Plugins

Drag-and-drop / paste / upload files and images; on non-multimodal models images are auto-described by a configured VLM.

Workspace-first enhanced sidebar for dsh Web that shadows the built-in workspace browser at low priority (one-click toggle back to the official one) and adds soft workspace archive/restore, per-workspace SVG icons and accent colors, drag reorder and title/path/session-content search, plus a ⌘K Spotlight palette fuzzy-searching workspaces and sessions; the host half ships read-only workspace_find/workspace_list model tools and /workspace-find /workspace-list slash commands. Bilingual zh/en.

One-click search-engine switcher beside the DeepSeek Harness model picker; changes the dsh-free-search provider, handy on overseas university networks that block the DeepSeek Official search endpoint.

Composer code-quote collapse for the DSH Web UI: pasting a `path:line` header followed by code folds the input into one compact inline quote token (Ctrl+Z reverses it), and at send time the `agent/pre-step` hook injects the full pasted snapshot to the model as a separate context message.

Draggable ring gauge showing live model output speed (tok/s) with an expandable per-step detail panel (exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).

Raises Node's HTTP headers/body timeouts for the whole DSH process (default 30 min, proxy-aware) so Ollama and LM Studio models that stay silent while thinking or generating a large tool call are not cut off at 5 minutes; replaces the node_modules undici patch.

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

Slash commands ported from other coding agents (setup, connect, install, trust, browse, doctor, status, model, memory, compact, resume, review, mcp, init, suggest, improve, refactor), a zero-dependency static scanner for plugin source, and an in-repo catalog of audited plugin report cards that cite file-and-line evidence.

Cost panel for DeepSeek Harness: meters every request from session events, prices it against a built-in catalog of 136 models across 16 providers, and shows the current model, account balance, session, today and month spend plus a monthly budget bar next to the composer. Bilingual zh/en.

Runs a parallel code review squad of read-only reviewer subagents (security, correctness, tests, style), each optionally on its own model, and aggregates one severity-grouped report from /review or a code_review tool call.

Annotate on selection, persist through refresh; send the notes with your message and the model answers each one.

Activity overview pane for the DSH web UI: running, awaiting-response and recent sessions with child agents, progress, model and reasoning level in one sidebar pane.

DSH Web GUI plugin: first-position 【概览】tab in the right panel (context window / session metrics with active-only 1s runtime / per-model usage & cost analysis) plus a settings entry 【DeepSeek 开放平台】that opens platform.deepseek.com. Web profile only, theme-a

Adds parametric CAD modeling, geometry validation, previews, design history, and STEP/STL export to DSH.

User-defined agents with automatic routing, model failover, and squad orchestration: six model tools (agent_dispatch / agent_followup / agent_list / agent_squad / agent_import_skill / agent_upsert), no built-in agents, a native right-tab panel (Overview / Agents / Squads / History), and a floating action ball.

One-click/auto sync provider model lists against /v1/models endpoint.

Explicit model routing for Main, Subagents, web_search, and image generation, plus a catalog-driven Composer and Plan Review picker with Model, Effort, Context, Fast, and Thinking variants.

Provider-first three-level model selector for the DSH Web model seat: pick a provider, then a model from that provider, with inline search on both levels, failed-provider retry rows, and a Model · Provider trigger.

Routes the harness through the OpenLLM gateway: a pure-config Cordis patch that adds an `openllm` provider to the in-box pi-ai adapter pointed at the local daemon (`127.0.0.1:8787/v1`, no API key held by dsh) and registers the `openllm mcp` stdio server (openllm, claude-context, supermemory tool groups).

Global Alt+M model command palette for DeepSeek Harness Web: fuzzy search over models and providers, favorites and recents, per-model reasoning effort, provider and model configuration, request retries, capacity presets, and optional OpenRouter image/video generation tools.

CodeAct agent loop for the DeepSeek Harness: a persistent IPython session as the model's action space, with harness tools bridged in as a virtual `__dsh__.tools` module.

Web search for DeepSeek Harness through Z.ai or Zhipu, with Coding Plan MCP quota and REST API billing modes, a native bilingual settings card, and support for reusing an existing ZAI_API_KEY.

Data-provider MCP server for football: results, stats, odds, standings, form and head-to-head for 18 European leagues (1993-94 →) and 8 cup competitions, for any MCP client. Also a DeepSeek Harness (dsh) plugin.

Re-validates Cloudflare Access JWTs at the DSH origin so Settings, Credentials, Agent Preset management, and model discovery work from a remote hostname.