Brandon/eng 290 make tool inputs actual objects and not strings (#1868)

* Improving tool calling to pass dictionaries instead of strings * Fix issues with parsing none/null * remove prints and unnecessary comments * Fix crew_test issues with function calling * improve prompting * add back in support for add_image * add tests for tool validation * revert back to figure out why tests are timing out * Update cassette * trying to find what is timing out * add back in guardrails * add back in manager delegation tests * Trying to fix tests * Force test to pass * Trying to fix tests * add in more role tests * add back old tool validation * updating tests * vcr * Fix tests * improve function llm logic * vcr 2 * drop llm * Failing test * add more tests back in * Revert tool validation
2026-01-10 08:38:30 +00:00 · 2025-01-10 17:16:46 -05:00
parent be8e33daf6
commit b8d07fee83
14 changed files with 857 additions and 3981 deletions
--- a/tests/cassettes/test_agent_tool_role_matching["Futel
+++ b/tests/cassettes/test_agent_tool_role_matching["Futel
@@ -0,0 +1,114 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Futel Official Infopoint.
+      Futel Football Club info\nYour personal goal is: Answer questions about Futel\nTo
+      give my best complete final answer to the task respond using the exact following
+      format:\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\nI MUST use these formats, my job depends on it!"}, {"role": "user",
+      "content": "\nCurrent Task: Test task\n\nThis is the expect criteria for your
+      final answer: Your best answer to your coworker asking you this, accounting
+      for the context shared.\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", "stop": ["\nObservation:"], "stream": false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '939'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=cwWdOaPJjFMNJaLtJfa8Kjqavswg5bzVRFzBX4gneGw-1736458417-1.0.1.1-bvf2HshgcMtgn7GdxqwySFDAIacGccDFfEXniBFTTDmbGMCiIIwf6t2DiwWnBldmUHixwc5kDO9gYs08g.feBA;
+        _cfuvid=WMw7PSqkYqQOieguBRs0uNkwNU92A.ZKbgDbCAcV3EQ-1736458417825-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.52.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.52.1
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AnuRqgg7eiHnDi2DOqdk99fiqOboz\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1736458422,\n  \"model\": \"gpt-4o-2024-08-06\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: Your best answer to your coworker asking you this, accounting for the
+      context shared. You MUST return the actual complete content as the final answer,
+      not a summary.\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      177,\n    \"completion_tokens\": 44,\n    \"total_tokens\": 221,\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  \"system_fingerprint\":
+      \"fp_703d4ff298\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ff78c164ad2c002-ATL
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 09 Jan 2025 21:33:43 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:
+      - '899'
+      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:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_9f5226208edb90a27987aaf7e0ca03d3
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1