Over the wire, the streaming looks like this
{"model":"gpt-oss:20b","created_at":"2025-12-10T22:37:12.234735277Z","message":{"role":"assistant","content":"","thinking":"?"},"done":false} {"model":"gpt-oss:20b","created_at":"2025-12-10T22:37:12.922828952Z","message":{"role":"assistant","content":"sen"},"done":false}
Digging a bit in the code, it’s N8N node → Language chain → ollama. Still tryng to find out where the thinkingand contenttags are concatenated.
But around here somewhere
languagechain.js - libs/providers/langchain-ollama/src/chat_models.ts@763
Or can be here at line 96. It dependes whether language chain should have an option to hide thinking or if N8N should have an option to pick textor message.content
master/packages/%40n8n/nodes-langchain/nodes/llms/N8nLlmTracing.ts@96