- 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
- Remove hardcoded preferred_provider=huggingface in podcast handlers
- Set preferred_provider=None to respect GPT_PROVIDER env var
- Change default model from Qwen to gpt-oss-120b:cerebras (the model user had access to)
- WaveSpeed will now use gpt-oss-120b model instead of Qwen
- Add HTTPException re-raise before generic Exception handler
- Use static error message instead of str(e) which was out of scope
- Fixes 'e is not associated with a value' error
- Returns HTTP 429 (usage limit) instead of 503 for provider failures
- Includes usage_info with error_type, operation_type, and suggestion
- Frontend SubscriptionContext can now display the modal
- Log gpt_provider and model in preflight info
- Return structured HTTP 503 with actionable error details
- Include available_providers, requested_provider, and suggestion
- Help users understand what went wrong and how to fix it
- Return 503 with structured error details instead of generic RuntimeError
- Include available_providers and requested_provider in error
- Add actionable suggestions for users
- Check if no providers configured and return specific error
- Add GPT_PROVIDER wavespeed/openai support in main_text_generation.py
- wavespeed_text_response now called when GPT_PROVIDER=wavespeed
- Fallback to tenant config when no GPT_PROVIDER set
- Add wavespeed provider mapping in provider_enum
- Fix generate_image() call to use options dict in podcast analysis
- Import APIKeyManager for provider key checking
- Use APIKeyManager.get_api_key() instead of get_api_key() function
- Add wavespeed provider to available_providers check
- Add detailed provider preflight logging with flow_type tag
- Improve fallback logic when preferred provider is unavailable
These improvements come from PRs #423-#431 while maintaining the modular textgen_utils structure.
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.
