jev 43
TypeSafe Jev as a first-class Cordis service and three model-visible tools for DeepSeek Harness — offline by default, egress disclosed, never default-on.
dsh plugin add jevcore-dshMillisecond System-1 judgement for every tool call in DeepSeek Harness: Jev-powered risk classification and evidence-gated auto-approval, fail-closed by construction.
dsh plugin add dsh-jev-interceptorGives DeepSeek Harness three automatic Jev judgments — prune oversized tool output, screen fetched pages for injected instructions, suggest which skill to use — plus the jev_ask and jev_gate tools, a persistent judgment ledger, and a /jev-status diagnosis
dsh plugin add dsh-jev-toolsdsh plugin: register locally-defined custom agents (~/.dsh/agents/*.md) as callable subagents via the use_agent tool, with continuable background dispatch, ask_agent follow-ups, the /registry-config management command, and the opt-in codemode (jev + store
dsh plugin add @aiwayds/dsh-subagent-registryAX-first macOS computer use for DeepSeek Harness: accessibility snapshots with stable refs, background input, Unicode typing, menus, apps, set-of-mark screenshots, on-device OCR, verified actions, and optional Jev (TypeSafe System One) semantic guards — 1
dsh plugin add dsh-macos-computer-useJev-judged context compaction for DeepSeek Harness. Two layers: prune stale tool results (semantic instead of size-only), and replace spent tool-call ranges with a deterministic receipt instead of a model-written summary.
dsh plugin add dsh-jev-pruneDSH 插件:把 TypeSafe Jev(System One 决策模型)注册为 agent 工具 jev_decide。调用 https://api.typesafe.ai/v1/systemone,让 agent 在路由/分级/guardrail 等场景拿到带校准概率的结构化判定(noul/choice/score),而不是让大模型瞎猜。
dsh plugin add dsh-jev-decideA DeepSeek Harness (DSH) plugin: through the TypeSafe Jev decision model (it reads each turn's instruction, classifies the task and picks a preset) or through its own tool calls, the agent switches model presets and thinking depth on its own, following th
dsh plugin add dsh-set-modelJev (TypeSafe System One) gives the human a second opinion, not the agent. When DSH's model asks you a multiple-choice question, dsh-jev-advisor builds a structured Jev request and floats the recommendation, probability spread and confidence beside the op
dsh plugin add dsh-jev-advisorFact-checking and evidence-based research skill for DeepSeek Harness: it types the request first (verify / explain / causal / compare / survey / metric), confirms the direction and runs a feasibility check, then emits a report skeleton that matches the re
dsh plugin add dsh-fact-checkTypeSafe Jev (System One decision model) for DeepSeek Harness: typed decisions in three question primitives, confidence-gated routing, a cost meter, and an automatic prompt-injection guard over untrusted tool results.
dsh plugin add dsh-typesafeCut LLM costs: route routine tasks to cheap subagent models (DeepSeek Harness plugin)
dsh plugin add dsh-jev-subagent-dispatchPlan Checkup for DeepSeek Harness: checks each step of a plan with Jev or a local LLM before you approve it, and marks the results on the plan review card.
dsh plugin add dsh-plan-checkupDeepSeek Harness plugin that wraps @stardeckai/lgtm — a Jev-powered linter for tests that pass but prove nothing. Ships the CLI as a dependency, reuses the TypeSafe credential stored in DSH, and exposes lgtm_audit / lgtm_status to the agent.
dsh plugin add lgtm-dshPer-turn model and reasoning-effort routing for DeepSeek Harness -- one Jev choice question per turn
dsh plugin add dsh-plugin-jev-routerPre-execution safety valve for DeepSeek Harness: a TypeSafe Jev question decides whether a shell command/script would irreversibly delete or overwrite real data. Four states (allow/revise/block/escalate), mounted on tools/pre-execute. Zero dependencies; W
dsh plugin add dsh-jev-guardJev-scored context compaction for DeepSeek Harness -- keep the messages that matter, compact the ones that do not
dsh plugin add dsh-plugin-jev-compactionJev (TypeSafe System One decision model) for DeepSeek Harness — seven tools: jev_decision (up to 25 typed questions in one parallel call, measured median 266-484 ms), jev_choose (rank 2-10 approaches), jev_batch (one set of up to 5 judgments over 1-20 tex
dsh plugin add dsh-jev-verify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。
dsh plugin add dsh-typesafe-ai-skill为每个 DeepSeek Harness 回答做质量与话题关联体检,并给出可复制的提示词改进建议。只观测不改写,默认本地评分,可选 Jev 精评。
dsh plugin add dsh-quality-lens决策模型原生工具插件:70ms 极速结构化决策、意图分流与状态打分。可直接下拉选择 dsh 已配置的提供商与模型(接口地址与 API Key 由提供商配置解析),也可手写 baseUrl / API Key / 模型 ID;决策模型按 /v1/models 的 modality 字段、静态 modality 与 classifier 协议识别;默认仍为 TypeSafe Jev 官方地址,支持 /v1/systemone 与 /v1/decisions 端点。
dsh plugin add @weniatall/dsh-jevRun the Jev MCP server inside DeepSeek Harness. Typed judgment tools (verify, screen, find, review, gate, and the rest) register as mcp__jev__*. Provider keys stay in DSH credentials. Jev is not a chat model.
