- In `g4f/Provider/needs_auth/OpenRouter.py`, removed import of `DEFAULT_MODEL`
- Changed `default_model` in `OpenRouter` from `DEFAULT_MODEL` to string `"openrouter/auto"`
- In `OpenRouterFree.get_models`, expanded filter condition to include models ending with `"/auto"` in addition to those ending with `":free"`
- In `g4f/Provider/needs_auth/Together.py`, changed `active_by_default` in `Together` class from `True` to `False
- In PerplexityLabs.py, added logic to filter consecutive assistant messages and update message array accordingly
- Modified PerplexityLabs.py to change "messages" field to use the new formatted message list
- Adjusted error handling in PerplexityLabs.py to include a newline in error messages
- Import os in BlackForestLabs_Flux1KontextDev.py and replace media filename assignment with basename if media is None
- In Groq.py, set "active_by_default" to True for the provider
- In OpenRouter.py, added "active_by_default" as True
- In Together.py, set "active_by_default" to True
- In HuggingFaceInference.py, set "working" to False
- In models.py, changed default_model to "openai/gpt-oss-120b" instead of previous value
- In backend_api.py, added a null check in jsonify_provider_models to return 404 if response is None, and simplified get_provider_models call
- Add new FreeRouter provider (based on OpenaiTemplate)
- Add new OpenRouter provider (needs auth) to access OpenRouter.ai service
- Update CablyAI provider imports to use Messages and AsyncResult
- Add support for new Gemini models including gemini-2.5-pro-exp, gemini-2.0-flash-thinking-exp, and gemini-deep-research
- Add processing for <think> tags in Gemini provider output by replacing <ctrl94>thought and <ctrl95> markers
- Update provider imports in __init__.py files to include the new providers
- Mark FreeRouter as not working initially
