- Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to model list
- Set MiniMax-M2.7 as default model
- Keep all previous models as alternatives
- Add model routing entries in any_model_map
- Add unit tests for MiniMax provider
* 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.
- Changed `api_base` to `base_url` in multiple provider files for consistency.
- Updated method signatures and internal references to use `base_url` instead of `api_base`.
- Adjusted the `OpenaiTemplate` class to accommodate the new `base_url` parameter.
- Enhanced the `ClientFactory` to support custom provider creation with `base_url`.
- Modified API request handling in the backend to align with the new naming convention.
- Add AIBadgr provider class extending OpenaiTemplate
- API endpoint: https://aibadgr.com/api/v1
- Full support for streaming, system messages, and message history
- Add example usage script in etc/examples/aibadgr.py
- Provider requires API key authentication
- **g4f/Provider/Copilot.py**
- Added `"Smart (GPT-5)"` to `models` list.
- Added `"gpt-5"` alias mapping to `"GPT-5"` in `model_aliases`.
- Introduced `mode` selection logic to support `"smart"` mode for GPT-5 models alongside existing `"reasoning"` and `"chat"` modes.
- **g4f/Provider/EasyChat.py**
- Added `get_models` class method to map `-free` models to aliases and store them in `cls.models`.
- Resolved model via `cls.get_model(model)` at start of `create_async_generator`.
- Reset `cls.captchaToken` to `None` at the beginning of `callback`.
- Wrapped main generator logic in a loop to allow retry once if `CLEAR-CAPTCHA-TOKEN` error occurs, clearing auth file and resetting args.
- **g4f/Provider/needs_auth/OpenaiChat.py**
- Added handling for image models: detect and set `image_model` flag, use `default_model` when sending requests if image model selected, and include `"picture_v2"` in `system_hints` when applicable.
- Replaced textarea/button detection code in page load sequence with `nodriver` `select` calls, sending "Hello" before clicking send button, and included profile button selection if class needs auth.
- **g4f/Provider/openai/models.py**
- Changed `default_image_model` from `"dall-e-3"` to `"gpt-image"`.
- Added `"gpt-5"` and `"gpt-5-thinking"` to `text_models` list.
- Added alias mapping for `"dall-e-3"` pointing to new `default_image_model`.
- Replaced all imports and usages of `see_stream` with `sse_stream` across:
- `g4f/Provider/Kimi.py`
- `g4f/Provider/hf_space/BlackForestLabs_Flux1KontextDev.py`
- `g4f/Provider/needs_auth/PuterJS.py`
- `g4f/Provider/template/OpenaiTemplate.py`
- `g4f/requests/__init__.py` (renamed function `see_stream` to `sse_stream`)
- Modified `g4f/Provider/needs_auth/GeminiPro.py`:
- Updated `default_model` from `gemini-2.5-flash-preview-04-17` to `gemini-2.5-flash`
- Removed `gemini-2.5-flash-preview-04-17` from `fallback_models`
- Updated `etc/tool/md2html.py`:
- Added `re` import
- Changed `process_single_file_with_output` to check if output file exists
- If exists, uses regex to update `<title>` and `itemprop="text">` content instead of writing full template
- If not, generates HTML using the template as before
* feat: add agent CLI, new providers, and update models
- Add a new `agent` mode to the CLI, a feature-rich AI coding assistant with capabilities for file system operations, code execution, git integration, and interactive chat.
- Add new provider `OperaAria` with support for vision, streaming, and conversation history.
- Add new provider `Startnest` with support for `gpt-4o-mini`, vision, and streaming.
- Move providers `FreeGpt` and `Websim` to the `not_working` directory.
- Delete the `OIVSCodeSer2` provider.
- Rename the CLI `client` mode to `chat` and refactor its argument parsing.
- In `g4f/Provider/DeepInfraChat.py`:
- Add a new `api_endpoint` attribute.
- Extensively update and reorganize the `models` list and `model_aliases` dictionary with numerous new models.
- In `g4f/Provider/LambdaChat.py`:
- Change the `default_model` to `deepseek-v3-0324`.
- In `g4f/Provider/Together.py`:
- Update aliases for `llama-3.1-405b`, `deepseek-r1`, and `flux`.
- Add new models including `gemma-3-27b`, `gemma-3n-e4b`, and `qwen-3-32b`.
- In `g4f/models.py`:
- Add new model definitions for `aria`, `deepseek_v3_0324_turbo`, `deepseek_r1_0528_turbo`, and several `gemma` variants.
- Remove the `mixtral_8x22b` model definition.
- Update the `best_provider` lists for `default`, `default_vision`, `gpt_4o_mini`, `gemini-1.5-pro`, `gemini-1.5-flash`, and others to reflect provider changes.
- In `g4f/Provider/__init__.py`:
- Add `OperaAria` and `Startnest` to the list of imported providers.
- Remove `FreeGpt`, `OIVSCodeSer2`, and `Websim` from imports.
- In `requirements.txt`:
- Add `rich` as a new dependency for the agent CLI.
* feat: add gemma-3-4b alias to DeepInfraChat
In g4f/Provider/DeepInfraChat.py, add the gemma-3-4b alias to the model_aliases dictionary.
The new alias points to the google/gemma-3-4b-it model.
* feat: add OIVSCodeSer2 provider
- Create the new provider file .
- The provider supports the model and includes a custom method to generate a .
- Import and include in .
- Add to the for in .
- Add to in .
* feat: add OIVSCodeSer2 provider
- Create the new provider file .
- The provider supports the model and includes a custom method to generate a .
- Import and include in .
- Add to the for in .
- Add to in .
* refactor: Migrate from duckduckgo-search to ddgs library
* Replaced the dependency with the new library.
* In , updated imports from to and to .
* Modified the function in to use an context manager instead of a global instance.
* Updated the function to catch the new exception.
* In , updated the web search import and installation instructions to use .
* Removed unnecessary comments and simplified f-string formatting in and .
* Added and to .
* Added , , and to the extras in .
* test: Update web search tests for ddgs library and cleanup code
* In `etc/unittest/web_search.py`, updated imports from `duckduckgo_search` to `ddgs` and `DDGSError`.
* Added an import for `MissingRequirementsError` in `etc/unittest/web_search.py`.
* Modified exception handling in web search tests to catch both `DDGSError` and `MissingRequirementsError`.
* Removed temporary modification comments in `g4f/cli/agent/agent.py` and `g4f/tools/web_search.py`.
* fix: remove unstable CLI feature due to critical errors
- Remove the experimental CLI coding assistant feature due to multiple stability issues and critical errors in production environments
- Delete the entire `g4f/cli/agent/` directory and all related functionality
- Remove `rich` dependency from `requirements.txt` as it was only used by the removed feature
- Remove `rich` from the `all` extras in `setup.py`
- Revert CLI mode naming from `chat` back to `client` for consistency
- Clean up argument parsing in CLI to remove references to the removed functionality
- Remove installation instructions and imports related to the unstable feature from documentation
This removal is necessary due to:
- Unpredictable behavior causing data loss risks
- Incompatibility with certain system configurations
- Security concerns with unrestricted file system access
- Excessive resource consumption in production environments
Note: This feature may be reintroduced in the future with a more stable and secure implementation that addresses the current limitations and safety concerns.
---------
Co-authored-by: kqlio67 <kqlio67@users.noreply.github.com>
H Lohaus