fix: Don't cache clients for passthrough auth providers (#2728)

# What does this PR do?

Some of our inference providers support passthrough authentication via
`x-llamastack-provider-data` header values. This fixes the providers
that support passthrough auth to not cache their clients to the backend
providers (mostly OpenAI client instances) so that the client connecting
to Llama Stack has to provide those auth values on each and every
request.

## Test Plan

I added some unit tests to ensure we're not caching clients across
requests for all the fixed providers in this PR.

```
uv run pytest -sv tests/unit/providers/inference/test_inference_client_caching.py
```


I also ran some of our OpenAI compatible API integration tests for each
of the changed providers, just to ensure they still work. Note that
these providers don't actually pass all these tests (for unrelated
reasons due to quirks of the Groq and Together SaaS services), but
enough of the tests passed to confirm the clients are still working as
intended.

### Together

```
ENABLE_TOGETHER="together" \
uv run llama stack run llama_stack/templates/starter/run.yaml

LLAMA_STACK_CONFIG=http://localhost:8321 \
uv run pytest -sv \
  tests/integration/inference/test_openai_completion.py \
  --text-model "together/meta-llama/Llama-3.1-8B-Instruct"
```

### OpenAI

```
ENABLE_OPENAI="openai" \
uv run llama stack run llama_stack/templates/starter/run.yaml

LLAMA_STACK_CONFIG=http://localhost:8321 \
uv run pytest -sv \
  tests/integration/inference/test_openai_completion.py \
  --text-model "openai/gpt-4o-mini"
```

### Groq

```
ENABLE_GROQ="groq" \
uv run llama stack run llama_stack/templates/starter/run.yaml

LLAMA_STACK_CONFIG=http://localhost:8321 \
uv run pytest -sv \
  tests/integration/inference/test_openai_completion.py \
  --text-model "groq/meta-llama/Llama-3.1-8B-Instruct"
```

---------

Signed-off-by: Ben Browning <bbrownin@redhat.com>

llama_stack/providers/remote/inference/together/together.py

@@ -68,19 +68,12 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
     def __init__(self, config: TogetherImplConfig) -> None:
         ModelRegistryHelper.__init__(self, MODEL_ENTRIES)
         self.config = config
-        self._client = None
-        self._openai_client = None
 
     async def initialize(self) -> None:
         pass
 
     async def shutdown(self) -> None:
-        if self._client:
-            # Together client has no close method, so just set to None
-            self._client = None
-        if self._openai_client:
-            await self._openai_client.close()
-            self._openai_client = None
+        pass
 
     async def completion(
         self,
@@ -108,29 +101,25 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
             return await self._nonstream_completion(request)
 
     def _get_client(self) -> AsyncTogether:
-        if not self._client:
-            together_api_key = None
-            config_api_key = self.config.api_key.get_secret_value() if self.config.api_key else None
-            if config_api_key:
-                together_api_key = config_api_key
-            else:
-                provider_data = self.get_request_provider_data()
-                if provider_data is None or not provider_data.together_api_key:
-                    raise ValueError(
-                        'Pass Together API Key in the header X-LlamaStack-Provider-Data as { "together_api_key": <your api key>}'
-                    )
-                together_api_key = provider_data.together_api_key
-            self._client = AsyncTogether(api_key=together_api_key)
-        return self._client
+        together_api_key = None
+        config_api_key = self.config.api_key.get_secret_value() if self.config.api_key else None
+        if config_api_key:
+            together_api_key = config_api_key
+        else:
+            provider_data = self.get_request_provider_data()
+            if provider_data is None or not provider_data.together_api_key:
+                raise ValueError(
+                    'Pass Together API Key in the header X-LlamaStack-Provider-Data as { "together_api_key": <your api key>}'
+                )
+            together_api_key = provider_data.together_api_key
+        return AsyncTogether(api_key=together_api_key)
 
     def _get_openai_client(self) -> AsyncOpenAI:
-        if not self._openai_client:
-            together_client = self._get_client().client
-            self._openai_client = AsyncOpenAI(
-                base_url=together_client.base_url,
-                api_key=together_client.api_key,
-            )
-        return self._openai_client
+        together_client = self._get_client().client
+        return AsyncOpenAI(
+            base_url=together_client.base_url,
+            api_key=together_client.api_key,
+        )
 
     async def _nonstream_completion(self, request: CompletionRequest) -> ChatCompletionResponse:
         params = await self._get_params(request)