refactor(provider): simplify LiteLLM requester usage handling

- Remove unused Anthropic-specific tool schema generation
  - Share completion argument construction between normal and streaming calls
  - Use LiteLLM/OpenAI native usage fields for monitoring
  - Collect stream token usage from LiteLLM stream_options
  - Update LiteLLM requester tests for unified usage fields

tests/unit_tests/provider/test_litellmchat.py

@@ -93,8 +93,6 @@ class TestExtractUsage:
         assert result['prompt_tokens'] == 100
         assert result['completion_tokens'] == 50
         assert result['total_tokens'] == 150
-        assert result['input_tokens'] == 100  # Compatibility alias
-        assert result['output_tokens'] == 50  # Compatibility alias
 
     def test_extract_usage_with_zero_values(self):
         """Test extraction when values are 0"""

tests/unit_tests/provider/test_tool_manager.py

@@ -1,7 +1,7 @@
 """Unit tests for ToolManager.
 
 Tests cover:
-- Tool schema generation for OpenAI and Anthropic
+- Tool schema generation for OpenAI/LiteLLM
 - Tool execution dispatch
 """
 
@@ -109,28 +109,6 @@ class TestToolManagerSchemaGeneration:
         assert tool2['type'] == 'function'
         assert tool2['function']['name'] == 'calculate'
 
-    @pytest.mark.asyncio
-    async def test_generate_tools_for_anthropic(self, mock_app, sample_tools):
-        """Test that generate_tools_for_anthropic produces correct schema."""
-        toolmgr = get_toolmgr_module()
-
-        manager = toolmgr.ToolManager(mock_app)
-        result = await manager.generate_tools_for_anthropic(sample_tools)
-
-        assert len(result) == 2
-
-        # Verify first tool schema (Anthropic format)
-        tool1 = result[0]
-        assert tool1['name'] == 'get_weather'
-        assert tool1['description'] == 'Get current weather for a location'
-        assert 'input_schema' in tool1
-        assert tool1['input_schema']['type'] == 'object'
-
-        # Verify second tool schema
-        tool2 = result[1]
-        assert tool2['name'] == 'calculate'
-        assert 'input_schema' in tool2
-
     @pytest.mark.asyncio
     async def test_generate_tools_empty_list(self, mock_app):
         """Test that generating tools from empty list returns empty list."""
@@ -141,9 +119,6 @@ class TestToolManagerSchemaGeneration:
         openai_result = await manager.generate_tools_for_openai([])
         assert openai_result == []
 
-        anthropic_result = await manager.generate_tools_for_anthropic([])
-        assert anthropic_result == []
-
     @pytest.mark.asyncio
     async def test_openai_schema_fields_complete(self, mock_app, sample_tools):
         """Test that OpenAI schema includes all required fields."""
@@ -161,20 +136,6 @@ class TestToolManagerSchemaGeneration:
             assert 'description' in func
             assert 'parameters' in func
 
-    @pytest.mark.asyncio
-    async def test_anthropic_schema_fields_complete(self, mock_app, sample_tools):
-        """Test that Anthropic schema includes all required fields."""
-        toolmgr = get_toolmgr_module()
-
-        manager = toolmgr.ToolManager(mock_app)
-        result = await manager.generate_tools_for_anthropic(sample_tools)
-
-        for tool_schema in result:
-            assert 'name' in tool_schema
-            assert 'description' in tool_schema
-            assert 'input_schema' in tool_schema
-
-
 class TestToolManagerExecuteFuncCall:
     """Tests for execute_func_call method."""