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

lib/crewai/tests/cassettes/agents/test_agent_execution.yaml

@@ -1,15 +1,6 @@
 interactions:
 - request:
-    body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour
-      personal goal is: test goal\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: How much is 1 + 1?\n\nThis
-      is the expected criteria for your final answer: the result of the math operation.\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-4.1-mini"}'
+    body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour personal goal is: test goal\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: How much is 1 + 1?\n\nThis is the expected criteria for your final answer: the result of the math operation.\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-4.1-mini"}'
     headers:
       User-Agent:
       - X-USER-AGENT-XXX
@@ -49,23 +40,13 @@ interactions:
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: !!binary |
-        H4sIAAAAAAAAAwAAAP//jJJRa9swEMff/SkOvS4Oseemjd+2lI09lLIRGGUrRpHPljpZUqVz01Hy
-        3YucNHa3DvYikH73P93/7p4SAKZqVgITkpPonE7Xd5f34fr71c23tXSbq883668f34vr3fby8X7D
-        ZlFht3co6EU1F7ZzGklZc8DCIyeMWbPzZXGxKhZFPoDO1qijrHWUFvMs7ZRRab7Iz9JFkWbFUS6t
-        EhhYCT8SAICn4YyFmhofWQmL2ctLhyHwFll5CgJg3ur4wngIKhA3xGYjFNYQmqH2jbR9K6mEL2Ds
-        DgQ30KoHBA5tNADchB36n+aTMlzDh+FWwkYieAy9JrANkEToOEmwDj2PLYAM3kEGKkA+n37ssekD
-        j+5Nr/UEcGMsDdLB8u2R7E8mtW2dt9vwh5Q1yqggK488WBMNBbKODXSfANwOzexf9Yc5bztHFdlf
-        OHyXLYtDPjYOcaT5xRGSJa4nqlU+eyNfVSNxpcNkHExwIbEepePseF8rOwHJxPXf1byV++BcmfZ/
-        0o9ACHSEdeU81kq8djyGeYw7/q+wU5eHgllA/6AEVqTQx0nU2PBeHxaPhd+BsKsaZVr0zqvD9jWu
-        Wp0vl3hWrLY5S/bJMwAAAP//AwDr1ycJjAMAAA==
+      string: "{\n  \"id\": \"chatcmpl-CjDqsOWMYRChpTMGYCQB3cOwbDxqT\",\n  \"object\": \"chat.completion\",\n  \"created\": 1764894042,\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: The result of the math operation 1 + 1 is 2.\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 164,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 192,\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_9766e549b2\"\n}\n"
     headers:
       CF-RAY:
       - CF-RAY-XXX
       Connection:
       - keep-alive
-      Content-Encoding:
-      - gzip
       Content-Type:
       - application/json
       Date: