* 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>
- Introduced `clean_name` function in `Cloudflare.py` to format model names by removing specific suffixes.
- Updated `model_aliases` in `Cloudflare` class with new model mappings, and cleaned up redundant entries.
- Set `models` in the `Cloudflare` class to use keys from `model_aliases`.
- Adjusted the caching logic in `Cloudflare` to include new headers for requests.
- Added `parent` and `login_url` attributes in `DeepInfraChat` class.
- Updated `PollinationsAI` to clean up model retrieval logic and fixed handling of existing checks.
- Refactored `HarProvider` to inherit models and aliases from `LegacyLMArena`.
- Implemented loading environment variables from `.env` file in `cookies.py`.
- Updated default headers in `defaults.py` for user agent and `sec-ch-ua`.
- Cleaned up various model references in `any_model_map.py` to reflect differences in audio, vision, and other model types.
- Added a more centralized handling for API key management in `run_tools.py` to accommodate new nomenclature.
- Enhanced existing logic to allow for more granular loading and utilization of API keys from environment variables.
- Replaced imports of `STATIC_URL` from `..constants` to `..config` in:
- `g4f/Provider/PollinationsAI.py`
- `g4f/Provider/PollinationsImage.py`
- Updated `client.py` to import `CONFIG_DIR` and `COOKIES_DIR` from `g4f.config` instead of defining platform-specific directories.
- Changed the handling of conversation history in `ConversationManager`:
- Updated `self.history` to retrieve data from `data.get("items", [])` instead of `data.get("history", [])`.
- Modified the `stream_response` function to use `media` instead of `image` for handling media content.
- Updated the `save_content` function to accept `media_content` of type `Optional[MediaResponse]` instead of `content`.
- Adjusted the `run_client_args` function to handle media URLs and files more effectively, appending valid media to a list.
- Removed the `constants.py` file and added a new `config.py` file to centralize configuration settings.
- Updated the `CookiesConfig` class to set `cookies_dir` based on the existence of `CUSTOM_COOKIES_DIR`.
- Adjusted the `render` function in `website.py` to correctly handle file paths and requests for HTML files.
- Updated various references to use the new `config` module instead of the removed `constants` module.
- Added GithubCopilotAPI provider to g4f/Provider/needs_auth and __init__.py
- Fixed typo "GGOGLE_SID_COOKIE" to "GOOGLE_SID_COOKIE" in Gemini.py and updated all references
- Updated PollinationsAI.py:
- Refined model aliases and removed/commented unused/legacy aliases
- Updated logic for loading audio and vision models, using swap_models for alias reversals
- Adjusted get_model and model loading methods for accuracy
- Changed default model lists for text, image, and vision models
- Updated conversation title and followup labels for followups tools
- Modified save_content in g4f/cli/client.py to handle url downloads for lists, allow cookies/headers, and removed duplicate HTTP download logic
- Added asyncio sleep after stdout writes in stream_response for smoother streaming
- Changed website.py render default to "home," adjusted chat route to accept any filename, and updated filenames used for rendering
- Updated model selection in g4f/models.py by removing PollinationsAI from best_provider and changing model provider order for specific models
- Enhanced media merging in g4f/tools/media.py to clarify comment about last user message and handle content appending for lists in render_messages
- Updated OpenaiTemplate.py to add an image_url field if media with http(s) URLs is present
- Adjusted test_provider_has_model in etc/unittest/models.py to skip providers requiring auth
- Updated `PollinationsAI.py` to strip trailing periods and newlines from the prompt before encoding.
- Modified the encoding of the prompt to remove trailing percent signs after URL encoding.
- Simplified the audio response handling in `PollinationsAI.py` by removing unnecessary checks and yielding chunks directly.
- Renamed `ARTA.py` to `deprecated/ARTA.py` and updated import paths accordingly in `__init__.py`.
- Changed the `working` status of the `ARTA` class to `False` to indicate it is deprecated.
- Enhanced the `Video` class in `Video.py` to include aspect ratio handling and improved URL response caching.
- Updated the `RequestConfig` class to use a dictionary for storing URLs associated with prompts.
- Removed references to the `ARTA` provider in various files, including `models.py` and `any_provider.py`.
- Adjusted the `best_provider` assignments in `models.py` to exclude `ARTA` and include `HuggingFaceMedia` where applicable.
- Updated the response handling in `Video.py` to yield cached responses when available.
- In `PollinationsImage.py`, added a new parameter `media` of type `MediaListType` to the class method.
- Changed the default value of `aspect_ratio` in `PollinationsImage.py` from `"1:1"` to `None`.
- Updated the call to `_generate_image` in `PollinationsImage.py` to include the new `media` parameter.
