Плагины

DeepSeek Harness (dsh) plugin: /refine command + settings panel for the dsh-continual-harness self-refinement engine — entry browsing, refinement history timeline, one-click rollback, auto-gate audit; engine optional at runtime.

OpenAI-compatible LLM adapter plugin for DeepSeek Harness with configurable default sampling parameters (temperature / topP / topK / penalties / seed) over a providers dict.

Host-anchored provider, authentication, catalog, policy, and model-selection extension for DeepSeek Harness.

Let text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.

LLM API rate limiting, concurrency control, queuing, and adaptive cooldown for DeepSeek Harness

Local Claude Code provider for DeepSeek Harness — runs your installed claude CLI as an LLM provider

DeepSeek Harness (dsh) plugin that exports a session as a self-contained, replayable HTML file — full transcript, faithful tool cards, and playback at the original timing.

FriendliAI serverless LLM adapter for DeepSeek Harness — OpenAI-compatible chat completions with dynamic model discovery and reasoning support

Declarative multi-agent pipeline executor for DeepSeek Harness (dsh): runs a manifest of confined role dispatches with mechanical gates and a machine-written evidence ledger. dsh 声明式多角色流水线执行器：按 manifest 派发受限子代理、机械门禁、机器写证据账本。

DeepSeek Harness (dsh) plugin that snapshots your workspace at every turn into a shadow git repository, so you can restore the files to any earlier turn. Your own .git is never touched, and plain directories work too.

Per-project LLM token usage and RMB cost in the DSH Web sidebar, split by input (cache miss), cache hit, and output with model price auto-pricing.

System parameter adjustment UI: grouped settings page for timeouts, parallelism, LLM retry policy, model params, web search, permissions and presets; safe profile-config editing with line-level YAML matching and post-write validation.

Rewrite the current composer draft through an auxiliary LLM call without sending a message.

MCP client hub (stdio / Streamable HTTP / SSE) with a web console for DeepSeek Harness — manage MCP servers, agent skills, slash commands, project & global memory, and prompt sections.

为原生 DeepSeek Harness 接入飞书 CodeM 模型。Use Feishu CodeM as the LLM provider for DeepSeek Harness (DSH) .

明眸 VisionBridge - Визуальный мост собственной разработки: когда слепая модель получает изображения, она автоматически вызывает визуальную модель для распознавания и передаёт распознанный текст обратно в основную модель; незаметно, настраиваемо, без потерь при обновлении.

Control your DeepSeek Harness agent from Feishu/Lark: DM a task, a DSH agent runs it with your LLM, and the answer comes back to the chat. Image understanding, image generation round-trip, feishu_send tools, resident launcher. Powered by lark-cli.

DeepSeek Harness (dsh) plugin for wallpaper theming — upload images from the Settings page, pick one, and the whole dsh web UI renders over it with an adjustable readability mask and blur.

DeepSeek Harness plugin: serve LLM calls with the OAuth tokens your local Codex CLI and Claude Code already hold, instead of a separately configured API key.

DeepSeek Harness 插件 — 通过读取企划书 / 半成品软件 / 资料预估特定模型的 token 消耗量并实时按各家定价计费

DeepSeek Harness 文字冒险/推理游戏插件:海龟汤、侦探推理、密室逃脱、剧本杀、时间循环、王国议会、单人跑团。确定性内核保证公平,LLM 担任主持人(GM)与 NPC;真相封存于引擎,永不进入模型上下文。

Scrape URLs to LLM-ready Markdown and search the web via the Firecrawl Cloud API.

DeepSeek Harness (dsh) plugin for machine-wide token usage statistics — a Settings page with totals, a contribution heatmap, streaks, and a per-model breakdown. Reads session logs from every dsh home; no cost estimates.