Plugins

Two-tier model routing: a strong tier plans, advises and reviews while a cheap tier implements, with plan-mode-aware auto routing, a high-impact escalation guard, failure auto-escalation, and subagent tiering.

Configurable DSH usage statistics: a sidebar text/card widget plus a detail dialog with per-provider and per-model breakdowns, cache-hit rates, token trends, and latency details (TTFT and duration).

PBR 3D model preview for game art: GLB/GLTF with textures, IBL environment lighting, orbit controls, and a material channel inspector (baseColor/normal/roughness/metallic/AO/emissive/wireframe); scalar channels shown as grayscale per PBR spec, via the pbr3d fence and pbr_render tool.

Four-module session companion: smart conversation export (Markdown/PDF/JSON/PNG long-image with privacy redaction and batch ZIP), context handoff summaries with template save/import, API cost optimization (live official pricing, peak/off-peak scheduling, daily/monthly budgets, model routing), and global conversation search with in-chat find (Ctrl+F, CSS Custom Highlight API).

DSH 插件:图片与文件直达纯文本模型——图片保留原生附件体验,PDF/Office/压缩包/视频/音频显示为附件栏方块,点击发送时自动转为工作区路径,配合 dsh-vision-toolkit 粘贴即看图。A DSH plugin that delivers images AND files to text-only models as workspace paths: images keep the native attachment UI, other files show as square chips in the rail, paths append on send — pairs with dsh-vision-toolkit.

MCP server manager plugin for DeepSeek Harness: Settings → MCP page, OAuth (PKCE + dynamic client registration) or static-token auth, tools registered as mcp__<name>__*

Hook DeepSeek Harness into a Hermes pipeline: dispatch-spec template, model-tier routing, orchestrator-run quality gates, git single-writer rule, as a SKILL.md pack (bundle installable).

OpenCode Go quota ring: click-to-cycle progress ring (5h/weekly/monthly) left of the model selector, colored by urgency, with reset countdowns on hover.

DeepSeek Harness tool plugin: run AgentFlow (material-canvas agent orchestrator) boards from the model

Big Fish Voice: makes the DSH web desktop pet speak. Whisper bubbles are read aloud automatically, left-clicking a bubble reads it, right-click/long-press reads it again, and clicking the pet replies with lines like 「主人，小鱼在这呢」. 10 offline Chinese voices: 2 local replica voices (鱼鱼酱 / 鱼鱼姐, no API key, ~58MB each) plus 8 Kokoro female voices (4 moe / 4 onee-san, models download on first use ~348MB, then work offline). Auto-reading can be throttled (unlimited / 30s / 60s / 3min); within one DSH instance only a single page plays audio. About 35KB package, inference in a worker thread, no dsh-pet files modified. The two replica voice models are for personal non-commercial use only.

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.

Side-panel Chrome and Firefox extension that lets DSH drive the tab you are on: pages reach the model as structured text with a numbered element list, and clicks, typing and navigation wait for your approval. Beyond upstream it adds viewport screenshots, opening a URL in a new window, scrolling inside nested scroll containers (chat transcripts, side panes, modal bodies), permission-mode, model and slash-command controls in the composer, and an opt-in developer-tools group (elements and CSS, page JavaScript, network requests) that is off by default and approved per call. The install is two halves: the bridge plugin comes from the prebuilt release tarball, and the companion extension ships as a tgz in the same release and is loaded unpacked, which is the only way Chrome accepts it. This project is a fork of omdsh-dev/dsh-browser: https://github.com/omdsh-dev/dsh-browser

Reuses the sign-in already held by the local Doubao desktop app as a DeepSeek Harness model provider — chat, Seedream image generation, and a live quota panel covering the 5-hour, weekly and activity-grant windows, showing what is LEFT rather than what is used. Windows x64 only, since the credential is decrypted with DPAPI.

Adds the official Google Antigravity ACP agent as a DeepSeek Harness model provider, with tool execution and approval kept in DSH, Node 22.19+ and a signed-in Antigravity account required, a per-model quota pill and a settings page.

Usage statistics: a usage and reference-cost panel for DeepSeek Harness with today, 7-day, 30-day, all-time and custom ranges aggregated by hour or day; a model filter and a per-model breakdown of requests, input and output tokens, cache, reference cost and share; a model-share card showing the top four models by total tokens with the rest grouped as others; a reference price list generated from opencode Zen and DeepSeek's published rates, with DeepSeek models billed by Beijing weekday peak/off-peak windows and Chinese public holidays; a pricing-match dialog to point an unmatched model at a reference model or type per-million rates by hand; reference cost switchable between ¥ and $ at a fixed 1 USD = 7 CNY; and a yearly heatmap drawn only with theme variables, with no third-party chart library.

Registers a local LLM provider that routes model calls to an OpenAI-compatible endpoint or the Ollama native API, with a connection-test card in the Models settings page and no account sign-in.

Cross-session usage and cost observatory for DSH — token trends from hourly lines to 90-day and 1-year heatmaps, per-model DeepSeek peak/off-peak pricing reconciled against the official balance, GLM/Kimi/MiniMax subscription-quota windows with burn-rate forecasts, cache-hit ring, project rankings, CSV export, and a dsh-tui terminal face.

Manage tool availability and groups for each Agent Preset, load tools on demand like Skills, and reduce model context usage.

Takes over the compaction threshold on every mounted engine: forces headroomTokens to -1e6 so the ratio is the only term in the trigger, keeps retention below it on every write path, reroutes the compaction call to a chosen model, and adds a panel with a one-click compaction button and a per-session compaction log.

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.

WeChat Official Account typesetting workbench: renders Markdown into inline-styled HTML you paste straight into the WeChat editor, with a sidebar panel, 11 themes and five model tools for block-level revision.

Calls your own chat.deepseek.com account as a second model from DSH: ask a question, analyze a file's line range, and check login state, plus a runtime skill and a settings-page login panel.

Configurable send and newline keys, a composer context menu with three sources (leave it to DSH and other plugins / browser menu / plugin-styled custom menu), a quick-command panel with categorized prompt lists where each prompt can append on every send or only on the first message of a session, a create-and-move row at the bottom of each category, a prompt optimizer that rewrites the draft with a separate model call, settings-panel size memory, and automatic x-opencode-session header injection for OpenCode routes. Prompt lists live in a global ~/.dsh/quick-prompts.json that is independent of the session and the project.