Lorenze/imp/native tool calling (#4258)

* wip restrcuturing agent executor and liteagent * fix: handle None task in AgentExecutor to prevent errors Added a check to ensure that if the task is None, the method returns early without attempting to access task properties. This change improves the robustness of the AgentExecutor by preventing potential errors when the task is not set. * refactor: streamline AgentExecutor initialization by removing redundant parameters Updated the Agent class to simplify the initialization of the AgentExecutor by removing unnecessary task and crew parameters in standalone mode. This change enhances code clarity and maintains backward compatibility by ensuring that the executor is correctly configured without redundant assignments. * wip: clean * ensure executors work inside a flow due to flow in flow async structure * refactor: enhance agent kickoff preparation by separating common logic Updated the Agent class to introduce a new private method that consolidates the common setup logic for both synchronous and asynchronous kickoff executions. This change improves code clarity and maintainability by reducing redundancy in the kickoff process, while ensuring that the agent can still execute effectively within both standalone and flow contexts. * linting and tests * fix test * refactor: improve test for Agent kickoff parameters Updated the test for the Agent class to ensure that the kickoff method correctly preserves parameters. The test now verifies the configuration of the agent after kickoff, enhancing clarity and maintainability. Additionally, the test for asynchronous kickoff within a flow context has been updated to reflect the Agent class instead of LiteAgent. * refactor: update test task guardrail process output for improved validation Refactored the test for task guardrail process output to enhance the validation of the output against the OpenAPI schema. The changes include a more structured request body and updated response handling to ensure compliance with the guardrail requirements. This update aims to improve the clarity and reliability of the test cases, ensuring that task outputs are correctly validated and feedback is appropriately provided. * test fix cassette * test fix cassette * working * working cassette * refactor: streamline agent execution and enhance flow compatibility Refactored the Agent class to simplify the execution method by removing the event loop check and clarifying the behavior when called from synchronous and asynchronous contexts. The changes ensure that the method operates seamlessly within flow methods, improving clarity in the documentation. Additionally, updated the AgentExecutor to set the response model to None, enhancing flexibility. New test cassettes were added to validate the functionality of agents within flow contexts, ensuring robust testing for both synchronous and asynchronous operations. * fixed cassette * Enhance Flow Execution Logic - Introduced conditional execution for start methods in the Flow class. - Unconditional start methods are prioritized during kickoff, while conditional starts are executed only if no unconditional starts are present. - Improved handling of cyclic flows by allowing re-execution of conditional start methods triggered by routers. - Added checks to continue execution chains for completed conditional starts. These changes improve the flexibility and control of flow execution, ensuring that the correct methods are triggered based on the defined conditions. * Enhance Agent and Flow Execution Logic - Updated the Agent class to automatically detect the event loop and return a coroutine when called within a Flow, simplifying async handling for users. - Modified Flow class to execute listeners sequentially, preventing race conditions on shared state during listener execution. - Improved handling of coroutine results from synchronous methods, ensuring proper execution flow and state management. These changes enhance the overall execution logic and user experience when working with agents and flows in CrewAI. * Enhance Flow Listener Logic and Agent Imports - Updated the Flow class to track fired OR listeners, ensuring that multi-source OR listeners only trigger once during execution. This prevents redundant executions and improves flow efficiency. - Cleared fired OR listeners during cyclic flow resets to allow re-execution in new cycles. - Modified the Agent class imports to include Coroutine from collections.abc, enhancing type handling for asynchronous operations. These changes improve the control and performance of flow execution in CrewAI, ensuring more predictable behavior in complex scenarios. * adjusted test due to new