remove conflicting default for tool prompt format in chat completion (#742)

# What does this PR do?
We are setting a default value of json for tool prompt format, which
conflicts with llama 3.2/3.3 models since they use python list. This PR
changes the defaults to None and in the code, we infer default based on
the model.

Addresses: #695 

Tests:
❯ LLAMA_STACK_BASE_URL=http://localhost:5000 pytest -v
tests/client-sdk/inference/test_inference.py -k
"test_text_chat_completion"

 pytest llama_stack/providers/tests/inference/test_prompt_adapter.py

llama_stack/providers/remote/inference/nvidia/nvidia.py

@@ -175,9 +175,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
         response_format: Optional[ResponseFormat] = None,
         tools: Optional[List[ToolDefinition]] = None,
         tool_choice: Optional[ToolChoice] = ToolChoice.auto,
-        tool_prompt_format: Optional[
-            ToolPromptFormat
-        ] = None,  # API default is ToolPromptFormat.json, we default to None to detect user input
+        tool_prompt_format: Optional[ToolPromptFormat] = None,
         stream: Optional[bool] = False,
         logprobs: Optional[LogProbConfig] = None,
     ) -> Union[