CATEGORY
Models & Usage DSH plugins
Verified manifests and exact versions in this category.
All plugins
876 plugins@chaoyuzhang/dsh-auto-routerAuto Router
Configurable Auto model routing tier for DeepSeek Harness
dsh-ai-modelsAi Models
AI model
dsh-plugin-token-usagePlugin Token Usage
DSH plugin for QwenPaw-style cross-session token usage statistics (/usage command + Web GUI panel)
dsh-api-meterApi Meter
Multi-provider API usage & balance monitor for DeepSeek Harness: dynamic provider discovery (DeepSeek / MiniMax / Moonshot / generic OpenAI-compatible), balance & quota dashboard, and an api_meter agent tool.
dsh-cost-statsCost Stats
DSH web client plugin: a per-conversation cost-statistics tab (token usage + estimated cost per model and per request)
dsh-operating-contextOperating Context
DeepSeek Harness settings page: cap every configured model service to a working context window, clamped to what each model can actually hold
@deepseek-ai/dsh-tool-tariffTool Tariff
DSH peak and off-peak electricity pricing period lookup + DeepSeek API balance lookup + peak-period switch reminder plugin (with top bar status badge)
@dsh-external/dsh-peakPeak
DeepSeek API Peak & Off-Peak (50% Discount) status indicator plugin for DeepSeek Harness (DSH)
dsh-subagent-conductorSubagent Conductor
EN: Settings and default-route layer for official DeepSeek Harness subagents: session/role/global model routing with a composer selector. ZH: 面向 DeepSeek Harness Web 官方子代理的设置与默认路由层：会话/角色/全局模型路由与输入框选择器。
dsh-ballastBallast
DSH Web 上下文窗口归因面板：通过 host token meter 按消息显示当前 surface 的 token 占用与摘要。Read-only per-message context-window attribution for DSH Web using the host token meter.
@dsh-external/dsh-subagent-model-pickerSubagent Model Picker
Allow the main session model to autonomously select a sub-agent model from the configured models
@goodandready/dsh-dsml-artifact-guardDsml Artifact Guard
Sanitizes leaked DeepSeek DSML closing tags from model text streams
modelspokeModelspoke
Local OpenAI-compatible model-server discovery + tiered reasoning-metadata resolution for DeepSeek Harness (dsh).
@alaxrpg/dsh-sensenova-providerSensenova Provider
Unofficial DeepSeek Harness LLM provider plugin for SenseNova (OpenAI-compatible). Registers the 'sensenova' provider route with multi-account API-key rotation, a Models-page card, and a live model catalog.
@dsh-plugins/dsh-opencode-goOpencode Go
DeepSeek Harness LLM provider plugin for OpenCode Go: registers the zen-go route (OpenAI-compatible chat/completions) and sends x-opencode-session per conversation.
dsh-workbuddy-xdpoolWorkbuddy Xdpool
Merge every locally signed-in WorkBuddy account into DeepSeek Harness as one auto-failing-over model pool (multi-account rotation, live credits and model catalog).
@dshp-inx/tavily-searchTavily Search
Tavily AI search provider for DeepSeek Harness: replaces the official DeepSeek web search (basic/advanced depth, per-credit billing) and adds a settings page for key management and connectivity testing.
@easytz/dsh-ui-balanceUi Balance
余额与费用：DeepSeek 余额、本次/日/周/月花费、各模型用量与实时单价。Balance and cost panel for DeepSeek Harness: balance, spend, per-model usage, live pricing.
@lovstudio/dsh-llm-configLlm Config
Reusable LLM configuration profile library exposed to browser consumers as a Remote
@lovstudio/dsh-account-balanceAccount Balance
DeepSeek Harness global account-balance card: live session/job status plus GLM / KIMI quota windows and OpenRouter / DeepSeek balances, pinned to the shell overlay bottom-right
dsh-trae-connectTrae Connect
将 Trae 订阅包含的模型接入 DeepSeek Harness — bring Trae subscription models into DeepSeek Harness.
dsh-thinkmeterThinkmeter
DSH client plugin: Think token-count display + optional tool-call grouping.
dsh-commandcode-usage-monitorCommandcode Usage Monitor
DSH plugin: real-time Command Code usage monitoring (Host backend + Browser extension/settings page). Retrieves /alpha/* usage/quota windows and provides an HTTP JSON query interface with per-round consumption statistics.
dsh-llm-capabilitiesLlm Capabilities
DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.
@tappat225/dsh-provider-hubProvider Hub
DSH LLM provider hub with a native model-configuration panel, gateway routes, model catalogs and live model discovery. Supports three wire protocols, custom User-Agent, model overrides and live routing without hand-editing settings.yaml.
dsh-better-model-selectBetter Model Select
DSH plugin: exposes per-provider balance / coding-plan usage (5h window + weekly) in a status bar pinned to the native session-stats row.
@jiesou/dsh-nous-portal-free-providerNous Portal Free Provider
Nous Portal free-tier provider for dsh: Portal OAuth (device-code) agent-key lifecycle behind an OpenAI-compatible harness route
dsh-model-picker-plusModel Picker Plus
A searchable, keyboard-friendly model picker with pinned favourites for the DeepSeek Harness web composer.
dsh-client-ui-model-searchClient Ui Model Search
Searchable, collapsible model selector for the DeepSeek Harness web UI. Replaces the composer model seat with a search box and per-provider group collapse while reusing the official shared model directory.
dsh-token-rushToken Rush
DSH Web GUI 会话悬浮仪表：实时 token / 消耗估算 / 账户余额，高峰时段自动变橙红色的 rush-hour 提示小窗，可拖动。A floating session HUD for the DSH Web GUI: live token spend, estimated cost and API balance, turning orange-red during DeepSeek rush hours.