cassette * ensure native tool calling works with liteagent * ensure response model is respected * Enhance Tool Name Handling for LLM Compatibility - Added a new function to replace invalid characters in function names with underscores, ensuring compatibility with LLM providers. - Updated the function to sanitize tool names before validation. - Modified the function to use sanitized names for tool registration. These changes improve the robustness of tool name handling, preventing potential issues with invalid characters in function names. * ensure we dont finalize batch on just a liteagent finishing * max tools per turn wip and ensure we drop print times * fix sync main issues * fix llm_call_completed event serialization issue * drop max_tools_iterations * for fixing model dump with state * Add extract_tool_call_info function to handle various tool call formats - Introduced a new utility function to extract tool call ID, name, and arguments from different provider formats (OpenAI, Gemini, Anthropic, and dictionary). - This enhancement improves the flexibility and compatibility of tool calls across multiple LLM providers, ensuring consistent handling of tool call information. - The function returns a tuple containing the call ID, function name, and function arguments, or None if the format is unrecognized. * Refactor AgentExecutor to support batch execution of native tool calls - Updated the method to process all tools from in a single batch, enhancing efficiency and reducing the number of interactions with the LLM. - Introduced a new utility function to streamline the extraction of tool call details, improving compatibility with various tool formats. - Removed the parameter, simplifying the initialization of the . - Enhanced logging and message handling to provide clearer insights during tool execution. - This refactor improves the overall performance and usability of the agent execution flow. * Update English translations for tool usage and reasoning instructions - Revised the `post_tool_reasoning` message to clarify the analysis process after tool usage, emphasizing the need to provide only the final answer if requirements are met. - Updated the `format` message to simplify the instructions for deciding between using a tool or providing a final answer, enhancing clarity for users. - These changes improve the overall user experience by providing clearer guidance on task execution and response formatting. * fix * fixing azure tests * organizae imports * dropped unused * Remove debug print statements from AgentExecutor to clean up the code and improve readability. This change enhances the overall performance of the agent execution flow by eliminating unnecessary console output during LLM calls and iterations. * linted * updated cassette * regen cassette * revert crew agent executor * adjust cassettes and dropped tests due to native tool implementation * adjust * ensure we properly fail tools and emit their events * Enhance tool handling and delegation tracking in agent executors - Implemented immediate return for tools with result_as_answer=True in crew_agent_executor.py. - Added delegation tracking functionality in agent_utils.py to increment delegations when specific tools are used. - Updated tool usage logic to handle caching more effectively in tool_usage.py. - Enhanced test cases to validate new delegation features and tool caching behavior. This update improves the efficiency of tool execution and enhances the delegation capabilities of agents. * Enhance tool handling and delegation tracking in agent executors - Implemented immediate return for tools with result_as_answer=True in crew_agent_executor.py. - Added delegation tracking functionality in agent_utils.py to increment delegations when specific tools are used. - Updated tool usage logic to handle caching more effectively in tool_usage.py. - Enhanced test cases to validate new delegation features and tool caching behavior. This update improves the efficiency of tool execution and enhances the delegation capabilities of agents. * fix cassettes * fix * regen cassettes * regen gemini * ensure we support bedrock * supporting bedrock * regen azure cassettes * Implement max usage count tracking for tools in agent executors - Added functionality to check if a tool has reached its maximum usage count before execution in both crew_agent_executor.py and agent_executor.py. - Enhanced error handling to return a message when a tool's usage limit is reached. - Updated tool usage logic in tool_usage.py to increment usage counts and print current usage status. - Introduced tests to validate max usage count behavior for native tool calling, ensuring proper enforcement and tracking. This update improves tool management by preventing overuse and providing clear feedback when limits are reached. * fix other test * fix test * drop logs * better tests * regen * regen all azure cassettes * regen again placeholder for cassette matching * fix: unify tool name sanitization across codebase * fix: include tool role messages in save_last_messages * fix: update sanitize_tool_name test expectations Align test expectations with unified sanitize_tool_name behavior that lowercases and splits camelCase for LLM provider compatibility. * fix: apply sanitize_tool_name consistently across codebase Unify tool name sanitization to ensure consistency between tool names shown to LLMs and tool name matching/lookup logic. * regen * fix: sanitize tool names in native tool call processing - Update extract_tool_call_info to return sanitized tool names - Fix delegation tool name matching to use sanitized names - Add sanitization in crew_agent_executor tool call extraction - Add sanitization in experimental agent_executor - Add sanitization in LLM.call function lookup - Update streaming utility to use sanitized names - Update base_agent_executor_mixin delegation check * Extract text content from parts directly to avoid warning about non-text parts * Add test case for Gemini token usage tracking - Introduced a new YAML cassette for tracking token usage in Gemini API responses. - Updated the test for Gemini to validate token usage metrics and response content. - Ensured proper integration with the Gemini model and API key handling. --------- Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
2026-05-04 16:52:37 +00:00 · 2026-01-22 17:44:03 -08:00
parent 06d953bf46
commit bd4d039f63
112 changed files with 18227 additions and 26180 deletions
--- a/lib/crewai/tests/cassettes/utilities/test_tools_emits_error_events.yaml
+++ b/lib/crewai/tests/cassettes/utilities/test_tools_emits_error_events.yaml
--- a/lib/crewai/tests/cassettes/utilities/test_tools_emits_finished_events.yaml
+++ b/lib/crewai/tests/cassettes/utilities/test_tools_emits_finished_events.yaml
@@ -1,506 +1,230 @@
 interactions:
 - request:
-    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
-      a helpful assistant that just says hi\nYour personal goal is: Just say hi\nYou
-      ONLY have access to the following tools, and should NEVER make up tools that
-      are not listed here:\n\nTool Name: say_hi\nTool Arguments: {}\nTool Description:
-      Say hi\n\nIMPORTANT: Use 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 [say_hi], 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: Just say
-      hi\n\nThis is the expect criteria for your final answer: hi\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-mini", "stop": ["\nObservation:"]}'
+    body: '{"messages":[{"role":"system","content":"You are base_agent. You are a
+      helpful assistant that just says hi\nYour personal goal is: Just say hi"},{"role":"user","content":"\nCurrent
+      Task: Just say hi\n\nThis is the expected criteria for your final answer: hi\nyou
+      MUST return the actual complete content as the final answer, not a summary.\n\nThis
+      is VERY important to you, your job depends on it!"}],"model":"gpt-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"say_hi","description":"Say
+      hi","parameters":{"properties":{},"type":"object"}}}]}'
    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
      accept:
      - application/json
      accept-encoding:
-      - gzip, deflate
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
      connection:
      - keep-alive
      content-length:
-      - '1275'
+      - '573'
      content-type:
      - application/json
-      cookie:
-      - _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000
      host:
      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
      x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
      x-stainless-retry-count:
      - '0'
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
-      - 3.12.8
+      - 3.13.3
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    content: "{\n  \"id\": \"chatcmpl-AzUA6kJQfpUvB4CGot4gSfAIR0foh\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1739217314,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"you should always think about what to
-      do  \\nAction: say_hi  \\nAction Input: {}  \",\n        \"refusal\": null\n
-      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
-      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 257,\n    \"completion_tokens\":
-      19,\n    \"total_tokens\": 276,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
-      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
