- Remove duplicate isinstance(chunk, RequestLogin) check at line 220
- Fix remaining RequestLogin handler to use chunk.to_string() instead of str(chunk)
- Resolves conflicting type checks issue where first check made second unreachable
Co-authored-by: hlohaus <983577+hlohaus@users.noreply.github.com>
* Fix Qwen provider implementation
- Re-enable cookie generation for authentication
- Update User-Agent header to latest version
- Fix Authorization header to only be added when token is present
- Add X-Requested-With and X-Source headers for proper API communication
- Force stream and incremental_output to True for consistent streaming behavior
- Set parent_id to None to prevent parent-child relationship issues
- Add conditional thinking functionality with proper feature_config when enable_thinking is True
- Improve header management for better compatibility with Qwen API
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
* Restore parent_id in Qwen provider for conversation support
---------
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Use context manager (with statement) to ensure file is properly closed
- Prevents file descriptor exhaustion after ~10 page reloads
- Fixes issue where web interface becomes unresponsive in Docker environments
Co-authored-by: hlohaus <983577+hlohaus@users.noreply.github.com>
* Yupp provider fix, vercel firewall bypass.
Refactor Yupp provider to use cloudscraper and ThreadPoolExecutor for improved performance and error handling. Update account management and request methods to streamline interactions with the Yupp API. bypassed yupp firewall for perfect performance and avoiding using unstable methods.
* Check for cloudscraper availability and update Yupp provider status accordingly
---------
Co-authored-by: GamerReady <135560754+GamerReady@users.noreply.github.com>
Co-authored-by: hlohaus <983577+hlohaus@users.noreply.github.com>
- Added Perplexity to the list of providers handled in model mapping.
- Simplified model mapping logic for Copilot and CopilotAccount.
- Updated handling of fallback models for Perplexity.
- Improved clean_name function to standardize model names, including new replacements for gpt-5 and Claude models.
- Adjusted model grouping logic to include additional prefixes for Mistral models.
