fix: ensure token usage recording, validate response model on stream

lib/crewai/tests/cassettes/test_output_json_dict_sequential.yaml

@@ -1,22 +1,7 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert
-      scorer, specialized in scoring titles.\nYour personal goal is: Score the title\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: Give me an integer score between 1-5 for the following title: ''The impact
-      of AI in the future of work''\n\nThis is the expected criteria for your final
-      answer: The score of the title.\nyou MUST return the actual complete content
-      as the final answer, not a summary.\nEnsure your final answer strictly adheres
-      to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\":
-      \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
-      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo
-      not include the OpenAPI schema in the final output. Ensure the final output
-      does not include any code block markers like ```json or ```python.\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-4.1-mini"}'
+    body: '{"messages":[{"role":"system","content":"You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\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: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work''\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\nEnsure your final answer strictly adheres to the following OpenAPI schema: {\n  \"properties\": {\n    \"score\": {\n      \"title\": \"Score\",\n      \"type\": \"integer\"\n    }\n  },\n  \"required\": [\n    \"score\"\n  ],\n  \"title\":
+      \"ScoreOutput\",\n  \"type\": \"object\",\n  \"additionalProperties\": false\n}\n\nDo not include the OpenAPI schema in the final output. Ensure the final output does not include any code block markers like ```json or ```python.\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-4.1-mini"}'
     headers:
       accept:
       - application/json
@@ -54,23 +39,13 @@ interactions:
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: !!binary |
-        H4sIAAAAAAAAAwAAAP//jFLBbpwwEL3zFSOflwgI2W64VYkq9VBVVVtFUYmQYwZw19iOPWyarvbf
-        K8NmIWkq9YLEvHnj997MPgJgsmYFMNFxEr1V8dVtm3y3n3fXw6cH9XC7pcubm4368nX7xOk3WwWG
-        uf+Jgp5ZZ8L0ViFJoydYOOSEYWr6bp2db5L1OhuB3tSoAq21FOdnadxLLeMsyS7iJI/T/EjvjBTo
-        WQE/IgCA/fgNQnWNv1gByeq50qP3vEVWnJoAmDMqVBj3XnrimthqBoXRhHrU/q0zQ9tRAR9Bm0cQ
-        XEMrdwgc2mAAuPaP6Er9QWqu4P34V8C+1AAl88I4LFkBeakPywccNoPnwaUelFoAXGtDPKQ0Wrs7
-        IoeTGWVa68y9f0VljdTSd5VD7o0Owj0Zy0b0EAHcjaENL3Jg1pneUkVmi+Nz2WU+zWPzshZodgTJ
-        EFdz/Txdr96YV9VIXCq/iJ0JLjqsZ+q8Iz7U0iyAaOH6bzVvzZ6cS93+z/gZEAItYV1Zh7UULx3P
-        bQ7DLf+r7ZTyKJh5dDspsCKJLmyixoYPajow5p88YV81UrforJPTlTW2ykW2uUibzTpj0SH6AwAA
-        //8DAAY2e2R0AwAA
+      string: "{\n  \"id\": \"chatcmpl-CYg0UpOvDuMqlqYkt9WW8lQSkyatz\",\n  \"object\": \"chat.completion\",\n  \"created\": 1762380662,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal Answer: {\\n  \\\"score\\\": 4\\n}\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 294,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 316,\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_4c2851f862\"\
+        \n}\n"
     headers:
       CF-RAY:
       - REDACTED-RAY
       Connection:
       - keep-alive
-      Content-Encoding:
-      - gzip
       Content-Type:
       - application/json
       Date:
@@ -78,11 +53,8 @@ interactions:
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=REDACTED;
-        path=/; expires=Wed, 05-Nov-25 22:41:02 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=REDACTED;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 22:41:02 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Strict-Transport-Security:
       - max-age=31536000; includeSubDomains; preload
       Transfer-Encoding: