Skip to content

Dsh Jev Decide

A DSH plugin, published to npm, that registers one agent tool, jev_decide, so a coding agent can ask TypeSafe's Jev a typed question and get a calibrated probability instead of guessing from intuition.

Stars
4
Language
JavaScript
License
MIT
Published by
Community
Author
nanami-0713
Last verified
Oct 2026

About this project

把 TypeSafe Jev("System One" 决策模型)接入 DSH:注册一个 agent 工具 jevdecide,让 agent 在需要"快而准的判断"时调用 Jev,而不是让对话模型凭感觉猜。. 插件配置的 apiKey(cordis patch config 或数据目录 config.json). 数据目录 $DSHHOME/plugins/dsh-jev-decide/config.json(或 cordis patch 的 config:):. v0.1.2 起包内自带 dsh.bundle(根目录 cordis.patch.yml):dsh plugin add 会自动把插件装配进 profile,无需手写任何接线;纯 npm install 仍只装包不装配。. 发版即自动发布:git tag vX.Y.Z && git push --tags → GitHub Actions 以 OIDC 免 token 发布(带 provenance 签名),无需任何长期 npm 凭据。.

Quoted from the project's README. Read the full README.

Highlights

  • Three question types in one tool: noul yes/no probability, choice with a full distribution, and score over ordered levels.
  • Zero build step, single-file plain ESM; the repo notes it consumes only defineTool from the host package.
  • Reuses the DSH credential seam at ~/.dsh/.credentials.yaml, so an existing TypeSafe key needs no duplication.
  • Ships its own dsh.bundle, so dsh plugin add wires it into a profile with no hand-written patch entry.

Watch out

The host does not inject its bundled dsh-tools into a plugin's module resolution chain, so a link: or local-path install needs npm install run inside the plugin directory to materialize the peer, and the semver prerelease match only selects the 0.1.0-rc.x tuple, which the author considers expected. The bundle arrived in 0.1.2, so anyone who hand-wired an insert on 0.1.1 will hit duplicate loader entry id and an unbootable profile unless they remove the manual entry first. The README also carries an ecosystem scan of four other DSH-plus-Jev integrations and is explicit that this one deliberately does only the tool registration, so multi-question calls and dual transports are not its job. Pricing and rate limits quoted there are provider-side figures that move with the model version, which is itself pinned in the default at a moving alias. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

4GitHub stars
Framework-agnostic guard layer that puts Jev in front of an agent's tool calls: a Choice risk tier, a Noul destructiveness check and a Score blast radius decide allow, deny or ask.
Jev Practices & Patterns#community#awesomejev#catalog-import
Minecraft setup where Hermes plans at milestones, Jev picks one bounded harness action per step, and Mineflayer code owns validity and execution with no screenshots.
Jev Practices & Patterns#community#awesomejev#catalog-import
6GitHub stars
Watch Jev play chess against OpenRouter LLMs or Stockfish, or play Jev yourself, with every weighed move, likelihood, clock, and finished game saved for replay.
Jev Practices & Patterns#community#awesomejev#catalog-import
3GitHub stars
A single-file port of jev-ultrafast that lets Jev drive an Ego Lite browser on macOS: an in-page script indexes visible controls and one typed-choice request returns both the operation and the target index.
Jev Practices & Patterns#community#awesomejev#catalog-import
2GitHub stars
A PAVE app and CLI for typed decisions (choice, score and noul) with calibrated probabilities, four providers including a local engine, and eval and calibrate commands.
Jev Practices & Patterns#community#awesomejev#catalog-import
1GitHub stars
Runnable benchmark putting Jev, jev-preview and Claude Sonnet 5 through one real agent task — classifying a tool call as readonly, destructive, privileged or exfiltration — on the same 60 labelled cases, with raw per-call results committed.
Jev Practices & Patterns#community#awesomejev#catalog-import

From the Jev guides

Original write-ups on what this entry is for.

Most Jev accuracy problems are state problems. What belongs in a state, what is a pre-made judgment to leave out, and why naming the slice you ask about matters more than the wording.
Jev Practices & Patterns#state#design#primitives
Read article
A Noul returns one number and no separate confidence. How to read the value, pin its boundary with criteria, split compound questions, and set a per-action threshold that matches the cost of being wrong.
Jev Practices & Patterns#noul#primitives#confidence
Read article
A Score is a weighted position, not a ruler. Why the number can land between levels, why levels are judged separately, and how to combine several atomic scores in code instead of one crowded rubric.
Jev Practices & Patterns#score#primitives#scoring
Read article
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai