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/agents/meta_reference/agent_instance.py

@@ -49,6 +49,7 @@ from llama_stack.apis.inference import (
     Inference,
     Message,
     OpenAIAssistantMessageParam,
+    OpenAIChatCompletionRequestParams,
     OpenAIDeveloperMessageParam,
     OpenAIMessageParam,
     OpenAISystemMessageParam,
@@ -582,7 +583,7 @@ class ChatAgent(ShieldRunnerMixin):
                 max_tokens = getattr(sampling_params, "max_tokens", None)
 
                 # Use OpenAI chat completion
-                openai_stream = await self.inference_api.openai_chat_completion(
+                params = OpenAIChatCompletionRequestParams(
                     model=self.agent_config.model,
                     messages=openai_messages,
                     tools=openai_tools if openai_tools else None,
@@ -593,6 +594,7 @@ class ChatAgent(ShieldRunnerMixin):
                     max_tokens=max_tokens,
                     stream=True,
                 )
+                openai_stream = await self.inference_api.openai_chat_completion(params)
 
                 # Convert OpenAI stream back to Llama Stack format
                 response_stream = convert_openai_chat_completion_stream(

llama_stack/providers/inline/agents/meta_reference/responses/streaming.py

@@ -41,6 +41,7 @@ from llama_stack.apis.inference import (
     Inference,
     OpenAIAssistantMessageParam,
     OpenAIChatCompletion,
+    OpenAIChatCompletionRequestParams,
     OpenAIChatCompletionToolCall,
     OpenAIChoice,
     OpenAIMessageParam,
@@ -130,7 +131,7 @@ class StreamingResponseOrchestrator:
             # (some providers don't support non-empty response_format when tools are present)
             response_format = None if self.ctx.response_format.type == "text" else self.ctx.response_format
             logger.debug(f"calling openai_chat_completion with tools: {self.ctx.chat_tools}")
-            completion_result = await self.inference_api.openai_chat_completion(
+            params = OpenAIChatCompletionRequestParams(
                 model=self.ctx.model,
                 messages=messages,
                 tools=self.ctx.chat_tools,
@@ -138,6 +139,7 @@ class StreamingResponseOrchestrator:
                 temperature=self.ctx.temperature,
                 response_format=response_format,
             )
+            completion_result = await self.inference_api.openai_chat_completion(params)
 
             # Process streaming chunks and build complete response
             completion_result_data = None