dsh-decide
Manifest validConnects DSH to decision models (TypeSafe Jev, TokenRhythm NeoHorse-Jev, OpenAI Decisions, and local System One endpoints) with decide, gate, rerank, and judge tools plus a settings page. Needs an API
dsh-decide
English | 简体中文
Multi-provider decision models for DeepSeek Harness (DSH): one pair of agent tools over TypeSafe Jev, TokenRhythm NeoHorse-Jev, OpenAI Decisions, and local System One servers.
Decision models are not chat models. They take a body of text (
state) plus named typed questions and return probabilities / labels / scores — no prose, no streaming, no messages. That is whydsh-decideadds tools and a settings page instead of a model in the model picker.
Providers
| id | Service | Dialect | Default model | Key |
|---|---|---|---|---|
typesafe | TypeSafe Jev | System One | jev-latest | TYPESAFE_API_KEY |
tokenrhythm | 基元律动 NeoHorse-Jev | System One | NeoHorse-Jev-4B | TOKENRHYTHM_API_KEY |
openai | OpenAI Decisions (beta) | OpenAI Decisions | gpt-6-luna | OPENAI_API_KEY |
local | Local System One server (Laya via Unsloth, self-hosted models) | System One | laya | optional / keyless |
Any other endpoint can be added as a custom provider with either dialect. The first enabled provider whose key resolves is used by default; set defaultProvider to pin one. Each provider card links to its website with the aichen referral tag appended.
Install
Development (this checkout; replace the path with your clone):
dsh plugin --profile desktop add link:F:\path\to\dsh-decide
Then restart DSH (host plugins are not hot-reloaded). In this repository the link is already installed; dsh plugin adds both the dependency and the bundle entry.
Published install is dsh plugin --profile desktop add dsh-decide once the package is on npm.
Settings
Settings → Decisions has four tabs:
- Providers — per-provider enable/disable, model, base URL, path, key status, save, test, list models, set default, and a form for custom providers.
- Examples — copyable prompts and the exact tool request, so users can start without reading docs.
- Behavior — confidence thresholds, request limits, cache, audit, and the optional execution guard.
- Usage — request/token/cost totals per provider for today and the last 7 days, plus recent decisions.
The page follows the DSH language setting. English and Chinese are complete; the other shipped DSH languages (Japanese, Spanish, French, German, Russian, Portuguese) translate the main interface and fall back to English for long help text. Contributions for the remaining strings are welcome.
Keys are written through the DSH credentials service; the page only ever reports whether a key is set and where it comes from. The state you judge is sent to the selected provider — do not put secrets in it.
Tools
decide
{
"state": "I was charged twice for my March subscription.",
"questions": [
{ "name": "billing", "type": "yesno", "instructions": "Is this about billing?" },
{
"name": "team",
"type": "choice",
"instructions": "Which team should handle this?",
"choices": [{ "label": "billing" }, { "label": "technical" }]
},
{
"name": "urgency",
"type": "score",
"instructions": "How urgent is this?",
"levels": [{ "label": "not urgent" }, { "label": "this week" }, { "label": "today" }]
}
]
}
Returns one answer per question with probability / choice / score, confidence where the provider supplies it, and uncertain from the configured thresholds. Set includeProbabilities: true to get the full distribution. provider overrides the default; state must be a string (serialize JSON first).
decide_gate
Asks one yes/no question — by default “could this action irreversibly delete, overwrite, or expose real data?” — and maps the probability to allow, review, or deny. Use it before destructive actions. The action text is sent to the provider; failures are reported as errors, never as approval.
decide_rerank (beta)
Scores a list of passages against a query and returns them sorted. Useful before stuffing retrieved context, when keyword search returned too much:
{
"query": "How do I rotate the API key?",
"documents": [
{ "id": "doc-1", "text": "..." },
{ "id": "doc-2", "text": "..." }
]
}
decide_judge (beta)
Judges a candidate answer or tool result against explicit yes/no checks and returns PASS / FAIL with one probability per check. Useful as a review gate or LLM-as-a-judge:
{
"task": "Answer the user's question about refunds",
"output": "...",
"checks": ["cites a source", "answers the question", "contains no invented policy"]
}
Experimental: loop triage
When enabled in Behavior → Experimental, the plugin listens on agent/pre-step, asks the decision model whether the new message is quick, deep, or tool, and appends a short hint to the turn. It is off by default, costs one decision call per turn, and its behavior may change between releases.
How to use in DSH
- Open Settings → Decisions → Providers, pick a provider, press Test, then Use as default.
- In chat, describe the decision and the options: “Use
decideto route this ticket to billing / technical / sales and score its urgency.” No skill is installed; the agent picks tools from their descriptions, and namingdecidejust makes the choice deterministic. - Before a risky shell command, say “call
decide_gatefirst and continue only if it says allow.” - For RAG or review flows, ask for
decide_rerank/decide_judge. - Optionally enable the execution guard or experimental loop triage in Behavior (both off by default; do not combine the guard with
dsh-jev-guard).
