:
-      - _cfuvid=ePJSDFdHag2D8lj21_ijAMWjoA6xfnPNxN4uekvC728-1727226247743-0.0.1.1-604800000;
-        __cf_bm=3giyBOIM0GNudFELtsBWYXwLrpLBTNLsh81wfXgu2tg-1727226247-1.0.1.1-ugUDz0c5EhmfVpyGtcdedlIWeDGuy2q0tXQTKVpv83HZhvxgBcS7SBL1wS4rapPM38yhfEcfwA79ARt3HQEzKA
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.47.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.47.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-ABAtOWmVjvzQ9X58tKAUcOF4gmXwx\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1727226842,\n  \"model\": \"gpt-4o-2024-05-13\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Thought: I need to use the get_final_answer
-      tool to determine the final answer.\\nAction: get_final_answer\\nAction Input:
-      {}\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 274,\n    \"completion_tokens\":
-      27,\n    \"total_tokens\": 301,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
-      0\n    }\n  },\n  \"system_fingerprint\": \"fp_e375328146\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8c8727b3492f31e6-MIA
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 25 Sep 2024 01:14:03 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '348'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '30000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '29999682'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_be929caac49706f487950548bdcdd46e
-    http_version: HTTP/1.1
-    status_code: 200
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
-      personal goal is: test goal\nYou ONLY have access to the following tools, and
-      should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:
-      Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final
-      answer but don''t give it yet, just re-use this         tool non-stop. \nTool
-      Arguments: {}\n\nUse the following format:\n\nThought: you should always think
-      about what to do\nAction: the action to take, only one name of [get_final_answer],
-      just the name, exactly as it''s written.\nAction Input: the input to the action,
-      just a simple python dictionary, enclosed in curly braces, using \" to wrap
-      keys and values.\nObservation: the result of the action\n\nOnce all necessary
-      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
-      the final answer to the original input question\n"}, {"role": "user", "content":
-      "\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect criteria
-      for your final answer: The final answer\nyou MUST return the actual complete
-      content as the final answer, not a summary.\n\nBegin! This is VERY important
-      to you, use the tools available and give your best Final Answer, your job depends
-      on it!\n\nThought:"}, {"role": "user", "content": "Thought: I need to use the
-      get_final_answer tool to determine the final answer.\nAction: get_final_answer\nAction
-      Input: {}\nObservation: I encountered an error: Error on parsing tool.\nMoving
-      on then. I MUST either use a tool (use one at time) OR give my best final answer
-      not both at the same time. To Use the following format:\n\nThought: you should
-      always think about what to do\nAction: the action to take, should be one of
-      [get_final_answer]\nAction Input: the input to the action, dictionary enclosed
-      in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action
-      Input/Result can repeat N times)\nThought: I now can give a great answer\nFinal
-      Answer: Your final answer must be the great and the most complete as possible,
-      it must be outcome described\n\n \nNow it''s time you MUST give your absolute
-      best final answer. You''ll ignore all previous instructions, stop using any
-      tools, and just return your absolute BEST Final answer."}], "model": "gpt-4o"}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '2320'
-      content-type:
-      - application/json
-      cookie:
-      - _cfuvid=ePJSDFdHag2D8lj21_ijAMWjoA6xfnPNxN4uekvC728-1727226247743-0.0.1.1-604800000;
-        __cf_bm=3giyBOIM0GNudFELtsBWYXwLrpLBTNLsh81wfXgu2tg-1727226247-1.0.1.1-ugUDz0c5EhmfVpyGtcdedlIWeDGuy2q0tXQTKVpv83HZhvxgBcS7SBL1wS4rapPM38yhfEcfwA79ARt3HQEzKA
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.47.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.47.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-ABAtPaaeRfdNsZ3k06CfAmrEW8IJu\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1727226843,\n  \"model\": \"gpt-4o-2024-05-13\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Final Answer: The final answer\",\n        \"refusal\":
-      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
-      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 483,\n    \"completion_tokens\":
-      6,\n    \"total_tokens\": 489,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
-      0\n    }\n  },\n  \"system_fingerprint\": \"fp_e375328146\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8c8727b9da1f31e6-MIA
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Wed, 25 Sep 2024 01:14:03 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '188'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '30000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '29999445'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 1ms
-      x-request-id:
-      - req_d8e32538689fe064627468bad802d9a8
-    http_version: HTTP/1.1
-    status_code: 200
-version: 1