Merge pull request 'fix(litellm): default max_tokens=4096 for the reasoning model' (#20) from fix/litellm-reasoning-max-tokens into main

litellm-config.yaml

@@ -7,6 +7,13 @@ model_list:
       model: openai/qwen3.8-27b-local
       api_base: http://llama-server:8080/v1
       api_key: local
+      # Qwen3 is a reasoning model — it spends output tokens on
+      # reasoning_content before ever writing content. Callers that don't
+      # set their own max_tokens (Open WebUI's default request didn't) hit
+      # llama.cpp's low default, so the model runs out mid-thought and
+      # content comes back empty. This is a floor, not a cap — any caller
+      # that passes its own max_tokens still overrides it.
+      max_tokens: 4096
     model_info:
       # Shadow cloud-cost estimate — priced against Claude Sonnet 5's published
       # rate, not real spend (this proxy only ever routes to the local model).