DeepSeek Harness Plugin Hub

CATEGORY

Models & Usage DSH plugins

Verified manifests and exact versions in this category.

All plugins

876 plugins
v0.2.9
dsh-model-health

Model Health

DSH plugin that lists all configured models with availability/latency testing, by reading $DSH_HOME/settings.yaml.

models-usage10
Updated 9/2/2026
v0.1.1
dsh-peak-block

Peak 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

models-usagesecurity-access10
Updated 9/2/2026
v0.3.1
@aiwayds/dsh-llm-proxy

Llm Proxy

dsh plugin: SYSTEM proxy (env) + LLM traffic-splitting proxy via a process-global undici routing dispatcher

models-usage10
Updated 9/2/2026
v0.1.0
dsh-gray-test

Gray 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

developer-toolsmodels-usage10
Updated 9/2/2026
v0.5.0
dsh-turn-cost

Turn 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

models-usage10
Updated 9/2/2026
v0.2.1
dsh-model-context-catalog

Model Context Catalog

Context-window metadata catalog and settings UI for configured DeepSeek Harness model routes.

models-usageui-customization10
Updated 9/1/2026
v0.4.9
dsh-llm-approve-for-me

Llm Approve For Me

Sessionless LLM sandbox approval reviewer for DeepSeek Harness.

security-accessmodels-usage10
Updated 9/1/2026
v0.10.3
dsh-model-palette

Model 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.

models-usageui-customization10
Updated 9/1/2026
v0.2.0
dsh-token-budget

Token Budget

A per-conversation total-token safety fuse for DeepSeek Harness

models-usage10
Updated 9/1/2026
v0.2.0
dsh-warm-minimal

Warm Minimal

DSH warm-minimal mode with an optional minimal bootstrap and configurable coordinator/worker model visibility.

agents-orchestrationmodels-usage10
Updated 9/1/2026
v0.1.6
dsh-claude-usage

Claude Usage

Anthropic Claude plan usage indicator for DeepSeek Harness

models-usage10
Updated 8/31/2026
v1.0.4
dsh-kernel-mesh

Kernel Mesh

Host-plane kernel mesh for DeepSeek Harness: kimi/grok/codex/minimax kernel adapters, L2 subagent recipes, and kernel tools.

agents-orchestrationmodels-usage10
Updated 8/31/2026
v0.1.0
dsh-balance-pie

Balance 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

models-usageui-customization10
Updated 8/30/2026
v0.3.1
dsh-deepseek-dashboard

Deepseek Dashboard

DeepSeek API balance and local token usage dashboard for DeepSeek Harness

models-usageui-customization10
Updated 8/30/2026
v0.1.0
dsh-fetch-timeouts

Fetch Timeouts

Raise Node's HTTP timeouts for the whole DeepSeek Harness process so slow local models are not cut off at 5 minutes

models-usage10
Updated 8/30/2026
v0.3.9
@skkjkk/dsh-usage-dashboard

Usage Dashboard

DSH usage statistics dashboard: token / cost / duration / session aggregation with trend, heatmap and calendar views (settings.section "数据看板").

models-usageui-customization10
Updated 8/30/2026
v0.2.0
dsh-llm-openai-completions

Llm 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.

models-usage10
Updated 8/30/2026
v1.0.0
@dsh-external/dsh-model-sync

Model 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.

models-usage10
Updated 8/29/2026
v0.1.1
dsh-tool-budget

Tool Budget

Hard-stop DeepSeek Harness tool use after a per-session call budget.

models-usage10
Updated 8/29/2026
v0.2.0
dsh-plugin-agent-budget

Plugin Agent Budget

Shared token budgets for DeepSeek Harness agent trees

models-usageagents-orchestration10
Updated 8/29/2026
v0.1.0
dsh-llm-gate

Llm Gate

Per-provider concurrency gate for DeepSeek Harness LLM requests

models-usage10
Updated 8/29/2026
v0.3.1
dsh-model-provider

Model 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).

models-usage10
Updated 8/29/2026
v0.1.4
@minyang2026/dsh-migrate-on-429

Migrate 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

models-usagememory-context10
Updated 8/28/2026
v1.0.0
dsh-cap-profile

Cap 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

models-usagememory-context10
Updated 8/28/2026
v0.1.0
@domitor-syh/dsh-ui-skin-switcher

Ui Skin Switcher

Model and reasoning-effort switcher: composer seat with an Off/Max effort slider over session.models / session.selectModel

models-usageui-customization10
Updated 8/28/2026
v0.2.0
dsh-subagent

Subagent

Named subagent profiles with configurable model routing and reasoning for DeepSeek Harness

agents-orchestrationmodels-usage10
Updated 8/28/2026
v0.1.1
dsh-ark-balance

Ark 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).

models-usage10
Updated 8/28/2026
v0.2.3-rc.1
dsh-oauth-login

Oauth Login

DSH-owned subscription login powered by Pi AI adapters: OAuth plus official Plan API keys, with an independent credential store.

security-accessmodels-usage10
Updated 8/28/2026
v0.2.0
api-monitor

Api 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).

models-usage10
Updated 8/28/2026
v0.3.0
dsh-codex-reasoning-router

Codex Reasoning Router

Composable multi-model agent roles and legacy Luna/Sol reasoning routing for DeepSeek Harness

agents-orchestrationmodels-usage10
Updated 8/27/2026