Plugins

Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.

DSCODE for Harness Desktop: coding collaboration, session memory, browser workflows and task management.

Integrates TypeSafe Jev for skill and file selection, task supervision, shared-finding corrections, tool-output filtering, approval assistance, and recorded-stage navigation in DeepSeek Harness; all features are disabled by default.

Classifies pending tool calls with Jev (TypeSafe AI's non-generative decision model) on tools/pre-execute — confident high-risk calls are denied, ambiguous ones escalated to approval — and auto-approves clearly-granted reversible calls on approval/request behind argument-evidence gating. Also subclasses the session-reference resolver so snapshots keep Jev-scored messages instead of dropping oldest-first. Degrades to stock behavior on any provider failure; shadow mode with a /jev-stats command; TypeSafe or OpenRouter endpoints; 64 tests.

Jev DSH 决策引擎｜面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness，通过 iPolloWork 支持 OpenCode、Codex Harness。

Jev-powered decision layer plugin for DeepSeek Harness

DeepSeek Harness plugin that turns Jev judgments into three automatic actions — pruning oversized tool output to the segments relevant to the request, screening fetched pages for instructions aimed at the model, and picking which skill fits the next step — plus the jev_ask and jev_gate tools, a judgment ledger that survives restarts, and a /jev-status report. Needs a TypeSafe API key; without one it is inert and sends nothing.

Intelligent token optimization via Jev System One triage, dynamic tool pruning, and subagent routing.

Auto-classify DeepSeek Harness sessions via Jev decision models or Agent tools, displayed as title emoji prefixes (wip 🚧, blocked ⏸️, review 👀, done ✅, plan 💡, bug 🐛). Features seamless lifecycle recovery, optional Jev inference (needs a Jev API key), model tool maintenance, and a visual settings panel.

AX-first macOS computer use for DeepSeek Harness: accessibility snapshots with stable refs, background input, Unicode typing, menus and apps, set-of-mark screenshots, on-device OCR and verified actions — 11 tools bridged to the macos-cu CLI.

Injects a per-turn skill-selection preface chosen by the local JEV model of the jev-decision-kit workspace, so the agent loads exactly those skills instead of browsing. Requires a separately set-up jev-decision-kit workspace (Python .venv, host/preface_worker.py, models/jev/head.json); without it the plugin injects nothing.

AX-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

Skill that fact-checks a claim against the open web rather than model memory: it splits the claim into independently checkable fact points, routes each point to the primary-source ladder for its domain (policy, academic, medical, financial, disaster and accidents, food safety, science, education, sports, entertainment, judicial, and more), searches domestic and international ecosystems in parallel, fetches primary pages, grades sources by type, re-searches with debunking keywords, and reports conclusion-first with a full URL and citation position behind every statement, keeping unverified and undecidable points separate from confirmed ones. Three factual judgements can be routed to a TypeSafe Jev (System One) decision model when a key is configured, falling back to the skill's deterministic rules when it is not; a model verdict can only lower a confidence tier.

Chinese multi-agent workflow with per-role model fallback, versioned Mermaid task plans, independent Agent and Jev reviews, persistent expert collaboration, and pure-function calculation tools.

TypeSafe Jev (System One decision model) as the jev_decide tool for DeepSeek Harness: noul, choice and score questions return calibrated probabilities; credentials reuse the DSH credential seam; 429/529 backoff retry built in.

Use the Jev (System One) decision-model paradigm with any OpenAI-compatible LLM — no TypeSafe key required. Registers a jev_decide tool that returns probability-distributed answers to typed questions (choice/score/boolean) in one call.

TypeSafe Jev as a first-class Cordis service and three model-visible tools for DeepSeek Harness — offline by default, egress disclosed, never default-on.

Shows JeV-selected task plans, progress updates and stage summaries in DSH chat, with native translation or lightweight summaries. Requires a JeV key; the Jev service is called externally and may bill. and hierarchical serial/parallel task flows.

Adds human-facing TypeSafe Jev advice to DSH multiple-choice prompts, on demand by default with optional automatic requests, recommendations, probabilities, confidence, close-call warnings, copyable suggestions, one-click adoption, profile-scoped card layouts, temporary decision preferences, optional request previews with common-credential masking, and local health checks with sanitized diagnostic exports.

Five-layer intent recognition pipeline (rules, pgvector retrieval, Jev scoring, fine-tuned arbitration, LLM fallback) with scenario management UI, PostgreSQL storage and distributable API services.

Browser provider for DeepSeek Harness: hand it a web task — open a page, click, type, fill a form, read what is on it — and it drives a real browser step by step, seeing an indexed table of what can be done on the current page instead of raw HTML or screenshots. Each step is one bundled-Jev decision rather than a full model turn (1.1 s median per step versus 2.8–3.6 s for chat-model turns in the repo benchmark), and the main conversation receives only the conclusion, so its context does not grow with the page. Targets come from the page it just read and a changed page is re-read rather than clicked blind, and it runs in the browser that Session owns, leaving your everyday Chrome untouched unless you switch to attach mode.

DeepSeek Harness (DSH) 推理等级自动选择插件：由 Jev System One 模型判断每条消息值多少思考量，按模型声明的等级自动推导档位，上下文信封让「继续」这类追问继承话题深度，低置信度向上取，任何失败都静默沿用原等级。 | Jev-driven reasoning effort per message: per-model ladders derived from what each model advertises, a fixed-size context envelope so follow-ups inherit topic depth, ties break upward, silent fallback on every failure path.

Decision layer for dsh: provider-agnostic typed judgments (Jev first) behind tool guardrail, model routing, result judging, and machine approval seams

Jev-scored context compaction for DeepSeek Harness -- keep the messages that matter, compact the ones that do not