- In `Local.py`, changed the `working` attribute from `True` to `has_requirements` and set `active_by_default` to `False`.
- In `Ollama.py`, set `active_by_default` to `False`.
- In `DeepSeekAPI.py`, set `active_by_default` to `has_dsk` and `needs_auth` to `True`.
- Modified the logic in `DeepSeekAPI.py` to yield `conversation` if `message_id` is present in the chunk.
- In `api.py`, added a new key `active_by_default` to the provider dictionary, determining its value based on `needs_auth`.
- In `types.py`, added a new attribute `active_by_default` to the `BaseProvider` class, initializing it to `None`.
- In `web_search.py`, added a type check for `prompt` to ensure it is a string before proceeding with the search logic.
- 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
- Updated `PollinationsAI.py` to import `quote` and `ClientTimeout` from `aiohttp`.
- Added `MissingAuthError` to error imports in `PollinationsAI.py`.
- Included `AudioResponse` in response imports in `PollinationsAI.py`.
- Expanded `image_models` in `PollinationsAI` to include "turbo" and "gptimage".
- Changed the initialization of `image_models` to use `cls.image_models.copy()`.
- Introduced `download_media` parameter in the `_generate_image` method.
- Added a condition to set `n = 1` if the model is "gptimage".
- Renamed `get_image_url` to `get_url_with_seed` and modified its logic to return the URL for "gptimage".
- Updated the session creation in `_generate_image` to include a timeout.
- Enhanced error handling in the image fetching logic to yield `Reasoning` status.
- Modified the media handling in `save_response_media` to yield `AudioResponse` based on `download_media`.
- Updated `OpenAIFM.py` to include `quote` and `AudioResponse` imports.
- Added `styles` to the `OpenAIFM` class and created a method to group models.
- Introduced `download_media` parameter in the `synthesize` method of `OpenAIFM`.
- Updated the `create_app` function in `api/__init__.py` to check for `a2wsgi` availability.
- Removed unused file handling routes in `api/__init__.py`.
- Updated `secure_filename` function in `files.py` to handle encoding more robustly.
- Added `download_media` to the `RequestConfig` model in `stubs.py`.
- Modified `get_filename_from_url` function to accept a second parameter `extension`, with a default value of ".md".
- Updated the return statement in `get_filename_from_url` to use the new `extension` parameter instead of the hardcoded ".md" suffix.
- Adjusted `get_filename` asynchronous function to pass the `extension` retrieved from `await get_file_extension(response)` into `get_filename_from_url`.
- Added UUID-based "x-xai-request-id" header and 403 error handling in Grok.py
- Updated backend_api.py to handle empty media results and unsupported file types with error raising and file cleanup
- Simplified render logic in website.py by removing is_live flag and related code
- Changed "audio/wav" MIME type to "audio/x-wav" in image/__init__.py
- Added is_valid_media and is_valid_audio functions to image/__init__.py for stricter media validation
- Enhanced MarkItDown integration in markitdown/__init__.py with convert_stream method supporting non-seekable streams
- Modified _transcribe_audio.py to use recognize_faster_whisper if available, fallback to recognize_google
- Updated providers/helper.py to prioritize "text" key in to_string function
- Improved stream_read_files in files.py to skip DOWNLOADS_FILE and adjust code block formatting
- Added get_filename_from_url utility in files.py for consistent filename generation from URLs
- Enhanced download_urls in files.py to use MarkItDown for URL conversion and improved error logging
- Improved render_part and related functions in media.py to use new media validation logic and handle more cases
- Adjusted merge_media and render_messages in media.py for stricter part filtering and validation
- Modified g4f/providers/response.py to ensure format_images_markdown returns the result directly without additional flags in the 'format_images_markdown' function.
- Updated g4f/gui/server/api.py to add 'tempfiles' parameter with default empty list to '_create_response_stream' method.
- Changed or added code in API response handling to iterate over 'tempfiles' and attempt to remove each file after response completion, with exception handling (try-except block with logger.exception).
- Adjusted g4f/Tools/files.py to fix tempfile creation: corrected the 'suffix' parameter in 'get_tempfile' to use 'suffix' directly instead of splitting.
- In g4f/tools/media.py, changed 'render_part' function to handle 'text' key properly, checking 'part.get("text")' and returning a dictionary with 'type': 'text' and 'text': value, if present.
