CATEGORY
Models & Usage DSH plugins
Verified manifests and exact versions in this category.
All plugins
875 plugins
dsh-plugin-cost-trackerPlugin Cost Tracker
Token cost tracker for DeepSeek Harness -- track usage, calculate costs, budget warnings
dsh-deepseek-quota-barDeepseek Quota Bar
DeepSeek API quota widget for the dsh web GUI: floating bottom-right card with a blood-bar of remaining balance vs month-opening balance, plus today/month spend and current conversation cost (fork of dsh-deepseek-quota).
@wycto/dsh-token-usageToken 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-vision-linkVision Link
Lightweight, route-preserving vision link for DSH: a configured vision model sees while the selected text model stays in control.
dsh-delegate-routerDelegate Router
Delegate light subagent tasks to cheaper models: automatic Flash/Pro routing for DeepSeek Harness subagent calls, with /delegate overrides, budget caps, and a routing-ledger panel.
@max-null/dsh-habitHabit
Self-learning habit engine for the DeepSeek Harness — detects user-correction signals, judges habits with a low-cost model on threshold, settles candidates behind a two-level human gate
dsh-plugin-llm-balancePlugin Llm Balance
DSH (DeepSeek Harness) plugin: a draggable API balance/quota floating card in the top-right corner of the page—automatically discovers providers such as DeepSeek / Moonshot / Kimi For Coding, changes color by balance tier, and refreshes in real time
@yilinxiao/dsh-mcp-lazyMcp Lazy
MCP lazy-loading, dynamic tool-loading, and Tool Router plugin for DeepSeek Harness with fail-open schema progressive disclosure: hide compatible MCP tool schemas until routed to reduce context bloat and save tokens, while explicit lazy connections stay w
deepseek-harness-quota-monitorDeepseek Harness Quota Monitor
Multi-provider quota monitor for DeepSeek Harness: balance type (query + JS parser) and window type (local sliding-window metering). Sidebar widget + settings section.
@aiwayds/dsh-llm-net-retryLlm Net Retry
dsh plugin: bounded retry for gateway network_error failures the stock retry policy cannot classify (e.g. OpenCode Zen finish_reason: network_error)
@xavier711/dsh-deepseek-usageDeepseek Usage
DeepSeek usage panel for the DSH Web GUI: account balance (official /user/balance API) plus per-model and per-workspace local session token statistics
dsh-analyticsAnalytics
Agent FinOps / token analytics for DeepSeek Harness: usage collection, time-aware cost engine, cache analysis, and session drill-down
@dougen/dsh-deepseek-usageDeepseek Usagealt · @dougen
DeepSeek balance sidebar plugin: balance (official API), current-tier unit price, and peak/off-peak period indicator lights, with Chinese and English interface support.
dsh-go-balanceGo Balance
OpenCode Go subscription balance widget for DeepSeek Harness Web: rolling/weekly/monthly quota remaining, shown at the right end of the composer tool row.
dsh-model-extensionModel Extension
DeepSeek Harness plugin: extended per-model LLM configuration (reasoning efforts, input modalities, compat flags) as a companion settings page
@kc0ed/dsh-bottom-barBottom Bar
Bottom bar statistics settings: configurable statistics row below the input box + estimated cost (including DeepSeek peak/off-peak pricing) + self-developed persistent ledger (full client-side reconciliation) + settings page (bottom bar).
dsh-langfuseLangfuse
dsh-langfuse: Langfuse LLM observability for DeepSeek Harness — one OpenTelemetry trace tree per agent session, with feedback scores and subagent lineage.
dsh-convo-costConvo Cost
Real-time cost tracking for the current DSH conversation: a composer-dock line showing the running token usage and DeepSeek official price estimate (base and peak/valley pricing).
dsh-session-costSession Cost
dsh plugin: show the estimated DeepSeek API cost of the current session in the web GUI stats strip (token usage × official pricing, peak/off-peak aware)
dsh-open-eyesOpen Eyes
Open Eyes for DeepSeek Harness: delegate images to a configurable multimodal model through OpenAI Responses, Chat Completions, or Anthropic Messages.
dsh-plugin-weaknet-adaptorPlugin Weaknet Adaptor
Weak-network adaptor for the DeepSeek Harness: transparent long-backoff model-stream retries (10-min cap), local response replay cache, heartbeat auto-reconnect, degraded-mode token economy, and a bilingual (zh/en) settings page. / 弱网适配插件：模型流长退避重试、本地响应缓存、
loongportLoongport
LoongPort DeepSeek Harness (dsh) Cordis bundle and setup CLI
@pinkbanana/dsh-balanceBalance
DeepSeek Harness plugin that shows API balances and models in Settings, with balance below the chat composer
dsh-usage-displayUsage Display
Multi-vendor balance/usage badge (with built-in DeepSeek balance and 智谱 GLM Coding Plan quota): the host retrieves data by round events and synchronizes it to the browser via SSE for display.
dsh-provider-billingProvider Billing
DeepSeek Harness plugin: provider account balance inside each Models settings row, queried through a loopback-pinned RPC channel with the stored API key kept on the host
@dushayulll/dsh-model-catalog-refreshModel Catalog Refresh
Append-only auto-sync for dsh llm-pi-ai provider catalogs (models.dev + OpenAI /models) with backup and restore. Discovers providers from your settings — no hard-coded provider in JSON.
smart-subagentSmart Subagent
Route fresh DeepSeek Harness subagents to registered provider/model pairs declared in role Markdown files
cortiq-dsh-llm-routerCortiq Dsh Llm Router
Умный маршрутизатор LLM-запросов для DeepSeek Harness (dsh). Классифицирует каждый промпт по типу задачи (code, math, translation и др.) и сложности (low/medium/high) через семантический роутер allaigate.com, затем делегирует вызов тому провайдеру, которы
dsh-llm-discoveryLlm Discovery
Engine-detecting endpoint model discovery with bundled-catalog enrichment for the DeepSeek Harness LLM seam
@siliconflow-official/dsh-llm-siliconflowLlm Siliconflow
SiliconFlow (OpenAI-compatible) chat-completions adapter plugin for the DeepSeek Harness LLM seam