CATEGORY
Verified manifests and exact versions in this category.
dsh-deepseek-cost-watchDeepSeek off-peak alert, account balance and live Session cost estimate for the DeepSeek Harness Web UI
@arcaneorion/dsh-model-selector-searchDSH session model selector with search and reasoning-effort pane: shadows the native conversation.input.model seat (independent cordis client plugin).
dsh-model-orchestratorGeneric Model Orchestrator for DeepSeek Harness: discovers the live model pool, profiles real model capabilities, and routes each unit of work to the best available model. Auto and Guided modes, specialist subagents, multi-agent orchestration, a dynamic Captain, and a web control panel. Domain-agnos
@wangmuy/dsh-provider-dispatcherA generic provider-dispatcher proxy for DeepSeek Harness. Mounts child plugins under a private isolate realm, records every register* call, and fans one operation out to all recorded children with a configurable strategy (parallel merge / race / bail).
dsh-liangwen-tideDeepSeek API peak/off-peak indicator + amount used today: displays “梁文峰” during peak hours and “梁文谷” during off-peak hours; strategies and pricing automatically follow the official pricing page. A peak/off-peak tide + today-cost indicator for the DeepSeek Harness Web GUI.
dsh-model-schedulerSearchable model picker plus automatic peak/off-peak model switching for the DeepSeek Harness Web GUI
ctx-budgetWhat will your agent's context cost before it runs? Audit instruction files, skills, MCP tool schemas and memory per source — with duplicates, always-on versus on-demand costs, and a budget you can enforce in CI.
dsh-missher-brainOptional shared local recall arbitration and provider status for official DeepSeek Harness
dsh-codex-adapterChatGPT-powered coding, image generation and web search for DeepSeek Harness, with account and usage settings.
dsh-cliproxyapiNative Codex and Antigravity subscription accounts inside DeepSeek Harness, based on CLIProxyAPI
dsh-live-model-catalogDSH plugin: keeps every llm-pi-ai route (custom providers included) in step with its endpoint's own /models — adds new models, fills contextWindow / maxTokens / input / reasoningEfforts, lets a route declare the thinking levels its endpoint never publishes, overrides the listing path, and makes the
dsh-prellm-routerSelf-evolving deterministic rule objects before DeepSeek Harness model calls
dsh-ui-peak-rateDSH web composer peak-rate badge: shows 🔥 2× when the session's model provider matches a configurable list during DeepSeek peak hours
dsh-subscription-loginsManage OpenAI, Anthropic, and Z.AI subscription credentials in DSH web
dsh-configurable-subagentsChoose sub-agent provider, model, and reasoning effort per delegation or through persistent defaults
dsh-local-telemetryLocal-first Harness runtime telemetry plugin: records request, model, tool, and plugin lifecycle metrics (latency, tokens, cost, errors, and cache), with content collection disabled by default. Local-first Harness telemetry plugin for DeepSeek Harness. npm package dsh-local-telemetry (the dsh-teleme
dsh-llm-configMulti-provider LLM configuration for the DeepSeek Harness LLM seam: declare any number of providers, each with its own endpoint, credential and per-model parameters, across the OpenAI Chat, OpenAI Responses, Anthropic Messages and Google Gemini wire formats.
dsh-axia-cachebilling虾算账: DSH cache billing plugin — real-time billing in a contextual pop-up (three-tier billing + actual event counting + Token statistics + unified currency using real-time exchange rates), with automatic pricing from the price catalog
dsh-usage-centerNative DSH settings page for daily provider usage, subscription quotas, and API price estimates.
dsh-llm-providers-uiShared LLM Providers settings shell, card order, and picker sort for DeepSeek Harness plugins
@openplan/dsh-fuseCost policy for the DeepSeek Harness: per-call metering plus a local fuse that enforces budget, model and reasoning-effort limits before any token is spent.
@local/dsh-usage-monitorDSH plugin: show DeepSeek API pricing, token usage/cost and account balance inside DeepSeek Harness (DSH).
dsh-plugin-opencode-sessionDSH profile bundle that injects a stable per-conversation x-opencode-session header into every opencode.ai model request, fixing OpenCode Go HTTP 400 MissingSessionID.
dsh-loomy-connectUse the models included with the Loomy desktop app in DeepSeek Harness with no configuration.
dsh-tidecostDSH sidebar supporting only the DeepSeek API: balance / peak and off-peak price alerts / incremental token spending / session budget warnings
dsh-plugin-token-heatmapGitHub-style daily token usage heatmap for DeepSeek Harness Web
dsh-usage-dockPer-session CNY cost pill in the composer dock: rides the shipped stats row and expands into the token buckets and both tariff bounds.
@andrepontesmelo/dsh-model-routerDSH plugin: declare VIRTUAL model ids bound to a pluggable routing algorithm (priority, round-robin) over real provider/model candidates; using the virtual id transparently dispatches to a real provider chosen by the algorithm, with failover.
dsh-llm-agent-bridgeBridges vendor agent SDKs into DeepSeek Harness as selectable LLM providers. Works in any DSH mode; DSH keeps its own prompt, tools, sandbox and approvals.
dsh-plugin-model-configFull model-configuration editor for the DeepSeek Harness web Settings > Models page: every field the deployment's model-config schema declares, not just the handful the shipped UI exposes.