Plugins

SSH terminals, SFTP file transfer and text editing inside DeepSeek Harness, with server troubleshooting through host models.

Workspace-wide sticky notes on an infinite canvas: notes are plain Markdown files, created manually, captured from conversations, or distilled by the AI, and can be handed back as context; ships 12 model tools and 5 bundled skills for creating, tagging, arranging, comparing and merging notes.

Adds a reasoning-level editor with OpenAI and Anthropic protocol presets (llm-pi-ai), input-modality switches and a 1M/128K context and max-output preset to model rows in Settings.

Team cost captain: meters every model call (subagents included), attributes each call to a member by workspace rules, prices it with the built-in DeepSeek 2026-09 catalog (peak/off-peak, CNY/USD) or user overrides, and appends it to a local JSONL ledger. Adds hot-reloadable member budgets, 80%/100% webhook alerts, optional over-budget enforcement, a team_cost_report tool with CSV export, and a settings-page team dashboard served over a Typert RPC service.

Notched reasoning-effort slider grouped with the model picker in the composer, with theme variables and English, French and Chinese labels.

Automatic model-tier routing for DeepSeek Harness: one user instruction enters, one tier decision comes out — complex intent is planned on the strong tier and implemented on the cheap tier, simple intent stays cheap throughout, with a deterministic guard and a TTL escalation fallback.

Standards-based OIDC identity, enterprise API-key binding, declarative branding, and OpenAI-compatible model integration for DeepSeek Harness

Call a new-api (one-api style) relay station's video model from the conversation with @-referenced image/video materials, supporting Seedance 2.0 and Happyhorse text-to-video and image-to-video across four relay protocols.

Model pricing for the DSH settings page: ~7,250 models / 213 providers with the harness catalog overlaid, honest lowest-listed comparison, session costs priced by the actual route, cache-leak attribution, and a verified promotion feed.

DeepSeek Harness Web plugin: per-model input-modality selector (text/image) on the Models settings page for third-party (pi-ai) providers.

Per-model system prompt injector for DeepSeek Harness: append custom prompt text to the END of the system prompt for locally configured models, matched by exact provider/model route or a provider-wide provider/* rule (both stack in order). A Settings page lists every configured provider and its models for per-route editing with instant effect, and rules persist to DSH_HOME so they survive restarts. Applies to main sessions, subagents, and workflow children alike.

Daruma resilience plugin for DeepSeek Harness — detects model-request failures and fails over to another channel to keep long tasks alive.

Balance badge that follows the active model provider: official readings for DeepSeek, Qwen Token Plan and Aliyun BSS, plus Moonshot and OpenRouter endpoints not yet key-verified.

Bing-backed web search provider for the built-in web_search tool: scrapes the public cn.bing.com HTML results page with no API key, reachable from mainland China, and keeps searches off the model's own search quota. Endpoint configurable.

Models+ settings page for the DSH web UI: per-model reasoning-effort tables, input modalities and compat flags saved through the official settings pipeline, with models.dev metadata prefill and API key management.

Peak/off-peak billing cost dial for the DSH Web GUI: session token usage billed at the official DeepSeek peak and off-peak rates, a rate dial with a model-colored needle and switch countdown, a balance ring with a low-balance alarm, drag-to-resize, and a minimized status-lamp mode.

A lightweight plugin that adds model thinking token statistics to the bottom Dock.

Inline Command Code plan usage badge in the DSH composer toolbar beside the model selector: 5h and weekly window usage plus remaining credits, clicking the badge opens an upward detail popover with reset countdowns; reuses the commandcode/report remote from @mars-sea/dsh-commandcode-provider.

Deterministic loop guard: denies a tool call repeated with identical arguments and caps per-agent calls, in code outside the model; incident log lets a parent interrupt a stuck subagent.

Real-time repetition guard for DeepSeek Harness (DSH): stops model generation when the same string repeats >=10 times in the streamed output. 实时检测 DSH 大模型流式输出中的重复内容，同一字符串重复十次以上立即停止生成。

Global prompt-injection / context-virus defense for DeepSeek Harness: scans tool arguments, tool results, pre-model messages and the outbound stream; quarantine/block/monitor modes, canary trap, and an evolvable on-disk signature library with learn/import/export.

Maintains reusable named subagent profiles for DeepSeek Harness and runs them with per-profile model, reasoning effort, and agent-preset settings.

Cut token cost in 4 layers without cutting model intelligence: handoff, rtk, headroom, caveman token-saving skills — each also available as a standalone installable plugin.

Installs a skill-router skill that semantically searches a local skill corpus on demand, keeping the corpus out of the per-turn model catalog.