-      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D0tf22fbIZC1zuDIm8CAr9K4GjuPO\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769106332,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+        \           \"id\": \"call_1W1J7qsl4RvxPEhk2Dtw4HQH\",\n            \"type\":
+        \"function\",\n            \"function\": {\n              \"name\": \"say_hi\",\n
+        \             \"arguments\": \"{}\"\n            }\n          }\n        ],\n
+        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
+        null,\n      \"finish_reason\": \"tool_calls\"\n    }\n  ],\n  \"usage\":
+        {\n    \"prompt_tokens\": 107,\n    \"completion_tokens\": 10,\n    \"total_tokens\":
+        117,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\":
+        0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
+        0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n
+        \     \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
    headers:
      CF-RAY:
-      - 90fea7d78e1fceb9-SJC
+      - CF-RAY-XXX
      Connection:
      - keep-alive
      Content-Type:
      - application/json
      Date:
-      - Mon, 10 Feb 2025 19:55:15 GMT
+      - Thu, 22 Jan 2026 18:25:33 GMT
      Server:
      - cloudflare
      Set-Cookie:
-      - __cf_bm=fmlg1wjOwuOwZhUUOEtL1tQYluAPumn7AHLF8s0EU2Y-1739217315-1.0.1.1-PQDvxn8TOhzaznlHjwVsqPZUzbAyJWFkvzCubfNJydTu2_AyA1cJ8hkM0khsEE4UY_xp8iPe2gSGmH1ydrDa0Q;
-        path=/; expires=Mon, 10-Feb-25 20:25:15 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
+      - SET-COOKIE-XXX
+      Strict-Transport-Security:
+      - STS-XXX
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
      access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
      alt-svc:
      - h3=":443"; ma=86400
      cf-cache-status:
      - DYNAMIC
      openai-organization:
-      - crewai-iuxna1
+      - OPENAI-ORG-XXX
      openai-processing-ms:
-      - '526'
+      - '1012'
+      openai-project:
+      - OPENAI-PROJECT-XXX
      openai-version:
      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '1263'
+      x-openai-proxy-wasm:
+      - v0.1
      x-ratelimit-limit-requests:
-      - '30000'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
      x-ratelimit-limit-tokens:
-      - '150000000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
      x-ratelimit-remaining-requests:
-      - '29999'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
      x-ratelimit-remaining-tokens:
-      - '149999703'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
      x-ratelimit-reset-requests:
-      - 2ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
      x-ratelimit-reset-tokens:
-      - 0s
+      - X-RATELIMIT-RESET-TOKENS-XXX
      x-request-id:
-      - req_f6358ff0cc7a2b8d2e167ab00a40f2a4
-    http_version: HTTP/1.1
-    status_code: 200
- request:
-    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
-      a helpful assistant that just says hi\nYour personal goal is: Just say hi\nYou
-      ONLY have access to the following tools, and should NEVER make up tools that
-      are not listed here:\n\nTool Name: say_hi\nTool Arguments: {}\nTool Description:
-      Say hi\n\nIMPORTANT: Use 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 [say_hi], 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: Just say
-      hi\n\nThis is the expect criteria for your final answer: hi\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": "you
-      should always think about what to do  \nAction: say_hi  \nAction Input: {}  \nObservation:
-      hi"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1410'
-      content-type:
-      - application/json
-      cookie:
-      - _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000;
-        __cf_bm=fmlg1wjOwuOwZhUUOEtL1tQYluAPumn7AHLF8s0EU2Y-1739217315-1.0.1.1-PQDvxn8TOhzaznlHjwVsqPZUzbAyJWFkvzCubfNJydTu2_AyA1cJ8hkM0khsEE4UY_xp8iPe2gSGmH1ydrDa0Q
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.8
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-AzUA7QdlQy1WZZijxNWUv25sZycg0\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1739217315,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"```\\nThought: I now know the final answer\\nFinal
-      Answer: hi\\n```\",\n        \"refusal\": null\n      },\n      \"logprobs\":
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-      283,\n    \"completion_tokens\": 17,\n    \"total_tokens\": 300,\n    \"prompt_tokens_details\":
-      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
-      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
-    headers:
-      CF-RAY:
-      - 90fea7dc5ba6ceb9-SJC
-      Connection:
-      - keep-alive
