Evan Reichard
c51c0ab070
All checks were successful
continuous-integration/drone/push Build is passing
vLLM sends thinking content in a "reasoning" delta field, unlike DeepSeek which uses "reasoning_content". Check both field names so thinking blocks render for vLLM-hosted models like qwen3.6-27b-thinking. Also update client tests to exercise thinking output and skip by default so they don't run in Drone CI (require live LLM API).