ci: test adjustments for Qwen3-0.6B (#3978)

Without this hint Qwen3-0.6B tends to reply with the full name
and sometimes doesn't reply with the correct drafted year.

---------

Signed-off-by: Derek Higgins <derekh@redhat.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>

tests/integration/telemetry/recordings/1fcfd86d8111374dc852cfdea6bfdb6a511f92cee84a6325b04ae84878512c30.json

@@ -30,7 +30,7 @@
             "index": 0,
             "logprobs": null,
             "message": {
-              "content": "import torch\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\n# Load the pre-trained model and tokenizer\nmodel_name = \"CompVis/transformers-base-uncased\"\nmodel = AutoModelForCausalLM.from_pretrained(model_name)\ntokenizer = AutoTokenizer.from_pretrained(model_name)\n\n# Set the temperature to 0.7\ntemperature = 0.7\n\n# Define a function to generate text\ndef generate_text(prompt, max_length=100):\n    input",
+              "content": "I can guide you through the process, but please note that testing OpenAI's models requires a bit of setup and potential API limits.\n\nOpenAI's API is designed to be used in a controlled environment for research purposes. You need an account on their platform and access to the API key.\n\nHere's how you can test a model with temperature 0.7 using Python:\n\n```python\nimport numpy as np\n\n# Replace 'YOUR_API_KEY' with your actual OpenAI API key.\nAPI_KEY",
               "refusal": null,
               "role": "assistant",
               "annotations": null,
@@ -55,5 +55,6 @@
       }
     },
     "is_streaming": false
-  }
+  },
+  "id_normalization_mapping": {}
 }