chore: ensure proper cassettes for agent tests

* chore: ensure proper cassettes for agent tests
* chore: tweak eval test to avoid race condition

lib/crewai/tests/agents/test_agent.py

@@ -307,27 +307,22 @@ def test_cache_hitting():
             event_handled = True
             condition.notify()
 
-    with (
+    task = Task(
-        patch.object(CacheHandler, "read") as read,
+        description="What is 2 times 6? Return only the result of the multiplication.",
-    ):
+        agent=agent,
-        read.return_value = "0"
+        expected_output="The result of the multiplication.",
-        task = Task(
+    )
-            description="What is 2 times 6? Ignore correctness and just return the result of the multiplication tool, you must use the tool.",
+    output = agent.execute_task(task)
-            agent=agent,
+    assert output == "12"
-            expected_output="The number that is the result of the multiplication tool.",
+
-        )
+    with condition:
-        output = agent.execute_task(task)
+        if not event_handled:
-        assert output == "0"
+            condition.wait(timeout=5)
-        read.assert_called_with(
+    assert event_handled, "Timeout waiting for tool usage event"
-            tool="multiplier", input='{"first_number": 2, "second_number": 6}'
+    assert len(received_events) == 1
-        )
+    assert isinstance(received_events[0], ToolUsageFinishedEvent)
-        with condition:
+    assert received_events[0].from_cache
-            if not event_handled:
+    assert received_events[0].output == "12"
-                condition.wait(timeout=5)
-        assert event_handled, "Timeout waiting for tool usage event"
-        assert len(received_events) == 1
-        assert isinstance(received_events[0], ToolUsageFinishedEvent)
-        assert received_events[0].from_cache
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])

