CATEGORY
Models & Usage DSH plugins
Verified manifests and exact versions in this category.
All plugins
876 pluginsdsh-model-healthModel Health
DSH plugin that lists all configured models with availability/latency testing, by reading $DSH_HOME/settings.yaml.
dsh-peak-blockPeak Block
Liang Wenfeng time-based interception of official DeepSeek API requests: during Beijing-time weekday peak hours, 09:00–12:00 and 14:00–18:00, automatically intercepts model requests sent to the official provider `deepseek-official`. Requests can be switched to a third-party relay or a reserved local
@aiwayds/dsh-llm-proxyLlm Proxy
dsh plugin: SYSTEM proxy (env) + LLM traffic-splitting proxy via a process-global undici routing dispatcher
dsh-gray-testGray Test
Gray model detection tool: one-click testing of 40 concurrent dsh sessions (V4 Pro + max thinking), with streaming monitoring of the chain of thought—occurrences of I'm/I'll are marked as gray super models, while occurrences of Let me are marked as normal models; the gray occurrence rate is calculat
dsh-turn-costTurn Cost
Per-conversation subscription quota share (Kimi/Aliyun Token Plan windows, model names from the log) plus per-turn/session estimated cost — shown in the dsh web UI
dsh-model-context-catalogModel Context Catalog
Context-window metadata catalog and settings UI for configured DeepSeek Harness model routes.
dsh-llm-approve-for-meLlm Approve For Me
Sessionless LLM sandbox approval reviewer for DeepSeek Harness.
dsh-model-paletteModel Palette
Global model command palette and provider/model configuration panel for DeepSeek Harness, with selective request retries, OpenRouter free-model import, loopback relays, online capacity presets, and optional media tools.
dsh-token-budgetToken Budget
A per-conversation total-token safety fuse for DeepSeek Harness
dsh-warm-minimalWarm Minimal
DSH warm-minimal mode with an optional minimal bootstrap and configurable coordinator/worker model visibility.
dsh-claude-usageClaude Usage
Anthropic Claude plan usage indicator for DeepSeek Harness
dsh-kernel-meshKernel Mesh
Host-plane kernel mesh for DeepSeek Harness: kimi/grok/codex/minimax kernel adapters, L2 subagent recipes, and kernel tools.
dsh-balance-pieBalance Pie
DSH plugin: A draggable floating balance pie chart showing the daily starting balance, each project's actual usage (calculated based on the actual decrease in balance), and the remaining balance; supports automatic recharge detection, allocation based on official peak/off-peak pricing, monthly histo
dsh-deepseek-dashboardDeepseek Dashboard
DeepSeek API balance and local token usage dashboard for DeepSeek Harness
dsh-fetch-timeoutsFetch Timeouts
Raise Node's HTTP timeouts for the whole DeepSeek Harness process so slow local models are not cut off at 5 minutes
@skkjkk/dsh-usage-dashboardUsage Dashboard
DSH usage statistics dashboard: token / cost / duration / session aggregation with trend, heatmap and calendar views (settings.section "数据看板").
dsh-llm-openai-completionsLlm Openai Completions
OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", enable_thinking / chat_template_kwargs / reasoning_effort driven by the llm-pi-ai model config, and a </think> split on the receive side — no pi-ai behavior guessing.
@dsh-external/dsh-model-syncModel Sync
One-click / auto model sync for DeepSeek Harness providers — reconciles stored model lists against each provider's /v1/models endpoint, with a Settings page toggle and conversation-open auto-sync.
dsh-tool-budgetTool Budget
Hard-stop DeepSeek Harness tool use after a per-session call budget.
dsh-plugin-agent-budgetPlugin Agent Budget
Shared token budgets for DeepSeek Harness agent trees
dsh-llm-gateLlm Gate
Per-provider concurrency gate for DeepSeek Harness LLM requests
dsh-model-providerModel Provider
Provider-first model selector for the DeepSeek Harness model seat: pick a provider, then a model from that provider — current model always shows Model · Provider; search and hardening (v0.3.1, verified against DSH 0.1.1-rc.2).
@minyang2026/dsh-migrate-on-429Migrate On 429
DeepSeek Harness (dsh) plugin: when a session keeps hitting 429 TPM rate limits (typically because the context has grown too long), automatically summarize the current session, hand the task over to a fresh session, and continue there — a true handoff (old session cancelled first), never parallel wo
dsh-cap-profileCap Profile
Model capability profiles: retrospective analysis of ~/.dsh historical sessions → per-model capability profiles (strengths/pitfalls/recommended usage) + a read-only observation window tab in the session area
@domitor-syh/dsh-ui-skin-switcherUi Skin Switcher
Model and reasoning-effort switcher: composer seat with an Off/Max effort slider over session.models / session.selectModel
dsh-subagentSubagent
Named subagent profiles with configurable model routing and reasoning for DeepSeek Harness
dsh-ark-balanceArk Balance
DeepSeek Harness plugin: Displays the remaining quota of the Volcengine Ark Collaboration Rewards Program free resource package in the lower-left corner of the web interface (based on @volcengine/ark-cli).
dsh-oauth-loginOauth Login
DSH-owned subscription login powered by Pi AI adapters: OAuth plus official Plan API keys, with an independent credential store.
api-monitorApi Monitor
Persistent API usage monitoring: DeepSeek/GLM Coding Plan/OpenCode Go/火山 Coding+Agent Plan balances and quotas, session tree tokens and costs (sidebar entry + standalone floating window).
dsh-codex-reasoning-routerCodex Reasoning Router
Composable multi-model agent roles and legacy Luna/Sol reasoning routing for DeepSeek Harness