Plugins

Drag documents into the dsh web chat; the agent reads them directly from the local filesystem and the right sidebar lists the outputs and file paths.

Call TypeSafe Jev / OpenRouter System One for noul, choice, and score (jev_ask / jev_check / jev_rank).

Live btop-style CPU/memory/temperature/GPU monitor tab for the DeepSeek Harness web GUI.

0.8.6 fixes a startup crash: the host runtime package is an optional peer, never an installed dependency. TypeSafe Jev (System One decision model) wired end to end into DeepSeek Harness (0.8.6). Seven tools: jev_decision (1-25 parallel atomic verdicts in one call; noul/choice/score; typed answers with calibrated confidence; measured median 266-484 ms; verdicts only, never prose), jev_choose (rank 2-10 candidate approaches - fit 0-3 and risk - into an explicit composite with a recommended pick), jev_batch (NEW in 0.8.6: one set of 1-5 judgments over 1-20 texts, one real call per text at bounded concurrency, returning a paste-ready markdown table sortable by a judged dimension; built-in sentiment/priority/intent/pii/spam presets; a failed row is reported as failed with the raw error, never guessed), jev_usage (locally measured usage: calls, tokens, estimated cost, latency median and p95, per-tool mix, rolling windows, projected burn rate, optional local hard budgets, and a declared-balance remainder), jev_overview (session ledger), jev_guard_status (guard counters plus a registrations block that surfaces per-surface registration failures) and jev_verify (frozen 27-question live benchmark at concurrency 6: 96.3%, 26/27). WHAT IS NEW IN 0.8.6 - the ledger survives a restart, the remainder is derived instead of invented, and the plugin can now do batch paperwork. (1) The local ledger persists to $DSH_HOME/jev-usage.json BY DEFAULT, so the cumulative total no longer resets when the host restarts. Two real bugs behind the old silent zero were found and fixed: the ledger path only honoured DSH_HOME (absent inside the host process, so persistence was silently disabled and the file name was null), and save() wrote the still-empty in-memory ring over the history file because it ran before the first load while the debounce window swallowed the follow-up write. (2) Remaining is derived, never invented: TypeSafe exposes no balance endpoint - /v1/usage, /v1/quota, /v1/account, /v1/account/balance, /v1/balance, /v1/credits, /v1/billing, /v1/me, /v1/limits and a dozen more all return 404, and only /v1/models answers, with no balance headers - so the panel shows the remainder as your declared balance (quota.declaredBalanceUsd) minus locally measured spend since quota.balanceSince, and says plainly that it cannot be fetched instead of printing a number. (3) The composer pill re-reads every 20 s instead of every 60 s, so a call you just made shows up while you are still looking at it. (4) The collapsed pill leads with the remainder once you declare a balance, and the cumulative row is renamed when the ledger is on disk. Every tool has an in-conversation structured view; the Settings > Plugins card covers credentials, tool switches, the auto-guard, the dashboard, the prompt section, usage/quota and auto-triage. Honest by design: no API key means an explicit error, never fabricated results; every registration is quarantined so a failure degrades one surface. Tests 38/38 (npm test, ~2.5 s). Client half applies on refresh; server half needs a host restart.

Semantic tool routing, skill discovery, and typed System One decisions for DeepSeek Harness powered by TypeSafe Jev.

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 System One model from TypeSafe, which returns a structured decision instead of prose — one yes-no question ("will this command irreversibly delete or overwrite real data?"), turning the answer into allow, revise, block or escalate; revise hands the model a safer rewrite, escalate offers a one-shot human token; exhausted credit or a missing API key degrades loudly instead of failing silent, and a missing key is requested in the conversation itself (`guard key set`, read from stdin); every verdict is appended to a shared audit log and the text people read is bilingual zh-CN/en.

DeepSeek Harness native immersive roleplay studio & companion system. Unifies decoupled character cards with Hindsight graph memory.

Tool-health sentinel for DSH: cross-session tool success/latency/error history, chronic-failure warning injected into the system prompt, report tool + /tool-health command + GET /dsh-tool-health/summary.

Makes the AI default to Mermaid diagrams in development conversations — system prompt guidance, a mermaid_validate syntax-check tool with real-parser validation, and an output gate that auto-fixes or removes broken diagrams. Rendering via dsh-mermaid.

Whale tray launcher for DeepSeek Harness: a Windows system-tray app and a macOS menu-bar app that start/stop the dsh service, summon the Web UI, restart and top up — running independently of the dsh process, like a Steam launcher for dsh.

Standing instructions edited in the DSH settings UI and injected into the system prompt of every subsequent turn.

Peak / off-peak rate badges for the model selector (every row) and the composer tool row, judged per provider by its own time zone and schedule; the live catalog is served from the host over a fenced route.

Injects your own saved context entries as a Remember row after each user message, per turn or once per session, with a Settings editor and a manager page.

Community skill marketplace for DeepSeek Harness: browse, search, and one-click install skills from awesome-skills-cn and the wider Claude Code / OpenClaw skill ecosystem.

dsh plugin: SYSTEM proxy (env) + LLM traffic-splitting proxy via a process-global undici routing dispatcher

Fullscreen business-app framework for DeepSeek Harness Web with a dark-sidebar workbench bundling a database connectivity tester and SQL query panel, a two-level knowledge base (bill and accounting) with local search and Word document ingestion, metadata environment comparison with alter-SQL generation, a data dictionary, agent log-search report demos, a system test-case runner, Evernote-style notes, developer utilities, and mini-games.

Expert market for DeepSeek Harness: WorkBuddy expert/expert-team system ported onto native agent presets, 425-expert catalog installed on demand, capability subtraction, and team delegation tools.

Browser notification plugin for DeepSeek Harness - system toasts when a task finishes, a run errors, or your input is needed (question / approval / plan review), click to open the session, per-type toggles, and no false 'done' while the main session waits on its subagents.

Injects native-Windows (non-WSL) PowerShell, encoding, filesystem, and cross-platform-build gotchas into the system prompt.

Install and call external Agent CLIs (Codex, Claude Code) from DSH without touching the system install. Each CLI gets its own Provider, model, reasoning effort and permission preset, callable directly or as a native subagent.

Injects a fixed system-prompt section so the agent always replies in Simplified Chinese — including the short narration between tool calls — unless you explicitly ask for another language. Applies to every session and preset without overriding the persona.

A production-ready UI Rewind/Revert plugin for DSH. Features inline prompt editing and a flawless dual-engine state recovery system (Workspace ShadowGit + External Tracker) with full support for forked sessions.

Three independent language channels for model output — tool-call descriptions (every tool-call card title, including run_code in PTC-style presets), thinking, and replies — each set to follow the web GUI language, force a specific language, or turn off (default: only descriptions, following the GUI). One global runtime-context prompt directive on the host; the client half reports the GUI language; a Settings plugin card switches the modes.