fix: telemetry fixes (inference and core telemetry) (#2733)

# What does this PR do?

I found a few issues while adding new metrics for various APIs:

currently metrics are only propagated in `chat_completion` and
`completion`

since most providers use the `openai_..` routes as the default in
`llama-stack-client inference chat-completion`, metrics are currently
not working as expected.

in order to get them working the following had to be done:

1. get the completion as usual
2. use new `openai_` versions of the metric gathering functions which
use `.usage` from the `OpenAI..` response types to gather the metrics
which are already populated.
3. define a `stream_generator` which counts the tokens and computes the
metrics (only for stream=True)
5. add metrics to response


NOTE: I could not add metrics to `openai_completion` where stream=True
because that ONLY returns an `OpenAICompletion` not an AsyncGenerator
that we can manipulate.


acquire the lock, and add event to the span as the other `_log_...`
methods do

some new output:

`llama-stack-client inference chat-completion --message hi`

<img width="2416" height="425" alt="Screenshot 2025-07-16 at 8 28 20 AM"
src="https://github.com/user-attachments/assets/ccdf1643-a184-4ddd-9641-d426c4d51326"
/>


and in the client:

<img width="763" height="319" alt="Screenshot 2025-07-16 at 8 28 32 AM"
src="https://github.com/user-attachments/assets/6bceb811-5201-47e9-9e16-8130f0d60007"
/>

these were not previously being recorded nor were they being printed to
the server due to the improper console sink handling

---------

Signed-off-by: Charlie Doern <cdoern@redhat.com>

tests/integration/recordings/responses/d4f56d7d1996.json

@@ -0,0 +1,56 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://localhost:11434/v1/v1/completions",
+    "headers": {},
+    "body": {
+      "model": "llama3.2:3b-instruct-fp16",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Test trace openai 2"
+        }
+      ],
+      "stream": false
+    },
+    "endpoint": "/v1/completions",
+    "model": "llama3.2:3b-instruct-fp16"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+      "__data__": {
+        "id": "chatcmpl-273",
+        "choices": [
+          {
+            "finish_reason": "stop",
+            "index": 0,
+            "logprobs": null,
+            "message": {
+              "content": "I'd be happy to help you test the OpenAI 2 model, also known as GPT-2. Keep in mind that I'll be providing information and guidance based on publicly available resources, and not directly testing the model myself.\n\nOpenAI 2 is a large language model developed by OpenAI Research, which was released in 2019. It's a transformer-based model with 1.5 billion parameters, making it one of the largest language models at that time.\n\nTo test the OpenAI 2 model, you can try the following:\n\n1. **Read the paper**: Start by reading the original paper published in the ArXiv preprint repository [1]. This will give you a deeper understanding of the model's architecture and capabilities.\n2. **Use online generators**: Websites like [2] and [3] provide interactive interfaces to test and generate text using the OpenAI 2 model.\n3. **Try code examples**: You can find code examples in various programming languages, such as Python, that demonstrate how to use the OpenAI 2 model for tasks like text processing and generation.\n\nSome specific things you might want to try when testing OpenAI 2 include:\n\n* Generating coherent paragraphs on a given topic\n* Answering questions based on context\n* Completing sentences or stories with missing information\n* Translating short texts from one language to another\n\nKeep in mind that the OpenAI 2 model is quite large and computationally intensive, so it might not be suitable for use on all devices or platforms.\n\nReferences:\n\n[1] Radford, A., Narasimhan, K., Salimans, T., & Sutskever, I. (2019). Improving Language Understanding by Generative Pre-Training. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL).\n\n[2] https://beta.openai.com/ (use the \"chat\" interface to interact with the OpenAI 2 model)\n\n[3] https://gpt2-test.openai.co/ (test a demo version of the OpenAI 2 model)\n\nI hope this helps! If you have any specific questions or need further guidance, feel free to ask.",
+              "refusal": null,
+              "role": "assistant",
+              "annotations": null,
+              "audio": null,
+              "function_call": null,
+              "tool_calls": null
+            }
+          }
+        ],
+        "created": 1754051834,
+        "model": "llama3.2:3b-instruct-fp16",
+        "object": "chat.completion",
+        "service_tier": null,
+        "system_fingerprint": "fp_ollama",
+        "usage": {
+          "completion_tokens": 450,
+          "prompt_tokens": 31,
+          "total_tokens": 481,
+          "completion_tokens_details": null,
+          "prompt_tokens_details": null
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}