The full walkthrough, example prompts, and troubleshooting table: docs/usage.md. 中文说明:docs/usage.zh.md.
Configure without the page
- id: decide
name: dsh-decide
config:
defaultProvider: tokenrhythm
maxQuestions: 8
timeoutMs: 20000
maxRetries: 2
thresholds:
choice: 0.7
score: 0.7
yesnoLow: 0.35
yesnoHigh: 0.65
providers:
tokenrhythm:
enabled: true
dialect: systemone
baseURL: https://tokenrhythm.studio/v1
path: /systemone
apiKeyEnv: TOKENRHYTHM_API_KEY
model: NeoHorse-Jev-4B
Precedence: profile config > ~/.dsh/decide/settings.json (written by the page) > defaults. Keys are never stored here.
Limits, confidence, cost
- Each provider declares its own limits (question count, choice/score counts, state size, body size). They are enforced locally before a request, with an actionable error.
- Do not reuse thresholds across providers. Jev, Laya and OpenAI compute confidence differently; the defaults threshold on the top probability for
choiceand onnoul/predicateprobability foryesno. Per-provider threshold overrides are supported. - Cost is estimated from
usage.input_tokensand a per-provider price (TypeSafe: $0.042/M input, output free). TokenRhythm and OpenAI prices are left unknown until configured. - Timeouts and network failures are not retried; only 429/5xx/529 responses are (the API has no documented idempotency key).
Privacy
stateis sent to the selected provider. Local providers keep it on the machine.- Audit records (
~/.dsh/decide/decisions.jsonl) store a hash and character count by default;storeState: fullis opt-in. - API keys live in the DSH credential store or the environment, never in settings or logs.
Development
npm test
The suite is offline: adapters, dialect normalization, limits, thresholds, retries, audit, routes, and a fake Cordis host. Node 20+; no runtime dependencies.
Known gaps
- The
tools/pre-executeguard is implemented but off by default (guard.enabled), and only checksbash/pwsh. Do not enable it together withdsh-jev-guard. decide_rerankanddecide_judgeare beta; loop triage (experimental.triage) is experimental and may change between releases.- Images /
boxquestions are not sent yet. - Native Laya
/predict(not System One) is not adapted; use the Unsloth System One endpoint or a proxy. - OpenAI Decisions is beta; the native path is configurable (
baseURL+path) if it moves.
About
Maintained by 老陈聊AI (Xiaohongshu). Provider website links carry the aichen referral tag so the author can track partnerships; the tag is a single constant in lib/providers.js.
License
MIT
Comments
Loading…
Similar plugins
by nanami-0713
DSH plugin: register TypeSafe Jev (System One decision model) as an agent tool — jev_decide returns calibrated probabilities (noul/choice/score) for routing/triage/guardrail judgments, no text generation. 把 TypeSafe Jev 决策模型注册为 DSH agent 工具
★ 4
↓ 214/wk
MIT
JavaScript
Sep 30, 2026
dsh plugin --profile web add dsh-jev-decideby BetterZflyee
Use the Jev (System One) decision-model paradigm with any OpenAI-compatible LLM — no TypeSafe key required. Registers a jev_decide tool on DeepSeek Harness (dsh).
★ 4
MIT
JavaScript
Sep 21, 2026
dsh plugin --profile web add dsh-jev-adapterby JiamingShi-JsPhys
DSH 模型矩阵调度中枢:本地 OpenAI 兼容网关 + 四种调度模式(含白嫖)+ 自动容灾 + SQLite 精确缓存
★ 2
MIT
TypeScript
Nov 6, 2026
dsh plugin --profile web add dsh-token-stewardDeepSeek Harness approval guardian: a reviewer model decides permission requests before they reach you, with a System One decision-API backend (TypeSafe Jev, SiliconFlow, self-hosted Laya), a configur
★ 0
dsh plugin --profile web add dsh-auto-review-jevby 7starsseeker
Pre-execution safety valve for DSH that judges with TypeSafe Jev: it hooks tools/pre-execute and decides every bash/pwsh call by first applying offline static rules, then by asking the Jev model — the
★ 0
MIT
JavaScript
Sep 29, 2026
dsh plugin --profile web add dsh-jev-guard把 TypeSafe / Jev(System One 判断模型)的构建技能注册进 DeepSeek Harness 的全局技能层:分类、路由、打分、抽取、置信度门控这类「让 AI 做判断」的任务,每个会话都能直接调用。不含任何密钥,API key 由使用者通过 OPENROUTER_API_KEY 环境变量提供。
★ 0
dsh plugin --profile web add dsh-typesafe-ai-skill