GitHub · Agent 与编排

JuneLearn/dsh-reasoning-settings

JuneLearn · repository · direct signal

Open source

让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度,并可为每次子 Agent 调用选择模型|Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call

SOURCE-DECLARED INSTALL

Open the public source page ↗

MEDIA REFERENCES

Captured in public view

Local and external references · rights noted

CONTEXT

Why it is here

让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度,并可为每次子 Agent 调用选择模型|Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call

Evidence updated 2026-08-15T06:08:50Z. Interaction numbers are platform-native snapshots; the evidence panel records the metric source and observation time. NULL means the public page did not expose a number at collection time.