Plugins

Keeps an unattended DeepSeek Harness session moving when nobody answers ask_user_question: it fronts the question waterfall, leaves a human answer untouched, and after a configurable window (120 s by default) submits the option marked (Recommended)/（推荐）, or the configured first/last fallback; plan reviews stay with the human unless explicitly enabled.

Umbrella Corporation theme for DeepSeek Harness with dark and light schemes, a spinning umbrella watermark and a HUD frame.

Adds a low-key companion panel with a pomodoro timer, a todo list, drink-water and stand-up reminders, plus lesson explanations and homework tutoring through the installed desktop pet.

Opens STL meshes in the right-Sidebar document preview: binary/ASCII parsing in the browser, a WebGL viewport, and size, volume, surface-area and watertightness statistics.

Periodic water, stand-up, eye-break and stretch reminders on your own work schedule, with daily and 7/30-day statistics and multiple switchable reminder plans.

土壤与地下水监测台账核对（按点位、监测项目、限值与超标判定核对台账自洽，仅提示差异，不作出定性结论）

Read, audit and diff Protocol Buffer definitions without installing protoc: a zero-dependency .proto parser exposing six tools (status, outline, describe, diff, audit, next_number). diff classifies every change as breaking, risky or additive and names the wire-format consequence; audit catches what protoc accepts but a reviewer should not — duplicated or illegal field numbers, reserved-range collisions, unresolved types, and unreserved gaps below the high-water mark.

Sit-and-water reminder for DeepSeek Harness, with a cat that sits in the corner of the Web GUI. A focus cycle of 30-90 minutes ends in a centered overlay plus a triple chime that gets you up to walk and drink; the later button answers with one real sourced case about prolonged sitting and one about dehydration (built-in library of 17 entries, each with publisher, date and a link to the original); stopping produces a session report with worked time, completed rounds, successful interruptions, snoozes, suggested drinks and a good/mid/bad grade. The cat can be dragged anywhere with its position remembered and loops one animation per state. The timer and the ledger live in the host half, so a page refresh never loses a cycle; it only reminds while a DSH page is open. Cycle lengths, chime volume, cat opacity and grade thresholds are configurable on the plugin settings page.

Ocean-blue theme for the DSH web interface: swimming fish, rising bubbles, a daily-quote ticker above the input box, and a replacement brand area; Settings → Marine Theme exposes 7 groups and 32 options (brand text and size, badge, primary color, watermark, fish, quotes, overall scale) that apply instantly without a reload, plus a two-step reset to defaults.

Wire-level LLM inspector: captures the raw HTTP request and response bodies of model provider calls and attributes each capture to the session that caused it through the llm/stream waterfall. The request pane renders the body as a collapsible tree with per-node sizes — one measured request was 98.6% a single 973-entry array — and the response pane reassembles the OpenAI-style SSE chunk stream into reasoning, content, tool calls and usage. Shown in a Conversation View tab and a loopback viewer page.

Keeps a redundant sandbox-escalation argument from failing a tool call. Escalating tools (pwsh, bash, write, edit) advertise the full sandbox_permissions enum, but DSH only accepts a level strictly wider than the one already in effect — a check its own source calls 'deliberately not a schema constraint'. A model that reflexively passes the argument therefore picks the level it is already at and the call dies before running with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "workspace-write" mode', costing some models a whole turn of retries. This plugin registers one tools/execute waterfall listener and, only on that documented rejection and only when the arguments really carried an escalation field, re-issues the identical call once without it. Safe by DSH's own documentation: the rejection precedes any execution ('nothing has run'), and the corrected call cannot match again, so the retry is loop-free. Reproduced and verified end to end — before: isError true, the command never ran; after: the command's real output, isError false, one tool/call and one tool/result. Zero dependencies.

Keeps every model request inside a per-provider allow-list, enforced at the agent/request waterfall: disallowed models are redirected to a fallback or refused; subagents stop inheriting stale creation-time routes; warns when consecutive requests would make a --models-max 1 llama.cpp router reload models. A one-entry list is a global single-model mode.

Let text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.

Share any DeepSeek Harness session as a self-contained read-only static webpage — timeline, collapsible tool calls & reasoning, default redaction, dual SHA-256 fingerprints, watermark. · 把 DSH 会话一键变成可分享的只读静态网页：单文件 HTML、离线可开、默认脱敏。

Spend gate for DeepSeek Harness: refuses over-budget model calls on the llm/stream waterfall, before they are billed. Auto-downgrade past a soft limit.