Plugins

MCP marketplace and management panel in the Web sidebar: one-click official templates (Apifox public/private, Apipost, MasterGo, Pixso), paste raw mcpServers JSON, and enable, edit or delete your services with hot reload.

Keeps long DSH sessions alive when a model channel starts failing: daruma takes over after the in-box retry gives up, trips a self-healing circuit breaker on repeated 429/5xx or a terminal error, and moves the next request to another channel in your chain. A panel beside the composer picks the backup by hand, switches show up as rows in the conversation, and every decision lands in a durable JSONL audit log.

Lab/project progress management for DeepSeek Harness: 16 progress_* agent tools (item CRUD, day-board pages, daily records, global search, overview, gantt, comments, import/export) plus a 「进度」sidebar tab in better-sidebar hosting the original web UI; data lives in the session project's .progress/progress.json.

Lets the AI insert streaming-generated UI into the conversation or a side panel, written in TSX — already one of the model's native languages, so there is no JSON schema to teach it. Rendered without flicker, state kept across frames with no hard remount, and a click in the card driving the next chat turn. Inline is where streaming matters most; the side Canvas is the more agentic shape. Cards get agentic capabilities of their own — run bash, curl, call the model, read and write files.

DSH Web plugin for managing sessions: archive/unarchive, guaranteed physical deletion (transcript files + ~/storages/*.json sweep), drag-and-drop workspace reassignment, and branch-based message editing (edit/retry/reroll with reversible version timelines

AI-driven source-code security scanning workbench: 5 model tools (start/finding/status/report/list) plus a /hawkeye web UI and JSON/Markdown/HTML vulnerability reports; zero-dependency Cordis plugin, installable as agent preset or npm package.

A pouch of practical micro-plugins for DSH: per-turn wall-clock time injection, safe restart, session ID header badge, Tavily search provider, configurable LLM request-header routes, and an MCP server console managing the official @deepseek-ai/dsh-mcp-client at runtime — add/edit/enable/disable/reconnect, per-tool switches, live status over SSE, mcpServers JSON import, and auto-migration of profile-YAML MCP entries.

Session manager panel under Settings → Plugins: list all sessions with title, cwd, agent preset, updated time, turns and steps, expand a row to view message history, delete non-running sessions, and export a session as JSON or Markdown via a browser Blob URL.

Capture AI web conversations to local JSON + SQLite, and port selected messages into agent harnesses as live, continuable sessions.

Bidirectional bridge between Hermes Agent and DeepSeek Harness. Hermes dispatches focused tasks via JSON-RPC over POST /mcp/collab (one-shot or continuable, nonce-bound amend, secret-bound consult reply); DSH lets you continue Hermes sessions as native DS

Structured machine-readable CI output for DeepSeek Harness: JSON/NDJSON session reports, JUnit XML, semantic exit codes, artifact collection and privacy redaction - a dsh profile bundle plus a standalone CLI.

Connects a Feishu self-built app over WebSocket, routes each chat to an independent DSH agent session, and streams replies through a Card JSON 2.0 card with plain-text fallback.

Safe, audited SQLite/PostgreSQL/MySQL access for dsh agents: schema introspection, enforced read-only queries, a write approval gate, and a durable JSONL SQL audit trail.

LLM debug console for DeepSeek Harness: captures the full content of every model call at the llm/stream waterfall (options, stream chunks, usage, wire protocol) and shows it in a DevTools-style docked panel, with shared-prefix context diffing, wire-JSON reconstruction, JSON export and a runtime-tunable capture policy.

Load testing with Grafana k6: smoke-test first, then run scripts and read percentiles from the JSON summary.

SMS forwarding webhook for DeepSeek Harness. Phone apps (SMS Forwarder, Tasker, or any HTTP POST) push messages to a local HTTP endpoint; the plugin stores them as JSONL and exposes sms_recent / sms_search tools so the agent can read SMS verification codes during tasks. Auto-extracts the first 4-8 digit OTP from each message, supports keyword filtering, and works over LAN or Tailscale.

Generate README.md for dsh plugin repositories from package.json + cordis.patch.yml + source layout — install/CLI/tools/dev/license sections, deterministic, zero runtime deps, read-only by default. CLI plus an agent-callable readme_forge tool.

Generate llms.txt for dsh plugin repositories from package.json + README — AI-readable discovery files, zero runtime deps, read-only by default. CLI plus an agent-callable llms_forge tool.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

Recover deleted or corrupted dsh sessions (session.jsonl.zstd) and memory (memory.db) from the raw disk, and repair rebuilt sessions that fail to resume via the /session-repair command in the web UI.

Personal bookkeeping for DeepSeek Harness: record expenses/income (single or batch), list, monthly/annual stats with trends, budgets with progress/over-limit alerts, soft-delete restore, CSV & self-contained HTML report. Zero deps, local JSON. 个人记账插件

dsh (DeepSeek Harness) 更新中心与插件市场：自托管 plugins.json 注册表（GitHub dsh-plugin 主题自动聚合 + npm 包名映射秒级安装），一键安装/更新/卸载/禁用插件与更新 dsh 本体。Update center & plugin marketplace for DeepSeek Harness.

Adds a produced-files card row to the chat and a resizable split-screen preview panel for workspace artifacts (Markdown, source code, CSV, JSON, images, HTML), plus a localhost port preview.

Runtime security gate on the tool pipeline: denies calls naming hosts outside an egress allowlist, redacts credentials from results at the canonical value rather than only the rendered content, and appends every decision to a JSONL audit log; ships in monitor-only mode.