-      Content-Type:
-      - application/json
-      Date:
-      - Mon, 10 Feb 2025 19:55:15 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '388'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '30000'
-      x-ratelimit-limit-tokens:
-      - '150000000'
-      x-ratelimit-remaining-requests:
-      - '29999'
-      x-ratelimit-remaining-tokens:
-      - '149999680'
-      x-ratelimit-reset-requests:
-      - 2ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_7d7c68b90b3a9c3ac6092fe17ac1185a
-    http_version: HTTP/1.1
-    status_code: 200
- request:
-    body: !!binary |
-      CoMzCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS2jIKEgoQY3Jld2FpLnRl
-      bGVtZXRyeRKOAgoQ2EINIGZRoXD589od63oHmBIIMfUgEWudUbIqDFRhc2sgQ3JlYXRlZDABOcjI
-      7lbu8CIYQZB471bu8CIYSi4KCGNyZXdfa2V5EiIKIGU1ODA3MDFkNTJlYjY1YWZmMjRlZWZlNzhj
-      NzQ2MjhjSjEKB2NyZXdfaWQSJgokNTE4ODdiOTktY2FlMy00Yjc4LWJjMGEtMDY4MmVmNWEzNGQ0
-      Si4KCHRhc2tfa2V5EiIKIDFiMTVlZjIzOTE1YjI3NTVlODlhMGVjM2IyNmExM2QySjEKB3Rhc2tf
-      aWQSJgokMzlmMDlmMWUtOTJmOC00ZGJiLTgzNDAtNjU2ZmVkMDk3ZjM0egIYAYUBAAEAABKkBwoQ
-      RzhWoF6ewSTS/qUc9yeFRhIIM3SNZCwjz5AqDENyZXcgQ3JlYXRlZDABOQjrGlru8CIYQdgbKVru
-      8CIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTAwLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4x
-      Mi44Si4KCGNyZXdfa2V5EiIKIGU1ODA3MDFkNTJlYjY1YWZmMjRlZWZlNzhjNzQ2MjhjSjEKB2Ny
-      ZXdfaWQSJgokYzk4ODFkY2YtMmM0MS00ZjRlLTgzMjctNjJjYjFhYjJkOTg4ShwKDGNyZXdfcHJv
-      Y2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90
-      YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrRAgoLY3Jld19hZ2VudHMSwQIK
-      vgJbeyJrZXkiOiAiYWQxNTMxNjFjNWM1YTg1NmFhMGQwNmIyNDljNGM2NGEiLCAiaWQiOiAiNTU2
-      NzJiMDgtOTU4ZC00MjljLWE3ZTctY2ZlN2U4Y2MwOGZkIiwgInJvbGUiOiAiYmFzZV9hZ2VudCIs
-      ICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVu
-      Y3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9u
-      X2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9y
-      ZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/wEKCmNyZXdfdGFza3MS8AEK7QFb
-      eyJrZXkiOiAiMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2YTEzZDIiLCAiaWQiOiAiMzlmMDlm
-      MWUtOTJmOC00ZGJiLTgzNDAtNjU2ZmVkMDk3ZjM0IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxz
-      ZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJiYXNlX2FnZW50IiwgImFn
-      ZW50X2tleSI6ICJhZDE1MzE2MWM1YzVhODU2YWEwZDA2YjI0OWM0YzY0YSIsICJ0b29sc19uYW1l
-      cyI6IFtdfV16AhgBhQEAAQAAEo4CChB8AxWkb2Uwpdc8RpyCRqw5EggJAxbgNu81XyoMVGFzayBD
-      cmVhdGVkMAE5+HQ8Wu7wIhhB+PE8Wu7wIhhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmViNjVh
-      ZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiRjOTg4MWRjZi0yYzQxLTRmNGUtODMyNy02
-      MmNiMWFiMmQ5ODhKLgoIdGFza19rZXkSIgogMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2YTEz
-      ZDJKMQoHdGFza19pZBImCiQzOWYwOWYxZS05MmY4LTRkYmItODM0MC02NTZmZWQwOTdmMzR6AhgB
-      hQEAAQAAEqQHChCcXvdbsgYC+gzCMrXs3LN/EgijKwJLCRIiHioMQ3JldyBDcmVhdGVkMAE5iJqz
-      vu7wIhhBqKC/vu7wIhhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMDAuMEoaCg5weXRob25fdmVy
-      c2lvbhIICgYzLjEyLjhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmViNjVhZmYyNGVlZmU3OGM3
-      NDYyOGNKMQoHY3Jld19pZBImCiQ2Zjk1ZWI3Yy0wOWM5LTQxOTYtYWFiYi1kOWIxNmMxMzZjODdK
-      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
-      bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBStECCgtjcmV3
-      X2FnZW50cxLBAgq+Alt7ImtleSI6ICJhZDE1MzE2MWM1YzVhODU2YWEwZDA2YjI0OWM0YzY0YSIs
-      ICJpZCI6ICI1NTY3MmIwOC05NThkLTQyOWMtYTdlNy1jZmU3ZThjYzA4ZmQiLCAicm9sZSI6ICJi
-      YXNlX2FnZW50IiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6
-      IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwg
-      ImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZh
-      bHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUr/AQoKY3Jld190
-      YXNrcxLwAQrtAVt7ImtleSI6ICIxYjE1ZWYyMzkxNWIyNzU1ZTg5YTBlYzNiMjZhMTNkMiIsICJp
-      ZCI6ICIzOWYwOWYxZS05MmY4LTRkYmItODM0MC02NTZmZWQwOTdmMzQiLCAiYXN5bmNfZXhlY3V0
-      aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogImJhc2Vf
-      YWdlbnQiLCAiYWdlbnRfa2V5IjogImFkMTUzMTYxYzVjNWE4NTZhYTBkMDZiMjQ5YzRjNjRhIiwg
-      InRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEExDo5nPLyHb2H8DfYjPoX4SCLEYs+24
-      8EenKgxUYXNrIENyZWF0ZWQwATmI4NG+7vAiGEFYZdK+7vAiGEouCghjcmV3X2tleRIiCiBlNTgw
-      NzAxZDUyZWI2NWFmZjI0ZWVmZTc4Yzc0NjI4Y0oxCgdjcmV3X2lkEiYKJDZmOTVlYjdjLTA5Yzkt
-      NDE5Ni1hYWJiLWQ5YjE2YzEzNmM4N0ouCgh0YXNrX2tleRIiCiAxYjE1ZWYyMzkxNWIyNzU1ZTg5
-      YTBlYzNiMjZhMTNkMkoxCgd0YXNrX2lkEiYKJDM5ZjA5ZjFlLTkyZjgtNGRiYi04MzQwLTY1NmZl
-      ZDA5N2YzNHoCGAGFAQABAAASpAcKEBBQzR2bcR/7woQ+VkaJ4kQSCD1LFx3SNPPPKgxDcmV3IENy