lib/crewai/tests/cassettes/test_agent_execute_task_with_tool.yaml

@@ -1,23 +1,22 @@
 interactions:
 - request:
-    body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
+    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: dummy_tool\nTool
       Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description:
-      Useful for when you need to get a dummy result for a query.\n\nUse the following
+      Useful for when you need to get a dummy result for a query.\n\nIMPORTANT: Use
-      format:\n\nThought: you should always think about what to do\nAction: the action
+      the following format in your response:\n\n```\nThought: you should always think
-      to take, only one name of [dummy_tool], just the name, exactly as it''s written.\nAction
+      about what to do\nAction: the action to take, only one name of [dummy_tool],
-      Input: the input to the action, just a simple python dictionary, enclosed in
+      just the name, exactly as it''s written.\nAction Input: the input to the action,
-      curly braces, using \" to wrap keys and values.\nObservation: the result of
+      just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
-      the action\n\nOnce all necessary information is gathered:\n\nThought: I now
+      values.\nObservation: the result of the action\n```\n\nOnce all necessary information
-      know the final answer\nFinal Answer: the final answer to the original input
+      is gathered, return the following format:\n\n```\nThought: I now know the final
-      question"}, {"role": "user", "content": "\nCurrent Task: Use the dummy tool
+      answer\nFinal Answer: the final answer to the original input question\n```"},{"role":"user","content":"\nCurrent
-      to get a result for ''test query''\n\nThis is the expect criteria for your final
+      Task: Use the dummy tool to get a result for ''test query''\n\nThis is the expected
-      answer: The result from the dummy tool\nyou MUST return the actual complete
+      criteria for your final answer: The result from the dummy tool\nyou MUST return
-      content as the final answer, not a summary.\n\nBegin! This is VERY important
+      the actual complete content as the final answer, not a summary.\n\nBegin! This
-      to you, use the tools available and give your best Final Answer, your job depends
+      is VERY important to you, use the tools available and give your best Final Answer,
-      on it!\n\nThought:"}], "model": "gpt-3.5-turbo", "stop": ["\nObservation:"],
+      your job depends on it!\n\nThought:"}],"model":"gpt-3.5-turbo"}'
-      "stream": false}'
     headers:
       accept:
       - application/json
@@ -26,13 +25,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1363'
+      - '1381'
       content-type:
       - application/json
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.52.1
+      - OpenAI/Python 1.109.1
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -42,35 +41,33 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.52.1
+      - 1.109.1
-      x-stainless-raw-response:
+      x-stainless-read-timeout:
-      - 'true'
+      - '600'
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.12.7
+      - 3.12.10
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-AmjTkjHtNtJfKGo6wS35grXEzfoqv\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1736177928,\n  \"model\": \"gpt-3.5-turbo-0125\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA4xTwW4TMRC95ytGvvSSVGlDWthbqYSIECAQSFRstXK8s7tuvR5jj5uGKv+O7CTd
-      \"assistant\",\n        \"content\": \"I should use the dummy tool to get a
+        FAriYtnz5j2/8YwfRgBC16IAoTrJqndmctl8ff3tJsxWd29vLu/7d1eXnz4vfq7cVft+1ohxYtDy
-      result for the 'test query'.\\n\\nAction: dummy_tool\\nAction Input: {\\\"query\\\":
+        BhXvWceKemeQNdktrDxKxqR6cn72YjqdzU/mGeipRpNorePJ7Hg+4eiXNJmenM53zI60wiAK+D4C
-      \\\"test query\\\"}\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+        AHjIa/Joa7wXBUzH+0iPIcgWRfGYBCA8mRQRMgQdWFoW4wFUZBlttr2A0FE0NcSAwB1CHft+XTGR
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        ASZokUGCxxANQ0M+pxwxBoYfEf366Li0FyoVXBww9zFYWBe5gIdS5OxS5H2NQXntUkaKfCCLYygF
-      271,\n    \"completion_tokens\": 31,\n    \"total_tokens\": 302,\n    \"prompt_tokens_details\":
+        rx2mcykC+1JsNqX9uAzo7+RW/8veHWR3nQzgkaO3WIPcIf92WtovHcW24wIWYGkFt2lJiY220oC0
-      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        YYW+tG/y6SKftvfudT31wytlH4fv6rGJQaa+2mjMASCtJc5l5I5e75DNYw8Ntc7TMvxGFY22OnSV
-      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        RxnIpn4FJicyuhkBXOdZiU/aL5yn3nHFdIv5utOXr7Z6YhjPAT2f7UAmlmaIz85Ox8/oVTWy1CYc
-      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+        TJtQUnVYD9RhNGWsNR0Ao4Oq/3TznPa2cm3b/5EfAKXQMdaV81hr9bTiIc1j+r1/S3t85WxYpEnU
-      null\n}\n"
+        CivW6FMnamxkNNt/JcI6MPZVo22L3nmdP1fq5Ggz+gUAAP//AwDDsh2ZWwQAAA==
     headers:
-      CF-Cache-Status:
-      - DYNAMIC
