@lengquan88/dsh-dual-auto
双模型 Auto 路由插件: flash 低成本直返 / pro 高成本升级 + 逃逸学习闭环 + 持久化互通
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add github:lengquan88/dsh-dual-auto#bffbf74bd115d27ef8419739505f585ea3ba16b1Dual Auto 以 @lengquan88/dsh-dual-auto 发布，当前版本为 0.1.2。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
Dual-model auto-routing plugin for the DeepSeek Harness (dsh).
Low-cost direct / high-cost upgrade with an escape-learning closed loop.
pnpm add @lengquan88/dsh-dual-auto
Add one row to your profile's cordis.patch.yml:
- insert:
- id: dual-auto
name: '@lengquan88/dsh-dual-auto'
Restart dsh web. The tools dual_model_route, dual_model_run, and
dual_model_mark become available in every session.
| Tool | Purpose |
|---|---|
dual_model_route | Six-criteria routing decision (length / context / domain coverage / rule conflict / confidence / novelty → six labels). Fingerprints that escaped once are force-upgraded. |
dual_model_run | Decision + real model call: direct → deepseek-v4-flash, upgrade → deepseek-v4-pro (auto-degrade to flash on failure, marked degraded). Probe tasks auto-validate against a gold set — wrong direct answers trigger escape learning. |
dual_model_mark | Mark the quality of a direct result. correct=false learns the fingerprint and rewrites the disk log marker; the same fingerprint is force-upgraded next time. |
State persists to output/dsh_router_{fingerprints,stats}.json and
dsh_router_decision_log.jsonl — interoperable with the project's Python
dao/model_router.py (v2 dict fingerprints load directly).
MIT