* Handle Cloudflare WAF errors in Qwen provider
Added detection and raising of CloudflareError when the response indicates an Aliyun WAF block. This improves error handling for cases where requests are blocked by Cloudflare.
* Improve Qwen and LMArena provider authentication handling
Refactors Qwen provider to better manage authentication cookies and cache, including fallback and refresh logic for Cloudflare errors and rate limits. Adds use of AuthFileMixin to Qwen, improves argument retrieval from cache or nodriver, and ensures cookies are merged after requests. Updates LMArena to prioritize args from kwargs before reading from cache, improving flexibility and reliability in authentication.
* Improve LMArena provider recaptcha handling and error logging
Refactors the LMArena provider to better handle recaptcha token acquisition and error cases, including new async methods for recaptcha retrieval and improved error logging. Updates dependencies and imports, and enhances the raise_for_status utility to detect LMArena-specific recaptcha validation failures.
* Add image upload and caching to LMArena provider
Introduces image upload support with caching in the LMArena provider by implementing a prepare_images method. Images are uploaded, cached by hash, and attached to user messages for models supporting vision. Refactors attachment handling to use the new upload logic and improves code formatting and error handling.
* Update and expand model definitions in LMArena.py
Replaces the previous 'models' list with an updated and expanded set of model definitions, including new fields such as 'name', 'rank', and 'rankByModality'. This change adds new models, updates capabilities, and provides more detailed metadata for each model, improving model selection and feature support.
* Improve reCAPTCHA handling and set default timeout
Refactors the reCAPTCHA execution to use the enterprise.ready callback and adds error handling for token retrieval. Also sets a default timeout of 5 minutes for StreamSession if not provided.
* Update LMArena.py
* StreamSession
* Improve error logging for Qwen Cloudflare errors
Replaces a generic debug log with a more detailed error log that includes the exception message when a CloudflareError is caught in the Qwen provider. This enhances troubleshooting by providing more context in logs.
* generate ssxmod
* Improve error handling for Qwen provider responses
Adds checks for JSON error responses and raises RuntimeError when 'success' is false or a 'code' is present in the response data. Also refines HTML error detection logic in raise_for_status.
* Update fingerprint.py
* Update Yupp.py
for test only
* Update Yupp.py
* Add Qwen bx-ua header generator and update Qwen provider
Introduces g4f/Provider/qwen/generate_ua.py for generating bx-ua headers, including AES encryption and fingerprinting logic. Updates Qwen provider to support dynamic UA/cookie handling and refactors image preparation in LMArena to handle empty media lists. Minor cleanup in cookie_generator.py and preparation for integrating bx-ua header in Qwen requests.
* Update LMArena.py
* Update LMArena.py
* Update LMArena.py
* Add user_info method to Yupp provider
Introduces a new async class method user_info to fetch and parse user details, credits, and model information from Yupp. Updates create_async_generator to yield user_info at the start of the conversation flow. Also fixes a bug in get_last_user_message call by passing a boolean for the prompt argument.
* Update Yupp.py
* Update models.py
* Update Yupp.py
* Enhance LMArena action ID handling and parsing
Refactored LMArena to dynamically extract and update action IDs from HTML/JS, replacing hardcoded values with a class-level dictionary. Added HTML parsing logic to load available actions and models, improving maintainability and adaptability to backend changes. Minor cleanup and improved code structure in Yupp and LMArena providers.
* Update LMArena.py
- 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
Introduces the wss_media method to stream media updates via websocket in OpenaiChat, and updates logic to yield media as it becomes available. Also adds wait_media as a fallback polling method, tracks image generation tasks in Conversation, and fixes a bug in curl_cffi.py when deleting the 'autoping' key from kwargs.
* Add image caching to Yupp provider
Introduces an image cache to avoid redundant uploads in the Yupp provider. Refactors media attachment handling into a new prepare_files method, improving efficiency and code organization. Updates .gitignore to exclude .idea directory.
* Refactor Yupp stream handling and chunk processing
Improves stream segmentation in the Yupp provider by introducing buffers for target, variant, quick, thinking, and extra streams. Refactors chunk processing to better handle image-gen, quick responses, and variant outputs, and adds more robust stream ID extraction and routing logic. Yields a consolidated JsonResponse with all stream segments for downstream use.
* Handle ClientResponseError in Yupp provider
Adds specific handling for aiohttp ClientResponseError in the Yupp provider. Marks account as invalid on 500 Internal Server Error, otherwise increments error count and raises ProviderException for other errors.
* Update Yupp.py
fix 429 'Too Many Requests'
* Update Yupp.py
* Improve Yupp provider account handling and request timeout
Refactored account loading to preserve account history and error counts when updating tokens. Enhanced request logic to support custom timeouts using aiohttp's ClientTimeout, allowing for more flexible timeout configuration.
* Update __init__.py
* Handle multi-line <think> and <yapp> blocks in Yupp
Added logic to capture and process multi-line <think> and <yapp class="image-gen"> blocks referenced by special IDs. Introduced block storage and extraction functions, enabling reasoning and image-gen content to be handled via references in the response stream.
* Update LMArena.py
Not Found Model error
* Refactor to use StreamSession in Qwen and Yupp providers
Replaced aiohttp.ClientSession with StreamSession in Qwen.py and Yupp.py for improved session handling. Updated exception and timeout references in Yupp.py to use aiohttp types. Improved default argument handling in StreamSession initialization.
* Update Yupp.py
* Add status parameter to get_generated_image method
Introduces a 'status' parameter to the get_generated_image method to allow passing image generation status. Updates method calls and response objects to include status in their metadata for improved tracking of image generation progress.
* Update OpenaiChat.py
* Refactor Qwen image upload and caching logic and token
Reworked the image upload flow in Qwen provider to use direct file uploads with OSS headers, added caching for uploaded images, and improved file type detection. Updated prepare_files to handle uploads via session and cache results, and added utility for generating OSS headers. Minor imports and typing adjustments included and token support.
* Refactor Qwen and Yupp providers for improved async handling
Updated Qwen provider to handle timeout via kwargs and improved type annotations. Refactored Yupp provider for better code organization, formatting, and async account rotation logic. Enhanced readability and maintainability by reordering imports, adding whitespace, and clarifying function implementations.
* Add image caching to OpenaiChat provider
Introduces an image cache mechanism to OpenaiChat for uploaded images, reducing redundant uploads and improving efficiency. Also refactors code for clarity, updates type hints, and makes minor formatting improvements throughout the file.
* Add image caching to Yupp provider
Introduces an image cache to avoid redundant uploads in the Yupp provider. Refactors media attachment handling into a new prepare_files method, improving efficiency and code organization. Updates .gitignore to exclude .idea directory.
* Refactor Yupp stream handling and chunk processing
Improves stream segmentation in the Yupp provider by introducing buffers for target, variant, quick, thinking, and extra streams. Refactors chunk processing to better handle image-gen, quick responses, and variant outputs, and adds more robust stream ID extraction and routing logic. Yields a consolidated JsonResponse with all stream segments for downstream use.
* Handle ClientResponseError in Yupp provider
Adds specific handling for aiohttp ClientResponseError in the Yupp provider. Marks account as invalid on 500 Internal Server Error, otherwise increments error count and raises ProviderException for other errors.
* Update Yupp.py
fix 429 'Too Many Requests'
* Update Yupp.py
- Added error handling around model retrieval to prevent crashes when a provider fails.
- Ensured that exceptions during model fetching are logged for debugging purposes.
- Cleaned up the indentation and structure of the model retrieval logic for better readability.