       CF-RAY:
-      - 8fdccc13af387bb2-ATL
+      - 9a3a73adce2d43c2-EWR
       Connection:
       - keep-alive
       Content-Encoding:
@@ -78,15 +75,17 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 06 Jan 2025 15:38:48 GMT
+      - Mon, 24 Nov 2025 16:58:36 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=PdbRW9vzO7559czIqn0xmXQjbN8_vV_J7k1DlkB4d_Y-1736177928-1.0.1.1-7yNcyljwqHI.TVflr9ZnkS705G.K5hgPbHpxRzcO3ZMFi5lHCBPs_KB5pFE043wYzPmDIHpn6fu6jIY9mlNoLQ;
+      - __cf_bm=Xa8khOM9zEqqwwmzvZrdS.nMU9nW06e0gk4Xg8ga5BI-1764003516-1.0.1.1-mR_vAWrgEyaykpsxgHq76VhaNTOdAWeNJweR1bmH1wVJgzoE0fuSPEKZMJy9Uon.1KBTV3yJVxLvQ4PjPLuE30IUdwY9Lrfbz.Rhb6UVbwY;
-        path=/; expires=Mon, 06-Jan-25 16:08:48 GMT; domain=.api.openai.com; HttpOnly;
+        path=/; expires=Mon, 24-Nov-25 17:28:36 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=lOOz0FbrrPaRb4IFEeHNcj7QghHzxI1tTV2N0jD9icA-1736177928767-0.0.1.1-604800000;
+      - _cfuvid=GP8hWglm1PiEe8AjYsdeCiIUtkA7483Hr9Ws4AZWe5U-1764003516772-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Strict-Transport-Security:
+      - max-age=31536000; includeSubDomains; preload
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
@@ -95,14 +94,20 @@ interactions:
       - X-Request-ID
       alt-svc:
       - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
       openai-organization:
-      - crewai-iuxna1
+      - REDACTED
       openai-processing-ms:
-      - '444'
+      - '1413'
+      openai-project:
+      - proj_xitITlrFeen7zjNSzML82h9x
       openai-version:
       - '2020-10-01'
-      strict-transport-security:
+      x-envoy-upstream-service-time:
-      - max-age=31536000; includeSubDomains; preload
+      - '1606'
+      x-openai-proxy-wasm:
+      - v0.1
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
@@ -110,36 +115,52 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '49999686'
+      - '49999684'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_5b3e93f5d4e6ab8feef83dc26b6eb623
+      - req_REDACTED
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
-    body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
+    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: dummy_tool\nTool
       Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description:
-      Useful for when you need to get a dummy result for a query.\n\nUse the following
+      Useful for when you need to get a dummy result for a query.\n\nIMPORTANT: Use
-      format:\n\nThought: you should always think about what to do\nAction: the action
+      the following format in your response:\n\n```\nThought: you should always think
-      to take, only one name of [dummy_tool], just the name, exactly as it''s written.\nAction
+      about what to do\nAction: the action to take, only one name of [dummy_tool],
-      Input: the input to the action, just a simple python dictionary, enclosed in
+      just the name, exactly as it''s written.\nAction Input: the input to the action,
-      curly braces, using \" to wrap keys and values.\nObservation: the result of
+      just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
-      the action\n\nOnce all necessary information is gathered:\n\nThought: I now
+      values.\nObservation: the result of the action\n```\n\nOnce all necessary information
-      know the final answer\nFinal Answer: the final answer to the original input
+      is gathered, return the following format:\n\n```\nThought: I now know the final
-      question"}, {"role": "user", "content": "\nCurrent Task: Use the dummy tool
+      answer\nFinal Answer: the final answer to the original input question\n```"},{"role":"user","content":"\nCurrent
-      to get a result for ''test query''\n\nThis is the expect criteria for your final
+      Task: Use the dummy tool to get a result for ''test query''\n\nThis is the expected
-      answer: The result from the dummy tool\nyou MUST return the actual complete
+      criteria for your final answer: The result from the dummy tool\nyou MUST return
-      content as the final answer, not a summary.\n\nBegin! This is VERY important
+      the actual complete content as the final answer, not a summary.\n\nBegin! This
-      to you, use the tools available and give your best Final Answer, your job depends
+      is VERY important to you, use the tools available and give your best Final Answer,
-      on it!\n\nThought:"}, {"role": "assistant", "content": "I should use the dummy
+      your job depends on it!\n\nThought:"},{"role":"assistant","content":"I should
-      tool to get a result for the ''test query''.\n\nAction: dummy_tool\nAction Input:
+      use the dummy_tool to get a result for the ''test query''.\nAction: dummy_tool\nAction
-      {\"query\": \"test query\"}\nObservation: Dummy result for: test query"}], "model":
+      Input: {\"query\": {\"description\": None, \"type\": \"str\"}}\nObservation:
