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/4096743baf8e.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 0"
+        }
+      ],
+      "stream": false
+    },
+    "endpoint": "/v1/completions",
+    "model": "llama3.2:3b-instruct-fp16"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+      "__data__": {
+        "id": "chatcmpl-695",
+        "choices": [
+          {
+            "finish_reason": "stop",
+            "index": 0,
+            "logprobs": null,
+            "message": {
+              "content": "You want to test the OpenAI API v0, but I need to clarify a few things.\n\nThe OpenAI API has undergone significant changes since its release in 2019. The v0 API was retired in favor of newer versions like v1 \"GPT-2\" and v3 \"GPT-3\".\n\nAfter verifying with OpenAI's Documentation: https://api.openai.com/docs/en/v1/basics, I found that there is no longer an API endpoint for testing with version 0.\n\nHowever, I can guide you through the steps to interact with the latest version of the OpenAI API, which should give you a similar experience:\n\nTo use the OpenAI v3 (GPT-3) API, you'll need to create an account on the OpenAI website and obtain an API key. Here are the general steps:\n\n1. Create an account on the OpenAI website: https://openai.com/\n2. Enable the API feature in your account settings\n3. Obtain an API key: go to your account dashboard \u2192 API\n4. Install a library that supports the v3 API, such as `python-openai` or `transformers`\n5. Use the library to send requests to the OpenAI API\n\nHere's some sample Python code using the `python-openai` library:\n\n```python\nimport openai\n\n# Initialize the OpenAI API client with your access token\naccess_token = \"YOUR_API_KEY_HERE\"\nopenai.api_key = access_token\nassistant = openai.pytorch.GPT3Small()\n\n# Test the assistant with a simple function call\nresponse = assistant.call(\n    prompt=\"Hello, how are you?\",\n)\nprint(response)\n```\n\nPlease note that this is just an example, and you should replace `YOUR_API_KEY_HERE` with your actual API key.\n\nIf you're interested in using an older version of the OpenAI API for testing, I can try to provide more guidance on implementing it. However, keep in mind that v0 is no longer supported by OpenAI, and this might lead to limitations or inconsistencies.",
+              "refusal": null,
+              "role": "assistant",
+              "annotations": null,
+              "audio": null,
+              "function_call": null,
+              "tool_calls": null
+            }
+          }
+        ],
+        "created": 1754051825,
+        "model": "llama3.2:3b-instruct-fp16",
+        "object": "chat.completion",
+        "service_tier": null,
+        "system_fingerprint": "fp_ollama",
+        "usage": {
+          "completion_tokens": 423,
+          "prompt_tokens": 31,
+          "total_tokens": 454,
+          "completion_tokens_details": null,
+          "prompt_tokens_details": null
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}