dsh-relay-fast
DeepSeek Harness relay plugin for reasoning-effort autofill, /models sync, and a capability-aware Fast toggle.
安装
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Rock-ql/dsh-relay-fast说明文档
阅读完整 README ↗可选配置
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。
Optional configuration
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.