- In PollinationsAI.py, modified get_image method to initialize responses set and manage concurrent image fetches with asyncio tasks, adding a while loop to yield responses as they complete
- Changed response index in get_image from 1 to 0 to align with zero-based indexing
- Introduced 'responses' set and 'finished' counter outside inner get_image function for proper progress tracking
- Updated gather() usage to run all get_image tasks concurrently after loop
- In __init__.py, enhanced use_aspect_ratio function: added checks if width and height are None before assigning aspect ratio-based defaults
- Assigned default width and height values for aspect ratios "1:1", "16:9", and "9:16" if not already specified in extra_body
- In copy_images.py, corrected get_filename function to convert tags to strings before joining with '+', ensuring proper filename formatting
- In response.py, refined is_content function to exclude Reasoning objects where is_thinking and token are both None
- Removed __eq__ method from Reasoning class to prevent comparison issues
- In web_search.py, simplified import by removing unused datetime and date modules
- Updated error handling in g4f/Provider/DDG.py to raise ResponseError instead of yield error strings
- Replaced yield statements with raises in g4f/Provider/DDG.py for HTTP and response errors
- Added response raising in g4f/Provider/DeepInfraChat.py for image upload responses
- Included model alias validation and error raising in g4f/Provider/hf/HuggingFaceMedia.py
- Corrected model alias dictionary key in g4f/Provider/hf_space/StabilityAI_SD35Large.py
- Ensured referrer parameter default value in g4f/Provider/PollinationsImage.py
- Removed duplicate imports and adjusted get_models method in g4f/Provider/har/__init__.py
- Modified g4f/gui/server/api.py to remove unused conversation parameter in _create_response_stream
- Fixed logic to handle single exception in g4f/providers/retry_provider.py
- Added missing import of JsonConversation in g4f/providers/retry_provider.py
- Corrected stream_read_files to replace extension in return string in g4f/tools/files.py
- Introduce `Qwen_Qwen_3` provider in `g4f/Provider/hf_space/Qwen_Qwen_3.py`
- Register Qwen_Qwen_3 in `g4f/Provider/hf_space/__init__.py` and add it to `HuggingSpace`
- Update `MarkItDown` in `g4f/Provider/audio/MarkItDown.py` to accept and forward `llm_client` and `llm_model` kwargs; add async handling for `text_content`
- Modify audio route in `g4f/api/__init__.py` to pass `llm_client` for MarkItDown and set `modalities` only for other providers
- Adjust `OpenaiChat` (needs_auth) to merge media for upload and check for media presence before requesting images
- Change `get_tempfile` in `g4f/tools/files.py` to determine suffix from file extension using `os.path.splitext`
- Refactor provider listing and model mapping in `AnyProvider.get_models()` (g4f/providers/any_provider.py) to update provider order, support new `HarProvider`, initialize attributes, and guard against model_aliases being None
- Ensure `AnyProvider.create_async_generator` calls `get_models` before working with providers
- Changed `generate_commit_message` return to `.strip("`").strip()` in `commit.py`
- Added new model mappings in `PollinationsAI.py`, including `gpt-4.1`, `gpt-4.1-mini`, and `deepseek-r1-distill-*`
- Removed `print` debug statement from `PollinationsAI.py` request payload
- Replaced temp file handling in `MarkItDown.py` with `get_tempfile` utility
- Added `get_tempfile` function to `files.py` for consistent tempfile creation
- Added `gpt-4.1` to `text_models` list in `models.py`
- Added `ModelNotSupportedError` to exception handling in `OpenaiChat.py`
- Updated message content creation to use `to_string()` in `OpenaiChat.py`
- Wrapped `get_model()` in try-except to ignore `ModelNotSupportedError` in `OpenaiChat.py`
- Adjusted `convert` endpoint in `api/__init__.py` to accept optional `provider` param
- Refactored `/api/markitdown` to reuse `convert()` handler in `api/__init__.py
- **g4f/Provider/har/__init__.py**
- `get_models`/`create_async`: iterate over `(domain, harFile)` and filter with `domain in request_url`
- `read_har_files` now yields `(domain, har_data)`; fixes file variable shadowing and uses `json.load`
- remove stray `print`, add type hint for `find_str`, replace manual loops with `yield from`
- small whitespace clean-up
- **g4f/Provider/needs_auth/Grok.py**
- `ImagePreview` now passes `auth_result.cookies` and `auth_result.headers`
- **g4f/Provider/needs_auth/OpenaiChat.py**
- add `Union` import; rename/refactor `get_generated_images` → `get_generated_image`
- support `file-service://` and `sediment://` pointers; choose correct download URL
- return `ImagePreview` or `ImageResponse` accordingly and stream each image part
- propagate 422 errors, update prompt assignment and image handling paths
- **g4f/client/__init__.py**
- drop unused `ignore_working` parameter in sync/async `Completions`
