CATEGORY
Models & Usage DSH plugins
Verified manifests and exact versions in this category.
All plugins
876 pluginsdsh-whale-girlWhale Girl
鲸鱼娘·灵动挂件: Balance / Usage / Context Progress / Easter Eggs
dsh-provider-vearkProvider Veark
火山方舟 Coding Plan LLM provider for DeepSeek Harness — 图片走 Ark Files API 优先（input_image + file_id），base64 data URL 自动兜底，Responses API 流式
dsh-catalog-refreshCatalog Refresh
Rebuild DSH's pi-ai model catalogues at runtime: fetches the live model lists from OpenRouter, OpenCode Zen, Fireworks, Groq, Together and DeepSeek and patches the harness's installed pi-ai MODELS registry, so the model picker and discovery show fresh models without hand-adding custom models.
dsh-codebuddy-modelsCodebuddy Models
CodeBuddy/WorkBuddy models bundle for DeepSeek Harness (dsh): reads the local desktop login and serves the CodeBuddy subscription as a native provider route in the model picker
@deepseek-ai/dsh-rssRss
RSS reading and model tools for DeepSeek Harness
dsh-plugin-token-heatmapPlugin Token Heatmap
GitHub-style daily token usage heatmap for DeepSeek Harness Web
dsh-token-ledger-proToken Ledger Pro
DSH billing statistics plugin: automatically identifies models, displays session/today/month-to-date spending in real time, supports balance checks and budget alerts, includes pricing catalogs for 16 providers (DeepSeek/豆包/腾讯混元/阿里千问/OpenAI/Anthropic/Kimi/智谱, etc.), bilingual Chinese and English
dsh-task-effortTask Effort
Auto-adjust model reasoning effort per task: off/low/high/max with task classification, peak-pricing-period capping, countdown notices, and in-turn error escalation
@wuxie233/dsh-agent-teamsAgent Teams
AgentTeams for DSH (Wuxie233 fork): per-member model routing, read-only role deny lists
dsh-subscription-antigravitySubscription Antigravity
Google Antigravity subscription reuse for DeepSeek Harness: local multi-account pool with quota visibility and switching, PKCE sign-in, and a loopback Gemini/Claude/GPT-OSS proxy. Unofficial; no telemetry.
dsh-plus-plusPlus Plus
DSH++ — a Windows-first lifecycle & provider manager for DeepSeek Harness (dsh). Minimal, local-first, zero-runtime-deps.
dsh-llamacppLlamacpp
DeepSeek Harness LLM adapter plugin for a local llama.cpp server over its OpenAI-compatible /v1/chat/completions API.
dsh-llm-latencyLlm Latency
Per-vendor/per-model LLM latency telemetry and cross-vendor benchmark plugin for DeepSeek Harness
dsh-model-selectorModel Selector
DeepSeek Harness model selector upgrade: one-level model & reasoning-effort picker with 5 Liang tiers, custom model aliases, and peak/off-peak price countdown.
@jason666not/dsh-submodel-changeSubmodel Change
Let the user pick which provider/model drives each subagent when the AI delegates.
dsh-better-model-settingBetter Model Setting
DSH plugin that replaces the official Models settings page: provider management, per-model reasoning effort, retry overrides, drag reorder, credential status, upstream model sync, and fixed model deletion
dsh-model-picker-searchModel Picker Search
Adds a search field inside the model picker menu of the composer. Drop-in replacement for the native model seat, sharing the same per-session ModelDirectory so /model popup, the effort selector, and the /model command stay consistent.
dsh-opencode-go-subOpencode Go Sub
OpenCode Go subscription + OpenCode Zen free tier for DeepSeek Harness: displays the complete model catalog like the official opencode client (30 subscription models + 5 free models), with zero-configuration automatic key discovery and automatic use of the Responses API for luna/grok.
dsh-call-shrinkCall Shrink
Compress N LLM calls into 1 — the ultimate call compression plugin for DeepSeek Harness (DSH): title short-circuiting + in-flight deduplication + 24h replay cache + batch coalescing.
dsh-model-capabilitiesModel Capabilities
Edit per-model `input` modalities (text/image) and `reasoningEfforts` from the DSH Settings UI instead of hand-editing settings.yaml. Works on DSH Web and DSH Desktop.
lynkr-dsh-pluginLynkr Dsh Plugin
DeepSeek Harness (dsh) plugin that registers Lynkr — a self-hosted, multi-provider LLM tier-routing gateway — as a custom OpenAI-compatible provider in settings.yaml.
dsh-llm-lmstudioLlm Lmstudio
LM Studio (OpenAI-compatible local server) chat-completions adapter plugin for DeepSeek Harness
dsh-qwen38-ninfer-compaction-fixQwen38 Ninfer Compaction Fix
DSH plugin (NInfer engine only): fixes compaction failure on local qwen3.8-27b gateways served by NInfer — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters; the same idea applies to other launch methods
dsh-model-auto-hot-switchModel Auto Hot Switch
Automatic per-task model hot-switching for DeepSeek Harness (dsh): image-aware tasks route to the vision model automatically, every other task keeps your default model. Zero extra tokens, no context disturbance.
dsh-whale-widget-plusWhale Widget Plus
A DeepSeek balance whale widget in the bottom-right corner of the DSH Web interface, featuring today’s usage, peak/off-peak pricing, random lines, sound effects, and per-round consumption statistics
xby-chucknorrisXby Chucknorris
ChuckNorris MCP server is a tool that provides enhanced prompts to large language models through dynamic schema adaptation, primarily for security research and evaluation.
dsh-token-usage-costToken Usage Cost
At-a-glance session token usage and cost: displays a token/cost chip after each turn and the cumulative session cost above the input bar. Prices are fetched automatically (LiteLLM pricing table, cached on the host), with per-model manual overrides and currency conversion. UI display only; not includ
dsh-super-subscriptionsSuper Subscriptions
Supercharged subscription-based LLM provider aggregator for DeepSeek Harness (ChatGPT/Codex, Grok, Google AntiGravity, Claude, Copilot) with unified auth, quota pooling, and zero-config defaults.
dsh-model-pricingModel Pricing
DSH Web plugin: Quick reference for the latest large language model prices and policies, sorted by market ranking, with USD/CNY switching, peak/off-peak tier pricing display, one-click online refreshing of the LiteLLM pricing database, and links to each provider’s official website
dsh-subagent-route-badgesSubagent Route Badges
在 DSH 已打开子代理的 Header 展示 provider、model 和 reasoning effort