-      ZWF0ZWQwATlotsW/7vAiGEEgA9C/7vAiGEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjEwMC4wShoK
-      DnB5dGhvbl92ZXJzaW9uEggKBjMuMTIuOEouCghjcmV3X2tleRIiCiBlNTgwNzAxZDUyZWI2NWFm
-      ZjI0ZWVmZTc4Yzc0NjI4Y0oxCgdjcmV3X2lkEiYKJDJiMWI2MGYzLTNlZTMtNGNjYi05MDM2LTdk
-      MzE4OTJiYjVkZkocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRIC
-      EABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxIC
-      GAFK0QIKC2NyZXdfYWdlbnRzEsECCr4CW3sia2V5IjogImFkMTUzMTYxYzVjNWE4NTZhYTBkMDZi
-      MjQ5YzRjNjRhIiwgImlkIjogIjU1NjcyYjA4LTk1OGQtNDI5Yy1hN2U3LWNmZTdlOGNjMDhmZCIs
-      ICJyb2xlIjogImJhc2VfYWdlbnQiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjAs
-      ICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0
-      LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVj
-      dXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1d
-      Sv8BCgpjcmV3X3Rhc2tzEvABCu0BW3sia2V5IjogIjFiMTVlZjIzOTE1YjI3NTVlODlhMGVjM2Iy
-      NmExM2QyIiwgImlkIjogIjM5ZjA5ZjFlLTkyZjgtNGRiYi04MzQwLTY1NmZlZDA5N2YzNCIsICJh
-      c3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3Jv
-      bGUiOiAiYmFzZV9hZ2VudCIsICJhZ2VudF9rZXkiOiAiYWQxNTMxNjFjNWM1YTg1NmFhMGQwNmIy
-      NDljNGM2NGEiLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKOAgoQmT07KMiFRgzOOPQf
-      I4bJPhIIqzN+pCYM6IUqDFRhc2sgQ3JlYXRlZDABOYjr3r/u8CIYQehY37/u8CIYSi4KCGNyZXdf
-      a2V5EiIKIGU1ODA3MDFkNTJlYjY1YWZmMjRlZWZlNzhjNzQ2MjhjSjEKB2NyZXdfaWQSJgokMmIx
-      YjYwZjMtM2VlMy00Y2NiLTkwMzYtN2QzMTg5MmJiNWRmSi4KCHRhc2tfa2V5EiIKIDFiMTVlZjIz
-      OTE1YjI3NTVlODlhMGVjM2IyNmExM2QySjEKB3Rhc2tfaWQSJgokMzlmMDlmMWUtOTJmOC00ZGJi
-      LTgzNDAtNjU2ZmVkMDk3ZjM0egIYAYUBAAEAABKkBwoQE53vZNAWshkoNK1bqTvovRII83djkBUL
-      EbcqDENyZXcgQ3JlYXRlZDABORBBzsDu8CIYQbAU2MDu8CIYShsKDmNyZXdhaV92ZXJzaW9uEgkK
-      BzAuMTAwLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMi44Si4KCGNyZXdfa2V5EiIKIGU1ODA3
-      MDFkNTJlYjY1YWZmMjRlZWZlNzhjNzQ2MjhjSjEKB2NyZXdfaWQSJgokNTQ0MWY0MWYtOTVjMC00
-      YzdkLTkxM2QtNDUxODcwY2YyZjYzShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2Ny
-      ZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJf
-      b2ZfYWdlbnRzEgIYAUrRAgoLY3Jld19hZ2VudHMSwQIKvgJbeyJrZXkiOiAiYWQxNTMxNjFjNWM1
-      YTg1NmFhMGQwNmIyNDljNGM2NGEiLCAiaWQiOiAiNTU2NzJiMDgtOTU4ZC00MjljLWE3ZTctY2Zl
-      N2U4Y2MwOGZkIiwgInJvbGUiOiAiYmFzZV9hZ2VudCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4
-      X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwg
-      ImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxv
-      d19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19u
-      YW1lcyI6IFtdfV1K/wEKCmNyZXdfdGFza3MS8AEK7QFbeyJrZXkiOiAiMWIxNWVmMjM5MTViMjc1
-      NWU4OWEwZWMzYjI2YTEzZDIiLCAiaWQiOiAiMzlmMDlmMWUtOTJmOC00ZGJiLTgzNDAtNjU2ZmVk
-      MDk3ZjM0IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNl
-      LCAiYWdlbnRfcm9sZSI6ICJiYXNlX2FnZW50IiwgImFnZW50X2tleSI6ICJhZDE1MzE2MWM1YzVh
-      ODU2YWEwZDA2YjI0OWM0YzY0YSIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChBV
-      JNEz3VIdOlQM9VT3bctVEgisogN707a2AioMVGFzayBDcmVhdGVkMAE5kGbnwO7wIhhBaMDnwO7w
-      IhhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmViNjVhZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jl
-      d19pZBImCiQ1NDQxZjQxZi05NWMwLTRjN2QtOTEzZC00NTE4NzBjZjJmNjNKLgoIdGFza19rZXkS
-      IgogMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2YTEzZDJKMQoHdGFza19pZBImCiQzOWYwOWYx
-      ZS05MmY4LTRkYmItODM0MC02NTZmZWQwOTdmMzR6AhgBhQEAAQAAErQHChDA7zaLCfy56rd5t3oS
-      rDPZEgjYoSW3mq6WJyoMQ3JldyBDcmVhdGVkMAE5cP/5we7wIhhBIH0Dwu7wIhhKGwoOY3Jld2Fp
-      X3ZlcnNpb24SCQoHMC4xMDAuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjEyLjhKLgoIY3Jld19r
-      ZXkSIgogZTU4MDcwMWQ1MmViNjVhZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiRmNjcz
-      MTc1ZS04Y2Q1LTQ1ZWUtYTZiOS0xYWFjMTliODQxZWJKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVl
-      bnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVj
-      cmV3X251bWJlcl9vZl9hZ2VudHMSAhgBStkCCgtjcmV3X2FnZW50cxLJAgrGAlt7ImtleSI6ICJh
-      ZDE1MzE2MWM1YzVhODU2YWEwZDA2YjI0OWM0YzY0YSIsICJpZCI6ICJmMGUwMGIzZi0wZWNmLTQ2
-      OGQtYjdjMC0yZmJhN2I5OTc5YjMiLCAicm9sZSI6ICJiYXNlX2FnZW50IiwgInZlcmJvc2U/Ijog
-      ZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5n
-      X2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBm
-      YWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0Ijog
-      MiwgInRvb2xzX25hbWVzIjogWyJzYXlfaGkiXX1dSocCCgpjcmV3X3Rhc2tzEvgBCvUBW3sia2V5
-      IjogIjFiMTVlZjIzOTE1YjI3NTVlODlhMGVjM2IyNmExM2QyIiwgImlkIjogImFhMGFmMmE2LTdm
-      MTktNDZmNi1iMjMxLTg1M2JjYzYxYzhiZiIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJo
-      dW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiYmFzZV9hZ2VudCIsICJhZ2VudF9r
-      ZXkiOiAiYWQxNTMxNjFjNWM1YTg1NmFhMGQwNmIyNDljNGM2NGEiLCAidG9vbHNfbmFtZXMiOiBb
-      InNheV9oaSJdfV16AhgBhQEAAQAAEo4CChBH8NUZY1Cv8sM2lfQLaEogEgiFlW7Wp7QpdyoMVGFz
-      ayBDcmVhdGVkMAE5MNkPwu7wIhhBUCcQwu7wIhhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmVi
-      NjVhZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiRmNjczMTc1ZS04Y2Q1LTQ1ZWUtYTZi
-      OS0xYWFjMTliODQxZWJKLgoIdGFza19rZXkSIgogMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2
-      YTEzZDJKMQoHdGFza19pZBImCiRhYTBhZjJhNi03ZjE5LTQ2ZjYtYjIzMS04NTNiY2M2MWM4YmZ6
-      AhgBhQEAAQAAEooBChCJg/wSACw+HIDy4vvYISP/EgjoC/oI/1V0cCoKVG9vbCBVc2FnZTABOWA0
-      ifTu8CIYQTD0lPTu8CIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTAwLjBKFQoJdG9vbF9uYW1l
-      EggKBnNheV9oaUoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '6534'
-      Content-Type:
-      - application/x-protobuf
-      User-Agent:
-      - OTel-OTLP-Exporter-Python/1.27.0
-    method: POST
-    uri: https://telemetry.crewai.com:4319/v1/traces
-  response:
-    body:
-      string: "\n\0"
-    headers:
-      Content-Length:
-      - '2'
-      Content-Type:
-      - application/x-protobuf
-      Date:
-      - Mon, 10 Feb 2025 19:55:17 GMT
+      - X-REQUEST-ID-XXX
    status:
      code: 200
      message: OK
 - request:
-    body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
-      completed based on the description, expected output, and actual results.\n\nTask
-      Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n```\n\nPlease
-      provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
-      from 0 to 10 evaluating on completion, quality, and overall performance- Entities
-      extracted from the task output, if any, their type, description, and relationships"}],
-      "model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
-      "TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
-      "description": "Correctly extracted `TaskEvaluation` with all the required parameters
-      with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
-      {"description": "The name of the entity.", "title": "Name", "type": "string"},
-      "type": {"description": "The type of the entity.", "title": "Type", "type":
-      "string"}, "description": {"description": "Description of the entity.", "title":
-      "Description", "type": "string"}, "relationships": {"description": "Relationships
-      of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
-      "array"}}, "required": ["name", "type", "description", "relationships"], "title":
-      "Entity", "type": "object"}}, "properties": {"suggestions": {"description":
-      "Suggestions to improve future similar tasks.", "items": {"type": "string"},
-      "title": "Suggestions", "type": "array"}, "quality": {"description": "A score
-      from 0 to 10 evaluating on completion, quality, and overall performance, all
-      taking into account the task description, expected output, and the result of
-      the task.", "title": "Quality", "type": "number"}, "entities": {"description":
-      "Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
-      "title": "Entities", "type": "array"}}, "required": ["entities", "quality",
-      "suggestions"], "type": "object"}}}]}'
+    body: '{"messages":[{"role":"system","content":"You are base_agent. You are a
+      helpful assistant that just says hi\nYour personal goal is: Just say hi"},{"role":"user","content":"\nCurrent
+      Task: Just say hi\n\nThis is the expected criteria for your final answer: hi\nyou
+      MUST return the actual complete content as the final answer, not a summary.\n\nThis
+      is VERY important to you, your job depends on it!"},{"role":"assistant","content":null,"tool_calls":[{"id":"call_1W1J7qsl4RvxPEhk2Dtw4HQH","type":"function","function":{"name":"say_hi","arguments":"{}"}}]},{"role":"tool","tool_call_id":"call_1W1J7qsl4RvxPEhk2Dtw4HQH","content":"hi"},{"role":"user","content":"Analyze
+      the tool result. If requirements are met, provide the Final Answer. Otherwise,
+      call the next tool. Deliver only the answer without meta-commentary."}],"model":"gpt-4.1-mini","tool_choice":"auto","tools":[{"type":"function","function":{"name":"say_hi","description":"Say
+      hi","parameters":{"properties":{},"type":"object"}}}]}'
    headers:
+      User-Agent:
+      - X-USER-AGENT-XXX
      accept:
      - application/json
      accept-encoding:
-      - gzip, deflate
+      - ACCEPT-ENCODING-XXX
+      authorization:
+      - AUTHORIZATION-XXX
      connection:
      - keep-alive
      content-length:
-      - '1967'
+      - '989'
      content-type:
      - application/json
      cookie:
-      - _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000;
-        __cf_bm=fmlg1wjOwuOwZhUUOEtL1tQYluAPumn7AHLF8s0EU2Y-1739217315-1.0.1.1-PQDvxn8TOhzaznlHjwVsqPZUzbAyJWFkvzCubfNJydTu2_AyA1cJ8hkM0khsEE4UY_xp8iPe2gSGmH1ydrDa0Q
+      - COOKIE-XXX
      host:
      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
      x-stainless-arch:
-      - arm64
+      - X-STAINLESS-ARCH-XXX
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
-      - MacOS
+      - X-STAINLESS-OS-XXX
      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
+      - 1.83.0
+      x-stainless-read-timeout:
+      - X-STAINLESS-READ-TIMEOUT-XXX
      x-stainless-retry-count:
      - '0'
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
-      - 3.12.8
+      - 3.13.3
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
-    content: "{\n  \"id\": \"chatcmpl-AzUA8oE0A2d99i1Khpu0CI7fSgRtZ\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1739217316,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
-      \           \"id\": \"call_bk3duHRErK1qCyvWJ1uVmmGl\",\n            \"type\":
-      \"function\",\n            \"function\": {\n              \"name\": \"TaskEvaluation\",\n
-      \             \"arguments\": \"{\\\"suggestions\\\":[\\\"Provide more context
-      or details for similar tasks to enhance clarity.\\\",\\\"Specify desired tone
-      or style for the output.\\\",\\\"Consider adding more variety in tasks to keep
-      engagement high.\\\"],\\\"quality\\\":10,\\\"entities\\\":[{\\\"name\\\":\\\"hi\\\",\\\"type\\\":\\\"greeting\\\",\\\"description\\\":\\\"A
-      casual way to say hello or acknowledge someone's presence.\\\",\\\"relationships\\\":[\\\"used
-      as a greeting\\\",\\\"expresses friendliness\\\"]}]}\"\n            }\n          }\n
-      \       ],\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
-      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-      275,\n    \"completion_tokens\": 80,\n    \"total_tokens\": 355,\n    \"prompt_tokens_details\":
-      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
-      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
-      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    body:
+      string: "{\n  \"id\": \"chatcmpl-D0tf3PACWSkcoq9h5ZN5dxKracOvg\",\n  \"object\":
+        \"chat.completion\",\n  \"created\": 1769106333,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n
+        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        \"assistant\",\n        \"content\": \"hi\",\n        \"refusal\": null,\n
+        \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 161,\n    \"completion_tokens\":
+        2,\n    \"total_tokens\": 163,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+        0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+        {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+        0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+        \"default\",\n  \"system_fingerprint\": \"fp_376a7ccef1\"\n}\n"
    headers:
      CF-RAY:
-      - 90fea7dfef41ceb9-SJC
+      - CF-RAY-XXX
      Connection:
      - keep-alive
      Content-Type:
      - application/json
      Date:
-      - Mon, 10 Feb 2025 19:55:17 GMT
+      - Thu, 22 Jan 2026 18:25:33 GMT
      Server:
      - cloudflare
+      Strict-Transport-Security:
+      - STS-XXX
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
-      - nosniff
+      - X-CONTENT-TYPE-XXX
      access-control-expose-headers:
-      - X-Request-ID
+      - ACCESS-CONTROL-XXX
      alt-svc:
      - h3=":443"; ma=86400
      cf-cache-status:
      - DYNAMIC
      openai-organization:
-      - crewai-iuxna1
+      - OPENAI-ORG-XXX
      openai-processing-ms:
-      - '1535'
+      - '297'
+      openai-project:
+      - OPENAI-PROJECT-XXX
      openai-version:
      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '322'
+      x-openai-proxy-wasm:
+      - v0.1
      x-ratelimit-limit-requests:
-      - '30000'
+      - X-RATELIMIT-LIMIT-REQUESTS-XXX
      x-ratelimit-limit-tokens:
-      - '150000000'
+      - X-RATELIMIT-LIMIT-TOKENS-XXX
      x-ratelimit-remaining-requests:
-      - '29999'
+      - X-RATELIMIT-REMAINING-REQUESTS-XXX
      x-ratelimit-remaining-tokens:
-      - '149999874'
+      - X-RATELIMIT-REMAINING-TOKENS-XXX
      x-ratelimit-reset-requests:
-      - 2ms
+      - X-RATELIMIT-RESET-REQUESTS-XXX
      x-ratelimit-reset-tokens:
-      - 0s
+      - X-RATELIMIT-RESET-TOKENS-XXX
      x-request-id:
-      - req_55d8eb91b4318245556b73d3f4c1e7c4
-    http_version: HTTP/1.1
-    status_code: 200
+      - X-REQUEST-ID-XXX
+    status:
+      code: 200
+      message: OK
 version: 1