-      "gpt-3.5-turbo", "stop": ["\nObservation:"], "stream": false}'
+      \nI encountered an error while trying to use the tool. This was the error: Arguments
+      validation failed: 1 validation error for Dummy_Tool\nquery\n  Input should
+      be a valid string [type=string_type, input_value={''description'': ''None'',
+      ''type'': ''str''}, input_type=dict]\n    For further information visit https://errors.pydantic.dev/2.12/v/string_type.\n
+      Tool dummy_tool accepts these inputs: Tool Name: dummy_tool\nTool Arguments:
+      {''query'': {''description'': None, ''type'': ''str''}}\nTool Description: Useful
+      for when you need to get a dummy result for a query..\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. When responding, I must use the following format:\n\n```\nThought:
+      you should always think about what to do\nAction: the action to take, should
+      be one of [dummy_tool]\nAction Input: the input to the action, dictionary enclosed
+      in curly braces\nObservation: the result of the action\n```\nThis Thought/Action/Action
+      Input/Result can repeat N times. Once I know the final answer, I must return
+      the following format:\n\n```\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```"}],"model":"gpt-3.5-turbo"}'
     headers:
       accept:
       - application/json
@@ -148,16 +169,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1574'
+      - '2841'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=PdbRW9vzO7559czIqn0xmXQjbN8_vV_J7k1DlkB4d_Y-1736177928-1.0.1.1-7yNcyljwqHI.TVflr9ZnkS705G.K5hgPbHpxRzcO3ZMFi5lHCBPs_KB5pFE043wYzPmDIHpn6fu6jIY9mlNoLQ;
+      - __cf_bm=Xa8khOM9zEqqwwmzvZrdS.nMU9nW06e0gk4Xg8ga5BI-1764003516-1.0.1.1-mR_vAWrgEyaykpsxgHq76VhaNTOdAWeNJweR1bmH1wVJgzoE0fuSPEKZMJy9Uon.1KBTV3yJVxLvQ4PjPLuE30IUdwY9Lrfbz.Rhb6UVbwY;
-        _cfuvid=lOOz0FbrrPaRb4IFEeHNcj7QghHzxI1tTV2N0jD9icA-1736177928767-0.0.1.1-604800000
+        _cfuvid=GP8hWglm1PiEe8AjYsdeCiIUtkA7483Hr9Ws4AZWe5U-1764003516772-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.52.1
+      - OpenAI/Python 1.109.1
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -167,34 +188,34 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.52.1
+      - 1.109.1
-      x-stainless-raw-response:
+      x-stainless-read-timeout:
-      - 'true'
+      - '600'
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.12.7
+      - 3.12.10
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-AmjTkjtDnt98YQ3k4y71C523EQM9p\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1736177928,\n  \"model\": \"gpt-3.5-turbo-0125\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAAwAAAP//pFPbahsxEH33Vwx6yYtt7LhO0n1LWgomlFKaFko3LLJ2dletdrSRRklN
-      \"assistant\",\n        \"content\": \"Final Answer: Dummy result for: test
+        8L8HyZdd9wKFvgikM2cuOmeeRwBClyIDoRrJqu3M5E31+UaeL+ct335c3Ty8/frFLW5vF6G9dNfv
-      query\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        xTgy7Po7Kj6wpsq2nUHWlnawcigZY9b55cWr2WyxnF8loLUlmkirO54spssJB7e2k9n8fLlnNlYr
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 315,\n    \"completion_tokens\":
+        9CKDbyMAgOd0xh6pxJ8ig9n48NKi97JGkR2DAISzJr4I6b32LInFuAeVJUZKbd81NtQNZ7CCJ20M
-      9,\n    \"total_tokens\": 324,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        KOscKgZuEDR1gaGyrpUMkkpgt4HgNdUJLkPbbgq21oCspaZpTtcqzp4NoMMbrGKyDJ5z8RDQbXKR
-      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+        QS4YPcP+vs3pw9qje5S7HDndNQgOfTAMlbNtXxRSUe0z+BSUQu+rYMwG7JqlJixB7sMOZOsS96wv
-      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        dzbNKRY4Dk/2CZQkqPUjgoQ6CgeS/BO6nN5pkgau0+0/ag4lcFgFL6MFKBgzACSR5fQFSfz7PbI9
-      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
+        ym1s3Tm79r9QRaVJ+6ZwKL2lKK1n24mEbkcA98lW4cQponO27bhg+wNTuYvzva1E7+Qevbzag2xZ
-      null\n}\n"
+        mgHr9QE4yVeUyFIbPzCmUFI1WPbU3sUylNoOgNFg6t+7+VPu3eSa6n9J3wNKYcdYFp3DUqvTifsw
+        h3HR/xZ2/OXUsIgu1goL1uiiEiVWMpjdCgq/8YxtUWmq0XVOpz2MSo62oxcAAAD//wMA+UmELoYE
+        AAA=
     headers:
-      CF-Cache-Status:
-      - DYNAMIC
       CF-RAY:
-      - 8fdccc171b647bb2-ATL
+      - 9a3a73bbf9d943c2-EWR
       Connection:
       - keep-alive
       Content-Encoding:
@@ -202,9 +223,11 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Mon, 06 Jan 2025 15:38:49 GMT
+      - Mon, 24 Nov 2025 16:58:39 GMT
       Server:
       - cloudflare
+      Strict-Transport-Security:
+      - max-age=31536000; includeSubDomains; preload
       Transfer-Encoding:
       - chunked
       X-Content-Type-Options:
@@ -213,14 +236,20 @@ interactions:
       - X-Request-ID
       alt-svc:
       - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
       openai-organization:
-      - crewai-iuxna1
+      - REDACTED
       openai-processing-ms:
-      - '249'
+      - '1513'
+      openai-project:
+      - proj_xitITlrFeen7zjNSzML82h9x
       openai-version:
       - '2020-10-01'
-      strict-transport-security:
