test

# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
Completes the refactoring started in previous commit by:

1. **Fix library client** (critical): Add logic to detect Pydantic model parameters
   and construct them properly from request bodies. The key fix is to NOT exclude
   any params when converting the body for Pydantic models - we need all fields
   to pass to the Pydantic constructor.

   Before: _convert_body excluded all params, leaving body empty for Pydantic construction
   After: Check for Pydantic params first, skip exclusion, construct model with full body

2. **Update remaining providers** to use new Pydantic-based signatures:
   - litellm_openai_mixin: Extract extra fields via __pydantic_extra__
   - databricks: Use TYPE_CHECKING import for params type
   - llama_openai_compat: Use TYPE_CHECKING import for params type
   - sentence_transformers: Update method signatures to use params

3. **Update unit tests** to use new Pydantic signature:
   - test_openai_mixin.py: Use OpenAIChatCompletionRequestParams

This fixes test failures where the library client was trying to construct
Pydantic models with empty dictionaries.
The previous fix had a bug: it called _convert_body() which only keeps fields
that match function parameter names. For Pydantic methods with signature:
  openai_chat_completion(params: OpenAIChatCompletionRequestParams)

The signature only has 'params', but the body has 'model', 'messages', etc.
So _convert_body() returned an empty dict.

Fix: Skip _convert_body() entirely for Pydantic params. Use the raw body
directly to construct the Pydantic model (after stripping NOT_GIVENs).

This properly fixes the ValidationError where required fields were missing.
The streaming code path (_call_streaming) had the same issue as non-streaming:
it called _convert_body() which returned empty dict for Pydantic params.

Applied the same fix as commit 7476c0ae:
- Detect Pydantic model parameters before body conversion
- Skip _convert_body() for Pydantic params
- Construct Pydantic model directly from raw body (after stripping NOT_GIVENs)

This fixes streaming endpoints like openai_chat_completion with stream=True.
The streaming code path (_call_streaming) had the same issue as non-streaming:
it called _convert_body() which returned empty dict for Pydantic params.

Applied the same fix as commit 7476c0ae:
- Detect Pydantic model parameters before body conversion
- Skip _convert_body() for Pydantic params
- Construct Pydantic model directly from raw body (after stripping NOT_GIVENs)

This fixes streaming endpoints like openai_chat_completion with stream=True.

llama_stack/providers/inline/safety/llama_guard/llama_guard.py

@@ -10,7 +10,13 @@ from string import Template
 from typing import Any
 
 from llama_stack.apis.common.content_types import ImageContentItem, TextContentItem
-from llama_stack.apis.inference import Inference, Message, UserMessage
+from llama_stack.apis.inference import (
+    Inference,
+    Message,
+    OpenAIChatCompletionRequestParams,
+    OpenAIUserMessageParam,
+    UserMessage,
+)
 from llama_stack.apis.safety import (
     RunShieldResponse,
     Safety,
@@ -290,20 +296,21 @@ class LlamaGuardShield:
         else:
             shield_input_message = self.build_text_shield_input(messages)
 
-        response = await self.inference_api.openai_chat_completion(
+        params = OpenAIChatCompletionRequestParams(
             model=self.model,
             messages=[shield_input_message],
             stream=False,
             temperature=0.0,  # default is 1, which is too high for safety
         )
+        response = await self.inference_api.openai_chat_completion(params)
         content = response.choices[0].message.content
         content = content.strip()
         return self.get_shield_response(content)
 
-    def build_text_shield_input(self, messages: list[Message]) -> UserMessage:
-        return UserMessage(content=self.build_prompt(messages))
+    def build_text_shield_input(self, messages: list[Message]) -> OpenAIUserMessageParam:
+        return OpenAIUserMessageParam(role="user", content=self.build_prompt(messages))
 
-    def build_vision_shield_input(self, messages: list[Message]) -> UserMessage:
+    def build_vision_shield_input(self, messages: list[Message]) -> OpenAIUserMessageParam:
         conversation = []
         most_recent_img = None
 
@@ -335,7 +342,7 @@ class LlamaGuardShield:
             prompt.append(most_recent_img)
         prompt.append(self.build_prompt(conversation[::-1]))
 
-        return UserMessage(content=prompt)
+        return OpenAIUserMessageParam(role="user", content=prompt)
 
     def build_prompt(self, messages: list[Message]) -> str:
         categories = self.get_safety_categories()
@@ -377,11 +384,12 @@ class LlamaGuardShield:
         # TODO: Add Image based support for OpenAI Moderations
         shield_input_message = self.build_text_shield_input(messages)
 
-        response = await self.inference_api.openai_chat_completion(
+        params = OpenAIChatCompletionRequestParams(
             model=self.model,
             messages=[shield_input_message],
             stream=False,
         )
+        response = await self.inference_api.openai_chat_completion(params)
         content = response.choices[0].message.content
         content = content.strip()
         return self.get_moderation_object(content)