zhangzhangco/dsh-tier-router ↗★ 0
dsh-tier-router
Automatic tier-based model routing for DeepSeek Harness: a virtual `smart` model classifies each request by difficulty (hard / normal / easy) and by vision need, then delegates it to the models you already configured. 三级难度 + 视觉自动路由,虚拟 smart 模型零配置接入。 适合已配置多模型,想通过虚拟smart模型实现自动分流的用户。
Other repositories with this package name
Install
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zhangzhangco/dsh-tier-routerREADME
Read the full README ↗Configuration
Settings live in the tier-router namespace as flat fields. Edit them in the settings card or write
them directly:
tier-router:
enabled: true
classifier: heuristic # heuristic | llm
hardProvider: codex-local
hardModel: gpt-6-astra
hardEffort: '' # e.g. low / high / max; empty = unspecified
normalProvider: codex-local
normalModel: gpt-5.5
normalEffort: ''
easyProvider: gpudev
easyModel: qwen3.8-27b-q5
easyEffort: ''
visionProvider: codex-local
visionModel: gpt-6-astra
visionEffort: ''
visionMode: replace # replace (structured evidence, default) | route (whole turn)
visionCacheTtl: 3600 # seconds of vision-evidence cache; 0 disables
visionFallbacks: [] # [{provider, model}] explicit vision fallbacks
fallbackProvider: '' # last resort; empty = the session default model
fallbackModel: ''
llmClassifierProvider: '' # classifier: llm; empty = reuse the easy tier
llmClassifierModel: ''
| Field | Default | Meaning |
|---|---|---|
enabled | true | Master switch; when off, requests go to the session default model. |
classifier | heuristic | heuristic (built-in scoring) or llm (a model decides the tier). |
hardProvider / hardModel / hardEffort | codex-local / gpt-6-astra / '' | Hardest tier. |
normalProvider / normalModel / normalEffort | codex-local / gpt-5.5 / '' | Everyday tier. |
easyProvider / easyModel / easyEffort | gpudev / qwen3.8-27b-q5 / '' | Cheapest tier. |
visionProvider / visionModel / visionEffort | codex-local / gpt-6-astra / '' | Image tier. |
visionMode | replace | Image handling; see below. |
visionCacheTtl | 3600 | Vision-evidence cache in seconds. |
visionFallbacks | [] | Explicit vision fallbacks before the default model. |
fallbackProvider / fallbackModel | '' | Route used when no tier is configured; empty = session default. |
llmClassifierProvider / llmClassifierModel | '' | Classifier model for classifier: llm. |
classifierTimeoutMs | 4000 | Budget for the LLM classifier. On timeout the heuristic decides immediately and the slow answer is cached for later requests. |
visionTimeoutMs | 60000 | Budget for one vision-sidecar call, so a hung vision provider cannot stall the turn. |
contextGuard | true | Skip routes whose known context window cannot hold the request. |