drscrewdriver/dsh-thinking-levels

README 摘要

dsh-thinking-levels Per-round thinking-level ( reasoning effort ) control for DeepSeek Harness (dsh): pick Auto (a mask) in the session model selector and the plugin schedules low / high / max from the recent tool-call history before submitting the API effort — or fix a wire level ( off / low / high / max ) manually. Cheap tool rounds stay cheap; heavy work never starves. 中文文档 · English In a multi-step tool chain, the model re-thinks before every tool call — and that thinking dominates the wall-clock time (a 50-step agent task can spend minutes reasoning between tools). dsh-thinking-levels plugs into the agent/request waterfall that dsh re-resolves for every step (registered with prepend so the session model-selection assembly cannot overwrite its decision) and injects a thinking level into the next model request. Levels Level Meaning Where off thinking disabled (manual only — never auto-picked) model selector / default level low manual pick for simple chat tasks (cheap rounds stay cheap) model selector / default level high the official default effort model selector / default level max heavy work model selector / default level auto mask : schedule per step from the recent tool-call…

分类