+      x-envoy-upstream-service-time:
-      - max-age=31536000; includeSubDomains; preload
+      - '1753'
+      x-openai-proxy-wasm:
+      - v0.1
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
@@ -228,103 +257,156 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '49999643'
+      - '49999334'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
       - 0s
       x-request-id:
-      - req_cdc7b25a3877bb9a7cb7c6d2645ff447
+      - req_REDACTED
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
-    body: '{"trace_id": "1581aff1-2567-43f4-a1f2-a2816533eb7d", "execution_type":
+    body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour
-      "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null,
+      personal goal is: test goal\nYou ONLY have access to the following tools, and
-      "crew_name": "Unknown Crew", "flow_name": null, "crewai_version": "0.201.1",
+      should NEVER make up tools that are not listed here:\n\nTool Name: dummy_tool\nTool
-      "privacy_level": "standard"}, "execution_metadata": {"expected_duration_estimate":
+      Arguments: {''query'': {''description'': None, ''type'': ''str''}}\nTool Description:
-      300, "agent_count": 0, "task_count": 0, "flow_method_count": 0, "execution_started_at":
+      Useful for when you need to get a dummy result for a query.\n\nIMPORTANT: Use
-      "2025-10-08T18:11:28.008595+00:00"}}'
+      the following format in your response:\n\n```\nThought: you should always think
+      about what to do\nAction: the action to take, only one name of [dummy_tool],
+      just the name, exactly as it''s written.\nAction Input: the input to the action,
+      just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
+      values.\nObservation: the result of the action\n```\n\nOnce all necessary information
+      is gathered, return the following format:\n\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 dummy tool to get a result for ''test query''\n\nThis is the expected
+      criteria for your final answer: The result from the dummy tool\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":"assistant","content":"I should
+      use the dummy_tool to get a result for the ''test query''.\nAction: dummy_tool\nAction
+      Input: {\"query\": {\"description\": None, \"type\": \"str\"}}\nObservation:
+      \nI encountered an error while trying to use the tool. This was the error: Arguments
+      validation failed: 1 validation error for Dummy_Tool\nquery\n  Input should
+      be a valid string [type=string_type, input_value={''description'': ''None'',
+      ''type'': ''str''}, input_type=dict]\n    For further information visit https://errors.pydantic.dev/2.12/v/string_type.\n
+      Tool dummy_tool accepts these inputs: Tool Name: dummy_tool\nTool Arguments:
+      {''query'': {''description'': None, ''type'': ''str''}}\nTool Description: Useful
+      for when you need to get a dummy result for a query..\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. When responding, I must use the following format:\n\n```\nThought:
+      you should always think about what to do\nAction: the action to take, should
+      be one of [dummy_tool]\nAction Input: the input to the action, dictionary enclosed
+      in curly braces\nObservation: the result of the action\n```\nThis Thought/Action/Action
+      Input/Result can repeat N times. Once I know the final answer, I must return
+      the following format:\n\n```\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```"},{"role":"assistant","content":"Thought:
+      I will correct the input format and try using the dummy_tool again.\nAction:
+      dummy_tool\nAction Input: {\"query\": \"test query\"}\nObservation: Dummy result
+      for: test query"}],"model":"gpt-3.5-turbo"}'
     headers:
-      Accept:
+      accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate, zstd
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '436'
-      Content-Type:
       - application/json
-      User-Agent:
+      accept-encoding:
-      - CrewAI-CLI/0.201.1
+      - gzip, deflate
-      X-Crewai-Organization-Id:
+      connection:
-      - d3a3d10c-35db-423f-a7a4-c026030ba64d
+      - keep-alive
-      X-Crewai-Version:
+      content-length:
-      - 0.201.1
+      - '3057'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=Xa8khOM9zEqqwwmzvZrdS.nMU9nW06e0gk4Xg8ga5BI-1764003516-1.0.1.1-mR_vAWrgEyaykpsxgHq76VhaNTOdAWeNJweR1bmH1wVJgzoE0fuSPEKZMJy9Uon.1KBTV3yJVxLvQ4PjPLuE30IUdwY9Lrfbz.Rhb6UVbwY;
+        _cfuvid=GP8hWglm1PiEe8AjYsdeCiIUtkA7483Hr9Ws4AZWe5U-1764003516772-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.109.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.109.1
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.10
     method: POST
-    uri: http://localhost:3000/crewai_plus/api/v1/tracing/batches
