refactor: remove dead inference API code and clean up imports (#4093)

# What does this PR do?

Delete ~2,000 lines of dead code from the old bespoke inference API that
was replaced by OpenAI-only API. This includes removing unused type
conversion functions, dead provider methods, and event_logger.py.

Clean up imports across the codebase to remove references to deleted
types. This eliminates unnecessary
code and dependencies, helping isolate the API package as a
self-contained module.

This is the last interdependency between the .api package and "exterior"
packages, meaning that now every other package in llama stack imports
the API, not the other way around.

## Test Plan

this is a structural change, no tests needed.

---------

Signed-off-by: Charlie Doern <cdoern@redhat.com>

tests/unit/providers/nvidia/test_safety.py

@@ -10,11 +10,13 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
-from llama_stack.apis.inference import CompletionMessage, UserMessage
+from llama_stack.apis.inference import (
+    OpenAIAssistantMessageParam,
+    OpenAIUserMessageParam,
+)
 from llama_stack.apis.resource import ResourceType
 from llama_stack.apis.safety import RunShieldResponse, ViolationLevel
 from llama_stack.apis.shields import Shield
-from llama_stack.models.llama.datatypes import StopReason
 from llama_stack.providers.remote.safety.nvidia.config import NVIDIASafetyConfig
 from llama_stack.providers.remote.safety.nvidia.nvidia import NVIDIASafetyAdapter
 
@@ -136,11 +138,9 @@ async def test_run_shield_allowed(nvidia_adapter, mock_guardrails_post):
 
     # Run the shield
     messages = [
-        UserMessage(role="user", content="Hello, how are you?"),
-        CompletionMessage(
-            role="assistant",
+        OpenAIUserMessageParam(content="Hello, how are you?"),
+        OpenAIAssistantMessageParam(
             content="I'm doing well, thank you for asking!",
-            stop_reason=StopReason.end_of_message,
             tool_calls=[],
         ),
     ]
@@ -191,13 +191,10 @@ async def test_run_shield_blocked(nvidia_adapter, mock_guardrails_post):
     # Mock Guardrails API response
     mock_guardrails_post.return_value = {"status": "blocked", "rails_status": {"reason": "harmful_content"}}
 
-    # Run the shield
     messages = [
-        UserMessage(role="user", content="Hello, how are you?"),
-        CompletionMessage(
-            role="assistant",
+        OpenAIUserMessageParam(content="Hello, how are you?"),
+        OpenAIAssistantMessageParam(
             content="I'm doing well, thank you for asking!",
-            stop_reason=StopReason.end_of_message,
             tool_calls=[],
         ),
     ]
@@ -243,7 +240,7 @@ async def test_run_shield_not_found(nvidia_adapter, mock_guardrails_post):
     adapter.shield_store.get_shield.return_value = None
 
     messages = [
-        UserMessage(role="user", content="Hello, how are you?"),
+        OpenAIUserMessageParam(content="Hello, how are you?"),
     ]
 
     with pytest.raises(ValueError):
@@ -274,11 +271,9 @@ async def test_run_shield_http_error(nvidia_adapter, mock_guardrails_post):
 
     # Running the shield should raise an exception
     messages = [
-        UserMessage(role="user", content="Hello, how are you?"),
-        CompletionMessage(
-            role="assistant",
+        OpenAIUserMessageParam(content="Hello, how are you?"),
+        OpenAIAssistantMessageParam(
             content="I'm doing well, thank you for asking!",
-            stop_reason=StopReason.end_of_message,
             tool_calls=[],
         ),
     ]