- In `g4f/__init__.py`, changed logger setup to use fixed "g4f" name and refactored `ChatCompletion.create` and `create_async` to share `_prepare_request` logic for preprocessing arguments
- In `g4f/config.py`, added `__future__.annotations`, `lru_cache` import, wrapped `get_config_dir` with `@lru_cache`, and simplified platform branch logic
- In `g4f/cookies.py`, added typing imports, renamed `browsers` to `BROWSERS`, reformatted `DOMAINS`, updated docstrings, improved loop logic in `load_cookies_from_browsers` with additional exception handling, split HAR/JSON parsing into `_parse_har_file` and `_parse_json_cookie_file`, and enhanced `read_cookie_files` with optional filters and `.env` loading
- In `g4f/debug.py`, added enable/disable logging functions, updated log handler typing, appended messages to `logs` in `log()`, and improved `error()` formatting
- In `g4f/errors.py`, introduced base `G4FError` and updated all exception classes to inherit from it or relevant subclasses, with descriptive docstrings for each
- In `g4f/files.py`, added `max_length` parameter to `secure_filename`, adjusted regex formatting, and added docstring; updated `get_bucket_dir` to sanitize parts inline with docstring
- In `g4f/typing.py`, added `__future__.annotations`, reorganized imports, restricted PIL import to type-checking, defined `ContentPart` and `Message` TypedDicts, updated type aliases and `__all__` to include new types
- In `g4f/version.py`, added `lru_cache` and request timeout constant, applied caching to `get_pypi_version` and `get_github_version`, added response validation and explicit exceptions, refactored `VersionUtils.current_version` with clearer sources and error on miss, changed `check_version` to return a boolean with optional silent mode, and improved error handling outputs
- Added file upload usage example with bucket_id in docs/file.md
- Fixed ARTA provider by refactoring error handling with a new raise_error function
- Simplified aspect_ratio handling in ARTA with proper default
- Improved AllenAI provider by cleaning up image handling logic
- Fixed Blackbox provider's media handling to properly process images
- Updated file tools to handle URL downloads correctly
- Fixed bucket_id pattern matching in ToolHandler.process_bucket_tool
- Cleaned up imports in typing.py by removing unnecessary sys import
- Fixed inconsistent function parameters in g4f/tools/files.py
- Fixed return value of upload_and_process function to return bucket_id
* Add Path and PathLike support when uploading images
Improve raise_for_status in special cases
Move ImageResponse to providers.response module
Improve OpenaiChat and OpenaiAccount providers
Add Sources for web_search in OpenaiChat
Add JsonConversation for import and export conversations to js
Add RequestLogin response type
Add TitleGeneration support in OpenaiChat and gui
* Improve Docker Container Guide in README.md
* Add tool calls api support, add search tool support
* Add multiple images support
* Add multiple images support in gui
* Support multiple images in legacy client and in the api
Fix some model names in provider model list
* Fix unittests
* Add vision and providers docs
* IterListProvider support for generating images
* Add missing get_har_files import in Copilot
* Fix typo in dall-e-3 model name
* Add image client unittests
* Add MicrosoftDesigner provider
* Import MicrosoftDesigner and add it to the model list
* Improve download of generated images, serve images in the api
Add support for conversation handling in the api
* Add orginal prompt to image response
* Add download images option in gui, fix loading model list in Airforce
* Add download images option in gui, fix loading model list in Airforce
Add AbstractProvider class
Add ProviderType type
Add get_last_provider function
Add version module and VersionUtils
Display used provider in gui
Fix error response in api