+    uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: '{"id":"30844ebe-8ac6-4f67-939a-7a072d792654","trace_id":"1581aff1-2567-43f4-a1f2-a2816533eb7d","execution_type":"crew","crew_name":"Unknown
+      string: !!binary |
-        Crew","flow_name":null,"status":"running","duration_ms":null,"crewai_version":"0.201.1","privacy_level":"standard","total_events":0,"execution_context":{"crew_fingerprint":null,"crew_name":"Unknown
+        H4sIAAAAAAAAAwAAAP//jFLBbhMxEL3vV4x8TqqkTULZWwFFAq4gpEK18npnd028HmOPW6Iq/47s
-        Crew","flow_name":null,"crewai_version":"0.201.1","privacy_level":"standard"},"created_at":"2025-10-08T18:11:28.353Z","updated_at":"2025-10-08T18:11:28.353Z"}'
+        pNktFKkXS/abN37vzTwWAEI3ogSheslqcGb+vv36rt7e0uqzbna0ut18uv8mtxSDrddKzBKD6p+o
+        +Il1oWhwBlmTPcLKo2RMXZdvNqvF4mq9fJuBgRo0idY5nl9drOccfU3zxfJyfWL2pBUGUcL3AgDg
+        MZ9Jo23wtyhhMXt6GTAE2aEoz0UAwpNJL0KGoANLy2I2gooso82yv/QUu55L+AiWHmCXDu4RWm2l
+        AWnDA/ofdptvN/lWwoc4DHvwGKJhaMmXwBgYfkX0++k3HtsYZLJpozETQFpLLFNM2eDdCTmcLRnq
+        nKc6/EUVrbY69JVHGcgm+YHJiYweCoC7HF18loZwngbHFdMO83ebzerYT4zTGtHl9QlkYmkmrOvL
+        2Qv9qgZZahMm4QslVY/NSB0nJWOjaQIUE9f/qnmp99G5tt1r2o+AUugYm8p5bLR67ngs85iW+X9l
+        55SzYBHQ32uFFWv0aRINtjKa45qJsA+MQ9Vq26F3XuddS5MsDsUfAAAA//8DANWDXp9qAwAA
     headers:
-      Content-Length:
+      CF-RAY:
-      - '496'
+      - 9a3a73cd4ff343c2-EWR
-      cache-control:
+      Connection:
-      - no-store
+      - keep-alive
-      content-security-policy:
+      Content-Encoding:
-      - 'default-src ''self'' *.crewai.com crewai.com; script-src ''self'' ''unsafe-inline''
+      - gzip
-        *.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com
+      Content-Type:
-        https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js
+      - application/json
-        https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map
+      Date:
-        https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com
+      - Mon, 24 Nov 2025 16:58:40 GMT
-        https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com
+      Server:
-        https://js-na1.hs-scripts.com https://share.descript.com/; style-src ''self''
+      - cloudflare
-        ''unsafe-inline'' *.crewai.com crewai.com https://cdn.jsdelivr.net/npm/apexcharts;
+      Strict-Transport-Security:
-        img-src ''self'' data: *.crewai.com crewai.com https://zeus.tools.crewai.com
+      - max-age=31536000; includeSubDomains; preload
-        https://dashboard.tools.crewai.com https://cdn.jsdelivr.net; font-src ''self''
+      Transfer-Encoding:
-        data: *.crewai.com crewai.com; connect-src ''self'' *.crewai.com crewai.com
+      - chunked
-        https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/*
+      X-Content-Type-Options:
-        https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/
-        https://*.sentry.io https://www.google-analytics.com ws://localhost:3036 wss://localhost:3036;
-        frame-src ''self'' *.crewai.com crewai.com https://connect.useparagon.com/
-        https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/
-        https://docs.google.com https://drive.google.com https://slides.google.com
-        https://accounts.google.com https://*.google.com https://www.youtube.com https://share.descript.com'
-      content-type:
-      - application/json; charset=utf-8
-      etag:
-      - W/"a548892c6a8a52833595a42b35b10009"
-      expires:
-      - '0'
-      permissions-policy:
-      - camera=(), microphone=(self), geolocation=()
-      pragma:
-      - no-cache
-      referrer-policy:
-      - strict-origin-when-cross-origin
-      server-timing:
-      - cache_read.active_support;dur=0.05, cache_fetch_hit.active_support;dur=0.00,
-        cache_read_multi.active_support;dur=0.12, start_processing.action_controller;dur=0.00,
-        sql.active_record;dur=30.46, instantiation.active_record;dur=0.38, feature_operation.flipper;dur=0.03,
-        start_transaction.active_record;dur=0.01, transaction.active_record;dur=16.78,
-        process_action.action_controller;dur=309.67
-      vary:
-      - Accept
-      x-content-type-options:
       - nosniff
-      x-frame-options:
+      access-control-expose-headers:
-      - SAMEORIGIN
+      - X-Request-ID
-      x-permitted-cross-domain-policies:
+      alt-svc:
-      - none
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - REDACTED
+      openai-processing-ms:
+      - '401'
+      openai-project:
+      - proj_xitITlrFeen7zjNSzML82h9x
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '421'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '50000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '49999290'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
       x-request-id:
-      - 7ec132be-e871-4b0a-93f7-81f8d7c0ccae
+      - req_REDACTED
-      x-runtime:
-      - '0.358533'
-      x-xss-protection:
-      - 1; mode=block
     status:
-      code: 201
+      code: 200
-      message: Created
+      message: OK
 version: 1

