test(telemetry): Telemetry Tests (#3805)

# What does this PR do?
Adds a test and a standardized way to build future tests out for
telemetry in llama stack.
Contributes to https://github.com/llamastack/llama-stack/issues/3806

## Test Plan
This is the test plan 😎

tests/integration/telemetry/recordings/0de60cd6a6ec3dbfc4a7601e77be8083caf34f49147ad1c25efae1de3f0b25e5.json

@@ -0,0 +1,57 @@
+{
+  "test_id": "tests/integration/telemetry/test_openai_telemetry.py::test_openai_completion_creates_telemetry[txt=ollama/llama3.2:3b-instruct-fp16]",
+  "request": {
+    "method": "POST",
+    "url": "http://0.0.0.0:11434/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "llama3.2:3b-instruct-fp16",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Test OpenAI telemetry creation"
+        }
+      ],
+      "stream": false
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "llama3.2:3b-instruct-fp16"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+      "__data__": {
+        "id": "rec-0de60cd6a6ec",
+        "choices": [
+          {
+            "finish_reason": "stop",
+            "index": 0,
+            "logprobs": null,
+            "message": {
+              "content": "I'm happy to help you with setting up and testing OpenAI's telemetry creation.\n\nOpenAI provides a feature called \"Telemetry\" which allows developers to collect data about their users' interactions with the model. To test this feature, we need to create a simple application that uses the OpenAI API and sends telemetry data to their servers.\n\nHere's an example code in Python that demonstrates how to create a simple telemetry creator:\n\n```python\nimport os\nfrom openai.api import API\n\n# Initialize the OpenAI API client\napi = API(os.environ['OPENAI_API_KEY'])\n\ndef create_user():\n    # Create a new user entity\n    user_entity = {\n        'id': 'user-123',\n        'name': 'John Doe',\n        'email': 'john.doe@example.com'\n    }\n    \n    # Send the user creation request to OpenAI\n    response = api.users.create(user_entity)\n    print(f\"User created: {response}\")\n\ndef create_transaction():\n    # Create a new transaction entity\n    transaction_entity = {\n        'id': 'tran-123',\n        'user_id': 'user-123',\n        'transaction_type': 'query'\n    }\n    \n    # Send the transaction creation request to OpenAI\n    response = api.transactions.create(transaction_entity)\n    print(f\"Transaction created: {response}\")\n\ndef send_telemetry_data():\n    # Create a new telemetry event entity\n    telemetry_event_entity = {\n        'id': 'telem-123',\n        'transaction_id': 'tran-123',\n        'data': '{ \"event\": \"test\", \"user_id\": 1 }'\n    }\n    \n    # Send the telemetry data to OpenAI\n    response = api.telemetry.create(telemetry_event_entity)\n    print(f\"Telemetry event sent: {response}\")\n\n# Test the telemetry creation\ncreate_user()\ncreate_transaction()\nsend_telemetry_data()\n```\n\nMake sure you replace `OPENAI_API_KEY` with your actual API key. Also, ensure that you have the OpenAI API client library installed by running `pip install openai`.\n\nOnce you've created the test code, run it and observe the behavior of the telemetry creation process.\n\nPlease let me know if you need further modifications or assistance!",
+              "refusal": null,
+              "role": "assistant",
+              "annotations": null,
+              "audio": null,
+              "function_call": null,
+              "tool_calls": null
+            }
+          }
+        ],
+        "created": 0,
+        "model": "llama3.2:3b-instruct-fp16",
+        "object": "chat.completion",
+        "service_tier": null,
+        "system_fingerprint": "fp_ollama",
+        "usage": {
+          "completion_tokens": 460,
+          "prompt_tokens": 30,
+          "total_tokens": 490,
+          "completion_tokens_details": null,
+          "prompt_tokens_details": null
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

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

@@ -0,0 +1,59 @@
+{
+  "test_id": "tests/integration/telemetry/test_completions.py::test_telemetry_format_completeness[txt=ollama/llama3.2:3b-instruct-fp16]",
+  "request": {
+    "method": "POST",
+    "url": "http://0.0.0.0:11434/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "llama3.2:3b-instruct-fp16",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Test trace openai with temperature 0.7"
+        }
+      ],
+      "max_tokens": 100,
+      "stream": false,
+      "temperature": 0.7
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "llama3.2:3b-instruct-fp16"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+      "__data__": {
+        "id": "rec-1fcfd86d8111",
+        "choices": [
+          {
+            "finish_reason": "length",
+            "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",
+              "refusal": null,
+              "role": "assistant",
+              "annotations": null,
+              "audio": null,
+              "function_call": null,
+              "tool_calls": null
+            }
+          }
+        ],
+        "created": 0,
+        "model": "llama3.2:3b-instruct-fp16",
+        "object": "chat.completion",
+        "service_tier": null,
+        "system_fingerprint": "fp_ollama",
+        "usage": {
+          "completion_tokens": 100,
+          "prompt_tokens": 35,
+          "total_tokens": 135,
+          "completion_tokens_details": null,
+          "prompt_tokens_details": null
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/telemetry/recordings/dba5042d6691c2fbc29f2172c0f175e235f2829cb1c3e49781dd2b1850e28775.json

@@ -0,0 +1,59 @@
+{
+  "test_id": "tests/integration/telemetry/test_completions.py::test_telemetry_format_completeness[txt=llama3.2:3b-instruct-fp16]",
+  "request": {
+    "method": "POST",
+    "url": "http://localhost:11434/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "llama3.2:3b-instruct-fp16",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Test trace openai with temperature 0.7"
+        }
+      ],
+      "max_tokens": 100,
+      "stream": false,
+      "temperature": 0.7
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "llama3.2:3b-instruct-fp16"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+      "__data__": {
+        "id": "rec-dba5042d6691",
+        "choices": [
+          {
+            "finish_reason": "length",
+            "index": 0,
+            "logprobs": null,
+            "message": {
+              "content": "To test the \"trace\" functionality of OpenAI's GPT-4 model at a temperature of 0.7, you can follow these steps:\n\n1. First, make sure you have an account with OpenAI and have been granted access to their API.\n\n2. You will need to install the `transformers` library, which is the official library for working with Transformers models like GPT-4:\n\n   ```bash\npip install transformers\n```\n\n3. Next, import the necessary",
+              "refusal": null,
+              "role": "assistant",
+              "annotations": null,
+              "audio": null,
+              "function_call": null,
+              "tool_calls": null
+            }
+          }
+        ],
+        "created": 0,
+        "model": "llama3.2:3b-instruct-fp16",
+        "object": "chat.completion",
+        "service_tier": null,
+        "system_fingerprint": "fp_ollama",
+        "usage": {
+          "completion_tokens": 100,
+          "prompt_tokens": 35,
+          "total_tokens": 135,
+          "completion_tokens_details": null,
+          "prompt_tokens_details": null
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}