- Fix text selection menu not showing: wire contentRef via inputRef on multiline TextField
- Fix blog title not truncating: add min-w-0 for flex item overflow
- Fix outline generation 500: escape curly braces in f-string prompt template
- Fix content generation 'NoneType not callable': replace SessionLocal() with get_session_for_user(), add db param to MediumBlogGenerator, fix signature mismatch in database_task_manager
- Fix writing assistant suggest 500: add auth + user_id to API endpoint and service, replace sync requests with httpx.AsyncClient
- Fix hallucination detector 404: explicitly include router in main.py and app.py
- Fix missing error_data in task failure responses
- Hide CopilotKit web inspector button
- Remove hardcoded fallback suggestions from SmartTypingAssist
- Fix stale closure refs in SmartTypingAssist handleTypingChange
- Add two-column editor layout, stats bar, section hover menu
- Various subscription, billing, and research module improvements
huggingface_provider.py:
- Add retry logic with _should_retry_hf_error and _is_non_retryable_hf_error
- Update default models from :groq to :cerebras (HF_FALLBACK_MODELS)
- Add fallback_models parameter to huggingface_text_response
- Add get_available_models with updated model list
main_text_generation.py:
- Add GPT_PROVIDER and TEXTGEN_AI_MODELS env var support
- Add preferred_provider and flow_type parameters to llm_text_gen
- Add HF_MODEL_MAPPING for short model name resolution
- Add flow_type logging tag for better observability
sif_agents.py:
- Add LOW_COST_SHARED_REMOTE_MODELS for SIF agents
- Update SharedLLMWrapper to use preferred_hf_models and flow_type
These changes preserve the modular textgen_utils structure while incorporating
the useful routing and retry logic improvements from the pending PRs.
- Modified _ensure_initialized() to run in background thread (non-blocking)
- Added _ensure_initialized_async() for truly async initialization
- Updated index_content() to return immediately without waiting for initialization
- Weights now load in background thread instead of blocking event loop
- Added initialization tracking to prevent duplicate initialization
- Modified today_workflow API to handle non-blocking indexing gracefully
- This prevents dashboard refresh from blocking other services
When a user accesses the dashboard, the indexing now happens in background
instead of blocking the HTTP response, allowing other services to function
normally while weights are being loaded.
