chore: refactor (chat)completions endpoints to use shared params struct (#3761)

# What does this PR do?

Converts openai(_chat)_completions params to pydantic BaseModel to
reduce code duplication across all providers.

## Test Plan
CI









---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/llamastack/llama-stack/pull/3761).
* #3777
* __->__ #3761

docs/static/llama-stack-spec.yaml

@@ -98,7 +98,7 @@ paths:
         content:
           application/json:
             schema:
-              $ref: '#/components/schemas/OpenaiChatCompletionRequest'
+              $ref: '#/components/schemas/OpenAIChatCompletionRequest'
         required: true
       deprecated: false
   /v1/chat/completions/{completion_id}:
@@ -167,7 +167,7 @@ paths:
         content:
           application/json:
             schema:
-              $ref: '#/components/schemas/OpenaiCompletionRequest'
+              $ref: '#/components/schemas/OpenAICompletionRequest'
         required: true
       deprecated: false
   /v1/conversations:
@@ -3824,7 +3824,7 @@ components:
       title: OpenAIResponseFormatText
       description: >-
         Text response format for OpenAI-compatible chat completion requests.
-    OpenaiChatCompletionRequest:
+    OpenAIChatCompletionRequest:
       type: object
       properties:
         model:
@@ -3966,7 +3966,9 @@ components:
       required:
         - model
         - messages
-      title: OpenaiChatCompletionRequest
+      title: OpenAIChatCompletionRequest
+      description: >-
+        Request parameters for OpenAI-compatible chat completion endpoint.
     OpenAIChatCompletion:
       type: object
       properties:
@@ -4132,7 +4134,7 @@ components:
         - model
         - input_messages
       title: OpenAICompletionWithInputMessages
-    OpenaiCompletionRequest:
+    OpenAICompletionRequest:
       type: object
       properties:
         model:
@@ -4224,8 +4226,14 @@ components:
           type: array
           items:
             type: string
+          description: >-
+            (Optional) vLLM-specific parameter for guided generation with a list of
+            choices.
         prompt_logprobs:
           type: integer
+          description: >-
+            (Optional) vLLM-specific parameter for number of log probabilities to
+            return for prompt tokens.
         suffix:
           type: string
           description: >-
@@ -4234,7 +4242,9 @@ components:
       required:
         - model
         - prompt
-      title: OpenaiCompletionRequest
+      title: OpenAICompletionRequest
+      description: >-
+        Request parameters for OpenAI-compatible completion endpoint.
     OpenAICompletion:
       type: object
       properties: