CATEGORY
Verified manifests and exact versions in this category.
dsh-qoder-link
DeepSeek Harness LLM adapter for Qoder CN and Qoder International subscriptions, built on the official Qoder Agent SDKs. Reuses the local qoderclicn / qodercli login, shows the account quota the Qoder clients display, and exposes a fully configurable sett
@steven-wu/dsh-cost-meter
dsh plugin: live USD cost badge (whole-session + per-turn) from provider token usage and a configurable pricing table.
dsh-glm-vision
GLM vision model plugin: registers the glm-vision provider route (glm-4.6v series, with image+text input declaration) and provides the glm_vision tool, allowing text-based primary models such as DeepSeek to directly call Zhipu vision models to analyze images.
dsh-plan-usage
Plan usage badge: displays three usage windows—5-hour, weekly limit, and monthly limit—in the bottom-right corner of the Web dialog. Supports OpenCode Go, GLM Coding Plan’s two channels (Z.AI International / 智谱), and Kimi Code membership plan quotas; monthly membership quotas can be enhanced via the
dsh-ballast
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-openrouter-spend
DeepSeek Harness plugin: shows what the OpenRouter account actually charged today — per chat and in total, under the composer and in Settings, split by model and API key.
@duke-dsh-plugins/dsh-model-prompt-injector
Append system prompts to locally configured models in DeepSeek Harness with exact provider/model matching or provider-level wildcards (provider/*), managed per model in settings and persisted across restarts.
@sharewiner/dsh-model-management
DSH model management, synchronized model visibility, and OpenAI Responses web search.
@zenmux/dsh-plugins
Use ZenMux models in DeepSeek Harness with OAuth login, model search, and protocol-aware routing
dsh-grok-subscription
Use a SuperGrok or X Premium Grok Build subscription in DeepSeek Harness
@logictan/dsh-better-reasoning-effort
Third-party provider reasoning-effort AND input-modality settings for DeepSeek Harness: thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models
@ak-103u/cline-upstream-provider
See which provider really serves your requests behind the Cline gateway, and how much of your Cline Pass quota is spent — a DeepSeek Harness plugin and a pi extension in one repository.
@linziyanleo/dsh-custom-provider
DSH plugin for static OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages providers
dsh-multi-model-provider
Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.
dsh-llm-trace-plugin
Capture the literal HTTP request/response of every LLM provider call (by patching globalThis.fetch) and show them in a Wire Trace session tab
dsh-jev-subagent-dispatch
Cut LLM costs: route routine tasks to cheap subagent models (DeepSeek Harness plugin)
dsh-copilot-catalog
Account-aware GitHub Copilot model discovery and Copilot-compatible wire identity for DeepSeek Harness, wrapping the existing pi-ai adapter.
dsh-mcp-lens
Cut MCP context and API cost in DeepSeek Harness with two model-facing tools, lazy discovery, and exact-schema calls
dsh-sidebar-balance
Minimalist, native-adaptive DeepSeek Harness balance widget: DeepSeek official account balance + OpenCode Go plan consumption ring in the sidebar footer, frosted-glass hover card, in-UI restart. · 极简原生风 DSH 余额插件:侧边栏常驻 DeepSeek 余额与 Go 套餐消耗圆环,磨砂悬浮卡,一键重启
dsh-openai-live
Full-duplex voice for DeepSeek Harness: a realtime capability seam, a GPT-Live-1 adapter, and a keyless replay backend.
dsh-quota-hub
Unified real-time quota dashboard for DeepSeek Harness: OpenCodeGo windows, DeepSeek balance, OpenRouter credits, SiliconFlow and Moonshot balances in one collapsible panel — auto-detects configured credentials, no keys leave the host.
@wycto/dsh-token-usage
Token Usage Logging and Statistics Dashboard: Records all DSH LLM API calls, supports second-level time-range queries, multidimensional filtering, grouped statistics, and CSV export
dsh-hypatia-auto-memory
Event-driven Hypatia memory for DSH: automatic conversation logging via session events, queued background consolidation (span summaries + work-unit extraction) with a dedicated model route, and recall injection — zero per-call model work in the main sessi
dsh-antigravity
Google Antigravity / Cloud Code Assist model provider for DeepSeek Harness
dsh-tokensforce
DeepSeek Harness plugin: tokensforce gateway integration — login onboarding, provider profiles, and the usage dashboard tab
dsh-commandcode-provider
Command Code provider plugin for DeepSeek Harness (dsh) — works with every Command Code plan including the $1 Go plan; uses the Studio authentication API key over /alpha/generate, not the Provider API
@dsh-one/dsh-llm-provider
A dsh plugin that replaces the built-in llm-pi-ai and llm-deepseek adapters, the model selector and the Models settings page with self-maintained versions, tracks upstream @earendil-works/pi-ai, adds OAuth/device-code sign-in for subscription providers (C
dsh-camel
Configurable adaptive request pacing and visible retries for DeepSeek Harness free-model rate limits.
dsh-analytics
Agent FinOps / token analytics for DeepSeek Harness: usage collection, time-aware cost engine, cache analysis, and session drill-down
dsh-opencode-cli-bridge
DeepSeek Harness plugin: bridge DSH to OpenCode-compatible models via the local OpenCode CLI (native LlmAdapter).