feat: introduce APIs for retrieving chat completion requests (#2145)

# What does this PR do?
This PR introduces APIs to retrieve past chat completion requests, which
will be used in the LS UI.

Our current `Telemetry` is ill-suited for this purpose as it's untyped
so we'd need to filter by obscure attribute names, making it brittle.

Since these APIs are 'provided by stack' and don't need to be
implemented by inference providers, we introduce a new InferenceProvider
class, containing the existing inference protocol, which is implemented
by inference providers.

The APIs are OpenAI-compliant, with an additional `input_messages`
field.


## Test Plan
This PR just adds the API and marks them provided_by_stack. S
tart stack server -> doesn't crash

llama_stack/providers/utils/inference/litellm_openai_mixin.py

@@ -19,7 +19,7 @@ from llama_stack.apis.inference import (
     ChatCompletionResponseStreamChunk,
     EmbeddingsResponse,
     EmbeddingTaskType,
-    Inference,
+    InferenceProvider,
     JsonSchemaResponseFormat,
     LogProbConfig,
     Message,
@@ -59,7 +59,7 @@ logger = get_logger(name=__name__, category="inference")
 
 class LiteLLMOpenAIMixin(
     ModelRegistryHelper,
-    Inference,
+    InferenceProvider,
     NeedsRequestProviderData,
 ):
     # TODO: avoid exposing the litellm specific model names to the user.