lib/crewai/tests/experimental/evaluation/test_agent_evaluator.py

@@ -128,8 +128,6 @@ class TestAgentEvaluator:
 
     @pytest.mark.vcr(filter_headers=["authorization"])
     def test_eval_specific_agents_from_crew(self, mock_crew):
-        from crewai.events.types.task_events import TaskCompletedEvent
-
         agent = Agent(
             role="Test Agent Eval",
             goal="Complete test tasks successfully",
@@ -145,7 +143,7 @@ class TestAgentEvaluator:
 
         events = {}
         results_condition = threading.Condition()
-        results_ready = False
+        completed_event_received = False
 
         agent_evaluator = AgentEvaluator(
             agents=[agent], evaluators=[GoalAlignmentEvaluator()]
@@ -158,29 +156,23 @@ class TestAgentEvaluator:
 
         @crewai_event_bus.on(AgentEvaluationCompletedEvent)
         async def capture_completed(source, event):
+            nonlocal completed_event_received
             if event.agent_id == str(agent.id):
                 events["completed"] = event
+                with results_condition:
+                    completed_event_received = True
+                    results_condition.notify()
 
         @crewai_event_bus.on(AgentEvaluationFailedEvent)
         def capture_failed(source, event):
             events["failed"] = event
 
-        @crewai_event_bus.on(TaskCompletedEvent)
-        async def on_task_completed(source, event):
-            nonlocal results_ready
-            if event.task and event.task.id == task.id:
-                while not agent_evaluator.get_evaluation_results().get(agent.role):
-                    pass
-                with results_condition:
-                    results_ready = True
-                    results_condition.notify()
-
         mock_crew.kickoff()
 
         with results_condition:
             assert results_condition.wait_for(
-                lambda: results_ready, timeout=5
+                lambda: completed_event_received, timeout=5
-            ), "Timeout waiting for evaluation results"
+            ), "Timeout waiting for evaluation completed event"
 
         assert events.keys() == {"started", "completed"}
         assert events["started"].agent_id == str(agent.id)