Lorenze/native inference sdks (#3619)

* ruff linted

* using native sdks with litellm fallback

* drop exa

* drop print on completion

* Refactor LLM and utility functions for type consistency

- Updated `max_tokens` parameter in `LLM` class to accept `float` in addition to `int`.
- Modified `create_llm` function to ensure consistent type hints and return types, now returning `LLM | BaseLLM | None`.
- Adjusted type hints for various parameters in `create_llm` and `_llm_via_environment_or_fallback` functions for improved clarity and type safety.
- Enhanced test cases to reflect changes in type handling and ensure proper instantiation of LLM instances.

* fix agent_tests

* fix litellm tests and usagemetrics fix

* drop print

* Refactor LLM event handling and improve test coverage

- Removed commented-out event emission for LLM call failures in `llm.py`.
- Added `from_agent` parameter to `CrewAgentExecutor` for better context in LLM responses.
- Enhanced test for LLM call failure to simulate OpenAI API failure and updated assertions for clarity.
- Updated agent and task ID assertions in tests to ensure they are consistently treated as strings.

* fix test_converter

* fixed tests/agents/test_agent.py

* Refactor LLM context length exception handling and improve provider integration

- Renamed `LLMContextLengthExceededException` to `LLMContextLengthExceededExceptionError` for clarity and consistency.
- Updated LLM class to pass the provider parameter correctly during initialization.
- Enhanced error handling in various LLM provider implementations to raise the new exception type.
- Adjusted tests to reflect the updated exception name and ensure proper error handling in context length scenarios.

* Enhance LLM context window handling across providers

- Introduced CONTEXT_WINDOW_USAGE_RATIO to adjust context window sizes dynamically for Anthropic, Azure, Gemini, and OpenAI LLMs.
- Added validation for context window sizes in Azure and Gemini providers to ensure they fall within acceptable limits.
- Updated context window size calculations to use the new ratio, improving consistency and adaptability across different models.
- Removed hardcoded context window sizes in favor of ratio-based calculations for better flexibility.

* fix test agent again

* fix test agent

* feat: add native LLM providers for Anthropic, Azure, and Gemini

- Introduced new completion implementations for Anthropic, Azure, and Gemini, integrating their respective SDKs.
- Added utility functions for tool validation and extraction to support function calling across LLM providers.
- Enhanced context window management and token usage extraction for each provider.
- Created a common utility module for shared functionality among LLM providers.

* chore: update dependencies and improve context management

- Removed direct dependency on `litellm` from the main dependencies and added it under extras for better modularity.
- Updated the `litellm` dependency specification to allow for greater flexibility in versioning.
- Refactored context length exception handling across various LLM providers to use a consistent error class.
- Enhanced platform-specific dependency markers for NVIDIA packages to ensure compatibility across different systems.

* refactor(tests): update LLM instantiation to include is_litellm flag in test cases

- Modified multiple test cases in test_llm.py to set the is_litellm parameter to True when instantiating the LLM class.
- This change ensures that the tests are aligned with the latest LLM configuration requirements and improves consistency across test scenarios.
- Adjusted relevant assertions and comments to reflect the updated LLM behavior.

* linter

* linted

* revert constants

* fix(tests): correct type hint in expected model description

- Updated the expected description in the test_generate_model_description_dict_field function to use 'Dict' instead of 'dict' for consistency with type hinting conventions.
- This change ensures that the test accurately reflects the expected output format for model descriptions.

* refactor(llm): enhance LLM instantiation and error handling

- Updated the LLM class to include validation for the model parameter, ensuring it is a non-empty string.
- Improved error handling by logging warnings when the native SDK fails, allowing for a fallback to LiteLLM.
- Adjusted the instantiation of LLM in test cases to consistently include the is_litellm flag, aligning with recent changes in LLM configuration.
- Modified relevant tests to reflect these updates, ensuring better coverage and accuracy in testing scenarios.

* fixed test

* refactor(llm): enhance token usage tracking and add copy methods

- Updated the LLM class to track token usage and log callbacks in streaming mode, improving monitoring capabilities.
- Introduced shallow and deep copy methods for the LLM instance, allowing for better management of LLM configurations and parameters.
- Adjusted test cases to instantiate LLM with the is_litellm flag, ensuring alignment with recent changes in LLM configuration.

* refactor(tests): reorganize imports and enhance error messages in test cases

- Cleaned up import statements in test_crew.py for better organization and readability.
- Enhanced error messages in test cases to use `re.escape` for improved regex matching, ensuring more robust error handling.
- Adjusted comments for clarity and consistency across test scenarios.
- Ensured that all necessary modules are imported correctly to avoid potential runtime issues.

lib/crewai/tests/utilities/test_converter.py

@@ -1,12 +1,9 @@
-import json
-import os
-
 # Tests for enums
 from enum import Enum
-from typing import Dict, List, Optional
+import json
+import os
 from unittest.mock import MagicMock, Mock, patch
 
-import pytest
 from crewai.llm import LLM
 from crewai.utilities.converter import (
     Converter,
@@ -21,6 +18,7 @@ from crewai.utilities.converter import (
 )
 from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 from pydantic import BaseModel
+import pytest
 
 
 @pytest.fixture(scope="module")
@@ -254,7 +252,7 @@ def test_supports_function_calling_true():
 
 
 def test_supports_function_calling_false():
-    llm = LLM(model="non-existent-model")
+    llm = LLM(model="non-existent-model", is_litellm=True)
     assert llm.supports_function_calling() is False
 
 
@@ -311,17 +309,17 @@ def test_generate_model_description_nested_model():
 
 def test_generate_model_description_optional_field():
     class ModelWithOptionalField(BaseModel):
-        name: Optional[str]
-        age: int
+        name: str
+        age: int | None
 
     description = generate_model_description(ModelWithOptionalField)
-    expected_description = '{\n  "name": Optional[str],\n  "age": int\n}'
+    expected_description = '{\n  "name": str,\n  "age": int | None\n}'
     assert description == expected_description
 
 
 def test_generate_model_description_list_field():
     class ModelWithListField(BaseModel):
-        items: List[int]
+        items: list[int]
 
     description = generate_model_description(ModelWithListField)
     expected_description = '{\n  "items": List[int]\n}'
@@ -330,7 +328,7 @@ def test_generate_model_description_list_field():
 
 def test_generate_model_description_dict_field():
     class ModelWithDictField(BaseModel):
-        attributes: Dict[str, int]
+        attributes: dict[str, int]
 
     description = generate_model_description(ModelWithDictField)
     expected_description = '{\n  "attributes": Dict[str, int]\n}'
@@ -470,7 +468,7 @@ def test_converter_retry_logic():
 def test_converter_with_optional_fields():
     class OptionalModel(BaseModel):
         name: str
-        age: Optional[int]
+        age: int | None
 
     llm = Mock(spec=LLM)
     llm.supports_function_calling.return_value = False
@@ -496,7 +494,7 @@ def test_converter_with_optional_fields():
 # Tests for list fields
 def test_converter_with_list_field():
     class ListModel(BaseModel):
-        items: List[int]
+        items: list[int]
 
     llm = Mock(spec=LLM)
     llm.supports_function_calling.return_value = False