Reasoning-capable local backends (deepseek-v4-flash-dspark on bosch) only emit a
separate reasoning stream when the request carries chat_template_kwargs.enable_thinking.
The proxy never asked, so clients (bullpen, OWUI) got reasoning inlined into content or
dropped. Now: if the routed local model matches /etc/llm-proxy/reasoning-models.json
(a JSON list of substrings; absent=off), inject enable_thinking. The byte-passthrough
relay already forwards the reasoning deltas untouched. Verified: dspark now streams
reasoning deltas through :8082.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Markus Fritsche