I gave my local LLM an escape hatch to Fable 5, and it solved the problems I couldn't
… """ response = claude.messages.create model="claude-fable-5", max tokens=4000, messages= {"role": "user", "content": prompt} , return "\n".join block.text for block in response.content if block.type == "text" The last step was passing this function to Qwen through Ollama’s tools parameter. …