* feat: add tool_call emulation for OpenAI API
Avoid forcing PollinationsAI when tools are present, and add an opt-in tool_emulation mode (or G4F_TOOL_EMULATION=1) to emit OpenAI-compatible tool_calls for providers that ignore tools.
* fix: avoid duplicate stream kwarg in tool emulation
Tool emulation calls the upstream provider with stream=False; remove stream/stream_timeout from forwarded kwargs to prevent conflicts.
* fix: prefer non-auth providers when api_key missing
When routing via AnyProvider without an api_key, try providers with needs_auth=false first to reduce MissingAuthError for tool-enabled clients like MarksCode.
* test: cover tool call emulation
Route tool_emulation through ToolSupportProvider (avoid circular imports) and add unittest coverage for multi-tool JSON plans and run_tools integration.
- Added `create_function` and `async_create_function` class attributes with default implementations in `base_provider.py` for `AbstractProvider`, `AsyncProvider`, and `AsyncGeneratorProvider`
- Updated `get_create_function` and `get_async_create_function` methods to return these class attributes
- Replaced calls to `provider.get_create_function()` and `provider.get_async_create_function()` with direct attribute access `provider.create_function` and `provider.async_create_function` across `g4f/__init__.py`, `g4f/client/__init__.py`, `g4f/providers/retry_provider.py`, and `g4f/tools/run_tools.py`
- Removed redundant `get_create_function` and `get_async_create_function` methods from `providers/base_provider.py` and `providers/types.py`
- Ensured all provider response calls now use the class attributes for creating completions asynchronously and synchronously as needed
hlohaus