reasoning

Per-round reasoning_effort optimizer for DeepSeek Harness (dsh): auto-downgrades tool-call reasoning for simple tool chains, lifting back for heavy work. Cuts thinking time between tool calls.

DeepSeek Harness (DSH) plugin: a "Thinking Language" selector under Settings → General that tells the model which language to reason in (chain of thought) via a system-prompt section. Zero extra calls, zero latency, 12 languages.

Capability-aware reasoning controls and Fast model routing for DeepSeek Harness

DeepSeek Harness client plugin: constant-rate typewriter reveal for assistant output and reasoning, with per-model gating.