CATEGORY
Models & Usage DSH plugins
Verified manifests and exact versions in this category.
All plugins
876 plugins@dsh-external/dsh-cost-guardCost Guard
成本守卫: A cost-saving plugin for DeepSeek V4-Flash-0731 pure API pricing—calculates session costs, cache hit rates, and the amount saved with full cache hits according to the official peak/off-peak tiers dated 2026-08-17 (peak: 09:00-12:00 / 14:00-18:00); ¥ budget guard (budget = hard limit: once the
dsh-model-accordionModel Accordion
Provider-folded model selector for the DSH Web composer with catalog-driven reasoning effort choices.
@local/dsh-advanced-model-editorAdvanced Model Editor
Advanced model configuration page for DSH WebUI
dsh-llm-web-bridgeLlm Web Bridge
DSH web plugin: bridge to third-party web LLMs (Gemini, ChatGPT, Doubao, custom) — agent-driven consult_llm tool with review/code-review/adversary/verify roles, text-log primary UI with on-demand live view, named sessions, token metering, headed/headless browser daemon.
dsh-budget-guardBudget Guard
DeepSeek Harness plugin: LLM cost metering with budget enforcement (deny/warn), peak-valley pricing and a live usage dashboard
dsh-llm-longcatLlm Longcat
LongCat (LongCat-2.0) adapter for the DeepSeek Harness LLM seam — 1M context, thinking mode, tool calling
@adverts13/dsh-auto-model-routerAuto Model Router
Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.
dsh-llm-governorLlm Governor
Multi-model governance, routing, fallback, quota, and usage for DeepSeek Harness
dsh-usage-guardUsage Guard
DSH usage statistics plugin: token collection, activity heatmap, cost estimation, over-limit guard
dsh-llm-autorouterLlm Autorouter
AutoRouter (model routing gateway / relay) LLM adapter for the DeepSeek Harness
dsh-token-usage-statsToken Usage Stats
DSH web plugin: cross-session token usage, request count, and optional cost analytics (ctx.tokenUsageStats), with a self-contained dashboard page and a sidebar footer entry.
dsh-companyCompany
Decision-driven AI company orchestration with HR governance, monetary budgets, model discovery, and deterministic audit for DeepSeek Harness
dsh-plugin-costPlugin Cost
DeepSeek Harness cost tracker: per-turn & total token usage and billing (DeepSeek pricing, peak/off-peak aware), rendered in the chat UI.
@taylorswitiger/dsh-plan-bridgePlan Bridge
Local multi-plan bridge for DeepSeek Harness: use your existing ChatGPT Codex, Claude, ZCode (GLM) and Qwen subscriptions through one loopback proxy, with a settings-page status card and one-click provisioning. No dsh core changes.
dsh-minimax-usageMinimax Usage
Show MiniMax Token Plan subscription usage in the DSH Web UI
dsh-router-traeworkRouter Traework
DSH plugin: TRAE SOLO supplier for dsh-router. Provides the traework supplier (free SOLO chat channel, ported from traework2api) to dsh-router through the router.suppliers cordis service.
@ycp424c/dsh-luna-vision-bridgeLuna Vision Bridge
DSH LLM adapter that transcribes native image attachments with Codex Luna before delegating to DeepSeek
dsh-tool-lipsyncTool Lipsync
FreeLipSync lip-sync talking video panel — an embedded DSH interface panel for uploading, text, audio, model selection, free generation, and recent generations. No Key or login required; does not consume model tokens.
dsh-ollama-usageOllama Usage
DeepSeek Harness 插件:可视化 Ollama Cloud 账号用量余量(每 5 小时会话用量 + 周用量),支持侧边栏双横条、设置页面板、API Key 与用量快照持久化、自动刷新与登录引导。Ollama Pro usage & remaining-quota visualization for DeepSeek Harness: 5-hour session + weekly quota bars in the sidebar footer, a full settings panel, persisted API key and usage snapshots, auto-
dsh-plan-bridgePlan Bridgealt · TaylorSwitiger
Local multi-plan bridge for DeepSeek Harness: use your existing ChatGPT Codex, Claude, ZCode (GLM) and Qwen subscriptions through one loopback proxy, with a settings-page status card and one-click provisioning. No dsh core changes.
dsh-kimi-subscriptionKimi Subscription
Use a Kimi Code membership in DeepSeek Harness through a dedicated Kimi subscription model route
dsh-token-optimizerToken Optimizer
Deterministic, recoverable tool-result compression and cache-aware compaction for DeepSeek Harness
dsh-llm-grokLlm Grok
xAI Grok subscription login and chat for DeepSeek Harness
dsh-llm-commandcodeLlm Commandcode
Command Code Provider API LLM plugin for DeepSeek Harness
dsh-claude-driverClaude Driver
DSH host plugin: drive the main session model through local Claude Code (official Claude Agent SDK) by taking over the llm/stream route `claude-code`.
dsh-web-search-zaiWeb Search Zai
Z.ai and Zhipu web search for DeepSeek Harness, with Coding Plan MCP quota, REST API billing, and bilingual settings.
dsh-model-fallbackModel Fallback
DeepSeek Harness plugin: pick configured model providers, and when a model fails with a model-related error the request automatically falls through the provider group's models (then the next selected provider) until one works, so the unfinished task keeps going. Adds its own Settings tab.
dsh-token-speedToken Speed
DSH web plugin: a draggable ring-gauge dashboard pinned to the bottom-right that shows live model output speed (tok/s), with an expandable detail panel (per-step exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).
deepseek-openai-codexDeepseek Openai Codex
Configuration-only DeepSeek Harness bundle that enables the built-in Pi-backed OpenAI Codex route
@ddtcorex/dsh-maestro-observeMaestro Observe
Maestro observe — trace/health/cost debug tooling (Phase 3)