Fix YAML agent ignoring model.options execution settings (#13365)

## Summary

Fixes #13349 

When loading agents from YAML files using
`AgentRegistry.create_from_file()` or `create_from_yaml()`, the
`model.options` field (containing settings like `response_format`,
`temperature`, etc.) were being added as regular `KernelArguments` dict
items instead of being placed in the `execution_settings` property. This
caused AI service calls to ignore these critical settings.

## Root Cause

In `_normalize_spec_fields()` method in
`python/semantic_kernel/agents/agent.py`, model options were being
passed to `KernelArguments` constructor as `**kwargs`:

```python
# OLD (buggy) CODE
arguments = KernelArguments(**model_options)
```

This made them regular dict items, but execution settings need to be in
the `execution_settings` property to be passed to AI services.

## Changes

Modified `_normalize_spec_fields()` in
`python/semantic_kernel/agents/agent.py`:
- Added import for `PromptExecutionSettings`
- Convert model.options to `PromptExecutionSettings` object before
creating `KernelArguments`
- Model options now correctly placed in `execution_settings` property
- Input defaults continue to be added as regular dict items (correct
behavior)

## Testing

- ✅ Created custom test verifying model.options are now in
execution_settings
- ✅ All 30 existing unit tests in `tests/unit/agents/test_agent.py` pass
- ✅ No breaking changes introduced
- ✅ Verified execution_settings passed programmatically still work
correctly

## Example

YAML file:
```yaml
type: chat_completion_agent
name: TestAgent
description: Test agent
instructions: You are a test agent
model:
  options:
    response_format: structured_output
    temperature: 0.7
```

**Before this fix:**
- `response_format` was in dict items (wrong location)
- AI service calls ignored it

**After this fix:**
- `response_format` is in `execution_settings.extension_data`
- AI service calls receive it properly

Author: yashwantbezawada

python/semantic_kernel/agents/agent.py

@@ -13,6 +13,7 @@
 from pydantic import Field, model_validator
 
 from semantic_kernel.agents.channels.agent_channel import AgentChannel
+from semantic_kernel.connectors.ai.prompt_execution_settings import PromptExecutionSettings
 from semantic_kernel.contents.chat_message_content import CMC_ITEM_TYPES, ChatMessageContent
 from semantic_kernel.contents.streaming_chat_message_content import StreamingChatMessageContent
 from semantic_kernel.contents.utils.author_role import AuthorRole
@@ -998,9 +999,19 @@ def _normalize_spec_fields(
             if v.get("default") is not None
         }
 
-        # Start with model options
-        arguments = KernelArguments(**model_options)
-        # Update with input defaults (only if not already provided by model options)
+        # Convert model options to execution settings
+        # Model options (like response_format, temperature, etc.) should be execution settings,
+        # not regular arguments
+        if model_options:
+            # Create PromptExecutionSettings from model options
+            # The PromptExecutionSettings constructor handles **kwargs by putting them in extension_data
+            # and then unpacking them to actual fields if they exist
+            exec_settings = PromptExecutionSettings(**model_options)
+            arguments = KernelArguments(settings=exec_settings)
+        else:
+            arguments = KernelArguments()
+
+        # Add input defaults as regular dict items (not execution settings)
         for k, v in input_defaults.items():
             if k not in arguments:
                 arguments[k] = v