deepseek-harness
deepseek-ai
DeepSeek Harness: Everything is a Plugin.
PROJECT TOPICS
PROJECT README
面向 DeepSeek Harness(DSH)Desktop/Web 的中转站增强插件。
llm-pi-ai 新增模型补上 reasoningEfforts;兼容 openai-completions 与 anthropic-messages,不覆盖已有声明。/models 同步缺失模型。fastModels 显式启用时显示;开启后发送 service_tier: "priority"。dsh plugin --profile desktop add github:Rock-ql/dsh-relay-fast
安装后重启 DSH Desktop。Web profile 可将 desktop 替换为对应 profile 名称。
在 profile 的 cordis.patch.yml 中覆盖插件配置:
- id: relay-fast
config:
autofill: true
fastTier: priority
fastModels:
- gpt-5* # 所有中转渠道的 GPT-5 模型
defaultSpeed: fast # 新会话默认 Fast;仍可手动切回 Standard
不配置 fastModels 时,插件只相信中转站 /models 返回的明确 Fast 能力元数据,不按模型名称猜测。
注意:开关能保证发送
service_tier: priority,但中转站可能忽略该字段。真实加速能力取决于上游。测试记录见 docs。
pnpm install
pnpm check
A relay enhancement plugin for DeepSeek Harness (DSH) Desktop/Web.
reasoningEfforts to new llm-pi-ai models. It is protocol-aware for openai-completions and anthropic-messages, and never overwrites existing declarations./models endpoint in Settings.fastModels. Fast requests send service_tier: "priority".dsh plugin --profile desktop add github:Rock-ql/dsh-relay-fast
Restart DSH Desktop after installation. For Web, replace desktop with the target profile name.
Override the plugin in the profile's cordis.patch.yml:
- id: relay-fast
config:
autofill: true
fastTier: priority
fastModels:
- gpt-5* # GPT-5 models on every relay route
defaultSpeed: fast # Fast by default; users can switch to Standard
Without fastModels, the plugin trusts only explicit Fast metadata returned by /models; it never guesses from model names.
The toggle guarantees that
service_tier: priorityis sent, but a relay may ignore it. Actual acceleration depends on the upstream service. See docs for test reports.
pnpm install
pnpm check
CLASSIFICATION EVIDENCE
系统优先读取 GitHub Topics,再与站内分类词典和词根规则比对。当前命中: 无有效分类标签。