- normalise `media` argument: accept single tuple, infer filename when missing, fix index loop
- `Images.create_variation` updated to use the new media logic
- **g4f/gui/server/api.py**
- expose `latest_version_cached` via `?cache=` query parameter
- **g4f/gui/server/backend_api.py**
- optional Markdown extraction via `MarkItDown`; save rendered text as `<file>.md`
- upload flow rewrites: copy to temp file, move to bucket/media dir, clean temp, store filenames
- introduce `has_markitdown` guard and improved logging/exception handling
- **g4f/tools/files.py**
- remove trailing spaces in HAR code-block header string
- **g4f/version.py**
- add `latest_version_cached` `@cached_property` for memoised version lookup
- 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
Update conversation body in OpenaiChat provider
Update ThinkingProcessor in run_tools
Add unittests for ThinkingProcessor
Update default headers in requests module
Add AuthFileMixin to base_provider
* New provider added(g4f/Provider/Websim.py)
* New provider added(g4f/Provider/Dynaspark.py)
* feat(g4f/gui/client/static/js/chat.v1.js): Enhance provider labeling for HuggingFace integrations
* feat(g4f/gui/server/api.py): add Hugging Face Space compatibility flag to provider data
* feat(g4f/models.py): add new providers and update model configurations
* Update g4f/Provider/__init__.py
* feat(g4f/Provider/AllenAI.py): expand model alias mappings for AllenAI provider
* feat(g4f/Provider/Blackbox.py): restructure image model handling and response processing
* feat(g4f/Provider/PollinationsAI.py): add new model aliases and streamline headers
* Update g4f/Provider/hf_space/*
* refactor(g4f/Provider/Copilot.py): update model alias mapping
* chore(g4f/models.py): update provider configurations for OpenAI models
* docs(docs/providers-and-models.md): update provider tables and model categorization
* fix(etc/examples/vision_images.py): update model and simplify client configuration
* fix(docs/providers-and-models.md): correct streaming status for GlhfChat provider
* docs(docs/providers-and-models.md): update provider capabilities and model documentation
* fix(models): update provider configurations for Mistral models
* fix(g4f/Provider/Blackbox.py): correct model alias key for Mistral variant
* feat(g4f/Provider/hf_space/CohereForAI_C4AI_Command.py): update supported model versions and aliases (close#2802)
* fix(documentation): correct model names and provider counts (https://github.com/xtekky/gpt4free/pull/2805#issuecomment-2727489835)
* fix(g4f/models.py): correct mistral model configurations
* fix(g4f/Provider/DeepInfraChat.py): correct mixtral-small alias key
* New provider added(g4f/Provider/LambdaChat.py)
* feat(g4f/models.py): add new providers and enhance model configurations
* docs(docs/providers-and-models.md): add LambdaChat provider and update model listings
* feat(g4f/models.py): add new Liquid AI model and enhance providers
* docs(docs/providers-and-models.md): update model listings and provider counts
* feat(g4f/Provider/LambdaChat.py): add conditional reasoning processing based on model
* fix(g4f/tools/run_tools.py): handle combined thinking tags in single chunk
* New provider added(g4f/Provider/Goabror.py)
* feat(g4f/Provider/Blackbox.py): implement dynamic session management and model access control
* refactor(g4f/models.py): update provider configurations and model entries
* docs(docs/providers-and-models.md): update model listings and provider counts
---------
Co-authored-by: kqlio67 <>
* docs(docs/providers-and-models.md): update documentation structure and model listings
* refactor(g4f/debug.py): add type hints and docstrings
* refactor(g4f/tools/run_tools.py): Restructure tool handling and improve modularity
* refactor(g4f/providers/response.py): enhance type hints and code documentation
* feat(g4f/models.py): Update model providers and add new models
* feat(g4f/Provider/Blackbox.py): add encrypted session handling and model updates
* fix(g4f/Provider/ChatGptEs.py): migrate to curl_cffi for request handling and improve error resilience
* feat(g4f/Provider/DeepInfraChat.py): Update default model and add new DeepSeek variants
* feat(g4f/Provider/Free2GPT.py): add Gemini models and streamline headers
* feat(g4f/Provider/FreeGpt.py): Add support for Gemini 1.5 Flash model
* feat(g4f/Provider/Liaobots.py): Add Claude 3.7 models and update default GPT-4o
* fix(g4f/Provider/PollinationsAI.py): Correct model mappings and generation parameters
* feat(g4f/Provider/PollinationsImage.py): Add class identifier label
* chore(g4f/Provider/TeachAnything.py): Update default model and simplify model handling
* (g4f/Provider/Mhystical.py): Remove class implementation
* chore(g4f/Provider/Prodia.py > g4f/Provider/not_working/Prodia.py): mark Prodia provider as non-working
* feat(g4f/Provider/Blackbox.py): Add Claude 3.7 Sonnet model alias
* chore(g4f/models.py): Update model configurations
* fix(g4f/Provider/ChatGptEs.py): improve request reliability and nonce detection
---------
Co-authored-by: kqlio67 <>