dsh plugin add dsh-jev-mcpTypeSafe AI's Jev decision provider for dsh-ai-providers.
dsh plugin add @dsh-ai-providers/typesafeJev (TypeSafe System One) as a Cordis service for DeepSeek Harness: one headless decide() call, no tools, no policy.
dsh plugin add @wowyuarm/dsh-jevdsh-decision-engine: a cheap judgement layer for DeepSeek Harness — a small decision model answers structured questions before the main model acts, so calls can be allowed, escalated, rerouted to a cheaper model, or skipped. All eight decision points (too
dsh plugin add dsh-decision-engineCodex-style auto-approval for DeepSeek Harness. An independent reviewer decides allow/deny, fail-closed, with a rationale for every decision. Engine: an LLM route, or TypeSafe's Jev (`reviewer.engine`). · DSH 插件:独立复核器裁决,引擎可选 LLM 路由或 Jev。
dsh plugin add dsh-approval-reviewJev (TypeSafe System One) adapter for the dsh decision layer
dsh plugin add @techs/dsh-decision-jevDeepSeek Harness plugin: Jev-backed guardrails for prompts, tool calls, tool results, and model responses.
dsh plugin add @codebam/dsh-jev-guardrailsDeepSeek Harness plugin: independent Jev capability and effort decisions, enforced fresh-child routes, decision visibility and allocation feedback
dsh plugin add dsh-auto-model-routingJev (TypeSafe System One) judgments at the DeepSeek Harness agent-loop gates: pre-step, pre-execute, post-execute, and turn-stopping. No UI dependencies; mount it in any Harness composition.
dsh plugin add dsh-jev-loopSemantic find tool for the pi coding agent and the DeepSeek Harness — a cascade-search port of jegrep / oh-my-pi jfind
dsh plugin add pi-jev-findTypeSafe (System One / Jev) decision primitives as a host service: typed noul/choice/score judgements through one named-question registry, with credential-reference key resolution, bounded timeout, retry, circuit breaker, cache and decision logs. Other pl
dsh plugin add @khorsheed/dsh-typesafeThe /JevLoop control panel for moqi: gates and API key from dsh-jev-loop, rendered through moqi's tuiHost seam.
dsh plugin add moqi-jev-loopdsh Web-only plugin: jev System One lowers reasoning effort to low for simple turns, with a dismissible composer hint
dsh plugin add @dsh-jev/effortPurpose-aware monitoring for DeepSeek Harness long-running commands
dsh plugin add @mskyurina/dsh-run-watchdogJev/System-One semantic pruning of stale tool results for DeepSeek Harness; keeps conversation text verbatim and forgets stale tool output before summary compaction is needed
dsh plugin add @yadsh/dsh-jev-compactionJev (TypeSafe System One) as a Cordis service for DeepSeek Harness: one headless decide() call, no tools, no policy.
dsh plugin add @contexera/dsh-jevDrive a browser from one natural-language goal: TypeSafe Jev picks the next operation and target from an indexed element table, so a DeepSeek Harness session spends one tool call instead of one turn per click.
dsh plugin add dsh-jev-ultrafastTypeSafe Jev approval review for Pi and DeepSeek Harness
dsh plugin add jev-reviewSubagent model control for DeepSeek Harness: pick a subagent model by hand per session, or let Jev assign one per task — both enforced on the subagent's own request.
dsh plugin add dsh-subagent-customdsh plugin: Jev-guided dispatch advice — before a turn starts, a TypeSafe Jev call decides whether the task belongs to a registered agent and which one, then injects a four-line, ignore-if-unsuited recommendation. Jev-optional: no key means silence.
dsh plugin add @aiwayds/dsh-agent-dispatchJeV 思维链外显:将 DeepSeek 的任务规划、进度与阶段小结呈现为聊天正文,支持轻量摘要、原生翻译及父子任务流程图,不改主模型上下文
dsh plugin add dsh-jev-progressAuto-classify DeepSeek Harness sessions via Jev decision models or Agent tools, displayed as title emoji prefixes (wip 🚧, review 👀, done ✅). dsh-session-prefix:基于 Jev 决策模型或 Agent 工具为会话自动分类,并将任务阶段直观展示为标题前缀 Emoji。
dsh plugin add dsh-session-prefix