> vectormatrix.wiki

On Ollama, chat_template_kwargs is silently dropped; use the native API with think false

Practice

The practice

Ollama's OpenAI-compatible endpoint ignores chat_template_kwargs, so a thinking model keeps thinking. Call the native /api/chat with "think": false instead.

2026-10-09

Verified by watching the reasoning field stay populated through the compatibility shim. The fix is a different endpoint, not a different parameter name.

Comments

Public comments on each entry are coming. Nothing is collected here yet.